diff options
Diffstat (limited to 'net')
492 files changed, 13903 insertions, 7006 deletions
diff --git a/net/802/fc.c b/net/802/fc.c index 1bb496ea997e..058a9f708918 100644 --- a/net/802/fc.c +++ b/net/802/fc.c @@ -49,7 +49,7 @@ static int fc_header(struct sk_buff *skb, struct net_device *dev, struct fcllc *fcllc; hdr_len = sizeof(struct fch_hdr) + sizeof(struct fcllc); - fch = (struct fch_hdr *)skb_push(skb, hdr_len); + fch = skb_push(skb, hdr_len); fcllc = (struct fcllc *)(fch+1); fcllc->dsap = fcllc->ssap = EXTENDED_SAP; fcllc->llc = UI_CMD; @@ -59,7 +59,7 @@ static int fc_header(struct sk_buff *skb, struct net_device *dev, else { hdr_len = sizeof(struct fch_hdr); - fch = (struct fch_hdr *)skb_push(skb, hdr_len); + fch = skb_push(skb, hdr_len); } if(saddr) diff --git a/net/802/fddi.c b/net/802/fddi.c index 6356623fc238..90f1416567a1 100644 --- a/net/802/fddi.c +++ b/net/802/fddi.c @@ -58,7 +58,7 @@ static int fddi_header(struct sk_buff *skb, struct net_device *dev, if(type != ETH_P_IP && type != ETH_P_IPV6 && type != ETH_P_ARP) hl=FDDI_K_8022_HLEN-3; - fddi = (struct fddihdr *)skb_push(skb, hl); + fddi = skb_push(skb, hl); fddi->fc = FDDI_FC_K_ASYNC_LLC_DEF; if(type == ETH_P_IP || type == ETH_P_IPV6 || type == ETH_P_ARP) { diff --git a/net/802/garp.c b/net/802/garp.c index b38ee6dcba45..2dac647ff420 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -221,7 +221,7 @@ static int garp_pdu_init(struct garp_applicant *app) skb->protocol = htons(ETH_P_802_2); skb_reserve(skb, LL_RESERVED_SPACE(app->dev) + LLC_RESERVE); - gp = (struct garp_pdu_hdr *)__skb_put(skb, sizeof(*gp)); + gp = __skb_put(skb, sizeof(*gp)); put_unaligned(htons(GARP_PROTOCOL_ID), &gp->protocol); app->pdu = skb; @@ -232,7 +232,7 @@ static int garp_pdu_append_end_mark(struct garp_applicant *app) { if (skb_tailroom(app->pdu) < sizeof(u8)) return -1; - *(u8 *)__skb_put(app->pdu, sizeof(u8)) = GARP_END_MARK; + __skb_put_u8(app->pdu, GARP_END_MARK); return 0; } @@ -268,7 +268,7 @@ static int garp_pdu_append_msg(struct garp_applicant *app, u8 attrtype) if (skb_tailroom(app->pdu) < sizeof(*gm)) return -1; - gm = (struct garp_msg_hdr *)__skb_put(app->pdu, sizeof(*gm)); + gm = __skb_put(app->pdu, sizeof(*gm)); gm->attrtype = attrtype; garp_cb(app->pdu)->cur_type = attrtype; return 0; @@ -299,7 +299,7 @@ again: len = sizeof(*ga) + attr->dlen; if (skb_tailroom(app->pdu) < len) goto queue; - ga = (struct garp_attr_hdr *)__skb_put(app->pdu, len); + ga = __skb_put(app->pdu, len); ga->len = len; ga->event = event; memcpy(ga->data, attr->data, attr->dlen); diff --git a/net/802/hippi.c b/net/802/hippi.c index 4460606e9c36..690308b9b94a 100644 --- a/net/802/hippi.c +++ b/net/802/hippi.c @@ -47,7 +47,7 @@ static int hippi_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { - struct hippi_hdr *hip = (struct hippi_hdr *)skb_push(skb, HIPPI_HLEN); + struct hippi_hdr *hip = skb_push(skb, HIPPI_HLEN); struct hippi_cb *hcb = (struct hippi_cb *) skb->cb; if (!len){ diff --git a/net/802/mrp.c b/net/802/mrp.c index 72db2785ef2c..be4dd3165347 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -311,7 +311,7 @@ static int mrp_pdu_init(struct mrp_applicant *app) skb_reset_network_header(skb); skb_reset_transport_header(skb); - ph = (struct mrp_pdu_hdr *)__skb_put(skb, sizeof(*ph)); + ph = __skb_put(skb, sizeof(*ph)); ph->version = app->app->version; app->pdu = skb; @@ -324,7 +324,7 @@ static int mrp_pdu_append_end_mark(struct mrp_applicant *app) if (skb_tailroom(app->pdu) < sizeof(*endmark)) return -1; - endmark = (__be16 *)__skb_put(app->pdu, sizeof(*endmark)); + endmark = __skb_put(app->pdu, sizeof(*endmark)); put_unaligned(MRP_END_MARK, endmark); return 0; } @@ -368,7 +368,7 @@ static int mrp_pdu_append_msg_hdr(struct mrp_applicant *app, if (skb_tailroom(app->pdu) < sizeof(*mh)) return -1; - mh = (struct mrp_msg_hdr *)__skb_put(app->pdu, sizeof(*mh)); + mh = __skb_put(app->pdu, sizeof(*mh)); mh->attrtype = attrtype; mh->attrlen = attrlen; mrp_cb(app->pdu)->mh = mh; @@ -382,8 +382,7 @@ static int mrp_pdu_append_vecattr_hdr(struct mrp_applicant *app, if (skb_tailroom(app->pdu) < sizeof(*vah) + attrlen) return -1; - vah = (struct mrp_vecattr_hdr *)__skb_put(app->pdu, - sizeof(*vah) + attrlen); + vah = __skb_put(app->pdu, sizeof(*vah) + attrlen); put_unaligned(0, &vah->lenflags); memcpy(vah->firstattrvalue, firstattrvalue, attrlen); mrp_cb(app->pdu)->vah = vah; @@ -435,7 +434,7 @@ again: if (!pos) { if (skb_tailroom(app->pdu) < sizeof(u8)) goto queue; - vaevents = (u8 *)__skb_put(app->pdu, sizeof(u8)); + vaevents = __skb_put(app->pdu, sizeof(u8)); } else { vaevents = (u8 *)(skb_tail_pointer(app->pdu) - sizeof(u8)); } diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index abc5f400fc71..f7e83f6d2e64 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -58,7 +58,7 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, int rc; if (!(vlan->flags & VLAN_FLAG_REORDER_HDR)) { - vhdr = (struct vlan_hdr *) skb_push(skb, VLAN_HLEN); + vhdr = skb_push(skb, VLAN_HLEN); vlan_tci = vlan->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority); @@ -797,12 +797,6 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup, #endif .ndo_fix_features = vlan_dev_fix_features, - .ndo_fdb_add = switchdev_port_fdb_add, - .ndo_fdb_del = switchdev_port_fdb_del, - .ndo_fdb_dump = switchdev_port_fdb_dump, - .ndo_bridge_setlink = switchdev_port_bridge_setlink, - .ndo_bridge_getlink = switchdev_port_bridge_getlink, - .ndo_bridge_dellink = switchdev_port_bridge_dellink, .ndo_get_lock_subclass = vlan_dev_get_lock_subclass, .ndo_get_iflink = vlan_dev_get_iflink, }; diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 9c94aad153b3..5e831de3103e 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -39,7 +39,8 @@ static inline int vlan_validate_qos_map(struct nlattr *attr) NULL); } -static int vlan_validate(struct nlattr *tb[], struct nlattr *data[]) +static int vlan_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ifla_vlan_flags *flags; u16 id; @@ -87,8 +88,9 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } -static int vlan_changelink(struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) +static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ifla_vlan_flags *flags; struct ifla_vlan_qos_mapping *m; @@ -115,7 +117,8 @@ static int vlan_changelink(struct net_device *dev, } static int vlan_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev; @@ -153,7 +156,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, else if (dev->mtu > max_mtu) return -EINVAL; - err = vlan_changelink(dev, tb, data); + err = vlan_changelink(dev, tb, data, extack); if (err < 0) return err; diff --git a/net/9p/client.c b/net/9p/client.c index 1218fb3b52da..4674235b0d9b 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -37,6 +37,7 @@ #include <linux/uio.h> #include <net/9p/9p.h> #include <linux/parser.h> +#include <linux/seq_file.h> #include <net/9p/client.h> #include <net/9p/transport.h> #include "protocol.h" @@ -77,6 +78,30 @@ inline int p9_is_proto_dotu(struct p9_client *clnt) } EXPORT_SYMBOL(p9_is_proto_dotu); +int p9_show_client_options(struct seq_file *m, struct p9_client *clnt) +{ + if (clnt->msize != 8192) + seq_printf(m, ",msize=%u", clnt->msize); + seq_printf(m, "trans=%s", clnt->trans_mod->name); + + switch (clnt->proto_version) { + case p9_proto_legacy: + seq_puts(m, ",noextend"); + break; + case p9_proto_2000u: + seq_puts(m, ",version=9p2000.u"); + break; + case p9_proto_2000L: + /* Default */ + break; + } + + if (clnt->trans_mod->show_options) + return clnt->trans_mod->show_options(m, clnt); + return 0; +} +EXPORT_SYMBOL(p9_show_client_options); + /* * Some error codes are taken directly from the server replies, * make sure they are valid. diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 7bc2208b6cc4..ddfa86648f95 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -41,6 +41,7 @@ #include <linux/file.h> #include <linux/parser.h> #include <linux/slab.h> +#include <linux/seq_file.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include <net/9p/transport.h> @@ -51,6 +52,9 @@ #define MAX_SOCK_BUF (64*1024) #define MAXPOLLWADDR 2 +static struct p9_trans_module p9_tcp_trans; +static struct p9_trans_module p9_fd_trans; + /** * struct p9_fd_opts - per-transport options * @rfd: file descriptor for reading (trans=fd) @@ -63,7 +67,7 @@ struct p9_fd_opts { int rfd; int wfd; u16 port; - int privport; + bool privport; }; /* @@ -95,7 +99,7 @@ enum { struct p9_poll_wait { struct p9_conn *conn; - wait_queue_t wait; + wait_queue_entry_t wait; wait_queue_head_t *wait_addr; }; @@ -522,7 +526,7 @@ error: clear_bit(Wworksched, &m->wsched); } -static int p9_pollwake(wait_queue_t *wait, unsigned int mode, int sync, void *key) +static int p9_pollwake(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key) { struct p9_poll_wait *pwait = container_of(wait, struct p9_poll_wait, wait); @@ -720,6 +724,20 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req) return 0; } +static int p9_fd_show_options(struct seq_file *m, struct p9_client *clnt) +{ + if (clnt->trans_mod == &p9_tcp_trans) { + if (clnt->trans_opts.tcp.port != P9_PORT) + seq_printf(m, "port=%u", clnt->trans_opts.tcp.port); + } else if (clnt->trans_mod == &p9_fd_trans) { + if (clnt->trans_opts.fd.rfd != ~0) + seq_printf(m, "rfd=%u", clnt->trans_opts.fd.rfd); + if (clnt->trans_opts.fd.wfd != ~0) + seq_printf(m, "wfd=%u", clnt->trans_opts.fd.wfd); + } + return 0; +} + /** * parse_opts - parse mount options into p9_fd_opts structure * @params: options string passed from mount @@ -738,7 +756,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) opts->port = P9_PORT; opts->rfd = ~0; opts->wfd = ~0; - opts->privport = 0; + opts->privport = false; if (!params) return 0; @@ -776,7 +794,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) opts->wfd = option; break; case Opt_privport: - opts->privport = 1; + opts->privport = true; break; default: continue; @@ -942,6 +960,8 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) csocket = NULL; + client->trans_opts.tcp.port = opts.port; + client->trans_opts.tcp.privport = opts.privport; sin_server.sin_family = AF_INET; sin_server.sin_addr.s_addr = in_aton(addr); sin_server.sin_port = htons(opts.port); @@ -1020,6 +1040,8 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args) struct p9_fd_opts opts; parse_opts(args, &opts); + client->trans_opts.fd.rfd = opts.rfd; + client->trans_opts.fd.wfd = opts.wfd; if (opts.rfd == ~0 || opts.wfd == ~0) { pr_err("Insufficient options for proto=fd\n"); @@ -1044,6 +1066,7 @@ static struct p9_trans_module p9_tcp_trans = { .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, + .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; @@ -1056,6 +1079,7 @@ static struct p9_trans_module p9_unix_trans = { .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, + .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; @@ -1068,6 +1092,7 @@ static struct p9_trans_module p9_fd_trans = { .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, + .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 553ed4ecb6a0..6d8e3031978f 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -43,6 +43,7 @@ #include <linux/parser.h> #include <linux/semaphore.h> #include <linux/slab.h> +#include <linux/seq_file.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include <net/9p/transport.h> @@ -70,6 +71,8 @@ * @dm_mr: DMA Memory Region pointer * @lkey: The local access only memory region key * @timeout: Number of uSecs to wait for connection management events + * @privport: Whether a privileged port may be used + * @port: The port to use * @sq_depth: The depth of the Send Queue * @sq_sem: Semaphore for the SQ * @rq_depth: The depth of the Receive Queue. @@ -95,6 +98,8 @@ struct p9_trans_rdma { struct ib_qp *qp; struct ib_cq *cq; long timeout; + bool privport; + u16 port; int sq_depth; struct semaphore sq_sem; int rq_depth; @@ -133,10 +138,10 @@ struct p9_rdma_context { */ struct p9_rdma_opts { short port; + bool privport; int sq_depth; int rq_depth; long timeout; - int privport; }; /* @@ -159,6 +164,23 @@ static match_table_t tokens = { {Opt_err, NULL}, }; +static int p9_rdma_show_options(struct seq_file *m, struct p9_client *clnt) +{ + struct p9_trans_rdma *rdma = clnt->trans; + + if (rdma->port != P9_PORT) + seq_printf(m, ",port=%u", rdma->port); + if (rdma->sq_depth != P9_RDMA_SQ_DEPTH) + seq_printf(m, ",sq=%u", rdma->sq_depth); + if (rdma->rq_depth != P9_RDMA_RQ_DEPTH) + seq_printf(m, ",rq=%u", rdma->rq_depth); + if (rdma->timeout != P9_RDMA_TIMEOUT) + seq_printf(m, ",timeout=%lu", rdma->timeout); + if (rdma->privport) + seq_puts(m, ",privport"); + return 0; +} + /** * parse_opts - parse mount options into rdma options structure * @params: options string passed from mount @@ -177,7 +199,7 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) opts->sq_depth = P9_RDMA_SQ_DEPTH; opts->rq_depth = P9_RDMA_RQ_DEPTH; opts->timeout = P9_RDMA_TIMEOUT; - opts->privport = 0; + opts->privport = false; if (!params) return 0; @@ -218,7 +240,7 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) opts->timeout = option; break; case Opt_privport: - opts->privport = 1; + opts->privport = true; break; default: continue; @@ -560,6 +582,8 @@ static struct p9_trans_rdma *alloc_rdma(struct p9_rdma_opts *opts) if (!rdma) return NULL; + rdma->port = opts->port; + rdma->privport = opts->privport; rdma->sq_depth = opts->sq_depth; rdma->rq_depth = opts->rq_depth; rdma->timeout = opts->timeout; @@ -733,6 +757,7 @@ static struct p9_trans_module p9_rdma_trans = { .request = rdma_request, .cancel = rdma_cancel, .cancelled = rdma_cancelled, + .show_options = p9_rdma_show_options, }; /** diff --git a/net/Kconfig b/net/Kconfig index 102f781a0131..7d57ef34b79c 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -55,6 +55,7 @@ menu "Networking options" source "net/packet/Kconfig" source "net/unix/Kconfig" +source "net/tls/Kconfig" source "net/xfrm/Kconfig" source "net/iucv/Kconfig" source "net/smc/Kconfig" diff --git a/net/Makefile b/net/Makefile index 9086ffbb5085..bed80fa398b7 100644 --- a/net/Makefile +++ b/net/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_LLC) += llc/ obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/ bpf/ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ +obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ obj-$(CONFIG_UNIX) += unix/ obj-$(CONFIG_NET) += ipv6/ diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 465cc24b41e5..5d035c1f1156 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1529,7 +1529,7 @@ static int ltalk_rcv(struct sk_buff *skb, struct net_device *dev, * The push leaves us with a ddephdr not an shdr, and * handily the port bytes in the right place preset. */ - ddp = (struct ddpehdr *) skb_push(skb, sizeof(*ddp) - 4); + ddp = skb_push(skb, sizeof(*ddp) - 4); /* Now fill in the long header */ @@ -1647,7 +1647,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) SOCK_DEBUG(sk, "SK %p: Begin build.\n", sk); - ddp = (struct ddpehdr *)skb_put(skb, sizeof(struct ddpehdr)); + ddp = skb_put(skb, sizeof(struct ddpehdr)); ddp->deh_len_hops = htons(len + sizeof(*ddp)); ddp->deh_dnet = usat->sat_addr.s_net; ddp->deh_snet = at->src_net; diff --git a/net/atm/br2684.c b/net/atm/br2684.c index fca84e111c89..4e111196f902 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -252,7 +252,7 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev, ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc; pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev); - atomic_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc); + refcount_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc); ATM_SKB(skb)->atm_options = atmvcc->atm_options; dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; diff --git a/net/atm/clip.c b/net/atm/clip.c index ec527b62f79d..f271a7bcf5b2 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -60,7 +60,7 @@ static int to_atmarpd(enum atmarp_ctrl_type type, int itf, __be32 ip) skb = alloc_skb(sizeof(struct atmarp_ctrl), GFP_ATOMIC); if (!skb) return -ENOMEM; - ctrl = (struct atmarp_ctrl *)skb_put(skb, sizeof(struct atmarp_ctrl)); + ctrl = skb_put(skb, sizeof(struct atmarp_ctrl)); ctrl->type = type; ctrl->itf_num = itf; ctrl->ip = ip; @@ -137,11 +137,11 @@ static int neigh_check_cb(struct neighbour *n) if (entry->vccs || time_before(jiffies, entry->expires)) return 0; - if (atomic_read(&n->refcnt) > 1) { + if (refcount_read(&n->refcnt) > 1) { struct sk_buff *skb; pr_debug("destruction postponed with ref %d\n", - atomic_read(&n->refcnt)); + refcount_read(&n->refcnt)); while ((skb = skb_dequeue(&n->arp_queue)) != NULL) dev_kfree_skb(skb); @@ -381,7 +381,7 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, memcpy(here, llc_oui, sizeof(llc_oui)); ((__be16 *) here)[3] = skb->protocol; } - atomic_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); ATM_SKB(skb)->atm_options = vcc->atm_options; entry->vccs->last_use = jiffies; pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, vcc, vcc->dev); @@ -767,7 +767,7 @@ static void atmarp_info(struct seq_file *seq, struct neighbour *n, seq_printf(seq, "(resolving)\n"); else seq_printf(seq, "(expired, ref %d)\n", - atomic_read(&entry->neigh->refcnt)); + refcount_read(&entry->neigh->refcnt)); } else if (!svc) { seq_printf(seq, "%d.%d.%d\n", clip_vcc->vcc->dev->number, diff --git a/net/atm/common.c b/net/atm/common.c index f06422f4108d..8a4f99114cd2 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -80,9 +80,9 @@ static void vcc_sock_destruct(struct sock *sk) printk(KERN_DEBUG "%s: rmem leakage (%d bytes) detected.\n", __func__, atomic_read(&sk->sk_rmem_alloc)); - if (atomic_read(&sk->sk_wmem_alloc)) + if (refcount_read(&sk->sk_wmem_alloc)) printk(KERN_DEBUG "%s: wmem leakage (%d bytes) detected.\n", - __func__, atomic_read(&sk->sk_wmem_alloc)); + __func__, refcount_read(&sk->sk_wmem_alloc)); } static void vcc_def_wakeup(struct sock *sk) @@ -101,7 +101,7 @@ static inline int vcc_writable(struct sock *sk) struct atm_vcc *vcc = atm_sk(sk); return (vcc->qos.txtp.max_sdu + - atomic_read(&sk->sk_wmem_alloc)) <= sk->sk_sndbuf; + refcount_read(&sk->sk_wmem_alloc)) <= sk->sk_sndbuf; } static void vcc_write_space(struct sock *sk) @@ -156,7 +156,7 @@ int vcc_create(struct net *net, struct socket *sock, int protocol, int family, i memset(&vcc->local, 0, sizeof(struct sockaddr_atmsvc)); memset(&vcc->remote, 0, sizeof(struct sockaddr_atmsvc)); vcc->qos.txtp.max_sdu = 1 << 16; /* for meta VCs */ - atomic_set(&sk->sk_wmem_alloc, 1); + refcount_set(&sk->sk_wmem_alloc, 1); atomic_set(&sk->sk_rmem_alloc, 0); vcc->push = NULL; vcc->pop = NULL; @@ -630,7 +630,7 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) goto out; } pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize); - atomic_add(skb->truesize, &sk->sk_wmem_alloc); + refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb->dev = NULL; /* for paths shared with net_device interfaces */ ATM_SKB(skb)->atm_options = vcc->atm_options; diff --git a/net/atm/lec.c b/net/atm/lec.c index 09cfe87f0a44..093fe8707731 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -101,12 +101,12 @@ static void lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc); /* must be done under lec_arp_lock */ static inline void lec_arp_hold(struct lec_arp_table *entry) { - atomic_inc(&entry->usage); + refcount_inc(&entry->usage); } static inline void lec_arp_put(struct lec_arp_table *entry) { - if (atomic_dec_and_test(&entry->usage)) + if (refcount_dec_and_test(&entry->usage)) kfree(entry); } @@ -181,7 +181,7 @@ lec_send(struct atm_vcc *vcc, struct sk_buff *skb) ATM_SKB(skb)->vcc = vcc; ATM_SKB(skb)->atm_options = vcc->atm_options; - atomic_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); if (vcc->send(vcc, skb) < 0) { dev->stats.tx_dropped++; return; @@ -345,7 +345,7 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb) int i; char *tmp; /* FIXME */ - atomic_sub(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc)); mesg = (struct atmlec_msg *)skb->data; tmp = skb->data; tmp += sizeof(struct atmlec_msg); @@ -1564,7 +1564,7 @@ static struct lec_arp_table *make_entry(struct lec_priv *priv, to_return->last_used = jiffies; to_return->priv = priv; skb_queue_head_init(&to_return->tx_wait); - atomic_set(&to_return->usage, 1); + refcount_set(&to_return->usage, 1); return to_return; } diff --git a/net/atm/lec_arpc.h b/net/atm/lec_arpc.h index ec67435a40a6..d923f53812a3 100644 --- a/net/atm/lec_arpc.h +++ b/net/atm/lec_arpc.h @@ -47,7 +47,7 @@ struct lec_arp_table { * the length of the tlvs array */ struct sk_buff_head tx_wait; /* wait queue for outgoing packets */ - atomic_t usage; /* usage count */ + refcount_t usage; /* usage count */ }; /* diff --git a/net/atm/mpc.c b/net/atm/mpc.c index a190800572bd..680a4b9095a1 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -555,7 +555,7 @@ static int send_via_shortcut(struct sk_buff *skb, struct mpoa_client *mpc) sizeof(struct llc_snap_hdr)); } - atomic_add(skb->truesize, &sk_atm(entry->shortcut)->sk_wmem_alloc); + refcount_add(skb->truesize, &sk_atm(entry->shortcut)->sk_wmem_alloc); ATM_SKB(skb)->atm_options = entry->shortcut->atm_options; entry->shortcut->send(entry->shortcut, skb); entry->packets_fwded++; @@ -911,7 +911,7 @@ static int msg_from_mpoad(struct atm_vcc *vcc, struct sk_buff *skb) struct mpoa_client *mpc = find_mpc_by_vcc(vcc); struct k_message *mesg = (struct k_message *)skb->data; - atomic_sub(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc)); if (mpc == NULL) { pr_info("no mpc found\n"); diff --git a/net/atm/mpoa_caches.c b/net/atm/mpoa_caches.c index a89fdebeffda..4ccaa16b1eb1 100644 --- a/net/atm/mpoa_caches.c +++ b/net/atm/mpoa_caches.c @@ -40,7 +40,7 @@ static in_cache_entry *in_cache_get(__be32 dst_ip, entry = client->in_cache; while (entry != NULL) { if (entry->ctrl_info.in_dst_ip == dst_ip) { - atomic_inc(&entry->use); + refcount_inc(&entry->use); read_unlock_bh(&client->ingress_lock); return entry; } @@ -61,7 +61,7 @@ static in_cache_entry *in_cache_get_with_mask(__be32 dst_ip, entry = client->in_cache; while (entry != NULL) { if ((entry->ctrl_info.in_dst_ip & mask) == (dst_ip & mask)) { - atomic_inc(&entry->use); + refcount_inc(&entry->use); read_unlock_bh(&client->ingress_lock); return entry; } @@ -82,7 +82,7 @@ static in_cache_entry *in_cache_get_by_vcc(struct atm_vcc *vcc, entry = client->in_cache; while (entry != NULL) { if (entry->shortcut == vcc) { - atomic_inc(&entry->use); + refcount_inc(&entry->use); read_unlock_bh(&client->ingress_lock); return entry; } @@ -105,7 +105,7 @@ static in_cache_entry *in_cache_add_entry(__be32 dst_ip, dprintk("adding an ingress entry, ip = %pI4\n", &dst_ip); - atomic_set(&entry->use, 1); + refcount_set(&entry->use, 1); dprintk("new_in_cache_entry: about to lock\n"); write_lock_bh(&client->ingress_lock); entry->next = client->in_cache; @@ -121,7 +121,7 @@ static in_cache_entry *in_cache_add_entry(__be32 dst_ip, entry->count = 1; entry->entry_state = INGRESS_INVALID; entry->ctrl_info.holding_time = HOLDING_TIME_DEFAULT; - atomic_inc(&entry->use); + refcount_inc(&entry->use); write_unlock_bh(&client->ingress_lock); dprintk("new_in_cache_entry: unlocked\n"); @@ -178,7 +178,7 @@ static int cache_hit(in_cache_entry *entry, struct mpoa_client *mpc) static void in_cache_put(in_cache_entry *entry) { - if (atomic_dec_and_test(&entry->use)) { + if (refcount_dec_and_test(&entry->use)) { memset(entry, 0, sizeof(in_cache_entry)); kfree(entry); } @@ -339,7 +339,7 @@ static eg_cache_entry *eg_cache_get_by_cache_id(__be32 cache_id, entry = mpc->eg_cache; while (entry != NULL) { if (entry->ctrl_info.cache_id == cache_id) { - atomic_inc(&entry->use); + refcount_inc(&entry->use); read_unlock_irq(&mpc->egress_lock); return entry; } @@ -360,7 +360,7 @@ static eg_cache_entry *eg_cache_get_by_tag(__be32 tag, struct mpoa_client *mpc) entry = mpc->eg_cache; while (entry != NULL) { if (entry->ctrl_info.tag == tag) { - atomic_inc(&entry->use); + refcount_inc(&entry->use); read_unlock_irqrestore(&mpc->egress_lock, flags); return entry; } @@ -382,7 +382,7 @@ static eg_cache_entry *eg_cache_get_by_vcc(struct atm_vcc *vcc, entry = mpc->eg_cache; while (entry != NULL) { if (entry->shortcut == vcc) { - atomic_inc(&entry->use); + refcount_inc(&entry->use); read_unlock_irqrestore(&mpc->egress_lock, flags); return entry; } @@ -402,7 +402,7 @@ static eg_cache_entry *eg_cache_get_by_src_ip(__be32 ipaddr, entry = mpc->eg_cache; while (entry != NULL) { if (entry->latest_ip_addr == ipaddr) { - atomic_inc(&entry->use); + refcount_inc(&entry->use); read_unlock_irq(&mpc->egress_lock); return entry; } @@ -415,7 +415,7 @@ static eg_cache_entry *eg_cache_get_by_src_ip(__be32 ipaddr, static void eg_cache_put(eg_cache_entry *entry) { - if (atomic_dec_and_test(&entry->use)) { + if (refcount_dec_and_test(&entry->use)) { memset(entry, 0, sizeof(eg_cache_entry)); kfree(entry); } @@ -468,7 +468,7 @@ static eg_cache_entry *eg_cache_add_entry(struct k_message *msg, dprintk("adding an egress entry, ip = %pI4, this should be our IP\n", &msg->content.eg_info.eg_dst_ip); - atomic_set(&entry->use, 1); + refcount_set(&entry->use, 1); dprintk("new_eg_cache_entry: about to lock\n"); write_lock_irq(&client->egress_lock); entry->next = client->eg_cache; @@ -484,7 +484,7 @@ static eg_cache_entry *eg_cache_add_entry(struct k_message *msg, dprintk("new_eg_cache_entry cache_id %u\n", ntohl(entry->ctrl_info.cache_id)); dprintk("mps_ip = %pI4\n", &entry->ctrl_info.mps_ip); - atomic_inc(&entry->use); + refcount_inc(&entry->use); write_unlock_irq(&client->egress_lock); dprintk("new_eg_cache_entry: unlocked\n"); diff --git a/net/atm/mpoa_caches.h b/net/atm/mpoa_caches.h index 8e5f78cf0be1..30fe34841ced 100644 --- a/net/atm/mpoa_caches.h +++ b/net/atm/mpoa_caches.h @@ -6,6 +6,7 @@ #include <linux/atm.h> #include <linux/atmdev.h> #include <linux/atmmpc.h> +#include <linux/refcount.h> struct mpoa_client; @@ -25,7 +26,7 @@ typedef struct in_cache_entry { struct atm_vcc *shortcut; uint8_t MPS_ctrl_ATM_addr[ATM_ESA_LEN]; struct in_ctrl_info ctrl_info; - atomic_t use; + refcount_t use; } in_cache_entry; struct in_cache_ops{ @@ -58,7 +59,7 @@ typedef struct eg_cache_entry{ uint16_t entry_state; __be32 latest_ip_addr; /* The src IP address of the last packet */ struct eg_ctrl_info ctrl_info; - atomic_t use; + refcount_t use; } eg_cache_entry; struct eg_cache_ops{ diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index c4e09846d1de..21d9d341a619 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -350,7 +350,7 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb) return 1; } - atomic_add(skb->truesize, &sk_atm(ATM_SKB(skb)->vcc)->sk_wmem_alloc); + refcount_add(skb->truesize, &sk_atm(ATM_SKB(skb)->vcc)->sk_wmem_alloc); ATM_SKB(skb)->atm_options = ATM_SKB(skb)->vcc->atm_options; pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, ATM_SKB(skb)->vcc, ATM_SKB(skb)->vcc->dev); diff --git a/net/atm/proc.c b/net/atm/proc.c index bbb6461a4b7f..4caca2a90ec4 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -61,7 +61,7 @@ static void atm_dev_info(struct seq_file *seq, const struct atm_dev *dev) add_stats(seq, "0", &dev->stats.aal0); seq_puts(seq, " "); add_stats(seq, "5", &dev->stats.aal5); - seq_printf(seq, "\t[%d]", atomic_read(&dev->refcnt)); + seq_printf(seq, "\t[%d]", refcount_read(&dev->refcnt)); seq_putc(seq, '\n'); } @@ -211,7 +211,7 @@ static void vcc_info(struct seq_file *seq, struct atm_vcc *vcc) vcc->flags, sk->sk_err, sk_wmem_alloc_get(sk), sk->sk_sndbuf, sk_rmem_alloc_get(sk), sk->sk_rcvbuf, - atomic_read(&sk->sk_refcnt)); + refcount_read(&sk->sk_refcnt)); } static void svc_info(struct seq_file *seq, struct atm_vcc *vcc) diff --git a/net/atm/raw.c b/net/atm/raw.c index 2e17e97a7a8b..821c0797553d 100644 --- a/net/atm/raw.c +++ b/net/atm/raw.c @@ -35,7 +35,7 @@ static void atm_pop_raw(struct atm_vcc *vcc, struct sk_buff *skb) pr_debug("(%d) %d -= %d\n", vcc->vci, sk_wmem_alloc_get(sk), skb->truesize); - atomic_sub(skb->truesize, &sk->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)); dev_kfree_skb_any(skb); sk->sk_write_space(sk); } diff --git a/net/atm/resources.c b/net/atm/resources.c index 0447d5d0b639..918244757b7d 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -109,7 +109,7 @@ struct atm_dev *atm_dev_register(const char *type, struct device *parent, else memset(&dev->flags, 0, sizeof(dev->flags)); memset(&dev->stats, 0, sizeof(dev->stats)); - atomic_set(&dev->refcnt, 1); + refcount_set(&dev->refcnt, 1); if (atm_proc_dev_register(dev) < 0) { pr_err("atm_proc_dev_register failed for dev %s\n", type); diff --git a/net/atm/signaling.c b/net/atm/signaling.c index adb6e3d21b1e..983c3a21a133 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -67,7 +67,7 @@ static int sigd_send(struct atm_vcc *vcc, struct sk_buff *skb) struct sock *sk; msg = (struct atmsvc_msg *) skb->data; - atomic_sub(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc)); vcc = *(struct atm_vcc **) &msg->vcc; pr_debug("%d (0x%lx)\n", (int)msg->type, (unsigned long)vcc); sk = sk_atm(vcc); @@ -150,8 +150,7 @@ void sigd_enq2(struct atm_vcc *vcc, enum atmsvc_msg_type type, pr_debug("%d (0x%p)\n", (int)type, vcc); while (!(skb = alloc_skb(sizeof(struct atmsvc_msg), GFP_KERNEL))) schedule(); - msg = (struct atmsvc_msg *)skb_put(skb, sizeof(struct atmsvc_msg)); - memset(msg, 0, sizeof(*msg)); + msg = skb_put_zero(skb, sizeof(struct atmsvc_msg)); msg->type = type; *(struct atm_vcc **) &msg->vcc = vcc; *(struct atm_vcc **) &msg->listen_vcc = listen_vcc; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index b7c486752b3a..f3f9d18891de 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -510,7 +510,7 @@ ax25_cb *ax25_create_cb(void) if ((ax25 = kzalloc(sizeof(*ax25), GFP_ATOMIC)) == NULL) return NULL; - atomic_set(&ax25->refcount, 1); + refcount_set(&ax25->refcount, 1); skb_queue_head_init(&ax25->write_queue); skb_queue_head_init(&ax25->frag_queue); @@ -1562,7 +1562,7 @@ static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) /* Add the PID if one is not supplied by the user in the skb */ if (!ax25->pidincl) - *skb_push(skb, 1) = sk->sk_protocol; + *(u8 *)skb_push(skb, 1) = sk->sk_protocol; if (sk->sk_type == SOCK_SEQPACKET) { /* Connected mode sockets go via the LAPB machine */ diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c index e1fda27cb27c..0446b892618a 100644 --- a/net/ax25/ax25_route.c +++ b/net/ax25/ax25_route.c @@ -114,7 +114,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) return -ENOMEM; } - atomic_set(&ax25_rt->refcount, 1); + refcount_set(&ax25_rt->refcount, 1); ax25_rt->callsign = route->dest_addr; ax25_rt->dev = ax25_dev->dev; ax25_rt->digipeat = NULL; diff --git a/net/ax25/ax25_uid.c b/net/ax25/ax25_uid.c index 0403b0def7e6..83b035f56202 100644 --- a/net/ax25/ax25_uid.c +++ b/net/ax25/ax25_uid.c @@ -107,7 +107,7 @@ int ax25_uid_ioctl(int cmd, struct sockaddr_ax25 *sax) if ((ax25_uid = kmalloc(sizeof(*ax25_uid), GFP_KERNEL)) == NULL) return -ENOMEM; - atomic_set(&ax25_uid->refcount, 1); + refcount_set(&ax25_uid->refcount, 1); ax25_uid->uid = sax25_kuid; ax25_uid->call = sax->sax25_call; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 495ba7cdcb04..a3501173e200 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -732,8 +732,8 @@ static void batadv_iv_ogm_aggregate(struct batadv_forw_packet *forw_packet_aggr, unsigned char *skb_buff; unsigned long new_direct_link_flag; - skb_buff = skb_put(forw_packet_aggr->skb, packet_len); - memcpy(skb_buff, packet_buff, packet_len); + skb_buff = skb_put_data(forw_packet_aggr->skb, packet_buff, + packet_len); forw_packet_aggr->packet_len += packet_len; forw_packet_aggr->num_packets++; @@ -1022,7 +1022,8 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, u8 tq_avg; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "update_originator(): Searching and updating originator entry of received packet\n"); + "%s(): Searching and updating originator entry of received packet\n", + __func__); rcu_read_lock(); hlist_for_each_entry_rcu(tmp_neigh_node, @@ -1944,7 +1945,7 @@ static void batadv_iv_ogm_orig_print(struct batadv_priv *bat_priv, batadv_iv_ogm_orig_print_neigh(orig_node, if_outgoing, seq); - seq_puts(seq, "\n"); + seq_putc(seq, '\n'); batman_count++; next: diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index a36c8e7291d6..4e2724c5b33d 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -400,7 +400,7 @@ static void batadv_v_orig_print(struct batadv_priv *bat_priv, neigh_node->if_incoming->net_dev->name); batadv_v_orig_print_neigh(orig_node, if_outgoing, seq); - seq_puts(seq, "\n"); + seq_putc(seq, '\n'); batman_count++; next: diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index b90c9903e246..bd1064d98e16 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -19,6 +19,7 @@ #include "main.h" #include <linux/atomic.h> +#include <linux/bitops.h> #include <linux/byteorder/generic.h> #include <linux/errno.h> #include <linux/etherdevice.h> @@ -29,6 +30,7 @@ #include <linux/kernel.h> #include <linux/kref.h> #include <linux/netdevice.h> +#include <linux/nl80211.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> @@ -109,8 +111,12 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) */ return 0; } - if (!ret) - return sinfo.expected_throughput / 100; + if (ret) + goto default_throughput; + if (!(sinfo.filled & BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT))) + goto default_throughput; + + return sinfo.expected_throughput / 100; } /* if not a wifi interface, check if this device provides data via @@ -340,9 +346,8 @@ int batadv_v_elp_iface_enable(struct batadv_hard_iface *hard_iface) goto out; skb_reserve(hard_iface->bat_v.elp_skb, ETH_HLEN + NET_IP_ALIGN); - elp_buff = skb_put(hard_iface->bat_v.elp_skb, BATADV_ELP_HLEN); + elp_buff = skb_put_zero(hard_iface->bat_v.elp_skb, BATADV_ELP_HLEN); elp_packet = (struct batadv_elp_packet *)elp_buff; - memset(elp_packet, 0, BATADV_ELP_HLEN); elp_packet->packet_type = BATADV_ELP; elp_packet->version = BATADV_COMPAT_VERSION; diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 03a35c9f456d..1e3dc374bfde 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -166,8 +166,7 @@ static void batadv_v_ogm_send(struct work_struct *work) goto reschedule; skb_reserve(skb, ETH_HLEN); - pkt_buff = skb_put(skb, ogm_buff_len); - memcpy(pkt_buff, ogm_buff, ogm_buff_len); + pkt_buff = skb_put_data(skb, ogm_buff, ogm_buff_len); ogm_packet = (struct batadv_ogm2_packet *)skb->data; ogm_packet->seqno = htonl(atomic_read(&bat_priv->bat_v.ogm_seqno)); @@ -382,8 +381,7 @@ static void batadv_v_ogm_forward(struct batadv_priv *bat_priv, goto out; skb_reserve(skb, ETH_HLEN); - skb_buff = skb_put(skb, packet_len); - memcpy(skb_buff, ogm_received, packet_len); + skb_buff = skb_put_data(skb, ogm_received, packet_len); /* apply forward penalty */ ogm_forward = (struct batadv_ogm2_packet *)skb_buff; diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index d07e89ec8467..cdd8e8e4df0b 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -394,7 +394,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, */ ether_addr_copy(ethhdr->h_source, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_send_claim(): CLAIM %pM on vid %d\n", mac, + "%s(): CLAIM %pM on vid %d\n", __func__, mac, batadv_print_vid(vid)); break; case BATADV_CLAIM_TYPE_UNCLAIM: @@ -403,7 +403,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, */ ether_addr_copy(hw_src, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_send_claim(): UNCLAIM %pM on vid %d\n", mac, + "%s(): UNCLAIM %pM on vid %d\n", __func__, mac, batadv_print_vid(vid)); break; case BATADV_CLAIM_TYPE_ANNOUNCE: @@ -412,7 +412,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, */ ether_addr_copy(hw_src, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_send_claim(): ANNOUNCE of %pM on vid %d\n", + "%s(): ANNOUNCE of %pM on vid %d\n", __func__, ethhdr->h_source, batadv_print_vid(vid)); break; case BATADV_CLAIM_TYPE_REQUEST: @@ -423,15 +423,15 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, ether_addr_copy(hw_src, mac); ether_addr_copy(ethhdr->h_dest, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_send_claim(): REQUEST of %pM to %pM on vid %d\n", + "%s(): REQUEST of %pM to %pM on vid %d\n", __func__, ethhdr->h_source, ethhdr->h_dest, batadv_print_vid(vid)); break; case BATADV_CLAIM_TYPE_LOOPDETECT: ether_addr_copy(ethhdr->h_source, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_send_claim(): LOOPDETECT of %pM to %pM on vid %d\n", - ethhdr->h_source, ethhdr->h_dest, + "%s(): LOOPDETECT of %pM to %pM on vid %d\n", + __func__, ethhdr->h_source, ethhdr->h_dest, batadv_print_vid(vid)); break; @@ -509,7 +509,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, u8 *orig, return entry; batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_get_backbone_gw(): not found (%pM, %d), creating new entry\n", + "%s(): not found (%pM, %d), creating new entry\n", __func__, orig, batadv_print_vid(vid)); entry = kzalloc(sizeof(*entry), GFP_ATOMIC); @@ -605,7 +605,8 @@ static void batadv_bla_answer_request(struct batadv_priv *bat_priv, int i; batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_answer_request(): received a claim request, send all of our own claims again\n"); + "%s(): received a claim request, send all of our own claims again\n", + __func__); backbone_gw = batadv_backbone_hash_find(bat_priv, primary_if->net_dev->dev_addr, @@ -718,8 +719,8 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, kref_init(&claim->refcount); batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_add_claim(): adding new entry %pM, vid %d to hash ...\n", - mac, batadv_print_vid(vid)); + "%s(): adding new entry %pM, vid %d to hash ...\n", + __func__, mac, batadv_print_vid(vid)); kref_get(&claim->refcount); hash_added = batadv_hash_add(bat_priv->bla.claim_hash, @@ -739,8 +740,9 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, goto claim_free_ref; batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_add_claim(): changing ownership for %pM, vid %d to gw %pM\n", - mac, batadv_print_vid(vid), backbone_gw->orig); + "%s(): changing ownership for %pM, vid %d to gw %pM\n", + __func__, mac, batadv_print_vid(vid), + backbone_gw->orig); remove_crc = true; } @@ -808,7 +810,7 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, if (!claim) return; - batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_del_claim(): %pM, vid %d\n", + batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): %pM, vid %d\n", __func__, mac, batadv_print_vid(vid)); batadv_hash_remove(bat_priv->bla.claim_hash, batadv_compare_claim, @@ -848,8 +850,8 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr, crc = ntohs(*((__be16 *)(&an_addr[4]))); batadv_dbg(BATADV_DBG_BLA, bat_priv, - "handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n", - batadv_print_vid(vid), backbone_gw->orig, crc); + "%s(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n", + __func__, batadv_print_vid(vid), backbone_gw->orig, crc); spin_lock_bh(&backbone_gw->crc_lock); backbone_crc = backbone_gw->crc; @@ -857,8 +859,8 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr, if (backbone_crc != crc) { batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, - "handle_announce(): CRC FAILED for %pM/%d (my = %#.4x, sent = %#.4x)\n", - backbone_gw->orig, + "%s(): CRC FAILED for %pM/%d (my = %#.4x, sent = %#.4x)\n", + __func__, backbone_gw->orig, batadv_print_vid(backbone_gw->vid), backbone_crc, crc); @@ -903,8 +905,8 @@ static bool batadv_handle_request(struct batadv_priv *bat_priv, return true; batadv_dbg(BATADV_DBG_BLA, bat_priv, - "handle_request(): REQUEST vid %d (sent by %pM)...\n", - batadv_print_vid(vid), ethhdr->h_source); + "%s(): REQUEST vid %d (sent by %pM)...\n", + __func__, batadv_print_vid(vid), ethhdr->h_source); batadv_bla_answer_request(bat_priv, primary_if, vid); return true; @@ -940,7 +942,7 @@ static bool batadv_handle_unclaim(struct batadv_priv *bat_priv, /* this must be an UNCLAIM frame */ batadv_dbg(BATADV_DBG_BLA, bat_priv, - "handle_unclaim(): UNCLAIM %pM on vid %d (sent by %pM)...\n", + "%s(): UNCLAIM %pM on vid %d (sent by %pM)...\n", __func__, claim_addr, batadv_print_vid(vid), backbone_gw->orig); batadv_bla_del_claim(bat_priv, claim_addr, vid); @@ -1160,9 +1162,9 @@ static bool batadv_bla_process_claim(struct batadv_priv *bat_priv, ethhdr); if (ret == 1) batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_process_claim(): received a claim frame from another group. From: %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", - ethhdr->h_source, batadv_print_vid(vid), hw_src, - hw_dst); + "%s(): received a claim frame from another group. From: %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", + __func__, ethhdr->h_source, batadv_print_vid(vid), + hw_src, hw_dst); if (ret < 2) return !!ret; @@ -1196,8 +1198,9 @@ static bool batadv_bla_process_claim(struct batadv_priv *bat_priv, } batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_process_claim(): ERROR - this looks like a claim frame, but is useless. eth src %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", - ethhdr->h_source, batadv_print_vid(vid), hw_src, hw_dst); + "%s(): ERROR - this looks like a claim frame, but is useless. eth src %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", + __func__, ethhdr->h_source, batadv_print_vid(vid), hw_src, + hw_dst); return true; } @@ -1237,8 +1240,8 @@ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) continue; batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, - "bla_purge_backbone_gw(): backbone gw %pM timed out\n", - backbone_gw->orig); + "%s(): backbone gw %pM timed out\n", + __func__, backbone_gw->orig); purge_now: /* don't wait for the pending request anymore */ @@ -1295,11 +1298,11 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, goto skip; batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_purge_claims(): timed out.\n"); + "%s(): timed out.\n", __func__); purge_now: batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_purge_claims(): %pM, vid %d\n", + "%s(): %pM, vid %d\n", __func__, claim->addr, claim->vid); batadv_handle_unclaim(bat_priv, primary_if, @@ -1851,8 +1854,8 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, */ batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_rx(): Unclaimed MAC %pM found. Claim it. Local: %s\n", - ethhdr->h_source, + "%s(): Unclaimed MAC %pM found. Claim it. Local: %s\n", + __func__, ethhdr->h_source, batadv_is_my_client(bat_priv, ethhdr->h_source, vid) ? "yes" : "no"); @@ -1978,15 +1981,15 @@ bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, * older than 100 ms to make sure we really * have a roaming client here. */ - batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_tx(): Roaming client %pM detected. Unclaim it.\n", - ethhdr->h_source); + batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): Roaming client %pM detected. Unclaim it.\n", + __func__, ethhdr->h_source); batadv_handle_unclaim(bat_priv, primary_if, primary_if->net_dev->dev_addr, ethhdr->h_source, vid); goto allow; } else { - batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_tx(): Race for claim %pM detected. Drop packet.\n", - ethhdr->h_source); + batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): Race for claim %pM detected. Drop packet.\n", + __func__, ethhdr->h_source); goto handled; } } diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 000ca2f113ab..6930d6b50f99 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -601,7 +601,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst, BATADV_DAT_ADDR_MAX); batadv_dbg(BATADV_DBG_DAT, bat_priv, - "dat_select_candidates(): IP=%pI4 hash(IP)=%u\n", &ip_dst, + "%s(): IP=%pI4 hash(IP)=%u\n", __func__, &ip_dst, ip_key); for (select = 0; select < BATADV_DAT_CANDIDATES_NUM; select++) diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 8f964beaac28..a98cf1104a30 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -296,8 +296,7 @@ batadv_frag_merge_packets(struct hlist_head *chain) /* Copy the payload of the each fragment into the last skb */ hlist_for_each_entry(entry, chain, list) { size = entry->skb->len - hdr_size; - memcpy(skb_put(skb_out, size), entry->skb->data + hdr_size, - size); + skb_put_data(skb_out, entry->skb->data + hdr_size, size); } free: diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 6308c9f0fd96..8ead292886d1 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -207,7 +207,7 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff, skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, ETH_HLEN); - icmp_header = (struct batadv_icmp_header *)skb_put(skb, packet_len); + icmp_header = skb_put(skb, packet_len); if (copy_from_user(icmp_header, buff, packet_len)) { len = -EFAULT; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 810f7d026f54..2be8f1f46529 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -24,7 +24,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2017.1" +#define BATADV_SOURCE_VERSION "2017.2" #endif /* B.A.T.M.A.N. parameters */ @@ -168,7 +168,7 @@ enum batadv_uev_type { /* Maximum number of fragments for one packet */ #define BATADV_FRAG_MAX_FRAGMENTS 16 /* Maxumim size of each fragment */ -#define BATADV_FRAG_MAX_FRAG_SIZE 1400 +#define BATADV_FRAG_MAX_FRAG_SIZE 1280 /* Time to keep fragments while waiting for rest of the fragments */ #define BATADV_FRAG_TIMEOUT 10000 diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index e1f6fc72fe3e..3604d7899e2c 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1935,9 +1935,7 @@ int batadv_nc_nodes_seq_print_text(struct seq_file *seq, void *offset) list) seq_printf(seq, "%pM ", nc_node->addr); - seq_puts(seq, "\n"); - - seq_puts(seq, " Outgoing: "); + seq_puts(seq, "\n Outgoing: "); /* For out_nc_node to this orig_node */ list_for_each_entry_rcu(nc_node, &orig_node->out_coding_list, diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index ae9f4d37d34f..f10e3ff26f9d 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -985,8 +985,8 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, batadv_orig_node_put(orig_node_gw); if (is_gw) { batadv_dbg(BATADV_DBG_BLA, bat_priv, - "recv_unicast_packet(): Dropped unicast pkt received from another backbone gw %pM.