diff options
Diffstat (limited to 'net')
169 files changed, 1579 insertions, 1067 deletions
diff --git a/net/9p/client.c b/net/9p/client.c index 854ca7a911c4..776618cd2be5 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -23,6 +23,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/errno.h> #include <linux/fs.h> @@ -81,15 +83,15 @@ static int get_protocol_version(char *s) if (!strcmp(s, "9p2000")) { version = p9_proto_legacy; - P9_DPRINTK(P9_DEBUG_9P, "Protocol version: Legacy\n"); + p9_debug(P9_DEBUG_9P, "Protocol version: Legacy\n"); } else if (!strcmp(s, "9p2000.u")) { version = p9_proto_2000u; - P9_DPRINTK(P9_DEBUG_9P, "Protocol version: 9P2000.u\n"); + p9_debug(P9_DEBUG_9P, "Protocol version: 9P2000.u\n"); } else if (!strcmp(s, "9p2000.L")) { version = p9_proto_2000L; - P9_DPRINTK(P9_DEBUG_9P, "Protocol version: 9P2000.L\n"); + p9_debug(P9_DEBUG_9P, "Protocol version: 9P2000.L\n"); } else - printk(KERN_INFO "9p: Unknown protocol version %s.\n", s); + pr_info("Unknown protocol version %s\n", s); return version; } @@ -119,8 +121,8 @@ static int parse_opts(char *opts, struct p9_client *clnt) tmp_options = kstrdup(opts, GFP_KERNEL); if (!tmp_options) { - P9_DPRINTK(P9_DEBUG_ERROR, - "failed to allocate copy of option string\n"); + p9_debug(P9_DEBUG_ERROR, + "failed to allocate copy of option string\n"); return -ENOMEM; } options = tmp_options; @@ -134,8 +136,8 @@ static int parse_opts(char *opts, struct p9_client *clnt) case Opt_msize: r = match_int(&args[0], &option); if (r < 0) { - P9_DPRINTK(P9_DEBUG_ERROR, - "integer field, but no integer?\n"); + p9_debug(P9_DEBUG_ERROR, + "integer field, but no integer?\n"); ret = r; continue; } @@ -145,15 +147,14 @@ static int parse_opts(char *opts, struct p9_client *clnt) s = match_strdup(&args[0]); if (!s) { ret = -ENOMEM; - P9_DPRINTK(P9_DEBUG_ERROR, - "problem allocating copy of trans arg\n"); + p9_debug(P9_DEBUG_ERROR, + "problem allocating copy of trans arg\n"); goto free_and_return; } clnt->trans_mod = v9fs_get_trans_by_name(s); if (clnt->trans_mod == NULL) { - printk(KERN_INFO - "9p: Could not find " - "request transport: %s\n", s); + pr_info("Could not find request transport: %s\n", + s); ret = -EINVAL; kfree(s); goto free_and_return; @@ -167,8 +168,8 @@ static int parse_opts(char *opts, struct p9_client *clnt) s = match_strdup(&args[0]); if (!s) { ret = -ENOMEM; - P9_DPRINTK(P9_DEBUG_ERROR, - "problem allocating copy of version arg\n"); + p9_debug(P9_DEBUG_ERROR, + "problem allocating copy of version arg\n"); goto free_and_return; } ret = get_protocol_version(s); @@ -225,7 +226,7 @@ p9_tag_alloc(struct p9_client *c, u16 tag, unsigned int max_size) sizeof(struct p9_req_t), GFP_ATOMIC); if (!c->reqs[row]) { - printk(KERN_ERR "Couldn't grow tag array\n"); + pr_err("Couldn't grow tag array\n"); spin_unlock_irqrestore(&c->lock, flags); return ERR_PTR(-ENOMEM); } @@ -244,7 +245,7 @@ p9_tag_alloc(struct p9_client *c, u16 tag, unsigned int max_size) if (!req->tc) { req->wq = kmalloc(sizeof(wait_queue_head_t), GFP_NOFS); if (!req->wq) { - printk(KERN_ERR "Couldn't grow tag array\n"); + pr_err("Couldn't grow tag array\n"); return ERR_PTR(-ENOMEM); } init_waitqueue_head(req->wq); @@ -253,7 +254,7 @@ p9_tag_alloc(struct p9_client *c, u16 tag, unsigned int max_size) 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"); + pr_err("Couldn't grow tag array\n"); kfree(req->tc); kfree(req->rc); kfree(req->wq); @@ -343,9 +344,9 @@ static void p9_tag_cleanup(struct p9_client *c) for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) { for (col = 0; col < P9_ROW_MAXTAG; col++) { if (c->reqs[row][col].status != REQ_STATUS_IDLE) { - P9_DPRINTK(P9_DEBUG_MUX, - "Attempting to cleanup non-free tag %d,%d\n", - row, col); + p9_debug(P9_DEBUG_MUX, + "Attempting to cleanup non-free tag %d,%d\n", + row, col); /* TODO: delay execution of cleanup */ return; } @@ -379,7 +380,7 @@ static void p9_tag_cleanup(struct p9_client *c) static void p9_free_req(struct p9_client *c, struct p9_req_t *r) { int tag = r->tc->tag; - P9_DPRINTK(P9_DEBUG_MUX, "clnt %p req %p tag: %d\n", c, r, tag); + p9_debug(P9_DEBUG_MUX, "clnt %p req %p tag: %d\n", c, r, tag); r->status = REQ_STATUS_IDLE; if (tag != P9_NOTAG && p9_idpool_check(tag, c->tagpool)) @@ -394,9 +395,9 @@ static void p9_free_req(struct p9_client *c, struct p9_req_t *r) */ void p9_client_cb(struct p9_client *c, struct p9_req_t *req) { - P9_DPRINTK(P9_DEBUG_MUX, " tag %d\n", req->tc->tag); + p9_debug(P9_DEBUG_MUX, " tag %d\n", req->tc->tag); wake_up(req->wq); - P9_DPRINTK(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag); + p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag); } EXPORT_SYMBOL(p9_client_cb); @@ -431,8 +432,8 @@ p9_parse_header(struct p9_fcall *pdu, int32_t *size, int8_t *type, int16_t *tag, pdu->id = r_type; pdu->tag = r_tag; - P9_DPRINTK(P9_DEBUG_9P, "<<< size=%d type: %d tag: %d\n", pdu->size, - pdu->id, pdu->tag); + p9_debug(P9_DEBUG_9P, "<<< size=%d type: %d tag: %d\n", + pdu->size, pdu->id, pdu->tag); if (type) *type = r_type; @@ -473,7 +474,7 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req) */ trace_9p_protocol_dump(c, req->rc); if (err) { - P9_DPRINTK(P9_DEBUG_ERROR, "couldn't parse header %d\n", err); + p9_debug(P9_DEBUG_ERROR, "couldn't parse header %d\n", err); return err; } if (type != P9_RERROR && type != P9_RLERROR) @@ -492,21 +493,21 @@ 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); + p9_debug(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); + p9_debug(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode); } return err; out_err: - P9_DPRINTK(P9_DEBUG_ERROR, "couldn't parse error%d\n", err); + p9_debug(P9_DEBUG_ERROR, "couldn't parse error%d\n", err); return err; } @@ -538,7 +539,7 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req, */ trace_9p_protocol_dump(c, req->rc); if (err) { - P9_DPRINTK(P9_DEBUG_ERROR, "couldn't parse header %d\n", err); + p9_debug(P9_DEBUG_ERROR, "couldn't parse header %d\n", err); return err; } @@ -601,22 +602,22 @@ static int p9_check_zc_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); + p9_debug(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); + p9_debug(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); + p9_debug(P9_DEBUG_ERROR, "couldn't parse error%d\n", err); return err; } @@ -645,7 +646,7 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq) if (err) return err; - P9_DPRINTK(P9_DEBUG_9P, ">>> TFLUSH tag %d\n", oldtag); + p9_debug(P9_DEBUG_9P, ">>> TFLUSH tag %d\n", oldtag); req = p9_client_rpc(c, P9_TFLUSH, "w", oldtag); if (IS_ERR(req)) @@ -670,7 +671,7 @@ static struct p9_req_t *p9_client_prepare_req(struct p9_client *c, int tag, err; struct p9_req_t *req; - P9_DPRINTK(P9_DEBUG_MUX, "client %p op %d\n", c, type); + p9_debug(P9_DEBUG_MUX, "client %p op %d\n", c, type); /* we allow for any status other than disconnected */ if (c->status == Disconnected) @@ -744,11 +745,11 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) req->status >= REQ_STATUS_RCVD); if (req->status == REQ_STATUS_ERROR) { - P9_DPRINTK(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err); + p9_debug(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"); + p9_debug(P9_DEBUG_MUX, "flushing\n"); sigpending = 1; clear_thread_flag(TIF_SIGPENDING); @@ -827,11 +828,11 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type, goto reterr; } if (req->status == REQ_STATUS_ERROR) { - P9_DPRINTK(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err); + p9_debug(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"); + p9_debug(P9_DEBUG_MUX, "flushing\n"); sigpending = 1; clear_thread_flag(TIF_SIGPENDING); @@ -865,7 +866,7 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt) struct p9_fid *fid; unsigned long flags; - P9_DPRINTK(P9_DEBUG_FID, "clnt %p\n", clnt); + p9_debug(P9_DEBUG_FID, "clnt %p\n", clnt); fid = kmalloc(sizeof(struct p9_fid), GFP_KERNEL); if (!fid) return ERR_PTR(-ENOMEM); @@ -898,7 +899,7 @@ static void p9_fid_destroy(struct p9_fid *fid) struct p9_client *clnt; unsigned long flags; - P9_DPRINTK(P9_DEBUG_FID, "fid %d\n", fid->fid); + p9_debug(P9_DEBUG_FID, "fid %d\n", fid->fid); clnt = fid->clnt; p9_idpool_put(fid->fid, clnt->fidpool); spin_lock_irqsave(&clnt->lock, flags); @@ -915,8 +916,8 @@ static int p9_client_version(struct p9_client *c) char *version; int msize; - P9_DPRINTK(P9_DEBUG_9P, ">>> TVERSION msize %d protocol %d\n", - c->msize, c->proto_version); + p9_debug(P9_DEBUG_9P, ">>> TVERSION msize %d protocol %d\n", + c->msize, c->proto_version); switch (c->proto_version) { case p9_proto_2000L: @@ -941,12 +942,12 @@ 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_debug(P9_DEBUG_9P, "version error %d\n", err); trace_9p_protocol_dump(c, req->rc); goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RVERSION msize %d %s\n", msize, version); + p9_debug(P9_DEBUG_9P, "<<< RVERSION msize %d %s\n", msize, version); if (!strncmp(version, "9P2000.L", 8)) c->proto_version = p9_proto_2000L; else if (!strncmp(version, "9P2000.u", 8)) @@ -996,8 +997,8 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) if (clnt->trans_mod == NULL) { err = -EPROTONOSUPPORT; - P9_DPRINTK(P9_DEBUG_ERROR, - "No transport defined or default transport\n"); + p9_debug(P9_DEBUG_ERROR, + "No transport defined or default transport\n"); goto destroy_tagpool; } @@ -1007,8 +1008,8 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) goto put_trans; } - P9_DPRINTK(P9_DEBUG_MUX, "clnt %p trans %p msize %d protocol %d\n", - clnt, clnt->trans_mod, clnt->msize, clnt->proto_version); + p9_debug(P9_DEBUG_MUX, "clnt %p trans %p msize %d protocol %d\n", + clnt, clnt->trans_mod, clnt->msize, clnt->proto_version); err = clnt->trans_mod->create(clnt, dev_name, options); if (err) @@ -1041,7 +1042,7 @@ void p9_client_destroy(struct p9_client *clnt) { struct p9_fid *fid, *fidptr; - P9_DPRINTK(P9_DEBUG_MUX, "clnt %p\n", clnt); + p9_debug(P9_DEBUG_MUX, "clnt %p\n", clnt); if (clnt->trans_mod) clnt->trans_mod->close(clnt); @@ -1049,7 +1050,7 @@ void p9_client_destroy(struct p9_client *clnt) v9fs_put_trans(clnt->trans_mod); list_for_each_entry_safe(fid, fidptr, &clnt->fidlist, flist) { - printk(KERN_INFO "Found fid %d not clunked\n", fid->fid); + pr_info("Found fid %d not clunked\n", fid->fid); p9_fid_destroy(fid); } @@ -1064,14 +1065,14 @@ EXPORT_SYMBOL(p9_client_destroy); void p9_client_disconnect(struct p9_client *clnt) { - P9_DPRINTK(P9_DEBUG_9P, "clnt %p\n", clnt); + p9_debug(P9_DEBUG_9P, "clnt %p\n", clnt); clnt->status = Disconnected; } EXPORT_SYMBOL(p9_client_disconnect); void p9_client_begin_disconnect(struct p9_client *clnt) { - P9_DPRINTK(P9_DEBUG_9P, "clnt %p\n", clnt); + p9_debug(P9_DEBUG_9P, "clnt %p\n", clnt); clnt->status = BeginDisconnect; } EXPORT_SYMBOL(p9_client_begin_disconnect); @@ -1085,8 +1086,8 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, struct p9_qid qid; - P9_DPRINTK(P9_DEBUG_9P, ">>> TATTACH afid %d uname %s aname %s\n", - afid ? afid->fid : -1, uname, aname); + p9_debug(P9_DEBUG_9P, ">>> TATTACH afid %d uname %s aname %s\n", + afid ? afid->fid : -1, uname, aname); fid = p9_fid_create(clnt); if (IS_ERR(fid)) { err = PTR_ERR(fid); @@ -1108,10 +1109,8 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RATTACH qid %x.%llx.%x\n", - qid.type, - (unsigned long long)qid.path, - qid.version); + p9_debug(P9_DEBUG_9P, "<<< RATTACH qid %x.%llx.%x\n", + qid.type, (unsigned long long)qid.path, qid.version); memmove(&fid->qid, &qid, sizeof(struct p9_qid)); @@ -1151,8 +1150,8 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, fid = oldfid; - P9_DPRINTK(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %ud wname[0] %s\n", - oldfid->fid, fid->fid, nwname, wnames ? wnames[0] : NULL); + p9_debug(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %ud wname[0] %s\n", + oldfid->fid, fid->fid, nwname, wnames ? wnames[0] : NULL); req = p9_client_rpc(clnt, P9_TWALK, "ddT", oldfid->fid, fid->fid, nwname, wnames); @@ -1169,7 +1168,7 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, } p9_free_req(clnt, req); - P9_DPRINTK(P9_DEBUG_9P, "<<< RWALK nwqid %d:\n", nwqids); + p9_debug(P9_DEBUG_9P, "<<< RWALK nwqid %d:\n", nwqids); if (nwqids != nwname) { err = -ENOENT; @@ -1177,7 +1176,7 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, } for (count = 0; count < nwqids; count++) - P9_DPRINTK(P9_DEBUG_9P, "<<< [%d] %x.%llx.%x\n", + p9_debug(P9_DEBUG_9P, "<<< [%d] %x.%llx.%x\n", count, wqids[count].type, (unsigned long long)wqids[count].path, wqids[count].version); @@ -1212,7 +1211,7 @@ int p9_client_open(struct p9_fid *fid, int mode) int iounit; clnt = fid->clnt; - P9_DPRINTK(P9_DEBUG_9P, ">>> %s fid %d mode %d\n", + p9_debug(P9_DEBUG_9P, ">>> %s fid %d mode %d\n", p9_is_proto_dotl(clnt) ? "TLOPEN" : "TOPEN", fid->fid, mode); err = 0; @@ -1234,7 +1233,7 @@ int p9_client_open(struct p9_fid *fid, int mode) goto free_and_error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< %s qid %x.%llx.%x iounit %x\n", + p9_debug(P9_DEBUG_9P, "<<< %s qid %x.%llx.%x iounit %x\n", p9_is_proto_dotl(clnt) ? "RLOPEN" : "ROPEN", qid.type, (unsigned long long)qid.path, qid.version, iounit); @@ -1256,7 +1255,7 @@ int p9_client_create_dotl(struct p9_fid *ofid, char *name, u32 flags, u32 mode, struct p9_req_t *req; int iounit; - P9_DPRINTK(P9_DEBUG_9P, + p9_debug(P9_DEBUG_9P, ">>> TLCREATE fid %d name %s flags %d mode %d gid %d\n", ofid->fid, name, flags, mode, gid); clnt = ofid->clnt; @@ -1277,7 +1276,7 @@ int p9_client_create_dotl(struct p9_fid *ofid, char *name, u32 flags, u32 mode, goto free_and_error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RLCREATE qid %x.%llx.%x iounit %x\n", + p9_debug(P9_DEBUG_9P, "<<< RLCREATE qid %x.%llx.%x iounit %x\n", qid->type, (unsigned long long)qid->path, qid->version, iounit); @@ -1301,7 +1300,7 @@ int p9_client_fcreate(struct p9_fid *fid, char *name, u32 perm, int mode, struct p9_qid qid; int iounit; - P9_DPRINTK(P9_DEBUG_9P, ">>> TCREATE fid %d name %s perm %d mode %d\n", + p9_debug(P9_DEBUG_9P, ">>> TCREATE fid %d name %s perm %d mode %d\n", fid->fid, name, perm, mode); err = 0; clnt = fid->clnt; @@ -1322,7 +1321,7 @@ int p9_client_fcreate(struct p9_fid *fid, char *name, u32 perm, int mode, goto free_and_error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RCREATE qid %x.%llx.%x iounit %x\n", + p9_debug(P9_DEBUG_9P, "<<< RCREATE qid %x.%llx.%x iounit %x\n", qid.type, (unsigned long long)qid.path, qid.version, iounit); @@ -1344,7 +1343,7 @@ int p9_client_symlink(struct p9_fid *dfid, char *name, char *symtgt, gid_t gid, struct p9_client *clnt; struct p9_req_t *req; - P9_DPRINTK(P9_DEBUG_9P, ">>> TSYMLINK dfid %d name %s symtgt %s\n", + p9_debug(P9_DEBUG_9P, ">>> TSYMLINK dfid %d name %s symtgt %s\n", dfid->fid, name, symtgt); clnt = dfid->clnt; @@ -1361,7 +1360,7 @@ int p9_client_symlink(struct p9_fid *dfid, char *name, char *symtgt, gid_t gid, goto free_and_error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RSYMLINK qid %x.%llx.%x\n", + p9_debug(P9_DEBUG_9P, "<<< RSYMLINK qid %x.%llx.%x\n", qid->type, (unsigned long long)qid->path, qid->version); free_and_error: @@ -1376,7 +1375,7 @@ int p9_client_link(struct p9_fid *dfid, struct p9_fid *oldfid, char *newname) struct p9_client *clnt; struct p9_req_t *req; - P9_DPRINTK(P9_DEBUG_9P, ">>> TLINK dfid %d oldfid %d newname %s\n", + p9_debug(P9_DEBUG_9P, ">>> TLINK dfid %d oldfid %d newname %s\n", dfid->fid, oldfid->fid, newname); clnt = dfid->clnt; req = p9_client_rpc(clnt, P9_TLINK, "dds", dfid->fid, oldfid->fid, @@ -1384,7 +1383,7 @@ int p9_client_link(struct p9_fid *dfid, struct p9_fid *oldfid, char *newname) if (IS_ERR(req)) return PTR_ERR(req); - P9_DPRINTK(P9_DEBUG_9P, "<<< RLINK\n"); + p9_debug(P9_DEBUG_9P, "<<< RLINK\n"); p9_free_req(clnt, req); return 0; } @@ -1396,7 +1395,7 @@ int p9_client_fsync(struct p9_fid *fid, int datasync) struct p9_client *clnt; struct p9_req_t *req; - P9_DPRINTK(P9_DEBUG_9P, ">>> TFSYNC fid %d datasync:%d\n", + p9_debug(P9_DEBUG_9P, ">>> TFSYNC fid %d datasync:%d\n", fid->fid, datasync); err = 0; clnt = fid->clnt; @@ -1407,7 +1406,7 @@ int p9_client_fsync(struct p9_fid *fid, int datasync) goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RFSYNC fid %d\n", fid->fid); + p9_debug(P9_DEBUG_9P, "<<< RFSYNC fid %d\n", fid->fid); p9_free_req(clnt, req); @@ -1423,12 +1422,13 @@ int p9_client_clunk(struct p9_fid *fid) struct p9_req_t *req; if (!fid) { - P9_EPRINTK(KERN_WARNING, "Trying to clunk with NULL fid\n"); + pr_warn("%s (%d): Trying to clunk with NULL fid\n", + __func__, task_pid_nr(current)); dump_stack(); return 0; } - P9_DPRINTK(P9_DEBUG_9P, ">>> TCLUNK fid %d\n", fid->fid); + p9_debug(P9_DEBUG_9P, ">>> TCLUNK fid %d\n", fid->fid); err = 0; clnt = fid->clnt; @@ -1438,7 +1438,7 @@ int p9_client_clunk(struct p9_fid *fid) goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RCLUNK fid %d\n", fid->fid); + p9_debug(P9_DEBUG_9P, "<<< RCLUNK fid %d\n", fid->fid); p9_free_req(clnt, req); error: @@ -1456,7 +1456,7 @@ int p9_client_remove(struct p9_fid *fid) struct p9_client *clnt; struct p9_req_t *req; - P9_DPRINTK(P9_DEBUG_9P, ">>> TREMOVE fid %d\n", fid->fid); + p9_debug(P9_DEBUG_9P, ">>> TREMOVE fid %d\n", fid->fid); err = 0; clnt = fid->clnt; @@ -1466,7 +1466,7 @@ int p9_client_remove(struct p9_fid *fid) goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RREMOVE fid %d\n", fid->fid); + p9_debug(P9_DEBUG_9P, "<<< RREMOVE fid %d\n", fid->fid); p9_free_req(clnt, req); error: @@ -1481,7 +1481,7 @@ int p9_client_unlinkat(struct p9_fid *dfid, const char *name, int flags) struct p9_req_t *req; struct p9_client *clnt; - P9_DPRINTK(P9_DEBUG_9P, ">>> TUNLINKAT fid %d %s %d\n", + p9_debug(P9_DEBUG_9P, ">>> TUNLINKAT fid %d %s %d\n", dfid->fid, name, flags); clnt = dfid->clnt; @@ -1490,7 +1490,7 @@ int p9_client_unlinkat(struct p9_fid *dfid, const char *name, int flags) err = PTR_ERR(req); goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RUNLINKAT fid %d %s\n", dfid->fid, name); + p9_debug(P9_DEBUG_9P, "<<< RUNLINKAT fid %d %s\n", dfid->fid, name); p9_free_req(clnt, req); error: @@ -1509,7 +1509,7 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, int err, rsize, non_zc = 0; - P9_DPRINTK(P9_DEBUG_9P, ">>> TREAD fid %d offset %llu %d\n", + p9_debug(P9_DEBUG_9P, ">>> TREAD fid %d offset %llu %d\n", fid->fid, (long long unsigned) offset, count); err = 0; clnt = fid->clnt; @@ -1552,7 +1552,7 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, goto free_and_error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RREAD count %d\n", count); + p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count); if (non_zc) { if (data) { @@ -1584,7 +1584,7 @@ p9_client_write(struct p9_fid *fid, char *data, const char __user *udata, struct p9_client *clnt; struct p9_req_t *req; - P9_DPRINTK(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %d\n", + p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %d\n", fid->fid, (long long unsigned) offset, count); err = 0; clnt = fid->clnt; @@ -1626,7 +1626,7 @@ p9_client_write(struct p9_fid *fid, char *data, const char __user *udata, goto free_and_error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RWRITE count %d\n", count); + p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count); p9_free_req(clnt, req); return count; @@ -1646,7 +1646,7 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid) struct p9_req_t *req; u16 ignored; - P9_DPRINTK(P9_DEBUG_9P, ">>> TSTAT fid %d\n", fid->fid); + p9_debug(P9_DEBUG_9P, ">>> TSTAT fid %d\n", fid->fid); if (!ret) return ERR_PTR(-ENOMEM); @@ -1667,7 +1667,7 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid) goto error; } - P9_DPRINTK(P9_DEBUG_9P, + p9_debug(P9_DEBUG_9P, "<<< RSTAT sz=%x type=%x dev=%x qid=%x.%llx.%x\n" "<<< mode=%8.8x atime=%8.8x mtime=%8.8x length=%llx\n" "<<< name=%s uid=%s gid=%s muid=%s extension=(%s)\n" @@ -1696,7 +1696,7 @@ struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid, GFP_KERNEL); struct p9_req_t *req; - P9_DPRINTK(P9_DEBUG_9P, ">>> TGETATTR fid %d, request_mask %lld\n", + p9_debug(P9_DEBUG_9P, ">>> TGETATTR fid %d, request_mask %lld\n", fid->fid, request_mask); if (!ret) @@ -1718,7 +1718,7 @@ struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid, goto error; } - P9_DPRINTK(P9_DEBUG_9P, + p9_debug(P9_DEBUG_9P, "<<< RGETATTR st_result_mask=%lld\n" "<<< qid=%x.%llx.%x\n" "<<< st_mode=%8.8x st_nlink=%llu\n" @@ -1784,8 +1784,8 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst) err = 0; clnt = fid->clnt; wst->size = p9_client_statsize(wst, clnt->proto_version); - P9_DPRINTK(P9_DEBUG_9P, ">>> TWSTAT fid %d\n", fid->fid); - P9_DPRINTK(P9_DEBUG_9P, + p9_debug(P9_DEBUG_9P, ">>> TWSTAT fid %d\n", fid->fid); + p9_debug(P9_DEBUG_9P, " sz=%x type=%x dev=%x qid=%x.%llx.%x\n" " mode=%8.8x atime=%8.8x mtime=%8.8x length=%llx\n" " name=%s uid=%s gid=%s muid=%s extension=(%s)\n" @@ -1802,7 +1802,7 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst) goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RWSTAT fid %d\n", fid->fid); + p9_debug(P9_DEBUG_9P, "<<< RWSTAT fid %d\n", fid->fid); p9_free_req(clnt, req); error: @@ -1818,8 +1818,8 @@ int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *p9attr) err = 0; clnt = fid->clnt; - P9_DPRINTK(P9_DEBUG_9P, ">>> TSETATTR fid %d\n", fid->fid); - P9_DPRINTK(P9_DEBUG_9P, + p9_debug(P9_DEBUG_9P, ">>> TSETATTR fid %d\n", fid->fid); + p9_debug(P9_DEBUG_9P, " valid=%x mode=%x uid=%d gid=%d size=%lld\n" " atime_sec=%lld atime_nsec=%lld\n" " mtime_sec=%lld mtime_nsec=%lld\n", @@ -1833,7 +1833,7 @@ int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *p9attr) err = PTR_ERR(req); goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RSETATTR fid %d\n", fid->fid); + p9_debug(P9_DEBUG_9P, "<<< RSETATTR fid %d\n", fid->fid); p9_free_req(clnt, req); error: return err; @@ -1849,7 +1849,7 @@ int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb) err = 0; clnt = fid->clnt; - P9_DPRINTK(P9_DEBUG_9P, ">>> TSTATFS fid %d\n", fid->fid); + p9_debug(P9_DEBUG_9P, ">>> TSTATFS fid %d\n", fid->fid); req = p9_client_rpc(clnt, P9_TSTATFS, "d", fid->fid); if (IS_ERR(req)) { @@ -1866,7 +1866,7 @@ int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb) goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RSTATFS fid %d type 0x%lx bsize %ld " + p9_debug(P9_DEBUG_9P, "<<< RSTATFS fid %d type 0x%lx bsize %ld " "blocks %llu bfree %llu bavail %llu files %llu ffree %llu " "fsid %llu namelen %ld\n", fid->fid, (long unsigned int)sb->type, (long int)sb->bsize, @@ -1889,7 +1889,7 @@ int p9_client_rename(struct p9_fid *fid, err = 0; clnt = fid->clnt; - P9_DPRINTK(P9_DEBUG_9P, ">>> TRENAME fid %d newdirfid %d name %s\n", + p9_debug(P9_DEBUG_9P, ">>> TRENAME fid %d newdirfid %d name %s\n", fid->fid, newdirfid->fid, name); req = p9_client_rpc(clnt, P9_TRENAME, "dds", fid->fid, @@ -1899,7 +1899,7 @@ int p9_client_rename(struct p9_fid *fid, goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RRENAME fid %d\n", fid->fid); + p9_debug(P9_DEBUG_9P, "<<< RRENAME fid %d\n", fid->fid); p9_free_req(clnt, req); error: @@ -1917,7 +1917,7 @@ int p9_client_renameat(struct p9_fid *olddirfid, const char *old_name, err = 0; clnt = olddirfid->clnt; - P9_DPRINTK(P9_DEBUG_9P, ">>> TRENAMEAT olddirfid %d old name %s" + p9_debug(P9_DEBUG_9P, ">>> TRENAMEAT olddirfid %d old name %s" " newdirfid %d new name %s\n", olddirfid->fid, old_name, newdirfid->fid, new_name); @@ -1928,7 +1928,7 @@ int p9_client_renameat(struct p9_fid *olddirfid, const char *old_name, goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RRENAMEAT newdirfid %d new name %s\n", + p9_debug(P9_DEBUG_9P, "<<< RRENAMEAT newdirfid %d new name %s\n", newdirfid->fid, new_name); p9_free_req(clnt, req); @@ -1956,7 +1956,7 @@ struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid, attr_fid = NULL; goto error; } - P9_DPRINTK(P9_DEBUG_9P, + p9_debug(P9_DEBUG_9P, ">>> TXATTRWALK file_fid %d, attr_fid %d name %s\n", file_fid->fid, attr_fid->fid, attr_name); @@ -1973,7 +1973,7 @@ struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid, goto clunk_fid; } p9_free_req(clnt, req); - P9_DPRINTK(P9_DEBUG_9P, "<<< RXATTRWALK fid %d size %llu\n", + p9_debug(P9_DEBUG_9P, "<<< RXATTRWALK fid %d size %llu\n", attr_fid->fid, *attr_size); return attr_fid; clunk_fid: @@ -1994,7 +1994,7 @@ int p9_client_xattrcreate(struct p9_fid *fid, const char *name, struct p9_req_t *req; struct p9_client *clnt; - P9_DPRINTK(P9_DEBUG_9P, + p9_debug(P9_DEBUG_9P, ">>> TXATTRCREATE fid %d name %s size %lld flag %d\n", fid->fid, name, (long long)attr_size, flags); err = 0; @@ -2005,7 +2005,7 @@ int p9_client_xattrcreate(struct p9_fid *fid, const char *name, err = PTR_ERR(req); goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RXATTRCREATE fid %d\n", fid->fid); + p9_debug(P9_DEBUG_9P, "<<< RXATTRCREATE fid %d\n", fid->fid); p9_free_req(clnt, req); error: return err; @@ -2019,7 +2019,7 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) struct p9_req_t *req; char *dataptr; - P9_DPRINTK(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n", + p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n", fid->fid, (long long unsigned) offset, count); err = 0; @@ -2056,7 +2056,7 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) goto free_and_error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count); + p9_debug(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count); if (non_zc) memmove(data, dataptr, count); @@ -2080,7 +2080,7 @@ int p9_client_mknod_dotl(struct p9_fid *fid, char *name, int mode, err = 0; clnt = fid->clnt; - P9_DPRINTK(P9_DEBUG_9P, ">>> TMKNOD fid %d name %s mode %d major %d " + p9_debug(P9_DEBUG_9P, ">>> TMKNOD fid %d name %s mode %d major %d " "minor %d\n", fid->fid, name, mode, MAJOR(rdev), MINOR(rdev)); req = p9_client_rpc(clnt, P9_TMKNOD, "dsdddd", fid->fid, name, mode, MAJOR(rdev), MINOR(rdev), gid); @@ -2092,7 +2092,7 @@ int p9_client_mknod_dotl(struct p9_fid *fid, char *name, int mode, trace_9p_protocol_dump(clnt, req->rc); goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RMKNOD qid %x.%llx.%x\n", qid->type, + p9_debug(P9_DEBUG_9P, "<<< RMKNOD qid %x.%llx.%x\n", qid->type, (unsigned long long)qid->path, qid->version); error: @@ -2111,7 +2111,7 @@ int p9_client_mkdir_dotl(struct p9_fid *fid, char *name, int mode, err = 0; clnt = fid->clnt; - P9_DPRINTK(P9_DEBUG_9P, ">>> TMKDIR fid %d name %s mode %d gid %d\n", + p9_debug(P9_DEBUG_9P, ">>> TMKDIR fid %d name %s mode %d gid %d\n", fid->fid, name, mode, gid); req = p9_client_rpc(clnt, P9_TMKDIR, "dsdd", fid->fid, name, mode, gid); @@ -2123,7 +2123,7 @@ int p9_client_mkdir_dotl(struct p9_fid *fid, char *name, int mode, trace_9p_protocol_dump(clnt, req->rc); goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RMKDIR qid %x.%llx.%x\n", qid->type, + p9_debug(P9_DEBUG_9P, "<<< RMKDIR qid %x.%llx.%x\n", qid->type, (unsigned long long)qid->path, qid->version); error: @@ -2141,7 +2141,7 @@ int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status) err = 0; clnt = fid->clnt; - P9_DPRINTK(P9_DEBUG_9P, ">>> TLOCK fid %d type %i flags %d " + p9_debug(P9_DEBUG_9P, ">>> TLOCK fid %d type %i flags %d " "start %lld length %lld proc_id %d client_id %s\n", fid->fid, flock->type, flock->flags, flock->start, flock->length, flock->proc_id, flock->client_id); @@ -2158,7 +2158,7 @@ int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status) trace_9p_protocol_dump(clnt, req->rc); goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RLOCK status %i\n", *status); + p9_debug(P9_DEBUG_9P, "<<< RLOCK status %i\n", *status); error: p9_free_req(clnt, req); return err; @@ -2174,7 +2174,7 @@ int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *glock) err = 0; clnt = fid->clnt; - P9_DPRINTK(P9_DEBUG_9P, ">>> TGETLOCK fid %d, type %i start %lld " + p9_debug(P9_DEBUG_9P, ">>> TGETLOCK fid %d, type %i start %lld " "length %lld proc_id %d client_id %s\n", fid->fid, glock->type, glock->start, glock->length, glock->proc_id, glock->client_id); @@ -2191,7 +2191,7 @@ int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *glock) trace_9p_protocol_dump(clnt, req->rc); goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RGETLOCK type %i start %lld length %lld " + p9_debug(P9_DEBUG_9P, "<<< RGETLOCK type %i start %lld length %lld " "proc_id %d client_id %s\n", glock->type, glock->start, glock->length, glock->proc_id, glock->client_id); error: @@ -2208,7 +2208,7 @@ int p9_client_readlink(struct p9_fid *fid, char **target) err = 0; clnt = fid->clnt; - P9_DPRINTK(P9_DEBUG_9P, ">>> TREADLINK fid %d\n", fid->fid); + p9_debug(P9_DEBUG_9P, ">>> TREADLINK fid %d\n", fid->fid); req = p9_client_rpc(clnt, P9_TREADLINK, "d", fid->fid); if (IS_ERR(req)) @@ -2219,7 +2219,7 @@ int p9_client_readlink(struct p9_fid *fid, char **target) trace_9p_protocol_dump(clnt, req->rc); goto error; } - P9_DPRINTK(P9_DEBUG_9P, "<<< RREADLINK target %s\n", *target); + p9_debug(P9_DEBUG_9P, "<<< RREADLINK target %s\n", *target); error: p9_free_req(clnt, req); return err; diff --git a/net/9p/error.c b/net/9p/error.c index 52518512a93e..2ab2de76010f 100644 --- a/net/9p/error.c +++ b/net/9p/error.c @@ -27,6 +27,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/list.h> #include <linux/jhash.h> @@ -237,8 +239,8 @@ int p9_errstr2errno(char *errstr, int len) if (errno == 0) { /* TODO: if error isn't found, add it dynamically */ errstr[len] = 0; - printk(KERN_ERR "%s: server reported unknown error %s\n", - __func__, errstr); + pr_err("%s: server reported unknown error %s\n", + __func__, errstr); errno = ESERVERFAULT; } diff --git a/net/9p/mod.c b/net/9p/mod.c index 2664d1292291..6ab36aea7727 100644 --- a/net/9p/mod.c +++ b/net/9p/mod.c @@ -24,7 +24,11 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> +#include <linux/errno.h> +#include <linux/sched.h> #include <linux/moduleparam.h> #include <net/9p/9p.h> #include <linux/fs.h> @@ -39,6 +43,29 @@ unsigned int p9_debug_level = 0; /* feature-rific global debug level */ EXPORT_SYMBOL(p9_debug_level); module_param_named(debug, p9_debug_level, uint, 0); MODULE_PARM_DESC(debug, "9P debugging level"); + +void _p9_debug(enum p9_debug_flags level, const char *func, + const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + if ((p9_debug_level & level) != level) + return; + + va_start(args, fmt); + + vaf.fmt = fmt; + vaf.va = &args; + + if (level == P9_DEBUG_9P) + pr_notice("(%8.8d) %pV", task_pid_nr(current), &vaf); + else + pr_notice("-- %s (%d): %pV", func, task_pid_nr(current), &vaf); + + va_end(args); +} +EXPORT_SYMBOL(_p9_debug); #endif /* @@ -147,7 +174,7 @@ static int __init init_p9(void) int ret = 0; p9_error_init(); - printk(KERN_INFO "Installing 9P2000 support\n"); + pr_info("Installing 9P2000 support\n"); p9_trans_fd_init(); return ret; @@ -160,7 +187,7 @@ static int __init init_p9(void) static void __exit exit_p9(void) { - printk(KERN_INFO "Unloading 9P2000 support\n"); + pr_info("Unloading 9P2000 support\n"); p9_trans_fd_exit(); } diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 55e10a96c902..9ee48cb30179 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -534,7 +534,7 @@ int p9stat_read(struct p9_client *clnt, char *buf, int len, struct p9_wstat *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_debug(P9_DEBUG_9P, "<<< p9stat_read failed: %d\n", ret); trace_9p_protocol_dump(clnt, &fake_pdu); } @@ -558,8 +558,8 @@ int p9pdu_finalize(struct p9_client *clnt, struct p9_fcall *pdu) pdu->size = size; trace_9p_protocol_dump(clnt, pdu); - P9_DPRINTK(P9_DEBUG_9P, ">>> size=%d type: %d tag: %d\n", pdu->size, - pdu->id, pdu->tag); + p9_debug(P9_DEBUG_9P, ">>> size=%d type: %d tag: %d\n", + pdu->size, pdu->id, pdu->tag); return err; } @@ -585,7 +585,7 @@ int p9dirent_read(struct p9_client *clnt, char *buf, int len, 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_debug(P9_DEBUG_9P, "<<< p9dirent_read failed: %d\n", ret); trace_9p_protocol_dump(clnt, &fake_pdu); goto out; } diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index fdfdb5747f63..fccae26fa674 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -25,6 +25,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/in.h> #include <linux/module.h> #include <linux/net.h> @@ -191,7 +193,7 @@ static void p9_conn_cancel(struct p9_conn *m, int err) unsigned long flags; LIST_HEAD(cancel_list); - P9_DPRINTK(P9_DEBUG_ERROR, "mux %p err %d\n", m, err); + p9_debug(P9_DEBUG_ERROR, "mux %p err %d\n", m, err); spin_lock_irqsave(&m->client->lock, flags); @@ -217,7 +219,7 @@ static void p9_conn_cancel(struct p9_conn *m, int err) spin_unlock_irqrestore(&m->client->lock, flags); list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) { - P9_DPRINTK(P9_DEBUG_ERROR, "call back req %p\n", req); + p9_debug(P9_DEBUG_ERROR, "call back req %p\n", req); list_del(&req->req_list); p9_client_cb(m->client, req); } @@ -275,7 +277,7 @@ static int p9_fd_read(struct p9_client *client, void *v, int len) return -EREMOTEIO; if (!