diff options
Diffstat (limited to 'net')
46 files changed, 810 insertions, 548 deletions
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index f1f2f7bb6661..163397f1fd5a 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/9p/client.c b/net/9p/client.c index 0505a03c374c..854ca7a911c4 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 df58375ea6b3..55e10a96c902 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 2431c0f38d56..2cc525fa49fa 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 9a70ebdec56e..de8df957867d 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 76309223bb02..173bb550a9eb 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 e317583fcc73..32aa9834229c 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/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 873fb3d8e56f..c7aafc7c5ed4 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, @@ -710,6 +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]; diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 1ae355750511..ab8d0fe6df5a 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -224,22 +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/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index c1c597e3e198..e0af7237cd92 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -673,7 +673,7 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) goto encrypt; auth: - if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) + if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) return 0; if (!hci_conn_auth(conn, sec_level, auth_type)) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index b84458dcc226..be84ae33ae36 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -613,7 +613,7 @@ static int hci_dev_do_close(struct hci_dev *hdev) if (!test_bit(HCI_RAW, &hdev->flags)) { set_bit(HCI_INIT, &hdev->flags); __hci_request(hdev, hci_reset_req, 0, - msecs_to_jiffies(250)); + msecs_to_jiffies(HCI_INIT_TIMEOUT)); clear_bit(HCI_INIT, &hdev->flags); } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 8cd12917733b..5ea94a1eecf2 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -251,7 +251,7 @@ static void l2cap_chan_timeout(unsigned long arg) if (sock_owned_by_user(sk)) { /* sk is owned by user. Try again later */ - __set_chan_timer(chan, HZ / 5); + __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); bh_unlock_sock(sk); chan_put(chan); return; @@ -2488,7 +2488,7 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd if (sock_owned_by_user(sk)) { l2cap_state_change(chan, BT_DISCONN); __clear_chan_timer(chan); - __set_chan_timer(chan, HZ / 5); + __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); break; } @@ -2661,7 +2661,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr default: sk->sk_err = ECONNRESET; - __set_chan_timer(chan, HZ * 5); + __set_chan_timer(chan, L2CAP_DISC_REJ_TIMEOUT); l2cap_send_disconn_req(conn, chan, ECONNRESET); goto done; } @@ -2718,7 +2718,7 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd if (sock_owned_by_user(sk)) { l2cap_state_change(chan, BT_DISCONN); __clear_chan_timer(chan); - __set_chan_timer(chan, HZ / 5); + __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); bh_unlock_sock(sk); return 0; } @@ -2752,7 +2752,7 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd if (sock_owned_by_user(sk)) { l2cap_state_change(chan,BT_DISCONN); __clear_chan_timer(chan); - __set_chan_timer(chan, HZ / 5); + __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); bh_unlock_sock(sk); return 0; } @@ -3998,7 +3998,7 @@ static inline void l2cap_check_encryption(struct l2cap_chan *chan, u8 encrypt) if (encrypt == 0x00) { if (chan->sec_level == BT_SECURITY_MEDIUM) { __clear_chan_timer(chan); - __set_chan_timer(chan, HZ * 5); + __set_chan_timer(chan, L2CAP_ENC_TIMEOUT); } else if (chan->sec_level == BT_SECURITY_HIGH) l2cap_chan_close(chan, ECONNREFUSED); } else { @@ -4066,7 +4066,7 @@ static int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) L2CAP_CONN_REQ, sizeof(req), &req); } else { __clear_chan_timer(chan); - __set_chan_timer(chan, HZ / 10); + __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); } } else if (chan->state == BT_CONNECT2) { struct l2cap_conn_rsp rsp; @@ -4086,7 +4086,7 @@ static int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) } } else { l2cap_state_change(chan, BT_DISCONN); - __set_chan_timer(chan, HZ / 10); + __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); res = L2CAP_CR_SEC_BLOCK; stat = L2CAP_CS_NO_INFO; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 5a94eec06caa..5caff4d47596 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -147,8 +147,6 @@ static int read_index_list(struct sock *sk) hci_del_off_timer(d); - set_bit(HCI_MGMT, &d->flags); - if (test_bit(HCI_SETUP, &d->flags)) continue; diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 38b618c96de6..4e32e18211f9 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1802,6 +1802,11 @@ static inline void rfcomm_process_dlcs(struct rfcomm_session *s) continue; } + if (test_bit(RFCOMM_ENC_DROP, &d->flags)) { + __rfcomm_dlc_close(d, ECONNREFUSED); + continue; + } + if (test_and_clear_bit(RFCOMM_AUTH_ACCEPT, &d->flags)) { rfcomm_dlc_clear_timer(d); if (d->out) { @@ -2077,7 +2082,7 @@ static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt) if (test_and_clear_bit(RFCOMM_SEC_PENDING, &d->flags)) { rfcomm_dlc_clear_timer(d); if (status || encrypt == 0x00) { - __rfcomm_dlc_close(d, ECONNREFUSED); + set_bit(RFCOMM_ENC_DROP, &d->flags); continue; } } @@ -2088,7 +2093,7 @@ static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt) rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT); continue; } else if (d->sec_level == BT_SECURITY_HIGH) { - __rfcomm_dlc_close(d, ECONNREFUSED); + set_bit(RFCOMM_ENC_DROP, &d->flags); continue; } } diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 