diff options
Diffstat (limited to 'net')
356 files changed, 15630 insertions, 6495 deletions
diff --git a/net/802/garp.c b/net/802/garp.c index 1610295..070bf44 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -553,7 +553,7 @@ static void garp_release_port(struct net_device *dev) if (rtnl_dereference(port->applicants[i])) return; } - rcu_assign_pointer(dev->garp_port, NULL); + RCU_INIT_POINTER(dev->garp_port, NULL); kfree_rcu(port, rcu); } @@ -605,7 +605,7 @@ void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl ASSERT_RTNL(); - rcu_assign_pointer(port->applicants[appl->type], NULL); + RCU_INIT_POINTER(port->applicants[appl->type], NULL); /* Delete timer and generate a final TRANSMIT_PDU event to flush out * all pending messages before the applicant is gone. */ diff --git a/net/802/stp.c b/net/802/stp.c index 978c30b..0e136ef 100644 --- a/net/802/stp.c +++ b/net/802/stp.c @@ -88,9 +88,9 @@ void stp_proto_unregister(const struct stp_proto *proto) { mutex_lock(&stp_proto_mutex); if (is_zero_ether_addr(proto->group_address)) - rcu_assign_pointer(stp_proto, NULL); + RCU_INIT_POINTER(stp_proto, NULL); else - rcu_assign_pointer(garp_protos[proto->group_address[5] - + RCU_INIT_POINTER(garp_protos[proto->group_address[5] - GARP_ADDR_MIN], NULL); synchronize_rcu(); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 8970ba1..5471628 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -133,7 +133,7 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) if (grp->nr_vlans == 0) { vlan_gvrp_uninit_applicant(real_dev); - rcu_assign_pointer(real_dev->vlgrp, NULL); + RCU_INIT_POINTER(real_dev->vlgrp, NULL); /* Free the group, after all cpu's are done. */ call_rcu(&grp->rcu, vlan_rcu_free); diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index f1f2f7b..163397f 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -4,7 +4,7 @@ #include <linux/netpoll.h> #include "vlan.h" -bool vlan_do_receive(struct sk_buff **skbp) +bool vlan_do_receive(struct sk_buff **skbp, bool last_handler) { struct sk_buff *skb = *skbp; u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK; @@ -13,7 +13,10 @@ bool vlan_do_receive(struct sk_buff **skbp) vlan_dev = vlan_find_dev(skb->dev, vlan_id); if (!vlan_dev) { - if (vlan_id) + /* Only the last call to vlan_do_receive() should change + * pkt_type to PACKET_OTHERHOST + */ + if (vlan_id && last_handler) skb->pkt_type = PACKET_OTHERHOST; return false; } diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 9d40a07..bc25286 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -470,10 +470,12 @@ static void vlan_dev_change_rx_flags(struct net_device *dev, int change) { struct net_device *real_dev = vlan_dev_info(dev)->real_dev; - if (change & IFF_ALLMULTI) - dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1); - if (change & IFF_PROMISC) - dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1); + if (dev->flags & IFF_UP) { + if (change & IFF_ALLMULTI) + dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1); + if (change & IFF_PROMISC) + dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1); + } } static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) @@ -610,7 +612,8 @@ static int vlan_ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { const struct vlan_dev_info *vlan = vlan_dev_info(dev); - return dev_ethtool_get_settings(vlan->real_dev, cmd); + + return __ethtool_get_settings(vlan->real_dev, cmd); } static void vlan_ethtool_get_drvinfo(struct net_device *dev, @@ -674,7 +677,6 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = vlan_dev_set_mac_address, .ndo_set_rx_mode = vlan_dev_set_rx_mode, - .ndo_set_multicast_list = vlan_dev_set_rx_mode, .ndo_change_rx_flags = vlan_dev_change_rx_flags, .ndo_do_ioctl = vlan_dev_ioctl, .ndo_neigh_setup = vlan_dev_neigh_setup, diff --git a/net/9p/client.c b/net/9p/client.c index 0505a03..854ca7a 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -38,6 +38,9 @@ #include <net/9p/transport.h> #include "protocol.h" +#define CREATE_TRACE_POINTS +#include <trace/events/9p.h> + /* * Client Option Parsing (code inspired by NFS code) * - a little lazy - parse all client options @@ -123,21 +126,19 @@ static int parse_opts(char *opts, struct p9_client *clnt) options = tmp_options; while ((p = strsep(&options, ",")) != NULL) { - int token; + int token, r; if (!*p) continue; token = match_token(p, tokens, args); - if (token < Opt_trans) { - int r = match_int(&args[0], &option); + switch (token) { + case Opt_msize: + r = match_int(&args[0], &option); if (r < 0) { P9_DPRINTK(P9_DEBUG_ERROR, - "integer field, but no integer?\n"); + "integer field, but no integer?\n"); ret = r; continue; } - } - switch (token) { - case Opt_msize: clnt->msize = option; break; case Opt_trans: @@ -203,11 +204,13 @@ free_and_return: * */ -static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag) +static struct p9_req_t * +p9_tag_alloc(struct p9_client *c, u16 tag, unsigned int max_size) { unsigned long flags; int row, col; struct p9_req_t *req; + int alloc_msize = min(c->msize, max_size); /* This looks up the original request by tag so we know which * buffer to read the data into */ @@ -245,23 +248,10 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag) return ERR_PTR(-ENOMEM); } init_waitqueue_head(req->wq); - if ((c->trans_mod->pref & P9_TRANS_PREF_PAYLOAD_MASK) == - P9_TRANS_PREF_PAYLOAD_SEP) { - int alloc_msize = min(c->msize, 4096); - req->tc = kmalloc(sizeof(struct p9_fcall)+alloc_msize, - GFP_NOFS); - req->tc->capacity = alloc_msize; - req->rc = kmalloc(sizeof(struct p9_fcall)+alloc_msize, - GFP_NOFS); - req->rc->capacity = alloc_msize; - } else { - req->tc = kmalloc(sizeof(struct p9_fcall)+c->msize, - GFP_NOFS); - req->tc->capacity = c->msize; - req->rc = kmalloc(sizeof(struct p9_fcall)+c->msize, - GFP_NOFS); - req->rc->capacity = c->msize; - } + req->tc = kmalloc(sizeof(struct p9_fcall) + alloc_msize, + GFP_NOFS); + req->rc = kmalloc(sizeof(struct p9_fcall) + alloc_msize, + GFP_NOFS); if ((!req->tc) || (!req->rc)) { printk(KERN_ERR "Couldn't grow tag array\n"); kfree(req->tc); @@ -271,6 +261,8 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag) req->wq = NULL; return ERR_PTR(-ENOMEM); } + req->tc->capacity = alloc_msize; + req->rc->capacity = alloc_msize; req->tc->sdata = (char *) req->tc + sizeof(struct p9_fcall); req->rc->sdata = (char *) req->rc + sizeof(struct p9_fcall); } @@ -475,37 +467,22 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req) int ecode; err = p9_parse_header(req->rc, NULL, &type, NULL, 0); + /* + * dump the response from server + * This should be after check errors which poplulate pdu_fcall. + */ + trace_9p_protocol_dump(c, req->rc); if (err) { P9_DPRINTK(P9_DEBUG_ERROR, "couldn't parse header %d\n", err); return err; } - if (type != P9_RERROR && type != P9_RLERROR) return 0; if (!p9_is_proto_dotl(c)) { char *ename; - - if (req->tc->pbuf_size) { - /* Handle user buffers */ - size_t len = req->rc->size - req->rc->offset; - if (req->tc->pubuf) { - /* User Buffer */ - err = copy_from_user( - &req->rc->sdata[req->rc->offset], - req->tc->pubuf, len); - if (err) { - err = -EFAULT; - goto out_err; - } - } else { - /* Kernel Buffer */ - memmove(&req->rc->sdata[req->rc->offset], - req->tc->pkbuf, len); - } - } err = p9pdu_readf(req->rc, c->proto_version, "s?d", - &ename, &ecode); + &ename, &ecode); if (err) goto out_err; @@ -515,11 +492,10 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req) if (!err || !IS_ERR_VALUE(err)) { err = p9_errstr2errno(ename, strlen(ename)); - P9_DPRINTK(P9_DEBUG_9P, "<<< RERROR (%d) %s\n", -ecode, - ename); - - kfree(ename); + P9_DPRINTK(P9_DEBUG_9P, "<<< RERROR (%d) %s\n", + -ecode, ename); } + kfree(ename); } else { err = p9pdu_readf(req->rc, c->proto_version, "d", &ecode); err = -ecode; @@ -527,7 +503,6 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req) P9_DPRINTK(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode); } - return err; out_err: @@ -536,6 +511,115 @@ out_err: return err; } +/** + * p9_check_zc_errors - check 9p packet for error return and process it + * @c: current client instance + * @req: request to parse and check for error conditions + * @in_hdrlen: Size of response protocol buffer. + * + * returns error code if one is discovered, otherwise returns 0 + * + * this will have to be more complicated if we have multiple + * error packet types + */ + +static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req, + char *uidata, int in_hdrlen, int kern_buf) +{ + int err; + int ecode; + int8_t type; + char *ename = NULL; + + err = p9_parse_header(req->rc, NULL, &type, NULL, 0); + /* + * dump the response from server + * This should be after parse_header which poplulate pdu_fcall. + */ + trace_9p_protocol_dump(c, req->rc); + if (err) { + P9_DPRINTK(P9_DEBUG_ERROR, "couldn't parse header %d\n", err); + return err; + } + + if (type != P9_RERROR && type != P9_RLERROR) + return 0; + + if (!p9_is_proto_dotl(c)) { + /* Error is reported in string format */ + uint16_t len; + /* 7 = header size for RERROR, 2 is the size of string len; */ + int inline_len = in_hdrlen - (7 + 2); + + /* Read the size of error string */ + err = p9pdu_readf(req->rc, c->proto_version, "w", &len); + if (err) + goto out_err; + + ename = kmalloc(len + 1, GFP_NOFS); + if (!ename) { + err = -ENOMEM; + goto out_err; + } + if (len <= inline_len) { + /* We have error in protocol buffer itself */ + if (pdu_read(req->rc, ename, len)) { + err = -EFAULT; + goto out_free; + + } + } else { + /* + * Part of the data is in user space buffer. + */ + if (pdu_read(req->rc, ename, inline_len)) { + err = -EFAULT; + goto out_free; + + } + if (kern_buf) { + memcpy(ename + inline_len, uidata, + len - inline_len); + } else { + err = copy_from_user(ename + inline_len, + uidata, len - inline_len); + if (err) { + err = -EFAULT; + goto out_free; + } + } + } + ename[len] = 0; + if (p9_is_proto_dotu(c)) { + /* For dotu we also have error code */ + err = p9pdu_readf(req->rc, + c->proto_version, "d", &ecode); + if (err) + goto out_free; + err = -ecode; + } + if (!err || !IS_ERR_VALUE(err)) { + err = p9_errstr2errno(ename, strlen(ename)); + + P9_DPRINTK(P9_DEBUG_9P, "<<< RERROR (%d) %s\n", + -ecode, ename); + } + kfree(ename); + } else { + err = p9pdu_readf(req->rc, c->proto_version, "d", &ecode); + err = -ecode; + + P9_DPRINTK(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode); + } + return err; + +out_free: + kfree(ename); +out_err: + P9_DPRINTK(P9_DEBUG_ERROR, "couldn't parse error%d\n", err); + return err; +} + static struct p9_req_t * p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...); @@ -579,23 +663,12 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq) return 0; } -/** - * p9_client_rpc - issue a request and wait for a response - * @c: client session - * @type: type of request - * @fmt: protocol format string (see protocol.c) - * - * Returns request structure (which client must free using p9_free_req) - */ - -static struct p9_req_t * -p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) +static struct p9_req_t *p9_client_prepare_req(struct p9_client *c, + int8_t type, int req_size, + const char *fmt, va_list ap) { - va_list ap; int tag, err; struct p9_req_t *req; - unsigned long flags; - int sigpending; P9_DPRINTK(P9_DEBUG_MUX, "client %p op %d\n", c, type); @@ -607,12 +680,6 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) if ((c->status == BeginDisconnect) && (type != P9_TCLUNK)) return ERR_PTR(-EIO); - if (signal_pending(current)) { - sigpending = 1; - clear_thread_flag(TIF_SIGPENDING); - } else - sigpending = 0; - tag = P9_NOTAG; if (type != P9_TVERSION) { tag = p9_idpool_get(c->tagpool); @@ -620,18 +687,51 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) return ERR_PTR(-ENOMEM); } - req = p9_tag_alloc(c, tag); + req = p9_tag_alloc(c, tag, req_size); if (IS_ERR(req)) return req; /* marshall the data */ p9pdu_prepare(req->tc, tag, type); - va_start(ap, fmt); err = p9pdu_vwritef(req->tc, c->proto_version, fmt, ap); - va_end(ap); if (err) goto reterr; - p9pdu_finalize(req->tc); + p9pdu_finalize(c, req->tc); + trace_9p_client_req(c, type, tag); + return req; +reterr: + p9_free_req(c, req); + return ERR_PTR(err); +} + +/** + * p9_client_rpc - issue a request and wait for a response + * @c: client session + * @type: type of request + * @fmt: protocol format string (see protocol.c) + * + * Returns request structure (which client must free using p9_free_req) + */ + +static struct p9_req_t * +p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) +{ + va_list ap; + int sigpending, err; + unsigned long flags; + struct p9_req_t *req; + + va_start(ap, fmt); + req = p9_client_prepare_req(c, type, c->msize, fmt, ap); + va_end(ap); + if (IS_ERR(req)) + return req; + + if (signal_pending(current)) { + sigpending = 1; + clear_thread_flag(TIF_SIGPENDING); + } else + sigpending = 0; err = c->trans_mod->request(c, req); if (err < 0) { @@ -639,18 +739,14 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) c->status = Disconnected; goto reterr; } - - P9_DPRINTK(P9_DEBUG_MUX, "wait %p tag: %d\n", req->wq, tag); + /* Wait for the response */ err = wait_event_interruptible(*req->wq, - req->status >= REQ_STATUS_RCVD); - P9_DPRINTK(P9_DEBUG_MUX, "wait %p tag: %d returned %d\n", - req->wq, tag, err); + req->status >= REQ_STATUS_RCVD); if (req->status == REQ_STATUS_ERROR) { P9_DPRINTK(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err); err = req->t_err; } - if ((err == -ERESTARTSYS) && (c->status == Connected)) { P9_DPRINTK(P9_DEBUG_MUX, "flushing\n"); sigpending = 1; @@ -663,25 +759,102 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) if (req->status == REQ_STATUS_RCVD) err = 0; } - if (sigpending) { spin_lock_irqsave(¤t->sighand->siglock, flags); recalc_sigpending(); spin_unlock_irqrestore(¤t->sighand->siglock, flags); } - if (err < 0) goto reterr; err = p9_check_errors(c, req); - if (!err) { - P9_DPRINTK(P9_DEBUG_MUX, "exit: client %p op %d\n", c, type); + trace_9p_client_res(c, type, req->rc->tag, err); + if (!err) + return req; +reterr: + p9_free_req(c, req); + return ERR_PTR(err); +} + +/** + * p9_client_zc_rpc - issue a request and wait for a response + * @c: client session + * @type: type of request + * @uidata: user bffer that should be ued for zero copy read + * @uodata: user buffer that shoud be user for zero copy write + * @inlen: read buffer size + * @olen: write buffer size + * @hdrlen: reader header size, This is the size of response protocol data + * @fmt: protocol format string (see protocol.c) + * + * Returns request structure (which client must free using p9_free_req) + */ +static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type, + char *uidata, char *uodata, + int inlen, int olen, int in_hdrlen, + int kern_buf, const char *fmt, ...) +{ + va_list ap; + int sigpending, err; + unsigned long flags; + struct p9_req_t *req; + + va_start(ap, fmt); + /* + * We allocate a inline protocol data of only 4k bytes. + * The actual content is passed in zero-copy fashion. + */ + req = p9_client_prepare_req(c, type, P9_ZC_HDR_SZ, fmt, ap); + va_end(ap); + if (IS_ERR(req)) return req; + + if (signal_pending(current)) { + sigpending = 1; + clear_thread_flag(TIF_SIGPENDING); + } else + sigpending = 0; + + /* If we are called with KERNEL_DS force kern_buf */ + if (segment_eq(get_fs(), KERNEL_DS)) + kern_buf = 1; + + err = c->trans_mod->zc_request(c, req, uidata, uodata, + inlen, olen, in_hdrlen, kern_buf); + if (err < 0) { + if (err == -EIO) + c->status = Disconnected; + goto reterr; + } + if (req->status == REQ_STATUS_ERROR) { + P9_DPRINTK(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err); + err = req->t_err; + } + if ((err == -ERESTARTSYS) && (c->status == Connected)) { + P9_DPRINTK(P9_DEBUG_MUX, "flushing\n"); + sigpending = 1; + clear_thread_flag(TIF_SIGPENDING); + + if (c->trans_mod->cancel(c, req)) + p9_client_flush(c, req); + + /* if we received the response anyway, don't signal error */ + if (req->status == REQ_STATUS_RCVD) + err = 0; + } + if (sigpending) { + spin_lock_irqsave(¤t->sighand->siglock, flags); + recalc_sigpending(); + spin_unlock_irqrestore(¤t->sighand->siglock, flags); } + if (err < 0) + goto reterr; + err = p9_check_zc_errors(c, req, uidata, in_hdrlen, kern_buf); + trace_9p_client_res(c, type, req->rc->tag, err); + if (!err) + return req; reterr: - P9_DPRINTK(P9_DEBUG_MUX, "exit: client %p op %d error: %d\n", c, type, - err); p9_free_req(c, req); return ERR_PTR(err); } @@ -769,7 +942,7 @@ static int p9_client_version(struct p9_client *c) err = p9pdu_readf(req->rc, c->proto_version, "ds", &msize, &version); if (err) { P9_DPRINTK(P9_DEBUG_9P, "version error %d\n", err); - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(c, req->rc); goto error; } @@ -906,15 +1079,14 @@ EXPORT_SYMBOL(p9_client_begin_disconnect); struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, char *uname, u32 n_uname, char *aname) { - int err; + int err = 0; struct p9_req_t *req; struct p9_fid *fid; struct p9_qid qid; - P9_DPRINTK(P9_DEBUG_9P, ">>> TATTACH afid %d uname %s aname %s\n", - afid ? afid->fid : -1, uname, aname); - err = 0; + P9_DPRINTK(P9_DEBUG_9P, ">>> TATTACH afid %d uname %s aname %s\n", + afid ? afid->fid : -1, uname, aname); fid = p9_fid_create(clnt); if (IS_ERR(fid)) { err = PTR_ERR(fid); @@ -931,7 +1103,7 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, err = p9pdu_readf(req->rc, clnt->proto_version, "Q", &qid); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); p9_free_req(clnt, req); goto error; } @@ -991,7 +1163,7 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, err = p9pdu_readf(req->rc, clnt->proto_version, "R", &nwqids, &wqids); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); p9_free_req(clnt, req); goto clunk_fid; } @@ -1058,7 +1230,7 @@ int p9_client_open(struct p9_fid *fid, int mode) err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", &qid, &iounit); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); goto free_and_error; } @@ -1101,7 +1273,7 @@ int p9_client_create_dotl(struct p9_fid *ofid, char *name, u32 flags, u32 mode, err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", qid, &iounit); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); goto free_and_error; } @@ -1146,7 +1318,7 @@ int p9_client_fcreate(struct p9_fid *fid, char *name, u32 perm, int mode, err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", &qid, &iounit); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); goto free_and_error; } @@ -1185,7 +1357,7 @@ int p9_client_symlink(struct p9_fid *dfid, char *name, char *symtgt, gid_t gid, err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); goto free_and_error; } @@ -1330,13 +1502,15 @@ int p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, u32 count) { - int err, rsize; - struct p9_client *clnt; - struct p9_req_t *req; char *dataptr; + int kernel_buf = 0; + struct p9_req_t *req; + struct p9_client *clnt; + int err, rsize, non_zc = 0; + - P9_DPRINTK(P9_DEBUG_9P, ">>> TREAD fid %d offset %llu %d\n", fid->fid, - (long long unsigned) offset, count); + P9_DPRINTK(P9_DEBUG_9P, ">>> TREAD fid %d offset %llu %d\n", + fid->fid, (long long unsigned) offset, count); err = 0; clnt = fid->clnt; @@ -1348,13 +1522,24 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, rsize = count; /* Don't bother zerocopy for small IO (< 1024) */ - if (((clnt->trans_mod->pref & P9_TRANS_PREF_PAYLOAD_MASK) == - P9_TRANS_PREF_PAYLOAD_SEP) && (rsize > 1024)) { - req = p9_client_rpc(clnt, P9_TREAD, "dqE", fid->fid, offset, - rsize, data, udata); + if (clnt->trans_mod->zc_request && rsize > 1024) { + char *indata; + if (data) { + kernel_buf = 1; + indata = data; + } else + indata = (char *)udata; + /* + * response header len is 11 + * PDU Header(7) + IO Size (4) + */ + req = p9_client_zc_rpc(clnt, P9_TREAD, indata, NULL, rsize, 0, + 11, kernel_buf, "dqd", fid->fid, + offset, rsize); } else { + non_zc = 1; req = p9_client_rpc(clnt, P9_TREAD, "dqd", fid->fid, offset, - rsize); + rsize); } if (IS_ERR(req)) { err = PTR_ERR(req); @@ -1363,14 +1548,13 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, err = p9pdu_readf(req->rc, clnt->proto_version, "D", &count, &dataptr); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); goto free_and_error; } P9_DPRINTK(P9_DEBUG_9P, "<<< RREAD count %d\n", count); - P9_DUMP_PKT(1, req->rc); - if (!req->tc->pbuf_size) { + if (non_zc) { if (data) { memmove(data, dataptr, count); } else { @@ -1396,6 +1580,7 @@ p9_client_write(struct p9_fid *fid, char *data, const char __user *udata, u64 offset, u32 count) { int err, rsize; + int kernel_buf = 0; struct p9_client *clnt; struct p9_req_t *req; @@ -1411,19 +1596,24 @@ p9_client_write(struct p9_fid *fid, char *data, const char __user *udata, if (count < rsize) rsize = count; - /* Don't bother zerocopy form small IO (< 1024) */ - if (((clnt->trans_mod->pref & P9_TRANS_PREF_PAYLOAD_MASK) == - P9_TRANS_PREF_PAYLOAD_SEP) && (rsize > 1024)) { - req = p9_client_rpc(clnt, P9_TWRITE, "dqE", fid->fid, offset, - rsize, data, udata); + /* Don't bother zerocopy for small IO (< 1024) */ + if (clnt->trans_mod->zc_request && rsize > 1024) { + char *odata; + if (data) { + kernel_buf = 1; + odata = data; + } else + odata = (char *)udata; + req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, odata, 0, rsize, + P9_ZC_HDR_SZ, kernel_buf, "dqd", + fid->fid, offset, rsize); } else { - if (data) req = p9_client_rpc(clnt, P9_TWRITE, "dqD", fid->fid, - offset, rsize, data); + offset, rsize, data); else req = p9_client_rpc(clnt, P9_TWRITE, "dqU", fid->fid, - offset, rsize, udata); + offset, rsize, udata); } if (IS_ERR(req)) { err = PTR_ERR(req); @@ -1432,7 +1622,7 @@ p9_client_write(struct p9_fid *fid, char *data, const char __user *udata, err = p9pdu_readf(req->rc, clnt->proto_version, "d", &count); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); goto free_and_error; } @@ -1472,7 +1662,7 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid) err = p9pdu_readf(req->rc, clnt->proto_version, "wS", &ignored, ret); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); p9_free_req(clnt, req); goto error; } @@ -1523,7 +1713,7 @@ struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid, err = p9pdu_readf(req->rc, clnt->proto_version, "A", ret); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); p9_free_req(clnt, req); goto error; } @@ -1671,7 +1861,7 @@ int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb) &sb->bsize, &sb->blocks, &sb->bfree, &sb->bavail, &sb->files, &sb->ffree, &sb->fsid, &sb->namelen); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); p9_free_req(clnt, req); goto error; } @@ -1778,7 +1968,7 @@ struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid, } err = p9pdu_readf(req->rc, clnt->proto_version, "q", attr_size); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); p9_free_req(clnt, req); goto clunk_fid; } @@ -1824,7 +2014,7 @@ EXPORT_SYMBOL_GPL(p9_client_xattrcreate); int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) { - int err, rsize; + int err, rsize, non_zc = 0; struct p9_client *clnt; struct p9_req_t *req; char *dataptr; @@ -1842,13 +2032,18 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) if (count < rsize) rsize = count; - if ((clnt->trans_mod->pref & P9_TRANS_PREF_PAYLOAD_MASK) == - P9_TRANS_PREF_PAYLOAD_SEP) { - req = p9_client_rpc(clnt, P9_TREADDIR, "dqF", fid->fid, - offset, rsize, data); + /* Don't bother zerocopy for small IO (< 1024) */ + if (clnt->trans_mod->zc_request && rsize > 1024) { + /* + * response header len is 11 + * PDU Header(7) + IO Size (4) + */ + req = p9_client_zc_rpc(clnt, P9_TREADDIR, data, NULL, rsize, 0, + 11, 1, "dqd", fid->fid, offset, rsize); } else { + non_zc = 1; req = p9_client_rpc(clnt, P9_TREADDIR, "dqd", fid->fid, - offset, rsize); + offset, rsize); } if (IS_ERR(req)) { err = PTR_ERR(req); @@ -1857,13 +2052,13 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) err = p9pdu_readf(req->rc, clnt->proto_version, "D", &count, &dataptr); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); goto free_and_error; } P9_DPRINTK(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count); - if (!req->tc->pbuf_size && data) + if (non_zc) memmove(data, dataptr, count); p9_free_req(clnt, req); @@ -1894,7 +2089,7 @@ int p9_client_mknod_dotl(struct p9_fid *fid, char *name, int mode, err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); goto error; } P9_DPRINTK(P9_DEBUG_9P, "<<< RMKNOD qid %x.%llx.%x\n", qid->type, @@ -1925,7 +2120,7 @@ int p9_client_mkdir_dotl(struct p9_fid *fid, char *name, int mode, err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); goto error; } P9_DPRINTK(P9_DEBUG_9P, "<<< RMKDIR qid %x.%llx.%x\n", qid->type, @@ -1960,7 +2155,7 @@ int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status) err = p9pdu_readf(req->rc, clnt->proto_version, "b", status); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); goto error; } P9_DPRINTK(P9_DEBUG_9P, "<<< RLOCK status %i\n", *status); @@ -1993,7 +2188,7 @@ int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *glock) &glock->start, &glock->length, &glock->proc_id, &glock->client_id); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); goto error; } P9_DPRINTK(P9_DEBUG_9P, "<<< RGETLOCK type %i start %lld length %lld " @@ -2021,7 +2216,7 @@ int p9_client_readlink(struct p9_fid *fid, char **target) err = p9pdu_readf(req->rc, clnt->proto_version, "s", target); if (err) { - P9_DUMP_PKT(1, req->rc); + trace_9p_protocol_dump(clnt, req->rc); goto error; } P9_DPRINTK(P9_DEBUG_9P, "<<< RREADLINK target %s\n", *target); diff --git a/net/9p/protocol.c b/net/9p/protocol.c index df58375..55e10a9 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -37,40 +37,11 @@ #include <net/9p/client.h> #include "protocol.h" +#include <trace/events/9p.h> + static int p9pdu_writef(struct p9_fcall *pdu, int proto_version, const char *fmt, ...); -#ifdef CONFIG_NET_9P_DEBUG -void -p9pdu_dump(int way, struct p9_fcall *pdu) -{ - int len = pdu->size; - - if ((p9_debug_level & P9_DEBUG_VPKT) != P9_DEBUG_VPKT) { - if ((p9_debug_level & P9_DEBUG_PKT) == P9_DEBUG_PKT) { - if (len > 32) - len = 32; - } else { - /* shouldn't happen */ - return; - } - } - - if (way) - print_hex_dump_bytes("[9P] ", DUMP_PREFIX_OFFSET, pdu->sdata, - len); - else - print_hex_dump_bytes("]9P[ ", DUMP_PREFIX_OFFSET, pdu->sdata, - len); -} -#else -void -p9pdu_dump(int way, struct p9_fcall *pdu) -{ -} -#endif -EXPORT_SYMBOL(p9pdu_dump); - void p9stat_free(struct p9_wstat *stbuf) { kfree(stbuf->name); @@ -81,7 +52,7 @@ void p9stat_free(struct p9_wstat *stbuf) } EXPORT_SYMBOL(p9stat_free); -static size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size) +size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size) { size_t len = min(pdu->size - pdu->offset, size); memcpy(data, &pdu->sdata[pdu->offset], len); @@ -108,26 +79,6 @@ pdu_write_u(struct p9_fcall *pdu, const char __user *udata, size_t size) return size - len; } -static size_t -pdu_write_urw(struct p9_fcall *pdu, const char *kdata, const char __user *udata, - size_t size) -{ - BUG_ON(pdu->size > P9_IOHDRSZ); - pdu->pubuf = (char __user *)udata; - pdu->pkbuf = (char *)kdata; - pdu->pbuf_size = size; - return 0; -} - -static size_t -pdu_write_readdir(struct p9_fcall *pdu, const char *kdata, size_t size) -{ - BUG_ON(pdu->size > P9_READDIRHDRSZ); - pdu->pkbuf = (char *)kdata; - pdu->pbuf_size = size; - return 0; -} - /* b - int8_t w - int16_t @@ -459,26 +410,6 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, errcode = -EFAULT; } break; - case 'E':{ - int32_t cnt = va_arg(ap, int32_t); - const char *k = 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)) - errcode = -EFAULT; - } - break; - case 'F':{ - int32_t cnt = va_arg(ap, int32_t); - const char *k = va_arg(ap, const void *); - errcode = p9pdu_writef(pdu, proto_version, "d", - cnt); - if (!errcode && pdu_write_readdir(pdu, k, cnt)) - errcode = -EFAULT; - } - break; case 'U':{ int32_t count = va_arg(ap, int32_t); const char __user *udata = @@ -591,7 +522,7 @@ p9pdu_writef(struct p9_fcall *pdu, int proto_version, const char *fmt, ...) return ret; } -int p9stat_read(char *buf, int len, struct p9_wstat *st, int proto_version) +int p9stat_read(struct p9_client *clnt, char *buf, int len, struct p9_wstat *st) { struct p9_fcall fake_pdu; int ret; @@ -601,10 +532,10 @@ int p9stat_read(char *buf, int len, struct p9_wstat *st, int proto_version) fake_pdu.sdata = buf; fake_pdu.offset = 0; - ret = p9pdu_readf(&fake_pdu, proto_version, "S", st); + ret = p9pdu_readf(&fake_pdu, clnt->proto_version, "S", st); if (ret) { P9_DPRINTK(P9_DEBUG_9P, "<<< p9stat_read failed: %d\n", ret); - P9_DUMP_PKT(0, &fake_pdu); + trace_9p_protocol_dump(clnt, &fake_pdu); } return ret; @@ -617,7 +548,7 @@ int p9pdu_prepare(struct p9_fcall *pdu, int16_t tag, int8_t type) return p9pdu_writef(pdu, 0, "dbw", 0, type, tag); } -int p9pdu_finalize(struct p9_fcall *pdu) +int p9pdu_finalize(struct p9_client *clnt, struct p9_fcall *pdu) { int size = pdu->size; int err; @@ -626,7 +557,7 @@ int p9pdu_finalize(struct p9_fcall *pdu) err = p9pdu_writef(pdu, 0, "d", size); pdu->size = size; - P9_DUMP_PKT(0, pdu); + trace_9p_protocol_dump(clnt, pdu); P9_DPRINTK(P9_DEBUG_9P, ">>> size=%d type: %d tag: %d\n", pdu->size, pdu->id, pdu->tag); @@ -637,14 +568,10 @@ void p9pdu_reset(struct p9_fcall *pdu) { pdu->offset = 0; pdu->size = 0; - pdu->private = NULL; - pdu->pubuf = NULL; - pdu->pkbuf = NULL; - pdu->pbuf_size = 0; } -int p9dirent_read(char *buf, int len, struct p9_dirent *dirent, - int proto_version) +int p9dirent_read(struct p9_client *clnt, char *buf, int len, + struct p9_dirent *dirent) { struct p9_fcall fake_pdu; int ret; @@ -655,11 +582,11 @@ int p9dirent_read(char *buf, int len, struct p9_dirent *dirent, fake_pdu.sdata = buf; fake_pdu.offset = 0; - ret = p9pdu_readf(&fake_pdu, proto_version, "Qqbs", &dirent->qid, - &dirent->d_off, &dirent->d_type, &nameptr); + ret = p9pdu_readf(&fake_pdu, clnt->proto_version, "Qqbs", &dirent->qid, + &dirent->d_off, &dirent->d_type, &nameptr); if (ret) { P9_DPRINTK(P9_DEBUG_9P, "<<< p9dirent_read failed: %d\n", ret); - P9_DUMP_PKT(1, &fake_pdu); + trace_9p_protocol_dump(clnt, &fake_pdu); goto out; } diff --git a/net/9p/protocol.h b/net/9p/protocol.h index 2431c0f..2cc525fa 100644 --- a/net/9p/protocol.h +++ b/net/9p/protocol.h @@ -29,6 +29,6 @@ int p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, va_list ap); int p9pdu_readf(struct p9_fcall *pdu, int proto_version, const char *fmt, ...); int p9pdu_prepare(struct p9_fcall *pdu, int16_t tag, int8_t type); -int p9pdu_finalize(struct p9_fcall *pdu); -void p9pdu_dump(int, struct p9_fcall *); +int p9pdu_finalize(struct p9_client *clnt, struct p9_fcall *pdu); void p9pdu_reset(struct p9_fcall *pdu); +size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size); diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c index 9a70ebd..de8df95 100644 --- a/net/9p/trans_common.c +++ b/net/9p/trans_common.c @@ -21,30 +21,25 @@ /** * p9_release_req_pages - Release pages after the transaction. - * @*private: PDU's private page of struct trans_rpage_info */ -void -p9_release_req_pages(struct trans_rpage_info *rpinfo) +void p9_release_pages(struct page **pages, int nr_pages) { int i = 0; - - while (rpinfo->rp_data[i] && rpinfo->rp_nr_pages--) { - put_page(rpinfo->rp_data[i]); + while (pages[i] && nr_pages--) { + put_page(pages[i]); i++; } } -EXPORT_SYMBOL(p9_release_req_pages); +EXPORT_SYMBOL(p9_release_pages); /** * p9_nr_pages - Return number of pages needed to accommodate the payload. */ -int -p9_nr_pages(struct p9_req_t *req) +int p9_nr_pages(char *data, int len) { 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; + start_page = (unsigned long)data >> PAGE_SHIFT; + end_page = ((unsigned long)data + len + PAGE_SIZE - 1) >> PAGE_SHIFT; return end_page - start_page; } EXPORT_SYMBOL(p9_nr_pages); @@ -58,35 +53,17 @@ EXPORT_SYMBOL(p9_nr_pages); * @nr_pages: number of pages to accommodate the payload * @rw: Indicates if the pages are for read or write. */ -int -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; - int32_t pdata_mapped_pages; - struct trans_rpage_info *rpinfo; - - *pdata_off = (__force size_t)req->tc->pubuf & (PAGE_SIZE-1); - if (*pdata_off) - first_page_bytes = min(((size_t)PAGE_SIZE - *pdata_off), - req->tc->pbuf_size); +int p9_payload_gup(char *data, int *nr_pages, struct page **pages, int write) +{ + int nr_mapped_pages; - 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; + nr_mapped_pages = get_user_pages_fast((unsigned long)data, + *nr_pages, write, pages); + if (nr_mapped_pages <= 0) + return nr_mapped_pages; - rpinfo->rp_nr_pages = pdata_mapped_pages; - if (*pdata_off) { - *pdata_len = first_page_bytes; - *pdata_len += min((req->tc->pbuf_size - *pdata_len), - ((size_t)pdata_mapped_pages - 1) << PAGE_SHIFT); - } else { - *pdata_len = min(req->tc->pbuf_size, - (size_t)pdata_mapped_pages << PAGE_SHIFT); - } + *nr_pages = nr_mapped_pages; return 0; } EXPORT_SYMBOL(p9_payload_gup); diff --git a/net/9p/trans_common.h b/net/9p/trans_common.h index 7630922..173bb55 100644 --- a/net/9p/trans_common.h +++ b/net/9p/trans_common.h @@ -12,21 +12,6 @@ * */ -/* TRUE if it is user context */ -#define P9_IS_USER_CONTEXT (!segment_eq(get_fs(), KERNEL_DS)) - -/** - * struct trans_rpage_info - To store mapped page information in PDU. - * @rp_alloc:Set if this structure is allocd, not a reuse unused space in pdu. - * @rp_nr_pages: Number of mapped pages - * @rp_data: Array of page pointers - */ -struct trans_rpage_info { - u8 rp_alloc; - int rp_nr_pages; - struct page *rp_data[0]; -}; - -void p9_release_req_pages(struct trans_rpage_info *); -int p9_payload_gup(struct p9_req_t *, size_t *, int *, int, u8); -int p9_nr_pages(struct p9_req_t *); +void p9_release_pages(struct page **, int); +int p9_payload_gup(char *, int *, struct page **, int); +int p9_nr_pages(char *, int); diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index e317583..32aa983 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -150,12 +150,10 @@ static void req_done(struct virtqueue *vq) while (1) { spin_lock_irqsave(&chan->lock, flags); rc = virtqueue_get_buf(chan->vq, &len); - 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. */ @@ -163,17 +161,6 @@ static void req_done(struct virtqueue *vq) 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; - } req->status = REQ_STATUS_RCVD; p9_client_cb(chan->client, req); } @@ -193,9 +180,8 @@ static void req_done(struct virtqueue *vq) * */ -static int -pack_sg_list(struct scatterlist *sg, int start, int limit, char *data, - int count) +static int pack_sg_list(struct scatterlist *sg, int start, + int limit, char *data, int count) { int s; int index = start; @@ -224,31 +210,36 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req) * this takes a list of pages. * @sg: scatter/gather list to pack into * @start: which segment of the sg_list to start at - * @pdata_off: Offset into the first page * @**pdata: a list of pages to add into sg. + * @nr_pages: number of pages to pack into the scatter/gather list + * @data: data to pack into scatter/gather list * @count: amount of data to pack into the scatter/gather list */ static int -pack_sg_list_p(struct scatterlist *sg, int start, int limit, size_t pdata_off, - struct page **pdata, int count) +pack_sg_list_p(struct scatterlist *sg, int start, int limit, + struct page **pdata, int nr_pages, char *data, int count) { - int s; - int i = 0; + int i = 0, s; + int data_off; int index = start; - if (pdata_off) { - s = min((int)(PAGE_SIZE - pdata_off), count); - sg_set_page(&sg[index++], pdata[i++], s, pdata_off); - count -= s; - } - - while (count) { - BUG_ON(index > limit); - s = min((int)PAGE_SIZE, count); - sg_set_page(&sg[index++], pdata[i++], s, 0); + BUG_ON(nr_pages > (limit - start)); + /* + * if the first page doesn't start at + * page boundary find the offset + */ + data_off = offset_in_page(data); + while (nr_pages) { + s = rest_of_page(data); + if (s > count) + s = count; + sg_set_page(&sg[index++], pdata[i++], s, data_off); + data_off = 0; + data += s; count -= s; + nr_pages--; } - return index-start; + return index - start; } /** @@ -261,114 +252,166 @@ pack_sg_list_p(struct scatterlist *sg, int start, int limit, size_t pdata_off, static int p9_virtio_request(struct p9_client *client, struct p9_req_t *req) { - int in, out, inp, outp; - struct virtio_chan *chan = client->trans; + int err; + int in, out; unsigned long flags; - size_t pdata_off = 0; - struct trans_rpage_info *rpinfo = NULL; - int err, pdata_len = 0; + struct virtio_chan *chan = client->trans; P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio request\n"); req->status = REQ_STATUS_SENT; +req_retry: + spin_lock_irqsave(&chan->lock, flags); + + /* Handle out VirtIO ring buffers */ + out = pack_sg_list(chan->sg, 0, + VIRTQUEUE_NUM, req->tc->sdata, req->tc->size); - if (req->tc->pbuf_size && (req->tc->pubuf && P9_IS_USER_CONTEXT)) { - int nr_pages = p9_nr_pages(req); - int rpinfo_size = sizeof(struct trans_rpage_info) + - sizeof(struct page *) * nr_pages; + in = pack_sg_list(chan->sg, out, + VIRTQUEUE_NUM, req->rc->sdata, req->rc->capacity); - if (atomic_read(&vp_pinned) >= chan->p9_max_pages) { - err = wait_event_interruptible(vp_wq, - atomic_read(&vp_pinned) < chan->p9_max_pages); + err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc); + if (err < 0) { + if (err == -ENOSPC) { + chan->ring_bufs_avail = 0; + spin_unlock_irqrestore(&chan->lock, flags); + err = wait_event_interruptible(*chan->vc_wq, + chan->ring_bufs_avail); 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; - rpinfo = (struct trans_rpage_info *)req->tc->private; - rpinfo->rp_alloc = 0; + P9_DPRINTK(P9_DEBUG_TRANS, "9p:Retry virtio request\n"); + goto req_retry; } else { - req->tc->private = kmalloc(rpinfo_size, GFP_NOFS); - if (!req->tc->private) { - P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: " - "private kmalloc returned NULL"); - return -ENOMEM; - } - rpinfo = (struct trans_rpage_info *)req->tc->private; - rpinfo->rp_alloc = 1; + spin_unlock_irqrestore(&chan->lock, flags); + P9_DPRINTK(P9_DEBUG_TRANS, + "9p debug: " + "virtio rpc add_buf returned failure"); + return -EIO; } + } + virtqueue_kick(chan->vq); + spin_unlock_irqrestore(&chan->lock, flags); - err = p9_payload_gup(req, &pdata_off, &pdata_len, nr_pages, - req->tc->id == P9_TREAD ? 1 : 0); - if (err < 0) { - if (rpinfo->rp_alloc) - kfree(rpinfo); + P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio request kicked\n"); + return 0; +} + +static int p9_get_mapped_pages(struct virtio_chan *chan, + struct page **pages, char *data, + int nr_pages, int write, int kern_buf) +{ + int err; + if (!kern_buf) { + /* + * We allow only p9_max_pages pinned. We wait for the + * Other zc request to finish here + */ + 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; + } + err = p9_payload_gup(data, &nr_pages, pages, write); + if (err < 0) return err; - } else { - atomic_add(rpinfo->rp_nr_pages, &vp_pinned); + atomic_add(nr_pages, &vp_pinned); + } else { + /* kernel buffer, no need to pin pages */ + int s, index = 0; + int count = nr_pages; + while (nr_pages) { + s = rest_of_page(data); + pages[index++] = virt_to_page(data); + data += s; + nr_pages--; } + nr_pages = count; } + return nr_pages; +} -req_retry_pinned: - spin_lock_irqsave(&chan->lock, flags); +/** + * p9_virtio_zc_request - issue a zero copy request + * @client: client instance issuing the request + * @req: request to be issued + * @uidata: user bffer that should be ued for zero copy read + * @uodata: user buffer that shoud be user for zero copy write + * @inlen: read buffer size + * @olen: write buffer size + * @hdrlen: reader header size, This is the size of response protocol data + * + */ +static int +p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req, + char *uidata, char *uodata, int inlen, + int outlen, int in_hdr_len, int kern_buf) +{ + int in, out, err; + unsigned long flags; + int in_nr_pages = 0, out_nr_pages = 0; + struct page **in_pages = NULL, **out_pages = NULL; + struct virtio_chan *chan = client->trans; - /* Handle out VirtIO ring buffers */ - out = pack_sg_list(chan->sg, 0, VIRTQUEUE_NUM, req->tc->sdata, - req->tc->size); - - if (req->tc->pbuf_size && (req->tc->id == P9_TWRITE)) { - /* We have additional write payload buffer to take care */ - if (req->tc->pubuf && P9_IS_USER_CONTEXT) { - outp = pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM, - pdata_off, rpinfo->rp_data, pdata_len); - } else { - 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); + P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio request\n"); + + if (uodata) { + out_nr_pages = p9_nr_pages(uodata, outlen); + out_pages = kmalloc(sizeof(struct page *) * out_nr_pages, + GFP_NOFS); + if (!out_pages) { + err = -ENOMEM; + goto err_out; + } + out_nr_pages = p9_get_mapped_pages(chan, out_pages, uodata, + out_nr_pages, 0, kern_buf); + if (out_nr_pages < 0) { + err = out_nr_pages; + kfree(out_pages); + out_pages = NULL; + goto err_out; } - out += outp; } - - /* Handle in VirtIO ring buffers */ - if (req->tc->pbuf_size && - ((req->tc->id == P9_TREAD) || (req->tc->id == P9_TREADDIR))) { - /* - * Take care of additional Read payload. - * 11 is the read/write header = PDU Header(7) + IO Size (4). - * Arrange in such a way that server places header in the - * alloced memory and payload onto the user buffer. - */ - inp = pack_sg_list(chan->sg, out, - VIRTQUEUE_NUM, req->rc->sdata, 11); - /* - * Running executables in the filesystem may result in - * a read request with kernel buffer as opposed to user buffer. - */ - if (req->tc->pubuf && P9_IS_USER_CONTEXT) { - in = pack_sg_list_p(chan->sg, out+inp, VIRTQUEUE_NUM, - pdata_off, rpinfo->rp_data, pdata_len); - } else { - 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); + if (uidata) { + in_nr_pages = p9_nr_pages(uidata, inlen); + in_pages = kmalloc(sizeof(struct page *) * in_nr_pages, + GFP_NOFS); + if (!in_pages) { + err = -ENOMEM; + goto err_out; + } + in_nr_pages = p9_get_mapped_pages(chan, in_pages, uidata, + in_nr_pages, 1, kern_buf); + if (in_nr_pages < 0) { + err = in_nr_pages; + kfree(in_pages); + in_pages = NULL; + goto err_out; } - in += inp; - } else { - in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, - req->rc->sdata, req->rc->capacity); } + req->status = REQ_STATUS_SENT; +req_retry_pinned: + spin_lock_irqsave(&chan->lock, flags); + /* out data */ + out = pack_sg_list(chan->sg, 0, + VIRTQUEUE_NUM, req->tc->sdata, req->tc->size); + + if (out_pages) + out += pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM, + out_pages, out_nr_pages, uodata, outlen); + /* + * Take care of in data + * For example TREAD have 11. + * 11 is the read/write header = PDU Header(7) + IO Size (4). + * Arrange in such a way that server places header in the + * alloced memory and payload onto the user buffer. + */ + in = pack_sg_list(chan->sg, out, + VIRTQUEUE_NUM, req->rc->sdata, in_hdr_len); + if (in_pages) + in += pack_sg_list_p(chan->sg, out + in, VIRTQUEUE_NUM, + in_pages, in_nr_pages, uidata, inlen); err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc); if (err < 0) { @@ -376,28 +419,45 @@ req_retry_pinned: chan->ring_bufs_avail = 0; spin_unlock_irqrestore(&chan->lock, flags); err = wait_event_interruptible(*chan->vc_wq, - chan->ring_bufs_avail); + chan->ring_bufs_avail); if (err == -ERESTARTSYS) - return err; + goto err_out; P9_DPRINTK(P9_DEBUG_TRANS, "9p:Retry virtio request\n"); goto req_retry_pinned; } else { spin_unlock_irqrestore(&chan->lock, flags); P9_DPRINTK(P9_DEBUG_TRANS, - "9p debug: " - "virtio rpc add_buf returned failure"); - if (rpinfo && rpinfo->rp_alloc) - kfree(rpinfo); - return -EIO; + "9p debug: " + "virtio rpc add_buf returned failure"); + err = -EIO; + goto err_out; } } - virtqueue_kick(chan->vq); spin_unlock_irqrestore(&chan->lock, flags); - P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio request kicked\n"); - return 0; + err = wait_event_interruptible(*req->wq, + req->status >= REQ_STATUS_RCVD); + /* + * Non kernel buffers are pinned, unpin them + */ +err_out: + if (!kern_buf) { + if (in_pages) { + p9_release_pages(in_pages, in_nr_pages); + atomic_sub(in_nr_pages, &vp_pinned); + } + if (out_pages) { + p9_release_pages(out_pages, out_nr_pages); + atomic_sub(out_nr_pages, &vp_pinned); + } + /* wakeup anybody waiting for slots to pin pages */ + wake_up(&vp_wq); + } + kfree(in_pages); + kfree(out_pages); + return err; } static ssize_t p9_mount_tag_show(struct device *dev, @@ -591,8 +651,8 @@ static struct p9_trans_module p9_virtio_trans = { .create = p9_virtio_create, .close = p9_virtio_close, .request = p9_virtio_request, + .zc_request = p9_virtio_zc_request, .cancel = p9_virtio_cancel, - /* * We leave one entry for input and one entry for response * headers. We also skip one more entry to accomodate, address @@ -600,7 +660,6 @@ static struct p9_trans_module p9_virtio_trans = { * page in zero copy. */ .maxsize = PAGE_SIZE * (VIRTQUEUE_NUM - 3), - .pref = P9_TRANS_PREF_PAYLOAD_SEP, .def = 0, .owner = THIS_MODULE, }; diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index b1fe7c3..bfa9ab9 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -951,13 +951,12 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset, /* checksum stuff in frags */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; - + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (copy > len) copy = len; diff --git a/net/atm/lec.c b/net/atm/lec.c index 215c9fa..f1964ca 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -643,7 +643,7 @@ static const struct net_device_ops lec_netdev_ops = { .ndo_start_xmit = lec_start_xmit, .ndo_change_mtu = lec_change_mtu, .ndo_tx_timeout = lec_tx_timeout, - .ndo_set_multicast_list = lec_set_multicast_list, + .ndo_set_rx_mode = lec_set_multicast_list, }; static const unsigned char lec_ctrl_magic[] = { diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index 2de93d0..ce68611 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -19,8 +19,8 @@ # obj-$(CONFIG_BATMAN_ADV) += batman-adv.o -batman-adv-y += aggregation.o batman-adv-y += bat_debugfs.o +batman-adv-y += bat_iv_ogm.o batman-adv-y += bat_sysfs.o batman-adv-y += bitarray.o batman-adv-y += gateway_client.o diff --git a/net/batman-adv/aggregation.c b/net/batman-adv/aggregation.c deleted file mode 100644 index 69467fe..0000000 --- a/net/batman-adv/aggregation.c +++ /dev/null @@ -1,293 +0,0 @@ -/* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: - * - * Marek Lindner, Simon Wunderlich - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA - * - */ - -#include "main.h" -#include "translation-table.h" -#include "aggregation.h" -#include "send.h" -#include "routing.h" -#include "hard-interface.h" - -/* return true if new_packet can be aggregated with forw_packet */ -static bool can_aggregate_with(const struct batman_packet *new_batman_packet, - struct bat_priv *bat_priv, - int packet_len, - unsigned long send_time, - bool directlink, - const struct hard_iface *if_incoming, - const struct forw_packet *forw_packet) -{ - struct batman_packet *batman_packet = - (struct batman_packet *)forw_packet->skb->data; - int aggregated_bytes = forw_packet->packet_len + packet_len; - struct hard_iface *primary_if = NULL; - bool res = false; - - /** - * we can aggregate the current packet to this aggregated packet - * if: - * - * - the send time is within our MAX_AGGREGATION_MS time - * - the resulting packet wont be bigger than - * MAX_AGGREGATION_BYTES - */ - - if (time_before(send_time, forw_packet->send_time) && - time_after_eq(send_time + msecs_to_jiffies(MAX_AGGREGATION_MS), - forw_packet->send_time) && - (aggregated_bytes <= MAX_AGGREGATION_BYTES)) { - - /** - * check aggregation compatibility - * -> direct link packets are broadcasted on - * their interface only - * -> aggregate packet if the current packet is - * a "global" packet as well as the base - * packet - */ - - primary_if = primary_if_get_selected(bat_priv); - if (!primary_if) - goto out; - - /* packets without direct link flag and high TTL - * are flooded through the net */ - if ((!directlink) && - (!(batman_packet->flags & DIRECTLINK)) && - (batman_packet->ttl != 1) && - - /* own packets originating non-primary - * interfaces leave only that interface */ - ((!forw_packet->own) || - (forw_packet->if_incoming == primary_if))) { - res = true; - goto out; - } - - /* if the incoming packet is sent via this one - * interface only - we still can aggregate */ - if ((directlink) && - (new_batman_packet->ttl == 1) && - (forw_packet->if_incoming == if_incoming) && - - /* packets from direct neighbors or - * own secondary interface packets - * (= secondary interface packets in general) */ - (batman_packet->flags & DIRECTLINK || - (forw_packet->own && - forw_packet->if_incoming != primary_if))) { - res = true; - goto out; - } - } - -out: - if (primary_if) - hardif_free_ref(primary_if); - return res; -} - -/* create a new aggregated packet and add this packet to it */ -static void new_aggregated_packet(const unsigned char *packet_buff, - int packet_len, unsigned long send_time, - bool direct_link, - struct hard_iface *if_incoming, - int own_packet) -{ - struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct forw_packet *forw_packet_aggr; - unsigned char *skb_buff; - - if (!atomic_inc_not_zero(&if_incoming->refcount)) - return; - - /* own packet should always be scheduled */ - if (!own_packet) { - if (!atomic_dec_not_zero(&bat_priv->batman_queue_left)) { - bat_dbg(DBG_BATMAN, bat_priv, - "batman packet queue full\n"); - goto out; - } - } - - forw_packet_aggr = kmalloc(sizeof(*forw_packet_aggr), GFP_ATOMIC); - if (!forw_packet_aggr) { - if (!own_packet) - atomic_inc(&bat_priv->batman_queue_left); - goto out; - } - - if ((atomic_read(&bat_priv->aggregated_ogms)) && - (packet_len < MAX_AGGREGATION_BYTES)) - forw_packet_aggr->skb = dev_alloc_skb(MAX_AGGREGATION_BYTES + - sizeof(struct ethhdr)); - else - forw_packet_aggr->skb = dev_alloc_skb(packet_len + - sizeof(struct ethhdr)); - - if (!forw_packet_aggr->skb) { - if (!own_packet) - atomic_inc(&bat_priv->batman_queue_left); - kfree(forw_packet_aggr); - goto out; - } - skb_reserve(forw_packet_aggr->skb, sizeof(struct ethhdr)); - - INIT_HLIST_NODE(&forw_packet_aggr->list); - - skb_buff = skb_put(forw_packet_aggr->skb, packet_len); - forw_packet_aggr->packet_len = packet_len; - memcpy(skb_buff, packet_buff, packet_len); - - forw_packet_aggr->own = own_packet; - forw_packet_aggr->if_incoming = if_incoming; - forw_packet_aggr->num_packets = 0; - forw_packet_aggr->direct_link_flags = NO_FLAGS; - forw_packet_aggr->send_time = send_time; - - /* save packet direct link flag status */ - if (direct_link) - forw_packet_aggr->direct_link_flags |= 1; - - /* add new packet to packet list */ - spin_lock_bh(&bat_priv->forw_bat_list_lock); - hlist_add_head(&forw_packet_aggr->list, &bat_priv->forw_bat_list); - spin_unlock_bh(&bat_priv->forw_bat_list_lock); - - /* start timer for this packet */ - INIT_DELAYED_WORK(&forw_packet_aggr->delayed_work, - send_outstanding_bat_packet); - queue_delayed_work(bat_event_workqueue, - &forw_packet_aggr->delayed_work, - send_time - jiffies); - - return; -out: - hardif_free_ref(if_incoming); -} - -/* aggregate a new packet into the existing aggregation */ -static void aggregate(struct forw_packet *forw_packet_aggr, - const unsigned char *packet_buff, int packet_len, - bool direct_link) -{ - unsigned char *skb_buff; - - skb_buff = skb_put(forw_packet_aggr->skb, packet_len); - memcpy(skb_buff, packet_buff, packet_len); - forw_packet_aggr->packet_len += packet_len; - forw_packet_aggr->num_packets++; - - /* save packet direct link flag status */ - if (direct_link) - forw_packet_aggr->direct_link_flags |= - (1 << forw_packet_aggr->num_packets); -} - -void add_bat_packet_to_list(struct bat_priv *bat_priv, - unsigned char *packet_buff, int packet_len, - struct hard_iface *if_incoming, int own_packet, - unsigned long send_time) -{ - /** - * _aggr -> pointer to the packet we want to aggregate with - * _pos -> pointer to the position in the queue - */ - struct forw_packet *forw_packet_aggr = NULL, *forw_packet_pos = NULL; - struct hlist_node *tmp_node; - struct batman_packet *batman_packet = - (struct batman_packet *)packet_buff; - bool direct_link = batman_packet->flags & DIRECTLINK ? 1 : 0; - - /* find position for the packet in the forward queue */ - spin_lock_bh(&bat_priv->forw_bat_list_lock); - /* own packets are not to be aggregated */ - if ((atomic_read(&bat_priv->aggregated_ogms)) && (!own_packet)) { - hlist_for_each_entry(forw_packet_pos, tmp_node, - &bat_priv->forw_bat_list, list) { - if (can_aggregate_with(batman_packet, - bat_priv, - packet_len, - send_time, - direct_link, - if_incoming, - forw_packet_pos)) { - forw_packet_aggr = forw_packet_pos; - break; - } - } - } - - /* nothing to aggregate with - either aggregation disabled or no - * suitable aggregation packet found */ - if (!forw_packet_aggr) { - /* the following section can run without the lock */ - spin_unlock_bh(&bat_priv->forw_bat_list_lock); - - /** - * if we could not aggregate this packet with one of the others - * we hold it back for a while, so that it might be aggregated - * later on - */ - if ((!own_packet) && - (atomic_read(&bat_priv->aggregated_ogms))) - send_time += msecs_to_jiffies(MAX_AGGREGATION_MS); - - new_aggregated_packet(packet_buff, packet_len, - send_time, direct_link, - if_incoming, own_packet); - } else { - aggregate(forw_packet_aggr, - packet_buff, packet_len, - direct_link); - spin_unlock_bh(&bat_priv->forw_bat_list_lock); - } -} - -/* unpack the aggregated packets and process them one by one */ -void receive_aggr_bat_packet(const struct ethhdr *ethhdr, - unsigned char *packet_buff, int packet_len, - struct hard_iface *if_incoming) -{ - struct batman_packet *batman_packet; - int buff_pos = 0; - unsigned char *tt_buff; - - batman_packet = (struct batman_packet *)packet_buff; - - do { - /* network to host order for our 32bit seqno and the - orig_interval */ - batman_packet->seqno = ntohl(batman_packet->seqno); - batman_packet->tt_crc = ntohs(batman_packet->tt_crc); - - tt_buff = packet_buff + buff_pos + BAT_PACKET_LEN; - - receive_bat_packet(ethhdr, batman_packet, tt_buff, if_incoming); - - buff_pos += BAT_PACKET_LEN + - tt_len(batman_packet->tt_num_changes); - - batman_packet = (struct batman_packet *) - (packet_buff + buff_pos); - } while (aggregated_packet(buff_pos, packet_len, - batman_packet->tt_num_changes)); -} diff --git a/net/batman-adv/aggregation.h b/net/batman-adv/aggregation.h deleted file mode 100644 index 216337b..0000000 --- a/net/batman-adv/aggregation.h +++ /dev/null @@ -1,46 +0,0 @@ -/* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: - * - * Marek Lindner, Simon Wunderlich - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA - * - */ - -#ifndef _NET_BATMAN_ADV_AGGREGATION_H_ -#define _NET_BATMAN_ADV_AGGREGATION_H_ - -#include "main.h" - -/* is there another aggregated packet here? */ -static inline int aggregated_packet(int buff_pos, int packet_len, - int tt_num_changes) -{ - int next_buff_pos = buff_pos + BAT_PACKET_LEN + (tt_num_changes * - sizeof(struct tt_change)); - - return (next_buff_pos <= packet_len) && - (next_buff_pos <= MAX_AGGREGATION_BYTES); -} - -void add_bat_packet_to_list(struct bat_priv *bat_priv, - unsigned char *packet_buff, int packet_len, - struct hard_iface *if_incoming, int own_packet, - unsigned long send_time); -void receive_aggr_bat_packet(const struct ethhdr *ethhdr, - unsigned char *packet_buff, int packet_len, - struct hard_iface *if_incoming); - -#endif /* _NET_BATMAN_ADV_AGGREGATION_H_ */ diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c new file mode 100644 index 0000000..3512e25 --- /dev/null +++ b/net/batman-adv/bat_iv_ogm.c @@ -0,0 +1,1170 @@ +/* + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * + * Marek Lindner, Simon Wunderlich + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA + * + */ + +#include "main.h" +#include "bat_ogm.h" +#include "translation-table.h" +#include "ring_buffer.h" +#include "originator.h" +#include "routing.h" +#include "gateway_common.h" +#include "gateway_client.h" +#include "hard-interface.h" +#include "send.h" + +void bat_ogm_init(struct hard_iface *hard_iface) +{ + struct batman_ogm_packet *batman_ogm_packet; + + hard_iface->packet_len = BATMAN_OGM_LEN; + hard_iface->packet_buff = kmalloc(hard_iface->packet_len, GFP_ATOMIC); + + batman_ogm_packet = (struct batman_ogm_packet *)hard_iface->packet_buff; + batman_ogm_packet->packet_type = BAT_OGM; + batman_ogm_packet->version = COMPAT_VERSION; + batman_ogm_packet->flags = NO_FLAGS; + batman_ogm_packet->ttl = 2; + batman_ogm_packet->tq = TQ_MAX_VALUE; + batman_ogm_packet->tt_num_changes = 0; + batman_ogm_packet->ttvn = 0; +} + +void bat_ogm_init_primary(struct hard_iface *hard_iface) +{ + struct batman_ogm_packet *batman_ogm_packet; + + batman_ogm_packet = (struct batman_ogm_packet *)hard_iface->packet_buff; + batman_ogm_packet->flags = PRIMARIES_FIRST_HOP; + batman_ogm_packet->ttl = TTL; +} + +void bat_ogm_update_mac(struct hard_iface *hard_iface) +{ + struct batman_ogm_packet *batman_ogm_packet; + + batman_ogm_packet = (struct batman_ogm_packet *)hard_iface->packet_buff; + memcpy(batman_ogm_packet->orig, + hard_iface->net_dev->dev_addr, ETH_ALEN); + memcpy(batman_ogm_packet->prev_sender, + hard_iface->net_dev->dev_addr, ETH_ALEN); +} + +/* when do we schedule our own ogm to be sent */ +static unsigned long bat_ogm_emit_send_time(const struct bat_priv *bat_priv) +{ + return jiffies + msecs_to_jiffies( + atomic_read(&bat_priv->orig_interval) - + JITTER + (random32() % 2*JITTER)); +} + +/* when do we schedule a ogm packet to be sent */ +static unsigned long bat_ogm_fwd_send_time(void) +{ + return jiffies + msecs_to_jiffies(random32() % (JITTER/2)); +} + +/* apply hop penalty for a normal link */ +static uint8_t hop_penalty(uint8_t tq, const struct bat_priv *bat_priv) +{ + int hop_penalty = atomic_read(&bat_priv->hop_penalty); + return (tq * (TQ_MAX_VALUE - hop_penalty)) / (TQ_MAX_VALUE); +} + +/* is there another aggregated packet here? */ +static int bat_ogm_aggr_packet(int buff_pos, int packet_len, + int tt_num_changes) +{ + int next_buff_pos = buff_pos + BATMAN_OGM_LEN + tt_len(tt_num_changes); + + return (next_buff_pos <= packet_len) && + (next_buff_pos <= MAX_AGGREGATION_BYTES); +} + +/* send a batman ogm to a given interface */ +static void bat_ogm_send_to_if(struct forw_packet *forw_packet, + struct hard_iface *hard_iface) +{ + struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + char *fwd_str; + uint8_t packet_num; + int16_t buff_pos; + struct batman_ogm_packet *batman_ogm_packet; + struct sk_buff *skb; + + if (hard_iface->if_status != IF_ACTIVE) + return; + + packet_num = 0; + buff_pos = 0; + batman_ogm_packet = (struct batman_ogm_packet *)forw_packet->skb->data; + + /* adjust all flags and log packets */ + while (bat_ogm_aggr_packet(buff_pos, forw_packet->packet_len, + batman_ogm_packet->tt_num_changes)) { + + /* we might have aggregated direct link packets with an + * ordinary base packet */ + if ((forw_packet->direct_link_flags & (1 << packet_num)) && + (forw_packet->if_incoming == hard_iface)) + batman_ogm_packet->flags |= DIRECTLINK; + else + batman_ogm_packet->flags &= ~DIRECTLINK; + + fwd_str = (packet_num > 0 ? "Forwarding" : (forw_packet->own ? + "Sending own" : + "Forwarding")); + bat_dbg(DBG_BATMAN, bat_priv, + "%s %spacket (originator %pM, seqno %d, TQ %d, TTL %d," + " IDF %s, ttvn %d) on interface %s [%pM]\n", + fwd_str, (packet_num > 0 ? "aggregated " : ""), + batman_ogm_packet->orig, + ntohl(batman_ogm_packet->seqno), + batman_ogm_packet->tq, batman_ogm_packet->ttl, + (batman_ogm_packet->flags & DIRECTLINK ? + "on" : "off"), + batman_ogm_packet->ttvn, hard_iface->net_dev->name, + hard_iface->net_dev->dev_addr); + + buff_pos += BATMAN_OGM_LEN + + tt_len(batman_ogm_packet->tt_num_changes); + packet_num++; + batman_ogm_packet = (struct batman_ogm_packet *) + (forw_packet->skb->data + buff_pos); + } + + /* create clone because function is called more than once */ + skb = skb_clone(forw_packet->skb, GFP_ATOMIC); + if (skb) + send_skb_packet(skb, hard_iface, broadcast_addr); +} + +/* send a batman ogm packet */ +void bat_ogm_emit(struct forw_packet *forw_packet) +{ + struct hard_iface *hard_iface; + struct net_device *soft_iface; + struct bat_priv *bat_priv; + struct hard_iface *primary_if = NULL; + struct batman_ogm_packet *batman_ogm_packet; + unsigned char directlink; + + batman_ogm_packet = (struct batman_ogm_packet *) + (forw_packet->skb->data); + directlink = (batman_ogm_packet->flags & DIRECTLINK ? 1 : 0); + + if (!forw_packet->if_incoming) { + pr_err("Error - can't forward packet: incoming iface not " + "specified\n"); + goto out; + } + + soft_iface = forw_packet->if_incoming->soft_iface; + bat_priv = netdev_priv(soft_iface); + + if (forw_packet->if_incoming->if_status != IF_ACTIVE) + goto out; + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + + /* multihomed peer assumed */ + /* non-primary OGMs are only broadcasted on their interface */ + if ((directlink && (batman_ogm_packet->ttl == 1)) || + (forw_packet->own && (forw_packet->if_incoming != primary_if))) { + + /* FIXME: what about aggregated packets ? */ + bat_dbg(DBG_BATMAN, bat_priv, + "%s packet (originator %pM, seqno %d, TTL %d) " + "on interface %s [%pM]\n", + (forw_packet->own ? "Sending own" : "Forwarding"), + batman_ogm_packet->orig, + ntohl(batman_ogm_packet->seqno), + batman_ogm_packet->ttl, + forw_packet->if_incoming->net_dev->name, + forw_packet->if_incoming->net_dev->dev_addr); + + /* skb is only used once and than forw_packet is free'd */ + send_skb_packet(forw_packet->skb, forw_packet->if_incoming, + broadcast_addr); + forw_packet->skb = NULL; + + goto out; + } + + /* broadcast on every interface */ + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &hardif_list, list) { + if (hard_iface->soft_iface != soft_iface) + continue; + + bat_ogm_send_to_if(forw_packet, hard_iface); + } + rcu_read_unlock(); + +out: + if (primary_if) + hardif_free_ref(primary_if); +} + +/* return true if new_packet can be aggregated with forw_packet */ +static bool bat_ogm_can_aggregate(const struct batman_ogm_packet + *new_batman_ogm_packet, + struct bat_priv *bat_priv, + int packet_len, unsigned long send_time, + bool directlink, + const struct hard_iface *if_incoming, + const struct forw_packet *forw_packet) +{ + struct batman_ogm_packet *batman_ogm_packet; + int aggregated_bytes = forw_packet->packet_len + packet_len; + struct hard_iface *primary_if = NULL; + bool res = false; + + batman_ogm_packet = (struct batman_ogm_packet *)forw_packet->skb->data; + + /** + * we can aggregate the current packet to this aggregated packet + * if: + * + * - the send time is within our MAX_AGGREGATION_MS time + * - the resulting packet wont be bigger than + * MAX_AGGREGATION_BYTES + */ + + if (time_before(send_time, forw_packet->send_time) && + time_after_eq(send_time + msecs_to_jiffies(MAX_AGGREGATION_MS), + forw_packet->send_time) && + (aggregated_bytes <= MAX_AGGREGATION_BYTES)) { + + /** + * check aggregation compatibility + * -> direct link packets are broadcasted on + * their interface only + * -> aggregate packet if the current packet is + * a "global" packet as well as the base + * packet + */ + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + + /* packets without direct link flag and high TTL + * are flooded through the net */ + if ((!directlink) && + (!(batman_ogm_packet->flags & DIRECTLINK)) && + (batman_ogm_packet->ttl != 1) && + + /* own packets originating non-primary + * interfaces leave only that interface */ + ((!forw_packet->own) || + (forw_packet->if_incoming == primary_if))) { + res = true; + goto out; + } + + /* if the incoming packet is sent via this one + * interface only - we still can aggregate */ + if ((directlink) && + (new_batman_ogm_packet->ttl == 1) && + (forw_packet->if_incoming == if_incoming) && + + /* packets from direct neighbors or + * own secondary interface packets + * (= secondary interface packets in general) */ + (batman_ogm_packet->flags & DIRECTLINK || + (forw_packet->own && + forw_packet->if_incoming != primary_if))) { + res = true; + goto out; + } + } + +out: + if (primary_if) + hardif_free_ref(primary_if); + return res; +} + +/* create a new aggregated packet and add this packet to it */ +static void bat_ogm_aggregate_new(const unsigned char *packet_buff, + int packet_len, unsigned long send_time, + bool direct_link, + struct hard_iface *if_incoming, + int own_packet) +{ + struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct forw_packet *forw_packet_aggr; + unsigned char *skb_buff; + + if (!atomic_inc_not_zero(&if_incoming->refcount)) + return; + + /* own packet should always be scheduled */ + if (!own_packet) { + if (!atomic_dec_not_zero(&bat_priv->batman_queue_left)) { + bat_dbg(DBG_BATMAN, bat_priv, + "batman packet queue full\n"); + goto out; + } + } + + forw_packet_aggr = kmalloc(sizeof(*forw_packet_aggr), GFP_ATOMIC); + if (!forw_packet_aggr) { + if (!own_packet) + atomic_inc(&bat_priv->batman_queue_left); + goto out; + } + + if ((atomic_read(&bat_priv->aggregated_ogms)) && + (packet_len < MAX_AGGREGATION_BYTES)) + forw_packet_aggr->skb = dev_alloc_skb(MAX_AGGREGATION_BYTES + + sizeof(struct ethhdr)); + else + forw_packet_aggr->skb = dev_alloc_skb(packet_len + + sizeof(struct ethhdr)); + + if (!forw_packet_aggr->skb) { + if (!own_packet) + atomic_inc(&bat_priv->batman_queue_left); + kfree(forw_packet_aggr); + goto out; + } + skb_reserve(forw_packet_aggr->skb, sizeof(struct ethhdr)); + + INIT_HLIST_NODE(&forw_packet_aggr->list); + + skb_buff = skb_put(forw_packet_aggr->skb, packet_len); + forw_packet_aggr->packet_len = packet_len; + memcpy(skb_buff, packet_buff, packet_len); + + forw_packet_aggr->own = own_packet; + forw_packet_aggr->if_incoming = if_incoming; + forw_packet_aggr->num_packets = 0; + forw_packet_aggr->direct_link_flags = NO_FLAGS; + forw_packet_aggr->send_time = send_time; + + /* save packet direct link flag status */ + if (direct_link) + forw_packet_aggr->direct_link_flags |= 1; + + /* add new packet to packet list */ + spin_lock_bh(&bat_priv->forw_bat_list_lock); + hlist_add_head(&forw_packet_aggr->list, &bat_priv->forw_bat_list); + spin_unlock_bh(&bat_priv->forw_bat_list_lock); + + /* start timer for this packet */ + INIT_DELAYED_WORK(&forw_packet_aggr->delayed_work, + send_outstanding_bat_ogm_packet); + queue_delayed_work(bat_event_workqueue, + &forw_packet_aggr->delayed_work, + send_time - jiffies); + + return; +out: + hardif_free_ref(if_incoming); +} + +/* aggregate a new packet into the existing ogm packet */ +static void bat_ogm_aggregate(struct forw_packet *forw_packet_aggr, + const unsigned char *packet_buff, + int packet_len, bool direct_link) +{ + unsigned char *skb_buff; + + skb_buff = skb_put(forw_packet_aggr->skb, packet_len); + memcpy(skb_buff, packet_buff, packet_len); + forw_packet_aggr->packet_len += packet_len; + forw_packet_aggr->num_packets++; + + /* save packet direct link flag status */ + if (direct_link) + forw_packet_aggr->direct_link_flags |= + (1 << forw_packet_aggr->num_packets); +} + +static void bat_ogm_queue_add(struct bat_priv *bat_priv, + unsigned char *packet_buff, + int packet_len, struct hard_iface *if_incoming, + int own_packet, unsigned long send_time) +{ + /** + * _aggr -> pointer to the packet we want to aggregate with + * _pos -> pointer to the position in the queue + */ + struct forw_packet *forw_packet_aggr = NULL, *forw_packet_pos = NULL; + struct hlist_node *tmp_node; + struct batman_ogm_packet *batman_ogm_packet; + bool direct_link; + + batman_ogm_packet = (struct batman_ogm_packet *)packet_buff; + direct_link = batman_ogm_packet->flags & DIRECTLINK ? 1 : 0; + + /* find position for the packet in the forward queue */ + spin_lock_bh(&bat_priv->forw_bat_list_lock); + /* own packets are not to be aggregated */ + if ((atomic_read(&bat_priv->aggregated_ogms)) && (!own_packet)) { + hlist_for_each_entry(forw_packet_pos, tmp_node, + &bat_priv->forw_bat_list, list) { + if (bat_ogm_can_aggregate(batman_ogm_packet, + bat_priv, packet_len, + send_time, direct_link, + if_incoming, + forw_packet_pos)) { + forw_packet_aggr = forw_packet_pos; + break; + } + } + } + + /* nothing to aggregate with - either aggregation disabled or no + * suitable aggregation packet found */ + if (!forw_packet_aggr) { + /* the following section can run without the lock */ + spin_unlock_bh(&bat_priv->forw_bat_list_lock); + + /** + * if we could not aggregate this packet with one of the others + * we hold it back for a while, so that it might be aggregated + * later on + */ + if ((!own_packet) && + (atomic_read(&bat_priv->aggregated_ogms))) + send_time += msecs_to_jiffies(MAX_AGGREGATION_MS); + + bat_ogm_aggregate_new(packet_buff, packet_len, + send_time, direct_link, + if_incoming, own_packet); + } else { + bat_ogm_aggregate(forw_packet_aggr, packet_buff, packet_len, + direct_link); + spin_unlock_bh(&bat_priv->forw_bat_list_lock); + } +} + +static void bat_ogm_forward(struct orig_node *orig_node, + const struct ethhdr *ethhdr, + struct batman_ogm_packet *batman_ogm_packet, + int directlink, struct hard_iface *if_incoming) +{ + struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct neigh_node *router; + uint8_t in_tq, in_ttl, tq_avg = 0; + uint8_t tt_num_changes; + + if (batman_ogm_packet->ttl <= 1) { + bat_dbg(DBG_BATMAN, bat_priv, "ttl exceeded\n"); + return; + } + + router = orig_node_get_router(orig_node); + + in_tq = batman_ogm_packet->tq; + in_ttl = batman_ogm_packet->ttl; + tt_num_changes = batman_ogm_packet->tt_num_changes; + + batman_ogm_packet->ttl--; + memcpy(batman_ogm_packet->prev_sender, ethhdr->h_source, ETH_ALEN); + + /* rebroadcast tq of our best ranking neighbor to ensure the rebroadcast + * of our best tq value */ + if (router && router->tq_avg != 0) { + + /* rebroadcast ogm of best ranking neighbor as is */ + if (!compare_eth(router->addr, ethhdr->h_source)) { + batman_ogm_packet->tq = router->tq_avg; + + if (router->last_ttl) + batman_ogm_packet->ttl = router->last_ttl - 1; + } + + tq_avg = router->tq_avg; + } + + if (router) + neigh_node_free_ref(router); + + /* apply hop penalty */ + batman_ogm_packet->tq = hop_penalty(batman_ogm_packet->tq, bat_priv); + + bat_dbg(DBG_BATMAN, bat_priv, + "Forwarding packet: tq_orig: %i, tq_avg: %i, " + "tq_forw: %i, ttl_orig: %i, ttl_forw: %i\n", + in_tq, tq_avg, batman_ogm_packet->tq, in_ttl - 1, + batman_ogm_packet->ttl); + + batman_ogm_packet->seqno = htonl(batman_ogm_packet->seqno); + batman_ogm_packet->tt_crc = htons(batman_ogm_packet->tt_crc); + + /* switch of primaries first hop flag when forwarding */ + batman_ogm_packet->flags &= ~PRIMARIES_FIRST_HOP; + if (directlink) + batman_ogm_packet->flags |= DIRECTLINK; + else + batman_ogm_packet->flags &= ~DIRECTLINK; + + bat_ogm_queue_add(bat_priv, (unsigned char *)batman_ogm_packet, + BATMAN_OGM_LEN + tt_len(tt_num_changes), + if_incoming, 0, bat_ogm_fwd_send_time()); +} + +void bat_ogm_schedule(struct hard_iface *hard_iface, int tt_num_changes) +{ + struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + struct batman_ogm_packet *batman_ogm_packet; + struct hard_iface *primary_if; + int vis_server; + + vis_server = atomic_read(&bat_priv->vis_mode); + primary_if = primary_if_get_selected(bat_priv); + + batman_ogm_packet = (struct batman_ogm_packet *)hard_iface->packet_buff; + + /* change sequence number to network order */ + batman_ogm_packet->seqno = + htonl((uint32_t)atomic_read(&hard_iface->seqno)); + + batman_ogm_packet->ttvn = atomic_read(&bat_priv->ttvn); + batman_ogm_packet->tt_crc = htons((uint16_t) + atomic_read(&bat_priv->tt_crc)); + if (tt_num_changes >= 0) + batman_ogm_packet->tt_num_changes = tt_num_changes; + + if (vis_server == VIS_TYPE_SERVER_SYNC) + batman_ogm_packet->flags |= VIS_SERVER; + else + batman_ogm_packet->flags &= ~VIS_SERVER; + + if ((hard_iface == primary_if) && + (atomic_read(&bat_priv->gw_mode) == GW_MODE_SERVER)) + batman_ogm_packet->gw_flags = + (uint8_t)atomic_read(&bat_priv->gw_bandwidth); + else + batman_ogm_packet->gw_flags = NO_FLAGS; + + atomic_inc(&hard_iface->seqno); + + slide_own_bcast_window(hard_iface); + bat_ogm_queue_add(bat_priv, hard_iface->packet_buff, + hard_iface->packet_len, hard_iface, 1, + bat_ogm_emit_send_time(bat_priv)); + + if (primary_if) + hardif_free_ref(primary_if); +} + +static void bat_ogm_orig_update(struct bat_priv *bat_priv, + struct orig_node *orig_node, + const struct ethhdr *ethhdr, + const struct batman_ogm_packet + *batman_ogm_packet, + struct hard_iface *if_incoming, + const unsigned char *tt_buff, int is_duplicate) +{ + struct neigh_node *neigh_node = NULL, *tmp_neigh_node = NULL; + struct neigh_node *router = NULL; + struct orig_node *orig_node_tmp; + struct hlist_node *node; + uint8_t bcast_own_sum_orig, bcast_own_sum_neigh; + + bat_dbg(DBG_BATMAN, bat_priv, "update_originator(): " + "Searching and updating originator entry of received packet\n"); + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp_neigh_node, node, + &orig_node->neigh_list, list) { + if (compare_eth(tmp_neigh_node->addr, ethhdr->h_source) && + (tmp_neigh_node->if_incoming == if_incoming) && + atomic_inc_not_zero(&tmp_neigh_node->refcount)) { + if (neigh_node) + neigh_node_free_ref(neigh_node); + neigh_node = tmp_neigh_node; + continue; + } + + if (is_duplicate) + continue; + + spin_lock_bh(&tmp_neigh_node->tq_lock); + ring_buffer_set(tmp_neigh_node->tq_recv, + &tmp_neigh_node->tq_index, 0); + tmp_neigh_node->tq_avg = + ring_buffer_avg(tmp_neigh_node->tq_recv); + spin_unlock_bh(&tmp_neigh_node->tq_lock); + } + + if (!neigh_node) { + struct orig_node *orig_tmp; + + orig_tmp = get_orig_node(bat_priv, ethhdr->h_source); + if (!orig_tmp) + goto unlock; + + neigh_node = create_neighbor(orig_node, orig_tmp, + ethhdr->h_source, if_incoming); + + orig_node_free_ref(orig_tmp); + if (!neigh_node) + goto unlock; + } else + bat_dbg(DBG_BATMAN, bat_priv, + "Updating existing last-hop neighbor of originator\n"); + + rcu_read_unlock(); + + orig_node->flags = batman_ogm_packet->flags; + neigh_node->last_valid = jiffies; + + spin_lock_bh(&neigh_node->tq_lock); + ring_buffer_set(neigh_node->tq_recv, + &neigh_node->tq_index, + batman_ogm_packet->tq); + neigh_node->tq_avg = ring_buffer_avg(neigh_node->tq_recv); + spin_unlock_bh(&neigh_node->tq_lock); + + if (!is_duplicate) { + orig_node->last_ttl = batman_ogm_packet->ttl; + neigh_node->last_ttl = batman_ogm_packet->ttl; + } + + bonding_candidate_add(orig_node, neigh_node); + + /* if this neighbor already is our next hop there is nothing + * to change */ + router = orig_node_get_router(orig_node); + if (router == neigh_node) + goto update_tt; + + /* if this neighbor does not offer a better TQ we won't consider it */ + if (router && (router->tq_avg > neigh_node->tq_avg)) + goto update_tt; + + /* if the TQ is the same and the link not more symmetric we + * won't consider it either */ + if (router && (neigh_node->tq_avg == router->tq_avg)) { + orig_node_tmp = router->orig_node; + spin_lock_bh(&orig_node_tmp->ogm_cnt_lock); + bcast_own_sum_orig = + orig_node_tmp->bcast_own_sum[if_incoming->if_num]; + spin_unlock_bh(&orig_node_tmp->ogm_cnt_lock); + + orig_node_tmp = neigh_node->orig_node; + spin_lock_bh(&orig_node_tmp->ogm_cnt_lock); + bcast_own_sum_neigh = + orig_node_tmp->bcast_own_sum[if_incoming->if_num]; + spin_unlock_bh(&orig_node_tmp->ogm_cnt_lock); + + if (bcast_own_sum_orig >= bcast_own_sum_neigh) + goto update_tt; + } + + update_route(bat_priv, orig_node, neigh_node); + +update_tt: + /* I have to check for transtable changes only if the OGM has been + * sent through a primary interface */ + if (((batman_ogm_packet->orig != ethhdr->h_source) && + (batman_ogm_packet->ttl > 2)) || + (batman_ogm_packet->flags & PRIMARIES_FIRST_HOP)) + tt_update_orig(bat_priv, orig_node, tt_buff, + batman_ogm_packet->tt_num_changes, + batman_ogm_packet->ttvn, + batman_ogm_packet->tt_crc); + + if (orig_node->gw_flags != batman_ogm_packet->gw_flags) + gw_node_update(bat_priv, orig_node, + batman_ogm_packet->gw_flags); + + orig_node->gw_flags = batman_ogm_packet->gw_flags; + + /* restart gateway selection if fast or late switching was enabled */ + if ((orig_node->gw_flags) && + (atomic_read(&bat_priv->gw_mode) == GW_MODE_CLIENT) && + (atomic_read(&bat_priv->gw_sel_class) > 2)) + gw_check_election(bat_priv, orig_node); + + goto out; + +unlock: + rcu_read_unlock(); +out: + if (neigh_node) + neigh_node_free_ref(neigh_node); + if (router) + neigh_node_free_ref(router); +} + +static int bat_ogm_calc_tq(struct orig_node *orig_node, + struct orig_node *orig_neigh_node, + struct batman_ogm_packet *batman_ogm_packet, + struct hard_iface *if_incoming) +{ + struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct neigh_node *neigh_node = NULL, *tmp_neigh_node; + struct hlist_node *node; + uint8_t total_count; + uint8_t orig_eq_count, neigh_rq_count, tq_own; + int tq_asym_penalty, ret = 0; + + /* find corresponding one hop neighbor */ + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp_neigh_node, node, + &orig_neigh_node->neigh_list, list) { + + if (!compare_eth(tmp_neigh_node->addr, orig_neigh_node->orig)) + continue; + + if (tmp_neigh_node->if_incoming != if_incoming) + continue; + + if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) + continue; + + neigh_node = tmp_neigh_node; + break; + } + rcu_read_unlock(); + + if (!neigh_node) + neigh_node = create_neighbor(orig_neigh_node, + orig_neigh_node, + orig_neigh_node->orig, + if_incoming); + + if (!neigh_node) + goto out; + + /* if orig_node is direct neighbor update neigh_node last_valid */ + if (orig_node == orig_neigh_node) + neigh_node->last_valid = jiffies; + + orig_node->last_valid = jiffies; + + /* find packet count of corresponding one hop neighbor */ + spin_lock_bh(&orig_node->ogm_cnt_lock); + orig_eq_count = orig_neigh_node->bcast_own_sum[if_incoming->if_num]; + neigh_rq_count = neigh_node->real_packet_count; + spin_unlock_bh(&orig_node->ogm_cnt_lock); + + /* pay attention to not get a value bigger than 100 % */ + total_count = (orig_eq_count > neigh_rq_count ? + neigh_rq_count : orig_eq_count); + + /* if we have too few packets (too less data) we set tq_own to zero */ + /* if we receive too few packets it is not considered bidirectional */ + if ((total_count < TQ_LOCAL_BIDRECT_SEND_MINIMUM) || + (neigh_rq_count < TQ_LOCAL_BIDRECT_RECV_MINIMUM)) + tq_own = 0; + else + /* neigh_node->real_packet_count is never zero as we + * only purge old information when getting new + * information */ + tq_own = (TQ_MAX_VALUE * total_count) / neigh_rq_count; + + /* + * 1 - ((1-x) ** 3), normalized to TQ_MAX_VALUE this does + * affect the nearly-symmetric links only a little, but + * punishes asymmetric links more. This will give a value + * between 0 and TQ_MAX_VALUE + */ + tq_asym_penalty = TQ_MAX_VALUE - (TQ_MAX_VALUE * + (TQ_LOCAL_WINDOW_SIZE - neigh_rq_count) * + (TQ_LOCAL_WINDOW_SIZE - neigh_rq_count) * + (TQ_LOCAL_WINDOW_SIZE - neigh_rq_count)) / + (TQ_LOCAL_WINDOW_SIZE * + TQ_LOCAL_WINDOW_SIZE * + TQ_LOCAL_WINDOW_SIZE); + + batman_ogm_packet->tq = ((batman_ogm_packet->tq * tq_own + * tq_asym_penalty) / + (TQ_MAX_VALUE * TQ_MAX_VALUE)); + + bat_dbg(DBG_BATMAN, bat_priv, + "bidirectional: " + "orig = %-15pM neigh = %-15pM => own_bcast = %2i, " + "real recv = %2i, local tq: %3i, asym_penalty: %3i, " + "total tq: %3i\n", + orig_node->orig, orig_neigh_node->orig, total_count, + neigh_rq_count, tq_own, tq_asym_penalty, batman_ogm_packet->tq); + + /* if link has the minimum required transmission quality + * consider it bidirectional */ + if (batman_ogm_packet->tq >= TQ_TOTAL_BIDRECT_LIMIT) + ret = 1; + +out: + if (neigh_node) + neigh_node_free_ref(neigh_node); + return ret; +} + +/* processes a batman packet for all interfaces, adjusts the sequence number and + * finds out whether it is a duplicate. + * returns: + * 1 the packet is a duplicate + * 0 the packet has not yet been received + * -1 the packet is old and has been received while the seqno window + * was protected. Caller should drop it. + */ +static int bat_ogm_update_seqnos(const struct ethhdr *ethhdr, + const struct batman_ogm_packet + *batman_ogm_packet, + const struct hard_iface *if_incoming) +{ + struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct orig_node *orig_node; + struct neigh_node *tmp_neigh_node; + struct hlist_node *node; + int is_duplicate = 0; + int32_t seq_diff; + int need_update = 0; + int set_mark, ret = -1; + + orig_node = get_orig_node(bat_priv, batman_ogm_packet->orig); + if (!orig_node) + return 0; + + spin_lock_bh(&orig_node->ogm_cnt_lock); + seq_diff = batman_ogm_packet->seqno - orig_node->last_real_seqno; + + /* signalize caller that the packet is to be dropped. */ + if (window_protected(bat_priv, seq_diff, + &orig_node->batman_seqno_reset)) + goto out; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp_neigh_node, node, + &orig_node->neigh_list, list) { + + is_duplicate |= get_bit_status(tmp_neigh_node->real_bits, + orig_node->last_real_seqno, + batman_ogm_packet->seqno); + + if (compare_eth(tmp_neigh_node->addr, ethhdr->h_source) && + (tmp_neigh_node->if_incoming == if_incoming)) + set_mark = 1; + else + set_mark = 0; + + /* if the window moved, set the update flag. */ + need_update |= bit_get_packet(bat_priv, + tmp_neigh_node->real_bits, + seq_diff, set_mark); + + tmp_neigh_node->real_packet_count = + bit_packet_count(tmp_neigh_node->real_bits); + } + rcu_read_unlock(); + + if (need_update) { + bat_dbg(DBG_BATMAN, bat_priv, + "updating last_seqno: old %d, new %d\n", + orig_node->last_real_seqno, batman_ogm_packet->seqno); + orig_node->last_real_seqno = batman_ogm_packet->seqno; + } + + ret = is_duplicate; + +out: + spin_unlock_bh(&orig_node->ogm_cnt_lock); + orig_node_free_ref(orig_node); + return ret; +} + +static void bat_ogm_process(const struct ethhdr *ethhdr, + struct batman_ogm_packet *batman_ogm_packet, + const unsigned char *tt_buff, + struct hard_iface *if_incoming) +{ + struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct hard_iface *hard_iface; + struct orig_node *orig_neigh_node, *orig_node; + struct neigh_node *router = NULL, *router_router = NULL; + struct neigh_node *orig_neigh_router = NULL; + int has_directlink_flag; + int is_my_addr = 0, is_my_orig = 0, is_my_oldorig = 0; + int is_broadcast = 0, is_bidirectional, is_single_hop_neigh; + int is_duplicate; + uint32_t if_incoming_seqno; + + /* Silently drop when the batman packet is actually not a + * correct packet. + * + * This might happen if a packet is padded (e.g. Ethernet has a + * minimum frame length of 64 byte) and the aggregation interprets + * it as an additional length. + * + * TODO: A more sane solution would be to have a bit in the + * batman_ogm_packet to detect whether the packet is the last + * packet in an aggregation. Here we expect that the padding + * is always zero (or not 0x01) + */ + if (batman_ogm_packet->packet_type != BAT_OGM) + return; + + /* could be changed by schedule_own_packet() */ + if_incoming_seqno = atomic_read(&if_incoming->seqno); + + has_directlink_flag = (batman_ogm_packet->flags & DIRECTLINK ? 1 : 0); + + is_single_hop_neigh = (compare_eth(ethhdr->h_source, + batman_ogm_packet->orig) ? 1 : 0); + + bat_dbg(DBG_BATMAN, bat_priv, + "Received BATMAN packet via NB: %pM, IF: %s [%pM] " + "(from OG: %pM, via prev OG: %pM, seqno %d, ttvn %u, " + "crc %u, changes %u, td %d, TTL %d, V %d, IDF %d)\n", + ethhdr->h_source, if_incoming->net_dev->name, + if_incoming->net_dev->dev_addr, batman_ogm_packet->orig, + batman_ogm_packet->prev_sender, batman_ogm_packet->seqno, + batman_ogm_packet->ttvn, batman_ogm_packet->tt_crc, + batman_ogm_packet->tt_num_changes, batman_ogm_packet->tq, + batman_ogm_packet->ttl, batman_ogm_packet->version, + has_directlink_flag); + + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &hardif_list, list) { + if (hard_iface->if_status != IF_ACTIVE) + continue; + + if (hard_iface->soft_iface != if_incoming->soft_iface) + continue; + + if (compare_eth(ethhdr->h_source, + hard_iface->net_dev->dev_addr)) + is_my_addr = 1; + + if (compare_eth(batman_ogm_packet->orig, + hard_iface->net_dev->dev_addr)) + is_my_orig = 1; + + if (compare_eth(batman_ogm_packet->prev_sender, + hard_iface->net_dev->dev_addr)) + is_my_oldorig = 1; + + if (is_broadcast_ether_addr(ethhdr->h_source)) + is_broadcast = 1; + } + rcu_read_unlock(); + + if (batman_ogm_packet->version != COMPAT_VERSION) { + bat_dbg(DBG_BATMAN, bat_priv, + "Drop packet: incompatible batman version (%i)\n", + batman_ogm_packet->version); + return; + } + + if (is_my_addr) { + bat_dbg(DBG_BATMAN, bat_priv, + "Drop packet: received my own broadcast (sender: %pM" + ")\n", + ethhdr->h_source); + return; + } + + if (is_broadcast) { + bat_dbg(DBG_BATMAN, bat_priv, "Drop packet: " + "ignoring all packets with broadcast source addr (sender: %pM" + ")\n", ethhdr->h_source); + return; + } + + if (is_my_orig) { + unsigned long *word; + int offset; + + orig_neigh_node = get_orig_node(bat_priv, ethhdr->h_source); + if (!orig_neigh_node) + return; + + /* neighbor has to indicate direct link and it has to + * come via the corresponding interface */ + /* save packet seqno for bidirectional check */ + if (has_directlink_flag && + compare_eth(if_incoming->net_dev->dev_addr, + batman_ogm_packet->orig)) { + offset = if_incoming->if_num * NUM_WORDS; + + spin_lock_bh(&orig_neigh_node->ogm_cnt_lock); + word = &(orig_neigh_node->bcast_own[offset]); + bit_mark(word, + if_incoming_seqno - + batman_ogm_packet->seqno - 2); + orig_neigh_node->bcast_own_sum[if_incoming->if_num] = + bit_packet_count(word); + spin_unlock_bh(&orig_neigh_node->ogm_cnt_lock); + } + + bat_dbg(DBG_BATMAN, bat_priv, "Drop packet: " + "originator packet from myself (via neighbor)\n"); + orig_node_free_ref(orig_neigh_node); + return; + } + + if (is_my_oldorig) { + bat_dbg(DBG_BATMAN, bat_priv, + "Drop packet: ignoring all rebroadcast echos (sender: " + "%pM)\n", ethhdr->h_source); + return; + } + + orig_node = get_orig_node(bat_priv, batman_ogm_packet->orig); + if (!orig_node) + return; + + is_duplicate = bat_ogm_update_seqnos(ethhdr, batman_ogm_packet, + if_incoming); + + if (is_duplicate == -1) { + bat_dbg(DBG_BATMAN, bat_priv, + "Drop packet: packet within seqno protection time " + "(sender: %pM)\n", ethhdr->h_source); + goto out; + } + + if (batman_ogm_packet->tq == 0) { + bat_dbg(DBG_BATMAN, bat_priv, + "Drop packet: originator packet with tq equal 0\n"); + goto out; + } + + router = orig_node_get_router(orig_node); + if (router) + router_router = orig_node_get_router(router->orig_node); + + /* avoid temporary routing loops */ + if (router && router_router && + (compare_eth(router->addr, batman_ogm_packet->prev_sender)) && + !(compare_eth(batman_ogm_packet->orig, + batman_ogm_packet->prev_sender)) && + (compare_eth(router->addr, router_router->addr))) { + bat_dbg(DBG_BATMAN, bat_priv, + "Drop packet: ignoring all rebroadcast packets that " + "may make me loop (sender: %pM)\n", ethhdr->h_source); + goto out; + } + + /* if sender is a direct neighbor the sender mac equals + * originator mac */ + orig_neigh_node = (is_single_hop_neigh ? + orig_node : + get_orig_node(bat_priv, ethhdr->h_source)); + if (!orig_neigh_node) + goto out; + + orig_neigh_router = orig_node_get_router(orig_neigh_node); + + /* drop packet if sender is not a direct neighbor and if we + * don't route towards it */ + if (!is_single_hop_neigh && (!orig_neigh_router)) { + bat_dbg(DBG_BATMAN, bat_priv, + "Drop packet: OGM via unknown neighbor!\n"); + goto out_neigh; + } + + is_bidirectional = bat_ogm_calc_tq(orig_node, orig_neigh_node, + batman_ogm_packet, if_incoming); + + bonding_save_primary(orig_node, orig_neigh_node, batman_ogm_packet); + + /* update ranking if it is not a duplicate or has the same + * seqno and similar ttl as the non-duplicate */ + if (is_bidirectional && + (!is_duplicate || + ((orig_node->last_real_seqno == batman_ogm_packet->seqno) && + (orig_node->last_ttl - 3 <= batman_ogm_packet->ttl)))) + bat_ogm_orig_update(bat_priv, orig_node, ethhdr, + batman_ogm_packet, if_incoming, + tt_buff, is_duplicate); + + /* is single hop (direct) neighbor */ + if (is_single_hop_neigh) { + + /* mark direct link on incoming interface */ + bat_ogm_forward(orig_node, ethhdr, batman_ogm_packet, + 1, if_incoming); + + bat_dbg(DBG_BATMAN, bat_priv, "Forwarding packet: " + "rebroadcast neighbor packet with direct link flag\n"); + goto out_neigh; + } + + /* multihop originator */ + if (!is_bidirectional) { + bat_dbg(DBG_BATMAN, bat_priv, + "Drop packet: not received via bidirectional link\n"); + goto out_neigh; + } + + if (is_duplicate) { + bat_dbg(DBG_BATMAN, bat_priv, + "Drop packet: duplicate packet received\n"); + goto out_neigh; + } + + bat_dbg(DBG_BATMAN, bat_priv, + "Forwarding packet: rebroadcast originator packet\n"); + bat_ogm_forward(orig_node, ethhdr, batman_ogm_packet, 0, if_incoming); + +out_neigh: + if ((orig_neigh_node) && (!is_single_hop_neigh)) + orig_node_free_ref(orig_neigh_node); +out: + if (router) + neigh_node_free_ref(router); + if (router_router) + neigh_node_free_ref(router_router); + if (orig_neigh_router) + neigh_node_free_ref(orig_neigh_router); + + orig_node_free_ref(orig_node); +} + +void bat_ogm_receive(const struct ethhdr *ethhdr, unsigned char *packet_buff, + int packet_len, struct hard_iface *if_incoming) +{ + struct batman_ogm_packet *batman_ogm_packet; + int buff_pos = 0; + unsigned char *tt_buff; + + batman_ogm_packet = (struct batman_ogm_packet *)packet_buff; + + /* unpack the aggregated packets and process them one by one */ + do { + /* network to host order for our 32bit seqno and the + orig_interval */ + batman_ogm_packet->seqno = ntohl(batman_ogm_packet->seqno); + batman_ogm_packet->tt_crc = ntohs(batman_ogm_packet->tt_crc); + + tt_buff = packet_buff + buff_pos + BATMAN_OGM_LEN; + + bat_ogm_process(ethhdr, batman_ogm_packet, + tt_buff, if_incoming); + + buff_pos += BATMAN_OGM_LEN + + tt_len(batman_ogm_packet->tt_num_changes); + + batman_ogm_packet = (struct batman_ogm_packet *) + (packet_buff + buff_pos); + } while (bat_ogm_aggr_packet(buff_pos, packet_len, + batman_ogm_packet->tt_num_changes)); +} diff --git a/net/batman-adv/bat_ogm.h b/net/batman-adv/bat_ogm.h new file mode 100644 index 0000000..69329c1 --- /dev/null +++ b/net/batman-adv/bat_ogm.h @@ -0,0 +1,35 @@ +/* + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * + * Marek Lindner, Simon Wunderlich + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA + * + */ + +#ifndef _NET_BATMAN_ADV_OGM_H_ +#define _NET_BATMAN_ADV_OGM_H_ + +#include "main.h" + +void bat_ogm_init(struct hard_iface *hard_iface); +void bat_ogm_init_primary(struct hard_iface *hard_iface); +void bat_ogm_update_mac(struct hard_iface *hard_iface); +void bat_ogm_schedule(struct hard_iface *hard_iface, int tt_num_changes); +void bat_ogm_emit(struct forw_packet *forw_packet); +void bat_ogm_receive(const struct ethhdr *ethhdr, unsigned char *packet_buff, + int packet_len, struct hard_iface *if_incoming); + +#endif /* _NET_BATMAN_ADV_OGM_H_ */ diff --git a/net/batman-adv/bat_sysfs.c b/net/batman-adv/bat_sysfs.c index cd15deb..b8a7414 100644 --- a/net/batman-adv/bat_sysfs.c +++ b/net/batman-adv/bat_sysfs.c @@ -380,6 +380,7 @@ static ssize_t store_gw_bwidth(struct kobject *kobj, struct attribute *attr, BAT_ATTR_BOOL(aggregated_ogms, S_IRUGO | S_IWUSR, NULL); BAT_ATTR_BOOL(bonding, S_IRUGO | S_IWUSR, NULL); BAT_ATTR_BOOL(fragmentation, S_IRUGO | S_IWUSR, update_min_mtu); +BAT_ATTR_BOOL(ap_isolation, S_IRUGO | S_IWUSR, NULL); static BAT_ATTR(vis_mode, S_IRUGO | S_IWUSR, show_vis_mode, store_vis_mode); static BAT_ATTR(gw_mode, S_IRUGO | S_IWUSR, show_gw_mode, store_gw_mode); BAT_ATTR_UINT(orig_interval, S_IRUGO | S_IWUSR, 2 * JITTER, INT_MAX, NULL); @@ -396,6 +397,7 @@ static struct bat_attribute *mesh_attrs[] = { &bat_attr_aggregated_ogms, &bat_attr_bonding, &bat_attr_fragmentation, + &bat_attr_ap_isolation, &bat_attr_vis_mode, &bat_attr_gw_mode, &bat_attr_orig_interval, diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index c1f4bfc..0be9ff3 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -97,12 +97,12 @@ static void bit_shift(unsigned long *seq_bits, int32_t n) (seq_bits[i - word_num - 1] >> (WORD_BIT_SIZE-word_offset)); /* and the upper part of the right half and shift it left to - * it's position */ + * its position */ /* for our example that would be: word[0] = 9800 + 0076 = * 9876 */ } - /* now for our last word, i==word_num, we only have the it's "left" - * half. that's the 1000 word in our example.*/ + /* now for our last word, i==word_num, we only have its "left" half. + * that's the 1000 word in our example.*/ seq_bits[i] = (seq_bits[i - word_num] << word_offset); diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 056180e..619fb73 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -532,14 +532,14 @@ static bool is_type_dhcprequest(struct sk_buff *skb, int header_len) pkt_len -= header_len + DHCP_OPTIONS_OFFSET + 1; /* Access the dhcp option lists. Each entry is made up by: - * - octect 1: option type - * - octect 2: option data len (only if type != 255 and 0) - * - octect 3: option data */ + * - octet 1: option type + * - octet 2: option data len (only if type != 255 and 0) + * - octet 3: option data */ while (*p != 255 && !ret) { - /* p now points to the first octect: option type */ + /* p now points to the first octet: option type */ if (*p == 53) { /* type 53 is the message type option. - * Jump the len octect and go to the data octect */ + * Jump the len octet and go to the data octet */ if (pkt_len < 2) goto out; p += 2; diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index db7aacf..7704df4 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -28,6 +28,7 @@ #include "bat_sysfs.h" #include "originator.h" #include "hash.h" +#include "bat_ogm.h" #include <linux/if_arp.h> @@ -131,7 +132,6 @@ static void primary_if_select(struct bat_priv *bat_priv, struct hard_iface *new_hard_iface) { struct hard_iface *curr_hard_iface; - struct batman_packet *batman_packet; ASSERT_RTNL(); @@ -147,10 +147,7 @@ static void primary_if_select(struct bat_priv *bat_priv, if (!new_hard_iface) return; - batman_packet = (struct batman_packet *)(new_hard_iface->packet_buff); - batman_packet->flags = PRIMARIES_FIRST_HOP; - batman_packet->ttl = TTL; - + bat_ogm_init_primary(new_hard_iface); primary_if_update_addr(bat_priv); } @@ -162,14 +159,6 @@ static bool hardif_is_iface_up(const struct hard_iface *hard_iface) return false; } -static void update_mac_addresses(struct hard_iface *hard_iface) -{ - memcpy(((struct batman_packet *)(hard_iface->packet_buff))->orig, - hard_iface->net_dev->dev_addr, ETH_ALEN); - memcpy(((struct batman_packet *)(hard_iface->packet_buff))->prev_sender, - hard_iface->net_dev->dev_addr, ETH_ALEN); -} - static void check_known_mac_addr(const struct net_device *net_dev) { const struct hard_iface *hard_iface; @@ -244,12 +233,12 @@ static void hardif_activate_interface(struct hard_iface *hard_iface) bat_priv = netdev_priv(hard_iface->soft_iface); - update_mac_addresses(hard_iface); + bat_ogm_update_mac(hard_iface); hard_iface->if_status = IF_TO_BE_ACTIVATED; /** * the first active interface becomes our primary interface or - * the next active interface after the old primay interface was removed + * the next active interface after the old primary interface was removed */ primary_if = primary_if_get_selected(bat_priv); if (!primary_if) @@ -283,7 +272,6 @@ int hardif_enable_interface(struct hard_iface *hard_iface, const char *iface_name) { struct bat_priv *bat_priv; - struct batman_packet *batman_packet; struct net_device *soft_iface; int ret; @@ -318,8 +306,8 @@ int hardif_enable_interface(struct hard_iface *hard_iface, hard_iface->soft_iface = soft_iface; bat_priv = netdev_priv(hard_iface->soft_iface); - hard_iface->packet_len = BAT_PACKET_LEN; - hard_iface->packet_buff = kmalloc(hard_iface->packet_len, GFP_ATOMIC); + + bat_ogm_init(hard_iface); if (!hard_iface->packet_buff) { bat_err(hard_iface->soft_iface, "Can't add interface packet " @@ -328,15 +316,6 @@ int hardif_enable_interface(struct hard_iface *hard_iface, goto err; } - batman_packet = (struct batman_packet *)(hard_iface->packet_buff); - batman_packet->packet_type = BAT_PACKET; - batman_packet->version = COMPAT_VERSION; - batman_packet->flags = NO_FLAGS; - batman_packet->ttl = 2; - batman_packet->tq = TQ_MAX_VALUE; - batman_packet->tt_num_changes = 0; - batman_packet->ttvn = 0; - hard_iface->if_num = bat_priv->num_ifaces; bat_priv->num_ifaces++; hard_iface->if_status = IF_INACTIVE; @@ -381,7 +360,7 @@ int hardif_enable_interface(struct hard_iface *hard_iface, hard_iface->net_dev->name); /* begin scheduling originator messages on that interface */ - schedule_own_packet(hard_iface); + schedule_bat_ogm(hard_iface); out: return 0; @@ -455,11 +434,8 @@ static struct hard_iface *hardif_add_interface(struct net_device *net_dev) dev_hold(net_dev); hard_iface = kmalloc(sizeof(*hard_iface), GFP_ATOMIC); - if (!hard_iface) { - pr_err("Can't add interface (%s): out of memory\n", - net_dev->name); + if (!hard_iface) goto release_dev; - } ret = sysfs_add_hardif(&hard_iface->hardif_obj, net_dev); if (ret) @@ -551,7 +527,7 @@ static int hard_if_event(struct notifier_block *this, goto hardif_put; check_known_mac_addr(hard_iface->net_dev); - update_mac_addresses(hard_iface); + bat_ogm_update_mac(hard_iface); bat_priv = netdev_priv(hard_iface->soft_iface); primary_if = primary_if_get_selected(bat_priv); @@ -573,14 +549,14 @@ out: return NOTIFY_DONE; } -/* receive a packet with the batman ethertype coming on a hard +/* incoming packets with the batman ethertype received on any active hard * interface */ static int batman_skb_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev) { struct bat_priv *bat_priv; - struct batman_packet *batman_packet; + struct batman_ogm_packet *batman_ogm_packet; struct hard_iface *hard_iface; int ret; @@ -612,22 +588,22 @@ static int batman_skb_recv(struct sk_buff *skb, struct net_device *dev, if (hard_iface->if_status != IF_ACTIVE) goto err_free; - batman_packet = (struct batman_packet *)skb->data; + batman_ogm_packet = (struct batman_ogm_packet *)skb->data; - if (batman_packet->version != COMPAT_VERSION) { + if (batman_ogm_packet->version != COMPAT_VERSION) { bat_dbg(DBG_BATMAN, bat_priv, "Drop packet: incompatible batman version (%i)\n", - batman_packet->version); + batman_ogm_packet->version); goto err_free; } /* all receive handlers return whether they received or reused * the supplied skb. if not, we have to free the skb. */ - switch (batman_packet->packet_type) { + switch (batman_ogm_packet->packet_type) { /* batman originator packet */ - case BAT_PACKET: - ret = recv_bat_packet(skb, hard_iface); + case BAT_OGM: + ret = recv_bat_ogm_packet(skb, hard_iface); break; /* batman icmp packet */ @@ -681,6 +657,36 @@ err_out: return NET_RX_DROP; } +/* This function returns true if the interface represented by ifindex is a + * 802.11 wireless device */ +bool is_wifi_iface(int ifindex) +{ + struct net_device *net_device = NULL; + bool ret = false; + + if (ifindex == NULL_IFINDEX) + goto out; + + net_device = dev_get_by_index(&init_net, ifindex); + if (!net_device) + goto out; + +#ifdef CONFIG_WIRELESS_EXT + /* pre-cfg80211 drivers have to implement WEXT, so it is possible to + * check for wireless_handlers != NULL */ + if (net_device->wireless_handlers) + ret = true; + else +#endif + /* cfg80211 drivers have to set ieee80211_ptr */ + if (net_device->ieee80211_ptr) + ret = true; +out: + if (net_device) + dev_put(net_device); + return ret; +} + struct notifier_block hard_if_notifier = { .notifier_call = hard_if_event, }; diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 442eacb..67f78d1 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -42,6 +42,7 @@ void hardif_remove_interfaces(void); int hardif_min_mtu(struct net_device *soft_iface); void update_min_mtu(struct net_device *soft_iface); void hardif_free_rcu(struct rcu_head *rcu); +bool is_wifi_iface(int ifindex); static inline void hardif_free_ref(struct hard_iface *hard_iface) { diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index dd5c9fd..d20aa71 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -76,19 +76,30 @@ static inline void hash_delete(struct hashtable_t *hash, hash_destroy(hash); } -/* adds data to the hashtable. returns 0 on success, -1 on error */ +/** + * hash_add - adds data to the hashtable + * @hash: storage hash table + * @compare: callback to determine if 2 hash elements are identical + * @choose: callback calculating the hash index + * @data: data passed to the aforementioned callbacks as argument + * @data_node: to be added element + * + * Returns 0 on success, 1 if the element already is in the hash + * and -1 on error. + */ + static inline int hash_add(struct hashtable_t *hash, hashdata_compare_cb compare, hashdata_choose_cb choose, const void *data, struct hlist_node *data_node) { - int index; + int index, ret = -1; struct hlist_head *head; struct hlist_node *node; spinlock_t *list_lock; /* spinlock to protect write access */ if (!hash) - goto err; + goto out; index = choose(data, hash->size); head = &hash->table[index]; @@ -99,6 +110,7 @@ static inline int hash_add(struct hashtable_t *hash, if (!compare(node, data)) continue; + ret = 1; goto err_unlock; } rcu_read_unlock(); @@ -108,12 +120,13 @@ static inline int hash_add(struct hashtable_t *hash, hlist_add_head_rcu(data_node, head); spin_unlock_bh(list_lock); - return 0; + ret = 0; + goto out; err_unlock: rcu_read_unlock(); -err: - return -1; +out: + return ret; } /* removes data from hash, if found. returns pointer do data on success, so you diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index b0f9068..fb87bdc 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -107,7 +107,7 @@ int mesh_init(struct net_device *soft_iface) if (tt_init(bat_priv) < 1) goto err; - tt_local_add(soft_iface, soft_iface->dev_addr); + tt_local_add(soft_iface, soft_iface->dev_addr, NULL_IFINDEX); if (vis_init(bat_priv) < 1) goto err; @@ -117,8 +117,6 @@ int mesh_init(struct net_device *soft_iface) goto end; err: - pr_err("Unable to allocate memory for mesh information structures: " - "out of mem ?\n"); mesh_free(soft_iface); return -1; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index a6df61a..964ad4d 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -28,7 +28,7 @@ #define DRIVER_DEVICE "batman-adv" #ifndef SOURCE_VERSION -#define SOURCE_VERSION "2011.3.0" +#define SOURCE_VERSION "2011.4.0" #endif /* B.A.T.M.A.N. parameters */ @@ -44,7 +44,7 @@ #define PURGE_TIMEOUT 200 #define TT_LOCAL_TIMEOUT 3600 /* in seconds */ #define TT_CLIENT_ROAM_TIMEOUT 600 -/* sliding packet range of received originator messages in squence numbers +/* sliding packet range of received originator messages in sequence numbers * (should be a multiple of our word size) */ #define TQ_LOCAL_WINDOW_SIZE 64 #define TT_REQUEST_TIMEOUT 3 /* seconds we have to keep pending tt_req */ @@ -62,6 +62,8 @@ #define NO_FLAGS 0 +#define NULL_IFINDEX 0 /* dummy ifindex used to avoid iface checks */ + #define NUM_WORDS (TQ_LOCAL_WINDOW_SIZE / WORD_BIT_SIZE) #define LOG_BUF_LEN 8192 /* has to be a power of 2 */ @@ -133,7 +135,7 @@ enum dbg_level { #include <linux/mutex.h> /* mutex */ #include <linux/module.h> /* needed by all modules */ #include <linux/netdevice.h> /* netdevice */ -#include <linux/etherdevice.h> /* ethernet address classifaction */ +#include <linux/etherdevice.h> /* ethernet address classification */ #include <linux/if_ether.h> /* ethernet header */ #include <linux/poll.h> /* poll_table */ #include <linux/kthread.h> /* kernel threads */ diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index f3c3f62..0e5b772 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -252,7 +252,7 @@ struct orig_node *get_orig_node(struct bat_priv *bat_priv, const uint8_t *addr) hash_added = hash_add(bat_priv->orig_hash, compare_orig, choose_orig, orig_node, &orig_node->hash_entry); - if (hash_added < 0) + if (hash_added != 0) goto free_bcast_own_sum; return orig_node; @@ -336,8 +336,7 @@ static bool purge_orig_node(struct bat_priv *bat_priv, } else { if (purge_orig_neighbors(bat_priv, orig_node, &best_neigh_node)) { - update_routes(bat_priv, orig_node, - best_neigh_node); + update_route(bat_priv, orig_node, best_neigh_node); } } @@ -493,10 +492,8 @@ static int orig_node_add_if(struct orig_node *orig_node, int max_if_num) data_ptr = kmalloc(max_if_num * sizeof(unsigned long) * NUM_WORDS, GFP_ATOMIC); - if (!data_ptr) { - pr_err("Can't resize orig: out of memory\n"); + if (!data_ptr) return -1; - } memcpy(data_ptr, orig_node->bcast_own, (max_if_num - 1) * sizeof(unsigned long) * NUM_WORDS); @@ -504,10 +501,8 @@ static int orig_node_add_if(struct orig_node *orig_node, int max_if_num) orig_node->bcast_own = data_ptr; data_ptr = kmalloc(max_if_num * sizeof(uint8_t), GFP_ATOMIC); - if (!data_ptr) { - pr_err("Can't resize orig: out of memory\n"); + if (!data_ptr) return -1; - } memcpy(data_ptr, orig_node->bcast_own_sum, (max_if_num - 1) * sizeof(uint8_t)); @@ -562,10 +557,8 @@ static int orig_node_del_if(struct orig_node *orig_node, chunk_size = sizeof(unsigned long) * NUM_WORDS; data_ptr = kmalloc(max_if_num * chunk_size, GFP_ATOMIC); - if (!data_ptr) { - pr_err("Can't resize orig: out of memory\n"); + if (!data_ptr) return -1; - } /* copy first part */ memcpy(data_ptr, orig_node->bcast_own, del_if_num * chunk_size); @@ -583,10 +576,8 @@ free_bcast_own: goto free_own_sum; data_ptr = kmalloc(max_if_num * sizeof(uint8_t), GFP_ATOMIC); - if (!data_ptr) { - pr_err("Can't resize orig: out of memory\n"); + if (!data_ptr) return -1; - } memcpy(data_ptr, orig_node->bcast_own_sum, del_if_num * sizeof(uint8_t)); diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index b76b4be..4d9e54c 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -25,14 +25,14 @@ #define ETH_P_BATMAN 0x4305 /* unofficial/not registered Ethertype */ enum bat_packettype { - BAT_PACKET = 0x01, - BAT_ICMP = 0x02, - BAT_UNICAST = 0x03, - BAT_BCAST = 0x04, - BAT_VIS = 0x05, + BAT_OGM = 0x01, + BAT_ICMP = 0x02, + BAT_UNICAST = 0x03, + BAT_BCAST = 0x04, + BAT_VIS = 0x05, BAT_UNICAST_FRAG = 0x06, - BAT_TT_QUERY = 0x07, - BAT_ROAM_ADV = 0x08 + BAT_TT_QUERY = 0x07, + BAT_ROAM_ADV = 0x08 }; /* this file is included by batctl which needs these defines */ @@ -84,12 +84,13 @@ enum tt_query_flags { enum tt_client_flags { TT_CLIENT_DEL = 1 << 0, TT_CLIENT_ROAM = 1 << 1, + TT_CLIENT_WIFI = 1 << 2, TT_CLIENT_NOPURGE = 1 << 8, TT_CLIENT_NEW = 1 << 9, TT_CLIENT_PENDING = 1 << 10 }; -struct batman_packet { +struct batman_ogm_packet { uint8_t packet_type; uint8_t version; /* batman version field */ uint8_t ttl; @@ -104,7 +105,7 @@ struct batman_packet { uint16_t tt_crc; } __packed; -#define BAT_PACKET_LEN sizeof(struct batman_packet) +#define BATMAN_OGM_LEN sizeof(struct batman_ogm_packet) struct icmp_packet { uint8_t packet_type; diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 0f32c81..f961cc5 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -22,18 +22,14 @@ #include "main.h" #include "routing.h" #include "send.h" -#include "hash.h" #include "soft-interface.h" #include "hard-interface.h" #include "icmp_socket.h" #include "translation-table.h" #include "originator.h" -#include "ring_buffer.h" #include "vis.h" -#include "aggregation.h" -#include "gateway_common.h" -#include "gateway_client.h" #include "unicast.h" +#include "bat_ogm.h" void slide_own_bcast_window(struct hard_iface *hard_iface) { @@ -64,69 +60,9 @@ void slide_own_bcast_window(struct hard_iface *hard_iface) } } -static void update_transtable(struct bat_priv *bat_priv, - struct orig_node *orig_node, - const unsigned char *tt_buff, - uint8_t tt_num_changes, uint8_t ttvn, - uint16_t tt_crc) -{ - uint8_t orig_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); - bool full_table = true; - - /* the ttvn increased by one -> we can apply the attached changes */ - if (ttvn - orig_ttvn == 1) { - /* the OGM could not contain the changes because they were too - * many to fit in one frame or because they have already been - * sent TT_OGM_APPEND_MAX times. In this case send a tt - * request */ - if (!tt_num_changes) { - full_table = false; - goto request_table; - } - - tt_update_changes(bat_priv, orig_node, tt_num_changes, ttvn, - (struct tt_change *)tt_buff); - - /* Even if we received the crc into the OGM, we prefer - * to recompute it to spot any possible inconsistency - * in the global table */ - orig_node->tt_crc = tt_global_crc(bat_priv, orig_node); - - /* The ttvn alone is not enough to guarantee consistency - * because a single value could repesent different states - * (due to the wrap around). Thus a node has to check whether - * the resulting table (after applying the changes) is still - * consistent or not. E.g. a node could disconnect while its - * ttvn is X and reconnect on ttvn = X + TTVN_MAX: in this case - * checking the CRC value is mandatory to detect the - * inconsistency */ - if (orig_node->tt_crc != tt_crc) - goto request_table; - - /* Roaming phase is over: tables are in sync again. I can - * unset the flag */ - orig_node->tt_poss_change = false; - } else { - /* if we missed more than one change or our tables are not - * in sync anymore -> request fresh tt data */ - if (ttvn != orig_ttvn || orig_node->tt_crc != tt_crc) { -request_table: - bat_dbg(DBG_TT, bat_priv, "TT inconsistency for %pM. " - "Need to retrieve the correct information " - "(ttvn: %u last_ttvn: %u crc: %u last_crc: " - "%u num_changes: %u)\n", orig_node->orig, ttvn, - orig_ttvn, tt_crc, orig_node->tt_crc, - tt_num_changes); - send_tt_request(bat_priv, orig_node, ttvn, tt_crc, - full_table); - return; - } - } -} - -static void update_route(struct bat_priv *bat_priv, - struct orig_node *orig_node, - struct neigh_node *neigh_node) +static void _update_route(struct bat_priv *bat_priv, + struct orig_node *orig_node, + struct neigh_node *neigh_node) { struct neigh_node *curr_router; @@ -170,8 +106,8 @@ static void update_route(struct bat_priv *bat_priv, neigh_node_free_ref(curr_router); } -void update_routes(struct bat_priv *bat_priv, struct orig_node *orig_node, - struct neigh_node *neigh_node) +void update_route(struct bat_priv *bat_priv, struct orig_node *orig_node, + struct neigh_node *neigh_node) { struct neigh_node *router = NULL; @@ -181,116 +117,13 @@ void update_routes(struct bat_priv *bat_priv, struct orig_node *orig_node, router = orig_node_get_router(orig_node); if (router != neigh_node) - update_route(bat_priv, orig_node, neigh_node); + _update_route(bat_priv, orig_node, neigh_node); out: if (router) neigh_node_free_ref(router); } -static int is_bidirectional_neigh(struct orig_node *orig_node, - struct orig_node *orig_neigh_node, - struct batman_packet *batman_packet, - struct hard_iface *if_incoming) -{ - struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct neigh_node *neigh_node = NULL, *tmp_neigh_node; - struct hlist_node *node; - uint8_t total_count; - uint8_t orig_eq_count, neigh_rq_count, tq_own; - int tq_asym_penalty, ret = 0; - - /* find corresponding one hop neighbor */ - rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_neigh_node, node, - &orig_neigh_node->neigh_list, list) { - - if (!compare_eth(tmp_neigh_node->addr, orig_neigh_node->orig)) - continue; - - if (tmp_neigh_node->if_incoming != if_incoming) - continue; - - if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) - continue; - - neigh_node = tmp_neigh_node; - break; - } - rcu_read_unlock(); - - if (!neigh_node) - neigh_node = create_neighbor(orig_neigh_node, - orig_neigh_node, - orig_neigh_node->orig, - if_incoming); - - if (!neigh_node) - goto out; - - /* if orig_node is direct neighbour update neigh_node last_valid */ - if (orig_node == orig_neigh_node) - neigh_node->last_valid = jiffies; - - orig_node->last_valid = jiffies; - - /* find packet count of corresponding one hop neighbor */ - spin_lock_bh(&orig_node->ogm_cnt_lock); - orig_eq_count = orig_neigh_node->bcast_own_sum[if_incoming->if_num]; - neigh_rq_count = neigh_node->real_packet_count; - spin_unlock_bh(&orig_node->ogm_cnt_lock); - - /* pay attention to not get a value bigger than 100 % */ - total_count = (orig_eq_count > neigh_rq_count ? - neigh_rq_count : orig_eq_count); - - /* if we have too few packets (too less data) we set tq_own to zero */ - /* if we receive too few packets it is not considered bidirectional */ - if ((total_count < TQ_LOCAL_BIDRECT_SEND_MINIMUM) || - (neigh_rq_count < TQ_LOCAL_BIDRECT_RECV_MINIMUM)) - tq_own = 0; - else - /* neigh_node->real_packet_count is never zero as we - * only purge old information when getting new - * information */ - tq_own = (TQ_MAX_VALUE * total_count) / neigh_rq_count; - - /* - * 1 - ((1-x) ** 3), normalized to TQ_MAX_VALUE this does - * affect the nearly-symmetric links only a little, but - * punishes asymmetric links more. This will give a value - * between 0 and TQ_MAX_VALUE - */ - tq_asym_penalty = TQ_MAX_VALUE - (TQ_MAX_VALUE * - (TQ_LOCAL_WINDOW_SIZE - neigh_rq_count) * - (TQ_LOCAL_WINDOW_SIZE - neigh_rq_count) * - (TQ_LOCAL_WINDOW_SIZE - neigh_rq_count)) / - (TQ_LOCAL_WINDOW_SIZE * - TQ_LOCAL_WINDOW_SIZE * - TQ_LOCAL_WINDOW_SIZE); - - batman_packet->tq = ((batman_packet->tq * tq_own * tq_asym_penalty) / - (TQ_MAX_VALUE * TQ_MAX_VALUE)); - - bat_dbg(DBG_BATMAN, bat_priv, - "bidirectional: " - "orig = %-15pM neigh = %-15pM => own_bcast = %2i, " - "real recv = %2i, local tq: %3i, asym_penalty: %3i, " - "total tq: %3i\n", - orig_node->orig, orig_neigh_node->orig, total_count, - neigh_rq_count, tq_own, tq_asym_penalty, batman_packet->tq); - - /* if link has the minimum required transmission quality - * consider it bidirectional */ - if (batman_packet->tq >= TQ_TOTAL_BIDRECT_LIMIT) - ret = 1; - -out: - if (neigh_node) - neigh_node_free_ref(neigh_node); - return ret; -} - /* caller must hold the neigh_list_lock */ void bonding_candidate_del(struct orig_node *orig_node, struct neigh_node *neigh_node) @@ -308,8 +141,8 @@ out: return; } -static void bonding_candidate_add(struct orig_node *orig_node, - struct neigh_node *neigh_node) +void bonding_candidate_add(struct orig_node *orig_node, + struct neigh_node *neigh_node) { struct hlist_node *node; struct neigh_node *tmp_neigh_node, *router = NULL; @@ -379,162 +212,23 @@ out: } /* copy primary address for bonding */ -static void bonding_save_primary(const struct orig_node *orig_node, - struct orig_node *orig_neigh_node, - const struct batman_packet *batman_packet) +void bonding_save_primary(const struct orig_node *orig_node, + struct orig_node *orig_neigh_node, + const struct batman_ogm_packet *batman_ogm_packet) { - if (!(batman_packet->flags & PRIMARIES_FIRST_HOP)) + if (!(batman_ogm_packet->flags & PRIMARIES_FIRST_HOP)) return; memcpy(orig_neigh_node->primary_addr, orig_node->orig, ETH_ALEN); } -static void update_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, - const struct ethhdr *ethhdr, - const struct batman_packet *batman_packet, - struct hard_iface *if_incoming, - const unsigned char *tt_buff, int is_duplicate) -{ - struct neigh_node *neigh_node = NULL, *tmp_neigh_node = NULL; - struct neigh_node *router = NULL; - struct orig_node *orig_node_tmp; - struct hlist_node *node; - uint8_t bcast_own_sum_orig, bcast_own_sum_neigh; - - bat_dbg(DBG_BATMAN, bat_priv, "update_originator(): " - "Searching and updating originator entry of received packet\n"); - - rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_neigh_node, node, - &orig_node->neigh_list, list) { - if (compare_eth(tmp_neigh_node->addr, ethhdr->h_source) && - (tmp_neigh_node->if_incoming == if_incoming) && - atomic_inc_not_zero(&tmp_neigh_node->refcount)) { - if (neigh_node) - neigh_node_free_ref(neigh_node); - neigh_node = tmp_neigh_node; - continue; - } - - if (is_duplicate) - continue; - - spin_lock_bh(&tmp_neigh_node->tq_lock); - ring_buffer_set(tmp_neigh_node->tq_recv, - &tmp_neigh_node->tq_index, 0); - tmp_neigh_node->tq_avg = - ring_buffer_avg(tmp_neigh_node->tq_recv); - spin_unlock_bh(&tmp_neigh_node->tq_lock); - } - - if (!neigh_node) { - struct orig_node *orig_tmp; - - orig_tmp = get_orig_node(bat_priv, ethhdr->h_source); - if (!orig_tmp) - goto unlock; - - neigh_node = create_neighbor(orig_node, orig_tmp, - ethhdr->h_source, if_incoming); - - orig_node_free_ref(orig_tmp); - if (!neigh_node) - goto unlock; - } else - bat_dbg(DBG_BATMAN, bat_priv, - "Updating existing last-hop neighbor of originator\n"); - - rcu_read_unlock(); - - orig_node->flags = batman_packet->flags; - neigh_node->last_valid = jiffies; - - spin_lock_bh(&neigh_node->tq_lock); - ring_buffer_set(neigh_node->tq_recv, - &neigh_node->tq_index, - batman_packet->tq); - neigh_node->tq_avg = ring_buffer_avg(neigh_node->tq_recv); - spin_unlock_bh(&neigh_node->tq_lock); - - if (!is_duplicate) { - orig_node->last_ttl = batman_packet->ttl; - neigh_node->last_ttl = batman_packet->ttl; - } - - bonding_candidate_add(orig_node, neigh_node); - - /* if this neighbor already is our next hop there is nothing - * to change */ - router = orig_node_get_router(orig_node); - if (router == neigh_node) - goto update_tt; - - /* if this neighbor does not offer a better TQ we won't consider it */ - if (router && (router->tq_avg > neigh_node->tq_avg)) - goto update_tt; - - /* if the TQ is the same and the link not more symetric we - * won't consider it either */ - if (router && (neigh_node->tq_avg == router->tq_avg)) { - orig_node_tmp = router->orig_node; - spin_lock_bh(&orig_node_tmp->ogm_cnt_lock); - bcast_own_sum_orig = - orig_node_tmp->bcast_own_sum[if_incoming->if_num]; - spin_unlock_bh(&orig_node_tmp->ogm_cnt_lock); - - orig_node_tmp = neigh_node->orig_node; - spin_lock_bh(&orig_node_tmp->ogm_cnt_lock); - bcast_own_sum_neigh = - orig_node_tmp->bcast_own_sum[if_incoming->if_num]; - spin_unlock_bh(&orig_node_tmp->ogm_cnt_lock); - - if (bcast_own_sum_orig >= bcast_own_sum_neigh) - goto update_tt; - } - - update_routes(bat_priv, orig_node, neigh_node); - -update_tt: - /* I have to check for transtable changes only if the OGM has been - * sent through a primary interface */ - if (((batman_packet->orig != ethhdr->h_source) && - (batman_packet->ttl > 2)) || - (batman_packet->flags & PRIMARIES_FIRST_HOP)) - update_transtable(bat_priv, orig_node, tt_buff, - batman_packet->tt_num_changes, - batman_packet->ttvn, - batman_packet->tt_crc); - - if (orig_node->gw_flags != batman_packet->gw_flags) - gw_node_update(bat_priv, orig_node, batman_packet->gw_flags); - - orig_node->gw_flags = batman_packet->gw_flags; - - /* restart gateway selection if fast or late switching was enabled */ - if ((orig_node->gw_flags) && - (atomic_read(&bat_priv->gw_mode) == GW_MODE_CLIENT) && - (atomic_read(&bat_priv->gw_sel_class) > 2)) - gw_check_election(bat_priv, orig_node); - - goto out; - -unlock: - rcu_read_unlock(); -out: - if (neigh_node) - neigh_node_free_ref(neigh_node); - if (router) - neigh_node_free_ref(router); -} - /* checks whether the host restarted and is in the protection time. * returns: * 0 if the packet is to be accepted * 1 if the packet is to be ignored. */ -static int window_protected(struct bat_priv *bat_priv, - int32_t seq_num_diff, - unsigned long *last_reset) +int window_protected(struct bat_priv *bat_priv, int32_t seq_num_diff, + unsigned long *last_reset) { if ((seq_num_diff <= -TQ_LOCAL_WINDOW_SIZE) || (seq_num_diff >= EXPECTED_SEQNO_RANGE)) { @@ -552,330 +246,12 @@ static int window_protected(struct bat_priv *bat_priv, return 0; } -/* processes a batman packet for all interfaces, adjusts the sequence number and - * finds out whether it is a duplicate. - * returns: - * 1 the packet is a duplicate - * 0 the packet has not yet been received - * -1 the packet is old and has been received while the seqno window - * was protected. Caller should drop it. - */ -static int count_real_packets(const struct ethhdr *ethhdr, - const struct batman_packet *batman_packet, - const struct hard_iface *if_incoming) -{ - struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct orig_node *orig_node; - struct neigh_node *tmp_neigh_node; - struct hlist_node *node; - int is_duplicate = 0; - int32_t seq_diff; - int need_update = 0; - int set_mark, ret = -1; - - orig_node = get_orig_node(bat_priv, batman_packet->orig); - if (!orig_node) - return 0; - - spin_lock_bh(&orig_node->ogm_cnt_lock); - seq_diff = batman_packet->seqno - orig_node->last_real_seqno; - - /* signalize caller that the packet is to be dropped. */ - if (window_protected(bat_priv, seq_diff, - &orig_node->batman_seqno_reset)) - goto out; - - rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_neigh_node, node, - &orig_node->neigh_list, list) { - - is_duplicate |= get_bit_status(tmp_neigh_node->real_bits, - orig_node->last_real_seqno, - batman_packet->seqno); - - if (compare_eth(tmp_neigh_node->addr, ethhdr->h_source) && - (tmp_neigh_node->if_incoming == if_incoming)) - set_mark = 1; - else - set_mark = 0; - - /* if the window moved, set the update flag. */ - need_update |= bit_get_packet(bat_priv, - tmp_neigh_node->real_bits, - seq_diff, set_mark); - - tmp_neigh_node->real_packet_count = - bit_packet_count(tmp_neigh_node->real_bits); - } - rcu_read_unlock(); - - if (need_update) { - bat_dbg(DBG_BATMAN, bat_priv, - "updating last_seqno: old %d, new %d\n", - orig_node->last_real_seqno, batman_packet->seqno); - orig_node->last_real_seqno = batman_packet->seqno; - } - - ret = is_duplicate; - -out: - spin_unlock_bh(&orig_node->ogm_cnt_lock); - orig_node_free_ref(orig_node); - return ret; -} - -void receive_bat_packet(const struct ethhdr *ethhdr, - struct batman_packet *batman_packet, - const unsigned char *tt_buff, - struct hard_iface *if_incoming) -{ - struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct hard_iface *hard_iface; - struct orig_node *orig_neigh_node, *orig_node; - struct neigh_node *router = NULL, *router_router = NULL; - struct neigh_node *orig_neigh_router = NULL; - int has_directlink_flag; - int is_my_addr = 0, is_my_orig = 0, is_my_oldorig = 0; - int is_broadcast = 0, is_bidirectional, is_single_hop_neigh; - int is_duplicate; - uint32_t if_incoming_seqno; - - /* Silently drop when the batman packet is actually not a - * correct packet. - * - * This might happen if a packet is padded (e.g. Ethernet has a - * minimum frame length of 64 byte) and the aggregation interprets - * it as an additional length. - * - * TODO: A more sane solution would be to have a bit in the - * batman_packet to detect whether the packet is the last - * packet in an aggregation. Here we expect that the padding - * is always zero (or not 0x01) - */ - if (batman_packet->packet_type != BAT_PACKET) - return; - - /* could be changed by schedule_own_packet() */ - if_incoming_seqno = atomic_read(&if_incoming->seqno); - - has_directlink_flag = (batman_packet->flags & DIRECTLINK ? 1 : 0); - - is_single_hop_neigh = (compare_eth(ethhdr->h_source, - batman_packet->orig) ? 1 : 0); - - bat_dbg(DBG_BATMAN, bat_priv, - "Received BATMAN packet via NB: %pM, IF: %s [%pM] " - "(from OG: %pM, via prev OG: %pM, seqno %d, ttvn %u, " - "crc %u, changes %u, td %d, TTL %d, V %d, IDF %d)\n", - ethhdr->h_source, if_incoming->net_dev->name, - if_incoming->net_dev->dev_addr, batman_packet->orig, - batman_packet->prev_sender, batman_packet->seqno, - batman_packet->ttvn, batman_packet->tt_crc, - batman_packet->tt_num_changes, batman_packet->tq, - batman_packet->ttl, batman_packet->version, - has_directlink_flag); - - rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &hardif_list, list) { - if (hard_iface->if_status != IF_ACTIVE) - continue; - - if (hard_iface->soft_iface != if_incoming->soft_iface) - continue; - - if (compare_eth(ethhdr->h_source, - hard_iface->net_dev->dev_addr)) - is_my_addr = 1; - - if (compare_eth(batman_packet->orig, - hard_iface->net_dev->dev_addr)) - is_my_orig = 1; - - if (compare_eth(batman_packet->prev_sender, - hard_iface->net_dev->dev_addr)) - is_my_oldorig = 1; - - if (is_broadcast_ether_addr(ethhdr->h_source)) - is_broadcast = 1; - } - rcu_read_unlock(); - - if (batman_packet->version != COMPAT_VERSION) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: incompatible batman version (%i)\n", - batman_packet->version); - return; - } - - if (is_my_addr) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: received my own broadcast (sender: %pM" - ")\n", - ethhdr->h_source); - return; - } - - if (is_broadcast) { - bat_dbg(DBG_BATMAN, bat_priv, "Drop packet: " - "ignoring all packets with broadcast source addr (sender: %pM" - ")\n", ethhdr->h_source); - return; - } - - if (is_my_orig) { - unsigned long *word; - int offset; - - orig_neigh_node = get_orig_node(bat_priv, ethhdr->h_source); - if (!orig_neigh_node) - return; - - /* neighbor has to indicate direct link and it has to - * come via the corresponding interface */ - /* save packet seqno for bidirectional check */ - if (has_directlink_flag && - compare_eth(if_incoming->net_dev->dev_addr, - batman_packet->orig)) { - offset = if_incoming->if_num * NUM_WORDS; - - spin_lock_bh(&orig_neigh_node->ogm_cnt_lock); - word = &(orig_neigh_node->bcast_own[offset]); - bit_mark(word, - if_incoming_seqno - batman_packet->seqno - 2); - orig_neigh_node->bcast_own_sum[if_incoming->if_num] = - bit_packet_count(word); - spin_unlock_bh(&orig_neigh_node->ogm_cnt_lock); - } - - bat_dbg(DBG_BATMAN, bat_priv, "Drop packet: " - "originator packet from myself (via neighbor)\n"); - orig_node_free_ref(orig_neigh_node); - return; - } - - if (is_my_oldorig) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: ignoring all rebroadcast echos (sender: " - "%pM)\n", ethhdr->h_source); - return; - } - - orig_node = get_orig_node(bat_priv, batman_packet->orig); - if (!orig_node) - return; - - is_duplicate = count_real_packets(ethhdr, batman_packet, if_incoming); - - if (is_duplicate == -1) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: packet within seqno protection time " - "(sender: %pM)\n", ethhdr->h_source); - goto out; - } - - if (batman_packet->tq == 0) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: originator packet with tq equal 0\n"); - goto out; - } - - router = orig_node_get_router(orig_node); - if (router) - router_router = orig_node_get_router(router->orig_node); - - /* avoid temporary routing loops */ - if (router && router_router && - (compare_eth(router->addr, batman_packet->prev_sender)) && - !(compare_eth(batman_packet->orig, batman_packet->prev_sender)) && - (compare_eth(router->addr, router_router->addr))) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: ignoring all rebroadcast packets that " - "may make me loop (sender: %pM)\n", ethhdr->h_source); - goto out; - } - - /* if sender is a direct neighbor the sender mac equals - * originator mac */ - orig_neigh_node = (is_single_hop_neigh ? - orig_node : - get_orig_node(bat_priv, ethhdr->h_source)); - if (!orig_neigh_node) - goto out; - - orig_neigh_router = orig_node_get_router(orig_neigh_node); - - /* drop packet if sender is not a direct neighbor and if we - * don't route towards it */ - if (!is_single_hop_neigh && (!orig_neigh_router)) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: OGM via unknown neighbor!\n"); - goto out_neigh; - } - - is_bidirectional = is_bidirectional_neigh(orig_node, orig_neigh_node, - batman_packet, if_incoming); - - bonding_save_primary(orig_node, orig_neigh_node, batman_packet); - - /* update ranking if it is not a duplicate or has the same - * seqno and similar ttl as the non-duplicate */ - if (is_bidirectional && - (!is_duplicate || - ((orig_node->last_real_seqno == batman_packet->seqno) && - (orig_node->last_ttl - 3 <= batman_packet->ttl)))) - update_orig(bat_priv, orig_node, ethhdr, batman_packet, - if_incoming, tt_buff, is_duplicate); - - /* is single hop (direct) neighbor */ - if (is_single_hop_neigh) { - - /* mark direct link on incoming interface */ - schedule_forward_packet(orig_node, ethhdr, batman_packet, - 1, if_incoming); - - bat_dbg(DBG_BATMAN, bat_priv, "Forwarding packet: " - "rebroadcast neighbor packet with direct link flag\n"); - goto out_neigh; - } - - /* multihop originator */ - if (!is_bidirectional) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: not received via bidirectional link\n"); - goto out_neigh; - } - - if (is_duplicate) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: duplicate packet received\n"); - goto out_neigh; - } - - bat_dbg(DBG_BATMAN, bat_priv, - "Forwarding packet: rebroadcast originator packet\n"); - schedule_forward_packet(orig_node, ethhdr, batman_packet, - 0, if_incoming); - -out_neigh: - if ((orig_neigh_node) && (!is_single_hop_neigh)) - orig_node_free_ref(orig_neigh_node); -out: - if (router) - neigh_node_free_ref(router); - if (router_router) - neigh_node_free_ref(router_router); - if (orig_neigh_router) - neigh_node_free_ref(orig_neigh_router); - - orig_node_free_ref(orig_node); -} - -int recv_bat_packet(struct sk_buff *skb, struct hard_iface *hard_iface) +int recv_bat_ogm_packet(struct sk_buff *skb, struct hard_iface *hard_iface) { struct ethhdr *ethhdr; /* drop packet if it has not necessary minimum size */ - if (unlikely(!pskb_may_pull(skb, sizeof(struct batman_packet)))) + if (unlikely(!pskb_may_pull(skb, BATMAN_OGM_LEN))) return NET_RX_DROP; ethhdr = (struct ethhdr *)skb_mac_header(skb); @@ -898,10 +274,7 @@ int recv_bat_packet(struct sk_buff *skb, struct hard_iface *hard_iface) ethhdr = (struct ethhdr *)skb_mac_header(skb); - receive_aggr_bat_packet(ethhdr, - skb->data, - skb_headlen(skb), - hard_iface); + bat_ogm_receive(ethhdr, skb->data, skb_headlen(skb), hard_iface); kfree_skb(skb); return NET_RX_SUCCESS; @@ -1243,7 +616,7 @@ int recv_tt_query(struct sk_buff *skb, struct hard_iface *recv_if) } break; case TT_RESPONSE: - /* packet needs to be linearised to access the TT changes */ + /* packet needs to be linearized to access the TT changes */ if (skb_linearize(skb) < 0) goto out; @@ -1300,7 +673,7 @@ int recv_roam_adv(struct sk_buff *skb, struct hard_iface *recv_if) roam_adv_packet->client); tt_global_add(bat_priv, orig_node, roam_adv_packet->client, - atomic_read(&orig_node->last_ttvn) + 1, true); + atomic_read(&orig_node->last_ttvn) + 1, true, false); /* Roaming phase starts: I have new information but the ttvn has not * been incremented yet. This flag will make me check all the incoming @@ -1536,7 +909,7 @@ static int check_unicast_ttvn(struct bat_priv *bat_priv, ethhdr = (struct ethhdr *)(skb->data + sizeof(struct unicast_packet)); - orig_node = transtable_search(bat_priv, ethhdr->h_dest); + orig_node = transtable_search(bat_priv, NULL, ethhdr->h_dest); if (!orig_node) { if (!is_my_client(bat_priv, ethhdr->h_dest)) diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index fb14e95..7aaee0f 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -23,19 +23,15 @@ #define _NET_BATMAN_ADV_ROUTING_H_ void slide_own_bcast_window(struct hard_iface *hard_iface); -void receive_bat_packet(const struct ethhdr *ethhdr, - struct batman_packet *batman_packet, - const unsigned char *tt_buff, - struct hard_iface *if_incoming); -void update_routes(struct bat_priv *bat_priv, struct orig_node *orig_node, - struct neigh_node *neigh_node); +void update_route(struct bat_priv *bat_priv, struct orig_node *orig_node, + struct neigh_node *neigh_node); int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_ucast_frag_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_bcast_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_vis_packet(struct sk_buff *skb, struct hard_iface *recv_if); -int recv_bat_packet(struct sk_buff *skb, struct hard_iface *recv_if); +int recv_bat_ogm_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_tt_query(struct sk_buff *skb, struct hard_iface *recv_if); int recv_roam_adv(struct sk_buff *skb, struct hard_iface *recv_if); struct neigh_node *find_router(struct bat_priv *bat_priv, @@ -43,5 +39,12 @@ struct neigh_node *find_router(struct bat_priv *bat_priv, const struct hard_iface *recv_if); void bonding_candidate_del(struct orig_node *orig_node, struct neigh_node *neigh_node); +void bonding_candidate_add(struct orig_node *orig_node, + struct neigh_node *neigh_node); +void bonding_save_primary(const struct orig_node *orig_node, + struct orig_node *orig_neigh_node, + const struct batman_ogm_packet *batman_ogm_packet); +int window_protected(struct bat_priv *bat_priv, int32_t seq_num_diff, + unsigned long *last_reset); #endif /* _NET_BATMAN_ADV_ROUTING_H_ */ diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 58d1447..8a684eb 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -26,33 +26,12 @@ #include "soft-interface.h" #include "hard-interface.h" #include "vis.h" -#include "aggregation.h" #include "gateway_common.h" #include "originator.h" +#include "bat_ogm.h" static void send_outstanding_bcast_packet(struct work_struct *work); -/* apply hop penalty for a normal link */ -static uint8_t hop_penalty(uint8_t tq, const struct bat_priv *bat_priv) -{ - int hop_penalty = atomic_read(&bat_priv->hop_penalty); - return (tq * (TQ_MAX_VALUE - hop_penalty)) / (TQ_MAX_VALUE); -} - -/* when do we schedule our own packet to be sent */ -static unsigned long own_send_time(const struct bat_priv *bat_priv) -{ - return jiffies + msecs_to_jiffies( - atomic_read(&bat_priv->orig_interval) - - JITTER + (random32() % 2*JITTER)); -} - -/* when do we schedule a forwarded packet to be sent */ -static unsigned long forward_send_time(void) -{ - return jiffies + msecs_to_jiffies(random32() % (JITTER/2)); -} - /* send out an already prepared packet to the given address via the * specified batman interface */ int send_skb_packet(struct sk_buff *skb, struct hard_iface *hard_iface, @@ -99,141 +78,17 @@ send_skb_err: return NET_XMIT_DROP; } -/* Send a packet to a given interface */ -static void send_packet_to_if(struct forw_packet *forw_packet, - struct hard_iface *hard_iface) -{ - struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - char *fwd_str; - uint8_t packet_num; - int16_t buff_pos; - struct batman_packet *batman_packet; - struct sk_buff *skb; - - if (hard_iface->if_status != IF_ACTIVE) - return; - - packet_num = 0; - buff_pos = 0; - batman_packet = (struct batman_packet *)forw_packet->skb->data; - - /* adjust all flags and log packets */ - while (aggregated_packet(buff_pos, - forw_packet->packet_len, - batman_packet->tt_num_changes)) { - - /* we might have aggregated direct link packets with an - * ordinary base packet */ - if ((forw_packet->direct_link_flags & (1 << packet_num)) && - (forw_packet->if_incoming == hard_iface)) - batman_packet->flags |= DIRECTLINK; - else - batman_packet->flags &= ~DIRECTLINK; - - fwd_str = (packet_num > 0 ? "Forwarding" : (forw_packet->own ? - "Sending own" : - "Forwarding")); - bat_dbg(DBG_BATMAN, bat_priv, - "%s %spacket (originator %pM, seqno %d, TQ %d, TTL %d," - " IDF %s, hvn %d) on interface %s [%pM]\n", - fwd_str, (packet_num > 0 ? "aggregated " : ""), - batman_packet->orig, ntohl(batman_packet->seqno), - batman_packet->tq, batman_packet->ttl, - (batman_packet->flags & DIRECTLINK ? - "on" : "off"), - batman_packet->ttvn, hard_iface->net_dev->name, - hard_iface->net_dev->dev_addr); - - buff_pos += sizeof(*batman_packet) + - tt_len(batman_packet->tt_num_changes); - packet_num++; - batman_packet = (struct batman_packet *) - (forw_packet->skb->data + buff_pos); - } - - /* create clone because function is called more than once */ - skb = skb_clone(forw_packet->skb, GFP_ATOMIC); - if (skb) - send_skb_packet(skb, hard_iface, broadcast_addr); -} - -/* send a batman packet */ -static void send_packet(struct forw_packet *forw_packet) -{ - struct hard_iface *hard_iface; - struct net_device *soft_iface; - struct bat_priv *bat_priv; - struct hard_iface *primary_if = NULL; - struct batman_packet *batman_packet = - (struct batman_packet *)(forw_packet->skb->data); - int directlink = (batman_packet->flags & DIRECTLINK ? 