(ts->rd->f_flags & O_NONBLOCK)) - P9_DPRINTK(P9_DEBUG_ERROR, "blocking read ...\n"); + p9_debug(P9_DEBUG_ERROR, "blocking read ...\n"); ret = kernel_read(ts->rd, ts->rd->f_pos, v, len); if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN) @@ -299,7 +301,7 @@ static void p9_read_work(struct work_struct *work) if (m->err < 0) return; - P9_DPRINTK(P9_DEBUG_TRANS, "start mux %p pos %d\n", m, m->rpos); + p9_debug(P9_DEBUG_TRANS, "start mux %p pos %d\n", m, m->rpos); if (!m->rbuf) { m->rbuf = m->tmp_buf; @@ -308,11 +310,11 @@ static void p9_read_work(struct work_struct *work) } clear_bit(Rpending, &m->wsched); - P9_DPRINTK(P9_DEBUG_TRANS, "read mux %p pos %d size: %d = %d\n", m, - m->rpos, m->rsize, m->rsize-m->rpos); + p9_debug(P9_DEBUG_TRANS, "read mux %p pos %d size: %d = %d\n", + m, m->rpos, m->rsize, m->rsize-m->rpos); err = p9_fd_read(m->client, m->rbuf + m->rpos, m->rsize - m->rpos); - P9_DPRINTK(P9_DEBUG_TRANS, "mux %p got %d bytes\n", m, err); + p9_debug(P9_DEBUG_TRANS, "mux %p got %d bytes\n", m, err); if (err == -EAGAIN) { clear_bit(Rworksched, &m->wsched); return; @@ -325,25 +327,25 @@ static void p9_read_work(struct work_struct *work) if ((!m->req) && (m->rpos == m->rsize)) { /* header read in */ u16 tag; - P9_DPRINTK(P9_DEBUG_TRANS, "got new header\n"); + p9_debug(P9_DEBUG_TRANS, "got new header\n"); n = le32_to_cpu(*(__le32 *) m->rbuf); /* read packet size */ if (n >= m->client->msize) { - P9_DPRINTK(P9_DEBUG_ERROR, - "requested packet size too big: %d\n", n); + p9_debug(P9_DEBUG_ERROR, + "requested packet size too big: %d\n", n); err = -EIO; goto error; } tag = le16_to_cpu(*(__le16 *) (m->rbuf+5)); /* read tag */ - P9_DPRINTK(P9_DEBUG_TRANS, - "mux %p pkt: size: %d bytes tag: %d\n", m, n, tag); + p9_debug(P9_DEBUG_TRANS, + "mux %p pkt: size: %d bytes tag: %d\n", m, n, tag); m->req = p9_tag_lookup(m->client, tag); if (!m->req || (m->req->status != REQ_STATUS_SENT && m->req->status != REQ_STATUS_FLSH)) { - P9_DPRINTK(P9_DEBUG_ERROR, "Unexpected packet tag %d\n", - tag); + p9_debug(P9_DEBUG_ERROR, "Unexpected packet tag %d\n", + tag); err = -EIO; goto error; } @@ -364,7 +366,7 @@ static void p9_read_work(struct work_struct *work) /* not an else because some packets (like clunk) have no payload */ if ((m->req) && (m->rpos == m->rsize)) { /* packet is read in */ - P9_DPRINTK(P9_DEBUG_TRANS, "got new packet\n"); + p9_debug(P9_DEBUG_TRANS, "got new packet\n"); spin_lock(&m->client->lock); if (m->req->status != REQ_STATUS_ERROR) m->req->status = REQ_STATUS_RCVD; @@ -384,7 +386,7 @@ static void p9_read_work(struct work_struct *work) n = p9_fd_poll(m->client, NULL); if (n & POLLIN) { - P9_DPRINTK(P9_DEBUG_TRANS, "sched read work %p\n", m); + p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m); schedule_work(&m->rq); } else clear_bit(Rworksched, &m->wsched); @@ -418,7 +420,7 @@ static int p9_fd_write(struct p9_client *client, void *v, int len) return -EREMOTEIO; if (!(ts->wr->f_flags & O_NONBLOCK)) - P9_DPRINTK(P9_DEBUG_ERROR, "blocking write ...\n"); + p9_debug(P9_DEBUG_ERROR, "blocking write ...\n"); oldfs = get_fs(); set_fs(get_ds()); @@ -460,7 +462,7 @@ static void p9_write_work(struct work_struct *work) req = list_entry(m->unsent_req_list.next, struct p9_req_t, req_list); req->status = REQ_STATUS_SENT; - P9_DPRINTK(P9_DEBUG_TRANS, "move req %p\n", req); + p9_debug(P9_DEBUG_TRANS, "move req %p\n", req); list_move_tail(&req->req_list, &m->req_list); m->wbuf = req->tc->sdata; @@ -469,11 +471,11 @@ static void p9_write_work(struct work_struct *work) spin_unlock(&m->client->lock); } - P9_DPRINTK(P9_DEBUG_TRANS, "mux %p pos %d size %d\n", m, m->wpos, - m->wsize); + p9_debug(P9_DEBUG_TRANS, "mux %p pos %d size %d\n", + m, m->wpos, m->wsize); clear_bit(Wpending, &m->wsched); err = p9_fd_write(m->client, m->wbuf + m->wpos, m->wsize - m->wpos); - P9_DPRINTK(P9_DEBUG_TRANS, "mux %p sent %d bytes\n", m, err); + p9_debug(P9_DEBUG_TRANS, "mux %p sent %d bytes\n", m, err); if (err == -EAGAIN) { clear_bit(Wworksched, &m->wsched); return; @@ -497,7 +499,7 @@ static void p9_write_work(struct work_struct *work) n = p9_fd_poll(m->client, NULL); if (n & POLLOUT) { - P9_DPRINTK(P9_DEBUG_TRANS, "sched write work %p\n", m); + p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m); schedule_work(&m->wq); } else clear_bit(Wworksched, &m->wsched); @@ -551,7 +553,7 @@ p9_pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) } if (!pwait) { - P9_DPRINTK(P9_DEBUG_ERROR, "not enough wait_address slots\n"); + p9_debug(P9_DEBUG_ERROR, "not enough wait_address slots\n"); return; } @@ -573,8 +575,7 @@ static struct p9_conn *p9_conn_create(struct p9_client *client) int n; struct p9_conn *m; - P9_DPRINTK(P9_DEBUG_TRANS, "client %p msize %d\n", client, - client->msize); + p9_debug(P9_DEBUG_TRANS, "client %p msize %d\n", client, client->msize); m = kzalloc(sizeof(struct p9_conn), GFP_KERNEL); if (!m) return ERR_PTR(-ENOMEM); @@ -591,12 +592,12 @@ static struct p9_conn *p9_conn_create(struct p9_client *client) n = p9_fd_poll(client, &m->pt); if (n & POLLIN) { - P9_DPRINTK(P9_DEBUG_TRANS, "mux %p can read\n", m); + p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m); set_bit(Rpending, &m->wsched); } if (n & POLLOUT) { - P9_DPRINTK(P9_DEBUG_TRANS, "mux %p can write\n", m); + p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m); set_bit(Wpending, &m->wsched); } @@ -618,7 +619,7 @@ static void p9_poll_mux(struct p9_conn *m) n = p9_fd_poll(m->client, NULL); if (n < 0 || n & (POLLERR | POLLHUP | POLLNVAL)) { - P9_DPRINTK(P9_DEBUG_TRANS, "error mux %p err %d\n", m, n); + p9_debug(P9_DEBUG_TRANS, "error mux %p err %d\n", m, n); if (n >= 0) n = -ECONNRESET; p9_conn_cancel(m, n); @@ -626,19 +627,19 @@ static void p9_poll_mux(struct p9_conn *m) if (n & POLLIN) { set_bit(Rpending, &m->wsched); - P9_DPRINTK(P9_DEBUG_TRANS, "mux %p can read\n", m); + p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m); if (!test_and_set_bit(Rworksched, &m->wsched)) { - P9_DPRINTK(P9_DEBUG_TRANS, "sched read work %p\n", m); + p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m); schedule_work(&m->rq); } } if (n & POLLOUT) { set_bit(Wpending, &m->wsched); - P9_DPRINTK(P9_DEBUG_TRANS, "mux %p can write\n", m); + p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m); if ((m->wsize || !list_empty(&m->unsent_req_list)) && !test_and_set_bit(Wworksched, &m->wsched)) { - P9_DPRINTK(P9_DEBUG_TRANS, "sched write work %p\n", m); + p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m); schedule_work(&m->wq); } } @@ -661,8 +662,8 @@ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req) struct p9_trans_fd *ts = client->trans; struct p9_conn *m = ts->conn; - P9_DPRINTK(P9_DEBUG_TRANS, "mux %p task %p tcall %p id %d\n", m, - current, req->tc, req->tc->id); + p9_debug(P9_DEBUG_TRANS, "mux %p task %p tcall %p id %d\n", + m, current, req->tc, req->tc->id); if (m->err < 0) return m->err; @@ -686,7 +687,7 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req) { int ret = 1; - P9_DPRINTK(P9_DEBUG_TRANS, "client %p req %p\n", client, req); + p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req); spin_lock(&client->lock); @@ -726,8 +727,8 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) tmp_options = kstrdup(params, GFP_KERNEL); if (!tmp_options) { - P9_DPRINTK(P9_DEBUG_ERROR, - "failed to allocate copy of option string\n"); + p9_debug(P9_DEBUG_ERROR, + "failed to allocate copy of option string\n"); return -ENOMEM; } options = tmp_options; @@ -741,8 +742,8 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) if (token != Opt_err) { r = match_int(&args[0], &option); if (r < 0) { - P9_DPRINTK(P9_DEBUG_ERROR, - "integer field, but no integer?\n"); + p9_debug(P9_DEBUG_ERROR, + "integer field, but no integer?\n"); continue; } } @@ -801,7 +802,8 @@ static int p9_socket_open(struct p9_client *client, struct socket *csocket) csocket->sk->sk_allocation = GFP_NOIO; fd = sock_map_fd(csocket, 0); if (fd < 0) { - P9_EPRINTK(KERN_ERR, "p9_socket_open: failed to map fd\n"); + pr_err("%s (%d): failed to map fd\n", + __func__, task_pid_nr(current)); sock_release(csocket); kfree(p); return fd; @@ -837,8 +839,8 @@ static int p9_socket_open(struct p9_client *client, struct socket *csocket) static void p9_conn_destroy(struct p9_conn *m) { - P9_DPRINTK(P9_DEBUG_TRANS, "mux %p prev %p next %p\n", m, - m->mux_list.prev, m->mux_list.next); + p9_debug(P9_DEBUG_TRANS, "mux %p prev %p next %p\n", + m, m->mux_list.prev, m->mux_list.next); p9_mux_poll_stop(m); cancel_work_sync(&m->rq); @@ -919,7 +921,8 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) err = __sock_create(read_pnet(¤t->nsproxy->net_ns), PF_INET, SOCK_STREAM, IPPROTO_TCP, &csocket, 1); if (err) { - P9_EPRINTK(KERN_ERR, "p9_trans_tcp: problem creating socket\n"); + pr_err("%s (%d): problem creating socket\n", + __func__, task_pid_nr(current)); return err; } @@ -927,9 +930,8 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) (struct sockaddr *)&sin_server, sizeof(struct sockaddr_in), 0); if (err < 0) { - P9_EPRINTK(KERN_ERR, - "p9_trans_tcp: problem connecting socket to %s\n", - addr); + pr_err("%s (%d): problem connecting socket to %s\n", + __func__, task_pid_nr(current), addr); sock_release(csocket); return err; } @@ -947,8 +949,8 @@ p9_fd_create_unix(struct p9_client *client, const char *addr, char *args) csocket = NULL; if (strlen(addr) >= UNIX_PATH_MAX) { - P9_EPRINTK(KERN_ERR, "p9_trans_unix: address too long: %s\n", - addr); + pr_err("%s (%d): address too long: %s\n", + __func__, task_pid_nr(current), addr); return -ENAMETOOLONG; } @@ -957,15 +959,16 @@ p9_fd_create_unix(struct p9_client *client, const char *addr, char *args) err = __sock_create(read_pnet(¤t->nsproxy->net_ns), PF_UNIX, SOCK_STREAM, 0, &csocket, 1); if (err < 0) { - P9_EPRINTK(KERN_ERR, "p9_trans_unix: problem creating socket\n"); + pr_err("%s (%d): problem creating socket\n", + __func__, task_pid_nr(current)); + return err; } err = csocket->ops->connect(csocket, (struct sockaddr *)&sun_server, sizeof(struct sockaddr_un) - 1, 0); if (err < 0) { - P9_EPRINTK(KERN_ERR, - "p9_trans_unix: problem connecting socket: %s: %d\n", - addr, err); + pr_err("%s (%d): problem connecting socket: %s: %d\n", + __func__, task_pid_nr(current), addr, err); sock_release(csocket); return err; } @@ -983,7 +986,7 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args) parse_opts(args, &opts); if (opts.rfd == ~0 || opts.wfd == ~0) { - printk(KERN_ERR "v9fs: Insufficient options for proto=fd\n"); + pr_err("Insufficient options for proto=fd\n"); return -ENOPROTOOPT; } @@ -1050,7 +1053,7 @@ static void p9_poll_workfn(struct work_struct *work) { unsigned long flags; - P9_DPRINTK(P9_DEBUG_TRANS, "start %p\n", current); + p9_debug(P9_DEBUG_TRANS, "start %p\n", current); spin_lock_irqsave(&p9_poll_lock, flags); while (!list_empty(&p9_poll_pending_list)) { @@ -1066,7 +1069,7 @@ static void p9_poll_workfn(struct work_struct *work) } spin_unlock_irqrestore(&p9_poll_lock, flags); - P9_DPRINTK(P9_DEBUG_TRANS, "finish\n"); + p9_debug(P9_DEBUG_TRANS, "finish\n"); } int p9_trans_fd_init(void) diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 159c50f1c6bf..2c69ddd691a1 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -26,6 +26,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/in.h> #include <linux/module.h> #include <linux/net.h> @@ -178,8 +180,8 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) tmp_options = kstrdup(params, GFP_KERNEL); if (!tmp_options) { - P9_DPRINTK(P9_DEBUG_ERROR, - "failed to allocate copy of option string\n"); + p9_debug(P9_DEBUG_ERROR, + "failed to allocate copy of option string\n"); return -ENOMEM; } options = tmp_options; @@ -192,8 +194,8 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) token = match_token(p, tokens, args); r = match_int(&args[0], &option); if (r < 0) { - P9_DPRINTK(P9_DEBUG_ERROR, - "integer field, but no integer?\n"); + p9_debug(P9_DEBUG_ERROR, + "integer field, but no integer?\n"); continue; } switch (token) { @@ -301,8 +303,7 @@ handle_recv(struct p9_client *client, struct p9_trans_rdma *rdma, return; err_out: - P9_DPRINTK(P9_DEBUG_ERROR, "req %p err %d status %d\n", - req, err, status); + p9_debug(P9_DEBUG_ERROR, "req %p err %d status %d\n", req, err, status); rdma->state = P9_RDMA_FLUSHING; client->status = Disconnected; } @@ -318,8 +319,8 @@ handle_send(struct p9_client *client, struct p9_trans_rdma *rdma, static void qp_event_handler(struct ib_event *event, void *context) { - P9_DPRINTK(P9_DEBUG_ERROR, "QP event %d context %p\n", event->event, - context); + p9_debug(P9_DEBUG_ERROR, "QP event %d context %p\n", + event->event, context); } static void cq_comp_handler(struct ib_cq *cq, void *cq_context) @@ -345,8 +346,7 @@ static void cq_comp_handler(struct ib_cq *cq, void *cq_context) break; default: - printk(KERN_ERR "9prdma: unexpected completion type, " - "c->wc_op=%d, wc.opcode=%d, status=%d\n", + pr_err("unexpected completion type, c->wc_op=%d, wc.opcode=%d, status=%d\n", c->wc_op, wc.opcode, wc.status); break; } @@ -356,7 +356,7 @@ static void cq_comp_handler(struct ib_cq *cq, void *cq_context) static void cq_event_handler(struct ib_event *e, void *v) { - P9_DPRINTK(P9_DEBUG_ERROR, "CQ event %d context %p\n", e->event, v); + p9_debug(P9_DEBUG_ERROR, "CQ event %d context %p\n", e->event, v); } static void rdma_destroy_trans(struct p9_trans_rdma *rdma) @@ -407,7 +407,7 @@ post_recv(struct p9_client *client, struct p9_rdma_context *c) return ib_post_recv(rdma->qp, &wr, &bad_wr); error: - P9_DPRINTK(P9_DEBUG_ERROR, "EIO\n"); + p9_debug(P9_DEBUG_ERROR, "EIO\n"); return -EIO; } @@ -500,7 +500,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) kfree(c); kfree(rpl_context->rc); kfree(rpl_context); - P9_DPRINTK(P9_DEBUG_ERROR, "EIO\n"); + p9_debug(P9_DEBUG_ERROR, "EIO\n"); return -EIO; err_free1: kfree(rpl_context->rc); diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 32aa9834229c..3d432068f627 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -26,6 +26,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/in.h> #include <linux/module.h> #include <linux/net.h> @@ -145,7 +147,7 @@ static void req_done(struct virtqueue *vq) struct p9_req_t *req; unsigned long flags; - P9_DPRINTK(P9_DEBUG_TRANS, ": request done\n"); + p9_debug(P9_DEBUG_TRANS, ": request done\n"); while (1) { spin_lock_irqsave(&chan->lock, flags); @@ -158,8 +160,8 @@ static void req_done(struct virtqueue *vq) spin_unlock_irqrestore(&chan->lock, flags); /* Wakeup if anyone waiting for VirtIO ring space. */ wake_up(chan->vc_wq); - P9_DPRINTK(P9_DEBUG_TRANS, ": rc %p\n", rc); - P9_DPRINTK(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag); + p9_debug(P9_DEBUG_TRANS, ": rc %p\n", rc); + p9_debug(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag); req = p9_tag_lookup(chan->client, rc->tag); req->status = REQ_STATUS_RCVD; p9_client_cb(chan->client, req); @@ -257,7 +259,7 @@ p9_virtio_request(struct p9_client *client, struct p9_req_t *req) unsigned long flags; struct virtio_chan *chan = client->trans; - P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio request\n"); + p9_debug(P9_DEBUG_TRANS, "9p debug: virtio request\n"); req->status = REQ_STATUS_SENT; req_retry: @@ -270,7 +272,8 @@ req_retry: in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, req->rc->sdata, req->rc->capacity); - err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc); + err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc, + GFP_ATOMIC); if (err < 0) { if (err == -ENOSPC) { chan->ring_bufs_avail = 0; @@ -280,20 +283,19 @@ req_retry: if (err == -ERESTARTSYS) return err; - P9_DPRINTK(P9_DEBUG_TRANS, "9p:Retry virtio request\n"); + p9_debug(P9_DEBUG_TRANS, "Retry virtio request\n"); goto req_retry; } else { spin_unlock_irqrestore(&chan->lock, flags); - P9_DPRINTK(P9_DEBUG_TRANS, - "9p debug: " - "virtio rpc add_buf returned failure"); + p9_debug(P9_DEBUG_TRANS, + "virtio rpc add_buf returned failure\n"); return -EIO; } } virtqueue_kick(chan->vq); spin_unlock_irqrestore(&chan->lock, flags); - P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio request kicked\n"); + p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n"); return 0; } @@ -354,7 +356,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req, struct page **in_pages = NULL, **out_pages = NULL; struct virtio_chan *chan = client->trans; - P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio request\n"); + p9_debug(P9_DEBUG_TRANS, "virtio request\n"); if (uodata) { out_nr_pages = p9_nr_pages(uodata, outlen); @@ -413,7 +415,8 @@ req_retry_pinned: 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); + err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc, + GFP_ATOMIC); if (err < 0) { if (err == -ENOSPC) { chan->ring_bufs_avail = 0; @@ -423,20 +426,19 @@ req_retry_pinned: if (err == -ERESTARTSYS) goto err_out; - P9_DPRINTK(P9_DEBUG_TRANS, "9p:Retry virtio request\n"); + p9_debug(P9_DEBUG_TRANS, "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"); + p9_debug(P9_DEBUG_TRANS, + "virtio rpc add_buf returned failure\n"); 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"); + p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n"); err = wait_event_interruptible(*req->wq, req->status >= REQ_STATUS_RCVD); /* @@ -491,7 +493,7 @@ static int p9_virtio_probe(struct virtio_device *vdev) chan = kmalloc(sizeof(struct virtio_chan), GFP_KERNEL); if (!chan) { - printk(KERN_ERR "9p: Failed to allocate virtio 9P channel\n"); + pr_err("Failed to allocate virtio 9P channel\n"); err = -ENOMEM; goto fail; } @@ -592,7 +594,7 @@ p9_virtio_create(struct p9_client *client, const char *devname, char *args) mutex_unlock(&virtio_9p_lock); if (!found) { - printk(KERN_ERR "9p: no channels available\n"); + pr_err("no channels available\n"); return ret; } diff --git a/net/9p/util.c b/net/9p/util.c index 9c1c9348ac35..6ceeeb384de7 100644 --- a/net/9p/util.c +++ b/net/9p/util.c @@ -106,7 +106,7 @@ retry: else if (error) return -1; - P9_DPRINTK(P9_DEBUG_MUX, " id %d pool %p\n", i, p); + p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", i, p); return i; } EXPORT_SYMBOL(p9_idpool_get); @@ -124,7 +124,7 @@ void p9_idpool_put(int id, struct p9_idpool *p) { unsigned long flags; - P9_DPRINTK(P9_DEBUG_MUX, " id %d pool %p\n", id, p); + p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", id, p); spin_lock_irqsave(&p->lock, flags); idr_remove(&p->pool, id); diff --git a/net/atm/clip.c b/net/atm/clip.c index c12c2582457c..127fe70a1baa 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -46,8 +46,8 @@ static struct net_device *clip_devs; static struct atm_vcc *atmarpd; -static struct neigh_table clip_tbl; static struct timer_list idle_timer; +static const struct neigh_ops clip_neigh_ops; static int to_atmarpd(enum atmarp_ctrl_type type, int itf, __be32 ip) { @@ -123,6 +123,8 @@ static int neigh_check_cb(struct neighbour *n) struct atmarp_entry *entry = neighbour_priv(n); struct clip_vcc *cv; + if (n->ops != &clip_neigh_ops) + return 0; for (cv = entry->vccs; cv; cv = cv->next) { unsigned long exp = cv->last_use + cv->idle_timeout; @@ -154,10 +156,10 @@ static int neigh_check_cb(struct neighbour *n) static void idle_timer_check(unsigned long dummy) { - write_lock(&clip_tbl.lock); - __neigh_for_each_release(&clip_tbl, neigh_check_cb); + write_lock(&arp_tbl.lock); + __neigh_for_each_release(&arp_tbl, neigh_check_cb); mod_timer(&idle_timer, jiffies + CLIP_CHECK_INTERVAL * HZ); - write_unlock(&clip_tbl.lock); + write_unlock(&arp_tbl.lock); } static int clip_arp_rcv(struct sk_buff *skb) diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index cdcfcabb34ab..72eb187a5f60 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -71,19 +71,16 @@ static const char *const bt_slock_key_strings[BT_MAX_PROTO] = { "slock-AF_BLUETOOTH-BTPROTO_AVDTP", }; -static inline void bt_sock_reclassify_lock(struct socket *sock, int proto) +void bt_sock_reclassify_lock(struct sock *sk, int proto) { - struct sock *sk = sock->sk; - - if (!sk) - return; - + BUG_ON(!sk); BUG_ON(sock_owned_by_user(sk)); sock_lock_init_class_and_name(sk, bt_slock_key_strings[proto], &bt_slock_key[proto], bt_key_strings[proto], &bt_lock_key[proto]); } +EXPORT_SYMBOL(bt_sock_reclassify_lock); int bt_sock_register(int proto, const struct net_proto_family *ops) { @@ -145,7 +142,8 @@ static int bt_sock_create(struct net *net, struct socket *sock, int proto, if (bt_proto[proto] && try_module_get(bt_proto[proto]->owner)) { err = bt_proto[proto]->create(net, sock, proto, kern); - bt_sock_reclassify_lock(sock, proto); + if (!err) + bt_sock_reclassify_lock(sock->sk, proto); module_put(bt_proto[proto]->owner); } @@ -156,17 +154,17 @@ static int bt_sock_create(struct net *net, struct socket *sock, int proto, void bt_sock_link(struct bt_sock_list *l, struct sock *sk) { - write_lock_bh(&l->lock); + write_lock(&l->lock); sk_add_node(sk, &l->head); - write_unlock_bh(&l->lock); + write_unlock(&l->lock); } EXPORT_SYMBOL(bt_sock_link); void bt_sock_unlink(struct bt_sock_list *l, struct sock *sk) { - write_lock_bh(&l->lock); + write_lock(&l->lock); sk_del_node_init(sk); - write_unlock_bh(&l->lock); + write_unlock(&l->lock); } EXPORT_SYMBOL(bt_sock_unlink); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 3db432473ad5..07bc69ed9498 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -635,6 +635,10 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->pend)) { struct hci_cp_auth_requested cp; + + /* encrypt must be pending if auth is also pending */ + set_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend); + cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED, sizeof(cp), &cp); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 845da3ee56a0..5aeb62491198 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -55,7 +55,7 @@ #define AUTO_OFF_TIMEOUT 2000 -int enable_hs; +bool enable_hs; static void hci_rx_work(struct work_struct *work); static void hci_cmd_work(struct work_struct *work); @@ -640,7 +640,8 @@ static int hci_dev_do_close(struct hci_dev *hdev) /* Reset device */ skb_queue_purge(&hdev->cmd_q); atomic_set(&hdev->cmd_cnt, 1); - if (!test_bit(HCI_RAW, &hdev->flags)) { + if (!test_bit(HCI_RAW, &hdev->flags) && + test_bit(HCI_QUIRK_NO_RESET, &hdev->quirks)) { set_bit(HCI_INIT, &hdev->flags); __hci_request(hdev, hci_reset_req, 0, msecs_to_jiffies(250)); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 4221bd256bdd..001307f81057 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -711,7 +711,14 @@ static void hci_cc_read_local_ext_features(struct hci_dev *hdev, if (rp->status) return; - memcpy(hdev->extfeatures, rp->features, 8); + switch (rp->page) { + case 0: + memcpy(hdev->features, rp->features, 8); + break; + case 1: + memcpy(hdev->host_features, rp->features, 8); + break; + } hci_req_complete(hdev, HCI_OP_READ_LOCAL_EXT_FEATURES, rp->status); } @@ -1047,9 +1054,7 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, case LE_SCANNING_DISABLED: clear_bit(HCI_LE_SCAN, &hdev->dev_flags); - cancel_delayed_work_sync(&hdev->adv_work); - queue_delayed_work(hdev->workqueue, &hdev->adv_work, - jiffies + ADV_CLEAR_TIMEOUT); + schedule_delayed_work(&hdev->adv_work, ADV_CLEAR_TIMEOUT); break; default: @@ -2266,20 +2271,19 @@ static inline void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *s struct hci_ev_num_comp_pkts *ev = (void *) skb->data; int i; - skb_pull(skb, sizeof(*ev)); - - BT_DBG("%s num_hndl %d", hdev->name, ev->num_hndl); - if (hdev->flow_ctl_mode != HCI_FLOW_CTL_MODE_PACKET_BASED) { BT_ERR("Wrong event for mode %d", hdev->flow_ctl_mode); return; } - if (skb->len < ev->num_hndl * 4) { + if (skb->len < sizeof(*ev) || skb->len < sizeof(*ev) + + ev->num_hndl * sizeof(struct hci_comp_pkts_info)) { BT_DBG("%s bad parameters", hdev->name); return; } + BT_DBG("%s num_hndl %d", hdev->name, ev->num_hndl); + for (i = 0; i < ev->num_hndl; i++) { struct hci_comp_pkts_info *info = &ev->handles[i]; struct hci_conn *conn; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 6d94616af312..0dcc96266779 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -767,7 +767,6 @@ static int hci_sock_dev_event(struct notifier_block *this, unsigned long event, /* Detach sockets from device */ read_lock(&hci_sk_list.lock); sk_for_each(sk, node, &hci_sk_list.head) { - local_bh_disable(); bh_lock_sock_nested(sk); if (hci_pi(sk)->hdev == hdev) { hci_pi(sk)->hdev = NULL; @@ -778,7 +777,6 @@ static int hci_sock_dev_event(struct notifier_block *this, unsigned long event, hci_dev_put(hdev); } bh_unlock_sock(sk); - local_bh_enable(); } read_unlock(&hci_sk_list.lock); } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index aa78d8c4b93b..32d338c30e65 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -165,7 +165,7 @@ int l2cap_add_psm(struct l2cap_chan *chan, bdaddr_t *src, __le16 psm) { int err; - write_lock_bh(&chan_list_lock); + write_lock(&chan_list_lock); if (psm && __l2cap_global_chan_by_addr(psm, src)) { err = -EADDRINUSE; @@ -190,17 +190,17 @@ int l2cap_add_psm(struct l2cap_chan *chan, bdaddr_t *src, __le16 psm) } done: - write_unlock_bh(&chan_list_lock); + write_unlock(&chan_list_lock); return err; } int l2cap_add_scid(struct l2cap_chan *chan, __u16 scid) { - write_lock_bh(&chan_list_lock); + write_lock(&chan_list_lock); chan->scid = scid; - write_unlock_bh(&chan_list_lock); + write_unlock(&chan_list_lock); return 0; } @@ -289,9 +289,9 @@ struct l2cap_chan *l2cap_chan_create(struct sock *sk) chan->sk = sk; - write_lock_bh(&chan_list_lock); + write_lock(&chan_list_lock); list_add(&chan->global_l, &chan_list); - write_unlock_bh(&chan_list_lock); + write_unlock(&chan_list_lock); INIT_DELAYED_WORK(&chan->chan_timer, l2cap_chan_timeout); @@ -306,9 +306,9 @@ struct l2cap_chan *l2cap_chan_create(struct sock *sk) void l2cap_chan_destroy(struct l2cap_chan *chan) { - write_lock_bh(&chan_list_lock); + write_lock(&chan_list_lock); list_del(&chan->global_l); - write_unlock_bh(&chan_list_lock); + write_unlock(&chan_list_lock); l2cap_chan_put(chan); } @@ -543,14 +543,14 @@ static u8 l2cap_get_ident(struct l2cap_conn *conn) * 200 - 254 are used by utilities like l2ping, etc. */ - spin_lock_bh(&conn->lock); + spin_lock(&conn->lock); if (++conn->tx_ident > 128) conn->tx_ident = 1; id = conn->tx_ident; - spin_unlock_bh(&conn->lock); + spin_unlock(&conn->lock); return id; } @@ -1018,10 +1018,10 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) hci_chan_del(conn->hchan); if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) - __cancel_delayed_work(&conn->info_timer); + cancel_delayed_work_sync(&conn->info_timer); if (test_and_clear_bit(HCI_CONN_LE_SMP_PEND, &hcon->pend)) { - __cancel_delayed_work(&conn->security_timer); + cancel_delayed_work_sync(&conn->security_timer); smp_chan_destroy(conn); } @@ -1120,7 +1120,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, bdaddr return c1; } -inline int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, bdaddr_t *dst) +int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, bdaddr_t *dst) { struct sock *sk = chan->sk; bdaddr_t *src = &bt_sk(sk)->src; @@ -1190,7 +1190,7 @@ inline int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, bdad } /* Set destination address and psm */ - bacpy(&bt_sk(sk)->dst, src); + bacpy(&bt_sk(sk)->dst, dst); chan->psm = psm; chan->dcid = cid; @@ -2574,7 +2574,7 @@ static inline int l2cap_command_rej(struct l2cap_conn *conn, struct l2cap_cmd_hd if ((conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) && cmd->ident == conn->info_ident) { - __cancel_delayed_work(&conn->info_timer); + cancel_delayed_work(&conn->info_timer); conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE; conn->info_ident = 0; @@ -2970,7 +2970,8 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr default: sk->sk_err = ECONNRESET; - __set_chan_timer(chan, L2CAP_DISC_REJ_TIMEOUT); + __set_chan_timer(chan, + msecs_to_jiffies(L2CAP_DISC_REJ_TIMEOUT)); l2cap_send_disconn_req(conn, chan, ECONNRESET); goto done; } @@ -3120,7 +3121,7 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn, struct l2cap_cm conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_DONE) return 0; - __cancel_delayed_work(&conn->info_timer); + cancel_delayed_work(&conn->info_timer); if (result != L2CAP_IR_SUCCESS) { conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE; @@ -4478,7 +4479,8 @@ 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, L2CAP_ENC_TIMEOUT); + __set_chan_timer(chan, + msecs_to_jiffies(L2CAP_ENC_TIMEOUT)); } else if (chan->sec_level == BT_SECURITY_HIGH) l2cap_chan_close(chan, ECONNREFUSED); } else { @@ -4499,7 +4501,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) if (hcon->type == LE_LINK) { smp_distribute_keys(conn, 0); - __cancel_delayed_work(&conn->security_timer); + cancel_delayed_work(&conn->security_timer); } rcu_read_lock(); @@ -4546,7 +4548,8 @@ 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, L2CAP_DISC_TIMEOUT); + __set_chan_timer(chan, + msecs_to_jiffies(L2CAP_DISC_TIMEOUT)); } } else if (chan->state == BT_CONNECT2) { struct l2cap_conn_rsp rsp; @@ -4566,7 +4569,8 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) } } else { l2cap_state_change(chan, BT_DISCONN); - __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); + __set_chan_timer(chan, + msecs_to_jiffies(L2CAP_DISC_TIMEOUT)); res = L2CAP_CR_SEC_BLOCK; stat = L2CAP_CS_NO_INFO; } @@ -4702,7 +4706,7 @@ static int l2cap_debugfs_show(struct seq_file *f, void *p) { struct l2cap_chan *c; - read_lock_bh(&chan_list_lock); + read_lock(&chan_list_lock); list_for_each_entry(c, &chan_list, global_l) { struct sock *sk = c->sk; @@ -4715,7 +4719,7 @@ static int l2cap_debugfs_show(struct seq_file *f, void *p) c->sec_level, c->mode); } - read_unlock_bh(&chan_list_lock); + read_unlock(&chan_list_lock); return 0; } diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 9ca5616166f7..401d9428ae4c 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -587,6 +587,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch if (smp_conn_security(conn, sec.level)) break; sk->sk_state = BT_CONFIG; + chan->state = BT_CONFIG; /* or for ACL link, under defer_setup time */ } else if (sk->sk_state == BT_CONNECT2 && @@ -731,6 +732,7 @@ static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct ms if (sk->sk_state == BT_CONNECT2 && bt_sk(sk)->defer_setup) { sk->sk_state = BT_CONFIG; + pi->chan->state = BT_CONFIG; __l2cap_connect_rsp_defer(pi->chan); release_sock(sk); @@ -847,6 +849,8 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(void *data) if (!sk) return NULL; + bt_sock_reclassify_lock(sk, BTPROTO_L2CAP); + l2cap_sock_init(sk, parent); return l2cap_pi(sk)->chan; @@ -1000,7 +1004,7 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int p INIT_LIST_HEAD(&bt_sk(sk)->accept_q); sk->sk_destruct = l2cap_sock_destruct; - sk->sk_sndtimeo = L2CAP_CONN_TIMEOUT; + sk->sk_sndtimeo = msecs_to_jiffies(L2CAP_CONN_TIMEOUT); sock_reset_flag(sk, SOCK_ZAPPED); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 2540944d871f..bc8e59dda78e 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -291,7 +291,7 @@ static u32 get_current_settings(struct hci_dev *hdev) if (!