\n", - orig_addr_gw); + "%s(): Dropped unicast pkt received from another backbone gw %pM.\n", + __func__, orig_addr_gw); goto free_skb; } } diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 403df596a73d..d239a9d72ac3 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -971,11 +971,11 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, if (hard_iface) batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "purge_outstanding_packets(): %s\n", - hard_iface->net_dev->name); + "%s(): %s\n", + __func__, hard_iface->net_dev->name); else batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "purge_outstanding_packets()\n"); + "%s()\n", __func__); /* claim bcast list for free() */ spin_lock_bh(&bat_priv->forw_bcast_list_lock); diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 556f9a865ddf..bfe8effe9238 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -27,6 +27,7 @@ #include <linux/etherdevice.h> #include <linux/fs.h> #include <linux/if_ether.h> +#include <linux/init.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/kref.h> @@ -594,7 +595,7 @@ static int batadv_tp_send_msg(struct batadv_tp_vars *tp_vars, const u8 *src, return BATADV_TP_REASON_MEMORY_ERROR; skb_reserve(skb, ETH_HLEN); - icmp = (struct batadv_icmp_tp_packet *)skb_put(skb, sizeof(*icmp)); + icmp = skb_put(skb, sizeof(*icmp)); /* fill the icmp header */ ether_addr_copy(icmp->dst, orig_node->orig); @@ -611,7 +612,7 @@ static int batadv_tp_send_msg(struct batadv_tp_vars *tp_vars, const u8 *src, icmp->timestamp = htonl(timestamp); data_len = len - sizeof(*icmp); - data = (u8 *)skb_put(skb, data_len); + data = skb_put(skb, data_len); batadv_tp_fill_prerandom(tp_vars, data, data_len); r = batadv_send_skb_to_orig(skb, orig_node, NULL); @@ -1189,7 +1190,7 @@ static int batadv_tp_send_ack(struct batadv_priv *bat_priv, const u8 *dst, } skb_reserve(skb, ETH_HLEN); - icmp = (struct batadv_icmp_tp_packet *)skb_put(skb, sizeof(*icmp)); + icmp = skb_put(skb, sizeof(*icmp)); icmp->packet_type = BATADV_ICMP; icmp->version = BATADV_COMPAT_VERSION; icmp->ttl = BATADV_TTL; @@ -1497,7 +1498,7 @@ void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb) /** * batadv_tp_meter_init - initialize global tp_meter structures */ -void batadv_tp_meter_init(void) +void __init batadv_tp_meter_init(void) { get_random_bytes(batadv_tp_prerandom, sizeof(batadv_tp_prerandom)); } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index e75b4937b497..e1133bc634b5 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -2488,18 +2488,16 @@ static bool _batadv_is_ap_isolated(struct batadv_tt_local_entry *tt_local_entry, struct batadv_tt_global_entry *tt_global_entry) { - bool ret = false; - if (tt_local_entry->common.flags & BATADV_TT_CLIENT_WIFI && tt_global_entry->common.flags & BATADV_TT_CLIENT_WIFI) - ret = true; + return true; /* check if the two clients are marked as isolated */ if (tt_local_entry->common.flags & BATADV_TT_CLIENT_ISOLA && tt_global_entry->common.flags & BATADV_TT_CLIENT_ISOLA) - ret = true; + return true; - return ret; + return false; } /** @@ -4010,19 +4008,22 @@ bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv, const unsigned char *addr, unsigned short vid) { - bool ret = false; + /* ignore loop detect macs, they are not supposed to be in the tt local + * data as well. + */ + if (batadv_bla_is_loopdetect_mac(addr)) + return false; if (!batadv_tt_global_add(bat_priv, orig_node, addr, vid, BATADV_TT_CLIENT_TEMP, atomic_read(&orig_node->last_ttvn))) - goto out; + return false; batadv_dbg(BATADV_DBG_TT, bat_priv, "Added temporary global client (addr: %pM, vid: %d, orig: %pM)\n", addr, batadv_print_vid(vid), orig_node->orig); - ret = true; -out: - return ret; + + return true; } /** diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index f0095fd79818..aad994edd3bb 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -239,7 +239,7 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb, } len -= sizeof(*cl); - cl = (void *) skb_pull(skb, sizeof(*cl)); + cl = skb_pull(skb, sizeof(*cl)); } /* Fall back to L2CAP init sequence */ @@ -279,7 +279,7 @@ static int a2mp_change_notify(struct amp_mgr *mgr, struct sk_buff *skb, while (skb->len >= sizeof(*cl)) { BT_DBG("Controller id %d type %d status %d", cl->id, cl->type, cl->status); - cl = (struct a2mp_cl *) skb_pull(skb, sizeof(*cl)); + cl = skb_pull(skb, sizeof(*cl)); } /* TODO send A2MP_CHANGE_RSP */ diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 42d0997e2fbb..91e3ba280706 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -657,7 +657,7 @@ static int bt_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%pK %-6d %-6u %-6u %-6u %-6lu %-6lu", sk, - atomic_read(&sk->sk_refcnt), + refcount_read(&sk->sk_refcnt), sk_rmem_alloc_get(sk), sk_wmem_alloc_get(sk), from_kuid(seq_user_ns(seq), sock_i_uid(sk)), @@ -733,7 +733,7 @@ void bt_procfs_cleanup(struct net *net, const char *name) EXPORT_SYMBOL(bt_procfs_init); EXPORT_SYMBOL(bt_procfs_cleanup); -static struct net_proto_family bt_sock_family_ops = { +static const struct net_proto_family bt_sock_family_ops = { .owner = THIS_MODULE, .family = PF_BLUETOOTH, .create = bt_sock_create, diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index fbf251fef70f..7b3965861013 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -374,25 +374,22 @@ static int bnep_rx_frame(struct bnep_session *s, struct sk_buff *skb) /* Decompress header and construct ether frame */ switch (type & BNEP_TYPE_MASK) { case BNEP_COMPRESSED: - memcpy(__skb_put(nskb, ETH_HLEN), &s->eh, ETH_HLEN); + __skb_put_data(nskb, &s->eh, ETH_HLEN); break; case BNEP_COMPRESSED_SRC_ONLY: - memcpy(__skb_put(nskb, ETH_ALEN), s->eh.h_dest, ETH_ALEN); - memcpy(__skb_put(nskb, ETH_ALEN), skb_mac_header(skb), ETH_ALEN); + __skb_put_data(nskb, s->eh.h_dest, ETH_ALEN); + __skb_put_data(nskb, skb_mac_header(skb), ETH_ALEN); put_unaligned(s->eh.h_proto, (__be16 *) __skb_put(nskb, 2)); break; case BNEP_COMPRESSED_DST_ONLY: - memcpy(__skb_put(nskb, ETH_ALEN), skb_mac_header(skb), - ETH_ALEN); - memcpy(__skb_put(nskb, ETH_ALEN + 2), s->eh.h_source, - ETH_ALEN + 2); + __skb_put_data(nskb, skb_mac_header(skb), ETH_ALEN); + __skb_put_data(nskb, s->eh.h_source, ETH_ALEN + 2); break; case BNEP_GENERAL: - memcpy(__skb_put(nskb, ETH_ALEN * 2), skb_mac_header(skb), - ETH_ALEN * 2); + __skb_put_data(nskb, skb_mac_header(skb), ETH_ALEN * 2); put_unaligned(s->eh.h_proto, (__be16 *) __skb_put(nskb, 2)); break; } @@ -484,16 +481,16 @@ static int bnep_session(void *arg) struct net_device *dev = s->dev; struct sock *sk = s->sock->sk; struct sk_buff *skb; - wait_queue_t wait; + DEFINE_WAIT_FUNC(wait, woken_wake_function); BT_DBG(""); set_user_nice(current, -15); - init_waitqueue_entry(&wait, current); add_wait_queue(sk_sleep(sk), &wait); while (1) { - set_current_state(TASK_INTERRUPTIBLE); + /* Ensure session->terminate is updated */ + smp_mb__before_atomic(); if (atomic_read(&s->terminate)) break; @@ -515,9 +512,8 @@ static int bnep_session(void *arg) break; netif_wake_queue(dev); - schedule(); + wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); } - __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); /* Cleanup session */ @@ -666,7 +662,7 @@ int bnep_del_connection(struct bnep_conndel_req *req) s = __bnep_get_session(req->dst); if (s) { atomic_inc(&s->terminate); - wake_up_process(s->task); + wake_up_interruptible(sk_sleep(s->sock->sk)); } else err = -ENOENT; diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c index 2b875edf77e1..1d4d7d415730 100644 --- a/net/bluetooth/bnep/netdev.c +++ b/net/bluetooth/bnep/netdev.c @@ -75,16 +75,16 @@ static void bnep_net_set_mc_list(struct net_device *dev) u8 start[ETH_ALEN] = { 0x01 }; /* Request all addresses */ - memcpy(__skb_put(skb, ETH_ALEN), start, ETH_ALEN); - memcpy(__skb_put(skb, ETH_ALEN), dev->broadcast, ETH_ALEN); + __skb_put_data(skb, start, ETH_ALEN); + __skb_put_data(skb, dev->broadcast, ETH_ALEN); r->len = htons(ETH_ALEN * 2); } else { struct netdev_hw_addr *ha; int i, len = skb->len; if (dev->flags & IFF_BROADCAST) { - memcpy(__skb_put(skb, ETH_ALEN), dev->broadcast, ETH_ALEN); - memcpy(__skb_put(skb, ETH_ALEN), dev->broadcast, ETH_ALEN); + __skb_put_data(skb, dev->broadcast, ETH_ALEN); + __skb_put_data(skb, dev->broadcast, ETH_ALEN); } /* FIXME: We should group addresses here. */ @@ -93,8 +93,8 @@ static void bnep_net_set_mc_list(struct net_device *dev) netdev_for_each_mc_addr(ha, dev) { if (i == BNEP_MAX_MULTICAST_FILTERS) break; - memcpy(__skb_put(skb, ETH_ALEN), ha->addr, ETH_ALEN); - memcpy(__skb_put(skb, ETH_ALEN), ha->addr, ETH_ALEN); + __skb_put_data(skb, ha->addr, ETH_ALEN); + __skb_put_data(skb, ha->addr, ETH_ALEN); i++; } diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 9e59b6654126..7f26a5a19ff6 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -122,7 +122,7 @@ static inline void cmtp_add_msgpart(struct cmtp_session *session, int id, const if (skb && (skb->len > 0)) skb_copy_from_linear_data(skb, skb_put(nskb, skb->len), skb->len); - memcpy(skb_put(nskb, count), buf, count); + skb_put_data(nskb, buf, count); session->reassembly[id] = nskb; @@ -280,16 +280,16 @@ static int cmtp_session(void *arg) struct cmtp_session *session = arg; struct sock *sk = session->sock->sk; struct sk_buff *skb; - wait_queue_t wait; + DEFINE_WAIT_FUNC(wait, woken_wake_function); BT_DBG("session %p", session); set_user_nice(current, -15); - init_waitqueue_entry(&wait, current); add_wait_queue(sk_sleep(sk), &wait); while (1) { - set_current_state(TASK_INTERRUPTIBLE); + /* Ensure session->terminate is updated */ + smp_mb__before_atomic(); if (atomic_read(&session->terminate)) break; @@ -306,9 +306,8 @@ static int cmtp_session(void *arg) cmtp_process_transmit(session); - schedule(); + wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); } - __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); down_write(&cmtp_session_sem); @@ -393,7 +392,7 @@ int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock) err = cmtp_attach_device(session); if (err < 0) { atomic_inc(&session->terminate); - wake_up_process(session->task); + wake_up_interruptible(sk_sleep(session->sock->sk)); up_write(&cmtp_session_sem); return err; } @@ -431,7 +430,11 @@ int cmtp_del_connection(struct cmtp_conndel_req *req) /* Stop session thread */ atomic_inc(&session->terminate); - wake_up_process(session->task); + + /* Ensure session->terminate is updated */ + smp_mb__after_atomic(); + + wake_up_interruptible(sk_sleep(session->sock->sk)); } else err = -ENOENT; diff --git a/net/bluetooth/ecdh_helper.c b/net/bluetooth/ecdh_helper.c index 24d4e60f8c48..c7b1a9aee579 100644 --- a/net/bluetooth/ecdh_helper.c +++ b/net/bluetooth/ecdh_helper.c @@ -89,11 +89,9 @@ bool compute_ecdh_secret(const u8 public_key[64], const u8 private_key[32], p.curve_id = ECC_CURVE_NIST_P256; buf_len = crypto_ecdh_key_len(&p); buf = kmalloc(buf_len, GFP_KERNEL); - if (!buf) { - pr_err("alg: kpp: Failed to allocate %d bytes for buf\n", - buf_len); + if (!buf) goto free_req; - } + crypto_ecdh_encode_key(buf, buf_len, &p); /* Set A private Key */ @@ -170,11 +168,8 @@ bool generate_ecdh_keys(u8 public_key[64], u8 private_key[32]) p.key_size = 32; buf_len = crypto_ecdh_key_len(&p); buf = kmalloc(buf_len, GFP_KERNEL); - if (!buf) { - pr_err("alg: kpp: Failed to allocate %d bytes for buf\n", - buf_len); + if (!buf) goto free_req; - } do { if (tries++ >= max_tries) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 05686776a5fb..6bc679cd3481 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -148,13 +148,13 @@ static ssize_t vendor_diag_write(struct file *file, const char __user *user_buf, return -EINVAL; /* When the diagnostic flags are not persistent and the transport - * is not active, then there is no need for the vendor callback. - * - * Instead just store the desired value. If needed the setting - * will be programmed when the controller gets powered on. + * is not active or in user channel operation, then there is no need + * for the vendor callback. Instead just store the desired value and + * the setting will be programmed when the controller gets powered on. */ if (test_bit(HCI_QUIRK_NON_PERSISTENT_DIAG, &hdev->quirks) && - !test_bit(HCI_RUNNING, &hdev->flags)) + (!test_bit(HCI_RUNNING, &hdev->flags) || + hci_dev_test_flag(hdev, HCI_USER_CHANNEL))) goto done; hci_req_sync_lock(hdev); @@ -548,6 +548,7 @@ static void hci_set_event_mask_page_2(struct hci_request *req) { struct hci_dev *hdev = req->hdev; u8 events[8] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; + bool changed = false; /* If Connectionless Slave Broadcast master role is supported * enable all necessary events for it. @@ -557,6 +558,7 @@ static void hci_set_event_mask_page_2(struct hci_request *req) events[1] |= 0x80; /* Synchronization Train Complete */ events[2] |= 0x10; /* Slave Page Response Timeout */ events[2] |= 0x20; /* CSB Channel Map Change */ + changed = true; } /* If Connectionless Slave Broadcast slave role is supported @@ -567,13 +569,24 @@ static void hci_set_event_mask_page_2(struct hci_request *req) events[2] |= 0x02; /* CSB Receive */ events[2] |= 0x04; /* CSB Timeout */ events[2] |= 0x08; /* Truncated Page Complete */ + changed = true; } /* Enable Authenticated Payload Timeout Expired event if supported */ - if (lmp_ping_capable(hdev) || hdev->le_features[0] & HCI_LE_PING) + if (lmp_ping_capable(hdev) || hdev->le_features[0] & HCI_LE_PING) { events[2] |= 0x80; + changed = true; + } - hci_req_add(req, HCI_OP_SET_EVENT_MASK_PAGE_2, sizeof(events), events); + /* Some Broadcom based controllers indicate support for Set Event + * Mask Page 2 command, but then actually do not support it. Since + * the default value is all bits set to zero, the command is only + * required if the event mask has to be changed. In case no change + * to the event mask is needed, skip this command. + */ + if (changed) + hci_req_add(req, HCI_OP_SET_EVENT_MASK_PAGE_2, + sizeof(events), events); } static int hci_init3_req(struct hci_request *req, unsigned long opt) @@ -635,6 +648,14 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) * Report */ + /* If the controller supports Channel Selection Algorithm #2 + * feature, enable the corresponding event. + */ + if (hdev->le_features[1] & HCI_LE_CHAN_SEL_ALG2) + events[2] |= 0x08; /* LE Channel Selection + * Algorithm + */ + /* If the controller supports the LE Set Scan Enable command, * enable the corresponding advertising report event. */ @@ -677,6 +698,12 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) if (hdev->commands[34] & 0x04) events[1] |= 0x01; /* LE Generate DHKey Complete */ + /* If the controller supports the LE Set Default PHY or + * LE Set PHY commands, enable the corresponding event. + */ + if (hdev->commands[35] & (0x20 | 0x40)) + events[1] |= 0x08; /* LE PHY Update Complete */ + hci_req_add(req, HCI_OP_LE_SET_EVENT_MASK, sizeof(events), events); @@ -771,6 +798,27 @@ static int hci_init4_req(struct hci_request *req, unsigned long opt) sizeof(support), &support); } + /* Set Suggested Default Data Length to maximum if supported */ + if (hdev->le_features[0] & HCI_LE_DATA_LEN_EXT) { + struct hci_cp_le_write_def_data_len cp; + + cp.tx_len = hdev->le_max_tx_len; + cp.tx_time = hdev->le_max_tx_time; + hci_req_add(req, HCI_OP_LE_WRITE_DEF_DATA_LEN, sizeof(cp), &cp); + } + + /* Set Default PHY parameters if command is supported */ + if (hdev->commands[35] & 0x20) { + struct hci_cp_le_set_default_phy cp; + + /* No transmitter PHY or receiver PHY preferences */ + cp.all_phys = 0x03; + cp.tx_phys = 0; + cp.rx_phys = 0; + + hci_req_add(req, HCI_OP_LE_SET_DEFAULT_PHY, sizeof(cp), &cp); + } + return 0; } @@ -1384,6 +1432,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) * completed. */ if (test_bit(HCI_QUIRK_NON_PERSISTENT_DIAG, &hdev->quirks) && + !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && hci_dev_test_flag(hdev, HCI_VENDOR_DIAG) && hdev->set_diag) ret = hdev->set_diag(hdev, true); @@ -3047,15 +3096,14 @@ int hci_register_dev(struct hci_dev *hdev) BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); - hdev->workqueue = alloc_workqueue("%s", WQ_HIGHPRI | WQ_UNBOUND | - WQ_MEM_RECLAIM, 1, hdev->name); + hdev->workqueue = alloc_ordered_workqueue("%s", WQ_HIGHPRI, hdev->name); if (!hdev->workqueue) { error = -ENOMEM; goto err; } - hdev->req_workqueue = alloc_workqueue("%s", WQ_HIGHPRI | WQ_UNBOUND | - WQ_MEM_RECLAIM, 1, hdev->name); + hdev->req_workqueue = alloc_ordered_workqueue("%s", WQ_HIGHPRI, + hdev->name); if (!hdev->req_workqueue) { destroy_workqueue(hdev->workqueue); error = -ENOMEM; @@ -3217,7 +3265,7 @@ int hci_reset_dev(struct hci_dev *hdev) return -ENOMEM; hci_skb_pkt_type(skb) = HCI_EVENT_PKT; - memcpy(skb_put(skb, 3), hw_err, 3); + skb_put_data(skb, hw_err, 3); /* Send Hardware Error to upper stack */ return hci_recv_frame(hdev, skb); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index b5faff458d8b..b73ac149de34 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -299,12 +299,12 @@ struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen, if (!skb) return NULL; - hdr = (struct hci_command_hdr *) skb_put(skb, HCI_COMMAND_HDR_SIZE); + hdr = skb_put(skb, HCI_COMMAND_HDR_SIZE); hdr->opcode = cpu_to_le16(opcode); hdr->plen = plen; if (plen) - memcpy(skb_put(skb, plen), param, plen); + skb_put_data(skb, param, plen); BT_DBG("skb len %d", skb->len); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 638bf0e1a2e3..65d734c165bd 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -332,7 +332,7 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) return; /* Put header before the data */ - hdr = (void *)skb_push(skb_copy, HCI_MON_HDR_SIZE); + hdr = skb_push(skb_copy, HCI_MON_HDR_SIZE); hdr->opcode = opcode; hdr->index = cpu_to_le16(hdev->id); hdr->len = cpu_to_le16(skb->len); @@ -379,11 +379,11 @@ void hci_send_monitor_ctrl_event(struct hci_dev *hdev, u16 event, put_unaligned_le16(event, skb_put(skb, 2)); if (data) - memcpy(skb_put(skb, data_len), data, data_len); + skb_put_data(skb, data, data_len); skb->tstamp = tstamp; - hdr = (void *)skb_push(skb, HCI_MON_HDR_SIZE); + hdr = skb_push(skb, HCI_MON_HDR_SIZE); hdr->opcode = cpu_to_le16(HCI_MON_CTRL_EVENT); hdr->index = index; hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); @@ -410,7 +410,7 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) if (!skb) return NULL; - ni = (void *)skb_put(skb, HCI_MON_NEW_INDEX_SIZE); + ni = skb_put(skb, HCI_MON_NEW_INDEX_SIZE); ni->type = hdev->dev_type; ni->bus = hdev->bus; bacpy(&ni->bdaddr, &hdev->bdaddr); @@ -438,7 +438,7 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) if (!skb) return NULL; - ii = (void *)skb_put(skb, HCI_MON_INDEX_INFO_SIZE); + ii = skb_put(skb, HCI_MON_INDEX_INFO_SIZE); bacpy(&ii->bdaddr, &hdev->bdaddr); ii->manufacturer = cpu_to_le16(hdev->manufacturer); @@ -467,7 +467,7 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) __net_timestamp(skb); - hdr = (void *)skb_push(skb, HCI_MON_HDR_SIZE); + hdr = skb_push(skb, HCI_MON_HDR_SIZE); hdr->opcode = opcode; hdr->index = cpu_to_le16(hdev->id); hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); @@ -515,14 +515,14 @@ static struct sk_buff *create_monitor_ctrl_open(struct sock *sk) put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); put_unaligned_le16(format, skb_put(skb, 2)); - memcpy(skb_put(skb, sizeof(ver)), ver, sizeof(ver)); + skb_put_data(skb, ver, sizeof(ver)); put_unaligned_le32(flags, skb_put(skb, 4)); - *skb_put(skb, 1) = TASK_COMM_LEN; - memcpy(skb_put(skb, TASK_COMM_LEN), hci_pi(sk)->comm, TASK_COMM_LEN); + skb_put_u8(skb, TASK_COMM_LEN); + skb_put_data(skb, hci_pi(sk)->comm, TASK_COMM_LEN); __net_timestamp(skb); - hdr = (void *)skb_push(skb, HCI_MON_HDR_SIZE); + hdr = skb_push(skb, HCI_MON_HDR_SIZE); hdr->opcode = cpu_to_le16(HCI_MON_CTRL_OPEN); if (hci_pi(sk)->hdev) hdr->index = cpu_to_le16(hci_pi(sk)->hdev->id); @@ -560,7 +560,7 @@ static struct sk_buff *create_monitor_ctrl_close(struct sock *sk) __net_timestamp(skb); - hdr = (void *)skb_push(skb, HCI_MON_HDR_SIZE); + hdr = skb_push(skb, HCI_MON_HDR_SIZE); hdr->opcode = cpu_to_le16(HCI_MON_CTRL_CLOSE); if (hci_pi(sk)->hdev) hdr->index = cpu_to_le16(hci_pi(sk)->hdev->id); @@ -586,11 +586,11 @@ static struct sk_buff *create_monitor_ctrl_command(struct sock *sk, u16 index, put_unaligned_le16(opcode, skb_put(skb, 2)); if (buf) - memcpy(skb_put(skb, len), buf, len); + skb_put_data(skb, buf, len); __net_timestamp(skb); - hdr = (void *)skb_push(skb, HCI_MON_HDR_SIZE); + hdr = skb_push(skb, HCI_MON_HDR_SIZE); hdr->opcode = cpu_to_le16(HCI_MON_CTRL_COMMAND); hdr->index = cpu_to_le16(index); hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); @@ -616,7 +616,7 @@ send_monitor_note(struct sock *sk, const char *fmt, ...) va_start(args, fmt); vsprintf(skb_put(skb, len), fmt, args); - *skb_put(skb, 1) = 0; + *(u8 *)skb_put(skb, 1) = 0; va_end(args); __net_timestamp(skb); @@ -703,11 +703,11 @@ static void hci_si_event(struct hci_dev *hdev, int type, int dlen, void *data) if (!skb) return; - hdr = (void *)skb_put(skb, HCI_EVENT_HDR_SIZE); + hdr = skb_put(skb, HCI_EVENT_HDR_SIZE); hdr->evt = HCI_EV_STACK_INTERNAL; hdr->plen = sizeof(*ev) + dlen; - ev = (void *)skb_put(skb, sizeof(*ev) + dlen); + ev = skb_put(skb, sizeof(*ev) + dlen); ev->type = type; memcpy(ev->data, data, dlen); diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 0bec4588c3c8..002743ea509c 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -36,6 +36,7 @@ #define VERSION "1.2" static DECLARE_RWSEM(hidp_session_sem); +static DECLARE_WAIT_QUEUE_HEAD(hidp_session_wq); static