1 : 0); - - if (!forw_packet->if_incoming) { - pr_err("Error - can't forward packet: incoming iface not " - "specified\n"); - goto out; - } - - soft_iface = forw_packet->if_incoming->soft_iface; - bat_priv = netdev_priv(soft_iface); - - if (forw_packet->if_incoming->if_status != IF_ACTIVE) - goto out; - - primary_if = primary_if_get_selected(bat_priv); - if (!primary_if) - goto out; - - /* multihomed peer assumed */ - /* non-primary OGMs are only broadcasted on their interface */ - if ((directlink && (batman_packet->ttl == 1)) || - (forw_packet->own && (forw_packet->if_incoming != primary_if))) { - - /* FIXME: what about aggregated packets ? */ - bat_dbg(DBG_BATMAN, bat_priv, - "%s packet (originator %pM, seqno %d, TTL %d) " - "on interface %s [%pM]\n", - (forw_packet->own ? "Sending own" : "Forwarding"), - batman_packet->orig, ntohl(batman_packet->seqno), - batman_packet->ttl, - forw_packet->if_incoming->net_dev->name, - forw_packet->if_incoming->net_dev->dev_addr); - - /* skb is only used once and than forw_packet is free'd */ - send_skb_packet(forw_packet->skb, forw_packet->if_incoming, - broadcast_addr); - forw_packet->skb = NULL; - - goto out; - } - - /* broadcast on every interface */ - rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &hardif_list, list) { - if (hard_iface->soft_iface != soft_iface) - continue; - - send_packet_to_if(forw_packet, hard_iface); - } - rcu_read_unlock(); - -out: - if (primary_if) - hardif_free_ref(primary_if); -} - static void realloc_packet_buffer(struct hard_iface *hard_iface, - int new_len) + int new_len) { unsigned char *new_buff; - struct batman_packet *batman_packet; new_buff = kmalloc(new_len, GFP_ATOMIC); /* keep old buffer if kmalloc should fail */ if (new_buff) { memcpy(new_buff, hard_iface->packet_buff, - sizeof(*batman_packet)); + BATMAN_OGM_LEN); kfree(hard_iface->packet_buff); hard_iface->packet_buff = new_buff; @@ -242,60 +97,48 @@ static void realloc_packet_buffer(struct hard_iface *hard_iface, } /* when calling this function (hard_iface == primary_if) has to be true */ -static void prepare_packet_buffer(struct bat_priv *bat_priv, +static int prepare_packet_buffer(struct bat_priv *bat_priv, struct hard_iface *hard_iface) { int new_len; - struct batman_packet *batman_packet; - new_len = BAT_PACKET_LEN + + new_len = BATMAN_OGM_LEN + tt_len((uint8_t)atomic_read(&bat_priv->tt_local_changes)); /* if we have too many changes for one packet don't send any * and wait for the tt table request which will be fragmented */ if (new_len > hard_iface->soft_iface->mtu) - new_len = BAT_PACKET_LEN; + new_len = BATMAN_OGM_LEN; realloc_packet_buffer(hard_iface, new_len); - batman_packet = (struct batman_packet *)hard_iface->packet_buff; atomic_set(&bat_priv->tt_crc, tt_local_crc(bat_priv)); /* reset the sending counter */ atomic_set(&bat_priv->tt_ogm_append_cnt, TT_OGM_APPEND_MAX); - batman_packet->tt_num_changes = tt_changes_fill_buffer(bat_priv, - hard_iface->packet_buff + BAT_PACKET_LEN, - hard_iface->packet_len - BAT_PACKET_LEN); - + return tt_changes_fill_buffer(bat_priv, + hard_iface->packet_buff + BATMAN_OGM_LEN, + hard_iface->packet_len - BATMAN_OGM_LEN); } -static void reset_packet_buffer(struct bat_priv *bat_priv, - struct hard_iface *hard_iface) +static int reset_packet_buffer(struct bat_priv *bat_priv, + struct hard_iface *hard_iface) { - struct batman_packet *batman_packet; - - realloc_packet_buffer(hard_iface, BAT_PACKET_LEN); - - batman_packet = (struct batman_packet *)hard_iface->packet_buff; - batman_packet->tt_num_changes = 0; + realloc_packet_buffer(hard_iface, BATMAN_OGM_LEN); + return 0; } -void schedule_own_packet(struct hard_iface *hard_iface) +void schedule_bat_ogm(struct hard_iface *hard_iface) { struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct hard_iface *primary_if; - unsigned long send_time; - struct batman_packet *batman_packet; - int vis_server; + int tt_num_changes = -1; if ((hard_iface->if_status == IF_NOT_IN_USE) || (hard_iface->if_status == IF_TO_BE_REMOVED)) return; - vis_server = atomic_read(&bat_priv->vis_mode); - primary_if = primary_if_get_selected(bat_priv); - /** * the interface gets activated here to avoid race conditions between * the moment of activating the interface in @@ -306,124 +149,26 @@ void schedule_own_packet(struct hard_iface *hard_iface) if (hard_iface->if_status == IF_TO_BE_ACTIVATED) hard_iface->if_status = IF_ACTIVE; + primary_if = primary_if_get_selected(bat_priv); + if (hard_iface == primary_if) { /* if at least one change happened */ if (atomic_read(&bat_priv->tt_local_changes) > 0) { tt_commit_changes(bat_priv); - prepare_packet_buffer(bat_priv, hard_iface); + tt_num_changes = prepare_packet_buffer(bat_priv, + hard_iface); } - /* if the changes have been sent enough times */ + /* if the changes have been sent often enough */ if (!atomic_dec_not_zero(&bat_priv->tt_ogm_append_cnt)) - reset_packet_buffer(bat_priv, hard_iface); + tt_num_changes = reset_packet_buffer(bat_priv, + hard_iface); } - /** - * NOTE: packet_buff might just have been re-allocated in - * prepare_packet_buffer() or in reset_packet_buffer() - */ - batman_packet = (struct batman_packet *)hard_iface->packet_buff; - - /* change sequence number to network order */ - batman_packet->seqno = - htonl((uint32_t)atomic_read(&hard_iface->seqno)); - - batman_packet->ttvn = atomic_read(&bat_priv->ttvn); - batman_packet->tt_crc = htons((uint16_t)atomic_read(&bat_priv->tt_crc)); - - if (vis_server == VIS_TYPE_SERVER_SYNC) - batman_packet->flags |= VIS_SERVER; - else - batman_packet->flags &= ~VIS_SERVER; - - if ((hard_iface == primary_if) && - (atomic_read(&bat_priv->gw_mode) == GW_MODE_SERVER)) - batman_packet->gw_flags = - (uint8_t)atomic_read(&bat_priv->gw_bandwidth); - else - batman_packet->gw_flags = NO_FLAGS; - - atomic_inc(&hard_iface->seqno); - - slide_own_bcast_window(hard_iface); - send_time = own_send_time(bat_priv); - add_bat_packet_to_list(bat_priv, - hard_iface->packet_buff, - hard_iface->packet_len, - hard_iface, 1, send_time); - if (primary_if) hardif_free_ref(primary_if); -} - -void schedule_forward_packet(struct orig_node *orig_node, - const struct ethhdr *ethhdr, - struct batman_packet *batman_packet, - int directlink, - struct hard_iface *if_incoming) -{ - struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct neigh_node *router; - uint8_t in_tq, in_ttl, tq_avg = 0; - unsigned long send_time; - uint8_t tt_num_changes; - - if (batman_packet->ttl <= 1) { - bat_dbg(DBG_BATMAN, bat_priv, "ttl exceeded\n"); - return; - } - - router = orig_node_get_router(orig_node); - - in_tq = batman_packet->tq; - in_ttl = batman_packet->ttl; - tt_num_changes = batman_packet->tt_num_changes; - - batman_packet->ttl--; - memcpy(batman_packet->prev_sender, ethhdr->h_source, ETH_ALEN); - - /* rebroadcast tq of our best ranking neighbor to ensure the rebroadcast - * of our best tq value */ - if (router && router->tq_avg != 0) { - - /* rebroadcast ogm of best ranking neighbor as is */ - if (!compare_eth(router->addr, ethhdr->h_source)) { - batman_packet->tq = router->tq_avg; - - if (router->last_ttl) - batman_packet->ttl = router->last_ttl - 1; - } - - tq_avg = router->tq_avg; - } - - if (router) - neigh_node_free_ref(router); - - /* apply hop penalty */ - batman_packet->tq = hop_penalty(batman_packet->tq, bat_priv); - - bat_dbg(DBG_BATMAN, bat_priv, - "Forwarding packet: tq_orig: %i, tq_avg: %i, " - "tq_forw: %i, ttl_orig: %i, ttl_forw: %i\n", - in_tq, tq_avg, batman_packet->tq, in_ttl - 1, - batman_packet->ttl); - - batman_packet->seqno = htonl(batman_packet->seqno); - batman_packet->tt_crc = htons(batman_packet->tt_crc); - - /* switch of primaries first hop flag when forwarding */ - batman_packet->flags &= ~PRIMARIES_FIRST_HOP; - if (directlink) - batman_packet->flags |= DIRECTLINK; - else - batman_packet->flags &= ~DIRECTLINK; - send_time = forward_send_time(); - add_bat_packet_to_list(bat_priv, - (unsigned char *)batman_packet, - sizeof(*batman_packet) + tt_len(tt_num_changes), - if_incoming, 0, send_time); + bat_ogm_schedule(hard_iface, tt_num_changes); } static void forw_packet_free(struct forw_packet *forw_packet) @@ -454,7 +199,7 @@ static void _add_bcast_packet_to_list(struct bat_priv *bat_priv, } /* add a broadcast packet to the queue and setup timers. broadcast packets - * are sent multiple times to increase probability for beeing received. + * are sent multiple times to increase probability for being received. * * This function returns NETDEV_TX_OK on success and NETDEV_TX_BUSY on * errors. @@ -557,7 +302,7 @@ out: atomic_inc(&bat_priv->bcast_queue_left); } -void send_outstanding_bat_packet(struct work_struct *work) +void send_outstanding_bat_ogm_packet(struct work_struct *work) { struct delayed_work *delayed_work = container_of(work, struct delayed_work, work); @@ -573,7 +318,7 @@ void send_outstanding_bat_packet(struct work_struct *work) if (atomic_read(&bat_priv->mesh_state) == MESH_DEACTIVATING) goto out; - send_packet(forw_packet); + bat_ogm_emit(forw_packet); /** * we have to have at least one packet in the queue @@ -581,7 +326,7 @@ void send_outstanding_bat_packet(struct work_struct *work) * shutting down */ if (forw_packet->own) - schedule_own_packet(forw_packet->if_incoming); + schedule_bat_ogm(forw_packet->if_incoming); out: /* don't count own packet */ @@ -612,7 +357,7 @@ void purge_outstanding_packets(struct bat_priv *bat_priv, &bat_priv->forw_bcast_list, list) { /** - * if purge_outstanding_packets() was called with an argmument + * if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface */ if ((hard_iface) && @@ -641,7 +386,7 @@ void purge_outstanding_packets(struct bat_priv *bat_priv, &bat_priv->forw_bat_list, list) { /** - * if purge_outstanding_packets() was called with an argmument + * if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface */ if ((hard_iface) && diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 1f2d1e8..c8ca3ef 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -24,15 +24,10 @@ int send_skb_packet(struct sk_buff *skb, struct hard_iface *hard_iface, const uint8_t *dst_addr); -void schedule_own_packet(struct hard_iface *hard_iface); -void schedule_forward_packet(struct orig_node *orig_node, - const struct ethhdr *ethhdr, - struct batman_packet *batman_packet, - int directlink, - struct hard_iface *if_outgoing); +void schedule_bat_ogm(struct hard_iface *hard_iface); int add_bcast_packet_to_list(struct bat_priv *bat_priv, const struct sk_buff *skb, unsigned long delay); -void send_outstanding_bat_packet(struct work_struct *work); +void send_outstanding_bat_ogm_packet(struct work_struct *work); void purge_outstanding_packets(struct bat_priv *bat_priv, const struct hard_iface *hard_iface); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 05dd351..f9cc957 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -445,30 +445,31 @@ static void softif_batman_recv(struct sk_buff *skb, struct net_device *dev, { struct bat_priv *bat_priv = netdev_priv(dev); struct ethhdr *ethhdr = (struct ethhdr *)skb->data; - struct batman_packet *batman_packet; + struct batman_ogm_packet *batman_ogm_packet; struct softif_neigh *softif_neigh = NULL; struct hard_iface *primary_if = NULL; struct softif_neigh *curr_softif_neigh = NULL; if (ntohs(ethhdr->h_proto) == ETH_P_8021Q) - batman_packet = (struct batman_packet *) + batman_ogm_packet = (struct batman_ogm_packet *) (skb->data + ETH_HLEN + VLAN_HLEN); else - batman_packet = (struct batman_packet *)(skb->data + ETH_HLEN); + batman_ogm_packet = (struct batman_ogm_packet *) + (skb->data + ETH_HLEN); - if (batman_packet->version != COMPAT_VERSION) + if (batman_ogm_packet->version != COMPAT_VERSION) goto out; - if (batman_packet->packet_type != BAT_PACKET) + if (batman_ogm_packet->packet_type != BAT_OGM) goto out; - if (!(batman_packet->flags & PRIMARIES_FIRST_HOP)) + if (!(batman_ogm_packet->flags & PRIMARIES_FIRST_HOP)) goto out; - if (is_my_mac(batman_packet->orig)) + if (is_my_mac(batman_ogm_packet->orig)) goto out; - softif_neigh = softif_neigh_get(bat_priv, batman_packet->orig, vid); + softif_neigh = softif_neigh_get(bat_priv, batman_ogm_packet->orig, vid); if (!softif_neigh) goto out; @@ -532,11 +533,11 @@ static int interface_set_mac_addr(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - /* only modify transtable if it has been initialised before */ + /* only modify transtable if it has been initialized before */ if (atomic_read(&bat_priv->mesh_state) == MESH_ACTIVE) { tt_local_remove(bat_priv, dev->dev_addr, "mac address changed", false); - tt_local_add(dev, addr->sa_data); + tt_local_add(dev, addr->sa_data, NULL_IFINDEX); } memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); @@ -595,11 +596,12 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) goto dropped; /* Register the client MAC in the transtable */ - tt_local_add(soft_iface, ethhdr->h_source); + tt_local_add(soft_iface, ethhdr->h_source, skb->skb_iif); - orig_node = transtable_search(bat_priv, ethhdr->h_dest); + orig_node = transtable_search(bat_priv, ethhdr->h_source, + ethhdr->h_dest); do_bcast = is_multicast_ether_addr(ethhdr->h_dest); - if (do_bcast || (orig_node && orig_node->gw_flags)) { + if (do_bcast || (orig_node && orig_node->gw_flags)) { ret = gw_is_target(bat_priv, skb, orig_node); if (ret < 0) @@ -739,6 +741,9 @@ void interface_rx(struct net_device *soft_iface, soft_iface->last_rx = jiffies; + if (is_ap_isolated(bat_priv, ethhdr->h_source, ethhdr->h_dest)) + goto dropped; + netif_rx(skb); goto out; @@ -796,10 +801,8 @@ struct net_device *softif_create(const char *name) soft_iface = alloc_netdev(sizeof(*bat_priv), name, interface_setup); - if (!soft_iface) { - pr_err("Unable to allocate the batman interface: %s\n", name); + if (!soft_iface) goto out; - } ret = register_netdevice(soft_iface); if (ret < 0) { @@ -812,6 +815,7 @@ struct net_device *softif_create(const char *name) atomic_set(&bat_priv->aggregated_ogms, 1); atomic_set(&bat_priv->bonding, 0); + atomic_set(&bat_priv->ap_isolation, 0); atomic_set(&bat_priv->vis_mode, VIS_TYPE_CLIENT_UPDATE); atomic_set(&bat_priv->gw_mode, GW_MODE_OFF); atomic_set(&bat_priv->gw_sel_class, 20); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index fb6931d..c7aafc7 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -137,10 +137,22 @@ static void tt_local_entry_free_ref(struct tt_local_entry *tt_local_entry) kfree_rcu(tt_local_entry, rcu); } +static void tt_global_entry_free_rcu(struct rcu_head *rcu) +{ + struct tt_global_entry *tt_global_entry; + + tt_global_entry = container_of(rcu, struct tt_global_entry, rcu); + + if (tt_global_entry->orig_node) + orig_node_free_ref(tt_global_entry->orig_node); + + kfree(tt_global_entry); +} + static void tt_global_entry_free_ref(struct tt_global_entry *tt_global_entry) { if (atomic_dec_and_test(&tt_global_entry->refcount)) - kfree_rcu(tt_global_entry, rcu); + call_rcu(&tt_global_entry->rcu, tt_global_entry_free_rcu); } static void tt_local_event(struct bat_priv *bat_priv, const uint8_t *addr, @@ -183,7 +195,8 @@ static int tt_local_init(struct bat_priv *bat_priv) return 1; } -void tt_local_add(struct net_device *soft_iface, const uint8_t *addr) +void tt_local_add(struct net_device *soft_iface, const uint8_t *addr, + int ifindex) { struct bat_priv *bat_priv = netdev_priv(soft_iface); struct tt_local_entry *tt_local_entry = NULL; @@ -207,6 +220,8 @@ void tt_local_add(struct net_device *soft_iface, const uint8_t *addr) memcpy(tt_local_entry->addr, addr, ETH_ALEN); tt_local_entry->last_seen = jiffies; tt_local_entry->flags = NO_FLAGS; + if (is_wifi_iface(ifindex)) + tt_local_entry->flags |= TT_CLIENT_WIFI; atomic_set(&tt_local_entry->refcount, 2); /* the batman interface mac address should never be purged */ @@ -329,7 +344,7 @@ int tt_local_seq_print_text(struct seq_file *seq, void *offset) rcu_read_lock(); __hlist_for_each_rcu(node, head) - buf_size += 21; + buf_size += 29; rcu_read_unlock(); } @@ -348,8 +363,19 @@ int tt_local_seq_print_text(struct seq_file *seq, void *offset) rcu_read_lock(); hlist_for_each_entry_rcu(tt_local_entry, node, head, hash_entry) { - pos += snprintf(buff + pos, 22, " * %pM\n", - tt_local_entry->addr); + pos += snprintf(buff + pos, 30, " * %pM " + "[%c%c%c%c%c]\n", + tt_local_entry->addr, + (tt_local_entry->flags & + TT_CLIENT_ROAM ? 'R' : '.'), + (tt_local_entry->flags & + TT_CLIENT_NOPURGE ? 'P' : '.'), + (tt_local_entry->flags & + TT_CLIENT_NEW ? 'N' : '.'), + (tt_local_entry->flags & + TT_CLIENT_PENDING ? 'X' : '.'), + (tt_local_entry->flags & + TT_CLIENT_WIFI ? 'W' : '.')); } rcu_read_unlock(); } @@ -369,8 +395,8 @@ static void tt_local_set_pending(struct bat_priv *bat_priv, tt_local_event(bat_priv, tt_local_entry->addr, tt_local_entry->flags | flags); - /* The local client has to be merked as "pending to be removed" but has - * to be kept in the table in order to send it in an full tables + /* The local client has to be marked as "pending to be removed" but has + * to be kept in the table in order to send it in a full table * response issued before the net ttvn increment (consistency check) */ tt_local_entry->flags |= TT_CLIENT_PENDING; } @@ -495,7 +521,8 @@ static void tt_changes_list_free(struct bat_priv *bat_priv) /* caller must hold orig_node refcount */ int tt_global_add(struct bat_priv *bat_priv, struct orig_node *orig_node, - const unsigned char *tt_addr, uint8_t ttvn, bool roaming) + const unsigned char *tt_addr, uint8_t ttvn, bool roaming, + bool wifi) { struct tt_global_entry *tt_global_entry; struct orig_node *orig_node_tmp; @@ -537,6 +564,9 @@ int tt_global_add(struct bat_priv *bat_priv, struct orig_node *orig_node, tt_global_entry->roam_at = 0; } + if (wifi) + tt_global_entry->flags |= TT_CLIENT_WIFI; + bat_dbg(DBG_TT, bat_priv, "Creating new global tt entry: %pM (via %pM)\n", tt_global_entry->addr, orig_node->orig); @@ -582,8 +612,8 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset) seq_printf(seq, "Globally announced TT entries received via the mesh %s\n", net_dev->name); - seq_printf(seq, " %-13s %s %-15s %s\n", - "Client", "(TTVN)", "Originator", "(Curr TTVN)"); + seq_printf(seq, " %-13s %s %-15s %s %s\n", + "Client", "(TTVN)", "Originator", "(Curr TTVN)", "Flags"); buf_size = 1; /* Estimate length for: " * xx:xx:xx:xx:xx:xx (ttvn) via @@ -593,7 +623,7 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset) rcu_read_lock(); __hlist_for_each_rcu(node, head) - buf_size += 59; + buf_size += 67; rcu_read_unlock(); } @@ -612,14 +642,20 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset) rcu_read_lock(); hlist_for_each_entry_rcu(tt_global_entry, node, head, hash_entry) { - pos += snprintf(buff + pos, 61, - " * %pM (%3u) via %pM (%3u)\n", - tt_global_entry->addr, + pos += snprintf(buff + pos, 69, + " * %pM (%3u) via %pM (%3u) " + "[%c%c%c]\n", tt_global_entry->addr, tt_global_entry->ttvn, tt_global_entry->orig_node->orig, (uint8_t) atomic_read( &tt_global_entry->orig_node-> - last_ttvn)); + last_ttvn), + (tt_global_entry->flags & + TT_CLIENT_ROAM ? 'R' : '.'), + (tt_global_entry->flags & + TT_CLIENT_PENDING ? 'X' : '.'), + (tt_global_entry->flags & + TT_CLIENT_WIFI ? 'W' : '.')); } rcu_read_unlock(); } @@ -686,6 +722,9 @@ void tt_global_del_orig(struct bat_priv *bat_priv, struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ + if (!hash) + return; + for (i = 0; i < hash->size; i++) { head = &hash->table[i]; list_lock = &hash->list_locks[i]; @@ -774,30 +813,56 @@ static void tt_global_table_free(struct bat_priv *bat_priv) bat_priv->tt_global_hash = NULL; } +static bool _is_ap_isolated(struct tt_local_entry *tt_local_entry, + struct tt_global_entry *tt_global_entry) +{ + bool ret = false; + + if (tt_local_entry->flags & TT_CLIENT_WIFI && + tt_global_entry->flags & TT_CLIENT_WIFI) + ret = true; + + return ret; +} + struct orig_node *transtable_search(struct bat_priv *bat_priv, - const uint8_t *addr) + const uint8_t *src, const uint8_t *addr) { - struct tt_global_entry *tt_global_entry; + struct tt_local_entry *tt_local_entry = NULL; + struct tt_global_entry *tt_global_entry = NULL; struct orig_node *orig_node = NULL; - tt_global_entry = tt_global_hash_find(bat_priv, addr); + if (src && atomic_read(&bat_priv->ap_isolation)) { + tt_local_entry = tt_local_hash_find(bat_priv, src); + if (!tt_local_entry) + goto out; + } + tt_global_entry = tt_global_hash_find(bat_priv, addr); if (!tt_global_entry) goto out; + /* check whether the clients should not communicate due to AP + * isolation */ + if (tt_local_entry && _is_ap_isolated(tt_local_entry, tt_global_entry)) + goto out; + if (!atomic_inc_not_zero(&tt_global_entry->orig_node->refcount)) - goto free_tt; + goto out; /* A global client marked as PENDING has already moved from that * originator */ if (tt_global_entry->flags & TT_CLIENT_PENDING) - goto free_tt; + goto out; orig_node = tt_global_entry->orig_node; -free_tt: - tt_global_entry_free_ref(tt_global_entry); out: + if (tt_global_entry) + tt_global_entry_free_ref(tt_global_entry); + if (tt_local_entry) + tt_local_entry_free_ref(tt_local_entry); + return orig_node; } @@ -999,7 +1064,6 @@ static struct sk_buff *tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, tt_response = (struct tt_query_packet *)skb_put(skb, tt_query_size + tt_len); tt_response->ttvn = ttvn; - tt_response->tt_data = htons(tt_tot); tt_change = (struct tt_change *)(skb->data + tt_query_size); tt_count = 0; @@ -1025,12 +1089,17 @@ static struct sk_buff *tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, } rcu_read_unlock(); + /* store in the message the number of entries we have successfully + * copied */ + tt_response->tt_data = htons(tt_count); + out: return skb; } -int send_tt_request(struct bat_priv *bat_priv, struct orig_node *dst_orig_node, - uint8_t ttvn, uint16_t tt_crc, bool full_table) +static int send_tt_request(struct bat_priv *bat_priv, + struct orig_node *dst_orig_node, + uint8_t ttvn, uint16_t tt_crc, bool full_table) { struct sk_buff *skb = NULL; struct tt_query_packet *tt_request; @@ -1137,12 +1206,12 @@ static bool send_other_tt_response(struct bat_priv *bat_priv, orig_ttvn = (uint8_t)atomic_read(&req_dst_orig_node->last_ttvn); req_ttvn = tt_request->ttvn; - /* I have not the requested data */ + /* I don't have the requested data */ if (orig_ttvn != req_ttvn || tt_request->tt_data != req_dst_orig_node->tt_crc) goto out; - /* If it has explicitly been requested the full table */ + /* If the full table has been explicitly requested */ if (tt_request->flags & TT_FULL_TABLE || !req_dst_orig_node->tt_buff) full_table = true; @@ -1363,7 +1432,9 @@ static void _tt_update_changes(struct bat_priv *bat_priv, (tt_change + i)->flags & TT_CLIENT_ROAM); else if (!tt_global_add(bat_priv, orig_node, - (tt_change + i)->addr, ttvn, false)) + (tt_change + i)->addr, ttvn, false, + (tt_change + i)->flags & + TT_CLIENT_WIFI)) /* In case of problem while storing a * global_entry, we stop the updating * procedure without committing the @@ -1403,9 +1474,10 @@ out: orig_node_free_ref(orig_node); } -void tt_update_changes(struct bat_priv *bat_priv, struct orig_node *orig_node, - uint16_t tt_num_changes, uint8_t ttvn, - struct tt_change *tt_change) +static void tt_update_changes(struct bat_priv *bat_priv, + struct orig_node *orig_node, + uint16_t tt_num_changes, uint8_t ttvn, + struct tt_change *tt_change) { _tt_update_changes(bat_priv, orig_node, tt_change, tt_num_changes, ttvn); @@ -1668,6 +1740,8 @@ static void tt_local_reset_flags(struct bat_priv *bat_priv, uint16_t flags) rcu_read_lock(); hlist_for_each_entry_rcu(tt_local_entry, node, head, hash_entry) { + if (!(tt_local_entry->flags & flags)) + continue; tt_local_entry->flags &= ~flags; atomic_inc(&bat_priv->num_local_tt); } @@ -1720,3 +1794,90 @@ void tt_commit_changes(struct bat_priv *bat_priv) atomic_inc(&bat_priv->ttvn); bat_priv->tt_poss_change = false; } + +bool is_ap_isolated(struct bat_priv *bat_priv, uint8_t *src, uint8_t *dst) +{ + struct tt_local_entry *tt_local_entry = NULL; + struct tt_global_entry *tt_global_entry = NULL; + bool ret = true; + + if (!atomic_read(&bat_priv->ap_isolation)) + return false; + + tt_local_entry = tt_local_hash_find(bat_priv, dst); + if (!tt_local_entry) + goto out; + + tt_global_entry = tt_global_hash_find(bat_priv, src); + if (!tt_global_entry) + goto out; + + if (_is_ap_isolated(tt_local_entry, tt_global_entry)) + goto out; + + ret = false; + +out: + if (tt_global_entry) + tt_global_entry_free_ref(tt_global_entry); + if (tt_local_entry) + tt_local_entry_free_ref(tt_local_entry); + return ret; +} + +void tt_update_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, + const unsigned char *tt_buff, uint8_t tt_num_changes, + uint8_t ttvn, uint16_t tt_crc) +{ + uint8_t orig_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); + bool full_table = true; + + /* the ttvn increased by one -> we can apply the attached changes */ + if (ttvn - orig_ttvn == 1) { + /* the OGM could not contain the changes due to their size or + * because they have already been sent TT_OGM_APPEND_MAX times. + * In this case send a tt request */ + if (!tt_num_changes) { + full_table = false; + goto request_table; + } + + tt_update_changes(bat_priv, orig_node, tt_num_changes, ttvn, + (struct tt_change *)tt_buff); + + /* Even if we received the precomputed crc with the OGM, we + * prefer to recompute it to spot any possible inconsistency + * in the global table */ + orig_node->tt_crc = tt_global_crc(bat_priv, orig_node); + + /* The ttvn alone is not enough to guarantee consistency + * because a single value could represent different states + * (due to the wrap around). Thus a node has to check whether + * the resulting table (after applying the changes) is still + * consistent or not. E.g. a node could disconnect while its + * ttvn is X and reconnect on ttvn = X + TTVN_MAX: in this case + * checking the CRC value is mandatory to detect the + * inconsistency */ + if (orig_node->tt_crc != tt_crc) + goto request_table; + + /* Roaming phase is over: tables are in sync again. I can + * unset the flag */ + orig_node->tt_poss_change = false; + } else { + /* if we missed more than one change or our tables are not + * in sync anymore -> request fresh tt data */ + if (ttvn != orig_ttvn || orig_node->tt_crc != tt_crc) { +request_table: + bat_dbg(DBG_TT, bat_priv, "TT inconsistency for %pM. " + "Need to retrieve the correct information " + "(ttvn: %u last_ttvn: %u crc: %u last_crc: " + "%u num_changes: %u)\n", orig_node->orig, ttvn, + orig_ttvn, tt_crc, orig_node->tt_crc, + tt_num_changes); + send_tt_request(bat_priv, orig_node, ttvn, tt_crc, + full_table); + return; + } + } +} diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index d4122cb..30efd49 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -26,15 +26,16 @@ int tt_len(int changes_num); int tt_changes_fill_buffer(struct bat_priv *bat_priv, unsigned char *buff, int buff_len); int tt_init(struct bat_priv *bat_priv); -void tt_local_add(struct net_device *soft_iface, const uint8_t *addr); +void tt_local_add(struct net_device *soft_iface, const uint8_t *addr, + int ifindex); void tt_local_remove(struct bat_priv *bat_priv, const uint8_t *addr, const char *message, bool roaming); int tt_local_seq_print_text(struct seq_file *seq, void *offset); void tt_global_add_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, const unsigned char *tt_buff, int tt_buff_len); -int tt_global_add(struct bat_priv *bat_priv, - struct orig_node *orig_node, const unsigned char *addr, - uint8_t ttvn, bool roaming); +int tt_global_add(struct bat_priv *bat_priv, struct orig_node *orig_node, + const unsigned char *addr, uint8_t ttvn, bool roaming, + bool wifi); int tt_global_seq_print_text(struct seq_file *seq, void *offset); void tt_global_del_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, const char *message); @@ -42,25 +43,23 @@ void tt_global_del(struct bat_priv *bat_priv, struct orig_node *orig_node, const unsigned char *addr, const char *message, bool roaming); struct orig_node *transtable_search(struct bat_priv *bat_priv, - const uint8_t *addr); + const uint8_t *src, const uint8_t *addr); void tt_save_orig_buffer(struct bat_priv *bat_priv, struct orig_node *orig_node, const unsigned char *tt_buff, uint8_t tt_num_changes); uint16_t tt_local_crc(struct bat_priv *bat_priv); uint16_t tt_global_crc(struct bat_priv *bat_priv, struct orig_node *orig_node); void tt_free(struct bat_priv *bat_priv); -int send_tt_request(struct bat_priv *bat_priv, - struct orig_node *dst_orig_node, uint8_t hvn, - uint16_t tt_crc, bool full_table); bool send_tt_response(struct bat_priv *bat_priv, struct tt_query_packet *tt_request); -void tt_update_changes(struct bat_priv *bat_priv, struct orig_node *orig_node, - uint16_t tt_num_changes, uint8_t ttvn, - struct tt_change *tt_change); bool is_my_client(struct bat_priv *bat_priv, const uint8_t *addr); void handle_tt_response(struct bat_priv *bat_priv, struct tt_query_packet *tt_response); void send_roam_adv(struct bat_priv *bat_priv, uint8_t *client, struct orig_node *orig_node); void tt_commit_changes(struct bat_priv *bat_priv); +bool is_ap_isolated(struct bat_priv *bat_priv, uint8_t *src, uint8_t *dst); +void tt_update_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, + const unsigned char *tt_buff, uint8_t tt_num_changes, + uint8_t ttvn, uint16_t tt_crc); #endif /* _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 25bd1db..ab8d0fe 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -57,7 +57,7 @@ struct hard_iface { * @batman_seqno_reset: time when the batman seqno window was reset * @gw_flags: flags related to gateway class * @flags: for now only VIS_SERVER flag - * @last_real_seqno: last and best known squence number + * @last_real_seqno: last and best known sequence number * @last_ttl: ttl of last received packet * @last_bcast_seqno: last broadcast sequence number received by this host * @@ -146,6 +146,7 @@ struct bat_priv { atomic_t aggregated_ogms; /* boolean */ atomic_t bonding; /* boolean */ atomic_t fragmentation; /* boolean */ + atomic_t ap_isolation; /* boolean */ atomic_t vis_mode; /* VIS_TYPE_* */ atomic_t gw_mode; /* GW_MODE_* */ atomic_t gw_sel_class; /* uint */ @@ -156,7 +157,7 @@ struct bat_priv { atomic_t bcast_seqno; atomic_t bcast_queue_left; atomic_t batman_queue_left; - atomic_t ttvn; /* tranlation table version number */ + atomic_t ttvn; /* translation table version number */ atomic_t tt_ogm_append_cnt; atomic_t tt_local_changes; /* changes registered in a OGM interval */ /* The tt_poss_change flag is used to detect an ongoing roaming phase. @@ -223,22 +224,22 @@ struct socket_packet { struct tt_local_entry { uint8_t addr[ETH_ALEN]; + struct hlist_node hash_entry; unsigned long last_seen; uint16_t flags; atomic_t refcount; struct rcu_head rcu; - struct hlist_node hash_entry; }; struct tt_global_entry { uint8_t addr[ETH_ALEN]; + struct hlist_node hash_entry; /* entry in the global table */ struct orig_node *orig_node; uint8_t ttvn; uint16_t flags; /* only TT_GLOBAL_ROAM is used */ unsigned long roam_at; /* time at which TT_GLOBAL_ROAM was set */ atomic_t refcount; struct rcu_head rcu; - struct hlist_node hash_entry; /* entry in the global table */ }; struct tt_change_node { diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index 32b125f..07d1c1d 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -299,8 +299,10 @@ int unicast_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv) goto find_router; } - /* check for tt host - increases orig_node refcount */ - orig_node = transtable_search(bat_priv, ethhdr->h_dest); + /* check for tt host - increases orig_node refcount. + * returns NULL in case of AP isolation */ + orig_node = transtable_search(bat_priv, ethhdr->h_source, + ethhdr->h_dest); find_router: /** diff --git a/net/batman-adv/unicast.h b/net/batman-adv/unicast.h index 62f54b9..8fd5535 100644 --- a/net/batman-adv/unicast.h +++ b/net/batman-adv/unicast.h @@ -24,7 +24,7 @@ #include "packet.h" -#define FRAG_TIMEOUT 10000 /* purge frag list entrys after time in ms */ +#define FRAG_TIMEOUT 10000 /* purge frag list entries after time in ms */ #define FRAG_BUFFER_SIZE 6 /* number of list elements in buffer */ int frag_reassemble_skb(struct sk_buff *skb, struct bat_priv *bat_priv, diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index 8a1b985..f81a6b6 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -131,7 +131,7 @@ static void vis_data_insert_interface(const uint8_t *interface, return; } - /* its a new address, add it to the list */ + /* it's a new address, add it to the list */ entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) return; @@ -465,7 +465,7 @@ static struct vis_info *add_packet(struct bat_priv *bat_priv, /* try to add it */ hash_added = hash_add(bat_priv->vis_hash, vis_info_cmp, vis_info_choose, info, &info->hash_entry); - if (hash_added < 0) { + if (hash_added != 0) { /* did not work (for some reason) */ kref_put(&info->refcount, free_info); info = NULL; @@ -887,10 +887,8 @@ int vis_init(struct bat_priv *bat_priv) } bat_priv->my_vis_info = kmalloc(MAX_VIS_PACKET_SIZE, GFP_ATOMIC); - if (!bat_priv->my_vis_info) { - pr_err("Can't initialize vis packet\n"); + if (!bat_priv->my_vis_info) goto err; - } bat_priv->my_vis_info->skb_packet = dev_alloc_skb(sizeof(*packet) + MAX_VIS_PACKET_SIZE + @@ -920,7 +918,7 @@ int vis_init(struct bat_priv *bat_priv) hash_added = hash_add(bat_priv->vis_hash, vis_info_cmp, vis_info_choose, bat_priv->my_vis_info, &bat_priv->my_vis_info->hash_entry); - if (hash_added < 0) { + if (hash_added != 0) { pr_err("Can't add own vis packet into hash\n"); /* not in hash, need to remove it manually. */ kref_put(&bat_priv->my_vis_info->refcount, free_info); diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 117e0d1..062124c 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -349,7 +349,7 @@ int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock, } chunk = min_t(unsigned int, skb->len, size); - if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) { + if (skb_copy_datagram_iovec(skb, 0, msg->msg_iov, chunk)) { skb_queue_head(&sk->sk_receive_queue, skb); if (!copied) copied = -EFAULT; @@ -361,7 +361,33 @@ int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock, sock_recv_ts_and_drops(msg, sk, skb); if (!(flags & MSG_PEEK)) { - skb_pull(skb, chunk); + int skb_len = skb_headlen(skb); + + if (chunk <= skb_len) { + __skb_pull(skb, chunk); + } else { + struct sk_buff *frag; + + __skb_pull(skb, skb_len); + chunk -= skb_len; + + skb_walk_frags(skb, frag) { + if (chunk <= frag->len) { + /* Pulling partial data */ + skb->len -= chunk; + skb->data_len -= chunk; + __skb_pull(frag, chunk); + break; + } else if (frag->len) { + /* Pulling all frag data */ + chunk -= frag->len; + skb->len -= frag->len; + skb->data_len -= frag->len; + __skb_pull(frag, frag->len); + } + } + } + if (skb->len) { skb_queue_head(&sk->sk_receive_queue, skb); break; diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index d9edfe8..91bcd3a 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -492,7 +492,10 @@ static int bnep_session(void *arg) /* RX */ while ((skb = skb_dequeue(&sk->sk_receive_queue))) { skb_orphan(skb); - bnep_rx_frame(s, skb); + if (!skb_linearize(skb)) + bnep_rx_frame(s, skb); + else + kfree_skb(skb); } if (sk->sk_state != BT_CONNECTED) diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c index d4f5dff..bc40864 100644 --- a/net/bluetooth/bnep/netdev.c +++ b/net/bluetooth/bnep/netdev.c @@ -217,7 +217,7 @@ static const struct net_device_ops bnep_netdev_ops = { .ndo_stop = bnep_net_close, .ndo_start_xmit = bnep_net_xmit, .ndo_validate_addr = eth_validate_addr, - .ndo_set_multicast_list = bnep_net_set_mc_list, + .ndo_set_rx_mode = bnep_net_set_mc_list, .ndo_set_mac_address = bnep_net_set_mac_addr, .ndo_tx_timeout = bnep_net_timeout, .ndo_change_mtu = eth_change_mtu, diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 521baa4..7d00ddf 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -302,7 +302,10 @@ static int cmtp_session(void *arg) while ((skb = skb_dequeue(&sk->sk_receive_queue))) { skb_orphan(skb); - cmtp_recv_frame(session, skb); + if (!skb_linearize(skb)) + cmtp_recv_frame(session, skb); + else + kfree_skb(skb); } cmtp_process_transmit(session); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index ea7f031..c1c597e 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -56,15 +56,15 @@ static void hci_le_connect(struct hci_conn *conn) conn->sec_level = BT_SECURITY_LOW; memset(&cp, 0, sizeof(cp)); - cp.scan_interval = cpu_to_le16(0x0004); - cp.scan_window = cpu_to_le16(0x0004); + cp.scan_interval = cpu_to_le16(0x0060); + cp.scan_window = cpu_to_le16(0x0030); bacpy(&cp.peer_addr, &conn->dst); cp.peer_addr_type = conn->dst_type; - cp.conn_interval_min = cpu_to_le16(0x0008); - cp.conn_interval_max = cpu_to_le16(0x0100); - cp.supervision_timeout = cpu_to_le16(0x0064); - cp.min_ce_len = cpu_to_le16(0x0001); - cp.max_ce_len = cpu_to_le16(0x0001); + cp.conn_interval_min = cpu_to_le16(0x0028); + cp.conn_interval_max = cpu_to_le16(0x0038); + cp.supervision_timeout = cpu_to_le16(0x002a); + cp.min_ce_len = cpu_to_le16(0x0000); + cp.max_ce_len = cpu_to_le16(0x0000); hci_send_cmd(hdev, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp); } @@ -218,7 +218,7 @@ void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __u8 rand[8], cp.handle = cpu_to_le16(conn->handle); memcpy(cp.ltk, ltk, sizeof(cp.ltk)); cp.ediv = ediv; - memcpy(cp.rand, rand, sizeof(rand)); + memcpy(cp.rand, rand, sizeof(cp.rand)); hci_send_cmd(hdev, HCI_OP_LE_START_ENC, sizeof(cp), &cp); } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 56943ad..b84458d 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1312,59 +1312,41 @@ int hci_blacklist_clear(struct hci_dev *hdev) int hci_blacklist_add(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct bdaddr_list *entry; - int err; if (bacmp(bdaddr, BDADDR_ANY) == 0) return -EBADF; - hci_dev_lock_bh(hdev); - - if (hci_blacklist_lookup(hdev, bdaddr)) { - err = -EEXIST; - goto err; - } + if (hci_blacklist_lookup(hdev, bdaddr)) + return -EEXIST; entry = kzalloc(sizeof(struct bdaddr_list), GFP_KERNEL); - if (!entry) { - err = -ENOMEM; - goto err; - } + if (!entry) + return -ENOMEM; bacpy(&entry->bdaddr, bdaddr); list_add(&entry->list, &hdev->blacklist); - err = 0; - -err: - hci_dev_unlock_bh(hdev); - return err; + return mgmt_device_blocked(hdev->id, bdaddr); } int hci_blacklist_del(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct bdaddr_list *entry; - int err = 0; - - hci_dev_lock_bh(hdev); if (bacmp(bdaddr, BDADDR_ANY) == 0) { - hci_blacklist_clear(hdev); - goto done; + return hci_blacklist_clear(hdev); } entry = hci_blacklist_lookup(hdev, bdaddr); if (!entry) { - err = -ENOENT; - goto done; + return -ENOENT; } list_del(&entry->list); kfree(entry); -done: - hci_dev_unlock_bh(hdev); - return err; + return mgmt_device_unblocked(hdev->id, bdaddr); } static void hci_clear_adv_cache(unsigned long arg) @@ -1523,11 +1505,6 @@ int hci_register_dev(struct hci_dev *hdev) if (!hdev->workqueue) goto nomem; - hdev->tfm = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(hdev->tfm)) - BT_INFO("Failed to load transform for ecb(aes): %ld", - PTR_ERR(hdev->tfm)); - hci_register_sysfs(hdev); hdev->rfkill = rfkill_alloc(hdev->name, &hdev->dev, @@ -1576,9 +1553,6 @@ int hci_unregister_dev(struct hci_dev *hdev) !test_bit(HCI_SETUP, &hdev->flags)) mgmt_index_removed(hdev->id); - if (!IS_ERR(hdev->tfm)) - crypto_free_blkcipher(hdev->tfm); - hci_notify(hdev, HCI_DEV_UNREG); if (hdev->rfkill) { @@ -2074,6 +2048,9 @@ static inline struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type, int min = c->sent; conn = c; } + + if (hci_conn_num(hdev, type) == num) + break; } if (conn) { @@ -2131,6 +2108,9 @@ static inline void hci_sched_acl(struct hci_dev *hdev) BT_DBG("%s", hdev->name); + if (!hci_conn_num(hdev, ACL_LINK)) + return; + if (!test_bit(HCI_RAW, &hdev->flags)) { /* ACL tx timeout must be longer than maximum * link supervision timeout (40.9 seconds) */ @@ -2162,6 +2142,9 @@ static inline void hci_sched_sco(struct hci_dev *hdev) BT_DBG("%s", hdev->name); + if (!hci_conn_num(hdev, SCO_LINK)) + return; + while (hdev->sco_cnt && (conn = hci_low_sent(hdev, SCO_LINK, "e))) { while (quote-- && (skb = skb_dequeue(&conn->data_q))) { BT_DBG("skb %p len %d", skb, skb->len); @@ -2182,6 +2165,9 @@ static inline void hci_sched_esco(struct hci_dev *hdev) BT_DBG("%s", hdev->name); + if (!hci_conn_num(hdev, ESCO_LINK)) + return; + while (hdev->sco_cnt && (conn = hci_low_sent(hdev, ESCO_LINK, "e))) { while (quote-- && (skb = skb_dequeue(&conn->data_q))) { BT_DBG("skb %p len %d", skb, skb->len); @@ -2202,6 +2188,9 @@ static inline void hci_sched_le(struct hci_dev *hdev) BT_DBG("%s", hdev->name); + if (!hci_conn_num(hdev, LE_LINK)) + return; + if (!test_bit(HCI_RAW, &hdev->flags)) { /* LE tx timeout must be longer than maximum * link supervision timeout (40.9 seconds) */ diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 7ef4eb4..d7d96b6 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -898,16 +898,15 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, if (!cp) return; - hci_dev_lock(hdev); - if (cp->enable == 0x01) { del_timer(&hdev->adv_timer); + + hci_dev_lock(hdev); hci_adv_entries_clear(hdev); + hci_dev_unlock(hdev); } else if (cp->enable == 0x00) { mod_timer(&hdev->adv_timer, jiffies + ADV_CLEAR_TIMEOUT); } - - hci_dev_unlock(hdev); } static void hci_cc_le_ltk_reply(struct hci_dev *hdev, struct sk_buff *skb) @@ -1103,9 +1102,10 @@ static int hci_outgoing_auth_needed(struct hci_dev *hdev, return 0; /* Only request authentication for SSP connections or non-SSP - * devices with sec_level HIGH */ + * devices with sec_level HIGH or if MITM protection is requested */ if (!(hdev->ssp_mode > 0 && conn->ssp_mode > 0) && - conn->pending_sec_level != BT_SECURITY_HIGH) + conn->pending_sec_level != BT_SECURITY_HIGH && + !(conn->auth_type & 0x01)) return 0; return 1; @@ -1412,7 +1412,7 @@ static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *s conn->state = BT_CONFIG; hci_conn_hold(conn); conn->disc_timeout = HCI_DISCONN_TIMEOUT; - mgmt_connected(hdev->id, &ev->bdaddr); + mgmt_connected(hdev->id, &ev->bdaddr, conn->type); } else conn->state = BT_CONNECTED; @@ -2174,7 +2174,10 @@ static inline void hci_pin_code_request_evt(struct hci_dev *hdev, struct sk_buff hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (conn && conn->state == BT_CONNECTED) { + if (!conn) + goto unlock; + + if (conn->state == BT_CONNECTED) { hci_conn_hold(conn); conn->disc_timeout = HCI_PAIRING_TIMEOUT; hci_conn_put(conn); @@ -2194,6 +2197,7 @@ static inline void hci_pin_code_request_evt(struct hci_dev *hdev, struct sk_buff mgmt_pin_code_request(hdev->id, &ev->bdaddr, secure); } +unlock: hci_dev_unlock(hdev); } @@ -2816,7 +2820,7 @@ static inline void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff goto unlock; } - mgmt_connected(hdev->id, &ev->bdaddr); + mgmt_connected(hdev->id, &ev->bdaddr, conn->type); conn->sec_level = BT_SECURITY_LOW; conn->handle = __le16_to_cpu(ev->handle); @@ -2834,19 +2838,17 @@ unlock: static inline void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) { - struct hci_ev_le_advertising_info *ev; - u8 num_reports; - - num_reports = skb->data[0]; - ev = (void *) &skb->data[1]; + u8 num_reports = skb->data[0]; + void *ptr = &skb->data[1]; hci_dev_lock(hdev); - hci_add_adv_entry(hdev, ev); + while (num_reports--) { + struct hci_ev_le_advertising_info *ev = ptr; - while (--num_reports) { - ev = (void *) (ev->data + ev->length + 1); hci_add_adv_entry(hdev, ev); + + ptr += sizeof(*ev) + ev->length + 1; } hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index ff02cf5..f6afe3d 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -183,21 +183,35 @@ static int hci_sock_release(struct socket *sock) static int hci_sock_blacklist_add(struct hci_dev *hdev, void __user *arg) { bdaddr_t bdaddr; + int err; if (copy_from_user(&bdaddr, arg, sizeof(bdaddr))) return -EFAULT; - return hci_blacklist_add(hdev, &bdaddr); + hci_dev_lock_bh(hdev); + + err = hci_blacklist_add(hdev, &bdaddr); + + hci_dev_unlock_bh(hdev); + + return err; } static int hci_sock_blacklist_del(struct hci_dev *hdev, void __user *arg) { bdaddr_t bdaddr; + int err; if (copy_from_user(&bdaddr, arg, sizeof(bdaddr))) return -EFAULT; - return hci_blacklist_del(hdev, &bdaddr); + hci_dev_lock_bh(hdev); + + err = hci_blacklist_del(hdev, &bdaddr); + + hci_dev_unlock_bh(hdev); + + return err; } /* Ioctls that require bound socket */ diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index a6c3aa8..22f1a6c 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -23,6 +23,8 @@ static inline char *link_typetostr(int type) return "SCO"; case ESCO_LINK: return "eSCO"; + case LE_LINK: + return "LE"; default: return "UNKNOWN"; } diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index fb68f34..075a3e9 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -716,12 +716,18 @@ static int hidp_session(void *arg) while ((skb = skb_dequeue(&ctrl_sk->sk_receive_queue))) { skb_orphan(skb); - hidp_recv_ctrl_frame(session, skb); + if (!skb_linearize(skb)) + hidp_recv_ctrl_frame(session, skb); + else + kfree_skb(skb); } while ((skb = skb_dequeue(&intr_sk->sk_receive_queue))) { skb_orphan(skb); - hidp_recv_intr_frame(session, skb); + if (!skb_linearize(skb)) + hidp_recv_intr_frame(session, skb); + else + kfree_skb(skb); } hidp_process_transmit(session); @@ -872,6 +878,9 @@ static int hidp_start(struct hid_device *hid) struct hidp_session *session = hid->driver_data; struct hid_report *report; + if (hid->quirks & HID_QUIRK_NO_INIT_REPORTS) + return 0; + list_for_each_entry(report, &hid->report_enum[HID_INPUT_REPORT]. report_list, list) hidp_send_report(session, report); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index b3bdb48..8cd1291 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -907,6 +907,9 @@ static void l2cap_conn_ready(struct l2cap_conn *conn) if (!conn->hcon->out && conn->hcon->type == LE_LINK) l2cap_le_conn_ready(conn); + if (conn->hcon->out && conn->hcon->type == LE_LINK) + smp_conn_security(conn, conn->hcon->pending_sec_level); + read_lock(&conn->chan_lock); list_for_each_entry(chan, &conn->chan_l, list) { @@ -986,8 +989,10 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) del_timer_sync(&conn->info_timer); - if (test_bit(HCI_CONN_ENCRYPT_PEND, &hcon->pend)) + if (test_and_clear_bit(HCI_CONN_LE_SMP_PEND, &hcon->pend)) { del_timer(&conn->security_timer); + smp_chan_destroy(conn); + } hcon->l2cap_data = NULL; kfree(conn); @@ -1240,7 +1245,7 @@ static void l2cap_drop_acked_frames(struct l2cap_chan *chan) __clear_retrans_timer(chan); } -void l2cap_do_send(struct l2cap_chan *chan, struct sk_buff *skb) +static void l2cap_do_send(struct l2cap_chan *chan, struct sk_buff *skb) { struct hci_conn *hcon = chan->conn->hcon; u16 flags; @@ -1256,7 +1261,7 @@ void l2cap_do_send(struct l2cap_chan *chan, struct sk_buff *skb) hci_send_acl(hcon, skb, flags); } -void l2cap_streaming_send(struct l2cap_chan *chan) +static void l2cap_streaming_send(struct l2cap_chan *chan) { struct sk_buff *skb; u16 control, fcs; @@ -1322,7 +1327,7 @@ static void l2cap_retransmit_one_frame(struct l2cap_chan *chan, u8 tx_seq) l2cap_do_send(chan, tx_skb); } -int l2cap_ertm_send(struct l2cap_chan *chan) +static int l2cap_ertm_send(struct l2cap_chan *chan) { struct sk_buff *skb, *tx_skb; u16 control, fcs; @@ -1460,7 +1465,7 @@ static inline int l2cap_skbuff_fromiovec(struct sock *sk, struct msghdr *msg, in return sent; } -struct sk_buff *l2cap_create_connless_pdu(struct l2cap_chan *chan, struct msghdr *msg, size_t len) +static struct sk_buff *l2cap_create_connless_pdu(struct l2cap_chan *chan, struct msghdr *msg, size_t len) { struct sock *sk = chan->sk; struct l2cap_conn *conn = chan->conn; @@ -1490,7 +1495,7 @@ struct sk_buff *l2cap_create_connless_pdu(struct l2cap_chan *chan, struct msghdr return skb; } -struct sk_buff *l2cap_create_basic_pdu(struct l2cap_chan *chan, struct msghdr *msg, size_t len) +static struct sk_buff *l2cap_create_basic_pdu(struct l2cap_chan *chan, struct msghdr *msg, size_t len) { struct sock *sk = chan->sk; struct l2cap_conn *conn = chan->conn; @@ -1519,7 +1524,9 @@ struct sk_buff *l2cap_create_basic_pdu(struct l2cap_chan *chan, struct msghdr *m return skb; } -struct sk_buff *l2cap_create_iframe_pdu(struct l2cap_chan *chan, struct msghdr *msg, size_t len, u16 control, u16 sdulen) +static struct sk_buff *l2cap_create_iframe_pdu(struct l2cap_chan *chan, + struct msghdr *msg, size_t len, + u16 control, u16 sdulen) { struct sock *sk = chan->sk; struct l2cap_conn *conn = chan->conn; @@ -1565,7 +1572,7 @@ struct sk_buff *l2cap_create_iframe_pdu(struct l2cap_chan *chan, struct msghdr * return skb; } -int l2cap_sar_segment_sdu(struct l2cap_chan *chan, struct msghdr *msg, size_t len) +static int l2cap_sar_segment_sdu(struct l2cap_chan *chan, struct msghdr *msg, size_t len) { struct sk_buff *skb; struct sk_buff_head sar_queue; @@ -3121,102 +3128,104 @@ static int l2cap_add_to_srej_queue(struct l2cap_chan *chan, struct sk_buff *skb, return 0; } -static int l2cap_ertm_reassembly_sdu(struct l2cap_chan *chan, struct sk_buff *skb, u16 control) +static void append_skb_frag(struct sk_buff *skb, + struct sk_buff *new_frag, struct sk_buff **last_frag) { - struct sk_buff *_skb; - int err; + /* skb->len reflects data in skb as well as all fragments + * skb->data_len reflects only data in fragments + */ + if (!skb_has_frag_list(skb)) + skb_shinfo(skb)->frag_list = new_frag; + + new_frag->next = NULL; + + (*last_frag)->next = new_frag; + *last_frag = new_frag; + + skb->len += new_frag->len; + skb->data_len += new_frag->len; + skb->truesize += new_frag->truesize; +} + +static int l2cap_reassemble_sdu(struct l2cap_chan *chan, struct sk_buff *skb, u16 control) +{ + int err = -EINVAL; switch (control & L2CAP_CTRL_SAR) { case L2CAP_SDU_UNSEGMENTED: - if (test_bit(CONN_SAR_SDU, &chan->conn_state)) - goto drop; + if (chan->sdu) + break; - return chan->ops->recv(chan->data, skb); + err = chan->ops->recv(chan->data, skb); + break; case L2CAP_SDU_START: - if (test_bit(CONN_SAR_SDU, &chan->conn_state)) - goto drop; + if (chan->sdu) + break; chan->sdu_len = get_unaligned_le16(skb->data); + skb_pull(skb, 2); - if (chan->sdu_len > chan->imtu) - goto disconnect; - - chan->sdu = bt_skb_alloc(chan->sdu_len, GFP_ATOMIC); - if (!chan->sdu) - return -ENOMEM; + if (chan->sdu_len > chan->imtu) { + err = -EMSGSIZE; + break; + } - /* pull sdu_len bytes only after alloc, because of Local Busy - * condition we have to be sure that this will be executed - * only once, i.e., when alloc does not fail */ - skb_pull(skb, 2); + if (skb->len >= chan->sdu_len) + break; - memcpy(skb_put(chan->sdu, skb->len), skb->data, skb->len); + chan->sdu = skb; + chan->sdu_last_frag = skb; - set_bit(CONN_SAR_SDU, &chan->conn_state); - chan->partial_sdu_len = skb->len; + skb = NULL; + err = 0; break; case L2CAP_SDU_CONTINUE: - if (!test_bit(CONN_SAR_SDU, &chan->conn_state)) - goto disconnect; - if (!chan->sdu) - goto disconnect; + break; - chan->partial_sdu_len += skb->len; - if (chan->partial_sdu_len > chan->sdu_len) - goto drop; + append_skb_frag(chan->sdu, skb, + &chan->sdu_last_frag); + skb = NULL; - memcpy(skb_put(chan->sdu, skb->len), skb->data, skb->len); + if (chan->sdu->len >= chan->sdu_len) + break; + err = 0; break; case L2CAP_SDU_END: - if (!test_bit(CONN_SAR_SDU, &chan->conn_state)) - goto disconnect; - if (!chan->sdu) - goto disconnect; - - chan->partial_sdu_len += skb->len; - - if (chan->partial_sdu_len > chan->imtu) - goto drop; + break; - if (chan->partial_sdu_len != chan->sdu_len) - goto drop; + append_skb_frag(chan->sdu, skb, + &chan->sdu_last_frag); + skb = NULL; - memcpy(skb_put(chan->sdu, skb->len), skb->data, skb->len); + if (chan->sdu->len != chan->sdu_len) + break; - _skb = skb_clone(chan->sdu, GFP_ATOMIC); - if (!_skb) { - return -ENOMEM; - } + err = chan->ops->recv(chan->data, chan->sdu); - err = chan->ops->recv(chan->data, _skb); - if (err < 0) { - kfree_skb(_skb); - return err; + if (!err) { + /* Reassembly complete */ + chan->sdu = NULL; + chan->sdu_last_frag = NULL; + chan->sdu_len = 0; } - - clear_bit(CONN_SAR_SDU, &chan->conn_state); - - kfree_skb(chan->sdu); break; } - kfree_skb(skb); - return 0; - -drop: - kfree_skb(chan->sdu); - chan->sdu = NULL; + if (err) { + kfree_skb(skb); + kfree_skb(chan->sdu); + chan->sdu = NULL; + chan->sdu_last_frag = NULL; + chan->sdu_len = 0; + } -disconnect: - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); - kfree_skb(skb); - return 0; + return err; } static void l2cap_ertm_enter_local_busy(struct l2cap_chan *chan) @@ -3270,99 +3279,6 @@ void l2cap_chan_busy(struct l2cap_chan *chan, int busy) } } -static int l2cap_streaming_reassembly_sdu(struct l2cap_chan *chan, struct sk_buff *skb, u16 control) -{ - struct sk_buff *_skb; - int err = -EINVAL; - - /* - * TODO: We have to notify the userland if some data is lost with the - * Streaming Mode. - */ - - switch (control & L2CAP_CTRL_SAR) { - case L2CAP_SDU_UNSEGMENTED: - if (test_bit(CONN_SAR_SDU, &chan->conn_state)) { - kfree_skb(chan->sdu); - break; - } - - err = chan->ops->recv(chan->data, skb); - if (!err) - return 0; - - break; - - case L2CAP_SDU_START: - if (test_bit(CONN_SAR_SDU, &chan->conn_state)) { - kfree_skb(chan->sdu); - break; - } - - chan->sdu_len = get_unaligned_le16(skb->data); - skb_pull(skb, 2); - - if (chan->sdu_len > chan->imtu) { - err = -EMSGSIZE; - break; - } - - chan->sdu = bt_skb_alloc(chan->sdu_len, GFP_ATOMIC); - if (!chan->sdu) { - err = -ENOMEM; - break; - } - - memcpy(skb_put(chan->sdu, skb->len), skb->data, skb->len); - - set_bit(CONN_SAR_SDU, &chan->conn_state); - chan->partial_sdu_len = skb->len; - err = 0; - break; - - case L2CAP_SDU_CONTINUE: - if (!test_bit(CONN_SAR_SDU, &chan->conn_state)) - break; - - memcpy(skb_put(chan->sdu, skb->len), skb->data, skb->len); - - chan->partial_sdu_len += skb->len; - if (chan->partial_sdu_len > chan->sdu_len) - kfree_skb(chan->sdu); - else - err = 0; - - break; - - case L2CAP_SDU_END: - if (!test_bit(CONN_SAR_SDU, &chan->conn_state)) - break; - - memcpy(skb_put(chan->sdu, skb->len), skb->data, skb->len); - - clear_bit(CONN_SAR_SDU, &chan->conn_state); - chan->partial_sdu_len += skb->len; - - if (chan->partial_sdu_len > chan->imtu) - goto drop; - - if (chan->partial_sdu_len == chan->sdu_len) { - _skb = skb_clone(chan->sdu, GFP_ATOMIC); - err = chan->ops->recv(chan->data, _skb); - if (err < 0) - kfree_skb(_skb); - } - err = 0; - -drop: - kfree_skb(chan->sdu); - break; - } - - kfree_skb(skb); - return err; -} - static void l2cap_check_srej_gap(struct l2cap_chan *chan, u8 tx_seq) { struct sk_buff *skb; @@ -3377,7 +3293,7 @@ static void l2cap_check_srej_gap(struct l2cap_chan *chan, u8 tx_seq) skb = skb_dequeue(&chan->srej_q); control = bt_cb(skb)->sar << L2CAP_CTRL_SAR_SHIFT; - err = l2cap_ertm_reassembly_sdu(chan, skb, control); + err = l2cap_reassemble_sdu(chan, skb, control); if (err < 0) { l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); @@ -3537,7 +3453,7 @@ expected: return 0; } - err = l2cap_ertm_reassembly_sdu(chan, skb, rx_control); + err = l2cap_reassemble_sdu(chan, skb, rx_control); chan->buffer_seq = (chan->buffer_seq + 1) % 64; if (err < 0) { l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); @@ -3853,12 +3769,20 @@ static inline int l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk tx_seq = __get_txseq(control); - if (chan->expected_tx_seq == tx_seq) - chan->expected_tx_seq = (chan->expected_tx_seq + 1) % 64; - else - chan->expected_tx_seq = (tx_seq + 1) % 64; + if (chan->expected_tx_seq != tx_seq) { + /* Frame(s) missing - must discard partial SDU */ + kfree_skb(chan->sdu); + chan->sdu = NULL; + chan->sdu_last_frag = NULL; + chan->sdu_len = 0; + + /* TODO: Notify userland of missing data */ + } + + chan->expected_tx_seq = (tx_seq + 1) % 64; - l2cap_streaming_reassembly_sdu(chan, skb, control); + if (l2cap_reassemble_sdu(chan, skb, control) == -EMSGSIZE) + l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); goto done; @@ -4093,6 +4017,11 @@ static int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) BT_DBG("conn %p", conn); + if (hcon->type == LE_LINK) { + smp_distribute_keys(conn, 0); + del_timer(&conn->security_timer); + } + read_lock(&conn->chan_lock); list_for_each_entry(chan, &conn->chan_l, list) { @@ -4105,9 +4034,7 @@ static int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) if (chan->scid == L2CAP_CID_LE_DATA) { if (!status && encrypt) { chan->sec_level = hcon->sec_level; - del_timer(&conn->security_timer); l2cap_chan_ready(sk); - smp_distribute_keys(conn, 0); } bh_unlock_sock(sk); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 61f1f62..e829236 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -26,6 +26,8 @@ /* Bluetooth L2CAP sockets. */ +#include <linux/security.h> + #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> @@ -933,6 +935,8 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) chan->force_reliable = pchan->force_reliable; chan->flushable = pchan->flushable; chan->force_active = pchan->force_active; + + security_sk_clone(parent, sk); } else { switch (sk->sk_type) { diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 53e109e..5a94eec 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -908,7 +908,7 @@ static int load_keys(struct sock *sk, u16 index, unsigned char *data, u16 len) struct hci_dev *hdev; struct mgmt_cp_load_keys *cp; u16 key_count, expected_len; - int i, err; + int i; cp = (void *) data; @@ -918,9 +918,9 @@ static int load_keys(struct sock *sk, u16 index, unsigned char *data, u16 len) key_count = get_unaligned_le16(&cp->key_count); expected_len = sizeof(*cp) + key_count * sizeof(struct mgmt_key_info); - if (expected_len > len) { - BT_ERR("load_keys: expected at least %u bytes, got %u bytes", - expected_len, len); + if (expected_len != len) { + BT_ERR("load_keys: expected %u bytes, got %u bytes", + len, expected_len); return -EINVAL; } @@ -942,36 +942,17 @@ static int load_keys(struct sock *sk, u16 index, unsigned char *data, u16 len) else clear_bit(HCI_DEBUG_KEYS, &hdev->flags); - len -= sizeof(*cp); - i = 0; - - while (i < len) { - struct mgmt_key_info *key = (void *) cp->keys + i; - - i += sizeof(*key) + key->dlen; - - if (key->type == HCI_LK_SMP_LTK) { - struct key_master_id *id = (void *) key->data; - - if (key->dlen != sizeof(struct key_master_id)) - continue; - - hci_add_ltk(hdev, 0, &key->bdaddr, key->pin_len, - id->ediv, id->rand, key->val); - - continue; - } + for (i = 0; i < key_count; i++) { + struct mgmt_key_info *key = &cp->keys[i]; hci_add_link_key(hdev, NULL, 0, &key->bdaddr, key->val, key->type, key->pin_len); } - err = cmd_complete(sk, index, MGMT_OP_LOAD_KEYS, NULL, 0); - hci_dev_unlock_bh(hdev); hci_dev_put(hdev); - return err; + return 0; } static int remove_key(struct sock *sk, u16 index, unsigned char *data, u16 len) @@ -1347,6 +1328,7 @@ static int pair_device(struct sock *sk, u16 index, unsigned char *data, u16 len) struct hci_dev *hdev; struct mgmt_cp_pair_device *cp; struct pending_cmd *cmd; + struct adv_entry *entry; u8 sec_level, auth_type; struct hci_conn *conn; int err; @@ -1364,15 +1346,20 @@ static int pair_device(struct sock *sk, u16 index, unsigned char *data, u16 len) hci_dev_lock_bh(hdev); - if (cp->io_cap == 0x03) { - sec_level = BT_SECURITY_MEDIUM; + sec_level = BT_SECURITY_MEDIUM; + if (cp->io_cap == 0x03) auth_type = HCI_AT_DEDICATED_BONDING; - } else { - sec_level = BT_SECURITY_HIGH; + else auth_type = HCI_AT_DEDICATED_BONDING_MITM; - } - conn = hci_connect(hdev, ACL_LINK, &cp->bdaddr, sec_level, auth_type); + entry = hci_find_adv_entry(hdev, &cp->bdaddr); + if (entry) + conn = hci_connect(hdev, LE_LINK, &cp->bdaddr, sec_level, + auth_type); + else + conn = hci_connect(hdev, ACL_LINK, &cp->bdaddr, sec_level, + auth_type); + if (IS_ERR(conn)) { err = PTR_ERR(conn); goto unlock; @@ -1391,7 +1378,10 @@ static int pair_device(struct sock *sk, u16 index, unsigned char *data, u16 len) goto unlock; } - conn->connect_cfm_cb = pairing_complete_cb; + /* For LE, just connecting isn't a proof that the pairing finished */ + if (!entry) + conn->connect_cfm_cb = pairing_complete_cb; + conn->security_cfm_cb = pairing_complete_cb; conn->disconn_cfm_cb = pairing_complete_cb; conn->io_capability = cp->io_cap; @@ -1689,13 +1679,12 @@ static int block_device(struct sock *sk, u16 index, unsigned char *data, u16 len) { struct hci_dev *hdev; - struct mgmt_cp_block_device *cp; + struct pending_cmd *cmd; + struct mgmt_cp_block_device *cp = (void *) data; int err; BT_DBG("hci%u", index); - cp = (void *) data; - if (len != sizeof(*cp)) return cmd_status(sk, index, MGMT_OP_BLOCK_DEVICE, EINVAL); @@ -1705,6 +1694,14 @@ static int block_device(struct sock *sk, u16 index, unsigned char *data, return cmd_status(sk, index, MGMT_OP_BLOCK_DEVICE, ENODEV); + hci_dev_lock_bh(hdev); + + cmd = mgmt_pending_add(sk, MGMT_OP_BLOCK_DEVICE, index, NULL, 0); + if (!cmd) { + err = -ENOMEM; + goto failed; + } + err = hci_blacklist_add(hdev, &cp->bdaddr); if (err < 0) @@ -1712,6 +1709,11 @@ static int block_device(struct sock *sk, u16 index, unsigned char *data, else err = cmd_complete(sk, index, MGMT_OP_BLOCK_DEVICE, NULL, 0); + + mgmt_pending_remove(cmd); + +failed: + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -1721,13 +1723,12 @@ static int unblock_device(struct sock *sk, u16 index, unsigned char *data, u16 len) { struct hci_dev *hdev; - struct mgmt_cp_unblock_device *cp; + struct pending_cmd *cmd; + struct mgmt_cp_unblock_device *cp = (void *) data; int err; BT_DBG("hci%u", index); - cp = (void *) data; - if (len != sizeof(*cp)) return cmd_status(sk, index, MGMT_OP_UNBLOCK_DEVICE, EINVAL); @@ -1737,6 +1738,14 @@ static int unblock_device(struct sock *sk, u16 index, unsigned char *data, return cmd_status(sk, index, MGMT_OP_UNBLOCK_DEVICE, ENODEV); + hci_dev_lock_bh(hdev); + + cmd = mgmt_pending_add(sk, MGMT_OP_UNBLOCK_DEVICE, index, NULL, 0); + if (!cmd) { + err = -ENOMEM; + goto failed; + } + err = hci_blacklist_del(hdev, &cp->bdaddr); if (err < 0) @@ -1744,6 +1753,67 @@ static int unblock_device(struct sock *sk, u16 index, unsigned char *data, else err = cmd_complete(sk, index, MGMT_OP_UNBLOCK_DEVICE, NULL, 0); + + mgmt_pending_remove(cmd); + +failed: + hci_dev_unlock_bh(hdev); + hci_dev_put(hdev); + + return err; +} + +static int set_fast_connectable(struct sock *sk, u16 index, + unsigned char *data, u16 len) +{ + struct hci_dev *hdev; + struct mgmt_cp_set_fast_connectable *cp = (void *) data; + struct hci_cp_write_page_scan_activity acp; + u8 type; + int err; + + BT_DBG("hci%u", index); + + if (len != sizeof(*cp)) + return cmd_status(sk, index, MGMT_OP_SET_FAST_CONNECTABLE, + EINVAL); + + hdev = hci_dev_get(index); + if (!hdev) + return cmd_status(sk, index, MGMT_OP_SET_FAST_CONNECTABLE, + ENODEV); + + hci_dev_lock(hdev); + + if (cp->enable) { + type = PAGE_SCAN_TYPE_INTERLACED; + acp.interval = 0x0024; /* 22.5 msec page scan interval */ + } else { + type = PAGE_SCAN_TYPE_STANDARD; /* default */ + acp.interval = 0x0800; /* default 1.28 sec page scan */ + } + + acp.window = 0x0012; /* default 11.25 msec page scan window */ + + err = hci_send_cmd(hdev, HCI_OP_WRITE_PAGE_SCAN_ACTIVITY, + sizeof(acp), &acp); + if (err < 0) { + err = cmd_status(sk, index, MGMT_OP_SET_FAST_CONNECTABLE, + -err); + goto done; + } + + err = hci_send_cmd(hdev, HCI_OP_WRITE_PAGE_SCAN_TYPE, 1, &type); + if (err < 0) { + err = cmd_status(sk, index, MGMT_OP_SET_FAST_CONNECTABLE, + -err); + goto done; + } + + err = cmd_complete(sk, index, MGMT_OP_SET_FAST_CONNECTABLE, + NULL, 0); +done: + hci_dev_unlock(hdev); hci_dev_put(hdev); return err; @@ -1869,6 +1939,10 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen) case MGMT_OP_UNBLOCK_DEVICE: err = unblock_device(sk, index, buf + sizeof(*hdr), len); break; + case MGMT_OP_SET_FAST_CONNECTABLE: + err = set_fast_connectable(sk, index, buf + sizeof(*hdr), + len); + break; default: BT_DBG("Unknown op %u", opcode); err = cmd_status(sk, index, opcode, 0x01); @@ -1977,35 +2051,25 @@ int mgmt_connectable(u16 index, u8 connectable) int mgmt_new_key(u16 index, struct link_key *key, u8 persistent) { - struct mgmt_ev_new_key *ev; - int err, total; - - total = sizeof(struct mgmt_ev_new_key) + key->dlen; - ev = kzalloc(total, GFP_ATOMIC); - if (!ev) - return -ENOMEM; - - bacpy(&ev->key.bdaddr, &key->bdaddr); - ev->key.type = key->type; - memcpy(ev->key.val, key->val, 16); - ev->key.pin_len = key->pin_len; - ev->key.dlen = key->dlen; - ev->store_hint = persistent; + struct mgmt_ev_new_key ev; - memcpy(ev->key.data, key->data, key->dlen); - - err = mgmt_event(MGMT_EV_NEW_KEY, index, ev, total, NULL); + memset(&ev, 0, sizeof(ev)); - kfree(ev); + ev.store_hint = persistent; + bacpy(&ev.key.bdaddr, &key->bdaddr); + ev.key.type = key->type; + memcpy(ev.key.val, key->val, 16); + ev.key.pin_len = key->pin_len; - return err; + return mgmt_event(MGMT_EV_NEW_KEY, index, &ev, sizeof(ev), NULL); } -int mgmt_connected(u16 index, bdaddr_t *bdaddr) +int mgmt_connected(u16 index, bdaddr_t *bdaddr, u8 link_type) { struct mgmt_ev_connected ev; bacpy(&ev.bdaddr, bdaddr); + ev.link_type = link_type; return mgmt_event(MGMT_EV_CONNECTED, index, &ev, sizeof(ev), NULL); } @@ -2260,12 +2324,14 @@ int mgmt_device_found(u16 index, bdaddr_t *bdaddr, u8 *dev_class, s8 rssi, memset(&ev, 0, sizeof(ev)); bacpy(&ev.bdaddr, bdaddr); - memcpy(ev.dev_class, dev_class, sizeof(ev.dev_class)); ev.rssi = rssi; if (eir) memcpy(ev.eir, eir, sizeof(ev.eir)); + if (dev_class) + memcpy(ev.dev_class, dev_class, sizeof(ev.dev_class)); + return mgmt_event(MGMT_EV_DEVICE_FOUND, index, &ev, sizeof(ev), NULL); } @@ -2286,3 +2352,29 @@ int mgmt_discovering(u16 index, u8 discovering) return mgmt_event(MGMT_EV_DISCOVERING, index, &discovering, sizeof(discovering), NULL); } + +int mgmt_device_blocked(u16 index, bdaddr_t *bdaddr) +{ + struct pending_cmd *cmd; + struct mgmt_ev_device_blocked ev; + + cmd = mgmt_pending_find(MGMT_OP_BLOCK_DEVICE, index); + + bacpy(&ev.bdaddr, bdaddr); + + return mgmt_event(MGMT_EV_DEVICE_BLOCKED, index, &ev, sizeof(ev), + cmd ? cmd->sk : NULL); +} + +int mgmt_device_unblocked(u16 index, bdaddr_t *bdaddr) +{ + struct pending_cmd *cmd; + struct mgmt_ev_device_unblocked ev; + + cmd = mgmt_pending_find(MGMT_OP_UNBLOCK_DEVICE, index); + + bacpy(&ev.bdaddr, bdaddr); + + return mgmt_event(MGMT_EV_DEVICE_UNBLOCKED, index, &ev, sizeof(ev), + cmd ? cmd->sk : NULL); +} diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 5ba3f6d..38b618c 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1853,7 +1853,10 @@ static inline void rfcomm_process_rx(struct rfcomm_session *s) /* Get data directly from socket receive queue without copying it. */ while ((skb = skb_dequeue(&sk->sk_receive_queue))) { skb_orphan(skb); - rfcomm_recv_frame(s, skb); + if (!skb_linearize(skb)) + rfcomm_recv_frame(s, skb); + else + kfree_skb(skb); } if (sk->sk_state == BT_CLOSED) { diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 482722b..5417f61 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -42,6 +42,7 @@ #include <linux/device.h> #include <linux/debugfs.h> #include <linux/seq_file.h> +#include <linux/security.h> #include <net/sock.h> #include <asm/system.h> @@ -264,6 +265,8 @@ static void rfcomm_sock_init(struct sock *sk, struct sock *parent) pi->sec_level = rfcomm_pi(parent)->sec_level; pi->role_switch = rfcomm_pi(parent)->role_switch; + + security_sk_clone(parent, sk); } else { pi->dlc->defer_setup = 0; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 8270f05..a324b00 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -41,6 +41,7 @@ #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/list.h> +#include <linux/security.h> #include <net/sock.h> #include <asm/system.h> @@ -403,8 +404,10 @@ static void sco_sock_init(struct sock *sk, struct sock *parent) { BT_DBG("sk %p", sk); - if (parent) + if (parent) { sk->sk_type = parent->sk_type; + security_sk_clone(parent, sk); + } } static struct proto sco_proto = { diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 391888b..759b635 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -182,18 +182,9 @@ static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data) return; hci_send_acl(conn->hcon, skb, 0); -} - -static __u8 seclevel_to_authreq(__u8 level) -{ - switch (level) { - case BT_SECURITY_HIGH: - /* Right now we don't support bonding */ - return SMP_AUTH_MITM; - default: - return SMP_AUTH_NONE; - } + mod_timer(&conn->security_timer, jiffies + + msecs_to_jiffies(SMP_TIMEOUT)); } static void build_pairing_cmd(struct l2cap_conn *conn, @@ -205,7 +196,7 @@ static void build_pairing_cmd(struct l2cap_conn *conn, dist_keys = 0; if (test_bit(HCI_PAIRABLE, &conn->hcon->hdev->flags)) { - dist_keys = SMP_DIST_ENC_KEY | SMP_DIST_ID_KEY | SMP_DIST_SIGN; + dist_keys = SMP_DIST_ENC_KEY; authreq |= SMP_AUTH_BONDING; } @@ -229,24 +220,184 @@ static void build_pairing_cmd(struct l2cap_conn *conn, static u8 check_enc_key_size(struct l2cap_conn *conn, __u8 max_key_size) { + struct smp_chan *smp = conn->smp_chan; + if ((max_key_size > SMP_MAX_ENC_KEY_SIZE) || (max_key_size < SMP_MIN_ENC_KEY_SIZE)) return SMP_ENC_KEY_SIZE; - conn->smp_key_size = max_key_size; + smp->smp_key_size = max_key_size; return 0; } +static void confirm_work(struct work_struct *work) +{ + struct smp_chan *smp = container_of(work, struct smp_chan, confirm); + struct l2cap_conn *conn = smp->conn; + struct crypto_blkcipher *tfm; + struct smp_cmd_pairing_confirm cp; + int ret; + u8 res[16], reason; + + BT_DBG("conn %p", conn); + + tfm = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(tfm)) { + reason = SMP_UNSPECIFIED; + goto error; + } + + smp->tfm = tfm; + + if (conn->hcon->out) + ret = smp_c1(tfm, smp->tk, smp->prnd, smp->preq, smp->prsp, 0, + conn->src, conn->hcon->dst_type, conn->dst, + res); + else + ret = smp_c1(tfm, smp->tk, smp->prnd, smp->preq, smp->prsp, + conn->hcon->dst_type, conn->dst, 0, conn->src, + res); + if (ret) { + reason = SMP_UNSPECIFIED; + goto error; + } + + swap128(res, cp.confirm_val); + smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp); + + return; + +error: + smp_send_cmd(conn, SMP_CMD_PAIRING_FAIL, sizeof(reason), &reason); + smp_chan_destroy(conn); +} + +static void random_work(struct work_struct *work) +{ + struct smp_chan *smp = container_of(work, struct smp_chan, random); + struct l2cap_conn *conn = smp->conn; + struct hci_conn *hcon = conn->hcon; + struct crypto_blkcipher *tfm = smp->tfm; + u8 reason, confirm[16], res[16], key[16]; + int ret; + + if (IS_ERR_OR_NULL(tfm)) { + reason = SMP_UNSPECIFIED; + goto error; + } + + BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave"); + + if (hcon->out) + ret = smp_c1(tfm, smp->tk, smp->rrnd, smp->preq, smp->prsp, 0, + conn->src, hcon->dst_type, conn->dst, + res); + else + ret = smp_c1(tfm, smp->tk, smp->rrnd, smp->preq, smp->prsp, + hcon->dst_type, conn->dst, 0, conn->src, + res); + if (ret) { + reason = SMP_UNSPECIFIED; + goto error; + } + + swap128(res, confirm); + + if (memcmp(smp->pcnf, confirm, sizeof(smp->pcnf)) != 0) { + BT_ERR("Pairing failed (confirmation values mismatch)"); + reason = SMP_CONFIRM_FAILED; + goto error; + } + + if (hcon->out) { + u8 stk[16], rand[8]; + __le16 ediv; + + memset(rand, 0, sizeof(rand)); + ediv = 0; + + smp_s1(tfm, smp->tk, smp->rrnd, smp->prnd, key); + swap128(key, stk); + + memset(stk + smp->smp_key_size, 0, + SMP_MAX_ENC_KEY_SIZE - smp->smp_key_size); + + if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &hcon->pend)) { + reason = SMP_UNSPECIFIED; + goto error; + } + + hci_le_start_enc(hcon, ediv, rand, stk); + hcon->enc_key_size = smp->smp_key_size; + } else { + u8 stk[16], r[16], rand[8]; + __le16 ediv; + + memset(rand, 0, sizeof(rand)); + ediv = 0; + + swap128(smp->prnd, r); + smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(r), r); + + smp_s1(tfm, smp->tk, smp->prnd, smp->rrnd, key); + swap128(key, stk); + + memset(stk + smp->smp_key_size, 0, + SMP_MAX_ENC_KEY_SIZE - smp->smp_key_size); + + hci_add_ltk(hcon->hdev, 0, conn->dst, smp->smp_key_size, + ediv, rand, stk); + } + + return; + +error: + smp_send_cmd(conn, SMP_CMD_PAIRING_FAIL, sizeof(reason), &reason); + smp_chan_destroy(conn); +} + +static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) +{ + struct smp_chan *smp; + + smp = kzalloc(sizeof(struct smp_chan), GFP_ATOMIC); + if (!smp) + return NULL; + + INIT_WORK(&smp->confirm, confirm_work); + INIT_WORK(&smp->random, random_work); + + smp->conn = conn; + conn->smp_chan = smp; + + hci_conn_hold(conn->hcon); + + return smp; +} + +void smp_chan_destroy(struct l2cap_conn *conn) +{ + kfree(conn->smp_chan); + hci_conn_put(conn->hcon); +} + static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_cmd_pairing rsp, *req = (void *) skb->data; + struct smp_chan *smp; u8 key_size; + int ret; BT_DBG("conn %p", conn); - conn->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&conn->preq[1], req, sizeof(*req)); + if (!test_and_set_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->pend)) + smp = smp_chan_create(conn); + + smp = conn->smp_chan; + + smp->preq[0] = SMP_CMD_PAIRING_REQ; + memcpy(&smp->preq[1], req, sizeof(*req)); skb_pull(skb, sizeof(*req)); if (req->oob_flag) @@ -260,32 +411,33 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) return SMP_ENC_KEY_SIZE; /* Just works */ - memset(conn->tk, 0, sizeof(conn->tk)); + memset(smp->tk, 0, sizeof(smp->tk)); + + ret = smp_rand(smp->prnd); + if (ret) + return SMP_UNSPECIFIED; - conn->prsp[0] = SMP_CMD_PAIRING_RSP; - memcpy(&conn->prsp[1], &rsp, sizeof(rsp)); + smp->prsp[0] = SMP_CMD_PAIRING_RSP; + memcpy(&smp->prsp[1], &rsp, sizeof(rsp)); smp_send_cmd(conn, SMP_CMD_PAIRING_RSP, sizeof(rsp), &rsp); - mod_timer(&conn->security_timer, jiffies + - msecs_to_jiffies(SMP_TIMEOUT)); - return 0; } static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_cmd_pairing *req, *rsp = (void *) skb->data; - struct smp_cmd_pairing_confirm cp; - struct crypto_blkcipher *tfm = conn->hcon->hdev->tfm; + struct smp_chan *smp = conn->smp_chan; + struct hci_dev *hdev = conn->hcon->hdev; + u8 key_size; int ret; - u8 res[16], key_size; BT_DBG("conn %p", conn); skb_pull(skb, sizeof(*rsp)); - req = (void *) &conn->preq[1]; + req = (void *) &smp->preq[1]; key_size = min(req->max_key_size, rsp->max_key_size); if (check_enc_key_size(conn, key_size)) @@ -295,222 +447,154 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) return SMP_OOB_NOT_AVAIL; /* Just works */ - memset(conn->tk, 0, sizeof(conn->tk)); - - conn->prsp[0] = SMP_CMD_PAIRING_RSP; - memcpy(&conn->prsp[1], rsp, sizeof(*rsp)); - - ret = smp_rand(conn->prnd); - if (ret) - return SMP_UNSPECIFIED; + memset(smp->tk, 0, sizeof(smp->tk)); - ret = smp_c1(tfm, conn->tk, conn->prnd, conn->preq, conn->prsp, 0, - conn->src, conn->hcon->dst_type, conn->dst, res); + ret = smp_rand(smp->prnd); if (ret) return SMP_UNSPECIFIED; - swap128(res, cp.confirm_val); + smp->prsp[0] = SMP_CMD_PAIRING_RSP; + memcpy(&smp->prsp[1], rsp, sizeof(*rsp)); - smp_send_cmd(conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp); + queue_work(hdev->workqueue, &smp->confirm); return 0; } static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) { - struct crypto_blkcipher *tfm = conn->hcon->hdev->tfm; + struct smp_chan *smp = conn->smp_chan; + struct hci_dev *hdev = conn->hcon->hdev; BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave"); - memcpy(conn->pcnf, skb->data, sizeof(conn->pcnf)); - skb_pull(skb, sizeof(conn->pcnf)); + memcpy(smp->pcnf, skb->data, sizeof(smp->pcnf)); + skb_pull(skb, sizeof(smp->pcnf)); if (conn->hcon->out) { u8 random[16]; - swap128(conn->prnd, random); + swap128(smp->prnd, random); smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(random), random); } else { - struct smp_cmd_pairing_confirm cp; - int ret; - u8 res[16]; - - ret = smp_rand(conn->prnd); - if (ret) - return SMP_UNSPECIFIED; - - ret = smp_c1(tfm, conn->tk, conn->prnd, conn->preq, conn->prsp, - conn->hcon->dst_type, conn->dst, - 0, conn->src, res); - if (ret) - return SMP_CONFIRM_FAILED; - - swap128(res, cp.confirm_val); - - smp_send_cmd(conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp); + queue_work(hdev->workqueue, &smp->confirm); } - mod_timer(&conn->security_timer, jiffies + - msecs_to_jiffies(SMP_TIMEOUT)); - return 0; } static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) { - struct hci_conn *hcon = conn->hcon; - struct crypto_blkcipher *tfm = hcon->hdev->tfm; - int ret; - u8 key[16], res[16], random[16], confirm[16]; + struct smp_chan *smp = conn->smp_chan; + struct hci_dev *hdev = conn->hcon->hdev; - swap128(skb->data, random); - skb_pull(skb, sizeof(random)); - - if (conn->hcon->out) - ret = smp_c1(tfm, conn->tk, random, conn->preq, conn->prsp, 0, - conn->src, conn->hcon->dst_type, conn->dst, - res); - else - ret = smp_c1(tfm, conn->tk, random, conn->preq, conn->prsp, - conn->hcon->dst_type, conn->dst, 0, conn->src, - res); - if (ret) - return SMP_UNSPECIFIED; - - BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave"); - - swap128(res, confirm); - - if (memcmp(conn->pcnf, confirm, sizeof(conn->pcnf)) != 0) { - BT_ERR("Pairing failed (confirmation values mismatch)"); - return SMP_CONFIRM_FAILED; - } - - if (conn->hcon->out) { - u8 stk[16], rand[8]; - __le16 ediv; - - memset(rand, 0, sizeof(rand)); - ediv = 0; + BT_DBG("conn %p", conn); - smp_s1(tfm, conn->tk, random, conn->prnd, key); - swap128(key, stk); + swap128(skb->data, smp->rrnd); + skb_pull(skb, sizeof(smp->rrnd)); - memset(stk + conn->smp_key_size, 0, - SMP_MAX_ENC_KEY_SIZE - conn->smp_key_size); + queue_work(hdev->workqueue, &smp->random); - hci_le_start_enc(hcon, ediv, rand, stk); - hcon->enc_key_size = conn->smp_key_size; - } else { - u8 stk[16], r[16], rand[8]; - __le16 ediv; + return 0; +} - memset(rand, 0, sizeof(rand)); - ediv = 0; +static u8 smp_ltk_encrypt(struct l2cap_conn *conn) +{ + struct link_key *key; + struct key_master_id *master; + struct hci_conn *hcon = conn->hcon; - swap128(conn->prnd, r); - smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(r), r); + key = hci_find_link_key_type(hcon->hdev, conn->dst, + HCI_LK_SMP_LTK); + if (!key) + return 0; - smp_s1(tfm, conn->tk, conn->prnd, random, key); - swap128(key, stk); + if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, + &hcon->pend)) + return 1; - memset(stk + conn->smp_key_size, 0, - SMP_MAX_ENC_KEY_SIZE - conn->smp_key_size); + master = (void *) key->data; + hci_le_start_enc(hcon, master->ediv, master->rand, + key->val); + hcon->enc_key_size = key->pin_len; - hci_add_ltk(conn->hcon->hdev, 0, conn->dst, conn->smp_key_size, - ediv, rand, stk); - } + return 1; - return 0; } - static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_cmd_security_req *rp = (void *) skb->data; struct smp_cmd_pairing cp; struct hci_conn *hcon = conn->hcon; + struct smp_chan *smp; BT_DBG("conn %p", conn); - if (test_bit(HCI_CONN_ENCRYPT_PEND, &hcon->pend)) + hcon->pending_sec_level = BT_SECURITY_MEDIUM; + + if (smp_ltk_encrypt(conn)) return 0; + if (test_and_set_bit(HCI_CONN_LE_SMP_PEND, &hcon->pend)) + return 0; + + smp = smp_chan_create(conn); + skb_pull(skb, sizeof(*rp)); memset(&cp, 0, sizeof(cp)); build_pairing_cmd(conn, &cp, NULL, rp->auth_req); - conn->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&conn->preq[1], &cp, sizeof(cp)); + smp->preq[0] = SMP_CMD_PAIRING_REQ; + memcpy(&smp->preq[1], &cp, sizeof(cp)); smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - mod_timer(&conn->security_timer, jiffies + - msecs_to_jiffies(SMP_TIMEOUT)); - - set_bit(HCI_CONN_ENCRYPT_PEND, &hcon->pend); - return 0; } int smp_conn_security(struct l2cap_conn *conn, __u8 sec_level) { struct hci_conn *hcon = conn->hcon; - __u8 authreq; + struct smp_chan *smp = conn->smp_chan; BT_DBG("conn %p hcon %p level 0x%2.2x", conn, hcon, sec_level); if (!lmp_host_le_capable(hcon->hdev)) return 1; - if (IS_ERR(hcon->hdev->tfm)) - return 1; - - if (test_bit(HCI_CONN_ENCRYPT_PEND, &hcon->pend)) - return 0; - if (sec_level == BT_SECURITY_LOW) return 1; if (hcon->sec_level >= sec_level) return 1; - authreq = seclevel_to_authreq(sec_level); - - if (hcon->link_mode & HCI_LM_MASTER) { - struct smp_cmd_pairing cp; - struct link_key *key; + if (hcon->link_mode & HCI_LM_MASTER) + if (smp_ltk_encrypt(conn)) + goto done; - key = hci_find_link_key_type(hcon->hdev, conn->dst, - HCI_LK_SMP_LTK); - if (key) { - struct key_master_id *master = (void *) key->data; + if (test_and_set_bit(HCI_CONN_LE_SMP_PEND, &hcon->pend)) + return 0; - hci_le_start_enc(hcon, master->ediv, master->rand, - key->val); - hcon->enc_key_size = key->pin_len; + smp = smp_chan_create(conn); - goto done; - } - - build_pairing_cmd(conn, &cp, NULL, authreq); - conn->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&conn->preq[1], &cp, sizeof(cp)); + if (hcon->link_mode & HCI_LM_MASTER) { + struct smp_cmd_pairing cp; - mod_timer(&conn->security_timer, jiffies + - msecs_to_jiffies(SMP_TIMEOUT)); + build_pairing_cmd(conn, &cp, NULL, SMP_AUTH_NONE); + smp->preq[0] = SMP_CMD_PAIRING_REQ; + memcpy(&smp->preq[1], &cp, sizeof(cp)); smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); } else { struct smp_cmd_security_req cp; - cp.auth_req = authreq; + cp.auth_req = SMP_AUTH_NONE; smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); } done: hcon->pending_sec_level = sec_level; - set_bit(HCI_CONN_ENCRYPT_PEND, &hcon->pend); return 0; } @@ -518,10 +602,11 @@ done: static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_cmd_encrypt_info *rp = (void *) skb->data; + struct smp_chan *smp = conn->smp_chan; skb_pull(skb, sizeof(*rp)); - memcpy(conn->tk, rp->ltk, sizeof(conn->tk)); + memcpy(smp->tk, rp->ltk, sizeof(smp->tk)); return 0; } @@ -529,11 +614,12 @@ static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb) static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_cmd_master_ident *rp = (void *) skb->data; + struct smp_chan *smp = conn->smp_chan; skb_pull(skb, sizeof(*rp)); - hci_add_ltk(conn->hcon->hdev, 1, conn->src, conn->smp_key_size, - rp->ediv, rp->rand, conn->tk); + hci_add_ltk(conn->hcon->hdev, 1, conn->src, smp->smp_key_size, + rp->ediv, rp->rand, smp->tk); smp_distribute_keys(conn, 1); @@ -552,12 +638,6 @@ int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb) goto done; } - if (IS_ERR(conn->hcon->hdev->tfm)) { - err = PTR_ERR(conn->hcon->hdev->tfm); - reason = SMP_PAIRING_NOTSUPP; - goto done; - } - skb_pull(skb, sizeof(code)); switch (code) { @@ -621,20 +701,21 @@ done: int smp_distribute_keys(struct l2cap_conn *conn, __u8 force) { struct smp_cmd_pairing *req, *rsp; + struct smp_chan *smp = conn->smp_chan; __u8 *keydist; BT_DBG("conn %p force %d", conn, force); - if (IS_ERR(conn->hcon->hdev->tfm)) - return PTR_ERR(conn->hcon->hdev->tfm); + if (!test_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->pend)) + return 0; - rsp = (void *) &conn->prsp[1]; + rsp = (void *) &smp->prsp[1]; /* The responder sends its keys first */ if (!force && conn->hcon->out && (rsp->resp_key_dist & 0x07)) return 0; - req = (void *) &conn->preq[1]; + req = (void *) &smp->preq[1]; if (conn->hcon->out) { keydist = &rsp->init_key_dist; @@ -658,7 +739,7 @@ int smp_distribute_keys(struct l2cap_conn *conn, __u8 force) smp_send_cmd(conn, SMP_CMD_ENCRYPT_INFO, sizeof(enc), &enc); - hci_add_ltk(conn->hcon->hdev, 1, conn->dst, conn->smp_key_size, + hci_add_ltk(conn->hcon->hdev, 1, conn->dst, smp->smp_key_size, ediv, ident.rand, enc.ltk); ident.ediv = cpu_to_le16(ediv); @@ -698,5 +779,11 @@ int smp_distribute_keys(struct l2cap_conn *conn, __u8 force) *keydist &= ~SMP_DIST_SIGN; } + if (conn->hcon->out || force) { + clear_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->pend); + del_timer(&conn->security_timer); + smp_chan_destroy(conn); + } + return 0; } diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 32b8f9f..feb77ea 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -91,7 +91,6 @@ static int br_dev_open(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); - netif_carrier_off(dev); netdev_update_features(dev); netif_start_queue(dev); br_stp_enable_bridge(br); @@ -108,8 +107,6 @@ static int br_dev_stop(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); - netif_carrier_off(dev); - br_stp_disable_bridge(br); br_multicast_stop(br); @@ -304,7 +301,7 @@ static const struct net_device_ops br_netdev_ops = { .ndo_start_xmit = br_dev_xmit, .ndo_get_stats64 = br_get_stats64, .ndo_set_mac_address = br_set_mac_address, - .ndo_set_multicast_list = br_dev_set_multicast_list, + .ndo_set_rx_mode = br_dev_set_multicast_list, .ndo_change_mtu = br_change_mtu, .ndo_do_ioctl = br_dev_ioctl, #ifdef CONFIG_NET_POLL_CONTROLLER @@ -361,6 +358,8 @@ void br_dev_setup(struct net_device *dev) memcpy(br->group_addr, br_group_address, ETH_ALEN); br->stp_enabled = BR_NO_STP; + br->group_fwd_mask = BR_GROUPFWD_DEFAULT; + br->designated_root = br->bridge_id; br->bridge_max_age = br->max_age = 20 * HZ; br->bridge_hello_time = br->hello_time = 2 * HZ; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 68def3b..c8e7861 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -558,19 +558,28 @@ skip: /* Create new static fdb entry */ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, - __u16 state) + __u16 state, __u16 flags) { struct net_bridge *br = source->br; struct hlist_head *head = &br->hash[br_mac_hash(addr)]; struct net_bridge_fdb_entry *fdb; fdb = fdb_find(head, addr); - if (fdb) - return -EEXIST; + if (fdb == NULL) { + if (!(flags & NLM_F_CREATE)) + return -ENOENT; - fdb = fdb_create(head, source, addr); - if (!fdb) - return -ENOMEM; + fdb = fdb_create(head, source, addr); + if (!fdb) + return -ENOMEM; + } else { + if (flags & NLM_F_EXCL) + return -EEXIST; + + if (flags & NLM_F_REPLACE) + fdb->updated = fdb->used = jiffies; + fdb->is_local = fdb->is_static = 0; + } if (state & NUD_PERMANENT) fdb->is_local = fdb->is_static = 1; @@ -626,7 +635,7 @@ int br_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) } spin_lock_bh(&p->br->hash_lock); - err = fdb_add_entry(p, addr, ndm->ndm_state); + err = fdb_add_entry(p, addr, ndm->ndm_state, nlh->nlmsg_flags); spin_unlock_bh(&p->br->hash_lock); return err; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index e738154..f603e5b 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -13,6 +13,7 @@ #include <linux/kernel.h> #include <linux/netdevice.h> +#include <linux/etherdevice.h> #include <linux/netpoll.h> #include <linux/ethtool.h> #include <linux/if_arp.h> @@ -33,20 +34,18 @@ */ static int port_cost(struct net_device *dev) { - if (dev->ethtool_ops && dev->ethtool_ops->get_settings) { - struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET, }; - - if (!dev_ethtool_get_settings(dev, &ecmd)) { - switch (ethtool_cmd_speed(&ecmd)) { - case SPEED_10000: - return 2; - case SPEED_1000: - return 4; - case SPEED_100: - return 19; - case SPEED_10: - return 100; - } + struct ethtool_cmd ecmd; + + if (!__ethtool_get_settings(dev, &ecmd)) { + switch (ethtool_cmd_speed(&ecmd)) { + case SPEED_10000: + return 2; + case SPEED_1000: + return 4; + case SPEED_100: + return 19; + case SPEED_10: + return 100; } } @@ -161,9 +160,10 @@ static void del_nbp(struct net_bridge_port *p) call_rcu(&p->rcu, destroy_nbp_rcu); } -/* called with RTNL */ -static void del_br(struct net_bridge *br, struct list_head *head) +/* Delete bridge device */ +void br_dev_delete(struct net_device *dev, struct list_head *head) { + struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p, *n; list_for_each_entry_safe(p, n, &br->port_list, list) { @@ -268,7 +268,7 @@ int br_del_bridge(struct net *net, const char *name) } else - del_br(netdev_priv(dev), NULL); + br_dev_delete(dev, NULL); rtnl_unlock(); return ret; @@ -324,7 +324,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) /* Don't allow bridging non-ethernet like devices */ if ((dev->flags & IFF_LOOPBACK) || - dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN) + dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN || + !is_valid_ether_addr(dev->dev_addr)) return -EINVAL; /* No bridging of bridges */ @@ -352,10 +353,6 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) err = kobject_init_and_add(&p->kobj, &brport_ktype, &(dev->dev.kobj), SYSFS_BRIDGE_PORT_ATTR); if (err) - goto err0; - - err = br_fdb_insert(br, p, dev->dev_addr); - if (err) goto err1; err = br_sysfs_addif(p); @@ -396,6 +393,9 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) dev_set_mtu(br->dev, br_min_mtu(br)); + if (br_fdb_insert(br, p, dev->dev_addr)) + netdev_err(dev, "failed insert local address bridge forwarding table\n"); + kobject_uevent(&p->kobj, KOBJ_ADD); return 0; @@ -405,11 +405,9 @@ err4: err3: sysfs_remove_link(br->ifobj, p->dev->name); err2: - br_fdb_delete_by_port(br, p, 1); -err1: kobject_put(&p->kobj); p = NULL; /* kobject_put frees */ -err0: +err1: dev_set_promiscuity(dev, -1); put_back: dev_put(dev); @@ -449,7 +447,7 @@ void __net_exit br_net_exit(struct net *net) rtnl_lock(); for_each_netdev(net, dev) if (dev->priv_flags & IFF_EBRIDGE) - del_br(netdev_priv(dev), &list); + br_dev_delete(dev, &list); unregister_netdevice_many(&list); rtnl_unlock(); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index f06ee39..6f9f8c0 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -162,14 +162,37 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) p = br_port_get_rcu(skb->dev); if (unlikely(is_link_local(dest))) { - /* Pause frames shouldn't be passed up by driver anyway */ - if (skb->protocol == htons(ETH_P_PAUSE)) + /* + * See IEEE 802.1D Table 7-10 Reserved addresses + * + * Assignment Value + * Bridge Group Address 01-80-C2-00-00-00 + * (MAC Control) 802.3 01-80-C2-00-00-01 + * (Link Aggregation) 802.3 01-80-C2-00-00-02 + * 802.1X PAE address 01-80-C2-00-00-03 + * + * 802.1AB LLDP 01-80-C2-00-00-0E + * + * Others reserved for future standardization + */ + switch (dest[5]) { + case 0x00: /* Bridge Group Address */ + /* If STP is turned off, + then must forward to keep loop detection */ + if (p->br->stp_enabled == BR_NO_STP) + goto forward; + break; + + case 0x01: /* IEEE MAC (Pause) */ goto drop; - /* If STP is turned off, then forward */ - if (p->br->stp_enabled == BR_NO_STP && dest[5] == 0) - goto forward; + default: + /* Allow selective forwarding for most other protocols */ + if (p->br->group_fwd_mask & (1u << dest[5])) + goto forward; + } + /* Deliver packet to local host only */ if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev, NULL, br_handle_local_finish)) { return RX_HANDLER_CONSUMED; /* consumed by filter */ diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 5b1ed1b..e5f9ece3 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -210,6 +210,7 @@ static struct rtnl_link_ops br_link_ops __read_mostly = { .priv_size = sizeof(struct net_bridge), .setup = br_dev_setup, .validate = br_validate, + .dellink = br_dev_delete, }; int __init br_netlink_init(void) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 78cc364..d7d6fb0 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -29,6 +29,11 @@ #define BR_VERSION "2.3" +/* Control of forwarding link local multicast */ +#define BR_GROUPFWD_DEFAULT 0 +/* Don't allow forwarding control protocols like STP and LLDP */ +#define BR_GROUPFWD_RESTRICTED 0x4007u + /* Path to usermode spanning tree program */ #define BR_STP_PROG "/sbin/bridge-stp" @@ -193,6 +198,8 @@ struct net_bridge unsigned long flags; #define BR_SET_MAC_ADDR 0x00000001 + u16 group_fwd_mask; + /* STP */ bridge_id designated_root; bridge_id bridge_id; @@ -294,6 +301,7 @@ static inline int br_is_root_bridge(const struct net_bridge *br) /* br_device.c */ extern void br_dev_setup(struct net_device *dev); +extern void br_dev_delete(struct net_device *dev, struct list_head *list); extern netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev); #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 68b893e..c236c0e 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -149,6 +149,39 @@ static ssize_t store_stp_state(struct device *d, static DEVICE_ATTR(stp_state, S_IRUGO | S_IWUSR, show_stp_state, store_stp_state); +static ssize_t show_group_fwd_mask(struct device *d, + struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%#x\n", br->group_fwd_mask); +} + + +static ssize_t store_group_fwd_mask(struct device *d, + struct device_attribute *attr, const char *buf, + size_t len) +{ + struct net_bridge *br = to_bridge(d); + char *endp; + unsigned long val; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + val = simple_strtoul(buf, &endp, 0); + if (endp == buf) + return -EINVAL; + + if (val & BR_GROUPFWD_RESTRICTED) + return -EINVAL; + + br->group_fwd_mask = val; + + return len; +} +static DEVICE_ATTR(group_fwd_mask, S_IRUGO | S_IWUSR, show_group_fwd_mask, + store_group_fwd_mask); + static ssize_t show_priority(struct device *d, struct device_attribute *attr, char *buf) { @@ -652,6 +685,7 @@ static struct attribute *bridge_attrs[] = { &dev_attr_max_age.attr, &dev_attr_ageing_time.attr, &dev_attr_stp_state.attr, + &dev_attr_group_fwd_mask.attr, &dev_attr_priority.attr, &dev_attr_bridge_id.attr, &dev_attr_root_id.attr, diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index bf2a333..5449294 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -102,16 +102,15 @@ static struct sk_buff *ulog_alloc_skb(unsigned int size) unsigned int n; n = max(size, nlbufsiz); - skb = alloc_skb(n, GFP_ATOMIC); + skb = alloc_skb(n, GFP_ATOMIC | __GFP_NOWARN); if (!skb) { - pr_debug("cannot alloc whole buffer of size %ub!\n", n); if (n > size) { /* try to allocate only as much as we need for * current packet */ skb = alloc_skb(size, GFP_ATOMIC); if (!skb) - pr_debug("cannot even allocate " - "buffer of size %ub\n", size); + pr_debug("cannot even allocate buffer of size %ub\n", + size); } } diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 1bcaf36..40d8258 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -87,14 +87,14 @@ static int __init ebtable_broute_init(void) if (ret < 0) return ret; /* see br_input.c */ - rcu_assign_pointer(br_should_route_hook, + RCU_INIT_POINTER(br_should_route_hook, (br_should_route_hook_t *)ebt_broute); return 0; } static void __exit ebtable_broute_fini(void) { - rcu_assign_pointer(br_should_route_hook, NULL); + RCU_INIT_POINTER(br_should_route_hook, NULL); synchronize_net(); unregister_pernet_subsys(&broute_net_ops); } diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 7f9ac07..47fc8f3 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -212,8 +212,7 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what, enum cfcnfg_phy_preference pref; enum cfcnfg_phy_type phy_type; struct cfcnfg *cfg; - struct caif_device_entry_list *caifdevs = - caif_device_list(dev_net(dev)); + struct caif_device_entry_list *caifdevs; if (dev->type != ARPHRD_CAIF) return 0; @@ -222,6 +221,8 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what, if (cfg == NULL) return 0; + caifdevs = caif_device_list(dev_net(dev)); + switch (what) { case NETDEV_REGISTER: caifd = caif_device_alloc(dev); diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index 52fe33b..00523ec 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -78,10 +78,8 @@ struct cfcnfg *cfcnfg_create(void) /* Initiate this layer */ this = kzalloc(sizeof(struct cfcnfg), GFP_ATOMIC); - if (!this) { - pr_warn("Out of memory\n"); + if (!this) return NULL; - } this->mux = cfmuxl_create(); if (!this->mux) goto out_of_mem; @@ -108,8 +106,6 @@ struct cfcnfg *cfcnfg_create(void) return this; out_of_mem: - pr_warn("Out of memory\n"); - synchronize_rcu(); kfree(this->mux); @@ -448,10 +444,8 @@ cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, enum cfctrl_srv serv, "- unknown channel type\n"); goto unlock; } - if (!servicel) { - pr_warn("Out of memory\n"); + if (!servicel) goto unlock; - } layer_set_dn(servicel, cnfg->mux); cfmuxl_set_uplayer(cnfg->mux, servicel, channel_id); layer_set_up(servicel, adapt_layer); @@ -473,7 +467,7 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg, enum cfcnfg_phy_type phy_type, { struct cflayer *frml; struct cflayer *phy_driver = NULL; - struct cfcnfg_phyinfo *phyinfo; + struct cfcnfg_phyinfo *phyinfo = NULL; int i; u8 phyid; @@ -488,25 +482,25 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg, enum cfcnfg_phy_type phy_type, goto got_phyid; } pr_warn("Too many CAIF Link Layers (max 6)\n"); - goto out; + goto out_err; got_phyid: phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC); + if (!phyinfo) + goto out_err; switch (phy_type) { case CFPHYTYPE_FRAG: phy_driver = cfserl_create(CFPHYTYPE_FRAG, phyid, stx); - if (!phy_driver) { - pr_warn("Out of memory\n"); - goto out; - } + if (!phy_driver) + goto out_err; break; case CFPHYTYPE_CAIF: phy_driver = NULL; break; default: - goto out; + goto out_err; } phy_layer->id = phyid; phyinfo->pref = pref; @@ -520,11 +514,8 @@ got_phyid: frml = cffrml_create(phyid, fcs); - if (!frml) { - pr_warn("Out of memory\n"); - kfree(phyinfo); - goto out; - } + if (!frml) + goto out_err; phyinfo->frm_layer = frml; layer_set_up(frml, cnfg->mux); @@ -540,7 +531,12 @@ got_phyid: } list_add_rcu(&phyinfo->node, &cnfg->phys); -out: + mutex_unlock(&cnfg->lock); + return; + +out_err: + kfree(phy_driver); + kfree(phyinfo); mutex_unlock(&cnfg->lock); } EXPORT_SYMBOL(cfcnfg_add_phy_layer); diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c index e22671b..5cf5222 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -35,15 +35,12 @@ struct cflayer *cfctrl_create(void) { struct dev_info dev_info; struct cfctrl *this = - kmalloc(sizeof(struct cfctrl), GFP_ATOMIC); - if (!this) { - pr_warn("Out of memory\n"); + kzalloc(sizeof(struct cfctrl), GFP_ATOMIC); + if (!this) return NULL; - } caif_assert(offsetof(struct cfctrl, serv.layer) == 0); memset(&dev_info, 0, sizeof(dev_info)); dev_info.id = 0xff; - memset(this, 0, sizeof(*this)); cfsrvl_init(&this->serv, 0, &dev_info, false); atomic_set(&this->req_seq_no, 1); atomic_set(&this->rsp_seq_no, 1); @@ -180,10 +177,8 @@ void cfctrl_enum_req(struct cflayer *layer, u8 physlinkid) struct cfctrl *cfctrl = container_obj(layer); struct cfpkt *pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); struct cflayer *dn = cfctrl->serv.layer.dn; - if (!pkt) { - pr_warn("Out of memory\n"); + if (!pkt) return; - } if (!dn) { pr_debug("not able to send enum request\n"); return; @@ -224,10 +219,8 @@ int cfctrl_linkup_request(struct cflayer *layer, } pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); - if (!pkt) { - pr_warn("Out of memory\n"); + if (!pkt) return -ENOMEM; - } cfpkt_addbdy(pkt, CFCTRL_CMD_LINK_SETUP); cfpkt_addbdy(pkt, (param->chtype << 4) | param->linktype); cfpkt_addbdy(pkt, (param->priority << 3) | param->phyid); @@ -275,10 +268,8 @@ int cfctrl_linkup_request(struct cflayer *layer, return -EINVAL; } req = kzalloc(sizeof(*req), GFP_KERNEL); - if (!req) { - pr_warn("Out of memory\n"); + if (!req) return -ENOMEM; - } req->client_layer = user_layer; req->cmd = CFCTRL_CMD_LINK_SETUP; req->param = *param; @@ -312,10 +303,8 @@ int cfctrl_linkdown_req(struct cflayer *layer, u8 channelid, struct cfpkt *pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); struct cflayer *dn = cfctrl->serv.layer.dn; - if (!pkt) { - pr_warn("Out of memory\n"); + if (!pkt) return -ENOMEM; - } if (!dn) { pr_debug("not able to send link-down request\n"); diff --git a/net/caif/cfdbgl.c b/net/caif/cfdbgl.c index 11a2af4..65d6ef3 100644 --- a/net/caif/cfdbgl.c +++ b/net/caif/cfdbgl.c @@ -19,13 +19,10 @@ static int cfdbgl_transmit(struct cflayer *layr, struct cfpkt *pkt); struct cflayer *cfdbgl_create(u8 channel_id, struct dev_info *dev_info) { - struct cfsrvl *dbg = kmalloc(sizeof(struct cfsrvl), GFP_ATOMIC); - if (!dbg) { - pr_warn("Out of memory\n"); + struct cfsrvl *dbg = kzalloc(sizeof(struct cfsrvl), GFP_ATOMIC); + if (!dbg) return NULL; - } caif_assert(offsetof(struct cfsrvl, layer) == 0); - memset(dbg, 0, sizeof(struct cfsrvl)); cfsrvl_init(dbg, channel_id, dev_info, false); dbg->layer.receive = cfdbgl_receive; dbg->layer.transmit = cfdbgl_transmit; diff --git a/net/caif/cfdgml.c b/net/caif/cfdgml.c index 0382dec..0f5ff27 100644 --- a/net/caif/cfdgml.c +++ b/net/caif/cfdgml.c @@ -26,13 +26,10 @@ static int cfdgml_transmit(struct cflayer *layr, struct cfpkt *pkt); struct cflayer *cfdgml_create(u8 channel_id, struct dev_info *dev_info) { - struct cfsrvl *dgm = kmalloc(sizeof(struct cfsrvl), GFP_ATOMIC); - if (!dgm) { - pr_warn("Out of memory\n"); + struct cfsrvl *dgm = kzalloc(sizeof(struct cfsrvl), GFP_ATOMIC); + if (!dgm) return NULL; - } caif_assert(offsetof(struct cfsrvl, layer) == 0); - memset(dgm, 0, sizeof(struct cfsrvl)); cfsrvl_init(dgm, channel_id, dev_info, true); dgm->layer.receive = cfdgml_receive; dgm->layer.transmit = cfdgml_transmit; diff --git a/net/caif/cffrml.c b/net/caif/cffrml.c index 04204b2..f399211 100644 --- a/net/caif/cffrml.c +++ b/net/caif/cffrml.c @@ -34,11 +34,9 @@ static u32 cffrml_rcv_error; static u32 cffrml_rcv_checsum_error; struct cflayer *cffrml_create(u16 phyid, bool use_fcs) { - struct cffrml *this = kmalloc(sizeof(struct cffrml), GFP_ATOMIC); - if (!this) { - pr_warn("Out of memory\n"); + struct cffrml *this = kzalloc(sizeof(struct cffrml), GFP_ATOMIC); + if (!this) return NULL; - } this->pcpu_refcnt = alloc_percpu(int); if (this->pcpu_refcnt == NULL) { kfree(this); @@ -47,7 +45,6 @@ struct cflayer *cffrml_create(u16 phyid, bool use_fcs) caif_assert(offsetof(struct cffrml, layer) == 0); - memset(this, 0, sizeof(struct cflayer)); this->layer.receive = cffrml_receive; this->layer.transmit = cffrml_transmit; this->layer.ctrlcmd = cffrml_ctrlcmd; diff --git a/net/caif/cfmuxl.c b/net/caif/cfmuxl.c index c23979e..b36f24a 100644 --- a/net/caif/cfmuxl.c +++ b/net/caif/cfmuxl.c @@ -108,7 +108,7 @@ struct cflayer *cfmuxl_remove_dnlayer(struct cflayer *layr, u8 phyid) int idx = phyid % DN_CACHE_SIZE; spin_lock_bh(&muxl->transmit_lock); - rcu_assign_pointer(muxl->dn_cache[idx], NULL); + RCU_INIT_POINTER(muxl->dn_cache[idx], NULL); dn = get_from_id(&muxl->frml_list, phyid); if (dn == NULL) goto out; @@ -164,7 +164,7 @@ struct cflayer *cfmuxl_remove_uplayer(struct cflayer *layr, u8 id) if (up == NULL) goto out; - rcu_assign_pointer(muxl->up_cache[idx], NULL); + RCU_INIT_POINTER(muxl->up_cache[idx], NULL); list_del_rcu(&up->node); out: spin_unlock_bh(&muxl->receive_lock); @@ -261,7 +261,7 @@ static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, idx = layer->id % UP_CACHE_SIZE; spin_lock_bh(&muxl->receive_lock); - rcu_assign_pointer(muxl->up_cache[idx], NULL); + RCU_INIT_POINTER(muxl->up_cache[idx], NULL); list_del_rcu(&layer->node); spin_unlock_bh(&muxl->receive_lock); } diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c index 0deabb4..81660f8 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -46,13 +46,10 @@ struct cflayer *cfrfml_create(u8 channel_id, struct dev_info *dev_info, int mtu_size) { int tmp; - struct cfrfml *this = - kzalloc(sizeof(struct cfrfml), GFP_ATOMIC); + struct cfrfml *this = kzalloc(sizeof(struct cfrfml), GFP_ATOMIC); - if (!this) { - pr_warn("Out of memory\n"); + if (!this) return NULL; - } cfsrvl_init(&this->serv, channel_id, dev_info, false); this->serv.release = cfrfml_release; diff --git a/net/caif/cfserl.c b/net/caif/cfserl.c index 2715c84..797c8d1 100644 --- a/net/caif/cfserl.c +++ b/net/caif/cfserl.c @@ -33,13 +33,10 @@ static void cfserl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, struct cflayer *cfserl_create(int type, int instance, bool use_stx) { - struct cfserl *this = kmalloc(sizeof(struct cfserl), GFP_ATOMIC); - if (!this) { - pr_warn("Out of memory\n"); + struct cfserl *this = kzalloc(sizeof(struct cfserl), GFP_ATOMIC); + if (!this) return NULL; - } caif_assert(offsetof(struct cfserl, layer) == 0); - memset(this, 0, sizeof(struct cfserl)); this->layer.receive = cfserl_receive; this->layer.transmit = cfserl_transmit; this->layer.ctrlcmd = cfserl_ctrlcmd; diff --git a/net/caif/cfsrvl.c b/net/caif/cfsrvl.c index 535a1e7..b99f5b2 100644 --- a/net/caif/cfsrvl.c +++ b/net/caif/cfsrvl.c @@ -108,10 +108,8 @@ static int cfservl_modemcmd(struct cflayer *layr, enum caif_modemcmd ctrl) struct caif_payload_info *info; u8 flow_on = SRVL_FLOW_ON; pkt = cfpkt_create(SRVL_CTRL_PKT_SIZE); - if (!pkt) { - pr_warn("Out of memory\n"); + if (!pkt) return -ENOMEM; - } if (cfpkt_add_head(pkt, &flow_on, 1) < 0) { pr_err("Packet is erroneous!\n"); @@ -130,10 +128,8 @@ static int cfservl_modemcmd(struct cflayer *layr, enum caif_modemcmd ctrl) struct caif_payload_info *info; u8 flow_off = SRVL_FLOW_OFF; pkt = cfpkt_create(SRVL_CTRL_PKT_SIZE); - if (!pkt) { - pr_warn("Out of memory\n"); + if (!pkt) return -ENOMEM; - } if (cfpkt_add_head(pkt, &flow_off, 1) < 0) { pr_err("Packet is erroneous!\n"); diff --git a/net/caif/cfutill.c b/net/caif/cfutill.c index 98e027d..53e49f3 100644 --- a/net/caif/cfutill.c +++ b/net/caif/cfutill.c @@ -26,13 +26,10 @@ static int cfutill_transmit(struct cflayer *layr, struct cfpkt *pkt); struct cflayer *cfutill_create(u8 channel_id, struct dev_info *dev_info) { - struct cfsrvl *util = kmalloc(sizeof(struct cfsrvl), GFP_ATOMIC); - if (!util) { - pr_warn("Out of memory\n"); + struct cfsrvl *util = kzalloc(sizeof(struct cfsrvl), GFP_ATOMIC); + if (!util) return NULL; - } caif_assert(offsetof(struct cfsrvl, layer) == 0); - memset(util, 0, sizeof(struct cfsrvl)); cfsrvl_init(util, channel_id, dev_info, true); util->layer.receive = cfutill_receive; util->layer.transmit = cfutill_transmit; diff --git a/net/caif/cfveil.c b/net/caif/cfveil.c index 3ec83fb..910ab06 100644 --- a/net/caif/cfveil.c +++ b/net/caif/cfveil.c @@ -25,13 +25,10 @@ static int cfvei_transmit(struct cflayer *layr, struct cfpkt *pkt); struct cflayer *cfvei_create(u8 channel_id, struct dev_info *dev_info) { - struct cfsrvl *vei = kmalloc(sizeof(struct cfsrvl), GFP_ATOMIC); - if (!vei) { - pr_warn("Out of memory\n"); + struct cfsrvl *vei = kzalloc(sizeof(struct cfsrvl), GFP_ATOMIC); + if (!vei) return NULL; - } caif_assert(offsetof(struct cfsrvl, layer) == 0); - memset(vei, 0, sizeof(struct cfsrvl)); cfsrvl_init(vei, channel_id, dev_info, true); vei->layer.receive = cfvei_receive; vei->layer.transmit = cfvei_transmit; diff --git a/net/caif/cfvidl.c b/net/caif/cfvidl.c index b2f5989..e3f37db 100644 --- a/net/caif/cfvidl.c +++ b/net/caif/cfvidl.c @@ -21,14 +21,11 @@ static int cfvidl_transmit(struct cflayer *layr, struct cfpkt *pkt); struct cflayer *cfvidl_create(u8 channel_id, struct dev_info *dev_info) { - struct cfsrvl *vid = kmalloc(sizeof(struct cfsrvl), GFP_ATOMIC); - if (!vid) { - pr_warn("Out of memory\n"); + struct cfsrvl *vid = kzalloc(sizeof(struct cfsrvl), GFP_ATOMIC); + if (!vid) return NULL; - } caif_assert(offsetof(struct cfsrvl, layer) == 0); - memset(vid, 0, sizeof(struct cfsrvl)); cfsrvl_init(vid, channel_id, dev_info, false); vid->layer.receive = cfvidl_receive; vid->layer.transmit = cfvidl_transmit; diff --git a/net/can/Kconfig b/net/can/Kconfig index 89395b2..0320069 100644 --- a/net/can/Kconfig +++ b/net/can/Kconfig @@ -40,5 +40,16 @@ config CAN_BCM CAN messages are used on the bus (e.g. in automotive environments). To use the Broadcast Manager, use AF_CAN with protocol CAN_BCM. +config CAN_GW + tristate "CAN Gateway/Router (with netlink configuration)" + depends on CAN + default N + ---help--- + The CAN Gateway/Router is used to route (and modify) CAN frames. + It is based on the PF_CAN core infrastructure for msg filtering and + msg sending and can optionally modify routed CAN frames on the fly. + CAN frames can be routed between CAN network interfaces (one hop). + They can be modified with AND/OR/XOR/SET operations as configured + by the netlink configuration interface known e.g. from iptables. source "drivers/net/can/Kconfig" diff --git a/net/can/Makefile b/net/can/Makefile index 2d3894b3..cef49eb 100644 --- a/net/can/Makefile +++ b/net/can/Makefile @@ -10,3 +10,6 @@ can-raw-y := raw.o obj-$(CONFIG_CAN_BCM) += can-bcm.o can-bcm-y := bcm.o + +obj-$(CONFIG_CAN_GW) += can-gw.o +can-gw-y := gw.o diff --git a/net/can/af_can.c b/net/can/af_can.c index 9b0c32a..0ce2ad0 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -38,8 +38,6 @@ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * - * Send feedback to <socketcan-users@lists.berlios.de> - * */ #include <linux/module.h> @@ -719,7 +717,7 @@ int can_proto_register(const struct can_proto *cp) proto); err = -EBUSY; } else - rcu_assign_pointer(proto_tab[proto], cp); + RCU_INIT_POINTER(proto_tab[proto], cp); mutex_unlock(&proto_tab_lock); @@ -740,7 +738,7 @@ void can_proto_unregister(const struct can_proto *cp) mutex_lock(&proto_tab_lock); BUG_ON(proto_tab[proto] != cp); - rcu_assign_pointer(proto_tab[proto], NULL); + RCU_INIT_POINTER(proto_tab[proto], NULL); mutex_unlock(&proto_tab_lock); synchronize_rcu(); diff --git a/net/can/af_can.h b/net/can/af_can.h index 34253b8..fd882db 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -35,8 +35,6 @@ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * - * Send feedback to <socketcan-users@lists.berlios.de> - * */ #ifndef AF_CAN_H diff --git a/net/can/bcm.c b/net/can/bcm.c index d6c8ae5..151b773 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -37,8 +37,6 @@ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * - * Send feedback to <socketcan-users@lists.berlios.de> - * */ #include <linux/module.h> @@ -344,6 +342,18 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, } } +static void bcm_tx_start_timer(struct bcm_op *op) +{ + if (op->kt_ival1.tv64 && op->count) + hrtimer_start(&op->timer, + ktime_add(ktime_get(), op->kt_ival1), + HRTIMER_MODE_ABS); + else if (op->kt_ival2.tv64) + hrtimer_start(&op->timer, + ktime_add(ktime_get(), op->kt_ival2), + HRTIMER_MODE_ABS); +} + static void bcm_tx_timeout_tsklet(unsigned long data) { struct bcm_op *op = (struct bcm_op *)data; @@ -365,26 +375,12 @@ static void bcm_tx_timeout_tsklet(unsigned long data) bcm_send_to_user(op, &msg_head, NULL, 0); } - } - - if (op->kt_ival1.tv64 && (op->count > 0)) { - - /* send (next) frame */ bcm_can_tx(op); - hrtimer_start(&op->timer, - ktime_add(ktime_get(), op->kt_ival1), - HRTIMER_MODE_ABS); - } else { - if (op->kt_ival2.tv64) { + } else if (op->kt_ival2.tv64) + bcm_can_tx(op); - /* send (next) frame */ - bcm_can_tx(op); - hrtimer_start(&op->timer, - ktime_add(ktime_get(), op->kt_ival2), - HRTIMER_MODE_ABS); - } - } + bcm_tx_start_timer(op); } /* @@ -964,23 +960,20 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, hrtimer_cancel(&op->timer); } - if ((op->flags & STARTTIMER) && - ((op->kt_ival1.tv64 && op->count) || op->kt_ival2.tv64)) { - + if (op->flags & STARTTIMER) { + hrtimer_cancel(&op->timer); /* spec: send can_frame when starting timer */ op->flags |= TX_ANNOUNCE; - - if (op->kt_ival1.tv64 && (op->count > 0)) { - /* op->count-- is done in bcm_tx_timeout_handler */ - hrtimer_start(&op->timer, op->kt_ival1, - HRTIMER_MODE_REL); - } else - hrtimer_start(&op->timer, op->kt_ival2, - HRTIMER_MODE_REL); } - if (op->flags & TX_ANNOUNCE) + if (op->flags & TX_ANNOUNCE) { bcm_can_tx(op); + if (op->count) + op->count--; + } + + if (op->flags & STARTTIMER) + bcm_tx_start_timer(op); return msg_head->nframes * CFSIZ + MHSIZ; } diff --git a/net/can/gw.c b/net/can/gw.c new file mode 100644 index 0000000..3d79b12 --- /dev/null +++ b/net/can/gw.c @@ -0,0 +1,957 @@ +/* + * gw.c - CAN frame Gateway/Router/Bridge with netlink interface + * + * Copyright (c) 2011 Volkswagen Group Electronic Research + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of Volkswagen nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * Alternatively, provided that this notice is retained in full, this + * software may be distributed under the terms of the GNU General + * Public License ("GPL") version 2, in which case the provisions of the + * GPL apply INSTEAD OF those given above. + * + * The provided data structures and external interfaces from this code + * are not restricted to be used by modules with a GPL compatible license. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH + * DAMAGE. + * + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/types.h> +#include <linux/list.h> +#include <linux/spinlock.h> +#include <linux/rcupdate.h> +#include <linux/rculist.h> +#include <linux/net.h> +#include <linux/netdevice.h> +#include <linux/if_arp.h> +#include <linux/skbuff.h> +#include <linux/can.h> +#include <linux/can/core.h> +#include <linux/can/gw.h> +#include <net/rtnetlink.h> +#include <net/net_namespace.h> +#include <net/sock.h> + +#define CAN_GW_VERSION "20101209" +static __initdata const char banner[] = + KERN_INFO "can: netlink gateway (rev " CAN_GW_VERSION ")\n"; + +MODULE_DESCRIPTION("PF_CAN netlink gateway"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); +MODULE_ALIAS("can-gw"); + +HLIST_HEAD(cgw_list); +static struct notifier_block notifier; + +static struct kmem_cache *cgw_cache __read_mostly; + +/* structure that contains the (on-the-fly) CAN frame modifications */ +struct cf_mod { + struct { + struct can_frame and; + struct can_frame or; + struct can_frame xor; + struct can_frame set; + } modframe; + struct { + u8 and; + u8 or; + u8 xor; + u8 set; + } modtype; + void (*modfunc[MAX_MODFUNCTIONS])(struct can_frame *cf, + struct cf_mod *mod); + + /* CAN frame checksum calculation after CAN frame modifications */ + struct { + struct cgw_csum_xor xor; + struct cgw_csum_crc8 crc8; + } csum; + struct { + void (*xor)(struct can_frame *cf, struct cgw_csum_xor *xor); + void (*crc8)(struct can_frame *cf, struct cgw_csum_crc8 *crc8); + } csumfunc; +}; + + +/* + * So far we just support CAN -> CAN routing and frame modifications. + * + * The internal can_can_gw structure contains data and attributes for + * a CAN -> CAN gateway job. + */ +struct can_can_gw { + struct can_filter filter; + int src_idx; + int dst_idx; +}; + +/* list entry for CAN gateways jobs */ +struct cgw_job { + struct hlist_node list; + struct rcu_head rcu; + u32 handled_frames; + u32 dropped_frames; + struct cf_mod mod; + union { + /* CAN frame data source */ + struct net_device *dev; + } src; + union { + /* CAN frame data destination */ + struct net_device *dev; + } dst; + union { + struct can_can_gw ccgw; + /* tbc */ + }; + u8 gwtype; + u16 flags; +}; + +/* modification functions that are invoked in the hot path in can_can_gw_rcv */ + +#define MODFUNC(func, op) static void func(struct can_frame *cf, \ + struct cf_mod *mod) { op ; } + +MODFUNC(mod_and_id, cf->can_id &= mod->modframe.and.can_id) +MODFUNC(mod_and_dlc, cf->can_dlc &= mod->modframe.and.can_dlc) +MODFUNC(mod_and_data, *(u64 *)cf->data &= *(u64 *)mod->modframe.and.data) +MODFUNC(mod_or_id, cf->can_id |= mod->modframe.or.can_id) +MODFUNC(mod_or_dlc, cf->can_dlc |= mod->modframe.or.can_dlc) +MODFUNC(mod_or_data, *(u64 *)cf->data |= *(u64 *)mod->modframe.or.data) +MODFUNC(mod_xor_id, cf->can_id ^= mod->modframe.xor.can_id) +MODFUNC(mod_xor_dlc, cf->can_dlc ^= mod->modframe.xor.can_dlc) +MODFUNC(mod_xor_data, *(u64 *)cf->data ^= *(u64 *)mod->modframe.xor.data) +MODFUNC(mod_set_id, cf->can_id = mod->modframe.set.can_id) +MODFUNC(mod_set_dlc, cf->can_dlc = mod->modframe.set.can_dlc) +MODFUNC(mod_set_data, *(u64 *)cf->data = *(u64 *)mod->modframe.set.data) + +static inline void canframecpy(struct can_frame *dst, struct can_frame *src) +{ + /* + * Copy the struct members separately to ensure that no uninitialized + * data are copied in the 3 bytes hole of the struct. This is needed + * to make easy compares of the data in the struct cf_mod. + */ + + dst->can_id = src->can_id; + dst->can_dlc = src->can_dlc; + *(u64 *)dst->data = *(u64 *)src->data; +} + +static int cgw_chk_csum_parms(s8 fr, s8 to, s8 re) +{ + /* + * absolute dlc values 0 .. 7 => 0 .. 7, e.g. data [0] + * relative to received dlc -1 .. -8 : + * e.g. for received dlc = 8 + * -1 => index = 7 (data[7]) + * -3 => index = 5 (data[5]) + * -8 => index = 0 (data[0]) + */ + + if (fr > -9 && fr < 8 && + to > -9 && to < 8 && + re > -9 && re < 8) + return 0; + else + return -EINVAL; +} + +static inline int calc_idx(int idx, int rx_dlc) +{ + if (idx < 0) + return rx_dlc + idx; + else + return idx; +} + +static void cgw_csum_xor_rel(struct can_frame *cf, struct cgw_csum_xor *xor) +{ + int from = calc_idx(xor->from_idx, cf->can_dlc); + int to = calc_idx(xor->to_idx, cf->can_dlc); + int res = calc_idx(xor->result_idx, cf->can_dlc); + u8 val = xor->init_xor_val; + int i; + + if (from < 0 || to < 0 || res < 0) + return; + + if (from <= to) { + for (i = from; i <= to; i++) + val ^= cf->data[i]; + } else { + for (i = from; i >= to; i--) + val ^= cf->data[i]; + } + + cf->data[res] = val; +} + +static void cgw_csum_xor_pos(struct can_frame *cf, struct cgw_csum_xor *xor) +{ + u8 val = xor->init_xor_val; + int i; + + for (i = xor->from_idx; i <= xor->to_idx; i++) + val ^= cf->data[i]; + + cf->data[xor->result_idx] = val; +} + +static void cgw_csum_xor_neg(struct can_frame *cf, struct cgw_csum_xor *xor) +{ + u8 val = xor->init_xor_val; + int i; + + for (i = xor->from_idx; i >= xor->to_idx; i--) + val ^= cf->data[i]; + + cf->data[xor->result_idx] = val; +} + +static void cgw_csum_crc8_rel(struct can_frame *cf, struct cgw_csum_crc8 *crc8) +{ + int from = calc_idx(crc8->from_idx, cf->can_dlc); + int to = calc_idx(crc8->to_idx, cf->can_dlc); + int res = calc_idx(crc8->result_idx, cf->can_dlc); + u8 crc = crc8->init_crc_val; + int i; + + if (from < 0 || to < 0 || res < 0) + return; + + if (from <= to) { + for (i = crc8->from_idx; i <= crc8->to_idx; i++) + crc = crc8->crctab[crc^cf->data[i]]; + } else { + for (i = crc8->from_idx; i >= crc8->to_idx; i--) + crc = crc8->crctab[crc^cf->data[i]]; + } + + switch (crc8->profile) { + + case CGW_CRC8PRF_1U8: + crc = crc8->crctab[crc^crc8->profile_data[0]]; + break; + + case CGW_CRC8PRF_16U8: + crc = crc8->crctab[crc^crc8->profile_data[cf->data[1] & 0xF]]; + break; + + case CGW_CRC8PRF_SFFID_XOR: + crc = crc8->crctab[crc^(cf->can_id & 0xFF)^ + (cf->can_id >> 8 & 0xFF)]; + break; + + } + + cf->data[crc8->result_idx] = crc^crc8->final_xor_val; +} + +static void cgw_csum_crc8_pos(struct can_frame *cf, struct cgw_csum_crc8 *crc8) +{ + u8 crc = crc8->init_crc_val; + int i; + + for (i = crc8->from_idx; i <= crc8->to_idx; i++) + crc = crc8->crctab[crc^cf->data[i]]; + + switch (crc8->profile) { + + case CGW_CRC8PRF_1U8: + crc = crc8->crctab[crc^crc8->profile_data[0]]; + break; + + case CGW_CRC8PRF_16U8: + crc = crc8->crctab[crc^crc8->profile_data[cf->data[1] & 0xF]]; + break; + + case CGW_CRC8PRF_SFFID_XOR: + crc = crc8->crctab[crc^(cf->can_id & 0xFF)^ + (cf->can_id >> 8 & 0xFF)]; + break; + } + + cf->data[crc8->result_idx] = crc^crc8->final_xor_val; +} + +static void cgw_csum_crc8_neg(struct can_frame *cf, struct cgw_csum_crc8 *crc8) +{ + u8 crc = crc8->init_crc_val; + int i; + + for (i = crc8->from_idx; i >= crc8->to_idx; i--) + crc = crc8->crctab[crc^cf->data[i]]; + + switch (crc8->profile) { + + case CGW_CRC8PRF_1U8: + crc = crc8->crctab[crc^crc8->profile_data[0]]; + break; + + case CGW_CRC8PRF_16U8: + crc = crc8->crctab[crc^crc8->profile_data[cf->data[1] & 0xF]]; + break; + + case CGW_CRC8PRF_SFFID_XOR: + crc = crc8->crctab[crc^(cf->can_id & 0xFF)^ + (cf->can_id >> 8 & 0xFF)]; + break; + } + + cf->data[crc8->result_idx] = crc^crc8->final_xor_val; +} + +/* the receive & process & send function */ +static void can_can_gw_rcv(struct sk_buff *skb, void *data) +{ + struct cgw_job *gwj = (struct cgw_job *)data; + struct can_frame *cf; + struct sk_buff *nskb; + int modidx = 0; + + /* do not handle already routed frames - see comment below */ + if (skb_mac_header_was_set(skb)) + return; + + if (!(gwj->dst.dev->flags & IFF_UP)) { + gwj->dropped_frames++; + return; + } + + /* + * clone the given skb, which has not been done in can_rcv() + * + * When there is at least one modification function activated, + * we need to copy the skb as we want to modify skb->data. + */ + if (gwj->mod.modfunc[0]) + nskb = skb_copy(skb, GFP_ATOMIC); + else + nskb = skb_clone(skb, GFP_ATOMIC); + + if (!nskb) { + gwj->dropped_frames++; + return; + } + + /* + * Mark routed frames by setting some mac header length which is + * not relevant for the CAN frames located in the skb->data section. + * + * As dev->header_ops is not set in CAN netdevices no one is ever + * accessing the various header offsets in the CAN skbuffs anyway. + * E.g. using the packet socket to read CAN frames is still working. + */ + skb_set_mac_header(nskb, 8); + nskb->dev = gwj->dst.dev; + + /* pointer to modifiable CAN frame */ + cf = (struct can_frame *)nskb->data; + + /* perform preprocessed modification functions if there are any */ + while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx]) + (*gwj->mod.modfunc[modidx++])(cf, &gwj->mod); + + /* check for checksum updates when the CAN frame has been modified */ + if (modidx) { + if (gwj->mod.csumfunc.crc8) + (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); + + if (gwj->mod.csumfunc.xor) + (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor); + } + + /* clear the skb timestamp if not configured the other way */ + if (!(gwj->flags & CGW_FLAGS_CAN_SRC_TSTAMP)) + nskb->tstamp.tv64 = 0; + + /* send to netdevice */ + if (can_send(nskb, gwj->flags & CGW_FLAGS_CAN_ECHO)) + gwj->dropped_frames++; + else + gwj->handled_frames++; +} + +static inline int cgw_register_filter(struct cgw_job *gwj) +{ + return can_rx_register(gwj->src.dev, gwj->ccgw.filter.can_id, + gwj->ccgw.filter.can_mask, can_can_gw_rcv, + gwj, "gw"); +} + +static inline void cgw_unregister_filter(struct cgw_job *gwj) +{ + can_rx_unregister(gwj->src.dev, gwj->ccgw.filter.can_id, + gwj->ccgw.filter.can_mask, can_can_gw_rcv, gwj); +} + +static int cgw_notifier(struct notifier_block *nb, + unsigned long msg, void *data) +{ + struct net_device *dev = (struct net_device *)data; + + if (!net_eq(dev_net(dev), &init_net)) + return NOTIFY_DONE; + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + + if (msg == NETDEV_UNREGISTER) { + + struct cgw_job *gwj = NULL; + struct hlist_node *n, *nx; + + ASSERT_RTNL(); + + hlist_for_each_entry_safe(gwj, n, nx, &cgw_list, list) { + + if (gwj->src.dev == dev || gwj->dst.dev == dev) { + hlist_del(&gwj->list); + cgw_unregister_filter(gwj); + kfree(gwj); + } + } + } + + return NOTIFY_DONE; +} + +static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj) +{ + struct cgw_frame_mod mb; + struct rtcanmsg *rtcan; + struct nlmsghdr *nlh = nlmsg_put(skb, 0, 0, 0, sizeof(*rtcan), 0); + if (!nlh) + return -EMSGSIZE; + + rtcan = nlmsg_data(nlh); + rtcan->can_family = AF_CAN; + rtcan->gwtype = gwj->gwtype; + rtcan->flags = gwj->flags; + + /* add statistics if available */ + + if (gwj->handled_frames) { + if (nla_put_u32(skb, CGW_HANDLED, gwj->handled_frames) < 0) + goto cancel; + else + nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(u32)); + } + + if (gwj->dropped_frames) { + if (nla_put_u32(skb, CGW_DROPPED, gwj->dropped_frames) < 0) + goto cancel; + else + nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(u32)); + } + + /* check non default settings of attributes */ + + if (gwj->mod.modtype.and) { + memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); + mb.modtype = gwj->mod.modtype.and; + if (nla_put(skb, CGW_MOD_AND, sizeof(mb), &mb) < 0) + goto cancel; + else + nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(mb)); + } + + if (gwj->mod.modtype.or) { + memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); + mb.modtype = gwj->mod.modtype.or; + if (nla_put(skb, CGW_MOD_OR, sizeof(mb), &mb) < 0) + goto cancel; + else + nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(mb)); + } + + if (gwj->mod.modtype.xor) { + memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); + mb.modtype = gwj->mod.modtype.xor; + if (nla_put(skb, CGW_MOD_XOR, sizeof(mb), &mb) < 0) + goto cancel; + else + nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(mb)); + } + + if (gwj->mod.modtype.set) { + memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); + mb.modtype = gwj->mod.modtype.set; + if (nla_put(skb, CGW_MOD_SET, sizeof(mb), &mb) < 0) + goto cancel; + else + nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(mb)); + } + + if (gwj->mod.csumfunc.crc8) { + if (nla_put(skb, CGW_CS_CRC8, CGW_CS_CRC8_LEN, + &gwj->mod.csum.crc8) < 0) + goto cancel; + else + nlh->nlmsg_len += NLA_HDRLEN + \ + NLA_ALIGN(CGW_CS_CRC8_LEN); + } + + if (gwj->mod.csumfunc.xor) { + if (nla_put(skb, CGW_CS_XOR, CGW_CS_XOR_LEN, + &gwj->mod.csum.xor) < 0) + goto cancel; + else + nlh->nlmsg_len += NLA_HDRLEN + \ + NLA_ALIGN(CGW_CS_XOR_LEN); + } + + if (gwj->gwtype == CGW_TYPE_CAN_CAN) { + + if (gwj->ccgw.filter.can_id || gwj->ccgw.filter.can_mask) { + if (nla_put(skb, CGW_FILTER, sizeof(struct can_filter), + &gwj->ccgw.filter) < 0) + goto cancel; + else + nlh->nlmsg_len += NLA_HDRLEN + + NLA_ALIGN(sizeof(struct can_filter)); + } + + if (nla_put_u32(skb, CGW_SRC_IF, gwj->ccgw.src_idx) < 0) + goto cancel; + else + nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(u32)); + + if (nla_put_u32(skb, CGW_DST_IF, gwj->ccgw.dst_idx) < 0) + goto cancel; + else + nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(u32)); + } + + return skb->len; + +cancel: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +/* Dump information about all CAN gateway jobs, in response to RTM_GETROUTE */ +static int cgw_dump_jobs(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct cgw_job *gwj = NULL; + struct hlist_node *n; + int idx = 0; + int s_idx = cb->args[0]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(gwj, n, &cgw_list, list) { + if (idx < s_idx) + goto cont; + + if (cgw_put_job(skb, gwj) < 0) + break; +cont: + idx++; + } + rcu_read_unlock(); + + cb->args[0] = idx; + + return skb->len; +} + +/* check for common and gwtype specific attributes */ +static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, + u8 gwtype, void *gwtypeattr) +{ + struct nlattr *tb[CGW_MAX+1]; + struct cgw_frame_mod mb; + int modidx = 0; + int err = 0; + + /* initialize modification & checksum data space */ + memset(mod, 0, sizeof(*mod)); + + err = nlmsg_parse(nlh, sizeof(struct rtcanmsg), tb, CGW_MAX, NULL); + if (err < 0) + return err; + + /* check for AND/OR/XOR/SET modifications */ + + if (tb[CGW_MOD_AND] && + nla_len(tb[CGW_MOD_AND]) == CGW_MODATTR_LEN) { + nla_memcpy(&mb, tb[CGW_MOD_AND], CGW_MODATTR_LEN); + + canframecpy(&mod->modframe.and, &mb.cf); + mod->modtype.and = mb.modtype; + + if (mb.modtype & CGW_MOD_ID) + mod->modfunc[modidx++] = mod_and_id; + + if (mb.modtype & CGW_MOD_DLC) + mod->modfunc[modidx++] = mod_and_dlc; + + if (mb.modtype & CGW_MOD_DATA) + mod->modfunc[modidx++] = mod_and_data; + } + + if (tb[CGW_MOD_OR] && + nla_len(tb[CGW_MOD_OR]) == CGW_MODATTR_LEN) { + nla_memcpy(&mb, tb[CGW_MOD_OR], CGW_MODATTR_LEN); + + canframecpy(&mod->modframe.or, &mb.cf); + mod->modtype.or = mb.modtype; + + if (mb.modtype & CGW_MOD_ID) + mod->modfunc[modidx++] = mod_or_id; + + if (mb.modtype & CGW_MOD_DLC) + mod->modfunc[modidx++] = mod_or_dlc; + + if (mb.modtype & CGW_MOD_DATA) + mod->modfunc[modidx++] = mod_or_data; + } + + if (tb[CGW_MOD_XOR] && + nla_len(tb[CGW_MOD_XOR]) == CGW_MODATTR_LEN) { + nla_memcpy(&mb, tb[CGW_MOD_XOR], CGW_MODATTR_LEN); + + canframecpy(&mod->modframe.xor, &mb.cf); + mod->modtype.xor = mb.modtype; + + if (mb.modtype & CGW_MOD_ID) + mod->modfunc[modidx++] = mod_xor_id; + + if (mb.modtype & CGW_MOD_DLC) + mod->modfunc[modidx++] = mod_xor_dlc; + + if (mb.modtype & CGW_MOD_DATA) + mod->modfunc[modidx++] = mod_xor_data; + } + + if (tb[CGW_MOD_SET] && + nla_len(tb[CGW_MOD_SET]) == CGW_MODATTR_LEN) { + nla_memcpy(&mb, tb[CGW_MOD_SET], CGW_MODATTR_LEN); + + canframecpy(&mod->modframe.set, &mb.cf); + mod->modtype.set = mb.modtype; + + if (mb.modtype & CGW_MOD_ID) + mod->modfunc[modidx++] = mod_set_id; + + if (mb.modtype & CGW_MOD_DLC) + mod->modfunc[modidx++] = mod_set_dlc; + + if (mb.modtype & CGW_MOD_DATA) + mod->modfunc[modidx++] = mod_set_data; + } + + /* check for checksum operations after CAN frame modifications */ + if (modidx) { + + if (tb[CGW_CS_CRC8] && + nla_len(tb[CGW_CS_CRC8]) == CGW_CS_CRC8_LEN) { + + struct cgw_csum_crc8 *c = (struct cgw_csum_crc8 *)\ + nla_data(tb[CGW_CS_CRC8]); + + err = cgw_chk_csum_parms(c->from_idx, c->to_idx, + c->result_idx); + if (err) + return err; + + nla_memcpy(&mod->csum.crc8, tb[CGW_CS_CRC8], + CGW_CS_CRC8_LEN); + + /* + * select dedicated processing function to reduce + * runtime operations in receive hot path. + */ + if (c->from_idx < 0 || c->to_idx < 0 || + c->result_idx < 0) + mod->csumfunc.crc8 = cgw_csum_crc8_rel; + else if (c->from_idx <= c->to_idx) + mod->csumfunc.crc8 = cgw_csum_crc8_pos; + else + mod->csumfunc.crc8 = cgw_csum_crc8_neg; + } + + if (tb[CGW_CS_XOR] && + nla_len(tb[CGW_CS_XOR]) == CGW_CS_XOR_LEN) { + + struct cgw_csum_xor *c = (struct cgw_csum_xor *)\ + nla_data(tb[CGW_CS_XOR]); + + err = cgw_chk_csum_parms(c->from_idx, c->to_idx, + c->result_idx); + if (err) + return err; + + nla_memcpy(&mod->csum.xor, tb[CGW_CS_XOR], + CGW_CS_XOR_LEN); + + /* + * select dedicated processing function to reduce + * runtime operations in receive hot path. + */ + if (c->from_idx < 0 || c->to_idx < 0 || + c->result_idx < 0) + mod->csumfunc.xor = cgw_csum_xor_rel; + else if (c->from_idx <= c->to_idx) + mod->csumfunc.xor = cgw_csum_xor_pos; + else + mod->csumfunc.xor = cgw_csum_xor_neg; + } + } + + if (gwtype == CGW_TYPE_CAN_CAN) { + + /* check CGW_TYPE_CAN_CAN specific attributes */ + + struct can_can_gw *ccgw = (struct can_can_gw *)gwtypeattr; + memset(ccgw, 0, sizeof(*ccgw)); + + /* check for can_filter in attributes */ + if (tb[CGW_FILTER] && + nla_len(tb[CGW_FILTER]) == sizeof(struct can_filter)) + nla_memcpy(&ccgw->filter, tb[CGW_FILTER], + sizeof(struct can_filter)); + + err = -ENODEV; + + /* specifying two interfaces is mandatory */ + if (!tb[CGW_SRC_IF] || !tb[CGW_DST_IF]) + return err; + + if (nla_len(tb[CGW_SRC_IF]) == sizeof(u32)) + nla_memcpy(&ccgw->src_idx, tb[CGW_SRC_IF], + sizeof(u32)); + + if (nla_len(tb[CGW_DST_IF]) == sizeof(u32)) + nla_memcpy(&ccgw->dst_idx, tb[CGW_DST_IF], + sizeof(u32)); + + /* both indices set to 0 for flushing all routing entries */ + if (!ccgw->src_idx && !ccgw->dst_idx) + return 0; + + /* only one index set to 0 is an error */ + if (!ccgw->src_idx || !ccgw->dst_idx) + return err; + } + + /* add the checks for other gwtypes here */ + + return 0; +} + +static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, + void *arg) +{ + struct rtcanmsg *r; + struct cgw_job *gwj; + int err = 0; + + if (nlmsg_len(nlh) < sizeof(*r)) + return -EINVAL; + + r = nlmsg_data(nlh); + if (r->can_family != AF_CAN) + return -EPFNOSUPPORT; + + /* so far we only support CAN -> CAN routings */ + if (r->gwtype != CGW_TYPE_CAN_CAN) + return -EINVAL; + + gwj = kmem_cache_alloc(cgw_cache, GFP_KERNEL); + if (!gwj) + return -ENOMEM; + + gwj->handled_frames = 0; + gwj->dropped_frames = 0; + gwj->flags = r->flags; + gwj->gwtype = r->gwtype; + + err = cgw_parse_attr(nlh, &gwj->mod, CGW_TYPE_CAN_CAN, &gwj->ccgw); + if (err < 0) + goto out; + + err = -ENODEV; + + /* ifindex == 0 is not allowed for job creation */ + if (!gwj->ccgw.src_idx || !gwj->ccgw.dst_idx) + goto out; + + gwj->src.dev = dev_get_by_index(&init_net, gwj->ccgw.src_idx); + + if (!gwj->src.dev) + goto out; + + /* check for CAN netdev not using header_ops - see gw_rcv() */ + if (gwj->src.dev->type != ARPHRD_CAN || gwj->src.dev->header_ops) + goto put_src_out; + + gwj->dst.dev = dev_get_by_index(&init_net, gwj->ccgw.dst_idx); + + if (!gwj->dst.dev) + goto put_src_out; + + /* check for CAN netdev not using header_ops - see gw_rcv() */ + if (gwj->dst.dev->type != ARPHRD_CAN || gwj->dst.dev->header_ops) + goto put_src_dst_out; + + ASSERT_RTNL(); + + err = cgw_register_filter(gwj); + if (!err) + hlist_add_head_rcu(&gwj->list, &cgw_list); + +put_src_dst_out: + dev_put(gwj->dst.dev); +put_src_out: + dev_put(gwj->src.dev); +out: + if (err) + kmem_cache_free(cgw_cache, gwj); + + return err; +} + +static void cgw_remove_all_jobs(void) +{ + struct cgw_job *gwj = NULL; + struct hlist_node *n, *nx; + + ASSERT_RTNL(); + + hlist_for_each_entry_safe(gwj, n, nx, &cgw_list, list) { + hlist_del(&gwj->list); + cgw_unregister_filter(gwj); + kfree(gwj); + } +} + +static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +{ + struct cgw_job *gwj = NULL; + struct hlist_node *n, *nx; + struct rtcanmsg *r; + struct cf_mod mod; + struct can_can_gw ccgw; + int err = 0; + + if (nlmsg_len(nlh) < sizeof(*r)) + return -EINVAL; + + r = nlmsg_data(nlh); + if (r->can_family != AF_CAN) + return -EPFNOSUPPORT; + + /* so far we only support CAN -> CAN routings */ + if (r->gwtype != CGW_TYPE_CAN_CAN) + return -EINVAL; + + err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw); + if (err < 0) + return err; + + /* two interface indices both set to 0 => remove all entries */ + if (!ccgw.src_idx && !ccgw.dst_idx) { + cgw_remove_all_jobs(); + return 0; + } + + err = -EINVAL; + + ASSERT_RTNL(); + + /* remove only the first matching entry */ + hlist_for_each_entry_safe(gwj, n, nx, &cgw_list, list) { + + if (gwj->flags != r->flags) + continue; + + if (memcmp(&gwj->mod, &mod, sizeof(mod))) + continue; + + /* if (r->gwtype == CGW_TYPE_CAN_CAN) - is made sure here */ + if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) + continue; + + hlist_del(&gwj->list); + cgw_unregister_filter(gwj); + kfree(gwj); + err = 0; + break; + } + + return err; +} + +static __init int cgw_module_init(void) +{ + printk(banner); + + cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job), + 0, 0, NULL); + + if (!cgw_cache) + return -ENOMEM; + + /* set notifier */ + notifier.notifier_call = cgw_notifier; + register_netdevice_notifier(¬ifier); + + if (__rtnl_register(PF_CAN, RTM_GETROUTE, NULL, cgw_dump_jobs, NULL)) { + unregister_netdevice_notifier(¬ifier); + kmem_cache_destroy(cgw_cache); + return -ENOBUFS; + } + + /* Only the first call to __rtnl_register can fail */ + __rtnl_register(PF_CAN, RTM_NEWROUTE, cgw_create_job, NULL, NULL); + __rtnl_register(PF_CAN, RTM_DELROUTE, cgw_remove_job, NULL, NULL); + + return 0; +} + +static __exit void cgw_module_exit(void) +{ + rtnl_unregister_all(PF_CAN); + + unregister_netdevice_notifier(¬ifier); + + rtnl_lock(); + cgw_remove_all_jobs(); + rtnl_unlock(); + + rcu_barrier(); /* Wait for completion of call_rcu()'s */ + + kmem_cache_destroy(cgw_cache); +} + +module_init(cgw_module_init); +module_exit(cgw_module_exit); diff --git a/net/can/proc.c b/net/can/proc.c index 0016f73..ba873c3 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -37,8 +37,6 @@ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * - * Send feedback to <socketcan-users@lists.berlios.de> - * */ #include <linux/module.h> diff --git a/net/can/raw.c b/net/can/raw.c index dea99a6..cde1b4a 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -37,8 +37,6 @@ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * - * Send feedback to <socketcan-users@lists.berlios.de> - * */ #include <linux/module.h> diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig index be683f2..cc04dd6 100644 --- a/net/ceph/Kconfig +++ b/net/ceph/Kconfig @@ -27,3 +27,17 @@ config CEPH_LIB_PRETTYDEBUG If unsure, say N. +config CEPH_LIB_USE_DNS_RESOLVER + bool "Use in-kernel support for DNS lookup" + depends on CEPH_LIB + select DNS_RESOLVER + default n + help + If you say Y here, hostnames (e.g. monitor addresses) will + be resolved using the CONFIG_DNS_RESOLVER facility. + + For information on how to use CONFIG_DNS_RESOLVER consult + Documentation/networking/dns_resolver.txt + + If unsure, say N. + diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 2883ea0..97f70e5 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -432,9 +432,12 @@ EXPORT_SYMBOL(ceph_client_id); /* * create a fresh client instance */ -struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private) +struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, + unsigned supported_features, + unsigned required_features) { struct ceph_client *client; + struct ceph_entity_addr *myaddr = NULL; int err = -ENOMEM; client = kzalloc(sizeof(*client), GFP_KERNEL); @@ -449,15 +452,27 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private) client->auth_err = 0; client->extra_mon_dispatch = NULL; - client->supported_features = CEPH_FEATURE_SUPPORTED_DEFAULT; - client->required_features = CEPH_FEATURE_REQUIRED_DEFAULT; - - client->msgr = NULL; + client->supported_features = CEPH_FEATURE_SUPPORTED_DEFAULT | + supported_features; + client->required_features = CEPH_FEATURE_REQUIRED_DEFAULT | + required_features; + + /* msgr */ + if (ceph_test_opt(client, MYIP)) + myaddr = &client->options->my_addr; + client->msgr = ceph_messenger_create(myaddr, + client->supported_features, + client->required_features); + if (IS_ERR(client->msgr)) { + err = PTR_ERR(client->msgr); + goto fail; + } + client->msgr->nocrc = ceph_test_opt(client, NOCRC); /* subsystems */ err = ceph_monc_init(&client->monc, client); if (err < 0) - goto fail; + goto fail_msgr; err = ceph_osdc_init(&client->osdc, client); if (err < 0) goto fail_monc; @@ -466,6 +481,8 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private) fail_monc: ceph_monc_stop(&client->monc); +fail_msgr: + ceph_messenger_destroy(client->msgr); fail: kfree(client); return ERR_PTR(err); @@ -490,8 +507,7 @@ void ceph_destroy_client(struct ceph_client *client) ceph_debugfs_client_cleanup(client); - if (client->msgr) - ceph_messenger_destroy(client->msgr); + ceph_messenger_destroy(client->msgr); ceph_destroy_options(client->options); @@ -514,24 +530,9 @@ static int have_mon_and_osd_map(struct ceph_client *client) */ int __ceph_open_session(struct ceph_client *client, unsigned long started) { - struct ceph_entity_addr *myaddr = NULL; int err; unsigned long timeout = client->options->mount_timeout * HZ; - /* initialize the messenger */ - if (client->msgr == NULL) { - if (ceph_test_opt(client, MYIP)) - myaddr = &client->options->my_addr; - client->msgr = ceph_messenger_create(myaddr, - client->supported_features, - client->required_features); - if (IS_ERR(client->msgr)) { - client->msgr = NULL; - return PTR_ERR(client->msgr); - } - client->msgr->nocrc = ceph_test_opt(client, NOCRC); - } - /* open session, and wait for mon and osd maps */ err = ceph_monc_open_session(&client->monc); if (err < 0) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 9918e9e..f466930 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -11,6 +11,7 @@ #include <linux/string.h> #include <linux/bio.h> #include <linux/blkdev.h> +#include <linux/dns_resolver.h> #include <net/tcp.h> #include <linux/ceph/libceph.h> @@ -1078,6 +1079,101 @@ static void addr_set_port(struct sockaddr_storage *ss, int p) } /* + * Unlike other *_pton function semantics, zero indicates success. + */ +static int ceph_pton(const char *str, size_t len, struct sockaddr_storage *ss, + char delim, const char **ipend) +{ + struct sockaddr_in *in4 = (void *)ss; + struct sockaddr_in6 *in6 = (void *)ss; + + memset(ss, 0, sizeof(*ss)); + + if (in4_pton(str, len, (u8 *)&in4->sin_addr.s_addr, delim, ipend)) { + ss->ss_family = AF_INET; + return 0; + } + + if (in6_pton(str, len, (u8 *)&in6->sin6_addr.s6_addr, delim, ipend)) { + ss->ss_family = AF_INET6; + return 0; + } + + return -EINVAL; +} + +/* + * Extract hostname string and resolve using kernel DNS facility. + */ +#ifdef CONFIG_CEPH_LIB_USE_DNS_RESOLVER +static int ceph_dns_resolve_name(const char *name, size_t namelen, + struct sockaddr_storage *ss, char delim, const char **ipend) +{ + const char *end, *delim_p; + char *colon_p, *ip_addr = NULL; + int ip_len, ret; + + /* + * The end of the hostname occurs immediately preceding the delimiter or + * the port marker (':') where the delimiter takes precedence. + */ + delim_p = memchr(name, delim, namelen); + colon_p = memchr(name, ':', namelen); + + if (delim_p && colon_p) + end = delim_p < colon_p ? delim_p : colon_p; + else if (!delim_p && colon_p) + end = colon_p; + else { + end = delim_p; + if (!end) /* case: hostname:/ */ + end = name + namelen; + } + + if (end <= name) + return -EINVAL; + + /* do dns_resolve upcall */ + ip_len = dns_query(NULL, name, end - name, NULL, &ip_addr, NULL); + if (ip_len > 0) + ret = ceph_pton(ip_addr, ip_len, ss, -1, NULL); + else + ret = -ESRCH; + + kfree(ip_addr); + + *ipend = end; + + pr_info("resolve '%.