7f9ac0742d19..47fc8f3a47cf 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/core/dev.c b/net/core/dev.c index b7ba81afc6f9..6ba50a1e404c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3283,18 +3283,18 @@ another_round: 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)) + if (vlan_do_receive(&skb, !rx_handler)) goto another_round; else if (unlikely(!skb)) goto out; } - rx_handler = rcu_dereference(skb->dev->rx_handler); if (rx_handler) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); @@ -6450,7 +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; @@ -6465,6 +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/sock.c b/net/core/sock.c index 5a087626bb3a..4ed7b1d12f5e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1257,6 +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; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index b74f76117dcf..17ee85ce148d 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/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 85a2fbebd7ef..66363b689ad6 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -345,6 +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 diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e39239e6426e..d0611a5de45f 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -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); diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 2916200f90c1..fee46d5a2f12 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -248,7 +248,7 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) /* Restore final destination back after routing done */ ipv6_addr_copy(&fl6.daddr, &np->daddr); - res = ip6_xmit(sk, skb, &fl6, np->opt); + res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); rcu_read_unlock(); return res; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 1c9bf8b5c30a..84d0bd5cac93 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); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fb545edef6ea..57b82dc1ae91 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/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c8683fcc487a..10b2b3165a1a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -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); } @@ -979,7 +979,7 @@ 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) { const struct tcphdr *th = tcp_hdr(skb); struct tcphdr *t1; @@ -1060,7 +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); @@ -1093,13 +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) @@ -1109,7 +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); } @@ -1118,7 +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); } diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index b3cc8b3989a9..253695d43fd9 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/mac80211/cfg.c b/net/mac80211/cfg.c index 000a8ba987cd..65b72ae2b4e0 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -832,6 +832,12 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, if (is_multicast_ether_addr(mac)) return -EINVAL; + /* Only TDLS-supporting stations can add TDLS peers */ + if ((params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)) && + !((wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS) && + sdata->vif.type == NL80211_IFTYPE_STATION)) + return -ENOTSUPP; + sta = sta_info_alloc(sdata, mac, GFP_KERNEL); if (!sta) return -ENOMEM; @@ -841,12 +847,6 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, 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 || diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 30fc9e7c5c53..e2447096c94a 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -389,6 +389,7 @@ struct ieee80211_if_managed { unsigned long timers_running; /* used for quiesce/restart */ bool powersave; /* powersave requested for this iface */ + bool broken_ap; /* AP is broken -- turn off powersave */ enum ieee80211_smps_mode req_smps, /* requested smps mode */ ap_smps, /* smps mode AP thinks we're in */ driver_smps_mode; /* smps mode request */ diff --git a/net/mac80211/main.c b/net/mac80211/main.c index d4ee6d234a78..d999bf3b84e1 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> diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 0e5d8daba1ee..d3b408cda08d 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> @@ -637,6 +637,9 @@ static bool ieee80211_powersave_allowed(struct ieee80211_sub_if_data *sdata) if (!mgd->powersave) return false; + if (mgd->broken_ap) + return false; + if (!mgd->associated) return false; @@ -1482,6 +1485,7 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk, int i, j, err; bool have_higher_than_11mbit = false; u16 ap_ht_cap_flags; + int min_rate = INT_MAX, min_rate_index = -1; /* AssocResp and ReassocResp have identical structure */ @@ -1489,10 +1493,21 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk, capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info); if ((aid & (BIT(15) | BIT(14))) != (BIT(15) | BIT(14))) - printk(KERN_DEBUG "%s: invalid aid value %d; bits 15:14 not " - "set\n", sdata->name, aid); + printk(KERN_DEBUG + "%s: invalid AID value 0x%x; bits 15:14 not set\n", + sdata->name, aid); aid &= ~(BIT(15) | BIT(14)); + ifmgd->broken_ap = false; + + if (aid == 0 || aid > IEEE80211_MAX_AID) { + printk(KERN_DEBUG + "%s: invalid AID value %d (out of range), turn off PS\n", + sdata->name, aid); + aid = 0; + ifmgd->broken_ap = true; + } + pos = mgmt->u.assoc_resp.variable; ieee802_11_parse_elems(pos, len - (pos - (u8 *) mgmt), &elems); @@ -1537,6 +1552,10 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk, rates |= BIT(j); if (is_basic) basic_rates |= BIT(j); + if (rate < min_rate) { + min_rate = rate; + min_rate_index = j; + } break; } } @@ -1554,11 +1573,25 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk, rates |= BIT(j); if (is_basic) basic_rates |= BIT(j); + if (rate < min_rate) { + min_rate = rate; + min_rate_index = j; + } break; } } } + /* + * some buggy APs don't advertise basic_rates. use the lowest + * supported rate instead. + */ + if (unlikely(!basic_rates) && min_rate_index >= 0) { + printk(KERN_DEBUG "%s: No basic rates in AssocResp. " + "Using min supported rate instead.