(hdev->features[4] & LMP_NO_BREDR)) settings |= MGMT_SETTING_BREDR; - if (hdev->extfeatures[0] & LMP_HOST_LE) + if (hdev->host_features[0] & LMP_HOST_LE) settings |= MGMT_SETTING_LE; if (test_bit(HCI_AUTH, &hdev->flags)) @@ -2756,7 +2756,7 @@ int mgmt_stop_discovery_failed(struct hci_dev *hdev, u8 status) if (!cmd) return -ENOENT; - err = cmd_status(cmd->sk, hdev->id, cmd->opcode, status); + err = cmd_status(cmd->sk, hdev->id, cmd->opcode, mgmt_status(status)); mgmt_pending_remove(cmd); return err; diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 501649bf5596..8a602388f1e7 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1164,12 +1164,18 @@ static int rfcomm_recv_ua(struct rfcomm_session *s, u8 dlci) break; case BT_DISCONN: - /* When socket is closed and we are not RFCOMM - * initiator rfcomm_process_rx already calls - * rfcomm_session_put() */ - if (s->sock->sk->sk_state != BT_CLOSED) - if (list_empty(&s->dlcs)) - rfcomm_session_put(s); + /* rfcomm_session_put is called later so don't do + * anything here otherwise we will mess up the session + * reference counter: + * + * (a) when we are the initiator dlc_unlink will drive + * the reference counter to 0 (there is no initial put + * after session_add) + * + * (b) when we are not the initiator rfcomm_rx_process + * will explicitly call put to balance the initial hold + * done after session add. + */ break; } } diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index aea2bdd1510f..22169c3f1482 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -370,7 +370,7 @@ static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr goto done; } - write_lock_bh(&rfcomm_sk_list.lock); + write_lock(&rfcomm_sk_list.lock); if (sa->rc_channel && __rfcomm_get_sock_by_addr(sa->rc_channel, &sa->rc_bdaddr)) { err = -EADDRINUSE; @@ -381,7 +381,7 @@ static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr sk->sk_state = BT_BOUND; } - write_unlock_bh(&rfcomm_sk_list.lock); + write_unlock(&rfcomm_sk_list.lock); done: release_sock(sk); @@ -455,7 +455,7 @@ static int rfcomm_sock_listen(struct socket *sock, int backlog) err = -EINVAL; - write_lock_bh(&rfcomm_sk_list.lock); + write_lock(&rfcomm_sk_list.lock); for (channel = 1; channel < 31; channel++) if (!__rfcomm_get_sock_by_addr(channel, src)) { @@ -464,7 +464,7 @@ static int rfcomm_sock_listen(struct socket *sock, int backlog) break; } - write_unlock_bh(&rfcomm_sk_list.lock); + write_unlock(&rfcomm_sk_list.lock); if (err < 0) goto done; @@ -956,6 +956,8 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc * if (!sk) goto done; + bt_sock_reclassify_lock(sk, BTPROTO_RFCOMM); + rfcomm_sock_init(sk, parent); bacpy(&bt_sk(sk)->src, &src); bacpy(&bt_sk(sk)->dst, &dst); @@ -982,7 +984,7 @@ static int rfcomm_sock_debugfs_show(struct seq_file *f, void *p) struct sock *sk; struct hlist_node *node; - read_lock_bh(&rfcomm_sk_list.lock); + read_lock(&rfcomm_sk_list.lock); sk_for_each(sk, node, &rfcomm_sk_list.head) { seq_printf(f, "%s %s %d %d\n", @@ -991,7 +993,7 @@ static int rfcomm_sock_debugfs_show(struct seq_file *f, void *p) sk->sk_state, rfcomm_pi(sk)->channel); } - read_unlock_bh(&rfcomm_sk_list.lock); + read_unlock(&rfcomm_sk_list.lock); return 0; } diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index fa8f4de53b99..a2d4f5122a6a 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -76,7 +76,7 @@ struct rfcomm_dev { }; static LIST_HEAD(rfcomm_dev_list); -static DEFINE_RWLOCK(rfcomm_dev_lock); +static DEFINE_SPINLOCK(rfcomm_dev_lock); static void rfcomm_dev_data_ready(struct rfcomm_dlc *dlc, struct sk_buff *skb); static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err); @@ -146,7 +146,7 @@ static inline struct rfcomm_dev *rfcomm_dev_get(int id) { struct rfcomm_dev *dev; - read_lock(&rfcomm_dev_lock); + spin_lock(&rfcomm_dev_lock); dev = __rfcomm_dev_get(id); @@ -157,7 +157,7 @@ static inline struct rfcomm_dev *rfcomm_dev_get(int id) rfcomm_dev_hold(dev); } - read_unlock(&rfcomm_dev_lock); + spin_unlock(&rfcomm_dev_lock); return dev; } @@ -205,7 +205,7 @@ static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) if (!dev) return -ENOMEM; - write_lock_bh(&rfcomm_dev_lock); + spin_lock(&rfcomm_dev_lock); if (req->dev_id < 0) { dev->id = 0; @@ -290,7 +290,7 @@ static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) __module_get(THIS_MODULE); out: - write_unlock_bh(&rfcomm_dev_lock); + spin_unlock(&rfcomm_dev_lock); if (err < 0) goto free; @@ -327,9 +327,9 @@ static void rfcomm_dev_del(struct rfcomm_dev *dev) if (atomic_read(&dev->opened) > 0) return; - write_lock_bh(&rfcomm_dev_lock); + spin_lock(&rfcomm_dev_lock); list_del_init(&dev->list); - write_unlock_bh(&rfcomm_dev_lock); + spin_unlock(&rfcomm_dev_lock); rfcomm_dev_put(dev); } @@ -473,7 +473,7 @@ static int rfcomm_get_dev_list(void __user *arg) di = dl->dev_info; - read_lock_bh(&rfcomm_dev_lock); + spin_lock(&rfcomm_dev_lock); list_for_each_entry(dev, &rfcomm_dev_list, list) { if (test_bit(RFCOMM_TTY_RELEASED, &dev->flags)) @@ -488,7 +488,7 @@ static int rfcomm_get_dev_list(void __user *arg) break; } - read_unlock_bh(&rfcomm_dev_lock); + spin_unlock(&rfcomm_dev_lock); dl->dev_num = n; size = sizeof(*dl) + n * sizeof(*di); @@ -766,9 +766,9 @@ static void rfcomm_tty_close(struct tty_struct *tty, struct file *filp) rfcomm_dlc_unlock(dev->dlc); if (test_bit(RFCOMM_TTY_RELEASED, &dev->flags)) { - write_lock_bh(&rfcomm_dev_lock); + spin_lock(&rfcomm_dev_lock); list_del_init(&dev->list); - write_unlock_bh(&rfcomm_dev_lock); + spin_unlock(&rfcomm_dev_lock); rfcomm_dev_put(dev); } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 5dc2f2126fac..8bf26d1bc5c1 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -482,7 +482,7 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_le goto done; } - write_lock_bh(&sco_sk_list.lock); + write_lock(&sco_sk_list.lock); if (bacmp(src, BDADDR_ANY) && __sco_get_sock_by_addr(src)) { err = -EADDRINUSE; @@ -492,7 +492,7 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_le sk->sk_state = BT_BOUND; } - write_unlock_bh(&sco_sk_list.lock); + write_unlock(&sco_sk_list.lock); done: release_sock(sk); @@ -965,14 +965,14 @@ static int sco_debugfs_show(struct seq_file *f, void *p) struct sock *sk; struct hlist_node *node; - read_lock_bh(&sco_sk_list.lock); + read_lock(&sco_sk_list.lock); sk_for_each(sk, node, &sco_sk_list.head) { seq_printf(f, "%s %s %d\n", batostr(&bt_sk(sk)->src), batostr(&bt_sk(sk)->dst), sk->sk_state); } - read_unlock_bh(&sco_sk_list.lock); + read_unlock(&sco_sk_list.lock); return 0; } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index f963f6b1884f..5ba0c844d508 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -146,7 +146,7 @@ void br_fdb_cleanup(unsigned long _data) unsigned long next_timer = jiffies + br->ageing_time; int i; - spin_lock_bh(&br->hash_lock); + spin_lock(&br->hash_lock); for (i = 0; i < BR_HASH_SIZE; i++) { struct net_bridge_fdb_entry *f; struct hlist_node *h, *n; @@ -162,7 +162,7 @@ void br_fdb_cleanup(unsigned long _data) next_timer = this_timer; } } - spin_unlock_bh(&br->hash_lock); + spin_unlock(&br->hash_lock); mod_timer(&br->gc_timer, round_jiffies_up(next_timer)); } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 568d5bf17534..702a1ae9220b 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -446,8 +446,11 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, ip6h->nexthdr = IPPROTO_HOPOPTS; ip6h->hop_limit = 1; ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1)); - ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0, - &ip6h->saddr); + if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0, + &ip6h->saddr)) { + kfree_skb(skb); + return NULL; + } ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); hopopt = (u8 *)(ip6h + 1); diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 84122472656c..dec4f3817133 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -62,6 +62,15 @@ static int brnf_filter_pppoe_tagged __read_mostly = 0; #define brnf_filter_pppoe_tagged 0 #endif +#define IS_IP(skb) \ + (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IP)) + +#define IS_IPV6(skb) \ + (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IPV6)) + +#define IS_ARP(skb) \ + (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_ARP)) + static inline __be16 vlan_proto(const struct sk_buff *skb) { if (vlan_tx_tag_present(skb)) @@ -639,8 +648,7 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb, return NF_DROP; br = p->br; - if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) || - IS_PPPOE_IPV6(skb)) { + if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) { if (!brnf_call_ip6tables && !br->nf_call_ip6tables) return NF_ACCEPT; @@ -651,8 +659,7 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb, if (!brnf_call_iptables && !br->nf_call_iptables) return NF_ACCEPT; - if (skb->protocol != htons(ETH_P_IP) && !IS_VLAN_IP(skb) && - !IS_PPPOE_IP(skb)) + if (!IS_IP(skb) && !IS_VLAN_IP(skb) && !IS_PPPOE_IP(skb)) return NF_ACCEPT; nf_bridge_pull_encap_header_rcsum(skb); @@ -701,7 +708,7 @@ static int br_nf_forward_finish(struct sk_buff *skb) struct nf_bridge_info *nf_bridge = skb->nf_bridge; struct net_device *in; - if (skb->protocol != htons(ETH_P_ARP) && !IS_VLAN_ARP(skb)) { + if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) { in = nf_bridge->physindev; if (nf_bridge->mask & BRNF_PKT_TYPE) { skb->pkt_type = PACKET_OTHERHOST; @@ -718,6 +725,7 @@ static int br_nf_forward_finish(struct sk_buff *skb) return 0; } + /* This is the 'purely bridged' case. For IP, we pass the packet to * netfilter with indev and outdev set to the bridge device, * but we are still able to filter on the 'real' indev/outdev @@ -744,11 +752,9 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb, if (!parent) return NF_DROP; - if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb) || - IS_PPPOE_IP(skb)) + if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb)) pf = PF_INET; - else if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) || - IS_PPPOE_IPV6(skb)) + else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) pf = PF_INET6; else return NF_ACCEPT; @@ -795,7 +801,7 @@ static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff *skb, if (!brnf_call_arptables && !br->nf_call_arptables) return NF_ACCEPT; - if (skb->protocol != htons(ETH_P_ARP)) { + if (!IS_ARP(skb)) { if (!IS_VLAN_ARP(skb)) return NF_ACCEPT; nf_bridge_pull_encap_header(skb); @@ -853,11 +859,9 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, if (!realoutdev) return NF_DROP; - if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb) || - IS_PPPOE_IP(skb)) + if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb)) pf = PF_INET; - else if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) || - IS_PPPOE_IPV6(skb)) + else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) pf = PF_INET6; else return NF_ACCEPT; diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index dd147d78a588..8c836d96ba76 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -17,9 +17,9 @@ #include "br_private_stp.h" /* since time values in bpdu are in jiffies and then scaled (1/256) - * before sending, make sure that is at least one. + * before sending, make sure that is at least one STP tick. */ -#define MESSAGE_AGE_INCR ((HZ < 256) ? 1 : (HZ/256)) +#define MESSAGE_AGE_INCR ((HZ / 256) + 1) static const char *const br_port_state_names[] = { [BR_STATE_DISABLED] = "disabled", @@ -31,7 +31,7 @@ static const char *const br_port_state_names[] = { void br_log_state(const struct net_bridge_port *p) { - br_info(p->br, "port %u(%s) entering %s state\n", + br_info(p->br, "port %u(%s) entered %s state\n", (unsigned) p->port_no, p->dev->name, br_port_state_names[p->state]); } @@ -186,7 +186,7 @@ static void br_record_config_information(struct net_bridge_port *p, p->designated_cost = bpdu->root_path_cost; p->designated_bridge = bpdu->bridge_id; p->designated_port = bpdu->port_id; - p->designated_age = jiffies + bpdu->message_age; + p->designated_age = jiffies - bpdu->message_age; mod_timer(&p->message_age_timer, jiffies + (p->br->max_age - bpdu->message_age)); diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 19308e305d85..f494496373d6 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -98,14 +98,13 @@ void br_stp_disable_port(struct net_bridge_port *p) struct net_bridge *br = p->br; int wasroot; - br_log_state(p); - wasroot = br_is_root_bridge(br); br_become_designated_port(p); p->state = BR_STATE_DISABLED; p->topology_change_ack = 0; p->config_pending = 0; + br_log_state(p); br_ifinfo_notify(RTM_NEWLINK, p); del_timer(&p->message_age_timer); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 5864cc491369..5fe2ff3b01ef 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1335,7 +1335,12 @@ static inline int ebt_make_matchname(const struct ebt_entry_match *m, const char *base, char __user *ubase) { char __user *hlp = ubase + ((char *)m - base); - if (copy_to_user(hlp, m->u.match->name, EBT_FUNCTION_MAXNAMELEN)) + char name[EBT_FUNCTION_MAXNAMELEN] = {}; + + /* ebtables expects 32 bytes long names but xt_match names are 29 bytes + long. Copy 29 bytes and fill remaining bytes with zeroes. */ + strncpy(name, m->u.match->name, sizeof(name)); + if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN)) return -EFAULT; return 0; } @@ -1344,7 +1349,10 @@ static inline int ebt_make_watchername(const struct ebt_entry_watcher *w, const char *base, char __user *ubase) { char __user *hlp = ubase + ((char *)w - base); - if (copy_to_user(hlp , w->u.watcher->name, EBT_FUNCTION_MAXNAMELEN)) + char name[EBT_FUNCTION_MAXNAMELEN] = {}; + + strncpy(name, w->u.watcher->name, sizeof(name)); + if (copy_to_user(hlp , name, EBT_FUNCTION_MAXNAMELEN)) return -EFAULT; return 0; } @@ -1355,6 +1363,7 @@ ebt_make_names(struct ebt_entry *e, const char *base, char __user *ubase) int ret; char __user *hlp; const struct ebt_entry_target *t; + char name[EBT_FUNCTION_MAXNAMELEN] = {}; if (e->bitmask == 0) return 0; @@ -1368,7 +1377,8 @@ ebt_make_names(struct ebt_entry *e, const char *base, char __user *ubase) ret = EBT_WATCHER_ITERATE(e, ebt_make_watchername, base, ubase); if (ret != 0) return ret; - if (copy_to_user(hlp, t->u.target->name, EBT_FUNCTION_MAXNAMELEN)) + strncpy(name, t->u.target->name, sizeof(name)); + if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN)) return -EFAULT; return 0; } @@ -1893,10 +1903,7 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, switch (compat_mwt) { case EBT_COMPAT_MATCH: - match = try_then_request_module(xt_find_match(NFPROTO_BRIDGE, - name, 0), "ebt_%s", name); - if (match == NULL) - return -ENOENT; + match = xt_request_find_match(NFPROTO_BRIDGE, name, 0); if (IS_ERR(match)) return PTR_ERR(match); @@ -1915,10 +1922,7 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, break; case EBT_COMPAT_WATCHER: /* fallthrough */ case EBT_COMPAT_TARGET: - wt = try_then_request_module(xt_find_target(NFPROTO_BRIDGE, - name, 0), "ebt_%s", name); - if (wt == NULL) - return -ENOENT; + wt = xt_request_find_target(NFPROTO_BRIDGE, name, 0); if (IS_ERR(wt)) return PTR_ERR(wt); off = xt_compat_target_offset(wt); diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index b0ce14fbf6ef..82c57069415f 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -59,8 +59,6 @@ struct cfcnfg *get_cfcnfg(struct net *net) { struct caif_net *caifn; caifn = net_generic(net, caif_net_id); - if (!caifn) - return NULL; return caifn->cfg; } EXPORT_SYMBOL(get_cfcnfg); @@ -69,19 +67,17 @@ static struct caif_device_entry_list *caif_device_list(struct net *net) { struct caif_net *caifn; caifn = net_generic(net, caif_net_id); - if (!caifn) - return NULL; return &caifn->caifdevs; } static void caifd_put(struct caif_device_entry *e) { - irqsafe_cpu_dec(*e->pcpu_refcnt); + this_cpu_dec(*e->pcpu_refcnt); } static void caifd_hold(struct caif_device_entry *e) { - irqsafe_cpu_inc(*e->pcpu_refcnt); + this_cpu_inc(*e->pcpu_refcnt); } static int caifd_refcnt_read(struct caif_device_entry *e) @@ -99,8 +95,6 @@ static struct caif_device_entry *caif_device_alloc(struct net_device *dev) struct caif_device_entry *caifd; caifdevs = caif_device_list(dev_net(dev)); - if (!caifdevs) - return NULL; caifd = kzalloc(sizeof(*caifd), GFP_KERNEL); if (!caifd) @@ -120,8 +114,6 @@ static struct caif_device_entry *caif_get(struct net_device *dev) struct caif_device_entry_list *caifdevs = caif_device_list(dev_net(dev)); struct caif_device_entry *caifd; - if (!caifdevs) - return NULL; list_for_each_entry_rcu(caifd, &caifdevs->list, list) { if (caifd->netdev == dev) @@ -146,15 +138,17 @@ void caif_flow_cb(struct sk_buff *skb) spin_lock_bh(&caifd->flow_lock); send_xoff = caifd->xoff; caifd->xoff = 0; - if (!WARN_ON(caifd->xoff_skb_dtor == NULL)) { - WARN_ON(caifd->xoff_skb != skb); - dtor = caifd->xoff_skb_dtor; - caifd->xoff_skb = NULL; - caifd->xoff_skb_dtor = NULL; - } + dtor = caifd->xoff_skb_dtor; + + if (WARN_ON(caifd->xoff_skb != skb)) + skb = NULL; + + caifd->xoff_skb = NULL; + caifd->xoff_skb_dtor = NULL; + spin_unlock_bh(&caifd->flow_lock); - if (dtor) + if (dtor && skb) dtor(skb); if (send_xoff) @@ -319,8 +313,6 @@ void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, struct caif_device_entry_list *caifdevs; caifdevs = caif_device_list(dev_net(dev)); - if (!cfg || !caifdevs) - return; caifd = caif_device_alloc(dev); if (!caifd) return; @@ -372,8 +364,6 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what, cfg = get_cfcnfg(dev_net(dev)); caifdevs = caif_device_list(dev_net(dev)); - if (!cfg || !caifdevs) - return 0; caifd = caif_get(dev); if (caifd == NULL && dev->type != ARPHRD_CAIF) @@ -505,9 +495,6 @@ static struct notifier_block caif_device_notifier = { static int caif_init_net(struct net *net) { struct caif_net *caifn = net_generic(net, caif_net_id); - if (WARN_ON(!caifn)) - return -EINVAL; - INIT_LIST_HEAD(&caifn->caifdevs.list); mutex_init(&caifn->caifdevs.lock); @@ -525,9 +512,6 @@ static void caif_exit_net(struct net *net) caif_device_list(net); struct cfcnfg *cfg = get_cfcnfg(net); - if (!cfg || !caifdevs) - return; - rtnl_lock(); mutex_lock(&caifdevs->lock); @@ -567,7 +551,7 @@ static int __init caif_device_init(void) { int result; - result = register_pernet_device(&caif_net_ops); + result = register_pernet_subsys(&caif_net_ops); if (result) return result; @@ -580,7 +564,7 @@ static int __init caif_device_init(void) static void __exit caif_device_exit(void) { - unregister_pernet_device(&caif_net_ops); + unregister_pernet_subsys(&caif_net_ops); unregister_netdevice_notifier(&caif_device_notifier); dev_remove_pack(&caif_packet_type); } diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index a98628086452..a97d97a3a512 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -539,8 +539,10 @@ static int transmit_skb(struct sk_buff *skb, struct caifsock *cf_sk, pkt = cfpkt_fromnative(CAIF_DIR_OUT, skb); memset(skb->cb, 0, sizeof(struct caif_payload_info)); - if (cf_sk->layer.dn == NULL) + if (cf_sk->layer.dn == NULL) { + kfree_skb(skb); return -EINVAL; + } return cf_sk->layer.dn->transmit(cf_sk->layer.dn, pkt); } @@ -683,10 +685,10 @@ static int caif_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, } err = transmit_skb(skb, cf_sk, msg->msg_flags&MSG_DONTWAIT, timeo); - if (err < 0) { - kfree_skb(skb); + if (err < 0) + /* skb is already freed */ goto pipe_err; - } + sent += size; } diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c index 5fc9eca8cd41..fd7cbf5aa895 100644 --- a/net/caif/caif_usb.c +++ b/net/caif/caif_usb.c @@ -11,7 +11,6 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/slab.h> -#include <linux/netdevice.h> #include <linux/mii.h> #include <linux/usb.h> #include <linux/usb/usbnet.h> @@ -27,7 +26,7 @@ MODULE_LICENSE("GPL"); #define CFUSB_ALIGNMENT 4 /* Number of bytes to align. */ #define CFUSB_MAX_HEADLEN (CFUSB_PAD_DESCR_SZ + CFUSB_ALIGNMENT-1) #define STE_USB_VID 0x04cc /* USB Product ID for ST-Ericsson */ -#define STE_USB_PID_CAIF 0x2306 /* Product id for CAIF Modems */ +#define STE_USB_PID_CAIF 0x230f /* Product id for CAIF Modems */ struct cfusbl { struct cflayer layer; diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index 598aafb4cb51..ba9cfd47778a 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -309,7 +309,6 @@ int caif_connect_client(struct net *net, struct caif_connect_request *conn_req, int err; struct cfctrl_link_param param; struct cfcnfg *cfg = get_cfcnfg(net); - caif_assert(cfg != NULL); rcu_read_lock(); err = caif_connect_req_to_link_param(cfg, conn_req, ¶m); diff --git a/net/caif/cffrml.c b/net/caif/cffrml.c index d3ca87bf23b7..0a7df7ef062d 100644 --- a/net/caif/cffrml.c +++ b/net/caif/cffrml.c @@ -177,14 +177,14 @@ void cffrml_put(struct cflayer *layr) { struct cffrml *this = container_obj(layr); if (layr != NULL && this->pcpu_refcnt != NULL) - irqsafe_cpu_dec(*this->pcpu_refcnt); + this_cpu_dec(*this->pcpu_refcnt); } void cffrml_hold(struct cflayer *layr) { struct cffrml *this = container_obj(layr); if (layr != NULL && this->pcpu_refcnt != NULL) - irqsafe_cpu_inc(*this->pcpu_refcnt); + this_cpu_inc(*this->pcpu_refcnt); } int cffrml_refcnt_read(struct cflayer *layr) diff --git a/net/caif/cfmuxl.c b/net/caif/cfmuxl.c index b36f24a4c8e7..94b08612a4d8 100644 --- a/net/caif/cfmuxl.c +++ b/net/caif/cfmuxl.c @@ -248,7 +248,6 @@ static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, { struct cfmuxl *muxl = container_obj(layr); struct cflayer *layer; - int idx; rcu_read_lock(); list_for_each_entry_rcu(layer, &muxl->srvl_list, node) { @@ -257,14 +256,9 @@ static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, if ((ctrl == _CAIF_CTRLCMD_PHYIF_DOWN_IND || ctrl == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND) && - layer->id != 0) { - - idx = layer->id % UP_CACHE_SIZE; - spin_lock_bh(&muxl->receive_lock); - RCU_INIT_POINTER(muxl->up_cache[idx], NULL); - list_del_rcu(&layer->node); - spin_unlock_bh(&muxl->receive_lock); - } + layer->id != 0) + cfmuxl_remove_uplayer(layr, layer->id); + /* NOTE: ctrlcmd is not allowed to block */ layer->ctrlcmd(layer, ctrl, phyid); } diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 97f70e50ad3b..761ad9d6cc3b 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -85,8 +85,6 @@ int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid) } else { pr_info("client%lld fsid %pU\n", ceph_client_id(client), fsid); memcpy(&client->fsid, fsid, sizeof(*fsid)); - ceph_debugfs_client_init(client); - client->have_fsid = true; } return 0; } diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index 3a94eae7abe9..b79747c4b645 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -510,10 +510,15 @@ int crush_do_rule(struct crush_map *map, switch (rule->steps[step].op) { case CRUSH_RULE_TAKE: w[0] = rule->steps[step].arg1; - if (force_pos >= 0) { - BUG_ON(force_context[force_pos] != w[0]); + + /* find position in force_context/hierarchy */ + while (force_pos >= 0 && + force_context[force_pos] != w[0]) force_pos--; - } + /* and move past it */ + if (force_pos >= 0) + force_pos--; + wsize = 1; break; diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 85f3bc0a7062..b780cb7947dd 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -15,10 +15,9 @@ int ceph_crypto_key_clone(struct ceph_crypto_key *dst, const struct ceph_crypto_key *src) { memcpy(dst, src, sizeof(struct ceph_crypto_key)); - dst->key = kmalloc(src->len, GFP_NOFS); + dst->key = kmemdup(src->key, src->len, GFP_NOFS); if (!dst->key) return -ENOMEM; - memcpy(dst->key, src->key, src->len); return 0; } diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 0b62deae42bd..1845cde26227 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -8,8 +8,8 @@ #include <linux/ceph/mon_client.h> #include <linux/ceph/libceph.h> +#include <linux/ceph/debugfs.h> #include <linux/ceph/decode.h> - #include <linux/ceph/auth.h> /* @@ -340,8 +340,19 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc, client->monc.monmap = monmap; kfree(old); + if (!client->have_fsid) { + client->have_fsid = true; + mutex_unlock(&monc->mutex); + /* + * do debugfs initialization without mutex to avoid + * creating a locking dependency + */ + ceph_debugfs_client_init(client); + goto out_unlocked; + } out: mutex_unlock(&monc->mutex); +out_unlocked: wake_up_all(&client->auth_wq); } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index f4f3f58f5234..5e254055c910 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -29,8 +29,8 @@ static void __register_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req); static void __unregister_linger_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req); -static int __send_request(struct ceph_osd_client *osdc, - struct ceph_osd_request *req); +static void __send_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req); static int op_needs_trail(int op) { @@ -1022,8 +1022,8 @@ out: /* * caller should hold map_sem (for read) and request_mutex */ -static int __send_request(struct ceph_osd_client *osdc, - struct ceph_osd_request *req) +static void __send_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) { struct ceph_osd_request_head *reqhead; @@ -1041,7 +1041,6 @@ static int __send_request(struct ceph_osd_client *osdc, ceph_msg_get(req->r_request); /* send consumes a ref */ ceph_con_send(&req->r_osd->o_con, req->r_request); req->r_sent = req->r_osd->o_incarnation; - return 0; } /* @@ -1726,17 +1725,9 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc, dout("send_request %p no up osds in pg\n", req); ceph_monc_request_next_osdmap(&osdc->client->monc); } else { - rc = __send_request(osdc, req); - if (rc) { - if (nofail) { - dout("osdc_start_request failed send, " - " will retry %lld\n", req->r_tid); - rc = 0; - } else { - __unregister_request(osdc, req); - } - } + __send_request(osdc, req); } + rc = 0; } out_unlock: diff --git a/net/core/dev.c b/net/core/dev.c index f494675471a9..6ca32f6b3105 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1887,6 +1887,23 @@ void skb_set_dev(struct sk_buff *skb, struct net_device *dev) EXPORT_SYMBOL(skb_set_dev); #endif /* CONFIG_NET_NS */ +static void skb_warn_bad_offload(const struct sk_buff *skb) +{ + static const netdev_features_t null_features = 0; + struct net_device *dev = skb->dev; + const char *driver = ""; + + if (dev && dev->dev.parent) + driver = dev_driver_string(dev->dev.parent); + + WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d gso_size=%d " + "gso_type=%d ip_summed=%d\n", + driver, dev ? &dev->features : &null_features, + skb->sk ? &skb->sk->sk_route_caps : &null_features, + skb->len, skb->data_len, skb_shinfo(skb)->gso_size, + skb_shinfo(skb)->gso_type, skb->ip_summed); +} + /* * Invalidate hardware checksum when packet is to be mangled, and * complete checksum manually on outgoing path. @@ -1900,8 +1917,8 @@ int skb_checksum_help(struct sk_buff *skb) goto out_set_summed; if (unlikely(skb_shinfo(skb)->gso_size)) { - /* Let GSO fix up the checksum. */ - goto out_set_summed; + skb_warn_bad_offload(skb); + return -EINVAL; } offset = skb_checksum_start_offset(skb); @@ -1961,16 +1978,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, __skb_pull(skb, skb->mac_len); if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { - struct net_device *dev = skb->dev; - struct ethtool_drvinfo info = {}; - - if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo) - dev->ethtool_ops->get_drvinfo(dev, &info); - - WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d ip_summed=%d\n", - info.driver, dev ? &dev->features : NULL, - skb->sk ? &skb->sk->sk_route_caps : NULL, - skb->len, skb->data_len, skb->ip_summed); + skb_warn_bad_offload(skb); if (skb_header_cloned(skb) && (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) @@ -3492,14 +3500,20 @@ static inline gro_result_t __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff *p; + unsigned int maclen = skb->dev->hard_header_len; for (p = napi->gro_list; p; p = p->next) { unsigned long diffs; diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; - diffs |= compare_ether_header(skb_mac_header(p), - skb_gro_mac_header(skb)); + if (maclen == ETH_HLEN) + diffs |= compare_ether_header(skb_mac_header(p), + skb_gro_mac_header(skb)); + else if (!diffs) + diffs = memcmp(skb_mac_header(p), + skb_gro_mac_header(skb), + maclen); NAPI_GRO_CB(p)->same_flow = !diffs; NAPI_GRO_CB(p)->flush = 0; } diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index febba516db62..29c07fef9228 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -427,7 +427,7 @@ EXPORT_SYMBOL(dev_uc_del); * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be - * locked by netif_tx_lock_bh. + * locked by netif_addr_lock_bh. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. @@ -439,11 +439,11 @@ int dev_uc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_bh(to); + netif_addr_lock_nested(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); - netif_addr_unlock_bh(to); + netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_uc_sync); @@ -463,7 +463,7 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from) return; netif_addr_lock_bh(from); - netif_addr_lock(to); + netif_addr_lock_nested(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); @@ -590,7 +590,7 @@ EXPORT_SYMBOL(dev_mc_del_global); * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be - * locked by netif_tx_lock_bh. + * locked by netif_addr_lock_bh. * * This function is intended to be called from the ndo_set_rx_mode * function of layered software devices. @@ -602,11 +602,11 @@ int dev_mc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_bh(to); + netif_addr_lock_nested(to); err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); - netif_addr_unlock_bh(to); + netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_mc_sync); @@ -626,7 +626,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from) return; netif_addr_lock_bh(from); - netif_addr_lock(to); + netif_addr_lock_nested(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 921aa2b4b415..3f79db1b612a 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1190,6 +1190,8 @@ static noinline_for_stack int ethtool_flash_device(struct net_device *dev, if (!dev->ethtool_ops->flash_device) return -EOPNOTSUPP; + efl.data[ETHTOOL_FLASH_MAX_FILENAME - 1] = 0; + return dev->ethtool_ops->flash_device(dev, &efl); } @@ -1311,6 +1313,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GRXCSUM: case ETHTOOL_GTXCSUM: case ETHTOOL_GSG: + case ETHTOOL_GSSET_INFO: case ETHTOOL_GSTRINGS: case ETHTOOL_GTSO: case ETHTOOL_GPERMADDR: diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 0985b9b14b80..a225089df5b6 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1,4 +1,5 @@ #include <linux/skbuff.h> +#include <linux/export.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/if_vlan.h> diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e287346e0934..2a83914b0277 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -826,6 +826,8 @@ next_elt: write_unlock_bh(&tbl->lock); cond_resched(); write_lock_bh(&tbl->lock); + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); } /* Cycle through all hash buckets every base_reachable_time/2 ticks. * ARP entry timeouts range from 1/2 base_reachable_time to 3/2 diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index abf4393a77b3..a1727cda03d7 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -929,7 +929,7 @@ static ssize_t bql_show_inflight(struct netdev_queue *queue, } static struct netdev_queue_attribute bql_inflight_attribute = - __ATTR(inflight, S_IRUGO | S_IWUSR, bql_show_inflight, NULL); + __ATTR(inflight, S_IRUGO, bql_show_inflight, NULL); #define BQL_ATTR(NAME, FIELD) \ static ssize_t bql_show_ ## NAME(struct netdev_queue *queue, \ @@ -1177,9 +1177,9 @@ static ssize_t store_xps_map(struct netdev_queue *queue, nonempty = 1; } - if (nonempty) - RCU_INIT_POINTER(dev->xps_maps, new_dev_maps); - else { + if (nonempty) { + rcu_assign_pointer(dev->xps_maps, new_dev_maps); + } else { kfree(new_dev_maps); RCU_INIT_POINTER(dev->xps_maps, NULL); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index aefcd7acbffa..0e950fda9a0a 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -30,6 +30,20 @@ EXPORT_SYMBOL(init_net); #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ +static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; + +static struct net_generic *net_alloc_generic(void) +{ + struct net_generic *ng; + size_t generic_size = offsetof(struct net_generic, ptr[max_gen_ptrs]); + + ng = kzalloc(generic_size, GFP_KERNEL); + if (ng) + ng->len = max_gen_ptrs; + + return ng; +} + static int net_assign_generic(struct net *net, int id, void *data) { struct net_generic *ng, *old_ng; @@ -43,8 +57,7 @@ static int net_assign_generic(struct net *net, int id, void *data) if (old_ng->len >= id) goto assign; - ng = kzalloc(sizeof(struct net_generic) + - id * sizeof(void *), GFP_KERNEL); + ng = net_alloc_generic(); if (ng == NULL) return -ENOMEM; @@ -59,7 +72,6 @@ static int net_assign_generic(struct net *net, int id, void *data) * the old copy for kfree after a grace period. */ - ng->len = id; memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*)); rcu_assign_pointer(net->gen, ng); @@ -161,18 +173,6 @@ out_undo: goto out; } -static struct net_generic *net_alloc_generic(void) -{ - struct net_generic *ng; - size_t generic_size = sizeof(struct net_generic) + - INITIAL_NET_GEN_PTRS * sizeof(void *); - - ng = kzalloc(generic_size, GFP_KERNEL); - if (ng) - ng->len = INITIAL_NET_GEN_PTRS; - - return ng; -} #ifdef CONFIG_NET_NS static struct kmem_cache *net_cachep; @@ -483,6 +483,7 @@ again: } return error; } + max_gen_ptrs = max_t(unsigned int, max_gen_ptrs, *ops->id); } error = __register_pernet_operations(list, ops); if (error) { diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 0d38808a2305..ddefc513b44a 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -194,7 +194,7 @@ static void netpoll_poll_dev(struct net_device *dev) poll_napi(dev); - if (dev->priv_flags & IFF_SLAVE) { + if (dev->flags & IFF_SLAVE) { if (dev->npinfo) { struct net_device *bond_dev = dev->master; struct sk_buff *skb; @@ -765,7 +765,7 @@ int __netpoll_setup(struct netpoll *np) } /* last thing to do is link it to the net device structure */ - RCU_INIT_POINTER(ndev->npinfo, npinfo); + rcu_assign_pointer(ndev->npinfo, npinfo); return 0; diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 3a9fd4826b75..4dacc44637ef 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -58,11 +58,12 @@ static int get_prioidx(u32 *prio) spin_lock_irqsave(&prioidx_map_lock, flags); prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ); + if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) { + spin_unlock_irqrestore(&prioidx_map_lock, flags); + return -ENOSPC; + } set_bit(prioidx, prioidx_map); spin_unlock_irqrestore(&prioidx_map_lock, flags); - if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) - return -ENOSPC; - atomic_set(&max_prioidx, prioidx); *prio = prioidx; return 0; @@ -107,7 +108,7 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len) static void update_netdev_tables(void) { struct net_device *dev; - u32 max_len = atomic_read(&max_prioidx); + u32 max_len = atomic_read(&max_prioidx) + 1; struct netprio_map *map; rtnl_lock(); @@ -270,7 +271,6 @@ static int netprio_device_event(struct notifier_block *unused, { struct net_device *dev = ptr; struct netprio_map *old; - u32 max_len = atomic_read(&max_prioidx); /* * Note this is called with rtnl_lock held so we have update side @@ -278,11 +278,6 @@ static int netprio_device_event(struct notifier_block *unused, */ switch (event) { - - case NETDEV_REGISTER: - if (max_len) - extend_netdev_table(dev, max_len); - break; case NETDEV_UNREGISTER: old = rtnl_dereference(dev->priomap); RCU_INIT_POINTER(dev->priomap, NULL); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 449fe0f068f8..4d8ce93cd503 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -767,8 +767,8 @@ done: return i; } -static unsigned long num_arg(const char __user * user_buffer, - unsigned long maxlen, unsigned long *num) +static long num_arg(const char __user *user_buffer, unsigned long maxlen, + unsigned long *num) { int i; *num = 0; @@ -2024,13 +2024,13 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) pr_warning("WARNING: Requested queue_map_min (zero-based) (%d) exceeds valid range [0 - %d] for (%d) queues on %s, resetting\n", pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq, pkt_dev->odevname); - pkt_dev->queue_map_min = ntxq - 1; + pkt_dev->queue_map_min = (ntxq ?: 1) - 1; } if (pkt_dev->queue_map_max >= ntxq) { pr_warning("WARNING: Requested queue_map_max (zero-based) (%d) exceeds valid range [0 - %d] for (%d) queues on %s, resetting\n", pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq, pkt_dev->odevname); - pkt_dev->queue_map_max = ntxq - 1; + pkt_dev->queue_map_max = (ntxq ?: 1) - 1; } /* Default to the interface's mac if not explicitly set. */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index dbf2ddafd52d..f965dce6f20f 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -60,7 +60,6 @@ struct rtnl_link { }; static DEFINE_MUTEX(rtnl_mutex); -static u16 min_ifinfo_dump_size; void rtnl_lock(void) { @@ -724,10 +723,11 @@ static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b) } /* All VF info */ -static inline int rtnl_vfinfo_size(const struct net_device *dev) +static inline int rtnl_vfinfo_size(const struct net_device *dev, + u32 ext_filter_mask) { - if (dev->dev.parent && dev_is_pci(dev->dev.parent)) { - + if (dev->dev.parent && dev_is_pci(dev->dev.parent) && + (ext_filter_mask & RTEXT_FILTER_VF)) { int num_vfs = dev_num_vf(dev->dev.parent); size_t size = nla_total_size(sizeof(struct nlattr)); size += nla_total_size(num_vfs * sizeof(struct nlattr)); @@ -766,7 +766,8 @@ static size_t rtnl_port_size(const struct net_device *dev) return port_self_size; } -static noinline size_t if_nlmsg_size(const struct net_device *dev) +static noinline size_t if_nlmsg_size(const struct net_device *dev, + u32 ext_filter_mask) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ @@ -784,8 +785,9 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev) + nla_total_size(4) /* IFLA_MASTER */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ - + nla_total_size(4) /* IFLA_NUM_VF */ - + rtnl_vfinfo_size(dev) /* IFLA_VFINFO_LIST */ + + nla_total_size(ext_filter_mask + & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */ + + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev); /* IFLA_AF_SPEC */ @@ -868,7 +870,7 @@ static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, - unsigned int flags) + unsigned int flags, u32 ext_filter_mask) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -941,10 +943,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; copy_rtnl_link_stats64(nla_data(attr), stats); - if (dev->dev.parent) + if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF)) NLA_PUT_U32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)); - if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) { + if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent + && (ext_filter_mask & RTEXT_FILTER_VF)) { int i; struct nlattr *vfinfo, *vf; @@ -1048,6 +1051,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) struct net_device *dev; struct hlist_head *head; struct hlist_node *node; + struct nlattr *tb[IFLA_MAX+1]; + u32 ext_filter_mask = 0; s_h = cb->args[0]; s_idx = cb->args[1]; @@ -1055,6 +1060,13 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); cb->seq = net->dev_base_seq; + if (nlmsg_parse(cb->nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, + ifla_policy) >= 0) { + + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + } + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; @@ -1064,7 +1076,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI) <= 0) + NLM_F_MULTI, + ext_filter_mask) <= 0) goto out; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -1100,6 +1113,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_VF_PORTS] = { .type = NLA_NESTED }, [IFLA_PORT_SELF] = { .type = NLA_NESTED }, [IFLA_AF_SPEC] = { .type = NLA_NESTED }, + [IFLA_EXT_MASK] = { .type = NLA_U32 }, }; EXPORT_SYMBOL(ifla_policy); @@ -1509,6 +1523,7 @@ errout: if (send_addr_notify) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return err; } @@ -1839,6 +1854,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) struct net_device *dev = NULL; struct sk_buff *nskb; int err; + u32 ext_filter_mask = 0; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); if (err < 0) @@ -1847,6 +1863,9 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) dev = __dev_get_by_index(net, ifm->ifi_index); @@ -1858,12 +1877,12 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (dev == NULL) return -ENODEV; - nskb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL); + nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL); if (nskb == NULL) return -ENOBUFS; err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).pid, - nlh->nlmsg_seq, 0, 0); + nlh->nlmsg_seq, 0, 0, ext_filter_mask); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); @@ -1874,8 +1893,32 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) return err; } -static u16 rtnl_calcit(struct sk_buff *skb) +static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) { + struct net *net = sock_net(skb->sk); + struct net_device *dev; + struct nlattr *tb[IFLA_MAX+1]; + u32 ext_filter_mask = 0; + u16 min_ifinfo_dump_size = 0; + + if (nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, + ifla_policy) >= 0) { + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + } + + if (!ext_filter_mask) + return NLMSG_GOODSIZE; + /* + * traverse the list of net devices and compute the minimum + * buffer size based upon the filter mask. + */ + list_for_each_entry(dev, &net->dev_base_head, dev_list) { + min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size, + if_nlmsg_size(dev, + ext_filter_mask)); + } + return min_ifinfo_dump_size; } @@ -1910,13 +1953,11 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) int err = -ENOBUFS; size_t if_info_size; - skb = nlmsg_new((if_info_size = if_nlmsg_size(dev)), GFP_KERNEL); + skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), GFP_KERNEL); if (skb == NULL) goto errout; - min_ifinfo_dump_size = max_t(u16, if_info_size, min_ifinfo_dump_size); - - err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0); + err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -1960,7 +2001,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) sz_idx = type>>2; kind = type&3; - if (kind != 2 && security_netlink_recv(skb, CAP_NET_ADMIN)) + if (kind != 2 && !capable(CAP_NET_ADMIN)) return -EPERM; if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { @@ -1974,7 +2015,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return -EOPNOTSUPP; calcit = rtnl_get_calcit(family, type); if (calcit) - min_dump_alloc = calcit(skb); + min_dump_alloc = calcit(skb, nlh); __rtnl_unlock(); rtnl = net->rtnl; diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 6fd44606fdd1..99b2596531bb 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -46,7 +46,7 @@ __u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) - secret[i] = net_secret[i] + daddr[i]; + secret[i] = net_secret[i] + (__force u32)daddr[i]; secret[4] = net_secret[4] + (((__force u16)sport << 16) + (__force u16)dport); for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) diff --git a/net/core/sock.c b/net/core/sock.c index 002939cfc069..02f8dfe320b7 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -112,6 +112,7 @@ #include <linux/highmem.h> #include <linux/user_namespace.h> #include <linux/jump_label.h> +#include <linux/memcontrol.h> #include <asm/uaccess.h> #include <asm/system.h> @@ -1170,13 +1171,10 @@ EXPORT_SYMBOL(sock_update_classid); void sock_update_netprioidx(struct sock *sk) { - struct cgroup_netprio_state *state; if (in_interrupt()) return; - rcu_read_lock(); - state = task_netprio_state(current); - sk->sk_cgrp_prioidx = state ? state->prioidx : 0; - rcu_read_unlock(); + + sk->sk_cgrp_prioidx = task_netprioidx(current); } EXPORT_SYMBOL_GPL(sock_update_netprioidx); #endif @@ -1272,6 +1270,12 @@ void sk_release_kernel(struct sock *sk) } EXPORT_SYMBOL(sk_release_kernel); +static void sk_update_clone(const struct sock *sk, struct sock *newsk) +{ + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + sock_update_memcg(newsk); +} + /** * sk_clone_lock - clone a socket, and lock its clone * @sk: the socket to clone @@ -1362,6 +1366,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sk_set_socket(newsk, NULL); newsk->sk_wq = NULL; + sk_update_clone(sk, newsk); + if (newsk->sk_prot->sockets_allocated) sk_sockets_allocated_inc(newsk); @@ -1818,7 +1824,7 @@ suppress_allocation: /* Alas. Undo changes. */ sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM; - sk_memory_allocated_sub(sk, amt, parent_status); + sk_memory_allocated_sub(sk, amt); return 0; } @@ -1831,7 +1837,7 @@ EXPORT_SYMBOL(__sk_mem_schedule); void __sk_mem_reclaim(struct sock *sk) { sk_memory_allocated_sub(sk, - sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT, 0); + sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT); sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1; if (sk_under_memory_pressure(sk) && diff --git a/net/dccp/diag.c b/net/dccp/diag.c index 8f1625753377..028fc43aacbd 100644 --- a/net/dccp/diag.c +++ b/net/dccp/diag.c @@ -49,13 +49,13 @@ static void dccp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, } static void dccp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req *r, struct nlattr *bc) + struct inet_diag_req_v2 *r, struct nlattr *bc) { inet_diag_dump_icsk(&dccp_hashinfo, skb, cb, r, bc); } static int dccp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, - struct inet_diag_req *req) + struct inet_diag_req_v2 *req) { return inet_diag_dump_one_icsk(&dccp_hashinfo, in_skb, nlh, req); } diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 2ab16e12520c..74d321a60e7b 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_INIT_POINTER(dn_db->ifa_list, ifa); + rcu_assign_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_INIT_POINTER(dev->dn_ptr, dn_db); + rcu_assign_pointer(dev->dn_ptr, dn_db); dn_db->dev = dev; init_timer(&dn_db->timer); diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index 69975e0bcdea..1531135130db 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -108,7 +108,7 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb) if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len) return; - if (security_netlink_recv(skb, CAP_NET_ADMIN)) + if (!capable(CAP_NET_ADMIN)) RCV_SKB_FAIL(-EPERM); /* Eventually we might send routing messages too */ diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 1a8f93bd2d4f..d183262943d9 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -163,8 +163,6 @@ config IP_PNP_RARP operating on your network. Read <file:Documentation/filesystems/nfs/nfsroot.txt> for details. -# not yet ready.. -# bool ' IP: ARP support' CONFIG_IP_PNP_ARP config NET_IPIP tristate "IP: tunneling" select INET_TUNNEL @@ -410,8 +408,12 @@ config INET_TCP_DIAG def_tristate INET_DIAG config INET_UDP_DIAG - depends on INET_DIAG - def_tristate INET_DIAG && IPV6 + tristate "UDP: socket monitoring interface" + depends on INET_DIAG && (IPV6 || IPV6=n) + default n + ---help--- + Support for UDP socket monitoring interface used by the ss tool. + If unsure, say Y. menuconfig TCP_CONG_ADVANCED bool "TCP: advanced congestion control" diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 59402be133f0..63e49890ad31 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -863,7 +863,8 @@ static int arp_process(struct sk_buff *skb) if (addr_type == RTN_UNICAST && (arp_fwd_proxy(in_dev, dev, rt) || arp_fwd_pvlan(in_dev, dev, rt, sip, tip) || - pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) { + (rt->dst.dev != dev && + pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) neigh_release(n); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 65f01dc47565..e41c40f48cfe 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_INIT_POINTER(dev->ip_ptr, in_dev); + rcu_assign_pointer(dev->ip_ptr, in_dev); out: return in_dev; out_kfree: diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index d04b13ae18fe..2b555a5521e0 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -205,7 +205,7 @@ static inline struct tnode *node_parent_rcu(const struct rt_trie_node *node) return (struct tnode *)(parent & ~NODE_TYPE_MASK); } -/* Same as RCU_INIT_POINTER +/* Same as rcu_assign_pointer * but that macro() assumes that value is a pointer. */ static inline void node_set_parent(struct rt_trie_node *node, struct tnode *ptr) @@ -529,7 +529,7 @@ static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node * if (n) node_set_parent(n, tn); - RCU_INIT_POINTER(tn->child[i], n); + rcu_assign_pointer(tn->child[i], n); } #define MAX_WORK 10 @@ -1015,7 +1015,7 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) tp = node_parent((struct rt_trie_node *) tn); if (!tp) - RCU_INIT_POINTER(t->trie, (struct rt_trie_node *)tn); + rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tnode_free_flush(); if (!tp) @@ -1027,7 +1027,7 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) if (IS_TNODE(tn)) tn = (struct tnode *)resize(t, (struct tnode *)tn); - RCU_INIT_POINTER(t->trie, (struct rt_trie_node *)tn); + rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tnode_free_flush(); } @@ -1164,7 +1164,7 @@ 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_INIT_POINTER(t->trie, (struct rt_trie_node *)tn); + rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tp = tn; } } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index fa057d105bef..450e5d21ed2a 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -880,6 +880,8 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, * to be intended in a v3 query. */ max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); + if (!max_delay) + max_delay = 1; /* can't mod w/ 0 */ } else { /* v3 */ if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) return; @@ -1247,7 +1249,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) im->next_rcu = in_dev->mc_list; in_dev->mc_count++; - RCU_INIT_POINTER(in_dev->mc_list, im); + rcu_assign_pointer(in_dev->mc_list, im); #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im->multiaddr); @@ -1819,7 +1821,7 @@ 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_INIT_POINTER(inet->mc_list, iml); + rcu_assign_pointer(inet->mc_list, iml); ip_mc_inc_group(in_dev, addr); err = 0; done: @@ -2006,7 +2008,7 @@ 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_INIT_POINTER(pmc->sflist, newpsl); + rcu_assign_pointer(pmc->sflist, newpsl); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ @@ -2109,7 +2111,7 @@ 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_INIT_POINTER(pmc->sflist, newpsl); + rcu_assign_pointer(pmc->sflist, newpsl); pmc->sfmode = msf->imsf_fmode; err = 0; done: diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 2e4e24476c4c..19d66cefd7d3 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -123,11 +123,14 @@ again: smallest_size = tb->num_owners; smallest_rover = rover; if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) { - spin_unlock(&head->lock); snum = smallest_rover; - goto have_snum; + goto tb_found; } } + if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) { + snum = rover; + goto tb_found; + } goto next; } break; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 2240a8e8c44d..fcf281819cd4 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -71,7 +71,7 @@ static inline void inet_diag_unlock_handler( } int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, - struct sk_buff *skb, struct inet_diag_req *req, + struct sk_buff *skb, struct inet_diag_req_v2 *req, u32 pid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { @@ -193,7 +193,7 @@ nlmsg_failure: EXPORT_SYMBOL_GPL(inet_sk_diag_fill); static int inet_csk_diag_fill(struct sock *sk, - struct sk_buff *skb, struct inet_diag_req *req, + struct sk_buff *skb, struct inet_diag_req_v2 *req, u32 pid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { @@ -202,7 +202,7 @@ static int inet_csk_diag_fill(struct sock *sk, } static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, - struct sk_buff *skb, struct inet_diag_req *req, + struct sk_buff *skb, struct inet_diag_req_v2 *req, u32 pid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { @@ -253,7 +253,7 @@ nlmsg_failure: } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, - struct inet_diag_req *r, u32 pid, u32 seq, u16 nlmsg_flags, + struct inet_diag_req_v2 *r, u32 pid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { if (sk->sk_state == TCP_TIME_WAIT) @@ -264,7 +264,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, } int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb, - const struct nlmsghdr *nlh, struct inet_diag_req *req) + const struct nlmsghdr *nlh, struct inet_diag_req_v2 *req) { int err; struct sock *sk; @@ -333,7 +333,7 @@ EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk); static int inet_diag_get_exact(struct sk_buff *in_skb, const struct nlmsghdr *nlh, - struct inet_diag_req *req) + struct inet_diag_req_v2 *req) { const struct inet_diag_handler *handler; int err; @@ -540,7 +540,7 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) static int inet_csk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req *r, + struct inet_diag_req_v2 *r, const struct nlattr *bc) { if (!inet_diag_bc_sk(bc, sk)) @@ -554,7 +554,7 @@ static int inet_csk_diag_dump(struct sock *sk, static int inet_twsk_diag_dump(struct inet_timewait_sock *tw, struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req *r, + struct inet_diag_req_v2 *r, const struct nlattr *bc) { if (bc != NULL) { @@ -639,7 +639,7 @@ nlmsg_failure: static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, struct netlink_callback *cb, - struct inet_diag_req *r, + struct inet_diag_req_v2 *r, const struct nlattr *bc) { struct inet_diag_entry entry; @@ -721,7 +721,7 @@ out: } void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, - struct netlink_callback *cb, struct inet_diag_req *r, struct nlattr *bc) + struct netlink_callback *cb, struct inet_diag_req_v2 *r, struct nlattr *bc) { int i, num; int s_i, s_num; @@ -872,7 +872,7 @@ out: EXPORT_SYMBOL_GPL(inet_diag_dump_icsk); static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req *r, struct nlattr *bc) + struct inet_diag_req_v2 *r, struct nlattr *bc) { const struct inet_diag_handler *handler; @@ -887,12 +887,12 @@ static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *bc = NULL; - int hdrlen = sizeof(struct inet_diag_req); + int hdrlen = sizeof(struct inet_diag_req_v2); if (nlmsg_attrlen(cb->nlh, hdrlen)) bc = nlmsg_find_attr(cb->nlh, hdrlen, INET_DIAG_REQ_BYTECODE); - return __inet_diag_dump(skb, cb, (struct inet_diag_req *)NLMSG_DATA(cb->nlh), bc); + return __inet_diag_dump(skb, cb, (struct inet_diag_req_v2 *)NLMSG_DATA(cb->nlh), bc); } static inline int inet_diag_type2proto(int type) @@ -909,10 +909,10 @@ static inline int inet_diag_type2proto(int type) static int inet_diag_dump_compat(struct sk_buff *skb, struct netlink_callback *cb) { - struct inet_diag_req_compat *rc = NLMSG_DATA(cb->nlh); - struct inet_diag_req req; + struct inet_diag_req *rc = NLMSG_DATA(cb->nlh); + struct inet_diag_req_v2 req; struct nlattr *bc = NULL; - int hdrlen = sizeof(struct inet_diag_req_compat); + int hdrlen = sizeof(struct inet_diag_req); req.sdiag_family = AF_UNSPEC; /* compatibility */ req.sdiag_protocol = inet_diag_type2proto(cb->nlh->nlmsg_type); @@ -929,8 +929,8 @@ static int inet_diag_dump_compat(struct sk_buff *skb, struct netlink_callback *c static int inet_diag_get_exact_compat(struct sk_buff *in_skb, const struct nlmsghdr *nlh) { - struct inet_diag_req_compat *rc = NLMSG_DATA(nlh); - struct inet_diag_req req; + struct inet_diag_req *rc = NLMSG_DATA(nlh); + struct inet_diag_req_v2 req; req.sdiag_family = rc->idiag_family; req.sdiag_protocol = inet_diag_type2proto(nlh->nlmsg_type); @@ -943,7 +943,7 @@ static int inet_diag_get_exact_compat(struct sk_buff *in_skb, static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) { - int hdrlen = sizeof(struct inet_diag_req_compat); + int hdrlen = sizeof(struct inet_diag_req); if (nlh->nlmsg_type >= INET_DIAG_GETSOCK_MAX || nlmsg_len(nlh) < hdrlen) @@ -970,7 +970,7 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) { - int hdrlen = sizeof(struct inet_diag_req); + int hdrlen = sizeof(struct inet_diag_req_v2); if (nlmsg_len(h) < hdrlen) return -EINVAL; @@ -990,7 +990,7 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) inet_diag_dump, NULL, 0); } - return inet_diag_get_exact(skb, h, (struct inet_diag_req *)NLMSG_DATA(h)); + return inet_diag_get_exact(skb, h, (struct inet_diag_req_v2 *)NLMSG_DATA(h)); } static struct sock_diag_handler inet_diag_handler = { diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 86f13c67ea85..d4d61b694fab 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -17,6 +17,7 @@ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/net.h> +#include <linux/workqueue.h> #include <net/ip.h> #include <net/inetpeer.h> #include <net/secure_seq.h> @@ -66,6 +67,11 @@ static struct kmem_cache *peer_cachep __read_mostly; +static LIST_HEAD(gc_list); +static const int gc_delay = 60 * HZ; +static struct delayed_work gc_work; +static DEFINE_SPINLOCK(gc_lock); + #define node_height(x) x->avl_height #define peer_avl_empty ((struct inet_peer *)&peer_fake_node) @@ -102,6 +108,50 @@ int inet_peer_threshold __read_mostly = 65536 + 128; /* start to throw entries m int inet_peer_minttl __read_mostly = 120 * HZ; /* TTL under high load: 120 sec */ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min */ +static void inetpeer_gc_worker(struct work_struct *work) +{ + struct inet_peer *p, *n; + LIST_HEAD(list); + + spin_lock_bh(&gc_lock); + list_replace_init(&gc_list, &list); + spin_unlock_bh(&gc_lock); + + if (list_empty(&list)) + return; + + list_for_each_entry_safe(p, n, &list, gc_list) { + + if(need_resched()) + cond_resched(); + + if (p->avl_left != peer_avl_empty) { + list_add_tail(&p->avl_left->gc_list, &list); + p->avl_left = peer_avl_empty; + } + + if (p->avl_right != peer_avl_empty) { + list_add_tail(&p->avl_right->gc_list, &list); + p->avl_right = peer_avl_empty; + } + + n = list_entry(p->gc_list.next, struct inet_peer, gc_list); + + if (!atomic_read(&p->refcnt)) { + list_del(&p->gc_list); + kmem_cache_free(peer_cachep, p); + } + } + + if (list_empty(&list)) + return; + + spin_lock_bh(&gc_lock); + list_splice(&list, &gc_list); + spin_unlock_bh(&gc_lock); + + schedule_delayed_work(&gc_work, gc_delay); +} /* Called from ip_output.c:ip_init */ void __init inet_initpeers(void) @@ -126,6 +176,7 @@ void __init inet_initpeers(void) 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); + INIT_DELAYED_WORK_DEFERRABLE(&gc_work, inetpeer_gc_worker); } static int addr_compare(const struct inetpeer_addr *a, @@ -136,7 +187,7 @@ static int addr_compare(const struct inetpeer_addr *a, for (i = 0; i < n; i++) { if (a->addr.a6[i] == b->addr.a6[i]) continue; - if (a->addr.a6[i] < b->addr.a6[i]) + if ((__force u32)a->addr.a6[i] < (__force u32)b->addr.a6[i]) return -1; return 1; } @@ -448,7 +499,7 @@ relookup: p->pmtu_expires = 0; p->pmtu_orig = 0; memset(&p->redirect_learned, 0, sizeof(p->redirect_learned)); - + INIT_LIST_HEAD(&p->gc_list); /* Link the node. */ link_to_pool(p, base); @@ -508,3 +559,30 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout) return rc; } EXPORT_SYMBOL(inet_peer_xrlim_allow); + +void inetpeer_invalidate_tree(int family) +{ + struct inet_peer *old, *new, *prev; + struct inet_peer_base *base = family_to_base(family); + + write_seqlock_bh(&base->lock); + + old = base->root; + if (old == peer_avl_empty_rcu) + goto out; + + new = peer_avl_empty_rcu; + + prev = cmpxchg(&base->root, old, new); + if (prev == old) { + base->total = 0; + spin_lock(&gc_lock); + list_add_tail(&prev->gc_list, &gc_list); + spin_unlock(&gc_lock); + schedule_delayed_work(&gc_work, gc_delay); + } + +out: + write_sequnlock_bh(&base->lock); +} +EXPORT_SYMBOL(inetpeer_invalidate_tree); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index fdaabf2f2b68..1f23a57aa9e6 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -392,7 +392,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) /* Is this the final fragment? */ if ((flags & IP_MF) == 0) { /* If we already have some bits beyond end - * or have different end, the segment is corrrupted. + * or have different end, the segment is corrupted. */ if (end < qp->q.len || ((qp->q.last_in & INET_FRAG_LAST_IN) && end != qp->q.len)) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 2b53a1f7abf6..38673d2860e2 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -65,7 +65,7 @@ it is infeasible task. The most general solutions would be to keep skb->encapsulation counter (sort of local ttl), and silently drop packet when it expires. It is a good - solution, but it supposes maintaing new variable in ALL + solution, but it supposes maintaining new variable in ALL skb, even if no tunneling is used. Current solution: xmit_recursion breaks dead loops. This is a percpu @@ -91,14 +91,14 @@ One of them is to parse packet trying to detect inner encapsulation made by our node. It is difficult or even impossible, especially, - taking into account fragmentation. TO be short, tt is not solution at all. + taking into account fragmentation. TO be short, ttl is not solution at all. Current solution: The solution was UNEXPECTEDLY SIMPLE. We force DF flag on tunnels with preconfigured hop limit, that is ALL. :-) Well, it does not remove the problem completely, but exponential growth of network traffic is changed to linear (branches, that exceed pmtu are pruned) and tunnel mtu - fastly degrades to value <68, where looping stops. + rapidly degrades to value <68, where looping stops. Yes, it is not good if there exists a router in the loop, which does not force DF, even when encapsulating packets have DF set. But it is not our problem! Nobody could accuse us, we made @@ -422,6 +422,10 @@ static struct ip_tunnel *ipgre_tunnel_locate(struct net *net, if (register_netdevice(dev) < 0) goto failed_free; + /* Can use a lockless transmit, unless we generate output sequences */ + if (!