LIST_HEAD(hidp_session_list); static unsigned char hidp_keycode[256] = { @@ -112,9 +113,9 @@ static int hidp_send_message(struct hidp_session *session, struct socket *sock, return -ENOMEM; } - *skb_put(skb, 1) = hdr; + skb_put_u8(skb, hdr); if (data && size > 0) - memcpy(skb_put(skb, size), data, size); + skb_put_data(skb, data, size); skb_queue_tail(transmit, skb); wake_up_interruptible(sk_sleep(sk)); @@ -1068,12 +1069,12 @@ static int hidp_session_start_sync(struct hidp_session *session) * Wake up session thread and notify it to stop. This is asynchronous and * returns immediately. Call this whenever a runtime error occurs and you want * the session to stop. - * Note: wake_up_process() performs any necessary memory-barriers for us. + * Note: wake_up_interruptible() performs any necessary memory-barriers for us. */ static void hidp_session_terminate(struct hidp_session *session) { atomic_inc(&session->terminate); - wake_up_process(session->task); + wake_up_interruptible(&hidp_session_wq); } /* @@ -1180,7 +1181,9 @@ static void hidp_session_run(struct hidp_session *session) struct sock *ctrl_sk = session->ctrl_sock->sk; struct sock *intr_sk = session->intr_sock->sk; struct sk_buff *skb; + DEFINE_WAIT_FUNC(wait, woken_wake_function); + add_wait_queue(&hidp_session_wq, &wait); for (;;) { /* * This thread can be woken up two ways: @@ -1188,12 +1191,10 @@ static void hidp_session_run(struct hidp_session *session) * session->terminate flag and wakes this thread up. * - Via modifying the socket state of ctrl/intr_sock. This * thread is woken up by ->sk_state_changed(). - * - * Note: set_current_state() performs any necessary - * memory-barriers for us. */ - set_current_state(TASK_INTERRUPTIBLE); + /* Ensure session->terminate is updated */ + smp_mb__before_atomic(); if (atomic_read(&session->terminate)) break; @@ -1227,11 +1228,22 @@ static void hidp_session_run(struct hidp_session *session) hidp_process_transmit(session, &session->ctrl_transmit, session->ctrl_sock); - schedule(); + wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); } + remove_wait_queue(&hidp_session_wq, &wait); atomic_inc(&session->terminate); - set_current_state(TASK_RUNNING); + + /* Ensure session->terminate is updated */ + smp_mb__after_atomic(); +} + +static int hidp_session_wake_function(wait_queue_entry_t *wait, + unsigned int mode, + int sync, void *key) +{ + wake_up_interruptible(&hidp_session_wq); + return false; } /* @@ -1244,7 +1256,8 @@ static void hidp_session_run(struct hidp_session *session) static int hidp_session_thread(void *arg) { struct hidp_session *session = arg; - wait_queue_t ctrl_wait, intr_wait; + DEFINE_WAIT_FUNC(ctrl_wait, hidp_session_wake_function); + DEFINE_WAIT_FUNC(intr_wait, hidp_session_wake_function); BT_DBG("session %p", session); @@ -1254,8 +1267,6 @@ static int hidp_session_thread(void *arg) set_user_nice(current, -15); hidp_set_timer(session); - init_waitqueue_entry(&ctrl_wait, current); - init_waitqueue_entry(&intr_wait, current); add_wait_queue(sk_sleep(session->ctrl_sock->sk), &ctrl_wait); add_wait_queue(sk_sleep(session->intr_sock->sk), &intr_wait); /* This memory barrier is paired with wq_has_sleeper(). See diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index f88ac99528ce..303c779bfe38 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1048,7 +1048,7 @@ static struct sk_buff *l2cap_create_sframe_pdu(struct l2cap_chan *chan, if (!skb) return ERR_PTR(-ENOMEM); - lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); + lh = skb_put(skb, L2CAP_HDR_SIZE); lh->len = cpu_to_le16(hlen - L2CAP_HDR_SIZE); lh->cid = cpu_to_le16(chan->dcid); @@ -2182,7 +2182,7 @@ static struct sk_buff *l2cap_create_connless_pdu(struct l2cap_chan *chan, return skb; /* Create L2CAP header */ - lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); + lh = skb_put(skb, L2CAP_HDR_SIZE); lh->cid = cpu_to_le16(chan->dcid); lh->len = cpu_to_le16(len + L2CAP_PSMLEN_SIZE); put_unaligned(chan->psm, (__le16 *) skb_put(skb, L2CAP_PSMLEN_SIZE)); @@ -2213,7 +2213,7 @@ static struct sk_buff *l2cap_create_basic_pdu(struct l2cap_chan *chan, return skb; /* Create L2CAP header */ - lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); + lh = skb_put(skb, L2CAP_HDR_SIZE); lh->cid = cpu_to_le16(chan->dcid); lh->len = cpu_to_le16(len); @@ -2255,7 +2255,7 @@ static struct sk_buff *l2cap_create_iframe_pdu(struct l2cap_chan *chan, return skb; /* Create L2CAP header */ - lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); + lh = skb_put(skb, L2CAP_HDR_SIZE); lh->cid = cpu_to_le16(chan->dcid); lh->len = cpu_to_le16(len + (hlen - L2CAP_HDR_SIZE)); @@ -2373,7 +2373,7 @@ static struct sk_buff *l2cap_create_le_flowctl_pdu(struct l2cap_chan *chan, return skb; /* Create L2CAP header */ - lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); + lh = skb_put(skb, L2CAP_HDR_SIZE); lh->cid = cpu_to_le16(chan->dcid); lh->len = cpu_to_le16(len + (hlen - L2CAP_HDR_SIZE)); @@ -2908,7 +2908,7 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, u8 code, if (!skb) return NULL; - lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); + lh = skb_put(skb, L2CAP_HDR_SIZE); lh->len = cpu_to_le16(L2CAP_CMD_HDR_SIZE + dlen); if (conn->hcon->type == LE_LINK) @@ -2916,14 +2916,14 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, u8 code, else lh->cid = cpu_to_le16(L2CAP_CID_SIGNALING); - cmd = (struct l2cap_cmd_hdr *) skb_put(skb, L2CAP_CMD_HDR_SIZE); + cmd = skb_put(skb, L2CAP_CMD_HDR_SIZE); cmd->code = code; cmd->ident = ident; cmd->len = cpu_to_le16(dlen); if (dlen) { count -= L2CAP_HDR_SIZE + L2CAP_CMD_HDR_SIZE; - memcpy(skb_put(skb, count), data, count); + skb_put_data(skb, data, count); data += count; } @@ -2938,7 +2938,7 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, u8 code, if (!*frag) goto fail; - memcpy(skb_put(*frag, count), data, count); + skb_put_data(*frag, data, count); len -= count; data += count; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 507b80d59dec..67a8642f57ea 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -87,7 +87,8 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) BT_DBG("sk %p", sk); - if (!addr || addr->sa_family != AF_BLUETOOTH) + if (!addr || alen < offsetofend(struct sockaddr, sa_family) || + addr->sa_family != AF_BLUETOOTH) return -EINVAL; memset(&la, 0, sizeof(la)); @@ -181,7 +182,7 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, BT_DBG("sk %p", sk); - if (!addr || alen < sizeof(addr->sa_family) || + if (!addr || alen < offsetofend(struct sockaddr, sa_family) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; diff --git a/net/bluetooth/mgmt_util.c b/net/bluetooth/mgmt_util.c index c933bd08c1fe..0d0a6d77b9e8 100644 --- a/net/bluetooth/mgmt_util.c +++ b/net/bluetooth/mgmt_util.c @@ -44,11 +44,11 @@ static struct sk_buff *create_monitor_ctrl_event(__le16 index, u32 cookie, put_unaligned_le16(opcode, skb_put(skb, 2)); if (buf) - memcpy(skb_put(skb, len), buf, len); + skb_put_data(skb, buf, len); __net_timestamp(skb); - hdr = (void *)skb_push(skb, HCI_MON_HDR_SIZE); + hdr = skb_push(skb, HCI_MON_HDR_SIZE); hdr->opcode = cpu_to_le16(HCI_MON_CTRL_EVENT); hdr->index = index; hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); @@ -66,7 +66,7 @@ int mgmt_send_event(u16 event, struct hci_dev *hdev, unsigned short channel, if (!skb) return -ENOMEM; - hdr = (void *) skb_put(skb, sizeof(*hdr)); + hdr = skb_put(skb, sizeof(*hdr)); hdr->opcode = cpu_to_le16(event); if (hdev) hdr->index = cpu_to_le16(hdev->id); @@ -75,7 +75,7 @@ int mgmt_send_event(u16 event, struct hci_dev *hdev, unsigned short channel, hdr->len = cpu_to_le16(data_len); if (data) - memcpy(skb_put(skb, data_len), data, data_len); + skb_put_data(skb, data, data_len); /* Time stamp */ __net_timestamp(skb); @@ -103,13 +103,13 @@ int mgmt_cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status) if (!skb) return -ENOMEM; - hdr = (void *) skb_put(skb, sizeof(*hdr)); + hdr = skb_put(skb, sizeof(*hdr)); hdr->opcode = cpu_to_le16(MGMT_EV_CMD_STATUS); hdr->index = cpu_to_le16(index); hdr->len = cpu_to_le16(sizeof(*ev)); - ev = (void *) skb_put(skb, sizeof(*ev)); + ev = skb_put(skb, sizeof(*ev)); ev->status = status; ev->opcode = cpu_to_le16(cmd); @@ -147,13 +147,13 @@ int mgmt_cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status, if (!skb) return -ENOMEM; - hdr = (void *) skb_put(skb, sizeof(*hdr)); + hdr = skb_put(skb, sizeof(*hdr)); hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE); hdr->index = cpu_to_le16(index); hdr->len = cpu_to_le16(sizeof(*ev) + rp_len); - ev = (void *) skb_put(skb, sizeof(*ev) + rp_len); + ev = skb_put(skb, sizeof(*ev) + rp_len); ev->opcode = cpu_to_le16(cmd); ev->status = status; diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 8ebca9033d60..4a0b41d75c84 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -863,7 +863,7 @@ static int rfcomm_queue_disc(struct rfcomm_dlc *d) if (!skb) return -ENOMEM; - cmd = (void *) __skb_put(skb, sizeof(*cmd)); + cmd = __skb_put(skb, sizeof(*cmd)); cmd->addr = d->addr; cmd->ctrl = __ctrl(RFCOMM_DISC, 1); cmd->len = __len8(0); @@ -1149,10 +1149,10 @@ static void rfcomm_make_uih(struct sk_buff *skb, u8 addr) u8 *crc; if (len > 127) { - hdr = (void *) skb_push(skb, 4); + hdr = skb_push(skb, 4); put_unaligned(cpu_to_le16(__len16(len)), (__le16 *) &hdr->len); } else { - hdr = (void *) skb_push(skb, 3); + hdr = skb_push(skb, 3); hdr->len = __len8(len); } hdr->addr = addr; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index ac3c650cb234..1aaccf637479 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -197,7 +197,7 @@ static void rfcomm_sock_kill(struct sock *sk) if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket) return; - BT_DBG("sk %p state %d refcnt %d", sk, sk->sk_state, atomic_read(&sk->sk_refcnt)); + BT_DBG("sk %p state %d refcnt %d", sk, sk->sk_state, refcount_read(&sk->sk_refcnt)); /* Kill poor orphan */ bt_sock_unlink(&rfcomm_sk_list, sk); @@ -339,7 +339,8 @@ static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr struct sock *sk = sock->sk; int len, err = 0; - if (!addr || addr->sa_family != AF_BLUETOOTH) + if (!addr || addr_len < offsetofend(struct sockaddr, sa_family) || + addr->sa_family != AF_BLUETOOTH) return -EINVAL; memset(&sa, 0, sizeof(sa)); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 2f2cb5e27cdd..5f3074cb6b4d 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -798,7 +798,7 @@ static int rfcomm_tty_write(struct tty_struct *tty, const unsigned char *buf, in skb_reserve(skb, RFCOMM_SKB_HEAD_RESERVE); - memcpy(skb_put(skb, size), buf + sent, size); + skb_put_data(skb, buf + sent, size); rfcomm_dlc_send_noerror(dlc, skb); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 728e0c8dc8e7..795e920a3281 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -524,10 +524,8 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr); - if (!addr || addr->sa_family != AF_BLUETOOTH) - return -EINVAL; - - if (addr_len < sizeof(struct sockaddr_sco)) + if (!addr || addr_len < sizeof(struct sockaddr_sco) || + addr->sa_family != AF_BLUETOOTH) return -EINVAL; lock_sock(sk); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 14585edc9439..a0ef89772c36 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -23,6 +23,7 @@ #include <linux/debugfs.h> #include <linux/scatterlist.h> #include <linux/crypto.h> +#include <crypto/algapi.h> #include <crypto/b128ops.h> #include <crypto/hash.h> @@ -523,7 +524,7 @@ bool smp_irk_matches(struct hci_dev *hdev, const u8 irk[16], if (err) return false; - return !memcmp(bdaddr->b, hash, 3); + return !crypto_memneq(bdaddr->b, hash, 3); } int smp_generate_rpa(struct hci_dev *hdev, const u8 irk[16], bdaddr_t *rpa) @@ -579,7 +580,7 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]) /* This is unlikely, but we need to check that * we didn't accidentially generate a debug key. */ - if (memcmp(smp->local_sk, debug_sk, 32)) + if (crypto_memneq(smp->local_sk, debug_sk, 32)) break; } smp->debug_key = false; @@ -993,7 +994,7 @@ static u8 smp_random(struct smp_chan *smp) if (ret) return SMP_UNSPECIFIED; - if (memcmp(smp->pcnf, confirm, sizeof(smp->pcnf)) != 0) { + if (crypto_memneq(smp->pcnf, confirm, sizeof(smp->pcnf))) { BT_ERR("Pairing failed (confirmation values mismatch)"); return SMP_CONFIRM_FAILED; } @@ -1512,7 +1513,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) smp->rrnd, r, cfm)) return SMP_UNSPECIFIED; - if (memcmp(smp->pcnf, cfm, 16)) + if (crypto_memneq(smp->pcnf, cfm, 16)) return SMP_CONFIRM_FAILED; smp->passkey_round++; @@ -1908,7 +1909,7 @@ static u8 sc_send_public_key(struct smp_chan *smp) /* This is unlikely, but we need to check that * we didn't accidentially generate a debug key. */ - if (memcmp(smp->local_sk, debug_sk, 32)) + if (crypto_memneq(smp->local_sk, debug_sk, 32)) break; } } @@ -2176,7 +2177,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) if (err) return SMP_UNSPECIFIED; - if (memcmp(smp->pcnf, cfm, 16)) + if (crypto_memneq(smp->pcnf, cfm, 16)) return SMP_CONFIRM_FAILED; } else { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), @@ -2660,7 +2661,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) if (err) return SMP_UNSPECIFIED; - if (memcmp(cfm.confirm_val, smp->pcnf, 16)) + if (crypto_memneq(cfm.confirm_val, smp->pcnf, 16)) return SMP_CONFIRM_FAILED; } @@ -2693,7 +2694,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) else hcon->pending_sec_level = BT_SECURITY_FIPS; - if (!memcmp(debug_pk, smp->remote_pk, 64)) + if (!crypto_memneq(debug_pk, smp->remote_pk, 64)) set_bit(SMP_FLAG_DEBUG_KEY, &smp->flags); if (smp->method == DSP_PASSKEY) { @@ -2792,7 +2793,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) if (err) return SMP_UNSPECIFIED; - if (memcmp(check->e, e, 16)) + if (crypto_memneq(check->e, e, 16)) return SMP_DHKEY_CHECK_FAILED; if (!hcon->out) { @@ -3506,10 +3507,10 @@ static int __init test_debug_key(void) if (!generate_ecdh_keys(pk, sk)) return -EINVAL; - if (memcmp(sk, debug_sk, 32)) + if (crypto_memneq(sk, debug_sk, 32)) return -EINVAL; - if (memcmp(pk, debug_pk, 64)) + if (crypto_memneq(pk, debug_pk, 64)) return -EINVAL; return 0; @@ -3529,7 +3530,7 @@ static int __init test_ah(struct crypto_cipher *tfm_aes) if (err) return err; - if (memcmp(res, exp, 3)) + if (crypto_memneq(res, exp, 3)) return -EINVAL; return 0; @@ -3559,7 +3560,7 @@ static int __init test_c1(struct crypto_cipher *tfm_aes) if (err) return err; - if (memcmp(res, exp, 16)) + if (crypto_memneq(res, exp, 16)) return -EINVAL; return 0; @@ -3584,7 +3585,7 @@ static int __init test_s1(struct crypto_cipher *tfm_aes) if (err) return err; - if (memcmp(res, exp, 16)) + if (crypto_memneq(res, exp, 16)) return -EINVAL; return 0; @@ -3616,7 +3617,7 @@ static int __init test_f4(struct crypto_shash *tfm_cmac) if (err) return err; - if (memcmp(res, exp, 16)) + if (crypto_memneq(res, exp, 16)) return -EINVAL; return 0; @@ -3650,10 +3651,10 @@ static int __init test_f5(struct crypto_shash *tfm_cmac) if (err) return err; - if (memcmp(mackey, exp_mackey, 16)) + if (crypto_memneq(mackey, exp_mackey, 16)) return -EINVAL; - if (memcmp(ltk, exp_ltk, 16)) + if (crypto_memneq(ltk, exp_ltk, 16)) return -EINVAL; return 0; @@ -3686,7 +3687,7 @@ static int __init test_f6(struct crypto_shash *tfm_cmac) if (err) return err; - if (memcmp(res, exp, 16)) + if (crypto_memneq(res, exp, 16)) return -EINVAL; return 0; @@ -3740,7 +3741,7 @@ static int __init test_h6(struct crypto_shash *tfm_cmac) if (err) return err; - if (memcmp(res, exp, 16)) + if (crypto_memneq(res, exp, 16)) return -EINVAL; return 0; diff --git a/net/bridge/br.c b/net/bridge/br.c index 889e5640455f..1407d1ba7577 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -121,7 +121,7 @@ static struct notifier_block br_device_notifier = { .notifier_call = br_device_event }; -/* called with RTNL */ +/* called with RTNL or RCU */ static int br_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -131,27 +131,36 @@ static int br_switchdev_event(struct notifier_block *unused, struct switchdev_notifier_fdb_info *fdb_info; int err = NOTIFY_DONE; - p = br_port_get_rtnl(dev); + p = br_port_get_rtnl_rcu(dev); if (!p) goto out; br = p->br; switch (event) { - case SWITCHDEV_FDB_ADD: + case SWITCHDEV_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, fdb_info->vid); - if (err) + if (err) { err = notifier_from_errno(err); + break; + } + br_fdb_offloaded_set(br, p, fdb_info->addr, + fdb_info->vid); break; - case SWITCHDEV_FDB_DEL: + case SWITCHDEV_FDB_DEL_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_del(br, p, fdb_info->addr, fdb_info->vid); if (err) err = notifier_from_errno(err); break; + case SWITCHDEV_FDB_OFFLOADED: + fdb_info = ptr; + br_fdb_offloaded_set(br, p, fdb_info->addr, + fdb_info->vid); + break; } out: diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index f0f3447e8aa4..861ae2a165f4 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -34,11 +34,11 @@ static struct lock_class_key bridge_netdev_addr_lock_key; netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); - const unsigned char *dest = skb->data; struct net_bridge_fdb_entry *dst; struct net_bridge_mdb_entry *mdst; struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); const struct nf_br_ops *nf_ops; + const unsigned char *dest; u16 vid = 0; rcu_read_lock(); @@ -61,6 +61,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid)) goto out; + dest = eth_hdr(skb)->h_dest; if (is_broadcast_ether_addr(dest)) { br_flood(br, skb, BR_PKT_BROADCAST, false, true); } else if (is_multicast_ether_addr(dest)) { diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index ab0c7cc8448f..a5e4a736a984 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -511,6 +511,7 @@ static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head, fdb->is_static = is_static; fdb->added_by_user = 0; fdb->added_by_external_learn = 0; + fdb->offloaded = 0; fdb->updated = fdb->used = jiffies; hlist_add_head_rcu(&fdb->hlist, head); } @@ -647,11 +648,16 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, ndm->ndm_family = AF_BRIDGE; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = fdb->added_by_external_learn ? NTF_EXT_LEARNED : 0; + ndm->ndm_flags = 0; ndm->ndm_type = 0; ndm->ndm_ifindex = fdb->dst ? fdb->dst->dev->ifindex : br->dev->ifindex; ndm->ndm_state = fdb_to_nud(br, fdb); + if (fdb->offloaded) + ndm->ndm_flags |= NTF_OFFLOADED; + if (fdb->added_by_external_learn) + ndm->ndm_flags |= NTF_EXT_LEARNED; + if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr)) goto nla_put_failure; if (nla_put_u32(skb, NDA_MASTER, br->dev->ifindex)) @@ -690,6 +696,8 @@ static void fdb_notify(struct net_bridge *br, struct sk_buff *skb; int err = -ENOBUFS; + br_switchdev_fdb_notify(fdb, type); + skb = nlmsg_new(fdb_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) goto errout; @@ -1071,11 +1079,11 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p) int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid) { - struct hlist_head *head; struct net_bridge_fdb_entry *fdb; + struct hlist_head *head; + bool modified = false; int err = 0; - ASSERT_RTNL(); spin_lock_bh(&br->hash_lock); head = &br->hash[br_mac_hash(addr, vid)]; @@ -1088,14 +1096,25 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, } fdb->added_by_external_learn = 1; fdb_notify(br, fdb, RTM_NEWNEIGH); - } else if (fdb->added_by_external_learn) { - /* Refresh entry */ - fdb->updated = fdb->used = jiffies; - } else if (!fdb->added_by_user) { - /* Take over SW learned entry */ - fdb->added_by_external_learn = 1; + } else { fdb->updated = jiffies; - fdb_notify(br, fdb, RTM_NEWNEIGH); + + if (fdb->dst != p) { + fdb->dst = p; + modified = true; + } + + if (fdb->added_by_external_learn) { + /* Refresh entry */ + fdb->used = jiffies; + } else if (!fdb->added_by_user) { + /* Take over SW learned entry */ + fdb->added_by_external_learn = 1; + modified = true; + } + + if (modified) + fdb_notify(br, fdb, RTM_NEWNEIGH); } err_unlock: @@ -1110,7 +1129,6 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, struct net_bridge_fdb_entry *fdb; int err = 0; - ASSERT_RTNL(); spin_lock_bh(&br->hash_lock); fdb = br_fdb_find(br, addr, vid); @@ -1123,3 +1141,17 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, return err; } + +void br_fdb_offloaded_set(struct net_bridge *br, struct net_bridge_port *p, + const unsigned char *addr, u16 vid) +{ + struct net_bridge_fdb_entry *fdb; + + spin_lock_bh(&br->hash_lock); + + fdb = br_fdb_find(br, addr, vid); + if (fdb) + fdb->offloaded = 1; + + spin_unlock_bh(&br->hash_lock); +} diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 7f8d05cf9065..f3aef22931ab 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -138,7 +138,7 @@ void br_manage_promisc(struct net_bridge *br) /* If vlan filtering is disabled or bridge interface is placed * into promiscuous mode, place all ports in promiscuous mode. */ - if ((br->dev->flags & IFF_PROMISC) || !br_vlan_enabled(br)) + if ((br->dev->flags & IFF_PROMISC) || !br_vlan_enabled(br->dev)) set_all = true; list_for_each_entry(p, &br->port_list, list) { diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 013f2290bfa5..7637f58c1226 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -131,11 +131,11 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_bridge_port *p = br_port_get_rcu(skb->dev); - const unsigned char *dest = eth_hdr(skb)->h_dest; enum br_pkt_type pkt_type = BR_PKT_UNICAST; struct net_bridge_fdb_entry *dst = NULL; struct net_bridge_mdb_entry *mdst; bool local_rcv, mcast_hit = false; + const unsigned char *dest; struct net_bridge *br; u16 vid = 0; @@ -153,6 +153,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false); local_rcv = !!