*s' (ret=%d): %s\n", (int)(end - name), name, + ret, ret ? "failed" : ceph_pr_addr(ss)); + + return ret; +} +#else +static inline int ceph_dns_resolve_name(const char *name, size_t namelen, + struct sockaddr_storage *ss, char delim, const char **ipend) +{ + return -EINVAL; +} +#endif + +/* + * Parse a server name (IP or hostname). If a valid IP address is not found + * then try to extract a hostname to resolve using userspace DNS upcall. + */ +static int ceph_parse_server_name(const char *name, size_t namelen, + struct sockaddr_storage *ss, char delim, const char **ipend) +{ + int ret; + + ret = ceph_pton(name, namelen, ss, delim, ipend); + if (ret) + ret = ceph_dns_resolve_name(name, namelen, ss, delim, ipend); + + return ret; +} + +/* * Parse an ip[:port] list into an addr array. Use the default * monitor port if a port isn't specified. */ @@ -1085,15 +1181,13 @@ int ceph_parse_ips(const char *c, const char *end, struct ceph_entity_addr *addr, int max_count, int *count) { - int i; + int i, ret = -EINVAL; const char *p = c; dout("parse_ips on '%.*s'\n", (int)(end-c), c); for (i = 0; i < max_count; i++) { const char *ipend; struct sockaddr_storage *ss = &addr[i].in_addr; - struct sockaddr_in *in4 = (void *)ss; - struct sockaddr_in6 *in6 = (void *)ss; int port; char delim = ','; @@ -1102,15 +1196,11 @@ int ceph_parse_ips(const char *c, const char *end, p++; } - memset(ss, 0, sizeof(*ss)); - if (in4_pton(p, end - p, (u8 *)&in4->sin_addr.s_addr, - delim, &ipend)) - ss->ss_family = AF_INET; - else if (in6_pton(p, end - p, (u8 *)&in6->sin6_addr.s6_addr, - delim, &ipend)) - ss->ss_family = AF_INET6; - else + ret = ceph_parse_server_name(p, end - p, ss, delim, &ipend); + if (ret) goto bad; + ret = -EINVAL; + p = ipend; if (delim == ']') { @@ -1155,7 +1245,7 @@ int ceph_parse_ips(const char *c, const char *end, bad: pr_err("parse_ips bad ip '%.*s'\n", (int)(end - c), c); - return -EINVAL; + return ret; } EXPORT_SYMBOL(ceph_parse_ips); @@ -2281,7 +2371,8 @@ EXPORT_SYMBOL(ceph_con_keepalive); * construct a new message with given type, size * the new msg has a ref count of 1. */ -struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags) +struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, + bool can_fail) { struct ceph_msg *m; @@ -2333,7 +2424,7 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags) m->front.iov_base = kmalloc(front_len, flags); } if (m->front.iov_base == NULL) { - pr_err("msg_new can't allocate %d bytes\n", + dout("ceph_msg_new can't allocate %d bytes\n", front_len); goto out2; } @@ -2348,7 +2439,14 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags) out2: ceph_msg_put(m); out: - pr_err("msg_new can't create type %d front %d\n", type, front_len); + if (!can_fail) { + pr_err("msg_new can't create type %d front %d\n", type, + front_len); + WARN_ON(1); + } else { + dout("msg_new can't create type %d front %d\n", type, + front_len); + } return NULL; } EXPORT_SYMBOL(ceph_msg_new); @@ -2398,7 +2496,7 @@ static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con, } if (!msg) { *skip = 0; - msg = ceph_msg_new(type, front_len, GFP_NOFS); + msg = ceph_msg_new(type, front_len, GFP_NOFS, false); if (!msg) { pr_err("unable to allocate msg type %d len %d\n", type, front_len); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index cbe31fa..0b62dea 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -116,14 +116,12 @@ static void __send_prepared_auth_request(struct ceph_mon_client *monc, int len) */ static void __close_session(struct ceph_mon_client *monc) { - if (monc->con) { - dout("__close_session closing mon%d\n", monc->cur_mon); - ceph_con_revoke(monc->con, monc->m_auth); - ceph_con_close(monc->con); - monc->cur_mon = -1; - monc->pending_auth = 0; - ceph_auth_reset(monc->auth); - } + dout("__close_session closing mon%d\n", monc->cur_mon); + ceph_con_revoke(monc->con, monc->m_auth); + ceph_con_close(monc->con); + monc->cur_mon = -1; + monc->pending_auth = 0; + ceph_auth_reset(monc->auth); } /* @@ -302,15 +300,6 @@ void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc) */ int ceph_monc_open_session(struct ceph_mon_client *monc) { - if (!monc->con) { - monc->con = kmalloc(sizeof(*monc->con), GFP_KERNEL); - if (!monc->con) - return -ENOMEM; - ceph_con_init(monc->client->msgr, monc->con); - monc->con->private = monc; - monc->con->ops = &mon_con_ops; - } - mutex_lock(&monc->mutex); __open_session(monc); __schedule_delayed(monc); @@ -528,10 +517,12 @@ int ceph_monc_do_statfs(struct ceph_mon_client *monc, struct ceph_statfs *buf) init_completion(&req->completion); err = -ENOMEM; - req->request = ceph_msg_new(CEPH_MSG_STATFS, sizeof(*h), GFP_NOFS); + req->request = ceph_msg_new(CEPH_MSG_STATFS, sizeof(*h), GFP_NOFS, + true); if (!req->request) goto out; - req->reply = ceph_msg_new(CEPH_MSG_STATFS_REPLY, 1024, GFP_NOFS); + req->reply = ceph_msg_new(CEPH_MSG_STATFS_REPLY, 1024, GFP_NOFS, + true); if (!req->reply) goto out; @@ -626,10 +617,12 @@ int ceph_monc_do_poolop(struct ceph_mon_client *monc, u32 op, init_completion(&req->completion); err = -ENOMEM; - req->request = ceph_msg_new(CEPH_MSG_POOLOP, sizeof(*h), GFP_NOFS); + req->request = ceph_msg_new(CEPH_MSG_POOLOP, sizeof(*h), GFP_NOFS, + true); if (!req->request) goto out; - req->reply = ceph_msg_new(CEPH_MSG_POOLOP_REPLY, 1024, GFP_NOFS); + req->reply = ceph_msg_new(CEPH_MSG_POOLOP_REPLY, 1024, GFP_NOFS, + true); if (!req->reply) goto out; @@ -755,13 +748,21 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl) if (err) goto out; - monc->con = NULL; + /* connection */ + monc->con = kmalloc(sizeof(*monc->con), GFP_KERNEL); + if (!monc->con) + goto out_monmap; + ceph_con_init(monc->client->msgr, monc->con); + monc->con->private = monc; + monc->con->ops = &mon_con_ops; /* authentication */ monc->auth = ceph_auth_init(cl->options->name, cl->options->key); - if (IS_ERR(monc->auth)) - return PTR_ERR(monc->auth); + if (IS_ERR(monc->auth)) { + err = PTR_ERR(monc->auth); + goto out_con; + } monc->auth->want_keys = CEPH_ENTITY_TYPE_AUTH | CEPH_ENTITY_TYPE_MON | CEPH_ENTITY_TYPE_OSD | CEPH_ENTITY_TYPE_MDS; @@ -770,19 +771,21 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl) err = -ENOMEM; monc->m_subscribe_ack = ceph_msg_new(CEPH_MSG_MON_SUBSCRIBE_ACK, sizeof(struct ceph_mon_subscribe_ack), - GFP_NOFS); + GFP_NOFS, true); if (!monc->m_subscribe_ack) - goto out_monmap; + goto out_auth; - monc->m_subscribe = ceph_msg_new(CEPH_MSG_MON_SUBSCRIBE, 96, GFP_NOFS); + monc->m_subscribe = ceph_msg_new(CEPH_MSG_MON_SUBSCRIBE, 96, GFP_NOFS, + true); if (!monc->m_subscribe) goto out_subscribe_ack; - monc->m_auth_reply = ceph_msg_new(CEPH_MSG_AUTH_REPLY, 4096, GFP_NOFS); + monc->m_auth_reply = ceph_msg_new(CEPH_MSG_AUTH_REPLY, 4096, GFP_NOFS, + true); if (!monc->m_auth_reply) goto out_subscribe; - monc->m_auth = ceph_msg_new(CEPH_MSG_AUTH, 4096, GFP_NOFS); + monc->m_auth = ceph_msg_new(CEPH_MSG_AUTH, 4096, GFP_NOFS, true); monc->pending_auth = 0; if (!monc->m_auth) goto out_auth_reply; @@ -808,6 +811,10 @@ out_subscribe: ceph_msg_put(monc->m_subscribe); out_subscribe_ack: ceph_msg_put(monc->m_subscribe_ack); +out_auth: + ceph_auth_destroy(monc->auth); +out_con: + monc->con->ops->put(monc->con); out_monmap: kfree(monc->monmap); out: @@ -822,11 +829,11 @@ void ceph_monc_stop(struct ceph_mon_client *monc) mutex_lock(&monc->mutex); __close_session(monc); - if (monc->con) { - monc->con->private = NULL; - monc->con->ops->put(monc->con); - monc->con = NULL; - } + + monc->con->private = NULL; + monc->con->ops->put(monc->con); + monc->con = NULL; + mutex_unlock(&monc->mutex); ceph_auth_destroy(monc->auth); @@ -973,7 +980,7 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con, case CEPH_MSG_MON_MAP: case CEPH_MSG_MDS_MAP: case CEPH_MSG_OSD_MAP: - m = ceph_msg_new(type, front_len, GFP_NOFS); + m = ceph_msg_new(type, front_len, GFP_NOFS, false); break; } @@ -1000,7 +1007,7 @@ static void mon_fault(struct ceph_connection *con) if (!con->private) goto out; - if (monc->con && !monc->hunting) + if (!monc->hunting) pr_info("mon%d %s session lost, " "hunting for new mon\n", monc->cur_mon, ceph_pr_addr(&monc->con->peer_addr.in_addr)); diff --git a/net/ceph/msgpool.c b/net/ceph/msgpool.c index 1f4cb30..11d5f41 100644 --- a/net/ceph/msgpool.c +++ b/net/ceph/msgpool.c @@ -12,7 +12,7 @@ static void *msgpool_alloc(gfp_t gfp_mask, void *arg) struct ceph_msgpool *pool = arg; struct ceph_msg *msg; - msg = ceph_msg_new(0, pool->front_len, gfp_mask); + msg = ceph_msg_new(0, pool->front_len, gfp_mask, true); if (!msg) { dout("msgpool_alloc %s failed\n", pool->name); } else { @@ -61,7 +61,7 @@ struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, WARN_ON(1); /* try to alloc a fresh message */ - return ceph_msg_new(0, front_len, GFP_NOFS); + return ceph_msg_new(0, front_len, GFP_NOFS, false); } msg = mempool_alloc(pool->pool, GFP_NOFS); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 88ad8a2..733e4600 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -227,7 +227,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0); else msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, - OSD_OPREPLY_FRONT_LEN, gfp_flags); + OSD_OPREPLY_FRONT_LEN, gfp_flags, true); if (!msg) { ceph_osdc_put_request(req); return NULL; @@ -250,7 +250,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, if (use_mempool) msg = ceph_msgpool_get(&osdc->msgpool_op, 0); else - msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp_flags); + msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp_flags, true); if (!msg) { ceph_osdc_put_request(req); return NULL; @@ -943,7 +943,7 @@ EXPORT_SYMBOL(ceph_osdc_set_request_linger); * Caller should hold map_sem for read and request_mutex. */ static int __map_request(struct ceph_osd_client *osdc, - struct ceph_osd_request *req) + struct ceph_osd_request *req, int force_resend) { struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base; struct ceph_pg pgid; @@ -967,7 +967,8 @@ static int __map_request(struct ceph_osd_client *osdc, num = err; } - if ((req->r_osd && req->r_osd->o_osd == o && + if ((!force_resend && + req->r_osd && req->r_osd->o_osd == o && req->r_sent >= req->r_osd->o_incarnation && req->r_num_pg_osds == num && memcmp(req->r_pg_osds, acting, sizeof(acting[0])*num) == 0) || @@ -1289,18 +1290,18 @@ static void reset_changed_osds(struct ceph_osd_client *osdc) * * Caller should hold map_sem for read and request_mutex. */ -static void kick_requests(struct ceph_osd_client *osdc) +static void kick_requests(struct ceph_osd_client *osdc, int force_resend) { struct ceph_osd_request *req, *nreq; struct rb_node *p; int needmap = 0; int err; - dout("kick_requests\n"); + dout("kick_requests %s\n", force_resend ? " (force resend)" : ""); 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); - err = __map_request(osdc, req); + err = __map_request(osdc, req, force_resend); if (err < 0) continue; /* error */ if (req->r_osd == NULL) { @@ -1318,7 +1319,7 @@ static void kick_requests(struct ceph_osd_client *osdc) r_linger_item) { dout("linger req=%p req->r_osd=%p\n", req, req->r_osd); - err = __map_request(osdc, req); + err = __map_request(osdc, req, force_resend); if (err == 0) continue; /* no change and no osd was specified */ if (err < 0) @@ -1395,7 +1396,7 @@ 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); + kick_requests(osdc, 0); reset_changed_osds(osdc); } else { dout("ignoring incremental map %u len %d\n", @@ -1423,6 +1424,8 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) "older than our %u\n", epoch, maplen, osdc->osdmap->epoch); } else { + int skipped_map = 0; + dout("taking full map %u len %d\n", epoch, maplen); newmap = osdmap_decode(&p, p+maplen); if (IS_ERR(newmap)) { @@ -1432,9 +1435,12 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) BUG_ON(!newmap); oldmap = osdc->osdmap; osdc->osdmap = newmap; - if (oldmap) + if (oldmap) { + if (oldmap->epoch + 1 < newmap->epoch) + skipped_map = 1; ceph_osdmap_destroy(oldmap); - kick_requests(osdc); + } + kick_requests(osdc, skipped_map); } p += maplen; nr_maps--; @@ -1707,7 +1713,7 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc, * the request still han't been touched yet. */ if (req->r_sent == 0) { - rc = __map_request(osdc, req); + rc = __map_request(osdc, req, 0); if (rc < 0) { if (nofail) { dout("osdc_start_request failed map, " @@ -2032,7 +2038,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, if (front > req->r_reply->front.iov_len) { pr_warning("get_reply front %d > preallocated %d\n", front, (int)req->r_reply->front.iov_len); - m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front, GFP_NOFS); + m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front, GFP_NOFS, false); if (!m) goto out; ceph_msg_put(req->r_reply); @@ -2080,7 +2086,7 @@ 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); + return ceph_msg_new(type, front, GFP_NOFS, false); case CEPH_MSG_OSD_OPREPLY: return get_reply(con, hdr, skip); default: diff --git a/net/core/datagram.c b/net/core/datagram.c index 18ac112..68bbf9f 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -324,15 +324,15 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, /* Copy paged appendix. Hmm... why does this look so complicated? */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { int err; u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - struct page *page = frag->page; + struct page *page = skb_frag_page(frag); if (copy > len) copy = len; @@ -410,15 +410,15 @@ int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset, /* Copy paged appendix. Hmm... why does this look so complicated? */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { int err; u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - struct page *page = frag->page; + struct page *page = skb_frag_page(frag); if (copy > len) copy = len; @@ -500,15 +500,15 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, /* Copy paged appendix. Hmm... why does this look so complicated? */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { int err; u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - struct page *page = frag->page; + struct page *page = skb_frag_page(frag); if (copy > len) copy = len; @@ -585,16 +585,16 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { __wsum csum2; int err = 0; u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - struct page *page = frag->page; + struct page *page = skb_frag_page(frag); if (copy > len) copy = len; diff --git a/net/core/dev.c b/net/core/dev.c index b10ff0a..6ba50a1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -133,6 +133,10 @@ #include <linux/pci.h> #include <linux/inetdevice.h> #include <linux/cpu_rmap.h> +#include <linux/if_tunnel.h> +#include <linux/if_pppox.h> +#include <linux/ppp_defs.h> +#include <linux/net_tstamp.h> #include "net-sysfs.h" @@ -1474,6 +1478,57 @@ static inline void net_timestamp_check(struct sk_buff *skb) __net_timestamp(skb); } +static int net_hwtstamp_validate(struct ifreq *ifr) +{ + struct hwtstamp_config cfg; + enum hwtstamp_tx_types tx_type; + enum hwtstamp_rx_filters rx_filter; + int tx_type_valid = 0; + int rx_filter_valid = 0; + + if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) + return -EFAULT; + + if (cfg.flags) /* reserved for future extensions */ + return -EINVAL; + + tx_type = cfg.tx_type; + rx_filter = cfg.rx_filter; + + switch (tx_type) { + case HWTSTAMP_TX_OFF: + case HWTSTAMP_TX_ON: + case HWTSTAMP_TX_ONESTEP_SYNC: + tx_type_valid = 1; + break; + } + + switch (rx_filter) { + case HWTSTAMP_FILTER_NONE: + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + rx_filter_valid = 1; + break; + } + + if (!tx_type_valid || !rx_filter_valid) + return -ERANGE; + + return 0; +} + static inline bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb) { @@ -1955,9 +2010,11 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) #ifdef CONFIG_HIGHMEM int i; if (!(dev->features & NETIF_F_HIGHDMA)) { - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - if (PageHighMem(skb_shinfo(skb)->frags[i].page)) + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + if (PageHighMem(skb_frag_page(frag))) return 1; + } } if (PCI_DMA_BUS_IS_PHYS) { @@ -1966,7 +2023,8 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) if (!pdev) return 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - dma_addr_t addr = page_to_phys(skb_shinfo(skb)->frags[i].page); + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + dma_addr_t addr = page_to_phys(skb_frag_page(frag)); if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask) return 1; } @@ -2527,25 +2585,31 @@ static inline void ____napi_schedule(struct softnet_data *sd, /* * __skb_get_rxhash: calculate a flow hash based on src/dst addresses - * and src/dst port numbers. Returns a non-zero hash number on success - * and 0 on failure. + * and src/dst port numbers. Sets rxhash in skb to non-zero hash value + * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb + * if hash is a canonical 4-tuple hash over transport ports. */ -__u32 __skb_get_rxhash(struct sk_buff *skb) +void __skb_get_rxhash(struct sk_buff *skb) { int nhoff, hash = 0, poff; const struct ipv6hdr *ip6; const struct iphdr *ip; + const struct vlan_hdr *vlan; u8 ip_proto; - u32 addr1, addr2, ihl; + u32 addr1, addr2; + u16 proto; union { u32 v32; u16 v16[2]; } ports; nhoff = skb_network_offset(skb); + proto = skb->protocol; - switch (skb->protocol) { +again: + switch (proto) { case __constant_htons(ETH_P_IP): +ip: if (!pskb_may_pull(skb, sizeof(*ip) + nhoff)) goto done; @@ -2556,9 +2620,10 @@ __u32 __skb_get_rxhash(struct sk_buff *skb) ip_proto = ip->protocol; addr1 = (__force u32) ip->saddr; addr2 = (__force u32) ip->daddr; - ihl = ip->ihl; + nhoff += ip->ihl * 4; break; case __constant_htons(ETH_P_IPV6): +ipv6: if (!pskb_may_pull(skb, sizeof(*ip6) + nhoff)) goto done; @@ -2566,20 +2631,71 @@ __u32 __skb_get_rxhash(struct sk_buff *skb) ip_proto = ip6->nexthdr; addr1 = (__force u32) ip6->saddr.s6_addr32[3]; addr2 = (__force u32) ip6->daddr.s6_addr32[3]; - ihl = (40 >> 2); + nhoff += 40; break; + case __constant_htons(ETH_P_8021Q): + if (!pskb_may_pull(skb, sizeof(*vlan) + nhoff)) + goto done; + vlan = (const struct vlan_hdr *) (skb->data + nhoff); + proto = vlan->h_vlan_encapsulated_proto; + nhoff += sizeof(*vlan); + goto again; + case __constant_htons(ETH_P_PPP_SES): + if (!pskb_may_pull(skb, PPPOE_SES_HLEN + nhoff)) + goto done; + proto = *((__be16 *) (skb->data + nhoff + + sizeof(struct pppoe_hdr))); + nhoff += PPPOE_SES_HLEN; + switch (proto) { + case __constant_htons(PPP_IP): + goto ip; + case __constant_htons(PPP_IPV6): + goto ipv6; + default: + goto done; + } default: goto done; } + switch (ip_proto) { + case IPPROTO_GRE: + if (pskb_may_pull(skb, nhoff + 16)) { + u8 *h = skb->data + nhoff; + __be16 flags = *(__be16 *)h; + + /* + * Only look inside GRE if version zero and no + * routing + */ + if (!(flags & (GRE_VERSION|GRE_ROUTING))) { + proto = *(__be16 *)(h + 2); + nhoff += 4; + if (flags & GRE_CSUM) + nhoff += 4; + if (flags & GRE_KEY) + nhoff += 4; + if (flags & GRE_SEQ) + nhoff += 4; + goto again; + } + } + break; + case IPPROTO_IPIP: + goto again; + default: + break; + } + ports.v32 = 0; poff = proto_ports_offset(ip_proto); if (poff >= 0) { - nhoff += ihl * 4 + poff; + nhoff += poff; if (pskb_may_pull(skb, nhoff + 4)) { ports.v32 = * (__force u32 *) (skb->data + nhoff); if (ports.v16[1] < ports.v16[0]) swap(ports.v16[0], ports.v16[1]); + skb->l4_rxhash = 1; } } @@ -2592,7 +2708,7 @@ __u32 __skb_get_rxhash(struct sk_buff *skb) hash = 1; done: - return hash; + skb->rxhash = hash; } EXPORT_SYMBOL(__skb_get_rxhash); @@ -2606,10 +2722,7 @@ static struct rps_dev_flow * set_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow *rflow, u16 next_cpu) { - u16 tcpu; - - tcpu = rflow->cpu = next_cpu; - if (tcpu != RPS_NO_CPU) { + if (next_cpu != RPS_NO_CPU) { #ifdef CONFIG_RFS_ACCEL struct netdev_rx_queue *rxqueue; struct rps_dev_flow_table *flow_table; @@ -2637,16 +2750,16 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb, goto out; old_rflow = rflow; rflow = &flow_table->flows[flow_id]; - rflow->cpu = next_cpu; rflow->filter = rc; if (old_rflow->filter == rflow->filter) old_rflow->filter = RPS_NO_FILTER; out: #endif rflow->last_qtail = - per_cpu(softnet_data, tcpu).input_queue_head; + per_cpu(softnet_data, next_cpu).input_queue_head; } + rflow->cpu = next_cpu; return rflow; } @@ -2681,13 +2794,13 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, map = rcu_dereference(rxqueue->rps_map); if (map) { if (map->len == 1 && - !rcu_dereference_raw(rxqueue->rps_flow_table)) { + !rcu_access_pointer(rxqueue->rps_flow_table)) { tcpu = map->cpus[0]; if (cpu_online(tcpu)) cpu = tcpu; goto done; } - } else if (!rcu_dereference_raw(rxqueue->rps_flow_table)) { + } else if (!rcu_access_pointer(rxqueue->rps_flow_table)) { goto done; } @@ -3102,8 +3215,8 @@ void netdev_rx_handler_unregister(struct net_device *dev) { ASSERT_RTNL(); - rcu_assign_pointer(dev->rx_handler, NULL); - rcu_assign_pointer(dev->rx_handler_data, NULL); + RCU_INIT_POINTER(dev->rx_handler, NULL); + RCU_INIT_POINTER(dev->rx_handler_data, NULL); } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); @@ -3171,6 +3284,17 @@ ncls: #endif rx_handler = rcu_dereference(skb->dev->rx_handler); + if (vlan_tx_tag_present(skb)) { + if (pt_prev) { + ret = deliver_skb(skb, pt_prev, orig_dev); + pt_prev = NULL; + } + if (vlan_do_receive(&skb, !rx_handler)) + goto another_round; + else if (unlikely(!skb)) + goto out; + } + if (rx_handler) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); @@ -3190,18 +3314,6 @@ ncls: } } - if (vlan_tx_tag_present(skb)) { - if (pt_prev) { - ret = deliver_skb(skb, pt_prev, orig_dev); - pt_prev = NULL; - } - if (vlan_do_receive(&skb)) { - ret = __netif_receive_skb(skb); - goto out; - } else if (unlikely(!skb)) - goto out; - } - /* deliver only exact match when indicated */ null_or_dev = deliver_exact ? skb->dev : NULL; @@ -3429,10 +3541,10 @@ pull: skb->data_len -= grow; skb_shinfo(skb)->frags[0].page_offset += grow; - skb_shinfo(skb)->frags[0].size -= grow; + skb_frag_size_sub(&skb_shinfo(skb)->frags[0], grow); - if (unlikely(!skb_shinfo(skb)->frags[0].size)) { - put_page(skb_shinfo(skb)->frags[0].page); + if (unlikely(!skb_frag_size(&skb_shinfo(skb)->frags[0]))) { + skb_frag_unref(skb, 0); memmove(skb_shinfo(skb)->frags, skb_shinfo(skb)->frags + 1, --skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t)); @@ -3496,11 +3608,10 @@ void skb_gro_reset_offset(struct sk_buff *skb) NAPI_GRO_CB(skb)->frag0_len = 0; if (skb->mac_header == skb->tail && - !PageHighMem(skb_shinfo(skb)->frags[0].page)) { + !PageHighMem(skb_frag_page(&skb_shinfo(skb)->frags[0]))) { NAPI_GRO_CB(skb)->frag0 = - page_address(skb_shinfo(skb)->frags[0].page) + - skb_shinfo(skb)->frags[0].page_offset; - NAPI_GRO_CB(skb)->frag0_len = skb_shinfo(skb)->frags[0].size; + skb_frag_address(&skb_shinfo(skb)->frags[0]); + NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(&skb_shinfo(skb)->frags[0]); } } EXPORT_SYMBOL(skb_gro_reset_offset); @@ -3982,6 +4093,60 @@ static int dev_ifconf(struct net *net, char __user *arg) } #ifdef CONFIG_PROC_FS + +#define BUCKET_SPACE (32 - NETDEV_HASHBITS) + +struct dev_iter_state { + struct seq_net_private p; + unsigned int pos; /* bucket << BUCKET_SPACE + offset */ +}; + +#define get_bucket(x) ((x) >> BUCKET_SPACE) +#define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1)) +#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o)) + +static inline struct net_device *dev_from_same_bucket(struct seq_file *seq) +{ + struct dev_iter_state *state = seq->private; + struct net *net = seq_file_net(seq); + struct net_device *dev; + struct hlist_node *p; + struct hlist_head *h; + unsigned int count, bucket, offset; + + bucket = get_bucket(state->pos); + offset = get_offset(state->pos); + h = &net->dev_name_head[bucket]; + count = 0; + hlist_for_each_entry_rcu(dev, p, h, name_hlist) { + if (count++ == offset) { + state->pos = set_bucket_offset(bucket, count); + return dev; + } + } + + return NULL; +} + +static inline struct net_device *dev_from_new_bucket(struct seq_file *seq) +{ + struct dev_iter_state *state = seq->private; + struct net_device *dev; + unsigned int bucket; + + bucket = get_bucket(state->pos); + do { + dev = dev_from_same_bucket(seq); + if (dev) + return dev; + + bucket++; + state->pos = set_bucket_offset(bucket, 0); + } while (bucket < NETDEV_HASHENTRIES); + + return NULL; +} + /* * This is invoked by the /proc filesystem handler to display a device * in detail. @@ -3989,33 +4154,33 @@ static int dev_ifconf(struct net *net, char __user *arg) void *dev_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { - struct net *net = seq_file_net(seq); - loff_t off; - struct net_device *dev; + struct dev_iter_state *state = seq->private; rcu_read_lock(); if (!*pos) return SEQ_START_TOKEN; - off = 1; - for_each_netdev_rcu(net, dev) - if (off++ == *pos) - return dev; + /* check for end of the hash */ + if (state->pos == 0 && *pos > 1) + return NULL; - return NULL; + return dev_from_new_bucket(seq); } void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct net_device *dev = v; + struct net_device *dev; + + ++*pos; if (v == SEQ_START_TOKEN) - dev = first_net_device_rcu(seq_file_net(seq)); - else - dev = next_net_device_rcu(dev); + return dev_from_new_bucket(seq); - ++*pos; - return dev; + dev = dev_from_same_bucket(seq); + if (dev) + return dev; + + return dev_from_new_bucket(seq); } void dev_seq_stop(struct seq_file *seq, void *v) @@ -4114,7 +4279,7 @@ static const struct seq_operations dev_seq_ops = { static int dev_seq_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &dev_seq_ops, - sizeof(struct seq_net_private)); + sizeof(struct dev_iter_state)); } static const struct file_operations dev_seq_fops = { @@ -4497,9 +4662,7 @@ void __dev_set_rx_mode(struct net_device *dev) if (!netif_device_present(dev)) return; - if (ops->ndo_set_rx_mode) - ops->ndo_set_rx_mode(dev); - else { + if (!(dev->priv_flags & IFF_UNICAST_FLT)) { /* Unicast addresses changes may only happen under the rtnl, * therefore calling __dev_set_promiscuity here is safe. */ @@ -4510,10 +4673,10 @@ void __dev_set_rx_mode(struct net_device *dev) __dev_set_promiscuity(dev, -1); dev->uc_promisc = false; } - - if (ops->ndo_set_multicast_list) - ops->ndo_set_multicast_list(dev); } + + if (ops->ndo_set_rx_mode) + ops->ndo_set_rx_mode(dev); } void dev_set_rx_mode(struct net_device *dev) @@ -4524,30 +4687,6 @@ void dev_set_rx_mode(struct net_device *dev) } /** - * dev_ethtool_get_settings - call device's ethtool_ops::get_settings() - * @dev: device - * @cmd: memory area for ethtool_ops::get_settings() result - * - * The cmd arg is initialized properly (cleared and - * ethtool_cmd::cmd field set to ETHTOOL_GSET). - * - * Return device's ethtool_ops::get_settings() result value or - * -EOPNOTSUPP when device doesn't expose - * ethtool_ops::get_settings() operation. - */ -int dev_ethtool_get_settings(struct net_device *dev, - struct ethtool_cmd *cmd) -{ - if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings) - return -EOPNOTSUPP; - - memset(cmd, 0, sizeof(struct ethtool_cmd)); - cmd->cmd = ETHTOOL_GSET; - return dev->ethtool_ops->get_settings(dev, cmd); -} -EXPORT_SYMBOL(dev_ethtool_get_settings); - -/** * dev_get_flags - get flags reported to userspace * @dev: device * @@ -4863,7 +5002,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) return -EOPNOTSUPP; case SIOCADDMULTI: - if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) || + if (!ops->ndo_set_rx_mode || ifr->ifr_hwaddr.sa_family != AF_UNSPEC) return -EINVAL; if (!netif_device_present(dev)) @@ -4871,7 +5010,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data); case SIOCDELMULTI: - if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) || + if (!ops->ndo_set_rx_mode || ifr->ifr_hwaddr.sa_family != AF_UNSPEC) return -EINVAL; if (!netif_device_present(dev)) @@ -4888,6 +5027,12 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) ifr->ifr_newname[IFNAMSIZ-1] = '\0'; return dev_change_name(dev, ifr->ifr_newname); + case SIOCSHWTSTAMP: + err = net_hwtstamp_validate(ifr); + if (err) + return err; + /* fall through */ + /* * Unknown or private ioctl */ @@ -5202,7 +5347,7 @@ static void rollback_registered_many(struct list_head *head) dev = list_first_entry(head, struct net_device, unreg_list); call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); - rcu_barrier(); + synchronize_net(); list_for_each_entry(dev, head, unreg_list) dev_put(dev); @@ -5715,6 +5860,12 @@ void netdev_run_todo(void) __rtnl_unlock(); + /* Wait for rcu callbacks to finish before attempting to drain + * the device list. This usually avoids a 250ms wait. + */ + if (!list_empty(&list)) + rcu_barrier(); + while (!list_empty(&list)) { struct net_device *dev = list_first_entry(&list, struct net_device, todo_list); @@ -5735,8 +5886,8 @@ void netdev_run_todo(void) /* paranoia */ BUG_ON(netdev_refcnt_read(dev)); - WARN_ON(rcu_dereference_raw(dev->ip_ptr)); - WARN_ON(rcu_dereference_raw(dev->ip6_ptr)); + WARN_ON(rcu_access_pointer(dev->ip_ptr)); + WARN_ON(rcu_access_pointer(dev->ip6_ptr)); WARN_ON(dev->dn_ptr); if (dev->destructor) @@ -5940,7 +6091,7 @@ void free_netdev(struct net_device *dev) kfree(dev->_rx); #endif - kfree(rcu_dereference_raw(dev->ingress_queue)); + kfree(rcu_dereference_protected(dev->ingress_queue, 1)); /* Flush device addresses */ dev_addr_flush(dev); @@ -6115,6 +6266,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); /* * Flush the unicast and multicast chains @@ -6298,7 +6450,7 @@ const char *netdev_drivername(const struct net_device *dev) return empty; } -static int __netdev_printk(const char *level, const struct net_device *dev, +int __netdev_printk(const char *level, const struct net_device *dev, struct va_format *vaf) { int r; @@ -6313,6 +6465,7 @@ static int __netdev_printk(const char *level, const struct net_device *dev, return r; } +EXPORT_SYMBOL(__netdev_printk); int netdev_printk(const char *level, const struct net_device *dev, const char *format, ...) diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index e2e6693..283d1b8 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -591,8 +591,8 @@ EXPORT_SYMBOL(dev_mc_del_global); * addresses that have no users left. The source device must be * locked by netif_tx_lock_bh. * - * This function is intended to be called from the dev->set_multicast_list - * or dev->set_rx_mode function of layered software devices. + * This function is intended to be called from the ndo_set_rx_mode + * function of layered software devices. */ int dev_mc_sync(struct net_device *to, struct net_device *from) { diff --git a/net/core/dst.c b/net/core/dst.c index 14b33baf..d5e2c4c 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -171,7 +171,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, dst_init_metrics(dst, dst_default_metrics, true); dst->expires = 0UL; dst->path = dst; - dst->_neighbour = NULL; + RCU_INIT_POINTER(dst->_neighbour, NULL); #ifdef CONFIG_XFRM dst->xfrm = NULL; #endif @@ -229,11 +229,11 @@ struct dst_entry *dst_destroy(struct dst_entry * dst) smp_rmb(); again: - neigh = dst->_neighbour; + neigh = rcu_dereference_protected(dst->_neighbour, 1); child = dst->child; if (neigh) { - dst->_neighbour = NULL; + RCU_INIT_POINTER(dst->_neighbour, NULL); neigh_release(neigh); } @@ -360,14 +360,19 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, if (!unregister) { dst->input = dst->output = dst_discard; } else { + struct neighbour *neigh; + dst->dev = dev_net(dst->dev)->loopback_dev; dev_hold(dst->dev); dev_put(dev); - if (dst->_neighbour && dst->_neighbour->dev == dev) { - dst->_neighbour->dev = dst->dev; + rcu_read_lock(); + neigh = dst_get_neighbour(dst); + if (neigh && neigh->dev == dev) { + neigh->dev = dst->dev; dev_hold(dst->dev); dev_put(dev); } + rcu_read_unlock(); } } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 6cdba5f..f444817 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -569,15 +569,25 @@ int __ethtool_set_flags(struct net_device *dev, u32 data) return 0; } -static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) +int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { - struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET }; - int err; + ASSERT_RTNL(); - if (!dev->ethtool_ops->get_settings) + if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings) return -EOPNOTSUPP; - err = dev->ethtool_ops->get_settings(dev, &cmd); + memset(cmd, 0, sizeof(struct ethtool_cmd)); + cmd->cmd = ETHTOOL_GSET; + return dev->ethtool_ops->get_settings(dev, cmd); +} +EXPORT_SYMBOL(__ethtool_get_settings); + +static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) +{ + int err; + struct ethtool_cmd cmd; + + err = __ethtool_get_settings(dev, &cmd); if (err < 0) return err; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 3231b46..57e8f95 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -475,8 +475,11 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) list_del_rcu(&rule->list); - if (rule->action == FR_ACT_GOTO) + if (rule->action == FR_ACT_GOTO) { ops->nr_goto_rules--; + if (rtnl_dereference(rule->ctarget) == NULL) + ops->unresolved_rules--; + } /* * Check if this rule is a target to any of them. If so, @@ -487,7 +490,7 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (ops->nr_goto_rules > 0) { list_for_each_entry(tmp, &ops->rules_list, list) { if (rtnl_dereference(tmp->ctarget) == rule) { - rcu_assign_pointer(tmp->ctarget, NULL); + RCU_INIT_POINTER(tmp->ctarget, NULL); ops->unresolved_rules++; } } @@ -545,7 +548,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh->flags = rule->flags; if (rule->action == FR_ACT_GOTO && - rcu_dereference_raw(rule->ctarget) == NULL) + rcu_access_pointer(rule->ctarget) == NULL) frh->flags |= FIB_RULE_UNRESOLVED; if (rule->iifname[0]) { diff --git a/net/core/filter.c b/net/core/filter.c index 36f975f..5dea452 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -436,7 +436,7 @@ error: * * Returns 0 if the rule set is legal or -EINVAL if not. */ -int sk_chk_filter(struct sock_filter *filter, int flen) +int sk_chk_filter(struct sock_filter *filter, unsigned int flen) { /* * Valid instructions are initialized to non-0. @@ -645,7 +645,7 @@ int sk_detach_filter(struct sock *sk) filter = rcu_dereference_protected(sk->sk_filter, sock_owned_by_user(sk)); if (filter) { - rcu_assign_pointer(sk->sk_filter, NULL); + RCU_INIT_POINTER(sk->sk_filter, NULL); sk_filter_uncharge(sk, filter); ret = 0; } diff --git a/net/core/flow.c b/net/core/flow.c index 555a456..8ae42de 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -413,7 +413,7 @@ static int __init flow_cache_init(struct flow_cache *fc) for_each_online_cpu(i) { if (flow_cache_cpu_prepare(fc, i)) - return -ENOMEM; + goto err; } fc->hotcpu_notifier = (struct notifier_block){ .notifier_call = flow_cache_cpu, @@ -426,6 +426,18 @@ static int __init flow_cache_init(struct flow_cache *fc) add_timer(&fc->rnd_timer); return 0; + +err: + for_each_possible_cpu(i) { + struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i); + kfree(fcp->hash_table); + fcp->hash_table = NULL; + } + + free_percpu(fc->percpu); + fc->percpu = NULL; + + return -ENOMEM; } static int __init flow_cache_init_global(void) diff --git a/net/core/kmap_skb.h b/net/core/kmap_skb.h index 283c2b99..81e1ed7 100644 --- a/net/core/kmap_skb.h +++ b/net/core/kmap_skb.h @@ -7,7 +7,7 @@ static inline void *kmap_skb_frag(const skb_frag_t *frag) local_bh_disable(); #endif - return kmap_atomic(frag->page, KM_SKB_DATA_SOFTIRQ); + return kmap_atomic(skb_frag_page(frag), KM_SKB_DATA_SOFTIRQ); } static inline void kunmap_skb_frag(void *vaddr) diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 357bd4e..c3519c6 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -78,8 +78,13 @@ static void rfc2863_policy(struct net_device *dev) static bool linkwatch_urgent_event(struct net_device *dev) { - return netif_running(dev) && netif_carrier_ok(dev) && - qdisc_tx_changing(dev); + if (!netif_running(dev)) + return false; + + if (dev->ifindex != dev->iflink) + return true; + + return netif_carrier_ok(dev) && qdisc_tx_changing(dev); } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 1334d7e..039d51e 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -844,6 +844,19 @@ static void neigh_invalidate(struct neighbour *neigh) skb_queue_purge(&neigh->arp_queue); } +static void neigh_probe(struct neighbour *neigh) + __releases(neigh->lock) +{ + struct sk_buff *skb = skb_peek(&neigh->arp_queue); + /* keep skb alive even if arp_queue overflows */ + if (skb) + skb = skb_copy(skb, GFP_ATOMIC); + write_unlock(&neigh->lock); + neigh->ops->solicit(neigh, skb); + atomic_inc(&neigh->probes); + kfree_skb(skb); +} + /* Called when a timer expires for a neighbour entry. */ static void neigh_timer_handler(unsigned long arg) @@ -859,12 +872,8 @@ static void neigh_timer_handler(unsigned long arg) now = jiffies; next = now + HZ; - if (!(state & NUD_IN_TIMER)) { -#ifndef CONFIG_SMP - printk(KERN_WARNING "neigh: timer & !nud_in_timer\n"); -#endif + if (!(state & NUD_IN_TIMER)) goto out; - } if (state & NUD_REACHABLE) { if (time_before_eq(now, @@ -920,14 +929,7 @@ static void neigh_timer_handler(unsigned long arg) neigh_hold(neigh); } if (neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) { - struct sk_buff *skb = skb_peek(&neigh->arp_queue); - /* keep skb alive even if arp_queue overflows */ - if (skb) - skb = skb_copy(skb, GFP_ATOMIC); - write_unlock(&neigh->lock); - neigh->ops->solicit(neigh, skb); - atomic_inc(&neigh->probes); - kfree_skb(skb); + neigh_probe(neigh); } else { out: write_unlock(&neigh->lock); @@ -942,7 +944,7 @@ out: int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) { int rc; - unsigned long now; + bool immediate_probe = false; write_lock_bh(&neigh->lock); @@ -950,14 +952,16 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE)) goto out_unlock_bh; - now = jiffies; - if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) { if (neigh->parms->mcast_probes + neigh->parms->app_probes) { + unsigned long next, now = jiffies; + atomic_set(&neigh->probes, neigh->parms->ucast_probes); neigh->nud_state = NUD_INCOMPLETE; - neigh->updated = jiffies; - neigh_add_timer(neigh, now + 1); + neigh->updated = now; + next = now + max(neigh->parms->retrans_time, HZ/2); + neigh_add_timer(neigh, next); + immediate_probe = true; } else { neigh->nud_state = NUD_FAILED; neigh->updated = jiffies; @@ -989,7 +993,11 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) rc = 1; } out_unlock_bh: - write_unlock_bh(&neigh->lock); + if (immediate_probe) + neigh_probe(neigh); + else + write_unlock(&neigh->lock); + local_bh_enable(); return rc; } EXPORT_SYMBOL(__neigh_event_send); @@ -1156,10 +1164,14 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, struct dst_entry *dst = skb_dst(skb); struct neighbour *n2, *n1 = neigh; write_unlock_bh(&neigh->lock); + + rcu_read_lock(); /* On shaper/eql skb->dst->neighbour != neigh :( */ if (dst && (n2 = dst_get_neighbour(dst)) != NULL) n1 = n2; n1->output(n1, skb); + rcu_read_unlock(); + write_lock_bh(&neigh->lock); } skb_queue_purge(&neigh->arp_queue); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 1683e5d..7604a63 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -147,7 +147,7 @@ static ssize_t show_speed(struct device *dev, if (netif_running(netdev)) { struct ethtool_cmd cmd; - if (!dev_ethtool_get_settings(netdev, &cmd)) + if (!__ethtool_get_settings(netdev, &cmd)) ret = sprintf(buf, fmt_udec, ethtool_cmd_speed(&cmd)); } rtnl_unlock(); @@ -165,7 +165,7 @@ static ssize_t show_duplex(struct device *dev, if (netif_running(netdev)) { struct ethtool_cmd cmd; - if (!dev_ethtool_get_settings(netdev, &cmd)) + if (!__ethtool_get_settings(netdev, &cmd)) ret = sprintf(buf, "%s\n", cmd.duplex ? "full" : "half"); } @@ -712,13 +712,13 @@ static void rx_queue_release(struct kobject *kobj) struct rps_dev_flow_table *flow_table; - map = rcu_dereference_raw(queue->rps_map); + map = rcu_dereference_protected(queue->rps_map, 1); if (map) { RCU_INIT_POINTER(queue->rps_map, NULL); kfree_rcu(map, rcu); } - flow_table = rcu_dereference_raw(queue->rps_flow_table); + flow_table = rcu_dereference_protected(queue->rps_flow_table, 1); if (flow_table) { RCU_INIT_POINTER(queue->rps_flow_table, NULL); call_rcu(&flow_table->rcu, rps_dev_flow_table_release); @@ -987,10 +987,10 @@ static ssize_t store_xps_map(struct netdev_queue *queue, } if (nonempty) - rcu_assign_pointer(dev->xps_maps, new_dev_maps); + RCU_INIT_POINTER(dev->xps_maps, new_dev_maps); else { kfree(new_dev_maps); - rcu_assign_pointer(dev->xps_maps, NULL); + RCU_INIT_POINTER(dev->xps_maps, NULL); } if (dev_maps) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 5262251..f57d946 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -762,7 +762,7 @@ int __netpoll_setup(struct netpoll *np) } /* last thing to do is link it to the net device structure */ - rcu_assign_pointer(ndev->npinfo, npinfo); + RCU_INIT_POINTER(ndev->npinfo, npinfo); return 0; @@ -903,7 +903,7 @@ void __netpoll_cleanup(struct netpoll *np) if (ops->ndo_netpoll_cleanup) ops->ndo_netpoll_cleanup(np->dev); - rcu_assign_pointer(np->dev->npinfo, NULL); + RCU_INIT_POINTER(np->dev->npinfo, NULL); /* avoid racing with NAPI reading npinfo */ synchronize_rcu_bh(); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index e35a6fb..0001c24 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2145,9 +2145,12 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) } start_time = ktime_now(); - if (remaining < 100000) - ndelay(remaining); /* really small just spin */ - else { + if (remaining < 100000) { + /* for small delays (<100us), just loop until limit is reached */ + do { + end_time = ktime_now(); + } while (ktime_lt(end_time, spin_until)); + } else { /* see do_nanosleep */ hrtimer_init_sleeper(&t, current); do { @@ -2162,8 +2165,8 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) hrtimer_cancel(&t.timer); } while (t.task && pkt_dev->running && !signal_pending(current)); __set_current_state(TASK_RUNNING); + end_time = ktime_now(); } - end_time = ktime_now(); pkt_dev->idle_acc += ktime_to_ns(ktime_sub(end_time, start_time)); pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay); @@ -2602,18 +2605,18 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, if (!pkt_dev->page) break; } - skb_shinfo(skb)->frags[i].page = pkt_dev->page; get_page(pkt_dev->page); + skb_frag_set_page(skb, i, pkt_dev->page); skb_shinfo(skb)->frags[i].page_offset = 0; /*last fragment, fill rest of data*/ if (i == (frags - 1)) - skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); + skb_frag_size_set(&skb_shinfo(skb)->frags[i], + (datalen < PAGE_SIZE ? datalen : PAGE_SIZE)); else - skb_shinfo(skb)->frags[i].size = frag_len; - datalen -= skb_shinfo(skb)->frags[i].size; - skb->len += skb_shinfo(skb)->frags[i].size; - skb->data_len += skb_shinfo(skb)->frags[i].size; + skb_frag_size_set(&skb_shinfo(skb)->frags[i], frag_len); + datalen -= skb_frag_size(&skb_shinfo(skb)->frags[i]); + skb->len += skb_frag_size(&skb_shinfo(skb)->frags[i]); + skb->data_len += skb_frag_size(&skb_shinfo(skb)->frags[i]); i++; skb_shinfo(skb)->nr_frags = i; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 99d9e95..9083e82 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -731,7 +731,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev) size += num_vfs * (nla_total_size(sizeof(struct ifla_vf_mac)) + nla_total_size(sizeof(struct ifla_vf_vlan)) + - nla_total_size(sizeof(struct ifla_vf_tx_rate))); + nla_total_size(sizeof(struct ifla_vf_tx_rate)) + + nla_total_size(sizeof(struct ifla_vf_spoofchk))); return size; } else return 0; @@ -954,13 +955,27 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct ifla_vf_mac vf_mac; struct ifla_vf_vlan vf_vlan; struct ifla_vf_tx_rate vf_tx_rate; + struct ifla_vf_spoofchk vf_spoofchk; + + /* + * Not all SR-IOV capable drivers support the + * spoofcheck query. Preset to -1 so the user + * space tool can detect that the driver didn't + * report anything. + */ + ivi.spoofchk = -1; if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi)) break; - vf_mac.vf = vf_vlan.vf = vf_tx_rate.vf = ivi.vf; + vf_mac.vf = + vf_vlan.vf = + vf_tx_rate.vf = + vf_spoofchk.vf = ivi.vf; + memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); vf_vlan.vlan = ivi.vlan; vf_vlan.qos = ivi.qos; vf_tx_rate.rate = ivi.tx_rate; + vf_spoofchk.setting = ivi.spoofchk; vf = nla_nest_start(skb, IFLA_VF_INFO); if (!vf) { nla_nest_cancel(skb, vfinfo); @@ -968,7 +983,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, } NLA_PUT(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac); NLA_PUT(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan); - NLA_PUT(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), &vf_tx_rate); + NLA_PUT(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), + &vf_tx_rate); + NLA_PUT(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk), + &vf_spoofchk); nla_nest_end(skb, vf); } nla_nest_end(skb, vfinfo); @@ -1202,6 +1220,15 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) ivt->rate); break; } + case IFLA_VF_SPOOFCHK: { + struct ifla_vf_spoofchk *ivs; + ivs = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_spoofchk) + err = ops->ndo_set_vf_spoofchk(dev, ivs->vf, + ivs->setting); + break; + } default: err = -EINVAL; break; @@ -1604,7 +1631,6 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net, dev_net_set(dev, net); dev->rtnl_link_ops = ops; dev->rtnl_link_state = RTNL_LINK_INITIALIZING; - dev->real_num_tx_queues = real_num_queues; if (tb[IFLA_MTU]) dev->mtu = nla_get_u32(tb[IFLA_MTU]); diff --git a/net/core/scm.c b/net/core/scm.c index 811b53f..ff52ad0 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -173,7 +173,7 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) if (err) goto error; - if (pid_vnr(p->pid) != p->creds.pid) { + if (!p->pid || pid_vnr(p->pid) != p->creds.pid) { struct pid *pid; err = -ESRCH; pid = find_get_pid(p->creds.pid); @@ -183,8 +183,9 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) p->pid = pid; } - if ((p->cred->euid != p->creds.uid) || - (p->cred->egid != p->creds.gid)) { + if (!p->cred || + (p->cred->euid != p->creds.uid) || + (p->cred->egid != p->creds.gid)) { struct cred *cred; err = -ENOMEM; cred = prepare_creds(); @@ -193,7 +194,8 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) cred->uid = cred->euid = p->creds.uid; cred->gid = cred->egid = p->creds.gid; - put_cred(p->cred); + if (p->cred) + put_cred(p->cred); p->cred = cred; } break; diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 45329d7..025233d 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -35,7 +35,7 @@ static u32 seq_scale(u32 seq) } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -__u32 secure_tcpv6_sequence_number(__be32 *saddr, __be32 *daddr, +__u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, __be16 sport, __be16 dport) { u32 secret[MD5_MESSAGE_BYTES / 4]; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 387703f..18a3ceb 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -184,11 +184,21 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, goto out; prefetchw(skb); + /* We do our best to align skb_shared_info on a separate cache + * line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives + * aligned memory blocks, unless SLUB/SLAB debug is enabled. + * Both skb->head and skb_shared_info are cache line aligned. + */ size = SKB_DATA_ALIGN(size); - data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info), - gfp_mask, node); + size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + data = kmalloc_node_track_caller(size, gfp_mask, node); if (!data) goto nodata; + /* kmalloc(size) might give us more room than requested. + * Put skb_shared_info exactly at the end of allocated zone, + * to allow max possible filling before reallocation. + */ + size = SKB_WITH_OVERHEAD(ksize(data)); prefetchw(data + size); /* @@ -197,7 +207,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * the tail pointer in struct sk_buff! */ memset(skb, 0, offsetof(struct sk_buff, tail)); - skb->truesize = size + sizeof(struct sk_buff); + /* Account for allocated memory : skb + skb->head */ + skb->truesize = SKB_TRUESIZE(size); atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -326,7 +337,7 @@ static void skb_release_data(struct sk_buff *skb) if (skb_shinfo(skb)->nr_frags) { int i; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - put_page(skb_shinfo(skb)->frags[i].page); + skb_frag_unref(skb, i); } /* @@ -475,6 +486,30 @@ void consume_skb(struct sk_buff *skb) EXPORT_SYMBOL(consume_skb); /** + * skb_recycle - clean up an skb for reuse + * @skb: buffer + * + * Recycles the skb to be reused as a receive buffer. This + * function does any necessary reference count dropping, and + * cleans up the skbuff as if it just came from __alloc_skb(). + */ +void skb_recycle(struct sk_buff *skb) +{ + struct skb_shared_info *shinfo; + + skb_release_head_state(skb); + + shinfo = skb_shinfo(skb); + memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); + atomic_set(&shinfo->dataref, 1); + + memset(skb, 0, offsetof(struct sk_buff, tail)); + skb->data = skb->head + NET_SKB_PAD; + skb_reset_tail_pointer(skb); +} +EXPORT_SYMBOL(skb_recycle); + +/** * skb_recycle_check - check if skb can be reused for receive * @skb: buffer * @skb_size: minimum receive buffer size @@ -488,33 +523,10 @@ EXPORT_SYMBOL(consume_skb); */ bool skb_recycle_check(struct sk_buff *skb, int skb_size) { - struct skb_shared_info *shinfo; - - if (irqs_disabled()) - return false; - - if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) - return false; - - if (skb_is_nonlinear(skb) || skb->fclone != SKB_FCLONE_UNAVAILABLE) + if (!skb_is_recycleable(skb, skb_size)) return false; - skb_size = SKB_DATA_ALIGN(skb_size + NET_SKB_PAD); - if (skb_end_pointer(skb) - skb->head < skb_size) - return false; - - if (skb_shared(skb) || skb_cloned(skb)) - return false; - - skb_release_head_state(skb); - - shinfo = skb_shinfo(skb); - memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); - atomic_set(&shinfo->dataref, 1); - - memset(skb, 0, offsetof(struct sk_buff, tail)); - skb->data = skb->head + NET_SKB_PAD; - skb_reset_tail_pointer(skb); + skb_recycle(skb); return true; } @@ -529,6 +541,8 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->mac_header = old->mac_header; skb_dst_copy(new, old); new->rxhash = old->rxhash; + new->ooo_okay = old->ooo_okay; + new->l4_rxhash = old->l4_rxhash; #ifdef CONFIG_XFRM new->sp = secpath_get(old->sp); #endif @@ -647,7 +661,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) } vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]); memcpy(page_address(page), - vaddr + f->page_offset, f->size); + vaddr + f->page_offset, skb_frag_size(f)); kunmap_skb_frag(vaddr); page->private = (unsigned long)head; head = page; @@ -655,14 +669,14 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) /* skb frags release userspace buffers */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - put_page(skb_shinfo(skb)->frags[i].page); + skb_frag_unref(skb, i); uarg->callback(uarg); /* skb frags point to kernel buffers */ for (i = skb_shinfo(skb)->nr_frags; i > 0; i--) { - skb_shinfo(skb)->frags[i - 1].page_offset = 0; - skb_shinfo(skb)->frags[i - 1].page = head; + __skb_fill_page_desc(skb, i-1, head, 0, + skb_shinfo(skb)->frags[i - 1].size); head = (struct page *)head->private; } @@ -820,7 +834,7 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i]; - get_page(skb_shinfo(n)->frags[i].page); + skb_frag_ref(skb, i); } skb_shinfo(n)->nr_frags = i; } @@ -911,7 +925,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, goto nofrags; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - get_page(skb_shinfo(skb)->frags[i].page); + skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); @@ -1178,20 +1192,20 @@ int ___pskb_trim(struct sk_buff *skb, unsigned int len) goto drop_pages; for (; i < nfrags; i++) { - int end = offset + skb_shinfo(skb)->frags[i].size; + int end = offset + skb_frag_size(&skb_shinfo(skb)->frags[i]); if (end < len) { offset = end; continue; } - skb_shinfo(skb)->frags[i++].size = len - offset; + skb_frag_size_set(&skb_shinfo(skb)->frags[i++], len - offset); drop_pages: skb_shinfo(skb)->nr_frags = i; for (; i < nfrags; i++) - put_page(skb_shinfo(skb)->frags[i].page); + skb_frag_unref(skb, i); if (skb_has_frag_list(skb)) skb_drop_fraglist(skb); @@ -1294,9 +1308,11 @@ unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta) /* Estimate size of pulled pages. */ eat = delta; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - if (skb_shinfo(skb)->frags[i].size >= eat) + int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); + + if (size >= eat) goto pull_pages; - eat -= skb_shinfo(skb)->frags[i].size; + eat -= size; } /* If we need update frag list, we are in troubles. @@ -1359,14 +1375,16 @@ pull_pages: eat = delta; k = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - if (skb_shinfo(skb)->frags[i].size <= eat) { - put_page(skb_shinfo(skb)->frags[i].page); - eat -= skb_shinfo(skb)->frags[i].size; + int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); + + if (size <= eat) { + skb_frag_unref(skb, i); + eat -= size; } else { skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i]; if (eat) { skb_shinfo(skb)->frags[k].page_offset += eat; - skb_shinfo(skb)->frags[k].size -= eat; + skb_frag_size_sub(&skb_shinfo(skb)->frags[k], eat); eat = 0; } k++; @@ -1421,7 +1439,7 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { u8 *vaddr; @@ -1619,7 +1637,8 @@ static int __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; - if (__splice_segment(f->page, f->page_offset, f->size, + if (__splice_segment(skb_frag_page(f), + f->page_offset, skb_frag_size(f), offset, len, skb, spd, 0, sk, pipe)) return 1; } @@ -1729,7 +1748,7 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) WARN_ON(start > offset + len); - end = start + frag->size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { u8 *vaddr; @@ -1802,7 +1821,7 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { __wsum csum2; u8 *vaddr; @@ -1877,7 +1896,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { __wsum csum2; u8 *vaddr; @@ -2150,7 +2169,7 @@ static inline void skb_split_no_header(struct sk_buff *skb, skb->data_len = len - pos; for (i = 0; i < nfrags; i++) { - int size = skb_shinfo(skb)->frags[i].size; + int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (pos + size > len) { skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i]; @@ -2164,10 +2183,10 @@ static inline void skb_split_no_header(struct sk_buff *skb, * where splitting is expensive. * 2. Split is accurately. We make this. */ - get_page(skb_shinfo(skb)->frags[i].page); + skb_frag_ref(skb, i); skb_shinfo(skb1)->frags[0].page_offset += len - pos; - skb_shinfo(skb1)->frags[0].size -= len - pos; - skb_shinfo(skb)->frags[i].size = len - pos; + skb_frag_size_sub(&skb_shinfo(skb1)->frags[0], len - pos); + skb_frag_size_set(&skb_shinfo(skb)->frags[i], len - pos); skb_shinfo(skb)->nr_frags++; } k++; @@ -2239,12 +2258,13 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) * commit all, so that we don't have to undo partial changes */ if (!to || - !skb_can_coalesce(tgt, to, fragfrom->page, fragfrom->page_offset)) { + !skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), + fragfrom->page_offset)) { merge = -1; } else { merge = to - 1; - todo -= fragfrom->size; + todo -= skb_frag_size(fragfrom); if (todo < 0) { if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt)) @@ -2254,8 +2274,8 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) fragfrom = &skb_shinfo(skb)->frags[from]; fragto = &skb_shinfo(tgt)->frags[merge]; - fragto->size += shiftlen; - fragfrom->size -= shiftlen; + skb_frag_size_add(fragto, shiftlen); + skb_frag_size_sub(fragfrom, shiftlen); fragfrom->page_offset += shiftlen; goto onlymerged; @@ -2279,20 +2299,20 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) fragfrom = &skb_shinfo(skb)->frags[from]; fragto = &skb_shinfo(tgt)->frags[to]; - if (todo >= fragfrom->size) { + if (todo >= skb_frag_size(fragfrom)) { *fragto = *fragfrom; - todo -= fragfrom->size; + todo -= skb_frag_size(fragfrom); from++; to++; } else { - get_page(fragfrom->page); + __skb_frag_ref(fragfrom); fragto->page = fragfrom->page; fragto->page_offset = fragfrom->page_offset; - fragto->size = todo; + skb_frag_size_set(fragto, todo); fragfrom->page_offset += todo; - fragfrom->size -= todo; + skb_frag_size_sub(fragfrom, todo); todo = 0; to++; @@ -2307,8 +2327,8 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) fragfrom = &skb_shinfo(skb)->frags[0]; fragto = &skb_shinfo(tgt)->frags[merge]; - fragto->size += fragfrom->size; - put_page(fragfrom->page); + skb_frag_size_add(fragto, skb_frag_size(fragfrom)); + __skb_frag_unref(fragfrom); } /* Reposition in the original skb */ @@ -2405,7 +2425,7 @@ next_skb: while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) { frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx]; - block_limit = frag->size + st->stepped_offset; + block_limit = skb_frag_size(frag) + st->stepped_offset; if (abs_offset < block_limit) { if (!st->frag_data) @@ -2423,7 +2443,7 @@ next_skb: } st->frag_idx++; - st->stepped_offset += frag->size; + st->stepped_offset += skb_frag_size(frag); } if (st->frag_data) { @@ -2553,14 +2573,13 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, left = PAGE_SIZE - frag->page_offset; copy = (length > left)? left : length; - ret = getfrag(from, (page_address(frag->page) + - frag->page_offset + frag->size), + ret = getfrag(from, skb_frag_address(frag) + skb_frag_size(frag), offset, copy, 0, skb); if (ret < 0) return -EFAULT; /* copy was successful so update the size parameters */ - frag->size += copy; + skb_frag_size_add(frag, copy); skb->len += copy; skb->data_len += copy; offset += copy; @@ -2706,12 +2725,12 @@ struct sk_buff *skb_segment(struct sk_buff *skb, u32 features) while (pos < offset + len && i < nfrags) { *frag = skb_shinfo(skb)->frags[i]; - get_page(frag->page); - size = frag->size; + __skb_frag_ref(frag); + size = skb_frag_size(frag); if (pos < offset) { frag->page_offset += offset - pos; - frag->size -= offset - pos; + skb_frag_size_sub(frag, offset - pos); } skb_shinfo(nskb)->nr_frags++; @@ -2720,7 +2739,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, u32 features) i++; pos += size; } else { - frag->size -= pos + size - (offset + len); + skb_frag_size_sub(frag, pos + size - (offset + len)); goto skip_fraglist; } @@ -2800,7 +2819,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) } while (--i); frag->page_offset += offset; - frag->size -= offset; + skb_frag_size_sub(frag, offset); skb->truesize -= skb->data_len; skb->len -= skb->data_len; @@ -2852,7 +2871,7 @@ merge: unsigned int eat = offset - headlen; skbinfo->frags[0].page_offset += eat; - skbinfo->frags[0].size -= eat; + skb_frag_size_sub(&skbinfo->frags[0], eat); skb->data_len -= eat; skb->len -= eat; offset = headlen; @@ -2923,13 +2942,13 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (copy > len) copy = len; - sg_set_page(&sg[elt], frag->page, copy, + sg_set_page(&sg[elt], skb_frag_page(frag), copy, frag->page_offset+offset-start); elt++; if (!(len -= copy)) diff --git a/net/core/sock.c b/net/core/sock.c index bc745d0..4ed7b1d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -207,7 +207,7 @@ static struct lock_class_key af_callback_keys[AF_MAX]; * not depend upon such differences. */ #define _SK_MEM_PACKETS 256 -#define _SK_MEM_OVERHEAD (sizeof(struct sk_buff) + 256) +#define _SK_MEM_OVERHEAD SKB_TRUESIZE(256) #define SK_WMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) #define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) @@ -387,7 +387,7 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { sk_tx_queue_clear(sk); - rcu_assign_pointer(sk->sk_dst_cache, NULL); + RCU_INIT_POINTER(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; } @@ -738,10 +738,7 @@ set_rcvbuf: /* We implement the SO_SNDLOWAT etc to not be settable (1003.1g 5.3) */ case SO_RXQ_OVFL: - if (valbool) - sock_set_flag(sk, SOCK_RXQ_OVFL); - else - sock_reset_flag(sk, SOCK_RXQ_OVFL); + sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool); break; default: ret = -ENOPROTOOPT; @@ -1158,7 +1155,7 @@ static void __sk_free(struct sock *sk) atomic_read(&sk->sk_wmem_alloc) == 0); if (filter) { sk_filter_uncharge(sk, filter); - rcu_assign_pointer(sk->sk_filter, NULL); + RCU_INIT_POINTER(sk->sk_filter, NULL); } sock_disable_timestamp(sk, SOCK_TIMESTAMP); @@ -1260,6 +1257,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ newsk->sk_destruct = NULL; + bh_unlock_sock(newsk); sk_free(newsk); newsk = NULL; goto out; @@ -1533,7 +1531,6 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, skb_shinfo(skb)->nr_frags = npages; for (i = 0; i < npages; i++) { struct page *page; - skb_frag_t *frag; page = alloc_pages(sk->sk_allocation, 0); if (!page) { @@ -1543,12 +1540,11 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, goto failure; } - frag = &skb_shinfo(skb)->frags[i]; - frag->page = page; - frag->page_offset = 0; - frag->size = (data_len >= PAGE_SIZE ? - PAGE_SIZE : - data_len); + __skb_fill_page_desc(skb, i, + page, 0, + (data_len >= PAGE_SIZE ? + PAGE_SIZE : + data_len)); data_len -= PAGE_SIZE; } diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 98a5264..82fb288 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -57,9 +57,13 @@ void skb_clone_tx_timestamp(struct sk_buff *skb) case PTP_CLASS_V2_VLAN: phydev = skb->dev->phydev; if (likely(phydev->drv->txtstamp)) { + if (!atomic_inc_not_zero(&sk->sk_refcnt)) + return; clone = skb_clone(skb, GFP_ATOMIC); - if (!clone) + if (!clone) { + sock_put(sk); return; + } clone->sk = sk; phydev->drv->txtstamp(phydev, clone, type); } @@ -77,8 +81,11 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, struct sock_exterr_skb *serr; int err; - if (!hwtstamps) + if (!hwtstamps) { + sock_put(sk); + kfree_skb(skb); return; + } *skb_hwtstamps(skb) = *hwtstamps; serr = SKB_EXT_ERR(skb); @@ -87,6 +94,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; skb->sk = NULL; err = sock_queue_err_skb(sk, skb); + sock_put(sk); if (err) kfree_skb(skb); } diff --git a/net/core/user_dma.c b/net/core/user_dma.c index 25d717e..2d7cf3d 100644 --- a/net/core/user_dma.c +++ b/net/core/user_dma.c @@ -71,14 +71,14 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, /* Copy paged appendix. Hmm... why does this look so complicated? */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(frag); copy = end - offset; if (copy > 0) { - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - struct page *page = frag->page; + struct page *page = skb_frag_page(frag); if (copy > len) copy = len; diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 3cb56af..9bfbc1d 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1255,7 +1255,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) spin_lock(&dcb_lock); list_for_each_entry(itr, &dcb_app_list, list) { - if (strncmp(itr->name, netdev->name, IFNAMSIZ) == 0) { + if (itr->ifindex == netdev->ifindex) { err = nla_put(skb, DCB_ATTR_IEEE_APP, sizeof(itr->app), &itr->app); if (err) { @@ -1412,7 +1412,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) goto dcb_unlock; list_for_each_entry(itr, &dcb_app_list, list) { - if (strncmp(itr->name, netdev->name, IFNAMSIZ) == 0) { + if (itr->ifindex == netdev->ifindex) { struct nlattr *app_nest = nla_nest_start(skb, DCB_ATTR_APP); if (!app_nest) @@ -2050,7 +2050,7 @@ u8 dcb_getapp(struct net_device *dev, struct dcb_app *app) list_for_each_entry(itr, &dcb_app_list, list) { if (itr->app.selector == app->selector && itr->app.protocol == app->protocol && - (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) { + itr->ifindex == dev->ifindex) { prio = itr->app.priority; break; } @@ -2073,15 +2073,17 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new) struct dcb_app_type *itr; struct dcb_app_type event; - memcpy(&event.name, dev->name, sizeof(event.name)); + event.ifindex = dev->ifindex; memcpy(&event.app, new, sizeof(event.app)); + if (dev->dcbnl_ops->getdcbx) + event.dcbx = dev->dcbnl_ops->getdcbx(dev); spin_lock(&dcb_lock); /* Search for existing match and replace */ list_for_each_entry(itr, &dcb_app_list, list) { if (itr->app.selector == new->selector && itr->app.protocol == new->protocol && - (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) { + itr->ifindex == dev->ifindex) { if (new->priority) itr->app.priority = new->priority; else { @@ -2101,7 +2103,7 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new) } memcpy(&entry->app, new, sizeof(*new)); - strncpy(entry->name, dev->name, IFNAMSIZ); + entry->ifindex = dev->ifindex; list_add(&entry->list, &dcb_app_list); } out: @@ -2127,7 +2129,7 @@ u8 dcb_ieee_getapp_mask(struct net_device *dev, struct dcb_app *app) list_for_each_entry(itr, &dcb_app_list, list) { if (itr->app.selector == app->selector && itr->app.protocol == app->protocol && - (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) { + itr->ifindex == dev->ifindex) { prio |= 1 << itr->app.priority; } } @@ -2150,8 +2152,10 @@ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new) struct dcb_app_type event; int err = 0; - memcpy(&event.name, dev->name, sizeof(event.name)); + event.ifindex = dev->ifindex; memcpy(&event.app, new, sizeof(event.app)); + if (dev->dcbnl_ops->getdcbx) + event.dcbx = dev->dcbnl_ops->getdcbx(dev); spin_lock(&dcb_lock); /* Search for existing match and abort if found */ @@ -2159,7 +2163,7 @@ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new) if (itr->app.selector == new->selector && itr->app.protocol == new->protocol && itr->app.priority == new->priority && - (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) { + itr->ifindex == dev->ifindex) { err = -EEXIST; goto out; } @@ -2173,7 +2177,7 @@ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new) } memcpy(&entry->app, new, sizeof(*new)); - strncpy(entry->name, dev->name, IFNAMSIZ); + entry->ifindex = dev->ifindex; list_add(&entry->list, &dcb_app_list); out: spin_unlock(&dcb_lock); @@ -2194,8 +2198,10 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del) struct dcb_app_type event; int err = -ENOENT; - memcpy(&event.name, dev->name, sizeof(event.name)); + event.ifindex = dev->ifindex; memcpy(&event.app, del, sizeof(event.app)); + if (dev->dcbnl_ops->getdcbx) + event.dcbx = dev->dcbnl_ops->getdcbx(dev); spin_lock(&dcb_lock); /* Search for existing match and remove it. */ @@ -2203,7 +2209,7 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del) if (itr->app.selector == del->selector && itr->app.protocol == del->protocol && itr->app.priority == del->priority && - (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) { + itr->ifindex == dev->ifindex) { list_del(&itr->list); kfree(itr); err = 0; diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index 0462040..67164bb 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -85,7 +85,6 @@ static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val) { - struct dccp_sock *dp = dccp_sk(sk); u32 max_ratio = DIV_ROUND_UP(ccid2_hc_tx_sk(sk)->tx_cwnd, 2); /* @@ -98,14 +97,33 @@ static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val) DCCP_WARN("Limiting Ack Ratio (%u) to %u\n", val, max_ratio); val = max_ratio; } - if (val > DCCPF_ACK_RATIO_MAX) - val = DCCPF_ACK_RATIO_MAX; + dccp_feat_signal_nn_change(sk, DCCPF_ACK_RATIO, + min_t(u32, val, DCCPF_ACK_RATIO_MAX)); +} - if (val == dp->dccps_l_ack_ratio) - return; +static void ccid2_check_l_ack_ratio(struct sock *sk) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - ccid2_pr_debug("changing local ack ratio to %u\n", val); - dp->dccps_l_ack_ratio = val; + /* + * After a loss, idle period, application limited period, or RTO we + * need to check that the ack ratio is still less than the congestion + * window. Otherwise, we will send an entire congestion window of + * packets and got no response because we haven't sent ack ratio + * packets yet. + * If the ack ratio does need to be reduced, we reduce it to half of + * the congestion window (or 1 if that's zero) instead of to the + * congestion window. This prevents problems if one ack is lost. + */ + if (dccp_feat_nn_get(sk, DCCPF_ACK_RATIO) > hc->tx_cwnd) + ccid2_change_l_ack_ratio(sk, hc->tx_cwnd/2 ? : 1U); +} + +static void ccid2_change_l_seq_window(struct sock *sk, u64 val) +{ + dccp_feat_signal_nn_change(sk, DCCPF_SEQUENCE_WINDOW, + clamp_val(val, DCCPF_SEQ_WMIN, + DCCPF_SEQ_WMAX)); } static void ccid2_hc_tx_rto_expire(unsigned long data) @@ -187,6 +205,8 @@ static void ccid2_cwnd_application_limited(struct sock *sk, const u32 now) } hc->tx_cwnd_used = 0; hc->tx_cwnd_stamp = now; + + ccid2_check_l_ack_ratio(sk); } /* This borrows the code of tcp_cwnd_restart() */ @@ -205,6 +225,8 @@ static void ccid2_cwnd_restart(struct sock *sk, const u32 now) hc->tx_cwnd_stamp = now; hc->tx_cwnd_used = 0; + + ccid2_check_l_ack_ratio(sk); } static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len) @@ -405,17 +427,37 @@ static void ccid2_new_ack(struct sock *sk, struct ccid2_seq *seqp, unsigned int *maxincr) { struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - - if (hc->tx_cwnd < hc->tx_ssthresh) { - if (*maxincr > 0 && ++hc->tx_packets_acked == 2) { + struct dccp_sock *dp = dccp_sk(sk); + int r_seq_used = hc->tx_cwnd / dp->dccps_l_ack_ratio; + + if (hc->tx_cwnd < dp->dccps_l_seq_win && + r_seq_used < dp->dccps_r_seq_win) { + if (hc->tx_cwnd < hc->tx_ssthresh) { + if (*maxincr > 0 && ++hc->tx_packets_acked >= 2) { + hc->tx_cwnd += 1; + *maxincr -= 1; + hc->tx_packets_acked = 0; + } + } else if (++hc->tx_packets_acked >= hc->tx_cwnd) { hc->tx_cwnd += 1; - *maxincr -= 1; hc->tx_packets_acked = 0; } - } else if (++hc->tx_packets_acked >= hc->tx_cwnd) { - hc->tx_cwnd += 1; - hc->tx_packets_acked = 0; } + + /* + * Adjust the local sequence window and the ack ratio to allow about + * 5 times the number of packets in the network (RFC 4340 7.5.2) + */ + if (r_seq_used * CCID2_WIN_CHANGE_FACTOR >= dp->dccps_r_seq_win) + ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio * 2); + else if (r_seq_used * CCID2_WIN_CHANGE_FACTOR < dp->dccps_r_seq_win/2) + ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio / 2 ? : 1U); + + if (hc->tx_cwnd * CCID2_WIN_CHANGE_FACTOR >= dp->dccps_l_seq_win) + ccid2_change_l_seq_window(sk, dp->dccps_l_seq_win * 2); + else if (hc->tx_cwnd * CCID2_WIN_CHANGE_FACTOR < dp->dccps_l_seq_win/2) + ccid2_change_l_seq_window(sk, dp->dccps_l_seq_win / 2); + /* * FIXME: RTT is sampled several times per acknowledgment (for each * entry in the Ack Vector), instead of once per Ack (as in TCP SACK). @@ -441,9 +483,7 @@ static void ccid2_congestion_event(struct sock *sk, struct ccid2_seq *seqp) hc->tx_cwnd = hc->tx_cwnd / 2 ? : 1U; hc->tx_ssthresh = max(hc->tx_cwnd, 2U); - /* Avoid spurious timeouts resulting from Ack Ratio > cwnd */ - if (dccp_sk(sk)->dccps_l_ack_ratio > hc->tx_cwnd) - ccid2_change_l_ack_ratio(sk, hc->tx_cwnd); + ccid2_check_l_ack_ratio(sk); } static int ccid2_hc_tx_parse_options(struct sock *sk, u8 packet_type, @@ -494,8 +534,16 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) if (hc->tx_rpdupack >= NUMDUPACK) { hc->tx_rpdupack = -1; /* XXX lame */ hc->tx_rpseq = 0; - +#ifdef __CCID2_COPES_GRACEFULLY_WITH_ACK_CONGESTION_CONTROL__ + /* + * FIXME: Ack Congestion Control is broken; in + * the current state instabilities occurred with + * Ack Ratios greater than 1; causing hang-ups + * and long RTO timeouts. This needs to be fixed + * before opening up dynamic changes. -- gerrit + */ ccid2_change_l_ack_ratio(sk, 2 * dp->dccps_l_ack_ratio); +#endif } } } diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h index f585d33..18c9754 100644 --- a/net/dccp/ccids/ccid2.h +++ b/net/dccp/ccids/ccid2.h @@ -43,6 +43,12 @@ struct ccid2_seq { #define CCID2_SEQBUF_LEN 1024 #define CCID2_SEQBUF_MAX 128 +/* + * Multiple of congestion window to keep the sequence window at + * (RFC 4340 7.5.2) + */ +#define CCID2_WIN_CHANGE_FACTOR 5 + /** * struct ccid2_hc_tx_sock - CCID2 TX half connection * @tx_{cwnd,ssthresh,pipe}: as per RFC 4341, section 5 diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 5fdb072..583490a 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -474,6 +474,7 @@ static inline int dccp_ack_pending(const struct sock *sk) return dccp_ackvec_pending(sk) || inet_csk_ack_scheduled(sk); } +extern int dccp_feat_signal_nn_change(struct sock *sk, u8 feat, u64 nn_val); extern int dccp_feat_finalise_settings(struct dccp_sock *dp); extern int dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq); extern int dccp_feat_insert_opts(struct dccp_sock*, struct dccp_request_sock*, diff --git a/net/dccp/feat.c b/net/dccp/feat.c index 568def9..23cea0e 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -12,6 +12,7 @@ * ----------- * o Feature negotiation is coordinated with connection setup (as in TCP), wild * changes of parameters of an established connection are not supported. + * o Changing non-negotiable (NN) values is supported in state OPEN/PARTOPEN. * o All currently known SP features have 1-byte quantities. If in the future * extensions of RFCs 4340..42 define features with item lengths larger than * one byte, a feature-specific extension of the code will be required. @@ -343,6 +344,20 @@ static int __dccp_feat_activate(struct sock *sk, const int idx, return dccp_feat_table[idx].activation_hdlr(sk, val, rx); } +/** + * dccp_feat_activate - Activate feature value on socket + * @sk: fully connected DCCP socket (after handshake is complete) + * @feat_num: feature to activate, one of %dccp_feature_numbers + * @local: whether local (1) or remote (0) @feat_num is meant + * @fval: the value (SP or NN) to activate, or NULL to use the default value + * For general use this function is preferable over __dccp_feat_activate(). + */ +static int dccp_feat_activate(struct sock *sk, u8 feat_num, bool local, + dccp_feat_val const *fval) +{ + return __dccp_feat_activate(sk, dccp_feat_index(feat_num), local, fval); +} + /* Test for "Req'd" feature (RFC 4340, 6.4) */ static inline int dccp_feat_must_be_understood(u8 feat_num) { @@ -650,11 +665,22 @@ int dccp_feat_insert_opts(struct dccp_sock *dp, struct dccp_request_sock *dreq, return -1; if (pos->needs_mandatory && dccp_insert_option_mandatory(skb)) return -1; - /* - * Enter CHANGING after transmitting the Change option (6.6.2). - */ - if (pos->state == FEAT_INITIALISING) - pos->state = FEAT_CHANGING; + + if (skb->sk->sk_state == DCCP_OPEN && + (opt == DCCPO_CONFIRM_R || opt == DCCPO_CONFIRM_L)) { + /* + * Confirms don't get retransmitted (6.6.3) once the + * connection is in state OPEN + */ + dccp_feat_list_pop(pos); + } else { + /* + * Enter CHANGING after transmitting the Change + * option (6.6.2). + */ + if (pos->state == FEAT_INITIALISING) + pos->state = FEAT_CHANGING; + } } return 0; } @@ -730,6 +756,70 @@ int dccp_feat_register_sp(struct sock *sk, u8 feat, u8 is_local, 0, list, len); } +/** + * dccp_feat_nn_get - Query current/pending value of NN feature + * @sk: DCCP socket of an established connection + * @feat: NN feature number from %dccp_feature_numbers + * For a known NN feature, returns value currently being negotiated, or + * current (confirmed) value if no negotiation is going on. + */ +u64 dccp_feat_nn_get(struct sock *sk, u8 feat) +{ + if (dccp_feat_type(feat) == FEAT_NN) { + struct dccp_sock *dp = dccp_sk(sk); + struct dccp_feat_entry *entry; + + entry = dccp_feat_list_lookup(&dp->dccps_featneg, feat, 1); + if (entry != NULL) + return entry->val.nn; + + switch (feat) { + case DCCPF_ACK_RATIO: + return dp->dccps_l_ack_ratio; + case DCCPF_SEQUENCE_WINDOW: + return dp->dccps_l_seq_win; + } + } + DCCP_BUG("attempt to look up unsupported feature %u", feat); + return 0; +} +EXPORT_SYMBOL_GPL(dccp_feat_nn_get); + +/** + * dccp_feat_signal_nn_change - Update NN values for an established connection + * @sk: DCCP socket of an established connection + * @feat: NN feature number from %dccp_feature_numbers + * @nn_val: the new value to use + * This function is used to communicate NN updates out-of-band. + */ +int dccp_feat_signal_nn_change(struct sock *sk, u8 feat, u64 nn_val) +{ + struct list_head *fn = &dccp_sk(sk)->dccps_featneg; + dccp_feat_val fval = { .nn = nn_val }; + struct dccp_feat_entry *entry; + + if (sk->sk_state != DCCP_OPEN && sk->sk_state != DCCP_PARTOPEN) + return 0; + + if (dccp_feat_type(feat) != FEAT_NN || + !dccp_feat_is_valid_nn_val(feat, nn_val)) + return -EINVAL; + + if (nn_val == dccp_feat_nn_get(sk, feat)) + return 0; /* already set or negotiation under way */ + + entry = dccp_feat_list_lookup(fn, feat, 1); + if (entry != NULL) { + dccp_pr_debug("Clobbering existing NN entry %llu -> %llu\n", + (unsigned long long)entry->val.nn, + (unsigned long long)nn_val); + dccp_feat_list_pop(entry); + } + + inet_csk_schedule_ack(sk); + return dccp_feat_push_change(fn, feat, 1, 0, &fval); +} +EXPORT_SYMBOL_GPL(dccp_feat_signal_nn_change); /* * Tracking features whose value depend on the choice of CCID @@ -1187,6 +1277,100 @@ confirmation_failed: } /** + * dccp_feat_handle_nn_established - Fast-path reception of NN options + * @sk: socket of an established DCCP connection + * @mandatory: whether @opt was preceded by a Mandatory option + * @opt: %DCCPO_CHANGE_L | %DCCPO_CONFIRM_R (NN only) + * @feat: NN number, one of %dccp_feature_numbers + * @val: NN value + * @len: length of @val in bytes + * This function combines the functionality of change_recv/confirm_recv, with + * the following differences (reset codes are the same): + * - cleanup after receiving the Confirm; + * - values are directly activated after successful parsing; + * - deliberately restricted to NN features. + * The restriction to NN features is essential since SP features can have non- + * predictable outcomes (depending on the remote configuration), and are inter- + * dependent (CCIDs for instance cause further dependencies). + */ +static u8 dccp_feat_handle_nn_established(struct sock *sk, u8 mandatory, u8 opt, + u8 feat, u8 *val, u8 len) +{ + struct list_head *fn = &dccp_sk(sk)->dccps_featneg; + const bool local = (opt == DCCPO_CONFIRM_R); + struct dccp_feat_entry *entry; + u8 type = dccp_feat_type(feat); + dccp_feat_val fval; + + dccp_feat_print_opt(opt, feat, val, len, mandatory); + + /* Ignore non-mandatory unknown and non-NN features */ + if (type == FEAT_UNKNOWN) { + if (local && !mandatory) + return 0; + goto fast_path_unknown; + } else if (type != FEAT_NN) { + return 0; + } + + /* + * We don't accept empty Confirms, since in fast-path feature + * negotiation the values are enabled immediately after sending + * the Change option. + * Empty Changes on the other hand are invalid (RFC 4340, 6.1). + */ + if (len == 0 || len > sizeof(fval.nn)) + goto fast_path_unknown; + + if (opt == DCCPO_CHANGE_L) { + fval.nn = dccp_decode_value_var(val, len); + if (!dccp_feat_is_valid_nn_val(feat, fval.nn)) + goto fast_path_unknown; + + if (dccp_feat_push_confirm(fn, feat, local, &fval) || + dccp_feat_activate(sk, feat, local, &fval)) + return DCCP_RESET_CODE_TOO_BUSY; + + /* set the `Ack Pending' flag to piggyback a Confirm */ + inet_csk_schedule_ack(sk); + + } else if (opt == DCCPO_CONFIRM_R) { + entry = dccp_feat_list_lookup(fn, feat, local); + if (entry == NULL || entry->state != FEAT_CHANGING) + return 0; + + fval.nn = dccp_decode_value_var(val, len); + /* + * Just ignore a value that doesn't match our current value. + * If the option changes twice within two RTTs, then at least + * one CONFIRM will be received for the old value after a + * new CHANGE was sent. + */ + if (fval.nn != entry->val.nn) + return 0; + + /* Only activate after receiving the Confirm option (6.6.1). */ + dccp_feat_activate(sk, feat, local, &fval); + + /* It has been confirmed - so remove the entry */ + dccp_feat_list_pop(entry); + + } else { + DCCP_WARN("Received illegal option %u\n", opt); + goto fast_path_failed; + } + return 0; + +fast_path_unknown: + if (!mandatory) + return dccp_push_empty_confirm(fn, feat, local); + +fast_path_failed: + return mandatory ? DCCP_RESET_CODE_MANDATORY_ERROR + : DCCP_RESET_CODE_OPTION_ERROR; +} + +/** * dccp_feat_parse_options - Process Feature-Negotiation Options * @sk: for general use and used by the client during connection setup * @dreq: used by the server during connection setup @@ -1221,6 +1405,14 @@ int dccp_feat_parse_options(struct sock *sk, struct dccp_request_sock *dreq, return dccp_feat_confirm_recv(fn, mandatory, opt, feat, val, len, server); } + break; + /* + * Support for exchanging NN options on an established connection. + */ + case DCCP_OPEN: + case DCCP_PARTOPEN: + return dccp_feat_handle_nn_established(sk, mandatory, opt, feat, + val, len); } return 0; /* ignore FN options in all other states */ } diff --git a/net/dccp/feat.h b/net/dccp/feat.h index e56a4e5..90b957d 100644 --- a/net/dccp/feat.h +++ b/net/dccp/feat.h @@ -129,6 +129,7 @@ extern int dccp_feat_clone_list(struct list_head const *, struct list_head *); extern void dccp_encode_value_var(const u64 value, u8 *to, const u8 len); extern u64 dccp_decode_value_var(const u8 *bf, const u8 len); +extern u64 dccp_feat_nn_get(struct sock *sk, u8 feat); extern int dccp_insert_option_mandatory(struct sk_buff *skb); extern int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat, diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 332639b..90a919a 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -433,6 +433,7 @@ exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: + bh_unlock_sock(newsk); sock_put(newsk); goto exit; } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index b74f761..17ee85c 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -271,7 +271,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, &ireq6->loc_addr, &ireq6->rmt_addr); ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr); - err = ip6_xmit(sk, skb, &fl6, opt); + err = ip6_xmit(sk, skb, &fl6, opt, np->tclass); err = net_xmit_eval(err); } @@ -326,7 +326,7 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL, false); if (!IS_ERR(dst)) { skb_dst_set(skb, dst); - ip6_xmit(ctl_sk, skb, &fl6, NULL); + ip6_xmit(ctl_sk, skb, &fl6, NULL, 0); DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS); return; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 152975d..e742f90 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -184,7 +184,6 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) dp->dccps_rate_last = jiffies; dp->dccps_role = DCCP_ROLE_UNDEFINED; dp->dccps_service = DCCP_SERVICE_CODE_IS_ABSENT; - dp->dccps_l_ack_ratio = dp->dccps_r_ack_ratio = 1; dp->dccps_tx_qlen = sysctl_dccp_tx_qlen; dccp_init_xmit_timers(sk); diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index ba4face..2ab16e1 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -388,7 +388,7 @@ static int dn_dev_insert_ifa(struct dn_dev *dn_db, struct dn_ifaddr *ifa) } ifa->ifa_next = dn_db->ifa_list; - rcu_assign_pointer(dn_db->ifa_list, ifa); + RCU_INIT_POINTER(dn_db->ifa_list, ifa); dn_ifaddr_notify(RTM_NEWADDR, ifa); blocking_notifier_call_chain(&dnaddr_chain, NETDEV_UP, ifa); @@ -1093,7 +1093,7 @@ static struct dn_dev *dn_dev_create(struct net_device *dev, int *err) memcpy(&dn_db->parms, p, sizeof(struct dn_dev_parms)); - rcu_assign_pointer(dev->dn_ptr, dn_db); + RCU_INIT_POINTER(dev->dn_ptr, dn_db); dn_db->dev = dev; init_timer(&dn_db->timer); @@ -1101,7 +1101,7 @@ static struct dn_dev *dn_dev_create(struct net_device *dev, int *err) dn_db->neigh_parms = neigh_parms_alloc(dev, &dn_neigh_table); if (!dn_db->neigh_parms) { - rcu_assign_pointer(dev->dn_ptr, NULL); + RCU_INIT_POINTER(dev->dn_ptr, NULL); kfree(dn_db); return NULL; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 0a47b6c..56cf9b8 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -301,7 +301,6 @@ static const struct net_device_ops dsa_netdev_ops = { .ndo_start_xmit = dsa_xmit, .ndo_change_rx_flags = dsa_slave_change_rx_flags, .ndo_set_rx_mode = dsa_slave_set_rx_mode, - .ndo_set_multicast_list = dsa_slave_set_rx_mode, .ndo_set_mac_address = dsa_slave_set_mac_address, .ndo_do_ioctl = dsa_slave_ioctl, }; @@ -314,7 +313,6 @@ static const struct net_device_ops edsa_netdev_ops = { .ndo_start_xmit = edsa_xmit, .ndo_change_rx_flags = dsa_slave_change_rx_flags, .ndo_set_rx_mode = dsa_slave_set_rx_mode, - .ndo_set_multicast_list = dsa_slave_set_rx_mode, .ndo_set_mac_address = dsa_slave_set_mac_address, .ndo_do_ioctl = dsa_slave_ioctl, }; @@ -327,7 +325,6 @@ static const struct net_device_ops trailer_netdev_ops = { .ndo_start_xmit = trailer_xmit, .ndo_change_rx_flags = dsa_slave_change_rx_flags, .ndo_set_rx_mode = dsa_slave_set_rx_mode, - .ndo_set_multicast_list = dsa_slave_set_rx_mode, .ndo_set_mac_address = dsa_slave_set_mac_address, .ndo_do_ioctl = dsa_slave_ioctl, }; diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c new file mode 100644 index 0000000..19d6aef --- /dev/null +++ b/net/ieee802154/6lowpan.c @@ -0,0 +1,891 @@ +/* + * Copyright 2011, Siemens AG + * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com> + */ + +/* + * Based on patches from Jon Smirl <jonsmirl@gmail.com> + * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + */ + +/* Jon's code is based on 6lowpan implementation for Contiki which is: + * Copyright (c) 2008, Swedish Institute of Computer Science. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the Institute nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#define DEBUG + +#include <linux/bitops.h> +#include <linux/if_arp.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/netdevice.h> +#include <net/af_ieee802154.h> +#include <net/ieee802154.h> +#include <net/ieee802154_netdev.h> +#include <net/ipv6.h> + +#include "6lowpan.h" + +/* TTL uncompression values */ +static const u8 lowpan_ttl_values[] = {0, 1, 64, 255}; + +static LIST_HEAD(lowpan_devices); + +/* + * Uncompression of linklocal: + * 0 -> 16 bytes from packet + * 1 -> 2 bytes from prefix - bunch of zeroes and 8 from packet + * 2 -> 2 bytes from prefix - zeroes + 2 from packet + * 3 -> 2 bytes from prefix - infer 8 bytes from lladdr + * + * NOTE: => the uncompress function does change 0xf to 0x10 + * NOTE: 0x00 => no-autoconfig => unspecified + */ +static const u8 lowpan_unc_llconf[] = {0x0f, 0x28, 0x22, 0x20}; + +/* + * Uncompression of ctx-based: + * 0 -> 0 bits from packet [unspecified / reserved] + * 1 -> 8 bytes from prefix - bunch of zeroes and 8 from packet + * 2 -> 8 bytes from prefix - zeroes + 2 from packet + * 3 -> 8 bytes from prefix - infer 8 bytes from lladdr + */ +static const u8 lowpan_unc_ctxconf[] = {0x00, 0x88, 0x82, 0x80}; + +/* + * Uncompression of ctx-base + * 0 -> 0 bits from packet + * 1 -> 2 bytes from prefix - bunch of zeroes 5 from packet + * 2 -> 2 bytes from prefix - zeroes + 3 from packet + * 3 -> 2 bytes from prefix - infer 1 bytes from lladdr + */ +static const u8 lowpan_unc_mxconf[] = {0x0f, 0x25, 0x23, 0x21}; + +/* Link local prefix */ +static const u8 lowpan_llprefix[] = {0xfe, 0x80}; + +/* private device info */ +struct lowpan_dev_info { + struct net_device *real_dev; /* real WPAN device ptr */ + struct mutex dev_list_mtx; /* mutex for list ops */ +}; + +struct lowpan_dev_record { + struct net_device *ldev; + struct list_head list; +}; + +static inline struct +lowpan_dev_info *lowpan_dev_info(const struct net_device *dev) +{ + return netdev_priv(dev); +} + +static inline void lowpan_address_flip(u8 *src, u8 *dest) +{ + int i; + for (i = 0; i < IEEE802154_ADDR_LEN; i++) + (dest)[IEEE802154_ADDR_LEN - i - 1] = (src)[i]; +} + +/* list of all 6lowpan devices, uses for package delivering */ +/* print data in line */ +static inline void lowpan_raw_dump_inline(const char *caller, char *msg, + unsigned char *buf, int len) +{ +#ifdef DEBUG + if (msg) + pr_debug("(%s) %s: ", caller, msg); + print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_NONE, + 16, 1, buf, len, false); +#endif /* DEBUG */ +} + +/* + * print data in a table format: + * + * addr: xx xx xx xx xx xx + * addr: xx xx xx xx xx xx + * ... + */ +static inline void lowpan_raw_dump_table(const char *caller, char *msg, + unsigned char *buf, int len) +{ +#ifdef DEBUG + if (msg) + pr_debug("(%s) %s:\n", caller, msg); + print_hex_dump(KERN_DEBUG, "\t", DUMP_PREFIX_OFFSET, + 16, 1, buf, len, false); +#endif /* DEBUG */ +} + +static u8 +lowpan_compress_addr_64(u8 **hc06_ptr, u8 shift, const struct in6_addr *ipaddr, + const unsigned char *lladdr) +{ + u8 val = 0; + + if (is_addr_mac_addr_based(ipaddr, lladdr)) + val = 3; /* 0-bits */ + else if (lowpan_is_iid_16_bit_compressable(ipaddr)) { + /* compress IID to 16 bits xxxx::XXXX */ + memcpy(*hc06_ptr, &ipaddr->s6_addr16[7], 2); + *hc06_ptr += 2; + val = 2; /* 16-bits */ + } else { + /* do not compress IID => xxxx::IID */ + memcpy(*hc06_ptr, &ipaddr->s6_addr16[4], 8); + *hc06_ptr += 8; + val = 1; /* 64-bits */ + } + + return rol8(val, shift); +} + +static void +lowpan_uip_ds6_set_addr_iid(struct in6_addr *ipaddr, unsigned char *lladdr) +{ + memcpy(&ipaddr->s6_addr[8], lladdr, IEEE802154_ALEN); + /* second bit-flip (Universe/Local) is done according RFC2464 */ + ipaddr->s6_addr[8] ^= 0x02; +} + +/* + * Uncompress addresses based on a prefix and a postfix with zeroes in + * between. If the postfix is zero in length it will use the link address + * to configure the IP address (autoconf style). + * pref_post_count takes a byte where the first nibble specify prefix count + * and the second postfix count (NOTE: 15/0xf => 16 bytes copy). + */ +static int +lowpan_uncompress_addr(struct sk_buff *skb, struct in6_addr *ipaddr, + u8 const *prefix, u8 pref_post_count, unsigned char *lladdr) +{ + u8 prefcount = pref_post_count >> 4; + u8 postcount = pref_post_count & 0x0f; + + /* full nibble 15 => 16 */ + prefcount = (prefcount == 15 ? 16 : prefcount); + postcount = (postcount == 15 ? 16 : postcount); + + if (lladdr) + lowpan_raw_dump_inline(__func__, "linklocal address", + lladdr, IEEE802154_ALEN); + if (prefcount > 0) + memcpy(ipaddr, prefix, prefcount); + + if (prefcount + postcount < 16) + memset(&ipaddr->s6_addr[prefcount], 0, + 16 - (prefcount + postcount)); + + if (postcount > 0) { + memcpy(&ipaddr->s6_addr[16 - postcount], skb->data, postcount); + skb_pull(skb, postcount); + } else if (prefcount > 0) { + if (lladdr == NULL) + return -EINVAL; + + /* no IID based configuration if no prefix and no data */ + lowpan_uip_ds6_set_addr_iid(ipaddr, lladdr); + } + + pr_debug("(%s): uncompressing %d + %d => ", __func__, prefcount, + postcount); + lowpan_raw_dump_inline(NULL, NULL, ipaddr->s6_addr, 16); + + return 0; +} + +static u8 lowpan_fetch_skb_u8(struct sk_buff *skb) +{ + u8 ret; + + ret = skb->data[0]; + skb_pull(skb, 1); + + return ret; +} + +static int lowpan_header_create(struct sk_buff *skb, + struct net_device *dev, + unsigned short type, const void *_daddr, + const void *_saddr, unsigned len) +{ + u8 tmp, iphc0, iphc1, *hc06_ptr; + struct ipv6hdr *hdr; + const u8 *saddr = _saddr; + const u8 *daddr = _daddr; + u8 *head; + struct ieee802154_addr sa, da; + + if (type != ETH_P_IPV6) + return 0; + /* TODO: + * if this package isn't ipv6 one, where should it be routed? + */ + head = kzalloc(100, GFP_KERNEL); + if (head == NULL) + return -ENOMEM; + + hdr = ipv6_hdr(skb); + hc06_ptr = head + 2; + + pr_debug("(%s): IPv6 header dump:\n\tversion = %d\n\tlength = %d\n" + "\tnexthdr = 0x%02x\n\thop_lim = %d\n", __func__, + hdr->version, ntohs(hdr->payload_len), hdr->nexthdr, + hdr->hop_limit); + + lowpan_raw_dump_table(__func__, "raw skb network header dump", + skb_network_header(skb), sizeof(struct ipv6hdr)); + + if (!saddr) + saddr = dev->dev_addr; + + lowpan_raw_dump_inline(__func__, "saddr", (unsigned char *)saddr, 8); + + /* + * As we copy some bit-length fields, in the IPHC encoding bytes, + * we sometimes use |= + * If the field is 0, and the current bit value in memory is 1, + * this does not work. We therefore reset the IPHC encoding here + */ + iphc0 = LOWPAN_DISPATCH_IPHC; + iphc1 = 0; + + /* TODO: context lookup */ + + lowpan_raw_dump_inline(__func__, "daddr", (unsigned char *)daddr, 8); + + /* + * Traffic class, flow label + * If flow label is 0, compress it. If traffic class is 0, compress it + * We have to process both in the same time as the offset of traffic + * class depends on the presence of version and flow label + */ + + /* hc06 format of TC is ECN | DSCP , original one is DSCP | ECN */ + tmp = (hdr->priority << 4) | (hdr->flow_lbl[0] >> 4); + tmp = ((tmp & 0x03) << 6) | (tmp >> 2); + + if (((hdr->flow_lbl[0] & 0x0F) == 0) && + (hdr->flow_lbl[1] == 0) && (hdr->flow_lbl[2] == 0)) { + /* flow label can be compressed */ + iphc0 |= LOWPAN_IPHC_FL_C; + if ((hdr->priority == 0) && + ((hdr->flow_lbl[0] & 0xF0) == 0)) { + /* compress (elide) all */ + iphc0 |= LOWPAN_IPHC_TC_C; + } else { + /* compress only the flow label */ + *hc06_ptr = tmp; + hc06_ptr += 1; + } + } else { + /* Flow label cannot be compressed */ + if ((hdr->priority == 0) && + ((hdr->flow_lbl[0] & 0xF0) == 0)) { + /* compress only traffic class */ + iphc0 |= LOWPAN_IPHC_TC_C; + *hc06_ptr = (tmp & 0xc0) | (hdr->flow_lbl[0] & 0x0F); + memcpy(hc06_ptr + 1, &hdr->flow_lbl[1], 2); + hc06_ptr += 3; + } else { + /* compress nothing */ + memcpy(hc06_ptr, &hdr, 4); + /* replace the top byte with new ECN | DSCP format */ + *hc06_ptr = tmp; + hc06_ptr += 4; + } + } + + /* NOTE: payload length is always compressed */ + + /* Next Header is compress if UDP */ + if (hdr->nexthdr == UIP_PROTO_UDP) + iphc0 |= LOWPAN_IPHC_NH_C; + +/* TODO: next header compression */ + + if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) { + *hc06_ptr = hdr->nexthdr; + hc06_ptr += 1; + } + + /* + * Hop limit + * if 1: compress, encoding is 01 + * if 64: compress, encoding is 10 + * if 255: compress, encoding is 11 + * else do not compress + */ + switch (hdr->hop_limit) { + case 1: + iphc0 |= LOWPAN_IPHC_TTL_1; + break; + case 64: + iphc0 |= LOWPAN_IPHC_TTL_64; + break; + case 255: + iphc0 |= LOWPAN_IPHC_TTL_255; + break; + default: + *hc06_ptr = hdr->hop_limit; + break; + } + + /* source address compression */ + if (is_addr_unspecified(&hdr->saddr)) { + pr_debug("(%s): source address is unspecified, setting SAC\n", + __func__); + iphc1 |= LOWPAN_IPHC_SAC; + /* TODO: context lookup */ + } else if (is_addr_link_local(&hdr->saddr)) { + pr_debug("(%s): source address is link-local\n", __func__); + iphc1 |= lowpan_compress_addr_64(&hc06_ptr, + LOWPAN_IPHC_SAM_BIT, &hdr->saddr, saddr); + } else { + pr_debug("(%s): send the full source address\n", __func__); + memcpy(hc06_ptr, &hdr->saddr.s6_addr16[0], 16); + hc06_ptr += 16; + } + + /* destination address compression */ + if (is_addr_mcast(&hdr->daddr)) { + pr_debug("(%s): destination address is multicast", __func__); + iphc1 |= LOWPAN_IPHC_M; + if (lowpan_is_mcast_addr_compressable8(&hdr->daddr)) { + pr_debug("compressed to 1 octet\n"); + iphc1 |= LOWPAN_IPHC_DAM_11; + /* use last byte */ + *hc06_ptr = hdr->daddr.s6_addr[15]; + hc06_ptr += 1; + } else if (lowpan_is_mcast_addr_compressable32(&hdr->daddr)) { + pr_debug("compressed to 4 octets\n"); + iphc1 |= LOWPAN_IPHC_DAM_10; + /* second byte + the last three */ + *hc06_ptr = hdr->daddr.s6_addr[1]; + memcpy(hc06_ptr + 1, &hdr->daddr.s6_addr[13], 3); + hc06_ptr += 4; + } else if (lowpan_is_mcast_addr_compressable48(&hdr->daddr)) { + pr_debug("compressed to 6 octets\n"); + iphc1 |= LOWPAN_IPHC_DAM_01; + /* second byte + the last five */ + *hc06_ptr = hdr->daddr.s6_addr[1]; + memcpy(hc06_ptr + 1, &hdr->daddr.s6_addr[11], 5); + hc06_ptr += 6; + } else { + pr_debug("using full address\n"); + iphc1 |= LOWPAN_IPHC_DAM_00; + memcpy(hc06_ptr, &hdr->daddr.s6_addr[0], 16); + hc06_ptr += 16; + } + } else { + pr_debug("(%s): destination address is unicast: ", __func__); + /* TODO: context lookup */ + if (is_addr_link_local(&hdr->daddr)) { + pr_debug("destination address is link-local\n"); + iphc1 |= lowpan_compress_addr_64(&hc06_ptr, + LOWPAN_IPHC_DAM_BIT, &hdr->daddr, daddr); + } else { + pr_debug("using full address\n"); + memcpy(hc06_ptr, &hdr->daddr.s6_addr16[0], 16); + hc06_ptr += 16; + } + } + + /* TODO: UDP header compression */ + /* TODO: Next Header compression */ + + head[0] = iphc0; + head[1] = iphc1; + + skb_pull(skb, sizeof(struct ipv6hdr)); + memcpy(skb_push(skb, hc06_ptr - head), head, hc06_ptr - head); + + kfree(head); + + lowpan_raw_dump_table(__func__, "raw skb data dump", skb->data, + skb->len); + + /* + * NOTE1: I'm still unsure about the fact that compression and WPAN + * header are created here and not later in the xmit. So wait for + * an opinion of net maintainers. + */ + /* + * NOTE2: to be absolutely correct, we must derive PANid information + * from MAC subif of the 'dev' and 'real_dev' network devices, but + * this isn't implemented in mainline yet, so currently we assign 0xff + */ + { + /* prepare wpan address data */ + sa.addr_type = IEEE802154_ADDR_LONG; + sa.pan_id = 0xff; + + da.addr_type = IEEE802154_ADDR_LONG; + da.pan_id = 0xff; + + memcpy(&(da.hwaddr), daddr, 8); + memcpy(&(sa.hwaddr), saddr, 8); + + mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA; + return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev, + type, (void *)&da, (void *)&sa, skb->len); + } +} + +static int lowpan_skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr) +{ + struct sk_buff *new; + struct lowpan_dev_record *entry; + int stat = NET_RX_SUCCESS; + + new = skb_copy_expand(skb, sizeof(struct ipv6hdr), skb_tailroom(skb), + GFP_ATOMIC); + kfree_skb(skb); + + if (!new) + return -ENOMEM; + + skb_push(new, sizeof(struct ipv6hdr)); + skb_reset_network_header(new); + skb_copy_to_linear_data(new, hdr, sizeof(struct ipv6hdr)); + + new->protocol = htons(ETH_P_IPV6); + new->pkt_type = PACKET_HOST; + + rcu_read_lock(); + list_for_each_entry_rcu(entry, &lowpan_devices, list) + if (lowpan_dev_info(entry->ldev)->real_dev == new->dev) { + skb = skb_copy(new, GFP_ATOMIC); + if (!skb) { + stat = -ENOMEM; + break; + } + + skb->dev = entry->ldev; + stat = netif_rx(skb); + } + rcu_read_unlock(); + + kfree_skb(new); + + return stat; +} + +static int +lowpan_process_data(struct sk_buff *skb) +{ + struct ipv6hdr hdr; + u8 tmp, iphc0, iphc1, num_context = 0; + u8 *_saddr, *_daddr; + int err; + + lowpan_raw_dump_table(__func__, "raw skb data dump", skb->data, + skb->len); + /* at least two bytes will be used for the encoding */ + if (skb->len < 2) + goto drop; + iphc0 = lowpan_fetch_skb_u8(skb); + iphc1 = lowpan_fetch_skb_u8(skb); + + _saddr = mac_cb(skb)->sa.hwaddr; + _daddr = mac_cb(skb)->da.hwaddr; + + pr_debug("(%s): iphc0 = %02x, iphc1 = %02x\n", __func__, iphc0, iphc1); + + /* another if the CID flag is set */ + if (iphc1 & LOWPAN_IPHC_CID) { + pr_debug("(%s): CID flag is set, increase header with one\n", + __func__); + if (!skb->len) + goto drop; + num_context = lowpan_fetch_skb_u8(skb); + } + + hdr.version = 6; + + /* Traffic Class and Flow Label */ + switch ((iphc0 & LOWPAN_IPHC_TF) >> 3) { + /* + * Traffic Class and FLow Label carried in-line + * ECN + DSCP + 4-bit Pad + Flow Label (4 bytes) + */ + case 0: /* 00b */ + if (!skb->len) + goto drop; + tmp = lowpan_fetch_skb_u8(skb); + memcpy(&hdr.flow_lbl, &skb->data[0], 3); + skb_pull(skb, 3); + hdr.priority = ((tmp >> 2) & 0x0f); + hdr.flow_lbl[0] = ((tmp >> 2) & 0x30) | (tmp << 6) | + (hdr.flow_lbl[0] & 0x0f); + break; + /* + * Traffic class carried in-line + * ECN + DSCP (1 byte), Flow Label is elided + */ + case 1: /* 10b */ + if (!skb->len) + goto drop; + tmp = lowpan_fetch_skb_u8(skb); + hdr.priority = ((tmp >> 2) & 0x0f); + hdr.flow_lbl[0] = ((tmp << 6) & 0xC0) | ((tmp >> 2) & 0x30); + hdr.flow_lbl[1] = 0; + hdr.flow_lbl[2] = 0; + break; + /* + * Flow Label carried in-line + * ECN + 2-bit Pad + Flow Label (3 bytes), DSCP is elided + */ + case 2: /* 01b */ + if (!skb->len) + goto drop; + tmp = lowpan_fetch_skb_u8(skb); + hdr.flow_lbl[0] = (skb->data[0] & 0x0F) | ((tmp >> 2) & 0x30); + memcpy(&hdr.flow_lbl[1], &skb->data[0], 2); + skb_pull(skb, 2); + break; + /* Traffic Class and Flow Label are elided */ + case 3: /* 11b */ + hdr.priority = 0; + hdr.flow_lbl[0] = 0; + hdr.flow_lbl[1] = 0; + hdr.flow_lbl[2] = 0; + break; + default: + break; + } + + /* Next Header */ + if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) { + /* Next header is carried inline */ + if (!skb->len) + goto drop; + hdr.nexthdr = lowpan_fetch_skb_u8(skb); + pr_debug("(%s): NH flag is set, next header is carried " + "inline: %02x\n", __func__, hdr.nexthdr); + } + + /* Hop Limit */ + if ((iphc0 & 0x03) != LOWPAN_IPHC_TTL_I) + hdr.hop_limit = lowpan_ttl_values[iphc0 & 0x03]; + else { + if (!skb->len) + goto drop; + hdr.hop_limit = lowpan_fetch_skb_u8(skb); + } + + /* Extract SAM to the tmp variable */ + tmp = ((iphc1 & LOWPAN_IPHC_SAM) >> LOWPAN_IPHC_SAM_BIT) & 0x03; + + /* Source address uncompression */ + pr_debug("(%s): source address stateless compression\n", __func__); + err = lowpan_uncompress_addr(skb, &hdr.saddr, lowpan_llprefix, + lowpan_unc_llconf[tmp], skb->data); + if (err) + goto drop; + + /* Extract DAM to the tmp variable */ + tmp = ((iphc1 & LOWPAN_IPHC_DAM_11) >> LOWPAN_IPHC_DAM_BIT) & 0x03; + + /* check for Multicast Compression */ + if (iphc1 & LOWPAN_IPHC_M) { + if (iphc1 & LOWPAN_IPHC_DAC) { + pr_debug("(%s): destination address context-based " + "multicast compression\n", __func__); + /* TODO: implement this */ + } else { + u8 prefix[] = {0xff, 0x02}; + + pr_debug("(%s): destination address non-context-based" + " multicast compression\n", __func__); + if (0 < tmp && tmp < 3) { + if (!skb->len) + goto drop; + else + prefix[1] = lowpan_fetch_skb_u8(skb); + } + + err = lowpan_uncompress_addr(skb, &hdr.daddr, prefix, + lowpan_unc_mxconf[tmp], NULL); + if (err) + goto drop; + } + } else { + pr_debug("(%s): destination address stateless compression\n", + __func__); + err = lowpan_uncompress_addr(skb, &hdr.daddr, lowpan_llprefix, + lowpan_unc_llconf[tmp], skb->data); + if (err) + goto drop; + } + + /* TODO: UDP header parse */ + + /* Not fragmented package */ + hdr.payload_len = htons(skb->len); + + pr_debug("(%s): skb headroom size = %d, data length = %d\n", __func__, + skb_headroom(skb), skb->len); + + pr_debug("(%s): IPv6 header dump:\n\tversion = %d\n\tlength = %d\n\t" + "nexthdr = 0x%02x\n\thop_lim = %d\n", __func__, hdr.version, + ntohs(hdr.payload_len), hdr.nexthdr, hdr.hop_limit); + + lowpan_raw_dump_table(__func__, "raw header dump", (u8 *)&hdr, + sizeof(hdr)); + return lowpan_skb_deliver(skb, &hdr); +drop: + kfree_skb(skb); + return -EINVAL; +} + +static int lowpan_set_address(struct net_device *dev, void *p) +{ + struct sockaddr *sa = p; + + if (netif_running(dev)) + return -EBUSY; + + /* TODO: validate addr */ + memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + + return 0; +} + +static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev) +{ + int err = 0; + + pr_debug("(%s): package xmit\n", __func__); + + skb->dev = lowpan_dev_info(dev)->real_dev; + if (skb->dev == NULL) { + pr_debug("(%s) ERROR: no real wpan device found\n", __func__); + dev_kfree_skb(skb); + } else + err = dev_queue_xmit(skb); + + return (err < 0 ? NETDEV_TX_BUSY : NETDEV_TX_OK); +} + +static void lowpan_dev_free(struct net_device *dev) +{ + dev_put(lowpan_dev_info(dev)->real_dev); + free_netdev(dev); +} + +static struct header_ops lowpan_header_ops = { + .create = lowpan_header_create, +}; + +static const struct net_device_ops lowpan_netdev_ops = { + .ndo_start_xmit = lowpan_xmit, + .ndo_set_mac_address = lowpan_set_address, +}; + +static void lowpan_setup(struct net_device *dev) +{ + pr_debug("(%s)\n", __func__); + + dev->addr_len = IEEE802154_ADDR_LEN; + memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN); + dev->type = ARPHRD_IEEE802154; + dev->features = NETIF_F_NO_CSUM; + /* Frame Control + Sequence Number + Address fields + Security Header */ + dev->hard_header_len = 2 + 1 + 20 + 14; + dev->needed_tailroom = 2; /* FCS */ + dev->mtu = 1281; + dev->tx_queue_len = 0; + dev->flags = IFF_NOARP | IFF_BROADCAST; + dev->watchdog_timeo = 0; + + dev->netdev_ops = &lowpan_netdev_ops; + dev->header_ops = &lowpan_header_ops; + dev->destructor = lowpan_dev_free; +} + +static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + pr_debug("(%s)\n", __func__); + + if (tb[IFLA_ADDRESS]) { + if (nla_len(tb[IFLA_ADDRESS]) != IEEE802154_ADDR_LEN) + return -EINVAL; + } + return 0; +} + +static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + if (!netif_running(dev)) + goto drop; + + if (dev->type != ARPHRD_IEEE802154) + goto drop; + + /* check that it's our buffer */ + if ((skb->data[0] & 0xe0) == 0x60) + lowpan_process_data(skb); + + return NET_RX_SUCCESS; + +drop: + kfree_skb(skb); + return NET_RX_DROP; +} + +static int lowpan_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net_device *real_dev; + struct lowpan_dev_record *entry; + + pr_debug("(%s)\n", __func__); + + if (!tb[IFLA_LINK]) + return -EINVAL; + /* find and hold real wpan device */ + real_dev = dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); + if (!real_dev) + return -ENODEV; + + lowpan_dev_info(dev)->real_dev = real_dev; + mutex_init(&lowpan_dev_info(dev)->dev_list_mtx); + + entry = kzalloc(sizeof(struct lowpan_dev_record), GFP_KERNEL); + if (!entry) { + dev_put(real_dev); + lowpan_dev_info(dev)->real_dev = NULL; + return -ENOMEM; + } + + entry->ldev = dev; + + mutex_lock(&lowpan_dev_info(dev)->dev_list_mtx); + INIT_LIST_HEAD(&entry->list); + list_add_tail(&entry->list, &lowpan_devices); + mutex_unlock(&lowpan_dev_info(dev)->dev_list_mtx); + + register_netdevice(dev); + + return 0; +} + +static void lowpan_dellink(struct net_device *dev, struct list_head *head) +{ + struct lowpan_dev_info *lowpan_dev = lowpan_dev_info(dev); + struct net_device *real_dev = lowpan_dev->real_dev; + struct lowpan_dev_record *entry; + struct lowpan_dev_record *tmp; + + ASSERT_RTNL(); + + mutex_lock(&lowpan_dev_info(dev)->dev_list_mtx); + list_for_each_entry_safe(entry, tmp, &lowpan_devices, list) { + if (entry->ldev == dev) { + list_del(&entry->list); + kfree(entry); + } + } + mutex_unlock(&lowpan_dev_info(dev)->dev_list_mtx); + + mutex_destroy(&lowpan_dev_info(dev)->dev_list_mtx); + + unregister_netdevice_queue(dev, head); + + dev_put(real_dev); +} + +static struct rtnl_link_ops lowpan_link_ops __read_mostly = { + .kind = "lowpan", + .priv_size = sizeof(struct lowpan_dev_info), + .setup = lowpan_setup, + .newlink = lowpan_newlink, + .dellink = lowpan_dellink, + .validate = lowpan_validate, +}; + +static inline int __init lowpan_netlink_init(void) +{ + return rtnl_link_register(&lowpan_link_ops); +} + +static inline void __init lowpan_netlink_fini(void) +{ + rtnl_link_unregister(&lowpan_link_ops); +} + +static struct packet_type lowpan_packet_type = { + .type = __constant_htons(ETH_P_IEEE802154), + .func = lowpan_rcv, +}; + +static int __init lowpan_init_module(void) +{ + int err = 0; + + pr_debug("(%s)\n", __func__); + + err = lowpan_netlink_init(); + if (err < 0) + goto out; + + dev_add_pack(&lowpan_packet_type); +out: + return err; +} + +static void __exit lowpan_cleanup_module(void) +{ + pr_debug("(%s)\n", __func__); + + lowpan_netlink_fini(); + + dev_remove_pack(&lowpan_packet_type); +} + +module_init(lowpan_init_module); +module_exit(lowpan_cleanup_module); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("lowpan"); diff --git a/net/ieee802154/6lowpan.h b/net/ieee802154/6lowpan.h new file mode 100644 index 0000000..5d8cf80 --- /dev/null +++ b/net/ieee802154/6lowpan.h @@ -0,0 +1,212 @@ +/* + * Copyright 2011, Siemens AG + * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com> + */ + +/* + * Based on patches from Jon Smirl <jonsmirl@gmail.com> + * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + */ + +/* Jon's code is based on 6lowpan implementation for Contiki which is: + * Copyright (c) 2008, Swedish Institute of Computer Science. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the Institute nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#ifndef __6LOWPAN_H__ +#define __6LOWPAN_H__ + +/* need to know address length to manipulate with it */ +#define IEEE802154_ALEN 8 + +#define UIP_802154_SHORTADDR_LEN 2 /* compressed ipv6 address length */ +#define UIP_IPH_LEN 40 /* ipv6 fixed header size */ +#define UIP_PROTO_UDP 17 /* ipv6 next header value for UDP */ +#define UIP_FRAGH_LEN 8 /* ipv6 fragment header size */ + +/* + * ipv6 address based on mac + * second bit-flip (Universe/Local) is done according RFC2464 + */ +#define is_addr_mac_addr_based(a, m) \ + ((((a)->s6_addr[8]) == (((m)[0]) ^ 0x02)) && \ + (((a)->s6_addr[9]) == (m)[1]) && \ + (((a)->s6_addr[10]) == (m)[2]) && \ + (((a)->s6_addr[11]) == (m)[3]) && \ + (((a)->s6_addr[12]) == (m)[4]) && \ + (((a)->s6_addr[13]) == (m)[5]) && \ + (((a)->s6_addr[14]) == (m)[6]) && \ + (((a)->s6_addr[15]) == (m)[7])) + +/* ipv6 address is unspecified */ +#define is_addr_unspecified(a) \ + ((((a)->s6_addr32[0]) == 0) && \ + (((a)->s6_addr32[1]) == 0) && \ + (((a)->s6_addr32[2]) == 0) && \ + (((a)->s6_addr32[3]) == 0)) + +/* compare ipv6 addresses prefixes */ +#define ipaddr_prefixcmp(addr1, addr2, length) \ + (memcmp(addr1, addr2, length >> 3) == 0) + +/* local link, i.e. FE80::/10 */ +#define is_addr_link_local(a) (((a)->s6_addr16[0]) == 0x80FE) + +/* + * check whether we can compress the IID to 16 bits, + * it's possible for unicast adresses with first 49 bits are zero only. + */ +#define lowpan_is_iid_16_bit_compressable(a) \ + ((((a)->s6_addr16[4]) == 0) && \ + (((a)->s6_addr16[5]) == 0) && \ + (((a)->s6_addr16[6]) == 0) && \ + ((((a)->s6_addr[14]) & 0x80) == 0)) + +/* multicast address */ +#define is_addr_mcast(a) (((a)->s6_addr[0]) == 0xFF) + +/* check whether the 112-bit gid of the multicast address is mappable to: */ + +/* 9 bits, for FF02::1 (all nodes) and FF02::2 (all routers) addresses only. */ +#define lowpan_is_mcast_addr_compressable(a) \ + ((((a)->s6_addr16[1]) == 0) && \ + (((a)->s6_addr16[2]) == 0) && \ + (((a)->s6_addr16[3]) == 0) && \ + (((a)->s6_addr16[4]) == 0) && \ + (((a)->s6_addr16[5]) == 0) && \ + (((a)->s6_addr16[6]) == 0) && \ + (((a)->s6_addr[14]) == 0) && \ + ((((a)->s6_addr[15]) == 1) || (((a)->s6_addr[15]) == 2))) + +/* 48 bits, FFXX::00XX:XXXX:XXXX */ +#define lowpan_is_mcast_addr_compressable48(a) \ + ((((a)->s6_addr16[1]) == 0) && \ + (((a)->s6_addr16[2]) == 0) && \ + (((a)->s6_addr16[3]) == 0) && \ + (((a)->s6_addr16[4]) == 0) && \ + (((a)->s6_addr[10]) == 0)) + +/* 32 bits, FFXX::00XX:XXXX */ +#define lowpan_is_mcast_addr_compressable32(a) \ + ((((a)->s6_addr16[1]) == 0) && \ + (((a)->s6_addr16[2]) == 0) && \ + (((a)->s6_addr16[3]) == 0) && \ + (((a)->s6_addr16[4]) == 0) && \ + (((a)->s6_addr16[5]) == 0) && \ + (((a)->s6_addr[12]) == 0)) + +/* 8 bits, FF02::00XX */ +#define lowpan_is_mcast_addr_compressable8(a) \ + ((((a)->s6_addr[1]) == 2) && \ + (((a)->s6_addr16[1]) == 0) && \ + (((a)->s6_addr16[2]) == 0) && \ + (((a)->s6_addr16[3]) == 0) && \ + (((a)->s6_addr16[4]) == 0) && \ + (((a)->s6_addr16[5]) == 0) && \ + (((a)->s6_addr16[6]) == 0) && \ + (((a)->s6_addr[14]) == 0)) + +#define lowpan_is_addr_broadcast(a) \ + ((((a)[0]) == 0xFF) && \ + (((a)[1]) == 0xFF) && \ + (((a)[2]) == 0xFF) && \ + (((a)[3]) == 0xFF) && \ + (((a)[4]) == 0xFF) && \ + (((a)[5]) == 0xFF) && \ + (((a)[6]) == 0xFF) && \ + (((a)[7]) == 0xFF)) + +#define LOWPAN_DISPATCH_IPV6 0x41 /* 01000001 = 65 */ +#define LOWPAN_DISPATCH_HC1 0x42 /* 01000010 = 66 */ +#define LOWPAN_DISPATCH_IPHC 0x60 /* 011xxxxx = ... */ +#define LOWPAN_DISPATCH_FRAG1 0xc0 /* 11000xxx */ +#define LOWPAN_DISPATCH_FRAGN 0xe0 /* 11100xxx */ + +/* + * Values of fields within the IPHC encoding first byte + * (C stands for compressed and I for inline) + */ +#define LOWPAN_IPHC_TF 0x18 + +#define LOWPAN_IPHC_FL_C 0x10 +#define LOWPAN_IPHC_TC_C 0x08 +#define LOWPAN_IPHC_NH_C 0x04 +#define LOWPAN_IPHC_TTL_1 0x01 +#define LOWPAN_IPHC_TTL_64 0x02 +#define LOWPAN_IPHC_TTL_255 0x03 +#define LOWPAN_IPHC_TTL_I 0x00 + + +/* Values of fields within the IPHC encoding second byte */ +#define LOWPAN_IPHC_CID 0x80 + +#define LOWPAN_IPHC_SAC 0x40 +#define LOWPAN_IPHC_SAM_00 0x00 +#define LOWPAN_IPHC_SAM_01 0x10 +#define LOWPAN_IPHC_SAM_10 0x20 +#define LOWPAN_IPHC_SAM 0x30 + +#define LOWPAN_IPHC_SAM_BIT 4 + +#define LOWPAN_IPHC_M 0x08 +#define LOWPAN_IPHC_DAC 0x04 +#define LOWPAN_IPHC_DAM_00 0x00 +#define LOWPAN_IPHC_DAM_01 0x01 +#define LOWPAN_IPHC_DAM_10 0x02 +#define LOWPAN_IPHC_DAM_11 0x03 + +#define LOWPAN_IPHC_DAM_BIT 0 +/* + * LOWPAN_UDP encoding (works together with IPHC) + */ +#define LOWPAN_NHC_UDP_MASK 0xF8 +#define LOWPAN_NHC_UDP_ID 0xF0 +#define LOWPAN_NHC_UDP_CHECKSUMC 0x04 +#define LOWPAN_NHC_UDP_CHECKSUMI 0x00 + +/* values for port compression, _with checksum_ ie bit 5 set to 0 */ +#define LOWPAN_NHC_UDP_CS_P_00 0xF0 /* all inline */ +#define LOWPAN_NHC_UDP_CS_P_01 0xF1 /* source 16bit inline, + dest = 0xF0 + 8 bit inline */ +#define LOWPAN_NHC_UDP_CS_P_10 0xF2 /* source = 0xF0 + 8bit inline, + dest = 16 bit inline */ +#define LOWPAN_NHC_UDP_CS_P_11 0xF3 /* source & dest = 0xF0B + 4bit inline */ + +#endif /* __6LOWPAN_H__ */ diff --git a/net/ieee802154/Kconfig b/net/ieee802154/Kconfig index 1c1de97..7dee650 100644 --- a/net/ieee802154/Kconfig +++ b/net/ieee802154/Kconfig @@ -10,3 +10,9 @@ config IEEE802154 Say Y here to compile LR-WPAN support into the kernel or say M to compile it as modules. + +config IEEE802154_6LOWPAN + tristate "6lowpan support over IEEE 802.15.4" + depends on IEEE802154 && IPV6 + ---help--- + IPv6 compression over IEEE 802.15.4. diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile index 5761185..d7716d6 100644 --- a/net/ieee802154/Makefile +++ b/net/ieee802154/Makefile @@ -1,3 +1,5 @@ -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 +obj-$(CONFIG_IEEE802154) += ieee802154.o af_802154.o +obj-$(CONFIG_IEEE802154_6LOWPAN) += 6lowpan.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 diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index dd2b947..1b5096a 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -893,7 +893,7 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) EXPORT_SYMBOL(inet_ioctl); #ifdef CONFIG_COMPAT -int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; int err = -ENOIOCTLCMD; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 2c2a98e..86f3b88 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -476,7 +476,7 @@ int cipso_v4_doi_add(struct cipso_v4_doi *doi_def, doi = doi_def->doi; doi_type = doi_def->type; - if (doi_def == NULL || doi_def->doi == CIPSO_V4_DOI_UNKNOWN) + if (doi_def->doi == CIPSO_V4_DOI_UNKNOWN) goto doi_add_return; for (iter = 0; iter < CIPSO_V4_TAG_MAXCNT; iter++) { switch (doi_def->tags[iter]) { diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index bc19bd0..c6b5092 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -258,7 +258,7 @@ static struct in_device *inetdev_init(struct net_device *dev) ip_mc_up(in_dev); /* we can receive as soon as ip_ptr is set -- do this last */ - rcu_assign_pointer(dev->ip_ptr, in_dev); + RCU_INIT_POINTER(dev->ip_ptr, in_dev); out: return in_dev; out_kfree: @@ -291,7 +291,7 @@ static void inetdev_destroy(struct in_device *in_dev) inet_free_ifa(ifa); } - rcu_assign_pointer(dev->ip_ptr, NULL); + RCU_INIT_POINTER(dev->ip_ptr, NULL); devinet_sysctl_unregister(in_dev); neigh_parms_release(&arp_tbl, in_dev->arp_parms); @@ -1175,7 +1175,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, switch (event) { case NETDEV_REGISTER: printk(KERN_DEBUG "inetdev_event: bug\n"); - rcu_assign_pointer(dev->ip_ptr, NULL); + RCU_INIT_POINTER(dev->ip_ptr, NULL); break; case NETDEV_UP: if (!inetdev_valid_mtu(dev->mtu)) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index de9e297..89d6f71 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -204,7 +204,7 @@ static inline struct tnode *node_parent_rcu(const struct rt_trie_node *node) return (struct tnode *)(parent & ~NODE_TYPE_MASK); } -/* Same as rcu_assign_pointer +/* Same as RCU_INIT_POINTER * but that macro() assumes that value is a pointer. */ static inline void node_set_parent(struct rt_trie_node *node, struct tnode *ptr) @@ -528,7 +528,7 @@ static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node * if (n) node_set_parent(n, tn); - rcu_assign_pointer(tn->child[i], n); + RCU_INIT_POINTER(tn->child[i], n); } #define MAX_WORK 10 @@ -1014,7 +1014,7 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) tp = node_parent((struct rt_trie_node *) tn); if (!tp) - rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); + RCU_INIT_POINTER(t->trie, (struct rt_trie_node *)tn); tnode_free_flush(); if (!tp) @@ -1026,7 +1026,7 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) if (IS_TNODE(tn)) tn = (struct tnode *)resize(t, (struct tnode *)tn); - rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); + RCU_INIT_POINTER(t->trie, (struct rt_trie_node *)tn); tnode_free_flush(); } @@ -1163,7 +1163,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) put_child(t, (struct tnode *)tp, cindex, (struct rt_trie_node *)tn); } else { - rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); + RCU_INIT_POINTER(t->trie, (struct rt_trie_node *)tn); tp = tn; } } @@ -1621,7 +1621,7 @@ static void trie_leaf_remove(struct trie *t, struct leaf *l) put_child(t, (struct tnode *)tp, cindex, NULL); trie_rebalance(t, tp); } else - rcu_assign_pointer(t->trie, NULL); + RCU_INIT_POINTER(t->trie, NULL); free_leaf(l); } diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c index dbfc21d..8cb1ebb 100644 --- a/net/ipv4/gre.c +++ b/net/ipv4/gre.c @@ -34,7 +34,7 @@ int gre_add_protocol(const struct gre_protocol *proto, u8 version) if (gre_proto[version]) goto err_out_unlock; - rcu_assign_pointer(gre_proto[version], proto); + RCU_INIT_POINTER(gre_proto[version], proto); spin_unlock(&gre_proto_lock); return 0; @@ -54,7 +54,7 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version) if (rcu_dereference_protected(gre_proto[version], lockdep_is_held(&gre_proto_lock)) != proto) goto err_out_unlock; - rcu_assign_pointer(gre_proto[version], NULL); + RCU_INIT_POINTER(gre_proto[version], NULL); spin_unlock(&gre_proto_lock); synchronize_rcu(); return 0; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 23ef31b..ab188ae 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -1152,10 +1152,9 @@ static int __net_init icmp_sk_init(struct net *net) net->ipv4.icmp_sk[i] = sk; /* Enough space for 2 64K ICMP packets, including - * sk_buff struct overhead. + * sk_buff/skb_shared_info struct overhead. */ - sk->sk_sndbuf = - (2 * ((64 * 1024) + sizeof(struct sk_buff))); + sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); /* * Speedup sock_wfree() diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d577199..c7472ef 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1009,7 +1009,7 @@ static void ip_mc_filter_add(struct in_device *in_dev, __be32 addr) /* Checking for IFF_MULTICAST here is WRONG-WRONG-WRONG. We will get multicast token leakage, when IFF_MULTICAST - is changed. This check should be done in dev->set_multicast_list + is changed. This check should be done in ndo_set_rx_mode routine. Something sort of: if (dev->mc_list && dev->flags&IFF_MULTICAST) { do it; } --ANK @@ -1242,7 +1242,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) im->next_rcu = in_dev->mc_list; in_dev->mc_count++; - rcu_assign_pointer(in_dev->mc_list, im); + RCU_INIT_POINTER(in_dev->mc_list, im); #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im->multiaddr); @@ -1813,7 +1813,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) iml->next_rcu = inet->mc_list; iml->sflist = NULL; iml->sfmode = MCAST_EXCLUDE; - rcu_assign_pointer(inet->mc_list, iml); + RCU_INIT_POINTER(inet->mc_list, iml); ip_mc_inc_group(in_dev, addr); err = 0; done: @@ -1835,7 +1835,7 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, } err = ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, psf->sl_count, psf->sl_addr, 0); - rcu_assign_pointer(iml->sflist, NULL); + RCU_INIT_POINTER(iml->sflist, NULL); /* decrease mem now to avoid the memleak warning */ atomic_sub(IP_SFLSIZE(psf->sl_max), &sk->sk_omem_alloc); kfree_rcu(psf, rcu); @@ -2000,7 +2000,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); kfree_rcu(psl, rcu); } - rcu_assign_pointer(pmc->sflist, newpsl); + RCU_INIT_POINTER(pmc->sflist, newpsl); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ @@ -2103,7 +2103,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) } else (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); - rcu_assign_pointer(pmc->sflist, newpsl); + RCU_INIT_POINTER(pmc->sflist, newpsl); pmc->sfmode = msf->imsf_fmode; err = 0; done: diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 389a2e6..f5e2bda 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -108,6 +108,9 @@ static int inet_csk_diag_fill(struct sock *sk, icsk->icsk_ca_ops->name); } + if ((ext & (1 << (INET_DIAG_TOS - 1))) && (sk->sk_family != AF_INET6)) + RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos); + r->idiag_family = sk->sk_family; r->idiag_state = sk->sk_state; r->idiag_timer = 0; @@ -130,6 +133,8 @@ static int inet_csk_diag_fill(struct sock *sk, &np->rcv_saddr); ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, &np->daddr); + if (ext & (1 << (INET_DIAG_TOS - 1))) + RTA_PUT_U8(skb, INET_DIAG_TOS, np->tclass); } #endif diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c index ef7ae60..cc280a3 100644 --- a/net/ipv4/inet_lro.c +++ b/net/ipv4/inet_lro.c @@ -244,11 +244,11 @@ static void lro_add_frags(struct net_lro_desc *lro_desc, skb->truesize += truesize; skb_frags[0].page_offset += hlen; - skb_frags[0].size -= hlen; + skb_frag_size_sub(&skb_frags[0], hlen); while (tcp_data_len > 0) { *(lro_desc->next_frag) = *skb_frags; - tcp_data_len -= skb_frags->size; + tcp_data_len -= skb_frag_size(skb_frags); lro_desc->next_frag++; skb_frags++; skb_shinfo(skb)->nr_frags++; @@ -400,14 +400,14 @@ static struct sk_buff *lro_gen_skb(struct net_lro_mgr *lro_mgr, skb_frags = skb_shinfo(skb)->frags; while (data_len > 0) { *skb_frags = *frags; - data_len -= frags->size; + data_len -= skb_frag_size(frags); skb_frags++; frags++; skb_shinfo(skb)->nr_frags++; } skb_shinfo(skb)->frags[0].page_offset += hdr_len; - skb_shinfo(skb)->frags[0].size -= hdr_len; + skb_frag_size_sub(&skb_shinfo(skb)->frags[0], hdr_len); skb->ip_summed = ip_summed; skb->csum = sum; @@ -433,7 +433,7 @@ static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr, if (!lro_mgr->get_frag_header || lro_mgr->get_frag_header(frags, (void *)&mac_hdr, (void *)&iph, (void *)&tcph, &flags, priv)) { - mac_hdr = page_address(frags->page) + frags->page_offset; + mac_hdr = skb_frag_address(frags); goto out1; } diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 3c8dfa1..44d65d5 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -183,6 +183,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat tw->tw_daddr = inet->inet_daddr; tw->tw_rcv_saddr = inet->inet_rcv_saddr; tw->tw_bound_dev_if = sk->sk_bound_dev_if; + tw->tw_tos = inet->tos; tw->tw_num = inet->inet_num; tw->tw_state = TCP_TIME_WAIT; tw->tw_substate = state; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 0e0ab98..fdaabf2 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -599,8 +599,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, head->next = clone; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); - for (i=0; i<skb_shinfo(head)->nr_frags; i++) - plen += skb_shinfo(head)->frags[i].size; + for (i = 0; i < skb_shinfo(head)->nr_frags; i++) + plen += skb_frag_size(&skb_shinfo(head)->frags[i]); clone->len = clone->data_len = head->data_len - plen; head->data_len -= clone->len; head->len -= clone->len; @@ -682,6 +682,42 @@ int ip_defrag(struct sk_buff *skb, u32 user) } EXPORT_SYMBOL(ip_defrag); +struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) +{ + const struct iphdr *iph; + u32 len; + + if (skb->protocol != htons(ETH_P_IP)) + return skb; + + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + return skb; + + iph = ip_hdr(skb); + if (iph->ihl < 5 || iph->version != 4) + return skb; + if (!pskb_may_pull(skb, iph->ihl*4)) + return skb; + iph = ip_hdr(skb); + len = ntohs(iph->tot_len); + if (skb->len < len || len < (iph->ihl * 4)) + return skb; + + if (ip_is_fragment(ip_hdr(skb))) { + skb = skb_share_check(skb, GFP_ATOMIC); + if (skb) { + if (pskb_trim_rcsum(skb, len)) + return skb; + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + if (ip_defrag(skb, user)) + return NULL; + skb->rxhash = 0; + } + } + return skb; +} +EXPORT_SYMBOL(ip_check_defrag); + #ifdef CONFIG_SYSCTL static int zero; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index d7bb94c..d55110e 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -835,8 +835,6 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (skb_headroom(skb) < max_headroom || skb_shared(skb)|| (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; if (!new_skb) { ip_rt_put(rt); dev->stats.tx_dropped++; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8c65633..0bc95f3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -989,13 +989,13 @@ alloc_new_skb: if (page && (left = PAGE_SIZE - off) > 0) { if (copy >= left) copy = left; - if (page != frag->page) { + if (page != skb_frag_page(frag)) { if (i == MAX_SKB_FRAGS) { err = -EMSGSIZE; goto error; } - get_page(page); skb_fill_page_desc(skb, i, page, off, 0); + skb_frag_ref(skb, i); frag = &skb_shinfo(skb)->frags[i]; } } else if (i < MAX_SKB_FRAGS) { @@ -1015,12 +1015,13 @@ alloc_new_skb: err = -EMSGSIZE; goto error; } - if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) { + if (getfrag(from, skb_frag_address(frag)+skb_frag_size(frag), + offset, copy, skb->len, skb) < 0) { err = -EFAULT; goto error; } cork->off += copy; - frag->size += copy; + skb_frag_size_add(frag, copy); skb->len += copy; skb->data_len += copy; skb->truesize += copy; @@ -1229,7 +1230,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, if (len > size) len = size; if (skb_can_coalesce(skb, i, page, offset)) { - skb_shinfo(skb)->frags[i-1].size += len; + skb_frag_size_add(&skb_shinfo(skb)->frags[i-1], len); } else if (i < MAX_SKB_FRAGS) { get_page(page); skb_fill_page_desc(skb, i, page, offset, len); @@ -1465,7 +1466,7 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset, * structure to pass arguments. */ void ip_send_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr, - struct ip_reply_arg *arg, unsigned int len) + const struct ip_reply_arg *arg, unsigned int len) { struct inet_sock *inet = inet_sk(sk); struct ip_options_data replyopts; @@ -1488,7 +1489,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr, } flowi4_init_output(&fl4, arg->bound_dev_if, 0, - RT_TOS(ip_hdr(skb)->tos), + RT_TOS(arg->tos), RT_SCOPE_UNIVERSE, sk->sk_protocol, ip_reply_arg_flowi_flags(arg), daddr, rt->rt_spec_dst, @@ -1505,7 +1506,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr, with locally disabled BH and that sk cannot be already spinlocked. */ bh_lock_sock(sk); - inet->tos = ip_hdr(skb)->tos; + inet->tos = arg->tos; sk->sk_priority = skb->priority; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 8905e92..09ff51b 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -33,6 +33,7 @@ #include <linux/netfilter.h> #include <linux/route.h> #include <linux/mroute.h> +#include <net/inet_ecn.h> #include <net/route.h> #include <net/xfrm.h> #include <net/compat.h> @@ -578,8 +579,8 @@ static int do_ip_setsockopt(struct sock *sk, int level, break; case IP_TOS: /* This sets both TOS and Precedence */ if (sk->sk_type == SOCK_STREAM) { - val &= ~3; - val |= inet->tos & 3; + val &= ~INET_ECN_MASK; + val |= inet->tos & INET_ECN_MASK; } if (inet->tos != val) { inet->tos = val; @@ -961,7 +962,7 @@ mc_msf_out: break; case IP_TRANSPARENT: - if (!capable(CAP_NET_ADMIN)) { + if (!!val && !capable(CAP_NET_RAW) && !capable(CAP_NET_ADMIN)) { err = -EPERM; break; } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 378b20b..065effd 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -231,7 +231,7 @@ static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t) (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { - rcu_assign_pointer(*tp, t->next); + RCU_INIT_POINTER(*tp, t->next); break; } } @@ -241,8 +241,8 @@ static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t) { struct ip_tunnel __rcu **tp = ipip_bucket(ipn, t); - rcu_assign_pointer(t->next, rtnl_dereference(*tp)); - rcu_assign_pointer(*tp, t); + RCU_INIT_POINTER(t->next, rtnl_dereference(*tp)); + RCU_INIT_POINTER(*tp, t); } static struct ip_tunnel * ipip_tunnel_locate(struct net *net, @@ -301,7 +301,7 @@ static void ipip_tunnel_uninit(struct net_device *dev) struct ipip_net *ipn = net_generic(net, ipip_net_id); if (dev == ipn->fb_tunnel_dev) - rcu_assign_pointer(ipn->tunnels_wc[0], NULL); + RCU_INIT_POINTER(ipn->tunnels_wc[0], NULL); else ipip_tunnel_unlink(ipn, netdev_priv(dev)); dev_put(dev); @@ -791,7 +791,7 @@ static int __net_init ipip_fb_tunnel_init(struct net_device *dev) return -ENOMEM; dev_hold(dev); - rcu_assign_pointer(ipn->tunnels_wc[0], tunnel); + RCU_INIT_POINTER(ipn->tunnels_wc[0], tunnel); return 0; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 58e8791..6164e98 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1176,7 +1176,7 @@ static void mrtsock_destruct(struct sock *sk) ipmr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; - rcu_assign_pointer(mrt->mroute_sk, NULL); + RCU_INIT_POINTER(mrt->mroute_sk, NULL); mroute_clean_tables(mrt); } } @@ -1203,7 +1203,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -ENOENT; if (optname != MRT_INIT) { - if (sk != rcu_dereference_raw(mrt->mroute_sk) && + if (sk != rcu_access_pointer(mrt->mroute_sk) && !capable(CAP_NET_ADMIN)) return -EACCES; } @@ -1224,13 +1224,13 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi ret = ip_ra_control(sk, 1, mrtsock_destruct); if (ret == 0) { - rcu_assign_pointer(mrt->mroute_sk, sk); + RCU_INIT_POINTER(mrt->mroute_sk, sk); IPV4_DEVCONF_ALL(net, MC_FORWARDING)++; } rtnl_unlock(); return ret; case MRT_DONE: - if (sk != rcu_dereference_raw(mrt->mroute_sk)) + if (sk != rcu_access_pointer(mrt->mroute_sk)) return -EACCES; return ip_ra_control(sk, 0, NULL); case MRT_ADD_VIF: diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index db8d22d..a639967 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -395,7 +395,6 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) config = clusterip_config_init(cipinfo, e->ip.dst.s_addr, dev); if (!config) { - pr_info("cannot allocate config\n"); dev_put(dev); return -ENOMEM; } diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 446e0f4..b550815 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -135,10 +135,8 @@ static struct sk_buff *ulog_alloc_skb(unsigned int size) * due to slab allocator restrictions */ n = max(size, nlbufsiz); - skb = alloc_skb(n, GFP_ATOMIC); + skb = alloc_skb(n, GFP_ATOMIC | __GFP_NOWARN); if (!skb) { - pr_debug("cannot alloc whole buffer %ub!