(nt->parms.o_flags & GRE_SEQ)) + dev->features |= NETIF_F_LLTX; + dev_hold(dev); ipgre_tunnel_link(ign, nt); return nt; @@ -453,8 +457,8 @@ static void ipgre_err(struct sk_buff *skb, u32 info) GRE tunnels with enabled checksum. Tell them "thank you". Well, I wonder, rfc1812 was written by Cisco employee, - what the hell these idiots break standrads established - by themself??? + what the hell these idiots break standards established + by themselves??? */ const struct iphdr *iph = (const struct iphdr *)skb->data; diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 1e60f7679075..42dd1a90edea 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -573,8 +573,8 @@ void ip_forward_options(struct sk_buff *skb) } if (srrptr + 3 <= srrspace) { opt->is_changed = 1; - ip_rt_get_source(&optptr[srrptr-1], skb, rt); ip_hdr(skb)->daddr = opt->nexthop; + ip_rt_get_source(&optptr[srrptr-1], skb, rt); optptr[2] = srrptr+4; } else if (net_ratelimit()) printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n"); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 7e4ec9fc2cef..6e412a60a91f 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -141,7 +141,7 @@ __be32 ic_servaddr = NONE; /* Boot server IP address */ __be32 root_server_addr = NONE; /* Address of NFS server */ u8 root_server_path[256] = { 0, }; /* Path to mount as root */ -u32 ic_dev_xid; /* Device under configuration */ +__be32 ic_dev_xid; /* Device under configuration */ /* vendor class identifier */ static char vendor_class_identifier[253] __initdata; @@ -859,9 +859,9 @@ static int __init ic_bootp_string(char *dest, char *src, int len, int max) */ static void __init ic_do_bootp_ext(u8 *ext) { - u8 servers; - int i; - u16 mtu; + u8 servers; + int i; + __be16 mtu; #ifdef IPCONFIG_DEBUG u8 *c; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 413ed1ba7a5a..22a199315309 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_INIT_POINTER(*tp, t->next); + rcu_assign_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_INIT_POINTER(t->next, rtnl_dereference(*tp)); - RCU_INIT_POINTER(*tp, t); + rcu_assign_pointer(t->next, rtnl_dereference(*tp)); + rcu_assign_pointer(*tp, t); } static struct ip_tunnel * ipip_tunnel_locate(struct net *net, @@ -792,7 +792,7 @@ static int __net_init ipip_fb_tunnel_init(struct net_device *dev) return -ENOMEM; dev_hold(dev); - RCU_INIT_POINTER(ipn->tunnels_wc[0], tunnel); + rcu_assign_pointer(ipn->tunnels_wc[0], tunnel); return 0; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 8e54490ee3f4..7bc2db6db8d4 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1225,7 +1225,7 @@ 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_INIT_POINTER(mrt->mroute_sk, sk); + rcu_assign_pointer(mrt->mroute_sk, sk); IPV4_DEVCONF_ALL(net, MC_FORWARDING)++; } rtnl_unlock(); diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index a057fe64debd..94d45e1f8882 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -431,7 +431,7 @@ __ipq_rcv_skb(struct sk_buff *skb) if (type <= IPQM_BASE) return; - if (security_netlink_recv(skb, CAP_NET_ADMIN)) + if (!capable(CAP_NET_ADMIN)) RCV_SKB_FAIL(-EPERM); spin_lock_bh(&queue_lock); diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index acdd002bb540..a708933dc230 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -317,7 +317,7 @@ nf_nat_setup_info(struct nf_conn *ct, srchash = hash_by_src(net, nf_ct_zone(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); spin_lock_bh(&nf_nat_lock); - /* nf_conntrack_alter_reply might re-allocate exntension aera */ + /* nf_conntrack_alter_reply might re-allocate extension area */ nat = nfct_nat(ct); nat->ct = ct; hlist_add_head_rcu(&nat->bysource, diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 43d4c3b22369..b072386cee21 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -140,13 +140,14 @@ static void ping_v4_unhash(struct sock *sk) write_lock_bh(&ping_table.lock); hlist_nulls_del(&sk->sk_nulls_node); sock_put(sk); - isk->inet_num = isk->inet_sport = 0; + isk->inet_num = 0; + isk->inet_sport = 0; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); write_unlock_bh(&ping_table.lock); } } -static struct sock *ping_v4_lookup(struct net *net, u32 saddr, u32 daddr, +static struct sock *ping_v4_lookup(struct net *net, __be32 saddr, __be32 daddr, u16 ident, int dif) { struct hlist_nulls_head *hslot = ping_hashslot(&ping_table, net, ident); @@ -154,15 +155,15 @@ static struct sock *ping_v4_lookup(struct net *net, u32 saddr, u32 daddr, struct inet_sock *isk; struct hlist_nulls_node *hnode; - pr_debug("try to find: num = %d, daddr = %ld, dif = %d\n", - (int)ident, (unsigned long)daddr, dif); + pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n", + (int)ident, &daddr, dif); read_lock_bh(&ping_table.lock); ping_portaddr_for_each_entry(sk, hnode, hslot) { isk = inet_sk(sk); - pr_debug("found: %p: num = %d, daddr = %ld, dif = %d\n", sk, - (int)isk->inet_num, (unsigned long)isk->inet_rcv_saddr, + pr_debug("found: %p: num = %d, daddr = %pI4, dif = %d\n", sk, + (int)isk->inet_num, &isk->inet_rcv_saddr, sk->sk_bound_dev_if); pr_debug("iterate\n"); @@ -254,7 +255,7 @@ static int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) sk, addr->sin_addr.s_addr, ntohs(addr->sin_port)); chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr); - if (addr->sin_addr.s_addr == INADDR_ANY) + if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) chk_addr_ret = RTN_LOCAL; if ((sysctl_ip_nonlocal_bind == 0 && @@ -278,9 +279,9 @@ static int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) goto out; } - pr_debug("after bind(): num = %d, daddr = %ld, dif = %d\n", + pr_debug("after bind(): num = %d, daddr = %pI4, dif = %d\n", (int)isk->inet_num, - (unsigned long) isk->inet_rcv_saddr, + &isk->inet_rcv_saddr, (int)sk->sk_bound_dev_if); err = 0; @@ -407,7 +408,7 @@ out: struct pingfakehdr { struct icmphdr icmph; struct iovec *iov; - u32 wcheck; + __wsum wcheck; }; static int ping_getfrag(void *from, char * to, @@ -459,7 +460,7 @@ static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct rtable *rt = NULL; struct ip_options_data opt_copy; int free = 0; - u32 saddr, daddr, faddr; + __be32 saddr, daddr, faddr; u8 tos; int err; @@ -629,6 +630,7 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, pr_debug("ping_recvmsg(sk=%p,sk->num=%u)\n", isk, isk->inet_num); + err = -EOPNOTSUPP; if (flags & MSG_OOB) goto out; @@ -696,8 +698,8 @@ void ping_rcv(struct sk_buff *skb) struct net *net = dev_net(skb->dev); struct iphdr *iph = ip_hdr(skb); struct icmphdr *icmph = icmp_hdr(skb); - u32 saddr = iph->saddr; - u32 daddr = iph->daddr; + __be32 saddr = iph->saddr; + __be32 daddr = iph->daddr; /* We assume the packet has already been checked by icmp_rcv */ diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 3569d8ecaeac..6afc807ee2ad 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -216,7 +216,6 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPPartialUndo", LINUX_MIB_TCPPARTIALUNDO), SNMP_MIB_ITEM("TCPDSACKUndo", LINUX_MIB_TCPDSACKUNDO), SNMP_MIB_ITEM("TCPLossUndo", LINUX_MIB_TCPLOSSUNDO), - SNMP_MIB_ITEM("TCPLoss", LINUX_MIB_TCPLOSS), SNMP_MIB_ITEM("TCPLostRetransmit", LINUX_MIB_TCPLOSTRETRANSMIT), SNMP_MIB_ITEM("TCPRenoFailures", LINUX_MIB_TCPRENOFAILURES), SNMP_MIB_ITEM("TCPSackFailures", LINUX_MIB_TCPSACKFAILURES), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index bcacf54e5418..019774796174 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -132,7 +132,6 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int rt_chain_length_max __read_mostly = 20; -static int redirect_genid; static struct delayed_work expires_work; static unsigned long expires_ljiffies; @@ -937,7 +936,7 @@ static void rt_cache_invalidate(struct net *net) get_random_bytes(&shuffle, sizeof(shuffle)); atomic_add(shuffle + 1U, &net->ipv4.rt_genid); - redirect_genid++; + inetpeer_invalidate_tree(AF_INET); } /* @@ -1485,10 +1484,8 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, peer = rt->peer; if (peer) { - if (peer->redirect_learned.a4 != new_gw || - peer->redirect_genid != redirect_genid) { + if (peer->redirect_learned.a4 != new_gw) { peer->redirect_learned.a4 = new_gw; - peer->redirect_genid = redirect_genid; atomic_inc(&__rt_peer_genid); } check_peer_redir(&rt->dst, peer); @@ -1793,8 +1790,6 @@ static void ipv4_validate_peer(struct rtable *rt) if (peer) { check_peer_pmtu(&rt->dst, peer); - if (peer->redirect_genid != redirect_genid) - peer->redirect_learned.a4 = 0; if (peer->redirect_learned.a4 && peer->redirect_learned.a4 != rt->rt_gateway) check_peer_redir(&rt->dst, peer); @@ -1958,8 +1953,7 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4, dst_init_metrics(&rt->dst, peer->metrics, false); check_peer_pmtu(&rt->dst, peer); - if (peer->redirect_genid != redirect_genid) - peer->redirect_learned.a4 = 0; + if (peer->redirect_learned.a4 && peer->redirect_learned.a4 != rt->rt_gateway) { rt->rt_gateway = peer->redirect_learned.a4; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 51fdbb490437..eab2a7fb15d1 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -278,6 +278,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, struct rtable *rt; __u8 rcv_wscale; bool ecn_ok = false; + struct flowi4 fl4; if (!sysctl_tcp_syncookies || !th->ack || th->rst) goto out; @@ -346,20 +347,16 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, * hasn't changed since we received the original syn, but I see * no easy way to do this. */ - { - struct flowi4 fl4; - - flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk), - RT_SCOPE_UNIVERSE, IPPROTO_TCP, - inet_sk_flowi_flags(sk), - (opt && opt->srr) ? opt->faddr : ireq->rmt_addr, - ireq->loc_addr, th->source, th->dest); - security_req_classify_flow(req, flowi4_to_flowi(&fl4)); - rt = ip_route_output_key(sock_net(sk), &fl4); - if (IS_ERR(rt)) { - reqsk_free(req); - goto out; - } + flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk), + RT_SCOPE_UNIVERSE, IPPROTO_TCP, + inet_sk_flowi_flags(sk), + (opt && opt->srr) ? opt->faddr : ireq->rmt_addr, + ireq->loc_addr, th->source, th->dest); + security_req_classify_flow(req, flowi4_to_flowi(&fl4)); + rt = ip_route_output_key(sock_net(sk), &fl4); + if (IS_ERR(rt)) { + reqsk_free(req); + goto out; } /* Try to redo what tcp_v4_send_synack did. */ @@ -373,5 +370,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->rcv_wscale = rcv_wscale; ret = get_cookie_sock(sk, skb, req, &rt->dst); + /* ip_queue_xmit() depends on our flow being setup + * Normal sockets get it right from inet_csk_route_child_sock() + */ + if (ret) + inet_sk(ret)->cork.fl.u.ip4 = fl4; out: return ret; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 4aa7e9dc0cbb..7a7724da9bff 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -778,7 +778,6 @@ EXPORT_SYMBOL_GPL(net_ipv4_ctl_path); static __net_init int ipv4_sysctl_init_net(struct net *net) { struct ctl_table *table; - unsigned long limit; table = ipv4_net_table; if (!net_eq(net, &init_net)) { @@ -814,11 +813,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) net->ipv4.sysctl_rt_cache_rebuild_count = 4; - limit = nr_free_buffer_pages() / 8; - limit = max(limit, 128UL); - net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3; - net->ipv4.sysctl_tcp_mem[1] = limit; - net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2; + tcp_init_mem(net); net->ipv4.ipv4_hdr = register_net_sysctl_table(net, net_ipv4_ctl_path, table); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9bcdec3ad772..22ef5f9fd2ff 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1876,6 +1876,20 @@ void tcp_shutdown(struct sock *sk, int how) } EXPORT_SYMBOL(tcp_shutdown); +bool tcp_check_oom(struct sock *sk, int shift) +{ + bool too_many_orphans, out_of_socket_memory; + + too_many_orphans = tcp_too_many_orphans(sk, shift); + out_of_socket_memory = tcp_out_of_memory(sk); + + if (too_many_orphans && net_ratelimit()) + pr_info("TCP: too many orphaned sockets\n"); + if (out_of_socket_memory && net_ratelimit()) + pr_info("TCP: out of memory -- consider tuning tcp_mem\n"); + return too_many_orphans || out_of_socket_memory; +} + void tcp_close(struct sock *sk, long timeout) { struct sk_buff *skb; @@ -2015,10 +2029,7 @@ adjudge_to_death: } if (sk->sk_state != TCP_CLOSE) { sk_mem_reclaim(sk); - if (tcp_too_many_orphans(sk, 0)) { - if (net_ratelimit()) - printk(KERN_INFO "TCP: too many of orphaned " - "sockets\n"); + if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC); NET_INC_STATS_BH(sock_net(sk), @@ -3216,11 +3227,21 @@ static int __init set_thash_entries(char *str) } __setup("thash_entries=", set_thash_entries); +void tcp_init_mem(struct net *net) +{ + unsigned long limit = nr_free_buffer_pages() / 8; + limit = max(limit, 128UL); + net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3; + net->ipv4.sysctl_tcp_mem[1] = limit; + net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2; +} + void __init tcp_init(void) { struct sk_buff *skb = NULL; unsigned long limit; - int i, max_share, cnt; + int max_share, cnt; + unsigned int i; unsigned long jiffy = jiffies; BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); @@ -3263,7 +3284,7 @@ void __init tcp_init(void) &tcp_hashinfo.bhash_size, NULL, 64 * 1024); - tcp_hashinfo.bhash_size = 1 << tcp_hashinfo.bhash_size; + tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; for (i = 0; i < tcp_hashinfo.bhash_size; i++) { spin_lock_init(&tcp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain); @@ -3276,9 +3297,10 @@ void __init tcp_init(void) sysctl_tcp_max_orphans = cnt / 2; sysctl_max_syn_backlog = max(128, cnt / 256); + tcp_init_mem(&init_net); /* Set per-socket limits to no more than 1/128 the pressure threshold */ - limit = ((unsigned long)init_net.ipv4.sysctl_tcp_mem[1]) - << (PAGE_SHIFT - 7); + limit = nr_free_buffer_pages() << (PAGE_SHIFT - 10); + limit = max(limit, 128UL); max_share = min(4UL*1024*1024, limit); sysctl_tcp_wmem[0] = SK_MEM_QUANTUM; diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index 6187eb4d1dcf..f45e1c242440 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -63,7 +63,6 @@ static inline void bictcp_reset(struct bictcp *ca) { ca->cnt = 0; ca->last_max_cwnd = 0; - ca->loss_cwnd = 0; ca->last_cwnd = 0; ca->last_time = 0; ca->epoch_start = 0; @@ -72,7 +71,11 @@ static inline void bictcp_reset(struct bictcp *ca) static void bictcp_init(struct sock *sk) { - bictcp_reset(inet_csk_ca(sk)); + struct bictcp *ca = inet_csk_ca(sk); + + bictcp_reset(ca); + ca->loss_cwnd = 0; + if (initial_ssthresh) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } @@ -127,7 +130,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) } /* if in slow start or link utilization is very low */ - if (ca->loss_cwnd == 0) { + if (ca->last_max_cwnd == 0) { if (ca->cnt > 20) /* increase cwnd 5% per RTT */ ca->cnt = 20; } @@ -185,7 +188,7 @@ static u32 bictcp_undo_cwnd(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); const struct bictcp *ca = inet_csk_ca(sk); - return max(tp->snd_cwnd, ca->last_max_cwnd); + return max(tp->snd_cwnd, ca->loss_cwnd); } static void bictcp_state(struct sock *sk, u8 new_state) diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index f376b05cca81..a9077f441cb2 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -107,7 +107,6 @@ static inline void bictcp_reset(struct bictcp *ca) { ca->cnt = 0; ca->last_max_cwnd = 0; - ca->loss_cwnd = 0; ca->last_cwnd = 0; ca->last_time = 0; ca->bic_origin_point = 0; @@ -142,7 +141,10 @@ static inline void bictcp_hystart_reset(struct sock *sk) static void bictcp_init(struct sock *sk) { - bictcp_reset(inet_csk_ca(sk)); + struct bictcp *ca = inet_csk_ca(sk); + + bictcp_reset(ca); + ca->loss_cwnd = 0; if (hystart) bictcp_hystart_reset(sk); @@ -275,7 +277,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) * The initial growth of cubic function may be too conservative * when the available bandwidth is still unknown. */ - if (ca->loss_cwnd == 0 && ca->cnt > 20) + if (ca->last_max_cwnd == 0 && ca->cnt > 20) ca->cnt = 20; /* increase cwnd 5% per RTT */ /* TCP Friendly */ @@ -342,7 +344,7 @@ static u32 bictcp_undo_cwnd(struct sock *sk) { struct bictcp *ca = inet_csk_ca(sk); - return max(tcp_sk(sk)->snd_cwnd, ca->last_max_cwnd); + return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); } static void bictcp_state(struct sock *sk, u8 new_state) diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 8cd357a8be79..ed3f2ad42e0f 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -35,13 +35,13 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, } static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req *r, struct nlattr *bc) + struct inet_diag_req_v2 *r, struct nlattr *bc) { inet_diag_dump_icsk(&tcp_hashinfo, skb, cb, r, bc); } static int tcp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, - struct inet_diag_req *req) + struct inet_diag_req_v2 *req) { return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2877c3e09587..b5e315f13641 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -105,7 +105,6 @@ int sysctl_tcp_abc __read_mostly; #define FLAG_SYN_ACKED 0x10 /* This ACK acknowledged SYN. */ #define FLAG_DATA_SACKED 0x20 /* New SACK. */ #define FLAG_ECE 0x40 /* ECE in this ACK */ -#define FLAG_DATA_LOST 0x80 /* SACK detected data lossage. */ #define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/ #define FLAG_ONLY_ORIG_SACKED 0x200 /* SACKs only non-rexmit sent before RTO */ #define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */ @@ -1040,13 +1039,11 @@ static void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, * These 6 states form finite state machine, controlled by the following events: * 1. New ACK (+SACK) arrives. (tcp_sacktag_write_queue()) * 2. Retransmission. (tcp_retransmit_skb(), tcp_xmit_retransmit_queue()) - * 3. Loss detection event of one of three flavors: + * 3. Loss detection event of two flavors: * A. Scoreboard estimator decided the packet is lost. * A'. Reno "three dupacks" marks head of queue lost. - * A''. Its FACK modfication, head until snd.fack is lost. - * B. SACK arrives sacking data transmitted after never retransmitted - * hole was sent out. - * C. SACK arrives sacking SND.NXT at the moment, when the + * A''. Its FACK modification, head until snd.fack is lost. + * B. SACK arrives sacking SND.NXT at the moment, when the * segment was retransmitted. * 4. D-SACK added new rule: D-SACK changes any tag to S. * @@ -1153,7 +1150,7 @@ static int tcp_is_sackblock_valid(struct tcp_sock *tp, int is_dsack, } /* Check for lost retransmit. This superb idea is borrowed from "ratehalving". - * Event "C". Later note: FACK people cheated me again 8), we have to account + * Event "B". Later note: FACK people cheated me again 8), we have to account * for reordering! Ugly, but should help. * * Search retransmitted skbs from write_queue that were sent when snd_nxt was @@ -1310,25 +1307,26 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, return in_sack; } -static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk, - struct tcp_sacktag_state *state, +/* Mark the given newly-SACKed range as such, adjusting counters and hints. */ +static u8 tcp_sacktag_one(struct sock *sk, + struct tcp_sacktag_state *state, u8 sacked, + u32 start_seq, u32 end_seq, int dup_sack, int pcount) { struct tcp_sock *tp = tcp_sk(sk); - u8 sacked = TCP_SKB_CB(skb)->sacked; int fack_count = state->fack_count; /* Account D-SACK for retransmitted packet. */ if (dup_sack && (sacked & TCPCB_RETRANS)) { if (tp->undo_marker && tp->undo_retrans && - after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker)) + after(end_seq, tp->undo_marker)) tp->undo_retrans--; if (sacked & TCPCB_SACKED_ACKED) state->reord = min(fack_count, state->reord); } /* Nothing to do; acked frame is about to be dropped (was ACKed). */ - if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) + if (!after(end_seq, tp->snd_una)) return sacked; if (!(sacked & TCPCB_SACKED_ACKED)) { @@ -1347,13 +1345,13 @@ static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk, /* New sack for not retransmitted frame, * which was in hole. It is reordering. */ - if (before(TCP_SKB_CB(skb)->seq, + if (before(start_seq, tcp_highest_sack_seq(tp))) state->reord = min(fack_count, state->reord); /* SACK enhanced F-RTO (RFC4138; Appendix B) */ - if (!after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark)) + if (!after(end_seq, tp->frto_highmark)) state->flag |= FLAG_ONLY_ORIG_SACKED; } @@ -1371,8 +1369,7 @@ static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk, /* Lost marker hint past SACKed? Tweak RFC3517 cnt */ if (!tcp_is_fack(tp) && (tp->lost_skb_hint != NULL) && - before(TCP_SKB_CB(skb)->seq, - TCP_SKB_CB(tp->lost_skb_hint)->seq)) + before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq)) tp->lost_cnt_hint += pcount; if (fack_count > tp->fackets_out) @@ -1391,6 +1388,9 @@ static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk, return sacked; } +/* Shift newly-SACKed bytes from this skb to the immediately previous + * already-SACKed sk_buff. Mark the newly-SACKed bytes as such. + */ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, struct tcp_sacktag_state *state, unsigned int pcount, int shifted, int mss, @@ -1398,9 +1398,20 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *prev = tcp_write_queue_prev(sk, skb); + u32 start_seq = TCP_SKB_CB(skb)->seq; /* start of newly-SACKed */ + u32 end_seq = start_seq + shifted; /* end of newly-SACKed */ BUG_ON(!pcount); + /* Adjust counters and hints for the newly sacked sequence + * range but discard the return value since prev is already + * marked. We must tag the range first because the seq + * advancement below implicitly advances + * tcp_highest_sack_seq() when skb is highest_sack. + */ + tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, + start_seq, end_seq, dup_sack, pcount); + if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; @@ -1427,9 +1438,6 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, skb_shinfo(skb)->gso_type = 0; } - /* We discard results */ - tcp_sacktag_one(skb, sk, state, dup_sack, pcount); - /* Difference in this won't matter, both ACKed by the same cumul. ACK */ TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS); @@ -1577,6 +1585,10 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, } } + /* tcp_sacktag_one() won't SACK-tag ranges below snd_una */ + if (!after(TCP_SKB_CB(skb)->seq + len, tp->snd_una)) + goto fallback; + if (!skb_shift(prev, skb, len)) goto fallback; if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack)) @@ -1667,10 +1679,14 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, break; if (in_sack) { - TCP_SKB_CB(skb)->sacked = tcp_sacktag_one(skb, sk, - state, - dup_sack, - tcp_skb_pcount(skb)); + TCP_SKB_CB(skb)->sacked = + tcp_sacktag_one(sk, + state, + TCP_SKB_CB(skb)->sacked, + TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(skb)->end_seq, + dup_sack, + tcp_skb_pcount(skb)); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) @@ -1844,10 +1860,6 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, if (found_dup_sack && ((i + 1) == first_sack_index)) next_dup = &sp[i + 1]; - /* Event "B" in the comment above. */ - if (after(end_seq, tp->high_seq)) - state.flag |= FLAG_DATA_LOST; - /* Skip too early cached blocks */ while (tcp_sack_cache_ok(tp, cache) && !before(start_seq, cache->end_seq)) @@ -2515,8 +2527,11 @@ static void tcp_timeout_skbs(struct sock *sk) tcp_verify_left_out(tp); } -/* Mark head of queue up as lost. With RFC3517 SACK, the packets is - * is against sacked "cnt", otherwise it's against facked "cnt" +/* Detect loss in event "A" above by marking head of queue up as lost. + * For FACK or non-SACK(Reno) senders, the first "packets" number of segments + * are considered lost. For RFC3517 SACK, a segment is considered lost if it + * has at least tp->reordering SACKed seqments above it; "packets" refers to + * the maximum SACKed segments to pass before reaching this limit. */ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) { @@ -2525,6 +2540,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) int cnt, oldcnt; int err; unsigned int mss; + /* Use SACK to deduce losses of new sequences sent during recovery */ + const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq; WARN_ON(packets > tp->packets_out); if (tp->lost_skb_hint) { @@ -2546,7 +2563,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) tp->lost_skb_hint = skb; tp->lost_cnt_hint = cnt; - if (after(TCP_SKB_CB(skb)->end_seq, tp->high_seq)) + if (after(TCP_SKB_CB(skb)->end_seq, loss_high)) break; oldcnt = cnt; @@ -2556,6 +2573,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) if (cnt > packets) { if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) || + (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || (oldcnt >= packets)) break; @@ -3033,19 +3051,10 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, if (tcp_check_sack_reneging(sk, flag)) return; - /* C. Process data loss notification, provided it is valid. */ - if (tcp_is_fack(tp) && (flag & FLAG_DATA_LOST) && - before(tp->snd_una, tp->high_seq) && - icsk->icsk_ca_state != TCP_CA_Open && - tp->fackets_out > tp->reordering) { - tcp_mark_head_lost(sk, tp->fackets_out - tp->reordering, 0); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSS); - } - - /* D. Check consistency of the current state. */ + /* C. Check consistency of the current state. */ tcp_verify_left_out(tp); - /* E. Check state exit conditions. State can be terminated + /* D. Check state exit conditions. State can be terminated * when high_seq is ACKed. */ if (icsk->icsk_ca_state == TCP_CA_Open) { WARN_ON(tp->retrans_out != 0); @@ -3077,7 +3086,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, } } - /* F. Process state. */ + /* E. Process state. */ switch (icsk->icsk_ca_state) { case TCP_CA_Recovery: if (!