(br->dev->flags & IFF_PROMISC); + dest = eth_hdr(skb)->h_dest; if (is_multicast_ether_addr(dest)) { /* by definition the broadcast is also a multicast address */ if (is_broadcast_ether_addr(dest)) { diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index b0845480a3ae..a0b11e7d67d9 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -323,7 +323,8 @@ static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p, __mdb_entry_to_br_ip(entry, &complete_info->ip); mdb.obj.complete_priv = complete_info; mdb.obj.complete = br_mdb_complete; - switchdev_port_obj_add(port_dev, &mdb.obj); + if (switchdev_port_obj_add(port_dev, &mdb.obj)) + kfree(complete_info); } } else if (port_dev && type == RTM_DELMDB) { switchdev_port_obj_del(port_dev, &mdb.obj); @@ -599,7 +600,7 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, return -EINVAL; vg = nbp_vlan_group(p); - if (br_vlan_enabled(br) && vg && entry->vid == 0) { + if (br_vlan_enabled(br->dev) && vg && entry->vid == 0) { list_for_each_entry(v, &vg->vlan_list, vlist) { entry->vid = v->vid; err = __br_mdb_add(net, br, entry); @@ -694,7 +695,7 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, return -EINVAL; vg = nbp_vlan_group(p); - if (br_vlan_enabled(br) && vg && entry->vid == 0) { + if (br_vlan_enabled(br->dev) && vg && entry->vid == 0) { list_for_each_entry(v, &vg->vlan_list, vlist) { entry->vid = v->vid; err = __br_mdb_del(br, entry); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index faa7261a992f..8dc5c8d69bcd 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2176,6 +2176,14 @@ unlock: return err; } +bool br_multicast_enabled(const struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + + return !br->multicast_disabled; +} +EXPORT_SYMBOL_GPL(br_multicast_enabled); + int br_multicast_set_querier(struct net_bridge *br, unsigned long val) { unsigned long max_delay; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 067cf0313449..2261e5194c82 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -149,12 +149,12 @@ static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = skb->nf_bridge; - if (atomic_read(&nf_bridge->use) > 1) { + if (refcount_read(&nf_bridge->use) > 1) { struct nf_bridge_info *tmp = nf_bridge_alloc(skb); if (tmp) { memcpy(tmp, nf_bridge, sizeof(struct nf_bridge_info)); - atomic_set(&tmp->use, 1); + refcount_set(&tmp->use, 1); } nf_bridge_put(nf_bridge); nf_bridge = tmp; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 32bd3ead9ba1..3bc890716c89 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -662,16 +662,26 @@ static int br_set_port_state(struct net_bridge_port *p, u8 state) } /* Set/clear or port flags based on attribute */ -static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[], - int attrtype, unsigned long mask) +static int br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[], + int attrtype, unsigned long mask) { - if (tb[attrtype]) { - u8 flag = nla_get_u8(tb[attrtype]); - if (flag) - p->flags |= mask; - else - p->flags &= ~mask; - } + unsigned long flags; + int err; + + if (!tb[attrtype]) + return 0; + + if (nla_get_u8(tb[attrtype])) + flags = p->flags | mask; + else + flags = p->flags & ~mask; + + err = br_switchdev_set_port_flag(p, flags, mask); + if (err) + return err; + + p->flags = flags; + return 0; } /* Process bridge protocol info on port */ @@ -681,20 +691,55 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) bool br_vlan_tunnel_old = false; int err; - br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); - br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); - br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE); - br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); - br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); - br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); - br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); - br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST, BR_MULTICAST_TO_UNICAST); - br_set_port_flag(p, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD); - br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); - br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); + err = br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); + if (err) + return err; + + err = br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); + if (err) + return err; + + err = br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE); + if (err) + return err; + + err = br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); + if (err) + return err; + + err = br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); + if (err) + return err; + + err = br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); + if (err) + return err; + + err = br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); + if (err) + return err; + + err = br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST, BR_MULTICAST_TO_UNICAST); + if (err) + return err; + + err = br_set_port_flag(p, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD); + if (err) + return err; + + err = br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); + if (err) + return err; + + err = br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); + if (err) + return err; br_vlan_tunnel_old = (p->flags & BR_VLAN_TUNNEL) ? true : false; - br_set_port_flag(p, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL); + err = br_set_port_flag(p, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL); + if (err) + return err; + if (br_vlan_tunnel_old && !(p->flags & BR_VLAN_TUNNEL)) nbp_vlan_tunnel_info_flush(p); @@ -813,7 +858,9 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) return err; } -static int br_validate(struct nlattr *tb[], struct nlattr *data[]) + +static int br_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) @@ -850,7 +897,8 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[]) static int br_port_slave_changelink(struct net_device *brdev, struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(brdev); int ret; @@ -915,7 +963,8 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(brdev); int err; @@ -1168,7 +1217,8 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], } static int br_dev_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); int err; @@ -1183,7 +1233,7 @@ static int br_dev_newlink(struct net *src_net, struct net_device *dev, if (err) return err; - err = br_changelink(dev, tb, data); + err = br_changelink(dev, tb, data, extack); if (err) unregister_netdevice(dev); return err; @@ -1251,7 +1301,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) u32 ageing_time = jiffies_to_clock_t(br->ageing_time); u32 stp_enabled = br->stp_enabled; u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; - u8 vlan_enabled = br_vlan_enabled(br); + u8 vlan_enabled = br_vlan_enabled(br->dev); u64 clockval; clockval = br_timer_value(&br->hello_timer); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 0d177280aa84..fd9ee73e0a6d 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -21,6 +21,7 @@ #include <net/ip6_fib.h> #include <linux/if_vlan.h> #include <linux/rhashtable.h> +#include <linux/refcount.h> #define BR_HASH_BITS 8 #define BR_HASH_SIZE (1 << BR_HASH_BITS) @@ -127,7 +128,7 @@ struct net_bridge_vlan { struct net_bridge_port *port; }; union { - atomic_t refcnt; + refcount_t refcnt; struct net_bridge_vlan *brvlan; }; @@ -169,7 +170,8 @@ struct net_bridge_fdb_entry { unsigned char is_local:1, is_static:1, added_by_user:1, - added_by_external_learn:1; + added_by_external_learn:1, + offloaded:1; /* write-heavy members should not affect lookups */ unsigned long updated ____cacheline_aligned_in_smp; @@ -284,6 +286,12 @@ static inline struct net_bridge_port *br_port_get_rtnl(const struct net_device * rtnl_dereference(dev->rx_handler_data) : NULL; } +static inline struct net_bridge_port *br_port_get_rtnl_rcu(const struct net_device *dev) +{ + return br_port_exists(dev) ? + rcu_dereference_rtnl(dev->rx_handler_data) : NULL; +} + struct net_bridge { spinlock_t lock; spinlock_t hash_lock; @@ -530,6 +538,8 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid); int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid); +void br_fdb_offloaded_set(struct net_bridge *br, struct net_bridge_port *p, + const unsigned char *addr, u16 vid); /* br_forward.c */ enum br_pkt_type { @@ -854,10 +864,6 @@ static inline u16 br_get_pvid(const struct net_bridge_vlan_group *vg) return vg->pvid; } -static inline int br_vlan_enabled(struct net_bridge *br) -{ - return br->vlan_enabled; -} #else static inline bool br_allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, @@ -945,11 +951,6 @@ static inline u16 br_get_pvid(const struct net_bridge_vlan_group *vg) return 0; } -static inline int br_vlan_enabled(struct net_bridge *br) -{ - return 0; -} - static inline int __br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) { @@ -1085,6 +1086,11 @@ void nbp_switchdev_frame_mark(const struct net_bridge_port *p, struct sk_buff *skb); bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, const struct sk_buff *skb); +int br_switchdev_set_port_flag(struct net_bridge_port *p, + unsigned long flags, + unsigned long mask); +void br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, + int type); #else static inline int nbp_switchdev_mark_set(struct net_bridge_port *p) { @@ -1101,6 +1107,18 @@ static inline bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, { return true; } + +static inline int br_switchdev_set_port_flag(struct net_bridge_port *p, + unsigned long flags, + unsigned long mask) +{ + return 0; +} + +static inline void +br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) +{ +} #endif /* CONFIG_NET_SWITCHDEV */ #endif diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 5881fbc114a9..1b75d6bf12bd 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -50,7 +50,7 @@ static void br_send_bpdu(struct net_bridge_port *p, skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, LLC_RESERVE); - memcpy(__skb_put(skb, length), data, length); + __skb_put_data(skb, data, length); llc_pdu_header_init(skb, LLC_PDU_TYPE_U, LLC_SAP_BSPAN, LLC_SAP_BSPAN, LLC_PDU_CMD); diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 6f12a5271219..89110319ef0f 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -150,7 +150,6 @@ static int br_stp_call_user(struct net_bridge *br, char *arg) static void br_stp_start(struct net_bridge *br) { - struct net_bridge_port *p; int err = -ENOENT; if (net_eq(dev_net(br->dev), &init_net)) @@ -169,11 +168,6 @@ static void br_stp_start(struct net_bridge *br) if (!err) { br->stp_enabled = BR_USER_STP; br_debug(br, "userspace STP started\n"); - - /* Stop hello and hold timers */ - del_timer(&br->hello_timer); - list_for_each_entry(p, &br->port_list, list) - del_timer(&p->hold_timer); } else { br->stp_enabled = BR_KERNEL_STP; br_debug(br, "using kernel STP\n"); @@ -189,7 +183,6 @@ static void br_stp_start(struct net_bridge *br) static void br_stp_stop(struct net_bridge *br) { - struct net_bridge_port *p; int err; if (br->stp_enabled == BR_USER_STP) { @@ -198,10 +191,6 @@ static void br_stp_stop(struct net_bridge *br) br_err(br, "failed to stop userspace STP (%d)\n", err); /* To start timers on any ports left in blocking */ - mod_timer(&br->hello_timer, jiffies + br->hello_time); - list_for_each_entry(p, &br->port_list, list) - mod_timer(&p->hold_timer, - round_jiffies(jiffies + BR_HOLD_TIME)); spin_lock_bh(&br->lock); br_port_state_selection(br); spin_unlock_bh(&br->lock); diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index f4097b900de1..181a44d0f1da 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -55,3 +55,79 @@ bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, return !skb->offload_fwd_mark || BR_INPUT_SKB_CB(skb)->offload_fwd_mark != p->offload_fwd_mark; } + +/* Flags that can be offloaded to hardware */ +#define BR_PORT_FLAGS_HW_OFFLOAD (BR_LEARNING | BR_FLOOD | \ + BR_MCAST_FLOOD | BR_BCAST_FLOOD) + +int br_switchdev_set_port_flag(struct net_bridge_port *p, + unsigned long flags, + unsigned long mask) +{ + struct switchdev_attr attr = { + .orig_dev = p->dev, + .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT, + }; + int err; + + if (mask & ~BR_PORT_FLAGS_HW_OFFLOAD) + return 0; + + err = switchdev_port_attr_get(p->dev, &attr); + if (err == -EOPNOTSUPP) + return 0; + if (err) + return err; + + /* Check if specific bridge flag attribute offload is supported */ + if (!(attr.u.brport_flags_support & mask)) { + br_warn(p->br, "bridge flag offload is not supported %u(%s)\n", + (unsigned int)p->port_no, p->dev->name); + return -EOPNOTSUPP; + } + + attr.id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS; + attr.flags = SWITCHDEV_F_DEFER; + attr.u.brport_flags = flags; + err = switchdev_port_attr_set(p->dev, &attr); + if (err) { + br_warn(p->br, "error setting offload flag on port %u(%s)\n", + (unsigned int)p->port_no, p->dev->name); + return err; + } + + return 0; +} + +static void +br_switchdev_fdb_call_notifiers(bool adding, const unsigned char *mac, + u16 vid, struct net_device *dev) +{ + struct switchdev_notifier_fdb_info info; + unsigned long notifier_type; + + info.addr = mac; + info.vid = vid; + notifier_type = adding ? SWITCHDEV_FDB_ADD_TO_DEVICE : SWITCHDEV_FDB_DEL_TO_DEVICE; + call_switchdev_notifiers(notifier_type, dev, &info.info); +} + +void +br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) +{ + if (!fdb->added_by_user) + return; + + switch (type) { + case RTM_DELNEIGH: + br_switchdev_fdb_call_notifiers(false, fdb->addr.addr, + fdb->vlan_id, + fdb->dst->dev); + break; + case RTM_NEWNEIGH: + br_switchdev_fdb_call_notifiers(true, fdb->addr.addr, + fdb->vlan_id, + fdb->dst->dev); + break; + } +} diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 0b5dd607444c..723f25eed8ea 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -865,7 +865,7 @@ static struct attribute *bridge_attrs[] = { NULL }; -static struct attribute_group bridge_group = { +static const struct attribute_group bridge_group = { .name = SYSFS_BRIDGE_ATTR, .attrs = bridge_attrs, }; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index b838213c408e..233a30040c91 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -158,7 +158,7 @@ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid if (WARN_ON(!masterv)) return NULL; } - atomic_inc(&masterv->refcnt); + refcount_inc(&masterv->refcnt); return masterv; } @@ -182,7 +182,7 @@ static void br_vlan_put_master(struct net_bridge_vlan *masterv) return; vg = br_vlan_group(masterv->br); - if (atomic_dec_and_test(&masterv->refcnt)) { + if (refcount_dec_and_test(&masterv->refcnt)) { rhashtable_remove_fast(&vg->vlan_hash, &masterv->vnode, br_vlan_rht_params); __vlan_del_list(masterv); @@ -573,7 +573,7 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) br_err(br, "failed insert local address into bridge forwarding table\n"); return ret; } - atomic_inc(&vlan->refcnt); + refcount_inc(&vlan->refcnt); vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY; vg->num_vlans++; } @@ -595,7 +595,7 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) vlan->flags &= ~BRIDGE_VLAN_INFO_PVID; vlan->br = br; if (flags & BRIDGE_VLAN_INFO_BRENTRY) - atomic_set(&vlan->refcnt, 1); + refcount_set(&vlan->refcnt, 1); ret = __vlan_add(vlan, flags); if (ret) { free_percpu(vlan->stats); @@ -706,6 +706,14 @@ int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) return __br_vlan_filter_toggle(br, val); } +bool br_vlan_enabled(const struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + + return !!br->vlan_enabled; +} +EXPORT_SYMBOL_GPL(br_vlan_enabled); + int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) { int err = 0; diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index e0bb624c3845..dfc86a0199da 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -61,7 +61,7 @@ static int ebt_dnat_tg_check(const struct xt_tgchk_param *par) (strcmp(par->table, "broute") != 0 || hook_mask & ~(1 << NF_BR_BROUTING))) return -EINVAL; - if (INVALID_TARGET) + if (ebt_invalid_target(info->target)) return -EINVAL; return 0; } diff --git a/net/bridge/netfilter/ebt_mark.c b/net/bridge/netfilter/ebt_mark.c index 66697cbd0a8b..19f0f9592d32 100644 --- a/net/bridge/netfilter/ebt_mark.c +++ b/net/bridge/netfilter/ebt_mark.c @@ -44,7 +44,7 @@ static int ebt_mark_tg_check(const struct xt_tgchk_param *par) tmp = info->target | ~EBT_VERDICT_BITS; if (BASE_CHAIN && tmp == EBT_RETURN) return -EINVAL; - if (tmp < -NUM_STANDARD_TARGETS || tmp >= 0) + if (ebt_invalid_target(tmp)) return -EINVAL; tmp = info->target & ~EBT_VERDICT_BITS; if (tmp != MARK_SET_VALUE && tmp != MARK_OR_VALUE && diff --git a/net/bridge/netfilter/ebt_nflog.c b/net/bridge/netfilter/ebt_nflog.c index c1dc48686200..da1c2fdc08c8 100644 --- a/net/bridge/netfilter/ebt_nflog.c +++ b/net/bridge/netfilter/ebt_nflog.c @@ -30,6 +30,7 @@ ebt_nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) li.u.ulog.copy_len = info->len; li.u.ulog.group = info->group; li.u.ulog.qthreshold = info->threshold; + li.u.ulog.flags = 0; nf_log_packet(net, PF_BRIDGE, xt_hooknum(par), skb, xt_in(par), xt_out(par), &li, "%s", info->prefix); diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index 8d2a85e0594e..a7223eaf490b 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -47,7 +47,7 @@ static int ebt_redirect_tg_check(const struct xt_tgchk_param *par) (strcmp(par->table, "broute") != 0 || hook_mask & ~(1 << NF_BR_BROUTING))) return -EINVAL; - if (INVALID_TARGET) + if (ebt_invalid_target(info->target)) return -EINVAL; return 0; } diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c index e56ccd060d26..11cf9e9e9222 100644 --- a/net/bridge/netfilter/ebt_snat.c +++ b/net/bridge/netfilter/ebt_snat.c @@ -51,7 +51,7 @@ static int ebt_snat_tg_check(const struct xt_tgchk_param *par) if (BASE_CHAIN && tmp == EBT_RETURN) return -EINVAL; - if (tmp < -NUM_STANDARD_TARGETS || tmp >= 0) + if (ebt_invalid_target(tmp)) return -EINVAL; tmp = info->target | EBT_VERDICT_BITS; if ((tmp & ~NAT_ARP_BIT) != ~NAT_ARP_BIT) diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index 346ef6b00b8f..eaf05de37f75 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -28,7 +28,7 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb, { struct ethhdr *eth; - eth = (struct ethhdr *)skb_push(nskb, ETH_HLEN); + eth = skb_push(nskb, ETH_HLEN); skb_reset_mac_header(nskb); ether_addr_copy(eth->h_source, eth_hdr(oldskb)->h_dest); ether_addr_copy(eth->h_dest, eth_hdr(oldskb)->h_source); @@ -107,11 +107,10 @@ static void nft_reject_br_send_v4_unreach(struct net *net, struct iphdr *niph; struct icmphdr *icmph; unsigned int len; - void *payload; __wsum csum; u8 proto; - if (oldskb->csum_bad || !nft_bridge_iphdr_validate(oldskb)) + if (!nft_bridge_iphdr_validate(oldskb)) return; /* IP header checks: fragment. */ @@ -147,13 +146,11 @@ static void nft_reject_br_send_v4_unreach(struct net *net, net->ipv4.sysctl_ip_default_ttl); skb_reset_transport_header(nskb); - icmph = (struct icmphdr *)skb_put(nskb, sizeof(struct icmphdr)); - memset(icmph, 0, sizeof(*icmph)); + icmph = skb_put_zero(nskb, sizeof(struct icmphdr)); icmph->type = ICMP_DEST_UNREACH; icmph->code = code; - payload = skb_put(nskb, len); - memcpy(payload, skb_network_header(oldskb), len); + skb_put_data(nskb, skb_network_header(oldskb), len); csum = csum_partial((void *)icmph, len + sizeof(struct icmphdr), 0); icmph->checksum = csum_fold(csum); @@ -226,9 +223,6 @@ static bool reject6_br_csum_ok(struct sk_buff *skb, int hook) __be16 fo; u8 proto = ip6h->nexthdr; - if (skb->csum_bad) - return false; - if (skb_csum_unnecessary(skb)) return true; @@ -252,7 +246,6 @@ static void nft_reject_br_send_v6_unreach(struct net *net, struct ipv6hdr *nip6h; struct icmp6hdr *icmp6h; unsigned int len; - void *payload; if (!nft_bridge_ip6hdr_validate(oldskb)) return; @@ -278,13 +271,11 @@ static void nft_reject_br_send_v6_unreach(struct net *net, net->ipv6.devconf_all->hop_limit); skb_reset_transport_header(nskb); - icmp6h = (struct icmp6hdr *)skb_put(nskb, sizeof(struct icmp6hdr)); - memset(icmp6h, 0, sizeof(*icmp6h)); + icmp6h = skb_put_zero(nskb, sizeof(struct icmp6hdr)); icmp6h->icmp6_type = ICMPV6_DEST_UNREACH; icmp6h->icmp6_code = code; - payload = skb_put(nskb, len); - memcpy(payload, skb_network_header(oldskb), len); + skb_put_data(nskb, skb_network_header(oldskb), len); nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr)); icmp6h->icmp6_cksum = diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 21f18ea2fce4..632d5a416d97 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -1013,7 +1013,7 @@ static const struct proto_ops caif_stream_ops = { static void caif_sock_destructor(struct sock *sk) { struct caifsock *cf_sk = container_of(sk, struct caifsock, sk); - caif_assert(!atomic_read(&sk->sk_wmem_alloc)); + caif_assert(!refcount_read(&sk->sk_wmem_alloc)); caif_assert(sk_unhashed(sk)); caif_assert(!sk->sk_socket); if (!sock_flag(sk, SOCK_DEAD)) { @@ -1103,7 +1103,7 @@ static int caif_create(struct net *net, struct socket *sock, int protocol, } -static struct net_proto_family caif_family_ops = { +static const struct net_proto_family caif_family_ops = { .family = PF_CAIF, .create = caif_create, .owner = THIS_MODULE, diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index fe3c53efb949..922ac1d605b3 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -461,7 +461,8 @@ static void caif_netlink_parms(struct nlattr *data[], } static int ipcaif_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { int ret; struct chnl_net *caifdev; @@ -484,7 +485,8 @@ static int ipcaif_newlink(struct net *src_net, struct net_device *dev, } static int ipcaif_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct chnl_net *caifdev; ASSERT_RTNL(); diff --git a/net/can/bcm.c b/net/can/bcm.c index 65432633a250..47a8748d953a 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -282,7 +282,7 @@ static void bcm_can_tx(struct bcm_op *op) can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; - memcpy(skb_put(skb, op->cfsiz), cf, op->cfsiz); + skb_put_data(skb, cf, op->cfsiz); /* send with loopback */ skb->dev = dev; @@ -318,13 +318,13 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, if (!skb) return; - memcpy(skb_put(skb, sizeof(*head)), head, sizeof(*head)); + skb_put_data(skb, head, sizeof(*head)); if (head->nframes) { /* CAN frames starting here */ firstframe = (struct canfd_frame *)skb_tail_pointer(skb); - memcpy(skb_put(skb, datalen), frames, datalen); + skb_put_data(skb, frames, datalen); /* * the BCM uses the flags-element of the canfd_frame diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 47e94b560ba0..5c036d2f401e 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -85,6 +85,7 @@ const char *ceph_msg_type_name(int type) case CEPH_MSG_OSD_OP: return "osd_op"; case CEPH_MSG_OSD_OPREPLY: return "osd_opreply"; case CEPH_MSG_WATCH_NOTIFY: return "watch_notify"; + case CEPH_MSG_OSD_BACKOFF: return "osd_backoff"; default: return "unknown"; } } @@ -598,7 +599,11 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private) { struct ceph_client *client; struct ceph_entity_addr *myaddr = NULL; - int err = -ENOMEM; + int err; + + err = wait_for_random_bytes(); + if (err < 0) + return ERR_PTR(err); client = kzalloc(sizeof(*client), GFP_KERNEL); if (client == NULL) diff --git a/net/ceph/crush/crush.c b/net/ceph/crush/crush.c index 5bf94c04f645..4b428f46a8ca 100644 --- a/net/ceph/crush/crush.c +++ b/net/ceph/crush/crush.c @@ -1,6 +1,7 @@ #ifdef __KERNEL__ # include <linux/slab.h> # include <linux/crush/crush.h> +void