\n", n); - if (n > size) { /* try to allocate only as much as we need for * current packet */ diff --git a/net/ipv4/netfilter/nf_nat_amanda.c b/net/ipv4/netfilter/nf_nat_amanda.c index 703f366f..7b22382 100644 --- a/net/ipv4/netfilter/nf_nat_amanda.c +++ b/net/ipv4/netfilter/nf_nat_amanda.c @@ -70,14 +70,14 @@ static unsigned int help(struct sk_buff *skb, static void __exit nf_nat_amanda_fini(void) { - rcu_assign_pointer(nf_nat_amanda_hook, NULL); + RCU_INIT_POINTER(nf_nat_amanda_hook, NULL); synchronize_rcu(); } static int __init nf_nat_amanda_init(void) { BUG_ON(nf_nat_amanda_hook != NULL); - rcu_assign_pointer(nf_nat_amanda_hook, help); + RCU_INIT_POINTER(nf_nat_amanda_hook, help); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 3346de5..447bc5c 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -514,7 +514,7 @@ int nf_nat_protocol_register(const struct nf_nat_protocol *proto) ret = -EBUSY; goto out; } - rcu_assign_pointer(nf_nat_protos[proto->protonum], proto); + RCU_INIT_POINTER(nf_nat_protos[proto->protonum], proto); out: spin_unlock_bh(&nf_nat_lock); return ret; @@ -525,7 +525,7 @@ EXPORT_SYMBOL(nf_nat_protocol_register); void nf_nat_protocol_unregister(const struct nf_nat_protocol *proto) { spin_lock_bh(&nf_nat_lock); - rcu_assign_pointer(nf_nat_protos[proto->protonum], + RCU_INIT_POINTER(nf_nat_protos[proto->protonum], &nf_nat_unknown_protocol); spin_unlock_bh(&nf_nat_lock); synchronize_rcu(); @@ -736,10 +736,10 @@ static int __init nf_nat_init(void) /* Sew in builtin protocols. */ spin_lock_bh(&nf_nat_lock); for (i = 0; i < MAX_IP_NAT_PROTO; i++) - rcu_assign_pointer(nf_nat_protos[i], &nf_nat_unknown_protocol); - rcu_assign_pointer(nf_nat_protos[IPPROTO_TCP], &nf_nat_protocol_tcp); - rcu_assign_pointer(nf_nat_protos[IPPROTO_UDP], &nf_nat_protocol_udp); - rcu_assign_pointer(nf_nat_protos[IPPROTO_ICMP], &nf_nat_protocol_icmp); + RCU_INIT_POINTER(nf_nat_protos[i], &nf_nat_unknown_protocol); + RCU_INIT_POINTER(nf_nat_protos[IPPROTO_TCP], &nf_nat_protocol_tcp); + RCU_INIT_POINTER(nf_nat_protos[IPPROTO_UDP], &nf_nat_protocol_udp); + RCU_INIT_POINTER(nf_nat_protos[IPPROTO_ICMP], &nf_nat_protocol_icmp); spin_unlock_bh(&nf_nat_lock); /* Initialize fake conntrack so that NAT will skip it */ @@ -748,12 +748,12 @@ static int __init nf_nat_init(void) l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET); BUG_ON(nf_nat_seq_adjust_hook != NULL); - rcu_assign_pointer(nf_nat_seq_adjust_hook, nf_nat_seq_adjust); + RCU_INIT_POINTER(nf_nat_seq_adjust_hook, nf_nat_seq_adjust); BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); - rcu_assign_pointer(nfnetlink_parse_nat_setup_hook, + RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, nfnetlink_parse_nat_setup); BUG_ON(nf_ct_nat_offset != NULL); - rcu_assign_pointer(nf_ct_nat_offset, nf_nat_get_offset); + RCU_INIT_POINTER(nf_ct_nat_offset, nf_nat_get_offset); return 0; cleanup_extend: @@ -766,9 +766,9 @@ static void __exit nf_nat_cleanup(void) unregister_pernet_subsys(&nf_nat_net_ops); nf_ct_l3proto_put(l3proto); nf_ct_extend_unregister(&nat_extend); - rcu_assign_pointer(nf_nat_seq_adjust_hook, NULL); - rcu_assign_pointer(nfnetlink_parse_nat_setup_hook, NULL); - rcu_assign_pointer(nf_ct_nat_offset, NULL); + RCU_INIT_POINTER(nf_nat_seq_adjust_hook, NULL); + RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); + RCU_INIT_POINTER(nf_ct_nat_offset, NULL); synchronize_net(); } diff --git a/net/ipv4/netfilter/nf_nat_ftp.c b/net/ipv4/netfilter/nf_nat_ftp.c index dc73abb..e462a95 100644 --- a/net/ipv4/netfilter/nf_nat_ftp.c +++ b/net/ipv4/netfilter/nf_nat_ftp.c @@ -113,14 +113,14 @@ out: static void __exit nf_nat_ftp_fini(void) { - rcu_assign_pointer(nf_nat_ftp_hook, NULL); + RCU_INIT_POINTER(nf_nat_ftp_hook, NULL); synchronize_rcu(); } static int __init nf_nat_ftp_init(void) { BUG_ON(nf_nat_ftp_hook != NULL); - rcu_assign_pointer(nf_nat_ftp_hook, nf_nat_ftp); + RCU_INIT_POINTER(nf_nat_ftp_hook, nf_nat_ftp); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 790f316..b9a1136 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -581,30 +581,30 @@ static int __init init(void) BUG_ON(nat_callforwarding_hook != NULL); BUG_ON(nat_q931_hook != NULL); - rcu_assign_pointer(set_h245_addr_hook, set_h245_addr); - rcu_assign_pointer(set_h225_addr_hook, set_h225_addr); - rcu_assign_pointer(set_sig_addr_hook, set_sig_addr); - rcu_assign_pointer(set_ras_addr_hook, set_ras_addr); - rcu_assign_pointer(nat_rtp_rtcp_hook, nat_rtp_rtcp); - rcu_assign_pointer(nat_t120_hook, nat_t120); - rcu_assign_pointer(nat_h245_hook, nat_h245); - rcu_assign_pointer(nat_callforwarding_hook, nat_callforwarding); - rcu_assign_pointer(nat_q931_hook, nat_q931); + RCU_INIT_POINTER(set_h245_addr_hook, set_h245_addr); + RCU_INIT_POINTER(set_h225_addr_hook, set_h225_addr); + RCU_INIT_POINTER(set_sig_addr_hook, set_sig_addr); + RCU_INIT_POINTER(set_ras_addr_hook, set_ras_addr); + RCU_INIT_POINTER(nat_rtp_rtcp_hook, nat_rtp_rtcp); + RCU_INIT_POINTER(nat_t120_hook, nat_t120); + RCU_INIT_POINTER(nat_h245_hook, nat_h245); + RCU_INIT_POINTER(nat_callforwarding_hook, nat_callforwarding); + RCU_INIT_POINTER(nat_q931_hook, nat_q931); return 0; } /****************************************************************************/ static void __exit fini(void) { - rcu_assign_pointer(set_h245_addr_hook, NULL); - rcu_assign_pointer(set_h225_addr_hook, NULL); - rcu_assign_pointer(set_sig_addr_hook, NULL); - rcu_assign_pointer(set_ras_addr_hook, NULL); - rcu_assign_pointer(nat_rtp_rtcp_hook, NULL); - rcu_assign_pointer(nat_t120_hook, NULL); - rcu_assign_pointer(nat_h245_hook, NULL); - rcu_assign_pointer(nat_callforwarding_hook, NULL); - rcu_assign_pointer(nat_q931_hook, NULL); + RCU_INIT_POINTER(set_h245_addr_hook, NULL); + RCU_INIT_POINTER(set_h225_addr_hook, NULL); + RCU_INIT_POINTER(set_sig_addr_hook, NULL); + RCU_INIT_POINTER(set_ras_addr_hook, NULL); + RCU_INIT_POINTER(nat_rtp_rtcp_hook, NULL); + RCU_INIT_POINTER(nat_t120_hook, NULL); + RCU_INIT_POINTER(nat_h245_hook, NULL); + RCU_INIT_POINTER(nat_callforwarding_hook, NULL); + RCU_INIT_POINTER(nat_q931_hook, NULL); synchronize_rcu(); } diff --git a/net/ipv4/netfilter/nf_nat_irc.c b/net/ipv4/netfilter/nf_nat_irc.c index 535e1a8..979ae16 100644 --- a/net/ipv4/netfilter/nf_nat_irc.c +++ b/net/ipv4/netfilter/nf_nat_irc.c @@ -75,14 +75,14 @@ static unsigned int help(struct sk_buff *skb, static void __exit nf_nat_irc_fini(void) { - rcu_assign_pointer(nf_nat_irc_hook, NULL); + RCU_INIT_POINTER(nf_nat_irc_hook, NULL); synchronize_rcu(); } static int __init nf_nat_irc_init(void) { BUG_ON(nf_nat_irc_hook != NULL); - rcu_assign_pointer(nf_nat_irc_hook, help); + RCU_INIT_POINTER(nf_nat_irc_hook, help); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 4c06003..3e8284b 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -282,25 +282,25 @@ static int __init nf_nat_helper_pptp_init(void) nf_nat_need_gre(); BUG_ON(nf_nat_pptp_hook_outbound != NULL); - rcu_assign_pointer(nf_nat_pptp_hook_outbound, pptp_outbound_pkt); + RCU_INIT_POINTER(nf_nat_pptp_hook_outbound, pptp_outbound_pkt); BUG_ON(nf_nat_pptp_hook_inbound != NULL); - rcu_assign_pointer(nf_nat_pptp_hook_inbound, pptp_inbound_pkt); + RCU_INIT_POINTER(nf_nat_pptp_hook_inbound, pptp_inbound_pkt); BUG_ON(nf_nat_pptp_hook_exp_gre != NULL); - rcu_assign_pointer(nf_nat_pptp_hook_exp_gre, pptp_exp_gre); + RCU_INIT_POINTER(nf_nat_pptp_hook_exp_gre, pptp_exp_gre); BUG_ON(nf_nat_pptp_hook_expectfn != NULL); - rcu_assign_pointer(nf_nat_pptp_hook_expectfn, pptp_nat_expected); + RCU_INIT_POINTER(nf_nat_pptp_hook_expectfn, pptp_nat_expected); return 0; } static void __exit nf_nat_helper_pptp_fini(void) { - rcu_assign_pointer(nf_nat_pptp_hook_expectfn, NULL); - rcu_assign_pointer(nf_nat_pptp_hook_exp_gre, NULL); - rcu_assign_pointer(nf_nat_pptp_hook_inbound, NULL); - rcu_assign_pointer(nf_nat_pptp_hook_outbound, NULL); + RCU_INIT_POINTER(nf_nat_pptp_hook_expectfn, NULL); + RCU_INIT_POINTER(nf_nat_pptp_hook_exp_gre, NULL); + RCU_INIT_POINTER(nf_nat_pptp_hook_inbound, NULL); + RCU_INIT_POINTER(nf_nat_pptp_hook_outbound, NULL); synchronize_rcu(); } diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index e40cf78..78844d9 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -528,13 +528,13 @@ err1: static void __exit nf_nat_sip_fini(void) { - rcu_assign_pointer(nf_nat_sip_hook, NULL); - rcu_assign_pointer(nf_nat_sip_seq_adjust_hook, NULL); - rcu_assign_pointer(nf_nat_sip_expect_hook, NULL); - rcu_assign_pointer(nf_nat_sdp_addr_hook, NULL); - rcu_assign_pointer(nf_nat_sdp_port_hook, NULL); - rcu_assign_pointer(nf_nat_sdp_session_hook, NULL); - rcu_assign_pointer(nf_nat_sdp_media_hook, NULL); + RCU_INIT_POINTER(nf_nat_sip_hook, NULL); + RCU_INIT_POINTER(nf_nat_sip_seq_adjust_hook, NULL); + RCU_INIT_POINTER(nf_nat_sip_expect_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_addr_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_port_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_session_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_media_hook, NULL); synchronize_rcu(); } @@ -547,13 +547,13 @@ static int __init nf_nat_sip_init(void) BUG_ON(nf_nat_sdp_port_hook != NULL); BUG_ON(nf_nat_sdp_session_hook != NULL); BUG_ON(nf_nat_sdp_media_hook != NULL); - rcu_assign_pointer(nf_nat_sip_hook, ip_nat_sip); - rcu_assign_pointer(nf_nat_sip_seq_adjust_hook, ip_nat_sip_seq_adjust); - rcu_assign_pointer(nf_nat_sip_expect_hook, ip_nat_sip_expect); - rcu_assign_pointer(nf_nat_sdp_addr_hook, ip_nat_sdp_addr); - rcu_assign_pointer(nf_nat_sdp_port_hook, ip_nat_sdp_port); - rcu_assign_pointer(nf_nat_sdp_session_hook, ip_nat_sdp_session); - rcu_assign_pointer(nf_nat_sdp_media_hook, ip_nat_sdp_media); + RCU_INIT_POINTER(nf_nat_sip_hook, ip_nat_sip); + RCU_INIT_POINTER(nf_nat_sip_seq_adjust_hook, ip_nat_sip_seq_adjust); + RCU_INIT_POINTER(nf_nat_sip_expect_hook, ip_nat_sip_expect); + RCU_INIT_POINTER(nf_nat_sdp_addr_hook, ip_nat_sdp_addr); + RCU_INIT_POINTER(nf_nat_sdp_port_hook, ip_nat_sdp_port); + RCU_INIT_POINTER(nf_nat_sdp_session_hook, ip_nat_sdp_session); + RCU_INIT_POINTER(nf_nat_sdp_media_hook, ip_nat_sdp_media); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 076b7c8..2133c30 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -400,11 +400,8 @@ static unsigned char asn1_octets_decode(struct asn1_ctx *ctx, *len = 0; *octets = kmalloc(eoc - ctx->pointer, GFP_ATOMIC); - if (*octets == NULL) { - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); + if (*octets == NULL) return 0; - } ptr = *octets; while (ctx->pointer < eoc) { @@ -451,11 +448,8 @@ static unsigned char asn1_oid_decode(struct asn1_ctx *ctx, return 0; *oid = kmalloc(size * sizeof(unsigned long), GFP_ATOMIC); - if (*oid == NULL) { - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); + if (*oid == NULL) return 0; - } optr = *oid; @@ -728,8 +722,6 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); if (*obj == NULL) { kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); return 0; } (*obj)->syntax.l[0] = l; @@ -744,8 +736,6 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, if (*obj == NULL) { kfree(p); kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); return 0; } memcpy((*obj)->syntax.c, p, len); @@ -759,8 +749,6 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, *obj = kmalloc(sizeof(struct snmp_object), GFP_ATOMIC); if (*obj == NULL) { kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); return 0; } if (!asn1_null_decode(ctx, end)) { @@ -780,8 +768,6 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, if (*obj == NULL) { kfree(lp); kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); return 0; } memcpy((*obj)->syntax.ul, lp, len); @@ -801,8 +787,6 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, if (*obj == NULL) { kfree(p); kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); return 0; } memcpy((*obj)->syntax.uc, p, len); @@ -819,8 +803,6 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); if (*obj == NULL) { kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); return 0; } (*obj)->syntax.ul[0] = ul; @@ -1310,7 +1292,7 @@ static int __init nf_nat_snmp_basic_init(void) int ret = 0; BUG_ON(nf_nat_snmp_hook != NULL); - rcu_assign_pointer(nf_nat_snmp_hook, help); + RCU_INIT_POINTER(nf_nat_snmp_hook, help); ret = nf_conntrack_helper_register(&snmp_trap_helper); if (ret < 0) { @@ -1322,7 +1304,7 @@ static int __init nf_nat_snmp_basic_init(void) static void __exit nf_nat_snmp_basic_fini(void) { - rcu_assign_pointer(nf_nat_snmp_hook, NULL); + RCU_INIT_POINTER(nf_nat_snmp_hook, NULL); nf_conntrack_helper_unregister(&snmp_trap_helper); } diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index a6e606e..9290048 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -284,7 +284,7 @@ static int __init nf_nat_standalone_init(void) #ifdef CONFIG_XFRM BUG_ON(ip_nat_decode_session != NULL); - rcu_assign_pointer(ip_nat_decode_session, nat_decode_session); + RCU_INIT_POINTER(ip_nat_decode_session, nat_decode_session); #endif ret = nf_nat_rule_init(); if (ret < 0) { @@ -302,7 +302,7 @@ static int __init nf_nat_standalone_init(void) nf_nat_rule_cleanup(); cleanup_decode_session: #ifdef CONFIG_XFRM - rcu_assign_pointer(ip_nat_decode_session, NULL); + RCU_INIT_POINTER(ip_nat_decode_session, NULL); synchronize_net(); #endif return ret; @@ -313,7 +313,7 @@ static void __exit nf_nat_standalone_fini(void) nf_unregister_hooks(nf_nat_ops, ARRAY_SIZE(nf_nat_ops)); nf_nat_rule_cleanup(); #ifdef CONFIG_XFRM - rcu_assign_pointer(ip_nat_decode_session, NULL); + RCU_INIT_POINTER(ip_nat_decode_session, NULL); synchronize_net(); #endif /* Conntrack caches are unregistered in nf_conntrack_cleanup */ diff --git a/net/ipv4/netfilter/nf_nat_tftp.c b/net/ipv4/netfilter/nf_nat_tftp.c index 7274a43..a2901bf 100644 --- a/net/ipv4/netfilter/nf_nat_tftp.c +++ b/net/ipv4/netfilter/nf_nat_tftp.c @@ -36,14 +36,14 @@ static unsigned int help(struct sk_buff *skb, static void __exit nf_nat_tftp_fini(void) { - rcu_assign_pointer(nf_nat_tftp_hook, NULL); + RCU_INIT_POINTER(nf_nat_tftp_hook, NULL); synchronize_rcu(); } static int __init nf_nat_tftp_init(void) { BUG_ON(nf_nat_tftp_hook != NULL); - rcu_assign_pointer(nf_nat_tftp_hook, help); + RCU_INIT_POINTER(nf_nat_tftp_hook, help); return 0; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 075212e..155138d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -120,7 +120,6 @@ static int ip_rt_max_size; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; -static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_redirect_number __read_mostly = 9; static int ip_rt_redirect_load __read_mostly = HZ / 50; @@ -324,7 +323,7 @@ static struct rtable *rt_cache_get_first(struct seq_file *seq) struct rtable *r = NULL; for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) { - if (!rcu_dereference_raw(rt_hash_table[st->bucket].chain)) + if (!rcu_access_pointer(rt_hash_table[st->bucket].chain)) continue; rcu_read_lock_bh(); r = rcu_dereference_bh(rt_hash_table[st->bucket].chain); @@ -350,7 +349,7 @@ static struct rtable *__rt_cache_get_next(struct seq_file *seq, do { if (--st->bucket < 0) return NULL; - } while (!rcu_dereference_raw(rt_hash_table[st->bucket].chain)); + } while (!rcu_access_pointer(rt_hash_table[st->bucket].chain)); rcu_read_lock_bh(); r = rcu_dereference_bh(rt_hash_table[st->bucket].chain); } @@ -761,7 +760,7 @@ static void rt_do_flush(struct net *net, int process_context) if (process_context && need_resched()) cond_resched(); - rth = rcu_dereference_raw(rt_hash_table[i].chain); + rth = rcu_access_pointer(rt_hash_table[i].chain); if (!rth) continue; @@ -1309,7 +1308,12 @@ static void rt_del(unsigned hash, struct rtable *rt) void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, __be32 saddr, struct net_device *dev) { + int s, i; struct in_device *in_dev = __in_dev_get_rcu(dev); + struct rtable *rt; + __be32 skeys[2] = { saddr, 0 }; + int ikeys[2] = { dev->ifindex, 0 }; + struct flowi4 fl4; struct inet_peer *peer; struct net *net; @@ -1332,13 +1336,34 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, goto reject_redirect; } - peer = inet_getpeer_v4(daddr, 1); - if (peer) { - peer->redirect_learned.a4 = new_gw; + memset(&fl4, 0, sizeof(fl4)); + fl4.daddr = daddr; + for (s = 0; s < 2; s++) { + for (i = 0; i < 2; i++) { + fl4.flowi4_oif = ikeys[i]; + fl4.saddr = skeys[s]; + rt = __ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) + continue; - inet_putpeer(peer); + if (rt->dst.error || rt->dst.dev != dev || + rt->rt_gateway != old_gw) { + ip_rt_put(rt); + continue; + } + + if (!rt->peer) + rt_bind_peer(rt, rt->rt_dst, 1); + + peer = rt->peer; + if (peer) { + peer->redirect_learned.a4 = new_gw; + atomic_inc(&__rt_peer_genid); + } - atomic_inc(&__rt_peer_genid); + ip_rt_put(rt); + return; + } } return; @@ -1568,11 +1593,10 @@ unsigned short ip_rt_frag_needed(struct net *net, const struct iphdr *iph, est_mtu = mtu; peer->pmtu_learned = mtu; peer->pmtu_expires = pmtu_expires; + atomic_inc(&__rt_peer_genid); } inet_putpeer(peer); - - atomic_inc(&__rt_peer_genid); } return est_mtu ? : new_mtu; } @@ -3121,13 +3145,6 @@ static ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec_jiffies, }, { - .procname = "gc_interval", - .data = &ip_rt_gc_interval, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { .procname = "redirect_load", .data = &ip_rt_redirect_load, .maxlen = sizeof(int), diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 3bc5c8f..d7b89b1 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -265,7 +265,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, struct ip_options *opt) { struct tcp_options_received tcp_opt; - u8 *hash_location; + const u8 *hash_location; struct inet_request_sock *ireq; struct tcp_request_sock *treq; struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 46febca..34f5db1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -374,7 +374,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) { unsigned int mask; struct sock *sk = sock->sk; - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); sock_poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == TCP_LISTEN) @@ -524,11 +524,11 @@ EXPORT_SYMBOL(tcp_ioctl); static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb) { - TCP_SKB_CB(skb)->flags |= TCPHDR_PSH; + TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; tp->pushed_seq = tp->write_seq; } -static inline int forced_push(struct tcp_sock *tp) +static inline int forced_push(const struct tcp_sock *tp) { return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1)); } @@ -540,7 +540,7 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb) skb->csum = 0; tcb->seq = tcb->end_seq = tp->write_seq; - tcb->flags = TCPHDR_ACK; + tcb->tcp_flags = TCPHDR_ACK; tcb->sacked = 0; skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); @@ -813,7 +813,7 @@ new_segment: goto wait_for_memory; if (can_coalesce) { - skb_shinfo(skb)->frags[i - 1].size += copy; + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { get_page(page); skb_fill_page_desc(skb, i, page, offset, copy); @@ -830,7 +830,7 @@ new_segment: skb_shinfo(skb)->gso_segs = 0; if (!copied) - TCP_SKB_CB(skb)->flags &= ~TCPHDR_PSH; + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; copied += copy; poffset += copy; @@ -891,9 +891,9 @@ EXPORT_SYMBOL(tcp_sendpage); #define TCP_PAGE(sk) (sk->sk_sndmsg_page) #define TCP_OFF(sk) (sk->sk_sndmsg_off) -static inline int select_size(struct sock *sk, int sg) +static inline int select_size(const struct sock *sk, int sg) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); int tmp = tp->mss_cache; if (sg) { @@ -1058,8 +1058,7 @@ new_segment: /* Update the skb. */ if (merge) { - skb_shinfo(skb)->frags[i - 1].size += - copy; + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { skb_fill_page_desc(skb, i, page, off, copy); if (TCP_PAGE(sk)) { @@ -1074,7 +1073,7 @@ new_segment: } if (!copied) - TCP_SKB_CB(skb)->flags &= ~TCPHDR_PSH; + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; tp->write_seq += copy; TCP_SKB_CB(skb)->end_seq += copy; @@ -1194,13 +1193,11 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) struct tcp_sock *tp = tcp_sk(sk); int time_to_ack = 0; -#if TCP_DEBUG struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq), "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n", tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt); -#endif if (inet_csk_ack_scheduled(sk)) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -2409,7 +2406,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); if (level != SOL_TCP) return icsk->icsk_af_ops->setsockopt(sk, level, optname, @@ -2431,9 +2428,9 @@ EXPORT_SYMBOL(compat_tcp_setsockopt); #endif /* Return information about state of tcp endpoint in API format. */ -void tcp_get_info(struct sock *sk, struct tcp_info *info) +void tcp_get_info(const struct sock *sk, struct tcp_info *info) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); u32 now = tcp_time_stamp; @@ -2455,8 +2452,10 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale; } - if (tp->ecn_flags&TCP_ECN_OK) + if (tp->ecn_flags & TCP_ECN_OK) info->tcpi_options |= TCPI_OPT_ECN; + if (tp->ecn_flags & TCP_ECN_SEEN) + info->tcpi_options |= TCPI_OPT_ECN_SEEN; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato); @@ -2857,26 +2856,25 @@ EXPORT_SYMBOL(tcp_gro_complete); #ifdef CONFIG_TCP_MD5SIG static unsigned long tcp_md5sig_users; -static struct tcp_md5sig_pool * __percpu *tcp_md5sig_pool; +static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool; static DEFINE_SPINLOCK(tcp_md5sig_pool_lock); -static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool * __percpu *pool) +static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool) { int cpu; + for_each_possible_cpu(cpu) { - struct tcp_md5sig_pool *p = *per_cpu_ptr(pool, cpu); - if (p) { - if (p->md5_desc.tfm) - crypto_free_hash(p->md5_desc.tfm); - kfree(p); - } + struct tcp_md5sig_pool *p = per_cpu_ptr(pool, cpu); + + if (p->md5_desc.tfm) + crypto_free_hash(p->md5_desc.tfm); } free_percpu(pool); } void tcp_free_md5sig_pool(void) { - struct tcp_md5sig_pool * __percpu *pool = NULL; + struct tcp_md5sig_pool __percpu *pool = NULL; spin_lock_bh(&tcp_md5sig_pool_lock); if (--tcp_md5sig_users == 0) { @@ -2889,30 +2887,24 @@ void tcp_free_md5sig_pool(void) } EXPORT_SYMBOL(tcp_free_md5sig_pool); -static struct tcp_md5sig_pool * __percpu * +static struct tcp_md5sig_pool __percpu * __tcp_alloc_md5sig_pool(struct sock *sk) { int cpu; - struct tcp_md5sig_pool * __percpu *pool; + struct tcp_md5sig_pool __percpu *pool; - pool = alloc_percpu(struct tcp_md5sig_pool *); + pool = alloc_percpu(struct tcp_md5sig_pool); if (!pool) return NULL; for_each_possible_cpu(cpu) { - struct tcp_md5sig_pool *p; struct crypto_hash *hash; - p = kzalloc(sizeof(*p), sk->sk_allocation); - if (!p) - goto out_free; - *per_cpu_ptr(pool, cpu) = p; - hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); if (!hash || IS_ERR(hash)) goto out_free; - p->md5_desc.tfm = hash; + per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash; } return pool; out_free: @@ -2920,9 +2912,9 @@ out_free: return NULL; } -struct tcp_md5sig_pool * __percpu *tcp_alloc_md5sig_pool(struct sock *sk) +struct tcp_md5sig_pool __percpu *tcp_alloc_md5sig_pool(struct sock *sk) { - struct tcp_md5sig_pool * __percpu *pool; + struct tcp_md5sig_pool __percpu *pool; int alloc = 0; retry: @@ -2941,7 +2933,7 @@ retry: if (alloc) { /* we cannot hold spinlock here because this may sleep. */ - struct tcp_md5sig_pool * __percpu *p; + struct tcp_md5sig_pool __percpu *p; p = __tcp_alloc_md5sig_pool(sk); spin_lock_bh(&tcp_md5sig_pool_lock); @@ -2974,7 +2966,7 @@ EXPORT_SYMBOL(tcp_alloc_md5sig_pool); */ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) { - struct tcp_md5sig_pool * __percpu *p; + struct tcp_md5sig_pool __percpu *p; local_bh_disable(); @@ -2985,7 +2977,7 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) spin_unlock(&tcp_md5sig_pool_lock); if (p) - return *this_cpu_ptr(p); + return this_cpu_ptr(p); local_bh_enable(); return NULL; @@ -3000,23 +2992,25 @@ void tcp_put_md5sig_pool(void) EXPORT_SYMBOL(tcp_put_md5sig_pool); int tcp_md5_hash_header(struct tcp_md5sig_pool *hp, - struct tcphdr *th) + const struct tcphdr *th) { struct scatterlist sg; + struct tcphdr hdr; int err; - __sum16 old_checksum = th->check; - th->check = 0; + /* We are not allowed to change tcphdr, make a local copy */ + memcpy(&hdr, th, sizeof(hdr)); + hdr.check = 0; + /* options aren't included in the hash */ - sg_init_one(&sg, th, sizeof(struct tcphdr)); - err = crypto_hash_update(&hp->md5_desc, &sg, sizeof(struct tcphdr)); - th->check = old_checksum; + sg_init_one(&sg, &hdr, sizeof(hdr)); + err = crypto_hash_update(&hp->md5_desc, &sg, sizeof(hdr)); return err; } EXPORT_SYMBOL(tcp_md5_hash_header); int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, - struct sk_buff *skb, unsigned header_len) + const struct sk_buff *skb, unsigned int header_len) { struct scatterlist sg; const struct tcphdr *tp = tcp_hdr(skb); @@ -3035,8 +3029,9 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, for (i = 0; i < shi->nr_frags; ++i) { const struct skb_frag_struct *f = &shi->frags[i]; - sg_set_page(&sg, f->page, f->size, f->page_offset); - if (crypto_hash_update(desc, &sg, f->size)) + struct page *page = skb_frag_page(f); + sg_set_page(&sg, page, skb_frag_size(f), f->page_offset); + if (crypto_hash_update(desc, &sg, skb_frag_size(f))) return 1; } @@ -3048,7 +3043,7 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, } EXPORT_SYMBOL(tcp_md5_hash_skb_data); -int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, struct tcp_md5sig_key *key) +int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key) { struct scatterlist sg; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 21fab3e..52b5c2d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -206,7 +206,7 @@ static inline void TCP_ECN_queue_cwr(struct tcp_sock *tp) tp->ecn_flags |= TCP_ECN_QUEUE_CWR; } -static inline void TCP_ECN_accept_cwr(struct tcp_sock *tp, struct sk_buff *skb) +static inline void TCP_ECN_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb) { if (tcp_hdr(skb)->cwr) tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; @@ -217,32 +217,41 @@ static inline void TCP_ECN_withdraw_cwr(struct tcp_sock *tp) tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; } -static inline void TCP_ECN_check_ce(struct tcp_sock *tp, struct sk_buff *skb) +static inline void TCP_ECN_check_ce(struct tcp_sock *tp, const struct sk_buff *skb) { - if (tp->ecn_flags & TCP_ECN_OK) { - if (INET_ECN_is_ce(TCP_SKB_CB(skb)->flags)) - tp->ecn_flags |= TCP_ECN_DEMAND_CWR; + if (!(tp->ecn_flags & TCP_ECN_OK)) + return; + + switch (TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK) { + case INET_ECN_NOT_ECT: /* Funny extension: if ECT is not set on a segment, - * it is surely retransmit. It is not in ECN RFC, - * but Linux follows this rule. */ - else if (INET_ECN_is_not_ect((TCP_SKB_CB(skb)->flags))) + * and we already seen ECT on a previous segment, + * it is probably a retransmit. + */ + if (tp->ecn_flags & TCP_ECN_SEEN) tcp_enter_quickack_mode((struct sock *)tp); + break; + case INET_ECN_CE: + tp->ecn_flags |= TCP_ECN_DEMAND_CWR; + /* fallinto */ + default: + tp->ecn_flags |= TCP_ECN_SEEN; } } -static inline void TCP_ECN_rcv_synack(struct tcp_sock *tp, struct tcphdr *th) +static inline void TCP_ECN_rcv_synack(struct tcp_sock *tp, const struct tcphdr *th) { if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || th->cwr)) tp->ecn_flags &= ~TCP_ECN_OK; } -static inline void TCP_ECN_rcv_syn(struct tcp_sock *tp, struct tcphdr *th) +static inline void TCP_ECN_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th) { if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || !th->cwr)) tp->ecn_flags &= ~TCP_ECN_OK; } -static inline int TCP_ECN_rcv_ecn_echo(struct tcp_sock *tp, struct tcphdr *th) +static inline int TCP_ECN_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr *th) { if (th->ece && !th->syn && (tp->ecn_flags & TCP_ECN_OK)) return 1; @@ -256,14 +265,11 @@ static inline int TCP_ECN_rcv_ecn_echo(struct tcp_sock *tp, struct tcphdr *th) static void tcp_fixup_sndbuf(struct sock *sk) { - int sndmem = tcp_sk(sk)->rx_opt.mss_clamp + MAX_TCP_HEADER + 16 + - sizeof(struct sk_buff); + int sndmem = SKB_TRUESIZE(tcp_sk(sk)->rx_opt.mss_clamp + MAX_TCP_HEADER); - if (sk->sk_sndbuf < 3 * sndmem) { - sk->sk_sndbuf = 3 * sndmem; - if (sk->sk_sndbuf > sysctl_tcp_wmem[2]) - sk->sk_sndbuf = sysctl_tcp_wmem[2]; - } + sndmem *= TCP_INIT_CWND; + if (sk->sk_sndbuf < sndmem) + sk->sk_sndbuf = min(sndmem, sysctl_tcp_wmem[2]); } /* 2. Tuning advertised window (window_clamp, rcv_ssthresh) @@ -309,7 +315,7 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb) return 0; } -static void tcp_grow_window(struct sock *sk, struct sk_buff *skb) +static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); @@ -339,17 +345,24 @@ static void tcp_grow_window(struct sock *sk, struct sk_buff *skb) static void tcp_fixup_rcvbuf(struct sock *sk) { - struct tcp_sock *tp = tcp_sk(sk); - int rcvmem = tp->advmss + MAX_TCP_HEADER + 16 + sizeof(struct sk_buff); + u32 mss = tcp_sk(sk)->advmss; + u32 icwnd = TCP_DEFAULT_INIT_RCVWND; + int rcvmem; - /* Try to select rcvbuf so that 4 mss-sized segments - * will fit to window and corresponding skbs will fit to our rcvbuf. - * (was 3; 4 is minimum to allow fast retransmit to work.) + /* Limit to 10 segments if mss <= 1460, + * or 14600/mss segments, with a minimum of two segments. */ - while (tcp_win_from_space(rcvmem) < tp->advmss) + if (mss > 1460) + icwnd = max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2); + + rcvmem = SKB_TRUESIZE(mss + MAX_TCP_HEADER); + while (tcp_win_from_space(rcvmem) < mss) rcvmem += 128; - if (sk->sk_rcvbuf < 4 * rcvmem) - sk->sk_rcvbuf = min(4 * rcvmem, sysctl_tcp_rmem[2]); + + rcvmem *= icwnd; + + if (sk->sk_rcvbuf < rcvmem) + sk->sk_rcvbuf = min(rcvmem, sysctl_tcp_rmem[2]); } /* 4. Try to fixup all. It is made immediately after connection enters @@ -416,7 +429,7 @@ static void tcp_clamp_window(struct sock *sk) */ void tcp_initialize_rcv_mss(struct sock *sk) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache); hint = min(hint, tp->rcv_wnd / 2); @@ -531,8 +544,7 @@ void tcp_rcv_space_adjust(struct sock *sk) space /= tp->advmss; if (!space) space = 1; - rcvmem = (tp->advmss + MAX_TCP_HEADER + - 16 + sizeof(struct sk_buff)); + rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER); while (tcp_win_from_space(rcvmem) < tp->advmss) rcvmem += 128; space *= rcvmem; @@ -812,7 +824,7 @@ void tcp_update_metrics(struct sock *sk) } } -__u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst) +__u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst) { __u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0); @@ -1204,7 +1216,7 @@ static void tcp_mark_lost_retrans(struct sock *sk) tp->lost_retrans_low = new_low_seq; } -static int tcp_check_dsack(struct sock *sk, struct sk_buff *ack_skb, +static int tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, struct tcp_sack_block_wire *sp, int num_sacks, u32 prior_snd_una) { @@ -1298,7 +1310,7 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, return in_sack; } -static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk, +static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk, struct tcp_sacktag_state *state, int dup_sack, int pcount) { @@ -1389,9 +1401,7 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, BUG_ON(!pcount); - /* Tweak before seqno plays */ - if (!tcp_is_fack(tp) && tcp_is_sack(tp) && tp->lost_skb_hint && - !before(TCP_SKB_CB(tp->lost_skb_hint)->seq, TCP_SKB_CB(skb)->seq)) + if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; TCP_SKB_CB(prev)->end_seq += shifted; @@ -1440,7 +1450,7 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tp->lost_cnt_hint -= tcp_skb_pcount(prev); } - TCP_SKB_CB(skb)->flags |= TCP_SKB_CB(prev)->flags; + TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(prev)->tcp_flags; if (skb == tcp_highest_sack(sk)) tcp_advance_highest_sack(sk, skb); @@ -1455,13 +1465,13 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, /* I wish gso_size would have a bit more sane initialization than * something-or-zero which complicates things */ -static int tcp_skb_seglen(struct sk_buff *skb) +static int tcp_skb_seglen(const struct sk_buff *skb) { return tcp_skb_pcount(skb) == 1 ? skb->len : tcp_skb_mss(skb); } /* Shifting pages past head area doesn't work */ -static int skb_can_shift(struct sk_buff *skb) +static int skb_can_shift(const struct sk_buff *skb) { return !skb_headlen(skb) && skb_is_nonlinear(skb); } @@ -1710,19 +1720,19 @@ static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb, return skb; } -static int tcp_sack_cache_ok(struct tcp_sock *tp, struct tcp_sack_block *cache) +static int tcp_sack_cache_ok(const struct tcp_sock *tp, const struct tcp_sack_block *cache) { return cache < tp->recv_sack_cache + ARRAY_SIZE(tp->recv_sack_cache); } static int -tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, +tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, u32 prior_snd_una) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - unsigned char *ptr = (skb_transport_header(ack_skb) + - TCP_SKB_CB(ack_skb)->sacked); + const unsigned char *ptr = (skb_transport_header(ack_skb) + + TCP_SKB_CB(ack_skb)->sacked); struct tcp_sack_block_wire *sp_wire = (struct tcp_sack_block_wire *)(ptr+2); struct tcp_sack_block sp[TCP_NUM_SACKS]; struct tcp_sack_block *cache; @@ -2286,7 +2296,7 @@ static int tcp_check_sack_reneging(struct sock *sk, int flag) return 0; } -static inline int tcp_fackets_out(struct tcp_sock *tp) +static inline int tcp_fackets_out(const struct tcp_sock *tp) { return tcp_is_reno(tp) ? tp->sacked_out + 1 : tp->fackets_out; } @@ -2306,19 +2316,20 @@ static inline int tcp_fackets_out(struct tcp_sock *tp) * they differ. Since neither occurs due to loss, TCP should really * ignore them. */ -static inline int tcp_dupack_heuristics(struct tcp_sock *tp) +static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) { return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1; } -static inline int tcp_skb_timedout(struct sock *sk, struct sk_buff *skb) +static inline int tcp_skb_timedout(const struct sock *sk, + const struct sk_buff *skb) { return tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto; } -static inline int tcp_head_timedout(struct sock *sk) +static inline int tcp_head_timedout(const struct sock *sk) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); return tp->packets_out && tcp_skb_timedout(sk, tcp_write_queue_head(sk)); @@ -2629,7 +2640,7 @@ static void tcp_cwnd_down(struct sock *sk, int flag) /* Nothing was retransmitted or returned timestamp is less * than timestamp of the first retransmission. */ -static inline int tcp_packet_delayed(struct tcp_sock *tp) +static inline int tcp_packet_delayed(const struct tcp_sock *tp) { return !tp->retrans_stamp || (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && @@ -2690,7 +2701,7 @@ static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh) tp->snd_cwnd_stamp = tcp_time_stamp; } -static inline int tcp_may_undo(struct tcp_sock *tp) +static inline int tcp_may_undo(const struct tcp_sock *tp) { return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp)); } @@ -2754,9 +2765,9 @@ static void tcp_try_undo_dsack(struct sock *sk) * that successive retransmissions of a segment must not advance * retrans_stamp under any conditions. */ -static int tcp_any_retrans_done(struct sock *sk) +static int tcp_any_retrans_done(const struct sock *sk) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; if (tp->retrans_out) @@ -2830,9 +2841,13 @@ 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); - /* 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; + + /* Do not moderate cwnd if it's already undone in cwr or recovery. */ + if (tp->undo_marker) { + if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR) + tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh); + else /* PRR */ + tp->snd_cwnd = tp->snd_ssthresh; tp->snd_cwnd_stamp = tcp_time_stamp; } tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); @@ -2950,6 +2965,38 @@ void tcp_simple_retransmit(struct sock *sk) } EXPORT_SYMBOL(tcp_simple_retransmit); +/* This function implements the PRR algorithm, specifcally the PRR-SSRB + * (proportional rate reduction with slow start reduction bound) as described in + * http://www.ietf.org/id/draft-mathis-tcpm-proportional-rate-reduction-01.txt. + * It computes the number of packets to send (sndcnt) based on packets newly + * delivered: + * 1) If the packets in flight is larger than ssthresh, PRR spreads the + * cwnd reductions across a full RTT. + * 2) If packets in flight is lower than ssthresh (such as due to excess + * losses and/or application stalls), do not perform any further cwnd + * reductions, but instead slow start up to ssthresh. + */ +static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked, + int fast_rexmit, int flag) +{ + struct tcp_sock *tp = tcp_sk(sk); + int sndcnt = 0; + int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp); + + if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) { + u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + + tp->prior_cwnd - 1; + sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out; + } else { + sndcnt = min_t(int, delta, + max_t(int, tp->prr_delivered - tp->prr_out, + newly_acked_sacked) + 1); + } + + sndcnt = max(sndcnt, (fast_rexmit ? 1 : 0)); + tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt; +} + /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and @@ -2961,7 +3008,8 @@ EXPORT_SYMBOL(tcp_simple_retransmit); * It does _not_ decide what to send, it is made in function * tcp_xmit_retransmit_queue(). */ -static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) +static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, + int newly_acked_sacked, int flag) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -3111,13 +3159,17 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) tp->bytes_acked = 0; tp->snd_cwnd_cnt = 0; + tp->prior_cwnd = tp->snd_cwnd; + tp->prr_delivered = 0; + tp->prr_out = 0; tcp_set_ca_state(sk, TCP_CA_Recovery); fast_rexmit = 1; } if (do_lost || (tcp_is_fack(tp) && tcp_head_timedout(sk))) tcp_update_scoreboard(sk, fast_rexmit); - tcp_cwnd_down(sk, flag); + tp->prr_delivered += newly_acked_sacked; + tcp_update_cwnd_in_recovery(sk, newly_acked_sacked, fast_rexmit, flag); tcp_xmit_retransmit_queue(sk); } @@ -3194,7 +3246,7 @@ static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) */ static void tcp_rearm_rto(struct sock *sk) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); if (!tp->packets_out) { inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); @@ -3298,7 +3350,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, * connection startup slow start one packet too * quickly. This is severely frowned upon behavior. */ - if (!(scb->flags & TCPHDR_SYN)) { + if (!(scb->tcp_flags & TCPHDR_SYN)) { flag |= FLAG_DATA_ACKED; } else { flag |= FLAG_SYN_ACKED; @@ -3446,7 +3498,7 @@ static inline int tcp_may_update_window(const struct tcp_sock *tp, * Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2 * and in FreeBSD. NetBSD's one is even worse.) is wrong. */ -static int tcp_ack_update_window(struct sock *sk, struct sk_buff *skb, u32 ack, +static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 ack, u32 ack_seq) { struct tcp_sock *tp = tcp_sk(sk); @@ -3622,7 +3674,7 @@ static int tcp_process_frto(struct sock *sk, int flag) } /* This routine deals with incoming acks, but not outgoing ones. */ -static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) +static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -3632,6 +3684,8 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) u32 prior_in_flight; u32 prior_fackets; int prior_packets; + int prior_sacked = tp->sacked_out; + int newly_acked_sacked = 0; int frto_cwnd = 0; /* If the ack is older than previous acks @@ -3703,6 +3757,9 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una); + newly_acked_sacked = (prior_packets - prior_sacked) - + (tp->packets_out - tp->sacked_out); + if (tp->frto_counter) frto_cwnd = tcp_process_frto(sk, flag); /* Guarantee sacktag reordering detection against wrap-arounds */ @@ -3715,7 +3772,7 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) tcp_may_raise_cwnd(sk, flag)) tcp_cong_avoid(sk, ack, prior_in_flight); tcp_fastretrans_alert(sk, prior_packets - tp->packets_out, - flag); + newly_acked_sacked, flag); } else { if ((flag & FLAG_DATA_ACKED) && !frto_cwnd) tcp_cong_avoid(sk, ack, prior_in_flight); @@ -3754,14 +3811,14 @@ old_ack: * But, this can also be called on packets in the established flow when * the fast version below fails. */ -void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, - u8 **hvpp, int estab) +void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx, + const u8 **hvpp, int estab) { - unsigned char *ptr; - struct tcphdr *th = tcp_hdr(skb); + const unsigned char *ptr; + const struct tcphdr *th = tcp_hdr(skb); int length = (th->doff * 4) - sizeof(struct tcphdr); - ptr = (unsigned char *)(th + 1); + ptr = (const unsigned char *)(th + 1); opt_rx->saw_tstamp = 0; while (length > 0) { @@ -3872,9 +3929,9 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, } EXPORT_SYMBOL(tcp_parse_options); -static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th) +static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr *th) { - __be32 *ptr = (__be32 *)(th + 1); + const __be32 *ptr = (const __be32 *)(th + 1); if (*ptr == htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP)) { @@ -3891,8 +3948,9 @@ static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th) /* Fast parse options. This hopes to only see timestamps. * If it is wrong it falls back on tcp_parse_options(). */ -static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th, - struct tcp_sock *tp, u8 **hvpp) +static int tcp_fast_parse_options(const struct sk_buff *skb, + const struct tcphdr *th, + struct tcp_sock *tp, const u8 **hvpp) { /* In the spirit of fast parsing, compare doff directly to constant * values. Because equality is used, short doff can be ignored here. @@ -3913,10 +3971,10 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th, /* * Parse MD5 Signature option */ -u8 *tcp_parse_md5sig_option(struct tcphdr *th) +const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) { - int length = (th->doff << 2) - sizeof (*th); - u8 *ptr = (u8*)(th + 1); + int length = (th->doff << 2) - sizeof(*th); + const u8 *ptr = (const u8 *)(th + 1); /* If the TCP option is too short, we can short cut */ if (length < TCPOLEN_MD5SIG) @@ -3993,8 +4051,8 @@ static inline void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) { - struct tcp_sock *tp = tcp_sk(sk); - struct tcphdr *th = tcp_hdr(skb); + const struct tcp_sock *tp = tcp_sk(sk); + const struct tcphdr *th = tcp_hdr(skb); u32 seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; @@ -4033,7 +4091,7 @@ static inline int tcp_paws_discard(const struct sock *sk, * (borrowed from freebsd) */ -static inline int tcp_sequence(struct tcp_sock *tp, u32 seq, u32 end_seq) +static inline int tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq) { return !before(end_seq, tp->rcv_wup) && !after(seq, tp->rcv_nxt + tcp_receive_window(tp)); @@ -4078,7 +4136,7 @@ static void tcp_reset(struct sock *sk) * * If we are in FINWAIT-2, a received FIN moves us to TIME-WAIT. */ -static void tcp_fin(struct sk_buff *skb, struct sock *sk, struct tcphdr *th) +static void tcp_fin(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -4190,7 +4248,7 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq) tcp_sack_extend(tp->duplicate_sack, seq, end_seq); } -static void tcp_send_dupack(struct sock *sk, struct sk_buff *skb) +static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); @@ -4349,7 +4407,7 @@ static void tcp_ofo_queue(struct sock *sk) __skb_queue_tail(&sk->sk_receive_queue, skb); tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; if (tcp_hdr(skb)->fin) - tcp_fin(skb, sk, tcp_hdr(skb)); + tcp_fin(sk); } } @@ -4377,7 +4435,7 @@ static inline int tcp_try_rmem_schedule(struct sock *sk, unsigned int size) static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) { - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); struct tcp_sock *tp = tcp_sk(sk); int eaten = -1; @@ -4431,7 +4489,7 @@ queue_and_out: if (skb->len) tcp_event_data_recv(sk, skb); if (th->fin) - tcp_fin(skb, sk, th); + tcp_fin(sk); if (!skb_queue_empty(&tp->out_of_order_queue)) { tcp_ofo_queue(sk); @@ -4861,9 +4919,9 @@ void tcp_cwnd_application_limited(struct sock *sk) tp->snd_cwnd_stamp = tcp_time_stamp; } -static int tcp_should_expand_sndbuf(struct sock *sk) +static int tcp_should_expand_sndbuf(const struct sock *sk) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); /* If the user specified a specific send buffer setting, do * not modify it. @@ -4897,8 +4955,10 @@ static void tcp_new_space(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); if (tcp_should_expand_sndbuf(sk)) { - int sndmem = max_t(u32, tp->rx_opt.mss_clamp, tp->mss_cache) + - MAX_TCP_HEADER + 16 + sizeof(struct sk_buff); + int sndmem = SKB_TRUESIZE(max_t(u32, + tp->rx_opt.mss_clamp, + tp->mss_cache) + + MAX_TCP_HEADER); int demanded = max_t(unsigned int, tp->snd_cwnd, tp->reordering + 1); sndmem *= 2 * demanded; @@ -4970,7 +5030,7 @@ static inline void tcp_ack_snd_check(struct sock *sk) * either form (or just set the sysctl tcp_stdurg). */ -static void tcp_check_urg(struct sock *sk, struct tcphdr *th) +static void tcp_check_urg(struct sock *sk, const struct tcphdr *th) { struct tcp_sock *tp = tcp_sk(sk); u32 ptr = ntohs(th->urg_ptr); @@ -5036,7 +5096,7 @@ static void tcp_check_urg(struct sock *sk, struct tcphdr *th) } /* This is the 'fast' part of urgent handling. */ -static void tcp_urg(struct sock *sk, struct sk_buff *skb, struct tcphdr *th) +static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th) { struct tcp_sock *tp = tcp_sk(sk); @@ -5157,9 +5217,9 @@ out: * play significant role here. */ static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, - struct tcphdr *th, int syn_inerr) + const struct tcphdr *th, int syn_inerr) { - u8 *hash_location; + const u8 *hash_location; struct tcp_sock *tp = tcp_sk(sk); /* RFC1323: H1. Apply PAWS check first. */ @@ -5240,7 +5300,7 @@ discard: * tcp_data_queue when everything is OK. */ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, - struct tcphdr *th, unsigned len) + const struct tcphdr *th, unsigned int len) { struct tcp_sock *tp = tcp_sk(sk); int res; @@ -5451,9 +5511,9 @@ discard: EXPORT_SYMBOL(tcp_rcv_established); static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, - struct tcphdr *th, unsigned len) + const struct tcphdr *th, unsigned int len) { - u8 *hash_location; + const u8 *hash_location; struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcp_cookie_values *cvp = tp->cookie_values; @@ -5728,7 +5788,7 @@ reset_and_undo: */ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, - struct tcphdr *th, unsigned len) + const struct tcphdr *th, unsigned int len) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c34f015..a744315 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -92,7 +92,7 @@ EXPORT_SYMBOL(sysctl_tcp_low_latency); static struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr); static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key, - __be32 daddr, __be32 saddr, struct tcphdr *th); + __be32 daddr, __be32 saddr, const struct tcphdr *th); #else static inline struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr) @@ -104,7 +104,7 @@ struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr) struct inet_hashinfo tcp_hashinfo; EXPORT_SYMBOL(tcp_hashinfo); -static inline __u32 tcp_v4_init_sequence(struct sk_buff *skb) +static inline __u32 tcp_v4_init_sequence(const struct sk_buff *skb) { return secure_tcp_sequence_number(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, @@ -552,7 +552,7 @@ static void __tcp_v4_send_check(struct sk_buff *skb, /* This routine computes an IPv4 TCP checksum. */ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) { - struct inet_sock *inet = inet_sk(sk); + const struct inet_sock *inet = inet_sk(sk); __tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr); } @@ -590,7 +590,7 @@ int tcp_v4_gso_send_check(struct sk_buff *skb) static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) { - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); struct { struct tcphdr th; #ifdef CONFIG_TCP_MD5SIG @@ -652,6 +652,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0; net = dev_net(skb_dst(skb)->dev); + arg.tos = ip_hdr(skb)->tos; ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr, &arg, arg.iov[0].iov_len); @@ -666,9 +667,9 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts, int oif, struct tcp_md5sig_key *key, - int reply_flags) + int reply_flags, u8 tos) { - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); struct { struct tcphdr th; __be32 opt[(TCPOLEN_TSTAMP_ALIGNED >> 2) @@ -726,7 +727,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, arg.csumoffset = offsetof(struct tcphdr, check) / 2; if (oif) arg.bound_dev_if = oif; - + arg.tos = tos; ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr, &arg, arg.iov[0].iov_len); @@ -743,7 +744,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), - tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0 + tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0, + tw->tw_tos ); inet_twsk_put(tw); @@ -757,7 +759,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, req->ts_recent, 0, tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr), - inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0); + inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, + ip_hdr(skb)->tos); } /* @@ -927,18 +930,21 @@ int tcp_v4_md5_do_add(struct sock *sk, __be32 addr, } sk_nocaps_add(sk, NETIF_F_GSO_MASK); } - if (tcp_alloc_md5sig_pool(sk) == NULL) { + + md5sig = tp->md5sig_info; + if (md5sig->entries4 == 0 && + tcp_alloc_md5sig_pool(sk) == NULL) { kfree(newkey); return -ENOMEM; } - md5sig = tp->md5sig_info; if (md5sig->alloced4 == md5sig->entries4) { keys = kmalloc((sizeof(*keys) * (md5sig->entries4 + 1)), GFP_ATOMIC); if (!keys) { kfree(newkey); - tcp_free_md5sig_pool(); + if (md5sig->entries4 == 0) + tcp_free_md5sig_pool(); return -ENOMEM; } @@ -982,6 +988,7 @@ int tcp_v4_md5_do_del(struct sock *sk, __be32 addr) kfree(tp->md5sig_info->keys4); tp->md5sig_info->keys4 = NULL; tp->md5sig_info->alloced4 = 0; + tcp_free_md5sig_pool(); } else if (tp->md5sig_info->entries4 != i) { /* Need to do some manipulation */ memmove(&tp->md5sig_info->keys4[i], @@ -989,7 +996,6 @@ int tcp_v4_md5_do_del(struct sock *sk, __be32 addr) (tp->md5sig_info->entries4 - i) * sizeof(struct tcp4_md5sig_key)); } - tcp_free_md5sig_pool(); return 0; } } @@ -1087,7 +1093,7 @@ static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, } static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key, - __be32 daddr, __be32 saddr, struct tcphdr *th) + __be32 daddr, __be32 saddr, const struct tcphdr *th) { struct tcp_md5sig_pool *hp; struct hash_desc *desc; @@ -1119,12 +1125,12 @@ clear_hash_noput: } int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, - struct sock *sk, struct request_sock *req, - struct sk_buff *skb) + const struct sock *sk, const struct request_sock *req, + const struct sk_buff *skb) { struct tcp_md5sig_pool *hp; struct hash_desc *desc; - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); __be32 saddr, daddr; if (sk) { @@ -1169,7 +1175,7 @@ clear_hash_noput: } EXPORT_SYMBOL(tcp_v4_md5_hash_skb); -static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb) +static int tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) { /* * This gets called for each TCP segment that arrives @@ -1179,10 +1185,10 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb) * o MD5 hash and we're not expecting one. * o MD5 hash and its wrong. */ - __u8 *hash_location = NULL; + const __u8 *hash_location = NULL; struct tcp_md5sig_key *hash_expected; const struct iphdr *iph = ip_hdr(skb); - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); int genhash; unsigned char newhash[16]; @@ -1245,7 +1251,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { struct tcp_extend_values tmp_ext; struct tcp_options_received tmp_opt; - u8 *hash_location; + const u8 *hash_location; struct request_sock *req; struct inet_request_sock *ireq; struct tcp_sock *tp = tcp_sk(sk); @@ -1504,6 +1510,7 @@ exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: + bh_unlock_sock(newsk); sock_put(newsk); goto exit; } @@ -1585,7 +1592,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) #endif if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - sock_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb); if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) { rsk = sk; goto reset; @@ -1602,7 +1609,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) goto discard; if (nsk != sk) { - sock_rps_save_rxhash(nsk, skb->rxhash); + sock_rps_save_rxhash(nsk, skb); if (tcp_child_process(sk, nsk, skb)) { rsk = nsk; goto reset; @@ -1610,7 +1617,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; } } else - sock_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb); if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) { rsk = sk; @@ -1642,7 +1649,7 @@ EXPORT_SYMBOL(tcp_v4_do_rcv); int tcp_v4_rcv(struct sk_buff *skb) { const struct iphdr *iph; - struct tcphdr *th; + const struct tcphdr *th; struct sock *sk; int ret; struct net *net = dev_net(skb->dev); @@ -1677,7 +1684,7 @@ int tcp_v4_rcv(struct sk_buff *skb) skb->len - th->doff * 4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->when = 0; - TCP_SKB_CB(skb)->flags = iph->tos; + TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); TCP_SKB_CB(skb)->sacked = 0; sk = __inet_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest); @@ -1806,7 +1813,7 @@ EXPORT_SYMBOL(tcp_v4_get_peer); void *tcp_v4_tw_get_peer(struct sock *sk) { - struct inet_timewait_sock *tw = inet_twsk(sk); + const struct inet_timewait_sock *tw = inet_twsk(sk); return inet_getpeer_v4(tw->tw_daddr, 1); } @@ -2333,7 +2340,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v) } } -static int tcp_seq_open(struct inode *inode, struct file *file) +int tcp_seq_open(struct inode *inode, struct file *file) { struct tcp_seq_afinfo *afinfo = PDE(inode)->data; struct tcp_iter_state *s; @@ -2349,23 +2356,19 @@ static int tcp_seq_open(struct inode *inode, struct file *file) s->last_pos = 0; return 0; } +EXPORT_SYMBOL(tcp_seq_open); int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo) { int rc = 0; struct proc_dir_entry *p; - afinfo->seq_fops.open = tcp_seq_open; - afinfo->seq_fops.read = seq_read; - afinfo->seq_fops.llseek = seq_lseek; - afinfo->seq_fops.release = seq_release_net; - afinfo->seq_ops.start = tcp_seq_start; afinfo->seq_ops.next = tcp_seq_next; afinfo->seq_ops.stop = tcp_seq_stop; p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net, - &afinfo->seq_fops, afinfo); + afinfo->seq_fops, afinfo); if (!p) rc = -ENOMEM; return rc; @@ -2378,7 +2381,7 @@ void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo) } EXPORT_SYMBOL(tcp_proc_unregister); -static void get_openreq4(struct sock *sk, struct request_sock *req, +static void get_openreq4(const struct sock *sk, const struct request_sock *req, struct seq_file *f, int i, int uid, int *len) { const struct inet_request_sock *ireq = inet_rsk(req); @@ -2408,9 +2411,9 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) { int timer_active; unsigned long timer_expires; - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - struct inet_sock *inet = inet_sk(sk); + const struct inet_sock *inet = inet_sk(sk); __be32 dest = inet->inet_daddr; __be32 src = inet->inet_rcv_saddr; __u16 destp = ntohs(inet->inet_dport); @@ -2459,7 +2462,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) len); } -static void get_timewait4_sock(struct inet_timewait_sock *tw, +static void get_timewait4_sock(const struct inet_timewait_sock *tw, struct seq_file *f, int i, int *len) { __be32 dest, src; @@ -2514,12 +2517,18 @@ out: return 0; } +static const struct file_operations tcp_afinfo_seq_fops = { + .owner = THIS_MODULE, + .open = tcp_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net +}; + static struct tcp_seq_afinfo tcp4_seq_afinfo = { .name = "tcp", .family = AF_INET, - .seq_fops = { - .owner = THIS_MODULE, - }, + .seq_fops = &tcp_afinfo_seq_fops, .seq_ops = { .show = tcp4_seq_show, }, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index d2fe4e0..66363b6 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -141,7 +141,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th) { struct tcp_options_received tmp_opt; - u8 *hash_location; + const u8 *hash_location; struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); int paws_reject = 0; @@ -328,6 +328,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); + tw->tw_transparent = inet_sk(sk)->transparent; tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; tcptw->tw_rcv_nxt = tp->rcv_nxt; tcptw->tw_snd_nxt = tp->snd_nxt; @@ -344,6 +345,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tw6 = inet6_twsk((struct sock *)tw); ipv6_addr_copy(&tw6->tw_v6_daddr, &np->daddr); ipv6_addr_copy(&tw6->tw_v6_rcv_saddr, &np->rcv_saddr); + tw->tw_tclass = np->tclass; tw->tw_ipv6only = np->ipv6only; } #endif @@ -566,7 +568,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock **prev) { struct tcp_options_received tmp_opt; - u8 *hash_location; + const u8 *hash_location; struct sock *child; const struct tcphdr *th = tcp_hdr(skb); __be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 882e0b0..980b98f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -65,7 +65,7 @@ EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size); /* Account for new data that has been sent to the network. */ -static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) +static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; @@ -89,9 +89,9 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) * Anything in between SND.UNA...SND.UNA+SND.WND also can be already * invalid. OK, let's make this for now: */ -static inline __u32 tcp_acceptable_seq(struct sock *sk) +static inline __u32 tcp_acceptable_seq(const struct sock *sk) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); if (!before(tcp_wnd_end(tp), tp->snd_nxt)) return tp->snd_nxt; @@ -116,7 +116,7 @@ static inline __u32 tcp_acceptable_seq(struct sock *sk) static __u16 tcp_advertise_mss(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = __sk_dst_get(sk); + const struct dst_entry *dst = __sk_dst_get(sk); int mss = tp->advmss; if (dst) { @@ -133,7 +133,7 @@ static __u16 tcp_advertise_mss(struct sock *sk) /* RFC2861. Reset CWND after idle period longer RTO to "restart window". * This is the first part of cwnd validation mechanism. */ -static void tcp_cwnd_restart(struct sock *sk, struct dst_entry *dst) +static void tcp_cwnd_restart(struct sock *sk, const struct dst_entry *dst) { struct tcp_sock *tp = tcp_sk(sk); s32 delta = tcp_time_stamp - tp->lsndtime; @@ -154,7 +154,7 @@ static void tcp_cwnd_restart(struct sock *sk, struct dst_entry *dst) /* Congestion state accounting after a packet has been sent. */ static void tcp_event_data_sent(struct tcp_sock *tp, - struct sk_buff *skb, struct sock *sk) + struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); const u32 now = tcp_time_stamp; @@ -295,11 +295,11 @@ static u16 tcp_select_window(struct sock *sk) } /* Packet ECN state for a SYN-ACK */ -static inline void TCP_ECN_send_synack(struct tcp_sock *tp, struct sk_buff *skb) +static inline void TCP_ECN_send_synack(const struct tcp_sock *tp, struct sk_buff *skb) { - TCP_SKB_CB(skb)->flags &= ~TCPHDR_CWR; + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR; if (!(tp->ecn_flags & TCP_ECN_OK)) - TCP_SKB_CB(skb)->flags &= ~TCPHDR_ECE; + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; } /* Packet ECN state for a SYN. */ @@ -309,13 +309,13 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb) tp->ecn_flags = 0; if (sysctl_tcp_ecn == 1) { - TCP_SKB_CB(skb)->flags |= TCPHDR_ECE | TCPHDR_CWR; + TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; tp->ecn_flags = TCP_ECN_OK; } } static __inline__ void -TCP_ECN_make_synack(struct request_sock *req, struct tcphdr *th) +TCP_ECN_make_synack(const struct request_sock *req, struct tcphdr *th) { if (inet_rsk(req)->ecn_ok) th->ece = 1; @@ -356,7 +356,7 @@ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - TCP_SKB_CB(skb)->flags = flags; + TCP_SKB_CB(skb)->tcp_flags = flags; TCP_SKB_CB(skb)->sacked = 0; skb_shinfo(skb)->gso_segs = 1; @@ -565,7 +565,8 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, */ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, - struct tcp_md5sig_key **md5) { + struct tcp_md5sig_key **md5) +{ struct tcp_sock *tp = tcp_sk(sk); struct tcp_cookie_values *cvp = tp->cookie_values; unsigned remaining = MAX_TCP_OPTION_SPACE; @@ -743,7 +744,8 @@ static unsigned tcp_synack_options(struct sock *sk, */ static unsigned tcp_established_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, - struct tcp_md5sig_key **md5) { + struct tcp_md5sig_key **md5) +{ struct tcp_skb_cb *tcb = skb ? TCP_SKB_CB(skb) : NULL; struct tcp_sock *tp = tcp_sk(sk); unsigned size = 0; @@ -826,7 +828,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, tcb = TCP_SKB_CB(skb); memset(&opts, 0, sizeof(opts)); - if (unlikely(tcb->flags & TCPHDR_SYN)) + if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) tcp_options_size = tcp_syn_options(sk, skb, &opts, &md5); else tcp_options_size = tcp_established_options(sk, skb, &opts, @@ -850,9 +852,9 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, th->seq = htonl(tcb->seq); th->ack_seq = htonl(tp->rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | - tcb->flags); + tcb->tcp_flags); - if (unlikely(tcb->flags & TCPHDR_SYN)) { + if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) { /* RFC1323: The window in SYN & SYN/ACK segments * is never scaled. */ @@ -875,7 +877,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, } tcp_options_write((__be32 *)(th + 1), tp, &opts); - if (likely((tcb->flags & TCPHDR_SYN) == 0)) + if (likely((tcb->tcp_flags & TCPHDR_SYN) == 0)) TCP_ECN_send(sk, skb, tcp_header_size); #ifdef CONFIG_TCP_MD5SIG @@ -889,11 +891,11 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, icsk->icsk_af_ops->send_check(sk, skb); - if (likely(tcb->flags & TCPHDR_ACK)) + if (likely(tcb->tcp_flags & TCPHDR_ACK)) tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); if (skb->len != tcp_header_size) - tcp_event_data_sent(tp, skb, sk); + tcp_event_data_sent(tp, sk); if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, @@ -926,7 +928,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) } /* Initialize TSO segments for a packet. */ -static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, +static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { if (skb->len <= mss_now || !sk_can_gso(sk) || @@ -947,7 +949,7 @@ static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, /* When a modification to fackets out becomes necessary, we need to check * skb is counted to fackets_out or not. */ -static void tcp_adjust_fackets_out(struct sock *sk, struct sk_buff *skb, +static void tcp_adjust_fackets_out(struct sock *sk, const struct sk_buff *skb, int decr) { struct tcp_sock *tp = tcp_sk(sk); @@ -962,7 +964,7 @@ static void tcp_adjust_fackets_out(struct sock *sk, struct sk_buff *skb, /* Pcount in the middle of the write queue got changed, we need to do various * tweaks to fix counters */ -static void tcp_adjust_pcount(struct sock *sk, struct sk_buff *skb, int decr) +static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int decr) { struct tcp_sock *tp = tcp_sk(sk); @@ -1032,9 +1034,9 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq; /* PSH and FIN should only be set in the second packet. */ - flags = TCP_SKB_CB(skb)->flags; - TCP_SKB_CB(skb)->flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); - TCP_SKB_CB(buff)->flags = flags; + flags = TCP_SKB_CB(skb)->tcp_flags; + TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); + TCP_SKB_CB(buff)->tcp_flags = flags; TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked; if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) { @@ -1094,14 +1096,16 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) eat = len; k = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - if (skb_shinfo(skb)->frags[i].size <= eat) { - put_page(skb_shinfo(skb)->frags[i].page); - eat -= skb_shinfo(skb)->frags[i].size; + int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); + + if (size <= eat) { + skb_frag_unref(skb, i); + eat -= size; } else { skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i]; if (eat) { skb_shinfo(skb)->frags[k].page_offset += eat; - skb_shinfo(skb)->frags[k].size -= eat; + skb_frag_size_sub(&skb_shinfo(skb)->frags[k], eat); eat = 0; } k++; @@ -1144,10 +1148,10 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) } /* Calculate MSS. Not accounting for SACKs here. */ -int tcp_mtu_to_mss(struct sock *sk, int pmtu) +int tcp_mtu_to_mss(const struct sock *sk, int pmtu) { - struct tcp_sock *tp = tcp_sk(sk); - struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcp_sock *tp = tcp_sk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); int mss_now; /* Calculate base mss without TCP options: @@ -1173,10 +1177,10 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu) } /* Inverse of above */ -int tcp_mss_to_mtu(struct sock *sk, int mss) +int tcp_mss_to_mtu(const struct sock *sk, int mss) { - struct tcp_sock *tp = tcp_sk(sk); - struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcp_sock *tp = tcp_sk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); int mtu; mtu = mss + @@ -1250,8 +1254,8 @@ EXPORT_SYMBOL(tcp_sync_mss); */ unsigned int tcp_current_mss(struct sock *sk) { - struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = __sk_dst_get(sk); + const struct tcp_sock *tp = tcp_sk(sk); + const struct dst_entry *dst = __sk_dst_get(sk); u32 mss_now; unsigned header_len; struct tcp_out_options opts; @@ -1311,10 +1315,10 @@ static void tcp_cwnd_validate(struct sock *sk) * modulo only when the receiver window alone is the limiting factor or * when we would be allowed to send the split-due-to-Nagle skb fully. */ -static unsigned int tcp_mss_split_point(struct sock *sk, struct sk_buff *skb, +static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb, unsigned int mss_now, unsigned int cwnd) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); u32 needed, window, cwnd_len; window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; @@ -1334,13 +1338,14 @@ static unsigned int tcp_mss_split_point(struct sock *sk, struct sk_buff *skb, /* Can at least one segment of SKB be sent right now, according to the * congestion window rules? If so, return how many segments are allowed. */ -static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp, - struct sk_buff *skb) +static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp, + const struct sk_buff *skb) { u32 in_flight, cwnd; /* Don't be strict about the congestion window for the final FIN. */ - if ((TCP_SKB_CB(skb)->flags & TCPHDR_FIN) && tcp_skb_pcount(skb) == 1) + if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) && + tcp_skb_pcount(skb) == 1) return 1; in_flight = tcp_packets_in_flight(tp); @@ -1355,7 +1360,7 @@ static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp, * This must be invoked the first time we consider transmitting * SKB onto the wire. */ -static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, +static int tcp_init_tso_segs(const struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { int tso_segs = tcp_skb_pcount(skb); @@ -1393,7 +1398,7 @@ static inline int tcp_nagle_check(const struct tcp_sock *tp, /* Return non-zero if the Nagle test allows this packet to be * sent now. */ -static inline int tcp_nagle_test(struct tcp_sock *tp, struct sk_buff *skb, +static inline int tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb, unsigned int cur_mss, int nonagle) { /* Nagle rule does not apply to frames, which sit in the middle of the @@ -1409,7 +1414,7 @@ static inline int tcp_nagle_test(struct tcp_sock *tp, struct sk_buff *skb, * Nagle can be ignored during F-RTO too (see RFC4138). */ if (tcp_urg_mode(tp) || (tp->frto_counter == 2) || - (TCP_SKB_CB(skb)->flags & TCPHDR_FIN)) + (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) return 1; if (!tcp_nagle_check(tp, skb, cur_mss, nonagle)) @@ -1419,7 +1424,7 @@ static inline int tcp_nagle_test(struct tcp_sock *tp, struct sk_buff *skb, } /* Does at least the first segment of SKB fit into the send window? */ -static inline int tcp_snd_wnd_test(struct tcp_sock *tp, struct sk_buff *skb, +static inline int tcp_snd_wnd_test(const struct tcp_sock *tp, const struct sk_buff *skb, unsigned int cur_mss) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; @@ -1434,10 +1439,10 @@ static inline int tcp_snd_wnd_test(struct tcp_sock *tp, struct sk_buff *skb, * should be put on the wire right now. If so, it returns the number of * packets allowed by the congestion window. */ -static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb, +static unsigned int tcp_snd_test(const struct sock *sk, struct sk_buff *skb, unsigned int cur_mss, int nonagle) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); unsigned int cwnd_quota; tcp_init_tso_segs(sk, skb, cur_mss); @@ -1455,7 +1460,7 @@ static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb, /* Test if sending is allowed right now. */ int tcp_may_send_now(struct sock *sk) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb = tcp_send_head(sk); return skb && @@ -1497,9 +1502,9 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq; /* PSH and FIN should only be set in the second packet. */ - flags = TCP_SKB_CB(skb)->flags; - TCP_SKB_CB(skb)->flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); - TCP_SKB_CB(buff)->flags = flags; + flags = TCP_SKB_CB(skb)->tcp_flags; + TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); + TCP_SKB_CB(buff)->tcp_flags = flags; /* This packet was never sent out yet, so no SACK bits. */ TCP_SKB_CB(buff)->sacked = 0; @@ -1530,7 +1535,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) u32 send_win, cong_win, limit, in_flight; int win_divisor; - if (TCP_SKB_CB(skb)->flags & TCPHDR_FIN) + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto send_now; if (icsk->icsk_ca_state != TCP_CA_Open) @@ -1657,7 +1662,7 @@ static int tcp_mtu_probe(struct sock *sk) TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq; TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size; - TCP_SKB_CB(nskb)->flags = TCPHDR_ACK; + TCP_SKB_CB(nskb)->tcp_flags = TCPHDR_ACK; TCP_SKB_CB(nskb)->sacked = 0; nskb->csum = 0; nskb->ip_summed = skb->ip_summed; @@ -1677,11 +1682,11 @@ static int tcp_mtu_probe(struct sock *sk) if (skb->len <= copy) { /* We've eaten all the data from this skb. * Throw it away. */ - TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags; + TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); } else { - TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags & + TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags & ~(TCPHDR_FIN|TCPHDR_PSH); if (!skb_shinfo(skb)->nr_frags) { skb_pull(skb, copy); @@ -1796,11 +1801,13 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, tcp_event_new_data_sent(sk, skb); tcp_minshall_update(tp, mss_now, skb); - sent_pkts++; + sent_pkts += tcp_skb_pcount(skb); if (push_one) break; } + if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery) + tp->prr_out += sent_pkts; if (likely(sent_pkts)) { tcp_cwnd_validate(sk); @@ -1985,7 +1992,7 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq; /* Merge over control information. This moves PSH/FIN etc. over */ - TCP_SKB_CB(skb)->flags |= TCP_SKB_CB(next_skb)->flags; + TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(next_skb)->tcp_flags; /* All done, get rid of second SKB and account for it so * packet counting does not break. @@ -2003,7 +2010,7 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) } /* Check if coalescing SKBs is legal. */ -static int tcp_can_collapse(struct sock *sk, struct sk_buff *skb) +static int tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) { if (tcp_skb_pcount(skb) > 1) return 0; @@ -2033,7 +2040,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, if (!sysctl_tcp_retrans_collapse) return; - if (TCP_SKB_CB(skb)->flags & TCPHDR_SYN) + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) return; tcp_for_write_queue_from_safe(skb, tmp, sk) { @@ -2125,12 +2132,12 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) * since it is cheap to do so and saves bytes on the network. */ if (skb->len > 0 && - (TCP_SKB_CB(skb)->flags & TCPHDR_FIN) && + (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) && tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) { if (!pskb_trim(skb, 0)) { /* Reuse, even though it does some unnecessary work */ tcp_init_nondata_skb(skb, TCP_SKB_CB(skb)->end_seq - 1, - TCP_SKB_CB(skb)->flags); + TCP_SKB_CB(skb)->tcp_flags); skb->ip_summed = CHECKSUM_NONE; } } @@ -2179,7 +2186,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) static int tcp_can_forward_retransmit(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); /* Forward retransmissions are possible only during Recovery. */ if (icsk->icsk_ca_state != TCP_CA_Recovery) @@ -2294,6 +2301,9 @@ begin_fwd: return; NET_INC_STATS_BH(sock_net(sk), mib_idx); + if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery) + tp->prr_out += tcp_skb_pcount(skb); + if (skb == tcp_write_queue_head(sk)) inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, @@ -2317,7 +2327,7 @@ void tcp_send_fin(struct sock *sk) mss_now = tcp_current_mss(sk); if (tcp_send_head(sk) != NULL) { - TCP_SKB_CB(skb)->flags |= TCPHDR_FIN; + TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(skb)->end_seq++; tp->write_seq++; } else { @@ -2379,11 +2389,11 @@ int tcp_send_synack(struct sock *sk) struct sk_buff *skb; skb = tcp_write_queue_head(sk); - if (skb == NULL || !(TCP_SKB_CB(skb)->flags & TCPHDR_SYN)) { + if (skb == NULL || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { printk(KERN_DEBUG "tcp_send_synack: wrong queue state\n"); return -EFAULT; } - if (!(TCP_SKB_CB(skb)->flags & TCPHDR_ACK)) { + if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC); if (nskb == NULL) @@ -2397,7 +2407,7 @@ int tcp_send_synack(struct sock *sk) skb = nskb; } - TCP_SKB_CB(skb)->flags |= TCPHDR_ACK; + TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ACK; TCP_ECN_send_synack(tcp_sk(sk), skb); } TCP_SKB_CB(skb)->when = tcp_time_stamp; @@ -2542,7 +2552,7 @@ EXPORT_SYMBOL(tcp_make_synack); /* Do all connect socket setups that can be done AF independent. */ static void tcp_connect_init(struct sock *sk) { - struct dst_entry *dst = __sk_dst_get(sk); + const struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); __u8 rcv_wscale; @@ -2794,13 +2804,13 @@ int tcp_write_wakeup(struct sock *sk) if (seg_size < TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq || skb->len > mss) { seg_size = min(seg_size, mss); - TCP_SKB_CB(skb)->flags |= TCPHDR_PSH; + TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; if (tcp_fragment(sk, skb, seg_size, mss)) return -1; } else if (!tcp_skb_pcount(skb)) tcp_set_skb_tso_segs(sk, skb, mss); - TCP_SKB_CB(skb)->flags |= TCPHDR_PSH; + TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; TCP_SKB_CB(skb)->when = tcp_time_stamp; err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); if (!err) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index ecd44b0..2e0f0af 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -334,7 +334,6 @@ void tcp_retransmit_timer(struct sock *sk) * connection. If the socket is an orphan, time it out, * we cannot allow such beasts to hang infinitely. */ -#ifdef TCP_DEBUG struct inet_sock *inet = inet_sk(sk); if (sk->sk_family == AF_INET) { LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", @@ -349,7 +348,6 @@ void tcp_retransmit_timer(struct sock *sk) inet->inet_num, tp->snd_una, tp->snd_nxt); } #endif -#endif if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) { tcp_write_err(sk); goto out; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1b5a193..ab0966d 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1267,7 +1267,7 @@ int udp_disconnect(struct sock *sk, int flags) sk->sk_state = TCP_CLOSE; inet->inet_daddr = 0; inet->inet_dport = 0; - sock_rps_save_rxhash(sk, 0); + sock_rps_reset_rxhash(sk); sk->sk_bound_dev_if = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); @@ -1355,7 +1355,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) int rc; if (inet_sk(sk)->inet_daddr) - sock_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb); rc = ip_queue_rcv_skb(sk, skb); if (rc < 0) { @@ -1397,6 +1397,8 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) nf_reset(skb); if (up->encap_type) { + int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); + /* * This is an encapsulation socket so pass the skb to * the socket's udp_encap_rcv() hook. Otherwise, just @@ -1409,11 +1411,11 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ /* if we're overly short, let UDP handle it */ - if (skb->len > sizeof(struct udphdr) && - up->encap_rcv != NULL) { + encap_rcv = ACCESS_ONCE(up->encap_rcv); + if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) { int ret; - ret = (*up->encap_rcv)(sk, skb); + ret = encap_rcv(sk, skb); if (ret <= 0) { UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INDATAGRAMS, @@ -1461,10 +1463,9 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } } - if (rcu_dereference_raw(sk->sk_filter)) { - if (udp_lib_checksum_complete(skb)) - goto drop; - } + if (rcu_access_pointer(sk->sk_filter) && + udp_lib_checksum_complete(skb)) + goto drop; if (sk_rcvqueues_full(sk, skb)) @@ -2038,7 +2039,7 @@ static void udp_seq_stop(struct seq_file *seq, void *v) spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); } -static int udp_seq_open(struct inode *inode, struct file *file) +int udp_seq_open(struct inode *inode, struct file *file) { struct udp_seq_afinfo *afinfo = PDE(inode)->data; struct udp_iter_state *s; @@ -2054,6 +2055,7 @@ static int udp_seq_open(struct inode *inode, struct file *file) s->udp_table = afinfo->udp_table; return err; } +EXPORT_SYMBOL(udp_seq_open); /* ------------------------------------------------------------------------ */ int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo) @@ -2061,17 +2063,12 @@ int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo) struct proc_dir_entry *p; int rc = 0; - afinfo->seq_fops.open = udp_seq_open; - afinfo->seq_fops.read = seq_read; - afinfo->seq_fops.llseek = seq_lseek; - afinfo->seq_fops.release = seq_release_net; - afinfo->seq_ops.start = udp_seq_start; afinfo->seq_ops.next = udp_seq_next; afinfo->seq_ops.stop = udp_seq_stop; p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net, - &afinfo->seq_fops, afinfo); + afinfo->seq_fops, afinfo); if (!p) rc = -ENOMEM; return rc; @@ -2121,14 +2118,20 @@ int udp4_seq_show(struct seq_file *seq, void *v) return 0; } +static const struct file_operations udp_afinfo_seq_fops = { + .owner = THIS_MODULE, + .open = udp_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net +}; + /* ------------------------------------------------------------------------ */ static struct udp_seq_afinfo udp4_seq_afinfo = { .name = "udp", .family = AF_INET, .udp_table = &udp_table, - .seq_fops = { - .owner = THIS_MODULE, - }, + .seq_fops = &udp_afinfo_seq_fops, .seq_ops = { .show = udp4_seq_show, }, diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index aee9963..08383eb 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -71,13 +71,20 @@ static struct inet_protosw udplite4_protosw = { }; #ifdef CONFIG_PROC_FS + +static const struct file_operations udplite_afinfo_seq_fops = { + .owner = THIS_MODULE, + .open = udp_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net +}; + static struct udp_seq_afinfo udplite4_seq_afinfo = { .name = "udplite", .family = AF_INET, .udp_table = &udplite_table, - .seq_fops = { - .owner = THIS_MODULE, - }, + .seq_fops = &udplite_afinfo_seq_fops, .seq_ops = { .show = udp4_seq_show, }, diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index fc5368a..a0b4c5d 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -79,13 +79,13 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, struct rtable *rt = (struct rtable *)xdst->route; const struct flowi4 *fl4 = &fl->u.ip4; - rt->rt_key_dst = fl4->daddr; - rt->rt_key_src = fl4->saddr; - rt->rt_key_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; + xdst->u.rt.rt_key_dst = fl4->daddr; + xdst->u.rt.rt_key_src = fl4->saddr; + xdst->u.rt.rt_key_tos = fl4->flowi4_tos; + xdst->u.rt.rt_route_iif = fl4->flowi4_iif; + xdst->u.rt.rt_iif = fl4->flowi4_iif; + xdst->u.rt.rt_oif = fl4->flowi4_oif; + xdst->u.rt.rt_mark = fl4->flowi4_mark; xdst->u.dst.dev = dev; dev_hold(dev); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 12368c5..d0611a5 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -428,7 +428,7 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) ndev->tstamp = jiffies; addrconf_sysctl_register(ndev); /* protected by rtnl_lock */ - rcu_assign_pointer(dev->ip6_ptr, ndev); + RCU_INIT_POINTER(dev->ip6_ptr, ndev); /* Join all-node multicast group */ ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes); @@ -824,12 +824,13 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *i { struct inet6_dev *idev = ifp->idev; struct in6_addr addr, *tmpaddr; - unsigned long tmp_prefered_lft, tmp_valid_lft, tmp_cstamp, tmp_tstamp, age; + unsigned long tmp_prefered_lft, tmp_valid_lft, tmp_tstamp, age; unsigned long regen_advance; int tmp_plen; int ret = 0; int max_addresses; u32 addr_flags; + unsigned long now = jiffies; write_lock(&idev->lock); if (ift) { @@ -874,7 +875,7 @@ retry: goto out; } memcpy(&addr.s6_addr[8], idev->rndid, 8); - age = (jiffies - ifp->tstamp) / HZ; + age = (now - ifp->tstamp) / HZ; tmp_valid_lft = min_t(__u32, ifp->valid_lft, idev->cnf.temp_valid_lft + age); @@ -884,7 +885,6 @@ retry: idev->cnf.max_desync_factor); tmp_plen = ifp->prefix_len; max_addresses = idev->cnf.max_addresses; - tmp_cstamp = ifp->cstamp; tmp_tstamp = ifp->tstamp; spin_unlock_bh(&ifp->lock); @@ -929,7 +929,7 @@ retry: ift->ifpub = ifp; ift->valid_lft = tmp_valid_lft; ift->prefered_lft = tmp_prefered_lft; - ift->cstamp = tmp_cstamp; + ift->cstamp = now; ift->tstamp = tmp_tstamp; spin_unlock_bh(&ift->lock); @@ -1713,6 +1713,40 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, ip6_route_add(&cfg); } + +static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, + int plen, + const struct net_device *dev, + u32 flags, u32 noflags) +{ + struct fib6_node *fn; + struct rt6_info *rt = NULL; + struct fib6_table *table; + + table = fib6_get_table(dev_net(dev), RT6_TABLE_PREFIX); + if (table == NULL) + return NULL; + + write_lock_bh(&table->tb6_lock); + fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0); + if (!fn) + goto out; + for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + if (rt->rt6i_dev->ifindex != dev->ifindex) + continue; + if ((rt->rt6i_flags & flags) != flags) + continue; + if ((noflags != 0) && ((rt->rt6i_flags & flags) != 0)) + continue; + dst_hold(&rt->dst); + break; + } +out: + write_unlock_bh(&table->tb6_lock); + return rt; +} + + /* Create "default" multicast route to the interface */ static void addrconf_add_mroute(struct net_device *dev) @@ -1842,10 +1876,13 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) if (addrconf_finite_timeout(rt_expires)) rt_expires *= HZ; - rt = rt6_lookup(net, &pinfo->prefix, NULL, - dev->ifindex, 1); + rt = addrconf_get_prefix_route(&pinfo->prefix, + pinfo->prefix_len, + dev, + RTF_ADDRCONF | RTF_PREFIX_RT, + RTF_GATEWAY | RTF_DEFAULT); - if (rt && addrconf_is_prefix_route(rt)) { + if (rt) { /* Autoconf prefix route */ if (valid_lft == 0) { ip6_del_rt(rt); @@ -1999,25 +2036,50 @@ ok: #ifdef CONFIG_IPV6_PRIVACY read_lock_bh(&in6_dev->lock); /* update all temporary addresses in the list */ - list_for_each_entry(ift, &in6_dev->tempaddr_list, tmp_list) { - /* - * When adjusting the lifetimes of an existing - * temporary address, only lower the lifetimes. - * Implementations must not increase the - * lifetimes of an existing temporary address - * when processing a Prefix Information Option. - */ + list_for_each_entry(ift, &in6_dev->tempaddr_list, + tmp_list) { + int age, max_valid, max_prefered; + if (ifp != ift->ifpub) continue; + /* + * RFC 4941 section 3.3: + * If a received option will extend the lifetime + * of a public address, the lifetimes of + * temporary addresses should be extended, + * subject to the overall constraint that no + * temporary addresses should ever remain + * "valid" or "preferred" for a time longer than + * (TEMP_VALID_LIFETIME) or + * (TEMP_PREFERRED_LIFETIME - DESYNC_FACTOR), + * respectively. + */ + age = (now - ift->cstamp) / HZ; + max_valid = in6_dev->cnf.temp_valid_lft - age; + if (max_valid < 0) + max_valid = 0; + + max_prefered = in6_dev->cnf.temp_prefered_lft - + in6_dev->cnf.max_desync_factor - + age; + if (max_prefered < 0) + max_prefered = 0; + + if (valid_lft > max_valid) + valid_lft = max_valid; + + if (prefered_lft > max_prefered) + prefered_lft = max_prefered; + spin_lock(&ift->lock); flags = ift->flags; - if (ift->valid_lft > valid_lft && - ift->valid_lft - valid_lft > (jiffies - ift->tstamp) / HZ) - ift->valid_lft = valid_lft + (jiffies - ift->tstamp) / HZ; - if (ift->prefered_lft > prefered_lft && - ift->prefered_lft - prefered_lft > (jiffies - ift->tstamp) / HZ) - ift->prefered_lft = prefered_lft + (jiffies - ift->tstamp) / HZ; + ift->valid_lft = valid_lft; + ift->prefered_lft = prefered_lft; + ift->tstamp = now; + if (prefered_lft > 0) + ift->flags &= ~IFA_F_DEPRECATED; + spin_unlock(&ift->lock); if (!(flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ift); @@ -2025,9 +2087,11 @@ ok: if ((create || list_empty(&in6_dev->tempaddr_list)) && in6_dev->cnf.use_tempaddr > 0) { /* - * When a new public address is created as described in [ADDRCONF], - * also create a new temporary address. Also create a temporary - * address if it's enabled but no temporary address currently exists. + * When a new public address is created as + * described in [ADDRCONF], also create a new + * temporary address. Also create a temporary + * address if it's enabled but no temporary + * address currently exists. */ read_unlock_bh(&in6_dev->lock); ipv6_create_tempaddr(ifp, NULL); @@ -2706,7 +2770,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) idev->dead = 1; /* protected by rtnl_lock */ - rcu_assign_pointer(dev->ip6_ptr, NULL); + RCU_INIT_POINTER(dev->ip6_ptr, NULL); /* Step 1.5: remove snmp6 entry */ snmp6_unregister_dev(idev); @@ -2969,12 +3033,12 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) ipv6_ifa_notify(RTM_NEWADDR, ifp); - /* If added prefix is link local and forwarding is off, - start sending router solicitations. + /* If added prefix is link local and we are prepared to process + router advertisements, start sending router solicitations. */ - if ((ifp->idev->cnf.forwarding == 0 || - ifp->idev->cnf.forwarding == 2) && + if (((ifp->idev->cnf.accept_ra == 1 && !ifp->idev->cnf.forwarding) || + ifp->idev->cnf.accept_ra == 2) && ifp->idev->cnf.rtr_solicits > 0 && (dev->flags&IFF_LOOPBACK) == 0 && (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)) { diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 3b5669a..d27c797 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -875,6 +875,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, skb_reset_transport_header(skb); __skb_push(skb, skb_gro_offset(skb)); + ops = rcu_dereference(inet6_protos[proto]); if (!ops || !ops->gro_receive) goto out_unlock; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index b46e9f8..e248069 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -297,10 +297,6 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) ipv6_addr_copy(&iph->daddr, &fl6->daddr); mtu_info = IP6CBMTU(skb); - if (!mtu_info) { - kfree_skb(skb); - return; - } mtu_info->ip6m_mtu = mtu; mtu_info->ip6m_addr.sin6_family = AF_INET6; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 79a485e..1318de4 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -273,12 +273,12 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) __u16 dstbuf; #endif - struct dst_entry *dst; + struct dst_entry *dst = skb_dst(skb); if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { - IP6_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), + IP6_INC_STATS_BH(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; @@ -289,9 +289,7 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) dstbuf = opt->dst1; #endif - dst = dst_clone(skb_dst(skb)); if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) { - dst_release(dst); skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; opt = IP6CB(skb); #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) @@ -304,7 +302,6 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) IP6_INC_STATS_BH(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); - dst_release(dst); return -1; } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 1190041..90868fb 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -490,7 +490,8 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) goto out_dst_release; } - idev = in6_dev_get(skb->dev); + rcu_read_lock(); + idev = __in6_dev_get(skb->dev); err = ip6_append_data(sk, icmpv6_getfrag, &msg, len + sizeof(struct icmp6hdr), @@ -500,19 +501,16 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) if (err) { ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); - goto out_put; + } else { + err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, + len + sizeof(struct icmp6hdr)); } - err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, len + sizeof(struct icmp6hdr)); - -out_put: - if (likely(idev != NULL)) - in6_dev_put(idev); + rcu_read_unlock(); out_dst_release: dst_release(dst); out: icmpv6_xmit_unlock(sk); } - EXPORT_SYMBOL(icmpv6_send); static void icmpv6_echo_reply(struct sk_buff *skb) @@ -569,7 +567,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - idev = in6_dev_get(skb->dev); + idev = __in6_dev_get(skb->dev); msg.skb = skb; msg.offset = 0; @@ -583,13 +581,10 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (err) { ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); - goto out_put; + } else { + err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, + skb->len + sizeof(struct icmp6hdr)); } - err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, skb->len + sizeof(struct icmp6hdr)); - -out_put: - if (likely(idev != NULL)) - in6_dev_put(idev); dst_release(dst); out: icmpv6_xmit_unlock(sk); @@ -840,8 +835,7 @@ static int __net_init icmpv6_sk_init(struct net *net) /* Enough space for 2 64K ICMP packets, including * sk_buff struct overhead. */ - sk->sk_sndbuf = - (2 * ((64 * 1024) + sizeof(struct sk_buff))); + sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); } return 0; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 8a58e8c..fee46d5 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -211,6 +211,7 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) struct flowi6 fl6; struct dst_entry *dst; struct in6_addr *final_p, final; + int res; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = sk->sk_protocol; @@ -241,12 +242,14 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) __inet6_csk_dst_store(sk, dst, NULL, NULL); } - skb_dst_set(skb, dst_clone(dst)); + rcu_read_lock(); + skb_dst_set_noref(skb, dst); /* Restore final destination back after routing done */ ipv6_addr_copy(&fl6.daddr, &np->daddr); - return ip6_xmit(sk, skb, &fl6, np->opt); + res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); + rcu_read_unlock(); + return res; } - EXPORT_SYMBOL_GPL(inet6_csk_xmit); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 320d91d..93718f3 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -28,10 +28,6 @@ #include <linux/list.h> #include <linux/slab.h> -#ifdef CONFIG_PROC_FS -#include <linux/proc_fs.h> -#endif - #include <net/ipv6.h> #include <net/ndisc.h> #include <net/addrconf.h> diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 4c882cf..84d0bd5 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -180,7 +180,7 @@ int ip6_output(struct sk_buff *skb) */ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, - struct ipv6_txoptions *opt) + struct ipv6_txoptions *opt, int tclass) { struct net *net = sock_net(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -190,7 +190,6 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, u8 proto = fl6->flowi6_proto; int seg_len = skb->len; int hlimit = -1; - int tclass = 0; u32 mtu; if (opt) { @@ -228,10 +227,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, /* * Fill in the IPv6 header */ - if (np) { - tclass = np->tclass; + if (np) hlimit = np->hop_limit; - } if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); @@ -1126,7 +1123,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, hh_len + fragheaderlen + transhdrlen + 20, (flags & MSG_DONTWAIT), &err); if (skb == NULL) - return -ENOMEM; + return err; /* reserve space for Hardware header */ skb_reserve(skb, hh_len); @@ -1193,6 +1190,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, struct sk_buff *skb; unsigned int maxfraglen, fragheaderlen; int exthdrlen; + int dst_exthdrlen; int hh_len; int mtu; int copy; @@ -1248,7 +1246,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, np->cork.hop_limit = hlimit; np->cork.tclass = tclass; mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? - rt->dst.dev->mtu : dst_mtu(rt->dst.path); + rt->dst.dev->mtu : dst_mtu(&rt->dst); if (np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; @@ -1259,16 +1257,17 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, cork->length = 0; sk->sk_sndmsg_page = NULL; sk->sk_sndmsg_off = 0; - exthdrlen = rt->dst.header_len + (opt ? opt->opt_flen : 0) - - rt->rt6i_nfheader_len; + exthdrlen = (opt ? opt->opt_flen : 0) - rt->rt6i_nfheader_len; length += exthdrlen; transhdrlen += exthdrlen; + dst_exthdrlen = rt->dst.header_len; } else { rt = (struct rt6_info *)cork->dst; fl6 = &inet->cork.fl.u.ip6; opt = np->cork.opt; transhdrlen = 0; exthdrlen = 0; + dst_exthdrlen = 0; mtu = cork->fragsize; } @@ -1368,6 +1367,8 @@ alloc_new_skb: else alloclen = datalen + fragheaderlen; + alloclen += dst_exthdrlen; + /* * The last fragment gets additional space at tail. * Note: we overallocate on fragments with MSG_MODE @@ -1419,9 +1420,9 @@ alloc_new_skb: /* * Find where to start putting bytes */ - data = skb_put(skb, fraglen); - skb_set_network_header(skb, exthdrlen); - data += fragheaderlen; + data = skb_put(skb, fraglen + dst_exthdrlen); + skb_set_network_header(skb, exthdrlen + dst_exthdrlen); + data += fragheaderlen + dst_exthdrlen; skb->transport_header = (skb->network_header + fragheaderlen); if (fraggap) { @@ -1434,6 +1435,7 @@ alloc_new_skb: pskb_trim_unique(skb_prev, maxfraglen); } copy = datalen - transhdrlen - fraggap; + if (copy < 0) { err = -EINVAL; kfree_skb(skb); @@ -1448,6 +1450,7 @@ alloc_new_skb: length -= datalen - fraggap; transhdrlen = 0; exthdrlen = 0; + dst_exthdrlen = 0; csummode = CHECKSUM_NONE; /* @@ -1480,13 +1483,13 @@ alloc_new_skb: if (page && (left = PAGE_SIZE - off) > 0) { if (copy >= left) copy = left; - if (page != frag->page) { + if (page != skb_frag_page(frag)) { if (i == MAX_SKB_FRAGS) { err = -EMSGSIZE; goto error; } - get_page(page); skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0); + skb_frag_ref(skb, i); frag = &skb_shinfo(skb)->frags[i]; } } else if(i < MAX_SKB_FRAGS) { @@ -1506,12 +1509,14 @@ alloc_new_skb: err = -EMSGSIZE; goto error; } - if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) { + if (getfrag(from, + skb_frag_address(frag) + skb_frag_size(frag), + offset, copy, skb->len, skb) < 0) { err = -EFAULT; goto error; } sk->sk_sndmsg_off += copy; - frag->size += copy; + skb_frag_size_add(frag, copy); skb->len += copy; skb->data_len += copy; skb->truesize += copy; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 0bc9888..bdc15c9 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -218,8 +218,8 @@ ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms); - rcu_assign_pointer(t->next , rtnl_dereference(*tp)); - rcu_assign_pointer(*tp, t); + RCU_INIT_POINTER(t->next , rtnl_dereference(*tp)); + RCU_INIT_POINTER(*tp, t); } /** @@ -237,7 +237,7 @@ ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { - rcu_assign_pointer(*tp, t->next); + RCU_INIT_POINTER(*tp, t->next); break; } } @@ -350,7 +350,7 @@ ip6_tnl_dev_uninit(struct net_device *dev) struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev == ip6n->fb_tnl_dev) - rcu_assign_pointer(ip6n->tnls_wc[0], NULL); + RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else ip6_tnl_unlink(ip6n, t); ip6_tnl_dst_reset(t); @@ -889,7 +889,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, struct net_device_stats *stats = &t->dev->stats; struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct ipv6_tel_txoption opt; - struct dst_entry *dst; + struct dst_entry *dst = NULL, *ndst = NULL; struct net_device *tdev; int mtu; unsigned int max_headroom = sizeof(struct ipv6hdr); @@ -897,19 +897,20 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, int err = -1; int pkt_len; - if ((dst = ip6_tnl_dst_check(t)) != NULL) - dst_hold(dst); - else { - dst = ip6_route_output(net, NULL, fl6); + if (!fl6->flowi6_mark) + dst = ip6_tnl_dst_check(t); + if (!dst) { + ndst = ip6_route_output(net, NULL, fl6); - if (dst->error) + if (ndst->error) goto tx_err_link_failure; - dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0); - if (IS_ERR(dst)) { - err = PTR_ERR(dst); - dst = NULL; + ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(fl6), NULL, 0); + if (IS_ERR(ndst)) { + err = PTR_ERR(ndst); + ndst = NULL; goto tx_err_link_failure; } + dst = ndst; } tdev = dst->dev; @@ -955,8 +956,12 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, skb = new_skb; } skb_dst_drop(skb); - skb_dst_set(skb, dst_clone(dst)); - + if (fl6->flowi6_mark) { + skb_dst_set(skb, dst); + ndst = NULL; + } else { + skb_dst_set_noref(skb, dst); + } skb->transport_header = skb->network_header; proto = fl6->flowi6_proto; @@ -987,13 +992,14 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, stats->tx_errors++; stats->tx_aborted_errors++; } - ip6_tnl_dst_store(t, dst); + if (ndst) + ip6_tnl_dst_store(t, ndst); return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: - dst_release(dst); + dst_release(ndst); return err; } @@ -1020,9 +1026,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) dsfield = ipv4_get_dsfield(iph); - if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)) + if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT) & IPV6_TCLASS_MASK; + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) + fl6.flowi6_mark = skb->mark; err = ip6_tnl_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu); if (err != 0) { @@ -1069,10 +1077,12 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) fl6.flowi6_proto = IPPROTO_IPV6; dsfield = ipv6_get_dsfield(ipv6h); - if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)) + if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK); - if ((t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)) + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL) fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK); + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) + fl6.flowi6_mark = skb->mark; err = ip6_tnl_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu); if (err != 0) { @@ -1439,7 +1449,7 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) t->parms.proto = IPPROTO_IPV6; dev_hold(dev); - rcu_assign_pointer(ip6n->tnls_wc[0], t); + RCU_INIT_POINTER(ip6n->tnls_wc[0], t); return 0; } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 2fbda5f..c99e3ee 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -343,7 +343,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, break; case IPV6_TRANSPARENT: - if (!capable(CAP_NET_ADMIN)) { + if (valbool && !capable(CAP_NET_ADMIN) && !capable(CAP_NET_RAW)) { retv = -EPERM; break; } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 9da6e02..44e5b7f 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -370,17 +370,14 @@ static int ndisc_constructor(struct neighbour *neigh) struct neigh_parms *parms; int is_multicast = ipv6_addr_is_multicast(addr); - rcu_read_lock(); in6_dev = in6_dev_get(dev); if (in6_dev == NULL) { - rcu_read_unlock(); return -EINVAL; } parms = in6_dev->nd_parms; __neigh_parms_put(neigh->parms); neigh->parms = neigh_parms_clone(parms); - rcu_read_unlock(); neigh->type = is_multicast ? RTN_MULTICAST : RTN_UNICAST; if (!dev->header_ops) { @@ -533,7 +530,8 @@ void ndisc_send_skb(struct sk_buff *skb, skb_dst_set(skb, dst); - idev = in6_dev_get(dst->dev); + rcu_read_lock(); + idev = __in6_dev_get(dst->dev); IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev, @@ -543,8 +541,7 @@ void ndisc_send_skb(struct sk_buff *skb, ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } - if (likely(idev != NULL)) - in6_dev_put(idev); + rcu_read_unlock(); } EXPORT_SYMBOL(ndisc_send_skb); @@ -1039,7 +1036,7 @@ static void ndisc_recv_rs(struct sk_buff *skb) if (skb->len < sizeof(*rs_msg)) return; - idev = in6_dev_get(skb->dev); + idev = __in6_dev_get(skb->dev); if (!idev) { if (net_ratelimit()) ND_PRINTK1("ICMP6 RS: can't find in6 device\n"); @@ -1080,7 +1077,7 @@ static void ndisc_recv_rs(struct sk_buff *skb) neigh_release(neigh); } out: - in6_dev_put(idev); + return; } static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) @@ -1179,7 +1176,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) * set the RA_RECV flag in the interface */ - in6_dev = in6_dev_get(skb->dev); + in6_dev = __in6_dev_get(skb->dev); if (in6_dev == NULL) { ND_PRINTK0(KERN_ERR "ICMPv6 RA: can't find inet6 device for %s.\n", @@ -1188,7 +1185,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) } if (!ndisc_parse_options(opt, optlen, &ndopts)) { - in6_dev_put(in6_dev); ND_PRINTK2(KERN_WARNING "ICMP6 RA: invalid ND options\n"); return; @@ -1225,6 +1221,9 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (!in6_dev->cnf.accept_ra_defrtr) goto skip_defrtr; + if (ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, NULL, 0)) + goto skip_defrtr; + lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); #ifdef CONFIG_IPV6_ROUTER_PREF @@ -1255,7 +1254,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) ND_PRINTK0(KERN_ERR "ICMPv6 RA: %s() failed to add default route.\n", __func__); - in6_dev_put(in6_dev); return; } @@ -1265,7 +1263,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) "ICMPv6 RA: %s() got default router without neighbour.\n", __func__); dst_release(&rt->dst); - in6_dev_put(in6_dev); return; } neigh->flags |= NTF_ROUTER; @@ -1349,6 +1346,9 @@ skip_linkparms: goto out; #ifdef CONFIG_IPV6_ROUTE_INFO + if (ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, NULL, 0)) + goto skip_routeinfo; + if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_ri; @@ -1366,6 +1366,8 @@ skip_linkparms: &ipv6_hdr(skb)->saddr); } } + +skip_routeinfo: #endif #ifdef CONFIG_IPV6_NDISC_NODETYPE @@ -1422,7 +1424,6 @@ out: dst_release(&rt->dst); else if (neigh) neigh_release(neigh); - in6_dev_put(in6_dev); } static void ndisc_redirect_rcv(struct sk_buff *skb) @@ -1481,13 +1482,11 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) return; } - in6_dev = in6_dev_get(skb->dev); + in6_dev = __in6_dev_get(skb->dev); if (!in6_dev) return; - if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects) { - in6_dev_put(in6_dev); + if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects) return; - } /* RFC2461 8.1: * The IP source address of the Redirect MUST be the same as the current @@ -1497,7 +1496,6 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) { ND_PRINTK2(KERN_WARNING "ICMPv6 Redirect: invalid ND options\n"); - in6_dev_put(in6_dev); return; } if (ndopts.nd_opts_tgt_lladdr) { @@ -1506,7 +1504,6 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) if (!lladdr) { ND_PRINTK2(KERN_WARNING "ICMPv6 Redirect: invalid link-layer address length\n"); - in6_dev_put(in6_dev); return; } } @@ -1518,7 +1515,6 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) on_link); neigh_release(neigh); } - in6_dev_put(in6_dev); } void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, @@ -1651,7 +1647,8 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, csum_partial(icmph, len, 0)); skb_dst_set(buff, dst); - idev = in6_dev_get(dst->dev); + rcu_read_lock(); + idev = __in6_dev_get(dst->dev); IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, buff, NULL, dst->dev, dst_output); @@ -1660,8 +1657,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } - if (likely(idev != NULL)) - in6_dev_put(idev); + rcu_read_unlock(); return; release: diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 30fcee4..8992cf6 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -100,9 +100,16 @@ static int nf_ip6_route(struct net *net, struct dst_entry **dst, .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; + struct dst_entry *result; + int err; + + result = ip6_route_output(net, sk, &fl->u.ip6); + err = result->error; + if (err) + dst_release(result); + else + *dst = result; + return err; } __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 0857272..38f00b0 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -182,7 +182,6 @@ fq_find(__be32 id, u32 user, struct in6_addr *src, struct in6_addr *dst) return container_of(q, struct nf_ct_frag6_queue, q); oom: - pr_debug("Can't alloc new queue\n"); return NULL; } @@ -370,16 +369,16 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) struct sk_buff *clone; int i, plen = 0; - if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL) { - pr_debug("Can't alloc skb\n"); + clone = alloc_skb(0, GFP_ATOMIC); + if (clone == NULL) goto out_oom; - } + clone->next = head->next; head->next = clone; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); - for (i=0; i<skb_shinfo(head)->nr_frags; i++) - plen += skb_shinfo(head)->frags[i].size; + for (i = 0; i < skb_shinfo(head)->nr_frags; i++) + plen += skb_frag_size(&skb_shinfo(head)->frags[i]); clone->len = clone->data_len = head->data_len - plen; head->data_len -= clone->len; head->len -= clone->len; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 343852e..6f7824e 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -130,14 +130,14 @@ static mh_filter_t __rcu *mh_filter __read_mostly; int rawv6_mh_filter_register(mh_filter_t filter) { - rcu_assign_pointer(mh_filter, filter); + RCU_INIT_POINTER(mh_filter, filter); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_register); int rawv6_mh_filter_unregister(mh_filter_t filter) { - rcu_assign_pointer(mh_filter, NULL); + RCU_INIT_POINTER(mh_filter, NULL); synchronize_rcu(); return 0; } @@ -372,9 +372,9 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, read_unlock(&raw_v6_hashinfo.lock); } -static inline int rawv6_rcv_skb(struct sock * sk, struct sk_buff * skb) +static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) { - if ((raw6_sk(sk)->checksum || rcu_dereference_raw(sk->sk_filter)) && + if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); @@ -542,8 +542,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, goto out; offset = rp->offset; - total_len = inet_sk(sk)->cork.base.length - (skb_network_header(skb) - - skb->data); + total_len = inet_sk(sk)->cork.base.length; if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 7b954e2..cc22099 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -464,8 +464,8 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, head->next = clone; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); - for (i=0; i<skb_shinfo(head)->nr_frags; i++) - plen += skb_shinfo(head)->frags[i].size; + for (i = 0; i < skb_shinfo(head)->nr_frags; i++) + plen += skb_frag_size(&skb_shinfo(head)->frags[i]); clone->len = clone->data_len = head->data_len - plen; head->data_len -= clone->len; head->len -= clone->len; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fb545ed..57b82dc 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1086,11 +1086,10 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->dst.output = ip6_output; dst_set_neighbour(&rt->dst, neigh); atomic_set(&rt->dst.__refcnt, 1); - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255); - ipv6_addr_copy(&rt->rt6i_dst.addr, addr); rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255); spin_lock_bh(&icmp6_dst_lock); rt->dst.next = icmp6_dst_gc_list; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 00b15ac..a7a1860 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -182,7 +182,7 @@ static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t) (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { - rcu_assign_pointer(*tp, t->next); + RCU_INIT_POINTER(*tp, t->next); break; } } @@ -192,8 +192,8 @@ static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t) { struct ip_tunnel __rcu **tp = ipip6_bucket(sitn, t); - rcu_assign_pointer(t->next, rtnl_dereference(*tp)); - rcu_assign_pointer(*tp, t); + RCU_INIT_POINTER(t->next, rtnl_dereference(*tp)); + RCU_INIT_POINTER(*tp, t); } static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) @@ -391,7 +391,7 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) p->addr = a->addr; p->flags = a->flags; t->prl_count++; - rcu_assign_pointer(t->prl, p); + RCU_INIT_POINTER(t->prl, p); out: return err; } @@ -474,7 +474,7 @@ static void ipip6_tunnel_uninit(struct net_device *dev) struct sit_net *sitn = net_generic(net, sit_net_id); if (dev == sitn->fb_tunnel_dev) { - rcu_assign_pointer(sitn->tunnels_wc[0], NULL); + RCU_INIT_POINTER(sitn->tunnels_wc[0], NULL); } else { ipip6_tunnel_unlink(sitn, netdev_priv(dev)); ipip6_tunnel_del_prl(netdev_priv(dev), NULL); @@ -1176,7 +1176,7 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; dev_hold(dev); - rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); + RCU_INIT_POINTER(sitn->tunnels_wc[0], tunnel); return 0; } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index ac83896..5a0d664 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -115,7 +115,7 @@ static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr, & COOKIEMASK; } -__u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp) +__u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb, __u16 *mssp) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); @@ -137,7 +137,7 @@ __u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp) jiffies / (HZ * 60), mssind); } -static inline int cookie_check(struct sk_buff *skb, __u32 cookie) +static inline int cookie_check(const struct sk_buff *skb, __u32 cookie) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); @@ -152,7 +152,7 @@ static inline int cookie_check(struct sk_buff *skb, __u32 cookie) struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) { struct tcp_options_received tcp_opt; - u8 *hash_location; + const u8 *hash_location; struct inet_request_sock *ireq; struct inet6_request_sock *ireq6; struct tcp_request_sock *treq; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 3c9fa61..36131d1 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -114,7 +114,7 @@ static __inline__ __sum16 tcp_v6_check(int len, return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base); } -static __u32 tcp_v6_init_sequence(struct sk_buff *skb) +static __u32 tcp_v6_init_sequence(const struct sk_buff *skb) { return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32, @@ -513,7 +513,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr); - err = ip6_xmit(sk, skb, &fl6, opt); + err = ip6_xmit(sk, skb, &fl6, opt, np->tclass); err = net_xmit_eval(err); } @@ -591,7 +591,8 @@ static int tcp_v6_md5_do_add(struct sock *sk, const struct in6_addr *peer, } sk_nocaps_add(sk, NETIF_F_GSO_MASK); } - if (tcp_alloc_md5sig_pool(sk) == NULL) { + if (tp->md5sig_info->entries6 == 0 && + tcp_alloc_md5sig_pool(sk) == NULL) { kfree(newkey); return -ENOMEM; } @@ -600,8 +601,9 @@ static int tcp_v6_md5_do_add(struct sock *sk, const struct in6_addr *peer, (tp->md5sig_info->entries6 + 1)), GFP_ATOMIC); if (!keys) { - tcp_free_md5sig_pool(); kfree(newkey); + if (tp->md5sig_info->entries6 == 0) + tcp_free_md5sig_pool(); return -ENOMEM; } @@ -647,6 +649,7 @@ static int tcp_v6_md5_do_del(struct sock *sk, const struct in6_addr *peer) kfree(tp->md5sig_info->keys6); tp->md5sig_info->keys6 = NULL; tp->md5sig_info->alloced6 = 0; + tcp_free_md5sig_pool(); } else { /* shrink the database */ if (tp->md5sig_info->entries6 != i) @@ -655,7 +658,6 @@ static int tcp_v6_md5_do_del(struct sock *sk, const struct in6_addr *peer) (tp->md5sig_info->entries6 - i) * sizeof (tp->md5sig_info->keys6[0])); } - tcp_free_md5sig_pool(); return 0; } } @@ -759,7 +761,7 @@ static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key, const struct in6_addr *daddr, struct in6_addr *saddr, - struct tcphdr *th) + const struct tcphdr *th) { struct tcp_md5sig_pool *hp; struct hash_desc *desc; @@ -791,13 +793,14 @@ clear_hash_noput: } static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, - struct sock *sk, struct request_sock *req, - struct sk_buff *skb) + const struct sock *sk, + const struct request_sock *req, + const struct sk_buff *skb) { const struct in6_addr *saddr, *daddr; struct tcp_md5sig_pool *hp; struct hash_desc *desc; - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); if (sk) { saddr = &inet6_sk(sk)->saddr; @@ -840,12 +843,12 @@ clear_hash_noput: return 1; } -static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb) +static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) { - __u8 *hash_location = NULL; + const __u8 *hash_location = NULL; struct tcp_md5sig_key *hash_expected; const struct ipv6hdr *ip6h = ipv6_hdr(skb); - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); int genhash; u8 newhash[16]; @@ -976,9 +979,10 @@ static int tcp6_gro_complete(struct sk_buff *skb) } static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, - u32 ts, struct tcp_md5sig_key *key, int rst) + u32 ts, struct tcp_md5sig_key *key, int rst, u8 tclass) { - struct tcphdr *th = tcp_hdr(skb), *t1; + const struct tcphdr *th = tcp_hdr(skb); + struct tcphdr *t1; struct sk_buff *buff; struct flowi6 fl6; struct net *net = dev_net(skb_dst(skb)->dev); @@ -1056,7 +1060,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL, false); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); - ip6_xmit(ctl_sk, buff, &fl6, NULL); + ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); if (rst) TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); @@ -1068,7 +1072,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) { - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); u32 seq = 0, ack_seq = 0; struct tcp_md5sig_key *key = NULL; @@ -1089,13 +1093,13 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2); - tcp_v6_send_response(skb, seq, ack_seq, 0, 0, key, 1); + tcp_v6_send_response(skb, seq, ack_seq, 0, 0, key, 1, 0); } static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts, - struct tcp_md5sig_key *key) + struct tcp_md5sig_key *key, u8 tclass) { - tcp_v6_send_response(skb, seq, ack, win, ts, key, 0); + tcp_v6_send_response(skb, seq, ack, win, ts, key, 0, tclass); } static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) @@ -1105,7 +1109,8 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v6_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw)); + tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw), + tw->tw_tclass); inet_twsk_put(tw); } @@ -1114,7 +1119,7 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent, - tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr)); + tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0); } @@ -1158,7 +1163,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { struct tcp_extend_values tmp_ext; struct tcp_options_received tmp_opt; - u8 *hash_location; + const u8 *hash_location; struct request_sock *req; struct inet6_request_sock *treq; struct ipv6_pinfo *np = inet6_sk(sk); @@ -1383,6 +1388,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); @@ -1447,6 +1454,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, First: no IPv4 options. */ newinet->inet_opt = NULL; + newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; /* Clone RX bits */ @@ -1603,7 +1611,7 @@ 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); + sock_rps_save_rxhash(sk, skb); if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) goto reset; if (opt_skb) @@ -1625,7 +1633,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) * the new socket.. */ if(nsk != sk) { - sock_rps_save_rxhash(nsk, skb->rxhash); + sock_rps_save_rxhash(nsk, skb); if (tcp_child_process(sk, nsk, skb)) goto reset; if (opt_skb) @@ -1633,7 +1641,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; } } else - sock_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb); if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) goto reset; @@ -1683,7 +1691,7 @@ ipv6_pktoptions: static int tcp_v6_rcv(struct sk_buff *skb) { - struct tcphdr *th; + const struct tcphdr *th; const struct ipv6hdr *hdr; struct sock *sk; int ret; @@ -1717,7 +1725,7 @@ static int tcp_v6_rcv(struct sk_buff *skb) skb->len - th->doff*4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->when = 0; - TCP_SKB_CB(skb)->flags = ipv6_get_dsfield(hdr); + TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr); TCP_SKB_CB(skb)->sacked = 0; sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest); @@ -1851,8 +1859,8 @@ static struct inet_peer *tcp_v6_get_peer(struct sock *sk, bool *release_it) static void *tcp_v6_tw_get_peer(struct sock *sk) { - struct inet6_timewait_sock *tw6 = inet6_twsk(sk); - struct inet_timewait_sock *tw = inet_twsk(sk); + const struct inet6_timewait_sock *tw6 = inet6_twsk(sk); + const struct inet_timewait_sock *tw = inet_twsk(sk); if (tw->tw_family == AF_INET) return tcp_v4_tw_get_peer(sk); @@ -2007,7 +2015,7 @@ static void tcp_v6_destroy_sock(struct sock *sk) #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, - struct sock *sk, struct request_sock *req, int i, int uid) + const struct sock *sk, struct request_sock *req, int i, int uid) { int ttd = req->expires - jiffies; const struct in6_addr *src = &inet6_rsk(req)->loc_addr; @@ -2043,10 +2051,10 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) __u16 destp, srcp; int timer_active; unsigned long timer_expires; - struct inet_sock *inet = inet_sk(sp); - struct tcp_sock *tp = tcp_sk(sp); + const struct inet_sock *inet = inet_sk(sp); + const struct tcp_sock *tp = tcp_sk(sp); const struct inet_connection_sock *icsk = inet_csk(sp); - struct ipv6_pinfo *np = inet6_sk(sp); + const struct ipv6_pinfo *np = inet6_sk(sp); dest = &np->daddr; src = &np->rcv_saddr; @@ -2098,7 +2106,7 @@ static void get_timewait6_sock(struct seq_file *seq, { const struct in6_addr *dest, *src; __u16 destp, srcp; - struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); + const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); int ttd = tw->tw_ttd - jiffies; if (ttd < 0) @@ -2153,12 +2161,18 @@ out: return 0; } +static const struct file_operations tcp6_afinfo_seq_fops = { + .owner = THIS_MODULE, + .open = tcp_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net +}; + static struct tcp_seq_afinfo tcp6_seq_afinfo = { .name = "tcp6", .family = AF_INET6, - .seq_fops = { - .owner = THIS_MODULE, - }, + .seq_fops = &tcp6_afinfo_seq_fops, .seq_ops = { .show = tcp6_seq_show, }, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index bb95e8e..846f4757 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -509,7 +509,7 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) int is_udplite = IS_UDPLITE(sk); if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) - sock_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto drop; @@ -533,7 +533,7 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) } } - if (rcu_dereference_raw(sk->sk_filter)) { + if (rcu_access_pointer(sk->sk_filter)) { if (udp_lib_checksum_complete(skb)) goto drop; } @@ -1424,13 +1424,19 @@ int udp6_seq_show(struct seq_file *seq, void *v) return 0; } +static const struct file_operations udp6_afinfo_seq_fops = { + .owner = THIS_MODULE, + .open = udp_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net +}; + static struct udp_seq_afinfo udp6_seq_afinfo = { .name = "udp6", .family = AF_INET6, .udp_table = &udp_table, - .seq_fops = { - .owner = THIS_MODULE, - }, + .seq_fops = &udp6_afinfo_seq_fops, .seq_ops = { .show = udp6_seq_show, }, diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 986c4de..8889aa2 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -93,13 +93,20 @@ void udplitev6_exit(void) } #ifdef CONFIG_PROC_FS + +static const struct file_operations udplite6_afinfo_seq_fops = { + .owner = THIS_MODULE, + .open = udp_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net +}; + static struct udp_seq_afinfo udplite6_seq_afinfo = { .name = "udplite6", .family = AF_INET6, .udp_table = &udplite_table, - .seq_fops = { - .owner = THIS_MODULE, - }, + .seq_fops = &udplite6_afinfo_seq_fops, .seq_ops = { .show = udp6_seq_show, }, diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 49a91c5f..faae417 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -28,6 +28,43 @@ int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, EXPORT_SYMBOL(xfrm6_find_1stfragopt); +static int xfrm6_local_dontfrag(struct sk_buff *skb) +{ + int proto; + struct sock *sk = skb->sk; + + if (sk) { + proto = sk->sk_protocol; + + if (proto == IPPROTO_UDP || proto == IPPROTO_RAW) + return inet6_sk(sk)->dontfrag; + } + + return 0; +} + +static void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu) +{ + struct flowi6 fl6; + struct sock *sk = skb->sk; + + fl6.flowi6_oif = sk->sk_bound_dev_if; + ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->daddr); + + ipv6_local_rxpmtu(sk, &fl6, mtu); +} + +static void xfrm6_local_error(struct sk_buff *skb, u32 mtu) +{ + struct flowi6 fl6; + struct sock *sk = skb->sk; + + fl6.fl6_dport = inet_sk(sk)->inet_dport; + ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->daddr); + + ipv6_local_error(sk, EMSGSIZE, &fl6, mtu); +} + static int xfrm6_tunnel_check_size(struct sk_buff *skb) { int mtu, ret = 0; @@ -39,7 +76,13 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) if (!skb->local_df && skb->len > mtu) { skb->dev = dst->dev; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + + if (xfrm6_local_dontfrag(skb)) + xfrm6_local_rxpmtu(skb, mtu); + else if (skb->sk) + xfrm6_local_error(skb, mtu); + else + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ret = -EMSGSIZE; } @@ -93,9 +136,18 @@ static int __xfrm6_output(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; + int mtu = ip6_skb_dst_mtu(skb); + + if (skb->len > mtu && xfrm6_local_dontfrag(skb)) { + xfrm6_local_rxpmtu(skb, mtu); + return -EMSGSIZE; + } else if (!skb->local_df && skb->len > mtu && skb->sk) { + xfrm6_local_error(skb, mtu); + return -EMSGSIZE; + } if ((x && x->props.mode == XFRM_MODE_TUNNEL) && - ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || + ((skb->len > mtu && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)))) { return ip6_fragment(skb, x->outer_mode->afinfo->output_finish); } diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index b3cc8b3..253695d 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -551,7 +551,7 @@ static void ircomm_tty_close(struct tty_struct *tty, struct file *filp) */ tty->closing = 1; if (self->closing_wait != ASYNC_CLOSING_WAIT_NONE) - tty_wait_until_sent(tty, self->closing_wait); + tty_wait_until_sent_from_close(tty, self->closing_wait); ircomm_tty_shutdown(self); diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c index e8d5f44..d14152e 100644 --- a/net/irda/irlan/irlan_eth.c +++ b/net/irda/irlan/irlan_eth.c @@ -50,7 +50,7 @@ static const struct net_device_ops irlan_eth_netdev_ops = { .ndo_open = irlan_eth_open, .ndo_stop = irlan_eth_close, .ndo_start_xmit = irlan_eth_xmit, - .ndo_set_multicast_list = irlan_eth_set_multicast_list, + .ndo_set_rx_mode = irlan_eth_set_multicast_list, .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, }; diff --git a/net/iucv/Kconfig b/net/iucv/Kconfig index 16ce9cd..497fbe7 100644 --- a/net/iucv/Kconfig +++ b/net/iucv/Kconfig @@ -1,15 +1,17 @@ config IUCV - tristate "IUCV support (S390 - z/VM only)" depends on S390 + def_tristate y if S390 + prompt "IUCV support (S390 - z/VM only)" help Select this option if you want to use inter-user communication under VM or VIF. If you run on z/VM, say "Y" to enable a fast communication link between VM guests. config AFIUCV - tristate "AF_IUCV support (S390 - z/VM only)" - depends on IUCV + depends on S390 + def_tristate m if QETH_L3 || IUCV + prompt "AF_IUCV Socket support (S390 - z/VM and HiperSockets transport)" help - Select this option if you want to use inter-user communication under - VM or VIF sockets. If you run on z/VM, say "Y" to enable a fast - communication link between VM guests. + Select this option if you want to use AF_IUCV socket applications + based on z/VM inter-user communication vehicle or based on + HiperSockets. diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index e2013e4..274d150 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -27,10 +27,9 @@ #include <asm/cpcmd.h> #include <linux/kmod.h> -#include <net/iucv/iucv.h> #include <net/iucv/af_iucv.h> -#define VERSION "1.1" +#define VERSION "1.2" static char iucv_userid[80]; @@ -42,6 +41,8 @@ static struct proto iucv_proto = { .obj_size = sizeof(struct iucv_sock), }; +static struct iucv_interface *pr_iucv; + /* special AF_IUCV IPRM messages */ static const u8 iprm_shutdown[8] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}; @@ -90,6 +91,12 @@ do { \ static void iucv_sock_kill(struct sock *sk); static void iucv_sock_close(struct sock *sk); +static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev); +static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, + struct sk_buff *skb, u8 flags); +static void afiucv_hs_callback_txnotify(struct sk_buff *, enum iucv_tx_notify); + /* Call Back functions */ static void iucv_callback_rx(struct iucv_path *, struct iucv_message *); static void iucv_callback_txdone(struct iucv_path *, struct iucv_message *); @@ -165,7 +172,7 @@ static int afiucv_pm_freeze(struct device *dev) case IUCV_CLOSING: case IUCV_CONNECTED: if (iucv->path) { - err = iucv_path_sever(iucv->path, NULL); + err = pr_iucv->path_sever(iucv->path, NULL); iucv_path_free(iucv->path); iucv->path = NULL; } @@ -229,7 +236,7 @@ static const struct dev_pm_ops afiucv_pm_ops = { static struct device_driver af_iucv_driver = { .owner = THIS_MODULE, .name = "afiucv", - .bus = &iucv_bus, + .bus = NULL, .pm = &afiucv_pm_ops, }; @@ -294,7 +301,11 @@ static inline int iucv_below_msglim(struct sock *sk) if (sk->sk_state != IUCV_CONNECTED) return 1; - return (skb_queue_len(&iucv->send_skb_q) < iucv->path->msglim); + if (iucv->transport == AF_IUCV_TRANS_IUCV) + return (skb_queue_len(&iucv->send_skb_q) < iucv->path->msglim); + else + return ((atomic_read(&iucv->msg_sent) < iucv->msglimit_peer) && + (atomic_read(&iucv->pendings) <= 0)); } /** @@ -312,6 +323,79 @@ static void iucv_sock_wake_msglim(struct sock *sk) rcu_read_unlock(); } +/** + * afiucv_hs_send() - send a message through HiperSockets transport + */ +static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, + struct sk_buff *skb, u8 flags) +{ + struct net *net = sock_net(sock); + struct iucv_sock *iucv = iucv_sk(sock); + struct af_iucv_trans_hdr *phs_hdr; + struct sk_buff *nskb; + int err, confirm_recv = 0; + + memset(skb->head, 0, ETH_HLEN); + phs_hdr = (struct af_iucv_trans_hdr *)skb_push(skb, + sizeof(struct af_iucv_trans_hdr)); + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_push(skb, ETH_HLEN); + skb_reset_mac_header(skb); + memset(phs_hdr, 0, sizeof(struct af_iucv_trans_hdr)); + + phs_hdr->magic = ETH_P_AF_IUCV; + phs_hdr->version = 1; + phs_hdr->flags = flags; + if (flags == AF_IUCV_FLAG_SYN) + phs_hdr->window = iucv->msglimit; + else if ((flags == AF_IUCV_FLAG_WIN) || !flags) { + confirm_recv = atomic_read(&iucv->msg_recv); + phs_hdr->window = confirm_recv; + if (confirm_recv) + phs_hdr->flags = phs_hdr->flags | AF_IUCV_FLAG_WIN; + } + memcpy(phs_hdr->destUserID, iucv->dst_user_id, 8); + memcpy(phs_hdr->destAppName, iucv->dst_name, 8); + memcpy(phs_hdr->srcUserID, iucv->src_user_id, 8); + memcpy(phs_hdr->srcAppName, iucv->src_name, 8); + ASCEBC(phs_hdr->destUserID, sizeof(phs_hdr->destUserID)); + ASCEBC(phs_hdr->destAppName, sizeof(phs_hdr->destAppName)); + ASCEBC(phs_hdr->srcUserID, sizeof(phs_hdr->srcUserID)); + ASCEBC(phs_hdr->srcAppName, sizeof(phs_hdr->srcAppName)); + if (imsg) + memcpy(&phs_hdr->iucv_hdr, imsg, sizeof(struct iucv_message)); + + rcu_read_lock(); + skb->dev = dev_get_by_index_rcu(net, sock->sk_bound_dev_if); + rcu_read_unlock(); + if (!skb->dev) + return -ENODEV; + if (!