(flag & FLAG_SND_UNA_ADVANCED)) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1eb4ad57670e..fd54c5f8a255 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -631,7 +631,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.iov[0].iov_len = sizeof(rep.th); #ifdef CONFIG_TCP_MD5SIG - key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr) : NULL; + key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->saddr) : NULL; if (key) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@ -651,6 +651,11 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0; + /* When socket is gone, all binding information is lost. + * routing might fail in this case. using iif for oif to + * make sure we can deliver it + */ + arg.bound_dev_if = sk ? sk->sk_bound_dev_if : inet_iif(skb); net = dev_net(skb_dst(skb)->dev); arg.tos = ip_hdr(skb)->tos; @@ -1461,9 +1466,13 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = newtp->write_seq ^ jiffies; - if (!dst && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) - goto put_and_exit; - + if (!dst) { + dst = inet_csk_route_child_sock(sk, newsk, req); + if (!dst) + goto put_and_exit; + } else { + /* syncookie case : see end of cookie_v4_check() */ + } sk_setup_caps(newsk, dst); tcp_mtup_init(newsk); diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 7fed04f875c1..49978788a9dc 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -108,7 +108,7 @@ void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) tcp = tcp_from_cgproto(cg_proto); percpu_counter_destroy(&tcp->tcp_sockets_allocated); - val = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE); + val = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT); if (val != RESOURCE_MAX) jump_label_dec(&memcg_socket_limit_enabled); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8c8de2780c7a..4ff3b6dc74fc 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1141,11 +1141,9 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) sk_mem_uncharge(sk, len); sock_set_flag(sk, SOCK_QUEUE_SHRUNK); - /* Any change of skb->len requires recalculation of tso - * factor and mss. - */ + /* Any change of skb->len requires recalculation of tso factor. */ if (tcp_skb_pcount(skb) > 1) - tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk)); + tcp_set_skb_tso_segs(sk, skb, tcp_skb_mss(skb)); return 0; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index a516d1e399df..cd2e0723266d 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -77,10 +77,7 @@ static int tcp_out_of_resources(struct sock *sk, int do_reset) if (sk->sk_err_soft) shift++; - if (tcp_too_many_orphans(sk, shift)) { - if (net_ratelimit()) - printk(KERN_INFO "Out of socket memory\n"); - + if (tcp_check_oom(sk, shift)) { /* Catch exceptional cases, when connection requires reset. * 1. Last segment was sent recently. */ if ((s32)(tcp_time_stamp - tp->lsndtime) <= TCP_TIMEWAIT_LEN || diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 69f8a7ca63dd..8a949f19deb6 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -15,11 +15,10 @@ #include <linux/udp.h> #include <net/udp.h> #include <net/udplite.h> -#include <linux/inet_diag.h> #include <linux/sock_diag.h> static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, - struct netlink_callback *cb, struct inet_diag_req *req, + struct netlink_callback *cb, struct inet_diag_req_v2 *req, struct nlattr *bc) { if (!inet_diag_bc_sk(bc, sk)) @@ -30,7 +29,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, } static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, - const struct nlmsghdr *nlh, struct inet_diag_req *req) + const struct nlmsghdr *nlh, struct inet_diag_req_v2 *req) { int err = -EINVAL; struct sock *sk; @@ -88,7 +87,7 @@ out_nosk: } static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req *r, struct nlattr *bc) + struct inet_diag_req_v2 *r, struct nlattr *bc) { int num, s_num, slot, s_slot; @@ -136,13 +135,13 @@ done: } static void udp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req *r, struct nlattr *bc) + struct inet_diag_req_v2 *r, struct nlattr *bc) { udp_dump(&udp_table, skb, cb, r, bc); } static int udp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, - struct inet_diag_req *req) + struct inet_diag_req_v2 *req) { return udp_dump_one(&udp_table, in_skb, nlh, req); } @@ -154,13 +153,13 @@ static const struct inet_diag_handler udp_diag_handler = { }; static void udplite_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req *r, struct nlattr *bc) + struct inet_diag_req_v2 *r, struct nlattr *bc) { udp_dump(&udplite_table, skb, cb, r, bc); } static int udplite_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, - struct inet_diag_req *req) + struct inet_diag_req_v2 *req) { return udp_dump_one(&udplite_table, in_skb, nlh, req); } diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c index 63418185f524..e3db3f915114 100644 --- a/net/ipv4/xfrm4_mode_beet.c +++ b/net/ipv4/xfrm4_mode_beet.c @@ -110,10 +110,7 @@ static int xfrm4_beet_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, sizeof(*iph)); skb_reset_network_header(skb); - - memmove(skb->data - skb->mac_len, skb_mac_header(skb), - skb->mac_len); - skb_set_mac_header(skb, -skb->mac_len); + skb_mac_header_rebuild(skb); xfrm4_beet_make_header(skb); diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 534972e114ac..ed4bf11ef9f4 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -66,7 +66,6 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { - const unsigned char *old_mac; int err = -EINVAL; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP) @@ -84,10 +83,9 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!(x->props.flags & XFRM_STATE_NOECN)) ipip_ecn_decapsulate(skb); - old_mac = skb_mac_header(skb); - skb_set_mac_header(skb, -skb->mac_len); - memmove(skb_mac_header(skb), old_mac, skb->mac_len); skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + err = 0; out: diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 0ba0866230c9..6b8ebc5da0e1 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -429,11 +429,15 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) ndev->tstamp = jiffies; addrconf_sysctl_register(ndev); /* protected by rtnl_lock */ - RCU_INIT_POINTER(dev->ip6_ptr, ndev); + rcu_assign_pointer(dev->ip6_ptr, ndev); /* Join all-node multicast group */ ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes); + /* Join all-router multicast group if forwarding is set */ + if (ndev->cnf.forwarding && dev && (dev->flags & IFF_MULTICAST)) + ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); + return ndev; } @@ -502,29 +506,31 @@ static void addrconf_forward_change(struct net *net, __s32 newf) rcu_read_unlock(); } -static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old) +static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) { struct net *net; + int old; + + if (!rtnl_trylock()) + return restart_syscall(); net = (struct net *)table->extra2; - if (p == &net->ipv6.devconf_dflt->forwarding) - return 0; + old = *p; + *p = newf; - if (!rtnl_trylock()) { - /* Restore the original values before restarting */ - *p = old; - return restart_syscall(); + if (p == &net->ipv6.devconf_dflt->forwarding) { + rtnl_unlock(); + return 0; } if (p == &net->ipv6.devconf_all->forwarding) { - __s32 newf = net->ipv6.devconf_all->forwarding; net->ipv6.devconf_dflt->forwarding = newf; addrconf_forward_change(net, newf); - } else if ((!*p) ^ (!old)) + } else if ((!newf) ^ (!old)) dev_forward_change((struct inet6_dev *)table->extra1); rtnl_unlock(); - if (*p) + if (newf) rt6_purge_dflt_routers(net); return 1; } @@ -4260,9 +4266,17 @@ int addrconf_sysctl_forward(ctl_table *ctl, int write, int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; + ctl_table lctl; int ret; - ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + /* + * ctl->data points to idev->cnf.forwarding, we should + * not modify it until we get the rtnl lock. + */ + lctl = *ctl; + lctl.data = &val; + + ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); if (write) ret = addrconf_fixup_forwarding(ctl, valp, val); @@ -4300,26 +4314,27 @@ static void addrconf_disable_change(struct net *net, __s32 newf) rcu_read_unlock(); } -static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int old) +static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) { struct net *net; + int old; + + if (!rtnl_trylock()) + return restart_syscall(); net = (struct net *)table->extra2; + old = *p; + *p = newf; - if (p == &net->ipv6.devconf_dflt->disable_ipv6) + if (p == &net->ipv6.devconf_dflt->disable_ipv6) { + rtnl_unlock(); return 0; - - if (!rtnl_trylock()) { - /* Restore the original values before restarting */ - *p = old; - return restart_syscall(); } if (p == &net->ipv6.devconf_all->disable_ipv6) { - __s32 newf = net->ipv6.devconf_all->disable_ipv6; net->ipv6.devconf_dflt->disable_ipv6 = newf; addrconf_disable_change(net, newf); - } else if ((!*p) ^ (!old)) + } else if ((!newf) ^ (!old)) dev_disable_change((struct inet6_dev *)table->extra1); rtnl_unlock(); @@ -4333,9 +4348,17 @@ int addrconf_sysctl_disable(ctl_table *ctl, int write, int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; + ctl_table lctl; int ret; - ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + /* + * ctl->data points to idev->cnf.disable_ipv6, we should + * not modify it until we get the rtnl lock. + */ + lctl = *ctl; + lctl.data = &val; + + ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); if (write) ret = addrconf_disable_ipv6(ctl, valp, val); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index ae08aee1773c..251e7cd75e89 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -575,7 +575,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) } if (np->rxopt.bits.rxorigdstaddr) { struct sockaddr_in6 sin6; - u16 *ports = (u16 *) skb_transport_header(skb); + __be16 *ports = (__be16 *) skb_transport_header(skb); if (skb_transport_offset(skb) + 4 <= skb->len) { /* All current transport protocols have the port numbers in the diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index e1f7761815f3..aa21da6a09cd 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_INIT_POINTER(t->next , rtnl_dereference(*tp)); - RCU_INIT_POINTER(*tp, t); + rcu_assign_pointer(t->next , rtnl_dereference(*tp)); + rcu_assign_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_INIT_POINTER(*tp, t->next); + rcu_assign_pointer(*tp, t->next); break; } } @@ -1450,7 +1450,7 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) t->parms.proto = IPPROTO_IPV6; dev_hold(dev); - RCU_INIT_POINTER(ip6n->tnls_wc[0], t); + rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index c7e95c8c579f..5aa3981a3922 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1926,8 +1926,10 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, }; dst = ip6_route_output(net, NULL, &fl6); - if (!dst) + if (dst->error) { + dst_release(dst); goto out_free; + } skb_dst_drop(skb); skb_dst_set(skb, dst); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index b853f06cc148..16c33e308121 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -257,7 +257,6 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net, if (rt) { dev = rt->dst.dev; - dev_hold(dev); dst_release(&rt->dst); } } else diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index d8f02ef88e59..c964958ac470 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1545,9 +1545,10 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex); dst = ip6_route_output(net, NULL, &fl6); - if (dst == NULL) + if (dst->error) { + dst_release(dst); return; - + } dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); if (IS_ERR(dst)) return; diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index fb80a23c6640..a34c9e4c792c 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -432,7 +432,7 @@ __ipq_rcv_skb(struct sk_buff *skb) if (type <= IPQM_BASE) return; - if (security_netlink_recv(skb, CAP_NET_ADMIN)) + if (!capable(CAP_NET_ADMIN)) RCV_SKB_FAIL(-EPERM); spin_lock_bh(&queue_lock); diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index fdeb6d03da81..da2e92d05c15 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -237,8 +237,8 @@ static int snmp6_dev_seq_show(struct seq_file *seq, void *v) struct inet6_dev *idev = (struct inet6_dev *)seq->private; seq_printf(seq, "%-32s\t%u\n", "ifIndex", idev->dev->ifindex); - snmp6_seq_show_item(seq, (void __percpu **)idev->stats.ipv6, NULL, - snmp6_ipstats_list); + snmp6_seq_show_item64(seq, (void __percpu **)idev->stats.ipv6, + snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp)); snmp6_seq_show_item(seq, NULL, idev->stats.icmpv6dev->mibs, snmp6_icmp6_list); snmp6_seq_show_icmpv6msg(seq, idev->stats.icmpv6msgdev->mibs); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a4894f4f1944..d02f7e4dd611 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -131,7 +131,7 @@ static mh_filter_t __rcu *mh_filter __read_mostly; int rawv6_mh_filter_register(mh_filter_t filter) { - RCU_INIT_POINTER(mh_filter, filter); + rcu_assign_pointer(mh_filter, filter); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_register); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 07361dfa8085..22b766407de1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1077,7 +1077,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct net *net = dev_net(dev); if (unlikely(!idev)) - return NULL; + return ERR_PTR(-ENODEV); rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0); if (unlikely(!rt)) { @@ -1091,6 +1091,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, else { neigh = ip6_neigh_lookup(&rt->dst, &fl6->daddr); if (IS_ERR(neigh)) { + in6_dev_put(idev); dst_free(&rt->dst); return ERR_CAST(neigh); } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3b6dac956bb0..133768e52912 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_INIT_POINTER(*tp, t->next); + rcu_assign_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_INIT_POINTER(t->next, rtnl_dereference(*tp)); - RCU_INIT_POINTER(*tp, t); + rcu_assign_pointer(t->next, rtnl_dereference(*tp)); + rcu_assign_pointer(*tp, t); } static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) @@ -393,7 +393,7 @@ 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_INIT_POINTER(t->prl, p); + rcu_assign_pointer(t->prl, p); out: return err; } @@ -1177,7 +1177,7 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; dev_hold(dev); - RCU_INIT_POINTER(sitn->tunnels_wc[0], tunnel); + rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); return 0; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 906c7ca43542..3edd05ae4388 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1083,7 +1083,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) #ifdef CONFIG_TCP_MD5SIG if (sk) - key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr); + key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr); #endif if (th->ack) diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index a81ce9450750..9949a356d62c 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -80,7 +80,6 @@ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb) { struct ipv6hdr *ip6h; - const unsigned char *old_mac; int size = sizeof(struct ipv6hdr); int err; @@ -90,10 +89,7 @@ static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb) __skb_push(skb, size); skb_reset_network_header(skb); - - old_mac = skb_mac_header(skb); - skb_set_mac_header(skb, -skb->mac_len); - memmove(skb_mac_header(skb), old_mac, skb->mac_len); + skb_mac_header_rebuild(skb); xfrm6_beet_make_header(skb); diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 261e6e6f487e..9f2095b19ad0 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -63,7 +63,6 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { int err = -EINVAL; - const unsigned char *old_mac; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6) goto out; @@ -80,10 +79,9 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!(x->props.flags & XFRM_STATE_NOECN)) ipip6_ecn_decapsulate(skb); - old_mac = skb_mac_header(skb); - skb_set_mac_header(skb, -skb->mac_len); - memmove(skb_mac_header(skb), old_mac, skb->mac_len); skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + err = 0; out: diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index d21e7ebd91ca..55670ec3cd0f 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -393,11 +393,6 @@ static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb) { int rc; - if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) - goto drop; - - nf_reset(skb); - /* Charge it to the socket, dropping if the queue is full. */ rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index a18e6c3d36e3..b9bef2c75026 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -713,6 +713,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, struct sk_buff *skb = NULL; struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); + unsigned long cpu_flags; size_t copied = 0; u32 peek_seq = 0; u32 *seq; @@ -838,7 +839,9 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, goto copy_uaddr; if (!(flags & MSG_PEEK)) { + spin_lock_irqsave(&sk->sk_receive_queue.lock, cpu_flags); sk_eat_skb(sk, skb, 0); + spin_unlock_irqrestore(&sk->sk_receive_queue.lock, cpu_flags); *seq = 0; } @@ -859,7 +862,9 @@ copy_uaddr: llc_cmsg_rcv(msg, skb); if (!(flags & MSG_PEEK)) { + spin_lock_irqsave(&sk->sk_receive_queue.lock, cpu_flags); sk_eat_skb(sk, skb, 0); + spin_unlock_irqrestore(&sk->sk_receive_queue.lock, cpu_flags); *seq = 0; } diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 96debba2c407..1068f668ac4e 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -332,7 +332,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, status = WLAN_STATUS_SUCCESS; /* activate it for RX */ - RCU_INIT_POINTER(sta->ampdu_mlme.tid_rx[tid], tid_agg_rx); + rcu_assign_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/cfg.c b/net/mac80211/cfg.c index 850bb96bd680..296620d6ca0c 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -616,7 +616,7 @@ static int ieee80211_config_beacon(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.dtim_period = new->dtim_period; - RCU_INIT_POINTER(sdata->u.ap.beacon, new); + rcu_assign_pointer(sdata->u.ap.beacon, new); synchronize_rcu(); @@ -791,7 +791,7 @@ static int sta_apply_parameters(struct ieee80211_local *local, if (set & BIT(NL80211_STA_FLAG_AUTHORIZED)) ret = sta_info_move_state_checked(sta, IEEE80211_STA_AUTHORIZED); - else + else if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ret = sta_info_move_state_checked(sta, IEEE80211_STA_ASSOC); if (ret) @@ -1033,7 +1033,7 @@ static int ieee80211_change_station(struct wiphy *wiphy, return -EBUSY; } - RCU_INIT_POINTER(vlansdata->u.vlan.sta, sta); + rcu_assign_pointer(vlansdata->u.vlan.sta, sta); } sta->sdata = vlansdata; diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index 38e6101190d9..59edcd95a58d 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -225,9 +225,9 @@ KEY_OPS(key); key, &key_##name##_ops); void ieee80211_debugfs_key_add(struct ieee80211_key *key) - { +{ static int keycount; - char buf[50]; + char buf[100]; struct sta_info *sta; if (!key->local->debugfs.keys) @@ -244,7 +244,8 @@ void ieee80211_debugfs_key_add(struct ieee80211_key *key) sta = key->sta; if (sta) { - sprintf(buf, "../../stations/%pM", sta->sta.addr); + sprintf(buf, "../../netdev:%s/stations/%pM", + sta->sdata->name, sta->sta.addr); key->debugfs.stalink = debugfs_create_symlink("station", key->debugfs.dir, buf); } diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 2406b3e7393f..d86217d56bd7 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -63,14 +63,14 @@ static ssize_t sta_flags_read(struct file *file, char __user *userbuf, 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%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(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)); + TEST(TDLS_PEER_AUTH), TEST(RATE_CONTROL)); #undef TEST return simple_read_from_buffer(userbuf, count, ppos, buf, res); } diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index f8a32bf98216..a4643969a13b 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -106,6 +106,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, sdata->drop_unencrypted = capability & WLAN_CAPABILITY_PRIVACY ? 1 : 0; + local->oper_channel = chan; channel_type = ifibss->channel_type; if (channel_type > NL80211_CHAN_HT20 && !cfg80211_can_beacon_sec_chan(local->hw.wiphy, chan, channel_type)) @@ -207,7 +208,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, *pos++ = 0; /* U-APSD no in use */ } - RCU_INIT_POINTER(ifibss->presp, skb); + rcu_assign_pointer(ifibss->presp, skb); sdata->vif.bss_conf.beacon_int = beacon_int; sdata->vif.bss_conf.basic_rates = basic_rates; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index e47768cb8cb3..8e2137bd87e2 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1314,6 +1314,7 @@ u32 __ieee80211_recalc_idle(struct ieee80211_local *local) continue; } /* count everything else */ + sdata->vif.bss_conf.idle = false; count++; } @@ -1331,6 +1332,9 @@ u32 __ieee80211_recalc_idle(struct ieee80211_local *local) hw_roc = true; list_for_each_entry(sdata, &local->interfaces, list) { + if (sdata->vif.type == NL80211_IFTYPE_MONITOR || + sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + continue; if (sdata->old_idle == sdata->vif.bss_conf.idle) continue; if (!ieee80211_sdata_running(sdata)) diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 0a0d94ad9b08..b142bd4c2390 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -910,6 +910,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) wiphy_debug(local->hw.wiphy, "Failed to initialize wep: %d\n", result); + ieee80211_led_init(local); + rtnl_lock(); result = ieee80211_init_rate_ctrl_alg(local, @@ -931,8 +933,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) rtnl_unlock(); - ieee80211_led_init(local); - local->network_latency_notifier.notifier_call = ieee80211_max_network_latency; result = pm_qos_add_notifier(PM_QOS_NETWORK_LATENCY, diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 73abb7524b2c..54df1b2bafd2 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -119,12 +119,12 @@ static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags, int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.mesh_action) + sizeof(mgmt->u.action.u.mesh_action); - skb = dev_alloc_skb(local->hw.extra_tx_headroom + + skb = dev_alloc_skb(local->tx_headroom + hdr_len + 2 + 37); /* max HWMP IE */ if (!skb) return -1; - skb_reserve(skb, local->hw.extra_tx_headroom); + skb_reserve(skb, local->tx_headroom); mgmt = (struct ieee80211_mgmt *) skb_put(skb, hdr_len); memset(mgmt, 0, hdr_len); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | @@ -250,12 +250,12 @@ int mesh_path_error_tx(u8 ttl, u8 *target, __le32 target_sn, if (time_before(jiffies, ifmsh->next_perr)) return -EAGAIN; - skb = dev_alloc_skb(local->hw.extra_tx_headroom + + skb = dev_alloc_skb(local->tx_headroom + hdr_len + 2 + 15 /* PERR IE */); if (!skb) return -1; - skb_reserve(skb, local->tx_headroom + local->hw.extra_tx_headroom); + skb_reserve(skb, local->tx_headroom); mgmt = (struct ieee80211_mgmt *) skb_put(skb, hdr_len); memset(mgmt, 0, hdr_len); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 41ef1b476442..a17251730b9e 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -172,7 +172,7 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.self_prot) + sizeof(mgmt->u.action.u.self_prot); - skb = dev_alloc_skb(local->hw.extra_tx_headroom + + skb = dev_alloc_skb(local->tx_headroom + hdr_len + 2 + /* capability info */ 2 + /* AID */ @@ -186,7 +186,7 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, sdata->u.mesh.ie_len); if (!skb) return -1; - skb_reserve(skb, local->hw.extra_tx_headroom); + skb_reserve(skb, local->tx_headroom); mgmt = (struct ieee80211_mgmt *) skb_put(skb, hdr_len); memset(mgmt, 0, hdr_len); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index ecb4c84c1bb3..295be92f7c77 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2750,7 +2750,6 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - struct ieee80211_work *wk; u8 bssid[ETH_ALEN]; bool assoc_bss = false; @@ -2763,30 +2762,47 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, assoc_bss = true; } else { bool not_auth_yet = false; + struct ieee80211_work *tmp, *wk = NULL; mutex_unlock(&ifmgd->mtx); mutex_lock(&local->mtx); - list_for_each_entry(wk, &local->work_list, list) { - if (wk->sdata != sdata) + list_for_each_entry(tmp, &local->work_list, list) { + if (tmp->sdata != sdata) continue; - if (wk->type != IEEE80211_WORK_DIRECT_PROBE && - wk->type != IEEE80211_WORK_AUTH && - wk->type != IEEE80211_WORK_ASSOC && - wk->type != IEEE80211_WORK_ASSOC_BEACON_WAIT) + if (tmp->type != IEEE80211_WORK_DIRECT_PROBE && + tmp->type != IEEE80211_WORK_AUTH && + tmp->type != IEEE80211_WORK_ASSOC && + tmp->type != IEEE80211_WORK_ASSOC_BEACON_WAIT) continue; - if (memcmp(req->bss->bssid, wk->filter_ta, ETH_ALEN)) + if (memcmp(req->bss->bssid, tmp->filter_ta, ETH_ALEN)) continue; - not_auth_yet = wk->type == IEEE80211_WORK_DIRECT_PROBE; - list_del_rcu(&wk->list); - free_work(wk); + not_auth_yet = tmp->type == IEEE80211_WORK_DIRECT_PROBE; + list_del_rcu(&tmp->list); + synchronize_rcu(); + wk = tmp; break; } mutex_unlock(&local->mtx); + if (wk && wk->type == IEEE80211_WORK_ASSOC) { + /* clean up dummy sta & TX sync */ + sta_info_destroy_addr(wk->sdata, wk->filter_ta); + if (wk->assoc.synced) + drv_finish_tx_sync(local, wk->sdata, + wk->filter_ta, + IEEE80211_TX_SYNC_ASSOC); + } else if (wk && wk->type == IEEE80211_WORK_AUTH) { + if (wk->probe_auth.synced) + drv_finish_tx_sync(local, wk->sdata, + wk->filter_ta, + IEEE80211_TX_SYNC_AUTH); + } + kfree(wk); + /* * If somebody requests authentication and we haven't * sent out an auth frame yet there's no need to send diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 5a5a7767d541..f9b8e819ca63 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -336,7 +336,7 @@ void rate_control_get_rate(struct ieee80211_sub_if_data *sdata, int i; u32 mask; - if (sta) { + if (sta && test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) { ista = &sta->sta; priv_sta = sta->rate_ctrl_priv; } @@ -344,7 +344,7 @@ void rate_control_get_rate(struct ieee80211_sub_if_data *sdata, for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { info->control.rates[i].idx = -1; info->control.rates[i].flags = 0; - info->control.rates[i].count = 1; + info->control.rates[i].count = 0; } if (sdata->local->hw.flags & IEEE80211_HW_HAS_RATE_CONTROL) diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h index 168427b0ffdc..80cfc006dd74 100644 --- a/net/mac80211/rate.h +++ b/net/mac80211/rate.h @@ -41,7 +41,7 @@ static inline void rate_control_tx_status(struct ieee80211_local *local, struct ieee80211_sta *ista = &sta->sta; void *priv_sta = sta->rate_ctrl_priv; - if (!ref) + if (!ref || !test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) return; ref->ops->tx_status(ref->priv, sband, ista, priv_sta, skb); @@ -62,6 +62,7 @@ static inline void rate_control_rate_init(struct sta_info *sta) sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; ref->ops->rate_init(ref->priv, sband, ista, priv_sta); + set_sta_flag(sta, WLAN_STA_RATE_CONTROL); } static inline void rate_control_rate_update(struct ieee80211_local *local, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index f407427c642f..5a5e504a8ffb 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -611,7 +611,7 @@ static void ieee80211_sta_reorder_release(struct ieee80211_hw *hw, index = seq_sub(tid_agg_rx->head_seq_num, tid_agg_rx->ssn) % tid_agg_rx->buf_size; if (!tid_agg_rx->reorder_buf[index] && - tid_agg_rx->stored_mpdu_num > 1) { + tid_agg_rx->stored_mpdu_num) { /* * No buffers ready to be released, but check whether any * frames in the reorder buffer have timed out. @@ -1979,6 +1979,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) mesh_path_error_tx(ifmsh->mshcfg.element_ttl, fwd_hdr->addr3, 0, reason, fwd_hdr->addr2, sdata); IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_no_route); + kfree_skb(fwd_skb); return RX_DROP_MONITOR; } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index b197136aea2c..ff11f6bf8266 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -73,7 +73,7 @@ static int sta_info_hash_del(struct ieee80211_local *local, if (!s) return -ENOENT; if (s == sta) { - RCU_INIT_POINTER(local->sta_hash[STA_HASH(sta->sta.addr)], + rcu_assign_pointer(local->sta_hash[STA_HASH(sta->sta.addr)], s->hnext); return 0; } @@ -83,7 +83,7 @@ static int sta_info_hash_del(struct ieee80211_local *local, s = rcu_dereference_protected(s->hnext, lockdep_is_held(&local->sta_mtx)); if (rcu_access_pointer(s->hnext)) { - RCU_INIT_POINTER(s->hnext, sta->hnext); + rcu_assign_pointer(s->hnext, sta->hnext); return 0; } @@ -226,7 +226,7 @@ static void sta_info_hash_add(struct ieee80211_local *local, { lockdep_assert_held(&local->sta_mtx); sta->hnext = local->sta_hash[STA_HASH(sta->sta.addr)]; - RCU_INIT_POINTER(local->sta_hash[STA_HASH(sta->sta.addr)], sta); + rcu_assign_pointer(local->sta_hash[STA_HASH(sta->sta.addr)], sta); } static void sta_unblock(struct work_struct *wk) @@ -238,9 +238,11 @@ static void sta_unblock(struct work_struct *wk) if (sta->dead) return; - if (!test_sta_flag(sta, WLAN_STA_PS_STA)) + if (!test_sta_flag(sta, WLAN_STA_PS_STA)) { + local_bh_disable(); ieee80211_sta_ps_deliver_wakeup(sta); - else if (test_and_clear_sta_flag(sta, WLAN_STA_PSPOLL)) { + local_bh_enable(); + } else if (test_and_clear_sta_flag(sta, WLAN_STA_PSPOLL)) { clear_sta_flag(sta, WLAN_STA_PS_DRIVER); local_bh_disable(); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 6f77f12dc3fc..bfed851d0d36 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -52,6 +52,7 @@ * @WLAN_STA_SP: Station is in a service period, so don't try to * reply to other uAPSD trigger frames or PS-Poll. * @WLAN_STA_4ADDR_EVENT: 4-addr event was already sent for this frame. + * @WLAN_STA_RATE_CONTROL: rate control was initialized for this station. */ enum ieee80211_sta_info_flags { WLAN_STA_AUTH, @@ -71,6 +72,7 @@ enum ieee80211_sta_info_flags { WLAN_STA_UAPSD, WLAN_STA_SP, WLAN_STA_4ADDR_EVENT, + WLAN_STA_RATE_CONTROL, }; enum ieee80211_sta_state { diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index edcd1c7ab83f..e05667cd5e76 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1001,8 +1001,6 @@ ieee80211_tx_h_stats(struct ieee80211_tx_data *tx) static ieee80211_tx_result debug_noinline ieee80211_tx_h_encrypt(struct ieee80211_tx_data *tx) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); - if (!tx->key) return TX_CONTINUE; @@ -1017,13 +1015,7 @@ ieee80211_tx_h_encrypt(struct ieee80211_tx_data *tx) case WLAN_CIPHER_SUITE_AES_CMAC: return ieee80211_crypto_aes_cmac_encrypt(tx); default: - /* handle hw-only algorithm */ - if (info->control.hw_key) { - ieee80211_tx_set_protected(tx); - return TX_CONTINUE; - } - break; - + return ieee80211_crypto_hw_encrypt(tx); } return TX_DROP; diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 93aab0715e8a..b758350919ff 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -106,7 +106,7 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) if (status->flag & RX_FLAG_MMIC_ERROR) goto mic_fail; - if (!(status->flag & RX_FLAG_IV_STRIPPED)) + if (!