clear_choose_args(struct crush_map *c); #else # include "crush_compat.h" # include "crush.h" @@ -127,6 +128,8 @@ void crush_destroy(struct crush_map *map) #ifndef __KERNEL__ kfree(map->choose_tries); +#else + clear_choose_args(map); #endif kfree(map); } diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index b5cd8c21bfdf..746b145bfd11 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -302,19 +302,42 @@ static __u64 crush_ln(unsigned int xin) * */ +static __u32 *get_choose_arg_weights(const struct crush_bucket_straw2 *bucket, + const struct crush_choose_arg *arg, + int position) +{ + if (!arg || !arg->weight_set || arg->weight_set_size == 0) + return bucket->item_weights; + + if (position >= arg->weight_set_size) + position = arg->weight_set_size - 1; + return arg->weight_set[position].weights; +} + +static __s32 *get_choose_arg_ids(const struct crush_bucket_straw2 *bucket, + const struct crush_choose_arg *arg) +{ + if (!arg || !arg->ids) + return bucket->h.items; + + return arg->ids; +} + static int bucket_straw2_choose(const struct crush_bucket_straw2 *bucket, - int x, int r) + int x, int r, + const struct crush_choose_arg *arg, + int position) { unsigned int i, high = 0; unsigned int u; - unsigned int w; __s64 ln, draw, high_draw = 0; + __u32 *weights = get_choose_arg_weights(bucket, arg, position); + __s32 *ids = get_choose_arg_ids(bucket, arg); for (i = 0; i < bucket->h.size; i++) { - w = bucket->item_weights[i]; - if (w) { - u = crush_hash32_3(bucket->h.hash, x, - bucket->h.items[i], r); + dprintk("weight 0x%x item %d\n", weights[i], ids[i]); + if (weights[i]) { + u = crush_hash32_3(bucket->h.hash, x, ids[i], r); u &= 0xffff; /* @@ -335,7 +358,7 @@ static int bucket_straw2_choose(const struct crush_bucket_straw2 *bucket, * weight means a larger (less negative) value * for draw. */ - draw = div64_s64(ln, w); + draw = div64_s64(ln, weights[i]); } else { draw = S64_MIN; } @@ -352,7 +375,9 @@ static int bucket_straw2_choose(const struct crush_bucket_straw2 *bucket, static int crush_bucket_choose(const struct crush_bucket *in, struct crush_work_bucket *work, - int x, int r) + int x, int r, + const struct crush_choose_arg *arg, + int position) { dprintk(" crush_bucket_choose %d x=%d r=%d\n", in->id, x, r); BUG_ON(in->size == 0); @@ -374,7 +399,7 @@ static int crush_bucket_choose(const struct crush_bucket *in, case CRUSH_BUCKET_STRAW2: return bucket_straw2_choose( (const struct crush_bucket_straw2 *)in, - x, r); + x, r, arg, position); default: dprintk("unknown bucket %d alg %d\n", in->id, in->alg); return in->items[0]; @@ -436,7 +461,8 @@ static int crush_choose_firstn(const struct crush_map *map, unsigned int vary_r, unsigned int stable, int *out2, - int parent_r) + int parent_r, + const struct crush_choose_arg *choose_args) { int rep; unsigned int ftotal, flocal; @@ -486,7 +512,10 @@ static int crush_choose_firstn(const struct crush_map *map, else item = crush_bucket_choose( in, work->work[-1-in->id], - x, r); + x, r, + (choose_args ? + &choose_args[-1-in->id] : 0), + outpos); if (item >= map->max_devices) { dprintk(" bad item %d\n", item); skip_rep = 1; @@ -543,7 +572,8 @@ static int crush_choose_firstn(const struct crush_map *map, vary_r, stable, NULL, - sub_r) <= outpos) + sub_r, + choose_args) <= outpos) /* didn't get leaf */ reject = 1; } else { @@ -620,7 +650,8 @@ static void crush_choose_indep(const struct crush_map *map, unsigned int recurse_tries, int recurse_to_leaf, int *out2, - int parent_r) + int parent_r, + const struct crush_choose_arg *choose_args) { const struct crush_bucket *in = bucket; int endpos = outpos + left; @@ -692,7 +723,10 @@ static void crush_choose_indep(const struct crush_map *map, item = crush_bucket_choose( in, work->work[-1-in->id], - x, r); + x, r, + (choose_args ? + &choose_args[-1-in->id] : 0), + outpos); if (item >= map->max_devices) { dprintk(" bad item %d\n", item); out[rep] = CRUSH_ITEM_NONE; @@ -746,7 +780,8 @@ static void crush_choose_indep(const struct crush_map *map, x, 1, numrep, 0, out2, rep, recurse_tries, 0, - 0, NULL, r); + 0, NULL, r, + choose_args); if (out2[rep] == CRUSH_ITEM_NONE) { /* placed nothing; no leaf */ break; @@ -823,7 +858,7 @@ void crush_init_workspace(const struct crush_map *map, void *v) * set the pointer first and then reserve the space for it to * point to by incrementing the point. */ - v += sizeof(struct crush_work *); + v += sizeof(struct crush_work); w->work = v; v += map->max_buckets * sizeof(struct crush_work_bucket *); for (b = 0; b < map->max_buckets; ++b) { @@ -854,11 +889,12 @@ void crush_init_workspace(const struct crush_map *map, void *v) * @weight: weight vector (for map leaves) * @weight_max: size of weight vector * @cwin: pointer to at least crush_work_size() bytes of memory + * @choose_args: weights and ids for each known bucket */ int crush_do_rule(const struct crush_map *map, int ruleno, int x, int *result, int result_max, const __u32 *weight, int weight_max, - void *cwin) + void *cwin, const struct crush_choose_arg *choose_args) { int result_len; struct crush_work *cw = cwin; @@ -968,11 +1004,6 @@ int crush_do_rule(const struct crush_map *map, for (i = 0; i < wsize; i++) { int bno; - /* - * see CRUSH_N, CRUSH_N_MINUS macros. - * basically, numrep <= 0 means relative to - * the provided result_max - */ numrep = curstep->arg1; if (numrep <= 0) { numrep += result_max; @@ -1013,7 +1044,8 @@ int crush_do_rule(const struct crush_map *map, vary_r, stable, c+osize, - 0); + 0, + choose_args); } else { out_size = ((numrep < (result_max-osize)) ? numrep : (result_max-osize)); @@ -1030,7 +1062,8 @@ int crush_do_rule(const struct crush_map *map, choose_leaf_tries : 1, recurse_to_leaf, c+osize, - 0); + 0, + choose_args); osize += out_size; } } diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c index 71ba13927b3d..fa5233e0d01c 100644 --- a/net/ceph/debugfs.c +++ b/net/ceph/debugfs.c @@ -77,7 +77,7 @@ static int osdmap_show(struct seq_file *s, void *p) } for (i = 0; i < map->max_osd; i++) { struct ceph_entity_addr *addr = &map->osd_addr[i]; - int state = map->osd_state[i]; + u32 state = map->osd_state[i]; char sb[64]; seq_printf(s, "osd%d\t%s\t%3d%%\t(%s)\t%3d%%\n", @@ -104,6 +104,29 @@ static int osdmap_show(struct seq_file *s, void *p) seq_printf(s, "primary_temp %llu.%x %d\n", pg->pgid.pool, pg->pgid.seed, pg->primary_temp.osd); } + for (n = rb_first(&map->pg_upmap); n; n = rb_next(n)) { + struct ceph_pg_mapping *pg = + rb_entry(n, struct ceph_pg_mapping, node); + + seq_printf(s, "pg_upmap %llu.%x [", pg->pgid.pool, + pg->pgid.seed); + for (i = 0; i < pg->pg_upmap.len; i++) + seq_printf(s, "%s%d", (i == 0 ? "" : ","), + pg->pg_upmap.osds[i]); + seq_printf(s, "]\n"); + } + for (n = rb_first(&map->pg_upmap_items); n; n = rb_next(n)) { + struct ceph_pg_mapping *pg = + rb_entry(n, struct ceph_pg_mapping, node); + + seq_printf(s, "pg_upmap_items %llu.%x [", pg->pgid.pool, + pg->pgid.seed); + for (i = 0; i < pg->pg_upmap_items.len; i++) + seq_printf(s, "%s%d->%d", (i == 0 ? "" : ","), + pg->pg_upmap_items.from_to[i][0], + pg->pg_upmap_items.from_to[i][1]); + seq_printf(s, "]\n"); + } up_read(&osdc->lock); return 0; @@ -147,17 +170,26 @@ static int monc_show(struct seq_file *s, void *p) return 0; } +static void dump_spgid(struct seq_file *s, const struct ceph_spg *spgid) +{ + seq_printf(s, "%llu.%x", spgid->pgid.pool, spgid->pgid.seed); + if (spgid->shard != CEPH_SPG_NOSHARD) + seq_printf(s, "s%d", spgid->shard); +} + static void dump_target(struct seq_file *s, struct ceph_osd_request_target *t) { int i; - seq_printf(s, "osd%d\t%llu.%x\t[", t->osd, t->pgid.pool, t->pgid.seed); + seq_printf(s, "osd%d\t%llu.%x\t", t->osd, t->pgid.pool, t->pgid.seed); + dump_spgid(s, &t->spgid); + seq_puts(s, "\t["); for (i = 0; i < t->up.size; i++) seq_printf(s, "%s%d", (!i ? "" : ","), t->up.osds[i]); seq_printf(s, "]/%d\t[", t->up.primary); for (i = 0; i < t->acting.size; i++) seq_printf(s, "%s%d", (!i ? "" : ","), t->acting.osds[i]); - seq_printf(s, "]/%d\t", t->acting.primary); + seq_printf(s, "]/%d\te%u\t", t->acting.primary, t->epoch); if (t->target_oloc.pool_ns) { seq_printf(s, "%*pE/%*pE\t0x%x", (int)t->target_oloc.pool_ns->len, @@ -234,6 +266,73 @@ static void dump_linger_requests(struct seq_file *s, struct ceph_osd *osd) mutex_unlock(&osd->lock); } +static void dump_snapid(struct seq_file *s, u64 snapid) +{ + if (snapid == CEPH_NOSNAP) + seq_puts(s, "head"); + else if (snapid == CEPH_SNAPDIR) + seq_puts(s, "snapdir"); + else + seq_printf(s, "%llx", snapid); +} + +static void dump_name_escaped(struct seq_file *s, unsigned char *name, + size_t len) +{ + size_t i; + + for (i = 0; i < len; i++) { + if (name[i] == '%' || name[i] == ':' || name[i] == '/' || + name[i] < 32 || name[i] >= 127) { + seq_printf(s, "%%%02x", name[i]); + } else { + seq_putc(s, name[i]); + } + } +} + +static void dump_hoid(struct seq_file *s, const struct ceph_hobject_id *hoid) +{ + if (hoid->snapid == 0 && hoid->hash == 0 && !hoid->is_max && + hoid->pool == S64_MIN) { + seq_puts(s, "MIN"); + return; + } + if (hoid->is_max) { + seq_puts(s, "MAX"); + return; + } + seq_printf(s, "%lld:%08x:", hoid->pool, hoid->hash_reverse_bits); + dump_name_escaped(s, hoid->nspace, hoid->nspace_len); + seq_putc(s, ':'); + dump_name_escaped(s, hoid->key, hoid->key_len); + seq_putc(s, ':'); + dump_name_escaped(s, hoid->oid, hoid->oid_len); + seq_putc(s, ':'); + dump_snapid(s, hoid->snapid); +} + +static void dump_backoffs(struct seq_file *s, struct ceph_osd *osd) +{ + struct rb_node *n; + + mutex_lock(&osd->lock); + for (n = rb_first(&osd->o_backoffs_by_id); n; n = rb_next(n)) { + struct ceph_osd_backoff *backoff = + rb_entry(n, struct ceph_osd_backoff, id_node); + + seq_printf(s, "osd%d\t", osd->o_osd); + dump_spgid(s, &backoff->spgid); + seq_printf(s, "\t%llu\t", backoff->id); + dump_hoid(s, backoff->begin); + seq_putc(s, '\t'); + dump_hoid(s, backoff->end); + seq_putc(s, '\n'); + } + + mutex_unlock(&osd->lock); +} + static int osdc_show(struct seq_file *s, void *pp) { struct ceph_client *client = s->private; @@ -259,6 +358,13 @@ static int osdc_show(struct seq_file *s, void *pp) } dump_linger_requests(s, &osdc->homeless_osd); + seq_puts(s, "BACKOFFS\n"); + for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { + struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); + + dump_backoffs(s, osd); + } + up_read(&osdc->lock); return 0; } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 588a91930051..b7cc615d42ef 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1288,13 +1288,16 @@ static void prepare_write_message(struct ceph_connection *con) m->hdr.seq = cpu_to_le64(++con->out_seq); m->needs_out_seq = false; } - WARN_ON(m->data_length != le32_to_cpu(m->hdr.data_len)); + + if (con->ops->reencode_message) + con->ops->reencode_message(m); dout("prepare_write_message %p seq %lld type %d len %d+%d+%zd\n", m, con->out_seq, le16_to_cpu(m->hdr.type), le32_to_cpu(m->hdr.front_len), le32_to_cpu(m->hdr.middle_len), m->data_length); - BUG_ON(le32_to_cpu(m->hdr.front_len) != m->front.iov_len); + WARN_ON(m->front.iov_len != le32_to_cpu(m->hdr.front_len)); + WARN_ON(m->data_length != le32_to_cpu(m->hdr.data_len)); /* tag + hdr + front + middle */ con_out_kvec_add(con, sizeof (tag_msg), &tag_msg); @@ -2033,8 +2036,7 @@ static int process_connect(struct ceph_connection *con) { u64 sup_feat = from_msgr(con->msgr)->supported_features; u64 req_feat = from_msgr(con->msgr)->required_features; - u64 server_feat = ceph_sanitize_features( - le64_to_cpu(con->in_reply.features)); + u64 server_feat = le64_to_cpu(con->in_reply.features); int ret; dout("process_connect on %p tag %d\n", con, (int)con->in_tag); @@ -3201,8 +3203,10 @@ static struct ceph_msg_data *ceph_msg_data_create(enum ceph_msg_data_type type) return NULL; data = kmem_cache_zalloc(ceph_msg_data_cache, GFP_NOFS); - if (data) - data->type = type; + if (!data) + return NULL; + + data->type = type; INIT_LIST_HEAD(&data->links); return data; diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 250f11f78609..875675765531 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -6,6 +6,7 @@ #include <linux/random.h> #include <linux/sched.h> +#include <linux/ceph/ceph_features.h> #include <linux/ceph/mon_client.h> #include <linux/ceph/libceph.h> #include <linux/ceph/debugfs.h> @@ -297,6 +298,10 @@ static void handle_subscribe_ack(struct ceph_mon_client *monc, mutex_lock(&monc->mutex); if (monc->sub_renew_sent) { + /* + * This is only needed for legacy (infernalis or older) + * MONs -- see delayed_work(). + */ monc->sub_renew_after = monc->sub_renew_sent + (seconds >> 1) * HZ - 1; dout("%s sent %lu duration %d renew after %lu\n", __func__, @@ -955,7 +960,8 @@ static void delayed_work(struct work_struct *work) __validate_auth(monc); } - if (is_auth) { + if (is_auth && + !(monc->con.peer_features & CEPH_FEATURE_MON_STATEFUL_SUB)) { unsigned long now = jiffies; dout("%s renew subs? now %lu renew after %lu\n", diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 924f07c36ddb..901bb8221366 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -12,6 +12,7 @@ #include <linux/bio.h> #endif +#include <linux/ceph/ceph_features.h> #include <linux/ceph/libceph.h> #include <linux/ceph/osd_client.h> #include <linux/ceph/messenger.h> @@ -49,6 +50,7 @@ static void link_linger(struct ceph_osd *osd, struct ceph_osd_linger_request *lreq); static void unlink_linger(struct ceph_osd *osd, struct ceph_osd_linger_request *lreq); +static void clear_backoffs(struct ceph_osd *osd); #if 1 static inline bool rwsem_is_wrlocked(struct rw_semaphore *sem) @@ -373,6 +375,7 @@ static void target_copy(struct ceph_osd_request_target *dest, ceph_oloc_copy(&dest->target_oloc, &src->target_oloc); dest->pgid = src->pgid; /* struct */ + dest->spgid = src->spgid; /* struct */ dest->pg_num = src->pg_num; dest->pg_num_mask = src->pg_num_mask; ceph_osds_copy(&dest->acting, &src->acting); @@ -384,6 +387,9 @@ static void target_copy(struct ceph_osd_request_target *dest, dest->flags = src->flags; dest->paused = src->paused; + dest->epoch = src->epoch; + dest->last_force_resend = src->last_force_resend; + dest->osd = src->osd; } @@ -537,7 +543,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, } EXPORT_SYMBOL(ceph_osdc_alloc_request); -static int ceph_oloc_encoding_size(struct ceph_object_locator *oloc) +static int ceph_oloc_encoding_size(const struct ceph_object_locator *oloc) { return 8 + 4 + 4 + 4 + (oloc->pool_ns ? oloc->pool_ns->len : 0); } @@ -552,17 +558,21 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp) WARN_ON(ceph_oloc_empty(&req->r_base_oloc)); /* create request message */ - msg_size = 4 + 4 + 4; /* client_inc, osdmap_epoch, flags */ - msg_size += 4 + 4 + 4 + 8; /* mtime, reassert_version */ + msg_size = CEPH_ENCODING_START_BLK_LEN + + CEPH_PGID_ENCODING_LEN + 1; /* spgid */ + msg_size += 4 + 4 + 4; /* hash, osdmap_epoch, flags */ + msg_size += CEPH_ENCODING_START_BLK_LEN + + sizeof(struct ceph_osd_reqid); /* reqid */ + msg_size += sizeof(struct ceph_blkin_trace_info); /* trace */ + msg_size += 4 + sizeof(struct ceph_timespec); /* client_inc, mtime */ msg_size += CEPH_ENCODING_START_BLK_LEN + ceph_oloc_encoding_size(&req->r_base_oloc); /* oloc */ - msg_size += 1 + 8 + 4 + 4; /* pgid */ msg_size += 4 + req->r_base_oid.name_len; /* oid */ msg_size += 2 + req->r_num_ops * sizeof(struct ceph_osd_op); msg_size += 8; /* snapid */ msg_size += 8; /* snap_seq */ msg_size += 4 + 8 * (req->r_snapc ? req->r_snapc->num_snaps : 0); - msg_size += 4; /* retry_attempt */ + msg_size += 4 + 8; /* retry_attempt, features */ if (req->r_mempool) msg = ceph_msgpool_get(&osdc->msgpool_op, 0); @@ -1010,6 +1020,8 @@ static void osd_init(struct ceph_osd *osd) RB_CLEAR_NODE(&osd->o_node); osd->o_requests = RB_ROOT; osd->o_linger_requests = RB_ROOT; + osd->o_backoff_mappings = RB_ROOT; + osd->o_backoffs_by_id = RB_ROOT; INIT_LIST_HEAD(&osd->o_osd_lru); INIT_LIST_HEAD(&osd->o_keepalive_item); osd->o_incarnation = 1; @@ -1021,6 +1033,8 @@ static void osd_cleanup(struct ceph_osd *osd) WARN_ON(!RB_EMPTY_NODE(&osd->o_node)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests)); + WARN_ON(!RB_EMPTY_ROOT(&osd->o_backoff_mappings)); + WARN_ON(!RB_EMPTY_ROOT(&osd->o_backoffs_by_id)); WARN_ON(!list_empty(&osd->o_osd_lru)); WARN_ON(!list_empty(&osd->o_keepalive_item)); @@ -1141,6 +1155,7 @@ static void close_osd(struct ceph_osd *osd) unlink_linger(osd, lreq); link_linger(&osdc->homeless_osd, lreq); } + clear_backoffs(osd); __remove_osd_from_lru(osd); erase_osd(&osdc->osds, osd); @@ -1297,7 +1312,7 @@ static bool target_should_be_paused(struct ceph_osd_client *osdc, ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || __pool_full(pi); - WARN_ON(pi->id != t->base_oloc.pool); + WARN_ON(pi->id != t->target_oloc.pool); return ((t->flags & CEPH_OSD_FLAG_READ) && pauserd) || ((t->flags & CEPH_OSD_FLAG_WRITE) && pausewr) || (osdc->osdmap->epoch < osdc->epoch_barrier); @@ -1311,19 +1326,21 @@ enum calc_target_result { static enum calc_target_result calc_target(struct ceph_osd_client *osdc, struct ceph_osd_request_target *t, - u32 *last_force_resend, + struct ceph_connection *con, bool any_change) { struct ceph_pg_pool_info *pi; struct ceph_pg pgid, last_pgid; struct ceph_osds up, acting; bool force_resend = false; - bool need_check_tiering = false; - bool need_resend = false; + bool unpaused = false; + bool legacy_change; + bool split = false; bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE); enum calc_target_result ct_res; int ret; + t->epoch = osdc->osdmap->epoch; pi = ceph_pg_pool_by_id(osdc->osdmap, t->base_oloc.pool); if (!pi) { t->osd = CEPH_HOMELESS_OSD; @@ -1332,33 +1349,33 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, } if (osdc->osdmap->epoch == pi->last_force_request_resend) { - if (last_force_resend && - *last_force_resend < pi->last_force_request_resend) { - *last_force_resend = pi->last_force_request_resend; + if (t->last_force_resend < pi->last_force_request_resend) { + t->last_force_resend = pi->last_force_request_resend; force_resend = true; - } else if (!last_force_resend) { + } else if (t->last_force_resend == 0) { force_resend = true; } } - if (ceph_oid_empty(&t->target_oid) || force_resend) { - ceph_oid_copy(&t->target_oid, &t->base_oid); - need_check_tiering = true; - } - if (ceph_oloc_empty(&t->target_oloc) || force_resend) { - ceph_oloc_copy(&t->target_oloc, &t->base_oloc); - need_check_tiering = true; - } - if (need_check_tiering && - (t->flags & CEPH_OSD_FLAG_IGNORE_OVERLAY) == 0) { + /* apply tiering */ + ceph_oid_copy(&t->target_oid, &t->base_oid); + ceph_oloc_copy(&t->target_oloc, &t->base_oloc); + if ((t->flags & CEPH_OSD_FLAG_IGNORE_OVERLAY) == 0) { if (t->flags & CEPH_OSD_FLAG_READ && pi->read_tier >= 0) t->target_oloc.pool = pi->read_tier; if (t->flags & CEPH_OSD_FLAG_WRITE && pi->write_tier >= 0) t->target_oloc.pool = pi->write_tier; + + pi = ceph_pg_pool_by_id(osdc->osdmap, t->target_oloc.pool); + if (!pi) { + t->osd = CEPH_HOMELESS_OSD; + ct_res = CALC_TARGET_POOL_DNE; + goto out; + } } - ret = ceph_object_locator_to_pg(osdc->osdmap, &t->target_oid, - &t->target_oloc, &pgid); + ret = __ceph_object_locator_to_pg(pi, &t->target_oid, &t->target_oloc, + &pgid); if (ret) { WARN_ON(ret != -ENOENT); t->osd = CEPH_HOMELESS_OSD; @@ -1368,7 +1385,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, last_pgid.pool = pgid.pool; last_pgid.seed = ceph_stable_mod(pgid.seed, t->pg_num, t->pg_num_mask); - ceph_pg_to_up_acting_osds(osdc->osdmap, &pgid, &up, &acting); + ceph_pg_to_up_acting_osds(osdc->osdmap, pi, &pgid, &up, &acting); if (any_change && ceph_is_new_interval(&t->acting, &acting, @@ -1387,13 +1404,16 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, if (t->paused && !target_should_be_paused(osdc, t, pi)) { t->paused = false; - need_resend = true; + unpaused = true; } + legacy_change = ceph_pg_compare(&t->pgid, &pgid) || + ceph_osds_changed(&t->acting, &acting, any_change); + if (t->pg_num) + split = ceph_pg_is_split(&last_pgid, t->pg_num, pi->pg_num); - if (ceph_pg_compare(&t->pgid, &pgid) || - ceph_osds_changed(&t->acting, &acting, any_change) || - force_resend) { + if (legacy_change || force_resend || split) { t->pgid = pgid; /* struct */ + ceph_pg_to_primary_shard(osdc->osdmap, pi, &pgid, &t->spgid); ceph_osds_copy(&t->acting, &acting); ceph_osds_copy(&t->up, &up); t->size = pi->size; @@ -1403,15 +1423,342 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, t->sort_bitwise = sort_bitwise; t->osd = acting.primary; - need_resend = true; } - ct_res = need_resend ? CALC_TARGET_NEED_RESEND : CALC_TARGET_NO_ACTION; + if (unpaused || legacy_change || force_resend || + (split && con && CEPH_HAVE_FEATURE(con->peer_features, + RESEND_ON_SPLIT))) + ct_res = CALC_TARGET_NEED_RESEND; + else + ct_res = CALC_TARGET_NO_ACTION; + out: dout("%s t %p -> ct_res %d osd %d\n", __func__, t, ct_res, t->osd); return ct_res; } +static struct ceph_spg_mapping *alloc_spg_mapping(void) +{ + struct ceph_spg_mapping *spg; + + spg = kmalloc(sizeof(*spg), GFP_NOIO); + if (!spg) + return NULL; + + RB_CLEAR_NODE(&spg->node); + spg->backoffs = RB_ROOT; + return spg; +} + +static void free_spg_mapping(struct ceph_spg_mapping *spg) +{ + WARN_ON(!RB_EMPTY_NODE(&spg->node)); + WARN_ON(!RB_EMPTY_ROOT(&spg->backoffs)); + + kfree(spg); +} + +/* + * rbtree of ceph_spg_mapping for handling map<spg_t, ...>, similar to + * ceph_pg_mapping. Used to track OSD backoffs -- a backoff [range] is + * defined only within a specific spgid; it does not pass anything to + * children on split, or to another primary. + */ +DEFINE_RB_FUNCS2(spg_mapping, struct ceph_spg_mapping, spgid, ceph_spg_compare, + RB_BYPTR, const struct ceph_spg *, node) + +static u64 hoid_get_bitwise_key(const struct ceph_hobject_id *hoid) +{ + return hoid->is_max ? 