(skb->dev->flags & IFF_UP)) + return -ENETDOWN; + if (skb->len > skb->dev->mtu) { + if (sock->sk_type == SOCK_SEQPACKET) + return -EMSGSIZE; + else + skb_trim(skb, skb->dev->mtu); + } + skb->protocol = ETH_P_AF_IUCV; + skb_shinfo(skb)->tx_flags |= SKBTX_DRV_NEEDS_SK_REF; + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return -ENOMEM; + skb_queue_tail(&iucv->send_skb_q, nskb); + err = dev_queue_xmit(skb); + if (err) { + skb_unlink(nskb, &iucv->send_skb_q); + kfree_skb(nskb); + } else { + atomic_sub(confirm_recv, &iucv->msg_recv); + WARN_ON(atomic_read(&iucv->msg_recv) < 0); + } + return err; +} + /* Timers */ static void iucv_sock_timeout(unsigned long arg) { @@ -380,6 +464,8 @@ static void iucv_sock_close(struct sock *sk) unsigned char user_data[16]; struct iucv_sock *iucv = iucv_sk(sk); unsigned long timeo; + int err, blen; + struct sk_buff *skb; iucv_sock_clear_timer(sk); lock_sock(sk); @@ -390,6 +476,20 @@ static void iucv_sock_close(struct sock *sk) break; case IUCV_CONNECTED: + if (iucv->transport == AF_IUCV_TRANS_HIPER) { + /* send fin */ + blen = sizeof(struct af_iucv_trans_hdr) + ETH_HLEN; + skb = sock_alloc_send_skb(sk, blen, 1, &err); + if (skb) { + skb_reserve(skb, + sizeof(struct af_iucv_trans_hdr) + + ETH_HLEN); + err = afiucv_hs_send(NULL, sk, skb, + AF_IUCV_FLAG_FIN); + } + sk->sk_state = IUCV_DISCONN; + sk->sk_state_change(sk); + } case IUCV_DISCONN: sk->sk_state = IUCV_CLOSING; sk->sk_state_change(sk); @@ -412,7 +512,7 @@ static void iucv_sock_close(struct sock *sk) low_nmcpy(user_data, iucv->src_name); high_nmcpy(user_data, iucv->dst_name); ASCEBC(user_data, sizeof(user_data)); - iucv_path_sever(iucv->path, user_data); + pr_iucv->path_sever(iucv->path, user_data); iucv_path_free(iucv->path); iucv->path = NULL; } @@ -444,23 +544,33 @@ static void iucv_sock_init(struct sock *sk, struct sock *parent) static struct sock *iucv_sock_alloc(struct socket *sock, int proto, gfp_t prio) { struct sock *sk; + struct iucv_sock *iucv; sk = sk_alloc(&init_net, PF_IUCV, prio, &iucv_proto); if (!sk) return NULL; + iucv = iucv_sk(sk); sock_init_data(sock, sk); - INIT_LIST_HEAD(&iucv_sk(sk)->accept_q); - spin_lock_init(&iucv_sk(sk)->accept_q_lock); - skb_queue_head_init(&iucv_sk(sk)->send_skb_q); - INIT_LIST_HEAD(&iucv_sk(sk)->message_q.list); - spin_lock_init(&iucv_sk(sk)->message_q.lock); - skb_queue_head_init(&iucv_sk(sk)->backlog_skb_q); - iucv_sk(sk)->send_tag = 0; - iucv_sk(sk)->flags = 0; - iucv_sk(sk)->msglimit = IUCV_QUEUELEN_DEFAULT; - iucv_sk(sk)->path = NULL; - memset(&iucv_sk(sk)->src_user_id , 0, 32); + INIT_LIST_HEAD(&iucv->accept_q); + spin_lock_init(&iucv->accept_q_lock); + skb_queue_head_init(&iucv->send_skb_q); + INIT_LIST_HEAD(&iucv->message_q.list); + spin_lock_init(&iucv->message_q.lock); + skb_queue_head_init(&iucv->backlog_skb_q); + iucv->send_tag = 0; + atomic_set(&iucv->pendings, 0); + iucv->flags = 0; + iucv->msglimit = 0; + atomic_set(&iucv->msg_sent, 0); + atomic_set(&iucv->msg_recv, 0); + iucv->path = NULL; + iucv->sk_txnotify = afiucv_hs_callback_txnotify; + memset(&iucv->src_user_id , 0, 32); + if (pr_iucv) + iucv->transport = AF_IUCV_TRANS_IUCV; + else + iucv->transport = AF_IUCV_TRANS_HIPER; sk->sk_destruct = iucv_sock_destruct; sk->sk_sndtimeo = IUCV_CONN_TIMEOUT; @@ -591,7 +701,9 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, struct sockaddr_iucv *sa = (struct sockaddr_iucv *) addr; struct sock *sk = sock->sk; struct iucv_sock *iucv; - int err; + int err = 0; + struct net_device *dev; + char uid[9]; /* Verify the input sockaddr */ if (!addr || addr->sa_family != AF_IUCV) @@ -610,19 +722,46 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, err = -EADDRINUSE; goto done_unlock; } - if (iucv->path) { - err = 0; + if (iucv->path) goto done_unlock; - } /* Bind the socket */ - memcpy(iucv->src_name, sa->siucv_name, 8); - /* Copy the user id */ - memcpy(iucv->src_user_id, iucv_userid, 8); - sk->sk_state = IUCV_BOUND; - err = 0; + if (pr_iucv) + if (!memcmp(sa->siucv_user_id, iucv_userid, 8)) + goto vm_bind; /* VM IUCV transport */ + /* try hiper transport */ + memcpy(uid, sa->siucv_user_id, sizeof(uid)); + ASCEBC(uid, 8); + rcu_read_lock(); + for_each_netdev_rcu(&init_net, dev) { + if (!memcmp(dev->perm_addr, uid, 8)) { + memcpy(iucv->src_name, sa->siucv_name, 8); + memcpy(iucv->src_user_id, sa->siucv_user_id, 8); + sock->sk->sk_bound_dev_if = dev->ifindex; + sk->sk_state = IUCV_BOUND; + iucv->transport = AF_IUCV_TRANS_HIPER; + if (!iucv->msglimit) + iucv->msglimit = IUCV_HIPER_MSGLIM_DEFAULT; + rcu_read_unlock(); + goto done_unlock; + } + } + rcu_read_unlock(); +vm_bind: + if (pr_iucv) { + /* use local userid for backward compat */ + memcpy(iucv->src_name, sa->siucv_name, 8); + memcpy(iucv->src_user_id, iucv_userid, 8); + sk->sk_state = IUCV_BOUND; + iucv->transport = AF_IUCV_TRANS_IUCV; + if (!iucv->msglimit) + iucv->msglimit = IUCV_QUEUELEN_DEFAULT; + goto done_unlock; + } + /* found no dev to bind */ + err = -ENODEV; done_unlock: /* Release the socket list lock */ write_unlock_bh(&iucv_sk_list.lock); @@ -658,45 +797,44 @@ static int iucv_sock_autobind(struct sock *sk) memcpy(&iucv->src_name, name, 8); + if (!iucv->msglimit) + iucv->msglimit = IUCV_QUEUELEN_DEFAULT; + return err; } -/* Connect an unconnected socket */ -static int iucv_sock_connect(struct socket *sock, struct sockaddr *addr, - int alen, int flags) +static int afiucv_hs_connect(struct socket *sock) { - struct sockaddr_iucv *sa = (struct sockaddr_iucv *) addr; struct sock *sk = sock->sk; - struct iucv_sock *iucv; - unsigned char user_data[16]; - int err; - - if (addr->sa_family != AF_IUCV || alen < sizeof(struct sockaddr_iucv)) - return -EINVAL; - - if (sk->sk_state != IUCV_OPEN && sk->sk_state != IUCV_BOUND) - return -EBADFD; - - if (sk->sk_type != SOCK_STREAM && sk->sk_type != SOCK_SEQPACKET) - return -EINVAL; + struct sk_buff *skb; + int blen = sizeof(struct af_iucv_trans_hdr) + ETH_HLEN; + int err = 0; - if (sk->sk_state == IUCV_OPEN) { - err = iucv_sock_autobind(sk); - if (unlikely(err)) - return err; + /* send syn */ + skb = sock_alloc_send_skb(sk, blen, 1, &err); + if (!skb) { + err = -ENOMEM; + goto done; } + skb->dev = NULL; + skb_reserve(skb, blen); + err = afiucv_hs_send(NULL, sk, skb, AF_IUCV_FLAG_SYN); +done: + return err; +} - lock_sock(sk); - - /* Set the destination information */ - memcpy(iucv_sk(sk)->dst_user_id, sa->siucv_user_id, 8); - memcpy(iucv_sk(sk)->dst_name, sa->siucv_name, 8); +static int afiucv_path_connect(struct socket *sock, struct sockaddr *addr) +{ + struct sockaddr_iucv *sa = (struct sockaddr_iucv *) addr; + struct sock *sk = sock->sk; + struct iucv_sock *iucv = iucv_sk(sk); + unsigned char user_data[16]; + int err; high_nmcpy(user_data, sa->siucv_name); - low_nmcpy(user_data, iucv_sk(sk)->src_name); + low_nmcpy(user_data, iucv->src_name); ASCEBC(user_data, sizeof(user_data)); - iucv = iucv_sk(sk); /* Create path. */ iucv->path = iucv_path_alloc(iucv->msglimit, IUCV_IPRMDATA, GFP_KERNEL); @@ -704,8 +842,9 @@ static int iucv_sock_connect(struct socket *sock, struct sockaddr *addr, err = -ENOMEM; goto done; } - err = iucv_path_connect(iucv->path, &af_iucv_handler, - sa->siucv_user_id, NULL, user_data, sk); + err = pr_iucv->path_connect(iucv->path, &af_iucv_handler, + sa->siucv_user_id, NULL, user_data, + sk); if (err) { iucv_path_free(iucv->path); iucv->path = NULL; @@ -724,21 +863,62 @@ static int iucv_sock_connect(struct socket *sock, struct sockaddr *addr, err = -ECONNREFUSED; break; } - goto done; } +done: + return err; +} - if (sk->sk_state != IUCV_CONNECTED) { +/* Connect an unconnected socket */ +static int iucv_sock_connect(struct socket *sock, struct sockaddr *addr, + int alen, int flags) +{ + struct sockaddr_iucv *sa = (struct sockaddr_iucv *) addr; + struct sock *sk = sock->sk; + struct iucv_sock *iucv = iucv_sk(sk); + int err; + + if (addr->sa_family != AF_IUCV || alen < sizeof(struct sockaddr_iucv)) + return -EINVAL; + + if (sk->sk_state != IUCV_OPEN && sk->sk_state != IUCV_BOUND) + return -EBADFD; + + if (sk->sk_state == IUCV_OPEN && + iucv->transport == AF_IUCV_TRANS_HIPER) + return -EBADFD; /* explicit bind required */ + + if (sk->sk_type != SOCK_STREAM && sk->sk_type != SOCK_SEQPACKET) + return -EINVAL; + + if (sk->sk_state == IUCV_OPEN) { + err = iucv_sock_autobind(sk); + if (unlikely(err)) + return err; + } + + lock_sock(sk); + + /* Set the destination information */ + memcpy(iucv->dst_user_id, sa->siucv_user_id, 8); + memcpy(iucv->dst_name, sa->siucv_name, 8); + + if (iucv->transport == AF_IUCV_TRANS_HIPER) + err = afiucv_hs_connect(sock); + else + err = afiucv_path_connect(sock, addr); + if (err) + goto done; + + if (sk->sk_state != IUCV_CONNECTED) err = iucv_sock_wait(sk, iucv_sock_in_state(sk, IUCV_CONNECTED, IUCV_DISCONN), sock_sndtimeo(sk, flags & O_NONBLOCK)); - } - if (sk->sk_state == IUCV_DISCONN) { + if (sk->sk_state == IUCV_DISCONN || sk->sk_state == IUCV_CLOSED) err = -ECONNREFUSED; - } - if (err) { - iucv_path_sever(iucv->path, NULL); + if (err && iucv->transport == AF_IUCV_TRANS_IUCV) { + pr_iucv->path_sever(iucv->path, NULL); iucv_path_free(iucv->path); iucv->path = NULL; } @@ -833,20 +1013,21 @@ static int iucv_sock_getname(struct socket *sock, struct sockaddr *addr, { struct sockaddr_iucv *siucv = (struct sockaddr_iucv *) addr; struct sock *sk = sock->sk; + struct iucv_sock *iucv = iucv_sk(sk); addr->sa_family = AF_IUCV; *len = sizeof(struct sockaddr_iucv); if (peer) { - memcpy(siucv->siucv_user_id, iucv_sk(sk)->dst_user_id, 8); - memcpy(siucv->siucv_name, &iucv_sk(sk)->dst_name, 8); + memcpy(siucv->siucv_user_id, iucv->dst_user_id, 8); + memcpy(siucv->siucv_name, iucv->dst_name, 8); } else { - memcpy(siucv->siucv_user_id, iucv_sk(sk)->src_user_id, 8); - memcpy(siucv->siucv_name, iucv_sk(sk)->src_name, 8); + memcpy(siucv->siucv_user_id, iucv->src_user_id, 8); + memcpy(siucv->siucv_name, iucv->src_name, 8); } memset(&siucv->siucv_port, 0, sizeof(siucv->siucv_port)); memset(&siucv->siucv_addr, 0, sizeof(siucv->siucv_addr)); - memset(siucv->siucv_nodeid, 0, sizeof(siucv->siucv_nodeid)); + memset(&siucv->siucv_nodeid, 0, sizeof(siucv->siucv_nodeid)); return 0; } @@ -871,7 +1052,7 @@ static int iucv_send_iprm(struct iucv_path *path, struct iucv_message *msg, memcpy(prmdata, (void *) skb->data, skb->len); prmdata[7] = 0xff - (u8) skb->len; - return iucv_message_send(path, msg, IUCV_IPRMDATA, 0, + return pr_iucv->message_send(path, msg, IUCV_IPRMDATA, 0, (void *) prmdata, 8); } @@ -960,9 +1141,16 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, * this is fine for SOCK_SEQPACKET (unless we want to support * segmented records using the MSG_EOR flag), but * for SOCK_STREAM we might want to improve it in future */ - skb = sock_alloc_send_skb(sk, len, noblock, &err); + if (iucv->transport == AF_IUCV_TRANS_HIPER) + skb = sock_alloc_send_skb(sk, + len + sizeof(struct af_iucv_trans_hdr) + ETH_HLEN, + noblock, &err); + else + skb = sock_alloc_send_skb(sk, len, noblock, &err); if (!skb) goto out; + if (iucv->transport == AF_IUCV_TRANS_HIPER) + skb_reserve(skb, sizeof(struct af_iucv_trans_hdr) + ETH_HLEN); if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) { err = -EFAULT; goto fail; @@ -983,6 +1171,15 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, /* increment and save iucv message tag for msg_completion cbk */ txmsg.tag = iucv->send_tag++; memcpy(CB_TAG(skb), &txmsg.tag, CB_TAG_LEN); + if (iucv->transport == AF_IUCV_TRANS_HIPER) { + atomic_inc(&iucv->msg_sent); + err = afiucv_hs_send(&txmsg, sk, skb, 0); + if (err) { + atomic_dec(&iucv->msg_sent); + goto fail; + } + goto release; + } skb_queue_tail(&iucv->send_skb_q, skb); if (((iucv->path->flags & IUCV_IPRMDATA) & iucv->flags) @@ -999,13 +1196,13 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, /* this error should never happen since the * IUCV_IPRMDATA path flag is set... sever path */ if (err == 0x15) { - iucv_path_sever(iucv->path, NULL); + pr_iucv->path_sever(iucv->path, NULL); skb_unlink(skb, &iucv->send_skb_q); err = -EPIPE; goto fail; } } else - err = iucv_message_send(iucv->path, &txmsg, 0, 0, + err = pr_iucv->message_send(iucv->path, &txmsg, 0, 0, (void *) skb->data, skb->len); if (err) { if (err == 3) { @@ -1023,6 +1220,7 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, goto fail; } +release: release_sock(sk); return len; @@ -1095,8 +1293,9 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb, skb->len = 0; } } else { - rc = iucv_message_receive(path, msg, msg->flags & IUCV_IPRMDATA, - skb->data, len, NULL); + rc = pr_iucv->message_receive(path, msg, + msg->flags & IUCV_IPRMDATA, + skb->data, len, NULL); if (rc) { kfree_skb(skb); return; @@ -1110,7 +1309,7 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb, kfree_skb(skb); skb = NULL; if (rc) { - iucv_path_sever(path, NULL); + pr_iucv->path_sever(path, NULL); return; } skb = skb_dequeue(&iucv_sk(sk)->backlog_skb_q); @@ -1154,7 +1353,8 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct sock *sk = sock->sk; struct iucv_sock *iucv = iucv_sk(sk); unsigned int copied, rlen; - struct sk_buff *skb, *rskb, *cskb; + struct sk_buff *skb, *rskb, *cskb, *sskb; + int blen; int err = 0; if ((sk->sk_state == IUCV_DISCONN || sk->sk_state == IUCV_SEVERED) && @@ -1179,7 +1379,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, copied = min_t(unsigned int, rlen, len); cskb = skb; - if (memcpy_toiovec(msg->msg_iov, cskb->data, copied)) { + if (skb_copy_datagram_iovec(cskb, 0, msg->msg_iov, copied)) { if (!(flags & MSG_PEEK)) skb_queue_head(&sk->sk_receive_queue, skb); return -EFAULT; @@ -1217,6 +1417,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, } kfree_skb(skb); + atomic_inc(&iucv->msg_recv); /* Queue backlog skbs */ spin_lock_bh(&iucv->message_q.lock); @@ -1233,6 +1434,24 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (skb_queue_empty(&iucv->backlog_skb_q)) { if (!list_empty(&iucv->message_q.list)) iucv_process_message_q(sk); + if (atomic_read(&iucv->msg_recv) >= + iucv->msglimit / 2) { + /* send WIN to peer */ + blen = sizeof(struct af_iucv_trans_hdr) + + ETH_HLEN; + sskb = sock_alloc_send_skb(sk, blen, 1, &err); + if (sskb) { + skb_reserve(sskb, + sizeof(struct af_iucv_trans_hdr) + + ETH_HLEN); + err = afiucv_hs_send(NULL, sk, sskb, + AF_IUCV_FLAG_WIN); + } + if (err) { + sk->sk_state = IUCV_DISCONN; + sk->sk_state_change(sk); + } + } } spin_unlock_bh(&iucv->message_q.lock); } @@ -1327,8 +1546,8 @@ static int iucv_sock_shutdown(struct socket *sock, int how) if (how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) { txmsg.class = 0; txmsg.tag = 0; - err = iucv_message_send(iucv->path, &txmsg, IUCV_IPRMDATA, 0, - (void *) iprm_shutdown, 8); + err = pr_iucv->message_send(iucv->path, &txmsg, IUCV_IPRMDATA, + 0, (void *) iprm_shutdown, 8); if (err) { switch (err) { case 1: @@ -1345,7 +1564,7 @@ static int iucv_sock_shutdown(struct socket *sock, int how) } if (how == RCV_SHUTDOWN || how == SHUTDOWN_MASK) { - err = iucv_path_quiesce(iucv_sk(sk)->path, NULL); + err = pr_iucv->path_quiesce(iucv->path, NULL); if (err) err = -ENOTCONN; @@ -1372,7 +1591,7 @@ static int iucv_sock_release(struct socket *sock) /* Unregister with IUCV base support */ if (iucv_sk(sk)->path) { - iucv_path_sever(iucv_sk(sk)->path, NULL); + pr_iucv->path_sever(iucv_sk(sk)->path, NULL); iucv_path_free(iucv_sk(sk)->path); iucv_sk(sk)->path = NULL; } @@ -1514,14 +1733,14 @@ static int iucv_callback_connreq(struct iucv_path *path, high_nmcpy(user_data, iucv->dst_name); ASCEBC(user_data, sizeof(user_data)); if (sk->sk_state != IUCV_LISTEN) { - err = iucv_path_sever(path, user_data); + err = pr_iucv->path_sever(path, user_data); iucv_path_free(path); goto fail; } /* Check for backlog size */ if (sk_acceptq_is_full(sk)) { - err = iucv_path_sever(path, user_data); + err = pr_iucv->path_sever(path, user_data); iucv_path_free(path); goto fail; } @@ -1529,7 +1748,7 @@ static int iucv_callback_connreq(struct iucv_path *path, /* Create the new socket */ nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC); if (!nsk) { - err = iucv_path_sever(path, user_data); + err = pr_iucv->path_sever(path, user_data); iucv_path_free(path); goto fail; } @@ -1553,9 +1772,9 @@ static int iucv_callback_connreq(struct iucv_path *path, /* set message limit for path based on msglimit of accepting socket */ niucv->msglimit = iucv->msglimit; path->msglim = iucv->msglimit; - err = iucv_path_accept(path, &af_iucv_handler, nuser_data, nsk); + err = pr_iucv->path_accept(path, &af_iucv_handler, nuser_data, nsk); if (err) { - err = iucv_path_sever(path, user_data); + err = pr_iucv->path_sever(path, user_data); iucv_path_free(path); iucv_sock_kill(nsk); goto fail; @@ -1589,7 +1808,7 @@ static void iucv_callback_rx(struct iucv_path *path, struct iucv_message *msg) int len; if (sk->sk_shutdown & RCV_SHUTDOWN) { - iucv_message_reject(path, msg); + pr_iucv->message_reject(path, msg); return; } @@ -1600,7 +1819,7 @@ static void iucv_callback_rx(struct iucv_path *path, struct iucv_message *msg) goto save_message; len = atomic_read(&sk->sk_rmem_alloc); - len += iucv_msg_length(msg) + sizeof(struct sk_buff); + len += SKB_TRUESIZE(iucv_msg_length(msg)); if (len > sk->sk_rcvbuf) goto save_message; @@ -1692,6 +1911,389 @@ static void iucv_callback_shutdown(struct iucv_path *path, u8 ipuser[16]) bh_unlock_sock(sk); } +/***************** HiperSockets transport callbacks ********************/ +static void afiucv_swap_src_dest(struct sk_buff *skb) +{ + struct af_iucv_trans_hdr *trans_hdr = + (struct af_iucv_trans_hdr *)skb->data; + char tmpID[8]; + char tmpName[8]; + + ASCEBC(trans_hdr->destUserID, sizeof(trans_hdr->destUserID)); + ASCEBC(trans_hdr->destAppName, sizeof(trans_hdr->destAppName)); + ASCEBC(trans_hdr->srcUserID, sizeof(trans_hdr->srcUserID)); + ASCEBC(trans_hdr->srcAppName, sizeof(trans_hdr->srcAppName)); + memcpy(tmpID, trans_hdr->srcUserID, 8); + memcpy(tmpName, trans_hdr->srcAppName, 8); + memcpy(trans_hdr->srcUserID, trans_hdr->destUserID, 8); + memcpy(trans_hdr->srcAppName, trans_hdr->destAppName, 8); + memcpy(trans_hdr->destUserID, tmpID, 8); + memcpy(trans_hdr->destAppName, tmpName, 8); + skb_push(skb, ETH_HLEN); + memset(skb->data, 0, ETH_HLEN); +} + +/** + * afiucv_hs_callback_syn - react on received SYN + **/ +static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb) +{ + struct sock *nsk; + struct iucv_sock *iucv, *niucv; + struct af_iucv_trans_hdr *trans_hdr; + int err; + + iucv = iucv_sk(sk); + trans_hdr = (struct af_iucv_trans_hdr *)skb->data; + if (!iucv) { + /* no sock - connection refused */ + afiucv_swap_src_dest(skb); + trans_hdr->flags = AF_IUCV_FLAG_SYN | AF_IUCV_FLAG_FIN; + err = dev_queue_xmit(skb); + goto out; + } + + nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC); + bh_lock_sock(sk); + if ((sk->sk_state != IUCV_LISTEN) || + sk_acceptq_is_full(sk) || + !nsk) { + /* error on server socket - connection refused */ + if (nsk) + sk_free(nsk); + afiucv_swap_src_dest(skb); + trans_hdr->flags = AF_IUCV_FLAG_SYN | AF_IUCV_FLAG_FIN; + err = dev_queue_xmit(skb); + bh_unlock_sock(sk); + goto out; + } + + niucv = iucv_sk(nsk); + iucv_sock_init(nsk, sk); + niucv->transport = AF_IUCV_TRANS_HIPER; + niucv->msglimit = iucv->msglimit; + if (!trans_hdr->window) + niucv->msglimit_peer = IUCV_HIPER_MSGLIM_DEFAULT; + else + niucv->msglimit_peer = trans_hdr->window; + memcpy(niucv->dst_name, trans_hdr->srcAppName, 8); + memcpy(niucv->dst_user_id, trans_hdr->srcUserID, 8); + memcpy(niucv->src_name, iucv->src_name, 8); + memcpy(niucv->src_user_id, iucv->src_user_id, 8); + nsk->sk_bound_dev_if = sk->sk_bound_dev_if; + afiucv_swap_src_dest(skb); + trans_hdr->flags = AF_IUCV_FLAG_SYN | AF_IUCV_FLAG_ACK; + trans_hdr->window = niucv->msglimit; + /* if receiver acks the xmit connection is established */ + err = dev_queue_xmit(skb); + if (!err) { + iucv_accept_enqueue(sk, nsk); + nsk->sk_state = IUCV_CONNECTED; + sk->sk_data_ready(sk, 1); + } else + iucv_sock_kill(nsk); + bh_unlock_sock(sk); + +out: + return NET_RX_SUCCESS; +} + +/** + * afiucv_hs_callback_synack() - react on received SYN-ACK + **/ +static int afiucv_hs_callback_synack(struct sock *sk, struct sk_buff *skb) +{ + struct iucv_sock *iucv = iucv_sk(sk); + struct af_iucv_trans_hdr *trans_hdr = + (struct af_iucv_trans_hdr *)skb->data; + + if (!iucv) + goto out; + if (sk->sk_state != IUCV_BOUND) + goto out; + bh_lock_sock(sk); + iucv->msglimit_peer = trans_hdr->window; + sk->sk_state = IUCV_CONNECTED; + sk->sk_state_change(sk); + bh_unlock_sock(sk); +out: + kfree_skb(skb); + return NET_RX_SUCCESS; +} + +/** + * afiucv_hs_callback_synfin() - react on received SYN_FIN + **/ +static int afiucv_hs_callback_synfin(struct sock *sk, struct sk_buff *skb) +{ + struct iucv_sock *iucv = iucv_sk(sk); + + if (!iucv) + goto out; + if (sk->sk_state != IUCV_BOUND) + goto out; + bh_lock_sock(sk); + sk->sk_state = IUCV_DISCONN; + sk->sk_state_change(sk); + bh_unlock_sock(sk); +out: + kfree_skb(skb); + return NET_RX_SUCCESS; +} + +/** + * afiucv_hs_callback_fin() - react on received FIN + **/ +static int afiucv_hs_callback_fin(struct sock *sk, struct sk_buff *skb) +{ + struct iucv_sock *iucv = iucv_sk(sk); + + /* other end of connection closed */ + if (iucv) { + bh_lock_sock(sk); + if (!list_empty(&iucv->accept_q)) + sk->sk_state = IUCV_SEVERED; + else + sk->sk_state = IUCV_DISCONN; + sk->sk_state_change(sk); + bh_unlock_sock(sk); + } + kfree_skb(skb); + return NET_RX_SUCCESS; +} + +/** + * afiucv_hs_callback_win() - react on received WIN + **/ +static int afiucv_hs_callback_win(struct sock *sk, struct sk_buff *skb) +{ + struct iucv_sock *iucv = iucv_sk(sk); + struct af_iucv_trans_hdr *trans_hdr = + (struct af_iucv_trans_hdr *)skb->data; + + if (!iucv) + return NET_RX_SUCCESS; + + if (sk->sk_state != IUCV_CONNECTED) + return NET_RX_SUCCESS; + + atomic_sub(trans_hdr->window, &iucv->msg_sent); + iucv_sock_wake_msglim(sk); + return NET_RX_SUCCESS; +} + +/** + * afiucv_hs_callback_rx() - react on received data + **/ +static int afiucv_hs_callback_rx(struct sock *sk, struct sk_buff *skb) +{ + struct iucv_sock *iucv = iucv_sk(sk); + + if (!iucv) { + kfree_skb(skb); + return NET_RX_SUCCESS; + } + + if (sk->sk_state != IUCV_CONNECTED) { + kfree_skb(skb); + return NET_RX_SUCCESS; + } + + /* write stuff from iucv_msg to skb cb */ + if (skb->len <= sizeof(struct af_iucv_trans_hdr)) { + kfree_skb(skb); + return NET_RX_SUCCESS; + } + skb_pull(skb, sizeof(struct af_iucv_trans_hdr)); + skb_reset_transport_header(skb); + skb_reset_network_header(skb); + spin_lock(&iucv->message_q.lock); + if (skb_queue_empty(&iucv->backlog_skb_q)) { + if (sock_queue_rcv_skb(sk, skb)) { + /* handle rcv queue full */ + skb_queue_tail(&iucv->backlog_skb_q, skb); + } + } else + skb_queue_tail(&iucv_sk(sk)->backlog_skb_q, skb); + spin_unlock(&iucv->message_q.lock); + return NET_RX_SUCCESS; +} + +/** + * afiucv_hs_rcv() - base function for arriving data through HiperSockets + * transport + * called from netif RX softirq + **/ +static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + struct hlist_node *node; + struct sock *sk; + struct iucv_sock *iucv; + struct af_iucv_trans_hdr *trans_hdr; + char nullstring[8]; + int err = 0; + + skb_pull(skb, ETH_HLEN); + trans_hdr = (struct af_iucv_trans_hdr *)skb->data; + EBCASC(trans_hdr->destAppName, sizeof(trans_hdr->destAppName)); + EBCASC(trans_hdr->destUserID, sizeof(trans_hdr->destUserID)); + EBCASC(trans_hdr->srcAppName, sizeof(trans_hdr->srcAppName)); + EBCASC(trans_hdr->srcUserID, sizeof(trans_hdr->srcUserID)); + memset(nullstring, 0, sizeof(nullstring)); + iucv = NULL; + sk = NULL; + read_lock(&iucv_sk_list.lock); + sk_for_each(sk, node, &iucv_sk_list.head) { + if (trans_hdr->flags == AF_IUCV_FLAG_SYN) { + if ((!memcmp(&iucv_sk(sk)->src_name, + trans_hdr->destAppName, 8)) && + (!memcmp(&iucv_sk(sk)->src_user_id, + trans_hdr->destUserID, 8)) && + (!memcmp(&iucv_sk(sk)->dst_name, nullstring, 8)) && + (!memcmp(&iucv_sk(sk)->dst_user_id, + nullstring, 8))) { + iucv = iucv_sk(sk); + break; + } + } else { + if ((!memcmp(&iucv_sk(sk)->src_name, + trans_hdr->destAppName, 8)) && + (!memcmp(&iucv_sk(sk)->src_user_id, + trans_hdr->destUserID, 8)) && + (!memcmp(&iucv_sk(sk)->dst_name, + trans_hdr->srcAppName, 8)) && + (!memcmp(&iucv_sk(sk)->dst_user_id, + trans_hdr->srcUserID, 8))) { + iucv = iucv_sk(sk); + break; + } + } + } + read_unlock(&iucv_sk_list.lock); + if (!iucv) + sk = NULL; + + /* no sock + how should we send with no sock + 1) send without sock no send rc checking? + 2) introduce default sock to handle this cases + + SYN -> send SYN|ACK in good case, send SYN|FIN in bad case + data -> send FIN + SYN|ACK, SYN|FIN, FIN -> no action? */ + + switch (trans_hdr->flags) { + case AF_IUCV_FLAG_SYN: + /* connect request */ + err = afiucv_hs_callback_syn(sk, skb); + break; + case (AF_IUCV_FLAG_SYN | AF_IUCV_FLAG_ACK): + /* connect request confirmed */ + err = afiucv_hs_callback_synack(sk, skb); + break; + case (AF_IUCV_FLAG_SYN | AF_IUCV_FLAG_FIN): + /* connect request refused */ + err = afiucv_hs_callback_synfin(sk, skb); + break; + case (AF_IUCV_FLAG_FIN): + /* close request */ + err = afiucv_hs_callback_fin(sk, skb); + break; + case (AF_IUCV_FLAG_WIN): + err = afiucv_hs_callback_win(sk, skb); + if (skb->len > sizeof(struct af_iucv_trans_hdr)) + err = afiucv_hs_callback_rx(sk, skb); + else + kfree(skb); + break; + case 0: + /* plain data frame */ + err = afiucv_hs_callback_rx(sk, skb); + break; + default: + ; + } + + return err; +} + +/** + * afiucv_hs_callback_txnotify() - handle send notifcations from HiperSockets + * transport + **/ +static void afiucv_hs_callback_txnotify(struct sk_buff *skb, + enum iucv_tx_notify n) +{ + struct sock *isk = skb->sk; + struct sock *sk = NULL; + struct iucv_sock *iucv = NULL; + struct sk_buff_head *list; + struct sk_buff *list_skb; + struct sk_buff *this = NULL; + unsigned long flags; + struct hlist_node *node; + + read_lock(&iucv_sk_list.lock); + sk_for_each(sk, node, &iucv_sk_list.head) + if (sk == isk) { + iucv = iucv_sk(sk); + break; + } + read_unlock(&iucv_sk_list.lock); + + if (!iucv) + return; + + bh_lock_sock(sk); + list = &iucv->send_skb_q; + list_skb = list->next; + if (skb_queue_empty(list)) + goto out_unlock; + + spin_lock_irqsave(&list->lock, flags); + while (list_skb != (struct sk_buff *)list) { + if (skb_shinfo(list_skb) == skb_shinfo(skb)) { + this = list_skb; + switch (n) { + case TX_NOTIFY_OK: + __skb_unlink(this, list); + iucv_sock_wake_msglim(sk); + kfree_skb(this); + break; + case TX_NOTIFY_PENDING: + atomic_inc(&iucv->pendings); + break; + case TX_NOTIFY_DELAYED_OK: + __skb_unlink(this, list); + atomic_dec(&iucv->pendings); + if (atomic_read(&iucv->pendings) <= 0) + iucv_sock_wake_msglim(sk); + kfree_skb(this); + break; + case TX_NOTIFY_UNREACHABLE: + case TX_NOTIFY_DELAYED_UNREACHABLE: + case TX_NOTIFY_TPQFULL: /* not yet used */ + case TX_NOTIFY_GENERALERROR: + case TX_NOTIFY_DELAYED_GENERALERROR: + __skb_unlink(this, list); + kfree_skb(this); + if (!list_empty(&iucv->accept_q)) + sk->sk_state = IUCV_SEVERED; + else + sk->sk_state = IUCV_DISCONN; + sk->sk_state_change(sk); + break; + } + break; + } + list_skb = list_skb->next; + } + spin_unlock_irqrestore(&list->lock, flags); + +out_unlock: + bh_unlock_sock(sk); +} static const struct proto_ops iucv_sock_ops = { .family = PF_IUCV, .owner = THIS_MODULE, @@ -1718,71 +2320,104 @@ static const struct net_proto_family iucv_sock_family_ops = { .create = iucv_sock_create, }; -static int __init afiucv_init(void) +static struct packet_type iucv_packet_type = { + .type = cpu_to_be16(ETH_P_AF_IUCV), + .func = afiucv_hs_rcv, +}; + +static int afiucv_iucv_init(void) { int err; - if (!MACHINE_IS_VM) { - pr_err("The af_iucv module cannot be loaded" - " without z/VM\n"); - err = -EPROTONOSUPPORT; - goto out; - } - cpcmd("QUERY USERID", iucv_userid, sizeof(iucv_userid), &err); - if (unlikely(err)) { - WARN_ON(err); - err = -EPROTONOSUPPORT; - goto out; - } - - err = iucv_register(&af_iucv_handler, 0); + err = pr_iucv->iucv_register(&af_iucv_handler, 0); if (err) goto out; - err = proto_register(&iucv_proto, 0); - if (err) - goto out_iucv; - err = sock_register(&iucv_sock_family_ops); - if (err) - goto out_proto; /* establish dummy device */ + af_iucv_driver.bus = pr_iucv->bus; err = driver_register(&af_iucv_driver); if (err) - goto out_sock; + goto out_iucv; af_iucv_dev = kzalloc(sizeof(struct device), GFP_KERNEL); if (!af_iucv_dev) { err = -ENOMEM; goto out_driver; } dev_set_name(af_iucv_dev, "af_iucv"); - af_iucv_dev->bus = &iucv_bus; - af_iucv_dev->parent = iucv_root; + af_iucv_dev->bus = pr_iucv->bus; + af_iucv_dev->parent = pr_iucv->root; af_iucv_dev->release = (void (*)(struct device *))kfree; af_iucv_dev->driver = &af_iucv_driver; err = device_register(af_iucv_dev); if (err) goto out_driver; - return 0; out_driver: driver_unregister(&af_iucv_driver); +out_iucv: + pr_iucv->iucv_unregister(&af_iucv_handler, 0); +out: + return err; +} + +static int __init afiucv_init(void) +{ + int err; + + if (MACHINE_IS_VM) { + cpcmd("QUERY USERID", iucv_userid, sizeof(iucv_userid), &err); + if (unlikely(err)) { + WARN_ON(err); + err = -EPROTONOSUPPORT; + goto out; + } + + pr_iucv = try_then_request_module(symbol_get(iucv_if), "iucv"); + if (!pr_iucv) { + printk(KERN_WARNING "iucv_if lookup failed\n"); + memset(&iucv_userid, 0, sizeof(iucv_userid)); + } + } else { + memset(&iucv_userid, 0, sizeof(iucv_userid)); + pr_iucv = NULL; + } + + err = proto_register(&iucv_proto, 0); + if (err) + goto out; + err = sock_register(&iucv_sock_family_ops); + if (err) + goto out_proto; + + if (pr_iucv) { + err = afiucv_iucv_init(); + if (err) + goto out_sock; + } + dev_add_pack(&iucv_packet_type); + return 0; + out_sock: sock_unregister(PF_IUCV); out_proto: proto_unregister(&iucv_proto); -out_iucv: - iucv_unregister(&af_iucv_handler, 0); out: + if (pr_iucv) + symbol_put(iucv_if); return err; } static void __exit afiucv_exit(void) { - device_unregister(af_iucv_dev); - driver_unregister(&af_iucv_driver); + if (pr_iucv) { + device_unregister(af_iucv_dev); + driver_unregister(&af_iucv_driver); + pr_iucv->iucv_unregister(&af_iucv_handler, 0); + symbol_put(iucv_if); + } + dev_remove_pack(&iucv_packet_type); sock_unregister(PF_IUCV); proto_unregister(&iucv_proto); - iucv_unregister(&af_iucv_handler, 0); } module_init(afiucv_init); @@ -1793,3 +2428,4 @@ MODULE_DESCRIPTION("IUCV Sockets ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_IUCV); + diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 075a380..403be43 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -1974,6 +1974,27 @@ out: return rc; } +struct iucv_interface iucv_if = { + .message_receive = iucv_message_receive, + .__message_receive = __iucv_message_receive, + .message_reply = iucv_message_reply, + .message_reject = iucv_message_reject, + .message_send = iucv_message_send, + .__message_send = __iucv_message_send, + .message_send2way = iucv_message_send2way, + .message_purge = iucv_message_purge, + .path_accept = iucv_path_accept, + .path_connect = iucv_path_connect, + .path_quiesce = iucv_path_quiesce, + .path_resume = iucv_path_resume, + .path_sever = iucv_path_sever, + .iucv_register = iucv_register, + .iucv_unregister = iucv_unregister, + .bus = NULL, + .root = NULL, +}; +EXPORT_SYMBOL(iucv_if); + /** * iucv_init * @@ -2038,6 +2059,8 @@ static int __init iucv_init(void) rc = bus_register(&iucv_bus); if (rc) goto out_reboot; + iucv_if.root = iucv_root; + iucv_if.bus = &iucv_bus; return 0; out_reboot: diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index ad4ac26..bf8d50c 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -397,6 +397,7 @@ static void l2tp_recv_dequeue(struct l2tp_session *session) * expect to send up next, dequeue it and any other * in-sequence packets behind it. */ +start: spin_lock_bh(&session->reorder_q.lock); skb_queue_walk_safe(&session->reorder_q, skb, tmp) { if (time_after(jiffies, L2TP_SKB_CB(skb)->expires)) { @@ -433,7 +434,7 @@ static void l2tp_recv_dequeue(struct l2tp_session *session) */ spin_unlock_bh(&session->reorder_q.lock); l2tp_recv_dequeue_skb(session, skb); - spin_lock_bh(&session->reorder_q.lock); + goto start; } out: @@ -1045,8 +1046,10 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len headroom = NET_SKB_PAD + sizeof(struct iphdr) + uhlen + hdr_len; old_headroom = skb_headroom(skb); - if (skb_cow_head(skb, headroom)) + if (skb_cow_head(skb, headroom)) { + dev_kfree_skb(skb); goto abort; + } new_headroom = skb_headroom(skb); skb_orphan(skb); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index f42cd09..8a90d75 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -395,6 +395,7 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) struct pppol2tp_session *ps; int old_headroom; int new_headroom; + int uhlen, headroom; if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) goto abort; @@ -413,7 +414,13 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) goto abort_put_sess; old_headroom = skb_headroom(skb); - if (skb_cow_head(skb, sizeof(ppph))) + uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; + headroom = NET_SKB_PAD + + sizeof(struct iphdr) + /* IP header */ + uhlen + /* UDP header (if L2TP_ENCAPTYPE_UDP) */ + session->hdr_len + /* L2TP header */ + sizeof(ppph); /* PPP header */ + if (skb_cow_head(skb, headroom)) goto abort_put_sess_tun; new_headroom = skb_headroom(skb); diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index 956b7e4..8d0324b 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -139,7 +139,8 @@ out: return lapb; } -int lapb_register(struct net_device *dev, struct lapb_register_struct *callbacks) +int lapb_register(struct net_device *dev, + const struct lapb_register_struct *callbacks) { struct lapb_cb *lapb; int rc = LAPB_BADTOKEN; @@ -158,7 +159,7 @@ int lapb_register(struct net_device *dev, struct lapb_register_struct *callbacks goto out; lapb->dev = dev; - lapb->callbacks = *callbacks; + lapb->callbacks = callbacks; __lapb_insert_cb(lapb); @@ -380,32 +381,32 @@ int lapb_data_received(struct net_device *dev, struct sk_buff *skb) void lapb_connect_confirmation(struct lapb_cb *lapb, int reason) { - if (lapb->callbacks.connect_confirmation) - lapb->callbacks.connect_confirmation(lapb->dev, reason); + if (lapb->callbacks->connect_confirmation) + lapb->callbacks->connect_confirmation(lapb->dev, reason); } void lapb_connect_indication(struct lapb_cb *lapb, int reason) { - if (lapb->callbacks.connect_indication) - lapb->callbacks.connect_indication(lapb->dev, reason); + if (lapb->callbacks->connect_indication) + lapb->callbacks->connect_indication(lapb->dev, reason); } void lapb_disconnect_confirmation(struct lapb_cb *lapb, int reason) { - if (lapb->callbacks.disconnect_confirmation) - lapb->callbacks.disconnect_confirmation(lapb->dev, reason); + if (lapb->callbacks->disconnect_confirmation) + lapb->callbacks->disconnect_confirmation(lapb->dev, reason); } void lapb_disconnect_indication(struct lapb_cb *lapb, int reason) { - if (lapb->callbacks.disconnect_indication) - lapb->callbacks.disconnect_indication(lapb->dev, reason); + if (lapb->callbacks->disconnect_indication) + lapb->callbacks->disconnect_indication(lapb->dev, reason); } int lapb_data_indication(struct lapb_cb *lapb, struct sk_buff *skb) { - if (lapb->callbacks.data_indication) - return lapb->callbacks.data_indication(lapb->dev, skb); + if (lapb->callbacks->data_indication) + return lapb->callbacks->data_indication(lapb->dev, skb); kfree_skb(skb); return NET_RX_SUCCESS; /* For now; must be != NET_RX_DROP */ @@ -415,8 +416,8 @@ int lapb_data_transmit(struct lapb_cb *lapb, struct sk_buff *skb) { int used = 0; - if (lapb->callbacks.data_transmit) { - lapb->callbacks.data_transmit(lapb->dev, skb); + if (lapb->callbacks->data_transmit) { + lapb->callbacks->data_transmit(lapb->dev, skb); used = 1; } diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index f5fdfcb..7d3b438 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -199,6 +199,19 @@ config MAC80211_VERBOSE_MPL_DEBUG Do not select this option. +config MAC80211_VERBOSE_MPATH_DEBUG + bool "Verbose mesh path debugging" + depends on MAC80211_DEBUG_MENU + depends on MAC80211_MESH + ---help--- + Selecting this option causes mac80211 to print out very + verbose mesh path selection debugging messages (when mac80211 + is taking part in a mesh network). + It should not be selected on production systems as those + messages are remotely triggerable. + + Do not select this option. + config MAC80211_VERBOSE_MHWMP_DEBUG bool "Verbose mesh HWMP routing debugging" depends on MAC80211_DEBUG_MENU @@ -212,6 +225,18 @@ config MAC80211_VERBOSE_MHWMP_DEBUG Do not select this option. +config MAC80211_VERBOSE_TDLS_DEBUG + bool "Verbose TDLS debugging" + depends on MAC80211_DEBUG_MENU + ---help--- + Selecting this option causes mac80211 to print out very + verbose TDLS selection debugging messages (when mac80211 + is a TDLS STA). + It should not be selected on production systems as those + messages are remotely triggerable. + + Do not select this option. + config MAC80211_DEBUG_COUNTERS bool "Extra statistics for TX/RX debugging" depends on MAC80211_DEBUG_MENU diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index fd1aaf2..97f3358 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -69,7 +69,7 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, if (!tid_rx) return; - rcu_assign_pointer(sta->ampdu_mlme.tid_rx[tid], NULL); + RCU_INIT_POINTER(sta->ampdu_mlme.tid_rx[tid], NULL); #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "Rx BA session stop requested for %pM tid %u\n", @@ -167,12 +167,8 @@ static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *d u16 capab; skb = dev_alloc_skb(sizeof(*mgmt) + local->hw.extra_tx_headroom); - - if (!skb) { - printk(KERN_DEBUG "%s: failed to allocate buffer " - "for addba resp frame\n", sdata->name); + if (!skb) return; - } skb_reserve(skb, local->hw.extra_tx_headroom); mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24); @@ -227,7 +223,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, status = WLAN_STATUS_REQUEST_DECLINED; - if (test_sta_flags(sta, WLAN_STA_BLOCK_BA)) { + if (test_sta_flag(sta, WLAN_STA_BLOCK_BA)) { #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "Suspend in progress. " "Denying ADDBA request\n"); @@ -279,14 +275,8 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, /* prepare A-MPDU MLME for Rx aggregation */ tid_agg_rx = kmalloc(sizeof(struct tid_ampdu_rx), GFP_KERNEL); - if (!tid_agg_rx) { -#ifdef CONFIG_MAC80211_HT_DEBUG - if (net_ratelimit()) - printk(KERN_ERR "allocate rx mlme to tid %d failed\n", - tid); -#endif + if (!tid_agg_rx) goto end; - } spin_lock_init(&tid_agg_rx->reorder_lock); @@ -306,11 +296,6 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, tid_agg_rx->reorder_time = kcalloc(buf_size, sizeof(unsigned long), GFP_KERNEL); if (!tid_agg_rx->reorder_buf || !tid_agg_rx->reorder_time) { -#ifdef CONFIG_MAC80211_HT_DEBUG - if (net_ratelimit()) - printk(KERN_ERR "can not allocate reordering buffer " - "to tid %d\n", tid); -#endif kfree(tid_agg_rx->reorder_buf); kfree(tid_agg_rx->reorder_time); kfree(tid_agg_rx); @@ -340,7 +325,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, status = WLAN_STATUS_SUCCESS; /* activate it for RX */ - rcu_assign_pointer(sta->ampdu_mlme.tid_rx[tid], tid_agg_rx); + RCU_INIT_POINTER(sta->ampdu_mlme.tid_rx[tid], tid_agg_rx); if (timeout) mod_timer(&tid_agg_rx->session_timer, TU_TO_EXP_TIME(timeout)); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index c8be8ef..2ac0339 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -68,11 +68,9 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata, skb = dev_alloc_skb(sizeof(*mgmt) + local->hw.extra_tx_headroom); - if (!skb) { - printk(KERN_ERR "%s: failed to allocate buffer " - "for addba request frame\n", sdata->name); + if (!skb) return; - } + skb_reserve(skb, local->hw.extra_tx_headroom); mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24); memset(mgmt, 0, 24); @@ -106,19 +104,18 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata, ieee80211_tx_skb(sdata, skb); } -void ieee80211_send_bar(struct ieee80211_sub_if_data *sdata, u8 *ra, u16 tid, u16 ssn) +void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn) { + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_bar *bar; u16 bar_control = 0; skb = dev_alloc_skb(sizeof(*bar) + local->hw.extra_tx_headroom); - if (!skb) { - printk(KERN_ERR "%s: failed to allocate buffer for " - "bar frame\n", sdata->name); + if (!skb) return; - } + skb_reserve(skb, local->hw.extra_tx_headroom); bar = (struct ieee80211_bar *)skb_put(skb, sizeof(*bar)); memset(bar, 0, sizeof(*bar)); @@ -128,13 +125,14 @@ void ieee80211_send_bar(struct ieee80211_sub_if_data *sdata, u8 *ra, u16 tid, u1 memcpy(bar->ta, sdata->vif.addr, ETH_ALEN); bar_control |= (u16)IEEE80211_BAR_CTRL_ACK_POLICY_NORMAL; bar_control |= (u16)IEEE80211_BAR_CTRL_CBMTID_COMPRESSED_BA; - bar_control |= (u16)(tid << 12); + bar_control |= (u16)(tid << IEEE80211_BAR_CTRL_TID_INFO_SHIFT); bar->control = cpu_to_le16(bar_control); bar->start_seq_num = cpu_to_le16(ssn); IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; ieee80211_tx_skb(sdata, skb); } +EXPORT_SYMBOL(ieee80211_send_bar); void ieee80211_assign_tid_tx(struct sta_info *sta, int tid, struct tid_ampdu_tx *tid_tx) @@ -364,7 +362,8 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, return -EINVAL; if ((tid >= STA_TID_NUM) || - !(local->hw.flags & IEEE80211_HW_AMPDU_AGGREGATION)) + !(local->hw.flags & IEEE80211_HW_AMPDU_AGGREGATION) || + (local->hw.flags & IEEE80211_HW_TX_AMPDU_SETUP_IN_HW)) return -EINVAL; #ifdef CONFIG_MAC80211_HT_DEBUG @@ -383,7 +382,7 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, sdata->vif.type != NL80211_IFTYPE_AP) return -EINVAL; - if (test_sta_flags(sta, WLAN_STA_BLOCK_BA)) { + if (test_sta_flag(sta, WLAN_STA_BLOCK_BA)) { #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "BA sessions blocked. " "Denying BA session request\n"); @@ -413,11 +412,6 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, /* prepare A-MPDU MLME for Tx aggregation */ tid_tx = kzalloc(sizeof(struct tid_ampdu_tx), GFP_ATOMIC); if (!tid_tx) { -#ifdef CONFIG_MAC80211_HT_DEBUG - if (net_ratelimit()) - printk(KERN_ERR "allocate tx mlme to tid %d failed\n", - tid); -#endif ret = -ENOMEM; goto err_unlock_sta; } @@ -574,14 +568,9 @@ void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, struct ieee80211_ra_tid *ra_tid; struct sk_buff *skb = dev_alloc_skb(0); - if (unlikely(!skb)) { -#ifdef CONFIG_MAC80211_HT_DEBUG - if (net_ratelimit()) - printk(KERN_WARNING "%s: Not enough memory, " - "dropping start BA session", sdata->name); -#endif + if (unlikely(!skb)) return; - } + ra_tid = (struct ieee80211_ra_tid *) &skb->cb; memcpy(&ra_tid->ra, ra, ETH_ALEN); ra_tid->tid = tid; @@ -727,14 +716,9 @@ void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, struct ieee80211_ra_tid *ra_tid; struct sk_buff *skb = dev_alloc_skb(0); - if (unlikely(!skb)) { -#ifdef CONFIG_MAC80211_HT_DEBUG - if (net_ratelimit()) - printk(KERN_WARNING "%s: Not enough memory, " - "dropping stop BA session", sdata->name); -#endif + if (unlikely(!skb)) return; - } + ra_tid = (struct ieee80211_ra_tid *) &skb->cb; memcpy(&ra_tid->ra, ra, ETH_ALEN); ra_tid->tid = tid; @@ -777,18 +761,14 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "switched off addBA timer for tid %d\n", tid); #endif - + /* + * IEEE 802.11-2007 7.3.1.14: + * In an ADDBA Response frame, when the Status Code field + * is set to 0, the Buffer Size subfield is set to a value + * of at least 1. + */ if (le16_to_cpu(mgmt->u.action.u.addba_resp.status) - == WLAN_STATUS_SUCCESS) { - /* - * IEEE 802.11-2007 7.3.1.14: - * In an ADDBA Response frame, when the Status Code field - * is set to 0, the Buffer Size subfield is set to a value - * of at least 1. - */ - if (!buf_size) - goto out; - + == WLAN_STATUS_SUCCESS && buf_size) { if (test_and_set_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state)) { /* ignore duplicate response */ diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 3d1b091..ebd7fb1 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -12,6 +12,7 @@ #include <linux/slab.h> #include <net/net_namespace.h> #include <linux/rcupdate.h> +#include <linux/if_ether.h> #include <net/cfg80211.h> #include "ieee80211_i.h" #include "driver-ops.h" @@ -62,7 +63,7 @@ static int ieee80211_change_iface(struct wiphy *wiphy, if (type == NL80211_IFTYPE_AP_VLAN && params && params->use_4addr == 0) - rcu_assign_pointer(sdata->u.vlan.sta, NULL); + RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); else if (type == NL80211_IFTYPE_STATION && params && params->use_4addr >= 0) sdata->u.mgd.use_4addr = params->use_4addr; @@ -343,7 +344,8 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) STATION_INFO_RX_BITRATE | STATION_INFO_RX_DROP_MISC | STATION_INFO_BSS_PARAM | - STATION_INFO_CONNECTED_TIME; + STATION_INFO_CONNECTED_TIME | + STATION_INFO_STA_FLAGS; do_posix_clock_monotonic_gettime(&uptime); sinfo->connected_time = uptime.tv_sec - sta->last_connected; @@ -403,6 +405,23 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) sinfo->bss_param.flags |= BSS_PARAM_FLAGS_SHORT_SLOT_TIME; sinfo->bss_param.dtim_period = sdata->local->hw.conf.ps_dtim_period; sinfo->bss_param.beacon_interval = sdata->vif.bss_conf.beacon_int; + + sinfo->sta_flags.set = 0; + sinfo->sta_flags.mask = BIT(NL80211_STA_FLAG_AUTHORIZED) | + BIT(NL80211_STA_FLAG_SHORT_PREAMBLE) | + BIT(NL80211_STA_FLAG_WME) | + BIT(NL80211_STA_FLAG_MFP) | + BIT(NL80211_STA_FLAG_AUTHENTICATED); + if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_AUTHORIZED); + if (test_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE)) + sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_SHORT_PREAMBLE); + if (test_sta_flag(sta, WLAN_STA_WME)) + sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_WME); + if (test_sta_flag(sta, WLAN_STA_MFP)) + sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_MFP); + if (test_sta_flag(sta, WLAN_STA_AUTH)) + sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_AUTHENTICATED); } @@ -455,6 +474,20 @@ static int ieee80211_get_station(struct wiphy *wiphy, struct net_device *dev, return ret; } +static void ieee80211_config_ap_ssid(struct ieee80211_sub_if_data *sdata, + struct beacon_parameters *params) +{ + struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; + + bss_conf->ssid_len = params->ssid_len; + + if (params->ssid_len) + memcpy(bss_conf->ssid, params->ssid, params->ssid_len); + + bss_conf->hidden_ssid = + (params->hidden_ssid != NL80211_HIDDEN_SSID_NOT_IN_USE); +} + /* * This handles both adding a beacon and setting new beacon info */ @@ -542,14 +575,17 @@ static int ieee80211_config_beacon(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.dtim_period = new->dtim_period; - rcu_assign_pointer(sdata->u.ap.beacon, new); + RCU_INIT_POINTER(sdata->u.ap.beacon, new); synchronize_rcu(); kfree(old); + ieee80211_config_ap_ssid(sdata, params); + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED | - BSS_CHANGED_BEACON); + BSS_CHANGED_BEACON | + BSS_CHANGED_SSID); return 0; } @@ -594,7 +630,7 @@ static int ieee80211_del_beacon(struct wiphy *wiphy, struct net_device *dev) if (!old) return -ENOENT; - rcu_assign_pointer(sdata->u.ap.beacon, NULL); + RCU_INIT_POINTER(sdata->u.ap.beacon, NULL); synchronize_rcu(); kfree(old); @@ -650,7 +686,6 @@ static void sta_apply_parameters(struct ieee80211_local *local, struct sta_info *sta, struct station_parameters *params) { - unsigned long flags; u32 rates; int i, j; struct ieee80211_supported_band *sband; @@ -659,43 +694,58 @@ static void sta_apply_parameters(struct ieee80211_local *local, sband = local->hw.wiphy->bands[local->oper_channel->band]; - spin_lock_irqsave(&sta->flaglock, flags); mask = params->sta_flags_mask; set = params->sta_flags_set; if (mask & BIT(NL80211_STA_FLAG_AUTHORIZED)) { - sta->flags &= ~WLAN_STA_AUTHORIZED; if (set & BIT(NL80211_STA_FLAG_AUTHORIZED)) - sta->flags |= WLAN_STA_AUTHORIZED; + set_sta_flag(sta, WLAN_STA_AUTHORIZED); + else + clear_sta_flag(sta, WLAN_STA_AUTHORIZED); } if (mask & BIT(NL80211_STA_FLAG_SHORT_PREAMBLE)) { - sta->flags &= ~WLAN_STA_SHORT_PREAMBLE; if (set & BIT(NL80211_STA_FLAG_SHORT_PREAMBLE)) - sta->flags |= WLAN_STA_SHORT_PREAMBLE; + set_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE); + else + clear_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE); } if (mask & BIT(NL80211_STA_FLAG_WME)) { - sta->flags &= ~WLAN_STA_WME; - sta->sta.wme = false; if (set & BIT(NL80211_STA_FLAG_WME)) { - sta->flags |= WLAN_STA_WME; + set_sta_flag(sta, WLAN_STA_WME); sta->sta.wme = true; + } else { + clear_sta_flag(sta, WLAN_STA_WME); + sta->sta.wme = false; } } if (mask & BIT(NL80211_STA_FLAG_MFP)) { - sta->flags &= ~WLAN_STA_MFP; if (set & BIT(NL80211_STA_FLAG_MFP)) - sta->flags |= WLAN_STA_MFP; + set_sta_flag(sta, WLAN_STA_MFP); + else + clear_sta_flag(sta, WLAN_STA_MFP); } if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED)) { - sta->flags &= ~WLAN_STA_AUTH; if (set & BIT(NL80211_STA_FLAG_AUTHENTICATED)) - sta->flags |= WLAN_STA_AUTH; + set_sta_flag(sta, WLAN_STA_AUTH); + else + clear_sta_flag(sta, WLAN_STA_AUTH); + } + + if (mask & BIT(NL80211_STA_FLAG_TDLS_PEER)) { + if (set & BIT(NL80211_STA_FLAG_TDLS_PEER)) + set_sta_flag(sta, WLAN_STA_TDLS_PEER); + else + clear_sta_flag(sta, WLAN_STA_TDLS_PEER); + } + + if (params->sta_modify_mask & STATION_PARAM_APPLY_UAPSD) { + sta->sta.uapsd_queues = params->uapsd_queues; + sta->sta.max_sp = params->max_sp; } - spin_unlock_irqrestore(&sta->flaglock, flags); /* * cfg80211 validates this (1-2007) and allows setting the AID @@ -786,10 +836,17 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, if (!sta) return -ENOMEM; - sta->flags = WLAN_STA_AUTH | WLAN_STA_ASSOC; + set_sta_flag(sta, WLAN_STA_AUTH); + set_sta_flag(sta, WLAN_STA_ASSOC); sta_apply_parameters(local, sta, params); + /* Only TDLS-supporting stations can add TDLS peers */ + if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && + !((wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS) && + sdata->vif.type == NL80211_IFTYPE_STATION)) + return -ENOTSUPP; + rate_control_rate_init(sta); layer2_update = sdata->vif.type == NL80211_IFTYPE_AP_VLAN || @@ -842,6 +899,14 @@ static int ieee80211_change_station(struct wiphy *wiphy, return -ENOENT; } + /* The TDLS bit cannot be toggled after the STA was added */ + if ((params->sta_flags_mask & BIT(NL80211_STA_FLAG_TDLS_PEER)) && + !!(params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)) != + !!test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { + rcu_read_unlock(); + return -EINVAL; + } + if (params->vlan && params->vlan != sta->sdata->dev) { vlansdata = IEEE80211_DEV_TO_SUB_IF(params->vlan); @@ -857,7 +922,7 @@ static int ieee80211_change_station(struct wiphy *wiphy, return -EBUSY; } - rcu_assign_pointer(vlansdata->u.vlan.sta, sta); + RCU_INIT_POINTER(vlansdata->u.vlan.sta, sta); } sta->sdata = vlansdata; @@ -918,7 +983,7 @@ static int ieee80211_del_mpath(struct wiphy *wiphy, struct net_device *dev, if (dst) return mesh_path_del(dst, sdata); - mesh_path_flush(sdata); + mesh_path_flush_by_iface(sdata); return 0; } @@ -1137,6 +1202,22 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy, conf->dot11MeshHWMPRootMode = nconf->dot11MeshHWMPRootMode; ieee80211_mesh_root_setup(ifmsh); } + if (_chg_mesh_attr(NL80211_MESHCONF_GATE_ANNOUNCEMENTS, mask)) { + /* our current gate announcement implementation rides on root + * announcements, so require this ifmsh to also be a root node + * */ + if (nconf->dot11MeshGateAnnouncementProtocol && + !conf->dot11MeshHWMPRootMode) { + conf->dot11MeshHWMPRootMode = 1; + ieee80211_mesh_root_setup(ifmsh); + } + conf->dot11MeshGateAnnouncementProtocol = + nconf->dot11MeshGateAnnouncementProtocol; + } + if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_RANN_INTERVAL, mask)) { + conf->dot11MeshHWMPRannInterval = + nconf->dot11MeshHWMPRannInterval; + } return 0; } @@ -1235,9 +1316,11 @@ static int ieee80211_change_bss(struct wiphy *wiphy, } static int ieee80211_set_txq_params(struct wiphy *wiphy, + struct net_device *dev, struct ieee80211_txq_params *params) { struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_tx_queue_params p; if (!local->ops->conf_tx) @@ -1258,8 +1341,8 @@ static int ieee80211_set_txq_params(struct wiphy *wiphy, if (params->queue >= local->hw.queues) return -EINVAL; - local->tx_conf[params->queue] = p; - if (drv_conf_tx(local, params->queue, &p)) { + sdata->tx_conf[params->queue] = p; + if (drv_conf_tx(local, sdata, params->queue, &p)) { wiphy_debug(local->hw.wiphy, "failed to set TX queue parameters for queue %d\n", params->queue); @@ -1821,7 +1904,7 @@ ieee80211_offchan_tx_done(struct ieee80211_work *wk, struct sk_buff *skb) * so in that case userspace will have to deal with it. */ - if (wk->offchan_tx.wait && wk->offchan_tx.frame) + if (wk->offchan_tx.wait && !wk->offchan_tx.status) cfg80211_mgmt_tx_status(wk->sdata->dev, (unsigned long) wk->offchan_tx.frame, wk->ie, wk->ie_len, false, GFP_KERNEL); @@ -1833,7 +1916,8 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_channel *chan, bool offchan, enum nl80211_channel_type channel_type, bool channel_type_valid, unsigned int wait, - const u8 *buf, size_t len, u64 *cookie) + const u8 *buf, size_t len, bool no_cck, + u64 *cookie) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; @@ -1860,6 +1944,9 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, flags |= IEEE80211_TX_CTL_TX_OFFCHAN; } + if (no_cck) + flags |= IEEE80211_TX_CTL_NO_CCK_RATE; + if (is_offchan && !offchan) return -EBUSY; @@ -1898,33 +1985,6 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, *cookie = (unsigned long) skb; - if (is_offchan && local->ops->offchannel_tx) { - int ret; - - IEEE80211_SKB_CB(skb)->band = chan->band; - - mutex_lock(&local->mtx); - - if (local->hw_offchan_tx_cookie) { - mutex_unlock(&local->mtx); - return -EBUSY; - } - - /* TODO: bitrate control, TX processing? */ - ret = drv_offchannel_tx(local, skb, chan, channel_type, wait); - - if (ret == 0) - local->hw_offchan_tx_cookie = *cookie; - mutex_unlock(&local->mtx); - - /* - * Allow driver to return 1 to indicate it wants to have the - * frame transmitted with a remain_on_channel + regular TX. - */ - if (ret != 1) - return ret; - } - if (is_offchan && local->ops->remain_on_channel) { unsigned int duration; int ret; @@ -2011,18 +2071,6 @@ static int ieee80211_mgmt_tx_cancel_wait(struct wiphy *wiphy, mutex_lock(&local->mtx); - if (local->ops->offchannel_tx_cancel_wait && - local->hw_offchan_tx_cookie == cookie) { - ret = drv_offchannel_tx_cancel_wait(local); - - if (!ret) - local->hw_offchan_tx_cookie = 0; - - mutex_unlock(&local->mtx); - - return ret; - } - if (local->ops->cancel_remain_on_channel) { cookie ^= 2; ret = ieee80211_cancel_remain_on_channel_hw(local, cookie); @@ -2123,6 +2171,323 @@ static int ieee80211_set_rekey_data(struct wiphy *wiphy, return 0; } +static void ieee80211_tdls_add_ext_capab(struct sk_buff *skb) +{ + u8 *pos = (void *)skb_put(skb, 7); + + *pos++ = WLAN_EID_EXT_CAPABILITY; + *pos++ = 5; /* len */ + *pos++ = 0x0; + *pos++ = 0x0; + *pos++ = 0x0; + *pos++ = 0x0; + *pos++ = WLAN_EXT_CAPA5_TDLS_ENABLED; +} + +static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + u16 capab; + + capab = 0; + if (local->oper_channel->band != IEEE80211_BAND_2GHZ) + return capab; + + if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE)) + capab |= WLAN_CAPABILITY_SHORT_SLOT_TIME; + if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_PREAMBLE_INCAPABLE)) + capab |= WLAN_CAPABILITY_SHORT_PREAMBLE; + + return capab; +} + +static void ieee80211_tdls_add_link_ie(struct sk_buff *skb, u8 *src_addr, + u8 *peer, u8 *bssid) +{ + struct ieee80211_tdls_lnkie *lnkid; + + lnkid = (void *)skb_put(skb, sizeof(struct ieee80211_tdls_lnkie)); + + lnkid->ie_type = WLAN_EID_LINK_ID; + lnkid->ie_len = sizeof(struct ieee80211_tdls_lnkie) - 2; + + memcpy(lnkid->bssid, bssid, ETH_ALEN); + memcpy(lnkid->init_sta, src_addr, ETH_ALEN); + memcpy(lnkid->resp_sta, peer, ETH_ALEN); +} + +static int +ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, + u8 *peer, u8 action_code, u8 dialog_token, + u16 status_code, struct sk_buff *skb) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_tdls_data *tf; + + tf = (void *)skb_put(skb, offsetof(struct ieee80211_tdls_data, u)); + + memcpy(tf->da, peer, ETH_ALEN); + memcpy(tf->sa, sdata->vif.addr, ETH_ALEN); + tf->ether_type = cpu_to_be16(ETH_P_TDLS); + tf->payload_type = WLAN_TDLS_SNAP_RFTYPE; + + switch (action_code) { + case WLAN_TDLS_SETUP_REQUEST: + tf->category = WLAN_CATEGORY_TDLS; + tf->action_code = WLAN_TDLS_SETUP_REQUEST; + + skb_put(skb, sizeof(tf->u.setup_req)); + tf->u.setup_req.dialog_token = dialog_token; + tf->u.setup_req.capability = + cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); + + ieee80211_add_srates_ie(&sdata->vif, skb); + ieee80211_add_ext_srates_ie(&sdata->vif, skb); + ieee80211_tdls_add_ext_capab(skb); + break; + case WLAN_TDLS_SETUP_RESPONSE: + tf->category = WLAN_CATEGORY_TDLS; + tf->action_code = WLAN_TDLS_SETUP_RESPONSE; + + skb_put(skb, sizeof(tf->u.setup_resp)); + tf->u.setup_resp.status_code = cpu_to_le16(status_code); + tf->u.setup_resp.dialog_token = dialog_token; + tf->u.setup_resp.capability = + cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); + + ieee80211_add_srates_ie(&sdata->vif, skb); + ieee80211_add_ext_srates_ie(&sdata->vif, skb); + ieee80211_tdls_add_ext_capab(skb); + break; + case WLAN_TDLS_SETUP_CONFIRM: + tf->category = WLAN_CATEGORY_TDLS; + tf->action_code = WLAN_TDLS_SETUP_CONFIRM; + + skb_put(skb, sizeof(tf->u.setup_cfm)); + tf->u.setup_cfm.status_code = cpu_to_le16(status_code); + tf->u.setup_cfm.dialog_token = dialog_token; + break; + case WLAN_TDLS_TEARDOWN: + tf->category = WLAN_CATEGORY_TDLS; + tf->action_code = WLAN_TDLS_TEARDOWN; + + skb_put(skb, sizeof(tf->u.teardown)); + tf->u.teardown.reason_code = cpu_to_le16(status_code); + break; + case WLAN_TDLS_DISCOVERY_REQUEST: + tf->category = WLAN_CATEGORY_TDLS; + tf->action_code = WLAN_TDLS_DISCOVERY_REQUEST; + + skb_put(skb, sizeof(tf->u.discover_req)); + tf->u.discover_req.dialog_token = dialog_token; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int +ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev, + u8 *peer, u8 action_code, u8 dialog_token, + u16 status_code, struct sk_buff *skb) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_mgmt *mgmt; + + mgmt = (void *)skb_put(skb, 24); + memset(mgmt, 0, 24); + memcpy(mgmt->da, peer, ETH_ALEN); + memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); + memcpy(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN); + + mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION); + + switch (action_code) { + case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: + skb_put(skb, 1 + sizeof(mgmt->u.action.u.tdls_discover_resp)); + mgmt->u.action.category = WLAN_CATEGORY_PUBLIC; + mgmt->u.action.u.tdls_discover_resp.action_code = + WLAN_PUB_ACTION_TDLS_DISCOVER_RES; + mgmt->u.action.u.tdls_discover_resp.dialog_token = + dialog_token; + mgmt->u.action.u.tdls_discover_resp.capability = + cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); + + ieee80211_add_srates_ie(&sdata->vif, skb); + ieee80211_add_ext_srates_ie(&sdata->vif, skb); + ieee80211_tdls_add_ext_capab(skb); + break; + default: + return -EINVAL; + } + + return 0; +} + +static int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, + u8 *peer, u8 action_code, u8 dialog_token, + u16 status_code, const u8 *extra_ies, + size_t extra_ies_len) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; + struct ieee80211_tx_info *info; + struct sk_buff *skb = NULL; + bool send_direct; + int ret; + + if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)) + return -ENOTSUPP; + + /* make sure we are in managed mode, and associated */ + if (sdata->vif.type != NL80211_IFTYPE_STATION || + !sdata->u.mgd.associated) + return -EINVAL; + +#ifdef CONFIG_MAC80211_VERBOSE_TDLS_DEBUG + printk(KERN_DEBUG "TDLS mgmt action %d peer %pM\n", action_code, peer); +#endif + + skb = dev_alloc_skb(local->hw.extra_tx_headroom + + max(sizeof(struct ieee80211_mgmt), + sizeof(struct ieee80211_tdls_data)) + + 50 + /* supported rates */ + 7 + /* ext capab */ + extra_ies_len + + sizeof(struct ieee80211_tdls_lnkie)); + if (!skb) + return -ENOMEM; + + info = IEEE80211_SKB_CB(skb); + skb_reserve(skb, local->hw.extra_tx_headroom); + + switch (action_code) { + case WLAN_TDLS_SETUP_REQUEST: + case WLAN_TDLS_SETUP_RESPONSE: + case WLAN_TDLS_SETUP_CONFIRM: + case WLAN_TDLS_TEARDOWN: + case WLAN_TDLS_DISCOVERY_REQUEST: + ret = ieee80211_prep_tdls_encap_data(wiphy, dev, peer, + action_code, dialog_token, + status_code, skb); + send_direct = false; + break; + case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: + ret = ieee80211_prep_tdls_direct(wiphy, dev, peer, action_code, + dialog_token, status_code, + skb); + send_direct = true; + break; + default: + ret = -ENOTSUPP; + break; + } + + if (ret < 0) + goto fail; + + if (extra_ies_len) + memcpy(skb_put(skb, extra_ies_len), extra_ies, extra_ies_len); + + /* the TDLS link IE is always added last */ + switch (action_code) { + case WLAN_TDLS_SETUP_REQUEST: + case WLAN_TDLS_SETUP_CONFIRM: + case WLAN_TDLS_TEARDOWN: + case WLAN_TDLS_DISCOVERY_REQUEST: + /* we are the initiator */ + ieee80211_tdls_add_link_ie(skb, sdata->vif.addr, peer, + sdata->u.mgd.bssid); + break; + case WLAN_TDLS_SETUP_RESPONSE: + case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: + /* we are the responder */ + ieee80211_tdls_add_link_ie(skb, peer, sdata->vif.addr, + sdata->u.mgd.bssid); + break; + default: + ret = -ENOTSUPP; + goto fail; + } + + if (send_direct) { + ieee80211_tx_skb(sdata, skb); + return 0; + } + + /* + * According to 802.11z: Setup req/resp are sent in AC_BK, otherwise + * we should default to AC_VI. + */ + switch (action_code) { + case WLAN_TDLS_SETUP_REQUEST: + case WLAN_TDLS_SETUP_RESPONSE: + skb_set_queue_mapping(skb, IEEE80211_AC_BK); + skb->priority = 2; + break; + default: + skb_set_queue_mapping(skb, IEEE80211_AC_VI); + skb->priority = 5; + break; + } + + /* disable bottom halves when entering the Tx path */ + local_bh_disable(); + ret = ieee80211_subif_start_xmit(skb, dev); + local_bh_enable(); + + return ret; + +fail: + dev_kfree_skb(skb); + return ret; +} + +static int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, + u8 *peer, enum nl80211_tdls_operation oper) +{ + struct sta_info *sta; + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)) + return -ENOTSUPP; + + if (sdata->vif.type != NL80211_IFTYPE_STATION) + return -EINVAL; + +#ifdef CONFIG_MAC80211_VERBOSE_TDLS_DEBUG + printk(KERN_DEBUG "TDLS oper %d peer %pM\n", oper, peer); +#endif + + switch (oper) { + case NL80211_TDLS_ENABLE_LINK: + rcu_read_lock(); + sta = sta_info_get(sdata, peer); + if (!sta) { + rcu_read_unlock(); + return -ENOLINK; + } + + set_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH); + rcu_read_unlock(); + break; + case NL80211_TDLS_DISABLE_LINK: + return sta_info_destroy_addr(sdata, peer); + case NL80211_TDLS_TEARDOWN: + case NL80211_TDLS_SETUP: + case NL80211_TDLS_DISCOVERY_REQ: + /* We don't support in-driver setup/teardown/discovery */ + return -ENOTSUPP; + default: + return -ENOTSUPP; + } + + return 0; +} + struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -2186,4 +2551,6 @@ struct cfg80211_ops mac80211_config_ops = { .set_ringparam = ieee80211_set_ringparam, .get_ringparam = ieee80211_get_ringparam, .set_rekey_data = ieee80211_set_rekey_data, + .tdls_oper = ieee80211_tdls_oper, + .tdls_mgmt = ieee80211_tdls_mgmt, }; diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 186e02f..883996b 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -78,57 +78,6 @@ DEBUGFS_READONLY_FILE(wep_iv, "%#08x", DEBUGFS_READONLY_FILE(rate_ctrl_alg, "%s", local->rate_ctrl ? local->rate_ctrl->ops->name : "hw/driver"); -static ssize_t tsf_read(struct file *file, char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct ieee80211_local *local = file->private_data; - u64 tsf; - - tsf = drv_get_tsf(local); - - return mac80211_format_buffer(user_buf, count, ppos, "0x%016llx\n", - (unsigned long long) tsf); -} - -static ssize_t tsf_write(struct file *file, - const char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct ieee80211_local *local = file->private_data; - unsigned long long tsf; - char buf[100]; - size_t len; - - len = min(count, sizeof(buf) - 1); - if (copy_from_user(buf, user_buf, len)) - return -EFAULT; - buf[len] = '\0'; - - if (strncmp(buf, "reset", 5) == 0) { - if (local->ops->reset_tsf) { - drv_reset_tsf(local); - wiphy_info(local->hw.wiphy, "debugfs reset TSF\n"); - } - } else { - tsf = simple_strtoul(buf, NULL, 0); - if (local->ops->set_tsf) { - drv_set_tsf(local, tsf); - wiphy_info(local->hw.wiphy, - "debugfs set TSF to %#018llx\n", tsf); - - } - } - - return count; -} - -static const struct file_operations tsf_ops = { - .read = tsf_read, - .write = tsf_write, - .open = mac80211_open_file_generic, - .llseek = default_llseek, -}; - static ssize_t reset_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { @@ -195,20 +144,12 @@ static ssize_t uapsd_queues_write(struct file *file, size_t count, loff_t *ppos) { struct ieee80211_local *local = file->private_data; - unsigned long val; - char buf[10]; - size_t len; + u8 val; int ret; - len = min(count, sizeof(buf) - 1); - if (copy_from_user(buf, user_buf, len)) - return -EFAULT; - buf[len] = '\0'; - - ret = strict_strtoul(buf, 0, &val); - + ret = kstrtou8_from_user(user_buf, count, 0, &val); if (ret) - return -EINVAL; + return ret; if (val & ~IEEE80211_WMM_IE_STA_QOSINFO_AC_MASK) return -ERANGE; @@ -305,6 +246,9 @@ static ssize_t hwflags_read(struct file *file, char __user *user_buf, char *buf = kzalloc(mxln, GFP_KERNEL); int sf = 0; /* how many written so far */ + if (!buf) + return 0; + sf += snprintf(buf, mxln - sf, "0x%x\n", local->hw.flags); if (local->hw.flags & IEEE80211_HW_HAS_RATE_CONTROL) sf += snprintf(buf + sf, mxln - sf, "HAS_RATE_CONTROL\n"); @@ -355,6 +299,8 @@ static ssize_t hwflags_read(struct file *file, char __user *user_buf, sf += snprintf(buf + sf, mxln - sf, "SUPPORTS_PER_STA_GTK\n"); if (local->hw.flags & IEEE80211_HW_AP_LINK_PS) sf += snprintf(buf + sf, mxln - sf, "AP_LINK_PS\n"); + if (local->hw.flags & IEEE80211_HW_TX_AMPDU_SETUP_IN_HW) + sf += snprintf(buf + sf, mxln - sf, "TX_AMPDU_SETUP_IN_HW\n"); rv = simple_read_from_buffer(user_buf, count, ppos, buf, strlen(buf)); kfree(buf); @@ -450,7 +396,6 @@ void debugfs_hw_add(struct ieee80211_local *local) DEBUGFS_ADD(frequency); DEBUGFS_ADD(total_ps_buffered); DEBUGFS_ADD(wep_iv); - DEBUGFS_ADD(tsf); DEBUGFS_ADD(queues); DEBUGFS_ADD_MODE(reset, 0200); DEBUGFS_ADD(noack); diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 9ea7c0d..9352819 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -21,6 +21,7 @@ #include "rate.h" #include "debugfs.h" #include "debugfs_netdev.h" +#include "driver-ops.h" static ssize_t ieee80211_if_read( struct ieee80211_sub_if_data *sdata, @@ -331,6 +332,46 @@ static ssize_t ieee80211_if_fmt_num_buffered_multicast( } __IEEE80211_IF_FILE(num_buffered_multicast, NULL); +/* IBSS attributes */ +static ssize_t ieee80211_if_fmt_tsf( + const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) +{ + struct ieee80211_local *local = sdata->local; + u64 tsf; + + tsf = drv_get_tsf(local, (struct ieee80211_sub_if_data *)sdata); + + return scnprintf(buf, buflen, "0x%016llx\n", (unsigned long long) tsf); +} + +static ssize_t ieee80211_if_parse_tsf( + struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) +{ + struct ieee80211_local *local = sdata->local; + unsigned long long tsf; + int ret; + + if (strncmp(buf, "reset", 5) == 0) { + if (local->ops->reset_tsf) { + drv_reset_tsf(local, sdata); + wiphy_info(local->hw.wiphy, "debugfs reset TSF\n"); + } + } else { + ret = kstrtoull(buf, 10, &tsf); + if (ret < 0) + return -EINVAL; + if (local->ops->set_tsf) { + drv_set_tsf(local, sdata, tsf); + wiphy_info(local->hw.wiphy, + "debugfs set TSF to %#018llx\n", tsf); + } + } + + return buflen; +} +__IEEE80211_IF_FILE_W(tsf); + + /* WDS attributes */ IEEE80211_IF_FILE(peer, u.wds.remote_addr, MAC); @@ -340,6 +381,8 @@ IEEE80211_IF_FILE(fwded_mcast, u.mesh.mshstats.fwded_mcast, DEC); IEEE80211_IF_FILE(fwded_unicast, u.mesh.mshstats.fwded_unicast, DEC); IEEE80211_IF_FILE(fwded_frames, u.mesh.mshstats.fwded_frames, DEC); IEEE80211_IF_FILE(dropped_frames_ttl, u.mesh.mshstats.dropped_frames_ttl, DEC); +IEEE80211_IF_FILE(dropped_frames_congestion, + u.mesh.mshstats.dropped_frames_congestion, DEC); IEEE80211_IF_FILE(dropped_frames_no_route, u.mesh.mshstats.dropped_frames_no_route, DEC); IEEE80211_IF_FILE(estab_plinks, u.mesh.mshstats.estab_plinks, ATOMIC); @@ -372,6 +415,10 @@ IEEE80211_IF_FILE(min_discovery_timeout, u.mesh.mshcfg.min_discovery_timeout, DEC); IEEE80211_IF_FILE(dot11MeshHWMPRootMode, u.mesh.mshcfg.dot11MeshHWMPRootMode, DEC); +IEEE80211_IF_FILE(dot11MeshGateAnnouncementProtocol, + u.mesh.mshcfg.dot11MeshGateAnnouncementProtocol, DEC); +IEEE80211_IF_FILE(dot11MeshHWMPRannInterval, + u.mesh.mshcfg.dot11MeshHWMPRannInterval, DEC); #endif @@ -415,6 +462,11 @@ static void add_ap_files(struct ieee80211_sub_if_data *sdata) DEBUGFS_ADD_MODE(tkip_mic_test, 0200); } +static void add_ibss_files(struct ieee80211_sub_if_data *sdata) +{ + DEBUGFS_ADD_MODE(tsf, 0600); +} + static void add_wds_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD(drop_unencrypted); @@ -459,6 +511,7 @@ static void add_mesh_stats(struct ieee80211_sub_if_data *sdata) MESHSTATS_ADD(fwded_frames); MESHSTATS_ADD(dropped_frames_ttl); MESHSTATS_ADD(dropped_frames_no_route); + MESHSTATS_ADD(dropped_frames_congestion); MESHSTATS_ADD(estab_plinks); #undef MESHSTATS_ADD } @@ -485,7 +538,9 @@ static void add_mesh_config(struct ieee80211_sub_if_data *sdata) MESHPARAMS_ADD(dot11MeshHWMPmaxPREQretries); MESHPARAMS_ADD(path_refresh_time); MESHPARAMS_ADD(min_discovery_timeout); - + MESHPARAMS_ADD(dot11MeshHWMPRootMode); + MESHPARAMS_ADD(dot11MeshHWMPRannInterval); + MESHPARAMS_ADD(dot11MeshGateAnnouncementProtocol); #undef MESHPARAMS_ADD } #endif @@ -506,7 +561,7 @@ static void add_files(struct ieee80211_sub_if_data *sdata) add_sta_files(sdata); break; case NL80211_IFTYPE_ADHOC: - /* XXX */ + add_ibss_files(sdata); break; case NL80211_IFTYPE_AP: add_ap_files(sdata); diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index a01d213..c5f3417 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -56,19 +56,22 @@ STA_FILE(last_signal, last_signal, D); static ssize_t sta_flags_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { - char buf[100]; + char buf[121]; struct sta_info *sta = file->private_data; - u32 staflags = get_sta_flags(sta); - int res = scnprintf(buf, sizeof(buf), "%s%s%s%s%s%s%s%s%s", - staflags & WLAN_STA_AUTH ? "AUTH\n" : "", - staflags & WLAN_STA_ASSOC ? "ASSOC\n" : "", - staflags & WLAN_STA_PS_STA ? "PS (sta)\n" : "", - staflags & WLAN_STA_PS_DRIVER ? "PS (driver)\n" : "", - staflags & WLAN_STA_AUTHORIZED ? "AUTHORIZED\n" : "", - staflags & WLAN_STA_SHORT_PREAMBLE ? "SHORT PREAMBLE\n" : "", - staflags & WLAN_STA_WME ? "WME\n" : "", - staflags & WLAN_STA_WDS ? "WDS\n" : "", - staflags & WLAN_STA_MFP ? "MFP\n" : ""); + +#define TEST(flg) \ + test_sta_flag(sta, WLAN_STA_##flg) ? #flg "\n" : "" + + int res = scnprintf(buf, sizeof(buf), + "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", + TEST(AUTH), TEST(ASSOC), TEST(PS_STA), + TEST(PS_DRIVER), TEST(AUTHORIZED), + TEST(SHORT_PREAMBLE), TEST(ASSOC_AP), + TEST(WME), TEST(WDS), TEST(CLEAR_PS_FILT), + TEST(MFP), TEST(BLOCK_BA), TEST(PSPOLL), + TEST(UAPSD), TEST(SP), TEST(TDLS_PEER), + TEST(TDLS_PEER_AUTH)); +#undef TEST return simple_read_from_buffer(userbuf, count, ppos, buf, res); } STA_OPS(flags); @@ -78,8 +81,14 @@ static ssize_t sta_num_ps_buf_frames_read(struct file *file, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; - return mac80211_format_buffer(userbuf, count, ppos, "%u\n", - skb_queue_len(&sta->ps_tx_buf)); + char buf[17*IEEE80211_NUM_ACS], *p = buf; + int ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) + p += scnprintf(p, sizeof(buf)+buf-p, "AC%d: %d\n", ac, + skb_queue_len(&sta->ps_tx_buf[ac]) + + skb_queue_len(&sta->tx_filtered[ac])); + return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); } STA_OPS(num_ps_buf_frames); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 1425380..5f165d7 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -413,50 +413,56 @@ static inline void drv_sta_remove(struct ieee80211_local *local, trace_drv_return_void(local); } -static inline int drv_conf_tx(struct ieee80211_local *local, u16 queue, +static inline int drv_conf_tx(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, u16 queue, const struct ieee80211_tx_queue_params *params) { int ret = -EOPNOTSUPP; might_sleep(); - trace_drv_conf_tx(local, queue, params); + trace_drv_conf_tx(local, sdata, queue, params); if (local->ops->conf_tx) - ret = local->ops->conf_tx(&local->hw, queue, params); + ret = local->ops->conf_tx(&local->hw, &sdata->vif, + queue, params); trace_drv_return_int(local, ret); return ret; } -static inline u64 drv_get_tsf(struct ieee80211_local *local) +static inline u64 drv_get_tsf(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) { u64 ret = -1ULL; might_sleep(); - trace_drv_get_tsf(local); + trace_drv_get_tsf(local, sdata); if (local->ops->get_tsf) - ret = local->ops->get_tsf(&local->hw); + ret = local->ops->get_tsf(&local->hw, &sdata->vif); trace_drv_return_u64(local, ret); return ret; } -static inline void drv_set_tsf(struct ieee80211_local *local, u64 tsf) +static inline void drv_set_tsf(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + u64 tsf) { might_sleep(); - trace_drv_set_tsf(local, tsf); + trace_drv_set_tsf(local, sdata, tsf); if (local->ops->set_tsf) - local->ops->set_tsf(&local->hw, tsf); + local->ops->set_tsf(&local->hw, &sdata->vif, tsf); trace_drv_return_void(local); } -static inline void drv_reset_tsf(struct ieee80211_local *local) +static inline void drv_reset_tsf(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) { might_sleep(); - trace_drv_reset_tsf(local); + trace_drv_reset_tsf(local, sdata); if (local->ops->reset_tsf) - local->ops->reset_tsf(&local->hw); + local->ops->reset_tsf(&local->hw, &sdata->vif); trace_drv_return_void(local); } @@ -590,37 +596,6 @@ static inline int drv_cancel_remain_on_channel(struct ieee80211_local *local) return ret; } -static inline int drv_offchannel_tx(struct ieee80211_local *local, - struct sk_buff *skb, - struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type, - unsigned int wait) -{ - int ret; - - might_sleep(); - - trace_drv_offchannel_tx(local, skb, chan, channel_type, wait); - ret = local->ops->offchannel_tx(&local->hw, skb, chan, - channel_type, wait); - trace_drv_return_int(local, ret); - - return ret; -} - -static inline int drv_offchannel_tx_cancel_wait(struct ieee80211_local *local) -{ - int ret; - - might_sleep(); - - trace_drv_offchannel_tx_cancel_wait(local); - ret = local->ops->offchannel_tx_cancel_wait(&local->hw); - trace_drv_return_int(local, ret); - - return ret; -} - static inline int drv_set_ringparam(struct ieee80211_local *local, u32 tx, u32 rx) { @@ -696,4 +671,34 @@ static inline void drv_rssi_callback(struct ieee80211_local *local, local->ops->rssi_callback(&local->hw, event); trace_drv_return_void(local); } + +static inline void +drv_release_buffered_frames(struct ieee80211_local *local, + struct sta_info *sta, u16 tids, int num_frames, + enum ieee80211_frame_release_type reason, + bool more_data) +{ + trace_drv_release_buffered_frames(local, &sta->sta, tids, num_frames, + reason, more_data); + if (local->ops->release_buffered_frames) + local->ops->release_buffered_frames(&local->hw, &sta->sta, tids, + num_frames, reason, + more_data); + trace_drv_return_void(local); +} + +static inline void +drv_allow_buffered_frames(struct ieee80211_local *local, + struct sta_info *sta, u16 tids, int num_frames, + enum ieee80211_frame_release_type reason, + bool more_data) +{ + trace_drv_allow_buffered_frames(local, &sta->sta, tids, num_frames, + reason, more_data); + if (local->ops->allow_buffered_frames) + local->ops->allow_buffered_frames(&local->hw, &sta->sta, + tids, num_frames, reason, + more_data); + trace_drv_return_void(local); +} #endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h index f47b00dc7..2af4fca 100644 --- a/net/mac80211/driver-trace.h +++ b/net/mac80211/driver-trace.h @@ -697,64 +697,76 @@ TRACE_EVENT(drv_sta_remove, ); TRACE_EVENT(drv_conf_tx, - TP_PROTO(struct ieee80211_local *local, u16 queue, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + u16 queue, const struct ieee80211_tx_queue_params *params), - TP_ARGS(local, queue, params), + TP_ARGS(local, sdata, queue, params), TP_STRUCT__entry( LOCAL_ENTRY + VIF_ENTRY __field(u16, queue) __field(u16, txop) __field(u16, cw_min) __field(u16, cw_max) __field(u8, aifs) + __field(bool, uapsd) ), TP_fast_assign( LOCAL_ASSIGN; + VIF_ASSIGN; __entry->queue = queue; __entry->txop = params->txop; __entry->cw_max = params->cw_max; __entry->cw_min = params->cw_min; __entry->aifs = params->aifs; + __entry->uapsd = params->uapsd; ), TP_printk( - LOCAL_PR_FMT " queue:%d", - LOCAL_PR_ARG, __entry->queue + LOCAL_PR_FMT VIF_PR_FMT " queue:%d", + LOCAL_PR_ARG, VIF_PR_ARG, __entry->queue ) ); -DEFINE_EVENT(local_only_evt, drv_get_tsf, - TP_PROTO(struct ieee80211_local *local), - TP_ARGS(local) +DEFINE_EVENT(local_sdata_evt, drv_get_tsf, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata), + TP_ARGS(local, sdata) ); TRACE_EVENT(drv_set_tsf, - TP_PROTO(struct ieee80211_local *local, u64 tsf), + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + u64 tsf), - TP_ARGS(local, tsf), + TP_ARGS(local, sdata, tsf), TP_STRUCT__entry( LOCAL_ENTRY + VIF_ENTRY __field(u64, tsf) ), TP_fast_assign( LOCAL_ASSIGN; + VIF_ASSIGN; __entry->tsf = tsf; ), TP_printk( - LOCAL_PR_FMT " tsf:%llu", - LOCAL_PR_ARG, (unsigned long long)__entry->tsf + LOCAL_PR_FMT VIF_PR_FMT " tsf:%llu", + LOCAL_PR_ARG, VIF_PR_ARG, (unsigned long long)__entry->tsf ) ); -DEFINE_EVENT(local_only_evt, drv_reset_tsf, - TP_PROTO(struct ieee80211_local *local), - TP_ARGS(local) +DEFINE_EVENT(local_sdata_evt, drv_reset_tsf, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata), + TP_ARGS(local, sdata) ); DEFINE_EVENT(local_only_evt, drv_tx_last_beacon, @@ -1117,6 +1129,61 @@ TRACE_EVENT(drv_rssi_callback, ) ); +DECLARE_EVENT_CLASS(release_evt, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sta *sta, + u16 tids, int num_frames, + enum ieee80211_frame_release_type reason, + bool more_data), + + TP_ARGS(local, sta, tids, num_frames, reason, more_data), + + TP_STRUCT__entry( + LOCAL_ENTRY + STA_ENTRY + __field(u16, tids) + __field(int, num_frames) + __field(int, reason) + __field(bool, more_data) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + STA_ASSIGN; + __entry->tids = tids; + __entry->num_frames = num_frames; + __entry->reason = reason; + __entry->more_data = more_data; + ), + + TP_printk( + LOCAL_PR_FMT STA_PR_FMT + " TIDs:0x%.4x frames:%d reason:%d more:%d", + LOCAL_PR_ARG, STA_PR_ARG, __entry->tids, __entry->num_frames, + __entry->reason, __entry->more_data + ) +); + +DEFINE_EVENT(release_evt, drv_release_buffered_frames, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sta *sta, + u16 tids, int num_frames, + enum ieee80211_frame_release_type reason, + bool more_data), + + TP_ARGS(local, sta, tids, num_frames, reason, more_data) +); + +DEFINE_EVENT(release_evt, drv_allow_buffered_frames, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sta *sta, + u16 tids, int num_frames, + enum ieee80211_frame_release_type reason, + bool more_data), + + TP_ARGS(local, sta, tids, num_frames, reason, more_data) +); + /* * Tracing for API calls that drivers call. */ @@ -1431,6 +1498,28 @@ TRACE_EVENT(api_enable_rssi_reports, ) ); +TRACE_EVENT(api_eosp, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sta *sta), + + TP_ARGS(local, sta), + + TP_STRUCT__entry( + LOCAL_ENTRY + STA_ENTRY + ), + + TP_fast_assign( + LOCAL_ASSIGN; + STA_ASSIGN; + ), + + TP_printk( + LOCAL_PR_FMT STA_PR_FMT, + LOCAL_PR_ARG, STA_PR_FMT + ) +); + /* * Tracing for internal functions * (which may also be called in response to driver calls) diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 7cfc286..f80a35c 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -130,7 +130,7 @@ void ieee80211_ba_session_work(struct work_struct *work) * down by the code that set the flag, so this * need not run. */ - if (test_sta_flags(sta, WLAN_STA_BLOCK_BA)) + if (test_sta_flag(sta, WLAN_STA_BLOCK_BA)) return; mutex_lock(&sta->ampdu_mlme.mtx); @@ -186,12 +186,8 @@ void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata, u16 params; skb = dev_alloc_skb(sizeof(*mgmt) + local->hw.extra_tx_headroom); - - if (!skb) { - printk(KERN_ERR "%s: failed to allocate buffer " - "for delba frame\n", sdata->name); + if (!skb) return; - } skb_reserve(skb, local->hw.extra_tx_headroom); mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24); diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 56c24ca..ede9a8b 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -81,10 +81,10 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, lockdep_assert_held(&ifibss->mtx); /* Reset own TSF to allow time synchronization work. */ - drv_reset_tsf(local); + drv_reset_tsf(local, sdata); skb = ifibss->skb; - rcu_assign_pointer(ifibss->presp, NULL); + RCU_INIT_POINTER(ifibss->presp, NULL); synchronize_rcu(); skb->data = skb->head; skb->len = 0; @@ -184,7 +184,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, *pos++ = 0; /* U-APSD no in use */ } - rcu_assign_pointer(ifibss->presp, skb); + RCU_INIT_POINTER(ifibss->presp, skb); sdata->vif.bss_conf.beacon_int = beacon_int; sdata->vif.bss_conf.basic_rates = basic_rates; @@ -314,7 +314,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, } if (sta && elems->wmm_info) - set_sta_flags(sta, WLAN_STA_WME); + set_sta_flag(sta, WLAN_STA_WME); rcu_read_unlock(); } @@ -382,7 +382,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, * second best option: get current TSF * (will return -1 if not supported) */ - rx_timestamp = drv_get_tsf(local); + rx_timestamp = drv_get_tsf(local, sdata); } #ifdef CONFIG_MAC80211_IBSS_DEBUG @@ -417,7 +417,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, * must be callable in atomic context. */ struct sta_info *ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata, - u8 *bssid,u8 *addr, u32 supp_rates, + u8 *bssid, u8 *addr, u32 supp_rates, gfp_t gfp) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; @@ -452,7 +452,7 @@ struct sta_info *ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata, return NULL; sta->last_rx = jiffies; - set_sta_flags(sta, WLAN_STA_AUTHORIZED); + set_sta_flag(sta, WLAN_STA_AUTHORIZED); /* make sure mandatory rates are always added */ sta->sta.supp_rates[band] = supp_rates | @@ -995,7 +995,7 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) kfree(sdata->u.ibss.ie); skb = rcu_dereference_protected(sdata->u.ibss.presp, lockdep_is_held(&sdata->u.ibss.mtx)); - rcu_assign_pointer(sdata->u.ibss.presp, NULL); + RCU_INIT_POINTER(sdata->u.ibss.presp, NULL); sdata->vif.bss_conf.ibss_joined = false; ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED | BSS_CHANGED_IBSS); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 400c09b..4c3d1f5 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -136,7 +136,6 @@ typedef unsigned __bitwise__ ieee80211_tx_result; #define TX_DROP ((__force ieee80211_tx_result) 1u) #define TX_QUEUED ((__force ieee80211_tx_result) 2u) -#define IEEE80211_TX_FRAGMENTED BIT(0) #define IEEE80211_TX_UNICAST BIT(1) #define IEEE80211_TX_PS_BUFFERED BIT(2) @@ -149,7 +148,6 @@ struct ieee80211_tx_data { struct ieee80211_channel *channel; - u16 ethertype; unsigned int flags; }; @@ -261,6 +259,7 @@ struct mesh_stats { __u32 fwded_frames; /* Mesh total forwarded frames */ __u32 dropped_frames_ttl; /* Not transmitted since mesh_ttl == 0*/ __u32 dropped_frames_no_route; /* Not transmitted, no route found */ + __u32 dropped_frames_congestion;/* Not forwarded due to congestion */ atomic_t estab_plinks; }; @@ -345,6 +344,7 @@ struct ieee80211_work { struct { struct sk_buff *frame; u32 wait; + bool status; } offchan_tx; }; @@ -514,6 +514,7 @@ struct ieee80211_if_mesh { struct mesh_config mshcfg; u32 mesh_seqnum; bool accepting_plinks; + int num_gates; const u8 *ie; u8 ie_len; enum { @@ -607,6 +608,8 @@ struct ieee80211_sub_if_data { __be16 control_port_protocol; bool control_port_no_encrypt; + struct ieee80211_tx_queue_params tx_conf[IEEE80211_MAX_QUEUES]; + struct work_struct work; struct sk_buff_head skb_queue; @@ -660,6 +663,11 @@ enum sdata_queue_type { enum { IEEE80211_RX_MSG = 1, IEEE80211_TX_STATUS_MSG = 2, + IEEE80211_EOSP_MSG = 3, +}; + +struct skb_eosp_msg_data { + u8 sta[ETH_ALEN], iface[ETH_ALEN]; }; enum queue_stop_reason { @@ -669,6 +677,7 @@ enum queue_stop_reason { IEEE80211_QUEUE_STOP_REASON_AGGREGATION, IEEE80211_QUEUE_STOP_REASON_SUSPEND, IEEE80211_QUEUE_STOP_REASON_SKB_ADD, + IEEE80211_QUEUE_STOP_REASON_CHTYPE_CHANGE, }; #ifdef CONFIG_MAC80211_LEDS @@ -748,7 +757,6 @@ struct ieee80211_local { struct workqueue_struct *workqueue; unsigned long queue_stop_reasons[IEEE80211_MAX_QUEUES]; - struct ieee80211_tx_queue_params tx_conf[IEEE80211_MAX_QUEUES]; /* also used to protect ampdu_ac_queue and amdpu_ac_stop_refcnt */ spinlock_t queue_stop_reason_lock; @@ -1002,7 +1010,6 @@ struct ieee80211_local { unsigned int hw_roc_duration; u32 hw_roc_cookie; bool hw_roc_for_tx; - unsigned long hw_offchan_tx_cookie; /* dummy netdev for use w/ NAPI */ struct net_device napi_dev; @@ -1022,69 +1029,6 @@ struct ieee80211_ra_tid { u16 tid; }; -/* Parsed Information Elements */ -struct ieee802_11_elems { - u8 *ie_start; - size_t total_len; - - /* pointers to IEs */ - u8 *ssid; - u8 *supp_rates; - u8 *fh_params; - u8 *ds_params; - u8 *cf_params; - struct ieee80211_tim_ie *tim; - u8 *ibss_params; - u8 *challenge; - u8 *wpa; - u8 *rsn; - u8 *erp_info; - u8 *ext_supp_rates; - u8 *wmm_info; - u8 *wmm_param; - struct ieee80211_ht_cap *ht_cap_elem; - struct ieee80211_ht_info *ht_info_elem; - struct ieee80211_meshconf_ie *mesh_config; - u8 *mesh_id; - u8 *peer_link; - u8 *preq; - u8 *prep; - u8 *perr; - struct ieee80211_rann_ie *rann; - u8 *ch_switch_elem; - u8 *country_elem; - u8 *pwr_constr_elem; - u8 *quiet_elem; /* first quite element */ - u8 *timeout_int; - - /* length of them, respectively */ - u8 ssid_len; - u8 supp_rates_len; - u8 fh_params_len; - u8 ds_params_len; - u8 cf_params_len; - u8 tim_len; - u8 ibss_params_len; - u8 challenge_len; - u8 wpa_len; - u8 rsn_len; - u8 erp_info_len; - u8 ext_supp_rates_len; - u8 wmm_info_len; - u8 wmm_param_len; - u8 mesh_id_len; - u8 peer_link_len; - u8 preq_len; - u8 prep_len; - u8 perr_len; - u8 ch_switch_elem_len; - u8 country_elem_len; - u8 pwr_constr_elem_len; - u8 quiet_elem_len; - u8 num_of_quiet_elem; /* can be more the one */ - u8 timeout_int_len; -}; - static inline struct ieee80211_local *hw_to_local( struct ieee80211_hw *hw) { @@ -1233,23 +1177,10 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev); -/* - * radiotap header for status frames - */ -struct ieee80211_tx_status_rtap_hdr { - struct ieee80211_radiotap_header hdr; - u8 rate; - u8 padding_for_rate; - __le16 tx_flags; - u8 data_retries; -} __packed; - - /* HT */ void ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_supported_band *sband, struct ieee80211_ht_cap *ht_cap_ie, struct ieee80211_sta_ht_cap *ht_cap); -void ieee80211_send_bar(struct ieee80211_sub_if_data *sdata, u8 *ra, u16 tid, u16 ssn); void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata, const u8 *da, u16 tid, u16 initiator, u16 reason_code); @@ -1333,6 +1264,7 @@ void mac80211_ev_michael_mic_failure(struct ieee80211_sub_if_data *sdata, int ke struct ieee80211_hdr *hdr, const u8 *tsc, gfp_t gfp); void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata); +void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void ieee80211_tx_skb(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void ieee802_11_parse_elems(u8 *start, size_t len, struct ieee802_11_elems *elems); @@ -1364,11 +1296,11 @@ void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason); void ieee80211_add_pending_skb(struct ieee80211_local *local, struct sk_buff *skb); -int ieee80211_add_pending_skbs(struct ieee80211_local *local, - struct sk_buff_head *skbs); -int ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, - struct sk_buff_head *skbs, - void (*fn)(void *data), void *data); +void ieee80211_add_pending_skbs(struct ieee80211_local *local, + struct sk_buff_head *skbs); +void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, + struct sk_buff_head *skbs, + void (*fn)(void *data), void *data); void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, @@ -1386,7 +1318,7 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, const u8 *ssid, size_t ssid_len, const u8 *ie, size_t ie_len, - u32 ratemask, bool directed); + u32 ratemask, bool directed, bool no_cck); void ieee80211_sta_def_wmm_params(struct ieee80211_sub_if_data *sdata, const size_t supp_rates_len, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 556e7e6..30d7355 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -299,8 +299,8 @@ static int ieee80211_do_open(struct net_device *dev, bool coming_up) goto err_del_interface; } - /* no locking required since STA is not live yet */ - sta->flags |= WLAN_STA_AUTHORIZED; + /* no atomic bitop required since STA is not live yet */ + set_sta_flag(sta, WLAN_STA_AUTHORIZED); res = sta_info_insert(sta); if (res) { @@ -456,21 +456,19 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, BSS_CHANGED_BEACON_ENABLED); /* remove beacon */ - rcu_assign_pointer(sdata->u.ap.beacon, NULL); + RCU_INIT_POINTER(sdata->u.ap.beacon, NULL); synchronize_rcu(); kfree(old_beacon); - /* free all potentially still buffered bcast frames */ - while ((skb = skb_dequeue(&sdata->u.ap.ps_bc_buf))) { - local->total_ps_buffered--; - dev_kfree_skb(skb); - } - /* down all dependent devices, that is VLANs */ list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans, u.vlan.list) dev_close(vlan->dev); WARN_ON(!list_empty(&sdata->u.ap.vlans)); + + /* free all potentially still buffered bcast frames */ + local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps_bc_buf); + skb_queue_purge(&sdata->u.ap.ps_bc_buf); } if (going_down) @@ -645,7 +643,7 @@ static const struct net_device_ops ieee80211_dataif_ops = { .ndo_stop = ieee80211_stop, .ndo_uninit = ieee80211_teardown_sdata, .ndo_start_xmit = ieee80211_subif_start_xmit, - .ndo_set_multicast_list = ieee80211_set_multicast_list, + .ndo_set_rx_mode = ieee80211_set_multicast_list, .ndo_change_mtu = ieee80211_change_mtu, .ndo_set_mac_address = ieee80211_change_mac, .ndo_select_queue = ieee80211_netdev_select_queue, @@ -689,7 +687,7 @@ static const struct net_device_ops ieee80211_monitorif_ops = { .ndo_stop = ieee80211_stop, .ndo_uninit = ieee80211_teardown_sdata, .ndo_start_xmit = ieee80211_monitor_start_xmit, - .ndo_set_multicast_list = ieee80211_set_multicast_list, + .ndo_set_rx_mode = ieee80211_set_multicast_list, .ndo_change_mtu = ieee80211_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_select_queue = ieee80211_monitor_select_queue, @@ -1214,6 +1212,9 @@ void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata) list_del_rcu(&sdata->list); mutex_unlock(&sdata->local->iflist_mtx); + if (ieee80211_vif_is_mesh(&sdata->vif)) + mesh_path_flush_by_iface(sdata); + synchronize_rcu(); unregister_netdevice(sdata->dev); } @@ -1233,6 +1234,9 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) { list_del(&sdata->list); + if (ieee80211_vif_is_mesh(&sdata->vif)) + mesh_path_flush_by_iface(sdata); + unregister_netdevice_queue(sdata->dev, &unreg_list); } mutex_unlock(&local->iflist_mtx); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 5150c6d..756b157 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -464,7 +464,7 @@ int ieee80211_key_link(struct ieee80211_key *key, * some hardware cannot handle TKIP with QoS, so * we indicate whether QoS could be in use. */ - if (test_sta_flags(sta, WLAN_STA_WME)) + if (test_sta_flag(sta, WLAN_STA_WME)) key->conf.flags |= IEEE80211_KEY_FLAG_WMM_STA; } else { if (sdata->vif.type == NL80211_IFTYPE_STATION) { @@ -478,7 +478,7 @@ int ieee80211_key_link(struct ieee80211_key *key, /* same here, the AP could be using QoS */ ap = sta_info_get(key->sdata, key->sdata->u.mgd.bssid); if (ap) { - if (test_sta_flags(ap, WLAN_STA_WME)) + if (test_sta_flag(ap, WLAN_STA_WME)) key->conf.flags |= IEEE80211_KEY_FLAG_WMM_STA; } diff --git a/net/mac80211/main.c b/net/mac80211/main.c index acb4423..d999bf3 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -19,7 +19,7 @@ #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/bitmap.h> -#include <linux/pm_qos_params.h> +#include <linux/pm_qos.h> #include <linux/inetdevice.h> #include <net/net_namespace.h> #include <net/cfg80211.h> @@ -325,6 +325,8 @@ u32 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata) static void ieee80211_tasklet_handler(unsigned long data) { struct ieee80211_local *local = (struct ieee80211_local *) data; + struct sta_info *sta, *tmp; + struct skb_eosp_msg_data *eosp_data; struct sk_buff *skb; while ((skb = skb_dequeue(&local->skb_queue)) || @@ -340,6 +342,18 @@ static void ieee80211_tasklet_handler(unsigned long data) skb->pkt_type = 0; ieee80211_tx_status(local_to_hw(local), skb); break; + case IEEE80211_EOSP_MSG: + eosp_data = (void *)skb->cb; + for_each_sta_info(local, eosp_data->sta, sta, tmp) { + /* skip wrong virtual interface */ + if (memcmp(eosp_data->iface, + sta->sdata->vif.addr, ETH_ALEN)) + continue; + clear_sta_flag(sta, WLAN_STA_SP); + break; + } + dev_kfree_skb(skb); + break; default: WARN(1, "mac80211: Packet is of unknown type %d\n", skb->pkt_type); @@ -608,6 +622,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, local->hw.max_rates = 1; local->hw.max_report_rates = 0; local->hw.max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF; + local->hw.max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF; local->hw.conf.long_frame_max_tx_count = wiphy->retry_long; local->hw.conf.short_frame_max_tx_count = wiphy->retry_short; local->user_power_level = -1; @@ -862,6 +877,10 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (local->ops->sched_scan_start) local->hw.wiphy->flags |= WIPHY_FLAG_SUPPORTS_SCHED_SCAN; + /* mac80211 based drivers don't support internal TDLS setup */ + if (local->hw.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS) + local->hw.wiphy->flags |= WIPHY_FLAG_TDLS_EXTERNAL_SETUP; + result = wiphy_register(local->hw.wiphy); if (result < 0) goto fail_wiphy_register; @@ -885,12 +904,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) * and we need some headroom for passing the frame to monitor * interfaces, but never both at the same time. */ -#ifndef __CHECKER__ - BUILD_BUG_ON(IEEE80211_TX_STATUS_HEADROOM != - sizeof(struct ieee80211_tx_status_rtap_hdr)); -#endif local->tx_headroom = max_t(unsigned int , local->hw.extra_tx_headroom, - sizeof(struct ieee80211_tx_status_rtap_hdr)); + IEEE80211_TX_STATUS_HEADROOM); debugfs_hw_add(local); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 29e9980..a7078fd 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -13,10 +13,6 @@ #include "ieee80211_i.h" #include "mesh.h" -#define IEEE80211_MESH_PEER_INACTIVITY_LIMIT (1800 * HZ) -#define IEEE80211_MESH_HOUSEKEEPING_INTERVAL (60 * HZ) -#define IEEE80211_MESH_RANN_INTERVAL (1 * HZ) - #define MESHCONF_CAPAB_ACCEPT_PLINKS 0x01 #define MESHCONF_CAPAB_FORWARDING 0x08 @@ -27,6 +23,17 @@ int mesh_allocated; static struct kmem_cache *rm_cache; +#ifdef CONFIG_MAC80211_MESH +bool mesh_action_is_path_sel(struct ieee80211_mgmt *mgmt) +{ + return (mgmt->u.action.u.mesh_action.action_code == + WLAN_MESH_ACTION_HWMP_PATH_SELECTION); +} +#else +bool mesh_action_is_path_sel(struct ieee80211_mgmt *mgmt) +{ return false; } +#endif + void ieee80211s_init(void) { mesh_pathtbl_init(); @@ -193,10 +200,9 @@ int mesh_rmc_check(u8 *sa, struct ieee80211s_hdr *mesh_hdr, } p = kmem_cache_alloc(rm_cache, GFP_ATOMIC); - if (!p) { - printk(KERN_DEBUG "o11s: could not allocate RMC entry\n"); + if (!p) return 0; - } + p->seqnum = seqnum; p->exp_time = jiffies + RMC_TIMEOUT; memcpy(p->sa, sa, ETH_ALEN); @@ -204,89 +210,136 @@ int mesh_rmc_check(u8 *sa, struct ieee80211s_hdr *mesh_hdr, return 0; } -void mesh_mgmt_ies_add(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata) +int +mesh_add_meshconf_ie(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata) { - struct ieee80211_local *local = sdata->local; - struct ieee80211_supported_band *sband; - u8 *pos; - int len, i, rate; - u8 neighbors; - - sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; - len = sband->n_bitrates; - if (len > 8) - len = 8; - pos = skb_put(skb, len + 2); - *pos++ = WLAN_EID_SUPP_RATES; - *pos++ = len; - for (i = 0; i < len; i++) { - rate = sband->bitrates[i].bitrate; - *pos++ = (u8) (rate / 5); - } - - if (sband->n_bitrates > len) { - pos = skb_put(skb, sband->n_bitrates - len + 2); - *pos++ = WLAN_EID_EXT_SUPP_RATES; - *pos++ = sband->n_bitrates - len; - for (i = len; i < sband->n_bitrates; i++) { - rate = sband->bitrates[i].bitrate; - *pos++ = (u8) (rate / 5); - } - } - - if (sband->band == IEEE80211_BAND_2GHZ) { - pos = skb_put(skb, 2 + 1); - *pos++ = WLAN_EID_DS_PARAMS; - *pos++ = 1; - *pos++ = ieee80211_frequency_to_channel(local->hw.conf.channel->center_freq); - } + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + u8 *pos, neighbors; + u8 meshconf_len = sizeof(struct ieee80211_meshconf_ie); - pos = skb_put(skb, 2 + sdata->u.mesh.mesh_id_len); - *pos++ = WLAN_EID_MESH_ID; - *pos++ = sdata->u.mesh.mesh_id_len; - if (sdata->u.mesh.mesh_id_len) - memcpy(pos, sdata->u.mesh.mesh_id, sdata->u.mesh.mesh_id_len); + if (skb_tailroom(skb) < 2 + meshconf_len) + return -ENOMEM; - pos = skb_put(skb, 2 + sizeof(struct ieee80211_meshconf_ie)); + pos = skb_put(skb, 2 + meshconf_len); *pos++ = WLAN_EID_MESH_CONFIG; - *pos++ = sizeof(struct ieee80211_meshconf_ie); + *pos++ = meshconf_len; /* Active path selection protocol ID */ - *pos++ = sdata->u.mesh.mesh_pp_id; - + *pos++ = ifmsh->mesh_pp_id; /* Active path selection metric ID */ - *pos++ = sdata->u.mesh.mesh_pm_id; - + *pos++ = ifmsh->mesh_pm_id; /* Congestion control mode identifier */ - *pos++ = sdata->u.mesh.mesh_cc_id; - + *pos++ = ifmsh->mesh_cc_id; /* Synchronization protocol identifier */ - *pos++ = sdata->u.mesh.mesh_sp_id; - + *pos++ = ifmsh->mesh_sp_id; /* Authentication Protocol identifier */ - *pos++ = sdata->u.mesh.mesh_auth_id; - + *pos++ = ifmsh->mesh_auth_id; /* Mesh Formation Info - number of neighbors */ - neighbors = atomic_read(&sdata->u.mesh.mshstats.estab_plinks); + neighbors = atomic_read(&ifmsh->mshstats.estab_plinks); /* Number of neighbor mesh STAs or 15 whichever is smaller */ neighbors = (neighbors > 15) ? 15 : neighbors; *pos++ = neighbors << 1; - /* Mesh capability */ - sdata->u.mesh.accepting_plinks = mesh_plink_availables(sdata); + ifmsh->accepting_plinks = mesh_plink_availables(sdata); *pos = MESHCONF_CAPAB_FORWARDING; - *pos++ |= sdata->u.mesh.accepting_plinks ? + *pos++ |= ifmsh->accepting_plinks ? MESHCONF_CAPAB_ACCEPT_PLINKS : 0x00; *pos++ = 0x00; - if (sdata->u.mesh.ie) { - int len = sdata->u.mesh.ie_len; - const u8 *data = sdata->u.mesh.ie; - if (skb_tailroom(skb) > len) - memcpy(skb_put(skb, len), data, len); + return 0; +} + +int +mesh_add_meshid_ie(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + u8 *pos; + + if (skb_tailroom(skb) < 2 + ifmsh->mesh_id_len) + return -ENOMEM; + + pos = skb_put(skb, 2 + ifmsh->mesh_id_len); + *pos++ = WLAN_EID_MESH_ID; + *pos++ = ifmsh->mesh_id_len; + if (ifmsh->mesh_id_len) + memcpy(pos, ifmsh->mesh_id, ifmsh->mesh_id_len); + + return 0; +} + +int +mesh_add_vendor_ies(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + u8 offset, len; + const u8 *data; + + if (!ifmsh->ie || !ifmsh->ie_len) + return 0; + + /* fast-forward to vendor IEs */ + offset = ieee80211_ie_split_vendor(ifmsh->ie, ifmsh->ie_len, 0); + + if (offset) { + len = ifmsh->ie_len - offset; + data = ifmsh->ie + offset; + if (skb_tailroom(skb) < len) + return -ENOMEM; + memcpy(skb_put(skb, len), data, len); } + + return 0; } +int +mesh_add_rsn_ie(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + u8 len = 0; + const u8 *data; + + if (!ifmsh->ie || !ifmsh->ie_len) + return 0; + + /* find RSN IE */ + data = ifmsh->ie; + while (data < ifmsh->ie + ifmsh->ie_len) { + if (*data == WLAN_EID_RSN) { + len = data[1] + 2; + break; + } + data++; + } + + if (len) { + if (skb_tailroom(skb) < len) + return -ENOMEM; + memcpy(skb_put(skb, len), data, len); + } + + return 0; +} + +int mesh_add_ds_params_ie(struct sk_buff *skb, + struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_supported_band *sband; + u8 *pos; + + if (skb_tailroom(skb) < 3) + return -ENOMEM; + + sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; + if (sband->band == IEEE80211_BAND_2GHZ) { + pos = skb_put(skb, 2 + 1); + *pos++ = WLAN_EID_DS_PARAMS; + *pos++ = 1; + *pos++ = ieee80211_frequency_to_channel(local->hw.conf.channel->center_freq); + } + + return 0; +} static void ieee80211_mesh_path_timer(unsigned long data) { @@ -352,8 +405,7 @@ int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc, memcpy(hdr->addr3, meshsa, ETH_ALEN); return 24; } else { - *fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | - IEEE80211_FCTL_TODS); + *fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS); /* RA TA DA SA */ memset(hdr->addr1, 0, ETH_ALEN); /* RA is resolved later */ memcpy(hdr->addr2, meshsa, ETH_ALEN); @@ -425,7 +477,8 @@ static void ieee80211_mesh_rootpath(struct ieee80211_sub_if_data *sdata) mesh_path_tx_root_frame(sdata); mod_timer(&ifmsh->mesh_path_root_timer, - round_jiffies(jiffies + IEEE80211_MESH_RANN_INTERVAL)); + round_jiffies(TU_TO_EXP_TIME( + ifmsh->mshcfg.dot11MeshHWMPRannInterval))); } #ifdef CONFIG_PM @@ -433,7 +486,7 @@ void ieee80211_mesh_quiesce(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - /* use atomic bitops in case both timers fire at the same time */ + /* use atomic bitops in case all timers fire at the same time */ if (del_timer_sync(&ifmsh->housekeeping_timer)) set_bit(TMR_RUNNING_HK, &ifmsh->timers_running); @@ -557,11 +610,18 @@ static void ieee80211_mesh_rx_mgmt_action(struct ieee80211_sub_if_data *sdata, struct ieee80211_rx_status *rx_status) { switch (mgmt->u.action.category) { - case WLAN_CATEGORY_MESH_ACTION: - mesh_rx_plink_frame(sdata, mgmt, len, rx_status); + case WLAN_CATEGORY_SELF_PROTECTED: + switch (mgmt->u.action.u.self_prot.action_code) { + case WLAN_SP_MESH_PEERING_OPEN: + case WLAN_SP_MESH_PEERING_CLOSE: + case WLAN_SP_MESH_PEERING_CONFIRM: + mesh_rx_plink_frame(sdata, mgmt, len, rx_status); + break; + } break; - case WLAN_CATEGORY_MESH_PATH_SEL: - mesh_rx_path_sel_frame(sdata, mgmt, len); + case WLAN_CATEGORY_MESH_ACTION: + if (mesh_action_is_path_sel(mgmt)) + mesh_rx_path_sel_frame(sdata, mgmt, len); break; } } @@ -633,6 +693,7 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) ifmsh->accepting_plinks = true; ifmsh->preq_id = 0; ifmsh->sn = 0; + ifmsh->num_gates = 0; atomic_set(&ifmsh->mpaths, 0); mesh_rmc_init(sdata); ifmsh->last_preq = jiffies; diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 249e733..8c00e2d 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -80,7 +80,10 @@ enum mesh_deferred_task_flags { * retry * @discovery_retries: number of discovery retries * @flags: mesh path flags, as specified on &enum mesh_path_flags - * @state_lock: mesh path state lock + * @state_lock: mesh path state lock used to protect changes to the + * mpath itself. No need to take this lock when adding or removing + * an mpath to a hash bucket on a path table. + * @is_gate: the destination station of this path is a mesh gate * * * The combination of dst and sdata is unique in the mesh path table. Since the @@ -104,6 +107,7 @@ struct mesh_path { u8 discovery_retries; enum mesh_path_flags flags; spinlock_t state_lock; + bool is_gate; }; /** @@ -120,6 +124,9 @@ struct mesh_path { * buckets * @mean_chain_len: maximum average length for the hash buckets' list, if it is * reached, the table will grow + * @known_gates: list of known mesh gates and their mpaths by the station. The + * gate's mpath may or may not be resolved and active. + * * rcu_head: RCU head to free the table */ struct mesh_table { @@ -133,6 +140,8 @@ struct mesh_table { int (*copy_node) (struct hlist_node *p, struct mesh_table *newtbl); int size_order; int mean_chain_len; + struct hlist_head *known_gates; + spinlock_t gates_lock; struct rcu_head rcu_head; }; @@ -166,6 +175,8 @@ struct mesh_rmc { u32 idx_mask; }; +#define IEEE80211_MESH_PEER_INACTIVITY_LIMIT (1800 * HZ) +#define IEEE80211_MESH_HOUSEKEEPING_INTERVAL (60 * HZ) #define MESH_DEFAULT_BEACON_INTERVAL 1000 /* in 1024 us units */ @@ -177,14 +188,6 @@ struct mesh_rmc { /* Maximum number of paths per interface */ #define MESH_MAX_MPATHS 1024 -/* Pending ANA approval */ -#define MESH_PATH_SEL_ACTION 0 - -/* PERR reason codes */ -#define PEER_RCODE_UNSPECIFIED 11 -#define PERR_RCODE_NO_ROUTE 12 -#define PERR_RCODE_DEST_UNREACH 13 - /* Public interfaces */ /* Various */ int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc, @@ -199,6 +202,16 @@ bool mesh_matches_local(struct ieee802_11_elems *ie, void mesh_ids_set_default(struct ieee80211_if_mesh *mesh); void mesh_mgmt_ies_add(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata); +int mesh_add_meshconf_ie(struct sk_buff *skb, + struct ieee80211_sub_if_data *sdata); +int mesh_add_meshid_ie(struct sk_buff *skb, + struct ieee80211_sub_if_data *sdata); +int mesh_add_rsn_ie(struct sk_buff *skb, + struct ieee80211_sub_if_data *sdata); +int mesh_add_vendor_ies(struct sk_buff *skb, + struct ieee80211_sub_if_data *sdata); +int mesh_add_ds_params_ie(struct sk_buff *skb, + struct ieee80211_sub_if_data *sdata); void mesh_rmc_free(struct ieee80211_sub_if_data *sdata); int mesh_rmc_init(struct ieee80211_sub_if_data *sdata); void ieee80211s_init(void); @@ -223,10 +236,13 @@ struct mesh_path *mesh_path_lookup_by_idx(int idx, struct ieee80211_sub_if_data *sdata); void mesh_path_fix_nexthop(struct mesh_path *mpath, struct sta_info *next_hop); void mesh_path_expire(struct ieee80211_sub_if_data *sdata); -void mesh_path_flush(struct ieee80211_sub_if_data *sdata); void mesh_rx_path_sel_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len); int mesh_path_add(u8 *dst, struct ieee80211_sub_if_data *sdata); + +int mesh_path_add_gate(struct mesh_path *mpath); +int mesh_path_send_to_gates(struct mesh_path *mpath); +int mesh_gate_num(struct ieee80211_sub_if_data *sdata); /* Mesh plinks */ void mesh_neighbour_update(u8 *hw_addr, u32 rates, struct ieee80211_sub_if_data *sdata, @@ -256,12 +272,14 @@ void mesh_pathtbl_unregister(void); int mesh_path_del(u8 *addr, struct ieee80211_sub_if_data *sdata); void mesh_path_timer(unsigned long data); void mesh_path_flush_by_nexthop(struct sta_info *sta); +void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata); void mesh_path_discard_frame(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata); void mesh_path_quiesce(struct ieee80211_sub_if_data *sdata); void mesh_path_restart(struct ieee80211_sub_if_data *sdata); void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata); +bool mesh_action_is_path_sel(struct ieee80211_mgmt *mgmt); extern int mesh_paths_generation; #ifdef CONFIG_MAC80211_MESH diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 3460108..174040a 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -8,10 +8,12 @@ */ #include <linux/slab.h> +#include "wme.h" #include "mesh.h" #ifdef CONFIG_MAC80211_VERBOSE_MHWMP_DEBUG -#define mhwmp_dbg(fmt, args...) printk(KERN_DEBUG "Mesh HWMP: " fmt, ##args) +#define mhwmp_dbg(fmt, args...) \ + printk(KERN_DEBUG "Mesh HWMP (%s): " fmt "\n", sdata->name, ##args) #else #define mhwmp_dbg(fmt, args...) do { (void)(0); } while (0) #endif @@ -68,12 +70,12 @@ static inline u32 u16_field_get(u8 *preq_elem, int offset, bool ae) #define PREP_IE_FLAGS(x) PREQ_IE_FLAGS(x) #define PREP_IE_HOPCOUNT(x) PREQ_IE_HOPCOUNT(x) #define PREP_IE_TTL(x) PREQ_IE_TTL(x) -#define PREP_IE_ORIG_ADDR(x) (x + 3) -#define PREP_IE_ORIG_SN(x) u32_field_get(x, 9, 0) +#define PREP_IE_ORIG_ADDR(x) (AE_F_SET(x) ? x + 27 : x + 21) +#define PREP_IE_ORIG_SN(x) u32_field_get(x, 27, AE_F_SET(x)) #define PREP_IE_LIFETIME(x) u32_field_get(x, 13, AE_F_SET(x)) #define PREP_IE_METRIC(x) u32_field_get(x, 17, AE_F_SET(x)) -#define PREP_IE_TARGET_ADDR(x) (AE_F_SET(x) ? x + 27 : x + 21) -#define PREP_IE_TARGET_SN(x) u32_field_get(x, 27, AE_F_SET(x)) +#define PREP_IE_TARGET_ADDR(x) (x + 3) +#define PREP_IE_TARGET_SN(x) u32_field_get(x, 9, 0) #define PERR_IE_TTL(x) (*(x)) #define PERR_IE_TARGET_FLAGS(x) (*(x + 2)) @@ -132,24 +134,25 @@ static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags, memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); /* BSSID == SA */ memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN); - mgmt->u.action.category = WLAN_CATEGORY_MESH_PATH_SEL; - mgmt->u.action.u.mesh_action.action_code = MESH_PATH_SEL_ACTION; + mgmt->u.action.category = WLAN_CATEGORY_MESH_ACTION; + mgmt->u.action.u.mesh_action.action_code = + WLAN_MESH_ACTION_HWMP_PATH_SELECTION; switch (action) { case MPATH_PREQ: - mhwmp_dbg("sending PREQ to %pM\n", target); + mhwmp_dbg("sending PREQ to %pM", target); ie_len = 37; pos = skb_put(skb, 2 + ie_len); *pos++ = WLAN_EID_PREQ; break; case MPATH_PREP: - mhwmp_dbg("sending PREP to %pM\n", target); + mhwmp_dbg("sending PREP to %pM", target); ie_len = 31; pos = skb_put(skb, 2 + ie_len); *pos++ = WLAN_EID_PREP; break; case MPATH_RANN: - mhwmp_dbg("sending RANN from %pM\n", orig_addr); + mhwmp_dbg("sending RANN from %pM", orig_addr); ie_len = sizeof(struct ieee80211_rann_ie); pos = skb_put(skb, 2 + ie_len); *pos++ = WLAN_EID_RANN; @@ -163,35 +166,63 @@ static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags, *pos++ = flags; *pos++ = hop_count; *pos++ = ttl; - if (action == MPATH_PREQ) { - memcpy(pos, &preq_id, 4); + if (action == MPATH_PREP) { + memcpy(pos, target, ETH_ALEN); + pos += ETH_ALEN; + memcpy(pos, &target_sn, 4); pos += 4; - } - memcpy(pos, orig_addr, ETH_ALEN); - pos += ETH_ALEN; - memcpy(pos, &orig_sn, 4); - pos += 4; - if (action != MPATH_RANN) { - memcpy(pos, &lifetime, 4); + } else { + if (action == MPATH_PREQ) { + memcpy(pos, &preq_id, 4); + pos += 4; + } + memcpy(pos, orig_addr, ETH_ALEN); + pos += ETH_ALEN; + memcpy(pos, &orig_sn, 4); pos += 4; } + memcpy(pos, &lifetime, 4); /* interval for RANN */ + pos += 4; memcpy(pos, &metric, 4); pos += 4; if (action == MPATH_PREQ) { - /* destination count */ - *pos++ = 1; + *pos++ = 1; /* destination count */ *pos++ = target_flags; - } - if (action != MPATH_RANN) { memcpy(pos, target, ETH_ALEN); pos += ETH_ALEN; memcpy(pos, &target_sn, 4); + pos += 4; + } else if (action == MPATH_PREP) { + memcpy(pos, orig_addr, ETH_ALEN); + pos += ETH_ALEN; + memcpy(pos, &orig_sn, 4); + pos += 4; } ieee80211_tx_skb(sdata, skb); return 0; } + +/* Headroom is not adjusted. Caller should ensure that skb has sufficient + * headroom in case the frame is encrypted. */ +static void prepare_frame_for_deferred_tx(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) +{ + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + + skb_set_mac_header(skb, 0); + skb_set_network_header(skb, 0); + skb_set_transport_header(skb, 0); + + /* Send all internal mgmt frames on VO. Accordingly set TID to 7. */ + skb_set_queue_mapping(skb, IEEE80211_AC_VO); + skb->priority = 7; + + info->control.vif = &sdata->vif; + ieee80211_set_qos_hdr(sdata, skb); +} + /** * mesh_send_path error - Sends a PERR mesh management frame * @@ -199,6 +230,10 @@ static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags, * @target_sn: SN of the broken destination * @target_rcode: reason code for this PERR * @ra: node this frame is addressed to + * + * Note: This function may be called with driver locks taken that the driver + * also acquires in the TX path. To avoid a deadlock we don't transmit the + * frame directly but add it to the pending queue instead. */ int mesh_path_error_tx(u8 ttl, u8 *target, __le32 target_sn, __le16 target_rcode, const u8 *ra, @@ -212,7 +247,7 @@ int mesh_path_error_tx(u8 ttl, u8 *target, __le32 target_sn, if (!skb) return -1; - skb_reserve(skb, local->hw.extra_tx_headroom); + skb_reserve(skb, local->tx_headroom + local->hw.extra_tx_headroom); /* 25 is the size of the common mgmt part (24) plus the size of the * common action part (1) */ @@ -224,9 +259,11 @@ int mesh_path_error_tx(u8 ttl, u8 *target, __le32 target_sn, memcpy(mgmt->da, ra, ETH_ALEN); memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); - /* BSSID is left zeroed, wildcard value */ - mgmt->u.action.category = WLAN_CATEGORY_MESH_PATH_SEL; - mgmt->u.action.u.mesh_action.action_code = MESH_PATH_SEL_ACTION; + /* BSSID == SA */ + memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN); + mgmt->u.action.category = WLAN_CATEGORY_MESH_ACTION; + mgmt->u.action.u.mesh_action.action_code = + WLAN_MESH_ACTION_HWMP_PATH_SELECTION; ie_len = 15; pos = skb_put(skb, 2 + ie_len); *pos++ = WLAN_EID_PERR; @@ -251,7 +288,9 @@ int mesh_path_error_tx(u8 ttl, u8 *target, __le32 target_sn, pos += 4; memcpy(pos, &target_rcode, 2); - ieee80211_tx_skb(sdata, skb); + /* see note in function header */ + prepare_frame_for_deferred_tx(sdata, skb); + ieee80211_add_pending_skb(local, skb); return 0; } @@ -449,7 +488,6 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, if (fresh_info) { mesh_path_assign_nexthop(mpath, sta); - mpath->flags &= ~MESH_PATH_SN_VALID; mpath->metric = last_hop_metric; mpath->exp_time = time_after(mpath->exp_time, exp_time) ? mpath->exp_time : exp_time; @@ -484,10 +522,10 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, orig_sn = PREQ_IE_ORIG_SN(preq_elem); target_flags = PREQ_IE_TARGET_F(preq_elem); - mhwmp_dbg("received PREQ from %pM\n", orig_addr); + mhwmp_dbg("received PREQ from %pM", orig_addr); if (memcmp(target_addr, sdata->vif.addr, ETH_ALEN) == 0) { - mhwmp_dbg("PREQ is for us\n"); + mhwmp_dbg("PREQ is for us"); forward = false; reply = true; metric = 0; @@ -523,7 +561,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, lifetime = PREQ_IE_LIFETIME(preq_elem); ttl = ifmsh->mshcfg.element_ttl; if (ttl != 0) { - mhwmp_dbg("replying to the PREQ\n"); + mhwmp_dbg("replying to the PREQ"); mesh_path_sel_frame_tx(MPATH_PREP, 0, target_addr, cpu_to_le32(target_sn), 0, orig_addr, cpu_to_le32(orig_sn), mgmt->sa, 0, ttl, @@ -543,7 +581,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, ifmsh->mshstats.dropped_frames_ttl++; return; } - mhwmp_dbg("forwarding the PREQ from %pM\n", orig_addr); + mhwmp_dbg("forwarding the PREQ from %pM", orig_addr); --ttl; flags = PREQ_IE_FLAGS(preq_elem); preq_id = PREQ_IE_PREQ_ID(preq_elem); @@ -578,7 +616,7 @@ static void hwmp_prep_frame_process(struct ieee80211_sub_if_data *sdata, u8 next_hop[ETH_ALEN]; u32 target_sn, orig_sn, lifetime; - mhwmp_dbg("received PREP from %pM\n", PREP_IE_ORIG_ADDR(prep_elem)); + mhwmp_dbg("received PREP from %pM", PREP_IE_ORIG_ADDR(prep_elem)); /* Note that we divert from the draft nomenclature and denominate * destination to what the draft refers to as origininator. So in this @@ -684,6 +722,8 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, u8 ttl, flags, hopcount; u8 *orig_addr; u32 orig_sn, metric; + u32 interval = ifmsh->mshcfg.dot11MeshHWMPRannInterval; + bool root_is_gate; ttl = rann->rann_ttl; if (ttl <= 1) { @@ -692,12 +732,19 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, } ttl--; flags = rann->rann_flags; + root_is_gate = !!(flags & RANN_FLAG_IS_GATE); orig_addr = rann->rann_addr; orig_sn = rann->rann_seq; hopcount = rann->rann_hopcount; hopcount++; metric = rann->rann_metric; - mhwmp_dbg("received RANN from %pM\n", orig_addr); + + /* Ignore our own RANNs */ + if (memcmp(orig_addr, sdata->vif.addr, ETH_ALEN) == 0) + return; + + mhwmp_dbg("received RANN from %pM (is_gate=%d)", orig_addr, + root_is_gate); rcu_read_lock(); mpath = mesh_path_lookup(orig_addr, sdata); @@ -709,18 +756,28 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, sdata->u.mesh.mshstats.dropped_frames_no_route++; return; } - mesh_queue_preq(mpath, - PREQ_Q_F_START | PREQ_Q_F_REFRESH); } + + if ((!(mpath->flags & (MESH_PATH_ACTIVE | MESH_PATH_RESOLVING)) || + time_after(jiffies, mpath->exp_time - 1*HZ)) && + !(mpath->flags & MESH_PATH_FIXED)) { + mhwmp_dbg("%s time to refresh root mpath %pM", sdata->name, + orig_addr); + mesh_queue_preq(mpath, PREQ_Q_F_START | PREQ_Q_F_REFRESH); + } + if (mpath->sn < orig_sn) { mesh_path_sel_frame_tx(MPATH_RANN, flags, orig_addr, cpu_to_le32(orig_sn), 0, NULL, 0, broadcast_addr, - hopcount, ttl, 0, + hopcount, ttl, cpu_to_le32(interval), cpu_to_le32(metric + mpath->metric), 0, sdata); mpath->sn = orig_sn; } + if (root_is_gate) + mesh_path_add_gate(mpath); + rcu_read_unlock(); } @@ -732,11 +789,20 @@ void mesh_rx_path_sel_frame(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems elems; size_t baselen; u32 last_hop_metric; + struct sta_info *sta; /* need action_code */ if (len < IEEE80211_MIN_ACTION_SIZE + 1) return; + rcu_read_lock(); + sta = sta_info_get(sdata, mgmt->sa); + if (!sta || sta->plink_state != NL80211_PLINK_ESTAB) { + rcu_read_unlock(); + return; + } + rcu_read_unlock(); + baselen = (u8 *) mgmt->u.action.u.mesh_action.variable - (u8 *) mgmt; ieee802_11_parse_elems(mgmt->u.action.u.mesh_action.variable, len - baselen, &elems); @@ -788,16 +854,16 @@ static void mesh_queue_preq(struct mesh_path *mpath, u8 flags) preq_node = kmalloc(sizeof(struct mesh_preq_queue), GFP_ATOMIC); if (!preq_node) { - mhwmp_dbg("could not allocate PREQ node\n"); + mhwmp_dbg("could not allocate PREQ node"); return; } - spin_lock(&ifmsh->mesh_preq_queue_lock); + spin_lock_bh(&ifmsh->mesh_preq_queue_lock); if (ifmsh->preq_queue_len == MAX_PREQ_QUEUE_LEN) { - spin_unlock(&ifmsh->mesh_preq_queue_lock); + spin_unlock_bh(&ifmsh->mesh_preq_queue_lock); kfree(preq_node); if (printk_ratelimit()) - mhwmp_dbg("PREQ node queue full\n"); + mhwmp_dbg("PREQ node queue full"); return; } @@ -806,7 +872,7 @@ static void mesh_queue_preq(struct mesh_path *mpath, u8 flags) list_add_tail(&preq_node->list, &ifmsh->preq_queue.list); ++ifmsh->preq_queue_len; - spin_unlock(&ifmsh->mesh_preq_queue_lock); + spin_unlock_bh(&ifmsh->mesh_preq_queue_lock); if (time_after(jiffies, ifmsh->last_preq + min_preq_int_jiff(sdata))) ieee80211_queue_work(&sdata->local->hw, &sdata->work); @@ -982,35 +1048,46 @@ void mesh_path_timer(unsigned long data) { struct mesh_path *mpath = (void *) data; struct ieee80211_sub_if_data *sdata = mpath->sdata; + int ret; if (sdata->local->quiescing) return; spin_lock_bh(&mpath->state_lock); if (mpath->flags & MESH_PATH_RESOLVED || - (!(mpath->flags & MESH_PATH_RESOLVING))) + (!(mpath->flags & MESH_PATH_RESOLVING))) { mpath->flags &= ~(MESH_PATH_RESOLVING | MESH_PATH_RESOLVED); - else if (mpath->discovery_retries < max_preq_retries(sdata)) { + spin_unlock_bh(&mpath->state_lock); + } else if (mpath->discovery_retries < max_preq_retries(sdata)) { ++mpath->discovery_retries; mpath->discovery_timeout *= 2; + spin_unlock_bh(&mpath->state_lock); mesh_queue_preq(mpath, 0); } else { mpath->flags = 0; mpath->exp_time = jiffies; - mesh_path_flush_pending(mpath); + spin_unlock_bh(&mpath->state_lock); + if (!mpath->is_gate && mesh_gate_num(sdata) > 0) { + ret = mesh_path_send_to_gates(mpath); + if (ret) + mhwmp_dbg("no gate was reachable"); + } else + mesh_path_flush_pending(mpath); } - - spin_unlock_bh(&mpath->state_lock); } void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + u32 interval = ifmsh->mshcfg.dot11MeshHWMPRannInterval; + u8 flags; - mesh_path_sel_frame_tx(MPATH_RANN, 0, sdata->vif.addr, + flags = (ifmsh->mshcfg.dot11MeshGateAnnouncementProtocol) + ? RANN_FLAG_IS_GATE : 0; + mesh_path_sel_frame_tx(MPATH_RANN, flags, sdata->vif.addr, cpu_to_le32(++ifmsh->sn), 0, NULL, 0, broadcast_addr, 0, sdata->u.mesh.mshcfg.element_ttl, - 0, 0, 0, sdata); + cpu_to_le32(interval), 0, 0, sdata); } diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 068ee65..7f54c50 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -14,9 +14,16 @@ #include <linux/spinlock.h> #include <linux/string.h> #include <net/mac80211.h> +#include "wme.h" #include "ieee80211_i.h" #include "mesh.h" +#ifdef CONFIG_MAC80211_VERBOSE_MPATH_DEBUG +#define mpath_dbg(fmt, args...) printk(KERN_DEBUG fmt, ##args) +#else +#define mpath_dbg(fmt, args...) do { (void)(0); } while (0) +#endif + /* There will be initially 2^INIT_PATHS_SIZE_ORDER buckets */ #define INIT_PATHS_SIZE_ORDER 2 @@ -42,8 +49,10 @@ static struct mesh_table __rcu *mpp_paths; /* Store paths for MPP&MAP */ int mesh_paths_generation; /* This lock will have the grow table function as writer and add / delete nodes - * as readers. When reading the table (i.e. doing lookups) we are well protected - * by RCU + * as readers. RCU provides sufficient protection only when reading the table + * (i.e. doing lookups). Adding or adding or removing nodes requires we take + * the read lock or we risk operating on an old table. The write lock is only + * needed when modifying the number of buckets a table. */ static DEFINE_RWLOCK(pathtbl_resize_lock); @@ -60,6 +69,8 @@ static inline struct mesh_table *resize_dereference_mpp_paths(void) lockdep_is_held(&pathtbl_resize_lock)); } +static int mesh_gate_add(struct mesh_table *tbl, struct mesh_path *mpath); + /* * CAREFUL -- "tbl" must not be an expression, * in particular not an rcu_dereference(), since @@ -103,6 +114,7 @@ static struct mesh_table *mesh_table_alloc(int size_order) sizeof(newtbl->hash_rnd)); for (i = 0; i <= newtbl->hash_mask; i++) spin_lock_init(&newtbl->hashwlock[i]); + spin_lock_init(&newtbl->gates_lock); return newtbl; } @@ -118,6 +130,7 @@ static void mesh_table_free(struct mesh_table *tbl, bool free_leafs) { struct hlist_head *mesh_hash; struct hlist_node *p, *q; + struct mpath_node *gate; int i; mesh_hash = tbl->hash_buckets; @@ -129,6 +142,17 @@ static void mesh_table_free(struct mesh_table *tbl, bool free_leafs) } spin_unlock_bh(&tbl->hashwlock[i]); } + if (free_leafs) { + spin_lock_bh(&tbl->gates_lock); + hlist_for_each_entry_safe(gate, p, q, + tbl->known_gates, list) { + hlist_del(&gate->list); + kfree(gate); + } + kfree(tbl->known_gates); + spin_unlock_bh(&tbl->gates_lock); + } + __mesh_table_free(tbl); } @@ -146,6 +170,7 @@ static int mesh_table_grow(struct mesh_table *oldtbl, newtbl->free_node = oldtbl->free_node; newtbl->mean_chain_len = oldtbl->mean_chain_len; newtbl->copy_node = oldtbl->copy_node; + newtbl->known_gates = oldtbl->known_gates; atomic_set(&newtbl->entries, atomic_read(&oldtbl->entries)); oldhash = oldtbl->hash_buckets; @@ -188,6 +213,7 @@ void mesh_path_assign_nexthop(struct mesh_path *mpath, struct sta_info *sta) struct ieee80211_hdr *hdr; struct sk_buff_head tmpq; unsigned long flags; + struct ieee80211_sub_if_data *sdata = mpath->sdata; rcu_assign_pointer(mpath->next_hop, sta); @@ -198,6 +224,8 @@ void mesh_path_assign_nexthop(struct mesh_path *mpath, struct sta_info *sta) while ((skb = __skb_dequeue(&mpath->frame_queue)) != NULL) { hdr = (struct ieee80211_hdr *) skb->data; memcpy(hdr->addr1, sta->sta.addr, ETH_ALEN); + skb_set_queue_mapping(skb, ieee80211_select_queue(sdata, skb)); + ieee80211_set_qos_hdr(sdata, skb); __skb_queue_tail(&tmpq, skb); } @@ -205,62 +233,128 @@ void mesh_path_assign_nexthop(struct mesh_path *mpath, struct sta_info *sta) spin_unlock_irqrestore(&mpath->frame_queue.lock, flags); } +static void prepare_for_gate(struct sk_buff *skb, char *dst_addr, + struct mesh_path *gate_mpath) +{ + struct ieee80211_hdr *hdr; + struct ieee80211s_hdr *mshdr; + int mesh_hdrlen, hdrlen; + char *next_hop; + + hdr = (struct ieee80211_hdr *) skb->data; + hdrlen = ieee80211_hdrlen(hdr->frame_control); + mshdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); + + if (!(mshdr->flags & MESH_FLAGS_AE)) { + /* size of the fixed part of the mesh header */ + mesh_hdrlen = 6; + + /* make room for the two extended addresses */ + skb_push(skb, 2 * ETH_ALEN); + memmove(skb->data, hdr, hdrlen + mesh_hdrlen); + + hdr = (struct ieee80211_hdr *) skb->data; + + /* we preserve the previous mesh header and only add + * the new addreses */ + mshdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); + mshdr->flags = MESH_FLAGS_AE_A5_A6; + memcpy(mshdr->eaddr1, hdr->addr3, ETH_ALEN); + memcpy(mshdr->eaddr2, hdr->addr4, ETH_ALEN); + } + + /* update next hop */ + hdr = (struct ieee80211_hdr *) skb->data; + rcu_read_lock(); + next_hop = rcu_dereference(gate_mpath->next_hop)->sta.addr; + memcpy(hdr->addr1, next_hop, ETH_ALEN); + rcu_read_unlock(); + memcpy(hdr->addr3, dst_addr, ETH_ALEN); +} /** - * mesh_path_lookup - look up a path in the mesh path table - * @dst: hardware address (ETH_ALEN length) of destination - * @sdata: local subif * - * Returns: pointer to the mesh path structure, or NULL if not found + * mesh_path_move_to_queue - Move or copy frames from one mpath queue to another * - * Locking: must be called within a read rcu section. + * This function is used to transfer or copy frames from an unresolved mpath to + * a gate mpath. The function also adds the Address Extension field and + * updates the next hop. + * + * If a frame already has an Address Extension field, only the next hop and + * destination addresses are updated. + * + * The gate mpath must be an active mpath with a valid mpath->next_hop. + * + * @mpath: An active mpath the frames will be sent to (i.e. the gate) + * @from_mpath: The failed mpath + * @copy: When true, copy all the frames to the new mpath queue. When false, + * move them. */ -struct mesh_path *mesh_path_lookup(u8 *dst, struct ieee80211_sub_if_data *sdata) +static void mesh_path_move_to_queue(struct mesh_path *gate_mpath, + struct mesh_path *from_mpath, + bool copy) { - struct mesh_path *mpath; - struct hlist_node *n; - struct hlist_head *bucket; - struct mesh_table *tbl; - struct mpath_node *node; + struct sk_buff *skb, *cp_skb = NULL; + struct sk_buff_head gateq, failq; + unsigned long flags; + int num_skbs; - tbl = rcu_dereference(mesh_paths); + BUG_ON(gate_mpath == from_mpath); + BUG_ON(!gate_mpath->next_hop); - bucket = &tbl->hash_buckets[mesh_table_hash(dst, sdata, tbl)]; - hlist_for_each_entry_rcu(node, n, bucket, list) { - mpath = node->mpath; - if (mpath->sdata == sdata && - memcmp(dst, mpath->dst, ETH_ALEN) == 0) { - if (MPATH_EXPIRED(mpath)) { - spin_lock_bh(&mpath->state_lock); - if (MPATH_EXPIRED(mpath)) - mpath->flags &= ~MESH_PATH_ACTIVE; - spin_unlock_bh(&mpath->state_lock); - } - return mpath; + __skb_queue_head_init(&gateq); + __skb_queue_head_init(&failq); + + spin_lock_irqsave(&from_mpath->frame_queue.lock, flags); + skb_queue_splice_init(&from_mpath->frame_queue, &failq); + spin_unlock_irqrestore(&from_mpath->frame_queue.lock, flags); + + num_skbs = skb_queue_len(&failq); + + while (num_skbs--) { + skb = __skb_dequeue(&failq); + if (copy) { + cp_skb = skb_copy(skb, GFP_ATOMIC); + if (cp_skb) + __skb_queue_tail(&failq, cp_skb); } + + prepare_for_gate(skb, gate_mpath->dst, gate_mpath); + __skb_queue_tail(&gateq, skb); } - return NULL; + + spin_lock_irqsave(&gate_mpath->frame_queue.lock, flags); + skb_queue_splice(&gateq, &gate_mpath->frame_queue); + mpath_dbg("Mpath queue for gate %pM has %d frames\n", + gate_mpath->dst, + skb_queue_len(&gate_mpath->frame_queue)); + spin_unlock_irqrestore(&gate_mpath->frame_queue.lock, flags); + + if (!copy) + return; + + spin_lock_irqsave(&from_mpath->frame_queue.lock, flags); + skb_queue_splice(&failq, &from_mpath->frame_queue); + spin_unlock_irqrestore(&from_mpath->frame_queue.lock, flags); } -struct mesh_path *mpp_path_lookup(u8 *dst, struct ieee80211_sub_if_data *sdata) + +static struct mesh_path *path_lookup(struct mesh_table *tbl, u8 *dst, + struct ieee80211_sub_if_data *sdata) { struct mesh_path *mpath; struct hlist_node *n; struct hlist_head *bucket; - struct mesh_table *tbl; struct mpath_node *node; - tbl = rcu_dereference(mpp_paths); - bucket = &tbl->hash_buckets[mesh_table_hash(dst, sdata, tbl)]; hlist_for_each_entry_rcu(node, n, bucket, list) { mpath = node->mpath; if (mpath->sdata == sdata && - memcmp(dst, mpath->dst, ETH_ALEN) == 0) { + memcmp(dst, mpath->dst, ETH_ALEN) == 0) { if (MPATH_EXPIRED(mpath)) { spin_lock_bh(&mpath->state_lock); - if (MPATH_EXPIRED(mpath)) - mpath->flags &= ~MESH_PATH_ACTIVE; + mpath->flags &= ~MESH_PATH_ACTIVE; spin_unlock_bh(&mpath->state_lock); } return mpath; @@ -269,6 +363,25 @@ struct mesh_path *mpp_path_lookup(u8 *dst, struct ieee80211_sub_if_data *sdata) return NULL; } +/** + * mesh_path_lookup - look up a path in the mesh path table + * @dst: hardware address (ETH_ALEN length) of destination + * @sdata: local subif + * + * Returns: pointer to the mesh path structure, or NULL if not found + * + * Locking: must be called within a read rcu section. + */ +struct mesh_path *mesh_path_lookup(u8 *dst, struct ieee80211_sub_if_data *sdata) +{ + return path_lookup(rcu_dereference(mesh_paths), dst, sdata); +} + +struct mesh_path *mpp_path_lookup(u8 *dst, struct ieee80211_sub_if_data *sdata) +{ + return path_lookup(rcu_dereference(mpp_paths), dst, sdata); +} + /** * mesh_path_lookup_by_idx - look up a path in the mesh path table by its index @@ -293,8 +406,7 @@ struct mesh_path *mesh_path_lookup_by_idx(int idx, struct ieee80211_sub_if_data if (j++ == idx) { if (MPATH_EXPIRED(node->mpath)) { spin_lock_bh(&node->mpath->state_lock); - if (MPATH_EXPIRED(node->mpath)) - node->mpath->flags &= ~MESH_PATH_ACTIVE; + node->mpath->flags &= ~MESH_PATH_ACTIVE; spin_unlock_bh(&node->mpath->state_lock); } return node->mpath; @@ -304,6 +416,109 @@ struct mesh_path *mesh_path_lookup_by_idx(int idx, struct ieee80211_sub_if_data return NULL; } +static void mesh_gate_node_reclaim(struct rcu_head *rp) +{ + struct mpath_node *node = container_of(rp, struct mpath_node, rcu); + kfree(node); +} + +/** + * mesh_gate_add - mark mpath as path to a mesh gate and add to known_gates + * @mesh_tbl: table which contains known_gates list + * @mpath: mpath to known mesh gate + * + * Returns: 0 on success + * + */ +static int mesh_gate_add(struct mesh_table *tbl, struct mesh_path *mpath) +{ + struct mpath_node *gate, *new_gate; + struct hlist_node *n; + int err; + + rcu_read_lock(); + tbl = rcu_dereference(tbl); + + hlist_for_each_entry_rcu(gate, n, tbl->known_gates, list) + if (gate->mpath == mpath) { + err = -EEXIST; + goto err_rcu; + } + + new_gate = kzalloc(sizeof(struct mpath_node), GFP_ATOMIC); + if (!new_gate) { + err = -ENOMEM; + goto err_rcu; + } + + mpath->is_gate = true; + mpath->sdata->u.mesh.num_gates++; + new_gate->mpath = mpath; + spin_lock_bh(&tbl->gates_lock); + hlist_add_head_rcu(&new_gate->list, tbl->known_gates); + spin_unlock_bh(&tbl->gates_lock); + rcu_read_unlock(); + mpath_dbg("Mesh path (%s): Recorded new gate: %pM. %d known gates\n", + mpath->sdata->name, mpath->dst, + mpath->sdata->u.mesh.num_gates); + return 0; +err_rcu: + rcu_read_unlock(); + return err; +} + +/** + * mesh_gate_del - remove a mesh gate from the list of known gates + * @tbl: table which holds our list of known gates + * @mpath: gate mpath + * + * Returns: 0 on success + * + * Locking: must be called inside rcu_read_lock() section + */ +static int mesh_gate_del(struct mesh_table *tbl, struct mesh_path *mpath) +{ + struct mpath_node *gate; + struct hlist_node *p, *q; + + tbl = rcu_dereference(tbl); + + hlist_for_each_entry_safe(gate, p, q, tbl->known_gates, list) + if (gate->mpath == mpath) { + spin_lock_bh(&tbl->gates_lock); + hlist_del_rcu(&gate->list); + call_rcu(&gate->rcu, mesh_gate_node_reclaim); + spin_unlock_bh(&tbl->gates_lock); + mpath->sdata->u.mesh.num_gates--; + mpath->is_gate = false; + mpath_dbg("Mesh path (%s): Deleted gate: %pM. " + "%d known gates\n", mpath->sdata->name, + mpath->dst, mpath->sdata->u.mesh.num_gates); + break; + } + + return 0; +} + +/** + * + * mesh_path_add_gate - add the given mpath to a mesh gate to our path table + * @mpath: gate path to add to table + */ +int mesh_path_add_gate(struct mesh_path *mpath) +{ + return mesh_gate_add(mesh_paths, mpath); +} + +/** + * mesh_gate_num - number of gates known to this interface + * @sdata: subif data + */ +int mesh_gate_num(struct ieee80211_sub_if_data *sdata) +{ + return sdata->u.mesh.num_gates; +} + /** * mesh_path_add - allocate and add a new path to the mesh path table * @addr: destination address of the path (ETH_ALEN length) @@ -481,6 +696,7 @@ int mpp_path_add(u8 *dst, u8 *mpp, struct ieee80211_sub_if_data *sdata) new_mpath->flags = 0; skb_queue_head_init(&new_mpath->frame_queue); new_node->mpath = new_mpath; + init_timer(&new_mpath->timer); new_mpath->exp_time = jiffies; spin_lock_init(&new_mpath->state_lock); @@ -539,28 +755,53 @@ void mesh_plink_broken(struct sta_info *sta) struct hlist_node *p; struct ieee80211_sub_if_data *sdata = sta->sdata; int i; + __le16 reason = cpu_to_le16(WLAN_REASON_MESH_PATH_DEST_UNREACHABLE); rcu_read_lock(); tbl = rcu_dereference(mesh_paths); for_each_mesh_entry(tbl, p, node, i) { mpath = node->mpath; - spin_lock_bh(&mpath->state_lock); if (rcu_dereference(mpath->next_hop) == sta && mpath->flags & MESH_PATH_ACTIVE && !(mpath->flags & MESH_PATH_FIXED)) { + spin_lock_bh(&mpath->state_lock); mpath->flags &= ~MESH_PATH_ACTIVE; ++mpath->sn; spin_unlock_bh(&mpath->state_lock); mesh_path_error_tx(sdata->u.mesh.mshcfg.element_ttl, mpath->dst, cpu_to_le32(mpath->sn), - cpu_to_le16(PERR_RCODE_DEST_UNREACH), - bcast, sdata); - } else - spin_unlock_bh(&mpath->state_lock); + reason, bcast, sdata); + } } rcu_read_unlock(); } +static void mesh_path_node_reclaim(struct rcu_head *rp) +{ + struct mpath_node *node = container_of(rp, struct mpath_node, rcu); + struct ieee80211_sub_if_data *sdata = node->mpath->sdata; + + del_timer_sync(&node->mpath->timer); + atomic_dec(&sdata->u.mesh.mpaths); + kfree(node->mpath); + kfree(node); +} + +/* needs to be called with the corresponding hashwlock taken */ +static void __mesh_path_del(struct mesh_table *tbl, struct mpath_node *node) +{ + struct mesh_path *mpath; + mpath = node->mpath; + spin_lock(&mpath->state_lock); + mpath->flags |= MESH_PATH_RESOLVING; + if (mpath->is_gate) + mesh_gate_del(tbl, mpath); + hlist_del_rcu(&node->list); + call_rcu(&node->rcu, mesh_path_node_reclaim); + spin_unlock(&mpath->state_lock); + atomic_dec(&tbl->entries); +} + /** * mesh_path_flush_by_nexthop - Deletes mesh paths if their next hop matches * @@ -581,42 +822,59 @@ void mesh_path_flush_by_nexthop(struct sta_info *sta) int i; rcu_read_lock(); - tbl = rcu_dereference(mesh_paths); + read_lock_bh(&pathtbl_resize_lock); + tbl = resize_dereference_mesh_paths(); for_each_mesh_entry(tbl, p, node, i) { mpath = node->mpath; - if (rcu_dereference(mpath->next_hop) == sta) - mesh_path_del(mpath->dst, mpath->sdata); + if (rcu_dereference(mpath->next_hop) == sta) { + spin_lock_bh(&tbl->hashwlock[i]); + __mesh_path_del(tbl, node); + spin_unlock_bh(&tbl->hashwlock[i]); + } } + read_unlock_bh(&pathtbl_resize_lock); rcu_read_unlock(); } -void mesh_path_flush(struct ieee80211_sub_if_data *sdata) +static void table_flush_by_iface(struct mesh_table *tbl, + struct ieee80211_sub_if_data *sdata) { - struct mesh_table *tbl; struct mesh_path *mpath; struct mpath_node *node; struct hlist_node *p; int i; - rcu_read_lock(); - tbl = rcu_dereference(mesh_paths); + WARN_ON(!rcu_read_lock_held()); for_each_mesh_entry(tbl, p, node, i) { mpath = node->mpath; - if (mpath->sdata == sdata) - mesh_path_del(mpath->dst, mpath->sdata); + if (mpath->sdata != sdata) + continue; + spin_lock_bh(&tbl->hashwlock[i]); + __mesh_path_del(tbl, node); + spin_unlock_bh(&tbl->hashwlock[i]); } - rcu_read_unlock(); } -static void mesh_path_node_reclaim(struct rcu_head *rp) +/** + * mesh_path_flush_by_iface - Deletes all mesh paths associated with a given iface + * + * This function deletes both mesh paths as well as mesh portal paths. + * + * @sdata - interface data to match + * + */ +void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) { - struct mpath_node *node = container_of(rp, struct mpath_node, rcu); - struct ieee80211_sub_if_data *sdata = node->mpath->sdata; + struct mesh_table *tbl; - del_timer_sync(&node->mpath->timer); - atomic_dec(&sdata->u.mesh.mpaths); - kfree(node->mpath); - kfree(node); + rcu_read_lock(); + read_lock_bh(&pathtbl_resize_lock); + tbl = resize_dereference_mesh_paths(); + table_flush_by_iface(tbl, sdata); + tbl = resize_dereference_mpp_paths(); + table_flush_by_iface(tbl, sdata); + read_unlock_bh(&pathtbl_resize_lock); + rcu_read_unlock(); } /** @@ -647,12 +905,7 @@ int mesh_path_del(u8 *addr, struct ieee80211_sub_if_data *sdata) mpath = node->mpath; if (mpath->sdata == sdata && memcmp(addr, mpath->dst, ETH_ALEN) == 0) { - spin_lock(&mpath->state_lock); - mpath->flags |= MESH_PATH_RESOLVING; - hlist_del_rcu(&node->list); - call_rcu(&node->rcu, mesh_path_node_reclaim); - atomic_dec(&tbl->entries); - spin_unlock(&mpath->state_lock); + __mesh_path_del(tbl, node); goto enddel; } } @@ -681,6 +934,58 @@ void mesh_path_tx_pending(struct mesh_path *mpath) } /** + * mesh_path_send_to_gates - sends pending frames to all known mesh gates + * + * @mpath: mesh path whose queue will be emptied + * + * If there is only one gate, the frames are transferred from the failed mpath + * queue to that gate's queue. If there are more than one gates, the frames + * are copied from each gate to the next. After frames are copied, the + * mpath queues are emptied onto the transmission queue. + */ +int mesh_path_send_to_gates(struct mesh_path *mpath) +{ + struct ieee80211_sub_if_data *sdata = mpath->sdata; + struct hlist_node *n; + struct mesh_table *tbl; + struct mesh_path *from_mpath = mpath; + struct mpath_node *gate = NULL; + bool copy = false; + struct hlist_head *known_gates; + + rcu_read_lock(); + tbl = rcu_dereference(mesh_paths); + known_gates = tbl->known_gates; + rcu_read_unlock(); + + if (!known_gates) + return -EHOSTUNREACH; + + hlist_for_each_entry_rcu(gate, n, known_gates, list) { + if (gate->mpath->sdata != sdata) + continue; + + if (gate->mpath->flags & MESH_PATH_ACTIVE) { + mpath_dbg("Forwarding to %pM\n", gate->mpath->dst); + mesh_path_move_to_queue(gate->mpath, from_mpath, copy); + from_mpath = gate->mpath; + copy = true; + } else { + mpath_dbg("Not forwarding %p\n", gate->mpath); + mpath_dbg("flags %x\n", gate->mpath->flags); + } + } + + hlist_for_each_entry_rcu(gate, n, known_gates, list) + if (gate->mpath->sdata == sdata) { + mpath_dbg("Sending to %pM\n", gate->mpath->dst); + mesh_path_tx_pending(gate->mpath); + } + + return (from_mpath == mpath) ? -EHOSTUNREACH : 0; +} + +/** * mesh_path_discard_frame - discard a frame whose path could not be resolved * * @skb: frame to discard @@ -699,18 +1004,23 @@ void mesh_path_discard_frame(struct sk_buff *skb, struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct mesh_path *mpath; u32 sn = 0; + __le16 reason = cpu_to_le16(WLAN_REASON_MESH_PATH_NOFORWARD); if (memcmp(hdr->addr4, sdata->vif.addr, ETH_ALEN) != 0) { u8 *ra, *da; da = hdr->addr3; ra = hdr->addr1; + rcu_read_lock(); mpath = mesh_path_lookup(da, sdata); - if (mpath) + if (mpath) { + spin_lock_bh(&mpath->state_lock); sn = ++mpath->sn; + spin_unlock_bh(&mpath->state_lock); + } + rcu_read_unlock(); mesh_path_error_tx(sdata->u.mesh.mshcfg.element_ttl, skb->data, - cpu_to_le32(sn), - cpu_to_le16(PERR_RCODE_NO_ROUTE), ra, sdata); + cpu_to_le32(sn), reason, ra, sdata); } kfree_skb(skb); @@ -728,8 +1038,7 @@ void mesh_path_flush_pending(struct mesh_path *mpath) { struct sk_buff *skb; - while ((skb = skb_dequeue(&mpath->frame_queue)) && - (mpath->flags & MESH_PATH_ACTIVE)) + while ((skb = skb_dequeue(&mpath->frame_queue)) != NULL) mesh_path_discard_frame(skb, mpath->sdata); } @@ -790,6 +1099,7 @@ static int mesh_path_node_copy(struct hlist_node *p, struct mesh_table *newtbl) int mesh_pathtbl_init(void) { struct mesh_table *tbl_path, *tbl_mpp; + int ret; tbl_path = mesh_table_alloc(INIT_PATHS_SIZE_ORDER); if (!tbl_path) @@ -797,21 +1107,40 @@ int mesh_pathtbl_init(void) tbl_path->free_node = &mesh_path_node_free; tbl_path->copy_node = &mesh_path_node_copy; tbl_path->mean_chain_len = MEAN_CHAIN_LEN; + tbl_path->known_gates = kzalloc(sizeof(struct hlist_head), GFP_ATOMIC); + if (!tbl_path->known_gates) { + ret = -ENOMEM; + goto free_path; + } + INIT_HLIST_HEAD(tbl_path->known_gates); + tbl_mpp = mesh_table_alloc(INIT_PATHS_SIZE_ORDER); if (!tbl_mpp) { - mesh_table_free(tbl_path, true); - return -ENOMEM; + ret = -ENOMEM; + goto free_path; } tbl_mpp->free_node = &mesh_path_node_free; tbl_mpp->copy_node = &mesh_path_node_copy; tbl_mpp->mean_chain_len = MEAN_CHAIN_LEN; + tbl_mpp->known_gates = kzalloc(sizeof(struct hlist_head), GFP_ATOMIC); + if (!tbl_mpp->known_gates) { + ret = -ENOMEM; + goto free_mpp; + } + INIT_HLIST_HEAD(tbl_mpp->known_gates); /* Need no locking since this is during init */ RCU_INIT_POINTER(mesh_paths, tbl_path); RCU_INIT_POINTER(mpp_paths, tbl_mpp); return 0; + +free_mpp: + mesh_table_free(tbl_mpp, true); +free_path: + mesh_table_free(tbl_path, true); + return ret; } void mesh_path_expire(struct ieee80211_sub_if_data *sdata) @@ -828,14 +1157,10 @@ void mesh_path_expire(struct ieee80211_sub_if_data *sdata) if (node->mpath->sdata != sdata) continue; mpath = node->mpath; - spin_lock_bh(&mpath->state_lock); if ((!(mpath->flags & MESH_PATH_RESOLVING)) && (!