(status->flag & RX_FLAG_IV_STRIPPED) && rx->key) goto update_iv; return RX_CONTINUE; @@ -643,3 +643,22 @@ ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx) return RX_CONTINUE; } + +ieee80211_tx_result +ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx) +{ + struct sk_buff *skb; + struct ieee80211_tx_info *info = NULL; + + skb_queue_walk(&tx->skbs, skb) { + info = IEEE80211_SKB_CB(skb); + + /* handle hw-only algorithm */ + if (!info->control.hw_key) + return TX_DROP; + } + + ieee80211_tx_set_protected(tx); + + return TX_CONTINUE; +} diff --git a/net/mac80211/wpa.h b/net/mac80211/wpa.h index baba0608313e..07e33f899c71 100644 --- a/net/mac80211/wpa.h +++ b/net/mac80211/wpa.h @@ -32,5 +32,7 @@ ieee80211_tx_result ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx); ieee80211_rx_result ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx); +ieee80211_tx_result +ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx); #endif /* WPA_H */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 86137b558f45..32dbf0fa89db 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -77,35 +77,42 @@ find_set_type(const char *name, u8 family, u8 revision) } /* Unlock, try to load a set type module and lock again */ -static int -try_to_load_type(const char *name) +static bool +load_settype(const char *name) { nfnl_unlock(); pr_debug("try to load ip_set_%s\n", name); if (request_module("ip_set_%s", name) < 0) { pr_warning("Can't find ip_set type %s\n", name); nfnl_lock(); - return -IPSET_ERR_FIND_TYPE; + return false; } nfnl_lock(); - return -EAGAIN; + return true; } /* Find a set type and reference it */ +#define find_set_type_get(name, family, revision, found) \ + __find_set_type_get(name, family, revision, found, false) + static int -find_set_type_get(const char *name, u8 family, u8 revision, - struct ip_set_type **found) +__find_set_type_get(const char *name, u8 family, u8 revision, + struct ip_set_type **found, bool retry) { struct ip_set_type *type; int err; + if (retry && !load_settype(name)) + return -IPSET_ERR_FIND_TYPE; + rcu_read_lock(); *found = find_set_type(name, family, revision); if (*found) { err = !try_module_get((*found)->me) ? -EFAULT : 0; goto unlock; } - /* Make sure the type is loaded but we don't support the revision */ + /* Make sure the type is already loaded + * but we don't support the revision */ list_for_each_entry_rcu(type, &ip_set_type_list, list) if (STREQ(type->name, name)) { err = -IPSET_ERR_FIND_TYPE; @@ -113,7 +120,8 @@ find_set_type_get(const char *name, u8 family, u8 revision, } rcu_read_unlock(); - return try_to_load_type(name); + return retry ? -IPSET_ERR_FIND_TYPE : + __find_set_type_get(name, family, revision, found, true); unlock: rcu_read_unlock(); @@ -124,12 +132,19 @@ unlock: * If we succeeded, the supported minimal and maximum revisions are * filled out. */ +#define find_set_type_minmax(name, family, min, max) \ + __find_set_type_minmax(name, family, min, max, false) + static int -find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max) +__find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max, + bool retry) { struct ip_set_type *type; bool found = false; + if (retry && !load_settype(name)) + return -IPSET_ERR_FIND_TYPE; + *min = 255; *max = 0; rcu_read_lock(); list_for_each_entry_rcu(type, &ip_set_type_list, list) @@ -145,7 +160,8 @@ find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max) if (found) return 0; - return try_to_load_type(name); + return retry ? -IPSET_ERR_FIND_TYPE : + __find_set_type_minmax(name, family, min, max, true); } #define family_name(f) ((f) == AF_INET ? "inet" : \ @@ -1126,6 +1142,7 @@ release_refcount: if (ret || !cb->args[2]) { pr_debug("release set %s\n", ip_set_list[index]->name); ip_set_put_byindex(index); + cb->args[2] = 0; } out: if (nlh) { diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index af4c0b8c5275..f9871385a65e 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -122,7 +122,6 @@ config IP_VS_RR config IP_VS_WRR tristate "weighted round-robin scheduling" - select GCD ---help--- The weighted robin-robin scheduling algorithm directs network connections to different real servers based on server weights diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 611c3359b94d..2555816e7788 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -232,6 +232,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc, __be16 dport = 0; /* destination port to forward */ unsigned int flags; struct ip_vs_conn_param param; + const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; union nf_inet_addr snet; /* source network of the client, after masking */ @@ -267,7 +268,6 @@ ip_vs_sched_persist(struct ip_vs_service *svc, { int protocol = iph.protocol; const union nf_inet_addr *vaddr = &iph.daddr; - const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; __be16 vport = 0; if (dst_port == svc->port) { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index e875f8902db3..fa4b82c8ae80 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -404,19 +404,49 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct, &net->ct.hash[repl_hash]); } -void nf_conntrack_hash_insert(struct nf_conn *ct) +int +nf_conntrack_hash_check_insert(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); unsigned int hash, repl_hash; + struct nf_conntrack_tuple_hash *h; + struct hlist_nulls_node *n; u16 zone; zone = nf_ct_zone(ct); - hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - repl_hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + repl_hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + + spin_lock_bh(&nf_conntrack_lock); + + /* See if there's one in the list already, including reverse */ + hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode) + if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &h->tuple) && + zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) + goto out; + hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode) + if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, + &h->tuple) && + zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) + goto out; + add_timer(&ct->timeout); + nf_conntrack_get(&ct->ct_general); __nf_conntrack_hash_insert(ct, hash, repl_hash); + NF_CT_STAT_INC(net, insert); + spin_unlock_bh(&nf_conntrack_lock); + + return 0; + +out: + NF_CT_STAT_INC(net, insert_failed); + spin_unlock_bh(&nf_conntrack_lock); + return -EEXIST; } -EXPORT_SYMBOL_GPL(nf_conntrack_hash_insert); +EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); /* Confirm a connection given skb; places it in hash table */ int @@ -605,8 +635,12 @@ static noinline int early_drop(struct net *net, unsigned int hash) if (del_timer(&ct->timeout)) { death_by_timeout((unsigned long)ct); - dropped = 1; - NF_CT_STAT_INC_ATOMIC(net, early_drop); + /* Check if we indeed killed this entry. Reliable event + delivery may have inserted it into the dying list. */ + if (test_bit(IPS_DYING_BIT, &ct->status)) { + dropped = 1; + NF_CT_STAT_INC_ATOMIC(net, early_drop); + } } nf_ct_put(ct); return dropped; @@ -777,7 +811,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, if (exp->helper) { help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help) - RCU_INIT_POINTER(help->helper, exp->helper); + rcu_assign_pointer(help->helper, exp->helper); } #ifdef CONFIG_NF_CONNTRACK_MARK diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index b62c4148b921..14af6329bdda 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -91,7 +91,7 @@ int nf_conntrack_register_notifier(struct net *net, ret = -EBUSY; goto out_unlock; } - RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, new); + rcu_assign_pointer(net->ct.nf_conntrack_event_cb, new); mutex_unlock(&nf_ct_ecache_mutex); return ret; @@ -128,7 +128,7 @@ int nf_ct_expect_register_notifier(struct net *net, ret = -EBUSY; goto out_unlock; } - RCU_INIT_POINTER(net->ct.nf_expect_event_cb, new); + rcu_assign_pointer(net->ct.nf_expect_event_cb, new); mutex_unlock(&nf_ct_ecache_mutex); return ret; diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 4605c947dcc4..641ff5f96718 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_INIT_POINTER(nf_ct_ext_types[type->id], type); + rcu_assign_pointer(nf_ct_ext_types[type->id], type); update_alloc_size(type); out: mutex_unlock(&nf_ct_ext_type_mutex); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index c9e0de08aa87..bbe23baa19b6 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -121,18 +121,6 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, int ret = 0; if (tmpl != NULL) { - /* we've got a userspace helper. */ - if (tmpl->status & IPS_USERSPACE_HELPER) { - help = nf_ct_helper_ext_add(ct, flags); - if (help == NULL) { - ret = -ENOMEM; - goto out; - } - rcu_assign_pointer(help->helper, NULL); - __set_bit(IPS_USERSPACE_HELPER_BIT, &ct->status); - ret = 0; - goto out; - } help = nfct_help(tmpl); if (help != NULL) helper = help->helper; @@ -157,7 +145,7 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, memset(&help->help, 0, sizeof(help->help)); } - RCU_INIT_POINTER(help->helper, helper); + rcu_assign_pointer(help->helper, helper); out: return ret; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index e07dc3ae930e..b49da6c925b3 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -943,20 +943,21 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, } } - if (nf_conntrack_event_report(IPCT_DESTROY, ct, - NETLINK_CB(skb).pid, - nlmsg_report(nlh)) < 0) { + if (del_timer(&ct->timeout)) { + if (nf_conntrack_event_report(IPCT_DESTROY, ct, + NETLINK_CB(skb).pid, + nlmsg_report(nlh)) < 0) { + nf_ct_delete_from_lists(ct); + /* we failed to report the event, try later */ + nf_ct_insert_dying_list(ct); + nf_ct_put(ct); + return 0; + } + /* death_by_timeout would report the event again */ + set_bit(IPS_DYING_BIT, &ct->status); nf_ct_delete_from_lists(ct); - /* we failed to report the event, try later */ - nf_ct_insert_dying_list(ct); nf_ct_put(ct); - return 0; } - - /* death_by_timeout would report the event again */ - set_bit(IPS_DYING_BIT, &ct->status); - - nf_ct_kill(ct); nf_ct_put(ct); return 0; @@ -1041,16 +1042,13 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, if (!parse_nat_setup) { #ifdef CONFIG_MODULES rcu_read_unlock(); - spin_unlock_bh(&nf_conntrack_lock); nfnl_unlock(); if (request_module("nf-nat-ipv4") < 0) { nfnl_lock(); - spin_lock_bh(&nf_conntrack_lock); rcu_read_lock(); return -EOPNOTSUPP; } nfnl_lock(); - spin_lock_bh(&nf_conntrack_lock); rcu_read_lock(); if (nfnetlink_parse_nat_setup_hook) return -EAGAIN; @@ -1172,7 +1170,7 @@ ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) return -EOPNOTSUPP; } - RCU_INIT_POINTER(help->helper, helper); + rcu_assign_pointer(help->helper, helper); return 0; } @@ -1367,15 +1365,12 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); - spin_unlock_bh(&nf_conntrack_lock); #ifdef CONFIG_MODULES if (request_module("nfct-helper-%s", helpname) < 0) { - spin_lock_bh(&nf_conntrack_lock); err = -EOPNOTSUPP; goto err1; } - spin_lock_bh(&nf_conntrack_lock); rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), @@ -1468,8 +1463,10 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, if (tstamp) tstamp->start = ktime_to_ns(ktime_get_real()); - add_timer(&ct->timeout); - nf_conntrack_hash_insert(ct); + err = nf_conntrack_hash_check_insert(ct); + if (err < 0) + goto err2; + rcu_read_unlock(); return ct; @@ -1490,6 +1487,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; struct nfgenmsg *nfmsg = nlmsg_data(nlh); + struct nf_conn *ct; u_int8_t u3 = nfmsg->nfgen_family; u16 zone; int err; @@ -1510,27 +1508,22 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, return err; } - spin_lock_bh(&nf_conntrack_lock); if (cda[CTA_TUPLE_ORIG]) - h = __nf_conntrack_find(net, zone, &otuple); + h = nf_conntrack_find_get(net, zone, &otuple); else if (cda[CTA_TUPLE_REPLY]) - h = __nf_conntrack_find(net, zone, &rtuple); + h = nf_conntrack_find_get(net, zone, &rtuple); if (h == NULL) { err = -ENOENT; if (nlh->nlmsg_flags & NLM_F_CREATE) { - struct nf_conn *ct; enum ip_conntrack_events events; ct = ctnetlink_create_conntrack(net, zone, cda, &otuple, &rtuple, u3); - if (IS_ERR(ct)) { - err = PTR_ERR(ct); - goto out_unlock; - } + if (IS_ERR(ct)) + return PTR_ERR(ct); + err = 0; - nf_conntrack_get(&ct->ct_general); - spin_unlock_bh(&nf_conntrack_lock); if (test_bit(IPS_EXPECTED_BIT, &ct->status)) events = IPCT_RELATED; else @@ -1545,23 +1538,19 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, ct, NETLINK_CB(skb).pid, nlmsg_report(nlh)); nf_ct_put(ct); - } else - spin_unlock_bh(&nf_conntrack_lock); + } return err; } /* implicit 'else' */ - /* We manipulate the conntrack inside the global conntrack table lock, - * so there's no need to increase the refcount */ err = -EEXIST; + ct = nf_ct_tuplehash_to_ctrack(h); if (!(nlh->nlmsg_flags & NLM_F_EXCL)) { - struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); - + spin_lock_bh(&nf_conntrack_lock); err = ctnetlink_change_conntrack(ct, cda); + spin_unlock_bh(&nf_conntrack_lock); if (err == 0) { - nf_conntrack_get(&ct->ct_general); - spin_unlock_bh(&nf_conntrack_lock); nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | @@ -1570,15 +1559,10 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, (1 << IPCT_MARK), ct, NETLINK_CB(skb).pid, nlmsg_report(nlh)); - nf_ct_put(ct); - } else - spin_unlock_bh(&nf_conntrack_lock); - - return err; + } } -out_unlock: - spin_unlock_bh(&nf_conntrack_lock); + nf_ct_put(ct); return err; } @@ -2042,10 +2026,6 @@ ctnetlink_create_expect(struct net *net, u16 zone, } help = nfct_help(ct); if (!help) { - err = -EOPNOTSUPP; - goto out; - } - if (test_bit(IPS_USERSPACE_HELPER_BIT, &ct->status)) { if (!cda[CTA_EXPECT_TIMEOUT]) { err = -EINVAL; goto out; diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index ce0c406f58a8..957374a234d4 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_INIT_POINTER(nf_loggers[pf], logger); + rcu_assign_pointer(nf_loggers[pf], logger); } 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_INIT_POINTER(nf_loggers[pf], logger); + rcu_assign_pointer(nf_loggers[pf], logger); mutex_unlock(&nf_log_mutex); return 0; } @@ -250,7 +250,7 @@ static int nf_log_proc_dostring(ctl_table *table, int write, mutex_unlock(&nf_log_mutex); return -ENOENT; } - RCU_INIT_POINTER(nf_loggers[tindex], logger); + rcu_assign_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 99ffd2885088..ce60cf0f6c11 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_INIT_POINTER(queue_handler[pf], qh); + rcu_assign_pointer(queue_handler[pf], qh); ret = 0; } mutex_unlock(&queue_handler_mutex); @@ -203,6 +203,27 @@ err: return status; } +#ifdef CONFIG_BRIDGE_NETFILTER +/* When called from bridge netfilter, skb->data must point to MAC header + * before calling skb_gso_segment(). Else, original MAC header is lost + * and segmented skbs will be sent to wrong destination. + */ +static void nf_bridge_adjust_skb_data(struct sk_buff *skb) +{ + if (skb->nf_bridge) + __skb_push(skb, skb->network_header - skb->mac_header); +} + +static void nf_bridge_adjust_segmented_data(struct sk_buff *skb) +{ + if (skb->nf_bridge) + __skb_pull(skb, skb->network_header - skb->mac_header); +} +#else +#define nf_bridge_adjust_skb_data(s) do {} while (0) +#define nf_bridge_adjust_segmented_data(s) do {} while (0) +#endif + int nf_queue(struct sk_buff *skb, struct list_head *elem, u_int8_t pf, unsigned int hook, @@ -212,7 +233,7 @@ int nf_queue(struct sk_buff *skb, unsigned int queuenum) { struct sk_buff *segs; - int err; + int err = -EINVAL; unsigned int queued; if (!skb_is_gso(skb)) @@ -228,23 +249,25 @@ int nf_queue(struct sk_buff *skb, break; } + nf_bridge_adjust_skb_data(skb); segs = skb_gso_segment(skb, 0); /* Does not use PTR_ERR to limit the number of error codes that can be * returned by nf_queue. For instance, callers rely on -ECANCELED to mean * 'ignore this hook'. */ if (IS_ERR(segs)) - return -EINVAL; - + goto out_err; queued = 0; err = 0; do { struct sk_buff *nskb = segs->next; segs->next = NULL; - if (err == 0) + if (err == 0) { + nf_bridge_adjust_segmented_data(segs); err = __nf_queue(segs, elem, pf, hook, indev, outdev, okfn, queuenum); + } if (err == 0) queued++; else @@ -252,11 +275,12 @@ int nf_queue(struct sk_buff *skb, segs = nskb; } while (segs); - /* also free orig skb if only some segments were queued */ - if (unlikely(err && queued)) - err = 0; - if (err == 0) + if (queued) { kfree_skb(skb); + return 0; + } + out_err: + nf_bridge_adjust_segmented_data(skb); return err; } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index c879c1a2370e..4d70785b953d 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_INIT_POINTER(subsys_table[n->subsys_id], n); + rcu_assign_pointer(subsys_table[n->subsys_id], n); nfnl_unlock(); return 0; @@ -130,7 +130,7 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) const struct nfnetlink_subsystem *ss; int type, err; - if (security_netlink_recv(skb, CAP_NET_ADMIN)) + if (!capable(CAP_NET_ADMIN)) return -EPERM; /* All the messages must at least contain nfgenmsg */ @@ -210,7 +210,7 @@ static int __net_init nfnetlink_net_init(struct net *net) if (!nfnl) return -ENOMEM; net->nfnl_stash = nfnl; - RCU_INIT_POINTER(net->nfnl, nfnl); + rcu_assign_pointer(net->nfnl, nfnl); return 0; } diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 8e87123f1373..0221d10de75a 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -62,8 +62,8 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par) int ret = 0; u8 proto; - if (info->flags & ~(XT_CT_NOTRACK | XT_CT_USERSPACE_HELPER)) - return -EOPNOTSUPP; + if (info->flags & ~XT_CT_NOTRACK) + return -EINVAL; if (info->flags & XT_CT_NOTRACK) { ct = nf_ct_untracked_get(); @@ -92,9 +92,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par) GFP_KERNEL)) goto err3; - if (info->flags & XT_CT_USERSPACE_HELPER) { - __set_bit(IPS_USERSPACE_HELPER_BIT, &ct->status); - } else if (info->helper[0]) { + if (info->helper[0]) { ret = -ENOENT; proto = xt_ct_find_proto(par); if (!proto) { diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 3aae66facf9f..4d5057902839 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -152,9 +152,10 @@ tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info) fl6.flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) | (iph->flow_lbl[1] << 8) | iph->flow_lbl[2]; dst = ip6_route_output(net, NULL, &fl6); - if (dst == NULL) + if (dst->error) { + dst_release(dst); return false; - + } skb_dst_drop(skb); skb_dst_set(skb, dst); skb->dev = dst->dev; diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 8e4992101875..d95f9c963cde 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -445,7 +445,6 @@ hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo, { __be16 _ports[2], *ports; u8 nexthdr; - __be16 frag_off; int poff; memset(dst, 0, sizeof(*dst)); @@ -466,6 +465,9 @@ hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo, break; #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) case NFPROTO_IPV6: + { + __be16 frag_off; + if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_DIP) { memcpy(&dst->ip6.dst, &ipv6_hdr(skb)->daddr, sizeof(dst->ip6.dst)); @@ -485,6 +487,7 @@ hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo, if ((int)protoff < 0) return -1; break; + } #endif default: BUG(); diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index 38204112b9f4..d8d424337550 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_INIT_POINTER(netlbl_domhsh, hsh_tbl); + rcu_assign_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_INIT_POINTER(netlbl_domhsh_def, entry); + rcu_assign_pointer(netlbl_domhsh_def, entry); } if (entry->type == NETLBL_NLTYPE_ADDRSELECT) { diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 4b5fa0fe78fd..e7ff694f1049 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_INIT_POINTER(netlbl_unlhsh_def, iface); + rcu_assign_pointer(netlbl_unlhsh_def, iface); } spin_unlock(&netlbl_unlhsh_lock); @@ -1447,11 +1447,9 @@ int __init netlbl_unlabel_init(u32 size) for (iter = 0; iter < hsh_tbl->size; iter++) INIT_LIST_HEAD(&hsh_tbl->tbl[iter]); - rcu_read_lock(); spin_lock(&netlbl_unlhsh_lock); - RCU_INIT_POINTER(netlbl_unlhsh, hsh_tbl); + rcu_assign_pointer(netlbl_unlhsh, hsh_tbl); spin_unlock(&netlbl_unlhsh_lock); - rcu_read_unlock(); register_netdevice_notifier(&netlbl_unlhsh_netdev_notifier); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index a403b618faa5..c29d2568c9e0 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -524,7 +524,7 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return -EOPNOTSUPP; if ((ops->flags & GENL_ADMIN_PERM) && - security_netlink_recv(skb, CAP_NET_ADMIN)) + !capable(CAP_NET_ADMIN)) return -EPERM; if (nlh->nlmsg_flags & NLM_F_DUMP) { diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 2725d1bdf291..48badffaafc1 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 Nicira Networks. + * Copyright (c) 2007-2012 Nicira Networks. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -145,9 +145,16 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh, inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb, *addr, new_addr, 1); } else if (nh->protocol == IPPROTO_UDP) { - if (likely(transport_len >= sizeof(struct udphdr))) - inet_proto_csum_replace4(&udp_hdr(skb)->check, skb, - *addr, new_addr, 1); + if (likely(transport_len >= sizeof(struct udphdr))) { + struct udphdr *uh = udp_hdr(skb); + + if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { + inet_proto_csum_replace4(&uh->check, skb, + *addr, new_addr, 1); + if (!uh->check) + uh->check = CSUM_MANGLED_0; + } + } } csum_replace4(&nh->check, *addr, new_addr); @@ -197,8 +204,22 @@ static void set_tp_port(struct sk_buff *skb, __be16 *port, skb->rxhash = 0; } -static int set_udp_port(struct sk_buff *skb, - const struct ovs_key_udp *udp_port_key) +static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port) +{ + struct udphdr *uh = udp_hdr(skb); + + if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) { + set_tp_port(skb, port, new_port, &uh->check); + + if (!uh->check) + uh->check = CSUM_MANGLED_0; + } else { + *port = new_port; + skb->rxhash = 0; + } +} + +static int set_udp(struct sk_buff *skb, const struct ovs_key_udp *udp_port_key) { struct udphdr *uh; int err; @@ -210,16 +231,15 @@ static int set_udp_port(struct sk_buff *skb, uh = udp_hdr(skb); if (udp_port_key->udp_src != uh->source) - set_tp_port(skb, &uh->source, udp_port_key->udp_src, &uh->check); + set_udp_port(skb, &uh->source, udp_port_key->udp_src); if (udp_port_key->udp_dst != uh->dest) - set_tp_port(skb, &uh->dest, udp_port_key->udp_dst, &uh->check); + set_udp_port(skb, &uh->dest, udp_port_key->udp_dst); return 0; } -static int set_tcp_port(struct sk_buff *skb, - const struct ovs_key_tcp *tcp_port_key) +static int set_tcp(struct sk_buff *skb, const struct ovs_key_tcp *tcp_port_key) { struct tcphdr *th; int err; @@ -328,11 +348,11 @@ static int execute_set_action(struct sk_buff *skb, break; case OVS_KEY_ATTR_TCP: - err = set_tcp_port(skb, nla_data(nested_attr)); + err = set_tcp(skb, nla_data(nested_attr)); break; case OVS_KEY_ATTR_UDP: - err = set_udp_port(skb, nla_data(nested_attr)); + err = set_udp(skb, nla_data(nested_attr)); break; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 9a2725114e99..2c030505b335 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 Nicira Networks. + * Copyright (c) 2007-2012 Nicira Networks. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -36,7 +36,6 @@ #include <linux/rcupdate.h> #include <linux/tcp.h> #include <linux/udp.h> -#include <linux/version.h> #include <linux/ethtool.h> #include <linux/wait.h> #include <asm/system.h> @@ -1397,9 +1396,8 @@ static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) int i = 0; list_for_each_entry(dp, &dps, list_node) { - if (i < skip) - continue; - if (ovs_dp_cmd_fill_info(dp, skb, NETLINK_CB(cb->skb).pid, + if (i >= skip && + ovs_dp_cmd_fill_info(dp, skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, OVS_DP_CMD_NEW) < 0) break; @@ -1523,6 +1521,9 @@ static struct vport *lookup_vport(struct ovs_header *ovs_header, vport = ovs_vport_locate(nla_data(a[OVS_VPORT_ATTR_NAME])); if (!vport) return ERR_PTR(-ENODEV); + if (ovs_header->dp_ifindex && + ovs_header->dp_ifindex != get_dpifindex(vport->dp)) + return ERR_PTR(-ENODEV); return vport; } else if (a[OVS_VPORT_ATTR_PORT_NO]) { u32 port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]); diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 5b9f884b7055..c73370cc1f02 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -25,7 +25,6 @@ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/u64_stats_sync.h> -#include <linux/version.h> #include "flow.h" diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index fe7f020a843e..1252c3081ef1 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -32,7 +32,6 @@ #include <linux/in.h> #include <linux/rcupdate.h> #include <linux/if_arp.h> -#include <linux/if_ether.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/tcp.h> diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 8fc28b86f2b3..322b8d206693 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -23,7 +23,6 @@ #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/skbuff.h> -#include <linux/version.h> #include "datapath.h" #include "vport-internal_dev.h" diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 7f0ef3794c51..6c066ba25dc7 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -27,7 +27,6 @@ #include <linux/rcupdate.h> #include <linux/rtnetlink.h> #include <linux/compat.h> -#include <linux/version.h> #include "vport.h" #include "vport-internal_dev.h" diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index bf10ea8fbbf9..d65f699fbf34 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_INIT_POINTER(proto_tab[protocol], pp); + rcu_assign_pointer(proto_tab[protocol], pp); mutex_unlock(&proto_tab_lock); return err; diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index c5827614376b..9b9a85ecc4c7 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -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_INIT_POINTER(routes->table[daddr], dev); + rcu_assign_pointer(routes->table[daddr], dev); dev_hold(dev); err = 0; } diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 3f8d0b1603b9..4c7eff30dfa9 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -680,7 +680,7 @@ int pn_sock_bind_res(struct sock *sk, u8 res) mutex_lock(&resource_mutex); if (pnres.sk[res] == NULL) { sock_hold(sk); - RCU_INIT_POINTER(pnres.sk[res], sk); + rcu_assign_pointer(pnres.sk[res], sk); ret = 0; } mutex_unlock(&resource_mutex); diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index bb6ad81b671d..424ff622ab5f 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -68,7 +68,6 @@ static int rds_release(struct socket *sock) { struct sock *sk = sock->sk; struct rds_sock *rs; - unsigned long flags; if (!sk) goto out; @@ -94,10 +93,10 @@ static int rds_release(struct socket *sock) rds_rdma_drop_keys(rs); rds_notify_queue_get(rs, NULL); - spin_lock_irqsave(&rds_sock_lock, flags); + spin_lock_bh(&rds_sock_lock); list_del_init(&rs->rs_item); rds_sock_count--; - spin_unlock_irqrestore(&rds_sock_lock, flags); + spin_unlock_bh(&rds_sock_lock); rds_trans_put(rs->rs_transport); @@ -409,7 +408,6 @@ static const struct proto_ops rds_proto_ops = { static int __rds_create(struct socket *sock, struct sock *sk, int protocol) { - unsigned long flags; struct rds_sock *rs; sock_init_data(sock, sk); @@ -426,10 +424,10 @@ static int __rds_create(struct socket *sock, struct sock *sk, int protocol) spin_lock_init(&rs->rs_rdma_lock); rs->rs_rdma_keys = RB_ROOT; - spin_lock_irqsave(&rds_sock_lock, flags); + spin_lock_bh(&rds_sock_lock); list_add_tail(&rs->rs_item, &rds_sock_list); rds_sock_count++; - spin_unlock_irqrestore(&rds_sock_lock, flags); + spin_unlock_bh(&rds_sock_lock); return 0; } @@ -471,12 +469,11 @@ static void rds_sock_inc_info(struct socket *sock, unsigned int len, { struct rds_sock *rs; struct rds_incoming *inc; - unsigned long flags; unsigned int total = 0; len /= sizeof(struct rds_info_message); - spin_lock_irqsave(&rds_sock_lock, flags); + spin_lock_bh(&rds_sock_lock); list_for_each_entry(rs, &rds_sock_list, rs_item) { read_lock(&rs->rs_recv_lock); @@ -492,7 +489,7 @@ static void rds_sock_inc_info(struct socket *sock, unsigned int len, read_unlock(&rs->rs_recv_lock); } - spin_unlock_irqrestore(&rds_sock_lock, flags); + spin_unlock_bh(&rds_sock_lock); lens->nr = total; lens->each = sizeof(struct rds_info_message); @@ -504,11 +501,10 @@ static void rds_sock_info(struct socket *sock, unsigned int len, { struct rds_info_socket sinfo; struct rds_sock *rs; - unsigned long flags; len /= sizeof(struct rds_info_socket); - spin_lock_irqsave(&rds_sock_lock, flags); + spin_lock_bh(&rds_sock_lock); if (len < rds_sock_count) goto out; @@ -529,7 +525,7 @@ out: lens->nr = rds_sock_count; lens->each = sizeof(struct rds_info_socket); - spin_unlock_irqrestore(&rds_sock_lock, flags); + spin_unlock_bh(&rds_sock_lock); } static void rds_exit(void) diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index 4e1de171866c..a817705ce2d0 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -477,17 +477,6 @@ void rds_iw_sync_mr(void *trans_private, int direction) } } -static inline unsigned int rds_iw_flush_goal(struct rds_iw_mr_pool *pool, int free_all) -{ - unsigned int item_count; - - item_count = atomic_read(&pool->item_count); - if (free_all) - return item_count; - - return 0; -} - /* * Flush our pool of MRs. * At a minimum, all currently unused MRs are unmapped. @@ -500,7 +489,7 @@ 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, unpinned = 0, free_goal; + unsigned int nfreed = 0, ncleaned = 0, unpinned = 0; int ret = 0; rds_iw_stats_inc(s_iw_rdma_mr_pool_flush); @@ -514,8 +503,6 @@ static int rds_iw_flush_mr_pool(struct rds_iw_mr_pool *pool, int free_all) list_splice_init(&pool->clean_list, &kill_list); spin_unlock_irqrestore(&pool->list_lock, flags); - free_goal = rds_iw_flush_goal(pool, free_all); - /* Batched invalidate of dirty MRs. * For FMR based MRs, the mappings on the unmap list are * actually members of an ibmr (ibmr->mapping). They either diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c index 4cba13e46ffd..ae3a035f5390 100644 --- a/net/rxrpc/ar-key.c +++ b/net/rxrpc/ar-key.c @@ -232,7 +232,7 @@ static int rxrpc_krb5_decode_principal(struct krb5_principal *princ, if (toklen <= (n_parts + 1) * 4) return -EINVAL; - princ->name_parts = kcalloc(sizeof(char *), n_parts, GFP_KERNEL); + princ->name_parts = kcalloc(n_parts, sizeof(char *), GFP_KERNEL); if (!princ->name_parts) return -ENOMEM; @@ -355,7 +355,7 @@ static int rxrpc_krb5_decode_tagged_array(struct krb5_tagged_data **_td, _debug("n_elem %d", n_elem); - td = kcalloc(sizeof(struct krb5_tagged_data), n_elem, + td = kcalloc(n_elem, sizeof(struct krb5_tagged_data), GFP_KERNEL); if (!td) return -ENOMEM; diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index e465064d39a3..7e267d7b9c75 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -148,8 +148,7 @@ struct choke_skb_cb { static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) < - sizeof(struct qdisc_skb_cb) + sizeof(struct choke_skb_cb)); + qdisc_cb_private_validate(skb, sizeof(struct choke_skb_cb)); return (struct choke_skb_cb *)qdisc_skb_cb(skb)->data; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index e7e1d0b57b3d..5da548fa7ae9 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -130,8 +130,7 @@ struct netem_skb_cb { static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) < - sizeof(struct qdisc_skb_cb) + sizeof(struct netem_skb_cb)); + qdisc_cb_private_validate(skb, sizeof(struct netem_skb_cb)); return (struct netem_skb_cb *)qdisc_skb_cb(skb)->data; } @@ -419,7 +418,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) cb = netem_skb_cb(skb); if (q->gap == 0 || /* not doing reordering */ - q->counter < q->gap || /* inside last reordering