0x100000000ull : hoid->hash_reverse_bits; +} + +static void hoid_get_effective_key(const struct ceph_hobject_id *hoid, + void **pkey, size_t *pkey_len) +{ + if (hoid->key_len) { + *pkey = hoid->key; + *pkey_len = hoid->key_len; + } else { + *pkey = hoid->oid; + *pkey_len = hoid->oid_len; + } +} + +static int compare_names(const void *name1, size_t name1_len, + const void *name2, size_t name2_len) +{ + int ret; + + ret = memcmp(name1, name2, min(name1_len, name2_len)); + if (!ret) { + if (name1_len < name2_len) + ret = -1; + else if (name1_len > name2_len) + ret = 1; + } + return ret; +} + +static int hoid_compare(const struct ceph_hobject_id *lhs, + const struct ceph_hobject_id *rhs) +{ + void *effective_key1, *effective_key2; + size_t effective_key1_len, effective_key2_len; + int ret; + + if (lhs->is_max < rhs->is_max) + return -1; + if (lhs->is_max > rhs->is_max) + return 1; + + if (lhs->pool < rhs->pool) + return -1; + if (lhs->pool > rhs->pool) + return 1; + + if (hoid_get_bitwise_key(lhs) < hoid_get_bitwise_key(rhs)) + return -1; + if (hoid_get_bitwise_key(lhs) > hoid_get_bitwise_key(rhs)) + return 1; + + ret = compare_names(lhs->nspace, lhs->nspace_len, + rhs->nspace, rhs->nspace_len); + if (ret) + return ret; + + hoid_get_effective_key(lhs, &effective_key1, &effective_key1_len); + hoid_get_effective_key(rhs, &effective_key2, &effective_key2_len); + ret = compare_names(effective_key1, effective_key1_len, + effective_key2, effective_key2_len); + if (ret) + return ret; + + ret = compare_names(lhs->oid, lhs->oid_len, rhs->oid, rhs->oid_len); + if (ret) + return ret; + + if (lhs->snapid < rhs->snapid) + return -1; + if (lhs->snapid > rhs->snapid) + return 1; + + return 0; +} + +/* + * For decoding ->begin and ->end of MOSDBackoff only -- no MIN/MAX + * compat stuff here. + * + * Assumes @hoid is zero-initialized. + */ +static int decode_hoid(void **p, void *end, struct ceph_hobject_id *hoid) +{ + u8 struct_v; + u32 struct_len; + int ret; + + ret = ceph_start_decoding(p, end, 4, "hobject_t", &struct_v, + &struct_len); + if (ret) + return ret; + + if (struct_v < 4) { + pr_err("got struct_v %d < 4 of hobject_t\n", struct_v); + goto e_inval; + } + + hoid->key = ceph_extract_encoded_string(p, end, &hoid->key_len, + GFP_NOIO); + if (IS_ERR(hoid->key)) { + ret = PTR_ERR(hoid->key); + hoid->key = NULL; + return ret; + } + + hoid->oid = ceph_extract_encoded_string(p, end, &hoid->oid_len, + GFP_NOIO); + if (IS_ERR(hoid->oid)) { + ret = PTR_ERR(hoid->oid); + hoid->oid = NULL; + return ret; + } + + ceph_decode_64_safe(p, end, hoid->snapid, e_inval); + ceph_decode_32_safe(p, end, hoid->hash, e_inval); + ceph_decode_8_safe(p, end, hoid->is_max, e_inval); + + hoid->nspace = ceph_extract_encoded_string(p, end, &hoid->nspace_len, + GFP_NOIO); + if (IS_ERR(hoid->nspace)) { + ret = PTR_ERR(hoid->nspace); + hoid->nspace = NULL; + return ret; + } + + ceph_decode_64_safe(p, end, hoid->pool, e_inval); + + ceph_hoid_build_hash_cache(hoid); + return 0; + +e_inval: + return -EINVAL; +} + +static int hoid_encoding_size(const struct ceph_hobject_id *hoid) +{ + return 8 + 4 + 1 + 8 + /* snapid, hash, is_max, pool */ + 4 + hoid->key_len + 4 + hoid->oid_len + 4 + hoid->nspace_len; +} + +static void encode_hoid(void **p, void *end, const struct ceph_hobject_id *hoid) +{ + ceph_start_encoding(p, 4, 3, hoid_encoding_size(hoid)); + ceph_encode_string(p, end, hoid->key, hoid->key_len); + ceph_encode_string(p, end, hoid->oid, hoid->oid_len); + ceph_encode_64(p, hoid->snapid); + ceph_encode_32(p, hoid->hash); + ceph_encode_8(p, hoid->is_max); + ceph_encode_string(p, end, hoid->nspace, hoid->nspace_len); + ceph_encode_64(p, hoid->pool); +} + +static void free_hoid(struct ceph_hobject_id *hoid) +{ + if (hoid) { + kfree(hoid->key); + kfree(hoid->oid); + kfree(hoid->nspace); + kfree(hoid); + } +} + +static struct ceph_osd_backoff *alloc_backoff(void) +{ + struct ceph_osd_backoff *backoff; + + backoff = kzalloc(sizeof(*backoff), GFP_NOIO); + if (!backoff) + return NULL; + + RB_CLEAR_NODE(&backoff->spg_node); + RB_CLEAR_NODE(&backoff->id_node); + return backoff; +} + +static void free_backoff(struct ceph_osd_backoff *backoff) +{ + WARN_ON(!RB_EMPTY_NODE(&backoff->spg_node)); + WARN_ON(!RB_EMPTY_NODE(&backoff->id_node)); + + free_hoid(backoff->begin); + free_hoid(backoff->end); + kfree(backoff); +} + +/* + * Within a specific spgid, backoffs are managed by ->begin hoid. + */ +DEFINE_RB_INSDEL_FUNCS2(backoff, struct ceph_osd_backoff, begin, hoid_compare, + RB_BYVAL, spg_node); + +static struct ceph_osd_backoff *lookup_containing_backoff(struct rb_root *root, + const struct ceph_hobject_id *hoid) +{ + struct rb_node *n = root->rb_node; + + while (n) { + struct ceph_osd_backoff *cur = + rb_entry(n, struct ceph_osd_backoff, spg_node); + int cmp; + + cmp = hoid_compare(hoid, cur->begin); + if (cmp < 0) { + n = n->rb_left; + } else if (cmp > 0) { + if (hoid_compare(hoid, cur->end) < 0) + return cur; + + n = n->rb_right; + } else { + return cur; + } + } + + return NULL; +} + +/* + * Each backoff has a unique id within its OSD session. + */ +DEFINE_RB_FUNCS(backoff_by_id, struct ceph_osd_backoff, id, id_node) + +static void clear_backoffs(struct ceph_osd *osd) +{ + while (!RB_EMPTY_ROOT(&osd->o_backoff_mappings)) { + struct ceph_spg_mapping *spg = + rb_entry(rb_first(&osd->o_backoff_mappings), + struct ceph_spg_mapping, node); + + while (!RB_EMPTY_ROOT(&spg->backoffs)) { + struct ceph_osd_backoff *backoff = + rb_entry(rb_first(&spg->backoffs), + struct ceph_osd_backoff, spg_node); + + erase_backoff(&spg->backoffs, backoff); + erase_backoff_by_id(&osd->o_backoffs_by_id, backoff); + free_backoff(backoff); + } + erase_spg_mapping(&osd->o_backoff_mappings, spg); + free_spg_mapping(spg); + } +} + +/* + * Set up a temporary, non-owning view into @t. + */ +static void hoid_fill_from_target(struct ceph_hobject_id *hoid, + const struct ceph_osd_request_target *t) +{ + hoid->key = NULL; + hoid->key_len = 0; + hoid->oid = t->target_oid.name; + hoid->oid_len = t->target_oid.name_len; + hoid->snapid = CEPH_NOSNAP; + hoid->hash = t->pgid.seed; + hoid->is_max = false; + if (t->target_oloc.pool_ns) { + hoid->nspace = t->target_oloc.pool_ns->str; + hoid->nspace_len = t->target_oloc.pool_ns->len; + } else { + hoid->nspace = NULL; + hoid->nspace_len = 0; + } + hoid->pool = t->target_oloc.pool; + ceph_hoid_build_hash_cache(hoid); +} + +static bool should_plug_request(struct ceph_osd_request *req) +{ + struct ceph_osd *osd = req->r_osd; + struct ceph_spg_mapping *spg; + struct ceph_osd_backoff *backoff; + struct ceph_hobject_id hoid; + + spg = lookup_spg_mapping(&osd->o_backoff_mappings, &req->r_t.spgid); + if (!spg) + return false; + + hoid_fill_from_target(&hoid, &req->r_t); + backoff = lookup_containing_backoff(&spg->backoffs, &hoid); + if (!backoff) + return false; + + dout("%s req %p tid %llu backoff osd%d spgid %llu.%xs%d id %llu\n", + __func__, req, req->r_tid, osd->o_osd, backoff->spgid.pgid.pool, + backoff->spgid.pgid.seed, backoff->spgid.shard, backoff->id); + return true; +} + static void setup_request_data(struct ceph_osd_request *req, struct ceph_msg *msg) { @@ -1483,7 +1830,37 @@ static void setup_request_data(struct ceph_osd_request *req, WARN_ON(data_len != msg->data_length); } -static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg) +static void encode_pgid(void **p, const struct ceph_pg *pgid) +{ + ceph_encode_8(p, 1); + ceph_encode_64(p, pgid->pool); + ceph_encode_32(p, pgid->seed); + ceph_encode_32(p, -1); /* preferred */ +} + +static void encode_spgid(void **p, const struct ceph_spg *spgid) +{ + ceph_start_encoding(p, 1, 1, CEPH_PGID_ENCODING_LEN + 1); + encode_pgid(p, &spgid->pgid); + ceph_encode_8(p, spgid->shard); +} + +static void encode_oloc(void **p, void *end, + const struct ceph_object_locator *oloc) +{ + ceph_start_encoding(p, 5, 4, ceph_oloc_encoding_size(oloc)); + ceph_encode_64(p, oloc->pool); + ceph_encode_32(p, -1); /* preferred */ + ceph_encode_32(p, 0); /* key len */ + if (oloc->pool_ns) + ceph_encode_string(p, end, oloc->pool_ns->str, + oloc->pool_ns->len); + else + ceph_encode_32(p, 0); +} + +static void encode_request_partial(struct ceph_osd_request *req, + struct ceph_msg *msg) { void *p = msg->front.iov_base; void *const end = p + msg->front_alloc_len; @@ -1500,38 +1877,27 @@ static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg) setup_request_data(req, msg); - ceph_encode_32(&p, 1); /* client_inc, always 1 */ + encode_spgid(&p, &req->r_t.spgid); /* actual spg */ + ceph_encode_32(&p, req->r_t.pgid.seed); /* raw hash */ ceph_encode_32(&p, req->r_osdc->osdmap->epoch); ceph_encode_32(&p, req->r_flags); - ceph_encode_timespec(p, &req->r_mtime); - p += sizeof(struct ceph_timespec); - /* reassert_version */ - memset(p, 0, sizeof(struct ceph_eversion)); - p += sizeof(struct ceph_eversion); - - /* oloc */ - ceph_start_encoding(&p, 5, 4, - ceph_oloc_encoding_size(&req->r_t.target_oloc)); - ceph_encode_64(&p, req->r_t.target_oloc.pool); - ceph_encode_32(&p, -1); /* preferred */ - ceph_encode_32(&p, 0); /* key len */ - if (req->r_t.target_oloc.pool_ns) - ceph_encode_string(&p, end, req->r_t.target_oloc.pool_ns->str, - req->r_t.target_oloc.pool_ns->len); - else - ceph_encode_32(&p, 0); + /* reqid */ + ceph_start_encoding(&p, 2, 2, sizeof(struct ceph_osd_reqid)); + memset(p, 0, sizeof(struct ceph_osd_reqid)); + p += sizeof(struct ceph_osd_reqid); + + /* trace */ + memset(p, 0, sizeof(struct ceph_blkin_trace_info)); + p += sizeof(struct ceph_blkin_trace_info); - /* pgid */ - ceph_encode_8(&p, 1); - ceph_encode_64(&p, req->r_t.pgid.pool); - ceph_encode_32(&p, req->r_t.pgid.seed); - ceph_encode_32(&p, -1); /* preferred */ + ceph_encode_32(&p, 0); /* client_inc, always 0 */ + ceph_encode_timespec(p, &req->r_mtime); + p += sizeof(struct ceph_timespec); - /* oid */ - ceph_encode_32(&p, req->r_t.target_oid.name_len); - memcpy(p, req->r_t.target_oid.name, req->r_t.target_oid.name_len); - p += req->r_t.target_oid.name_len; + encode_oloc(&p, end, &req->r_t.target_oloc); + ceph_encode_string(&p, end, req->r_t.target_oid.name, + req->r_t.target_oid.name_len); /* ops, can imply data */ ceph_encode_16(&p, req->r_num_ops); @@ -1552,11 +1918,10 @@ static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg) } ceph_encode_32(&p, req->r_attempts); /* retry_attempt */ + BUG_ON(p != end - 8); /* space for features */ - BUG_ON(p > end); - msg->front.iov_len = p - msg->front.iov_base; - msg->hdr.version = cpu_to_le16(4); /* MOSDOp v4 */ - msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); + msg->hdr.version = cpu_to_le16(8); /* MOSDOp v8 */ + /* front_len is finalized in encode_request_finish() */ msg->hdr.data_len = cpu_to_le32(data_len); /* * The header "data_off" is a hint to the receiver allowing it @@ -1565,9 +1930,99 @@ static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg) */ msg->hdr.data_off = cpu_to_le16(req->r_data_offset); - dout("%s req %p oid %s oid_len %d front %zu data %u\n", __func__, - req, req->r_t.target_oid.name, req->r_t.target_oid.name_len, - msg->front.iov_len, data_len); + dout("%s req %p msg %p oid %s oid_len %d\n", __func__, req, msg, + req->r_t.target_oid.name, req->r_t.target_oid.name_len); +} + +static void encode_request_finish(struct ceph_msg *msg) +{ + void *p = msg->front.iov_base; + void *const end = p + msg->front_alloc_len; + + if (CEPH_HAVE_FEATURE(msg->con->peer_features, RESEND_ON_SPLIT)) { + /* luminous OSD -- encode features and be done */ + p = end - 8; + ceph_encode_64(&p, msg->con->peer_features); + } else { + struct { + char spgid[CEPH_ENCODING_START_BLK_LEN + + CEPH_PGID_ENCODING_LEN + 1]; + __le32 hash; + __le32 epoch; + __le32 flags; + char reqid[CEPH_ENCODING_START_BLK_LEN + + sizeof(struct ceph_osd_reqid)]; + char trace[sizeof(struct ceph_blkin_trace_info)]; + __le32 client_inc; + struct ceph_timespec mtime; + } __packed head; + struct ceph_pg pgid; + void *oloc, *oid, *tail; + int oloc_len, oid_len, tail_len; + int len; + + /* + * Pre-luminous OSD -- reencode v8 into v4 using @head + * as a temporary buffer. Encode the raw PG; the rest + * is just a matter of moving oloc, oid and tail blobs + * around. + */ + memcpy(&head, p, sizeof(head)); + p += sizeof(head); + + oloc = p; + p += CEPH_ENCODING_START_BLK_LEN; + pgid.pool = ceph_decode_64(&p); + p += 4 + 4; /* preferred, key len */ + len = ceph_decode_32(&p); + p += len; /* nspace */ + oloc_len = p - oloc; + + oid = p; + len = ceph_decode_32(&p); + p += len; + oid_len = p - oid; + + tail = p; + tail_len = (end - p) - 8; + + p = msg->front.iov_base; + ceph_encode_copy(&p, &head.client_inc, sizeof(head.client_inc)); + ceph_encode_copy(&p, &head.epoch, sizeof(head.epoch)); + ceph_encode_copy(&p, &head.flags, sizeof(head.flags)); + ceph_encode_copy(&p, &head.mtime, sizeof(head.mtime)); + + /* reassert_version */ + memset(p, 0, sizeof(struct ceph_eversion)); + p += sizeof(struct ceph_eversion); + + BUG_ON(p >= oloc); + memmove(p, oloc, oloc_len); + p += oloc_len; + + pgid.seed = le32_to_cpu(head.hash); + encode_pgid(&p, &pgid); /* raw pg */ + + BUG_ON(p >= oid); + memmove(p, oid, oid_len); + p += oid_len; + + /* tail -- ops, snapid, snapc, retry_attempt */ + BUG_ON(p >= tail); + memmove(p, tail, tail_len); + p += tail_len; + + msg->hdr.version = cpu_to_le16(4); /* MOSDOp v4 */ + } + + BUG_ON(p > end); + msg->front.iov_len = p - msg->front.iov_base; + msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); + + dout("%s msg %p tid %llu %u+%u+%u v%d\n", __func__, msg, + le64_to_cpu(msg->hdr.tid), le32_to_cpu(msg->hdr.front_len), + le32_to_cpu(msg->hdr.middle_len), le32_to_cpu(msg->hdr.data_len), + le16_to_cpu(msg->hdr.version)); } /* @@ -1580,6 +2035,10 @@ static void send_request(struct ceph_osd_request *req) verify_osd_locked(osd); WARN_ON(osd->o_osd != req->r_t.osd); + /* backoff? */ + if (should_plug_request(req)) + return; + /* * We may have a previously queued request message hanging * around. Cancel it to avoid corrupting the msgr. @@ -1593,11 +2052,13 @@ static void send_request(struct ceph_osd_request *req) else WARN_ON(req->r_flags & CEPH_OSD_FLAG_RETRY); - encode_request(req, req->r_request); + encode_request_partial(req, req->r_request); - dout("%s req %p tid %llu to pg %llu.%x osd%d flags 0x%x attempt %d\n", + dout("%s req %p tid %llu to pgid %llu.%x spgid %llu.%xs%d osd%d e%u flags 0x%x attempt %d\n", __func__, req, req->r_tid, req->r_t.pgid.pool, req->r_t.pgid.seed, - req->r_t.osd, req->r_flags, req->r_attempts); + req->r_t.spgid.pgid.pool, req->r_t.spgid.pgid.seed, + req->r_t.spgid.shard, osd->o_osd, req->r_t.epoch, req->r_flags, + req->r_attempts); req->r_t.paused = false; req->r_stamp = jiffies; @@ -1645,7 +2106,7 @@ static void __submit_request(struct ceph_osd_request *req, bool wrlocked) dout("%s req %p wrlocked %d\n", __func__, req, wrlocked); again: - ct_res = calc_target(osdc, &req->r_t, &req->r_last_force_resend, false); + ct_res = calc_target(osdc, &req->r_t, NULL, false); if (ct_res == CALC_TARGET_POOL_DNE && !wrlocked) goto promote; @@ -1737,13 +2198,12 @@ static void submit_request(struct ceph_osd_request *req, bool wrlocked) static void finish_request(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; - struct ceph_osd *osd = req->r_osd; - verify_osd_locked(osd); + WARN_ON(lookup_request_mc(&osdc->map_checks, req->r_tid)); dout("%s req %p tid %llu\n", __func__, req, req->r_tid); - WARN_ON(lookup_request_mc(&osdc->map_checks, req->r_tid)); - unlink_request(osd, req); + if (req->r_osd) + unlink_request(req->r_osd, req); atomic_dec(&osdc->num_requests); /* @@ -2441,7 +2901,7 @@ static void linger_submit(struct ceph_osd_linger_request *lreq) struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd *osd; - calc_target(osdc, &lreq->t, &lreq->last_force_resend, false); + calc_target(osdc, &lreq->t, NULL, false); osd = lookup_create_osd(osdc, lreq->t.osd, true); link_linger(osd, lreq); @@ -3059,7 +3519,7 @@ recalc_linger_target(struct ceph_osd_linger_request *lreq) struct ceph_osd_client *osdc = lreq->osdc; enum calc_target_result ct_res; - ct_res = calc_target(osdc, &lreq->t, &lreq->last_force_resend, true); + ct_res = calc_target(osdc, &lreq->t, NULL, true); if (ct_res == CALC_TARGET_NEED_RESEND) { struct ceph_osd *osd; @@ -3117,6 +3577,7 @@ static void scan_requests(struct ceph_osd *osd, list_add_tail(&lreq->scan_item, need_resend_linger); break; case CALC_TARGET_POOL_DNE: + list_del_init(&lreq->scan_item); check_linger_pool_dne(lreq); break; } @@ -3130,8 +3591,8 @@ static void scan_requests(struct ceph_osd *osd, n = rb_next(n); /* unlink_request(), check_pool_dne() */ dout("%s req %p tid %llu\n", __func__, req, req->r_tid); - ct_res = calc_target(osdc, &req->r_t, - &req->r_last_force_resend, false); + ct_res = calc_target(osdc, &req->r_t, &req->r_osd->o_con, + false); switch (ct_res) { case CALC_TARGET_NO_ACTION: force_resend_writes = cleared_full || @@ -3229,8 +3690,25 @@ static void kick_requests(struct ceph_osd_client *osdc, struct list_head *need_resend_linger) { struct ceph_osd_linger_request *lreq, *nlreq; + enum calc_target_result ct_res; struct rb_node *n; + /* make sure need_resend targets reflect latest map */ + for (n = rb_first(need_resend); n; ) { + struct ceph_osd_request *req = + rb_entry(n, struct ceph_osd_request, r_node); + + n = rb_next(n); + + if (req->r_t.epoch < osdc->osdmap->epoch) { + ct_res = calc_target(osdc, &req->r_t, NULL, false); + if (ct_res == CALC_TARGET_POOL_DNE) { + erase_request(need_resend, req); + check_pool_dne(req); + } + } + } + for (n = rb_first(need_resend); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); @@ -3239,8 +3717,6 @@ static void kick_requests(struct ceph_osd_client *osdc, n = rb_next(n); erase_request(need_resend, req); /* before link_request() */ - WARN_ON(req->r_osd); - calc_target(osdc, &req->r_t, NULL, false); osd = lookup_create_osd(osdc, req->r_t.osd, true); link_request(osd, req); if (!req->r_linger) { @@ -3383,6 +3859,8 @@ static void kick_osd_requests(struct ceph_osd *osd) { struct rb_node *n; + clear_backoffs(osd); + for (n = rb_first(&osd->o_requests); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); @@ -3428,6 +3906,261 @@ out_unlock: up_write(&osdc->lock); } +struct MOSDBackoff { + struct ceph_spg spgid; + u32 map_epoch; + u8 op; + u64 id; + struct ceph_hobject_id *begin; + struct ceph_hobject_id *end; +}; + +static int decode_MOSDBackoff(const struct ceph_msg *msg, struct MOSDBackoff *m) +{ + void *p = msg->front.iov_base; + void *const end = p + msg->front.iov_len; + u8 struct_v; + u32 struct_len; + int ret; + + ret = ceph_start_decoding(&p, end, 1, "spg_t", &struct_v, &struct_len); + if (ret) + return ret; + + ret = ceph_decode_pgid(&p, end, &m->spgid.pgid); + if (ret) + return ret; + + ceph_decode_8_safe(&p, end, m->spgid.shard, e_inval); + ceph_decode_32_safe(&p, end, m->map_epoch, e_inval); + ceph_decode_8_safe(&p, end, m->op, e_inval); + ceph_decode_64_safe(&p, end, m->id, e_inval); + + m->begin = kzalloc(sizeof(*m->begin), GFP_NOIO); + if (!m->begin) + return -ENOMEM; + + ret = decode_hoid(&p, end, m->begin); + if (ret) { + free_hoid(m->begin); + return ret; + } + + m->end = kzalloc(sizeof(*m->end), GFP_NOIO); + if (!m->end) { + free_hoid(m->begin); + return -ENOMEM; + } + + ret = decode_hoid(&p, end, m->end); + if (ret) { + free_hoid(m->begin); + free_hoid(m->end); + return ret; + } + + return 0; + +e_inval: + return -EINVAL; +} + +static struct ceph_msg *create_backoff_message( + const struct ceph_osd_backoff *backoff, + u32 map_epoch) +{ + struct ceph_msg *msg; + void *p, *end; + int msg_size; + + msg_size = CEPH_ENCODING_START_BLK_LEN + + CEPH_PGID_ENCODING_LEN + 1; /* spgid */ + msg_size += 4 + 1 + 8; /* map_epoch, op, id */ + msg_size += CEPH_ENCODING_START_BLK_LEN + + hoid_encoding_size(backoff->begin); + msg_size += CEPH_ENCODING_START_BLK_LEN + + hoid_encoding_size(backoff->end); + + msg = ceph_msg_new(CEPH_MSG_OSD_BACKOFF, msg_size, GFP_NOIO, true); + if (!msg) + return NULL; + + p = msg->front.iov_base; + end = p + msg->front_alloc_len; + + encode_spgid(&p, &backoff->spgid); + ceph_encode_32(&p, map_epoch); + ceph_encode_8(&p, CEPH_OSD_BACKOFF_OP_ACK_BLOCK); + ceph_encode_64(&p, backoff->id); + encode_hoid(&p, end, backoff->begin); + encode_hoid(&p, end, backoff->end); + BUG_ON(p != end); + + msg->front.iov_len = p - msg->front.iov_base; + msg->hdr.version = cpu_to_le16(1); /* MOSDBackoff v1 */ + msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); + + return msg; +} + +static void handle_backoff_block(struct ceph_osd *osd, struct MOSDBackoff *m) +{ + struct ceph_spg_mapping *spg; + struct ceph_osd_backoff *backoff; + struct ceph_msg *msg; + + dout("%s osd%d spgid %llu.%xs%d id %llu\n", __func__, osd->o_osd, + m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id); + + spg = lookup_spg_mapping(&osd->o_backoff_mappings, &m->spgid); + if (!spg) { + spg = alloc_spg_mapping(); + if (!spg) { + pr_err("%s failed to allocate spg\n", __func__); + return; + } + spg->spgid = m->spgid; /* struct */ + insert_spg_mapping(&osd->o_backoff_mappings, spg); + } + + backoff = alloc_backoff(); + if (!backoff) { + pr_err("%s failed to allocate backoff\n", __func__); + return; + } + backoff->spgid = m->spgid; /* struct */ + backoff->id = m->id; + backoff->begin = m->begin; + m->begin = NULL; /* backoff now owns this */ + backoff->end = m->end; + m->end = NULL; /* ditto */ + + insert_backoff(&spg->backoffs, backoff); + insert_backoff_by_id(&osd->o_backoffs_by_id, backoff); + + /* + * Ack with original backoff's epoch so that the OSD can + * discard this if there was a PG split. + */ + msg = create_backoff_message(backoff, m->map_epoch); + if (!msg) { + pr_err("%s failed to allocate msg\n", __func__); + return; + } + ceph_con_send(&osd->o_con, msg); +} + +static bool target_contained_by(const struct ceph_osd_request_target *t, + const struct ceph_hobject_id *begin, + const struct ceph_hobject_id *end) +{ + struct ceph_hobject_id hoid; + int cmp; + + hoid_fill_from_target(&hoid, t); + cmp = hoid_compare(&hoid, begin); + return !cmp || (cmp > 0 && hoid_compare(&hoid, end) < 0); +} + +static void handle_backoff_unblock(struct ceph_osd *osd, + const struct MOSDBackoff *m) +{ + struct ceph_spg_mapping *spg; + struct ceph_osd_backoff *backoff; + struct rb_node *n; + + dout("%s osd%d spgid %llu.%xs%d id %llu\n", __func__, osd->o_osd, + m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id); + + backoff = lookup_backoff_by_id(&osd->o_backoffs_by_id, m->id); + if (!backoff) { + pr_err("%s osd%d spgid %llu.%xs%d id %llu backoff dne\n", + __func__, osd->o_osd, m->spgid.pgid.pool, + m->spgid.pgid.seed, m->spgid.shard, m->id); + return; + } + + if (hoid_compare(backoff->begin, m->begin) && + hoid_compare(backoff->end, m->end)) { + pr_err("%s osd%d spgid %llu.%xs%d id %llu bad range?