(mpath->flags & MESH_PATH_FIXED)) && - time_after(jiffies, mpath->exp_time + MESH_PATH_EXPIRE)) { - spin_unlock_bh(&mpath->state_lock); + time_after(jiffies, mpath->exp_time + MESH_PATH_EXPIRE)) mesh_path_del(mpath->dst, mpath->sdata); - } else - spin_unlock_bh(&mpath->state_lock); } rcu_read_unlock(); } @@ -843,6 +1168,6 @@ void mesh_path_expire(struct ieee80211_sub_if_data *sdata) void mesh_pathtbl_unregister(void) { /* no need for locking during exit path */ - mesh_table_free(rcu_dereference_raw(mesh_paths), true); - mesh_table_free(rcu_dereference_raw(mpp_paths), true); + mesh_table_free(rcu_dereference_protected(mesh_paths, 1), true); + mesh_table_free(rcu_dereference_protected(mpp_paths, 1), true); } diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index f4adc09..7e57f5d 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -19,35 +19,18 @@ #define mpl_dbg(fmt, args...) do { (void)(0); } while (0) #endif -#define PLINK_GET_LLID(p) (p + 4) -#define PLINK_GET_PLID(p) (p + 6) +#define PLINK_GET_LLID(p) (p + 2) +#define PLINK_GET_PLID(p) (p + 4) #define mod_plink_timer(s, t) (mod_timer(&s->plink_timer, \ jiffies + HZ * t / 1000)) -/* Peer link cancel reasons, all subject to ANA approval */ -#define MESH_LINK_CANCELLED 2 -#define MESH_MAX_NEIGHBORS 3 -#define MESH_CAPABILITY_POLICY_VIOLATION 4 -#define MESH_CLOSE_RCVD 5 -#define MESH_MAX_RETRIES 6 -#define MESH_CONFIRM_TIMEOUT 7 -#define MESH_SECURITY_ROLE_NEGOTIATION_DIFFERS 8 -#define MESH_SECURITY_AUTHENTICATION_IMPOSSIBLE 9 -#define MESH_SECURITY_FAILED_VERIFICATION 10 - #define dot11MeshMaxRetries(s) (s->u.mesh.mshcfg.dot11MeshMaxRetries) #define dot11MeshRetryTimeout(s) (s->u.mesh.mshcfg.dot11MeshRetryTimeout) #define dot11MeshConfirmTimeout(s) (s->u.mesh.mshcfg.dot11MeshConfirmTimeout) #define dot11MeshHoldingTimeout(s) (s->u.mesh.mshcfg.dot11MeshHoldingTimeout) #define dot11MeshMaxPeerLinks(s) (s->u.mesh.mshcfg.dot11MeshMaxPeerLinks) -enum plink_frame_type { - PLINK_OPEN = 1, - PLINK_CONFIRM, - PLINK_CLOSE -}; - enum plink_event { PLINK_UNDEFINED, OPN_ACPT, @@ -60,6 +43,10 @@ enum plink_event { CLS_IGNR }; +static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, + enum ieee80211_self_protected_actioncode action, + u8 *da, __le16 llid, __le16 plid, __le16 reason); + static inline void mesh_plink_inc_estab_count(struct ieee80211_sub_if_data *sdata) { @@ -105,7 +92,9 @@ static struct sta_info *mesh_plink_alloc(struct ieee80211_sub_if_data *sdata, if (!sta) return NULL; - sta->flags = WLAN_STA_AUTHORIZED | WLAN_STA_AUTH; + set_sta_flag(sta, WLAN_STA_AUTH); + set_sta_flag(sta, WLAN_STA_AUTHORIZED); + set_sta_flag(sta, WLAN_STA_WME); sta->sta.supp_rates[local->hw.conf.channel->band] = rates; rate_control_rate_init(sta); @@ -150,6 +139,10 @@ void mesh_plink_deactivate(struct sta_info *sta) spin_lock_bh(&sta->lock); deactivated = __mesh_plink_deactivate(sta); + sta->reason = cpu_to_le16(WLAN_REASON_MESH_PEER_CANCELED); + mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, + sta->sta.addr, sta->llid, sta->plid, + sta->reason); spin_unlock_bh(&sta->lock); if (deactivated) @@ -157,16 +150,16 @@ void mesh_plink_deactivate(struct sta_info *sta) } static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, - enum plink_frame_type action, u8 *da, __le16 llid, __le16 plid, - __le16 reason) { + enum ieee80211_self_protected_actioncode action, + u8 *da, __le16 llid, __le16 plid, __le16 reason) { struct ieee80211_local *local = sdata->local; struct sk_buff *skb = dev_alloc_skb(local->hw.extra_tx_headroom + 400 + sdata->u.mesh.ie_len); struct ieee80211_mgmt *mgmt; bool include_plid = false; - static const u8 meshpeeringproto[] = { 0x00, 0x0F, 0xAC, 0x2A }; + int ie_len = 4; + u16 peering_proto = 0; u8 *pos; - int ie_len; if (!skb) return -1; @@ -175,63 +168,75 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, * common action part (1) */ mgmt = (struct ieee80211_mgmt *) - skb_put(skb, 25 + sizeof(mgmt->u.action.u.plink_action)); - memset(mgmt, 0, 25 + sizeof(mgmt->u.action.u.plink_action)); + skb_put(skb, 25 + sizeof(mgmt->u.action.u.self_prot)); + memset(mgmt, 0, 25 + sizeof(mgmt->u.action.u.self_prot)); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); memcpy(mgmt->da, da, ETH_ALEN); memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN); - mgmt->u.action.category = WLAN_CATEGORY_MESH_ACTION; - mgmt->u.action.u.plink_action.action_code = action; - - if (action == PLINK_CLOSE) - mgmt->u.action.u.plink_action.aux = reason; - else { - mgmt->u.action.u.plink_action.aux = cpu_to_le16(0x0); - if (action == PLINK_CONFIRM) { - pos = skb_put(skb, 4); - /* two-byte status code followed by two-byte AID */ - memset(pos, 0, 2); + mgmt->u.action.category = WLAN_CATEGORY_SELF_PROTECTED; + mgmt->u.action.u.self_prot.action_code = action; + + if (action != WLAN_SP_MESH_PEERING_CLOSE) { + /* capability info */ + pos = skb_put(skb, 2); + memset(pos, 0, 2); + if (action == WLAN_SP_MESH_PEERING_CONFIRM) { + /* AID */ + pos = skb_put(skb, 2); memcpy(pos + 2, &plid, 2); } - mesh_mgmt_ies_add(skb, sdata); + if (ieee80211_add_srates_ie(&sdata->vif, skb) || + ieee80211_add_ext_srates_ie(&sdata->vif, skb) || + mesh_add_rsn_ie(skb, sdata) || + mesh_add_meshid_ie(skb, sdata) || + mesh_add_meshconf_ie(skb, sdata)) + return -1; + } else { /* WLAN_SP_MESH_PEERING_CLOSE */ + if (mesh_add_meshid_ie(skb, sdata)) + return -1; } - /* Add Peer Link Management element */ + /* Add Mesh Peering Management element */ switch (action) { - case PLINK_OPEN: - ie_len = 6; + case WLAN_SP_MESH_PEERING_OPEN: break; - case PLINK_CONFIRM: - ie_len = 8; + case WLAN_SP_MESH_PEERING_CONFIRM: + ie_len += 2; include_plid = true; break; - case PLINK_CLOSE: - default: - if (!plid) - ie_len = 8; - else { - ie_len = 10; + case WLAN_SP_MESH_PEERING_CLOSE: + if (plid) { + ie_len += 2; include_plid = true; } + ie_len += 2; /* reason code */ break; + default: + return -EINVAL; } + if (WARN_ON(skb_tailroom(skb) < 2 + ie_len)) + return -ENOMEM; + pos = skb_put(skb, 2 + ie_len); - *pos++ = WLAN_EID_PEER_LINK; + *pos++ = WLAN_EID_PEER_MGMT; *pos++ = ie_len; - memcpy(pos, meshpeeringproto, sizeof(meshpeeringproto)); - pos += 4; + memcpy(pos, &peering_proto, 2); + pos += 2; memcpy(pos, &llid, 2); + pos += 2; if (include_plid) { - pos += 2; memcpy(pos, &plid, 2); - } - if (action == PLINK_CLOSE) { pos += 2; + } + if (action == WLAN_SP_MESH_PEERING_CLOSE) { memcpy(pos, &reason, 2); + pos += 2; } + if (mesh_add_vendor_ies(skb, sdata)) + return -1; ieee80211_tx_skb(sdata, skb); return 0; @@ -322,21 +327,21 @@ static void mesh_plink_timer(unsigned long data) ++sta->plink_retries; mod_plink_timer(sta, sta->plink_timeout); spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, PLINK_OPEN, sta->sta.addr, llid, - 0, 0); + mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_OPEN, + sta->sta.addr, llid, 0, 0); break; } - reason = cpu_to_le16(MESH_MAX_RETRIES); + reason = cpu_to_le16(WLAN_REASON_MESH_MAX_RETRIES); /* fall through on else */ case NL80211_PLINK_CNF_RCVD: /* confirm timer */ if (!reason) - reason = cpu_to_le16(MESH_CONFIRM_TIMEOUT); + reason = cpu_to_le16(WLAN_REASON_MESH_CONFIRM_TIMEOUT); sta->plink_state = NL80211_PLINK_HOLDING; mod_plink_timer(sta, dot11MeshHoldingTimeout(sdata)); spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, PLINK_CLOSE, sta->sta.addr, llid, plid, - reason); + mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, + sta->sta.addr, llid, plid, reason); break; case NL80211_PLINK_HOLDING: /* holding timer */ @@ -380,7 +385,7 @@ int mesh_plink_open(struct sta_info *sta) __le16 llid; struct ieee80211_sub_if_data *sdata = sta->sdata; - if (!test_sta_flags(sta, WLAN_STA_AUTH)) + if (!test_sta_flag(sta, WLAN_STA_AUTH)) return -EPERM; spin_lock_bh(&sta->lock); @@ -396,7 +401,7 @@ int mesh_plink_open(struct sta_info *sta) mpl_dbg("Mesh plink: starting establishment with %pM\n", sta->sta.addr); - return mesh_plink_frame_tx(sdata, PLINK_OPEN, + return mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_OPEN, sta->sta.addr, llid, 0, 0); } @@ -422,7 +427,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m struct ieee802_11_elems elems; struct sta_info *sta; enum plink_event event; - enum plink_frame_type ftype; + enum ieee80211_self_protected_actioncode ftype; size_t baselen; bool deactivated, matches_local = true; u8 ie_len; @@ -449,14 +454,15 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m return; } - baseaddr = mgmt->u.action.u.plink_action.variable; - baselen = (u8 *) mgmt->u.action.u.plink_action.variable - (u8 *) mgmt; - if (mgmt->u.action.u.plink_action.action_code == PLINK_CONFIRM) { + baseaddr = mgmt->u.action.u.self_prot.variable; + baselen = (u8 *) mgmt->u.action.u.self_prot.variable - (u8 *) mgmt; + if (mgmt->u.action.u.self_prot.action_code == + WLAN_SP_MESH_PEERING_CONFIRM) { baseaddr += 4; baselen += 4; } ieee802_11_parse_elems(baseaddr, len - baselen, &elems); - if (!elems.peer_link) { + if (!elems.peering) { mpl_dbg("Mesh plink: missing necessary peer link ie\n"); return; } @@ -466,37 +472,40 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m return; } - ftype = mgmt->u.action.u.plink_action.action_code; - ie_len = elems.peer_link_len; - if ((ftype == PLINK_OPEN && ie_len != 6) || - (ftype == PLINK_CONFIRM && ie_len != 8) || - (ftype == PLINK_CLOSE && ie_len != 8 && ie_len != 10)) { + ftype = mgmt->u.action.u.self_prot.action_code; + ie_len = elems.peering_len; + if ((ftype == WLAN_SP_MESH_PEERING_OPEN && ie_len != 4) || + (ftype == WLAN_SP_MESH_PEERING_CONFIRM && ie_len != 6) || + (ftype == WLAN_SP_MESH_PEERING_CLOSE && ie_len != 6 + && ie_len != 8)) { mpl_dbg("Mesh plink: incorrect plink ie length %d %d\n", ftype, ie_len); return; } - if (ftype != PLINK_CLOSE && (!elems.mesh_id || !elems.mesh_config)) { + if (ftype != WLAN_SP_MESH_PEERING_CLOSE && + (!elems.mesh_id || !elems.mesh_config)) { mpl_dbg("Mesh plink: missing necessary ie\n"); return; } /* Note the lines below are correct, the llid in the frame is the plid * from the point of view of this host. */ - memcpy(&plid, PLINK_GET_LLID(elems.peer_link), 2); - if (ftype == PLINK_CONFIRM || (ftype == PLINK_CLOSE && ie_len == 10)) - memcpy(&llid, PLINK_GET_PLID(elems.peer_link), 2); + memcpy(&plid, PLINK_GET_LLID(elems.peering), 2); + if (ftype == WLAN_SP_MESH_PEERING_CONFIRM || + (ftype == WLAN_SP_MESH_PEERING_CLOSE && ie_len == 8)) + memcpy(&llid, PLINK_GET_PLID(elems.peering), 2); rcu_read_lock(); sta = sta_info_get(sdata, mgmt->sa); - if (!sta && ftype != PLINK_OPEN) { + if (!sta && ftype != WLAN_SP_MESH_PEERING_OPEN) { mpl_dbg("Mesh plink: cls or cnf from unknown peer\n"); rcu_read_unlock(); return; } - if (sta && !test_sta_flags(sta, WLAN_STA_AUTH)) { + if (sta && !test_sta_flag(sta, WLAN_STA_AUTH)) { mpl_dbg("Mesh plink: Action frame from non-authed peer\n"); rcu_read_unlock(); return; @@ -509,30 +518,30 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m /* Now we will figure out the appropriate event... */ event = PLINK_UNDEFINED; - if (ftype != PLINK_CLOSE && (!mesh_matches_local(&elems, sdata))) { + if (ftype != WLAN_SP_MESH_PEERING_CLOSE && + (!mesh_matches_local(&elems, sdata))) { matches_local = false; switch (ftype) { - case PLINK_OPEN: + case WLAN_SP_MESH_PEERING_OPEN: event = OPN_RJCT; break; - case PLINK_CONFIRM: + case WLAN_SP_MESH_PEERING_CONFIRM: event = CNF_RJCT; break; - case PLINK_CLOSE: - /* avoid warning */ + default: break; } } if (!sta && !matches_local) { rcu_read_unlock(); - reason = cpu_to_le16(MESH_CAPABILITY_POLICY_VIOLATION); + reason = cpu_to_le16(WLAN_REASON_MESH_CONFIG); llid = 0; - mesh_plink_frame_tx(sdata, PLINK_CLOSE, mgmt->sa, llid, - plid, reason); + mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, + mgmt->sa, llid, plid, reason); return; } else if (!sta) { - /* ftype == PLINK_OPEN */ + /* ftype == WLAN_SP_MESH_PEERING_OPEN */ u32 rates; rcu_read_unlock(); @@ -557,21 +566,21 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m } else if (matches_local) { spin_lock_bh(&sta->lock); switch (ftype) { - case PLINK_OPEN: + case WLAN_SP_MESH_PEERING_OPEN: if (!mesh_plink_free_count(sdata) || (sta->plid && sta->plid != plid)) event = OPN_IGNR; else event = OPN_ACPT; break; - case PLINK_CONFIRM: + case WLAN_SP_MESH_PEERING_CONFIRM: if (!mesh_plink_free_count(sdata) || (sta->llid != llid || sta->plid != plid)) event = CNF_IGNR; else event = CNF_ACPT; break; - case PLINK_CLOSE: + case WLAN_SP_MESH_PEERING_CLOSE: if (sta->plink_state == NL80211_PLINK_ESTAB) /* Do not check for llid or plid. This does not * follow the standard but since multiple plinks @@ -620,10 +629,12 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m sta->llid = llid; mesh_plink_timer_set(sta, dot11MeshRetryTimeout(sdata)); spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, PLINK_OPEN, sta->sta.addr, llid, - 0, 0); - mesh_plink_frame_tx(sdata, PLINK_CONFIRM, sta->sta.addr, - llid, plid, 0); + mesh_plink_frame_tx(sdata, + WLAN_SP_MESH_PEERING_OPEN, + sta->sta.addr, llid, 0, 0); + mesh_plink_frame_tx(sdata, + WLAN_SP_MESH_PEERING_CONFIRM, + sta->sta.addr, llid, plid, 0); break; default: spin_unlock_bh(&sta->lock); @@ -635,10 +646,10 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m switch (event) { case OPN_RJCT: case CNF_RJCT: - reason = cpu_to_le16(MESH_CAPABILITY_POLICY_VIOLATION); + reason = cpu_to_le16(WLAN_REASON_MESH_CONFIG); case CLS_ACPT: if (!reason) - reason = cpu_to_le16(MESH_CLOSE_RCVD); + reason = cpu_to_le16(WLAN_REASON_MESH_CLOSE); sta->reason = reason; sta->plink_state = NL80211_PLINK_HOLDING; if (!mod_plink_timer(sta, @@ -647,8 +658,9 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m llid = sta->llid; spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, PLINK_CLOSE, sta->sta.addr, llid, - plid, reason); + mesh_plink_frame_tx(sdata, + WLAN_SP_MESH_PEERING_CLOSE, + sta->sta.addr, llid, plid, reason); break; case OPN_ACPT: /* retry timer is left untouched */ @@ -656,8 +668,9 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m sta->plid = plid; llid = sta->llid; spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, PLINK_CONFIRM, sta->sta.addr, llid, - plid, 0); + mesh_plink_frame_tx(sdata, + WLAN_SP_MESH_PEERING_CONFIRM, + sta->sta.addr, llid, plid, 0); break; case CNF_ACPT: sta->plink_state = NL80211_PLINK_CNF_RCVD; @@ -677,10 +690,10 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m switch (event) { case OPN_RJCT: case CNF_RJCT: - reason = cpu_to_le16(MESH_CAPABILITY_POLICY_VIOLATION); + reason = cpu_to_le16(WLAN_REASON_MESH_CONFIG); case CLS_ACPT: if (!reason) - reason = cpu_to_le16(MESH_CLOSE_RCVD); + reason = cpu_to_le16(WLAN_REASON_MESH_CLOSE); sta->reason = reason; sta->plink_state = NL80211_PLINK_HOLDING; if (!mod_plink_timer(sta, @@ -689,14 +702,15 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m llid = sta->llid; spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, PLINK_CLOSE, sta->sta.addr, llid, - plid, reason); + mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, + sta->sta.addr, llid, plid, reason); break; case OPN_ACPT: llid = sta->llid; spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, PLINK_CONFIRM, sta->sta.addr, llid, - plid, 0); + mesh_plink_frame_tx(sdata, + WLAN_SP_MESH_PEERING_CONFIRM, + sta->sta.addr, llid, plid, 0); break; case CNF_ACPT: del_timer(&sta->plink_timer); @@ -717,10 +731,10 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m switch (event) { case OPN_RJCT: case CNF_RJCT: - reason = cpu_to_le16(MESH_CAPABILITY_POLICY_VIOLATION); + reason = cpu_to_le16(WLAN_REASON_MESH_CONFIG); case CLS_ACPT: if (!reason) - reason = cpu_to_le16(MESH_CLOSE_RCVD); + reason = cpu_to_le16(WLAN_REASON_MESH_CLOSE); sta->reason = reason; sta->plink_state = NL80211_PLINK_HOLDING; if (!mod_plink_timer(sta, @@ -729,8 +743,9 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m llid = sta->llid; spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, PLINK_CLOSE, sta->sta.addr, llid, - plid, reason); + mesh_plink_frame_tx(sdata, + WLAN_SP_MESH_PEERING_CLOSE, + sta->sta.addr, llid, plid, reason); break; case OPN_ACPT: del_timer(&sta->plink_timer); @@ -740,8 +755,9 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON); mpl_dbg("Mesh plink with %pM ESTABLISHED\n", sta->sta.addr); - mesh_plink_frame_tx(sdata, PLINK_CONFIRM, sta->sta.addr, llid, - plid, 0); + mesh_plink_frame_tx(sdata, + WLAN_SP_MESH_PEERING_CONFIRM, + sta->sta.addr, llid, plid, 0); break; default: spin_unlock_bh(&sta->lock); @@ -752,7 +768,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m case NL80211_PLINK_ESTAB: switch (event) { case CLS_ACPT: - reason = cpu_to_le16(MESH_CLOSE_RCVD); + reason = cpu_to_le16(WLAN_REASON_MESH_CLOSE); sta->reason = reason; deactivated = __mesh_plink_deactivate(sta); sta->plink_state = NL80211_PLINK_HOLDING; @@ -761,14 +777,15 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m spin_unlock_bh(&sta->lock); if (deactivated) ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON); - mesh_plink_frame_tx(sdata, PLINK_CLOSE, sta->sta.addr, llid, - plid, reason); + mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, + sta->sta.addr, llid, plid, reason); break; case OPN_ACPT: llid = sta->llid; spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, PLINK_CONFIRM, sta->sta.addr, llid, - plid, 0); + mesh_plink_frame_tx(sdata, + WLAN_SP_MESH_PEERING_CONFIRM, + sta->sta.addr, llid, plid, 0); break; default: spin_unlock_bh(&sta->lock); @@ -790,8 +807,8 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m llid = sta->llid; reason = sta->reason; spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, PLINK_CLOSE, sta->sta.addr, - llid, plid, reason); + mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, + sta->sta.addr, llid, plid, reason); break; default: spin_unlock_bh(&sta->lock); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index d6470c7..ba2da11 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -17,7 +17,7 @@ #include <linux/if_arp.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> -#include <linux/pm_qos_params.h> +#include <linux/pm_qos.h> #include <linux/crc32.h> #include <linux/slab.h> #include <net/mac80211.h> @@ -160,7 +160,8 @@ static int ecw2cw(int ecw) */ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, struct ieee80211_ht_info *hti, - const u8 *bssid, u16 ap_ht_cap_flags) + const u8 *bssid, u16 ap_ht_cap_flags, + bool beacon_htcap_ie) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; @@ -232,6 +233,21 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, WARN_ON(!ieee80211_set_channel_type(local, sdata, channel_type)); } + if (beacon_htcap_ie && (prev_chantype != channel_type)) { + /* + * Whenever the AP announces the HT mode change that can be + * 40MHz intolerant or etc., it would be safer to stop tx + * queues before doing hw config to avoid buffer overflow. + */ + ieee80211_stop_queues_by_reason(&sdata->local->hw, + IEEE80211_QUEUE_STOP_REASON_CHTYPE_CHANGE); + + /* flush out all packets */ + synchronize_net(); + + drv_flush(local, false); + } + /* channel_type change automatically detected */ ieee80211_hw_config(local, 0); @@ -243,6 +259,10 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, IEEE80211_RC_HT_CHANGED, channel_type); rcu_read_unlock(); + + if (beacon_htcap_ie) + ieee80211_wake_queues_by_reason(&sdata->local->hw, + IEEE80211_QUEUE_STOP_REASON_CHTYPE_CHANGE); } ht_opmode = le16_to_cpu(hti->operation_mode); @@ -271,11 +291,9 @@ static void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt; skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(*mgmt)); - if (!skb) { - printk(KERN_DEBUG "%s: failed to allocate buffer for " - "deauth/disassoc frame\n", sdata->name); + if (!skb) return; - } + skb_reserve(skb, local->hw.extra_tx_headroom); mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24); @@ -330,6 +348,7 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, { struct sk_buff *skb; struct ieee80211_hdr_3addr *nullfunc; + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif); if (!skb) @@ -340,6 +359,10 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, nullfunc->frame_control |= cpu_to_le16(IEEE80211_FCTL_PM); IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; + if (ifmgd->flags & (IEEE80211_STA_BEACON_POLL | + IEEE80211_STA_CONNECTION_POLL)) + IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_USE_MINRATE; + ieee80211_tx_skb(sdata, skb); } @@ -354,11 +377,9 @@ static void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, return; skb = dev_alloc_skb(local->hw.extra_tx_headroom + 30); - if (!skb) { - printk(KERN_DEBUG "%s: failed to allocate buffer for 4addr " - "nullfunc frame\n", sdata->name); + if (!skb) return; - } + skb_reserve(skb, local->hw.extra_tx_headroom); nullfunc = (struct ieee80211_hdr *) skb_put(skb, 30); @@ -394,6 +415,9 @@ static void ieee80211_chswitch_work(struct work_struct *work) /* call "hw_config" only if doing sw channel switch */ ieee80211_hw_config(sdata->local, IEEE80211_CONF_CHANGE_CHANNEL); + } else { + /* update the device channel directly */ + sdata->local->hw.conf.channel = sdata->local->oper_channel; } /* XXX: shouldn't really modify cfg80211-owned data! */ @@ -608,7 +632,7 @@ static bool ieee80211_powersave_allowed(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *mgd = &sdata->u.mgd; struct sta_info *sta = NULL; - u32 sta_flags = 0; + bool authorized = false; if (!mgd->powersave) return false; @@ -626,13 +650,10 @@ static bool ieee80211_powersave_allowed(struct ieee80211_sub_if_data *sdata) rcu_read_lock(); sta = sta_info_get(sdata, mgd->bssid); if (sta) - sta_flags = get_sta_flags(sta); + authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED); rcu_read_unlock(); - if (!(sta_flags & WLAN_STA_AUTHORIZED)) - return false; - - return true; + return authorized; } /* need to hold RTNL or interface lock */ @@ -917,8 +938,8 @@ static void ieee80211_sta_wmm_params(struct ieee80211_local *local, params.aifs, params.cw_min, params.cw_max, params.txop, params.uapsd); #endif - local->tx_conf[queue] = params; - if (drv_conf_tx(local, queue, ¶ms)) + sdata->tx_conf[queue] = params; + if (drv_conf_tx(local, sdata, queue, ¶ms)) wiphy_debug(local->hw.wiphy, "failed to set TX queue parameters for queue %d\n", queue); @@ -1076,7 +1097,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, mutex_lock(&local->sta_mtx); sta = sta_info_get(sdata, bssid); if (sta) { - set_sta_flags(sta, WLAN_STA_BLOCK_BA); + set_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_sta_tear_down_BA_sessions(sta, tx); } mutex_unlock(&local->sta_mtx); @@ -1118,8 +1139,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, changed |= BSS_CHANGED_BSSID | BSS_CHANGED_HT; ieee80211_bss_info_change_notify(sdata, changed); + /* remove AP and TDLS peers */ if (remove_sta) - sta_info_destroy_addr(sdata, bssid); + sta_info_flush(local, sdata); del_timer_sync(&sdata->u.mgd.conn_mon_timer); del_timer_sync(&sdata->u.mgd.bcn_mon_timer); @@ -1220,7 +1242,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) } else { ssid = ieee80211_bss_get_ie(ifmgd->associated, WLAN_EID_SSID); ieee80211_send_probe_req(sdata, dst, ssid + 2, ssid[1], NULL, 0, - (u32) -1, true); + (u32) -1, true, false); } ifmgd->probe_send_count++; @@ -1482,17 +1504,22 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk, ifmgd->aid = aid; - sta = sta_info_alloc(sdata, cbss->bssid, GFP_KERNEL); - if (!sta) { - printk(KERN_DEBUG "%s: failed to alloc STA entry for" - " the AP\n", sdata->name); + mutex_lock(&sdata->local->sta_mtx); + /* + * station info was already allocated and inserted before + * the association and should be available to us + */ + sta = sta_info_get_rx(sdata, cbss->bssid); + if (WARN_ON(!sta)) { + mutex_unlock(&sdata->local->sta_mtx); return false; } - set_sta_flags(sta, WLAN_STA_AUTH | WLAN_STA_ASSOC | - WLAN_STA_ASSOC_AP); + set_sta_flag(sta, WLAN_STA_AUTH); + set_sta_flag(sta, WLAN_STA_ASSOC); + set_sta_flag(sta, WLAN_STA_ASSOC_AP); if (!(ifmgd->flags & IEEE80211_STA_CONTROL_PORT)) - set_sta_flags(sta, WLAN_STA_AUTHORIZED); + set_sta_flag(sta, WLAN_STA_AUTHORIZED); rates = 0; basic_rates = 0; @@ -1551,12 +1578,13 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk, rate_control_rate_init(sta); if (ifmgd->flags & IEEE80211_STA_MFP_ENABLED) - set_sta_flags(sta, WLAN_STA_MFP); + set_sta_flag(sta, WLAN_STA_MFP); if (elems.wmm_param) - set_sta_flags(sta, WLAN_STA_WME); + set_sta_flag(sta, WLAN_STA_WME); - err = sta_info_insert(sta); + /* sta_info_reinsert will also unlock the mutex lock */ + err = sta_info_reinsert(sta); sta = NULL; if (err) { printk(KERN_DEBUG "%s: failed to insert STA entry for" @@ -1584,7 +1612,8 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk, (sdata->local->hw.queues >= 4) && !(ifmgd->flags & IEEE80211_STA_DISABLE_11N)) changed |= ieee80211_enable_ht(sdata, elems.ht_info_elem, - cbss->bssid, ap_ht_cap_flags); + cbss->bssid, ap_ht_cap_flags, + false); /* set AID and assoc capability, * ieee80211_set_associated() will tell the driver */ @@ -1918,7 +1947,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); changed |= ieee80211_enable_ht(sdata, elems.ht_info_elem, - bssid, ap_ht_cap_flags); + bssid, ap_ht_cap_flags, true); } /* Note: country IE parsing is done for us by cfg80211 */ @@ -2429,6 +2458,29 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, return 0; } +/* create and insert a dummy station entry */ +static int ieee80211_pre_assoc(struct ieee80211_sub_if_data *sdata, + u8 *bssid) { + struct sta_info *sta; + int err; + + sta = sta_info_alloc(sdata, bssid, GFP_KERNEL); + if (!sta) + return -ENOMEM; + + sta->dummy = true; + + err = sta_info_insert(sta); + sta = NULL; + if (err) { + printk(KERN_DEBUG "%s: failed to insert Dummy STA entry for" + " the AP (error %d)\n", sdata->name, err); + return err; + } + + return 0; +} + static enum work_done_result ieee80211_assoc_done(struct ieee80211_work *wk, struct sk_buff *skb) { @@ -2436,9 +2488,11 @@ static enum work_done_result ieee80211_assoc_done(struct ieee80211_work *wk, struct ieee80211_mgmt *mgmt; struct ieee80211_rx_status *rx_status; struct ieee802_11_elems elems; + struct cfg80211_bss *cbss = wk->assoc.bss; u16 status; if (!skb) { + sta_info_destroy_addr(wk->sdata, cbss->bssid); cfg80211_send_assoc_timeout(wk->sdata->dev, wk->filter_ta); goto destroy; } @@ -2468,12 +2522,16 @@ static enum work_done_result ieee80211_assoc_done(struct ieee80211_work *wk, if (!ieee80211_assoc_success(wk, mgmt, skb->len)) { mutex_unlock(&wk->sdata->u.mgd.mtx); /* oops -- internal error -- send timeout for now */ + sta_info_destroy_addr(wk->sdata, cbss->bssid); cfg80211_send_assoc_timeout(wk->sdata->dev, wk->filter_ta); return WORK_DONE_DESTROY; } mutex_unlock(&wk->sdata->u.mgd.mtx); + } else { + /* assoc failed - destroy the dummy station entry */ + sta_info_destroy_addr(wk->sdata, cbss->bssid); } cfg80211_send_rx_assoc(wk->sdata->dev, skb->data, skb->len); @@ -2492,7 +2550,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, struct ieee80211_bss *bss = (void *)req->bss->priv; struct ieee80211_work *wk; const u8 *ssid; - int i; + int i, err; mutex_lock(&ifmgd->mtx); if (ifmgd->associated) { @@ -2517,6 +2575,16 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, if (!wk) return -ENOMEM; + /* + * create a dummy station info entry in order + * to start accepting incoming EAPOL packets from the station + */ + err = ieee80211_pre_assoc(sdata, req->bss->bssid); + if (err) { + kfree(wk); + return err; + } + ifmgd->flags &= ~IEEE80211_STA_DISABLE_11N; ifmgd->flags &= ~IEEE80211_STA_NULLFUNC_ACKED; @@ -2674,7 +2742,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, req->reason_code, cookie, !req->local_state_change); if (assoc_bss) - sta_info_destroy_addr(sdata, bssid); + sta_info_flush(sdata->local, sdata); mutex_lock(&sdata->local->mtx); ieee80211_recalc_idle(sdata->local); @@ -2714,7 +2782,7 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_send_deauth_disassoc(sdata, req->bss->bssid, IEEE80211_STYPE_DISASSOC, req->reason_code, cookie, !req->local_state_change); - sta_info_destroy_addr(sdata, bssid); + sta_info_flush(sdata->local, sdata); mutex_lock(&sdata->local->mtx); ieee80211_recalc_idle(sdata->local); diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 6326d34..9ee7164 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -42,7 +42,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) if (hw->flags & IEEE80211_HW_AMPDU_AGGREGATION) { mutex_lock(&local->sta_mtx); list_for_each_entry(sta, &local->sta_list, list) { - set_sta_flags(sta, WLAN_STA_BLOCK_BA); + set_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_sta_tear_down_BA_sessions(sta, true); } mutex_unlock(&local->sta_mtx); diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 3d5a2cb..ff5c3aa 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -199,7 +199,7 @@ static void rate_control_release(struct kref *kref) kfree(ctrl_ref); } -static bool rc_no_data_or_no_ack(struct ieee80211_tx_rate_control *txrc) +static bool rc_no_data_or_no_ack_use_min(struct ieee80211_tx_rate_control *txrc) { struct sk_buff *skb = txrc->skb; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; @@ -208,7 +208,9 @@ static bool rc_no_data_or_no_ack(struct ieee80211_tx_rate_control *txrc) fc = hdr->frame_control; - return (info->flags & IEEE80211_TX_CTL_NO_ACK) || !ieee80211_is_data(fc); + return (info->flags & (IEEE80211_TX_CTL_NO_ACK | + IEEE80211_TX_CTL_USE_MINRATE)) || + !ieee80211_is_data(fc); } static void rc_send_low_broadcast(s8 *idx, u32 basic_rates, @@ -233,6 +235,27 @@ static void rc_send_low_broadcast(s8 *idx, u32 basic_rates, /* could not find a basic rate; use original selection */ } +static inline s8 +rate_lowest_non_cck_index(struct ieee80211_supported_band *sband, + struct ieee80211_sta *sta) +{ + int i; + + for (i = 0; i < sband->n_bitrates; i++) { + struct ieee80211_rate *srate = &sband->bitrates[i]; + if ((srate->bitrate == 10) || (srate->bitrate == 20) || + (srate->bitrate == 55) || (srate->bitrate == 110)) + continue; + + if (rate_supported(sta, sband->band, i)) + return i; + } + + /* No matching rate found */ + return 0; +} + + bool rate_control_send_low(struct ieee80211_sta *sta, void *priv_sta, struct ieee80211_tx_rate_control *txrc) @@ -241,8 +264,14 @@ bool rate_control_send_low(struct ieee80211_sta *sta, struct ieee80211_supported_band *sband = txrc->sband; int mcast_rate; - if (!sta || !priv_sta || rc_no_data_or_no_ack(txrc)) { - info->control.rates[0].idx = rate_lowest_index(txrc->sband, sta); + if (!sta || !priv_sta || rc_no_data_or_no_ack_use_min(txrc)) { + if ((sband->band != IEEE80211_BAND_2GHZ) || + !(info->flags & IEEE80211_TX_CTL_NO_CCK_RATE)) + info->control.rates[0].idx = + rate_lowest_index(txrc->sband, sta); + else + info->control.rates[0].idx = + rate_lowest_non_cck_index(txrc->sband, sta); info->control.rates[0].count = (info->flags & IEEE80211_TX_CTL_NO_ACK) ? 1 : txrc->hw->max_rate_tries; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 66a1eeb..cdb2853 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -281,6 +281,8 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) mr = minstrel_get_ratestats(mi, mg->max_tp_rate); if (cur_tp < mr->cur_tp) { + mi->max_tp_rate2 = mi->max_tp_rate; + cur_tp2 = cur_tp; mi->max_tp_rate = mg->max_tp_rate; cur_tp = mr->cur_tp; } @@ -452,7 +454,8 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, if (time_after(jiffies, mi->stats_update + (mp->update_interval / 2 * HZ) / 1000)) { minstrel_ht_update_stats(mp, mi); - minstrel_aggr_check(mp, sta, skb); + if (!(info->flags & IEEE80211_TX_CTL_AMPDU)) + minstrel_aggr_check(mp, sta, skb); } } @@ -608,7 +611,13 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, return mac80211_minstrel.get_rate(priv, sta, &msp->legacy, txrc); info->flags |= mi->tx_flags; - sample_idx = minstrel_get_sample_rate(mp, mi); + + /* Don't use EAPOL frames for sampling on non-mrr hw */ + if (mp->hw->max_rates == 1 && + txrc->skb->protocol == cpu_to_be16(ETH_P_PAE)) + sample_idx = -1; + else + sample_idx = minstrel_get_sample_rate(mp, mi); #ifdef CONFIG_MAC80211_DEBUGFS /* use fixed index if set */ diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index fe2c2a7..b867bd5 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -476,7 +476,6 @@ static ieee80211_rx_result ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; - unsigned int hdrlen = ieee80211_hdrlen(hdr->frame_control); char *dev_addr = rx->sdata->vif.addr; if (ieee80211_is_data(hdr->frame_control)) { @@ -524,14 +523,6 @@ ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx) } -#define msh_h_get(h, l) ((struct ieee80211s_hdr *) ((u8 *)h + l)) - - if (ieee80211_is_data(hdr->frame_control) && - is_multicast_ether_addr(hdr->addr1) && - mesh_rmc_check(hdr->addr3, msh_h_get(hdr, hdrlen), rx->sdata)) - return RX_DROP_MONITOR; -#undef msh_h_get - return RX_CONTINUE; } @@ -850,8 +841,21 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx) ieee80211_is_pspoll(hdr->frame_control)) && rx->sdata->vif.type != NL80211_IFTYPE_ADHOC && rx->sdata->vif.type != NL80211_IFTYPE_WDS && - (!rx->sta || !test_sta_flags(rx->sta, WLAN_STA_ASSOC)))) + (!rx->sta || !test_sta_flag(rx->sta, WLAN_STA_ASSOC)))) { + if (rx->sta && rx->sta->dummy && + ieee80211_is_data_present(hdr->frame_control)) { + u16 ethertype; + u8 *payload; + + payload = rx->skb->data + + ieee80211_hdrlen(hdr->frame_control); + ethertype = (payload[6] << 8) | payload[7]; + if (cpu_to_be16(ethertype) == + rx->sdata->control_port_protocol) + return RX_CONTINUE; + } return RX_DROP_MONITOR; + } return RX_CONTINUE; } @@ -1106,7 +1110,7 @@ static void ap_sta_ps_start(struct sta_info *sta) struct ieee80211_local *local = sdata->local; atomic_inc(&sdata->bss->num_sta_ps); - set_sta_flags(sta, WLAN_STA_PS_STA); + set_sta_flag(sta, WLAN_STA_PS_STA); if (!(local->hw.flags & IEEE80211_HW_AP_LINK_PS)) drv_sta_notify(local, sdata, STA_NOTIFY_SLEEP, &sta->sta); #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG @@ -1126,7 +1130,7 @@ static void ap_sta_ps_end(struct sta_info *sta) sdata->name, sta->sta.addr, sta->sta.aid); #endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ - if (test_sta_flags(sta, WLAN_STA_PS_DRIVER)) { + if (test_sta_flag(sta, WLAN_STA_PS_DRIVER)) { #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG printk(KERN_DEBUG "%s: STA %pM aid %d driver-ps-blocked\n", sdata->name, sta->sta.addr, sta->sta.aid); @@ -1145,7 +1149,7 @@ int ieee80211_sta_ps_transition(struct ieee80211_sta *sta, bool start) WARN_ON(!(sta_inf->local->hw.flags & IEEE80211_HW_AP_LINK_PS)); /* Don't let the same PS state be set twice */ - in_ps = test_sta_flags(sta_inf, WLAN_STA_PS_STA); + in_ps = test_sta_flag(sta_inf, WLAN_STA_PS_STA); if ((start && in_ps) || (!start && !in_ps)) return -EINVAL; @@ -1159,6 +1163,81 @@ int ieee80211_sta_ps_transition(struct ieee80211_sta *sta, bool start) EXPORT_SYMBOL(ieee80211_sta_ps_transition); static ieee80211_rx_result debug_noinline +ieee80211_rx_h_uapsd_and_pspoll(struct ieee80211_rx_data *rx) +{ + struct ieee80211_sub_if_data *sdata = rx->sdata; + struct ieee80211_hdr *hdr = (void *)rx->skb->data; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); + int tid, ac; + + if (!rx->sta || !(status->rx_flags & IEEE80211_RX_RA_MATCH)) + return RX_CONTINUE; + + if (sdata->vif.type != NL80211_IFTYPE_AP && + sdata->vif.type != NL80211_IFTYPE_AP_VLAN) + return RX_CONTINUE; + + /* + * The device handles station powersave, so don't do anything about + * uAPSD and PS-Poll frames (the latter shouldn't even come up from + * it to mac80211 since they're handled.) + */ + if (sdata->local->hw.flags & IEEE80211_HW_AP_LINK_PS) + return RX_CONTINUE; + + /* + * Don't do anything if the station isn't already asleep. In + * the uAPSD case, the station will probably be marked asleep, + * in the PS-Poll case the station must be confused ... + */ + if (!test_sta_flag(rx->sta, WLAN_STA_PS_STA)) + return RX_CONTINUE; + + if (unlikely(ieee80211_is_pspoll(hdr->frame_control))) { + if (!test_sta_flag(rx->sta, WLAN_STA_SP)) { + if (!test_sta_flag(rx->sta, WLAN_STA_PS_DRIVER)) + ieee80211_sta_ps_deliver_poll_response(rx->sta); + else + set_sta_flag(rx->sta, WLAN_STA_PSPOLL); + } + + /* Free PS Poll skb here instead of returning RX_DROP that would + * count as an dropped frame. */ + dev_kfree_skb(rx->skb); + + return RX_QUEUED; + } else if (!ieee80211_has_morefrags(hdr->frame_control) && + !(status->rx_flags & IEEE80211_RX_DEFERRED_RELEASE) && + ieee80211_has_pm(hdr->frame_control) && + (ieee80211_is_data_qos(hdr->frame_control) || + ieee80211_is_qos_nullfunc(hdr->frame_control))) { + tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; + ac = ieee802_1d_to_ac[tid & 7]; + + /* + * If this AC is not trigger-enabled do nothing. + * + * NB: This could/should check a separate bitmap of trigger- + * enabled queues, but for now we only implement uAPSD w/o + * TSPEC changes to the ACs, so they're always the same. + */ + if (!(rx->sta->sta.uapsd_queues & BIT(ac))) + return RX_CONTINUE; + + /* if we are in a service period, do nothing */ + if (test_sta_flag(rx->sta, WLAN_STA_SP)) + return RX_CONTINUE; + + if (!test_sta_flag(rx->sta, WLAN_STA_PS_DRIVER)) + ieee80211_sta_ps_deliver_uapsd(rx->sta); + else + set_sta_flag(rx->sta, WLAN_STA_UAPSD); + } + + return RX_CONTINUE; +} + +static ieee80211_rx_result debug_noinline ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) { struct sta_info *sta = rx->sta; @@ -1216,7 +1295,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) !(status->rx_flags & IEEE80211_RX_DEFERRED_RELEASE) && (rx->sdata->vif.type == NL80211_IFTYPE_AP || rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN)) { - if (test_sta_flags(sta, WLAN_STA_PS_STA)) { + if (test_sta_flag(sta, WLAN_STA_PS_STA)) { /* * Ignore doze->wake transitions that are * indicated by non-data frames, the standard @@ -1469,33 +1548,6 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) } static ieee80211_rx_result debug_noinline -ieee80211_rx_h_ps_poll(struct ieee80211_rx_data *rx) -{ - struct ieee80211_sub_if_data *sdata = rx->sdata; - __le16 fc = ((struct ieee80211_hdr *)rx->skb->data)->frame_control; - struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); - - if (likely(!rx->sta || !ieee80211_is_pspoll(fc) || - !(status->rx_flags & IEEE80211_RX_RA_MATCH))) - return RX_CONTINUE; - - if ((sdata->vif.type != NL80211_IFTYPE_AP) && - (sdata->vif.type != NL80211_IFTYPE_AP_VLAN)) - return RX_DROP_UNUSABLE; - - if (!test_sta_flags(rx->sta, WLAN_STA_PS_DRIVER)) - ieee80211_sta_ps_deliver_poll_response(rx->sta); - else - set_sta_flags(rx->sta, WLAN_STA_PSPOLL); - - /* Free PS Poll skb here instead of returning RX_DROP that would - * count as an dropped frame. */ - dev_kfree_skb(rx->skb); - - return RX_QUEUED; -} - -static ieee80211_rx_result debug_noinline ieee80211_rx_h_remove_qos_control(struct ieee80211_rx_data *rx) { u8 *data = rx->skb->data; @@ -1518,7 +1570,7 @@ static int ieee80211_802_1x_port_control(struct ieee80211_rx_data *rx) { if (unlikely(!rx->sta || - !test_sta_flags(rx->sta, WLAN_STA_AUTHORIZED))) + !test_sta_flag(rx->sta, WLAN_STA_AUTHORIZED))) return -EACCES; return 0; @@ -1561,7 +1613,7 @@ ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx) if (status->flag & RX_FLAG_DECRYPTED) return 0; - if (rx->sta && test_sta_flags(rx->sta, WLAN_STA_MFP)) { + if (rx->sta && test_sta_flag(rx->sta, WLAN_STA_MFP)) { if (unlikely(!ieee80211_has_protected(fc) && ieee80211_is_unicast_robust_mgmt_frame(rx->skb) && rx->key)) { @@ -1827,6 +1879,12 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) hdrlen = ieee80211_hdrlen(hdr->frame_control); mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); + /* frame is in RMC, don't forward */ + if (ieee80211_is_data(hdr->frame_control) && + is_multicast_ether_addr(hdr->addr1) && + mesh_rmc_check(hdr->addr3, mesh_hdr, rx->sdata)) + return RX_DROP_MONITOR; + if (!ieee80211_is_data(hdr->frame_control)) return RX_CONTINUE; @@ -1834,6 +1892,12 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) /* illegal frame */ return RX_DROP_MONITOR; + if (ieee80211_queue_stopped(&local->hw, skb_get_queue_mapping(skb))) { + IEEE80211_IFSTA_MESH_CTR_INC(&sdata->u.mesh, + dropped_frames_congestion); + return RX_DROP_MONITOR; + } + if (mesh_hdr->flags & MESH_FLAGS_AE) { struct mesh_path *mppath; char *proxied_addr; @@ -1889,13 +1953,13 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) memset(info, 0, sizeof(*info)); info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; info->control.vif = &rx->sdata->vif; - skb_set_queue_mapping(skb, - ieee80211_select_queue(rx->sdata, fwd_skb)); - ieee80211_set_qos_hdr(local, skb); - if (is_multicast_ether_addr(fwd_hdr->addr1)) + if (is_multicast_ether_addr(fwd_hdr->addr1)) { IEEE80211_IFSTA_MESH_CTR_INC(&sdata->u.mesh, fwded_mcast); - else { + skb_set_queue_mapping(fwd_skb, + ieee80211_select_queue(sdata, fwd_skb)); + ieee80211_set_qos_hdr(sdata, fwd_skb); + } else { int err; /* * Save TA to addr1 to send TA a path error if a @@ -2220,12 +2284,29 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) goto handled; } break; + case WLAN_CATEGORY_SELF_PROTECTED: + switch (mgmt->u.action.u.self_prot.action_code) { + case WLAN_SP_MESH_PEERING_OPEN: + case WLAN_SP_MESH_PEERING_CLOSE: + case WLAN_SP_MESH_PEERING_CONFIRM: + if (!ieee80211_vif_is_mesh(&sdata->vif)) + goto invalid; + if (sdata->u.mesh.security != IEEE80211_MESH_SEC_NONE) + /* userspace handles this frame */ + break; + goto queue; + case WLAN_SP_MGK_INFORM: + case WLAN_SP_MGK_ACK: + if (!ieee80211_vif_is_mesh(&sdata->vif)) + goto invalid; + break; + } + break; case WLAN_CATEGORY_MESH_ACTION: if (!ieee80211_vif_is_mesh(&sdata->vif)) break; - goto queue; - case WLAN_CATEGORY_MESH_PATH_SEL: - if (!mesh_path_sel_is_hwmp(sdata)) + if (mesh_action_is_path_sel(mgmt) && + (!mesh_path_sel_is_hwmp(sdata))) break; goto queue; } @@ -2534,17 +2615,17 @@ static void ieee80211_rx_handlers(struct ieee80211_rx_data *rx) CALL_RXH(ieee80211_rx_h_decrypt) CALL_RXH(ieee80211_rx_h_check_more_data) + CALL_RXH(ieee80211_rx_h_uapsd_and_pspoll) CALL_RXH(ieee80211_rx_h_sta_process) CALL_RXH(ieee80211_rx_h_defragment) - CALL_RXH(ieee80211_rx_h_ps_poll) CALL_RXH(ieee80211_rx_h_michael_mic_verify) /* must be after MMIC verify so header is counted in MPDU mic */ - CALL_RXH(ieee80211_rx_h_remove_qos_control) - CALL_RXH(ieee80211_rx_h_amsdu) #ifdef CONFIG_MAC80211_MESH if (ieee80211_vif_is_mesh(&rx->sdata->vif)) CALL_RXH(ieee80211_rx_h_mesh_fwding); #endif + CALL_RXH(ieee80211_rx_h_remove_qos_control) + CALL_RXH(ieee80211_rx_h_amsdu) CALL_RXH(ieee80211_rx_h_data) CALL_RXH(ieee80211_rx_h_ctrl); CALL_RXH(ieee80211_rx_h_mgmt_check) @@ -2686,7 +2767,9 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, } else if (!ieee80211_bssid_match(bssid, sdata->vif.addr)) { if (!(status->rx_flags & IEEE80211_RX_IN_SCAN) && - !ieee80211_is_beacon(hdr->frame_control)) + !ieee80211_is_beacon(hdr->frame_control) && + !(ieee80211_is_action(hdr->frame_control) && + sdata->vif.p2p)) return 0; status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } @@ -2791,7 +2874,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, if (ieee80211_is_data(fc)) { prev_sta = NULL; - for_each_sta_info(local, hdr->addr2, sta, tmp) { + for_each_sta_info_rx(local, hdr->addr2, sta, tmp) { if (!prev_sta) { prev_sta = sta; continue; @@ -2835,7 +2918,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, continue; } - rx.sta = sta_info_get_bss(prev, hdr->addr2); + rx.sta = sta_info_get_bss_rx(prev, hdr->addr2); rx.sdata = prev; ieee80211_prepare_and_rx_handle(&rx, skb, false); @@ -2843,7 +2926,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, } if (prev) { - rx.sta = sta_info_get_bss(prev, hdr->addr2); + rx.sta = sta_info_get_bss_rx(prev, hdr->addr2); rx.sdata = prev; if (ieee80211_prepare_and_rx_handle(&rx, skb, true)) diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 6f09eca..83a0b05 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -14,7 +14,7 @@ #include <linux/if_arp.h> #include <linux/rtnetlink.h> -#include <linux/pm_qos_params.h> +#include <linux/pm_qos.h> #include <net/sch_generic.h> #include <linux/slab.h> #include <net/mac80211.h> @@ -254,6 +254,7 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local) req->ie, req->ie_len, band, req->rates[band], 0); local->hw_scan_req->ie_len = ielen; + local->hw_scan_req->no_cck = req->no_cck; return true; } @@ -660,7 +661,8 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, local->scan_req->ssids[i].ssid, local->scan_req->ssids[i].ssid_len, local->scan_req->ie, local->scan_req->ie_len, - local->scan_req->rates[band], false); + local->scan_req->rates[band], false, + local->scan_req->no_cck); /* * After sending probe requests, wait for probe responses diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index 7733f66..578eea3 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -32,12 +32,8 @@ static void ieee80211_send_refuse_measurement_request(struct ieee80211_sub_if_da skb = dev_alloc_skb(sizeof(*msr_report) + local->hw.extra_tx_headroom + sizeof(struct ieee80211_msrment_ie)); - - if (!skb) { - printk(KERN_ERR "%s: failed to allocate buffer for " - "measurement report frame\n", sdata->name); + if (!skb) return; - } skb_reserve(skb, local->hw.extra_tx_headroom); msr_report = (struct ieee80211_mgmt *)skb_put(skb, 24); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 21070e9..ce962d2 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -24,6 +24,7 @@ #include "sta_info.h" #include "debugfs_sta.h" #include "mesh.h" +#include "wme.h" /** * DOC: STA information lifetime rules @@ -72,7 +73,7 @@ static int sta_info_hash_del(struct ieee80211_local *local, if (!s) return -ENOENT; if (s == sta) { - rcu_assign_pointer(local->sta_hash[STA_HASH(sta->sta.addr)], + RCU_INIT_POINTER(local->sta_hash[STA_HASH(sta->sta.addr)], s->hnext); return 0; } @@ -82,7 +83,7 @@ static int sta_info_hash_del(struct ieee80211_local *local, s = rcu_dereference_protected(s->hnext, lockdep_is_held(&local->sta_lock)); if (rcu_access_pointer(s->hnext)) { - rcu_assign_pointer(s->hnext, sta->hnext); + RCU_INIT_POINTER(s->hnext, sta->hnext); return 0; } @@ -100,6 +101,27 @@ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata, lockdep_is_held(&local->sta_lock) || lockdep_is_held(&local->sta_mtx)); while (sta) { + if (sta->sdata == sdata && !sta->dummy && + memcmp(sta->sta.addr, addr, ETH_ALEN) == 0) + break; + sta = rcu_dereference_check(sta->hnext, + lockdep_is_held(&local->sta_lock) || + lockdep_is_held(&local->sta_mtx)); + } + return sta; +} + +/* get a station info entry even if it is a dummy station*/ +struct sta_info *sta_info_get_rx(struct ieee80211_sub_if_data *sdata, + const u8 *addr) +{ + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + + sta = rcu_dereference_check(local->sta_hash[STA_HASH(addr)], + lockdep_is_held(&local->sta_lock) || + lockdep_is_held(&local->sta_mtx)); + while (sta) { if (sta->sdata == sdata && memcmp(sta->sta.addr, addr, ETH_ALEN) == 0) break; @@ -126,6 +148,32 @@ struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata, while (sta) { if ((sta->sdata == sdata || (sta->sdata->bss && sta->sdata->bss == sdata->bss)) && + !sta->dummy && + memcmp(sta->sta.addr, addr, ETH_ALEN) == 0) + break; + sta = rcu_dereference_check(sta->hnext, + lockdep_is_held(&local->sta_lock) || + lockdep_is_held(&local->sta_mtx)); + } + return sta; +} + +/* + * Get sta info either from the specified interface + * or from one of its vlans (including dummy stations) + */ +struct sta_info *sta_info_get_bss_rx(struct ieee80211_sub_if_data *sdata, + const u8 *addr) +{ + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + + sta = rcu_dereference_check(local->sta_hash[STA_HASH(addr)], + lockdep_is_held(&local->sta_lock) || + lockdep_is_held(&local->sta_mtx)); + while (sta) { + if ((sta->sdata == sdata || + (sta->sdata->bss && sta->sdata->bss == sdata->bss)) && memcmp(sta->sta.addr, addr, ETH_ALEN) == 0) break; sta = rcu_dereference_check(sta->hnext, @@ -184,7 +232,7 @@ static void sta_info_hash_add(struct ieee80211_local *local, struct sta_info *sta) { sta->hnext = local->sta_hash[STA_HASH(sta->sta.addr)]; - rcu_assign_pointer(local->sta_hash[STA_HASH(sta->sta.addr)], sta); + RCU_INIT_POINTER(local->sta_hash[STA_HASH(sta->sta.addr)], sta); } static void sta_unblock(struct work_struct *wk) @@ -196,13 +244,22 @@ static void sta_unblock(struct work_struct *wk) if (sta->dead) return; - if (!test_sta_flags(sta, WLAN_STA_PS_STA)) + if (!test_sta_flag(sta, WLAN_STA_PS_STA)) ieee80211_sta_ps_deliver_wakeup(sta); - else if (test_and_clear_sta_flags(sta, WLAN_STA_PSPOLL)) { - clear_sta_flags(sta, WLAN_STA_PS_DRIVER); + else if (test_and_clear_sta_flag(sta, WLAN_STA_PSPOLL)) { + clear_sta_flag(sta, WLAN_STA_PS_DRIVER); + + local_bh_disable(); ieee80211_sta_ps_deliver_poll_response(sta); + local_bh_enable(); + } else if (test_and_clear_sta_flag(sta, WLAN_STA_UAPSD)) { + clear_sta_flag(sta, WLAN_STA_PS_DRIVER); + + local_bh_disable(); + ieee80211_sta_ps_deliver_uapsd(sta); + local_bh_enable(); } else - clear_sta_flags(sta, WLAN_STA_PS_DRIVER); + clear_sta_flag(sta, WLAN_STA_PS_DRIVER); } static int sta_prepare_rate_control(struct ieee80211_local *local, @@ -235,7 +292,6 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, return NULL; spin_lock_init(&sta->lock); - spin_lock_init(&sta->flaglock); INIT_WORK(&sta->drv_unblock_wk, sta_unblock); INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work); mutex_init(&sta->ampdu_mlme.mtx); @@ -262,8 +318,10 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, */ sta->timer_to_tid[i] = i; } - skb_queue_head_init(&sta->ps_tx_buf); - skb_queue_head_init(&sta->tx_filtered); + for (i = 0; i < IEEE80211_NUM_ACS; i++) { + skb_queue_head_init(&sta->ps_tx_buf[i]); + skb_queue_head_init(&sta->tx_filtered[i]); + } for (i = 0; i < NUM_RX_DATA_QUEUES; i++) sta->last_seq_ctrl[i] = cpu_to_le16(USHRT_MAX); @@ -280,7 +338,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, return sta; } -static int sta_info_finish_insert(struct sta_info *sta, bool async) +static int sta_info_finish_insert(struct sta_info *sta, + bool async, bool dummy_reinsert) { struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; @@ -290,50 +349,58 @@ static int sta_info_finish_insert(struct sta_info *sta, bool async) lockdep_assert_held(&local->sta_mtx); - /* notify driver */ - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) - sdata = container_of(sdata->bss, - struct ieee80211_sub_if_data, - u.ap); - err = drv_sta_add(local, sdata, &sta->sta); - if (err) { - if (!async) - return err; - printk(KERN_DEBUG "%s: failed to add IBSS STA %pM to driver (%d)" - " - keeping it anyway.\n", - sdata->name, sta->sta.addr, err); - } else { - sta->uploaded = true; + if (!sta->dummy || dummy_reinsert) { + /* notify driver */ + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + sdata = container_of(sdata->bss, + struct ieee80211_sub_if_data, + u.ap); + err = drv_sta_add(local, sdata, &sta->sta); + if (err) { + if (!async) + return err; + printk(KERN_DEBUG "%s: failed to add IBSS STA %pM to " + "driver (%d) - keeping it anyway.\n", + sdata->name, sta->sta.addr, err); + } else { + sta->uploaded = true; #ifdef CONFIG_MAC80211_VERBOSE_DEBUG - if (async) - wiphy_debug(local->hw.wiphy, - "Finished adding IBSS STA %pM\n", - sta->sta.addr); + if (async) + wiphy_debug(local->hw.wiphy, + "Finished adding IBSS STA %pM\n", + sta->sta.addr); #endif + } + + sdata = sta->sdata; } - sdata = sta->sdata; + if (!dummy_reinsert) { + if (!async) { + local->num_sta++; + local->sta_generation++; + smp_mb(); - if (!async) { - local->num_sta++; - local->sta_generation++; - smp_mb(); + /* make the station visible */ + spin_lock_irqsave(&local->sta_lock, flags); + sta_info_hash_add(local, sta); + spin_unlock_irqrestore(&local->sta_lock, flags); + } - /* make the station visible */ - spin_lock_irqsave(&local->sta_lock, flags); - sta_info_hash_add(local, sta); - spin_unlock_irqrestore(&local->sta_lock, flags); + list_add(&sta->list, &local->sta_list); + } else { + sta->dummy = false; } - list_add(&sta->list, &local->sta_list); - - ieee80211_sta_debugfs_add(sta); - rate_control_add_sta_debugfs(sta); - - sinfo.filled = 0; - sinfo.generation = local->sta_generation; - cfg80211_new_sta(sdata->dev, sta->sta.addr, &sinfo, GFP_KERNEL); + if (!sta->dummy) { + ieee80211_sta_debugfs_add(sta); + rate_control_add_sta_debugfs(sta); + memset(&sinfo, 0, sizeof(sinfo)); + sinfo.filled = 0; + sinfo.generation = local->sta_generation; + cfg80211_new_sta(sdata->dev, sta->sta.addr, &sinfo, GFP_KERNEL); + } return 0; } @@ -350,7 +417,7 @@ static void sta_info_finish_pending(struct ieee80211_local *local) list_del(&sta->list); spin_unlock_irqrestore(&local->sta_lock, flags); - sta_info_finish_insert(sta, true); + sta_info_finish_insert(sta, true, false); spin_lock_irqsave(&local->sta_lock, flags); } @@ -367,106 +434,117 @@ static void sta_info_finish_work(struct work_struct *work) mutex_unlock(&local->sta_mtx); } -int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU) +static int sta_info_insert_check(struct sta_info *sta) { - struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; - unsigned long flags; - int err = 0; /* * Can't be a WARN_ON because it can be triggered through a race: * something inserts a STA (on one CPU) without holding the RTNL * and another CPU turns off the net device. */ - if (unlikely(!ieee80211_sdata_running(sdata))) { - err = -ENETDOWN; - rcu_read_lock(); - goto out_free; - } + if (unlikely(!ieee80211_sdata_running(sdata))) + return -ENETDOWN; if (WARN_ON(compare_ether_addr(sta->sta.addr, sdata->vif.addr) == 0 || - is_multicast_ether_addr(sta->sta.addr))) { - err = -EINVAL; + is_multicast_ether_addr(sta->sta.addr))) + return -EINVAL; + + return 0; +} + +static int sta_info_insert_ibss(struct sta_info *sta) __acquires(RCU) +{ + struct ieee80211_local *local = sta->local; + struct ieee80211_sub_if_data *sdata = sta->sdata; + unsigned long flags; + + spin_lock_irqsave(&local->sta_lock, flags); + /* check if STA exists already */ + if (sta_info_get_bss_rx(sdata, sta->sta.addr)) { + spin_unlock_irqrestore(&local->sta_lock, flags); rcu_read_lock(); - goto out_free; + return -EEXIST; } - /* - * In ad-hoc mode, we sometimes need to insert stations - * from tasklet context from the RX path. To avoid races, - * always do so in that case -- see the comment below. - */ - if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { - spin_lock_irqsave(&local->sta_lock, flags); - /* check if STA exists already */ - if (sta_info_get_bss(sdata, sta->sta.addr)) { - spin_unlock_irqrestore(&local->sta_lock, flags); - rcu_read_lock(); - err = -EEXIST; - goto out_free; - } - - local->num_sta++; - local->sta_generation++; - smp_mb(); - sta_info_hash_add(local, sta); + local->num_sta++; + local->sta_generation++; + smp_mb(); + sta_info_hash_add(local, sta); - list_add_tail(&sta->list, &local->sta_pending_list); + list_add_tail(&sta->list, &local->sta_pending_list); - rcu_read_lock(); - spin_unlock_irqrestore(&local->sta_lock, flags); + rcu_read_lock(); + spin_unlock_irqrestore(&local->sta_lock, flags); #ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(local->hw.wiphy, "Added IBSS STA %pM\n", - sta->sta.addr); + wiphy_debug(local->hw.wiphy, "Added IBSS STA %pM\n", + sta->sta.addr); #endif /* CONFIG_MAC80211_VERBOSE_DEBUG */ - ieee80211_queue_work(&local->hw, &local->sta_finish_work); + ieee80211_queue_work(&local->hw, &local->sta_finish_work); - return 0; - } + return 0; +} + +/* + * should be called with sta_mtx locked + * this function replaces the mutex lock + * with a RCU lock + */ +static int sta_info_insert_non_ibss(struct sta_info *sta) __acquires(RCU) +{ + struct ieee80211_local *local = sta->local; + struct ieee80211_sub_if_data *sdata = sta->sdata; + unsigned long flags; + struct sta_info *exist_sta; + bool dummy_reinsert = false; + int err = 0; + + lockdep_assert_held(&local->sta_mtx); /* * On first glance, this will look racy, because the code - * below this point, which inserts a station with sleeping, + * in this function, which inserts a station with sleeping, * unlocks the sta_lock between checking existence in the * hash table and inserting into it. * * However, it is not racy against itself because it keeps - * the mutex locked. It still seems to race against the - * above code that atomically inserts the station... That, - * however, is not true because the above code can only - * be invoked for IBSS interfaces, and the below code will - * not be -- and the two do not race against each other as - * the hash table also keys off the interface. + * the mutex locked. */ - might_sleep(); - - mutex_lock(&local->sta_mtx); - spin_lock_irqsave(&local->sta_lock, flags); - /* check if STA exists already */ - if (sta_info_get_bss(sdata, sta->sta.addr)) { - spin_unlock_irqrestore(&local->sta_lock, flags); - mutex_unlock(&local->sta_mtx); - rcu_read_lock(); - err = -EEXIST; - goto out_free; + /* + * check if STA exists already. + * only accept a scenario of a second call to sta_info_insert_non_ibss + * with a dummy station entry that was inserted earlier + * in that case - assume that the dummy station flag should + * be removed. + */ + exist_sta = sta_info_get_bss_rx(sdata, sta->sta.addr); + if (exist_sta) { + if (exist_sta == sta && sta->dummy) { + dummy_reinsert = true; + } else { + spin_unlock_irqrestore(&local->sta_lock, flags); + mutex_unlock(&local->sta_mtx); + rcu_read_lock(); + return -EEXIST; + } } spin_unlock_irqrestore(&local->sta_lock, flags); - err = sta_info_finish_insert(sta, false); + err = sta_info_finish_insert(sta, false, dummy_reinsert); if (err) { mutex_unlock(&local->sta_mtx); rcu_read_lock(); - goto out_free; + return err; } #ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(local->hw.wiphy, "Inserted STA %pM\n", sta->sta.addr); + wiphy_debug(local->hw.wiphy, "Inserted %sSTA %pM\n", + sta->dummy ? "dummy " : "", sta->sta.addr); #endif /* CONFIG_MAC80211_VERBOSE_DEBUG */ /* move reference to rcu-protected */ @@ -477,6 +555,51 @@ int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU) mesh_accept_plinks_update(sdata); return 0; +} + +int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU) +{ + struct ieee80211_local *local = sta->local; + struct ieee80211_sub_if_data *sdata = sta->sdata; + int err = 0; + + err = sta_info_insert_check(sta); + if (err) { + rcu_read_lock(); + goto out_free; + } + + /* + * In ad-hoc mode, we sometimes need to insert stations + * from tasklet context from the RX path. To avoid races, + * always do so in that case -- see the comment below. + */ + if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { + err = sta_info_insert_ibss(sta); + if (err) + goto out_free; + + return 0; + } + + /* + * It might seem that the function called below is in race against + * the function call above that atomically inserts the station... That, + * however, is not true because the above code can only + * be invoked for IBSS interfaces, and the below code will + * not be -- and the two do not race against each other as + * the hash table also keys off the interface. + */ + + might_sleep(); + + mutex_lock(&local->sta_mtx); + + err = sta_info_insert_non_ibss(sta); + if (err) + goto out_free; + + return 0; out_free: BUG_ON(!err); __sta_info_free(local, sta); @@ -492,6 +615,25 @@ int sta_info_insert(struct sta_info *sta) return err; } +/* Caller must hold sta->local->sta_mtx */ +int sta_info_reinsert(struct sta_info *sta) +{ + struct ieee80211_local *local = sta->local; + int err = 0; + + err = sta_info_insert_check(sta); + if (err) { + mutex_unlock(&local->sta_mtx); + return err; + } + + might_sleep(); + + err = sta_info_insert_non_ibss(sta); + rcu_read_unlock(); + return err; +} + static inline void __bss_tim_set(struct ieee80211_if_ap *bss, u16 aid) { /* @@ -510,64 +652,93 @@ static inline void __bss_tim_clear(struct ieee80211_if_ap *bss, u16 aid) bss->tim[aid / 8] &= ~(1 << (aid % 8)); } -static void __sta_info_set_tim_bit(struct ieee80211_if_ap *bss, - struct sta_info *sta) +static unsigned long ieee80211_tids_for_ac(int ac) { - BUG_ON(!bss); - - __bss_tim_set(bss, sta->sta.aid); - - if (sta->local->ops->set_tim) { - sta->local->tim_in_locked_section = true; - drv_set_tim(sta->local, &sta->sta, true); - sta->local->tim_in_locked_section = false; + /* If we ever support TIDs > 7, this obviously needs to be adjusted */ + switch (ac) { + case IEEE80211_AC_VO: + return BIT(6) | BIT(7); + case IEEE80211_AC_VI: + return BIT(4) | BIT(5); + case IEEE80211_AC_BE: + return BIT(0) | BIT(3); + case IEEE80211_AC_BK: + return BIT(1) | BIT(2); + default: + WARN_ON(1); + return 0; } } -void sta_info_set_tim_bit(struct sta_info *sta) +void sta_info_recalc_tim(struct sta_info *sta) { + struct ieee80211_local *local = sta->local; + struct ieee80211_if_ap *bss = sta->sdata->bss; unsigned long flags; + bool indicate_tim = false; + u8 ignore_for_tim = sta->sta.uapsd_queues; + int ac; - BUG_ON(!sta->sdata->bss); + if (WARN_ON_ONCE(!sta->sdata->bss)) + return; - spin_lock_irqsave(&sta->local->sta_lock, flags); - __sta_info_set_tim_bit(sta->sdata->bss, sta); - spin_unlock_irqrestore(&sta->local->sta_lock, flags); -} + /* No need to do anything if the driver does all */ + if (local->hw.flags & IEEE80211_HW_AP_LINK_PS) + return; -static void __sta_info_clear_tim_bit(struct ieee80211_if_ap *bss, - struct sta_info *sta) -{ - BUG_ON(!bss); + if (sta->dead) + goto done; + + /* + * If all ACs are delivery-enabled then we should build + * the TIM bit for all ACs anyway; if only some are then + * we ignore those and build the TIM bit using only the + * non-enabled ones. + */ + if (ignore_for_tim == BIT(IEEE80211_NUM_ACS) - 1) + ignore_for_tim = 0; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + unsigned long tids; - __bss_tim_clear(bss, sta->sta.aid); + if (ignore_for_tim & BIT(ac)) + continue; + + indicate_tim |= !skb_queue_empty(&sta->tx_filtered[ac]) || + !skb_queue_empty(&sta->ps_tx_buf[ac]); + if (indicate_tim) + break; - if (sta->local->ops->set_tim) { - sta->local->tim_in_locked_section = true; - drv_set_tim(sta->local, &sta->sta, false); - sta->local->tim_in_locked_section = false; + tids = ieee80211_tids_for_ac(ac); + + indicate_tim |= + sta->driver_buffered_tids & tids; } -} -void sta_info_clear_tim_bit(struct sta_info *sta) -{ - unsigned long flags; + done: + spin_lock_irqsave(&local->sta_lock, flags); - BUG_ON(!sta->sdata->bss); + if (indicate_tim) + __bss_tim_set(bss, sta->sta.aid); + else + __bss_tim_clear(bss, sta->sta.aid); - spin_lock_irqsave(&sta->local->sta_lock, flags); - __sta_info_clear_tim_bit(sta->sdata->bss, sta); - spin_unlock_irqrestore(&sta->local->sta_lock, flags); + if (local->ops->set_tim) { + local->tim_in_locked_section = true; + drv_set_tim(local, &sta->sta, indicate_tim); + local->tim_in_locked_section = false; + } + + spin_unlock_irqrestore(&local->sta_lock, flags); } -static int sta_info_buffer_expired(struct sta_info *sta, - struct sk_buff *skb) +static bool sta_info_buffer_expired(struct sta_info *sta, struct sk_buff *skb) { struct ieee80211_tx_info *info; int timeout; if (!skb) - return 0; + return false; info = IEEE80211_SKB_CB(skb); @@ -581,24 +752,59 @@ static int sta_info_buffer_expired(struct sta_info *sta, } -static bool sta_info_cleanup_expire_buffered(struct ieee80211_local *local, - struct sta_info *sta) +static bool sta_info_cleanup_expire_buffered_ac(struct ieee80211_local *local, + struct sta_info *sta, int ac) { unsigned long flags; struct sk_buff *skb; - if (skb_queue_empty(&sta->ps_tx_buf)) - return false; + /* + * First check for frames that should expire on the filtered + * queue. Frames here were rejected by the driver and are on + * a separate queue to avoid reordering with normal PS-buffered + * frames. They also aren't accounted for right now in the + * total_ps_buffered counter. + */ + for (;;) { + spin_lock_irqsave(&sta->tx_filtered[ac].lock, flags); + skb = skb_peek(&sta->tx_filtered[ac]); + if (sta_info_buffer_expired(sta, skb)) + skb = __skb_dequeue(&sta->tx_filtered[ac]); + else + skb = NULL; + spin_unlock_irqrestore(&sta->tx_filtered[ac].lock, flags); + /* + * Frames are queued in order, so if this one + * hasn't expired yet we can stop testing. If + * we actually reached the end of the queue we + * also need to stop, of course. + */ + if (!skb) + break; + dev_kfree_skb(skb); + } + + /* + * Now also check the normal PS-buffered queue, this will + * only find something if the filtered queue was emptied + * since the filtered frames are all before the normal PS + * buffered frames. + */ for (;;) { - spin_lock_irqsave(&sta->ps_tx_buf.lock, flags); - skb = skb_peek(&sta->ps_tx_buf); + spin_lock_irqsave(&sta->ps_tx_buf[ac].lock, flags); + skb = skb_peek(&sta->ps_tx_buf[ac]); if (sta_info_buffer_expired(sta, skb)) - skb = __skb_dequeue(&sta->ps_tx_buf); + skb = __skb_dequeue(&sta->ps_tx_buf[ac]); else skb = NULL; - spin_unlock_irqrestore(&sta->ps_tx_buf.lock, flags); + spin_unlock_irqrestore(&sta->ps_tx_buf[ac].lock, flags); + /* + * frames are queued in order, so if this one + * hasn't expired yet (or we reached the end of + * the queue) we can stop testing + */ if (!skb) break; @@ -608,22 +814,47 @@ static bool sta_info_cleanup_expire_buffered(struct ieee80211_local *local, sta->sta.addr); #endif dev_kfree_skb(skb); - - if (skb_queue_empty(&sta->ps_tx_buf) && - !test_sta_flags(sta, WLAN_STA_PS_DRIVER_BUF)) - sta_info_clear_tim_bit(sta); } - return true; + /* + * Finally, recalculate the TIM bit for this station -- it might + * now be clear because the station was too slow to retrieve its + * frames. + */ + sta_info_recalc_tim(sta); + + /* + * Return whether there are any frames still buffered, this is + * used to check whether the cleanup timer still needs to run, + * if there are no frames we don't need to rearm the timer. + */ + return !(skb_queue_empty(&sta->ps_tx_buf[ac]) && + skb_queue_empty(&sta->tx_filtered[ac])); +} + +static bool sta_info_cleanup_expire_buffered(struct ieee80211_local *local, + struct sta_info *sta) +{ + bool have_buffered = false; + int ac; + + /* This is only necessary for stations on BSS interfaces */ + if (!sta->sdata->bss) + return false; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) + have_buffered |= + sta_info_cleanup_expire_buffered_ac(local, sta, ac); + + return have_buffered; } static int __must_check __sta_info_destroy(struct sta_info *sta) { struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; - struct sk_buff *skb; unsigned long flags; - int ret, i; + int ret, i, ac; might_sleep(); @@ -639,7 +870,7 @@ static int __must_check __sta_info_destroy(struct sta_info *sta) * sessions -- block that to make sure the tear-down * will be sufficient. */ - set_sta_flags(sta, WLAN_STA_BLOCK_BA); + set_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_sta_tear_down_BA_sessions(sta, true); spin_lock_irqsave(&local->sta_lock, flags); @@ -660,19 +891,22 @@ static int __must_check __sta_info_destroy(struct sta_info *sta) sta->dead = true; - if (test_and_clear_sta_flags(sta, - WLAN_STA_PS_STA | WLAN_STA_PS_DRIVER)) { + if (test_sta_flag(sta, WLAN_STA_PS_STA) || + test_sta_flag(sta, WLAN_STA_PS_DRIVER)) { BUG_ON(!sdata->bss); + clear_sta_flag(sta, WLAN_STA_PS_STA); + clear_sta_flag(sta, WLAN_STA_PS_DRIVER); + atomic_dec(&sdata->bss->num_sta_ps); - sta_info_clear_tim_bit(sta); + sta_info_recalc_tim(sta); } local->num_sta--; local->sta_generation++; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) - rcu_assign_pointer(sdata->u.vlan.sta, NULL); + RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); if (sta->uploaded) { if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) @@ -691,6 +925,12 @@ static int __must_check __sta_info_destroy(struct sta_info *sta) */ synchronize_rcu(); + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + local->total_ps_buffered -= skb_queue_len(&sta->ps_tx_buf[ac]); + __skb_queue_purge(&sta->ps_tx_buf[ac]); + __skb_queue_purge(&sta->tx_filtered[ac]); + } + #ifdef CONFIG_MAC80211_MESH if (ieee80211_vif_is_mesh(&sdata->vif)) mesh_accept_plinks_update(sdata); @@ -713,14 +953,6 @@ static int __must_check __sta_info_destroy(struct sta_info *sta) } #endif - while ((skb = skb_dequeue(&sta->ps_tx_buf)) != NULL) { - local->total_ps_buffered--; - dev_kfree_skb_any(skb); - } - - while ((skb = skb_dequeue(&sta->tx_filtered)) != NULL) - dev_kfree_skb_any(skb); - __sta_info_free(local, sta); return 0; @@ -732,7 +964,7 @@ int sta_info_destroy_addr(struct ieee80211_sub_if_data *sdata, const u8 *addr) int ret; mutex_lock(&sdata->local->sta_mtx); - sta = sta_info_get(sdata, addr); + sta = sta_info_get_rx(sdata, addr); ret = __sta_info_destroy(sta); mutex_unlock(&sdata->local->sta_mtx); @@ -746,7 +978,7 @@ int sta_info_destroy_addr_bss(struct ieee80211_sub_if_data *sdata, int ret; mutex_lock(&sdata->local->sta_mtx); - sta = sta_info_get_bss(sdata, addr); + sta = sta_info_get_bss_rx(sdata, addr); ret = __sta_info_destroy(sta); mutex_unlock(&sdata->local->sta_mtx); @@ -886,7 +1118,8 @@ static void clear_sta_ps_flags(void *_sta) { struct sta_info *sta = _sta; - clear_sta_flags(sta, WLAN_STA_PS_DRIVER | WLAN_STA_PS_STA); + clear_sta_flag(sta, WLAN_STA_PS_DRIVER); + clear_sta_flag(sta, WLAN_STA_PS_STA); } /* powersave support code */ @@ -894,88 +1127,341 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; - int sent, buffered; + struct sk_buff_head pending; + int filtered = 0, buffered = 0, ac; + + clear_sta_flag(sta, WLAN_STA_SP); + + BUILD_BUG_ON(BITS_TO_LONGS(STA_TID_NUM) > 1); + sta->driver_buffered_tids = 0; - clear_sta_flags(sta, WLAN_STA_PS_DRIVER_BUF); if (!(local->hw.flags & IEEE80211_HW_AP_LINK_PS)) drv_sta_notify(local, sdata, STA_NOTIFY_AWAKE, &sta->sta); - if (!skb_queue_empty(&sta->ps_tx_buf)) - sta_info_clear_tim_bit(sta); + skb_queue_head_init(&pending); /* Send all buffered frames to the station */ - sent = ieee80211_add_pending_skbs(local, &sta->tx_filtered); - buffered = ieee80211_add_pending_skbs_fn(local, &sta->ps_tx_buf, - clear_sta_ps_flags, sta); - sent += buffered; + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + int count = skb_queue_len(&pending), tmp; + + skb_queue_splice_tail_init(&sta->tx_filtered[ac], &pending); + tmp = skb_queue_len(&pending); + filtered += tmp - count; + count = tmp; + + skb_queue_splice_tail_init(&sta->ps_tx_buf[ac], &pending); + tmp = skb_queue_len(&pending); + buffered += tmp - count; + } + + ieee80211_add_pending_skbs_fn(local, &pending, clear_sta_ps_flags, sta); + local->total_ps_buffered -= buffered; + sta_info_recalc_tim(sta); + #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG printk(KERN_DEBUG "%s: STA %pM aid %d sending %d filtered/%d PS frames " "since STA not sleeping anymore\n", sdata->name, - sta->sta.addr, sta->sta.aid, sent - buffered, buffered); + sta->sta.addr, sta->sta.aid, filtered, buffered); #endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ } -void ieee80211_sta_ps_deliver_poll_response(struct sta_info *sta) +static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, int tid, + enum ieee80211_frame_release_type reason) { - struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; + struct ieee80211_qos_hdr *nullfunc; struct sk_buff *skb; - int no_pending_pkts; + int size = sizeof(*nullfunc); + __le16 fc; + bool qos = test_sta_flag(sta, WLAN_STA_WME); + struct ieee80211_tx_info *info; - skb = skb_dequeue(&sta->tx_filtered); - if (!skb) { - skb = skb_dequeue(&sta->ps_tx_buf); - if (skb) - local->total_ps_buffered--; + if (qos) { + fc = cpu_to_le16(IEEE80211_FTYPE_DATA | + IEEE80211_STYPE_QOS_NULLFUNC | + IEEE80211_FCTL_FROMDS); + } else { + size -= 2; + fc = cpu_to_le16(IEEE80211_FTYPE_DATA | + IEEE80211_STYPE_NULLFUNC | + IEEE80211_FCTL_FROMDS); + } + + skb = dev_alloc_skb(local->hw.extra_tx_headroom + size); + if (!skb) + return; + + skb_reserve(skb, local->hw.extra_tx_headroom); + + nullfunc = (void *) skb_put(skb, size); + nullfunc->frame_control = fc; + nullfunc->duration_id = 0; + memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN); + memcpy(nullfunc->addr2, sdata->vif.addr, ETH_ALEN); + memcpy(nullfunc->addr3, sdata->vif.addr, ETH_ALEN); + + skb->priority = tid; + skb_set_queue_mapping(skb, ieee802_1d_to_ac[tid]); + if (qos) { + nullfunc->qos_ctrl = cpu_to_le16(tid); + + if (reason == IEEE80211_FRAME_RELEASE_UAPSD) + nullfunc->qos_ctrl |= + cpu_to_le16(IEEE80211_QOS_CTL_EOSP); } - no_pending_pkts = skb_queue_empty(&sta->tx_filtered) && - skb_queue_empty(&sta->ps_tx_buf); - if (skb) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_hdr *hdr = - (struct ieee80211_hdr *) skb->data; + info = IEEE80211_SKB_CB(skb); + + /* + * Tell TX path to send this frame even though the + * STA may still remain is PS mode after this frame + * exchange. Also set EOSP to indicate this packet + * ends the poll/service period. + */ + info->flags |= IEEE80211_TX_CTL_POLL_RESPONSE | + IEEE80211_TX_STATUS_EOSP | + IEEE80211_TX_CTL_REQ_TX_STATUS; + + drv_allow_buffered_frames(local, sta, BIT(tid), 1, reason, false); + + ieee80211_xmit(sdata, skb); +} + +static void +ieee80211_sta_ps_deliver_response(struct sta_info *sta, + int n_frames, u8 ignored_acs, + enum ieee80211_frame_release_type reason) +{ + struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_local *local = sdata->local; + bool found = false; + bool more_data = false; + int ac; + unsigned long driver_release_tids = 0; + struct sk_buff_head frames; + + /* Service or PS-Poll period starts */ + set_sta_flag(sta, WLAN_STA_SP); + + __skb_queue_head_init(&frames); + + /* + * Get response frame(s) and more data bit for it. + */ + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + unsigned long tids; + + if (ignored_acs & BIT(ac)) + continue; + + tids = ieee80211_tids_for_ac(ac); + + if (!found) { + driver_release_tids = sta->driver_buffered_tids & tids; + if (driver_release_tids) { + found = true; + } else { + struct sk_buff *skb; + + while (n_frames > 0) { + skb = skb_dequeue(&sta->tx_filtered[ac]); + if (!skb) { + skb = skb_dequeue( + &sta->ps_tx_buf[ac]); + if (skb) + local->total_ps_buffered--; + } + if (!skb) + break; + n_frames--; + found = true; + __skb_queue_tail(&frames, skb); + } + } + + /* + * If the driver has data on more than one TID then + * certainly there's more data if we release just a + * single frame now (from a single TID). + */ + if (reason == IEEE80211_FRAME_RELEASE_PSPOLL && + hweight16(driver_release_tids) > 1) { + more_data = true; + driver_release_tids = + BIT(ffs(driver_release_tids) - 1); + break; + } + } + + if (!skb_queue_empty(&sta->tx_filtered[ac]) || + !skb_queue_empty(&sta->ps_tx_buf[ac])) { + more_data = true; + break; + } + } + + if (!found) { + int tid; /* - * Tell TX path to send this frame even though the STA may - * still remain is PS mode after this frame exchange. + * For PS-Poll, this can only happen due to a race condition + * when we set the TIM bit and the station notices it, but + * before it can poll for the frame we expire it. + * + * For uAPSD, this is said in the standard (11.2.1.5 h): + * At each unscheduled SP for a non-AP STA, the AP shall + * attempt to transmit at least one MSDU or MMPDU, but no + * more than the value specified in the Max SP Length field + * in the QoS Capability element from delivery-enabled ACs, + * that are destined for the non-AP STA. + * + * Since we have no other MSDU/MMPDU, transmit a QoS null frame. */ - info->flags |= IEEE80211_TX_CTL_PSPOLL_RESPONSE; -#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - printk(KERN_DEBUG "STA %pM aid %d: PS Poll (entries after %d)\n", - sta->sta.addr, sta->sta.aid, - skb_queue_len(&sta->ps_tx_buf)); -#endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ + /* This will evaluate to 1, 3, 5 or 7. */ + tid = 7 - ((ffs(~ignored_acs) - 1) << 1); - /* Use MoreData flag to indicate whether there are more - * buffered frames for this STA */ - if (no_pending_pkts) - hdr->frame_control &= cpu_to_le16(~IEEE80211_FCTL_MOREDATA); - else - hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_MOREDATA); + ieee80211_send_null_response(sdata, sta, tid, reason); + return; + } + + if (!driver_release_tids) { + struct sk_buff_head pending; + struct sk_buff *skb; + int num = 0; + u16 tids = 0; + + skb_queue_head_init(&pending); + + while ((skb = __skb_dequeue(&frames))) { + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_hdr *hdr = (void *) skb->data; + u8 *qoshdr = NULL; + + num++; + + /* + * Tell TX path to send this frame even though the + * STA may still remain is PS mode after this frame + * exchange. + */ + info->flags |= IEEE80211_TX_CTL_POLL_RESPONSE; + + /* + * Use MoreData flag to indicate whether there are + * more buffered frames for this STA + */ + if (!more_data) + hdr->frame_control &= + cpu_to_le16(~IEEE80211_FCTL_MOREDATA); + else + hdr->frame_control |= + cpu_to_le16(IEEE80211_FCTL_MOREDATA); + + if (ieee80211_is_data_qos(hdr->frame_control) || + ieee80211_is_qos_nullfunc(hdr->frame_control)) + qoshdr = ieee80211_get_qos_ctl(hdr); + + /* set EOSP for the frame */ + if (reason == IEEE80211_FRAME_RELEASE_UAPSD && + qoshdr && skb_queue_empty(&frames)) + *qoshdr |= IEEE80211_QOS_CTL_EOSP; + + info->flags |= IEEE80211_TX_STATUS_EOSP | + IEEE80211_TX_CTL_REQ_TX_STATUS; + + if (qoshdr) + tids |= BIT(*qoshdr & IEEE80211_QOS_CTL_TID_MASK); + else + tids |= BIT(0); + + __skb_queue_tail(&pending, skb); + } - ieee80211_add_pending_skb(local, skb); + drv_allow_buffered_frames(local, sta, tids, num, + reason, more_data); - if (no_pending_pkts) - sta_info_clear_tim_bit(sta); -#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG + ieee80211_add_pending_skbs(local, &pending); + + sta_info_recalc_tim(sta); } else { /* - * FIXME: This can be the result of a race condition between - * us expiring a frame and the station polling for it. - * Should we send it a null-func frame indicating we - * have nothing buffered for it? + * We need to release a frame that is buffered somewhere in the + * driver ... it'll have to handle that. + * Note that, as per the comment above, it'll also have to see + * if there is more than just one frame on the specific TID that + * we're releasing from, and it needs to set the more-data bit + * accordingly if we tell it that there's no more data. If we do + * tell it there's more data, then of course the more-data bit + * needs to be set anyway. + */ + drv_release_buffered_frames(local, sta, driver_release_tids, + n_frames, reason, more_data); + + /* + * Note that we don't recalculate the TIM bit here as it would + * most likely have no effect at all unless the driver told us + * that the TID became empty before returning here from the + * release function. + * Either way, however, when the driver tells us that the TID + * became empty we'll do the TIM recalculation. */ - printk(KERN_DEBUG "%s: STA %pM sent PS Poll even " - "though there are no buffered frames for it\n", - sdata->name, sta->sta.addr); -#endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ } } +void ieee80211_sta_ps_deliver_poll_response(struct sta_info *sta) +{ + u8 ignore_for_response = sta->sta.uapsd_queues; + + /* + * If all ACs are delivery-enabled then we should reply + * from any of them, if only some are enabled we reply + * only from the non-enabled ones. + */ + if (ignore_for_response == BIT(IEEE80211_NUM_ACS) - 1) + ignore_for_response = 0; + + ieee80211_sta_ps_deliver_response(sta, 1, ignore_for_response, + IEEE80211_FRAME_RELEASE_PSPOLL); +} + +void ieee80211_sta_ps_deliver_uapsd(struct sta_info *sta) +{ + int n_frames = sta->sta.max_sp; + u8 delivery_enabled = sta->sta.uapsd_queues; + + /* + * If we ever grow support for TSPEC this might happen if + * the TSPEC update from hostapd comes in between a trigger + * frame setting WLAN_STA_UAPSD in the RX path and this + * actually getting called. + */ + if (!delivery_enabled) + return; + + switch (sta->sta.max_sp) { + case 1: + n_frames = 2; + break; + case 2: + n_frames = 4; + break; + case 3: + n_frames = 6; + break; + case 0: + /* XXX: what is a good value? */ + n_frames = 8; + break; + } + + ieee80211_sta_ps_deliver_response(sta, n_frames, ~delivery_enabled, + IEEE80211_FRAME_RELEASE_UAPSD); +} + void ieee80211_sta_block_awake(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, bool block) { @@ -984,17 +1470,50 @@ void ieee80211_sta_block_awake(struct ieee80211_hw *hw, trace_api_sta_block_awake(sta->local, pubsta, block); if (block) - set_sta_flags(sta, WLAN_STA_PS_DRIVER); - else if (test_sta_flags(sta, WLAN_STA_PS_DRIVER)) + set_sta_flag(sta, WLAN_STA_PS_DRIVER); + else if (test_sta_flag(sta, WLAN_STA_PS_DRIVER)) ieee80211_queue_work(hw, &sta->drv_unblock_wk); } EXPORT_SYMBOL(ieee80211_sta_block_awake); -void ieee80211_sta_set_tim(struct ieee80211_sta *pubsta) +void ieee80211_sta_eosp_irqsafe(struct ieee80211_sta *pubsta) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); + struct ieee80211_local *local = sta->local; + struct sk_buff *skb; + struct skb_eosp_msg_data *data; + + trace_api_eosp(local, pubsta); + + skb = alloc_skb(0, GFP_ATOMIC); + if (!skb) { + /* too bad ... but race is better than loss */ + clear_sta_flag(sta, WLAN_STA_SP); + return; + } + + data = (void *)skb->cb; + memcpy(data->sta, pubsta->addr, ETH_ALEN); + memcpy(data->iface, sta->sdata->vif.addr, ETH_ALEN); + skb->pkt_type = IEEE80211_EOSP_MSG; + skb_queue_tail(&local->skb_queue, skb); + tasklet_schedule(&local->tasklet); +} +EXPORT_SYMBOL(ieee80211_sta_eosp_irqsafe); + +void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta, + u8 tid, bool buffered) +{ + struct sta_info *sta = container_of(pubsta, struct sta_info, sta); + + if (WARN_ON(tid >= STA_TID_NUM)) + return; + + if (buffered) + set_bit(tid, &sta->driver_buffered_tids); + else + clear_bit(tid, &sta->driver_buffered_tids); - set_sta_flags(sta, WLAN_STA_PS_DRIVER_BUF); - sta_info_set_tim_bit(sta); + sta_info_recalc_tim(sta); } -EXPORT_SYMBOL(ieee80211_sta_set_tim); +EXPORT_SYMBOL(ieee80211_sta_set_buffered); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 28beb78..8c8ce05 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -19,7 +19,8 @@ /** * enum ieee80211_sta_info_flags - Stations flags * - * These flags are used with &struct sta_info's @flags member. + * These flags are used with &struct sta_info's @flags member, but + * only indirectly with set_sta_flag() and friends. * * @WLAN_STA_AUTH: Station is authenticated. * @WLAN_STA_ASSOC: Station is associated. @@ -43,24 +44,33 @@ * be in the queues * @WLAN_STA_PSPOLL: Station sent PS-poll while driver was keeping * station in power-save mode, reply when the driver unblocks. - * @WLAN_STA_PS_DRIVER_BUF: Station has frames pending in driver internal - * buffers. Automatically cleared on station wake-up. + * @WLAN_STA_TDLS_PEER: Station is a TDLS peer. + * @WLAN_STA_TDLS_PEER_AUTH: This TDLS peer is authorized to send direct + * packets. This means the link is enabled. + * @WLAN_STA_UAPSD: Station requested unscheduled SP while driver was + * keeping station in power-save mode, reply when the driver + * unblocks the station. + * @WLAN_STA_SP: Station is in a service period, so don't try to + * reply to other uAPSD trigger frames or PS-Poll. */ enum ieee80211_sta_info_flags { - WLAN_STA_AUTH = 1<<0, - WLAN_STA_ASSOC = 1<<1, - WLAN_STA_PS_STA = 1<<2, - WLAN_STA_AUTHORIZED = 1<<3, - WLAN_STA_SHORT_PREAMBLE = 1<<4, - WLAN_STA_ASSOC_AP = 1<<5, - WLAN_STA_WME = 1<<6, - WLAN_STA_WDS = 1<<7, - WLAN_STA_CLEAR_PS_FILT = 1<<9, - WLAN_STA_MFP = 1<<10, - WLAN_STA_BLOCK_BA = 1<<11, - WLAN_STA_PS_DRIVER = 1<<12, - WLAN_STA_PSPOLL = 1<<13, - WLAN_STA_PS_DRIVER_BUF = 1<<14, + WLAN_STA_AUTH, + WLAN_STA_ASSOC, + WLAN_STA_PS_STA, + WLAN_STA_AUTHORIZED, + WLAN_STA_SHORT_PREAMBLE, + WLAN_STA_ASSOC_AP, + WLAN_STA_WME, + WLAN_STA_WDS, + WLAN_STA_CLEAR_PS_FILT, + WLAN_STA_MFP, + WLAN_STA_BLOCK_BA, + WLAN_STA_PS_DRIVER, + WLAN_STA_PSPOLL, + WLAN_STA_TDLS_PEER, + WLAN_STA_TDLS_PEER_AUTH, + WLAN_STA_UAPSD, + WLAN_STA_SP, }; #define STA_TID_NUM 16 @@ -86,6 +96,8 @@ enum ieee80211_sta_info_flags { * @stop_initiator: initiator of a session stop * @tx_stop: TX DelBA frame when stopping * @buf_size: reorder buffer size at receiver + * @failed_bar_ssn: ssn of the last failed BAR tx attempt + * @bar_pending: BAR needs to be re-sent * * This structure's lifetime is managed by RCU, assignments to * the array holding it must hold the aggregation mutex. @@ -106,6 +118,9 @@ struct tid_ampdu_tx { u8 stop_initiator; bool tx_stop; u8 buf_size; + + u16 failed_bar_ssn; + bool bar_pending; }; /** @@ -198,15 +213,16 @@ struct sta_ampdu_mlme { * @last_rx_rate_flag: rx status flag of the last data packet * @lock: used for locking all fields that require locking, see comments * in the header file. - * @flaglock: spinlock for flags accesses * @drv_unblock_wk: used for driver PS unblocking * @listen_interval: listen interval of this station, when we're acting as AP - * @flags: STA flags, see &enum ieee80211_sta_info_flags - * @ps_tx_buf: buffer of frames to transmit to this station - * when it leaves power saving state - * @tx_filtered: buffer of frames we already tried to transmit - * but were filtered by hardware due to STA having entered - * power saving state + * @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly + * @ps_tx_buf: buffers (per AC) of frames to transmit to this station + * when it leaves power saving state or polls + * @tx_filtered: buffers (per AC) of frames we already tried to + * transmit but were filtered by hardware due to STA having + * entered power saving state, these are also delivered to + * the station when it leaves powersave or polls for frames + * @driver_buffered_tids: bitmap of TIDs the driver has data buffered on * @rx_packets: Number of MSDUs received from this STA * @rx_bytes: Number of bytes received from this STA * @wep_weak_iv_count: number of weak WEP IVs received from this station @@ -238,10 +254,12 @@ struct sta_ampdu_mlme { * @plink_timer: peer link watch timer * @plink_timer_was_running: used by suspend/resume to restore timers * @debugfs: debug filesystem info - * @sta: station information we share with the driver * @dead: set to true when sta is unlinked * @uploaded: set to true when sta is uploaded to the driver * @lost_packets: number of consecutive lost packets + * @dummy: indicate a dummy station created for receiving + * EAP frames before association + * @sta: station information we share with the driver */ struct sta_info { /* General information, mostly static */ @@ -254,7 +272,6 @@ struct sta_info { struct rate_control_ref *rate_ctrl; void *rate_ctrl_priv; spinlock_t lock; - spinlock_t flaglock; struct work_struct drv_unblock_wk; @@ -264,18 +281,16 @@ struct sta_info { bool uploaded; - /* - * frequently updated, locked with own spinlock (flaglock), - * use the accessors defined below - */ - u32 flags; + /* use the accessors defined below */ + unsigned long _flags; /* * STA powersave frame queues, no more than the internal * locking required. */ - struct sk_buff_head ps_tx_buf; - struct sk_buff_head tx_filtered; + struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS]; + struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS]; + unsigned long driver_buffered_tids; /* Updated from RX path only, no locking requirements */ unsigned long rx_packets, rx_bytes; @@ -336,6 +351,9 @@ struct sta_info { unsigned int lost_packets; + /* should be right in front of sta to be in the same cache line */ + bool dummy; + /* keep last! */ struct ieee80211_sta sta; }; @@ -348,60 +366,28 @@ static inline enum nl80211_plink_state sta_plink_state(struct sta_info *sta) return NL80211_PLINK_LISTEN; } -static inline void set_sta_flags(struct sta_info *sta, const u32 flags) +static inline void set_sta_flag(struct sta_info *sta, + enum ieee80211_sta_info_flags flag) { - unsigned long irqfl; - - spin_lock_irqsave(&sta->flaglock, irqfl); - sta->flags |= flags; - spin_unlock_irqrestore(&sta->flaglock, irqfl); + set_bit(flag, &sta->_flags); } -static inline void clear_sta_flags(struct sta_info *sta, const u32 flags) +static inline void clear_sta_flag(struct sta_info *sta, + enum ieee80211_sta_info_flags flag) { - unsigned long irqfl; - - spin_lock_irqsave(&sta->flaglock, irqfl); - sta->flags &= ~flags; - spin_unlock_irqrestore(&sta->flaglock, irqfl); + clear_bit(flag, &sta->_flags); } -static inline u32 test_sta_flags(struct sta_info *sta, const u32 flags) +static inline int test_sta_flag(struct sta_info *sta, + enum ieee80211_sta_info_flags flag) { - u32 ret; - unsigned long irqfl; - - spin_lock_irqsave(&sta->flaglock, irqfl); - ret = sta->flags & flags; - spin_unlock_irqrestore(&sta->flaglock, irqfl); - - return ret; -} - -static inline u32 test_and_clear_sta_flags(struct sta_info *sta, - const u32 flags) -{ - u32 ret; - unsigned long irqfl; - - spin_lock_irqsave(&sta->flaglock, irqfl); - ret = sta->flags & flags; - sta->flags &= ~flags; - spin_unlock_irqrestore(&sta->flaglock, irqfl); - - return ret; + return test_bit(flag, &sta->_flags); } -static inline u32 get_sta_flags(struct sta_info *sta) +static inline int test_and_clear_sta_flag(struct sta_info *sta, + enum ieee80211_sta_info_flags flag) { - u32 ret; - unsigned long irqfl; - - spin_lock_irqsave(&sta->flaglock, irqfl); - ret = sta->flags; - spin_unlock_irqrestore(&sta->flaglock, irqfl); - - return ret; + return test_and_clear_bit(flag, &sta->_flags); } void ieee80211_assign_tid_tx(struct sta_info *sta, int tid, @@ -419,8 +405,8 @@ rcu_dereference_protected_tid_tx(struct sta_info *sta, int tid) #define STA_HASH(sta) (sta[5]) -/* Maximum number of frames to buffer per power saving station */ -#define STA_MAX_TX_BUFFER 128 +/* Maximum number of frames to buffer per power saving station per AC */ +#define STA_MAX_TX_BUFFER 64 /* Minimum buffered frame expiry time. If STA uses listen interval that is * smaller than this value, the minimum value here is used instead. */ @@ -436,9 +422,15 @@ rcu_dereference_protected_tid_tx(struct sta_info *sta, int tid) struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata, const u8 *addr); +struct sta_info *sta_info_get_rx(struct ieee80211_sub_if_data *sdata, + const u8 *addr); + struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata, const u8 *addr); +struct sta_info *sta_info_get_bss_rx(struct ieee80211_sub_if_data *sdata, + const u8 *addr); + static inline void for_each_sta_info_type_check(struct ieee80211_local *local, const u8 *addr, @@ -459,6 +451,22 @@ void for_each_sta_info_type_check(struct ieee80211_local *local, _sta = nxt, \ nxt = _sta ? rcu_dereference(_sta->hnext) : NULL \ ) \ + /* run code only if address matches and it's not a dummy sta */ \ + if (memcmp(_sta->sta.addr, (_addr), ETH_ALEN) == 0 && \ + !_sta->dummy) + +#define for_each_sta_info_rx(local, _addr, _sta, nxt) \ + for ( /* initialise loop */ \ + _sta = rcu_dereference(local->sta_hash[STA_HASH(_addr)]),\ + nxt = _sta ? rcu_dereference(_sta->hnext) : NULL; \ + /* typecheck */ \ + for_each_sta_info_type_check(local, (_addr), _sta, nxt),\ + /* continue condition */ \ + _sta; \ + /* advance loop */ \ + _sta = nxt, \ + nxt = _sta ? rcu_dereference(_sta->hnext) : NULL \ + ) \ /* compare address and run code only if it matches */ \ if (memcmp(_sta->sta.addr, (_addr), ETH_ALEN) == 0) @@ -484,14 +492,14 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, int sta_info_insert(struct sta_info *sta); int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU); int sta_info_insert_atomic(struct sta_info *sta); +int sta_info_reinsert(struct sta_info *sta); int sta_info_destroy_addr(struct ieee80211_sub_if_data *sdata, const u8 *addr); int sta_info_destroy_addr_bss(struct ieee80211_sub_if_data *sdata, const u8 *addr); -void sta_info_set_tim_bit(struct sta_info *sta); -void sta_info_clear_tim_bit(struct sta_info *sta); +void sta_info_recalc_tim(struct sta_info *sta); void sta_info_init(struct ieee80211_local *local); void sta_info_stop(struct ieee80211_local *local); @@ -502,5 +510,6 @@ void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata, void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta); void ieee80211_sta_ps_deliver_poll_response(struct sta_info *sta); +void ieee80211_sta_ps_deliver_uapsd(struct sta_info *sta); #endif /* STA_INFO_H */ diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 1658efa..df643ce 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -14,6 +14,7 @@ #include "rate.h" #include "mesh.h" #include "led.h" +#include "wme.h" void ieee80211_tx_status_irqsafe(struct ieee80211_hw *hw, @@ -43,6 +44,8 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, struct sk_buff *skb) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_hdr *hdr = (void *)skb->data; + int ac; /* * This skb 'survived' a round-trip through the driver, and @@ -63,11 +66,37 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, sta->tx_filtered_count++; /* + * Clear more-data bit on filtered frames, it might be set + * but later frames might time out so it might have to be + * clear again ... It's all rather unlikely (this frame + * should time out first, right?) but let's not confuse + * peers unnecessarily. + */ + if (hdr->frame_control & cpu_to_le16(IEEE80211_FCTL_MOREDATA)) + hdr->frame_control &= ~cpu_to_le16(IEEE80211_FCTL_MOREDATA); + + if (ieee80211_is_data_qos(hdr->frame_control)) { + u8 *p = ieee80211_get_qos_ctl(hdr); + int tid = *p & IEEE80211_QOS_CTL_TID_MASK; + + /* + * Clear EOSP if set, this could happen e.g. + * if an absence period (us being a P2P GO) + * shortens the SP. + */ + if (*p & IEEE80211_QOS_CTL_EOSP) + *p &= ~IEEE80211_QOS_CTL_EOSP; + ac = ieee802_1d_to_ac[tid & 7]; + } else { + ac = IEEE80211_AC_BE; + } + + /* * Clear the TX filter mask for this STA when sending the next * packet. If the STA went to power save mode, this will happen * when it wakes up for the next time. */ - set_sta_flags(sta, WLAN_STA_CLEAR_PS_FILT); + set_sta_flag(sta, WLAN_STA_CLEAR_PS_FILT); /* * This code races in the following way: @@ -103,13 +132,19 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, * changes before calling TX status events if ordering can be * unknown. */ - if (test_sta_flags(sta, WLAN_STA_PS_STA) && - skb_queue_len(&sta->tx_filtered) < STA_MAX_TX_BUFFER) { - skb_queue_tail(&sta->tx_filtered, skb); + if (test_sta_flag(sta, WLAN_STA_PS_STA) && + skb_queue_len(&sta->tx_filtered[ac]) < STA_MAX_TX_BUFFER) { + skb_queue_tail(&sta->tx_filtered[ac], skb); + sta_info_recalc_tim(sta); + + if (!timer_pending(&local->sta_cleanup)) + mod_timer(&local->sta_cleanup, + round_jiffies(jiffies + + STA_INFO_CLEANUP_INTERVAL)); return; } - if (!test_sta_flags(sta, WLAN_STA_PS_STA) && + if (!test_sta_flag(sta, WLAN_STA_PS_STA) && !(info->flags & IEEE80211_TX_INTFL_RETRIED)) { /* Software retry the packet once */ info->flags |= IEEE80211_TX_INTFL_RETRIED; @@ -121,18 +156,38 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, if (net_ratelimit()) wiphy_debug(local->hw.wiphy, "dropped TX filtered frame, queue_len=%d PS=%d @%lu\n", - skb_queue_len(&sta->tx_filtered), - !!test_sta_flags(sta, WLAN_STA_PS_STA), jiffies); + skb_queue_len(&sta->tx_filtered[ac]), + !!test_sta_flag(sta, WLAN_STA_PS_STA), jiffies); #endif dev_kfree_skb(skb); } +static void ieee80211_check_pending_bar(struct sta_info *sta, u8 *addr, u8 tid) +{ + struct tid_ampdu_tx *tid_tx; + + tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]); + if (!tid_tx || !tid_tx->bar_pending) + return; + + tid_tx->bar_pending = false; + ieee80211_send_bar(&sta->sdata->vif, addr, tid, tid_tx->failed_bar_ssn); +} + static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *) skb->data; struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; + if (ieee80211_is_data_qos(mgmt->frame_control)) { + struct ieee80211_hdr *hdr = (void *) skb->data; + u8 *qc = ieee80211_get_qos_ctl(hdr); + u16 tid = qc[0] & 0xf; + + ieee80211_check_pending_bar(sta, hdr->addr1, tid); + } + if (ieee80211_is_action(mgmt->frame_control) && sdata->vif.type == NL80211_IFTYPE_STATION && mgmt->u.action.category == WLAN_CATEGORY_HT && @@ -161,6 +216,114 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb) } } +static void ieee80211_set_bar_pending(struct sta_info *sta, u8 tid, u16 ssn) +{ + struct tid_ampdu_tx *tid_tx; + + tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]); + if (!tid_tx) + return; + + tid_tx->failed_bar_ssn = ssn; + tid_tx->bar_pending = true; +} + +static int ieee80211_tx_radiotap_len(struct ieee80211_tx_info *info) +{ + int len = sizeof(struct ieee80211_radiotap_header); + + /* IEEE80211_RADIOTAP_RATE rate */ + if (info->status.rates[0].idx >= 0 && + !(info->status.rates[0].flags & IEEE80211_TX_RC_MCS)) + len += 2; + + /* IEEE80211_RADIOTAP_TX_FLAGS */ + len += 2; + + /* IEEE80211_RADIOTAP_DATA_RETRIES */ + len += 1; + + /* IEEE80211_TX_RC_MCS */ + if (info->status.rates[0].idx >= 0 && + info->status.rates[0].flags & IEEE80211_TX_RC_MCS) + len += 3; + + return len; +} + +static void ieee80211_add_tx_radiotap_header(struct ieee80211_supported_band + *sband, struct sk_buff *skb, + int retry_count, int rtap_len) +{ + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + struct ieee80211_radiotap_header *rthdr; + unsigned char *pos; + __le16 txflags; + + rthdr = (struct ieee80211_radiotap_header *) skb_push(skb, rtap_len); + + memset(rthdr, 0, rtap_len); + rthdr->it_len = cpu_to_le16(rtap_len); + rthdr->it_present = + cpu_to_le32((1 << IEEE80211_RADIOTAP_TX_FLAGS) | + (1 << IEEE80211_RADIOTAP_DATA_RETRIES)); + pos = (unsigned char *)(rthdr + 1); + + /* + * XXX: Once radiotap gets the bitmap reset thing the vendor + * extensions proposal contains, we can actually report + * the whole set of tries we did. + */ + + /* IEEE80211_RADIOTAP_RATE */ + if (info->status.rates[0].idx >= 0 && + !(info->status.rates[0].flags & IEEE80211_TX_RC_MCS)) { + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_RATE); + *pos = sband->bitrates[info->status.rates[0].idx].bitrate / 5; + /* padding for tx flags */ + pos += 2; + } + + /* IEEE80211_RADIOTAP_TX_FLAGS */ + txflags = 0; + if (!(info->flags & IEEE80211_TX_STAT_ACK) && + !is_multicast_ether_addr(hdr->addr1)) + txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_FAIL); + + if ((info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) || + (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT)) + txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_CTS); + else if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) + txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_RTS); + + put_unaligned_le16(txflags, pos); + pos += 2; + + /* IEEE80211_RADIOTAP_DATA_RETRIES */ + /* for now report the total retry_count */ + *pos = retry_count; + pos++; + + /* IEEE80211_TX_RC_MCS */ + if (info->status.rates[0].idx >= 0 && + info->status.rates[0].flags & IEEE80211_TX_RC_MCS) { + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_MCS); + pos[0] = IEEE80211_RADIOTAP_MCS_HAVE_MCS | + IEEE80211_RADIOTAP_MCS_HAVE_GI | + IEEE80211_RADIOTAP_MCS_HAVE_BW; + if (info->status.rates[0].flags & IEEE80211_TX_RC_SHORT_GI) + pos[1] |= IEEE80211_RADIOTAP_MCS_SGI; + if (info->status.rates[0].flags & IEEE80211_TX_RC_40_MHZ_WIDTH) + pos[1] |= IEEE80211_RADIOTAP_MCS_BW_40; + if (info->status.rates[0].flags & IEEE80211_TX_RC_GREEN_FIELD) + pos[1] |= IEEE80211_RADIOTAP_MCS_FMT_GF; + pos[2] = info->status.rates[0].idx; + pos += 3; + } + +} + /* * Use a static threshold for now, best value to be determined * by testing ... @@ -179,7 +342,6 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) u16 frag, type; __le16 fc; struct ieee80211_supported_band *sband; - struct ieee80211_tx_status_rtap_hdr *rthdr; struct ieee80211_sub_if_data *sdata; struct net_device *prev_dev = NULL; struct sta_info *sta, *tmp; @@ -187,6 +349,9 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) int rates_idx = -1; bool send_to_cooked; bool acked; + struct ieee80211_bar *bar; + u16 tid; + int rtap_len; for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { if (info->status.rates[i].idx < 0) { @@ -215,8 +380,11 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) if (memcmp(hdr->addr2, sta->sdata->vif.addr, ETH_ALEN)) continue; + if (info->flags & IEEE80211_TX_STATUS_EOSP) + clear_sta_flag(sta, WLAN_STA_SP); + acked = !!(info->flags & IEEE80211_TX_STAT_ACK); - if (!acked && test_sta_flags(sta, WLAN_STA_PS_STA)) { + if (!acked && test_sta_flag(sta, WLAN_STA_PS_STA)) { /* * The STA is in power save mode, so assume * that this TX packet failed because of that. @@ -239,10 +407,31 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) tid = qc[0] & 0xf; ssn = ((le16_to_cpu(hdr->seq_ctrl) + 0x10) & IEEE80211_SCTL_SEQ); - ieee80211_send_bar(sta->sdata, hdr->addr1, + ieee80211_send_bar(&sta->sdata->vif, hdr->addr1, tid, ssn); } + if (!acked && ieee80211_is_back_req(fc)) { + u16 control; + + /* + * BAR failed, store the last SSN and retry sending + * the BAR when the next unicast transmission on the + * same TID succeeds. + */ + bar = (struct ieee80211_bar *) skb->data; + control = le16_to_cpu(bar->control); + if (!(control & IEEE80211_BAR_CTRL_MULTI_TID)) { + u16 ssn = le16_to_cpu(bar->start_seq_num); + + tid = (control & + IEEE80211_BAR_CTRL_TID_INFO_MASK) >> + IEEE80211_BAR_CTRL_TID_INFO_SHIFT; + + ieee80211_set_bar_pending(sta, tid, ssn); + } + } + if (info->flags & IEEE80211_TX_STAT_TX_FILTERED) { ieee80211_handle_filtered_frame(local, sta, skb); rcu_read_unlock(); @@ -336,7 +525,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) continue; if (wk->offchan_tx.frame != skb) continue; - wk->offchan_tx.frame = NULL; + wk->offchan_tx.status = true; break; } rcu_read_unlock(); @@ -345,9 +534,6 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) local->hw_roc_skb_for_status = NULL; } - if (cookie == local->hw_offchan_tx_cookie) - local->hw_offchan_tx_cookie = 0; - cfg80211_mgmt_tx_status( skb->dev, cookie, skb->data, skb->len, !!(info->flags & IEEE80211_TX_STAT_ACK), GFP_ATOMIC); @@ -370,44 +556,13 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) } /* send frame to monitor interfaces now */ - - if (skb_headroom(skb) < sizeof(*rthdr)) { + rtap_len = ieee80211_tx_radiotap_len(info); + if (WARN_ON_ONCE(skb_headroom(skb) < rtap_len)) { printk(KERN_ERR "ieee80211_tx_status: headroom too small\n"); dev_kfree_skb(skb); return; } - - rthdr = (struct ieee80211_tx_status_rtap_hdr *) - skb_push(skb, sizeof(*rthdr)); - - memset(rthdr, 0, sizeof(*rthdr)); - rthdr->hdr.it_len = cpu_to_le16(sizeof(*rthdr)); - rthdr->hdr.it_present = - cpu_to_le32((1 << IEEE80211_RADIOTAP_TX_FLAGS) | - (1 << IEEE80211_RADIOTAP_DATA_RETRIES) | - (1 << IEEE80211_RADIOTAP_RATE)); - - if (!(info->flags & IEEE80211_TX_STAT_ACK) && - !is_multicast_ether_addr(hdr->addr1)) - rthdr->tx_flags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_FAIL); - - /* - * XXX: Once radiotap gets the bitmap reset thing the vendor - * extensions proposal contains, we can actually report - * the whole set of tries we did. - */ - if ((info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) || - (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT)) - rthdr->tx_flags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_CTS); - else if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) - rthdr->tx_flags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_RTS); - if (info->status.rates[0].idx >= 0 && - !(info->status.rates[0].flags & IEEE80211_TX_RC_MCS)) - rthdr->rate = sband->bitrates[ - info->status.rates[0].idx].bitrate / 5; - - /* for now report the total retry_count */ - rthdr->data_retries = retry_count; + ieee80211_add_tx_radiotap_header(sband, skb, retry_count, rtap_len); /* XXX: is this sufficient for BPF? */ skb_set_mac_header(skb, 0); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 8cb0d2d..48bbb96 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -253,7 +253,7 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx) struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); - u32 sta_flags; + bool assoc = false; if (unlikely(info->flags & IEEE80211_TX_CTL_INJECTED)) return TX_CONTINUE; @@ -284,10 +284,11 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx) if (tx->flags & IEEE80211_TX_PS_BUFFERED) return TX_CONTINUE; - sta_flags = tx->sta ? get_sta_flags(tx->sta) : 0; + if (tx->sta) + assoc = test_sta_flag(tx->sta, WLAN_STA_ASSOC); if (likely(tx->flags & IEEE80211_TX_UNICAST)) { - if (unlikely(!(sta_flags & WLAN_STA_ASSOC) && + if (unlikely(!assoc && tx->sdata->vif.type != NL80211_IFTYPE_ADHOC && ieee80211_is_data(hdr->frame_control))) { #ifdef CONFIG_MAC80211_VERBOSE_DEBUG @@ -343,13 +344,22 @@ static void purge_old_ps_buffers(struct ieee80211_local *local) total += skb_queue_len(&ap->ps_bc_buf); } + /* + * Drop one frame from each station from the lowest-priority + * AC that has frames at all. + */ list_for_each_entry_rcu(sta, &local->sta_list, list) { - skb = skb_dequeue(&sta->ps_tx_buf); - if (skb) { - purged++; - dev_kfree_skb(skb); + int ac; + + for (ac = IEEE80211_AC_BK; ac >= IEEE80211_AC_VO; ac--) { + skb = skb_dequeue(&sta->ps_tx_buf[ac]); + total += skb_queue_len(&sta->ps_tx_buf[ac]); + if (skb) { + purged++; + dev_kfree_skb(skb); + break; + } } - total += skb_queue_len(&sta->ps_tx_buf); } rcu_read_unlock(); @@ -418,7 +428,7 @@ static int ieee80211_use_mfp(__le16 fc, struct sta_info *sta, if (!ieee80211_is_mgmt(fc)) return 0; - if (sta == NULL || !test_sta_flags(sta, WLAN_STA_MFP)) + if (sta == NULL || !test_sta_flag(sta, WLAN_STA_MFP)) return 0; if (!ieee80211_is_robust_mgmt_frame((struct ieee80211_hdr *) @@ -435,7 +445,6 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; struct ieee80211_local *local = tx->local; - u32 staflags; if (unlikely(!sta || ieee80211_is_probe_resp(hdr->frame_control) || @@ -444,57 +453,52 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) ieee80211_is_reassoc_resp(hdr->frame_control))) return TX_CONTINUE; - staflags = get_sta_flags(sta); + if (unlikely((test_sta_flag(sta, WLAN_STA_PS_STA) || + test_sta_flag(sta, WLAN_STA_PS_DRIVER)) && + !(info->flags & IEEE80211_TX_CTL_POLL_RESPONSE))) { + int ac = skb_get_queue_mapping(tx->skb); - if (unlikely((staflags & (WLAN_STA_PS_STA | WLAN_STA_PS_DRIVER)) && - !(info->flags & IEEE80211_TX_CTL_PSPOLL_RESPONSE))) { #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - printk(KERN_DEBUG "STA %pM aid %d: PS buffer (entries " - "before %d)\n", - sta->sta.addr, sta->sta.aid, - skb_queue_len(&sta->ps_tx_buf)); + printk(KERN_DEBUG "STA %pM aid %d: PS buffer for AC %d\n", + sta->sta.addr, sta->sta.aid, ac); #endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER) purge_old_ps_buffers(tx->local); - if (skb_queue_len(&sta->ps_tx_buf) >= STA_MAX_TX_BUFFER) { - struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf); + if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) { + struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]); #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - if (net_ratelimit()) { - printk(KERN_DEBUG "%s: STA %pM TX " - "buffer full - dropping oldest frame\n", - tx->sdata->name, sta->sta.addr); - } + if (net_ratelimit()) + printk(KERN_DEBUG "%s: STA %pM TX buffer for " + "AC %d full - dropping oldest frame\n", + tx->sdata->name, sta->sta.addr, ac); #endif dev_kfree_skb(old); } else tx->local->total_ps_buffered++; - /* - * Queue frame to be sent after STA wakes up/polls, - * but don't set the TIM bit if the driver is blocking - * wakeup or poll response transmissions anyway. - */ - if (skb_queue_empty(&sta->ps_tx_buf) && - !(staflags & WLAN_STA_PS_DRIVER)) - sta_info_set_tim_bit(sta); - info->control.jiffies = jiffies; info->control.vif = &tx->sdata->vif; info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; - skb_queue_tail(&sta->ps_tx_buf, tx->skb); + skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb); if (!timer_pending(&local->sta_cleanup)) mod_timer(&local->sta_cleanup, round_jiffies(jiffies + STA_INFO_CLEANUP_INTERVAL)); + /* + * We queued up some frames, so the TIM bit might + * need to be set, recalculate it. + */ + sta_info_recalc_tim(sta); + return TX_QUEUED; } #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - else if (unlikely(staflags & WLAN_STA_PS_STA)) { - printk(KERN_DEBUG "%s: STA %pM in PS mode, but pspoll " - "set -> send frame\n", tx->sdata->name, - sta->sta.addr); + else if (unlikely(test_sta_flag(sta, WLAN_STA_PS_STA))) { + printk(KERN_DEBUG + "%s: STA %pM in PS mode, but polling/in SP -> send frame\n", + tx->sdata->name, sta->sta.addr); } #endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ @@ -552,7 +556,7 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) !(info->flags & IEEE80211_TX_CTL_INJECTED) && (!ieee80211_is_robust_mgmt_frame(hdr) || (ieee80211_is_action(hdr->frame_control) && - tx->sta && test_sta_flags(tx->sta, WLAN_STA_MFP)))) { + tx->sta && test_sta_flag(tx->sta, WLAN_STA_MFP)))) { I802_DEBUG_INC(tx->local->tx_handlers_drop_unencrypted); return TX_DROP; } else @@ -611,7 +615,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) u32 len; bool inval = false, rts = false, short_preamble = false; struct ieee80211_tx_rate_control txrc; - u32 sta_flags; + bool assoc = false; memset(&txrc, 0, sizeof(txrc)); @@ -647,17 +651,17 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) */ if (tx->sdata->vif.bss_conf.use_short_preamble && (ieee80211_is_data(hdr->frame_control) || - (tx->sta && test_sta_flags(tx->sta, WLAN_STA_SHORT_PREAMBLE)))) + (tx->sta && test_sta_flag(tx->sta, WLAN_STA_SHORT_PREAMBLE)))) txrc.short_preamble = short_preamble = true; - sta_flags = tx->sta ? get_sta_flags(tx->sta) : 0; + if (tx->sta) + assoc = test_sta_flag(tx->sta, WLAN_STA_ASSOC); /* * Lets not bother rate control if we're associated and cannot * talk to the sta. This should not happen. */ - if (WARN(test_bit(SCAN_SW_SCANNING, &tx->local->scanning) && - (sta_flags & WLAN_STA_ASSOC) && + if (WARN(test_bit(SCAN_SW_SCANNING, &tx->local->scanning) && assoc && !rate_usable_index_exists(sband, &tx->sta->sta), "%s: Dropped data frame as no usable bitrate found while " "scanning and associated. Target station: " @@ -800,6 +804,9 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) if (ieee80211_hdrlen(hdr->frame_control) < 24) return TX_CONTINUE; + if (ieee80211_is_qos_nullfunc(hdr->frame_control)) + return TX_CONTINUE; + /* * Anything but QoS data that has a sequence number field * (is long enough) gets a sequence number from the global @@ -891,7 +898,10 @@ ieee80211_tx_h_fragment(struct ieee80211_tx_data *tx) int hdrlen; int fragnum; - if (!(tx->flags & IEEE80211_TX_FRAGMENTED)) + if (info->flags & IEEE80211_TX_CTL_DONTFRAG) + return TX_CONTINUE; + + if (tx->local->ops->set_frag_threshold) return TX_CONTINUE; /* @@ -904,7 +914,7 @@ ieee80211_tx_h_fragment(struct ieee80211_tx_data *tx) hdrlen = ieee80211_hdrlen(hdr->frame_control); - /* internal error, why is TX_FRAGMENTED set? */ + /* internal error, why isn't DONTFRAG set? */ if (WARN_ON(skb->len + FCS_LEN <= frag_threshold)) return TX_DROP; @@ -1025,100 +1035,6 @@ ieee80211_tx_h_calculate_duration(struct ieee80211_tx_data *tx) /* actual transmit path */ -/* - * deal with packet injection down monitor interface - * with Radiotap Header -- only called for monitor mode interface - */ -static bool __ieee80211_parse_tx_radiotap(struct ieee80211_tx_data *tx, - struct sk_buff *skb) -{ - /* - * this is the moment to interpret and discard the radiotap header that - * must be at the start of the packet injected in Monitor mode - * - * Need to take some care with endian-ness since radiotap - * args are little-endian - */ - - struct ieee80211_radiotap_iterator iterator; - struct ieee80211_radiotap_header *rthdr = - (struct ieee80211_radiotap_header *) skb->data; - bool hw_frag; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - int ret = ieee80211_radiotap_iterator_init(&iterator, rthdr, skb->len, - NULL); - - info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; - tx->flags &= ~IEEE80211_TX_FRAGMENTED; - - /* packet is fragmented in HW if we have a non-NULL driver callback */ - hw_frag = (tx->local->ops->set_frag_threshold != NULL); - - /* - * for every radiotap entry that is present - * (ieee80211_radiotap_iterator_next returns -ENOENT when no more - * entries present, or -EINVAL on error) - */ - - while (!ret) { - ret = ieee80211_radiotap_iterator_next(&iterator); - - if (ret) - continue; - - /* see if this argument is something we can use */ - switch (iterator.this_arg_index) { - /* - * You must take care when dereferencing iterator.this_arg - * for multibyte types... the pointer is not aligned. Use - * get_unaligned((type *)iterator.this_arg) to dereference - * iterator.this_arg for type "type" safely on all arches. - */ - case IEEE80211_RADIOTAP_FLAGS: - if (*iterator.this_arg & IEEE80211_RADIOTAP_F_FCS) { - /* - * this indicates that the skb we have been - * handed has the 32-bit FCS CRC at the end... - * we should react to that by snipping it off - * because it will be recomputed and added - * on transmission - */ - if (skb->len < (iterator._max_length + FCS_LEN)) - return false; - - skb_trim(skb, skb->len - FCS_LEN); - } - if (*iterator.this_arg & IEEE80211_RADIOTAP_F_WEP) - info->flags &= ~IEEE80211_TX_INTFL_DONT_ENCRYPT; - if ((*iterator.this_arg & IEEE80211_RADIOTAP_F_FRAG) && - !hw_frag) - tx->flags |= IEEE80211_TX_FRAGMENTED; - break; - - /* - * Please update the file - * Documentation/networking/mac80211-injection.txt - * when parsing new fields here. - */ - - default: - break; - } - } - - if (ret != -ENOENT) /* ie, if we didn't simply run out of fields */ - return false; - - /* - * remove the radiotap header - * iterator->_max_length was sanity-checked against - * skb->len by iterator init - */ - skb_pull(skb, iterator._max_length); - - return true; -} - static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, struct sk_buff *skb, struct ieee80211_tx_info *info, @@ -1183,7 +1099,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct ieee80211_hdr *hdr; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - int hdrlen, tid; + int tid; u8 *qc; memset(tx, 0, sizeof(*tx)); @@ -1191,26 +1107,6 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, tx->local = local; tx->sdata = sdata; tx->channel = local->hw.conf.channel; - /* - * Set this flag (used below to indicate "automatic fragmentation"), - * it will be cleared/left by radiotap as desired. - * Only valid when fragmentation is done by the stack. - */ - if (!local->ops->set_frag_threshold) - tx->flags |= IEEE80211_TX_FRAGMENTED; - - /* process and remove the injection radiotap header */ - if (unlikely(info->flags & IEEE80211_TX_INTFL_HAS_RADIOTAP)) { - if (!__ieee80211_parse_tx_radiotap(tx, skb)) - return TX_DROP; - - /* - * __ieee80211_parse_tx_radiotap has now removed - * the radiotap header that was present and pre-filled - * 'tx' with tx control information. - */ - info->flags &= ~IEEE80211_TX_INTFL_HAS_RADIOTAP; - } /* * If this flag is set to true anywhere, and we get here, @@ -1232,7 +1128,9 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, tx->sta = sta_info_get(sdata, hdr->addr1); if (tx->sta && ieee80211_is_data_qos(hdr->frame_control) && - (local->hw.flags & IEEE80211_HW_AMPDU_AGGREGATION)) { + !ieee80211_is_qos_nullfunc(hdr->frame_control) && + (local->hw.flags & IEEE80211_HW_AMPDU_AGGREGATION) && + !(local->hw.flags & IEEE80211_HW_TX_AMPDU_SETUP_IN_HW)) { struct tid_ampdu_tx *tid_tx; qc = ieee80211_get_qos_ctl(hdr); @@ -1257,29 +1155,25 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, tx->flags |= IEEE80211_TX_UNICAST; if (unlikely(local->wifi_wme_noack_test)) info->flags |= IEEE80211_TX_CTL_NO_ACK; - else - info->flags &= ~IEEE80211_TX_CTL_NO_ACK; + /* + * Flags are initialized to 0. Hence, no need to + * explicitly unset IEEE80211_TX_CTL_NO_ACK since + * it might already be set for injected frames. + */ } - if (tx->flags & IEEE80211_TX_FRAGMENTED) { - if ((tx->flags & IEEE80211_TX_UNICAST) && - skb->len + FCS_LEN > local->hw.wiphy->frag_threshold && - !(info->flags & IEEE80211_TX_CTL_AMPDU)) - tx->flags |= IEEE80211_TX_FRAGMENTED; - else - tx->flags &= ~IEEE80211_TX_FRAGMENTED; + if (!(info->flags & IEEE80211_TX_CTL_DONTFRAG)) { + if (!(tx->flags & IEEE80211_TX_UNICAST) || + skb->len + FCS_LEN <= local->hw.wiphy->frag_threshold || + info->flags & IEEE80211_TX_CTL_AMPDU) + info->flags |= IEEE80211_TX_CTL_DONTFRAG; } if (!tx->sta) info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT; - else if (test_and_clear_sta_flags(tx->sta, WLAN_STA_CLEAR_PS_FILT)) + else if (test_and_clear_sta_flag(tx->sta, WLAN_STA_CLEAR_PS_FILT)) info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT; - hdrlen = ieee80211_hdrlen(hdr->frame_control); - if (skb->len > hdrlen + sizeof(rfc1042_header) + 2) { - u8 *pos = &skb->data[hdrlen + sizeof(rfc1042_header)]; - tx->ethertype = (pos[0] << 8) | pos[1]; - } info->flags |= IEEE80211_TX_CTL_FIRST_FRAGMENT; return TX_CONTINUE; @@ -1490,11 +1384,6 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, tail_need = max_t(int, tail_need, 0); } - if (head_need || tail_need) { - /* Sorry. Can't account for this any more */ - skb_orphan(skb); - } - if (skb_cloned(skb)) I802_DEBUG_INC(local->tx_expand_skb_head_cloned); else if (head_need || tail_need) @@ -1508,67 +1397,19 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, return -ENOMEM; } - /* update truesize too */ - skb->truesize += head_need + tail_need; - return 0; } -static void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb) +void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; - struct ieee80211_sub_if_data *tmp_sdata; int headroom; bool may_encrypt; rcu_read_lock(); - if (unlikely(sdata->vif.type == NL80211_IFTYPE_MONITOR)) { - int hdrlen; - u16 len_rthdr; - - info->flags |= IEEE80211_TX_CTL_INJECTED | - IEEE80211_TX_INTFL_HAS_RADIOTAP; - - len_rthdr = ieee80211_get_radiotap_len(skb->data); - hdr = (struct ieee80211_hdr *)(skb->data + len_rthdr); - hdrlen = ieee80211_hdrlen(hdr->frame_control); - - /* check the header is complete in the frame */ - if (likely(skb->len >= len_rthdr + hdrlen)) { - /* - * We process outgoing injected frames that have a - * local address we handle as though they are our - * own frames. - * This code here isn't entirely correct, the local - * MAC address is not necessarily enough to find - * the interface to use; for that proper VLAN/WDS - * support we will need a different mechanism. - */ - - list_for_each_entry_rcu(tmp_sdata, &local->interfaces, - list) { - if (!ieee80211_sdata_running(tmp_sdata)) - continue; - if (tmp_sdata->vif.type == - NL80211_IFTYPE_MONITOR || - tmp_sdata->vif.type == - NL80211_IFTYPE_AP_VLAN || - tmp_sdata->vif.type == - NL80211_IFTYPE_WDS) - continue; - if (compare_ether_addr(tmp_sdata->vif.addr, - hdr->addr2) == 0) { - sdata = tmp_sdata; - break; - } - } - } - } - may_encrypt = !(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT); headroom = local->tx_headroom; @@ -1595,11 +1436,94 @@ static void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, return; } - ieee80211_set_qos_hdr(local, skb); + ieee80211_set_qos_hdr(sdata, skb); ieee80211_tx(sdata, skb, false); rcu_read_unlock(); } +static bool ieee80211_parse_tx_radiotap(struct sk_buff *skb) +{ + struct ieee80211_radiotap_iterator iterator; + struct ieee80211_radiotap_header *rthdr = + (struct ieee80211_radiotap_header *) skb->data; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + int ret = ieee80211_radiotap_iterator_init(&iterator, rthdr, skb->len, + NULL); + u16 txflags; + + info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | + IEEE80211_TX_CTL_DONTFRAG; + + /* + * for every radiotap entry that is present + * (ieee80211_radiotap_iterator_next returns -ENOENT when no more + * entries present, or -EINVAL on error) + */ + + while (!ret) { + ret = ieee80211_radiotap_iterator_next(&iterator); + + if (ret) + continue; + + /* see if this argument is something we can use */ + switch (iterator.this_arg_index) { + /* + * You must take care when dereferencing iterator.this_arg + * for multibyte types... the pointer is not aligned. Use + * get_unaligned((type *)iterator.this_arg) to dereference + * iterator.this_arg for type "type" safely on all arches. + */ + case IEEE80211_RADIOTAP_FLAGS: + if (*iterator.this_arg & IEEE80211_RADIOTAP_F_FCS) { + /* + * this indicates that the skb we have been + * handed has the 32-bit FCS CRC at the end... + * we should react to that by snipping it off + * because it will be recomputed and added + * on transmission + */ + if (skb->len < (iterator._max_length + FCS_LEN)) + return false; + + skb_trim(skb, skb->len - FCS_LEN); + } + if (*iterator.this_arg & IEEE80211_RADIOTAP_F_WEP) + info->flags &= ~IEEE80211_TX_INTFL_DONT_ENCRYPT; + if (*iterator.this_arg & IEEE80211_RADIOTAP_F_FRAG) + info->flags &= ~IEEE80211_TX_CTL_DONTFRAG; + break; + + case IEEE80211_RADIOTAP_TX_FLAGS: + txflags = get_unaligned_le16(iterator.this_arg); + if (txflags & IEEE80211_RADIOTAP_F_TX_NOACK) + info->flags |= IEEE80211_TX_CTL_NO_ACK; + break; + + /* + * Please update the file + * Documentation/networking/mac80211-injection.txt + * when parsing new fields here. + */ + + default: + break; + } + } + + if (ret != -ENOENT) /* ie, if we didn't simply run out of fields */ + return false; + + /* + * remove the radiotap header + * iterator->_max_length was sanity-checked against + * skb->len by iterator init + */ + skb_pull(skb, iterator._max_length); + + return true; +} + netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -1608,7 +1532,10 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, struct ieee80211_radiotap_header *prthdr = (struct ieee80211_radiotap_header *)skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_hdr *hdr; + struct ieee80211_sub_if_data *tmp_sdata, *sdata; u16 len_rthdr; + int hdrlen; /* * Frame injection is not allowed if beaconing is not allowed @@ -1659,12 +1586,65 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, skb_set_network_header(skb, len_rthdr); skb_set_transport_header(skb, len_rthdr); + if (skb->len < len_rthdr + 2) + goto fail; + + hdr = (struct ieee80211_hdr *)(skb->data + len_rthdr); + hdrlen = ieee80211_hdrlen(hdr->frame_control); + + if (skb->len < len_rthdr + hdrlen) + goto fail; + + /* + * Initialize skb->protocol if the injected frame is a data frame + * carrying a rfc1042 header + */ + if (ieee80211_is_data(hdr->frame_control) && + skb->len >= len_rthdr + hdrlen + sizeof(rfc1042_header) + 2) { + u8 *payload = (u8 *)hdr + hdrlen; + + if (compare_ether_addr(payload, rfc1042_header) == 0) + skb->protocol = cpu_to_be16((payload[6] << 8) | + payload[7]); + } + memset(info, 0, sizeof(*info)); - info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS; + info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS | + IEEE80211_TX_CTL_INJECTED; + + /* process and remove the injection radiotap header */ + if (!ieee80211_parse_tx_radiotap(skb)) + goto fail; + + rcu_read_lock(); + + /* + * We process outgoing injected frames that have a local address + * we handle as though they are non-injected frames. + * This code here isn't entirely correct, the local MAC address + * isn't always enough to find the interface to use; for proper + * VLAN/WDS support we will need a different mechanism (which + * likely isn't going to be monitor interfaces). + */ + sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + list_for_each_entry_rcu(tmp_sdata, &local->interfaces, list) { + if (!ieee80211_sdata_running(tmp_sdata)) + continue; + if (tmp_sdata->vif.type == NL80211_IFTYPE_MONITOR || + tmp_sdata->vif.type == NL80211_IFTYPE_AP_VLAN || + tmp_sdata->vif.type == NL80211_IFTYPE_WDS) + continue; + if (compare_ether_addr(tmp_sdata->vif.addr, hdr->addr2) == 0) { + sdata = tmp_sdata; + break; + } + } + + ieee80211_xmit(sdata, skb); + rcu_read_unlock(); - /* pass the radiotap header up to xmit */ - ieee80211_xmit(IEEE80211_DEV_TO_SUB_IF(dev), skb); return NETDEV_TX_OK; fail: @@ -1703,8 +1683,9 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, int encaps_len, skip_header_bytes; int nh_pos, h_pos; struct sta_info *sta = NULL; - u32 sta_flags = 0; + bool wme_sta = false, authorized = false, tdls_auth = false; struct sk_buff *tmp_skb; + bool tdls_direct = false; if (unlikely(skb->len < ETH_HLEN)) { ret = NETDEV_TX_OK; @@ -1728,7 +1709,8 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, memcpy(hdr.addr3, skb->data, ETH_ALEN); memcpy(hdr.addr4, skb->data + ETH_ALEN, ETH_ALEN); hdrlen = 30; - sta_flags = get_sta_flags(sta); + authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED); + wme_sta = test_sta_flag(sta, WLAN_STA_WME); } rcu_read_unlock(); if (sta) @@ -1816,11 +1798,50 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, break; #endif case NL80211_IFTYPE_STATION: - memcpy(hdr.addr1, sdata->u.mgd.bssid, ETH_ALEN); - if (sdata->u.mgd.use_4addr && - cpu_to_be16(ethertype) != sdata->control_port_protocol) { - fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS); + if (sdata->wdev.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS) { + bool tdls_peer = false; + + rcu_read_lock(); + sta = sta_info_get(sdata, skb->data); + if (sta) { + authorized = test_sta_flag(sta, + WLAN_STA_AUTHORIZED); + wme_sta = test_sta_flag(sta, WLAN_STA_WME); + tdls_peer = test_sta_flag(sta, + WLAN_STA_TDLS_PEER); + tdls_auth = test_sta_flag(sta, + WLAN_STA_TDLS_PEER_AUTH); + } + rcu_read_unlock(); + + /* + * If the TDLS link is enabled, send everything + * directly. Otherwise, allow TDLS setup frames + * to be transmitted indirectly. + */ + tdls_direct = tdls_peer && (tdls_auth || + !(ethertype == ETH_P_TDLS && skb->len > 14 && + skb->data[14] == WLAN_TDLS_SNAP_RFTYPE)); + } + + if (tdls_direct) { + /* link during setup - throw out frames to peer */ + if (!tdls_auth) { + ret = NETDEV_TX_OK; + goto fail; + } + + /* DA SA BSSID */ + memcpy(hdr.addr1, skb->data, ETH_ALEN); + memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN); + memcpy(hdr.addr3, sdata->u.mgd.bssid, ETH_ALEN); + hdrlen = 24; + } else if (sdata->u.mgd.use_4addr && + cpu_to_be16(ethertype) != sdata->control_port_protocol) { + fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | + IEEE80211_FCTL_TODS); /* RA TA DA SA */ + memcpy(hdr.addr1, sdata->u.mgd.bssid, ETH_ALEN); memcpy(hdr.addr2, sdata->vif.addr, ETH_ALEN); memcpy(hdr.addr3, skb->data, ETH_ALEN); memcpy(hdr.addr4, skb->data + ETH_ALEN, ETH_ALEN); @@ -1828,6 +1849,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, } else { fc |= cpu_to_le16(IEEE80211_FCTL_TODS); /* BSSID SA DA */ + memcpy(hdr.addr1, sdata->u.mgd.bssid, ETH_ALEN); memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN); memcpy(hdr.addr3, skb->data, ETH_ALEN); hdrlen = 24; @@ -1853,13 +1875,19 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, if (!is_multicast_ether_addr(hdr.addr1)) { rcu_read_lock(); sta = sta_info_get(sdata, hdr.addr1); - if (sta) - sta_flags = get_sta_flags(sta); + if (sta) { + authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED); + wme_sta = test_sta_flag(sta, WLAN_STA_WME); + } rcu_read_unlock(); } + /* For mesh, the use of the QoS header is mandatory */ + if (ieee80211_vif_is_mesh(&sdata->vif)) + wme_sta = true; + /* receiver and we are QoS enabled, use a QoS type frame */ - if ((sta_flags & WLAN_STA_WME) && local->hw.queues >= 4) { + if (wme_sta && local->hw.queues >= 4) { fc |= cpu_to_le16(IEEE80211_STYPE_QOS_DATA); hdrlen += 2; } @@ -1868,12 +1896,10 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, * Drop unicast frames to unauthorised stations unless they are * EAPOL frames from the local station. */ - if (!ieee80211_vif_is_mesh(&sdata->vif) && - unlikely(!is_multicast_ether_addr(hdr.addr1) && - !(sta_flags & WLAN_STA_AUTHORIZED) && - !(cpu_to_be16(ethertype) == sdata->control_port_protocol && - compare_ether_addr(sdata->vif.addr, - skb->data + ETH_ALEN) == 0))) { + if (unlikely(!ieee80211_vif_is_mesh(&sdata->vif) && + !is_multicast_ether_addr(hdr.addr1) && !authorized && + (cpu_to_be16(ethertype) != sdata->control_port_protocol || + compare_ether_addr(sdata->vif.addr, skb->data + ETH_ALEN)))) { #ifdef CONFIG_MAC80211_VERBOSE_DEBUG if (net_ratelimit()) printk(KERN_DEBUG "%s: dropped frame to %pM" @@ -2275,13 +2301,23 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN); mgmt->u.beacon.beacon_int = cpu_to_le16(sdata->vif.bss_conf.beacon_int); - mgmt->u.beacon.capab_info = 0x0; /* 0x0 for MPs */ + mgmt->u.beacon.capab_info |= cpu_to_le16( + sdata->u.mesh.security ? WLAN_CAPABILITY_PRIVACY : 0); pos = skb_put(skb, 2); *pos++ = WLAN_EID_SSID; *pos++ = 0x0; - mesh_mgmt_ies_add(skb, sdata); + if (ieee80211_add_srates_ie(&sdata->vif, skb) || + mesh_add_ds_params_ie(skb, sdata) || + ieee80211_add_ext_srates_ie(&sdata->vif, skb) || + mesh_add_rsn_ie(skb, sdata) || + mesh_add_meshid_ie(skb, sdata) || + mesh_add_meshconf_ie(skb, sdata) || + mesh_add_vendor_ies(skb, sdata)) { + pr_err("o11s: couldn't add ies!\n"); + goto out; + } } else { WARN_ON(1); goto out; @@ -2335,11 +2371,9 @@ struct sk_buff *ieee80211_pspoll_get(struct ieee80211_hw *hw, local = sdata->local; skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(*pspoll)); - if (!skb) { - printk(KERN_DEBUG "%s: failed to allocate buffer for " - "pspoll template\n", sdata->name); + if (!skb) return NULL; - } + skb_reserve(skb, local->hw.extra_tx_headroom); pspoll = (struct ieee80211_pspoll *) skb_put(skb, sizeof(*pspoll)); @@ -2375,11 +2409,9 @@ struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw, local = sdata->local; skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(*nullfunc)); - if (!skb) { - printk(KERN_DEBUG "%s: failed to allocate buffer for nullfunc " - "template\n", sdata->name); + if (!skb) return NULL; - } + skb_reserve(skb, local->hw.extra_tx_headroom); nullfunc = (struct ieee80211_hdr_3addr *) skb_put(skb, @@ -2414,11 +2446,8 @@ struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw, skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(*hdr) + ie_ssid_len + ie_len); - if (!skb) { - printk(KERN_DEBUG "%s: failed to allocate buffer for probe " - "request template\n", sdata->name); + if (!skb) return NULL; - } skb_reserve(skb, local->hw.extra_tx_headroom); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index ddeb1b9..7439d26 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -19,7 +19,6 @@ #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/bitmap.h> -#include <linux/crc32.h> #include <net/net_namespace.h> #include <net/cfg80211.h> #include <net/rtnetlink.h> @@ -368,14 +367,14 @@ void ieee80211_add_pending_skb(struct ieee80211_local *local, spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } -int ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, - struct sk_buff_head *skbs, - void (*fn)(void *data), void *data) +void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, + struct sk_buff_head *skbs, + void (*fn)(void *data), void *data) { struct ieee80211_hw *hw = &local->hw; struct sk_buff *skb; unsigned long flags; - int queue, ret = 0, i; + int queue, i; spin_lock_irqsave(&local->queue_stop_reason_lock, flags); for (i = 0; i < hw->queues; i++) @@ -390,7 +389,6 @@ int ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, continue; } - ret++; queue = skb_get_queue_mapping(skb); __skb_queue_tail(&local->pending[queue], skb); } @@ -402,14 +400,12 @@ int ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, __ieee80211_wake_queue(hw, i, IEEE80211_QUEUE_STOP_REASON_SKB_ADD); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); - - return ret; } -int ieee80211_add_pending_skbs(struct ieee80211_local *local, - struct sk_buff_head *skbs) +void ieee80211_add_pending_skbs(struct ieee80211_local *local, + struct sk_buff_head *skbs) { - return ieee80211_add_pending_skbs_fn(local, skbs, NULL, NULL); + ieee80211_add_pending_skbs_fn(local, skbs, NULL, NULL); } void ieee80211_stop_queues_by_reason(struct ieee80211_hw *hw, @@ -573,172 +569,6 @@ void ieee802_11_parse_elems(u8 *start, size_t len, ieee802_11_parse_elems_crc(start, len, elems, 0, 0); } -u32 ieee802_11_parse_elems_crc(u8 *start, size_t len, - struct ieee802_11_elems *elems, - u64 filter, u32 crc) -{ - size_t left = len; - u8 *pos = start; - bool calc_crc = filter != 0; - - memset(elems, 0, sizeof(*elems)); - elems->ie_start = start; - elems->total_len = len; - - while (left >= 2) { - u8 id, elen; - - id = *pos++; - elen = *pos++; - left -= 2; - - if (elen > left) - break; - - if (calc_crc && id < 64 && (filter & (1ULL << id))) - crc = crc32_be(crc, pos - 2, elen + 2); - - switch (id) { - case WLAN_EID_SSID: - elems->ssid = pos; - elems->ssid_len = elen; - break; - case WLAN_EID_SUPP_RATES: - elems->supp_rates = pos; - elems->supp_rates_len = elen; - break; - case WLAN_EID_FH_PARAMS: - elems->fh_params = pos; - elems->fh_params_len = elen; - break; - case WLAN_EID_DS_PARAMS: - elems->ds_params = pos; - elems->ds_params_len = elen; - break; - case WLAN_EID_CF_PARAMS: - elems->cf_params = pos; - elems->cf_params_len = elen; - break; - case WLAN_EID_TIM: - if (elen >= sizeof(struct ieee80211_tim_ie)) { - elems->tim = (void *)pos; - elems->tim_len = elen; - } - break; - case WLAN_EID_IBSS_PARAMS: - elems->ibss_params = pos; - elems->ibss_params_len = elen; - break; - case WLAN_EID_CHALLENGE: - elems->challenge = pos; - elems->challenge_len = elen; - break; - case WLAN_EID_VENDOR_SPECIFIC: - if (elen >= 4 && pos[0] == 0x00 && pos[1] == 0x50 && - pos[2] == 0xf2) { - /* Microsoft OUI (00:50:F2) */ - - if (calc_crc) - crc = crc32_be(crc, pos - 2, elen + 2); - - if (pos[3] == 1) { - /* OUI Type 1 - WPA IE */ - elems->wpa = pos; - elems->wpa_len = elen; - } else if (elen >= 5 && pos[3] == 2) { - /* OUI Type 2 - WMM IE */ - if (pos[4] == 0) { - elems->wmm_info = pos; - elems->wmm_info_len = elen; - } else if (pos[4] == 1) { - elems->wmm_param = pos; - elems->wmm_param_len = elen; - } - } - } - break; - case WLAN_EID_RSN: - elems->rsn = pos; - elems->rsn_len = elen; - break; - case WLAN_EID_ERP_INFO: - elems->erp_info = pos; - elems->erp_info_len = elen; - break; - case WLAN_EID_EXT_SUPP_RATES: - elems->ext_supp_rates = pos; - elems->ext_supp_rates_len = elen; - break; - case WLAN_EID_HT_CAPABILITY: - if (elen >= sizeof(struct ieee80211_ht_cap)) - elems->ht_cap_elem = (void *)pos; - break; - case WLAN_EID_HT_INFORMATION: - if (elen >= sizeof(struct ieee80211_ht_info)) - elems->ht_info_elem = (void *)pos; - break; - case WLAN_EID_MESH_ID: - elems->mesh_id = pos; - elems->mesh_id_len = elen; - break; - case WLAN_EID_MESH_CONFIG: - if (elen >= sizeof(struct ieee80211_meshconf_ie)) - elems->mesh_config = (void *)pos; - break; - case WLAN_EID_PEER_LINK: - elems->peer_link = pos; - elems->peer_link_len = elen; - break; - case WLAN_EID_PREQ: - elems->preq = pos; - elems->preq_len = elen; - break; - case WLAN_EID_PREP: - elems->prep = pos; - elems->prep_len = elen; - break; - case WLAN_EID_PERR: - elems->perr = pos; - elems->perr_len = elen; - break; - case WLAN_EID_RANN: - if (elen >= sizeof(struct ieee80211_rann_ie)) - elems->rann = (void *)pos; - break; - case WLAN_EID_CHANNEL_SWITCH: - elems->ch_switch_elem = pos; - elems->ch_switch_elem_len = elen; - break; - case WLAN_EID_QUIET: - if (!elems->quiet_elem) { - elems->quiet_elem = pos; - elems->quiet_elem_len = elen; - } - elems->num_of_quiet_elem++; - break; - case WLAN_EID_COUNTRY: - elems->country_elem = pos; - elems->country_elem_len = elen; - break; - case WLAN_EID_PWR_CONSTRAINT: - elems->pwr_constr_elem = pos; - elems->pwr_constr_elem_len = elen; - break; - case WLAN_EID_TIMEOUT_INTERVAL: - elems->timeout_int = pos; - elems->timeout_int_len = elen; - break; - default: - break; - } - - left -= elen; - pos += elen; - } - - return crc; -} - void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; @@ -799,8 +629,8 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata) qparam.uapsd = false; - local->tx_conf[queue] = qparam; - drv_conf_tx(local, queue, &qparam); + sdata->tx_conf[queue] = qparam; + drv_conf_tx(local, sdata, queue, &qparam); } /* after reinitialize QoS TX queues setting to default, @@ -874,11 +704,9 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(*mgmt) + 6 + extra_len); - if (!skb) { - printk(KERN_DEBUG "%s: failed to allocate buffer for auth " - "frame\n", sdata->name); + if (!skb) return; - } + skb_reserve(skb, local->hw.extra_tx_headroom); mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24 + 6); @@ -1031,11 +859,8 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, /* FIXME: come up with a proper value */ buf = kmalloc(200 + ie_len, GFP_KERNEL); - if (!buf) { - printk(KERN_DEBUG "%s: failed to allocate temporary IE " - "buffer\n", sdata->name); + if (!buf) return NULL; - } /* * Do not send DS Channel parameter for directed probe requests @@ -1071,14 +896,18 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, const u8 *ssid, size_t ssid_len, const u8 *ie, size_t ie_len, - u32 ratemask, bool directed) + u32 ratemask, bool directed, bool no_cck) { struct sk_buff *skb; skb = ieee80211_build_probe_req(sdata, dst, ratemask, ssid, ssid_len, ie, ie_len, directed); - if (skb) + if (skb) { + if (no_cck) + IEEE80211_SKB_CB(skb)->flags |= + IEEE80211_TX_CTL_NO_CCK_RATE; ieee80211_tx_skb(sdata, skb); + } } u32 ieee80211_sta_get_rates(struct ieee80211_local *local, @@ -1205,14 +1034,22 @@ int ieee80211_reconfig(struct ieee80211_local *local) struct ieee80211_sub_if_data, u.ap); + memset(&sta->sta.drv_priv, 0, hw->sta_data_size); WARN_ON(drv_sta_add(local, sdata, &sta->sta)); } } mutex_unlock(&local->sta_mtx); /* reconfigure tx conf */ - for (i = 0; i < hw->queues; i++) - drv_conf_tx(local, i, &local->tx_conf[i]); + list_for_each_entry(sdata, &local->interfaces, list) { + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN || + sdata->vif.type == NL80211_IFTYPE_MONITOR || + !ieee80211_sdata_running(sdata)) + continue; + + for (i = 0; i < hw->queues; i++) + drv_conf_tx(local, sdata, i, &sdata->tx_conf[i]); + } /* reconfigure hardware */ ieee80211_hw_config(local, ~0); @@ -1248,6 +1085,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) changed |= BSS_CHANGED_IBSS; /* fall through */ case NL80211_IFTYPE_AP: + changed |= BSS_CHANGED_SSID; + /* fall through */ case NL80211_IFTYPE_MESH_POINT: changed |= BSS_CHANGED_BEACON | BSS_CHANGED_BEACON_ENABLED; @@ -1283,7 +1122,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) list_for_each_entry(sta, &local->sta_list, list) { ieee80211_sta_tear_down_BA_sessions(sta, true); - clear_sta_flags(sta, WLAN_STA_BLOCK_BA); + clear_sta_flag(sta, WLAN_STA_BLOCK_BA); } mutex_unlock(&local->sta_mtx); @@ -1522,3 +1361,60 @@ void ieee80211_disable_rssi_reports(struct ieee80211_vif *vif) _ieee80211_enable_rssi_reports(sdata, 0, 0); } EXPORT_SYMBOL(ieee80211_disable_rssi_reports); + +int ieee80211_add_srates_ie(struct ieee80211_vif *vif, struct sk_buff *skb) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_local *local = sdata->local; + struct ieee80211_supported_band *sband; + int rate; + u8 i, rates, *pos; + + sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; + rates = sband->n_bitrates; + if (rates > 8) + rates = 8; + + if (skb_tailroom(skb) < rates + 2) + return -ENOMEM; + + pos = skb_put(skb, rates + 2); + *pos++ = WLAN_EID_SUPP_RATES; + *pos++ = rates; + for (i = 0; i < rates; i++) { + rate = sband->bitrates[i].bitrate; + *pos++ = (u8) (rate / 5); + } + + return 0; +} + +int ieee80211_add_ext_srates_ie(struct ieee80211_vif *vif, struct sk_buff *skb) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_local *local = sdata->local; + struct ieee80211_supported_band *sband; + int rate; + u8 i, exrates, *pos; + + sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; + exrates = sband->n_bitrates; + if (exrates > 8) + exrates -= 8; + else + exrates = 0; + + if (skb_tailroom(skb) < exrates + 2) + return -ENOMEM; + + if (exrates) { + pos = skb_put(skb, exrates + 2); + *pos++ = WLAN_EID_EXT_SUPP_RATES; + *pos++ = exrates; + for (i = 8; i < sband->n_bitrates; i++) { + rate = sband->bitrates[i].bitrate; + *pos++ = (u8) (rate / 5); + } + } + return 0; +} diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 7a49532..fd52e69 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -72,7 +72,7 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_AP_VLAN: sta = rcu_dereference(sdata->u.vlan.sta); if (sta) { - qos = get_sta_flags(sta) & WLAN_STA_WME; + qos = test_sta_flag(sta, WLAN_STA_WME); break; } case NL80211_IFTYPE_AP: @@ -83,11 +83,7 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, break; #ifdef CONFIG_MAC80211_MESH case NL80211_IFTYPE_MESH_POINT: - /* - * XXX: This is clearly broken ... but already was before, - * because ieee80211_fill_mesh_addresses() would clear A1 - * except for multicast addresses. - */ + ra = skb->data; break; #endif case NL80211_IFTYPE_STATION: @@ -103,7 +99,7 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, if (!sta && ra && !is_multicast_ether_addr(ra)) { sta = sta_info_get(sdata, ra); if (sta) - qos = get_sta_flags(sta) & WLAN_STA_WME; + qos = test_sta_flag(sta, WLAN_STA_WME); } rcu_read_unlock(); @@ -139,7 +135,8 @@ u16 ieee80211_downgrade_queue(struct ieee80211_local *local, return ieee802_1d_to_ac[skb->priority]; } -void ieee80211_set_qos_hdr(struct ieee80211_local *local, struct sk_buff *skb) +void ieee80211_set_qos_hdr(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) { struct ieee80211_hdr *hdr = (void *)skb->data; @@ -150,10 +147,11 @@ void ieee80211_set_qos_hdr(struct ieee80211_local *local, struct sk_buff *skb) tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; - if (unlikely(local->wifi_wme_noack_test)) + if (unlikely(sdata->local->wifi_wme_noack_test)) ack_policy |= IEEE80211_QOS_CTL_ACK_POLICY_NOACK; - /* qos header is 2 bytes, second reserved */ + /* qos header is 2 bytes */ *p++ = ack_policy | tid; - *p = 0; + *p = ieee80211_vif_is_mesh(&sdata->vif) ? + (IEEE80211_QOS_CTL_MESH_CONTROL_PRESENT >> 8) : 0; } } diff --git a/net/mac80211/wme.h b/net/mac80211/wme.h index faead6d..34e166f 100644 --- a/net/mac80211/wme.h +++ b/net/mac80211/wme.h @@ -17,7 +17,8 @@ extern const int ieee802_1d_to_ac[8]; u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); -void ieee80211_set_qos_hdr(struct ieee80211_local *local, struct sk_buff *skb); +void ieee80211_set_qos_hdr(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb); u16 ieee80211_downgrade_queue(struct ieee80211_local *local, struct sk_buff *skb); diff --git a/net/mac80211/work.c b/net/mac80211/work.c index 380b9a7..94472eb 100644 --- a/net/mac80211/work.c +++ b/net/mac80211/work.c @@ -229,11 +229,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata, wk->ie_len + /* extra IEs */ 9, /* WMM */ GFP_KERNEL); - if (!skb) { - printk(KERN_DEBUG "%s: failed to allocate buffer for assoc " - "frame\n", sdata->name); + if (!skb) return; - } + skb_reserve(skb, local->hw.extra_tx_headroom); capab = WLAN_CAPABILITY_ESS; @@ -460,7 +458,7 @@ ieee80211_direct_probe(struct ieee80211_work *wk) */ ieee80211_send_probe_req(sdata, NULL, wk->probe_auth.ssid, wk->probe_auth.ssid_len, NULL, 0, - (u32) -1, true); + (u32) -1, true, false); wk->timeout = jiffies + IEEE80211_AUTH_TIMEOUT; run_again(local, wk->timeout); @@ -579,7 +577,7 @@ ieee80211_offchannel_tx(struct ieee80211_work *wk) /* * After this, offchan_tx.frame remains but now is no * longer a valid pointer -- we still need it as the - * cookie for canceling this work. + * cookie for canceling this work/status matching. */ ieee80211_tx_skb(wk->sdata, wk->offchan_tx.frame); diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 7bc8702..f614ce7 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -53,7 +53,8 @@ ieee80211_tx_h_michael_mic_add(struct ieee80211_tx_data *tx) } if (info->control.hw_key && - !