\n", sdata->name); + basic_rates = BIT(min_rate_index); + } + sta->sta.supp_rates[wk->chan->band] = rates; sdata->vif.bss_conf.basic_rates = basic_rates; diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 397343a59275..83a0b050b374 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> diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index ce962d2c8782..8eaa746ec7a2 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1354,12 +1354,12 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, * 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 + if (more_data || !skb_queue_empty(&frames)) 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)) diff --git a/net/mac80211/work.c b/net/mac80211/work.c index fab5092e3788..30da4e3f19f7 100644 --- a/net/mac80211/work.c +++ b/net/mac80211/work.c @@ -1057,14 +1057,13 @@ static void ieee80211_work_work(struct work_struct *work) continue; if (wk->chan != local->tmp_channel) continue; - if (ieee80211_work_ct_coexists(wk->chan_type, - local->tmp_channel_type)) + if (!ieee80211_work_ct_coexists(wk->chan_type, + local->tmp_channel_type)) continue; remain_off_channel = true; } if (!remain_off_channel && local->tmp_channel) { - bool on_oper_chan = ieee80211_cfg_on_oper_channel(local); local->tmp_channel = NULL; /* If tmp_channel wasn't operating channel, then * we need to go back on-channel. @@ -1074,7 +1073,7 @@ static void ieee80211_work_work(struct work_struct *work) * we still need to do a hardware config. Currently, * we cannot be here while scanning, however. */ - if (ieee80211_cfg_on_oper_channel(local) && !on_oper_chan) + if (!ieee80211_cfg_on_oper_channel(local)) ieee80211_hw_config(local, 0); /* At the least, we need to disable offchannel_ps, diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 32bff6d86cb2..8260b13d93c9 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/x_tables.c b/net/netfilter/x_tables.c index b0869fe3633b..71441b934ffd 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/rds/ib_cm.c b/net/rds/ib_cm.c index cd67026be2d5..51c868923f64 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/sctp/ipv6.c b/net/sctp/ipv6.c index aabaee41dd3e..810427833bcd 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/sunrpc/addr.c b/net/sunrpc/addr.c index 4195233c4914..4548757c9871 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 d4132754cbe1..afb56553dfe7 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -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 @@ -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/clnt.c b/net/sunrpc/clnt.c index c5347d29cfb7..f0268ea7e711 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 b181e3441323..bfddd68b31d3 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 e45d2fbbe5a8..f588b852d41c 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -410,7 +410,7 @@ 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 +437,7 @@ 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"), @@ -686,7 +686,7 @@ 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: diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 6a69a1131fb7..30d70abb4e2c 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. @@ -499,7 +511,7 @@ 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 +525,7 @@ 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 +548,11 @@ 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 +566,15 @@ 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 +659,7 @@ 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 +675,16 @@ 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); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index bd31208bbb61..d86bb673e1f6 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 767d494de7a2..dfd686eb0b7f 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/wireless/nl80211.c b/net/wireless/nl80211.c index 337be50aef3b..e97827ba8a58 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -132,8 +132,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_MESH_CONFIG] = { .type = NLA_NESTED }, [NL80211_ATTR_SUPPORT_MESH_AUTH] = { .type = NLA_FLAG }, - [NL80211_ATTR_HT_CAPABILITY] = { .type = NLA_BINARY, - .len = NL80211_HT_CAPABILITY_LEN }, + [NL80211_ATTR_HT_CAPABILITY] = { .len = NL80211_HT_CAPABILITY_LEN }, [NL80211_ATTR_MGMT_SUBTYPE] = { .type = NLA_U8 }, [NL80211_ATTR_IE] = { .type = NLA_BINARY, @@ -1253,6 +1252,12 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) goto bad_res; } + if (netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && + netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) { + result = -EINVAL; + goto bad_res; + } + nla_for_each_nested(nl_txq_params, info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS], rem_txq_params) { diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 0fb142410404..dc23b31594e0 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -259,17 +259,20 @@ 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); const u8 *ie2 = cfg80211_find_ie(num, ies2, len2); - int r; + /* equal if both missing */ if (!ie1 && !ie2) return 0; - if (!ie1 || !ie2) + /* sort missing IE before (left of) present IE */ + if (!ie1) return -1; + if (!ie2) + return 1; - r = memcmp(ie1 + 2, ie2 + 2, min(ie1[1], ie2[1])); - if (r == 0 && ie1[1] != ie2[1]) + /* sort by length first, then by contents */ + if (ie1[1] != ie2[1]) return ie2[1] - ie1[1]; - return r; + return memcmp(ie1 + 2, ie2 + 2, ie1[1]); } static bool is_bss(struct cfg80211_bss *a, |