gap */ + q->counter < q->gap - 1 || /* inside last reordering gap */ q->reorder < get_crandom(&q->reorder_cor)) { psched_time_t now; psched_tdiff_t delay; @@ -502,9 +501,8 @@ tfifo_dequeue: /* if more time remaining? */ if (cb->time_to_send <= psched_get_time()) { - skb = qdisc_dequeue_tail(sch); - if (unlikely(!skb)) - goto qdisc_dequeue; + __skb_unlink(skb, &sch->q); + sch->qstats.backlog -= qdisc_pkt_len(skb); #ifdef CONFIG_NET_CLS_ACT /* @@ -540,7 +538,6 @@ deliver: qdisc_watchdog_schedule(&q->watchdog, cb->time_to_send); } -qdisc_dequeue: if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); if (skb) diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 96e42cae4c7a..d7eea99333e9 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -94,8 +94,7 @@ struct sfb_skb_cb { static inline struct sfb_skb_cb *sfb_skb_cb(const struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) < - sizeof(struct qdisc_skb_cb) + sizeof(struct sfb_skb_cb)); + qdisc_cb_private_validate(skb, sizeof(struct sfb_skb_cb)); return (struct sfb_skb_cb *)qdisc_skb_cb(skb)->data; } diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 0a7964009e8c..02a21abea65e 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -24,6 +24,7 @@ #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/flow_keys.h> +#include <net/red.h> /* Stochastic Fairness Queuing algorithm. @@ -108,24 +109,30 @@ struct sfq_slot { struct sfq_head dep; /* anchor in dep[] chains */ unsigned short hash; /* hash value (index in ht[]) */ short allot; /* credit for this slot */ + + unsigned int backlog; + struct red_vars vars; }; struct sfq_sched_data { /* frequently used fields */ int limit; /* limit of total number of packets in this qdisc */ unsigned int divisor; /* number of slots in hash table */ - unsigned int maxflows; /* number of flows in flows array */ - int headdrop; - int maxdepth; /* limit of packets per flow */ + u8 headdrop; + u8 maxdepth; /* limit of packets per flow */ u32 perturbation; - struct tcf_proto *filter_list; - sfq_index cur_depth; /* depth of longest slot */ + u8 cur_depth; /* depth of longest slot */ + u8 flags; unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */ - struct sfq_slot *tail; /* current slot in round */ + struct tcf_proto *filter_list; sfq_index *ht; /* Hash table ('divisor' slots) */ struct sfq_slot *slots; /* Flows table ('maxflows' entries) */ + struct red_parms *red_parms; + struct tc_sfqred_stats stats; + struct sfq_slot *tail; /* current slot in round */ + struct sfq_head dep[SFQ_MAX_DEPTH + 1]; /* Linked lists of slots, indexed by depth * dep[0] : list of unused flows @@ -133,6 +140,7 @@ struct sfq_sched_data { * dep[X] : list of flows with X packets */ + unsigned int maxflows; /* number of flows in flows array */ int perturb_period; unsigned int quantum; /* Allotment per round: MUST BE >= MTU */ struct timer_list perturb_timer; @@ -158,9 +166,8 @@ struct sfq_skb_cb { static inline struct sfq_skb_cb *sfq_skb_cb(const struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) < - sizeof(struct qdisc_skb_cb) + sizeof(struct sfq_skb_cb)); - return (struct sfq_skb_cb *)qdisc_skb_cb(skb)->data; + qdisc_cb_private_validate(skb, sizeof(struct sfq_skb_cb)); + return (struct sfq_skb_cb *)qdisc_skb_cb(skb)->data; } static unsigned int sfq_hash(const struct sfq_sched_data *q, @@ -321,6 +328,7 @@ static unsigned int sfq_drop(struct Qdisc *sch) drop: skb = q->headdrop ? slot_dequeue_head(slot) : slot_dequeue_tail(slot); len = qdisc_pkt_len(skb); + slot->backlog -= len; sfq_dec(q, x); kfree_skb(skb); sch->q.qlen--; @@ -341,6 +349,23 @@ drop: return 0; } +/* Is ECN parameter configured */ +static int sfq_prob_mark(const struct sfq_sched_data *q) +{ + return q->flags & TC_RED_ECN; +} + +/* Should packets over max threshold just be marked */ +static int sfq_hard_mark(const struct sfq_sched_data *q) +{ + return (q->flags & (TC_RED_ECN | TC_RED_HARDDROP)) == TC_RED_ECN; +} + +static int sfq_headdrop(const struct sfq_sched_data *q) +{ + return q->headdrop; +} + static int sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) { @@ -349,6 +374,8 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) sfq_index x, qlen; struct sfq_slot *slot; int uninitialized_var(ret); + struct sk_buff *head; + int delta; hash = sfq_classify(skb, sch, &ret); if (hash == 0) { @@ -368,34 +395,90 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) q->ht[hash] = x; slot = &q->slots[x]; slot->hash = hash; + slot->backlog = 0; /* should already be 0 anyway... */ + red_set_vars(&slot->vars); + goto enqueue; } + if (q->red_parms) { + slot->vars.qavg = red_calc_qavg_no_idle_time(q->red_parms, + &slot->vars, + slot->backlog); + switch (red_action(q->red_parms, + &slot->vars, + slot->vars.qavg)) { + case RED_DONT_MARK: + break; - if (slot->qlen >= q->maxdepth) { - struct sk_buff *head; + case RED_PROB_MARK: + sch->qstats.overlimits++; + if (sfq_prob_mark(q)) { + /* We know we have at least one packet in queue */ + if (sfq_headdrop(q) && + INET_ECN_set_ce(slot->skblist_next)) { + q->stats.prob_mark_head++; + break; + } + if (INET_ECN_set_ce(skb)) { + q->stats.prob_mark++; + break; + } + } + q->stats.prob_drop++; + goto congestion_drop; + + case RED_HARD_MARK: + sch->qstats.overlimits++; + if (sfq_hard_mark(q)) { + /* We know we have at least one packet in queue */ + if (sfq_headdrop(q) && + INET_ECN_set_ce(slot->skblist_next)) { + q->stats.forced_mark_head++; + break; + } + if (INET_ECN_set_ce(skb)) { + q->stats.forced_mark++; + break; + } + } + q->stats.forced_drop++; + goto congestion_drop; + } + } - if (!q->headdrop) + if (slot->qlen >= q->maxdepth) { +congestion_drop: + if (!sfq_headdrop(q)) return qdisc_drop(skb, sch); + /* We know we have at least one packet in queue */ head = slot_dequeue_head(slot); - sch->qstats.backlog -= qdisc_pkt_len(head); + delta = qdisc_pkt_len(head) - qdisc_pkt_len(skb); + sch->qstats.backlog -= delta; + slot->backlog -= delta; qdisc_drop(head, sch); - sch->qstats.backlog += qdisc_pkt_len(skb); slot_queue_add(slot, skb); return NET_XMIT_CN; } +enqueue: sch->qstats.backlog += qdisc_pkt_len(skb); + slot->backlog += qdisc_pkt_len(skb); slot_queue_add(slot, skb); sfq_inc(q, x); if (slot->qlen == 1) { /* The flow is new */ if (q->tail == NULL) { /* It is the first flow */ slot->next = x; - q->tail = slot; } else { slot->next = q->tail->next; q->tail->next = x; } + /* We put this flow at the end of our flow list. + * This might sound unfair for a new flow to wait after old ones, + * but we could endup servicing new flows only, and freeze old ones. + */ + q->tail = slot; + /* We could use a bigger initial quantum for new flows */ slot->allot = q->scaled_quantum; } if (++sch->q.qlen <= q->limit) @@ -439,7 +522,7 @@ next_slot: qdisc_bstats_update(sch, skb); sch->q.qlen--; sch->qstats.backlog -= qdisc_pkt_len(skb); - + slot->backlog -= qdisc_pkt_len(skb); /* Is the slot empty? */ if (slot->qlen == 0) { q->ht[slot->hash] = SFQ_EMPTY_SLOT; @@ -490,6 +573,8 @@ static void sfq_rehash(struct Qdisc *sch) sfq_dec(q, i); __skb_queue_tail(&list, skb); } + slot->backlog = 0; + red_set_vars(&slot->vars); q->ht[slot->hash] = SFQ_EMPTY_SLOT; } q->tail = NULL; @@ -514,6 +599,11 @@ drop: sch->qstats.backlog -= qdisc_pkt_len(skb); if (slot->qlen >= q->maxdepth) goto drop; slot_queue_add(slot, skb); + if (q->red_parms) + slot->vars.qavg = red_calc_qavg(q->red_parms, + &slot->vars, + slot->backlog); + slot->backlog += qdisc_pkt_len(skb); sfq_inc(q, x); if (slot->qlen == 1) { /* The flow is new */ if (q->tail == NULL) { /* It is the first flow */ @@ -552,6 +642,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) struct tc_sfq_qopt *ctl = nla_data(opt); struct tc_sfq_qopt_v1 *ctl_v1 = NULL; unsigned int qlen; + struct red_parms *p = NULL; if (opt->nla_len < nla_attr_size(sizeof(*ctl))) return -EINVAL; @@ -560,7 +651,11 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) if (ctl->divisor && (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536)) return -EINVAL; - + if (ctl_v1 && ctl_v1->qth_min) { + p = kmalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + } sch_tree_lock(sch); if (ctl->quantum) { q->quantum = ctl->quantum; @@ -576,6 +671,16 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) if (ctl_v1) { if (ctl_v1->depth) q->maxdepth = min_t(u32, ctl_v1->depth, SFQ_MAX_DEPTH); + if (p) { + swap(q->red_parms, p); + red_set_parms(q->red_parms, + ctl_v1->qth_min, ctl_v1->qth_max, + ctl_v1->Wlog, + ctl_v1->Plog, ctl_v1->Scell_log, + NULL, + ctl_v1->max_P); + } + q->flags = ctl_v1->flags; q->headdrop = ctl_v1->headdrop; } if (ctl->limit) { @@ -594,6 +699,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) q->perturbation = net_random(); } sch_tree_unlock(sch); + kfree(p); return 0; } @@ -625,6 +731,7 @@ static void sfq_destroy(struct Qdisc *sch) del_timer_sync(&q->perturb_timer); sfq_free(q->ht); sfq_free(q->slots); + kfree(q->red_parms); } static int sfq_init(struct Qdisc *sch, struct nlattr *opt) @@ -683,6 +790,7 @@ static int sfq_dump(struct Qdisc *sch, struct sk_buff *skb) struct sfq_sched_data *q = qdisc_priv(sch); unsigned char *b = skb_tail_pointer(skb); struct tc_sfq_qopt_v1 opt; + struct red_parms *p = q->red_parms; memset(&opt, 0, sizeof(opt)); opt.v0.quantum = q->quantum; @@ -693,6 +801,17 @@ static int sfq_dump(struct Qdisc *sch, struct sk_buff *skb) opt.depth = q->maxdepth; opt.headdrop = q->headdrop; + if (p) { + opt.qth_min = p->qth_min >> p->Wlog; + opt.qth_max = p->qth_max >> p->Wlog; + opt.Wlog = p->Wlog; + opt.Plog = p->Plog; + opt.Scell_log = p->Scell_log; + opt.max_P = p->max_P; + } + memcpy(&opt.stats, &q->stats, sizeof(opt.stats)); + opt.flags = q->flags; + NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); return skb->len; @@ -747,15 +866,13 @@ static int sfq_dump_class_stats(struct Qdisc *sch, unsigned long cl, sfq_index idx = q->ht[cl - 1]; struct gnet_stats_queue qs = { 0 }; struct tc_sfq_xstats xstats = { 0 }; - struct sk_buff *skb; if (idx != SFQ_EMPTY_SLOT) { const struct sfq_slot *slot = &q->slots[idx]; xstats.allot = slot->allot << SFQ_ALLOT_SHIFT; qs.qlen = slot->qlen; - slot_queue_walk(slot, skb) - qs.backlog += qdisc_pkt_len(skb); + qs.backlog = slot->backlog; } if (gnet_stats_copy_queue(d, &qs) < 0) return -1; diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index c8cc24e282c3..68a385d7c3bd 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -415,7 +415,7 @@ static void sctp_endpoint_bh_rcv(struct work_struct *work) sctp_subtype_t subtype; sctp_state_t state; int error = 0; - int first_time = 1; /* is this the first time through the looop */ + int first_time = 1; /* is this the first time through the loop */ if (ep->base.dead) return; diff --git a/net/socket.c b/net/socket.c index e56162cd65b0..28a96af484b4 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2492,7 +2492,7 @@ int sock_register(const struct net_proto_family *ops) lockdep_is_held(&net_family_lock))) err = -EEXIST; else { - RCU_INIT_POINTER(net_families[ops->family], ops); + rcu_assign_pointer(net_families[ops->family], ops); err = 0; } spin_unlock(&net_family_lock); diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index e010a015d996..75762f346975 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -41,15 +41,17 @@ EXPORT_SYMBOL_GPL(rpc_lookup_cred); /* * Public call interface for looking up machine creds. */ -struct rpc_cred *rpc_lookup_machine_cred(void) +struct rpc_cred *rpc_lookup_machine_cred(const char *service_name) { struct auth_cred acred = { .uid = RPC_MACHINE_CRED_USERID, .gid = RPC_MACHINE_CRED_GROUPID, + .principal = service_name, .machine_cred = 1, }; - dprintk("RPC: looking up machine cred\n"); + dprintk("RPC: looking up machine cred for service %s\n", + service_name); return generic_auth.au_ops->lookup_cred(&generic_auth, &acred, 0); } EXPORT_SYMBOL_GPL(rpc_lookup_machine_cred); @@ -90,6 +92,7 @@ generic_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) if (gcred->acred.group_info != NULL) get_group_info(gcred->acred.group_info); gcred->acred.machine_cred = acred->machine_cred; + gcred->acred.principal = acred->principal; dprintk("RPC: allocated %s cred %p for uid %d gid %d\n", gcred->acred.machine_cred ? "machine" : "generic", @@ -121,6 +124,17 @@ generic_destroy_cred(struct rpc_cred *cred) call_rcu(&cred->cr_rcu, generic_free_cred_callback); } +static int +machine_cred_match(struct auth_cred *acred, struct generic_cred *gcred, int flags) +{ + if (!gcred->acred.machine_cred || + gcred->acred.principal != acred->principal || + gcred->acred.uid != acred->uid || + gcred->acred.gid != acred->gid) + return 0; + return 1; +} + /* * Match credentials against current process creds. */ @@ -130,9 +144,12 @@ generic_match(struct auth_cred *acred, struct rpc_cred *cred, int flags) struct generic_cred *gcred = container_of(cred, struct generic_cred, gc_base); int i; + if (acred->machine_cred) + return machine_cred_match(acred, gcred, flags); + if (gcred->acred.uid != acred->uid || gcred->acred.gid != acred->gid || - gcred->acred.machine_cred != acred->machine_cred) + gcred->acred.machine_cred != 0) goto out_nomatch; /* Optimisation in the case where pointers are identical... */ diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index afb56553dfe7..affa631ac1ab 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_INIT_POINTER(gss_cred->gc_ctx, ctx); + rcu_assign_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); @@ -392,7 +392,8 @@ static void gss_encode_v0_msg(struct gss_upcall_msg *gss_msg) } static void gss_encode_v1_msg(struct gss_upcall_msg *gss_msg, - struct rpc_clnt *clnt, int machine_cred) + struct rpc_clnt *clnt, + const char *service_name) { struct gss_api_mech *mech = gss_msg->auth->mech; char *p = gss_msg->databuf; @@ -407,12 +408,8 @@ static void gss_encode_v1_msg(struct gss_upcall_msg *gss_msg, p += len; gss_msg->msg.len += len; } - if (machine_cred) { - len = sprintf(p, "service=* "); - p += len; - gss_msg->msg.len += len; - } else if (!strcmp(clnt->cl_program->name, "nfs4_cb")) { - len = sprintf(p, "service=nfs "); + if (service_name != NULL) { + len = sprintf(p, "service=%s ", service_name); p += len; gss_msg->msg.len += len; } @@ -429,17 +426,18 @@ static void gss_encode_v1_msg(struct gss_upcall_msg *gss_msg, } static void gss_encode_msg(struct gss_upcall_msg *gss_msg, - struct rpc_clnt *clnt, int machine_cred) + struct rpc_clnt *clnt, + const char *service_name) { if (pipe_version == 0) gss_encode_v0_msg(gss_msg); else /* pipe_version == 1 */ - gss_encode_v1_msg(gss_msg, clnt, machine_cred); + gss_encode_v1_msg(gss_msg, clnt, service_name); } -static inline struct gss_upcall_msg * -gss_alloc_msg(struct gss_auth *gss_auth, uid_t uid, struct rpc_clnt *clnt, - int machine_cred) +static struct gss_upcall_msg * +gss_alloc_msg(struct gss_auth *gss_auth, struct rpc_clnt *clnt, + uid_t uid, const char *service_name) { struct gss_upcall_msg *gss_msg; int vers; @@ -459,7 +457,7 @@ gss_alloc_msg(struct gss_auth *gss_auth, uid_t uid, struct rpc_clnt *clnt, atomic_set(&gss_msg->count, 1); gss_msg->uid = uid; gss_msg->auth = gss_auth; - gss_encode_msg(gss_msg, clnt, machine_cred); + gss_encode_msg(gss_msg, clnt, service_name); return gss_msg; } @@ -471,7 +469,7 @@ gss_setup_upcall(struct rpc_clnt *clnt, struct gss_auth *gss_auth, struct rpc_cr struct gss_upcall_msg *gss_new, *gss_msg; uid_t uid = cred->cr_uid; - gss_new = gss_alloc_msg(gss_auth, uid, clnt, gss_cred->gc_machine_cred); + gss_new = gss_alloc_msg(gss_auth, clnt, uid, gss_cred->gc_principal); if (IS_ERR(gss_new)) return gss_new; gss_msg = gss_add_msg(gss_new); @@ -995,7 +993,9 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) */ cred->gc_base.cr_flags = 1UL << RPCAUTH_CRED_NEW; cred->gc_service = gss_auth->service; - cred->gc_machine_cred = acred->machine_cred; + cred->gc_principal = NULL; + if (acred->machine_cred) + cred->gc_principal = acred->principal; kref_get(&gss_auth->kref); return &cred->gc_base; @@ -1030,7 +1030,12 @@ gss_match(struct auth_cred *acred, struct rpc_cred *rc, int flags) if (!test_bit(RPCAUTH_CRED_UPTODATE, &rc->cr_flags)) return 0; out: - if (acred->machine_cred != gss_cred->gc_machine_cred) + if (acred->principal != NULL) { + if (gss_cred->gc_principal == NULL) + return 0; + return strcmp(acred->principal, gss_cred->gc_principal) == 0; + } + if (gss_cred->gc_principal != NULL) return 0; return rc->cr_uid == acred->uid; } @@ -1104,7 +1109,8 @@ static int gss_renew_cred(struct rpc_task *task) struct rpc_auth *auth = oldcred->cr_auth; struct auth_cred acred = { .uid = oldcred->cr_uid, - .machine_cred = gss_cred->gc_machine_cred, + .principal = gss_cred->gc_principal, + .machine_cred = (gss_cred->gc_principal != NULL ? 1 : 0), }; struct rpc_cred *new; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 03b56bc3b659..465df9ae1046 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1641,6 +1641,7 @@ int cache_register_net(struct cache_detail *cd, struct net *net) sunrpc_destroy_cache_detail(cd); return ret; } +EXPORT_SYMBOL_GPL(cache_register_net); int cache_register(struct cache_detail *cd) { @@ -1653,6 +1654,7 @@ void cache_unregister_net(struct cache_detail *cd, struct net *net) remove_cache_proc_entries(cd, net); sunrpc_destroy_cache_detail(cd); } +EXPORT_SYMBOL_GPL(cache_unregister_net); void cache_unregister(struct cache_detail *cd) { diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 00a1a2acd587..3341d8962786 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -18,6 +18,7 @@ #include <linux/smp.h> #include <linux/spinlock.h> #include <linux/mutex.h> +#include <linux/freezer.h> #include <linux/sunrpc/clnt.h> @@ -231,7 +232,7 @@ static int rpc_wait_bit_killable(void *word) { if (fatal_signal_pending(current)) return -ERESTARTSYS; - schedule(); + freezable_schedule(); return 0; } diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 9d01d46b05f3..e4aabc02368b 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -167,6 +167,7 @@ svc_pool_map_alloc_arrays(struct svc_pool_map *m, unsigned int maxpools) fail_free: kfree(m->to_pool); + m->to_pool = NULL; fail: return -ENOMEM; } @@ -285,9 +286,10 @@ svc_pool_map_put(void) mutex_lock(&svc_pool_map_mutex); if (!--m->count) { - m->mode = SVC_POOL_DEFAULT; kfree(m->to_pool); + m->to_pool = NULL; kfree(m->pool_to); + m->pool_to = NULL; m->npools = 0; } @@ -527,17 +529,20 @@ svc_destroy(struct svc_serv *serv) printk("svc_destroy: no threads for serv=%p!\n", serv); del_timer_sync(&serv->sv_temptimer); - - svc_close_all(&serv->sv_tempsocks); + /* + * The set of xprts (contained in the sv_tempsocks and + * sv_permsocks lists) is now constant, since it is modified + * only by accepting new sockets (done by service threads in + * svc_recv) or aging old ones (done by sv_temptimer), or + * configuration changes (excluded by whatever locking the + * caller is using--nfsd_mutex in the case of nfsd). So it's + * safe to traverse those lists and shut everything down: + */ + svc_close_all(serv); if (serv->sv_shutdown) serv->sv_shutdown(serv); - svc_close_all(&serv->sv_permsocks); - - BUG_ON(!list_empty(&serv->sv_permsocks)); - BUG_ON(!list_empty(&serv->sv_tempsocks)); - cache_clean_deferred(serv); if (svc_serv_is_pooled(serv)) @@ -683,8 +688,8 @@ found_pool: * Create or destroy enough new threads to make the number * of threads the given number. If `pool' is non-NULL, applies * only to threads in that pool, otherwise round-robins between - * all pools. Must be called with a svc_get() reference and - * the BKL or another lock to protect access to svc_serv fields. + * all pools. Caller must ensure that mutual exclusion between this and + * server startup or shutdown. * * Destroying threads relies on the service threads filling in * rqstp->rq_task, which only the nfs ones do. Assumes the serv diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 38649cfa4e81..74cb0d8e9ca1 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -22,6 +22,7 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt); static int svc_deferred_recv(struct svc_rqst *rqstp); static struct cache_deferred_req *svc_defer(struct cache_req *req); static void svc_age_temp_xprts(unsigned long closure); +static void svc_delete_xprt(struct svc_xprt *xprt); /* apparently the "standard" is that clients close * idle connections after 5 minutes, servers after @@ -147,8 +148,8 @@ EXPORT_SYMBOL_GPL(svc_xprt_put); * Called by transport drivers to initialize the transport independent * portion of the transport instance. */ -void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt, - struct svc_serv *serv) +void svc_xprt_init(struct net *net, struct svc_xprt_class *xcl, + struct svc_xprt *xprt, struct svc_serv *serv) { memset(xprt, 0, sizeof(*xprt)); xprt->xpt_class = xcl; @@ -163,7 +164,7 @@ void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt, spin_lock_init(&xprt->xpt_lock); set_bit(XPT_BUSY, &xprt->xpt_flags); rpc_init_wait_queue(&xprt->xpt_bc_pending, "xpt_bc_pending"); - xprt->xpt_net = get_net(&init_net); + xprt->xpt_net = get_net(net); } EXPORT_SYMBOL_GPL(svc_xprt_init); @@ -878,7 +879,7 @@ static void call_xpt_users(struct svc_xprt *xprt) /* * Remove a dead transport */ -void svc_delete_xprt(struct svc_xprt *xprt) +static void svc_delete_xprt(struct svc_xprt *xprt) { struct svc_serv *serv = xprt->xpt_server; struct svc_deferred_req *dr; @@ -893,14 +894,7 @@ void svc_delete_xprt(struct svc_xprt *xprt) spin_lock_bh(&serv->sv_lock); if (!test_and_set_bit(XPT_DETACHED, &xprt->xpt_flags)) list_del_init(&xprt->xpt_list); - /* - * The only time we're called while xpt_ready is still on a list - * is while the list itself is about to be destroyed (in - * svc_destroy). BUT svc_xprt_enqueue could still be attempting - * to add new entries to the sp_sockets list, so we can't leave - * a freed xprt on it. - */ - list_del_init(&xprt->xpt_ready); + BUG_ON(!list_empty(&xprt->xpt_ready)); if (test_bit(XPT_TEMP, &xprt->xpt_flags)) serv->sv_tmpcnt--; spin_unlock_bh(&serv->sv_lock); @@ -928,22 +922,48 @@ void svc_close_xprt(struct svc_xprt *xprt) } EXPORT_SYMBOL_GPL(svc_close_xprt); -void svc_close_all(struct list_head *xprt_list) +static void svc_close_list(struct list_head *xprt_list) +{ + struct svc_xprt *xprt; + + list_for_each_entry(xprt, xprt_list, xpt_list) { + set_bit(XPT_CLOSE, &xprt->xpt_flags); + set_bit(XPT_BUSY, &xprt->xpt_flags); + } +} + +void svc_close_all(struct svc_serv *serv) { + struct svc_pool *pool; struct svc_xprt *xprt; struct svc_xprt *tmp; + int i; + + svc_close_list(&serv->sv_tempsocks); + svc_close_list(&serv->sv_permsocks); + for (i = 0; i < serv->sv_nrpools; i++) { + pool = &serv->sv_pools[i]; + + spin_lock_bh(&pool->sp_lock); + while (!list_empty(&pool->sp_sockets)) { + xprt = list_first_entry(&pool->sp_sockets, struct svc_xprt, xpt_ready); + list_del_init(&xprt->xpt_ready); + } + spin_unlock_bh(&pool->sp_lock); + } /* - * The server is shutting down, and no more threads are running. - * svc_xprt_enqueue() might still be running, but at worst it - * will re-add the xprt to sp_sockets, which will soon get - * freed. So we don't bother with any more locking, and don't - * leave the close to the (nonexistent) server threads: + * At this point the sp_sockets lists will stay empty, since + * svc_enqueue will not add new entries without taking the + * sp_lock and checking XPT_BUSY. */ - list_for_each_entry_safe(xprt, tmp, xprt_list, xpt_list) { - set_bit(XPT_CLOSE, &xprt->xpt_flags); + list_for_each_entry_safe(xprt, tmp, &serv->sv_tempsocks, xpt_list) svc_delete_xprt(xprt); - } + list_for_each_entry_safe(xprt, tmp, &serv->sv_permsocks, xpt_list) + svc_delete_xprt(xprt); + + BUG_ON(!list_empty(&serv->sv_permsocks)); + BUG_ON(!list_empty(&serv->sv_tempsocks)); } /* diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 4653286fcc9e..464570906f80 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -739,7 +739,8 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv) { int err, level, optname, one = 1; - svc_xprt_init(&svc_udp_class, &svsk->sk_xprt, serv); + svc_xprt_init(sock_net(svsk->sk_sock->sk), &svc_udp_class, + &svsk->sk_xprt, serv); clear_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags); svsk->sk_sk->sk_data_ready = svc_udp_data_ready; svsk->sk_sk->sk_write_space = svc_write_space; @@ -1343,7 +1344,8 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) { struct sock *sk = svsk->sk_sk; - svc_xprt_init(&svc_tcp_class, &svsk->sk_xprt, serv); + svc_xprt_init(sock_net(svsk->sk_sock->sk), &svc_tcp_class, + &svsk->sk_xprt, serv); set_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags); if (sk->sk_state == TCP_LISTEN) { dprintk("setting up TCP socket for listening\n"); @@ -1659,7 +1661,7 @@ static struct svc_xprt *svc_bc_create_socket(struct svc_serv *serv, return ERR_PTR(-ENOMEM); xprt = &svsk->sk_xprt; - svc_xprt_init(&svc_tcp_bc_class, xprt, serv); + svc_xprt_init(net, &svc_tcp_bc_class, xprt, serv); serv->sv_bc_xprt = xprt; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 277ebd4bf095..593f4c605305 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -296,7 +296,7 @@ _copy_to_pages(struct page **pages, size_t pgbase, const char *p, size_t len) * Copies data into an arbitrary memory location from an array of pages * The copy is assumed to be non-overlapping. */ -static void +void _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len) { struct page **pgfrom; @@ -324,6 +324,7 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len) } while ((len -= copy) != 0); } +EXPORT_SYMBOL_GPL(_copy_from_pages); /* * xdr_shrink_bufhead diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index ba1296d88de0..894cb42db91d 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -453,7 +453,7 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, if (!cma_xprt) return NULL; - svc_xprt_init(&svc_rdma_class, &cma_xprt->sc_xprt, serv); + svc_xprt_init(&init_net, &svc_rdma_class, &cma_xprt->sc_xprt, serv); INIT_LIST_HEAD(&cma_xprt->sc_accept_q); INIT_LIST_HEAD(&cma_xprt->sc_dto_q); INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q); diff --git a/net/unix/Kconfig b/net/unix/Kconfig index c2128b10e5f9..8b31ab85d050 100644 --- a/net/unix/Kconfig +++ b/net/unix/Kconfig @@ -22,7 +22,7 @@ config UNIX config UNIX_DIAG tristate "UNIX: socket monitoring interface" depends on UNIX - default UNIX + default n ---help--- Support for UNIX socket monitoring interface used by the ss tool. If unsure, say Y. diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index aad8fb699989..85d3bb7490aa 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1918,7 +1918,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, struct sk_buff *skb; unix_state_lock(sk); - skb = skb_dequeue(&sk->sk_receive_queue); + skb = skb_peek(&sk->sk_receive_queue); if (skb == NULL) { unix_sk(sk)->recursion_level = 0; if (copied >= target) @@ -1958,11 +1958,8 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (check_creds) { /* Never glue messages from different writers */ if ((UNIXCB(skb).pid != siocb->scm->pid) || - (UNIXCB(skb).cred != siocb->scm->cred)) { - skb_queue_head(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + (UNIXCB(skb).cred != siocb->scm->cred)) break; - } } else { /* Copy credentials */ scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).cred); @@ -1977,8 +1974,6 @@ static int unix_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)) { - skb_queue_head(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); if (copied == 0) copied = -EFAULT; break; @@ -1993,13 +1988,10 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (UNIXCB(skb).fp) unix_detach_fds(siocb->scm, skb); - /* put the skb back if we didn't use it up.. */ - if (skb->len) { - skb_queue_head(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + if (skb->len) break; - } + skb_unlink(skb, &sk->sk_receive_queue); consume_skb(skb); if (siocb->scm->fp) @@ -2010,9 +2002,6 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (UNIXCB(skb).fp) siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp); - /* put message back and return */ - skb_queue_head(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); break; } } while (size); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b3d3cf8931cb..afeea32e04ad 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2250,6 +2250,7 @@ static const struct nla_policy sta_flags_policy[NL80211_STA_FLAG_MAX + 1] = { }; static int parse_station_flags(struct genl_info *info, + enum nl80211_iftype iftype, struct station_parameters *params) { struct nlattr *flags[NL80211_STA_FLAG_MAX + 1]; @@ -2283,8 +2284,33 @@ static int parse_station_flags(struct genl_info *info, nla, sta_flags_policy)) return -EINVAL; - params->sta_flags_mask = (1 << __NL80211_STA_FLAG_AFTER_LAST) - 1; - params->sta_flags_mask &= ~1; + /* + * Only allow certain flags for interface types so that + * other attributes are silently ignored. Remember that + * this is backward compatibility code with old userspace + * and shouldn't be hit in other cases anyway. + */ + switch (iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_P2P_GO: + params->sta_flags_mask = BIT(NL80211_STA_FLAG_AUTHORIZED) | + BIT(NL80211_STA_FLAG_SHORT_PREAMBLE) | + BIT(NL80211_STA_FLAG_WME) | + BIT(NL80211_STA_FLAG_MFP); + break; + case NL80211_IFTYPE_P2P_CLIENT: + case NL80211_IFTYPE_STATION: + params->sta_flags_mask = BIT(NL80211_STA_FLAG_AUTHORIZED) | + BIT(NL80211_STA_FLAG_TDLS_PEER); + break; + case NL80211_IFTYPE_MESH_POINT: + params->sta_flags_mask = BIT(NL80211_STA_FLAG_AUTHENTICATED) | + BIT(NL80211_STA_FLAG_MFP) | + BIT(NL80211_STA_FLAG_AUTHORIZED); + default: + return -EINVAL; + } for (flag = 1; flag <= NL80211_STA_FLAG_MAX; flag++) if (flags[flag]) @@ -2585,7 +2611,7 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->change_station) return -EOPNOTSUPP; - if (parse_station_flags(info, ¶ms)) + if (parse_station_flags(info, dev->ieee80211_ptr->iftype, ¶ms)) return -EINVAL; if (info->attrs[NL80211_ATTR_STA_PLINK_ACTION]) @@ -2731,7 +2757,7 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->add_station) return -EOPNOTSUPP; - if (parse_station_flags(info, ¶ms)) + if (parse_station_flags(info, dev->ieee80211_ptr->iftype, ¶ms)) return -EINVAL; switch (dev->ieee80211_ptr->iftype) { diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index e0d747a2e803..66b84fbf2746 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2290,7 +2290,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) link = &xfrm_dispatch[type]; /* All operations require privileges, even GET */ - if (security_netlink_recv(skb, CAP_NET_ADMIN)) + if (!capable(CAP_NET_ADMIN)) return -EPERM; if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) || @@ -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_INIT_POINTER(net->xfrm.nlsk, nlsk); + rcu_assign_pointer(net->xfrm.nlsk, nlsk); return 0; } |