(tx->flags & IEEE80211_TX_FRAGMENTED) && + (info->flags & IEEE80211_TX_CTL_DONTFRAG || + tx->local->ops->set_frag_threshold) && !(tx->key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC)) { /* hwaccel - with no need for SW-generated MMIC */ return TX_CONTINUE; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 32bff6d..8260b13 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -505,7 +505,7 @@ config NETFILTER_XT_TARGET_LED echo netfilter-ssh > /sys/class/leds/<ledname>/trigger For more information on the LEDs available on your system, see - Documentation/leds-class.txt + Documentation/leds/leds-class.txt config NETFILTER_XT_TARGET_MARK tristate '"MARK" target support' diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 899b71c..afca6c7 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -37,7 +37,7 @@ int nf_register_afinfo(const struct nf_afinfo *afinfo) err = mutex_lock_interruptible(&afinfo_mutex); if (err < 0) return err; - rcu_assign_pointer(nf_afinfo[afinfo->family], afinfo); + RCU_INIT_POINTER(nf_afinfo[afinfo->family], afinfo); mutex_unlock(&afinfo_mutex); return 0; } @@ -46,7 +46,7 @@ EXPORT_SYMBOL_GPL(nf_register_afinfo); void nf_unregister_afinfo(const struct nf_afinfo *afinfo) { mutex_lock(&afinfo_mutex); - rcu_assign_pointer(nf_afinfo[afinfo->family], NULL); + RCU_INIT_POINTER(nf_afinfo[afinfo->family], NULL); mutex_unlock(&afinfo_mutex); synchronize_rcu(); } @@ -180,17 +180,16 @@ next_hook: if (ret == 0) ret = -EPERM; } else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) { - ret = nf_queue(skb, elem, pf, hook, indev, outdev, okfn, - verdict >> NF_VERDICT_QBITS); - if (ret < 0) { - if (ret == -ECANCELED) + int err = nf_queue(skb, elem, pf, hook, indev, outdev, okfn, + verdict >> NF_VERDICT_QBITS); + if (err < 0) { + if (err == -ECANCELED) goto next_hook; - if (ret == -ESRCH && + if (err == -ESRCH && (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) goto next_hook; kfree_skb(skb); } - ret = 0; } rcu_read_unlock(); return ret; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index d7e86ef..86137b5 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1699,10 +1699,8 @@ ip_set_init(void) ip_set_list = kzalloc(sizeof(struct ip_set *) * ip_set_max, GFP_KERNEL); - if (!ip_set_list) { - pr_err("ip_set: Unable to create ip_set_list\n"); + if (!ip_set_list) return -ENOMEM; - } ret = nfnetlink_subsys_register(&ip_set_netlink_subsys); if (ret != 0) { diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 4f77bb1..093cc32 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -188,14 +188,13 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) } -static inline int +static inline void ip_vs_set_state(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, struct ip_vs_proto_data *pd) { - if (unlikely(!pd->pp->state_transition)) - return 0; - return pd->pp->state_transition(cp, direction, skb, pd); + if (likely(pd->pp->state_transition)) + pd->pp->state_transition(cp, direction, skb, pd); } static inline int @@ -530,7 +529,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, a cache_bypass connection entry */ ipvs = net_ipvs(net); if (ipvs->sysctl_cache_bypass && svc->fwmark && unicast) { - int ret, cs; + int ret; struct ip_vs_conn *cp; unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph.protocol == IPPROTO_UDP)? @@ -557,7 +556,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, ip_vs_in_stats(cp, skb); /* set state */ - cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); + ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); /* transmit the first SYN packet */ ret = cp->packet_xmit(skb, cp, pd->pp); @@ -1490,7 +1489,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; - int ret, restart, pkts; + int ret, pkts; struct netns_ipvs *ipvs; /* Already marked as IPVS request or reply? */ @@ -1591,7 +1590,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } ip_vs_in_stats(cp, skb); - restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); + ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); if (cp->packet_xmit) ret = cp->packet_xmit(skb, cp, pp); /* do not touch skb anymore */ @@ -1878,10 +1877,9 @@ static int __net_init __ip_vs_init(struct net *net) struct netns_ipvs *ipvs; ipvs = net_generic(net, ip_vs_net_id); - if (ipvs == NULL) { - pr_err("%s(): no memory.\n", __func__); + if (ipvs == NULL) return -ENOMEM; - } + /* Hold the beast until a service is registerd */ ipvs->enable = 0; ipvs->net = net; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 2b771dc..008bf97 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -856,15 +856,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, } dest = kzalloc(sizeof(struct ip_vs_dest), GFP_KERNEL); - if (dest == NULL) { - pr_err("%s(): no memory.\n", __func__); + if (dest == NULL) return -ENOMEM; - } + dest->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); - if (!dest->stats.cpustats) { - pr_err("%s() alloc_percpu failed\n", __func__); + if (!dest->stats.cpustats) goto err_alloc; - } dest->af = svc->af; dest->protocol = svc->protocol; @@ -1168,10 +1165,8 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, goto out_err; } svc->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); - if (!svc->stats.cpustats) { - pr_err("%s() alloc_percpu failed\n", __func__); + if (!svc->stats.cpustats) goto out_err; - } /* I'm the first user of the service */ atomic_set(&svc->usecnt, 0); @@ -2283,6 +2278,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) struct ip_vs_service *svc; struct ip_vs_dest_user *udest_compat; struct ip_vs_dest_user_kern udest; + struct netns_ipvs *ipvs = net_ipvs(net); if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -2303,6 +2299,24 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) /* increase the module use count */ ip_vs_use_count_inc(); + /* Handle daemons since they have another lock */ + if (cmd == IP_VS_SO_SET_STARTDAEMON || + cmd == IP_VS_SO_SET_STOPDAEMON) { + struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; + + if (mutex_lock_interruptible(&ipvs->sync_mutex)) { + ret = -ERESTARTSYS; + goto out_dec; + } + if (cmd == IP_VS_SO_SET_STARTDAEMON) + ret = start_sync_thread(net, dm->state, dm->mcast_ifn, + dm->syncid); + else + ret = stop_sync_thread(net, dm->state); + mutex_unlock(&ipvs->sync_mutex); + goto out_dec; + } + if (mutex_lock_interruptible(&__ip_vs_mutex)) { ret = -ERESTARTSYS; goto out_dec; @@ -2316,15 +2330,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) /* Set timeout values for (tcp tcpfin udp) */ ret = ip_vs_set_timeout(net, (struct ip_vs_timeout_user *)arg); goto out_unlock; - } else if (cmd == IP_VS_SO_SET_STARTDAEMON) { - struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; - ret = start_sync_thread(net, dm->state, dm->mcast_ifn, - dm->syncid); - goto out_unlock; - } else if (cmd == IP_VS_SO_SET_STOPDAEMON) { - struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; - ret = stop_sync_thread(net, dm->state); - goto out_unlock; } usvc_compat = (struct ip_vs_service_user *)arg; @@ -2584,6 +2589,33 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) if (copy_from_user(arg, user, copylen) != 0) return -EFAULT; + /* + * Handle daemons first since it has its own locking + */ + if (cmd == IP_VS_SO_GET_DAEMON) { + struct ip_vs_daemon_user d[2]; + + memset(&d, 0, sizeof(d)); + if (mutex_lock_interruptible(&ipvs->sync_mutex)) + return -ERESTARTSYS; + + if (ipvs->sync_state & IP_VS_STATE_MASTER) { + d[0].state = IP_VS_STATE_MASTER; + strlcpy(d[0].mcast_ifn, ipvs->master_mcast_ifn, + sizeof(d[0].mcast_ifn)); + d[0].syncid = ipvs->master_syncid; + } + if (ipvs->sync_state & IP_VS_STATE_BACKUP) { + d[1].state = IP_VS_STATE_BACKUP; + strlcpy(d[1].mcast_ifn, ipvs->backup_mcast_ifn, + sizeof(d[1].mcast_ifn)); + d[1].syncid = ipvs->backup_syncid; + } + if (copy_to_user(user, &d, sizeof(d)) != 0) + ret = -EFAULT; + mutex_unlock(&ipvs->sync_mutex); + return ret; + } if (mutex_lock_interruptible(&__ip_vs_mutex)) return -ERESTARTSYS; @@ -2681,28 +2713,6 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) } break; - case IP_VS_SO_GET_DAEMON: - { - struct ip_vs_daemon_user d[2]; - - memset(&d, 0, sizeof(d)); - if (ipvs->sync_state & IP_VS_STATE_MASTER) { - d[0].state = IP_VS_STATE_MASTER; - strlcpy(d[0].mcast_ifn, ipvs->master_mcast_ifn, - sizeof(d[0].mcast_ifn)); - d[0].syncid = ipvs->master_syncid; - } - if (ipvs->sync_state & IP_VS_STATE_BACKUP) { - d[1].state = IP_VS_STATE_BACKUP; - strlcpy(d[1].mcast_ifn, ipvs->backup_mcast_ifn, - sizeof(d[1].mcast_ifn)); - d[1].syncid = ipvs->backup_syncid; - } - if (copy_to_user(user, &d, sizeof(d)) != 0) - ret = -EFAULT; - } - break; - default: ret = -EINVAL; } @@ -3205,7 +3215,7 @@ static int ip_vs_genl_dump_daemons(struct sk_buff *skb, struct net *net = skb_sknet(skb); struct netns_ipvs *ipvs = net_ipvs(net); - mutex_lock(&__ip_vs_mutex); + mutex_lock(&ipvs->sync_mutex); if ((ipvs->sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) { if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_MASTER, ipvs->master_mcast_ifn, @@ -3225,7 +3235,7 @@ static int ip_vs_genl_dump_daemons(struct sk_buff *skb, } nla_put_failure: - mutex_unlock(&__ip_vs_mutex); + mutex_unlock(&ipvs->sync_mutex); return skb->len; } @@ -3271,13 +3281,9 @@ static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs) return ip_vs_set_timeout(net, &t); } -static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) +static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info) { - struct ip_vs_service *svc = NULL; - struct ip_vs_service_user_kern usvc; - struct ip_vs_dest_user_kern udest; int ret = 0, cmd; - int need_full_svc = 0, need_full_dest = 0; struct net *net; struct netns_ipvs *ipvs; @@ -3285,19 +3291,10 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; - mutex_lock(&__ip_vs_mutex); - - if (cmd == IPVS_CMD_FLUSH) { - ret = ip_vs_flush(net); - goto out; - } else if (cmd == IPVS_CMD_SET_CONFIG) { - ret = ip_vs_genl_set_config(net, info->attrs); - goto out; - } else if (cmd == IPVS_CMD_NEW_DAEMON || - cmd == IPVS_CMD_DEL_DAEMON) { - + if (cmd == IPVS_CMD_NEW_DAEMON || cmd == IPVS_CMD_DEL_DAEMON) { struct nlattr *daemon_attrs[IPVS_DAEMON_ATTR_MAX + 1]; + mutex_lock(&ipvs->sync_mutex); if (!info->attrs[IPVS_CMD_ATTR_DAEMON] || nla_parse_nested(daemon_attrs, IPVS_DAEMON_ATTR_MAX, info->attrs[IPVS_CMD_ATTR_DAEMON], @@ -3310,6 +3307,31 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) ret = ip_vs_genl_new_daemon(net, daemon_attrs); else ret = ip_vs_genl_del_daemon(net, daemon_attrs); +out: + mutex_unlock(&ipvs->sync_mutex); + } + return ret; +} + +static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) +{ + struct ip_vs_service *svc = NULL; + struct ip_vs_service_user_kern usvc; + struct ip_vs_dest_user_kern udest; + int ret = 0, cmd; + int need_full_svc = 0, need_full_dest = 0; + struct net *net; + + net = skb_sknet(skb); + cmd = info->genlhdr->cmd; + + mutex_lock(&__ip_vs_mutex); + + if (cmd == IPVS_CMD_FLUSH) { + ret = ip_vs_flush(net); + goto out; + } else if (cmd == IPVS_CMD_SET_CONFIG) { + ret = ip_vs_genl_set_config(net, info->attrs); goto out; } else if (cmd == IPVS_CMD_ZERO && !info->attrs[IPVS_CMD_ATTR_SERVICE]) { @@ -3392,10 +3414,8 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) void *reply; int ret, cmd, reply_cmd; struct net *net; - struct netns_ipvs *ipvs; net = skb_sknet(skb); - ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; if (cmd == IPVS_CMD_GET_SERVICE) @@ -3536,13 +3556,13 @@ static struct genl_ops ip_vs_genl_ops[] __read_mostly = { .cmd = IPVS_CMD_NEW_DAEMON, .flags = GENL_ADMIN_PERM, .policy = ip_vs_cmd_policy, - .doit = ip_vs_genl_set_cmd, + .doit = ip_vs_genl_set_daemon, }, { .cmd = IPVS_CMD_DEL_DAEMON, .flags = GENL_ADMIN_PERM, .policy = ip_vs_cmd_policy, - .doit = ip_vs_genl_set_cmd, + .doit = ip_vs_genl_set_daemon, }, { .cmd = IPVS_CMD_GET_DAEMON, @@ -3679,7 +3699,7 @@ int __net_init ip_vs_control_net_init(struct net *net) int idx; struct netns_ipvs *ipvs = net_ipvs(net); - ipvs->rs_lock = __RW_LOCK_UNLOCKED(ipvs->rs_lock); + rwlock_init(&ipvs->rs_lock); /* Initialize rs_table */ for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++) @@ -3691,10 +3711,9 @@ int __net_init ip_vs_control_net_init(struct net *net) /* procfs stats */ ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); - if (!ipvs->tot_stats.cpustats) { - pr_err("%s(): alloc_percpu.\n", __func__); + if (!ipvs->tot_stats.cpustats) return -ENOMEM; - } + spin_lock_init(&ipvs->tot_stats.lock); proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops); diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c index 95fd0d1..1c269e5 100644 --- a/net/netfilter/ipvs/ip_vs_dh.c +++ b/net/netfilter/ipvs/ip_vs_dh.c @@ -150,10 +150,9 @@ static int ip_vs_dh_init_svc(struct ip_vs_service *svc) /* allocate the DH table for this service */ tbl = kmalloc(sizeof(struct ip_vs_dh_bucket)*IP_VS_DH_TAB_SIZE, GFP_ATOMIC); - if (tbl == NULL) { - pr_err("%s(): no memory\n", __func__); + if (tbl == NULL) return -ENOMEM; - } + svc->sched_data = tbl; IP_VS_DBG(6, "DH hash table (memory=%Zdbytes) allocated for " "current service\n", diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 4490a32..538d74e 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -52,8 +52,9 @@ * List of ports (up to IP_VS_APP_MAX_PORTS) to be handled by helper * First port is set to the default port. */ +static unsigned int ports_count = 1; static unsigned short ports[IP_VS_APP_MAX_PORTS] = {21, 0}; -module_param_array(ports, ushort, NULL, 0); +module_param_array(ports, ushort, &ports_count, 0444); MODULE_PARM_DESC(ports, "Ports to monitor for FTP control commands"); @@ -449,7 +450,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net) if (ret) goto err_exit; - for (i=0; i<IP_VS_APP_MAX_PORTS; i++) { + for (i = 0; i < ports_count; i++) { if (!ports[i]) continue; ret = register_ip_vs_app_inc(net, app, app->protocol, ports[i]); diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 87e40ea..0f16283 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -202,10 +202,8 @@ ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, const union nf_inet_addr *daddr, en = ip_vs_lblc_get(dest->af, tbl, daddr); if (!en) { en = kmalloc(sizeof(*en), GFP_ATOMIC); - if (!en) { - pr_err("%s(): no memory\n", __func__); + if (!en) return NULL; - } en->af = dest->af; ip_vs_addr_copy(dest->af, &en->addr, daddr); @@ -345,10 +343,9 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc) * Allocate the ip_vs_lblc_table for this service */ tbl = kmalloc(sizeof(*tbl), GFP_ATOMIC); - if (tbl == NULL) { - pr_err("%s(): no memory\n", __func__); + if (tbl == NULL) return -ENOMEM; - } + svc->sched_data = tbl; IP_VS_DBG(6, "LBLC hash table (memory=%Zdbytes) allocated for " "current service\n", sizeof(*tbl)); diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 90f618a..eec797f 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -112,10 +112,8 @@ ip_vs_dest_set_insert(struct ip_vs_dest_set *set, struct ip_vs_dest *dest) } e = kmalloc(sizeof(*e), GFP_ATOMIC); - if (e == NULL) { - pr_err("%s(): no memory\n", __func__); + if (e == NULL) return NULL; - } atomic_inc(&dest->refcnt); e->dest = dest; @@ -373,10 +371,8 @@ ip_vs_lblcr_new(struct ip_vs_lblcr_table *tbl, const union nf_inet_addr *daddr, en = ip_vs_lblcr_get(dest->af, tbl, daddr); if (!en) { en = kmalloc(sizeof(*en), GFP_ATOMIC); - if (!en) { - pr_err("%s(): no memory\n", __func__); + if (!en) return NULL; - } en->af = dest->af; ip_vs_addr_copy(dest->af, &en->addr, daddr); @@ -516,10 +512,9 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc) * Allocate the ip_vs_lblcr_table for this service */ tbl = kmalloc(sizeof(*tbl), GFP_ATOMIC); - if (tbl == NULL) { - pr_err("%s(): no memory\n", __func__); + if (tbl == NULL) return -ENOMEM; - } + svc->sched_data = tbl; IP_VS_DBG(6, "LBLCR hash table (memory=%Zdbytes) allocated for " "current service\n", sizeof(*tbl)); diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index f454c80..022e77e 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -127,7 +127,7 @@ ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin) nf_conntrack_alter_reply(ct, &new_tuple); } -int ip_vs_confirm_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp) +int ip_vs_confirm_conntrack(struct sk_buff *skb) { return nf_conntrack_confirm(skb); } diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index 52d073c..8531293 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -74,10 +74,9 @@ register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp) struct ip_vs_proto_data *pd = kzalloc(sizeof(struct ip_vs_proto_data), GFP_ATOMIC); - if (!pd) { - pr_err("%s(): no memory.\n", __func__); + if (!pd) return -ENOMEM; - } + pd->pp = pp; /* For speed issues */ pd->next = ipvs->proto_data_table[hash]; ipvs->proto_data_table[hash] = pd; diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index d12ed53..1fbf7a2 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -906,7 +906,7 @@ static const char *sctp_state_name(int state) return "?"; } -static inline int +static inline void set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, int direction, const struct sk_buff *skb) { @@ -924,7 +924,7 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, sch = skb_header_pointer(skb, ihl + sizeof(sctp_sctphdr_t), sizeof(_sctpch), &_sctpch); if (sch == NULL) - return 0; + return; chunk_type = sch->type; /* @@ -993,21 +993,15 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, cp->timeout = pd->timeout_table[cp->state = next_state]; else /* What to do ? */ cp->timeout = sctp_timeouts[cp->state = next_state]; - - return 1; } -static int +static void sctp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, struct ip_vs_proto_data *pd) { - int ret = 0; - spin_lock(&cp->lock); - ret = set_sctp_state(pd, cp, direction, skb); + set_sctp_state(pd, cp, direction, skb); spin_unlock(&cp->lock); - - return ret; } static inline __u16 sctp_app_hashkey(__be16 port) diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index c0cc341..ef8641f 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -546,7 +546,7 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, /* * Handle state transitions */ -static int +static void tcp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, struct ip_vs_proto_data *pd) @@ -561,13 +561,11 @@ tcp_state_transition(struct ip_vs_conn *cp, int direction, th = skb_header_pointer(skb, ihl, sizeof(_tcph), &_tcph); if (th == NULL) - return 0; + return; spin_lock(&cp->lock); set_tcp_state(pd, cp, direction, th); spin_unlock(&cp->lock); - - return 1; } static inline __u16 tcp_app_hashkey(__be16 port) diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index f1282cb..f4b7262 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -454,18 +454,17 @@ static const char * udp_state_name(int state) return udp_state_name_table[state] ? udp_state_name_table[state] : "?"; } -static int +static void udp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, struct ip_vs_proto_data *pd) { if (unlikely(!pd)) { pr_err("UDP no ns data\n"); - return 0; + return; } cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL]; - return 1; } static void __udp_init(struct net *net, struct ip_vs_proto_data *pd) diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c index b5e2556..33815f4 100644 --- a/net/netfilter/ipvs/ip_vs_sh.c +++ b/net/netfilter/ipvs/ip_vs_sh.c @@ -147,10 +147,9 @@ static int ip_vs_sh_init_svc(struct ip_vs_service *svc) /* allocate the SH table for this service */ tbl = kmalloc(sizeof(struct ip_vs_sh_bucket)*IP_VS_SH_TAB_SIZE, GFP_ATOMIC); - if (tbl == NULL) { - pr_err("%s(): no memory\n", __func__); + if (tbl == NULL) return -ENOMEM; - } + svc->sched_data = tbl; IP_VS_DBG(6, "SH hash table (memory=%Zdbytes) allocated for " "current service\n", diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 7ee7215..3cdd479 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -61,6 +61,7 @@ #define SYNC_PROTO_VER 1 /* Protocol version in header */ +static struct lock_class_key __ipvs_sync_key; /* * IPVS sync connection entry * Version 0, i.e. original version. @@ -1545,6 +1546,7 @@ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %Zd bytes\n", sizeof(struct ip_vs_sync_conn_v0)); + if (state == IP_VS_STATE_MASTER) { if (ipvs->master_thread) return -EEXIST; @@ -1667,6 +1669,7 @@ int __net_init ip_vs_sync_net_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); + __mutex_init(&ipvs->sync_mutex, "ipvs->sync_mutex", &__ipvs_sync_key); INIT_LIST_HEAD(&ipvs->sync_queue); spin_lock_init(&ipvs->sync_lock); spin_lock_init(&ipvs->sync_buff_lock); @@ -1680,7 +1683,9 @@ int __net_init ip_vs_sync_net_init(struct net *net) void ip_vs_sync_net_cleanup(struct net *net) { int retc; + struct netns_ipvs *ipvs = net_ipvs(net); + mutex_lock(&ipvs->sync_mutex); retc = stop_sync_thread(net, IP_VS_STATE_MASTER); if (retc && retc != -ESRCH) pr_err("Failed to stop Master Daemon\n"); @@ -1688,4 +1693,5 @@ void ip_vs_sync_net_cleanup(struct net *net) retc = stop_sync_thread(net, IP_VS_STATE_BACKUP); if (retc && retc != -ESRCH) pr_err("Failed to stop Backup Daemon\n"); + mutex_unlock(&ipvs->sync_mutex); } diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c index 1ef41f5..fd0d4e0 100644 --- a/net/netfilter/ipvs/ip_vs_wrr.c +++ b/net/netfilter/ipvs/ip_vs_wrr.c @@ -85,10 +85,9 @@ static int ip_vs_wrr_init_svc(struct ip_vs_service *svc) * Allocate the mark variable for WRR scheduling */ mark = kmalloc(sizeof(struct ip_vs_wrr_mark), GFP_ATOMIC); - if (mark == NULL) { - pr_err("%s(): no memory\n", __func__); + if (mark == NULL) return -ENOMEM; - } + mark->cl = &svc->destinations; mark->cw = 0; mark->mw = ip_vs_wrr_max_weight(svc); diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index ee319a4..aa2d720 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -339,7 +339,7 @@ ip_vs_dst_reset(struct ip_vs_dest *dest) \ (skb)->ipvs_property = 1; \ if (unlikely((cp)->flags & IP_VS_CONN_F_NFCT)) \ - __ret = ip_vs_confirm_conntrack(skb, cp); \ + __ret = ip_vs_confirm_conntrack(skb); \ if (__ret == NF_ACCEPT) { \ nf_reset(skb); \ skb_forward_csum(skb); \ diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index f7af8b8..7202b06 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -661,7 +661,6 @@ __nf_conntrack_alloc(struct net *net, u16 zone, */ ct = kmem_cache_alloc(net->ct.nf_conntrack_cachep, gfp); if (ct == NULL) { - pr_debug("nf_conntrack_alloc: Can't alloc conntrack.\n"); atomic_dec(&net->ct.count); return ERR_PTR(-ENOMEM); } @@ -749,10 +748,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC, hash); - if (IS_ERR(ct)) { - pr_debug("Can't allocate conntrack.\n"); + if (IS_ERR(ct)) return (struct nf_conntrack_tuple_hash *)ct; - } if (!l4proto->new(ct, skb, dataoff)) { nf_conntrack_free(ct); @@ -779,7 +776,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, if (exp->helper) { help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help) - rcu_assign_pointer(help->helper, exp->helper); + RCU_INIT_POINTER(help->helper, exp->helper); } #ifdef CONFIG_NF_CONNTRACK_MARK @@ -1317,7 +1314,7 @@ static void nf_conntrack_cleanup_net(struct net *net) void nf_conntrack_cleanup(struct net *net) { if (net_eq(net, &init_net)) - rcu_assign_pointer(ip_ct_attach, NULL); + RCU_INIT_POINTER(ip_ct_attach, NULL); /* This makes sure all current packets have passed through netfilter framework. Roll on, two-stage module @@ -1327,7 +1324,7 @@ void nf_conntrack_cleanup(struct net *net) nf_conntrack_cleanup_net(net); if (net_eq(net, &init_net)) { - rcu_assign_pointer(nf_ct_destroy, NULL); + RCU_INIT_POINTER(nf_ct_destroy, NULL); nf_conntrack_cleanup_init_net(); } } @@ -1576,11 +1573,11 @@ int nf_conntrack_init(struct net *net) if (net_eq(net, &init_net)) { /* For use by REJECT target */ - rcu_assign_pointer(ip_ct_attach, nf_conntrack_attach); - rcu_assign_pointer(nf_ct_destroy, destroy_conntrack); + RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach); + RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack); /* Howto get NAT offsets */ - rcu_assign_pointer(nf_ct_nat_offset, NULL); + RCU_INIT_POINTER(nf_ct_nat_offset, NULL); } return 0; diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 63a1b91..3add994 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -94,7 +94,7 @@ int nf_conntrack_register_notifier(struct nf_ct_event_notifier *new) ret = -EBUSY; goto out_unlock; } - rcu_assign_pointer(nf_conntrack_event_cb, new); + RCU_INIT_POINTER(nf_conntrack_event_cb, new); mutex_unlock(&nf_ct_ecache_mutex); return ret; @@ -112,7 +112,7 @@ void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *new) notify = rcu_dereference_protected(nf_conntrack_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); BUG_ON(notify != new); - rcu_assign_pointer(nf_conntrack_event_cb, NULL); + RCU_INIT_POINTER(nf_conntrack_event_cb, NULL); mutex_unlock(&nf_ct_ecache_mutex); } EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier); @@ -129,7 +129,7 @@ int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *new) ret = -EBUSY; goto out_unlock; } - rcu_assign_pointer(nf_expect_event_cb, new); + RCU_INIT_POINTER(nf_expect_event_cb, new); mutex_unlock(&nf_ct_ecache_mutex); return ret; @@ -147,7 +147,7 @@ void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *new) notify = rcu_dereference_protected(nf_expect_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); BUG_ON(notify != new); - rcu_assign_pointer(nf_expect_event_cb, NULL); + RCU_INIT_POINTER(nf_expect_event_cb, NULL); mutex_unlock(&nf_ct_ecache_mutex); } EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier); diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 05ecdc2..4605c94 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -169,7 +169,7 @@ int nf_ct_extend_register(struct nf_ct_ext_type *type) before updating alloc_size */ type->alloc_size = ALIGN(sizeof(struct nf_ct_ext), type->align) + type->len; - rcu_assign_pointer(nf_ct_ext_types[type->id], type); + RCU_INIT_POINTER(nf_ct_ext_types[type->id], type); update_alloc_size(type); out: mutex_unlock(&nf_ct_ext_type_mutex); @@ -181,7 +181,7 @@ EXPORT_SYMBOL_GPL(nf_ct_extend_register); void nf_ct_extend_unregister(struct nf_ct_ext_type *type) { mutex_lock(&nf_ct_ext_type_mutex); - rcu_assign_pointer(nf_ct_ext_types[type->id], NULL); + RCU_INIT_POINTER(nf_ct_ext_types[type->id], NULL); update_alloc_size(type); mutex_unlock(&nf_ct_ext_type_mutex); rcu_barrier(); /* Wait for completion of call_rcu()'s */ diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 1bdfea3..93c4bdb 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -131,7 +131,7 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, helper = __nf_ct_helper_find(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); if (helper == NULL) { if (help) - rcu_assign_pointer(help->helper, NULL); + RCU_INIT_POINTER(help->helper, NULL); goto out; } @@ -145,7 +145,7 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, memset(&help->help, 0, sizeof(help->help)); } - rcu_assign_pointer(help->helper, helper); + RCU_INIT_POINTER(help->helper, helper); out: return ret; } @@ -162,7 +162,7 @@ static inline int unhelp(struct nf_conntrack_tuple_hash *i, lockdep_is_held(&nf_conntrack_lock) ) == me) { nf_conntrack_event(IPCT_HELPER, ct); - rcu_assign_pointer(help->helper, NULL); + RCU_INIT_POINTER(help->helper, NULL); } return 0; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 7dec88a..e58aa9b 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1125,7 +1125,7 @@ ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) if (help && help->helper) { /* we had a helper before ... */ nf_ct_remove_expectations(ct); - rcu_assign_pointer(help->helper, NULL); + RCU_INIT_POINTER(help->helper, NULL); } return 0; @@ -1163,7 +1163,7 @@ ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) return -EOPNOTSUPP; } - rcu_assign_pointer(help->helper, helper); + RCU_INIT_POINTER(help->helper, helper); return 0; } @@ -1386,7 +1386,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, } /* not in hash table yet so not strictly necessary */ - rcu_assign_pointer(help->helper, helper); + RCU_INIT_POINTER(help->helper, helper); } } else { /* try an implicit helper assignation */ diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index cf616e5..d69facd 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -241,8 +241,8 @@ static int gre_packet(struct nf_conn *ct, nf_ct_refresh_acct(ct, ctinfo, skb, ct->proto.gre.stream_timeout); /* Also, more likely to be important, and not a probe. */ - set_bit(IPS_ASSURED_BIT, &ct->status); - nf_conntrack_event_cache(IPCT_ASSURED, ct); + if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) + nf_conntrack_event_cache(IPCT_ASSURED, ct); } else nf_ct_refresh_acct(ct, ctinfo, skb, ct->proto.gre.timeout); diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 20714ed..ce0c406 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -55,7 +55,7 @@ int nf_log_register(u_int8_t pf, struct nf_logger *logger) llog = rcu_dereference_protected(nf_loggers[pf], lockdep_is_held(&nf_log_mutex)); if (llog == NULL) - rcu_assign_pointer(nf_loggers[pf], logger); + RCU_INIT_POINTER(nf_loggers[pf], logger); } mutex_unlock(&nf_log_mutex); @@ -74,7 +74,7 @@ void nf_log_unregister(struct nf_logger *logger) c_logger = rcu_dereference_protected(nf_loggers[i], lockdep_is_held(&nf_log_mutex)); if (c_logger == logger) - rcu_assign_pointer(nf_loggers[i], NULL); + RCU_INIT_POINTER(nf_loggers[i], NULL); list_del(&logger->list[i]); } mutex_unlock(&nf_log_mutex); @@ -92,7 +92,7 @@ int nf_log_bind_pf(u_int8_t pf, const struct nf_logger *logger) mutex_unlock(&nf_log_mutex); return -ENOENT; } - rcu_assign_pointer(nf_loggers[pf], logger); + RCU_INIT_POINTER(nf_loggers[pf], logger); mutex_unlock(&nf_log_mutex); return 0; } @@ -103,7 +103,7 @@ void nf_log_unbind_pf(u_int8_t pf) if (pf >= ARRAY_SIZE(nf_loggers)) return; mutex_lock(&nf_log_mutex); - rcu_assign_pointer(nf_loggers[pf], NULL); + RCU_INIT_POINTER(nf_loggers[pf], NULL); mutex_unlock(&nf_log_mutex); } EXPORT_SYMBOL(nf_log_unbind_pf); @@ -250,7 +250,7 @@ static int nf_log_proc_dostring(ctl_table *table, int write, mutex_unlock(&nf_log_mutex); return -ENOENT; } - rcu_assign_pointer(nf_loggers[tindex], logger); + RCU_INIT_POINTER(nf_loggers[tindex], logger); mutex_unlock(&nf_log_mutex); } else { mutex_lock(&nf_log_mutex); diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 84d0fd4..99ffd28 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -40,7 +40,7 @@ int nf_register_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh) else if (old) ret = -EBUSY; else { - rcu_assign_pointer(queue_handler[pf], qh); + RCU_INIT_POINTER(queue_handler[pf], qh); ret = 0; } mutex_unlock(&queue_handler_mutex); @@ -65,7 +65,7 @@ int nf_unregister_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh) return -EINVAL; } - rcu_assign_pointer(queue_handler[pf], NULL); + RCU_INIT_POINTER(queue_handler[pf], NULL); mutex_unlock(&queue_handler_mutex); synchronize_rcu(); @@ -84,7 +84,7 @@ void nf_unregister_queue_handlers(const struct nf_queue_handler *qh) queue_handler[pf], lockdep_is_held(&queue_handler_mutex) ) == qh) - rcu_assign_pointer(queue_handler[pf], NULL); + RCU_INIT_POINTER(queue_handler[pf], NULL); } mutex_unlock(&queue_handler_mutex); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 1905976..c879c1a 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -59,7 +59,7 @@ int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n) nfnl_unlock(); return -EBUSY; } - rcu_assign_pointer(subsys_table[n->subsys_id], n); + RCU_INIT_POINTER(subsys_table[n->subsys_id], n); nfnl_unlock(); return 0; @@ -210,7 +210,7 @@ static int __net_init nfnetlink_net_init(struct net *net) if (!nfnl) return -ENOMEM; net->nfnl_stash = nfnl; - rcu_assign_pointer(net->nfnl, nfnl); + RCU_INIT_POINTER(net->nfnl, nfnl); return 0; } @@ -219,7 +219,7 @@ static void __net_exit nfnetlink_net_exit_batch(struct list_head *net_exit_list) struct net *net; list_for_each_entry(net, net_exit_list, exit_list) - rcu_assign_pointer(net->nfnl, NULL); + RCU_INIT_POINTER(net->nfnl, NULL); synchronize_net(); list_for_each_entry(net, net_exit_list, exit_list) netlink_kernel_release(net->nfnl_stash); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 2d8158a..66b2c54 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -307,17 +307,14 @@ nfulnl_alloc_skb(unsigned int inst_size, unsigned int pkt_size) n = max(inst_size, pkt_size); skb = alloc_skb(n, GFP_ATOMIC); if (!skb) { - pr_notice("nfnetlink_log: can't alloc whole buffer (%u bytes)\n", - inst_size); - if (n > pkt_size) { /* try to allocate only as much as we need for current * packet */ skb = alloc_skb(pkt_size, GFP_ATOMIC); if (!skb) - pr_err("nfnetlink_log: can't even alloc %u " - "bytes\n", pkt_size); + pr_err("nfnetlink_log: can't even alloc %u bytes\n", + pkt_size); } } diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index b0869fe..71441b9 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -776,12 +776,11 @@ static int xt_jumpstack_alloc(struct xt_table_info *i) size = sizeof(void **) * nr_cpu_ids; if (size > PAGE_SIZE) - i->jumpstack = vmalloc(size); + i->jumpstack = vzalloc(size); else - i->jumpstack = kmalloc(size, GFP_KERNEL); + i->jumpstack = kzalloc(size, GFP_KERNEL); if (i->jumpstack == NULL) return -ENOMEM; - memset(i->jumpstack, 0, size); i->stacksize *= xt_jumpstack_multiplier; size = sizeof(void *) * i->stacksize; diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 3bdd443..f407ebc1 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -122,14 +122,12 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) info->timer = kmalloc(sizeof(*info->timer), GFP_KERNEL); if (!info->timer) { - pr_debug("couldn't alloc timer\n"); ret = -ENOMEM; goto out; } info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL); if (!info->timer->attr.attr.name) { - pr_debug("couldn't alloc attribute name\n"); ret = -ENOMEM; goto out_free_timer; } diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 9228ee0d..dfd52ba 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -176,10 +176,7 @@ dsthash_alloc_init(struct xt_hashlimit_htable *ht, ent = NULL; } else ent = kmem_cache_alloc(hashlimit_cachep, GFP_ATOMIC); - if (!ent) { - if (net_ratelimit()) - pr_err("cannot allocate dsthash_ent\n"); - } else { + if (ent) { memcpy(&ent->dst, dst, sizeof(ent->dst)); spin_lock_init(&ent->lock); diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index 7d8083c..3f905e5 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -282,7 +282,7 @@ int __init netlbl_domhsh_init(u32 size) INIT_LIST_HEAD(&hsh_tbl->tbl[iter]); spin_lock(&netlbl_domhsh_lock); - rcu_assign_pointer(netlbl_domhsh, hsh_tbl); + RCU_INIT_POINTER(netlbl_domhsh, hsh_tbl); spin_unlock(&netlbl_domhsh_lock); return 0; @@ -330,7 +330,7 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry, &rcu_dereference(netlbl_domhsh)->tbl[bkt]); } else { INIT_LIST_HEAD(&entry->list); - rcu_assign_pointer(netlbl_domhsh_def, entry); + RCU_INIT_POINTER(netlbl_domhsh_def, entry); } if (entry->type == NETLBL_NLTYPE_ADDRSELECT) { @@ -451,7 +451,7 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, if (entry != rcu_dereference(netlbl_domhsh_def)) list_del_rcu(&entry->list); else - rcu_assign_pointer(netlbl_domhsh_def, NULL); + RCU_INIT_POINTER(netlbl_domhsh_def, NULL); } else ret_val = -ENOENT; spin_unlock(&netlbl_domhsh_lock); diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index e6e8236..e251c2c 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -354,7 +354,7 @@ static struct netlbl_unlhsh_iface *netlbl_unlhsh_add_iface(int ifindex) INIT_LIST_HEAD(&iface->list); if (netlbl_unlhsh_rcu_deref(netlbl_unlhsh_def) != NULL) goto add_iface_failure; - rcu_assign_pointer(netlbl_unlhsh_def, iface); + RCU_INIT_POINTER(netlbl_unlhsh_def, iface); } spin_unlock(&netlbl_unlhsh_lock); @@ -621,7 +621,7 @@ static void netlbl_unlhsh_condremove_iface(struct netlbl_unlhsh_iface *iface) if (iface->ifindex > 0) list_del_rcu(&iface->list); else - rcu_assign_pointer(netlbl_unlhsh_def, NULL); + RCU_INIT_POINTER(netlbl_unlhsh_def, NULL); spin_unlock(&netlbl_unlhsh_lock); call_rcu(&iface->rcu, netlbl_unlhsh_free_iface); @@ -1449,7 +1449,7 @@ int __init netlbl_unlabel_init(u32 size) rcu_read_lock(); spin_lock(&netlbl_unlhsh_lock); - rcu_assign_pointer(netlbl_unlhsh, hsh_tbl); + RCU_INIT_POINTER(netlbl_unlhsh, hsh_tbl); spin_unlock(&netlbl_unlhsh_lock); rcu_read_unlock(); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 0a4db02..1201b6d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1324,10 +1324,9 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, if (msg->msg_flags&MSG_OOB) return -EOPNOTSUPP; - if (NULL == siocb->scm) { + if (NULL == siocb->scm) siocb->scm = &scm; - memset(&scm, 0, sizeof(scm)); - } + err = scm_send(sock, msg, siocb->scm); if (err < 0) return err; @@ -1578,7 +1577,7 @@ int __netlink_change_ngroups(struct sock *sk, unsigned int groups) new = kzalloc(sizeof(*new) + NLGRPSZ(groups), GFP_ATOMIC); if (!new) return -ENOMEM; - old = rcu_dereference_raw(tbl->listeners); + old = rcu_dereference_protected(tbl->listeners, 1); memcpy(new->masks, old->masks, NLGRPSZ(tbl->groups)); rcu_assign_pointer(tbl->listeners, new); diff --git a/net/nfc/Kconfig b/net/nfc/Kconfig index 33e095b1..58cddad 100644 --- a/net/nfc/Kconfig +++ b/net/nfc/Kconfig @@ -13,4 +13,6 @@ menuconfig NFC To compile this support as a module, choose M here: the module will be called nfc. +source "net/nfc/nci/Kconfig" + source "drivers/nfc/Kconfig" diff --git a/net/nfc/Makefile b/net/nfc/Makefile index 16250c3..fbb550f 100644 --- a/net/nfc/Makefile +++ b/net/nfc/Makefile @@ -3,5 +3,6 @@ # obj-$(CONFIG_NFC) += nfc.o +obj-$(CONFIG_NFC_NCI) += nci/ nfc-objs := core.o netlink.o af_nfc.o rawsock.o diff --git a/net/nfc/core.c b/net/nfc/core.c index b6fd4e1..47e02c1 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -53,6 +53,80 @@ int nfc_printk(const char *level, const char *format, ...) EXPORT_SYMBOL(nfc_printk); /** + * nfc_dev_up - turn on the NFC device + * + * @dev: The nfc device to be turned on + * + * The device remains up until the nfc_dev_down function is called. + */ +int nfc_dev_up(struct nfc_dev *dev) +{ + int rc = 0; + + nfc_dbg("dev_name=%s", dev_name(&dev->dev)); + + device_lock(&dev->dev); + + if (!device_is_registered(&dev->dev)) { + rc = -ENODEV; + goto error; + } + + if (dev->dev_up) { + rc = -EALREADY; + goto error; + } + + if (dev->ops->dev_up) + rc = dev->ops->dev_up(dev); + + if (!rc) + dev->dev_up = true; + +error: + device_unlock(&dev->dev); + return rc; +} + +/** + * nfc_dev_down - turn off the NFC device + * + * @dev: The nfc device to be turned off + */ +int nfc_dev_down(struct nfc_dev *dev) +{ + int rc = 0; + + nfc_dbg("dev_name=%s", dev_name(&dev->dev)); + + device_lock(&dev->dev); + + if (!device_is_registered(&dev->dev)) { + rc = -ENODEV; + goto error; + } + + if (!dev->dev_up) { + rc = -EALREADY; + goto error; + } + + if (dev->polling || dev->remote_activated) { + rc = -EBUSY; + goto error; + } + + if (dev->ops->dev_down) + dev->ops->dev_down(dev); + + dev->dev_up = false; + +error: + device_unlock(&dev->dev); + return rc; +} + +/** * nfc_start_poll - start polling for nfc targets * * @dev: The nfc device that must start polling @@ -144,6 +218,8 @@ int nfc_activate_target(struct nfc_dev *dev, u32 target_idx, u32 protocol) } rc = dev->ops->activate_target(dev, target_idx, protocol); + if (!rc) + dev->remote_activated = true; error: device_unlock(&dev->dev); @@ -170,6 +246,7 @@ int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx) } dev->ops->deactivate_target(dev, target_idx); + dev->remote_activated = false; error: device_unlock(&dev->dev); @@ -322,7 +399,9 @@ struct nfc_dev *nfc_get_device(unsigned idx) * @supported_protocols: NFC protocols supported by the device */ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, - u32 supported_protocols) + u32 supported_protocols, + int tx_headroom, + int tx_tailroom) { static atomic_t dev_no = ATOMIC_INIT(0); struct nfc_dev *dev; @@ -345,6 +424,8 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, dev->ops = ops; dev->supported_protocols = supported_protocols; + dev->tx_headroom = tx_headroom; + dev->tx_tailroom = tx_tailroom; spin_lock_init(&dev->targets_lock); nfc_genl_data_init(&dev->genl_data); diff --git a/net/nfc/nci/Kconfig b/net/nfc/nci/Kconfig new file mode 100644 index 0000000..decdc49 --- /dev/null +++ b/net/nfc/nci/Kconfig @@ -0,0 +1,10 @@ +config NFC_NCI + depends on NFC && EXPERIMENTAL + tristate "NCI protocol support (EXPERIMENTAL)" + default n + help + NCI (NFC Controller Interface) is a communication protocol between + an NFC Controller (NFCC) and a Device Host (DH). + + Say Y here to compile NCI support into the kernel or say M to + compile it as module (nci). diff --git a/net/nfc/nci/Makefile b/net/nfc/nci/Makefile new file mode 100644 index 0000000..cdb3a2e --- /dev/null +++ b/net/nfc/nci/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the Linux NFC NCI layer. +# + +obj-$(CONFIG_NFC_NCI) += nci.o + +nci-objs := core.o data.o lib.o ntf.o rsp.o
\ No newline at end of file diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c new file mode 100644 index 0000000..4047e29 --- /dev/null +++ b/net/nfc/nci/core.c @@ -0,0 +1,797 @@ +/* + * The NFC Controller Interface is the communication protocol between an + * NFC Controller (NFCC) and a Device Host (DH). + * + * Copyright (C) 2011 Texas Instruments, Inc. + * + * Written by Ilan Elias <ilane@ti.com> + * + * Acknowledgements: + * This file is based on hci_core.c, which was written + * by Maxim Krasnyansky. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include <linux/types.h> +#include <linux/workqueue.h> +#include <linux/completion.h> +#include <linux/sched.h> +#include <linux/bitops.h> +#include <linux/skbuff.h> + +#include "../nfc.h" +#include <net/nfc/nci.h> +#include <net/nfc/nci_core.h> +#include <linux/nfc.h> + +static void nci_cmd_work(struct work_struct *work); +static void nci_rx_work(struct work_struct *work); +static void nci_tx_work(struct work_struct *work); + +/* ---- NCI requests ---- */ + +void nci_req_complete(struct nci_dev *ndev, int result) +{ + if (ndev->req_status == NCI_REQ_PEND) { + ndev->req_result = result; + ndev->req_status = NCI_REQ_DONE; + complete(&ndev->req_completion); + } +} + +static void nci_req_cancel(struct nci_dev *ndev, int err) +{ + if (ndev->req_status == NCI_REQ_PEND) { + ndev->req_result = err; + ndev->req_status = NCI_REQ_CANCELED; + complete(&ndev->req_completion); + } +} + +/* Execute request and wait for completion. */ +static int __nci_request(struct nci_dev *ndev, + void (*req)(struct nci_dev *ndev, unsigned long opt), + unsigned long opt, + __u32 timeout) +{ + int rc = 0; + unsigned long completion_rc; + + ndev->req_status = NCI_REQ_PEND; + + init_completion(&ndev->req_completion); + req(ndev, opt); + completion_rc = wait_for_completion_interruptible_timeout( + &ndev->req_completion, + timeout); + + nfc_dbg("wait_for_completion return %ld", completion_rc); + + if (completion_rc > 0) { + switch (ndev->req_status) { + case NCI_REQ_DONE: + rc = nci_to_errno(ndev->req_result); + break; + + case NCI_REQ_CANCELED: + rc = -ndev->req_result; + break; + + default: + rc = -ETIMEDOUT; + break; + } + } else { + nfc_err("wait_for_completion_interruptible_timeout failed %ld", + completion_rc); + + rc = ((completion_rc == 0) ? (-ETIMEDOUT) : (completion_rc)); + } + + ndev->req_status = ndev->req_result = 0; + + return rc; +} + +static inline int nci_request(struct nci_dev *ndev, + void (*req)(struct nci_dev *ndev, unsigned long opt), + unsigned long opt, __u32 timeout) +{ + int rc; + + if (!test_bit(NCI_UP, &ndev->flags)) + return -ENETDOWN; + + /* Serialize all requests */ + mutex_lock(&ndev->req_lock); + rc = __nci_request(ndev, req, opt, timeout); + mutex_unlock(&ndev->req_lock); + + return rc; +} + +static void nci_reset_req(struct nci_dev *ndev, unsigned long opt) +{ + nci_send_cmd(ndev, NCI_OP_CORE_RESET_CMD, 0, NULL); +} + +static void nci_init_req(struct nci_dev *ndev, unsigned long opt) +{ + nci_send_cmd(ndev, NCI_OP_CORE_INIT_CMD, 0, NULL); +} + +static void nci_init_complete_req(struct nci_dev *ndev, unsigned long opt) +{ + struct nci_core_conn_create_cmd conn_cmd; + struct nci_rf_disc_map_cmd cmd; + struct disc_map_config *cfg = cmd.mapping_configs; + __u8 *num = &cmd.num_mapping_configs; + int i; + + /* create static rf connection */ + conn_cmd.target_handle = 0; + conn_cmd.num_target_specific_params = 0; + nci_send_cmd(ndev, NCI_OP_CORE_CONN_CREATE_CMD, 2, &conn_cmd); + + /* set rf mapping configurations */ + *num = 0; + + /* by default mapping is set to NCI_RF_INTERFACE_FRAME */ + for (i = 0; i < ndev->num_supported_rf_interfaces; i++) { + if (ndev->supported_rf_interfaces[i] == + NCI_RF_INTERFACE_ISO_DEP) { + cfg[*num].rf_protocol = NCI_RF_PROTOCOL_ISO_DEP; + cfg[*num].mode = NCI_DISC_MAP_MODE_BOTH; + cfg[*num].rf_interface_type = NCI_RF_INTERFACE_ISO_DEP; + (*num)++; + } else if (ndev->supported_rf_interfaces[i] == + NCI_RF_INTERFACE_NFC_DEP) { + cfg[*num].rf_protocol = NCI_RF_PROTOCOL_NFC_DEP; + cfg[*num].mode = NCI_DISC_MAP_MODE_BOTH; + cfg[*num].rf_interface_type = NCI_RF_INTERFACE_NFC_DEP; + (*num)++; + } + + if (*num == NCI_MAX_NUM_MAPPING_CONFIGS) + break; + } + + nci_send_cmd(ndev, NCI_OP_RF_DISCOVER_MAP_CMD, + (1 + ((*num)*sizeof(struct disc_map_config))), + &cmd); +} + +static void nci_rf_discover_req(struct nci_dev *ndev, unsigned long opt) +{ + struct nci_rf_disc_cmd cmd; + __u32 protocols = opt; + + cmd.num_disc_configs = 0; + + if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) && + (protocols & NFC_PROTO_JEWEL_MASK + || protocols & NFC_PROTO_MIFARE_MASK + || protocols & NFC_PROTO_ISO14443_MASK + || protocols & NFC_PROTO_NFC_DEP_MASK)) { + cmd.disc_configs[cmd.num_disc_configs].type = + NCI_DISCOVERY_TYPE_POLL_A_PASSIVE; + cmd.disc_configs[cmd.num_disc_configs].frequency = 1; + cmd.num_disc_configs++; + } + + if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) && + (protocols & NFC_PROTO_ISO14443_MASK)) { + cmd.disc_configs[cmd.num_disc_configs].type = + NCI_DISCOVERY_TYPE_POLL_B_PASSIVE; + cmd.disc_configs[cmd.num_disc_configs].frequency = 1; + cmd.num_disc_configs++; + } + + if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) && + (protocols & NFC_PROTO_FELICA_MASK + || protocols & NFC_PROTO_NFC_DEP_MASK)) { + cmd.disc_configs[cmd.num_disc_configs].type = + NCI_DISCOVERY_TYPE_POLL_F_PASSIVE; + cmd.disc_configs[cmd.num_disc_configs].frequency = 1; + cmd.num_disc_configs++; + } + + nci_send_cmd(ndev, NCI_OP_RF_DISCOVER_CMD, + (1 + (cmd.num_disc_configs*sizeof(struct disc_config))), + &cmd); +} + +static void nci_rf_deactivate_req(struct nci_dev *ndev, unsigned long opt) +{ + struct nci_rf_deactivate_cmd cmd; + + cmd.type = NCI_DEACTIVATE_TYPE_IDLE_MODE; + + nci_send_cmd(ndev, NCI_OP_RF_DEACTIVATE_CMD, + sizeof(struct nci_rf_deactivate_cmd), + &cmd); +} + +static int nci_open_device(struct nci_dev *ndev) +{ + int rc = 0; + + mutex_lock(&ndev->req_lock); + + if (test_bit(NCI_UP, &ndev->flags)) { + rc = -EALREADY; + goto done; + } + + if (ndev->ops->open(ndev)) { + rc = -EIO; + goto done; + } + + atomic_set(&ndev->cmd_cnt, 1); + + set_bit(NCI_INIT, &ndev->flags); + + rc = __nci_request(ndev, nci_reset_req, 0, + msecs_to_jiffies(NCI_RESET_TIMEOUT)); + + if (!rc) { + rc = __nci_request(ndev, nci_init_req, 0, + msecs_to_jiffies(NCI_INIT_TIMEOUT)); + } + + if (!rc) { + rc = __nci_request(ndev, nci_init_complete_req, 0, + msecs_to_jiffies(NCI_INIT_TIMEOUT)); + } + + clear_bit(NCI_INIT, &ndev->flags); + + if (!rc) { + set_bit(NCI_UP, &ndev->flags); + } else { + /* Init failed, cleanup */ + skb_queue_purge(&ndev->cmd_q); + skb_queue_purge(&ndev->rx_q); + skb_queue_purge(&ndev->tx_q); + + ndev->ops->close(ndev); + ndev->flags = 0; + } + +done: + mutex_unlock(&ndev->req_lock); + return rc; +} + +static int nci_close_device(struct nci_dev *ndev) +{ + nci_req_cancel(ndev, ENODEV); + mutex_lock(&ndev->req_lock); + + if (!test_and_clear_bit(NCI_UP, &ndev->flags)) { + del_timer_sync(&ndev->cmd_timer); + mutex_unlock(&ndev->req_lock); + return 0; + } + + /* Drop RX and TX queues */ + skb_queue_purge(&ndev->rx_q); + skb_queue_purge(&ndev->tx_q); + + /* Flush RX and TX wq */ + flush_workqueue(ndev->rx_wq); + flush_workqueue(ndev->tx_wq); + + /* Reset device */ + skb_queue_purge(&ndev->cmd_q); + atomic_set(&ndev->cmd_cnt, 1); + + set_bit(NCI_INIT, &ndev->flags); + __nci_request(ndev, nci_reset_req, 0, + msecs_to_jiffies(NCI_RESET_TIMEOUT)); + clear_bit(NCI_INIT, &ndev->flags); + + /* Flush cmd wq */ + flush_workqueue(ndev->cmd_wq); + + /* After this point our queues are empty + * and no works are scheduled. */ + ndev->ops->close(ndev); + + /* Clear flags */ + ndev->flags = 0; + + mutex_unlock(&ndev->req_lock); + + return 0; +} + +/* NCI command timer function */ +static void nci_cmd_timer(unsigned long arg) +{ + struct nci_dev *ndev = (void *) arg; + + nfc_dbg("entry"); + + atomic_set(&ndev->cmd_cnt, 1); + queue_work(ndev->cmd_wq, &ndev->cmd_work); +} + +static int nci_dev_up(struct nfc_dev *nfc_dev) +{ + struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); + + nfc_dbg("entry"); + + return nci_open_device(ndev); +} + +static int nci_dev_down(struct nfc_dev *nfc_dev) +{ + struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); + + nfc_dbg("entry"); + + return nci_close_device(ndev); +} + +static int nci_start_poll(struct nfc_dev *nfc_dev, __u32 protocols) +{ + struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); + int rc; + + nfc_dbg("entry"); + + if (test_bit(NCI_DISCOVERY, &ndev->flags)) { + nfc_err("unable to start poll, since poll is already active"); + return -EBUSY; + } + + if (ndev->target_active_prot) { + nfc_err("there is an active target"); + return -EBUSY; + } + + if (test_bit(NCI_POLL_ACTIVE, &ndev->flags)) { + nfc_dbg("target is active, implicitly deactivate..."); + + rc = nci_request(ndev, nci_rf_deactivate_req, 0, + msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT)); + if (rc) + return -EBUSY; + } + + rc = nci_request(ndev, nci_rf_discover_req, protocols, + msecs_to_jiffies(NCI_RF_DISC_TIMEOUT)); + + if (!rc) + ndev->poll_prots = protocols; + + return rc; +} + +static void nci_stop_poll(struct nfc_dev *nfc_dev) +{ + struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); + + nfc_dbg("entry"); + + if (!test_bit(NCI_DISCOVERY, &ndev->flags)) { + nfc_err("unable to stop poll, since poll is not active"); + return; + } + + nci_request(ndev, nci_rf_deactivate_req, 0, + msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT)); +} + +static int nci_activate_target(struct nfc_dev *nfc_dev, __u32 target_idx, + __u32 protocol) +{ + struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); + + nfc_dbg("entry, target_idx %d, protocol 0x%x", target_idx, protocol); + + if (!test_bit(NCI_POLL_ACTIVE, &ndev->flags)) { + nfc_err("there is no available target to activate"); + return -EINVAL; + } + + if (ndev->target_active_prot) { + nfc_err("there is already an active target"); + return -EBUSY; + } + + if (!(ndev->target_available_prots & (1 << protocol))) { + nfc_err("target does not support the requested protocol 0x%x", + protocol); + return -EINVAL; + } + + ndev->target_active_prot = protocol; + ndev->target_available_prots = 0; + + return 0; +} + +static void nci_deactivate_target(struct nfc_dev *nfc_dev, __u32 target_idx) +{ + struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); + + nfc_dbg("entry, target_idx %d", target_idx); + + if (!ndev->target_active_prot) { + nfc_err("unable to deactivate target, no active target"); + return; + } + + ndev->target_active_prot = 0; + + if (test_bit(NCI_POLL_ACTIVE, &ndev->flags)) { + nci_request(ndev, nci_rf_deactivate_req, 0, + msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT)); + } +} + +static int nci_data_exchange(struct nfc_dev *nfc_dev, __u32 target_idx, + struct sk_buff *skb, + data_exchange_cb_t cb, + void *cb_context) +{ + struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); + int rc; + + nfc_dbg("entry, target_idx %d, len %d", target_idx, skb->len); + + if (!ndev->target_active_prot) { + nfc_err("unable to exchange data, no active target"); + return -EINVAL; + } + + if (test_and_set_bit(NCI_DATA_EXCHANGE, &ndev->flags)) + return -EBUSY; + + /* store cb and context to be used on receiving data */ + ndev->data_exchange_cb = cb; + ndev->data_exchange_cb_context = cb_context; + + rc = nci_send_data(ndev, ndev->conn_id, skb); + if (rc) + clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); + + return rc; +} + +static struct nfc_ops nci_nfc_ops = { + .dev_up = nci_dev_up, + .dev_down = nci_dev_down, + .start_poll = nci_start_poll, + .stop_poll = nci_stop_poll, + .activate_target = nci_activate_target, + .deactivate_target = nci_deactivate_target, + .data_exchange = nci_data_exchange, +}; + +/* ---- Interface to NCI drivers ---- */ + +/** + * nci_allocate_device - allocate a new nci device + * + * @ops: device operations + * @supported_protocols: NFC protocols supported by the device + */ +struct nci_dev *nci_allocate_device(struct nci_ops *ops, + __u32 supported_protocols, + int tx_headroom, + int tx_tailroom) +{ + struct nci_dev *ndev; + + nfc_dbg("entry, supported_protocols 0x%x", supported_protocols); + + if (!ops->open || !ops->close || !ops->send) + return NULL; + + if (!supported_protocols) + return NULL; + + ndev = kzalloc(sizeof(struct nci_dev), GFP_KERNEL); + if (!ndev) + return NULL; + + ndev->ops = ops; + ndev->tx_headroom = tx_headroom; + ndev->tx_tailroom = tx_tailroom; + + ndev->nfc_dev = nfc_allocate_device(&nci_nfc_ops, + supported_protocols, + tx_headroom + NCI_DATA_HDR_SIZE, + tx_tailroom); + if (!ndev->nfc_dev) + goto free_exit; + + nfc_set_drvdata(ndev->nfc_dev, ndev); + + return ndev; + +free_exit: + kfree(ndev); + return NULL; +} +EXPORT_SYMBOL(nci_allocate_device); + +/** + * nci_free_device - deallocate nci device + * + * @ndev: The nci device to deallocate + */ +void nci_free_device(struct nci_dev *ndev) +{ + nfc_dbg("entry"); + + nfc_free_device(ndev->nfc_dev); + kfree(ndev); +} +EXPORT_SYMBOL(nci_free_device); + +/** + * nci_register_device - register a nci device in the nfc subsystem + * + * @dev: The nci device to register + */ +int nci_register_device(struct nci_dev *ndev) +{ + int rc; + struct device *dev = &ndev->nfc_dev->dev; + char name[32]; + + nfc_dbg("entry"); + + rc = nfc_register_device(ndev->nfc_dev); + if (rc) + goto exit; + + ndev->flags = 0; + + INIT_WORK(&ndev->cmd_work, nci_cmd_work); + snprintf(name, sizeof(name), "%s_nci_cmd_wq", dev_name(dev)); + ndev->cmd_wq = create_singlethread_workqueue(name); + if (!ndev->cmd_wq) { + rc = -ENOMEM; + goto unreg_exit; + } + + INIT_WORK(&ndev->rx_work, nci_rx_work); + snprintf(name, sizeof(name), "%s_nci_rx_wq", dev_name(dev)); + ndev->rx_wq = create_singlethread_workqueue(name); + if (!ndev->rx_wq) { + rc = -ENOMEM; + goto destroy_cmd_wq_exit; + } + + INIT_WORK(&ndev->tx_work, nci_tx_work); + snprintf(name, sizeof(name), "%s_nci_tx_wq", dev_name(dev)); + ndev->tx_wq = create_singlethread_workqueue(name); + if (!ndev->tx_wq) { + rc = -ENOMEM; + goto destroy_rx_wq_exit; + } + + skb_queue_head_init(&ndev->cmd_q); + skb_queue_head_init(&ndev->rx_q); + skb_queue_head_init(&ndev->tx_q); + + setup_timer(&ndev->cmd_timer, nci_cmd_timer, + (unsigned long) ndev); + + mutex_init(&ndev->req_lock); + + goto exit; + +destroy_rx_wq_exit: + destroy_workqueue(ndev->rx_wq); + +destroy_cmd_wq_exit: + destroy_workqueue(ndev->cmd_wq); + +unreg_exit: + nfc_unregister_device(ndev->nfc_dev); + +exit: + return rc; +} +EXPORT_SYMBOL(nci_register_device); + +/** + * nci_unregister_device - unregister a nci device in the nfc subsystem + * + * @dev: The nci device to unregister + */ +void nci_unregister_device(struct nci_dev *ndev) +{ + nfc_dbg("entry"); + + nci_close_device(ndev); + + destroy_workqueue(ndev->cmd_wq); + destroy_workqueue(ndev->rx_wq); + destroy_workqueue(ndev->tx_wq); + + nfc_unregister_device(ndev->nfc_dev); +} +EXPORT_SYMBOL(nci_unregister_device); + +/** + * nci_recv_frame - receive frame from NCI drivers + * + * @skb: The sk_buff to receive + */ +int nci_recv_frame(struct sk_buff *skb) +{ + struct nci_dev *ndev = (struct nci_dev *) skb->dev; + + nfc_dbg("entry, len %d", skb->len); + + if (!ndev || (!test_bit(NCI_UP, &ndev->flags) + && !test_bit(NCI_INIT, &ndev->flags))) { + kfree_skb(skb); + return -ENXIO; + } + + /* Queue frame for rx worker thread */ + skb_queue_tail(&ndev->rx_q, skb); + queue_work(ndev->rx_wq, &ndev->rx_work); + + return 0; +} +EXPORT_SYMBOL(nci_recv_frame); + +static int nci_send_frame(struct sk_buff *skb) +{ + struct nci_dev *ndev = (struct nci_dev *) skb->dev; + + nfc_dbg("entry, len %d", skb->len); + + if (!ndev) { + kfree_skb(skb); + return -ENODEV; + } + + /* Get rid of skb owner, prior to sending to the driver. */ + skb_orphan(skb); + + return ndev->ops->send(skb); +} + +/* Send NCI command */ +int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload) +{ + struct nci_ctrl_hdr *hdr; + struct sk_buff *skb; + + nfc_dbg("entry, opcode 0x%x, plen %d", opcode, plen); + + skb = nci_skb_alloc(ndev, (NCI_CTRL_HDR_SIZE + plen), GFP_KERNEL); + if (!skb) { + nfc_err("no memory for command"); + return -ENOMEM; + } + + hdr = (struct nci_ctrl_hdr *) skb_put(skb, NCI_CTRL_HDR_SIZE); + hdr->gid = nci_opcode_gid(opcode); + hdr->oid = nci_opcode_oid(opcode); + hdr->plen = plen; + + nci_mt_set((__u8 *)hdr, NCI_MT_CMD_PKT); + nci_pbf_set((__u8 *)hdr, NCI_PBF_LAST); + + if (plen) + memcpy(skb_put(skb, plen), payload, plen); + + skb->dev = (void *) ndev; + + skb_queue_tail(&ndev->cmd_q, skb); + queue_work(ndev->cmd_wq, &ndev->cmd_work); + + return 0; +} + +/* ---- NCI TX Data worker thread ---- */ + +static void nci_tx_work(struct work_struct *work) +{ + struct nci_dev *ndev = container_of(work, struct nci_dev, tx_work); + struct sk_buff *skb; + + nfc_dbg("entry, credits_cnt %d", atomic_read(&ndev->credits_cnt)); + + /* Send queued tx data */ + while (atomic_read(&ndev->credits_cnt)) { + skb = skb_dequeue(&ndev->tx_q); + if (!skb) + return; + + atomic_dec(&ndev->credits_cnt); + + nfc_dbg("NCI TX: MT=data, PBF=%d, conn_id=%d, plen=%d", + nci_pbf(skb->data), + nci_conn_id(skb->data), + nci_plen(skb->data)); + + nci_send_frame(skb); + } +} + +/* ----- NCI RX worker thread (data & control) ----- */ + +static void nci_rx_work(struct work_struct *work) +{ + struct nci_dev *ndev = container_of(work, struct nci_dev, rx_work); + struct sk_buff *skb; + + while ((skb = skb_dequeue(&ndev->rx_q))) { + /* Process frame */ + switch (nci_mt(skb->data)) { + case NCI_MT_RSP_PKT: + nci_rsp_packet(ndev, skb); + break; + + case NCI_MT_NTF_PKT: + nci_ntf_packet(ndev, skb); + break; + + case NCI_MT_DATA_PKT: + nci_rx_data_packet(ndev, skb); + break; + + default: + nfc_err("unknown MT 0x%x", nci_mt(skb->data)); + kfree_skb(skb); + break; + } + } +} + +/* ----- NCI TX CMD worker thread ----- */ + +static void nci_cmd_work(struct work_struct *work) +{ + struct nci_dev *ndev = container_of(work, struct nci_dev, cmd_work); + struct sk_buff *skb; + + nfc_dbg("entry, cmd_cnt %d", atomic_read(&ndev->cmd_cnt)); + + /* Send queued command */ + if (atomic_read(&ndev->cmd_cnt)) { + skb = skb_dequeue(&ndev->cmd_q); + if (!skb) + return; + + atomic_dec(&ndev->cmd_cnt); + + nfc_dbg("NCI TX: MT=cmd, PBF=%d, GID=0x%x, OID=0x%x, plen=%d", + nci_pbf(skb->data), + nci_opcode_gid(nci_opcode(skb->data)), + nci_opcode_oid(nci_opcode(skb->data)), + nci_plen(skb->data)); + + nci_send_frame(skb); + + mod_timer(&ndev->cmd_timer, + jiffies + msecs_to_jiffies(NCI_CMD_TIMEOUT)); + } +} diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c new file mode 100644 index 0000000..e5ed90f --- /dev/null +++ b/net/nfc/nci/data.c @@ -0,0 +1,247 @@ +/* + * The NFC Controller Interface is the communication protocol between an + * NFC Controller (NFCC) and a Device Host (DH). + * + * Copyright (C) 2011 Texas Instruments, Inc. + * + * Written by Ilan Elias <ilane@ti.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include <linux/types.h> +#include <linux/interrupt.h> +#include <linux/wait.h> +#include <linux/bitops.h> +#include <linux/skbuff.h> + +#include "../nfc.h" +#include <net/nfc/nci.h> +#include <net/nfc/nci_core.h> +#include <linux/nfc.h> + +/* Complete data exchange transaction and forward skb to nfc core */ +void nci_data_exchange_complete(struct nci_dev *ndev, + struct sk_buff *skb, + int err) +{ + data_exchange_cb_t cb = ndev->data_exchange_cb; + void *cb_context = ndev->data_exchange_cb_context; + + nfc_dbg("entry, len %d, err %d", ((skb) ? (skb->len) : (0)), err); + + if (cb) { + ndev->data_exchange_cb = NULL; + ndev->data_exchange_cb_context = 0; + + /* forward skb to nfc core */ + cb(cb_context, skb, err); + } else if (skb) { + nfc_err("no rx callback, dropping rx data..."); + + /* no waiting callback, free skb */ + kfree_skb(skb); + } + + clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); +} + +/* ----------------- NCI TX Data ----------------- */ + +static inline void nci_push_data_hdr(struct nci_dev *ndev, + __u8 conn_id, + struct sk_buff *skb, + __u8 pbf) +{ + struct nci_data_hdr *hdr; + int plen = skb->len; + + hdr = (struct nci_data_hdr *) skb_push(skb, NCI_DATA_HDR_SIZE); + hdr->conn_id = conn_id; + hdr->rfu = 0; + hdr->plen = plen; + + nci_mt_set((__u8 *)hdr, NCI_MT_DATA_PKT); + nci_pbf_set((__u8 *)hdr, pbf); + + skb->dev = (void *) ndev; +} + +static int nci_queue_tx_data_frags(struct nci_dev *ndev, + __u8 conn_id, + struct sk_buff *skb) { + int total_len = skb->len; + unsigned char *data = skb->data; + unsigned long flags; + struct sk_buff_head frags_q; + struct sk_buff *skb_frag; + int frag_len; + int rc = 0; + + nfc_dbg("entry, conn_id 0x%x, total_len %d", conn_id, total_len); + + __skb_queue_head_init(&frags_q); + + while (total_len) { + frag_len = min_t(int, total_len, ndev->max_pkt_payload_size); + + skb_frag = nci_skb_alloc(ndev, + (NCI_DATA_HDR_SIZE + frag_len), + GFP_KERNEL); + if (skb_frag == NULL) { + rc = -ENOMEM; + goto free_exit; + } + skb_reserve(skb_frag, NCI_DATA_HDR_SIZE); + + /* first, copy the data */ + memcpy(skb_put(skb_frag, frag_len), data, frag_len); + + /* second, set the header */ + nci_push_data_hdr(ndev, conn_id, skb_frag, + ((total_len == frag_len) ? (NCI_PBF_LAST) : (NCI_PBF_CONT))); + + __skb_queue_tail(&frags_q, skb_frag); + + data += frag_len; + total_len -= frag_len; + + nfc_dbg("frag_len %d, remaining total_len %d", + frag_len, total_len); + } + + /* queue all fragments atomically */ + spin_lock_irqsave(&ndev->tx_q.lock, flags); + + while ((skb_frag = __skb_dequeue(&frags_q)) != NULL) + __skb_queue_tail(&ndev->tx_q, skb_frag); + + spin_unlock_irqrestore(&ndev->tx_q.lock, flags); + + /* free the original skb */ + kfree_skb(skb); + + goto exit; + +free_exit: + while ((skb_frag = __skb_dequeue(&frags_q)) != NULL) + kfree_skb(skb_frag); + +exit: + return rc; +} + +/* Send NCI data */ +int nci_send_data(struct nci_dev *ndev, __u8 conn_id, struct sk_buff *skb) +{ + int rc = 0; + + nfc_dbg("entry, conn_id 0x%x, plen %d", conn_id, skb->len); + + /* check if the packet need to be fragmented */ + if (skb->len <= ndev->max_pkt_payload_size) { + /* no need to fragment packet */ + nci_push_data_hdr(ndev, conn_id, skb, NCI_PBF_LAST); + + skb_queue_tail(&ndev->tx_q, skb); + } else { + /* fragment packet and queue the fragments */ + rc = nci_queue_tx_data_frags(ndev, conn_id, skb); + if (rc) { + nfc_err("failed to fragment tx data packet"); + goto free_exit; + } + } + + queue_work(ndev->tx_wq, &ndev->tx_work); + + goto exit; + +free_exit: + kfree_skb(skb); + +exit: + return rc; +} + +/* ----------------- NCI RX Data ----------------- */ + +static void nci_add_rx_data_frag(struct nci_dev *ndev, + struct sk_buff *skb, + __u8 pbf) +{ + int reassembly_len; + int err = 0; + + if (ndev->rx_data_reassembly) { + reassembly_len = ndev->rx_data_reassembly->len; + + /* first, make enough room for the already accumulated data */ + if (skb_cow_head(skb, reassembly_len)) { + nfc_err("error adding room for accumulated rx data"); + + kfree_skb(skb); + skb = 0; + + kfree_skb(ndev->rx_data_reassembly); + ndev->rx_data_reassembly = 0; + + err = -ENOMEM; + goto exit; + } + + /* second, combine the two fragments */ + memcpy(skb_push(skb, reassembly_len), + ndev->rx_data_reassembly->data, + reassembly_len); + + /* third, free old reassembly */ + kfree_skb(ndev->rx_data_reassembly); + ndev->rx_data_reassembly = 0; + } + + if (pbf == NCI_PBF_CONT) { + /* need to wait for next fragment, store skb and exit */ + ndev->rx_data_reassembly = skb; + return; + } + +exit: + nci_data_exchange_complete(ndev, skb, err); +} + +/* Rx Data packet */ +void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb) +{ + __u8 pbf = nci_pbf(skb->data); + + nfc_dbg("entry, len %d", skb->len); + + nfc_dbg("NCI RX: MT=data, PBF=%d, conn_id=%d, plen=%d", + nci_pbf(skb->data), + nci_conn_id(skb->data), + nci_plen(skb->data)); + + /* strip the nci data header */ + skb_pull(skb, NCI_DATA_HDR_SIZE); + + if (ndev->target_active_prot == NFC_PROTO_MIFARE) { + /* frame I/F => remove the status byte */ + nfc_dbg("NFC_PROTO_MIFARE => remove the status byte"); + skb_trim(skb, (skb->len - 1)); + } + + nci_add_rx_data_frag(ndev, skb, pbf); +} diff --git a/net/nfc/nci/lib.c b/net/nfc/nci/lib.c new file mode 100644 index 0000000..b19dc2f --- /dev/null +++ b/net/nfc/nci/lib.c @@ -0,0 +1,94 @@ +/* + * The NFC Controller Interface is the communication protocol between an + * NFC Controller (NFCC) and a Device Host (DH). + * + * Copyright (C) 2011 Texas Instruments, Inc. + * + * Written by Ilan Elias <ilane@ti.com> + * + * Acknowledgements: + * This file is based on lib.c, which was written + * by Maxim Krasnyansky. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/errno.h> + +#include <net/nfc/nci.h> + +/* NCI status codes to Unix errno mapping */ +int nci_to_errno(__u8 code) +{ + switch (code) { + case NCI_STATUS_OK: + return 0; + + case NCI_STATUS_REJECTED: + return -EBUSY; + + case NCI_STATUS_MESSAGE_CORRUPTED: + return -EBADMSG; + + case NCI_STATUS_BUFFER_FULL: + return -ENOBUFS; + + case NCI_STATUS_NOT_INITIALIZED: + return -EHOSTDOWN; + + case NCI_STATUS_SYNTAX_ERROR: + case NCI_STATUS_SEMANTIC_ERROR: + case NCI_STATUS_INVALID_PARAM: + case NCI_STATUS_RF_PROTOCOL_ERROR: + case NCI_STATUS_NFCEE_PROTOCOL_ERROR: + return -EPROTO; + + case NCI_STATUS_UNKNOWN_GID: + case NCI_STATUS_UNKNOWN_OID: + return -EBADRQC; + + case NCI_STATUS_MESSAGE_SIZE_EXCEEDED: + return -EMSGSIZE; + + case NCI_STATUS_DISCOVERY_ALREADY_STARTED: + return -EALREADY; + + case NCI_STATUS_DISCOVERY_TARGET_ACTIVATION_FAILED: + case NCI_STATUS_NFCEE_INTERFACE_ACTIVATION_FAILED: + return -ECONNREFUSED; + + case NCI_STATUS_RF_TRANSMISSION_ERROR: + case NCI_STATUS_NFCEE_TRANSMISSION_ERROR: + return -ECOMM; + + case NCI_STATUS_RF_TIMEOUT_ERROR: + case NCI_STATUS_NFCEE_TIMEOUT_ERROR: + return -ETIMEDOUT; + + case NCI_STATUS_RF_LINK_LOSS_ERROR: + return -ENOLINK; + + case NCI_STATUS_MAX_ACTIVE_NFCEE_INTERFACES_REACHED: + return -EDQUOT; + + case NCI_STATUS_FAILED: + default: + return -ENOSYS; + } +} +EXPORT_SYMBOL(nci_to_errno); diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c new file mode 100644 index 0000000..96633f5 --- /dev/null +++ b/net/nfc/nci/ntf.c @@ -0,0 +1,258 @@ +/* + * The NFC Controller Interface is the communication protocol between an + * NFC Controller (NFCC) and a Device Host (DH). + * + * Copyright (C) 2011 Texas Instruments, Inc. + * + * Written by Ilan Elias <ilane@ti.com> + * + * Acknowledgements: + * This file is based on hci_event.c, which was written + * by Maxim Krasnyansky. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include <linux/types.h> +#include <linux/interrupt.h> +#include <linux/bitops.h> +#include <linux/skbuff.h> + +#include "../nfc.h" +#include <net/nfc/nci.h> +#include <net/nfc/nci_core.h> +#include <linux/nfc.h> + +/* Handle NCI Notification packets */ + +static void nci_core_conn_credits_ntf_packet(struct nci_dev *ndev, + struct sk_buff *skb) +{ + struct nci_core_conn_credit_ntf *ntf = (void *) skb->data; + int i; + + nfc_dbg("entry, num_entries %d", ntf->num_entries); + + if (ntf->num_entries > NCI_MAX_NUM_CONN) + ntf->num_entries = NCI_MAX_NUM_CONN; + + /* update the credits */ + for (i = 0; i < ntf->num_entries; i++) { + nfc_dbg("entry[%d]: conn_id %d, credits %d", i, + ntf->conn_entries[i].conn_id, + ntf->conn_entries[i].credits); + + if (ntf->conn_entries[i].conn_id == ndev->conn_id) { + /* found static rf connection */ + atomic_add(ntf->conn_entries[i].credits, + &ndev->credits_cnt); + } + } + + /* trigger the next tx */ + if (!skb_queue_empty(&ndev->tx_q)) + queue_work(ndev->tx_wq, &ndev->tx_work); +} + +static void nci_rf_field_info_ntf_packet(struct nci_dev *ndev, + struct sk_buff *skb) +{ + struct nci_rf_field_info_ntf *ntf = (void *) skb->data; + + nfc_dbg("entry, rf_field_status %d", ntf->rf_field_status); +} + +static int nci_rf_activate_nfca_passive_poll(struct nci_dev *ndev, + struct nci_rf_activate_ntf *ntf, __u8 *data) +{ + struct rf_tech_specific_params_nfca_poll *nfca_poll; + struct activation_params_nfca_poll_iso_dep *nfca_poll_iso_dep; + + nfca_poll = &ntf->rf_tech_specific_params.nfca_poll; + nfca_poll_iso_dep = &ntf->activation_params.nfca_poll_iso_dep; + + nfca_poll->sens_res = __le16_to_cpu(*((__u16 *)data)); + data += 2; + + nfca_poll->nfcid1_len = *data++; + + nfc_dbg("sens_res 0x%x, nfcid1_len %d", + nfca_poll->sens_res, + nfca_poll->nfcid1_len); + + memcpy(nfca_poll->nfcid1, data, nfca_poll->nfcid1_len); + data += nfca_poll->nfcid1_len; + + nfca_poll->sel_res_len = *data++; + + if (nfca_poll->sel_res_len != 0) + nfca_poll->sel_res = *data++; + + ntf->rf_interface_type = *data++; + ntf->activation_params_len = *data++; + + nfc_dbg("sel_res_len %d, sel_res 0x%x, rf_interface_type %d, activation_params_len %d", + nfca_poll->sel_res_len, + nfca_poll->sel_res, + ntf->rf_interface_type, + ntf->activation_params_len); + + switch (ntf->rf_interface_type) { + case NCI_RF_INTERFACE_ISO_DEP: + nfca_poll_iso_dep->rats_res_len = *data++; + if (nfca_poll_iso_dep->rats_res_len > 0) { + memcpy(nfca_poll_iso_dep->rats_res, + data, + nfca_poll_iso_dep->rats_res_len); + } + break; + + case NCI_RF_INTERFACE_FRAME: + /* no activation params */ + break; + + default: + nfc_err("unsupported rf_interface_type 0x%x", + ntf->rf_interface_type); + return -EPROTO; + } + + return 0; +} + +static void nci_target_found(struct nci_dev *ndev, + struct nci_rf_activate_ntf *ntf) +{ + struct nfc_target nfc_tgt; + + if (ntf->rf_protocol == NCI_RF_PROTOCOL_T2T) /* T2T MifareUL */ + nfc_tgt.supported_protocols = NFC_PROTO_MIFARE_MASK; + else if (ntf->rf_protocol == NCI_RF_PROTOCOL_ISO_DEP) /* 4A */ + nfc_tgt.supported_protocols = NFC_PROTO_ISO14443_MASK; + + nfc_tgt.sens_res = ntf->rf_tech_specific_params.nfca_poll.sens_res; + nfc_tgt.sel_res = ntf->rf_tech_specific_params.nfca_poll.sel_res; + + if (!(nfc_tgt.supported_protocols & ndev->poll_prots)) { + nfc_dbg("the target found does not have the desired protocol"); + return; + } + + nfc_dbg("new target found, supported_protocols 0x%x", + nfc_tgt.supported_protocols); + + ndev->target_available_prots = nfc_tgt.supported_protocols; + + nfc_targets_found(ndev->nfc_dev, &nfc_tgt, 1); +} + +static void nci_rf_activate_ntf_packet(struct nci_dev *ndev, + struct sk_buff *skb) +{ + struct nci_rf_activate_ntf ntf; + __u8 *data = skb->data; + int rc = -1; + + clear_bit(NCI_DISCOVERY, &ndev->flags); + set_bit(NCI_POLL_ACTIVE, &ndev->flags); + + ntf.target_handle = *data++; + ntf.rf_protocol = *data++; + ntf.rf_tech_and_mode = *data++; + ntf.rf_tech_specific_params_len = *data++; + + nfc_dbg("target_handle %d, rf_protocol 0x%x, rf_tech_and_mode 0x%x, rf_tech_specific_params_len %d", + ntf.target_handle, + ntf.rf_protocol, + ntf.rf_tech_and_mode, + ntf.rf_tech_specific_params_len); + + switch (ntf.rf_tech_and_mode) { + case NCI_NFC_A_PASSIVE_POLL_MODE: + rc = nci_rf_activate_nfca_passive_poll(ndev, &ntf, + data); + break; + + default: + nfc_err("unsupported rf_tech_and_mode 0x%x", + ntf.rf_tech_and_mode); + return; + } + + if (!rc) + nci_target_found(ndev, &ntf); +} + +static void nci_rf_deactivate_ntf_packet(struct nci_dev *ndev, + struct sk_buff *skb) +{ + __u8 type = skb->data[0]; + + nfc_dbg("entry, type 0x%x", type); + + clear_bit(NCI_POLL_ACTIVE, &ndev->flags); + ndev->target_active_prot = 0; + + /* drop tx data queue */ + skb_queue_purge(&ndev->tx_q); + + /* drop partial rx data packet */ + if (ndev->rx_data_reassembly) { + kfree_skb(ndev->rx_data_reassembly); + ndev->rx_data_reassembly = 0; + } + + /* complete the data exchange transaction, if exists */ + if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags)) + nci_data_exchange_complete(ndev, NULL, -EIO); +} + +void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb) +{ + __u16 ntf_opcode = nci_opcode(skb->data); + + nfc_dbg("NCI RX: MT=ntf, PBF=%d, GID=0x%x, OID=0x%x, plen=%d", + nci_pbf(skb->data), + nci_opcode_gid(ntf_opcode), + nci_opcode_oid(ntf_opcode), + nci_plen(skb->data)); + + /* strip the nci control header */ + skb_pull(skb, NCI_CTRL_HDR_SIZE); + + switch (ntf_opcode) { + case NCI_OP_CORE_CONN_CREDITS_NTF: + nci_core_conn_credits_ntf_packet(ndev, skb); + break; + + case NCI_OP_RF_FIELD_INFO_NTF: + nci_rf_field_info_ntf_packet(ndev, skb); + break; + + case NCI_OP_RF_ACTIVATE_NTF: + nci_rf_activate_ntf_packet(ndev, skb); + break; + + case NCI_OP_RF_DEACTIVATE_NTF: + nci_rf_deactivate_ntf_packet(ndev, skb); + break; + + default: + nfc_err("unknown ntf opcode 0x%x", ntf_opcode); + break; + } + + kfree_skb(skb); +} diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c new file mode 100644 index 0000000..0403d4c --- /dev/null +++ b/net/nfc/nci/rsp.c @@ -0,0 +1,226 @@ +/* + * The NFC Controller Interface is the communication protocol between an + * NFC Controller (NFCC) and a Device Host (DH). + * + * Copyright (C) 2011 Texas Instruments, Inc. + * + * Written by Ilan Elias <ilane@ti.com> + * + * Acknowledgements: + * This file is based on hci_event.c, which was written + * by Maxim Krasnyansky. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include <linux/types.h> +#include <linux/interrupt.h> +#include <linux/bitops.h> +#include <linux/skbuff.h> + +#include "../nfc.h" +#include <net/nfc/nci.h> +#include <net/nfc/nci_core.h> + +/* Handle NCI Response packets */ + +static void nci_core_reset_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb) +{ + struct nci_core_reset_rsp *rsp = (void *) skb->data; + + nfc_dbg("entry, status 0x%x", rsp->status); + + if (rsp->status == NCI_STATUS_OK) + ndev->nci_ver = rsp->nci_ver; + + nfc_dbg("nci_ver 0x%x", ndev->nci_ver); + + nci_req_complete(ndev, rsp->status); +} + +static void nci_core_init_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb) +{ + struct nci_core_init_rsp_1 *rsp_1 = (void *) skb->data; + struct nci_core_init_rsp_2 *rsp_2; + + nfc_dbg("entry, status 0x%x", rsp_1->status); + + if (rsp_1->status != NCI_STATUS_OK) + return; + + ndev->nfcc_features = __le32_to_cpu(rsp_1->nfcc_features); + ndev->num_supported_rf_interfaces = rsp_1->num_supported_rf_interfaces; + + if (ndev->num_supported_rf_interfaces > + NCI_MAX_SUPPORTED_RF_INTERFACES) { + ndev->num_supported_rf_interfaces = + NCI_MAX_SUPPORTED_RF_INTERFACES; + } + + memcpy(ndev->supported_rf_interfaces, + rsp_1->supported_rf_interfaces, + ndev->num_supported_rf_interfaces); + + rsp_2 = (void *) (skb->data + 6 + ndev->num_supported_rf_interfaces); + + ndev->max_logical_connections = + rsp_2->max_logical_connections; + ndev->max_routing_table_size = + __le16_to_cpu(rsp_2->max_routing_table_size); + ndev->max_control_packet_payload_length = + rsp_2->max_control_packet_payload_length; + ndev->rf_sending_buffer_size = + __le16_to_cpu(rsp_2->rf_sending_buffer_size); + ndev->rf_receiving_buffer_size = + __le16_to_cpu(rsp_2->rf_receiving_buffer_size); + ndev->manufacturer_id = + __le16_to_cpu(rsp_2->manufacturer_id); + + nfc_dbg("nfcc_features 0x%x", + ndev->nfcc_features); + nfc_dbg("num_supported_rf_interfaces %d", + ndev->num_supported_rf_interfaces); + nfc_dbg("supported_rf_interfaces[0] 0x%x", + ndev->supported_rf_interfaces[0]); + nfc_dbg("supported_rf_interfaces[1] 0x%x", + ndev->supported_rf_interfaces[1]); + nfc_dbg("supported_rf_interfaces[2] 0x%x", + ndev->supported_rf_interfaces[2]); + nfc_dbg("supported_rf_interfaces[3] 0x%x", + ndev->supported_rf_interfaces[3]); + nfc_dbg("max_logical_connections %d", + ndev->max_logical_connections); + nfc_dbg("max_routing_table_size %d", + ndev->max_routing_table_size); + nfc_dbg("max_control_packet_payload_length %d", + ndev->max_control_packet_payload_length); + nfc_dbg("rf_sending_buffer_size %d", + ndev->rf_sending_buffer_size); + nfc_dbg("rf_receiving_buffer_size %d", + ndev->rf_receiving_buffer_size); + nfc_dbg("manufacturer_id 0x%x", + ndev->manufacturer_id); + + nci_req_complete(ndev, rsp_1->status); +} + +static void nci_core_conn_create_rsp_packet(struct nci_dev *ndev, + struct sk_buff *skb) +{ + struct nci_core_conn_create_rsp *rsp = (void *) skb->data; + + nfc_dbg("entry, status 0x%x", rsp->status); + + if (rsp->status != NCI_STATUS_OK) + return; + + ndev->max_pkt_payload_size = rsp->max_pkt_payload_size; + ndev->initial_num_credits = rsp->initial_num_credits; + ndev->conn_id = rsp->conn_id; + + atomic_set(&ndev->credits_cnt, ndev->initial_num_credits); + + nfc_dbg("max_pkt_payload_size %d", ndev->max_pkt_payload_size); + nfc_dbg("initial_num_credits %d", ndev->initial_num_credits); + nfc_dbg("conn_id %d", ndev->conn_id); +} + +static void nci_rf_disc_map_rsp_packet(struct nci_dev *ndev, + struct sk_buff *skb) +{ + __u8 status = skb->data[0]; + + nfc_dbg("entry, status 0x%x", status); + + nci_req_complete(ndev, status); +} + +static void nci_rf_disc_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb) +{ + __u8 status = skb->data[0]; + + nfc_dbg("entry, status 0x%x", status); + + if (status == NCI_STATUS_OK) + set_bit(NCI_DISCOVERY, &ndev->flags); + + nci_req_complete(ndev, status); +} + +static void nci_rf_deactivate_rsp_packet(struct nci_dev *ndev, + struct sk_buff *skb) +{ + __u8 status = skb->data[0]; + + nfc_dbg("entry, status 0x%x", status); + + clear_bit(NCI_DISCOVERY, &ndev->flags); + + nci_req_complete(ndev, status); +} + +void nci_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb) +{ + __u16 rsp_opcode = nci_opcode(skb->data); + + /* we got a rsp, stop the cmd timer */ + del_timer(&ndev->cmd_timer); + + nfc_dbg("NCI RX: MT=rsp, PBF=%d, GID=0x%x, OID=0x%x, plen=%d", + nci_pbf(skb->data), + nci_opcode_gid(rsp_opcode), + nci_opcode_oid(rsp_opcode), + nci_plen(skb->data)); + + /* strip the nci control header */ + skb_pull(skb, NCI_CTRL_HDR_SIZE); + + switch (rsp_opcode) { + case NCI_OP_CORE_RESET_RSP: + nci_core_reset_rsp_packet(ndev, skb); + break; + + case NCI_OP_CORE_INIT_RSP: + nci_core_init_rsp_packet(ndev, skb); + break; + + case NCI_OP_CORE_CONN_CREATE_RSP: + nci_core_conn_create_rsp_packet(ndev, skb); + break; + + case NCI_OP_RF_DISCOVER_MAP_RSP: + nci_rf_disc_map_rsp_packet(ndev, skb); + break; + + case NCI_OP_RF_DISCOVER_RSP: + nci_rf_disc_rsp_packet(ndev, skb); + break; + + case NCI_OP_RF_DEACTIVATE_RSP: + nci_rf_deactivate_rsp_packet(ndev, skb); + break; + + default: + nfc_err("unknown rsp opcode 0x%x", rsp_opcode); + break; + } + + kfree_skb(skb); + + /* trigger the next cmd */ + atomic_set(&ndev->cmd_cnt, 1); + if (!skb_queue_empty(&ndev->cmd_q)) + queue_work(ndev->cmd_wq, &ndev->cmd_work); +} diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index ccdff79..03f8818 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -367,6 +367,52 @@ out_putdev: return rc; } +static int nfc_genl_dev_up(struct sk_buff *skb, struct genl_info *info) +{ + struct nfc_dev *dev; + int rc; + u32 idx; + + nfc_dbg("entry"); + + if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + return -EINVAL; + + idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); + + dev = nfc_get_device(idx); + if (!dev) + return -ENODEV; + + rc = nfc_dev_up(dev); + + nfc_put_device(dev); + return rc; +} + +static int nfc_genl_dev_down(struct sk_buff *skb, struct genl_info *info) +{ + struct nfc_dev *dev; + int rc; + u32 idx; + + nfc_dbg("entry"); + + if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + return -EINVAL; + + idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); + + dev = nfc_get_device(idx); + if (!dev) + return -ENODEV; + + rc = nfc_dev_down(dev); + + nfc_put_device(dev); + return rc; +} + static int nfc_genl_start_poll(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; @@ -441,6 +487,16 @@ static struct genl_ops nfc_genl_ops[] = { .policy = nfc_genl_policy, }, { + .cmd = NFC_CMD_DEV_UP, + .doit = nfc_genl_dev_up, + .policy = nfc_genl_policy, + }, + { + .cmd = NFC_CMD_DEV_DOWN, + .doit = nfc_genl_dev_down, + .policy = nfc_genl_policy, + }, + { .cmd = NFC_CMD_START_POLL, .doit = nfc_genl_start_poll, .policy = nfc_genl_policy, diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index aaf9832..d86583f 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -24,10 +24,10 @@ #ifndef __LOCAL_NFC_H #define __LOCAL_NFC_H -#include <net/nfc.h> +#include <net/nfc/nfc.h> #include <net/sock.h> -__attribute__((format (printf, 2, 3))) +__printf(2, 3) int nfc_printk(const char *level, const char *fmt, ...); #define nfc_info(fmt, arg...) nfc_printk(KERN_INFO, fmt, ##arg) @@ -101,6 +101,10 @@ static inline void nfc_device_iter_exit(struct class_dev_iter *iter) class_dev_iter_exit(iter); } +int nfc_dev_up(struct nfc_dev *dev); + +int nfc_dev_down(struct nfc_dev *dev); + int nfc_start_poll(struct nfc_dev *dev, u32 protocols); int nfc_stop_poll(struct nfc_dev *dev); diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 52de84a..9fd652a 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -123,11 +123,7 @@ error: static int rawsock_add_header(struct sk_buff *skb) { - - if (skb_cow_head(skb, 1)) - return -ENOMEM; - - *skb_push(skb, 1) = 0; + *skb_push(skb, NFC_HEADER_SIZE) = 0; return 0; } @@ -197,6 +193,7 @@ static int rawsock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; + struct nfc_dev *dev = nfc_rawsock(sk)->dev; struct sk_buff *skb; int rc; @@ -208,11 +205,13 @@ static int rawsock_sendmsg(struct kiocb *iocb, struct socket *sock, if (sock->state != SS_CONNECTED) return -ENOTCONN; - skb = sock_alloc_send_skb(sk, len, msg->msg_flags & MSG_DONTWAIT, - &rc); + skb = sock_alloc_send_skb(sk, len + dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE, + msg->msg_flags & MSG_DONTWAIT, &rc); if (!skb) return rc; + skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); + rc = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len); if (rc < 0) { kfree_skb(skb); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c698cec..82a6f34 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -40,6 +40,10 @@ * byte arrays at the end of sockaddr_ll * and packet_mreq. * Johann Baudy : Added TX RING. + * Chetan Loke : Implemented TPACKET_V3 block abstraction + * layer. + * Copyright (C) 2011, <lokec@ccs.neu.edu> + * * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -161,9 +165,56 @@ struct packet_mreq_max { unsigned char mr_address[MAX_ADDR_LEN]; }; -static int packet_set_ring(struct sock *sk, struct tpacket_req *req, +static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring); + +#define V3_ALIGNMENT (8) + +#define BLK_HDR_LEN (ALIGN(sizeof(struct tpacket_block_desc), V3_ALIGNMENT)) + +#define BLK_PLUS_PRIV(sz_of_priv) \ + (BLK_HDR_LEN + ALIGN((sz_of_priv), V3_ALIGNMENT)) + +/* kbdq - kernel block descriptor queue */ +struct tpacket_kbdq_core { + struct pgv *pkbdq; + unsigned int feature_req_word; + unsigned int hdrlen; + unsigned char reset_pending_on_curr_blk; + unsigned char delete_blk_timer; + unsigned short kactive_blk_num; + unsigned short blk_sizeof_priv; + + /* last_kactive_blk_num: + * trick to see if user-space has caught up + * in order to avoid refreshing timer when every single pkt arrives. + */ + unsigned short last_kactive_blk_num; + + char *pkblk_start; + char *pkblk_end; + int kblk_size; + unsigned int knum_blocks; + uint64_t knxt_seq_num; + char *prev; + char *nxt_offset; + struct sk_buff *skb; + + atomic_t blk_fill_in_prog; + + /* Default is set to 8ms */ +#define DEFAULT_PRB_RETIRE_TOV (8) + + unsigned short retire_blk_tov; + unsigned short version; + unsigned long tov_in_jiffies; + + /* timer to retire an outstanding block */ + struct timer_list retire_blk_timer; +}; + +#define PGV_FROM_VMALLOC 1 struct pgv { char *buffer; }; @@ -179,12 +230,44 @@ struct packet_ring_buffer { unsigned int pg_vec_pages; unsigned int pg_vec_len; + struct tpacket_kbdq_core prb_bdqc; atomic_t pending; }; +#define BLOCK_STATUS(x) ((x)->hdr.bh1.block_status) +#define BLOCK_NUM_PKTS(x) ((x)->hdr.bh1.num_pkts) +#define BLOCK_O2FP(x) ((x)->hdr.bh1.offset_to_first_pkt) +#define BLOCK_LEN(x) ((x)->hdr.bh1.blk_len) +#define BLOCK_SNUM(x) ((x)->hdr.bh1.seq_num) +#define BLOCK_O2PRIV(x) ((x)->offset_to_priv) +#define BLOCK_PRIV(x) ((void *)((char *)(x) + BLOCK_O2PRIV(x))) + struct packet_sock; static int tpacket_snd(struct packet_sock *po, struct msghdr *msg); +static void *packet_previous_frame(struct packet_sock *po, + struct packet_ring_buffer *rb, + int status); +static void packet_increment_head(struct packet_ring_buffer *buff); +static int prb_curr_blk_in_use(struct tpacket_kbdq_core *, + struct tpacket_block_desc *); +static void *prb_dispatch_next_block(struct tpacket_kbdq_core *, + struct packet_sock *); +static void prb_retire_current_block(struct tpacket_kbdq_core *, + struct packet_sock *, unsigned int status); +static int prb_queue_frozen(struct tpacket_kbdq_core *); +static void prb_open_block(struct tpacket_kbdq_core *, + struct tpacket_block_desc *); +static void prb_retire_rx_blk_timer_expired(unsigned long); +static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *); +static void prb_init_blk_timer(struct packet_sock *, + struct tpacket_kbdq_core *, + void (*func) (unsigned long)); +static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); +static void prb_clear_rxhash(struct tpacket_kbdq_core *, + struct tpacket3_hdr *); +static void prb_fill_vlan_info(struct tpacket_kbdq_core *, + struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); struct packet_fanout; @@ -193,6 +276,7 @@ struct packet_sock { struct sock sk; struct packet_fanout *fanout; struct tpacket_stats stats; + union tpacket_stats_u stats_u; struct packet_ring_buffer rx_ring; struct packet_ring_buffer tx_ring; int copy_thresh; @@ -242,7 +326,16 @@ struct packet_skb_cb { #define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb)) -static inline struct packet_sock *pkt_sk(struct sock *sk) +#define GET_PBDQC_FROM_RB(x) ((struct tpacket_kbdq_core *)(&(x)->prb_bdqc)) +#define GET_PBLOCK_DESC(x, bid) \ + ((struct tpacket_block_desc *)((x)->pkbdq[(bid)].buffer)) +#define GET_CURR_PBLOCK_DESC_FROM_CORE(x) \ + ((struct tpacket_block_desc *)((x)->pkbdq[(x)->kactive_blk_num].buffer)) +#define GET_NEXT_PRB_BLK_NUM(x) \ + (((x)->kactive_blk_num < ((x)->knum_blocks-1)) ? \ + ((x)->kactive_blk_num+1) : 0) + +static struct packet_sock *pkt_sk(struct sock *sk) { return (struct packet_sock *)sk; } @@ -325,8 +418,9 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) h.h2->tp_status = status; flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; + case TPACKET_V3: default: - pr_err("TPACKET version not supported\n"); + WARN(1, "TPACKET version not supported.\n"); BUG(); } @@ -351,8 +445,9 @@ static int __packet_get_status(struct packet_sock *po, void *frame) case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); return h.h2->tp_status; + case TPACKET_V3: default: - pr_err("TPACKET version not supported\n"); + WARN(1, "TPACKET version not supported.\n"); BUG(); return 0; } @@ -382,14 +477,678 @@ static void *packet_lookup_frame(struct packet_sock *po, return h.raw; } -static inline void *packet_current_frame(struct packet_sock *po, +static void *packet_current_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { return packet_lookup_frame(po, rb, rb->head, status); } -static inline void *packet_previous_frame(struct packet_sock *po, +static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) +{ + del_timer_sync(&pkc->retire_blk_timer); +} + +static void prb_shutdown_retire_blk_timer(struct packet_sock *po, + int tx_ring, + struct sk_buff_head *rb_queue) +{ + struct tpacket_kbdq_core *pkc; + + pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc; + + spin_lock(&rb_queue->lock); + pkc->delete_blk_timer = 1; + spin_unlock(&rb_queue->lock); + + prb_del_retire_blk_timer(pkc); +} + +static void prb_init_blk_timer(struct packet_sock *po, + struct tpacket_kbdq_core *pkc, + void (*func) (unsigned long)) +{ + init_timer(&pkc->retire_blk_timer); + pkc->retire_blk_timer.data = (long)po; + pkc->retire_blk_timer.function = func; + pkc->retire_blk_timer.expires = jiffies; +} + +static void prb_setup_retire_blk_timer(struct packet_sock *po, int tx_ring) +{ + struct tpacket_kbdq_core *pkc; + + if (tx_ring) + BUG(); + + pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc; + prb_init_blk_timer(po, pkc, prb_retire_rx_blk_timer_expired); +} + +static int prb_calc_retire_blk_tmo(struct packet_sock *po, + int blk_size_in_bytes) +{ + struct net_device *dev; + unsigned int mbits = 0, msec = 0, div = 0, tmo = 0; + struct ethtool_cmd ecmd; + int err; + + rtnl_lock(); + dev = __dev_get_by_index(sock_net(&po->sk), po->ifindex); + if (unlikely(!dev)) { + rtnl_unlock(); + return DEFAULT_PRB_RETIRE_TOV; + } + err = __ethtool_get_settings(dev, &ecmd); + rtnl_unlock(); + if (!err) { + switch (ecmd.speed) { + case SPEED_10000: + msec = 1; + div = 10000/1000; + break; + case SPEED_1000: + msec = 1; + div = 1000/1000; + break; + /* + * If the link speed is so slow you don't really + * need to worry about perf anyways + */ + case SPEED_100: + case SPEED_10: + default: + return DEFAULT_PRB_RETIRE_TOV; + } + } + + mbits = (blk_size_in_bytes * 8) / (1024 * 1024); + + if (div) + mbits /= div; + + tmo = mbits * msec; + + if (div) + return tmo+1; + return tmo; +} + +static void prb_init_ft_ops(struct tpacket_kbdq_core *p1, + union tpacket_req_u *req_u) +{ + p1->feature_req_word = req_u->req3.tp_feature_req_word; +} + +static void init_prb_bdqc(struct packet_sock *po, + struct packet_ring_buffer *rb, + struct pgv *pg_vec, + union tpacket_req_u *req_u, int tx_ring) +{ + struct tpacket_kbdq_core *p1 = &rb->prb_bdqc; + struct tpacket_block_desc *pbd; + + memset(p1, 0x0, sizeof(*p1)); + + p1->knxt_seq_num = 1; + p1->pkbdq = pg_vec; + pbd = (struct tpacket_block_desc *)pg_vec[0].buffer; + p1->pkblk_start = (char *)pg_vec[0].buffer; + p1->kblk_size = req_u->req3.tp_block_size; + p1->knum_blocks = req_u->req3.tp_block_nr; + p1->hdrlen = po->tp_hdrlen; + p1->version = po->tp_version; + p1->last_kactive_blk_num = 0; + po->stats_u.stats3.tp_freeze_q_cnt = 0; + if (req_u->req3.tp_retire_blk_tov) + p1->retire_blk_tov = req_u->req3.tp_retire_blk_tov; + else + p1->retire_blk_tov = prb_calc_retire_blk_tmo(po, + req_u->req3.tp_block_size); + p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov); + p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; + + prb_init_ft_ops(p1, req_u); + prb_setup_retire_blk_timer(po, tx_ring); + prb_open_block(p1, pbd); +} + +/* Do NOT update the last_blk_num first. + * Assumes sk_buff_head lock is held. + */ +static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc) +{ + mod_timer(&pkc->retire_blk_timer, + jiffies + pkc->tov_in_jiffies); + pkc->last_kactive_blk_num = pkc->kactive_blk_num; +} + +/* + * Timer logic: + * 1) We refresh the timer only when we open a block. + * By doing this we don't waste cycles refreshing the timer + * on packet-by-packet basis. + * + * With a 1MB block-size, on a 1Gbps line, it will take + * i) ~8 ms to fill a block + ii) memcpy etc. + * In this cut we are not accounting for the memcpy time. + * + * So, if the user sets the 'tmo' to 10ms then the timer + * will never fire while the block is still getting filled + * (which is what we want). However, the user could choose + * to close a block early and that's fine. + * + * But when the timer does fire, we check whether or not to refresh it. + * Since the tmo granularity is in msecs, it is not too expensive + * to refresh the timer, lets say every '8' msecs. + * Either the user can set the 'tmo' or we can derive it based on + * a) line-speed and b) block-size. + * prb_calc_retire_blk_tmo() calculates the tmo. + * + */ +static void prb_retire_rx_blk_timer_expired(unsigned long data) +{ + struct packet_sock *po = (struct packet_sock *)data; + struct tpacket_kbdq_core *pkc = &po->rx_ring.prb_bdqc; + unsigned int frozen; + struct tpacket_block_desc *pbd; + + spin_lock(&po->sk.sk_receive_queue.lock); + + frozen = prb_queue_frozen(pkc); + pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); + + if (unlikely(pkc->delete_blk_timer)) + goto out; + + /* We only need to plug the race when the block is partially filled. + * tpacket_rcv: + * lock(); increment BLOCK_NUM_PKTS; unlock() + * copy_bits() is in progress ... + * timer fires on other cpu: + * we can't retire the current block because copy_bits + * is in progress. + * + */ + if (BLOCK_NUM_PKTS(pbd)) { + while (atomic_read(&pkc->blk_fill_in_prog)) { + /* Waiting for skb_copy_bits to finish... */ + cpu_relax(); + } + } + + if (pkc->last_kactive_blk_num == pkc->kactive_blk_num) { + if (!frozen) { + prb_retire_current_block(pkc, po, TP_STATUS_BLK_TMO); + if (!prb_dispatch_next_block(pkc, po)) + goto refresh_timer; + else + goto out; + } else { + /* Case 1. Queue was frozen because user-space was + * lagging behind. + */ + if (prb_curr_blk_in_use(pkc, pbd)) { + /* + * Ok, user-space is still behind. + * So just refresh the timer. + */ + goto refresh_timer; + } else { + /* Case 2. queue was frozen,user-space caught up, + * now the link went idle && the timer fired. + * We don't have a block to close.So we open this + * block and restart the timer. + * opening a block thaws the queue,restarts timer + * Thawing/timer-refresh is a side effect. + */ + prb_open_block(pkc, pbd); + goto out; + } + } + } + +refresh_timer: + _prb_refresh_rx_retire_blk_timer(pkc); + +out: + spin_unlock(&po->sk.sk_receive_queue.lock); +} + +static void prb_flush_block(struct tpacket_kbdq_core *pkc1, + struct tpacket_block_desc *pbd1, __u32 status) +{ + /* Flush everything minus the block header */ + +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 + u8 *start, *end; + + start = (u8 *)pbd1; + + /* Skip the block header(we know header WILL fit in 4K) */ + start += PAGE_SIZE; + + end = (u8 *)PAGE_ALIGN((unsigned long)pkc1->pkblk_end); + for (; start < end; start += PAGE_SIZE) + flush_dcache_page(pgv_to_page(start)); + + smp_wmb(); +#endif + + /* Now update the block status. */ + + BLOCK_STATUS(pbd1) = status; + + /* Flush the block header */ + +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 + start = (u8 *)pbd1; + flush_dcache_page(pgv_to_page(start)); + + smp_wmb(); +#endif +} + +/* + * Side effect: + * + * 1) flush the block + * 2) Increment active_blk_num + * + * Note:We DONT refresh the timer on purpose. + * Because almost always the next block will be opened. + */ +static void prb_close_block(struct tpacket_kbdq_core *pkc1, + struct tpacket_block_desc *pbd1, + struct packet_sock *po, unsigned int stat) +{ + __u32 status = TP_STATUS_USER | stat; + + struct tpacket3_hdr *last_pkt; + struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; + + if (po->stats.tp_drops) + status |= TP_STATUS_LOSING; + + last_pkt = (struct tpacket3_hdr *)pkc1->prev; + last_pkt->tp_next_offset = 0; + + /* Get the ts of the last pkt */ + if (BLOCK_NUM_PKTS(pbd1)) { + h1->ts_last_pkt.ts_sec = last_pkt->tp_sec; + h1->ts_last_pkt.ts_nsec = last_pkt->tp_nsec; + } else { + /* Ok, we tmo'd - so get the current time */ + struct timespec ts; + getnstimeofday(&ts); + h1->ts_last_pkt.ts_sec = ts.tv_sec; + h1->ts_last_pkt.ts_nsec = ts.tv_nsec; + } + + smp_wmb(); + + /* Flush the block */ + prb_flush_block(pkc1, pbd1, status); + + pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1); +} + +static void prb_thaw_queue(struct tpacket_kbdq_core *pkc) +{ + pkc->reset_pending_on_curr_blk = 0; +} + +/* + * Side effect of opening a block: + * + * 1) prb_queue is thawed. + * 2) retire_blk_timer is refreshed. + * + */ +static void prb_open_block(struct tpacket_kbdq_core *pkc1, + struct tpacket_block_desc *pbd1) +{ + struct timespec ts; + struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; + + smp_rmb(); + + if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd1))) { + + /* We could have just memset this but we will lose the + * flexibility of making the priv area sticky + */ + BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++; + BLOCK_NUM_PKTS(pbd1) = 0; + BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); + getnstimeofday(&ts); + h1->ts_first_pkt.ts_sec = ts.tv_sec; + h1->ts_first_pkt.ts_nsec = ts.tv_nsec; + pkc1->pkblk_start = (char *)pbd1; + pkc1->nxt_offset = (char *)(pkc1->pkblk_start + + BLK_PLUS_PRIV(pkc1->blk_sizeof_priv)); + BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); + BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN; + pbd1->version = pkc1->version; + pkc1->prev = pkc1->nxt_offset; + pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size; + prb_thaw_queue(pkc1); + _prb_refresh_rx_retire_blk_timer(pkc1); + + smp_wmb(); + + return; + } + + WARN(1, "ERROR block:%p is NOT FREE status:%d kactive_blk_num:%d\n", + pbd1, BLOCK_STATUS(pbd1), pkc1->kactive_blk_num); + dump_stack(); + BUG(); +} + +/* + * Queue freeze logic: + * 1) Assume tp_block_nr = 8 blocks. + * 2) At time 't0', user opens Rx ring. + * 3) Some time past 't0', kernel starts filling blocks starting from 0 .. 7 + * 4) user-space is either sleeping or processing block '0'. + * 5) tpacket_rcv is currently filling block '7', since there is no space left, + * it will close block-7,loop around and try to fill block '0'. + * call-flow: + * __packet_lookup_frame_in_block + * prb_retire_current_block() + * prb_dispatch_next_block() + * |->(BLOCK_STATUS == USER) evaluates to true + * 5.1) Since block-0 is currently in-use, we just freeze the queue. + * 6) Now there are two cases: + * 6.1) Link goes idle right after the queue is frozen. + * But remember, the last open_block() refreshed the timer. + * When this timer expires,it will refresh itself so that we can + * re-open block-0 in near future. + * 6.2) Link is busy and keeps on receiving packets. This is a simple + * case and __packet_lookup_frame_in_block will check if block-0 + * is free and can now be re-used. + */ +static void prb_freeze_queue(struct tpacket_kbdq_core *pkc, + struct packet_sock *po) +{ + pkc->reset_pending_on_curr_blk = 1; + po->stats_u.stats3.tp_freeze_q_cnt++; +} + +#define TOTAL_PKT_LEN_INCL_ALIGN(length) (ALIGN((length), V3_ALIGNMENT)) + +/* + * If the next block is free then we will dispatch it + * and return a good offset. + * Else, we will freeze the queue. + * So, caller must check the return value. + */ +static void *prb_dispatch_next_block(struct tpacket_kbdq_core *pkc, + struct packet_sock *po) +{ + struct tpacket_block_desc *pbd; + + smp_rmb(); + + /* 1. Get current block num */ + pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); + + /* 2. If this block is currently in_use then freeze the queue */ + if (TP_STATUS_USER & BLOCK_STATUS(pbd)) { + prb_freeze_queue(pkc, po); + return NULL; + } + + /* + * 3. + * open this block and return the offset where the first packet + * needs to get stored. + */ + prb_open_block(pkc, pbd); + return (void *)pkc->nxt_offset; +} + +static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, + struct packet_sock *po, unsigned int status) +{ + struct tpacket_block_desc *pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); + + /* retire/close the current block */ + if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd))) { + /* + * Plug the case where copy_bits() is in progress on + * cpu-0 and tpacket_rcv() got invoked on cpu-1, didn't + * have space to copy the pkt in the current block and + * called prb_retire_current_block() + * + * We don't need to worry about the TMO case because + * the timer-handler already handled this case. + */ + if (!(status & TP_STATUS_BLK_TMO)) { + while (atomic_read(&pkc->blk_fill_in_prog)) { + /* Waiting for skb_copy_bits to finish... */ + cpu_relax(); + } + } + prb_close_block(pkc, pbd, po, status); + return; + } + + WARN(1, "ERROR-pbd[%d]:%p\n", pkc->kactive_blk_num, pbd); + dump_stack(); + BUG(); +} + +static int prb_curr_blk_in_use(struct tpacket_kbdq_core *pkc, + struct tpacket_block_desc *pbd) +{ + return TP_STATUS_USER & BLOCK_STATUS(pbd); +} + +static int prb_queue_frozen(struct tpacket_kbdq_core *pkc) +{ + return pkc->reset_pending_on_curr_blk; +} + +static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb) +{ + struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); + atomic_dec(&pkc->blk_fill_in_prog); +} + +static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc, + struct tpacket3_hdr *ppd) +{ + ppd->hv1.tp_rxhash = skb_get_rxhash(pkc->skb); +} + +static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, + struct tpacket3_hdr *ppd) +{ + ppd->hv1.tp_rxhash = 0; +} + +static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, + struct tpacket3_hdr *ppd) +{ + if (vlan_tx_tag_present(pkc->skb)) { + ppd->hv1.tp_vlan_tci = vlan_tx_tag_get(pkc->skb); + ppd->tp_status = TP_STATUS_VLAN_VALID; + } else { + ppd->hv1.tp_vlan_tci = ppd->tp_status = 0; + } +} + +static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc, + struct tpacket3_hdr *ppd) +{ + prb_fill_vlan_info(pkc, ppd); + + if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH) + prb_fill_rxhash(pkc, ppd); + else + prb_clear_rxhash(pkc, ppd); +} + +static void prb_fill_curr_block(char *curr, + struct tpacket_kbdq_core *pkc, + struct tpacket_block_desc *pbd, + unsigned int len) +{ + struct tpacket3_hdr *ppd; + + ppd = (struct tpacket3_hdr *)curr; + ppd->tp_next_offset = TOTAL_PKT_LEN_INCL_ALIGN(len); + pkc->prev = curr; + pkc->nxt_offset += TOTAL_PKT_LEN_INCL_ALIGN(len); + BLOCK_LEN(pbd) += TOTAL_PKT_LEN_INCL_ALIGN(len); + BLOCK_NUM_PKTS(pbd) += 1; + atomic_inc(&pkc->blk_fill_in_prog); + prb_run_all_ft_ops(pkc, ppd); +} + +/* Assumes caller has the sk->rx_queue.lock */ +static void *__packet_lookup_frame_in_block(struct packet_sock *po, + struct sk_buff *skb, + int status, + unsigned int len + ) +{ + struct tpacket_kbdq_core *pkc; + struct tpacket_block_desc *pbd; + char *curr, *end; + + pkc = GET_PBDQC_FROM_RB(((struct packet_ring_buffer *)&po->rx_ring)); + pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); + + /* Queue is frozen when user space is lagging behind */ + if (prb_queue_frozen(pkc)) { + /* + * Check if that last block which caused the queue to freeze, + * is still in_use by user-space. + */ + if (prb_curr_blk_in_use(pkc, pbd)) { + /* Can't record this packet */ + return NULL; + } else { + /* + * Ok, the block was released by user-space. + * Now let's open that block. + * opening a block also thaws the queue. + * Thawing is a side effect. + */ + prb_open_block(pkc, pbd); + } + } + + smp_mb(); + curr = pkc->nxt_offset; + pkc->skb = skb; + end = (char *) ((char *)pbd + pkc->kblk_size); + + /* first try the current block */ + if (curr+TOTAL_PKT_LEN_INCL_ALIGN(len) < end) { + prb_fill_curr_block(curr, pkc, pbd, len); + return (void *)curr; + } + + /* Ok, close the current block */ + prb_retire_current_block(pkc, po, 0); + + /* Now, try to dispatch the next block */ + curr = (char *)prb_dispatch_next_block(pkc, po); + if (curr) { + pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); + prb_fill_curr_block(curr, pkc, pbd, len); + return (void *)curr; + } + + /* + * No free blocks are available.user_space hasn't caught up yet. + * Queue was just frozen and now this packet will get dropped. + */ + return NULL; +} + +static void *packet_current_rx_frame(struct packet_sock *po, + struct sk_buff *skb, + int status, unsigned int len) +{ + char *curr = NULL; + switch (po->tp_version) { + case TPACKET_V1: + case TPACKET_V2: + curr = packet_lookup_frame(po, &po->rx_ring, + po->rx_ring.head, status); + return curr; + case TPACKET_V3: + return __packet_lookup_frame_in_block(po, skb, status, len); + default: + WARN(1, "TPACKET version not supported\n"); + BUG(); + return 0; + } +} + +static void *prb_lookup_block(struct packet_sock *po, + struct packet_ring_buffer *rb, + unsigned int previous, + int status) +{ + struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); + struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, previous); + + if (status != BLOCK_STATUS(pbd)) + return NULL; + return pbd; +} + +static int prb_previous_blk_num(struct packet_ring_buffer *rb) +{ + unsigned int prev; + if (rb->prb_bdqc.kactive_blk_num) + prev = rb->prb_bdqc.kactive_blk_num-1; + else + prev = rb->prb_bdqc.knum_blocks-1; + return prev; +} + +/* Assumes caller has held the rx_queue.lock */ +static void *__prb_previous_block(struct packet_sock *po, + struct packet_ring_buffer *rb, + int status) +{ + unsigned int previous = prb_previous_blk_num(rb); + return prb_lookup_block(po, rb, previous, status); +} + +static void *packet_previous_rx_frame(struct packet_sock *po, + struct packet_ring_buffer *rb, + int status) +{ + if (po->tp_version <= TPACKET_V2) + return packet_previous_frame(po, rb, status); + + return __prb_previous_block(po, rb, status); +} + +static void packet_increment_rx_head(struct packet_sock *po, + struct packet_ring_buffer *rb) +{ + switch (po->tp_version) { + case TPACKET_V1: + case TPACKET_V2: + return packet_increment_head(rb); + case TPACKET_V3: + default: + WARN(1, "TPACKET version not supported.\n"); + BUG(); + return; + } +} + +static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { @@ -397,7 +1156,7 @@ static inline void *packet_previous_frame(struct packet_sock *po, return packet_lookup_frame(po, rb, previous, status); } -static inline void packet_increment_head(struct packet_ring_buffer *buff) +static void packet_increment_head(struct packet_ring_buffer *buff) { buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; } @@ -454,43 +1213,6 @@ static struct sock *fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *sk return f->arr[cpu % num]; } -static struct sk_buff *fanout_check_defrag(struct sk_buff *skb) -{ -#ifdef CONFIG_INET - const struct iphdr *iph; - u32 len; - - if (skb->protocol != htons(ETH_P_IP)) - return skb; - - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - return skb; - - iph = ip_hdr(skb); - if (iph->ihl < 5 || iph->version != 4) - return skb; - if (!pskb_may_pull(skb, iph->ihl*4)) - return skb; - iph = ip_hdr(skb); - len = ntohs(iph->tot_len); - if (skb->len < len || len < (iph->ihl * 4)) - return skb; - - if (ip_is_fragment(ip_hdr(skb))) { - skb = skb_share_check(skb, GFP_ATOMIC); - if (skb) { - if (pskb_trim_rcsum(skb, len)) - return skb; - memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); - if (ip_defrag(skb, IP_DEFRAG_AF_PACKET)) - return NULL; - skb->rxhash = 0; - } - } -#endif - return skb; -} - static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { @@ -509,7 +1231,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, case PACKET_FANOUT_HASH: default: if (f->defrag) { - skb = fanout_check_defrag(skb); + skb = ip_check_defrag(skb, IP_DEFRAG_AF_PACKET); if (!skb) return 0; } @@ -836,7 +1558,7 @@ out_free: return err; } -static inline unsigned int run_filter(const struct sk_buff *skb, +static unsigned int run_filter(const struct sk_buff *skb, const struct sock *sk, unsigned int res) { @@ -961,7 +1683,10 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, return 0; drop_n_acct: - po->stats.tp_drops = atomic_inc_return(&sk->sk_drops); + spin_lock(&sk->sk_receive_queue.lock); + po->stats.tp_drops++; + atomic_inc(&sk->sk_drops); + spin_unlock(&sk->sk_receive_queue.lock); drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { @@ -982,12 +1707,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, union { struct tpacket_hdr *h1; struct tpacket2_hdr *h2; + struct tpacket3_hdr *h3; void *raw; } h; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; - unsigned long status = TP_STATUS_LOSING|TP_STATUS_USER; + unsigned long status = TP_STATUS_USER; unsigned short macoff, netoff, hdrlen; struct sk_buff *copy_skb = NULL; struct timeval tv; @@ -1033,37 +1759,46 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, po->tp_reserve; macoff = netoff - maclen; } - - if (macoff + snaplen > po->rx_ring.frame_size) { - if (po->copy_thresh && - atomic_read(&sk->sk_rmem_alloc) + skb->truesize < - (unsigned)sk->sk_rcvbuf) { - if (skb_shared(skb)) { - copy_skb = skb_clone(skb, GFP_ATOMIC); - } else { - copy_skb = skb_get(skb); - skb_head = skb->data; + if (po->tp_version <= TPACKET_V2) { + if (macoff + snaplen > po->rx_ring.frame_size) { + if (po->copy_thresh && + atomic_read(&sk->sk_rmem_alloc) + skb->truesize + < (unsigned)sk->sk_rcvbuf) { + if (skb_shared(skb)) { + copy_skb = skb_clone(skb, GFP_ATOMIC); + } else { + copy_skb = skb_get(skb); + skb_head = skb->data; + } + if (copy_skb) + skb_set_owner_r(copy_skb, sk); } - if (copy_skb) - skb_set_owner_r(copy_skb, sk); + snaplen = po->rx_ring.frame_size - macoff; + if ((int)snaplen < 0) + snaplen = 0; } - snaplen = po->rx_ring.frame_size - macoff; - if ((int)snaplen < 0) - snaplen = 0; } - spin_lock(&sk->sk_receive_queue.lock); - h.raw = packet_current_frame(po, &po->rx_ring, TP_STATUS_KERNEL); + h.raw = packet_current_rx_frame(po, skb, + TP_STATUS_KERNEL, (macoff+snaplen)); if (!h.raw) goto ring_is_full; - packet_increment_head(&po->rx_ring); + if (po->tp_version <= TPACKET_V2) { + packet_increment_rx_head(po, &po->rx_ring); + /* + * LOSING will be reported till you read the stats, + * because it's COR - Clear On Read. + * Anyways, moving it for V1/V2 only as V3 doesn't need this + * at packet level. + */ + if (po->stats.tp_drops) + status |= TP_STATUS_LOSING; + } po->stats.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; __skb_queue_tail(&sk->sk_receive_queue, copy_skb); } - if (!po->stats.tp_drops) - status &= ~TP_STATUS_LOSING; spin_unlock(&sk->sk_receive_queue.lock); skb_copy_bits(skb, 0, h.raw + macoff, snaplen); @@ -1114,6 +1849,29 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h2->tp_padding = 0; hdrlen = sizeof(*h.h2); break; + case TPACKET_V3: + /* tp_nxt_offset,vlan are already populated above. + * So DONT clear those fields here + */ + h.h3->tp_status |= status; + h.h3->tp_len = skb->len; + h.h3->tp_snaplen = snaplen; + h.h3->tp_mac = macoff; + h.h3->tp_net = netoff; + if ((po->tp_tstamp & SOF_TIMESTAMPING_SYS_HARDWARE) + && shhwtstamps->syststamp.tv64) + ts = ktime_to_timespec(shhwtstamps->syststamp); + else if ((po->tp_tstamp & SOF_TIMESTAMPING_RAW_HARDWARE) + && shhwtstamps->hwtstamp.tv64) + ts = ktime_to_timespec(shhwtstamps->hwtstamp); + else if (skb->tstamp.tv64) + ts = ktime_to_timespec(skb->tstamp); + else + getnstimeofday(&ts); + h.h3->tp_sec = ts.tv_sec; + h.h3->tp_nsec = ts.tv_nsec; + hdrlen = sizeof(*h.h3); + break; default: BUG(); } @@ -1134,13 +1892,19 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, { u8 *start, *end; - end = (u8 *)PAGE_ALIGN((unsigned long)h.raw + macoff + snaplen); - for (start = h.raw; start < end; start += PAGE_SIZE) - flush_dcache_page(pgv_to_page(start)); + if (po->tp_version <= TPACKET_V2) { + end = (u8 *)PAGE_ALIGN((unsigned long)h.raw + + macoff + snaplen); + for (start = h.raw; start < end; start += PAGE_SIZE) + flush_dcache_page(pgv_to_page(start)); + } smp_wmb(); } #endif - __packet_set_status(po, h.raw, status); + if (po->tp_version <= TPACKET_V2) + __packet_set_status(po, h.raw, status); + else + prb_clear_blk_fill_status(&po->rx_ring); sk->sk_data_ready(sk, 0); @@ -1167,8 +1931,6 @@ static void tpacket_destruct_skb(struct sk_buff *skb) struct packet_sock *po = pkt_sk(skb->sk); void *ph; - BUG_ON(skb == NULL); - if (likely(po->tx_ring.pg_vec)) { ph = skb_shinfo(skb)->destructor_arg; BUG_ON(__packet_get_status(po, ph) != TP_STATUS_SENDING); @@ -1405,10 +2167,10 @@ out: return err; } -static inline struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad, - size_t reserve, size_t len, - size_t linear, int noblock, - int *err) +static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad, + size_t reserve, size_t len, + size_t linear, int noblock, + int *err) { struct sk_buff *skb; @@ -1631,7 +2393,7 @@ static int packet_release(struct socket *sock) struct sock *sk = sock->sk; struct packet_sock *po; struct net *net; - struct tpacket_req req; + union tpacket_req_u req_u; if (!sk) return 0; @@ -1654,13 +2416,13 @@ static int packet_release(struct socket *sock) packet_flush_mclist(sk); - memset(&req, 0, sizeof(req)); + memset(&req_u, 0, sizeof(req_u)); if (po->rx_ring.pg_vec) - packet_set_ring(sk, &req, 1, 0); + packet_set_ring(sk, &req_u, 1, 0); if (po->tx_ring.pg_vec) - packet_set_ring(sk, &req, 1, 1); + packet_set_ring(sk, &req_u, 1, 1); fanout_release(sk); @@ -2280,15 +3042,27 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv case PACKET_RX_RING: case PACKET_TX_RING: { - struct tpacket_req req; + union tpacket_req_u req_u; + int len; - if (optlen < sizeof(req)) + switch (po->tp_version) { + case TPACKET_V1: + case TPACKET_V2: + len = sizeof(req_u.req); + break; + case TPACKET_V3: + default: + len = sizeof(req_u.req3); + break; + } + if (optlen < len) return -EINVAL; if (pkt_sk(sk)->has_vnet_hdr) return -EINVAL; - if (copy_from_user(&req, optval, sizeof(req))) + if (copy_from_user(&req_u.req, optval, len)) return -EFAULT; - return packet_set_ring(sk, &req, 0, optname == PACKET_TX_RING); + return packet_set_ring(sk, &req_u, 0, + optname == PACKET_TX_RING); } case PACKET_COPY_THRESH: { @@ -2315,6 +3089,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv switch (val) { case TPACKET_V1: case TPACKET_V2: + case TPACKET_V3: po->tp_version = val; return 0; default: @@ -2424,6 +3199,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, struct packet_sock *po = pkt_sk(sk); void *data; struct tpacket_stats st; + union tpacket_stats_u st_u; if (level != SOL_PACKET) return -ENOPROTOOPT; @@ -2436,15 +3212,27 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, switch (optname) { case PACKET_STATISTICS: - if (len > sizeof(struct tpacket_stats)) - len = sizeof(struct tpacket_stats); + if (po->tp_version == TPACKET_V3) { + len = sizeof(struct tpacket_stats_v3); + } else { + if (len > sizeof(struct tpacket_stats)) + len = sizeof(struct tpacket_stats); + } spin_lock_bh(&sk->sk_receive_queue.lock); - st = po->stats; + if (po->tp_version == TPACKET_V3) { + memcpy(&st_u.stats3, &po->stats, + sizeof(struct tpacket_stats)); + st_u.stats3.tp_freeze_q_cnt = + po->stats_u.stats3.tp_freeze_q_cnt; + st_u.stats3.tp_packets += po->stats.tp_drops; + data = &st_u.stats3; + } else { + st = po->stats; + st.tp_packets += st.tp_drops; + data = &st; + } memset(&po->stats, 0, sizeof(st)); spin_unlock_bh(&sk->sk_receive_queue.lock); - st.tp_packets += st.tp_drops; - - data = &st; break; case PACKET_AUXDATA: if (len > sizeof(int)) @@ -2485,6 +3273,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, case TPACKET_V2: val = sizeof(struct tpacket2_hdr); break; + case TPACKET_V3: + val = sizeof(struct tpacket3_hdr); + break; default: return -EINVAL; } @@ -2641,7 +3432,8 @@ static unsigned int packet_poll(struct file *file, struct socket *sock, spin_lock_bh(&sk->sk_receive_queue.lock); if (po->rx_ring.pg_vec) { - if (!packet_previous_frame(po, &po->rx_ring, TP_STATUS_KERNEL)) + if (!packet_previous_rx_frame(po, &po->rx_ring, + TP_STATUS_KERNEL)) mask |= POLLIN | POLLRDNORM; } spin_unlock_bh(&sk->sk_receive_queue.lock); @@ -2702,7 +3494,7 @@ static void free_pg_vec(struct pgv *pg_vec, unsigned int order, kfree(pg_vec); } -static inline char *alloc_one_pg_vec_page(unsigned long order) +static char *alloc_one_pg_vec_page(unsigned long order) { char *buffer = NULL; gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | @@ -2760,7 +3552,7 @@ out_free_pgvec: goto out; } -static int packet_set_ring(struct sock *sk, struct tpacket_req *req, +static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring) { struct pgv *pg_vec = NULL; @@ -2769,7 +3561,15 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, struct packet_ring_buffer *rb; struct sk_buff_head *rb_queue; __be16 num; - int err; + int err = -EINVAL; + /* Added to avoid minimal code churn */ + struct tpacket_req *req = &req_u->req; + + /* Opening a Tx-ring is NOT supported in TPACKET_V3 */ + if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) { + WARN(1, "Tx-ring is not supported.\n"); + goto out; + } rb = tx_ring ? &po->tx_ring : &po->rx_ring; rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; @@ -2795,6 +3595,9 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, case TPACKET_V2: po->tp_hdrlen = TPACKET2_HDRLEN; break; + case TPACKET_V3: + po->tp_hdrlen = TPACKET3_HDRLEN; + break; } err = -EINVAL; @@ -2820,6 +3623,17 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, pg_vec = alloc_pg_vec(req, order); if (unlikely(!pg_vec)) goto out; + switch (po->tp_version) { + case TPACKET_V3: + /* Transmit path is not supported. We checked + * it above but just being paranoid + */ + if (!tx_ring) + init_prb_bdqc(po, rb, pg_vec, req_u, tx_ring); + break; + default: + break; + } } /* Done */ else { @@ -2872,7 +3686,11 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, register_prot_hook(sk); } spin_unlock(&po->bind_lock); - + if (closing && (po->tp_version > TPACKET_V2)) { + /* Because we don't support block-based V3 on tx-ring */ + if (!tx_ring) + prb_shutdown_retire_blk_timer(po, tx_ring, rb_queue); + } release_sock(sk); if (pg_vec) diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index c6fffd9..bf10ea8 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -480,7 +480,7 @@ int __init_or_module phonet_proto_register(unsigned int protocol, if (proto_tab[protocol]) err = -EBUSY; else - rcu_assign_pointer(proto_tab[protocol], pp); + RCU_INIT_POINTER(proto_tab[protocol], pp); mutex_unlock(&proto_tab_lock); return err; @@ -491,7 +491,7 @@ void phonet_proto_unregister(unsigned int protocol, struct phonet_protocol *pp) { mutex_lock(&proto_tab_lock); BUG_ON(proto_tab[protocol] != pp); - rcu_assign_pointer(proto_tab[protocol], NULL); + RCU_INIT_POINTER(proto_tab[protocol], NULL); mutex_unlock(&proto_tab_lock); synchronize_rcu(); proto_unregister(pp->prot); diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index d2df8f3..c582761 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -276,7 +276,7 @@ static void phonet_route_autodel(struct net_device *dev) mutex_lock(&pnn->routes.lock); for (i = 0; i < 64; i++) if (dev == pnn->routes.table[i]) { - rcu_assign_pointer(pnn->routes.table[i], NULL); + RCU_INIT_POINTER(pnn->routes.table[i], NULL); set_bit(i, deleted); } mutex_unlock(&pnn->routes.lock); @@ -390,7 +390,7 @@ int phonet_route_add(struct net_device *dev, u8 daddr) daddr = daddr >> 2; mutex_lock(&routes->lock); if (routes->table[daddr] == NULL) { - rcu_assign_pointer(routes->table[daddr], dev); + RCU_INIT_POINTER(routes->table[daddr], dev); dev_hold(dev); err = 0; } @@ -406,7 +406,7 @@ int phonet_route_del(struct net_device *dev, u8 daddr) daddr = daddr >> 2; mutex_lock(&routes->lock); if (dev == routes->table[daddr]) - rcu_assign_pointer(routes->table[daddr], NULL); + RCU_INIT_POINTER(routes->table[daddr], NULL); else dev = NULL; mutex_unlock(&routes->lock); diff --git a/net/phonet/socket.c b/net/phonet/socket.c index ab07711..676d18d 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -679,7 +679,7 @@ int pn_sock_bind_res(struct sock *sk, u8 res) mutex_lock(&resource_mutex); if (pnres.sk[res] == NULL) { sock_hold(sk); - rcu_assign_pointer(pnres.sk[res], sk); + RCU_INIT_POINTER(pnres.sk[res], sk); ret = 0; } mutex_unlock(&resource_mutex); @@ -695,7 +695,7 @@ int pn_sock_unbind_res(struct sock *sk, u8 res) mutex_lock(&resource_mutex); if (pnres.sk[res] == sk) { - rcu_assign_pointer(pnres.sk[res], NULL); + RCU_INIT_POINTER(pnres.sk[res], NULL); ret = 0; } mutex_unlock(&resource_mutex); @@ -714,7 +714,7 @@ void pn_sock_unbind_all_res(struct sock *sk) mutex_lock(&resource_mutex); for (res = 0; res < 256; res++) { if (pnres.sk[res] == sk) { - rcu_assign_pointer(pnres.sk[res], NULL); + RCU_INIT_POINTER(pnres.sk[res], NULL); match++; } } diff --git a/net/rds/Kconfig b/net/rds/Kconfig index ec753b3..4cf6dc7 100644 --- a/net/rds/Kconfig +++ b/net/rds/Kconfig @@ -9,6 +9,7 @@ config RDS config RDS_RDMA tristate "RDS over Infiniband and iWARP" + select LLIST depends on RDS && INFINIBAND && INFINIBAND_ADDR_TRANS ---help--- Allow RDS to use Infiniband and iWARP as a transport. diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index cd67026..51c8689 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -375,23 +375,21 @@ static int rds_ib_setup_qp(struct rds_connection *conn) goto out; } - ic->i_sends = vmalloc_node(ic->i_send_ring.w_nr * sizeof(struct rds_ib_send_work), + ic->i_sends = vzalloc_node(ic->i_send_ring.w_nr * sizeof(struct rds_ib_send_work), ibdev_to_node(dev)); if (!ic->i_sends) { ret = -ENOMEM; rdsdebug("send allocation failed\n"); goto out; } - memset(ic->i_sends, 0, ic->i_send_ring.w_nr * sizeof(struct rds_ib_send_work)); - ic->i_recvs = vmalloc_node(ic->i_recv_ring.w_nr * sizeof(struct rds_ib_recv_work), + ic->i_recvs = vzalloc_node(ic->i_recv_ring.w_nr * sizeof(struct rds_ib_recv_work), ibdev_to_node(dev)); if (!ic->i_recvs) { ret = -ENOMEM; rdsdebug("recv allocation failed\n"); goto out; } - memset(ic->i_recvs, 0, ic->i_recv_ring.w_nr * sizeof(struct rds_ib_recv_work)); rds_ib_recv_init_ack(ic); diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 819c35a..e8fdb17 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -33,10 +33,10 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/rculist.h> +#include <linux/llist.h> #include "rds.h" #include "ib.h" -#include "xlist.h" static DEFINE_PER_CPU(unsigned long, clean_list_grace); #define CLEAN_LIST_BUSY_BIT 0 @@ -49,7 +49,7 @@ struct rds_ib_mr { struct rds_ib_mr_pool *pool; struct ib_fmr *fmr; - struct xlist_head xlist; + struct llist_node llnode; /* unmap_list is for freeing */ struct list_head unmap_list; @@ -71,9 +71,9 @@ struct rds_ib_mr_pool { atomic_t item_count; /* total # of MRs */ atomic_t dirty_count; /* # dirty of MRs */ - struct xlist_head drop_list; /* MRs that have reached their max_maps limit */ - struct xlist_head free_list; /* unused MRs */ - struct xlist_head clean_list; /* global unused & unamapped MRs */ + struct llist_head drop_list; /* MRs that have reached their max_maps limit */ + struct llist_head free_list; /* unused MRs */ + struct llist_head clean_list; /* global unused & unamapped MRs */ wait_queue_head_t flush_wait; atomic_t free_pinned; /* memory pinned by free MRs */ @@ -220,9 +220,9 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev) if (!pool) return ERR_PTR(-ENOMEM); - INIT_XLIST_HEAD(&pool->free_list); - INIT_XLIST_HEAD(&pool->drop_list); - INIT_XLIST_HEAD(&pool->clean_list); + init_llist_head(&pool->free_list); + init_llist_head(&pool->drop_list); + init_llist_head(&pool->clean_list); mutex_init(&pool->flush_lock); init_waitqueue_head(&pool->flush_wait); INIT_DELAYED_WORK(&pool->flush_worker, rds_ib_mr_pool_flush_worker); @@ -260,26 +260,18 @@ void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *pool) kfree(pool); } -static void refill_local(struct rds_ib_mr_pool *pool, struct xlist_head *xl, - struct rds_ib_mr **ibmr_ret) -{ - struct xlist_head *ibmr_xl; - ibmr_xl = xlist_del_head_fast(xl); - *ibmr_ret = list_entry(ibmr_xl, struct rds_ib_mr, xlist); -} - static inline struct rds_ib_mr *rds_ib_reuse_fmr(struct rds_ib_mr_pool *pool) { struct rds_ib_mr *ibmr = NULL; - struct xlist_head *ret; + struct llist_node *ret; unsigned long *flag; preempt_disable(); flag = &__get_cpu_var(clean_list_grace); set_bit(CLEAN_LIST_BUSY_BIT, flag); - ret = xlist_del_head(&pool->clean_list); + ret = llist_del_first(&pool->clean_list); if (ret) - ibmr = list_entry(ret, struct rds_ib_mr, xlist); + ibmr = llist_entry(ret, struct rds_ib_mr, llnode); clear_bit(CLEAN_LIST_BUSY_BIT, flag); preempt_enable(); @@ -529,46 +521,44 @@ static inline unsigned int rds_ib_flush_goal(struct rds_ib_mr_pool *pool, int fr } /* - * given an xlist of mrs, put them all into the list_head for more processing + * given an llist of mrs, put them all into the list_head for more processing */ -static void xlist_append_to_list(struct xlist_head *xlist, struct list_head *list) +static void llist_append_to_list(struct llist_head *llist, struct list_head *list) { struct rds_ib_mr *ibmr; - struct xlist_head splice; - struct xlist_head *cur; - struct xlist_head *next; - - splice.next = NULL; - xlist_splice(xlist, &splice); - cur = splice.next; - while (cur) { - next = cur->next; - ibmr = list_entry(cur, struct rds_ib_mr, xlist); + struct llist_node *node; + struct llist_node *next; + + node = llist_del_all(llist); + while (node) { + next = node->next; + ibmr = llist_entry(node, struct rds_ib_mr, llnode); list_add_tail(&ibmr->unmap_list, list); - cur = next; + node = next; } } /* - * this takes a list head of mrs and turns it into an xlist of clusters. - * each cluster has an xlist of MR_CLUSTER_SIZE mrs that are ready for - * reuse. + * this takes a list head of mrs and turns it into linked llist nodes + * of clusters. Each cluster has linked llist nodes of + * MR_CLUSTER_SIZE mrs that are ready for reuse. */ -static void list_append_to_xlist(struct rds_ib_mr_pool *pool, - struct list_head *list, struct xlist_head *xlist, - struct xlist_head **tail_ret) +static void list_to_llist_nodes(struct rds_ib_mr_pool *pool, + struct list_head *list, + struct llist_node **nodes_head, + struct llist_node **nodes_tail) { struct rds_ib_mr *ibmr; - struct xlist_head *cur_mr = xlist; - struct xlist_head *tail_mr = NULL; + struct llist_node *cur = NULL; + struct llist_node **next = nodes_head; list_for_each_entry(ibmr, list, unmap_list) { - tail_mr = &ibmr->xlist; - tail_mr->next = NULL; - cur_mr->next = tail_mr; - cur_mr = tail_mr; + cur = &ibmr->llnode; + *next = cur; + next = &cur->next; } - *tail_ret = tail_mr; + *next = NULL; + *nodes_tail = cur; } /* @@ -581,8 +571,8 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool, int free_all, struct rds_ib_mr **ibmr_ret) { struct rds_ib_mr *ibmr, *next; - struct xlist_head clean_xlist; - struct xlist_head *clean_tail; + struct llist_node *clean_nodes; + struct llist_node *clean_tail; LIST_HEAD(unmap_list); LIST_HEAD(fmr_list); unsigned long unpinned = 0; @@ -603,7 +593,7 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool, prepare_to_wait(&pool->flush_wait, &wait, TASK_UNINTERRUPTIBLE); - if (xlist_empty(&pool->clean_list)) + if (llist_empty(&pool->clean_list)) schedule(); ibmr = rds_ib_reuse_fmr(pool); @@ -628,10 +618,10 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool, /* Get the list of all MRs to be dropped. Ordering matters - * we want to put drop_list ahead of free_list. */ - xlist_append_to_list(&pool->drop_list, &unmap_list); - xlist_append_to_list(&pool->free_list, &unmap_list); + llist_append_to_list(&pool->drop_list, &unmap_list); + llist_append_to_list(&pool->free_list, &unmap_list); if (free_all) - xlist_append_to_list(&pool->clean_list, &unmap_list); + llist_append_to_list(&pool->clean_list, &unmap_list); free_goal = rds_ib_flush_goal(pool, free_all); @@ -663,22 +653,22 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool, if (!list_empty(&unmap_list)) { /* we have to make sure that none of the things we're about * to put on the clean list would race with other cpus trying - * to pull items off. The xlist would explode if we managed to + * to pull items off. The llist would explode if we managed to * remove something from the clean list and then add it back again - * while another CPU was spinning on that same item in xlist_del_head. + * while another CPU was spinning on that same item in llist_del_first. * - * This is pretty unlikely, but just in case wait for an xlist grace period + * This is pretty unlikely, but just in case wait for an llist grace period * here before adding anything back into the clean list. */ wait_clean_list_grace(); - list_append_to_xlist(pool, &unmap_list, &clean_xlist, &clean_tail); + list_to_llist_nodes(pool, &unmap_list, &clean_nodes, &clean_tail); if (ibmr_ret) - refill_local(pool, &clean_xlist, ibmr_ret); + *ibmr_ret = llist_entry(clean_nodes, struct rds_ib_mr, llnode); - /* refill_local may have emptied our list */ - if (!xlist_empty(&clean_xlist)) - xlist_add(clean_xlist.next, clean_tail, &pool->clean_list); + /* more than one entry in llist nodes */ + if (clean_nodes->next) + llist_add_batch(clean_nodes->next, clean_tail, &pool->clean_list); } @@ -711,9 +701,9 @@ void rds_ib_free_mr(void *trans_private, int invalidate) /* Return it to the pool's free list */ if (ibmr->remap_count >= pool->fmr_attr.max_maps) - xlist_add(&ibmr->xlist, &ibmr->xlist, &pool->drop_list); + llist_add(&ibmr->llnode, &pool->drop_list); else - xlist_add(&ibmr->xlist, &ibmr->xlist, &pool->free_list); + llist_add(&ibmr->llnode, &pool->free_list); atomic_add(ibmr->sg_len, &pool->free_pinned); atomic_inc(&pool->dirty_count); diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index 8b77edb..4e1de17 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -84,7 +84,8 @@ static int rds_iw_map_fastreg(struct rds_iw_mr_pool *pool, static void rds_iw_free_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr); static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool, struct list_head *unmap_list, - struct list_head *kill_list); + struct list_head *kill_list, + int *unpinned); static void rds_iw_destroy_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr); static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwdev, struct rdma_cm_id **cm_id) @@ -499,7 +500,7 @@ static int rds_iw_flush_mr_pool(struct rds_iw_mr_pool *pool, int free_all) LIST_HEAD(unmap_list); LIST_HEAD(kill_list); unsigned long flags; - unsigned int nfreed = 0, ncleaned = 0, free_goal; + unsigned int nfreed = 0, ncleaned = 0, unpinned = 0, free_goal; int ret = 0; rds_iw_stats_inc(s_iw_rdma_mr_pool_flush); @@ -524,7 +525,8 @@ static int rds_iw_flush_mr_pool(struct rds_iw_mr_pool *pool, int free_all) * will be destroyed by the unmap function. */ if (!list_empty(&unmap_list)) { - ncleaned = rds_iw_unmap_fastreg_list(pool, &unmap_list, &kill_list); + ncleaned = rds_iw_unmap_fastreg_list(pool, &unmap_list, + &kill_list, &unpinned); /* If we've been asked to destroy all MRs, move those * that were simply cleaned to the kill list */ if (free_all) @@ -548,6 +550,7 @@ static int rds_iw_flush_mr_pool(struct rds_iw_mr_pool *pool, int free_all) spin_unlock_irqrestore(&pool->list_lock, flags); } + atomic_sub(unpinned, &pool->free_pinned); atomic_sub(ncleaned, &pool->dirty_count); atomic_sub(nfreed, &pool->item_count); @@ -828,7 +831,8 @@ static void rds_iw_free_fastreg(struct rds_iw_mr_pool *pool, static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool, struct list_head *unmap_list, - struct list_head *kill_list) + struct list_head *kill_list, + int *unpinned) { struct rds_iw_mapping *mapping, *next; unsigned int ncleaned = 0; @@ -855,6 +859,7 @@ static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool, spin_lock_irqsave(&pool->list_lock, flags); list_for_each_entry_safe(mapping, next, unmap_list, m_list) { + *unpinned += mapping->m_sg.len; list_move(&mapping->m_list, &laundered); ncleaned++; } diff --git a/net/rds/rds.h b/net/rds/rds.h index da8adac..7eaba18 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -36,8 +36,8 @@ #define rdsdebug(fmt, args...) pr_debug("%s(): " fmt, __func__ , ##args) #else /* sigh, pr_debug() causes unused variable warnings */ -static inline void __attribute__ ((format (printf, 1, 2))) -rdsdebug(char *fmt, ...) +static inline __printf(1, 2) +void rdsdebug(char *fmt, ...) { } #endif @@ -625,8 +625,8 @@ void rds_for_each_conn_info(struct socket *sock, unsigned int len, struct rds_info_lengths *lens, int (*visitor)(struct rds_connection *, void *), size_t item_len); -void __rds_conn_error(struct rds_connection *conn, const char *, ...) - __attribute__ ((format (printf, 2, 3))); +__printf(2, 3) +void __rds_conn_error(struct rds_connection *conn, const char *, ...); #define rds_conn_error(conn, fmt...) \ __rds_conn_error(conn, KERN_WARNING "RDS: " fmt) diff --git a/net/rds/xlist.h b/net/rds/xlist.h deleted file mode 100644 index e6b5190..0000000 --- a/net/rds/xlist.h +++ /dev/null @@ -1,80 +0,0 @@ -#ifndef _LINUX_XLIST_H -#define _LINUX_XLIST_H - -#include <linux/stddef.h> -#include <linux/poison.h> -#include <linux/prefetch.h> -#include <asm/system.h> - -struct xlist_head { - struct xlist_head *next; -}; - -static inline void INIT_XLIST_HEAD(struct xlist_head *list) -{ - list->next = NULL; -} - -static inline int xlist_empty(struct xlist_head *head) -{ - return head->next == NULL; -} - -static inline void xlist_add(struct xlist_head *new, struct xlist_head *tail, - struct xlist_head *head) -{ - struct xlist_head *cur; - struct xlist_head *check; - - while (1) { - cur = head->next; - tail->next = cur; - check = cmpxchg(&head->next, cur, new); - if (check == cur) - break; - } -} - -static inline struct xlist_head *xlist_del_head(struct xlist_head *head) -{ - struct xlist_head *cur; - struct xlist_head *check; - struct xlist_head *next; - - while (1) { - cur = head->next; - if (!cur) - goto out; - - next = cur->next; - check = cmpxchg(&head->next, cur, next); - if (check == cur) - goto out; - } -out: - return cur; -} - -static inline struct xlist_head *xlist_del_head_fast(struct xlist_head *head) -{ - struct xlist_head *cur; - - cur = head->next; - if (!cur) - return NULL; - - head->next = cur->next; - return cur; -} - -static inline void xlist_splice(struct xlist_head *list, - struct xlist_head *head) -{ - struct xlist_head *cur; - - WARN_ON(head->next); - cur = xchg(&list->next, NULL); - head->next = cur; -} - -#endif diff --git a/net/rfkill/core.c b/net/rfkill/core.c index be90640..5be1957 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -235,7 +235,7 @@ static bool __rfkill_set_hw_state(struct rfkill *rfkill, else rfkill->state &= ~RFKILL_BLOCK_HW; *change = prev != blocked; - any = rfkill->state & RFKILL_BLOCK_ANY; + any = !!(rfkill->state & RFKILL_BLOCK_ANY); spin_unlock_irqrestore(&rfkill->lock, flags); rfkill_led_trigger_event(rfkill); diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 256c5dd..128677d 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -101,6 +101,14 @@ static int rfkill_gpio_probe(struct platform_device *pdev) if (!rfkill) return -ENOMEM; + if (pdata->gpio_runtime_setup) { + ret = pdata->gpio_runtime_setup(pdev); + if (ret) { + pr_warn("%s: can't set up gpio\n", __func__); + return ret; + } + } + rfkill->pdata = pdata; len = strlen(pdata->name); @@ -182,7 +190,10 @@ fail_alloc: static int rfkill_gpio_remove(struct platform_device *pdev) { struct rfkill_gpio_data *rfkill = platform_get_drvdata(pdev); + struct rfkill_gpio_platform_data *pdata = pdev->dev.platform_data; + if (pdata->gpio_runtime_close) + pdata->gpio_runtime_close(pdev); rfkill_unregister(rfkill->rfkill_dev); rfkill_destroy(rfkill->rfkill_dev); if (gpio_is_valid(rfkill->pdata->shutdown_gpio)) diff --git a/net/rfkill/rfkill-regulator.c b/net/rfkill/rfkill-regulator.c index 18dc512..3ca7277 100644 --- a/net/rfkill/rfkill-regulator.c +++ b/net/rfkill/rfkill-regulator.c @@ -90,7 +90,6 @@ static int __devinit rfkill_regulator_probe(struct platform_device *pdev) pdata->type, &rfkill_regulator_ops, rfkill_data); if (rf_kill == NULL) { - dev_err(&pdev->dev, "Cannot alloc rfkill device\n"); ret = -ENOMEM; goto err_rfkill_alloc; } diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 6994214..9e087d8 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -65,132 +65,134 @@ static inline u32 addr_fold(void *addr) return (a & 0xFFFFFFFF) ^ (BITS_PER_LONG > 32 ? a >> 32 : 0); } -static u32 flow_get_src(struct sk_buff *skb) +static u32 flow_get_src(const struct sk_buff *skb, int nhoff) { + __be32 *data = NULL, hdata; + switch (skb->protocol) { case htons(ETH_P_IP): - if (pskb_network_may_pull(skb, sizeof(struct iphdr))) - return ntohl(ip_hdr(skb)->saddr); + data = skb_header_pointer(skb, + nhoff + offsetof(struct iphdr, + saddr), + 4, &hdata); break; case htons(ETH_P_IPV6): - if (pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) - return ntohl(ipv6_hdr(skb)->saddr.s6_addr32[3]); + data = skb_header_pointer(skb, + nhoff + offsetof(struct ipv6hdr, + saddr.s6_addr32[3]), + 4, &hdata); break; } + if (data) + return ntohl(*data); return addr_fold(skb->sk); } -static u32 flow_get_dst(struct sk_buff *skb) +static u32 flow_get_dst(const struct sk_buff *skb, int nhoff) { + __be32 *data = NULL, hdata; + switch (skb->protocol) { case htons(ETH_P_IP): - if (pskb_network_may_pull(skb, sizeof(struct iphdr))) - return ntohl(ip_hdr(skb)->daddr); + data = skb_header_pointer(skb, + nhoff + offsetof(struct iphdr, + daddr), + 4, &hdata); break; case htons(ETH_P_IPV6): - if (pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) - return ntohl(ipv6_hdr(skb)->daddr.s6_addr32[3]); + data = skb_header_pointer(skb, + nhoff + offsetof(struct ipv6hdr, + daddr.s6_addr32[3]), + 4, &hdata); break; } + if (data) + return ntohl(*data); return addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol; } -static u32 flow_get_proto(struct sk_buff *skb) +static u32 flow_get_proto(const struct sk_buff *skb, int nhoff) { + __u8 *data = NULL, hdata; + switch (skb->protocol) { case htons(ETH_P_IP): - return pskb_network_may_pull(skb, sizeof(struct iphdr)) ? - ip_hdr(skb)->protocol : 0; + data = skb_header_pointer(skb, + nhoff + offsetof(struct iphdr, + protocol), + 1, &hdata); + break; case htons(ETH_P_IPV6): - return pskb_network_may_pull(skb, sizeof(struct ipv6hdr)) ? - ipv6_hdr(skb)->nexthdr : 0; - default: - return 0; + data = skb_header_pointer(skb, + nhoff + offsetof(struct ipv6hdr, + nexthdr), + 1, &hdata); + break; } + if (data) + return *data; + return 0; } -static u32 flow_get_proto_src(struct sk_buff *skb) +/* helper function to get either src or dst port */ +static __be16 *flow_get_proto_common(const struct sk_buff *skb, int nhoff, + __be16 *_port, int dst) { + __be16 *port = NULL; + int poff; + switch (skb->protocol) { case htons(ETH_P_IP): { - struct iphdr *iph; - int poff; + struct iphdr *iph, _iph; - if (!pskb_network_may_pull(skb, sizeof(*iph))) + iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); + if (!iph) break; - iph = ip_hdr(skb); if (ip_is_fragment(iph)) break; poff = proto_ports_offset(iph->protocol); - if (poff >= 0 && - pskb_network_may_pull(skb, iph->ihl * 4 + 2 + poff)) { - iph = ip_hdr(skb); - return ntohs(*(__be16 *)((void *)iph + iph->ihl * 4 + - poff)); - } + if (poff >= 0) + port = skb_header_pointer(skb, + nhoff + iph->ihl * 4 + poff + dst, + sizeof(*_port), _port); break; } case htons(ETH_P_IPV6): { - struct ipv6hdr *iph; - int poff; + struct ipv6hdr *iph, _iph; - if (!pskb_network_may_pull(skb, sizeof(*iph))) + iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); + if (!iph) break; - iph = ipv6_hdr(skb); poff = proto_ports_offset(iph->nexthdr); - if (poff >= 0 && - pskb_network_may_pull(skb, sizeof(*iph) + poff + 2)) { - iph = ipv6_hdr(skb); - return ntohs(*(__be16 *)((void *)iph + sizeof(*iph) + - poff)); - } + if (poff >= 0) + port = skb_header_pointer(skb, + nhoff + sizeof(*iph) + poff + dst, + sizeof(*_port), _port); break; } } - return addr_fold(skb->sk); + return port; } -static u32 flow_get_proto_dst(struct sk_buff *skb) +static u32 flow_get_proto_src(const struct sk_buff *skb, int nhoff) { - switch (skb->protocol) { - case htons(ETH_P_IP): { - struct iphdr *iph; - int poff; + __be16 _port, *port = flow_get_proto_common(skb, nhoff, &_port, 0); - if (!pskb_network_may_pull(skb, sizeof(*iph))) - break; - iph = ip_hdr(skb); - if (ip_is_fragment(iph)) - break; - poff = proto_ports_offset(iph->protocol); - if (poff >= 0 && - pskb_network_may_pull(skb, iph->ihl * 4 + 4 + poff)) { - iph = ip_hdr(skb); - return ntohs(*(__be16 *)((void *)iph + iph->ihl * 4 + - 2 + poff)); - } - break; - } - case htons(ETH_P_IPV6): { - struct ipv6hdr *iph; - int poff; + if (port) + return ntohs(*port); - if (!pskb_network_may_pull(skb, sizeof(*iph))) - break; - iph = ipv6_hdr(skb); - poff = proto_ports_offset(iph->nexthdr); - if (poff >= 0 && - pskb_network_may_pull(skb, sizeof(*iph) + poff + 4)) { - iph = ipv6_hdr(skb); - return ntohs(*(__be16 *)((void *)iph + sizeof(*iph) + - poff + 2)); - } - break; - } - } + return addr_fold(skb->sk); +} + +static u32 flow_get_proto_dst(const struct sk_buff *skb, int nhoff) +{ + __be16 _port, *port = flow_get_proto_common(skb, nhoff, &_port, 2); + + if (port) + return ntohs(*port); return addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol; } @@ -223,7 +225,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb) #define CTTUPLE(skb, member) \ ({ \ enum ip_conntrack_info ctinfo; \ - struct nf_conn *ct = nf_ct_get(skb, &ctinfo); \ + const struct nf_conn *ct = nf_ct_get(skb, &ctinfo); \ if (ct == NULL) \ goto fallback; \ ct->tuplehash[CTINFO2DIR(ctinfo)].tuple.member; \ @@ -236,7 +238,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb) }) #endif -static u32 flow_get_nfct_src(struct sk_buff *skb) +static u32 flow_get_nfct_src(const struct sk_buff *skb, int nhoff) { switch (skb->protocol) { case htons(ETH_P_IP): @@ -245,10 +247,10 @@ static u32 flow_get_nfct_src(struct sk_buff *skb) return ntohl(CTTUPLE(skb, src.u3.ip6[3])); } fallback: - return flow_get_src(skb); + return flow_get_src(skb, nhoff); } -static u32 flow_get_nfct_dst(struct sk_buff *skb) +static u32 flow_get_nfct_dst(const struct sk_buff *skb, int nhoff) { switch (skb->protocol) { case htons(ETH_P_IP): @@ -257,21 +259,21 @@ static u32 flow_get_nfct_dst(struct sk_buff *skb) return ntohl(CTTUPLE(skb, dst.u3.ip6[3])); } fallback: - return flow_get_dst(skb); + return flow_get_dst(skb, nhoff); } -static u32 flow_get_nfct_proto_src(struct sk_buff *skb) +static u32 flow_get_nfct_proto_src(const struct sk_buff *skb, int nhoff) { return ntohs(CTTUPLE(skb, src.u.all)); fallback: - return flow_get_proto_src(skb); + return flow_get_proto_src(skb, nhoff); } -static u32 flow_get_nfct_proto_dst(struct sk_buff *skb) +static u32 flow_get_nfct_proto_dst(const struct sk_buff *skb, int nhoff) { return ntohs(CTTUPLE(skb, dst.u.all)); fallback: - return flow_get_proto_dst(skb); + return flow_get_proto_dst(skb, nhoff); } static u32 flow_get_rtclassid(const struct sk_buff *skb) @@ -313,17 +315,19 @@ static u32 flow_get_rxhash(struct sk_buff *skb) static u32 flow_key_get(struct sk_buff *skb, int key) { + int nhoff = skb_network_offset(skb); + switch (key) { case FLOW_KEY_SRC: - return flow_get_src(skb); + return flow_get_src(skb, nhoff); case FLOW_KEY_DST: - return flow_get_dst(skb); + return flow_get_dst(skb, nhoff); case FLOW_KEY_PROTO: - return flow_get_proto(skb); + return flow_get_proto(skb, nhoff); case FLOW_KEY_PROTO_SRC: - return flow_get_proto_src(skb); + return flow_get_proto_src(skb, nhoff); case FLOW_KEY_PROTO_DST: - return flow_get_proto_dst(skb); + return flow_get_proto_dst(skb, nhoff); case FLOW_KEY_IIF: return flow_get_iif(skb); case FLOW_KEY_PRIORITY: @@ -333,13 +337,13 @@ static u32 flow_key_get(struct sk_buff *skb, int key) case FLOW_KEY_NFCT: return flow_get_nfct(skb); case FLOW_KEY_NFCT_SRC: - return flow_get_nfct_src(skb); + return flow_get_nfct_src(skb, nhoff); case FLOW_KEY_NFCT_DST: - return flow_get_nfct_dst(skb); + return flow_get_nfct_dst(skb, nhoff); case FLOW_KEY_NFCT_PROTO_SRC: - return flow_get_nfct_proto_src(skb); + return flow_get_nfct_proto_src(skb, nhoff); case FLOW_KEY_NFCT_PROTO_DST: - return flow_get_nfct_proto_dst(skb); + return flow_get_nfct_proto_dst(skb, nhoff); case FLOW_KEY_RTCLASSID: return flow_get_rtclassid(skb); case FLOW_KEY_SKUID: diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 0a833d0..e83c272 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -287,6 +287,12 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch) u32 r, slot, salt, sfbhash; int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + if (unlikely(sch->q.qlen >= q->limit)) { + sch->qstats.overlimits++; + q->stats.queuedrop++; + goto drop; + } + if (q->rehash_interval > 0) { unsigned long limit = q->rehash_time + q->rehash_interval; @@ -332,12 +338,9 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch) slot ^= 1; sfb_skb_cb(skb)->hashes[slot] = 0; - if (unlikely(minqlen >= q->max || sch->q.qlen >= q->limit)) { + if (unlikely(minqlen >= q->max)) { sch->qstats.overlimits++; - if (minqlen >= q->max) - q->stats.bucketdrop++; - else - q->stats.queuedrop++; + q->stats.bucketdrop++; goto drop; } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index dc16b90..152b5b3 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -282,6 +282,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->peer.asconf_capable = 1; asoc->asconf_addr_del_pending = NULL; asoc->src_out_of_asoc_ok = 0; + asoc->new_transport = NULL; /* Create an input queue. */ sctp_inq_init(&asoc->base.inqueue); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index aabaee4..8104278 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -243,7 +243,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) if (!(transport->param_flags & SPP_PMTUD_ENABLE)) skb->local_df = 1; - return ip6_xmit(sk, skb, &fl6, np->opt); + return ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); } /* Returns the dst cache entry for the given source and destination ip diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index a6d27bf..14c2b06 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -917,6 +917,8 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) * current cwnd). */ if (!list_empty(&q->retransmit)) { + if (asoc->peer.retran_path->state == SCTP_UNCONFIRMED) + goto sctp_flush_out; if (transport == asoc->peer.retran_path) goto retran; @@ -989,6 +991,8 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) ((new_transport->state == SCTP_INACTIVE) || (new_transport->state == SCTP_UNCONFIRMED))) new_transport = asoc->peer.active_path; + if (new_transport->state == SCTP_UNCONFIRMED) + continue; /* Change packets if necessary. */ if (new_transport != transport) { diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 91784f4..61b9fca 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1299,7 +1299,7 @@ SCTP_STATIC __init int sctp_init(void) max_share = min(4UL*1024*1024, limit); sysctl_sctp_rmem[0] = SK_MEM_QUANTUM; /* give each asoc 1 page min */ - sysctl_sctp_rmem[1] = (1500 *(sizeof(struct sk_buff) + 1)); + sysctl_sctp_rmem[1] = 1500 * SKB_TRUESIZE(1); sysctl_sctp_rmem[2] = max(sysctl_sctp_rmem[1], max_share); sysctl_sctp_wmem[0] = SK_MEM_QUANTUM; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 81db4e3..0121e0a 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3015,6 +3015,7 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, /* Start the heartbeat timer. */ if (!mod_timer(&peer->hb_timer, sctp_transport_timeout(peer))) sctp_transport_hold(peer); + asoc->new_transport = peer; break; case SCTP_PARAM_DEL_IP: /* ADDIP 4.3 D7) If a request is received to delete the diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index a0f31e6..891f5db 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3618,6 +3618,11 @@ sctp_disposition_t sctp_sf_do_asconf(const struct sctp_endpoint *ep, */ asconf_ack->dest = chunk->source; sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(asconf_ack)); + if (asoc->new_transport) { + sctp_sf_heartbeat(ep, asoc, type, asoc->new_transport, + commands); + ((struct sctp_association *)asoc)->new_transport = NULL; + } return SCTP_DISPOSITION_CONSUME; } diff --git a/net/socket.c b/net/socket.c index ffe92ca..2877647 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2472,7 +2472,7 @@ int sock_register(const struct net_proto_family *ops) lockdep_is_held(&net_family_lock))) err = -EEXIST; else { - rcu_assign_pointer(net_families[ops->family], ops); + RCU_INIT_POINTER(net_families[ops->family], ops); err = 0; } spin_unlock(&net_family_lock); @@ -2500,7 +2500,7 @@ void sock_unregister(int family) BUG_ON(family < 0 || family >= NPROTO); spin_lock(&net_family_lock); - rcu_assign_pointer(net_families[family], NULL); + RCU_INIT_POINTER(net_families[family], NULL); spin_unlock(&net_family_lock); synchronize_rcu(); diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c index 4195233..4548757 100644 --- a/net/sunrpc/addr.c +++ b/net/sunrpc/addr.c @@ -255,12 +255,13 @@ EXPORT_SYMBOL_GPL(rpc_pton); /** * rpc_sockaddr2uaddr - Construct a universal address string from @sap. * @sap: socket address + * @gfp_flags: allocation mode * * Returns a %NUL-terminated string in dynamically allocated memory; * otherwise NULL is returned if an error occurred. Caller must * free the returned string. */ -char *rpc_sockaddr2uaddr(const struct sockaddr *sap) +char *rpc_sockaddr2uaddr(const struct sockaddr *sap, gfp_t gfp_flags) { char portbuf[RPCBIND_MAXUADDRPLEN]; char addrbuf[RPCBIND_MAXUADDRLEN]; @@ -288,9 +289,8 @@ char *rpc_sockaddr2uaddr(const struct sockaddr *sap) if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) > sizeof(addrbuf)) return NULL; - return kstrdup(addrbuf, GFP_KERNEL); + return kstrdup(addrbuf, gfp_flags); } -EXPORT_SYMBOL_GPL(rpc_sockaddr2uaddr); /** * rpc_uaddr2sockaddr - convert a universal address to a socket address. diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 364eb45..afb5655 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -122,7 +122,7 @@ gss_cred_set_ctx(struct rpc_cred *cred, struct gss_cl_ctx *ctx) if (!test_bit(RPCAUTH_CRED_NEW, &cred->cr_flags)) return; gss_get_ctx(ctx); - rcu_assign_pointer(gss_cred->gc_ctx, ctx); + RCU_INIT_POINTER(gss_cred->gc_ctx, ctx); set_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags); smp_mb__before_clear_bit(); clear_bit(RPCAUTH_CRED_NEW, &cred->cr_flags); @@ -603,26 +603,6 @@ out: return err; } -static ssize_t -gss_pipe_upcall(struct file *filp, struct rpc_pipe_msg *msg, - char __user *dst, size_t buflen) -{ - char *data = (char *)msg->data + msg->copied; - size_t mlen = min(msg->len, buflen); - unsigned long left; - - left = copy_to_user(dst, data, mlen); - if (left == mlen) { - msg->errno = -EFAULT; - return -EFAULT; - } - - mlen -= left; - msg->copied += mlen; - msg->errno = 0; - return mlen; -} - #define MSG_BUF_MAXSIZE 1024 static ssize_t @@ -970,7 +950,7 @@ gss_destroy_nullcred(struct rpc_cred *cred) struct gss_auth *gss_auth = container_of(cred->cr_auth, struct gss_auth, rpc_auth); struct gss_cl_ctx *ctx = gss_cred->gc_ctx; - rcu_assign_pointer(gss_cred->gc_ctx, NULL); + RCU_INIT_POINTER(gss_cred->gc_ctx, NULL); call_rcu(&cred->cr_rcu, gss_free_cred_callback); if (ctx) gss_put_ctx(ctx); @@ -1590,7 +1570,7 @@ static const struct rpc_credops gss_nullops = { }; static const struct rpc_pipe_ops gss_upcall_ops_v0 = { - .upcall = gss_pipe_upcall, + .upcall = rpc_pipe_generic_upcall, .downcall = gss_pipe_downcall, .destroy_msg = gss_pipe_destroy_msg, .open_pipe = gss_pipe_open_v0, @@ -1598,7 +1578,7 @@ static const struct rpc_pipe_ops gss_upcall_ops_v0 = { }; static const struct rpc_pipe_ops gss_upcall_ops_v1 = { - .upcall = gss_pipe_upcall, + .upcall = rpc_pipe_generic_upcall, .downcall = gss_pipe_downcall, .destroy_msg = gss_pipe_destroy_msg, .open_pipe = gss_pipe_open_v1, diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index 4cb70dc..e50502d 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -129,6 +129,9 @@ unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int flags) for (i = 0; i < groups ; i++) if (cred->uc_gids[i] != GROUP_AT(acred->group_info, i)) return 0; + if (groups < NFS_NGROUPS && + cred->uc_gids[groups] != NOGROUP) + return 0; return 1; } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index c5347d2..f0268ea 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -850,7 +850,9 @@ rpc_restart_call_prepare(struct rpc_task *task) { if (RPC_ASSASSINATED(task)) return 0; - task->tk_action = rpc_prepare_task; + task->tk_action = call_start; + if (task->tk_ops->rpc_call_prepare != NULL) + task->tk_action = rpc_prepare_task; return 1; } EXPORT_SYMBOL_GPL(rpc_restart_call_prepare); diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index b181e34..bfddd68 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -77,6 +77,26 @@ rpc_timeout_upcall_queue(struct work_struct *work) rpc_purge_list(rpci, &free_list, destroy_msg, -ETIMEDOUT); } +ssize_t rpc_pipe_generic_upcall(struct file *filp, struct rpc_pipe_msg *msg, + char __user *dst, size_t buflen) +{ + char *data = (char *)msg->data + msg->copied; + size_t mlen = min(msg->len - msg->copied, buflen); + unsigned long left; + + left = copy_to_user(dst, data, mlen); + if (left == mlen) { + msg->errno = -EFAULT; + return -EFAULT; + } + + mlen -= left; + msg->copied += mlen; + msg->errno = 0; + return mlen; +} +EXPORT_SYMBOL_GPL(rpc_pipe_generic_upcall); + /** * rpc_queue_upcall - queue an upcall message to userspace * @inode: inode of upcall pipe on which to queue given message @@ -1084,3 +1104,6 @@ void unregister_rpc_pipefs(void) kmem_cache_destroy(rpc_inode_cachep); unregister_filesystem(&rpc_pipe_fs_type); } + +/* Make 'mount -t rpc_pipefs ...' autoload this module. */ +MODULE_ALIAS("rpc_pipefs"); diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index e45d2fb..8761bf8 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -114,6 +114,9 @@ static struct rpc_program rpcb_program; static struct rpc_clnt * rpcb_local_clnt; static struct rpc_clnt * rpcb_local_clnt4; +DEFINE_SPINLOCK(rpcb_clnt_lock); +unsigned int rpcb_users; + struct rpcbind_args { struct rpc_xprt * r_xprt; @@ -161,6 +164,56 @@ static void rpcb_map_release(void *data) kfree(map); } +static int rpcb_get_local(void) +{ + int cnt; + + spin_lock(&rpcb_clnt_lock); + if (rpcb_users) + rpcb_users++; + cnt = rpcb_users; + spin_unlock(&rpcb_clnt_lock); + + return cnt; +} + +void rpcb_put_local(void) +{ + struct rpc_clnt *clnt = rpcb_local_clnt; + struct rpc_clnt *clnt4 = rpcb_local_clnt4; + int shutdown; + + spin_lock(&rpcb_clnt_lock); + if (--rpcb_users == 0) { + rpcb_local_clnt = NULL; + rpcb_local_clnt4 = NULL; + } + shutdown = !rpcb_users; + spin_unlock(&rpcb_clnt_lock); + + if (shutdown) { + /* + * cleanup_rpcb_clnt - remove xprtsock's sysctls, unregister + */ + if (clnt4) + rpc_shutdown_client(clnt4); + if (clnt) + rpc_shutdown_client(clnt); + } +} + +static void rpcb_set_local(struct rpc_clnt *clnt, struct rpc_clnt *clnt4) +{ + /* Protected by rpcb_create_local_mutex */ + rpcb_local_clnt = clnt; + rpcb_local_clnt4 = clnt4; + smp_wmb(); + rpcb_users = 1; + dprintk("RPC: created new rpcb local clients (rpcb_local_clnt: " + "%p, rpcb_local_clnt4: %p)\n", rpcb_local_clnt, + rpcb_local_clnt4); +} + /* * Returns zero on success, otherwise a negative errno value * is returned. @@ -205,9 +258,7 @@ static int rpcb_create_local_unix(void) clnt4 = NULL; } - /* Protected by rpcb_create_local_mutex */ - rpcb_local_clnt = clnt; - rpcb_local_clnt4 = clnt4; + rpcb_set_local(clnt, clnt4); out: return result; @@ -259,9 +310,7 @@ static int rpcb_create_local_net(void) clnt4 = NULL; } - /* Protected by rpcb_create_local_mutex */ - rpcb_local_clnt = clnt; - rpcb_local_clnt4 = clnt4; + rpcb_set_local(clnt, clnt4); out: return result; @@ -271,16 +320,16 @@ out: * Returns zero on success, otherwise a negative errno value * is returned. */ -static int rpcb_create_local(void) +int rpcb_create_local(void) { static DEFINE_MUTEX(rpcb_create_local_mutex); int result = 0; - if (rpcb_local_clnt) + if (rpcb_get_local()) return result; mutex_lock(&rpcb_create_local_mutex); - if (rpcb_local_clnt) + if (rpcb_get_local()) goto out; if (rpcb_create_local_unix() != 0) @@ -382,11 +431,6 @@ int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port) struct rpc_message msg = { .rpc_argp = &map, }; - int error; - - error = rpcb_create_local(); - if (error) - return error; dprintk("RPC: %sregistering (%u, %u, %d, %u) with local " "rpcbind\n", (port ? "" : "un"), @@ -410,7 +454,7 @@ static int rpcb_register_inet4(const struct sockaddr *sap, unsigned short port = ntohs(sin->sin_port); int result; - map->r_addr = rpc_sockaddr2uaddr(sap); + map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL); dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " "local rpcbind\n", (port ? "" : "un"), @@ -437,7 +481,7 @@ static int rpcb_register_inet6(const struct sockaddr *sap, unsigned short port = ntohs(sin6->sin6_port); int result; - map->r_addr = rpc_sockaddr2uaddr(sap); + map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL); dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " "local rpcbind\n", (port ? "" : "un"), @@ -522,11 +566,7 @@ int rpcb_v4_register(const u32 program, const u32 version, struct rpc_message msg = { .rpc_argp = &map, }; - int error; - error = rpcb_create_local(); - if (error) - return error; if (rpcb_local_clnt4 == NULL) return -EPROTONOSUPPORT; @@ -686,7 +726,7 @@ void rpcb_getport_async(struct rpc_task *task) case RPCBVERS_4: case RPCBVERS_3: map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID); - map->r_addr = rpc_sockaddr2uaddr(sap); + map->r_addr = rpc_sockaddr2uaddr(sap, GFP_ATOMIC); map->r_owner = ""; break; case RPCBVERS_2: @@ -1060,15 +1100,3 @@ static struct rpc_program rpcb_program = { .version = rpcb_version, .stats = &rpcb_stats, }; - -/** - * cleanup_rpcb_clnt - remove xprtsock's sysctls, unregister - * - */ -void cleanup_rpcb_clnt(void) -{ - if (rpcb_local_clnt4) - rpc_shutdown_client(rpcb_local_clnt4); - if (rpcb_local_clnt) - rpc_shutdown_client(rpcb_local_clnt); -} diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index 9d08091..8ec9778 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -61,8 +61,6 @@ static struct pernet_operations sunrpc_net_ops = { extern struct cache_detail unix_gid_cache; -extern void cleanup_rpcb_clnt(void); - static int __init init_sunrpc(void) { @@ -102,7 +100,6 @@ out: static void __exit cleanup_sunrpc(void) { - cleanup_rpcb_clnt(); rpcauth_remove_module(); cleanup_socket_xprt(); svc_cleanup_xprt_sock(); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 6a69a11..6e03888 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -295,6 +295,18 @@ svc_pool_map_put(void) } +static int svc_pool_map_get_node(unsigned int pidx) +{ + const struct svc_pool_map *m = &svc_pool_map; + + if (m->count) { + if (m->mode == SVC_POOL_PERCPU) + return cpu_to_node(m->pool_to[pidx]); + if (m->mode == SVC_POOL_PERNODE) + return m->pool_to[pidx]; + } + return NUMA_NO_NODE; +} /* * Set the given thread's cpus_allowed mask so that it * will only run on cpus in the given pool. @@ -354,6 +366,42 @@ svc_pool_for_cpu(struct svc_serv *serv, int cpu) return &serv->sv_pools[pidx % serv->sv_nrpools]; } +static int svc_rpcb_setup(struct svc_serv *serv) +{ + int err; + + err = rpcb_create_local(); + if (err) + return err; + + /* Remove any stale portmap registrations */ + svc_unregister(serv); + return 0; +} + +void svc_rpcb_cleanup(struct svc_serv *serv) +{ + svc_unregister(serv); + rpcb_put_local(); +} +EXPORT_SYMBOL_GPL(svc_rpcb_cleanup); + +static int svc_uses_rpcbind(struct svc_serv *serv) +{ + struct svc_program *progp; + unsigned int i; + + for (progp = serv->sv_program; progp; progp = progp->pg_next) { + for (i = 0; i < progp->pg_nvers; i++) { + if (progp->pg_vers[i] == NULL) + continue; + if (progp->pg_vers[i]->vs_hidden == 0) + return 1; + } + } + + return 0; +} /* * Create an RPC service @@ -419,8 +467,15 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, spin_lock_init(&pool->sp_lock); } - /* Remove any stale portmap registrations */ - svc_unregister(serv); + if (svc_uses_rpcbind(serv)) { + if (svc_rpcb_setup(serv) < 0) { + kfree(serv->sv_pools); + kfree(serv); + return NULL; + } + if (!serv->sv_shutdown) + serv->sv_shutdown = svc_rpcb_cleanup; + } return serv; } @@ -488,7 +543,6 @@ svc_destroy(struct svc_serv *serv) if (svc_serv_is_pooled(serv)) svc_pool_map_put(); - svc_unregister(serv); kfree(serv->sv_pools); kfree(serv); } @@ -499,7 +553,7 @@ EXPORT_SYMBOL_GPL(svc_destroy); * We allocate pages and place them in rq_argpages. */ static int -svc_init_buffer(struct svc_rqst *rqstp, unsigned int size) +svc_init_buffer(struct svc_rqst *rqstp, unsigned int size, int node) { unsigned int pages, arghi; @@ -513,7 +567,7 @@ svc_init_buffer(struct svc_rqst *rqstp, unsigned int size) arghi = 0; BUG_ON(pages > RPCSVC_MAXPAGES); while (pages) { - struct page *p = alloc_page(GFP_KERNEL); + struct page *p = alloc_pages_node(node, GFP_KERNEL, 0); if (!p) break; rqstp->rq_pages[arghi++] = p; @@ -536,11 +590,11 @@ svc_release_buffer(struct svc_rqst *rqstp) } struct svc_rqst * -svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool) +svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) { struct svc_rqst *rqstp; - rqstp = kzalloc(sizeof(*rqstp), GFP_KERNEL); + rqstp = kzalloc_node(sizeof(*rqstp), GFP_KERNEL, node); if (!rqstp) goto out_enomem; @@ -554,15 +608,15 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool) rqstp->rq_server = serv; rqstp->rq_pool = pool; - rqstp->rq_argp = kmalloc(serv->sv_xdrsize, GFP_KERNEL); + rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node); if (!rqstp->rq_argp) goto out_thread; - rqstp->rq_resp = kmalloc(serv->sv_xdrsize, GFP_KERNEL); + rqstp->rq_resp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node); if (!rqstp->rq_resp) goto out_thread; - if (!svc_init_buffer(rqstp, serv->sv_max_mesg)) + if (!svc_init_buffer(rqstp, serv->sv_max_mesg, node)) goto out_thread; return rqstp; @@ -647,6 +701,7 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) struct svc_pool *chosen_pool; int error = 0; unsigned int state = serv->sv_nrthreads-1; + int node; if (pool == NULL) { /* The -1 assumes caller has done a svc_get() */ @@ -662,14 +717,16 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) nrservs--; chosen_pool = choose_pool(serv, pool, &state); - rqstp = svc_prepare_thread(serv, chosen_pool); + node = svc_pool_map_get_node(chosen_pool->sp_id); + rqstp = svc_prepare_thread(serv, chosen_pool, node); if (IS_ERR(rqstp)) { error = PTR_ERR(rqstp); break; } __module_get(serv->sv_module); - task = kthread_create(serv->sv_function, rqstp, serv->sv_name); + task = kthread_create_on_node(serv->sv_function, rqstp, + node, serv->sv_name); if (IS_ERR(task)) { error = PTR_ERR(task); module_put(serv->sv_module); @@ -956,9 +1013,8 @@ static void svc_unregister(const struct svc_serv *serv) /* * Printk the given error with the address of the client that caused it. */ -static int -__attribute__ ((format (printf, 2, 3))) -svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) +static __printf(2, 3) +int svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) { va_list args; int r; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index bd31208..d86bb67 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -254,8 +254,6 @@ EXPORT_SYMBOL_GPL(svc_create_xprt); */ void svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt) { - struct sockaddr *sin; - memcpy(&rqstp->rq_addr, &xprt->xpt_remote, xprt->xpt_remotelen); rqstp->rq_addrlen = xprt->xpt_remotelen; @@ -263,15 +261,8 @@ void svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt) * Destination address in request is needed for binding the * source address in RPC replies/callbacks later. */ - sin = (struct sockaddr *)&xprt->xpt_local; - switch (sin->sa_family) { - case AF_INET: - rqstp->rq_daddr.addr = ((struct sockaddr_in *)sin)->sin_addr; - break; - case AF_INET6: - rqstp->rq_daddr.addr6 = ((struct sockaddr_in6 *)sin)->sin6_addr; - break; - } + memcpy(&rqstp->rq_daddr, &xprt->xpt_local, xprt->xpt_locallen); + rqstp->rq_daddrlen = xprt->xpt_locallen; } EXPORT_SYMBOL_GPL(svc_xprt_copy_addrs); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 767d494..dfd686e 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -143,19 +143,20 @@ static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh) cmh->cmsg_level = SOL_IP; cmh->cmsg_type = IP_PKTINFO; pki->ipi_ifindex = 0; - pki->ipi_spec_dst.s_addr = rqstp->rq_daddr.addr.s_addr; + pki->ipi_spec_dst.s_addr = + svc_daddr_in(rqstp)->sin_addr.s_addr; cmh->cmsg_len = CMSG_LEN(sizeof(*pki)); } break; case AF_INET6: { struct in6_pktinfo *pki = CMSG_DATA(cmh); + struct sockaddr_in6 *daddr = svc_daddr_in6(rqstp); cmh->cmsg_level = SOL_IPV6; cmh->cmsg_type = IPV6_PKTINFO; - pki->ipi6_ifindex = 0; - ipv6_addr_copy(&pki->ipi6_addr, - &rqstp->rq_daddr.addr6); + pki->ipi6_ifindex = daddr->sin6_scope_id; + ipv6_addr_copy(&pki->ipi6_addr, &daddr->sin6_addr); cmh->cmsg_len = CMSG_LEN(sizeof(*pki)); } break; @@ -498,9 +499,13 @@ static int svc_udp_get_dest_address4(struct svc_rqst *rqstp, struct cmsghdr *cmh) { struct in_pktinfo *pki = CMSG_DATA(cmh); + struct sockaddr_in *daddr = svc_daddr_in(rqstp); + if (cmh->cmsg_type != IP_PKTINFO) return 0; - rqstp->rq_daddr.addr.s_addr = pki->ipi_spec_dst.s_addr; + + daddr->sin_family = AF_INET; + daddr->sin_addr.s_addr = pki->ipi_spec_dst.s_addr; return 1; } @@ -511,9 +516,14 @@ static int svc_udp_get_dest_address6(struct svc_rqst *rqstp, struct cmsghdr *cmh) { struct in6_pktinfo *pki = CMSG_DATA(cmh); + struct sockaddr_in6 *daddr = svc_daddr_in6(rqstp); + if (cmh->cmsg_type != IPV6_PKTINFO) return 0; - ipv6_addr_copy(&rqstp->rq_daddr.addr6, &pki->ipi6_addr); + + daddr->sin6_family = AF_INET6; + ipv6_addr_copy(&daddr->sin6_addr, &pki->ipi6_addr); + daddr->sin6_scope_id = pki->ipi6_ifindex; return 1; } @@ -614,6 +624,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) skb_free_datagram_locked(svsk->sk_sk, skb); return 0; } + rqstp->rq_daddrlen = svc_addr_len(svc_daddr(rqstp)); if (skb_is_nonlinear(skb)) { /* we have to copy */ diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 759b318..28908f5 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -39,6 +39,7 @@ #include "link.h" #include "port.h" #include "bcast.h" +#include "name_distr.h" #define MAX_PKT_DEFAULT_MCAST 1500 /* bcast link max packet size (fixed) */ @@ -298,14 +299,9 @@ static void bclink_send_nack(struct tipc_node *n_ptr) msg_set_bcgap_to(msg, n_ptr->bclink.gap_to); msg_set_bcast_tag(msg, tipc_own_tag); - if (tipc_bearer_send(&bcbearer->bearer, buf, NULL)) { - bcl->stats.sent_nacks++; - buf_discard(buf); - } else { - tipc_bearer_schedule(bcl->b_ptr, bcl); - bcl->proto_msg_queue = buf; - bcl->stats.bearer_congs++; - } + tipc_bearer_send(&bcbearer->bearer, buf, NULL); + bcl->stats.sent_nacks++; + buf_discard(buf); /* * Ensure we doesn't send another NACK msg to the node @@ -426,20 +422,28 @@ int tipc_bclink_send_msg(struct sk_buff *buf) void tipc_bclink_recv_pkt(struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); - struct tipc_node *node = tipc_node_find(msg_prevnode(msg)); + struct tipc_node *node; u32 next_in; u32 seqno; struct sk_buff *deferred; - if (unlikely(!node || !tipc_node_is_up(node) || !node->bclink.supported || - (msg_mc_netid(msg) != tipc_net_id))) { - buf_discard(buf); - return; - } + /* Screen out unwanted broadcast messages */ + + if (msg_mc_netid(msg) != tipc_net_id) + goto exit; + + node = tipc_node_find(msg_prevnode(msg)); + if (unlikely(!node)) + goto exit; + + tipc_node_lock(node); + if (unlikely(!node->bclink.supported)) + goto unlock; if (unlikely(msg_user(msg) == BCAST_PROTOCOL)) { + if (msg_type(msg) != STATE_MSG) + goto unlock; if (msg_destnode(msg) == tipc_own_addr) { - tipc_node_lock(node); tipc_bclink_acknowledge(node, msg_bcast_ack(msg)); tipc_node_unlock(node); spin_lock_bh(&bc_lock); @@ -449,18 +453,18 @@ void tipc_bclink_recv_pkt(struct sk_buff *buf) msg_bcgap_to(msg)); spin_unlock_bh(&bc_lock); } else { + tipc_node_unlock(node); tipc_bclink_peek_nack(msg_destnode(msg), msg_bcast_tag(msg), msg_bcgap_after(msg), msg_bcgap_to(msg)); } - buf_discard(buf); - return; + goto exit; } - tipc_node_lock(node); + /* Handle in-sequence broadcast message */ + receive: - deferred = node->bclink.deferred_head; next_in = mod(node->bclink.last_in + 1); seqno = msg_seqno(msg); @@ -474,7 +478,10 @@ receive: } if (likely(msg_isdata(msg))) { tipc_node_unlock(node); - tipc_port_recv_mcast(buf, NULL); + if (likely(msg_mcast(msg))) + tipc_port_recv_mcast(buf, NULL); + else + buf_discard(buf); } else if (msg_user(msg) == MSG_BUNDLER) { bcl->stats.recv_bundles++; bcl->stats.recv_bundled += msg_msgcnt(msg); @@ -487,18 +494,22 @@ receive: bcl->stats.recv_fragmented++; tipc_node_unlock(node); tipc_net_route_msg(buf); + } else if (msg_user(msg) == NAME_DISTRIBUTOR) { + tipc_node_unlock(node); + tipc_named_recv(buf); } else { tipc_node_unlock(node); - tipc_net_route_msg(buf); + buf_discard(buf); } + buf = NULL; + tipc_node_lock(node); + deferred = node->bclink.deferred_head; if (deferred && (buf_seqno(deferred) == mod(next_in + 1))) { - tipc_node_lock(node); buf = deferred; msg = buf_msg(buf); node->bclink.deferred_head = deferred->next; goto receive; } - return; } else if (less(next_in, seqno)) { u32 gap_after = node->bclink.gap_after; u32 gap_to = node->bclink.gap_to; @@ -513,6 +524,7 @@ receive: else if (less(gap_after, seqno) && less(seqno, gap_to)) node->bclink.gap_to = seqno; } + buf = NULL; if (bclink_ack_allowed(node->bclink.nack_sync)) { if (gap_to != gap_after) bclink_send_nack(node); @@ -520,9 +532,11 @@ receive: } } else { bcl->stats.duplicates++; - buf_discard(buf); } +unlock: tipc_node_unlock(node); +exit: + buf_discard(buf); } u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr) @@ -535,10 +549,11 @@ u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr) /** * tipc_bcbearer_send - send a packet through the broadcast pseudo-bearer * - * Send through as many bearers as necessary to reach all nodes - * that support TIPC multicasting. + * Send packet over as many bearers as necessary to reach all nodes + * that have joined the broadcast link. * - * Returns 0 if packet sent successfully, non-zero if not + * Returns 0 (packet sent successfully) under all circumstances, + * since the broadcast link's pseudo-bearer never blocks */ static int tipc_bcbearer_send(struct sk_buff *buf, @@ -547,7 +562,12 @@ static int tipc_bcbearer_send(struct sk_buff *buf, { int bp_index; - /* Prepare buffer for broadcasting (if first time trying to send it) */ + /* + * Prepare broadcast link message for reliable transmission, + * if first time trying to send it; + * preparation is skipped for broadcast link protocol messages + * since they are sent in an unreliable manner and don't need it + */ if (likely(!msg_non_seq(buf_msg(buf)))) { struct tipc_msg *msg; @@ -596,18 +616,12 @@ static int tipc_bcbearer_send(struct sk_buff *buf, } if (bcbearer->remains_new.count == 0) - return 0; + break; /* all targets reached */ bcbearer->remains = bcbearer->remains_new; } - /* - * Unable to reach all targets (indicate success, since currently - * there isn't code in place to properly block & unblock the - * pseudo-bearer used by the broadcast link) - */ - - return TIPC_OK; + return 0; } /** @@ -667,27 +681,6 @@ void tipc_bcbearer_sort(void) spin_unlock_bh(&bc_lock); } -/** - * tipc_bcbearer_push - resolve bearer congestion - * - * Forces bclink to push out any unsent packets, until all packets are gone - * or congestion reoccurs. - * No locks set when function called - */ - -void tipc_bcbearer_push(void) -{ - struct tipc_bearer *b_ptr; - - spin_lock_bh(&bc_lock); - b_ptr = &bcbearer->bearer; - if (b_ptr->blocked) { - b_ptr->blocked = 0; - tipc_bearer_lock_push(b_ptr); - } - spin_unlock_bh(&bc_lock); -} - int tipc_bclink_stats(char *buf, const u32 buf_size) { @@ -764,7 +757,7 @@ int tipc_bclink_init(void) bcbearer = kzalloc(sizeof(*bcbearer), GFP_ATOMIC); bclink = kzalloc(sizeof(*bclink), GFP_ATOMIC); if (!bcbearer || !bclink) { - warn("Multicast link creation failed, no memory\n"); + warn("Broadcast link creation failed, no memory\n"); kfree(bcbearer); bcbearer = NULL; kfree(bclink); @@ -775,7 +768,7 @@ int tipc_bclink_init(void) INIT_LIST_HEAD(&bcbearer->bearer.cong_links); bcbearer->bearer.media = &bcbearer->media; bcbearer->media.send_msg = tipc_bcbearer_send; - sprintf(bcbearer->media.name, "tipc-multicast"); + sprintf(bcbearer->media.name, "tipc-broadcast"); bcl = &bclink->link; INIT_LIST_HEAD(&bcl->waiting_ports); diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 500c97f..06740da 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -101,6 +101,5 @@ int tipc_bclink_stats(char *stats_buf, const u32 buf_size); int tipc_bclink_reset_stats(void); int tipc_bclink_set_queue_limits(u32 limit); void tipc_bcbearer_sort(void); -void tipc_bcbearer_push(void); #endif diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 85eba9c..e2202de 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -385,13 +385,9 @@ static int bearer_push(struct tipc_bearer *b_ptr) void tipc_bearer_lock_push(struct tipc_bearer *b_ptr) { - int res; - spin_lock_bh(&b_ptr->lock); - res = bearer_push(b_ptr); + bearer_push(b_ptr); spin_unlock_bh(&b_ptr->lock); - if (res) - tipc_bcbearer_push(); } @@ -608,6 +604,7 @@ int tipc_block_bearer(const char *name) info("Blocking bearer <%s>\n", name); spin_lock_bh(&b_ptr->lock); b_ptr->blocked = 1; + list_splice_init(&b_ptr->cong_links, &b_ptr->links); list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { struct tipc_node *n_ptr = l_ptr->owner; @@ -635,6 +632,7 @@ static void bearer_disable(struct tipc_bearer *b_ptr) spin_lock_bh(&b_ptr->lock); b_ptr->blocked = 1; b_ptr->media->disable_bearer(b_ptr); + list_splice_init(&b_ptr->cong_links, &b_ptr->links); list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { tipc_link_delete(l_ptr); } diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 5ad70ef..d696f9e 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -39,8 +39,8 @@ #include "bcast.h" -#define MAX_BEARERS 8 -#define MAX_MEDIA 4 +#define MAX_BEARERS 2 +#define MAX_MEDIA 2 /* * Identifiers of supported TIPC media types diff --git a/net/tipc/config.h b/net/tipc/config.h index 443159a..80da6eb 100644 --- a/net/tipc/config.h +++ b/net/tipc/config.h @@ -65,7 +65,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *req_tlv_area, int req_tlv_space, int headroom); -void tipc_cfg_link_event(u32 addr, char *name, int up); int tipc_cfg_init(void); void tipc_cfg_stop(void); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 0987933..f2fb96e 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -159,12 +159,6 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) } tipc_node_lock(n_ptr); - /* Don't talk to neighbor during cleanup after last session */ - if (n_ptr->cleanup_required) { - tipc_node_unlock(n_ptr); - return; - } - link = n_ptr->links[b_ptr->identity]; /* Create a link endpoint for this bearer, if necessary */ diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index b69092e..e728d4c 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -2,7 +2,7 @@ * net/tipc/eth_media.c: Ethernet bearer support for TIPC * * Copyright (c) 2001-2007, Ericsson AB - * Copyright (c) 2005-2007, Wind River Systems + * Copyright (c) 2005-2008, 2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -37,7 +37,7 @@ #include "core.h" #include "bearer.h" -#define MAX_ETH_BEARERS 2 +#define MAX_ETH_BEARERS MAX_BEARERS #define ETH_LINK_PRIORITY TIPC_DEF_LINK_PRI #define ETH_LINK_TOLERANCE TIPC_DEF_LINK_TOL #define ETH_LINK_WINDOW TIPC_DEF_LINK_WIN @@ -144,31 +144,27 @@ static int enable_bearer(struct tipc_bearer *tb_ptr) /* Find device with specified name */ + read_lock(&dev_base_lock); for_each_netdev(&init_net, pdev) { if (!strncmp(pdev->name, driver_name, IFNAMSIZ)) { dev = pdev; + dev_hold(dev); break; } } + read_unlock(&dev_base_lock); if (!dev) return -ENODEV; - /* Find Ethernet bearer for device (or create one) */ - - while ((eb_ptr != stop) && eb_ptr->dev && (eb_ptr->dev != dev)) - eb_ptr++; - if (eb_ptr == stop) - return -EDQUOT; - if (!eb_ptr->dev) { - eb_ptr->dev = dev; - eb_ptr->tipc_packet_type.type = htons(ETH_P_TIPC); - eb_ptr->tipc_packet_type.dev = dev; - eb_ptr->tipc_packet_type.func = recv_msg; - eb_ptr->tipc_packet_type.af_packet_priv = eb_ptr; - INIT_LIST_HEAD(&(eb_ptr->tipc_packet_type.list)); - dev_hold(dev); - dev_add_pack(&eb_ptr->tipc_packet_type); - } + /* Create Ethernet bearer for device */ + + eb_ptr->dev = dev; + eb_ptr->tipc_packet_type.type = htons(ETH_P_TIPC); + eb_ptr->tipc_packet_type.dev = dev; + eb_ptr->tipc_packet_type.func = recv_msg; + eb_ptr->tipc_packet_type.af_packet_priv = eb_ptr; + INIT_LIST_HEAD(&(eb_ptr->tipc_packet_type.list)); + dev_add_pack(&eb_ptr->tipc_packet_type); /* Associate TIPC bearer with Ethernet bearer */ diff --git a/net/tipc/link.c b/net/tipc/link.c index f89570c..ae98a72 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -332,15 +332,16 @@ struct link *tipc_link_create(struct tipc_node *n_ptr, l_ptr->addr = peer; if_name = strchr(b_ptr->name, ':') + 1; - sprintf(l_ptr->name, "%u.%u.%u:%s-%u.%u.%u:", + sprintf(l_ptr->name, "%u.%u.%u:%s-%u.%u.%u:unknown", tipc_zone(tipc_own_addr), tipc_cluster(tipc_own_addr), tipc_node(tipc_own_addr), if_name, tipc_zone(peer), tipc_cluster(peer), tipc_node(peer)); - /* note: peer i/f is appended to link name by reset/activate */ + /* note: peer i/f name is updated by reset/activate message */ memcpy(&l_ptr->media_addr, media_addr, sizeof(*media_addr)); l_ptr->owner = n_ptr; l_ptr->checkpoint = 1; + l_ptr->peer_session = INVALID_SESSION; l_ptr->b_ptr = b_ptr; link_set_supervision_props(l_ptr, b_ptr->media->tolerance); l_ptr->state = RESET_UNKNOWN; @@ -536,9 +537,6 @@ void tipc_link_stop(struct link *l_ptr) l_ptr->proto_msg_queue = NULL; } -/* LINK EVENT CODE IS NOT SUPPORTED AT PRESENT */ -#define link_send_event(fcn, l_ptr, up) do { } while (0) - void tipc_link_reset(struct link *l_ptr) { struct sk_buff *buf; @@ -596,10 +594,6 @@ void tipc_link_reset(struct link *l_ptr) l_ptr->fsm_msg_cnt = 0; l_ptr->stale_count = 0; link_reset_statistics(l_ptr); - - link_send_event(tipc_cfg_link_event, l_ptr, 0); - if (!in_own_cluster(l_ptr->addr)) - link_send_event(tipc_disc_link_event, l_ptr, 0); } @@ -608,9 +602,6 @@ static void link_activate(struct link *l_ptr) l_ptr->next_in_no = l_ptr->stats.recv_info = 1; tipc_node_link_up(l_ptr->owner, l_ptr); tipc_bearer_add_dest(l_ptr->b_ptr, l_ptr->addr); - link_send_event(tipc_cfg_link_event, l_ptr, 1); - if (!in_own_cluster(l_ptr->addr)) - link_send_event(tipc_disc_link_event, l_ptr, 1); } /** @@ -985,6 +976,51 @@ int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector) } /* + * tipc_link_send_names - send name table entries to new neighbor + * + * Send routine for bulk delivery of name table messages when contact + * with a new neighbor occurs. No link congestion checking is performed + * because name table messages *must* be delivered. The messages must be + * small enough not to require fragmentation. + * Called without any locks held. + */ + +void tipc_link_send_names(struct list_head *message_list, u32 dest) +{ + struct tipc_node *n_ptr; + struct link *l_ptr; + struct sk_buff *buf; + struct sk_buff *temp_buf; + + if (list_empty(message_list)) + return; + + read_lock_bh(&tipc_net_lock); + n_ptr = tipc_node_find(dest); + if (n_ptr) { + tipc_node_lock(n_ptr); + l_ptr = n_ptr->active_links[0]; + if (l_ptr) { + /* convert circular list to linear list */ + ((struct sk_buff *)message_list->prev)->next = NULL; + link_add_chain_to_outqueue(l_ptr, + (struct sk_buff *)message_list->next, 0); + tipc_link_push_queue(l_ptr); + INIT_LIST_HEAD(message_list); + } + tipc_node_unlock(n_ptr); + } + read_unlock_bh(&tipc_net_lock); + + /* discard the messages if they couldn't be sent */ + + list_for_each_safe(buf, temp_buf, ((struct sk_buff *)message_list)) { + list_del((struct list_head *)buf); + buf_discard(buf); + } +} + +/* * link_send_buf_fast: Entry for data messages where the * destination link is known and the header is complete, * inclusive total message length. Very time critical. @@ -1031,9 +1067,6 @@ int tipc_send_buf_fast(struct sk_buff *buf, u32 destnode) u32 selector = msg_origport(buf_msg(buf)) & 1; u32 dummy; - if (destnode == tipc_own_addr) - return tipc_port_recv_msg(buf); - read_lock_bh(&tipc_net_lock); n_ptr = tipc_node_find(destnode); if (likely(n_ptr)) { @@ -1658,19 +1691,12 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) continue; } + /* Discard unicast link messages destined for another node */ + if (unlikely(!msg_short(msg) && (msg_destnode(msg) != tipc_own_addr))) goto cont; - /* Discard non-routeable messages destined for another node */ - - if (unlikely(!msg_isdata(msg) && - (msg_destnode(msg) != tipc_own_addr))) { - if ((msg_user(msg) != CONN_MANAGER) && - (msg_user(msg) != MSG_FRAGMENTER)) - goto cont; - } - /* Locate neighboring node that sent message */ n_ptr = tipc_node_find(msg_prevnode(msg)); @@ -1678,17 +1704,24 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) goto cont; tipc_node_lock(n_ptr); - /* Don't talk to neighbor during cleanup after last session */ + /* Locate unicast link endpoint that should handle message */ - if (n_ptr->cleanup_required) { + l_ptr = n_ptr->links[b_ptr->identity]; + if (unlikely(!l_ptr)) { tipc_node_unlock(n_ptr); goto cont; } - /* Locate unicast link endpoint that should handle message */ + /* Verify that communication with node is currently allowed */ - l_ptr = n_ptr->links[b_ptr->identity]; - if (unlikely(!l_ptr)) { + if ((n_ptr->block_setup & WAIT_PEER_DOWN) && + msg_user(msg) == LINK_PROTOCOL && + (msg_type(msg) == RESET_MSG || + msg_type(msg) == ACTIVATE_MSG) && + !msg_redundant_link(msg)) + n_ptr->block_setup &= ~WAIT_PEER_DOWN; + + if (n_ptr->block_setup) { tipc_node_unlock(n_ptr); goto cont; } @@ -1923,6 +1956,12 @@ void tipc_link_send_proto_msg(struct link *l_ptr, u32 msg_typ, int probe_msg, if (link_blocked(l_ptr)) return; + + /* Abort non-RESET send if communication with node is prohibited */ + + if ((l_ptr->owner->block_setup) && (msg_typ != RESET_MSG)) + return; + msg_set_type(msg, msg_typ); msg_set_net_plane(msg, l_ptr->b_ptr->net_plane); msg_set_bcast_ack(msg, mod(l_ptr->owner->bclink.last_in)); @@ -2051,9 +2090,19 @@ static void link_recv_proto_msg(struct link *l_ptr, struct sk_buff *buf) case RESET_MSG: if (!link_working_unknown(l_ptr) && (l_ptr->peer_session != INVALID_SESSION)) { - if (msg_session(msg) == l_ptr->peer_session) - break; /* duplicate: ignore */ + if (less_eq(msg_session(msg), l_ptr->peer_session)) + break; /* duplicate or old reset: ignore */ + } + + if (!msg_redundant_link(msg) && (link_working_working(l_ptr) || + link_working_unknown(l_ptr))) { + /* + * peer has lost contact -- don't allow peer's links + * to reactivate before we recognize loss & clean up + */ + l_ptr->owner->block_setup = WAIT_NODE_DOWN; } + /* fall thru' */ case ACTIVATE_MSG: /* Update link settings according other endpoint's values */ diff --git a/net/tipc/link.h b/net/tipc/link.h index 74fbeca..e56cb53 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -223,6 +223,7 @@ struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, int req_tlv_s struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_space); void tipc_link_reset(struct link *l_ptr); int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector); +void tipc_link_send_names(struct list_head *message_list, u32 dest); int tipc_link_send_buf(struct link *l_ptr, struct sk_buff *buf); u32 tipc_link_get_max_pkt(u32 dest, u32 selector); int tipc_link_send_sections_fast(struct tipc_port *sender, diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index cd356e5..b7ca1bd 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -173,18 +173,40 @@ void tipc_named_withdraw(struct publication *publ) * tipc_named_node_up - tell specified node about all publications by this node */ -void tipc_named_node_up(unsigned long node) +void tipc_named_node_up(unsigned long nodearg) { + struct tipc_node *n_ptr; + struct link *l_ptr; struct publication *publ; struct distr_item *item = NULL; struct sk_buff *buf = NULL; + struct list_head message_list; + u32 node = (u32)nodearg; u32 left = 0; u32 rest; - u32 max_item_buf; + u32 max_item_buf = 0; + + /* compute maximum amount of publication data to send per message */ + + read_lock_bh(&tipc_net_lock); + n_ptr = tipc_node_find(node); + if (n_ptr) { + tipc_node_lock(n_ptr); + l_ptr = n_ptr->active_links[0]; + if (l_ptr) + max_item_buf = ((l_ptr->max_pkt - INT_H_SIZE) / + ITEM_SIZE) * ITEM_SIZE; + tipc_node_unlock(n_ptr); + } + read_unlock_bh(&tipc_net_lock); + if (!max_item_buf) + return; + + /* create list of publication messages, then send them as a unit */ + + INIT_LIST_HEAD(&message_list); read_lock_bh(&tipc_nametbl_lock); - max_item_buf = TIPC_MAX_USER_MSG_SIZE / ITEM_SIZE; - max_item_buf *= ITEM_SIZE; rest = publ_cnt * ITEM_SIZE; list_for_each_entry(publ, &publ_root, local_list) { @@ -202,13 +224,14 @@ void tipc_named_node_up(unsigned long node) item++; left -= ITEM_SIZE; if (!left) { - msg_set_link_selector(buf_msg(buf), node); - tipc_link_send(buf, node, node); + list_add_tail((struct list_head *)buf, &message_list); buf = NULL; } } exit: read_unlock_bh(&tipc_nametbl_lock); + + tipc_link_send_names(&message_list, (u32)node); } /** diff --git a/net/tipc/net.c b/net/tipc/net.c index 68b3dd6..fafef6c 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -141,17 +141,6 @@ void tipc_net_route_msg(struct sk_buff *buf) return; msg = buf_msg(buf); - msg_incr_reroute_cnt(msg); - if (msg_reroute_cnt(msg) > 6) { - if (msg_errcode(msg)) { - buf_discard(buf); - } else { - tipc_reject_msg(buf, msg_destport(msg) ? - TIPC_ERR_NO_PORT : TIPC_ERR_NO_NAME); - } - return; - } - /* Handle message for this node */ dnode = msg_short(msg) ? tipc_own_addr : msg_destnode(msg); if (tipc_in_scope(dnode, tipc_own_addr)) { diff --git a/net/tipc/node.c b/net/tipc/node.c index 2d106ef..27b4bb0 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -112,6 +112,7 @@ struct tipc_node *tipc_node_create(u32 addr) break; } list_add_tail(&n_ptr->list, &temp_node->list); + n_ptr->block_setup = WAIT_PEER_DOWN; tipc_num_nodes++; @@ -312,7 +313,7 @@ static void node_established_contact(struct tipc_node *n_ptr) } } -static void node_cleanup_finished(unsigned long node_addr) +static void node_name_purge_complete(unsigned long node_addr) { struct tipc_node *n_ptr; @@ -320,7 +321,7 @@ static void node_cleanup_finished(unsigned long node_addr) n_ptr = tipc_node_find(node_addr); if (n_ptr) { tipc_node_lock(n_ptr); - n_ptr->cleanup_required = 0; + n_ptr->block_setup &= ~WAIT_NAMES_GONE; tipc_node_unlock(n_ptr); } read_unlock_bh(&tipc_net_lock); @@ -331,28 +332,32 @@ static void node_lost_contact(struct tipc_node *n_ptr) char addr_string[16]; u32 i; - /* Clean up broadcast reception remains */ - n_ptr->bclink.gap_after = n_ptr->bclink.gap_to = 0; - while (n_ptr->bclink.deferred_head) { - struct sk_buff *buf = n_ptr->bclink.deferred_head; - n_ptr->bclink.deferred_head = buf->next; - buf_discard(buf); - } - if (n_ptr->bclink.defragm) { - buf_discard(n_ptr->bclink.defragm); - n_ptr->bclink.defragm = NULL; - } + info("Lost contact with %s\n", + tipc_addr_string_fill(addr_string, n_ptr->addr)); + + /* Flush broadcast link info associated with lost node */ if (n_ptr->bclink.supported) { + n_ptr->bclink.gap_after = n_ptr->bclink.gap_to = 0; + while (n_ptr->bclink.deferred_head) { + struct sk_buff *buf = n_ptr->bclink.deferred_head; + n_ptr->bclink.deferred_head = buf->next; + buf_discard(buf); + } + + if (n_ptr->bclink.defragm) { + buf_discard(n_ptr->bclink.defragm); + n_ptr->bclink.defragm = NULL; + } + + tipc_nmap_remove(&tipc_bcast_nmap, n_ptr->addr); tipc_bclink_acknowledge(n_ptr, mod(n_ptr->bclink.acked + 10000)); - tipc_nmap_remove(&tipc_bcast_nmap, n_ptr->addr); if (n_ptr->addr < tipc_own_addr) tipc_own_tag--; - } - info("Lost contact with %s\n", - tipc_addr_string_fill(addr_string, n_ptr->addr)); + n_ptr->bclink.supported = 0; + } /* Abort link changeover */ for (i = 0; i < MAX_BEARERS; i++) { @@ -367,10 +372,10 @@ static void node_lost_contact(struct tipc_node *n_ptr) /* Notify subscribers */ tipc_nodesub_notify(n_ptr); - /* Prevent re-contact with node until all cleanup is done */ + /* Prevent re-contact with node until cleanup is done */ - n_ptr->cleanup_required = 1; - tipc_k_signal((Handler)node_cleanup_finished, n_ptr->addr); + n_ptr->block_setup = WAIT_PEER_DOWN | WAIT_NAMES_GONE; + tipc_k_signal((Handler)node_name_purge_complete, n_ptr->addr); } struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space) diff --git a/net/tipc/node.h b/net/tipc/node.h index 5c61afc..4f15cb4 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -42,6 +42,12 @@ #include "net.h" #include "bearer.h" +/* Flags used to block (re)establishment of contact with a neighboring node */ + +#define WAIT_PEER_DOWN 0x0001 /* wait to see that peer's links are down */ +#define WAIT_NAMES_GONE 0x0002 /* wait for peer's publications to be purged */ +#define WAIT_NODE_DOWN 0x0004 /* wait until peer node is declared down */ + /** * struct tipc_node - TIPC node structure * @addr: network address of node @@ -52,7 +58,7 @@ * @active_links: pointers to active links to node * @links: pointers to all links to node * @working_links: number of working links to node (both active and standby) - * @cleanup_required: non-zero if cleaning up after a prior loss of contact + * @block_setup: bit mask of conditions preventing link establishment to node * @link_cnt: number of links to node * @permit_changeover: non-zero if node has redundant links to this system * @bclink: broadcast-related info @@ -77,7 +83,7 @@ struct tipc_node { struct link *links[MAX_BEARERS]; int link_cnt; int working_links; - int cleanup_required; + int block_setup; int permit_changeover; struct { int supported; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index adb2eff..9440a3d 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -49,7 +49,7 @@ struct tipc_sock { struct sock sk; struct tipc_port *p; struct tipc_portid peer_name; - long conn_timeout; + unsigned int conn_timeout; }; #define tipc_sk(sk) ((struct tipc_sock *)(sk)) @@ -231,7 +231,7 @@ static int tipc_create(struct net *net, struct socket *sock, int protocol, sock_init_data(sock, sk); sk->sk_backlog_rcv = backlog_rcv; tipc_sk(sk)->p = tp_ptr; - tipc_sk(sk)->conn_timeout = msecs_to_jiffies(CONN_TIMEOUT_DEFAULT); + tipc_sk(sk)->conn_timeout = CONN_TIMEOUT_DEFAULT; spin_unlock_bh(tp_ptr->lock); @@ -525,6 +525,7 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, struct tipc_port *tport = tipc_sk_port(sk); struct sockaddr_tipc *dest = (struct sockaddr_tipc *)m->msg_name; int needs_conn; + long timeout_val; int res = -EINVAL; if (unlikely(!dest)) @@ -564,6 +565,8 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, reject_rx_queue(sk); } + timeout_val = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); + do { if (dest->addrtype == TIPC_ADDR_NAME) { res = dest_name_check(dest, m); @@ -600,16 +603,14 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, sock->state = SS_CONNECTING; break; } - if (m->msg_flags & MSG_DONTWAIT) { - res = -EWOULDBLOCK; + if (timeout_val <= 0L) { + res = timeout_val ? timeout_val : -EWOULDBLOCK; break; } release_sock(sk); - res = wait_event_interruptible(*sk_sleep(sk), - !tport->congested); + timeout_val = wait_event_interruptible_timeout(*sk_sleep(sk), + !tport->congested, timeout_val); lock_sock(sk); - if (res) - break; } while (1); exit: @@ -636,6 +637,7 @@ static int send_packet(struct kiocb *iocb, struct socket *sock, struct sock *sk = sock->sk; struct tipc_port *tport = tipc_sk_port(sk); struct sockaddr_tipc *dest = (struct sockaddr_tipc *)m->msg_name; + long timeout_val; int res; /* Handle implied connection establishment */ @@ -650,6 +652,8 @@ static int send_packet(struct kiocb *iocb, struct socket *sock, if (iocb) lock_sock(sk); + timeout_val = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); + do { if (unlikely(sock->state != SS_CONNECTED)) { if (sock->state == SS_DISCONNECTING) @@ -663,16 +667,14 @@ static int send_packet(struct kiocb *iocb, struct socket *sock, total_len); if (likely(res != -ELINKCONG)) break; - if (m->msg_flags & MSG_DONTWAIT) { - res = -EWOULDBLOCK; + if (timeout_val <= 0L) { + res = timeout_val ? timeout_val : -EWOULDBLOCK; break; } release_sock(sk); - res = wait_event_interruptible(*sk_sleep(sk), - (!tport->congested || !tport->connected)); + timeout_val = wait_event_interruptible_timeout(*sk_sleep(sk), + (!tport->congested || !tport->connected), timeout_val); lock_sock(sk); - if (res) - break; } while (1); if (iocb) @@ -1369,7 +1371,7 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, struct msghdr m = {NULL,}; struct sk_buff *buf; struct tipc_msg *msg; - long timeout; + unsigned int timeout; int res; lock_sock(sk); @@ -1434,7 +1436,8 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, res = wait_event_interruptible_timeout(*sk_sleep(sk), (!skb_queue_empty(&sk->sk_receive_queue) || (sock->state != SS_CONNECTING)), - timeout ? timeout : MAX_SCHEDULE_TIMEOUT); + timeout ? (long)msecs_to_jiffies(timeout) + : MAX_SCHEDULE_TIMEOUT); lock_sock(sk); if (res > 0) { @@ -1480,9 +1483,7 @@ static int listen(struct socket *sock, int len) lock_sock(sk); - if (sock->state == SS_READY) - res = -EOPNOTSUPP; - else if (sock->state != SS_UNCONNECTED) + if (sock->state != SS_UNCONNECTED) res = -EINVAL; else { sock->state = SS_LISTENING; @@ -1510,10 +1511,6 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) lock_sock(sk); - if (sock->state == SS_READY) { - res = -EOPNOTSUPP; - goto exit; - } if (sock->state != SS_LISTENING) { res = -EINVAL; goto exit; @@ -1696,7 +1693,7 @@ static int setsockopt(struct socket *sock, res = tipc_set_portunreturnable(tport->ref, value); break; case TIPC_CONN_TIMEOUT: - tipc_sk(sk)->conn_timeout = msecs_to_jiffies(value); + tipc_sk(sk)->conn_timeout = value; /* no need to set "res", since already 0 at this point */ break; default: @@ -1752,7 +1749,7 @@ static int getsockopt(struct socket *sock, res = tipc_portunreturnable(tport->ref, &value); break; case TIPC_CONN_TIMEOUT: - value = jiffies_to_msecs(tipc_sk(sk)->conn_timeout); + value = tipc_sk(sk)->conn_timeout; /* no need to set "res", since already 0 at this point */ break; case TIPC_NODE_RECVQ_DEPTH: @@ -1790,11 +1787,11 @@ static const struct proto_ops msg_ops = { .bind = bind, .connect = connect, .socketpair = sock_no_socketpair, - .accept = accept, + .accept = sock_no_accept, .getname = get_name, .poll = poll, .ioctl = sock_no_ioctl, - .listen = listen, + .listen = sock_no_listen, .shutdown = shutdown, .setsockopt = setsockopt, .getsockopt = getsockopt, diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 6cf7268..1983717 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -151,7 +151,7 @@ void tipc_subscr_report_overlap(struct subscription *sub, if (!must && !(sub->filter & TIPC_SUB_PORTS)) return; - sub->event_cb(sub, found_lower, found_upper, event, port_ref, node); + subscr_send_event(sub, found_lower, found_upper, event, port_ref, node); } /** @@ -365,7 +365,6 @@ static struct subscription *subscr_subscribe(struct tipc_subscr *s, subscr_terminate(subscriber); return NULL; } - sub->event_cb = subscr_send_event; INIT_LIST_HEAD(&sub->nameseq_list); list_add(&sub->subscription_list, &subscriber->subscription_list); sub->server_ref = subscriber->port_ref; diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index 45d89bf..4b06ef6 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -39,16 +39,11 @@ struct subscription; -typedef void (*tipc_subscr_event) (struct subscription *sub, - u32 found_lower, u32 found_upper, - u32 event, u32 port_ref, u32 node); - /** * struct subscription - TIPC network topology subscription object * @seq: name sequence associated with subscription * @timeout: duration of subscription (in ms) * @filter: event filtering to be done for subscription - * @event_cb: routine invoked when a subscription event is detected * @timer: timer governing subscription duration (optional) * @nameseq_list: adjacent subscriptions in name sequence's subscription list * @subscription_list: adjacent subscriptions in subscriber's subscription list @@ -61,7 +56,6 @@ struct subscription { struct tipc_name_seq seq; u32 timeout; u32 filter; - tipc_subscr_event event_cb; struct timer_list timer; struct list_head nameseq_list; struct list_head subscription_list; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ec68e1c..466fbcc 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1381,8 +1381,10 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) { int err = 0; + UNIXCB(skb).pid = get_pid(scm->pid); - UNIXCB(skb).cred = get_cred(scm->cred); + if (scm->cred) + UNIXCB(skb).cred = get_cred(scm->cred); UNIXCB(skb).fp = NULL; if (scm->fp && send_fds) err = unix_attach_fds(scm, skb); @@ -1392,6 +1394,24 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen } /* + * Some apps rely on write() giving SCM_CREDENTIALS + * We include credentials if source or destination socket + * asserted SOCK_PASSCRED. + */ +static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock, + const struct sock *other) +{ + if (UNIXCB(skb).cred) + return; + if (test_bit(SOCK_PASSCRED, &sock->flags) || + !other->sk_socket || + test_bit(SOCK_PASSCRED, &other->sk_socket->flags)) { + UNIXCB(skb).pid = get_pid(task_tgid(current)); + UNIXCB(skb).cred = get_current_cred(); + } +} + +/* * Send AF_UNIX data. */ @@ -1538,6 +1558,7 @@ restart: if (sock_flag(other, SOCK_RCVTSTAMP)) __net_timestamp(skb); + maybe_add_creds(skb, sock, other); skb_queue_tail(&other->sk_receive_queue, skb); if (max_level > unix_sk(other)->recursion_level) unix_sk(other)->recursion_level = max_level; @@ -1652,6 +1673,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, (other->sk_shutdown & RCV_SHUTDOWN)) goto pipe_err_free; + maybe_add_creds(skb, sock, other); skb_queue_tail(&other->sk_receive_queue, skb); if (max_level > unix_sk(other)->recursion_level) unix_sk(other)->recursion_level = max_level; diff --git a/net/wireless/core.c b/net/wireless/core.c index c148651..220f3bd 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -582,7 +582,7 @@ int wiphy_register(struct wiphy *wiphy) } /* set up regulatory info */ - wiphy_update_regulatory(wiphy, NL80211_REGDOM_SET_BY_CORE); + regulatory_update(wiphy, NL80211_REGDOM_SET_BY_CORE); list_add_rcu(&rdev->list, &cfg80211_rdev_list); cfg80211_rdev_list_generation++; diff --git a/net/wireless/core.h b/net/wireless/core.h index 8672e02..b9ec306 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -279,8 +279,6 @@ extern int cfg80211_dev_rename(struct cfg80211_registered_device *rdev, char *newname); void ieee80211_set_bitrate_flags(struct wiphy *wiphy); -void wiphy_update_regulatory(struct wiphy *wiphy, - enum nl80211_reg_initiator setby); void cfg80211_bss_expire(struct cfg80211_registered_device *dev); void cfg80211_bss_age(struct cfg80211_registered_device *dev, @@ -377,7 +375,8 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, struct ieee80211_channel *chan, bool offchan, enum nl80211_channel_type channel_type, bool channel_type_valid, unsigned int wait, - const u8 *buf, size_t len, u64 *cookie); + const u8 *buf, size_t len, bool no_cck, + u64 *cookie); /* SME */ int __cfg80211_connect(struct cfg80211_registered_device *rdev, @@ -408,6 +407,7 @@ void cfg80211_sme_failed_assoc(struct wireless_dev *wdev); bool cfg80211_sme_failed_reassoc(struct wireless_dev *wdev); /* internal helpers */ +bool cfg80211_supported_cipher_suite(struct wiphy *wiphy, u32 cipher); int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, bool pairwise, const u8 *mac_addr); diff --git a/net/wireless/lib80211.c b/net/wireless/lib80211.c index 3268fac..a55c27b 100644 --- a/net/wireless/lib80211.c +++ b/net/wireless/lib80211.c @@ -41,6 +41,11 @@ struct lib80211_crypto_alg { static LIST_HEAD(lib80211_crypto_algs); static DEFINE_SPINLOCK(lib80211_crypto_lock); +static void lib80211_crypt_deinit_entries(struct lib80211_crypt_info *info, + int force); +static void lib80211_crypt_quiescing(struct lib80211_crypt_info *info); +static void lib80211_crypt_deinit_handler(unsigned long data); + const char *print_ssid(char *buf, const char *ssid, u8 ssid_len) { const char *s = ssid; @@ -111,7 +116,8 @@ void lib80211_crypt_info_free(struct lib80211_crypt_info *info) } EXPORT_SYMBOL(lib80211_crypt_info_free); -void lib80211_crypt_deinit_entries(struct lib80211_crypt_info *info, int force) +static void lib80211_crypt_deinit_entries(struct lib80211_crypt_info *info, + int force) { struct lib80211_crypt_data *entry, *next; unsigned long flags; @@ -131,10 +137,9 @@ void lib80211_crypt_deinit_entries(struct lib80211_crypt_info *info, int force) } spin_unlock_irqrestore(info->lock, flags); } -EXPORT_SYMBOL(lib80211_crypt_deinit_entries); /* After this, crypt_deinit_list won't accept new members */ -void lib80211_crypt_quiescing(struct lib80211_crypt_info *info) +static void lib80211_crypt_quiescing(struct lib80211_crypt_info *info) { unsigned long flags; @@ -142,9 +147,8 @@ void lib80211_crypt_quiescing(struct lib80211_crypt_info *info) info->crypt_quiesced = 1; spin_unlock_irqrestore(info->lock, flags); } -EXPORT_SYMBOL(lib80211_crypt_quiescing); -void lib80211_crypt_deinit_handler(unsigned long data) +static void lib80211_crypt_deinit_handler(unsigned long data) { struct lib80211_crypt_info *info = (struct lib80211_crypt_info *)data; unsigned long flags; @@ -160,7 +164,6 @@ void lib80211_crypt_deinit_handler(unsigned long data) } spin_unlock_irqrestore(info->lock, flags); } -EXPORT_SYMBOL(lib80211_crypt_deinit_handler); void lib80211_crypt_delayed_deinit(struct lib80211_crypt_info *info, struct lib80211_crypt_data **crypt) diff --git a/net/wireless/lib80211_crypt_ccmp.c b/net/wireless/lib80211_crypt_ccmp.c index dacb3b4..755738d 100644 --- a/net/wireless/lib80211_crypt_ccmp.c +++ b/net/wireless/lib80211_crypt_ccmp.c @@ -77,8 +77,6 @@ static void *lib80211_ccmp_init(int key_idx) priv->tfm = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(priv->tfm)) { - printk(KERN_DEBUG "lib80211_crypt_ccmp: could not allocate " - "crypto API aes\n"); priv->tfm = NULL; goto fail; } diff --git a/net/wireless/lib80211_crypt_tkip.c b/net/wireless/lib80211_crypt_tkip.c index 7ea4f2b..3873484 100644 --- a/net/wireless/lib80211_crypt_tkip.c +++ b/net/wireless/lib80211_crypt_tkip.c @@ -101,7 +101,6 @@ static void *lib80211_tkip_init(int key_idx) priv->tx_tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(priv->tx_tfm_arc4)) { - printk(KERN_DEBUG pr_fmt("could not allocate crypto API arc4\n")); priv->tx_tfm_arc4 = NULL; goto fail; } @@ -109,7 +108,6 @@ static void *lib80211_tkip_init(int key_idx) priv->tx_tfm_michael = crypto_alloc_hash("michael_mic", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(priv->tx_tfm_michael)) { - printk(KERN_DEBUG pr_fmt("could not allocate crypto API michael_mic\n")); priv->tx_tfm_michael = NULL; goto fail; } @@ -117,7 +115,6 @@ static void *lib80211_tkip_init(int key_idx) priv->rx_tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(priv->rx_tfm_arc4)) { - printk(KERN_DEBUG pr_fmt("could not allocate crypto API arc4\n")); priv->rx_tfm_arc4 = NULL; goto fail; } @@ -125,7 +122,6 @@ static void *lib80211_tkip_init(int key_idx) priv->rx_tfm_michael = crypto_alloc_hash("michael_mic", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(priv->rx_tfm_michael)) { - printk(KERN_DEBUG pr_fmt("could not allocate crypto API michael_mic\n")); priv->rx_tfm_michael = NULL; goto fail; } diff --git a/net/wireless/lib80211_crypt_wep.c b/net/wireless/lib80211_crypt_wep.c index 2f265e0..c130401 100644 --- a/net/wireless/lib80211_crypt_wep.c +++ b/net/wireless/lib80211_crypt_wep.c @@ -50,16 +50,12 @@ static void *lib80211_wep_init(int keyidx) priv->tx_tfm = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(priv->tx_tfm)) { - printk(KERN_DEBUG "lib80211_crypt_wep: could not allocate " - "crypto API arc4\n"); priv->tx_tfm = NULL; goto fail; } priv->rx_tfm = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(priv->rx_tfm)) { - printk(KERN_DEBUG "lib80211_crypt_wep: could not allocate " - "crypto API arc4\n"); priv->rx_tfm = NULL; goto fail; } diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index 5c11608..4423e64 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -12,6 +12,7 @@ #define MESH_HOLD_T 100 #define MESH_PATH_TIMEOUT 5000 +#define MESH_RANN_INTERVAL 5000 /* * Minimum interval between two consecutive PREQs originated by the same @@ -49,6 +50,8 @@ const struct mesh_config default_mesh_config = { .dot11MeshHWMPmaxPREQretries = MESH_MAX_PREQ_RETRIES, .path_refresh_time = MESH_PATH_REFRESH_TIME, .min_discovery_timeout = MESH_MIN_DISCOVERY_TIMEOUT, + .dot11MeshHWMPRannInterval = MESH_RANN_INTERVAL, + .dot11MeshGateAnnouncementProtocol = false, }; const struct mesh_setup default_mesh_setup = { diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 832f657..21fc970 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -900,7 +900,8 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, struct ieee80211_channel *chan, bool offchan, enum nl80211_channel_type channel_type, bool channel_type_valid, unsigned int wait, - const u8 *buf, size_t len, u64 *cookie) + const u8 *buf, size_t len, bool no_cck, + u64 *cookie) { struct wireless_dev *wdev = dev->ieee80211_ptr; const struct ieee80211_mgmt *mgmt; @@ -991,7 +992,7 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, /* Transmit the Action frame as requested by user space */ return rdev->ops->mgmt_tx(&rdev->wiphy, dev, chan, offchan, channel_type, channel_type_valid, - wait, buf, len, cookie); + wait, buf, len, no_cck, cookie); } bool cfg80211_rx_mgmt(struct net_device *dev, int freq, const u8 *buf, @@ -1095,3 +1096,14 @@ void cfg80211_gtk_rekey_notify(struct net_device *dev, const u8 *bssid, nl80211_gtk_rekey_notify(rdev, dev, bssid, replay_ctr, gfp); } EXPORT_SYMBOL(cfg80211_gtk_rekey_notify); + +void cfg80211_pmksa_candidate_notify(struct net_device *dev, int index, + const u8 *bssid, bool preauth, gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + + nl80211_pmksa_candidate_notify(rdev, dev, index, bssid, preauth, gfp); +} +EXPORT_SYMBOL(cfg80211_pmksa_candidate_notify); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ea40d54..48260c2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -23,6 +23,12 @@ #include "nl80211.h" #include "reg.h" +static bool nl80211_valid_auth_type(enum nl80211_auth_type auth_type); +static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, + struct genl_info *info, + struct cfg80211_crypto_settings *settings, + int cipher_limit); + static int nl80211_pre_doit(struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info); static void nl80211_post_doit(struct genl_ops *ops, struct sk_buff *skb, @@ -178,6 +184,19 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_SCHED_SCAN_INTERVAL] = { .type = NLA_U32 }, [NL80211_ATTR_REKEY_DATA] = { .type = NLA_NESTED }, [NL80211_ATTR_SCAN_SUPP_RATES] = { .type = NLA_NESTED }, + [NL80211_ATTR_HIDDEN_SSID] = { .type = NLA_U32 }, + [NL80211_ATTR_IE_PROBE_RESP] = { .type = NLA_BINARY, + .len = IEEE80211_MAX_DATA_LEN }, + [NL80211_ATTR_IE_ASSOC_RESP] = { .type = NLA_BINARY, + .len = IEEE80211_MAX_DATA_LEN }, + [NL80211_ATTR_ROAM_SUPPORT] = { .type = NLA_FLAG }, + [NL80211_ATTR_SCHED_SCAN_MATCH] = { .type = NLA_NESTED }, + [NL80211_ATTR_TX_NO_CCK_RATE] = { .type = NLA_FLAG }, + [NL80211_ATTR_TDLS_ACTION] = { .type = NLA_U8 }, + [NL80211_ATTR_TDLS_DIALOG_TOKEN] = { .type = NLA_U8 }, + [NL80211_ATTR_TDLS_OPERATION] = { .type = NLA_U8 }, + [NL80211_ATTR_TDLS_SUPPORT] = { .type = NLA_FLAG }, + [NL80211_ATTR_TDLS_EXTERNAL_SETUP] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -220,6 +239,12 @@ nl80211_rekey_policy[NUM_NL80211_REKEY_DATA] = { [NL80211_REKEY_DATA_REPLAY_CTR] = { .len = NL80211_REPLAY_CTR_LEN }, }; +static const struct nla_policy +nl80211_match_policy[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1] = { + [NL80211_ATTR_SCHED_SCAN_MATCH_SSID] = { .type = NLA_BINARY, + .len = IEEE80211_MAX_SSID_LEN }, +}; + /* ifidx get helper */ static int nl80211_get_ifidx(struct netlink_callback *cb) { @@ -703,11 +728,21 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, dev->wiphy.max_scan_ie_len); NLA_PUT_U16(msg, NL80211_ATTR_MAX_SCHED_SCAN_IE_LEN, dev->wiphy.max_sched_scan_ie_len); + NLA_PUT_U8(msg, NL80211_ATTR_MAX_MATCH_SETS, + dev->wiphy.max_match_sets); if (dev->wiphy.flags & WIPHY_FLAG_IBSS_RSN) NLA_PUT_FLAG(msg, NL80211_ATTR_SUPPORT_IBSS_RSN); if (dev->wiphy.flags & WIPHY_FLAG_MESH_AUTH) NLA_PUT_FLAG(msg, NL80211_ATTR_SUPPORT_MESH_AUTH); + if (dev->wiphy.flags & WIPHY_FLAG_AP_UAPSD) + NLA_PUT_FLAG(msg, NL80211_ATTR_SUPPORT_AP_UAPSD); + if (dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_FW_ROAM) + NLA_PUT_FLAG(msg, NL80211_ATTR_ROAM_SUPPORT); + if (dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) + NLA_PUT_FLAG(msg, NL80211_ATTR_TDLS_SUPPORT); + if (dev->wiphy.flags & WIPHY_FLAG_TDLS_EXTERNAL_SETUP) + NLA_PUT_FLAG(msg, NL80211_ATTR_TDLS_EXTERNAL_SETUP); NLA_PUT(msg, NL80211_ATTR_CIPHER_SUITES, sizeof(u32) * dev->wiphy.n_cipher_suites, @@ -850,6 +885,10 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, } CMD(set_channel, SET_CHANNEL); CMD(set_wds_peer, SET_WDS_PEER); + if (dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) { + CMD(tdls_mgmt, TDLS_MGMT); + CMD(tdls_oper, TDLS_OPER); + } if (dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) CMD(sched_scan_start, START_SCHED_SCAN); @@ -871,8 +910,7 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, NLA_PUT_U32(msg, NL80211_ATTR_MAX_REMAIN_ON_CHANNEL_DURATION, dev->wiphy.max_remain_on_channel_duration); - /* for now at least assume all drivers have it */ - if (dev->ops->mgmt_tx) + if (dev->ops->mgmt_tx_cancel_wait) NLA_PUT_FLAG(msg, NL80211_ATTR_OFFCHANNEL_TX_OK); if (mgmt_stypes) { @@ -1210,6 +1248,11 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) goto bad_res; } + if (!netdev) { + result = -EINVAL; + goto bad_res; + } + nla_for_each_nested(nl_txq_params, info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS], rem_txq_params) { @@ -1222,6 +1265,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) goto bad_res; result = rdev->ops->set_txq_params(&rdev->wiphy, + netdev, &txq_params); if (result) goto bad_res; @@ -1985,7 +2029,10 @@ static int nl80211_addset_beacon(struct sk_buff *skb, struct genl_info *info) struct beacon_parameters params; int haveinfo = 0, err; - if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_BEACON_TAIL])) + if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_BEACON_TAIL]) || + !is_valid_ie_attr(info->attrs[NL80211_ATTR_IE]) || + !is_valid_ie_attr(info->attrs[NL80211_ATTR_IE_PROBE_RESP]) || + !is_valid_ie_attr(info->attrs[NL80211_ATTR_IE_ASSOC_RESP])) return -EINVAL; if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && @@ -2011,6 +2058,49 @@ static int nl80211_addset_beacon(struct sk_buff *skb, struct genl_info *info) if (err) return err; + /* + * In theory, some of these attributes could be required for + * NEW_BEACON, but since they were not used when the command was + * originally added, keep them optional for old user space + * programs to work with drivers that do not need the additional + * information. + */ + if (info->attrs[NL80211_ATTR_SSID]) { + params.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); + params.ssid_len = + nla_len(info->attrs[NL80211_ATTR_SSID]); + if (params.ssid_len == 0 || + params.ssid_len > IEEE80211_MAX_SSID_LEN) + return -EINVAL; + } + + if (info->attrs[NL80211_ATTR_HIDDEN_SSID]) { + params.hidden_ssid = nla_get_u32( + info->attrs[NL80211_ATTR_HIDDEN_SSID]); + if (params.hidden_ssid != + NL80211_HIDDEN_SSID_NOT_IN_USE && + params.hidden_ssid != + NL80211_HIDDEN_SSID_ZERO_LEN && + params.hidden_ssid != + NL80211_HIDDEN_SSID_ZERO_CONTENTS) + return -EINVAL; + } + + params.privacy = !!info->attrs[NL80211_ATTR_PRIVACY]; + + if (info->attrs[NL80211_ATTR_AUTH_TYPE]) { + params.auth_type = nla_get_u32( + info->attrs[NL80211_ATTR_AUTH_TYPE]); + if (!nl80211_valid_auth_type(params.auth_type)) + return -EINVAL; + } else + params.auth_type = NL80211_AUTHTYPE_AUTOMATIC; + + err = nl80211_crypto_settings(rdev, info, ¶ms.crypto, + NL80211_MAX_NR_CIPHER_SUITES); + if (err) + return err; + call = rdev->ops->add_beacon; break; case NL80211_CMD_SET_BEACON: @@ -2041,6 +2131,25 @@ static int nl80211_addset_beacon(struct sk_buff *skb, struct genl_info *info) if (!haveinfo) return -EINVAL; + if (info->attrs[NL80211_ATTR_IE]) { + params.beacon_ies = nla_data(info->attrs[NL80211_ATTR_IE]); + params.beacon_ies_len = nla_len(info->attrs[NL80211_ATTR_IE]); + } + + if (info->attrs[NL80211_ATTR_IE_PROBE_RESP]) { + params.proberesp_ies = + nla_data(info->attrs[NL80211_ATTR_IE_PROBE_RESP]); + params.proberesp_ies_len = + nla_len(info->attrs[NL80211_ATTR_IE_PROBE_RESP]); + } + + if (info->attrs[NL80211_ATTR_IE_ASSOC_RESP]) { + params.assocresp_ies = + nla_data(info->attrs[NL80211_ATTR_IE_ASSOC_RESP]); + params.assocresp_ies_len = + nla_len(info->attrs[NL80211_ATTR_IE_ASSOC_RESP]); + } + err = call(&rdev->wiphy, dev, ¶ms); if (!err && params.interval) wdev->beacon_interval = params.interval; @@ -2235,8 +2344,16 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, nla_nest_end(msg, bss_param); } + if (sinfo->filled & STATION_INFO_STA_FLAGS) + NLA_PUT(msg, NL80211_STA_INFO_STA_FLAGS, + sizeof(struct nl80211_sta_flag_update), + &sinfo->sta_flags); nla_nest_end(msg, sinfoattr); + if (sinfo->filled & STATION_INFO_ASSOC_REQ_IES) + NLA_PUT(msg, NL80211_ATTR_IE, sinfo->assoc_req_ies_len, + sinfo->assoc_req_ies); + return genlmsg_end(msg, hdr); nla_put_failure: @@ -2264,6 +2381,7 @@ static int nl80211_dump_station(struct sk_buff *skb, } while (1) { + memset(&sinfo, 0, sizeof(sinfo)); err = dev->ops->dump_station(&dev->wiphy, netdev, sta_idx, mac_addr, &sinfo); if (err == -ENOENT) @@ -2416,18 +2534,25 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) break; case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_STATION: - /* disallow everything but AUTHORIZED flag */ + /* disallow things sta doesn't support */ if (params.plink_action) err = -EINVAL; if (params.vlan) err = -EINVAL; - if (params.supported_rates) + if (params.supported_rates && + !(params.sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER))) err = -EINVAL; if (params.ht_capa) err = -EINVAL; if (params.listen_interval >= 0) err = -EINVAL; - if (params.sta_flags_mask & ~BIT(NL80211_STA_FLAG_AUTHORIZED)) + if (params.sta_flags_mask & + ~(BIT(NL80211_STA_FLAG_AUTHORIZED) | + BIT(NL80211_STA_FLAG_TDLS_PEER))) + err = -EINVAL; + /* can't change the TDLS bit */ + if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)) && + (params.sta_flags_mask & BIT(NL80211_STA_FLAG_TDLS_PEER))) err = -EINVAL; break; case NL80211_IFTYPE_MESH_POINT: @@ -2465,6 +2590,12 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) return err; } +static struct nla_policy +nl80211_sta_wme_policy[NL80211_STA_WME_MAX + 1] __read_mostly = { + [NL80211_STA_WME_UAPSD_QUEUES] = { .type = NLA_U8 }, + [NL80211_STA_WME_MAX_SP] = { .type = NLA_U8 }, +}; + static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -2510,10 +2641,50 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) if (parse_station_flags(info, ¶ms)) return -EINVAL; + /* parse WME attributes if sta is WME capable */ + if ((rdev->wiphy.flags & WIPHY_FLAG_AP_UAPSD) && + (params.sta_flags_set & BIT(NL80211_STA_FLAG_WME)) && + info->attrs[NL80211_ATTR_STA_WME]) { + struct nlattr *tb[NL80211_STA_WME_MAX + 1]; + struct nlattr *nla; + + nla = info->attrs[NL80211_ATTR_STA_WME]; + err = nla_parse_nested(tb, NL80211_STA_WME_MAX, nla, + nl80211_sta_wme_policy); + if (err) + return err; + + if (tb[NL80211_STA_WME_UAPSD_QUEUES]) + params.uapsd_queues = + nla_get_u8(tb[NL80211_STA_WME_UAPSD_QUEUES]); + if (params.uapsd_queues & ~IEEE80211_WMM_IE_STA_QOSINFO_AC_MASK) + return -EINVAL; + + if (tb[NL80211_STA_WME_MAX_SP]) + params.max_sp = + nla_get_u8(tb[NL80211_STA_WME_MAX_SP]); + + if (params.max_sp & ~IEEE80211_WMM_IE_STA_QOSINFO_SP_MASK) + return -EINVAL; + + params.sta_modify_mask |= STATION_PARAM_APPLY_UAPSD; + } + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP_VLAN && dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) + return -EINVAL; + + /* + * Only managed stations can add TDLS peers, and only when the + * wiphy supports external TDLS setup. + */ + if (dev->ieee80211_ptr->iftype == NL80211_IFTYPE_STATION && + !((params.sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)) && + (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) && + (rdev->wiphy.flags & WIPHY_FLAG_TDLS_EXTERNAL_SETUP))) return -EINVAL; err = get_vlan(info, rdev, ¶ms.vlan); @@ -2955,6 +3126,10 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, cur_params.dot11MeshHWMPnetDiameterTraversalTime); NLA_PUT_U8(msg, NL80211_MESHCONF_HWMP_ROOTMODE, cur_params.dot11MeshHWMPRootMode); + NLA_PUT_U16(msg, NL80211_MESHCONF_HWMP_RANN_INTERVAL, + cur_params.dot11MeshHWMPRannInterval); + NLA_PUT_U8(msg, NL80211_MESHCONF_GATE_ANNOUNCEMENTS, + cur_params.dot11MeshGateAnnouncementProtocol); nla_nest_end(msg, pinfoattr); genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); @@ -2982,6 +3157,9 @@ static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_A [NL80211_MESHCONF_HWMP_ACTIVE_PATH_TIMEOUT] = { .type = NLA_U32 }, [NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL] = { .type = NLA_U16 }, [NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME] = { .type = NLA_U16 }, + [NL80211_MESHCONF_HWMP_ROOTMODE] = { .type = NLA_U8 }, + [NL80211_MESHCONF_HWMP_RANN_INTERVAL] = { .type = NLA_U16 }, + [NL80211_MESHCONF_GATE_ANNOUNCEMENTS] = { .type = NLA_U8 }, }; static const struct nla_policy @@ -3060,6 +3238,14 @@ do {\ dot11MeshHWMPRootMode, mask, NL80211_MESHCONF_HWMP_ROOTMODE, nla_get_u8); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, + dot11MeshHWMPRannInterval, mask, + NL80211_MESHCONF_HWMP_RANN_INTERVAL, + nla_get_u16); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, + dot11MeshGateAnnouncementProtocol, mask, + NL80211_MESHCONF_GATE_ANNOUNCEMENTS, + nla_get_u8); if (mask_out) *mask_out = mask; @@ -3477,6 +3663,9 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) } } + request->no_cck = + nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]); + request->dev = dev; request->wiphy = &rdev->wiphy; @@ -3503,10 +3692,11 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, struct net_device *dev = info->user_ptr[1]; struct nlattr *attr; struct wiphy *wiphy; - int err, tmp, n_ssids = 0, n_channels, i; + int err, tmp, n_ssids = 0, n_match_sets = 0, n_channels, i; u32 interval; enum ieee80211_band band; size_t ie_len; + struct nlattr *tb[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1]; if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) || !rdev->ops->sched_scan_start) @@ -3545,6 +3735,15 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, if (n_ssids > wiphy->max_sched_scan_ssids) return -EINVAL; + if (info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH]) + nla_for_each_nested(attr, + info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH], + tmp) + n_match_sets++; + + if (n_match_sets > wiphy->max_match_sets) + return -EINVAL; + if (info->attrs[NL80211_ATTR_IE]) ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); else @@ -3562,6 +3761,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, request = kzalloc(sizeof(*request) + sizeof(*request->ssids) * n_ssids + + sizeof(*request->match_sets) * n_match_sets + sizeof(*request->channels) * n_channels + ie_len, GFP_KERNEL); if (!request) { @@ -3579,6 +3779,18 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, request->ie = (void *)(request->channels + n_channels); } + if (n_match_sets) { + if (request->ie) + request->match_sets = (void *)(request->ie + ie_len); + else if (request->ssids) + request->match_sets = + (void *)(request->ssids + n_ssids); + else + request->match_sets = + (void *)(request->channels + n_channels); + } + request->n_match_sets = n_match_sets; + i = 0; if (info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]) { /* user specified, bail out if channel not found */ @@ -3643,6 +3855,31 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, } } + i = 0; + if (info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH]) { + nla_for_each_nested(attr, + info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH], + tmp) { + struct nlattr *ssid; + + nla_parse(tb, NL80211_SCHED_SCAN_MATCH_ATTR_MAX, + nla_data(attr), nla_len(attr), + nl80211_match_policy); + ssid = tb[NL80211_ATTR_SCHED_SCAN_MATCH_SSID]; + if (ssid) { + if (nla_len(ssid) > IEEE80211_MAX_SSID_LEN) { + err = -EINVAL; + goto out_free; + } + memcpy(request->match_sets[i].ssid.ssid, + nla_data(ssid), nla_len(ssid)); + request->match_sets[i].ssid.ssid_len = + nla_len(ssid); + } + i++; + } + } + if (info->attrs[NL80211_ATTR_IE]) { request->ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); memcpy((void *)request->ie, @@ -3935,22 +4172,6 @@ static bool nl80211_valid_wpa_versions(u32 wpa_versions) NL80211_WPA_VERSION_2)); } -static bool nl80211_valid_akm_suite(u32 akm) -{ - return akm == WLAN_AKM_SUITE_8021X || - akm == WLAN_AKM_SUITE_PSK; -} - -static bool nl80211_valid_cipher_suite(u32 cipher) -{ - return cipher == WLAN_CIPHER_SUITE_WEP40 || - cipher == WLAN_CIPHER_SUITE_WEP104 || - cipher == WLAN_CIPHER_SUITE_TKIP || - cipher == WLAN_CIPHER_SUITE_CCMP || - cipher == WLAN_CIPHER_SUITE_AES_CMAC; -} - - static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -4083,7 +4304,8 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, memcpy(settings->ciphers_pairwise, data, len); for (i = 0; i < settings->n_ciphers_pairwise; i++) - if (!nl80211_valid_cipher_suite( + if (!cfg80211_supported_cipher_suite( + &rdev->wiphy, settings->ciphers_pairwise[i])) return -EINVAL; } @@ -4091,7 +4313,8 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, if (info->attrs[NL80211_ATTR_CIPHER_SUITE_GROUP]) { settings->cipher_group = nla_get_u32(info->attrs[NL80211_ATTR_CIPHER_SUITE_GROUP]); - if (!nl80211_valid_cipher_suite(settings->cipher_group)) + if (!cfg80211_supported_cipher_suite(&rdev->wiphy, + settings->cipher_group)) return -EINVAL; } @@ -4104,7 +4327,7 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, if (info->attrs[NL80211_ATTR_AKM_SUITES]) { void *data; - int len, i; + int len; data = nla_data(info->attrs[NL80211_ATTR_AKM_SUITES]); len = nla_len(info->attrs[NL80211_ATTR_AKM_SUITES]); @@ -4117,10 +4340,6 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, return -EINVAL; memcpy(settings->akm_suites, data, len); - - for (i = 0; i < settings->n_akm_suites; i++) - if (!nl80211_valid_akm_suite(settings->akm_suites[i])) - return -EINVAL; } return 0; @@ -4339,8 +4558,12 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) wiphy = &rdev->wiphy; - if (info->attrs[NL80211_ATTR_MAC]) + if (info->attrs[NL80211_ATTR_MAC]) { ibss.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); + + if (!is_valid_ether_addr(ibss.bssid)) + return -EINVAL; + } ibss.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); ibss.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); @@ -4777,6 +5000,57 @@ static int nl80211_flush_pmksa(struct sk_buff *skb, struct genl_info *info) return rdev->ops->flush_pmksa(&rdev->wiphy, dev); } +static int nl80211_tdls_mgmt(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + u8 action_code, dialog_token; + u16 status_code; + u8 *peer; + + if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) || + !rdev->ops->tdls_mgmt) + return -EOPNOTSUPP; + + if (!info->attrs[NL80211_ATTR_TDLS_ACTION] || + !info->attrs[NL80211_ATTR_STATUS_CODE] || + !info->attrs[NL80211_ATTR_TDLS_DIALOG_TOKEN] || + !info->attrs[NL80211_ATTR_IE] || + !info->attrs[NL80211_ATTR_MAC]) + return -EINVAL; + + peer = nla_data(info->attrs[NL80211_ATTR_MAC]); + action_code = nla_get_u8(info->attrs[NL80211_ATTR_TDLS_ACTION]); + status_code = nla_get_u16(info->attrs[NL80211_ATTR_STATUS_CODE]); + dialog_token = nla_get_u8(info->attrs[NL80211_ATTR_TDLS_DIALOG_TOKEN]); + + return rdev->ops->tdls_mgmt(&rdev->wiphy, dev, peer, action_code, + dialog_token, status_code, + nla_data(info->attrs[NL80211_ATTR_IE]), + nla_len(info->attrs[NL80211_ATTR_IE])); +} + +static int nl80211_tdls_oper(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + enum nl80211_tdls_operation operation; + u8 *peer; + + if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) || + !rdev->ops->tdls_oper) + return -EOPNOTSUPP; + + if (!info->attrs[NL80211_ATTR_TDLS_OPERATION] || + !info->attrs[NL80211_ATTR_MAC]) + return -EINVAL; + + operation = nla_get_u8(info->attrs[NL80211_ATTR_TDLS_OPERATION]); + peer = nla_data(info->attrs[NL80211_ATTR_MAC]); + + return rdev->ops->tdls_oper(&rdev->wiphy, dev, peer, operation); +} + static int nl80211_remain_on_channel(struct sk_buff *skb, struct genl_info *info) { @@ -4997,6 +5271,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) struct sk_buff *msg; unsigned int wait = 0; bool offchan; + bool no_cck; if (!info->attrs[NL80211_ATTR_FRAME] || !info->attrs[NL80211_ATTR_WIPHY_FREQ]) @@ -5033,6 +5308,8 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) offchan = info->attrs[NL80211_ATTR_OFFCHANNEL_TX_OK]; + no_cck = nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]); + freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); chan = rdev_freq_to_chan(rdev, freq, channel_type); if (chan == NULL) @@ -5053,7 +5330,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) channel_type_valid, wait, nla_data(info->attrs[NL80211_ATTR_FRAME]), nla_len(info->attrs[NL80211_ATTR_FRAME]), - &cookie); + no_cck, &cookie); if (err) goto free_msg; @@ -6089,6 +6366,22 @@ static struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_TDLS_MGMT, + .doit = nl80211_tdls_mgmt, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, + { + .cmd = NL80211_CMD_TDLS_OPER, + .doit = nl80211_tdls_oper, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, }; static struct genl_multicast_group nl80211_mlme_mcgrp = { @@ -7078,6 +7371,52 @@ void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev, nlmsg_free(msg); } +void nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev, + struct net_device *netdev, int index, + const u8 *bssid, bool preauth, gfp_t gfp) +{ + struct sk_buff *msg; + struct nlattr *attr; + void *hdr; + + msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_PMKSA_CANDIDATE); + if (!hdr) { + nlmsg_free(msg); + return; + } + + NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); + NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); + + attr = nla_nest_start(msg, NL80211_ATTR_PMKSA_CANDIDATE); + if (!attr) + goto nla_put_failure; + + NLA_PUT_U32(msg, NL80211_PMKSA_CANDIDATE_INDEX, index); + NLA_PUT(msg, NL80211_PMKSA_CANDIDATE_BSSID, ETH_ALEN, bssid); + if (preauth) + NLA_PUT_FLAG(msg, NL80211_PMKSA_CANDIDATE_PREAUTH); + + nla_nest_end(msg, attr); + + if (genlmsg_end(msg, hdr) < 0) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + void nl80211_send_cqm_pktloss_notify(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *peer, diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 5d69c56..f24a1fb 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -113,4 +113,8 @@ void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *bssid, const u8 *replay_ctr, gfp_t gfp); +void nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev, + struct net_device *netdev, int index, + const u8 *bssid, bool preauth, gfp_t gfp); + #endif /* __NET_WIRELESS_NL80211_H */ diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 68a471b..2520a1b 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -49,10 +49,8 @@ #include "nl80211.h" #ifdef CONFIG_CFG80211_REG_DEBUG -#define REG_DBG_PRINT(format, args...) \ - do { \ - printk(KERN_DEBUG pr_fmt(format), ##args); \ - } while (0) +#define REG_DBG_PRINT(format, args...) \ + printk(KERN_DEBUG pr_fmt(format), ##args) #else #define REG_DBG_PRINT(args...) #endif @@ -753,9 +751,10 @@ static void chan_reg_rule_print_dbg(struct ieee80211_channel *chan, chan->center_freq, KHZ_TO_MHZ(desired_bw_khz)); - REG_DBG_PRINT("%d KHz - %d KHz @ KHz), (%s mBi, %d mBm)\n", + REG_DBG_PRINT("%d KHz - %d KHz @ %d KHz), (%s mBi, %d mBm)\n", freq_range->start_freq_khz, freq_range->end_freq_khz, + freq_range->max_bandwidth_khz, max_antenna_gain, power_rule->max_eirp); } @@ -891,7 +890,7 @@ static bool ignore_reg_update(struct wiphy *wiphy, wiphy->flags & WIPHY_FLAG_CUSTOM_REGULATORY) { REG_DBG_PRINT("Ignoring regulatory request %s " "since the driver uses its own custom " - "regulatory domain ", + "regulatory domain\n", reg_initiator_name(initiator)); return true; } @@ -905,7 +904,7 @@ static bool ignore_reg_update(struct wiphy *wiphy, !is_world_regdom(last_request->alpha2)) { REG_DBG_PRINT("Ignoring regulatory request %s " "since the driver requires its own regulatory " - "domain to be set first", + "domain to be set first\n", reg_initiator_name(initiator)); return true; } @@ -913,14 +912,6 @@ static bool ignore_reg_update(struct wiphy *wiphy, return false; } -static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator) -{ - struct cfg80211_registered_device *rdev; - - list_for_each_entry(rdev, &cfg80211_rdev_list, list) - wiphy_update_regulatory(&rdev->wiphy, initiator); -} - static void handle_reg_beacon(struct wiphy *wiphy, unsigned int chan_idx, struct reg_beacon *reg_beacon) @@ -1120,11 +1111,13 @@ static void reg_process_ht_flags(struct wiphy *wiphy) } -void wiphy_update_regulatory(struct wiphy *wiphy, - enum nl80211_reg_initiator initiator) +static void wiphy_update_regulatory(struct wiphy *wiphy, + enum nl80211_reg_initiator initiator) { enum ieee80211_band band; + assert_reg_lock(); + if (ignore_reg_update(wiphy, initiator)) return; @@ -1139,6 +1132,22 @@ void wiphy_update_regulatory(struct wiphy *wiphy, wiphy->reg_notifier(wiphy, last_request); } +void regulatory_update(struct wiphy *wiphy, + enum nl80211_reg_initiator setby) +{ + mutex_lock(®_mutex); + wiphy_update_regulatory(wiphy, setby); + mutex_unlock(®_mutex); +} + +static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator) +{ + struct cfg80211_registered_device *rdev; + + list_for_each_entry(rdev, &cfg80211_rdev_list, list) + wiphy_update_regulatory(&rdev->wiphy, initiator); +} + static void handle_channel_custom(struct wiphy *wiphy, enum ieee80211_band band, unsigned int chan_idx, @@ -1475,7 +1484,7 @@ static void reg_process_pending_hints(void) /* When last_request->processed becomes true this will be rescheduled */ if (last_request && !last_request->processed) { REG_DBG_PRINT("Pending regulatory request, waiting " - "for it to be processed..."); + "for it to be processed...\n"); goto out; } @@ -2188,7 +2197,7 @@ out: static void reg_timeout_work(struct work_struct *work) { REG_DBG_PRINT("Timeout while waiting for CRDA to reply, " - "restoring regulatory settings"); + "restoring regulatory settings\n"); restore_regulatory_settings(true); } diff --git a/net/wireless/reg.h b/net/wireless/reg.h index b67d1c3..4a56799 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -16,6 +16,8 @@ void regulatory_exit(void); int set_regdom(const struct ieee80211_regdomain *rd); +void regulatory_update(struct wiphy *wiphy, enum nl80211_reg_initiator setby); + /** * regulatory_hint_found_beacon - hints a beacon was found on a channel * @wiphy: the wireless device where the beacon was found on diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 2936cb8..0fb1424 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -12,6 +12,7 @@ #include <linux/etherdevice.h> #include <net/arp.h> #include <net/cfg80211.h> +#include <net/cfg80211-wext.h> #include <net/iw_handler.h> #include "core.h" #include "nl80211.h" @@ -227,6 +228,33 @@ const u8 *cfg80211_find_ie(u8 eid, const u8 *ies, int len) } EXPORT_SYMBOL(cfg80211_find_ie); +const u8 *cfg80211_find_vendor_ie(unsigned int oui, u8 oui_type, + const u8 *ies, int len) +{ + struct ieee80211_vendor_ie *ie; + const u8 *pos = ies, *end = ies + len; + int ie_oui; + + while (pos < end) { + pos = cfg80211_find_ie(WLAN_EID_VENDOR_SPECIFIC, pos, + end - pos); + if (!pos) + return NULL; + + if (end - pos < sizeof(*ie)) + return NULL; + + ie = (struct ieee80211_vendor_ie *)pos; + ie_oui = ie->oui[0] << 16 | ie->oui[1] << 8 | ie->oui[2]; + if (ie_oui == oui && ie->oui_type == oui_type) + return pos; + + pos += 2 + ie->len; + } + return NULL; +} +EXPORT_SYMBOL(cfg80211_find_vendor_ie); + static int cmp_ies(u8 num, u8 *ies1, size_t len1, u8 *ies2, size_t len2) { const u8 *ie1 = cfg80211_find_ie(num, ies1, len1); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index dec0fa2..6e86d5a 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -110,17 +110,22 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) else { int i = 0, j; enum ieee80211_band band; + struct ieee80211_supported_band *bands; + struct ieee80211_channel *channel; for (band = 0; band < IEEE80211_NUM_BANDS; band++) { - if (!wdev->wiphy->bands[band]) + bands = wdev->wiphy->bands[band]; + if (!bands) continue; - for (j = 0; j < wdev->wiphy->bands[band]->n_channels; - i++, j++) - request->channels[i] = - &wdev->wiphy->bands[band]->channels[j]; - request->rates[band] = - (1 << wdev->wiphy->bands[band]->n_bitrates) - 1; + for (j = 0; j < bands->n_channels; j++) { + channel = &bands->channels[j]; + if (channel->flags & IEEE80211_CHAN_DISABLED) + continue; + request->channels[i++] = channel; + } + request->rates[band] = (1 << bands->n_bitrates) - 1; } + n_channels = i; } request->n_channels = n_channels; request->ssids = (void *)&request->channels[n_channels]; diff --git a/net/wireless/util.c b/net/wireless/util.c index be75a3a..2f178f7 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -6,6 +6,7 @@ #include <linux/bitops.h> #include <linux/etherdevice.h> #include <linux/slab.h> +#include <linux/crc32.h> #include <net/cfg80211.h> #include <net/ip.h> #include "core.h" @@ -150,12 +151,19 @@ void ieee80211_set_bitrate_flags(struct wiphy *wiphy) set_mandatory_flags_band(wiphy->bands[band], band); } +bool cfg80211_supported_cipher_suite(struct wiphy *wiphy, u32 cipher) +{ + int i; + for (i = 0; i < wiphy->n_cipher_suites; i++) + if (cipher == wiphy->cipher_suites[i]) + return true; + return false; +} + int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, bool pairwise, const u8 *mac_addr) { - int i; - if (key_idx > 5) return -EINVAL; @@ -225,10 +233,7 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, } } - for (i = 0; i < rdev->wiphy.n_cipher_suites; i++) - if (params->cipher == rdev->wiphy.cipher_suites[i]) - break; - if (i == rdev->wiphy.n_cipher_suites) + if (!cfg80211_supported_cipher_suite(&rdev->wiphy, params->cipher)) return -EINVAL; return 0; @@ -391,8 +396,9 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, } break; case cpu_to_le16(0): - if (iftype != NL80211_IFTYPE_ADHOC) - return -1; + if (iftype != NL80211_IFTYPE_ADHOC && + iftype != NL80211_IFTYPE_STATION) + return -1; break; } @@ -512,10 +518,9 @@ int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr, if (head_need) skb_orphan(skb); - if (pskb_expand_head(skb, head_need, 0, GFP_ATOMIC)) { - pr_err("failed to reallocate Tx buffer\n"); + if (pskb_expand_head(skb, head_need, 0, GFP_ATOMIC)) return -ENOMEM; - } + skb->truesize += head_need; } @@ -1044,3 +1049,170 @@ int ieee80211_get_ratemask(struct ieee80211_supported_band *sband, return 0; } + +u32 ieee802_11_parse_elems_crc(u8 *start, size_t len, + struct ieee802_11_elems *elems, + u64 filter, u32 crc) +{ + size_t left = len; + u8 *pos = start; + bool calc_crc = filter != 0; + + memset(elems, 0, sizeof(*elems)); + elems->ie_start = start; + elems->total_len = len; + + while (left >= 2) { + u8 id, elen; + + id = *pos++; + elen = *pos++; + left -= 2; + + if (elen > left) + break; + + if (calc_crc && id < 64 && (filter & (1ULL << id))) + crc = crc32_be(crc, pos - 2, elen + 2); + + switch (id) { + case WLAN_EID_SSID: + elems->ssid = pos; + elems->ssid_len = elen; + break; + case WLAN_EID_SUPP_RATES: + elems->supp_rates = pos; + elems->supp_rates_len = elen; + break; + case WLAN_EID_FH_PARAMS: + elems->fh_params = pos; + elems->fh_params_len = elen; + break; + case WLAN_EID_DS_PARAMS: + elems->ds_params = pos; + elems->ds_params_len = elen; + break; + case WLAN_EID_CF_PARAMS: + elems->cf_params = pos; + elems->cf_params_len = elen; + break; + case WLAN_EID_TIM: + if (elen >= sizeof(struct ieee80211_tim_ie)) { + elems->tim = (void *)pos; + elems->tim_len = elen; + } + break; + case WLAN_EID_IBSS_PARAMS: + elems->ibss_params = pos; + elems->ibss_params_len = elen; + break; + case WLAN_EID_CHALLENGE: + elems->challenge = pos; + elems->challenge_len = elen; + break; + case WLAN_EID_VENDOR_SPECIFIC: + if (elen >= 4 && pos[0] == 0x00 && pos[1] == 0x50 && + pos[2] == 0xf2) { + /* Microsoft OUI (00:50:F2) */ + + if (calc_crc) + crc = crc32_be(crc, pos - 2, elen + 2); + + if (pos[3] == 1) { + /* OUI Type 1 - WPA IE */ + elems->wpa = pos; + elems->wpa_len = elen; + } else if (elen >= 5 && pos[3] == 2) { + /* OUI Type 2 - WMM IE */ + if (pos[4] == 0) { + elems->wmm_info = pos; + elems->wmm_info_len = elen; + } else if (pos[4] == 1) { + elems->wmm_param = pos; + elems->wmm_param_len = elen; + } + } + } + break; + case WLAN_EID_RSN: + elems->rsn = pos; + elems->rsn_len = elen; + break; + case WLAN_EID_ERP_INFO: + elems->erp_info = pos; + elems->erp_info_len = elen; + break; + case WLAN_EID_EXT_SUPP_RATES: + elems->ext_supp_rates = pos; + elems->ext_supp_rates_len = elen; + break; + case WLAN_EID_HT_CAPABILITY: + if (elen >= sizeof(struct ieee80211_ht_cap)) + elems->ht_cap_elem = (void *)pos; + break; + case WLAN_EID_HT_INFORMATION: + if (elen >= sizeof(struct ieee80211_ht_info)) + elems->ht_info_elem = (void *)pos; + break; + case WLAN_EID_MESH_ID: + elems->mesh_id = pos; + elems->mesh_id_len = elen; + break; + case WLAN_EID_MESH_CONFIG: + if (elen >= sizeof(struct ieee80211_meshconf_ie)) + elems->mesh_config = (void *)pos; + break; + case WLAN_EID_PEER_MGMT: + elems->peering = pos; + elems->peering_len = elen; + break; + case WLAN_EID_PREQ: + elems->preq = pos; + elems->preq_len = elen; + break; + case WLAN_EID_PREP: + elems->prep = pos; + elems->prep_len = elen; + break; + case WLAN_EID_PERR: + elems->perr = pos; + elems->perr_len = elen; + break; + case WLAN_EID_RANN: + if (elen >= sizeof(struct ieee80211_rann_ie)) + elems->rann = (void *)pos; + break; + case WLAN_EID_CHANNEL_SWITCH: + elems->ch_switch_elem = pos; + elems->ch_switch_elem_len = elen; + break; + case WLAN_EID_QUIET: + if (!elems->quiet_elem) { + elems->quiet_elem = pos; + elems->quiet_elem_len = elen; + } + elems->num_of_quiet_elem++; + break; + case WLAN_EID_COUNTRY: + elems->country_elem = pos; + elems->country_elem_len = elen; + break; + case WLAN_EID_PWR_CONSTRAINT: + elems->pwr_constr_elem = pos; + elems->pwr_constr_elem_len = elen; + break; + case WLAN_EID_TIMEOUT_INTERVAL: + elems->timeout_int = pos; + elems->timeout_int_len = elen; + break; + default: + break; + } + + left -= elen; + pos += elen; + } + + return crc; +} +EXPORT_SYMBOL(ieee802_11_parse_elems_crc); diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 0bf169b..62f121d 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -15,6 +15,7 @@ #include <linux/slab.h> #include <net/iw_handler.h> #include <net/cfg80211.h> +#include <net/cfg80211-wext.h> #include "wext-compat.h" #include "core.h" @@ -363,9 +364,9 @@ int cfg80211_wext_giwfrag(struct net_device *dev, } EXPORT_SYMBOL_GPL(cfg80211_wext_giwfrag); -int cfg80211_wext_siwretry(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *retry, char *extra) +static int cfg80211_wext_siwretry(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *retry, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); @@ -402,7 +403,6 @@ int cfg80211_wext_siwretry(struct net_device *dev, return err; } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwretry); int cfg80211_wext_giwretry(struct net_device *dev, struct iw_request_info *info, @@ -593,9 +593,9 @@ static int cfg80211_set_encryption(struct cfg80211_registered_device *rdev, return err; } -int cfg80211_wext_siwencode(struct net_device *dev, - struct iw_request_info *info, - struct iw_point *erq, char *keybuf) +static int cfg80211_wext_siwencode(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *erq, char *keybuf) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); @@ -652,11 +652,10 @@ int cfg80211_wext_siwencode(struct net_device *dev, wdev->wext.default_key == -1, idx, ¶ms); } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwencode); -int cfg80211_wext_siwencodeext(struct net_device *dev, - struct iw_request_info *info, - struct iw_point *erq, char *extra) +static int cfg80211_wext_siwencodeext(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *erq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); @@ -744,11 +743,10 @@ int cfg80211_wext_siwencodeext(struct net_device *dev, ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY, idx, ¶ms); } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwencodeext); -int cfg80211_wext_giwencode(struct net_device *dev, - struct iw_request_info *info, - struct iw_point *erq, char *keybuf) +static int cfg80211_wext_giwencode(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *erq, char *keybuf) { struct wireless_dev *wdev = dev->ieee80211_ptr; int idx; @@ -782,11 +780,10 @@ int cfg80211_wext_giwencode(struct net_device *dev, return 0; } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwencode); -int cfg80211_wext_siwfreq(struct net_device *dev, - struct iw_request_info *info, - struct iw_freq *wextfreq, char *extra) +static int cfg80211_wext_siwfreq(struct net_device *dev, + struct iw_request_info *info, + struct iw_freq *wextfreq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); @@ -815,11 +812,10 @@ int cfg80211_wext_siwfreq(struct net_device *dev, return -EOPNOTSUPP; } } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwfreq); -int cfg80211_wext_giwfreq(struct net_device *dev, - struct iw_request_info *info, - struct iw_freq *freq, char *extra) +static int cfg80211_wext_giwfreq(struct net_device *dev, + struct iw_request_info *info, + struct iw_freq *freq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -836,11 +832,10 @@ int cfg80211_wext_giwfreq(struct net_device *dev, return 0; } } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwfreq); -int cfg80211_wext_siwtxpower(struct net_device *dev, - struct iw_request_info *info, - union iwreq_data *data, char *extra) +static int cfg80211_wext_siwtxpower(struct net_device *dev, + struct iw_request_info *info, + union iwreq_data *data, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); @@ -889,11 +884,10 @@ int cfg80211_wext_siwtxpower(struct net_device *dev, return rdev->ops->set_tx_power(wdev->wiphy, type, DBM_TO_MBM(dbm)); } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwtxpower); -int cfg80211_wext_giwtxpower(struct net_device *dev, - struct iw_request_info *info, - union iwreq_data *data, char *extra) +static int cfg80211_wext_giwtxpower(struct net_device *dev, + struct iw_request_info *info, + union iwreq_data *data, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); @@ -919,7 +913,6 @@ int cfg80211_wext_giwtxpower(struct net_device *dev, return 0; } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwtxpower); static int cfg80211_set_auth_alg(struct wireless_dev *wdev, s32 auth_alg) @@ -1070,9 +1063,9 @@ static int cfg80211_set_key_mgt(struct wireless_dev *wdev, u32 key_mgt) return 0; } -int cfg80211_wext_siwauth(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *data, char *extra) +static int cfg80211_wext_siwauth(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *data, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -1102,21 +1095,19 @@ int cfg80211_wext_siwauth(struct net_device *dev, return -EOPNOTSUPP; } } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwauth); -int cfg80211_wext_giwauth(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *data, char *extra) +static int cfg80211_wext_giwauth(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *data, char *extra) { /* XXX: what do we need? */ return -EOPNOTSUPP; } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwauth); -int cfg80211_wext_siwpower(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *wrq, char *extra) +static int cfg80211_wext_siwpower(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *wrq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); @@ -1160,11 +1151,10 @@ int cfg80211_wext_siwpower(struct net_device *dev, return 0; } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwpower); -int cfg80211_wext_giwpower(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *wrq, char *extra) +static int cfg80211_wext_giwpower(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *wrq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -1172,7 +1162,6 @@ int cfg80211_wext_giwpower(struct net_device *dev, return 0; } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwpower); static int cfg80211_wds_wext_siwap(struct net_device *dev, struct iw_request_info *info, @@ -1218,9 +1207,9 @@ static int cfg80211_wds_wext_giwap(struct net_device *dev, return 0; } -int cfg80211_wext_siwrate(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *rate, char *extra) +static int cfg80211_wext_siwrate(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *rate, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); @@ -1268,11 +1257,10 @@ int cfg80211_wext_siwrate(struct net_device *dev, return rdev->ops->set_bitrate_mask(wdev->wiphy, dev, NULL, &mask); } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwrate); -int cfg80211_wext_giwrate(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *rate, char *extra) +static int cfg80211_wext_giwrate(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *rate, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); @@ -1308,10 +1296,9 @@ int cfg80211_wext_giwrate(struct net_device *dev, return 0; } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwrate); /* Get wireless statistics. Called by /proc/net/wireless and by SIOCGIWSTATS */ -struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) +static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); @@ -1376,11 +1363,10 @@ struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) return &wstats; } -EXPORT_SYMBOL_GPL(cfg80211_wireless_stats); -int cfg80211_wext_siwap(struct net_device *dev, - struct iw_request_info *info, - struct sockaddr *ap_addr, char *extra) +static int cfg80211_wext_siwap(struct net_device *dev, + struct iw_request_info *info, + struct sockaddr *ap_addr, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -1395,11 +1381,10 @@ int cfg80211_wext_siwap(struct net_device *dev, return -EOPNOTSUPP; } } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwap); -int cfg80211_wext_giwap(struct net_device *dev, - struct iw_request_info *info, - struct sockaddr *ap_addr, char *extra) +static int cfg80211_wext_giwap(struct net_device *dev, + struct iw_request_info *info, + struct sockaddr *ap_addr, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -1414,11 +1399,10 @@ int cfg80211_wext_giwap(struct net_device *dev, return -EOPNOTSUPP; } } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwap); -int cfg80211_wext_siwessid(struct net_device *dev, - struct iw_request_info *info, - struct iw_point *data, char *ssid) +static int cfg80211_wext_siwessid(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -1431,11 +1415,10 @@ int cfg80211_wext_siwessid(struct net_device *dev, return -EOPNOTSUPP; } } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwessid); -int cfg80211_wext_giwessid(struct net_device *dev, - struct iw_request_info *info, - struct iw_point *data, char *ssid) +static int cfg80211_wext_giwessid(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -1451,11 +1434,10 @@ int cfg80211_wext_giwessid(struct net_device *dev, return -EOPNOTSUPP; } } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwessid); -int cfg80211_wext_siwpmksa(struct net_device *dev, - struct iw_request_info *info, - struct iw_point *data, char *extra) +static int cfg80211_wext_siwpmksa(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *data, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); @@ -1493,7 +1475,6 @@ int cfg80211_wext_siwpmksa(struct net_device *dev, return -EOPNOTSUPP; } } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwpmksa); static const iw_handler cfg80211_handlers[] = { [IW_IOCTL_IDX(SIOCGIWNAME)] = (iw_handler) cfg80211_wext_giwname, diff --git a/net/wireless/wext-compat.h b/net/wireless/wext-compat.h index 20b3dae..5d766b0 100644 --- a/net/wireless/wext-compat.h +++ b/net/wireless/wext-compat.h @@ -42,6 +42,14 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, struct iw_request_info *info, struct iw_point *data, char *ssid); +int cfg80211_wext_siwmlme(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *data, char *extra); +int cfg80211_wext_siwgenie(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *data, char *extra); + + int cfg80211_wext_freq(struct wiphy *wiphy, struct iw_freq *freq); diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index 6fffe62..0d4b8c3 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -9,6 +9,7 @@ #include <linux/if_arp.h> #include <linux/slab.h> #include <net/cfg80211.h> +#include <net/cfg80211-wext.h> #include "wext-compat.h" #include "nl80211.h" @@ -365,7 +366,6 @@ int cfg80211_wext_siwgenie(struct net_device *dev, wdev_unlock(wdev); return err; } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwgenie); int cfg80211_wext_siwmlme(struct net_device *dev, struct iw_request_info *info, @@ -402,4 +402,3 @@ int cfg80211_wext_siwmlme(struct net_device *dev, return err; } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwmlme); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index d306154..3e16c6a 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -91,7 +91,7 @@ int x25_parse_address_block(struct sk_buff *skb, int needed; int rc; - if (skb->len < 1) { + if (!pskb_may_pull(skb, 1)) { /* packet has no address block */ rc = 0; goto empty; @@ -100,7 +100,7 @@ int x25_parse_address_block(struct sk_buff *skb, len = *skb->data; needed = 1 + (len >> 4) + (len & 0x0f); - if (skb->len < needed) { + if (!pskb_may_pull(skb, needed)) { /* packet is too short to hold the addresses it claims to hold */ rc = -1; @@ -295,7 +295,8 @@ static struct sock *x25_find_listener(struct x25_address *addr, * Found a listening socket, now check the incoming * call user data vs this sockets call user data */ - if(skb->len > 0 && x25_sk(s)->cudmatchlength > 0) { + if (x25_sk(s)->cudmatchlength > 0 && + skb->len >= x25_sk(s)->cudmatchlength) { if((memcmp(x25_sk(s)->calluserdata.cuddata, skb->data, x25_sk(s)->cudmatchlength)) == 0) { @@ -951,14 +952,27 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, * * Facilities length is mandatory in call request packets */ - if (skb->len < 1) + if (!pskb_may_pull(skb, 1)) goto out_clear_request; len = skb->data[0] + 1; - if (skb->len < len) + if (!pskb_may_pull(skb, len)) goto out_clear_request; skb_pull(skb,len); /* + * Ensure that the amount of call user data is valid. + */ + if (skb->len > X25_MAX_CUD_LEN) + goto out_clear_request; + + /* + * Get all the call user data so it can be used in + * x25_find_listener and skb_copy_from_linear_data up ahead. + */ + if (!pskb_may_pull(skb, skb->len)) + goto out_clear_request; + + /* * Find a listener for the particular address/cud pair. */ sk = x25_find_listener(&source_addr,skb); @@ -1166,6 +1180,9 @@ static int x25_sendmsg(struct kiocb *iocb, struct socket *sock, * byte of the user data is the logical value of the Q Bit. */ if (test_bit(X25_Q_BIT_FLAG, &x25->flags)) { + if (!pskb_may_pull(skb, 1)) + goto out_kfree_skb; + qbit = skb->data[0]; skb_pull(skb, 1); } @@ -1244,12 +1261,19 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, struct x25_sock *x25 = x25_sk(sk); struct sockaddr_x25 *sx25 = (struct sockaddr_x25 *)msg->msg_name; size_t copied; - int qbit; + int qbit, header_len; struct sk_buff *skb; unsigned char *asmptr; int rc = -ENOTCONN; lock_sock(sk); + + if (x25->neighbour == NULL) + goto out; + + header_len = x25->neighbour->extended ? + X25_EXT_MIN_LEN : X25_STD_MIN_LEN; + /* * This works for seqpacket too. The receiver has ordered the queue for * us! We do one quick check first though @@ -1265,6 +1289,9 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, skb = skb_dequeue(&x25->interrupt_in_queue); + if (!pskb_may_pull(skb, X25_STD_MIN_LEN)) + goto out_free_dgram; + skb_pull(skb, X25_STD_MIN_LEN); /* @@ -1285,10 +1312,12 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) goto out; + if (!pskb_may_pull(skb, header_len)) + goto out_free_dgram; + qbit = (skb->data[0] & X25_Q_BIT) == X25_Q_BIT; - skb_pull(skb, x25->neighbour->extended ? - X25_EXT_MIN_LEN : X25_STD_MIN_LEN); + skb_pull(skb, header_len); if (test_bit(X25_Q_BIT_FLAG, &x25->flags)) { asmptr = skb_push(skb, 1); diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index e547ca1..fa2b418 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -32,6 +32,9 @@ static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb) unsigned short frametype; unsigned int lci; + if (!pskb_may_pull(skb, X25_STD_MIN_LEN)) + return 0; + frametype = skb->data[2]; lci = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF); @@ -115,6 +118,9 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev, goto drop; } + if (!pskb_may_pull(skb, 1)) + return 0; + switch (skb->data[0]) { case X25_IFACE_DATA: diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index f77e4e7..36384a1 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -44,7 +44,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, struct x25_dte_facilities *dte_facs, unsigned long *vc_fac_mask) { - unsigned char *p = skb->data; + unsigned char *p; unsigned int len; *vc_fac_mask = 0; @@ -60,14 +60,16 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, memset(dte_facs->called_ae, '\0', sizeof(dte_facs->called_ae)); memset(dte_facs->calling_ae, '\0', sizeof(dte_facs->calling_ae)); - if (skb->len < 1) + if (!pskb_may_pull(skb, 1)) return 0; - len = *p++; + len = skb->data[0]; - if (len >= skb->len) + if (!pskb_may_pull(skb, 1 + len)) return -1; + p = skb->data + 1; + while (len > 0) { switch (*p & X25_FAC_CLASS_MASK) { case X25_FAC_CLASS_A: diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index 0b073b5..a49cd4e 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -107,6 +107,8 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp /* * Parse the data in the frame. */ + if (!pskb_may_pull(skb, X25_STD_MIN_LEN)) + goto out_clear; skb_pull(skb, X25_STD_MIN_LEN); len = x25_parse_address_block(skb, &source_addr, @@ -127,9 +129,11 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp * Copy any Call User Data. */ if (skb->len > 0) { - skb_copy_from_linear_data(skb, - x25->calluserdata.cuddata, - skb->len); + if (skb->len > X25_MAX_CUD_LEN) + goto out_clear; + + skb_copy_bits(skb, 0, x25->calluserdata.cuddata, + skb->len); x25->calluserdata.cudlength = skb->len; } if (!sock_flag(sk, SOCK_DEAD)) @@ -137,6 +141,9 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp break; } case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) + goto out_clear; + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); x25_disconnect(sk, ECONNREFUSED, skb->data[3], skb->data[4]); break; @@ -164,6 +171,9 @@ static int x25_state2_machine(struct sock *sk, struct sk_buff *skb, int frametyp switch (frametype) { case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) + goto out_clear; + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); x25_disconnect(sk, 0, skb->data[3], skb->data[4]); break; @@ -177,6 +187,11 @@ static int x25_state2_machine(struct sock *sk, struct sk_buff *skb, int frametyp } return 0; + +out_clear: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25_start_t23timer(sk); + return 0; } /* @@ -206,6 +221,9 @@ static int x25_state3_machine(struct sock *sk, struct sk_buff *skb, int frametyp break; case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) + goto out_clear; + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); x25_disconnect(sk, 0, skb->data[3], skb->data[4]); break; @@ -304,6 +322,12 @@ static int x25_state3_machine(struct sock *sk, struct sk_buff *skb, int frametyp } return queued; + +out_clear: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25->state = X25_STATE_2; + x25_start_t23timer(sk); + return 0; } /* @@ -313,13 +337,13 @@ static int x25_state3_machine(struct sock *sk, struct sk_buff *skb, int frametyp */ static int x25_state4_machine(struct sock *sk, struct sk_buff *skb, int frametype) { + struct x25_sock *x25 = x25_sk(sk); + switch (frametype) { case X25_RESET_REQUEST: x25_write_internal(sk, X25_RESET_CONFIRMATION); case X25_RESET_CONFIRMATION: { - struct x25_sock *x25 = x25_sk(sk); - x25_stop_timer(sk); x25->condition = 0x00; x25->va = 0; @@ -331,6 +355,9 @@ static int x25_state4_machine(struct sock *sk, struct sk_buff *skb, int frametyp break; } case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) + goto out_clear; + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); x25_disconnect(sk, 0, skb->data[3], skb->data[4]); break; @@ -340,6 +367,12 @@ static int x25_state4_machine(struct sock *sk, struct sk_buff *skb, int frametyp } return 0; + +out_clear: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25->state = X25_STATE_2; + x25_start_t23timer(sk); + return 0; } /* Higher level upcall for a LAPB frame */ diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c index 037958f..4acacf3 100644 --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -90,6 +90,9 @@ void x25_link_control(struct sk_buff *skb, struct x25_neigh *nb, break; case X25_DIAGNOSTIC: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 4)) + break; + printk(KERN_WARNING "x25: diagnostic #%d - %02X %02X %02X\n", skb->data[3], skb->data[4], skb->data[5], skb->data[6]); diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index 24a342e..5170d52 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -269,7 +269,11 @@ int x25_decode(struct sock *sk, struct sk_buff *skb, int *ns, int *nr, int *q, int *d, int *m) { struct x25_sock *x25 = x25_sk(sk); - unsigned char *frame = skb->data; + unsigned char *frame; + + if (!pskb_may_pull(skb, X25_STD_MIN_LEN)) + return X25_ILLEGAL; + frame = skb->data; *ns = *nr = *q = *d = *m = 0; @@ -294,6 +298,10 @@ int x25_decode(struct sock *sk, struct sk_buff *skb, int *ns, int *nr, int *q, if (frame[2] == X25_RR || frame[2] == X25_RNR || frame[2] == X25_REJ) { + if (!pskb_may_pull(skb, X25_EXT_MIN_LEN)) + return X25_ILLEGAL; + frame = skb->data; + *nr = (frame[3] >> 1) & 0x7F; return frame[2]; } @@ -308,6 +316,10 @@ int x25_decode(struct sock *sk, struct sk_buff *skb, int *ns, int *nr, int *q, if (x25->neighbour->extended) { if ((frame[2] & 0x01) == X25_DATA) { + if (!pskb_may_pull(skb, X25_EXT_MIN_LEN)) + return X25_ILLEGAL; + frame = skb->data; + *q = (frame[0] & X25_Q_BIT) == X25_Q_BIT; *d = (frame[0] & X25_D_BIT) == X25_D_BIT; *m = (frame[3] & X25_EXT_M_BIT) == X25_EXT_M_BIT; diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index fc91ad7..e5246fb 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -70,26 +70,29 @@ static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb) while ((scratch += len, dlen -= len) > 0) { skb_frag_t *frag; + struct page *page; err = -EMSGSIZE; if (WARN_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) goto out; frag = skb_shinfo(skb)->frags + skb_shinfo(skb)->nr_frags; - frag->page = alloc_page(GFP_ATOMIC); + page = alloc_page(GFP_ATOMIC); err = -ENOMEM; - if (!frag->page) + if (!page) goto out; + __skb_frag_set_page(frag, page); + len = PAGE_SIZE; if (dlen < len) len = dlen; - memcpy(page_address(frag->page), scratch, len); - frag->page_offset = 0; - frag->size = len; + skb_frag_size_set(frag, len); + memcpy(skb_frag_address(frag), scratch, len); + skb->truesize += len; skb->data_len += len; skb->len += len; diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index b11ea69..6ca3574 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -203,8 +203,6 @@ static int xfrm_replay_check_bmp(struct xfrm_state *x, if (!replay_esn->replay_window) return 0; - pos = (replay_esn->seq - 1) % replay_esn->replay_window; - if (unlikely(seq == 0)) goto err; @@ -216,19 +214,18 @@ static int xfrm_replay_check_bmp(struct xfrm_state *x, goto err; } - if (pos >= diff) { + pos = (replay_esn->seq - 1) % replay_esn->replay_window; + + if (pos >= diff) bitnr = (pos - diff) % replay_esn->replay_window; - nr = bitnr >> 5; - bitnr = bitnr & 0x1F; - if (replay_esn->bmp[nr] & (1U << bitnr)) - goto err_replay; - } else { + else bitnr = replay_esn->replay_window - (diff - pos); - nr = bitnr >> 5; - bitnr = bitnr & 0x1F; - if (replay_esn->bmp[nr] & (1U << bitnr)) - goto err_replay; - } + + nr = bitnr >> 5; + bitnr = bitnr & 0x1F; + if (replay_esn->bmp[nr] & (1U << bitnr)) + goto err_replay; + return 0; err_replay: @@ -259,39 +256,27 @@ static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq) bitnr = bitnr & 0x1F; replay_esn->bmp[nr] &= ~(1U << bitnr); } - - bitnr = (pos + diff) % replay_esn->replay_window; - nr = bitnr >> 5; - bitnr = bitnr & 0x1F; - replay_esn->bmp[nr] |= (1U << bitnr); } else { nr = (replay_esn->replay_window - 1) >> 5; for (i = 0; i <= nr; i++) replay_esn->bmp[i] = 0; - - bitnr = (pos + diff) % replay_esn->replay_window; - nr = bitnr >> 5; - bitnr = bitnr & 0x1F; - replay_esn->bmp[nr] |= (1U << bitnr); } + bitnr = (pos + diff) % replay_esn->replay_window; replay_esn->seq = seq; } else { diff = replay_esn->seq - seq; - if (pos >= diff) { + if (pos >= diff) bitnr = (pos - diff) % replay_esn->replay_window; - nr = bitnr >> 5; - bitnr = bitnr & 0x1F; - replay_esn->bmp[nr] |= (1U << bitnr); - } else { + else bitnr = replay_esn->replay_window - (diff - pos); - nr = bitnr >> 5; - bitnr = bitnr & 0x1F; - replay_esn->bmp[nr] |= (1U << bitnr); - } } + nr = bitnr >> 5; + bitnr = bitnr & 0x1F; + replay_esn->bmp[nr] |= (1U << bitnr); + if (xfrm_aevent_is_on(xs_net(x))) xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } @@ -390,8 +375,6 @@ static int xfrm_replay_check_esn(struct xfrm_state *x, 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; @@ -415,19 +398,18 @@ static int xfrm_replay_check_esn(struct xfrm_state *x, goto err; } - if (pos >= diff) { + pos = (replay_esn->seq - 1) % replay_esn->replay_window; + + if (pos >= diff) bitnr = (pos - diff) % replay_esn->replay_window; - nr = bitnr >> 5; - bitnr = bitnr & 0x1F; - if (replay_esn->bmp[nr] & (1U << bitnr)) - goto err_replay; - } else { + else bitnr = replay_esn->replay_window - (diff - pos); - nr = bitnr >> 5; - bitnr = bitnr & 0x1F; - if (replay_esn->bmp[nr] & (1U << bitnr)) - goto err_replay; - } + + nr = bitnr >> 5; + bitnr = bitnr & 0x1F; + if (replay_esn->bmp[nr] & (1U << bitnr)) + goto err_replay; + return 0; err_replay: @@ -465,22 +447,13 @@ static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq) bitnr = bitnr & 0x1F; replay_esn->bmp[nr] &= ~(1U << bitnr); } - - bitnr = (pos + diff) % replay_esn->replay_window; - nr = bitnr >> 5; - bitnr = bitnr & 0x1F; - replay_esn->bmp[nr] |= (1U << bitnr); } else { nr = (replay_esn->replay_window - 1) >> 5; for (i = 0; i <= nr; i++) replay_esn->bmp[i] = 0; - - bitnr = (pos + diff) % replay_esn->replay_window; - nr = bitnr >> 5; - bitnr = bitnr & 0x1F; - replay_esn->bmp[nr] |= (1U << bitnr); } + bitnr = (pos + diff) % replay_esn->replay_window; replay_esn->seq = seq; if (unlikely(wrap > 0)) @@ -488,19 +461,16 @@ static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq) } else { diff = replay_esn->seq - seq; - if (pos >= diff) { + if (pos >= diff) bitnr = (pos - diff) % replay_esn->replay_window; - nr = bitnr >> 5; - bitnr = bitnr & 0x1F; - replay_esn->bmp[nr] |= (1U << bitnr); - } else { + else bitnr = replay_esn->replay_window - (diff - pos); - nr = bitnr >> 5; - bitnr = bitnr & 0x1F; - replay_esn->bmp[nr] |= (1U << bitnr); - } } + nr = bitnr >> 5; + bitnr = bitnr & 0x1F; + replay_esn->bmp[nr] |= (1U << bitnr); + if (xfrm_aevent_is_on(xs_net(x))) xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 0256b8a..d0a42df 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2927,7 +2927,7 @@ static int __net_init xfrm_user_net_init(struct net *net) if (nlsk == NULL) return -ENOMEM; net->xfrm.nlsk_stash = nlsk; /* Don't set to NULL */ - rcu_assign_pointer(net->xfrm.nlsk, nlsk); + RCU_INIT_POINTER(net->xfrm.nlsk, nlsk); return 0; } @@ -2935,7 +2935,7 @@ static void __net_exit xfrm_user_net_exit(struct list_head *net_exit_list) { struct net *net; list_for_each_entry(net, net_exit_list, exit_list) - rcu_assign_pointer(net->xfrm.nlsk, NULL); + RCU_INIT_POINTER(net->xfrm.nlsk, NULL); synchronize_net(); list_for_each_entry(net, net_exit_list, exit_list) netlink_kernel_release(net->xfrm.nlsk_stash); |