\n", + __func__, osd->o_osd, m->spgid.pgid.pool, + m->spgid.pgid.seed, m->spgid.shard, m->id); + /* unblock it anyway... */ + } + + spg = lookup_spg_mapping(&osd->o_backoff_mappings, &backoff->spgid); + BUG_ON(!spg); + + erase_backoff(&spg->backoffs, backoff); + erase_backoff_by_id(&osd->o_backoffs_by_id, backoff); + free_backoff(backoff); + + if (RB_EMPTY_ROOT(&spg->backoffs)) { + erase_spg_mapping(&osd->o_backoff_mappings, spg); + free_spg_mapping(spg); + } + + for (n = rb_first(&osd->o_requests); n; n = rb_next(n)) { + struct ceph_osd_request *req = + rb_entry(n, struct ceph_osd_request, r_node); + + if (!ceph_spg_compare(&req->r_t.spgid, &m->spgid)) { + /* + * Match against @m, not @backoff -- the PG may + * have split on the OSD. + */ + if (target_contained_by(&req->r_t, m->begin, m->end)) { + /* + * If no other installed backoff applies, + * resend. + */ + send_request(req); + } + } + } +} + +static void handle_backoff(struct ceph_osd *osd, struct ceph_msg *msg) +{ + struct ceph_osd_client *osdc = osd->o_osdc; + struct MOSDBackoff m; + int ret; + + down_read(&osdc->lock); + if (!osd_registered(osd)) { + dout("%s osd%d unknown\n", __func__, osd->o_osd); + up_read(&osdc->lock); + return; + } + WARN_ON(osd->o_osd != le64_to_cpu(msg->hdr.src.num)); + + mutex_lock(&osd->lock); + ret = decode_MOSDBackoff(msg, &m); + if (ret) { + pr_err("failed to decode MOSDBackoff: %d\n", ret); + ceph_msg_dump(msg); + goto out_unlock; + } + + switch (m.op) { + case CEPH_OSD_BACKOFF_OP_BLOCK: + handle_backoff_block(osd, &m); + break; + case CEPH_OSD_BACKOFF_OP_UNBLOCK: + handle_backoff_unblock(osd, &m); + break; + default: + pr_err("%s osd%d unknown op %d\n", __func__, osd->o_osd, m.op); + } + + free_hoid(m.begin); + free_hoid(m.end); + +out_unlock: + mutex_unlock(&osd->lock); + up_read(&osdc->lock); +} + /* * Process osd watch notifications */ @@ -4365,6 +5098,9 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) case CEPH_MSG_OSD_OPREPLY: handle_reply(osd, msg); break; + case CEPH_MSG_OSD_BACKOFF: + handle_backoff(osd, msg); + break; case CEPH_MSG_WATCH_NOTIFY: handle_watch_notify(osdc, msg); break; @@ -4487,6 +5223,7 @@ static struct ceph_msg *alloc_msg(struct ceph_connection *con, *skip = 0; switch (type) { case CEPH_MSG_OSD_MAP: + case CEPH_MSG_OSD_BACKOFF: case CEPH_MSG_WATCH_NOTIFY: return alloc_msg_with_page_vector(hdr); case CEPH_MSG_OSD_OPREPLY: @@ -4571,6 +5308,14 @@ static int invalidate_authorizer(struct ceph_connection *con) return ceph_monc_validate_auth(&osdc->client->monc); } +static void osd_reencode_message(struct ceph_msg *msg) +{ + int type = le16_to_cpu(msg->hdr.type); + + if (type == CEPH_MSG_OSD_OP) + encode_request_finish(msg); +} + static int osd_sign_message(struct ceph_msg *msg) { struct ceph_osd *o = msg->con->private; @@ -4595,6 +5340,7 @@ static const struct ceph_connection_operations osd_con_ops = { .verify_authorizer_reply = verify_authorizer_reply, .invalidate_authorizer = invalidate_authorizer, .alloc_msg = alloc_msg, + .reencode_message = osd_reencode_message, .sign_message = osd_sign_message, .check_message_signature = osd_check_message_signature, .fault = osd_fault, diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 55e3a477f92d..64ae9f89773a 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -11,7 +11,7 @@ #include <linux/crush/hash.h> #include <linux/crush/mapper.h> -char *ceph_osdmap_state_str(char *str, int len, int state) +char *ceph_osdmap_state_str(char *str, int len, u32 state) { if (!len) return str; @@ -138,19 +138,175 @@ bad: return -EINVAL; } -static int skip_name_map(void **p, void *end) +static struct crush_choose_arg_map *alloc_choose_arg_map(void) { - int len; - ceph_decode_32_safe(p, end, len ,bad); - while (len--) { - int strlen; - *p += sizeof(u32); - ceph_decode_32_safe(p, end, strlen, bad); - *p += strlen; + struct crush_choose_arg_map *arg_map; + + arg_map = kzalloc(sizeof(*arg_map), GFP_NOIO); + if (!arg_map) + return NULL; + + RB_CLEAR_NODE(&arg_map->node); + return arg_map; } - return 0; -bad: - return -EINVAL; + +static void free_choose_arg_map(struct crush_choose_arg_map *arg_map) +{ + if (arg_map) { + int i, j; + + WARN_ON(!RB_EMPTY_NODE(&arg_map->node)); + + for (i = 0; i < arg_map->size; i++) { + struct crush_choose_arg *arg = &arg_map->args[i]; + + for (j = 0; j < arg->weight_set_size; j++) + kfree(arg->weight_set[j].weights); + kfree(arg->weight_set); + kfree(arg->ids); + } + kfree(arg_map->args); + kfree(arg_map); + } +} + +DEFINE_RB_FUNCS(choose_arg_map, struct crush_choose_arg_map, choose_args_index, + node); + +void clear_choose_args(struct crush_map *c) +{ + while (!RB_EMPTY_ROOT(&c->choose_args)) { + struct crush_choose_arg_map *arg_map = + rb_entry(rb_first(&c->choose_args), + struct crush_choose_arg_map, node); + + erase_choose_arg_map(&c->choose_args, arg_map); + free_choose_arg_map(arg_map); + } +} + +static u32 *decode_array_32_alloc(void **p, void *end, u32 *plen) +{ + u32 *a = NULL; + u32 len; + int ret; + + ceph_decode_32_safe(p, end, len, e_inval); + if (len) { + u32 i; + + a = kmalloc_array(len, sizeof(u32), GFP_NOIO); + if (!a) { + ret = -ENOMEM; + goto fail; + } + + ceph_decode_need(p, end, len * sizeof(u32), e_inval); + for (i = 0; i < len; i++) + a[i] = ceph_decode_32(p); + } + + *plen = len; + return a; + +e_inval: + ret = -EINVAL; +fail: + kfree(a); + return ERR_PTR(ret); +} + +/* + * Assumes @arg is zero-initialized. + */ +static int decode_choose_arg(void **p, void *end, struct crush_choose_arg *arg) +{ + int ret; + + ceph_decode_32_safe(p, end, arg->weight_set_size, e_inval); + if (arg->weight_set_size) { + u32 i; + + arg->weight_set = kmalloc_array(arg->weight_set_size, + sizeof(*arg->weight_set), + GFP_NOIO); + if (!arg->weight_set) + return -ENOMEM; + + for (i = 0; i < arg->weight_set_size; i++) { + struct crush_weight_set *w = &arg->weight_set[i]; + + w->weights = decode_array_32_alloc(p, end, &w->size); + if (IS_ERR(w->weights)) { + ret = PTR_ERR(w->weights); + w->weights = NULL; + return ret; + } + } + } + + arg->ids = decode_array_32_alloc(p, end, &arg->ids_size); + if (IS_ERR(arg->ids)) { + ret = PTR_ERR(arg->ids); + arg->ids = NULL; + return ret; + } + + return 0; + +e_inval: + return -EINVAL; +} + +static int decode_choose_args(void **p, void *end, struct crush_map *c) +{ + struct crush_choose_arg_map *arg_map = NULL; + u32 num_choose_arg_maps, num_buckets; + int ret; + + ceph_decode_32_safe(p, end, num_choose_arg_maps, e_inval); + while (num_choose_arg_maps--) { + arg_map = alloc_choose_arg_map(); + if (!arg_map) { + ret = -ENOMEM; + goto fail; + } + + ceph_decode_64_safe(p, end, arg_map->choose_args_index, + e_inval); + arg_map->size = c->max_buckets; + arg_map->args = kcalloc(arg_map->size, sizeof(*arg_map->args), + GFP_NOIO); + if (!arg_map->args) { + ret = -ENOMEM; + goto fail; + } + + ceph_decode_32_safe(p, end, num_buckets, e_inval); + while (num_buckets--) { + struct crush_choose_arg *arg; + u32 bucket_index; + + ceph_decode_32_safe(p, end, bucket_index, e_inval); + if (bucket_index >= arg_map->size) + goto e_inval; + + arg = &arg_map->args[bucket_index]; + ret = decode_choose_arg(p, end, arg); + if (ret) + goto fail; + } + + insert_choose_arg_map(&c->choose_args, arg_map); + } + + return 0; + +e_inval: + ret = -EINVAL; +fail: + free_choose_arg_map(arg_map); + return ret; } static void crush_finalize(struct crush_map *c) @@ -182,12 +338,11 @@ static void crush_finalize(struct crush_map *c) static struct crush_map *crush_decode(void *pbyval, void *end) { struct crush_map *c; - int err = -EINVAL; + int err; int i, j; void **p = &pbyval; void *start = pbyval; u32 magic; - u32 num_name_maps; dout("crush_decode %p to %p len %d\n", *p, end, (int)(end - *p)); @@ -195,6 +350,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end) if (c == NULL) return ERR_PTR(-ENOMEM); + c->choose_args = RB_ROOT; + /* set tunables to default values */ c->choose_local_tries = 2; c->choose_local_fallback_tries = 5; @@ -250,7 +407,6 @@ static struct crush_map *crush_decode(void *pbyval, void *end) size = sizeof(struct crush_bucket_straw2); break; default: - err = -EINVAL; goto bad; } BUG_ON(size == 0); @@ -282,31 +438,31 @@ static struct crush_map *crush_decode(void *pbyval, void *end) err = crush_decode_uniform_bucket(p, end, (struct crush_bucket_uniform *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_LIST: err = crush_decode_list_bucket(p, end, (struct crush_bucket_list *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_TREE: err = crush_decode_tree_bucket(p, end, (struct crush_bucket_tree *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_STRAW: err = crush_decode_straw_bucket(p, end, (struct crush_bucket_straw *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_STRAW2: err = crush_decode_straw2_bucket(p, end, (struct crush_bucket_straw2 *)b); if (err < 0) - goto bad; + goto fail; break; } } @@ -317,7 +473,6 @@ static struct crush_map *crush_decode(void *pbyval, void *end) u32 yes; struct crush_rule *r; - err = -EINVAL; ceph_decode_32_safe(p, end, yes, bad); if (!yes) { dout("crush_decode NO rule %d off %x %p to %p\n", @@ -332,7 +487,6 @@ static struct crush_map *crush_decode(void *pbyval, void *end) /* len */ ceph_decode_32_safe(p, end, yes, bad); #if BITS_PER_LONG == 32 - err = -EINVAL; if (yes > (ULONG_MAX - sizeof(*r)) / sizeof(struct crush_rule_step)) goto bad; @@ -353,12 +507,9 @@ static struct crush_map *crush_decode(void *pbyval, void *end) } } - /* ignore trailing name maps. */ - for (num_name_maps = 0; num_name_maps < 3; num_name_maps++) { - err = skip_name_map(p, end); - if (err < 0) - goto done; - } + ceph_decode_skip_map(p, end, 32, string, bad); /* type_map */ + ceph_decode_skip_map(p, end, 32, string, bad); /* name_map */ + ceph_decode_skip_map(p, end, 32, string, bad); /* rule_name_map */ /* tunables */ ceph_decode_need(p, end, 3*sizeof(u32), done); @@ -391,6 +542,21 @@ static struct crush_map *crush_decode(void *pbyval, void *end) dout("crush decode tunable chooseleaf_stable = %d\n", c->chooseleaf_stable); + if (*p != end) { + /* class_map */ + ceph_decode_skip_map(p, end, 32, 32, bad); + /* class_name */ + ceph_decode_skip_map(p, end, 32, string, bad); + /* class_bucket */ + ceph_decode_skip_map_of_map(p, end, 32, 32, 32, bad); + } + + if (*p != end) { + err = decode_choose_args(p, end, c); + if (err) + goto fail; + } + done: crush_finalize(c); dout("crush_decode success\n"); @@ -398,10 +564,14 @@ done: badmem: err = -ENOMEM; -bad: +fail: dout("crush_decode fail %d\n", err); crush_destroy(c); return ERR_PTR(err); + +bad: + err = -EINVAL; + goto fail; } int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs) @@ -418,75 +588,49 @@ int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs) return 0; } -/* - * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid - * to a set of osds) and primary_temp (explicit primary setting) - */ -static int __insert_pg_mapping(struct ceph_pg_mapping *new, - struct rb_root *root) +int ceph_spg_compare(const struct ceph_spg *lhs, const struct ceph_spg *rhs) { - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - struct ceph_pg_mapping *pg = NULL; - int c; + int ret; - dout("__insert_pg_mapping %llx %p\n", *(u64 *)&new->pgid, new); - while (*p) { - parent = *p; - pg = rb_entry(parent, struct ceph_pg_mapping, node); - c = ceph_pg_compare(&new->pgid, &pg->pgid); - if (c < 0) - p = &(*p)->rb_left; - else if (c > 0) - p = &(*p)->rb_right; - else - return -EEXIST; - } + ret = ceph_pg_compare(&lhs->pgid, &rhs->pgid); + if (ret) + return ret; + + if (lhs->shard < rhs->shard) + return -1; + if (lhs->shard > rhs->shard) + return 1; - rb_link_node(&new->node, parent, p); - rb_insert_color(&new->node, root); return 0; } -static struct ceph_pg_mapping *__lookup_pg_mapping(struct rb_root *root, - struct ceph_pg pgid) +static struct ceph_pg_mapping *alloc_pg_mapping(size_t payload_len) { - struct rb_node *n = root->rb_node; struct ceph_pg_mapping *pg; - int c; - while (n) { - pg = rb_entry(n, struct ceph_pg_mapping, node); - c = ceph_pg_compare(&pgid, &pg->pgid); - if (c < 0) { - n = n->rb_left; - } else if (c > 0) { - n = n->rb_right; - } else { - dout("__lookup_pg_mapping %lld.%x got %p\n", - pgid.pool, pgid.seed, pg); - return pg; - } - } - return NULL; + pg = kmalloc(sizeof(*pg) + payload_len, GFP_NOIO); + if (!pg) + return NULL; + + RB_CLEAR_NODE(&pg->node); + return pg; } -static int __remove_pg_mapping(struct rb_root *root, struct ceph_pg pgid) +static void free_pg_mapping(struct ceph_pg_mapping *pg) { - struct ceph_pg_mapping *pg = __lookup_pg_mapping(root, pgid); + WARN_ON(!RB_EMPTY_NODE(&pg->node)); - if (pg) { - dout("__remove_pg_mapping %lld.%x %p\n", pgid.pool, pgid.seed, - pg); - rb_erase(&pg->node, root); - kfree(pg); - return 0; - } - dout("__remove_pg_mapping %lld.%x dne\n", pgid.pool, pgid.seed); - return -ENOENT; + kfree(pg); } /* + * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid + * to a set of osds) and primary_temp (explicit primary setting) + */ +DEFINE_RB_FUNCS2(pg_mapping, struct ceph_pg_mapping, pgid, ceph_pg_compare, + RB_BYPTR, const struct ceph_pg *, node) + +/* * rbtree of pg pool info */ static int __insert_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *new) @@ -682,11 +826,48 @@ static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) *p += len; } + /* + * last_force_op_resend_preluminous, will be overridden if the + * map was encoded with RESEND_ON_SPLIT + */ if (ev >= 15) pi->last_force_request_resend = ceph_decode_32(p); else pi->last_force_request_resend = 0; + if (ev >= 16) + *p += 4; /* skip min_read_recency_for_promote */ + + if (ev >= 17) + *p += 8; /* skip expected_num_objects */ + + if (ev >= 19) + *p += 4; /* skip cache_target_dirty_high_ratio_micro */ + + if (ev >= 20) + *p += 4; /* skip min_write_recency_for_promote */ + + if (ev >= 21) + *p += 1; /* skip use_gmt_hitset */ + + if (ev >= 22) + *p += 1; /* skip fast_read */ + + if (ev >= 23) { + *p += 4; /* skip hit_set_grade_decay_rate */ + *p += 4; /* skip hit_set_search_last_n */ + } + + if (ev >= 24) { + /* skip opts */ + *p += 1 + 1; /* versions */ + len = ceph_decode_32(p); + *p += len; + } + + if (ev >= 25) + pi->last_force_request_resend = ceph_decode_32(p); + /* ignore the rest */ *p = pool_end; @@ -743,6 +924,8 @@ struct ceph_osdmap *ceph_osdmap_alloc(void) map->pool_max = -1; map->pg_temp = RB_ROOT; map->primary_temp = RB_ROOT; + map->pg_upmap = RB_ROOT; + map->pg_upmap_items = RB_ROOT; mutex_init(&map->crush_workspace_mutex); return map; @@ -757,14 +940,28 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map) struct ceph_pg_mapping *pg = rb_entry(rb_first(&map->pg_temp), struct ceph_pg_mapping, node); - rb_erase(&pg->node, &map->pg_temp); - kfree(pg); + erase_pg_mapping(&map->pg_temp, pg); + free_pg_mapping(pg); } while (!RB_EMPTY_ROOT(&map->primary_temp)) { struct ceph_pg_mapping *pg = rb_entry(rb_first(&map->primary_temp), struct ceph_pg_mapping, node); - rb_erase(&pg->node, &map->primary_temp); + erase_pg_mapping(&map->primary_temp, pg); + free_pg_mapping(pg); + } + while (!RB_EMPTY_ROOT(&map->pg_upmap)) { + struct ceph_pg_mapping *pg = + rb_entry(rb_first(&map->pg_upmap), + struct ceph_pg_mapping, node); + rb_erase(&pg->node, &map->pg_upmap); + kfree(pg); + } + while (!RB_EMPTY_ROOT(&map->pg_upmap_items)) { + struct ceph_pg_mapping *pg = + rb_entry(rb_first(&map->pg_upmap_items), + struct ceph_pg_mapping, node); + rb_erase(&pg->node, &map->pg_upmap_items); kfree(pg); } while (!RB_EMPTY_ROOT(&map->pg_pools)) { @@ -788,7 +985,7 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map) */ static int osdmap_set_max_osd(struct ceph_osdmap *map, int max) { - u8 *state; + u32 *state; u32 *weight; struct ceph_entity_addr *addr; int i; @@ -964,47 +1161,40 @@ static int decode_new_pools(void **p, void *end, struct ceph_osdmap *map) return __decode_pools(p, end, map, true); } -static int __decode_pg_temp(void **p, void *end, struct ceph_osdmap *map, - bool incremental) +typedef struct ceph_pg_mapping *(*decode_mapping_fn_t)(void **, void *, bool); + +static int decode_pg_mapping(void **p, void *end, struct rb_root *mapping_root, + decode_mapping_fn_t fn, bool incremental) { u32 n; + WARN_ON(!incremental && !fn); + ceph_decode_32_safe(p, end, n, e_inval); while (n--) { + struct ceph_pg_mapping *pg; struct ceph_pg pgid; - u32 len, i; int ret; ret = ceph_decode_pgid(p, end, &pgid); if (ret) return ret; - ceph_decode_32_safe(p, end, len, e_inval); - - ret = __remove_pg_mapping(&map->pg_temp, pgid); - BUG_ON(!incremental && ret != -ENOENT); - - if (!incremental || len > 0) { - struct ceph_pg_mapping *pg; - - ceph_decode_need(p, end, len*sizeof(u32), e_inval); - - if (len > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) - return -EINVAL; - - pg = kzalloc(sizeof(*pg) + len*sizeof(u32), GFP_NOFS); - if (!pg) - return -ENOMEM; + pg = lookup_pg_mapping(mapping_root, &pgid); + if (pg) { + WARN_ON(!incremental); + erase_pg_mapping(mapping_root, pg); + free_pg_mapping(pg); + } - pg->pgid = pgid; - pg->pg_temp.len = len; - for (i = 0; i < len; i++) - pg->pg_temp.osds[i] = ceph_decode_32(p); + if (fn) { + pg = fn(p, end, incremental); + if (IS_ERR(pg)) + return PTR_ERR(pg); - ret = __insert_pg_mapping(pg, &map->pg_temp); - if (ret) { - kfree(pg); - return ret; + if (pg) { + pg->pgid = pgid; /* struct */ + insert_pg_mapping(mapping_root, pg); } } } @@ -1015,69 +1205,77 @@ e_inval: return -EINVAL; } +static struct ceph_pg_mapping *__decode_pg_temp(void **p, void *end, + bool incremental) +{ + struct ceph_pg_mapping *pg; + u32 len, i; + + ceph_decode_32_safe(p, end, len, e_inval); + if (len == 0 && incremental) + return NULL; /* new_pg_temp: [] to remove */ + if (len > (SIZE_MAX - sizeof(*pg)) / sizeof(u32)) + return ERR_PTR(-EINVAL); + + ceph_decode_need(p, end, len * sizeof(u32), e_inval); + pg = alloc_pg_mapping(len * sizeof(u32)); + if (!pg) + return ERR_PTR(-ENOMEM); + + pg->pg_temp.len = len; + for (i = 0; i < len; i++) + pg->pg_temp.osds[i] = ceph_decode_32(p); + + return pg; + +e_inval: + return ERR_PTR(-EINVAL); +} + static int decode_pg_temp(void **p, void *end, struct ceph_osdmap *map) { - return __decode_pg_temp(p, end, map, false); + return decode_pg_mapping(p, end, &map->pg_temp, __decode_pg_temp, + false); } static int decode_new_pg_temp(void **p, void *end, struct ceph_osdmap *map) { - return __decode_pg_temp(p, end, map, true); + return decode_pg_mapping(p, end, &map->pg_temp, __decode_pg_temp, + true); } -static int __decode_primary_temp(void **p, void *end, struct ceph_osdmap *map, - bool incremental) +static struct ceph_pg_mapping *__decode_primary_temp(void **p, void *end, + bool incremental) { - u32 n; - - ceph_decode_32_safe(p, end, n, e_inval); - while (n--) { - struct ceph_pg pgid; - u32 osd; - int ret; - - ret = ceph_decode_pgid(p, end, &pgid); - if (ret) - return ret; - - ceph_decode_32_safe(p, end, osd, e_inval); - - ret = __remove_pg_mapping(&map->primary_temp, pgid); - BUG_ON(!incremental && ret != -ENOENT); - - if (!incremental || osd != (u32)-1) { - struct ceph_pg_mapping *pg; - - pg = kzalloc(sizeof(*pg), GFP_NOFS); - if (!pg) - return -ENOMEM; + struct ceph_pg_mapping *pg; + u32 osd; - pg->pgid = pgid; - pg->primary_temp.osd = osd; + ceph_decode_32_safe(p, end, osd, e_inval); + if (osd == (u32)-1 && incremental) + return NULL; /* new_primary_temp: -1 to remove */ - ret = __insert_pg_mapping(pg, &map->primary_temp); - if (ret) { - kfree(pg); - return ret; - } - } - } + pg = alloc_pg_mapping(0); + if (!pg) + return ERR_PTR(-ENOMEM); - return 0; + pg->primary_temp.osd = osd; + return pg; e_inval: - return -EINVAL; + return ERR_PTR(-EINVAL); } static int decode_primary_temp(void **p, void *end, struct ceph_osdmap *map) { - return __decode_primary_temp(p, end, map, false); + return decode_pg_mapping(p, end, &map->primary_temp, + __decode_primary_temp, false); } static int decode_new_primary_temp(void **p, void *end, struct ceph_osdmap *map) { - return __decode_primary_temp(p, end, map, true); + return decode_pg_mapping(p, end, &map->primary_temp, + __decode_primary_temp, true); } u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd) @@ -1168,6 +1366,75 @@ e_inval: return -EINVAL; } +static struct ceph_pg_mapping *__decode_pg_upmap(void **p, void *end, + bool __unused) +{ + return __decode_pg_temp(p, end, false); +} + +static int decode_pg_upmap(void **p, void *end, struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->pg_upmap, __decode_pg_upmap, + false); +} + +static int decode_new_pg_upmap(void **p, void *end, struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->pg_upmap, __decode_pg_upmap, + true); +} + +static int decode_old_pg_upmap(void **p, void *end, struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->pg_upmap, NULL, true); +} + +static struct ceph_pg_mapping *__decode_pg_upmap_items(void **p, void *end, + bool __unused) +{ + struct ceph_pg_mapping *pg; + u32 len, i; + + ceph_decode_32_safe(p, end, len, e_inval); + if (len > (SIZE_MAX - sizeof(*pg)) / (2 * sizeof(u32))) + return ERR_PTR(-EINVAL); + + ceph_decode_need(p, end, 2 * len * sizeof(u32), e_inval); + pg = alloc_pg_mapping(2 * len * sizeof(u32)); + if (!pg) + return ERR_PTR(-ENOMEM); + + pg->pg_upmap_items.len = len; + for (i = 0; i < len; i++) { + pg->pg_upmap_items.from_to[i][0] = ceph_decode_32(p); + pg->pg_upmap_items.from_to[i][1] = ceph_decode_32(p); + } + + return pg; + +e_inval: + return ERR_PTR(-EINVAL); +} + +static int decode_pg_upmap_items(void **p, void *end, struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->pg_upmap_items, + __decode_pg_upmap_items, false); +} + +static int decode_new_pg_upmap_items(void **p, void *end, + struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->pg_upmap_items, + __decode_pg_upmap_items, true); +} + +static int decode_old_pg_upmap_items(void **p, void *end, + struct ceph_osdmap *map) +{ + return decode_pg_mapping(p, end, &map->pg_upmap_items, NULL, true); +} + /* * decode a full map. */ @@ -1218,13 +1485,21 @@ static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map) /* osd_state, osd_weight, osd_addrs->client_addr */ ceph_decode_need(p, end, 3*sizeof(u32) + - map->max_osd*(1 + sizeof(*map->osd_weight) + + map->max_osd*((struct_v >= 5 ? sizeof(u32) : + sizeof(u8)) + + sizeof(*map->osd_weight) + sizeof(*map->osd_addr)), e_inval); if (ceph_decode_32(p) != map->max_osd) goto e_inval; - ceph_decode_copy(p, map->osd_state, map->max_osd); + if (struct_v >= 5) { + for (i = 0; i < map->max_osd; i++) + map->osd_state[i] = ceph_decode_32(p); + } else { + for (i = 0; i < map->max_osd; i++) + map->osd_state[i] = ceph_decode_8(p); + } if (ceph_decode_32(p) != map->max_osd) goto e_inval; @@ -1257,9 +1532,7 @@ static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map) if (err) goto bad; } else { - /* XXX can this happen? */ - kfree(map->osd_primary_affinity); - map->osd_primary_affinity = NULL; + WARN_ON(map->osd_primary_affinity); } /* crush */ @@ -1268,6 +1541,26 @@ static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map) if (err) goto bad; + *p += len; + if (struct_v >= 3) { + /* erasure_code_profiles */ + ceph_decode_skip_map_of_map(p, end, string, string, string, + e_inval); + } + + if (struct_v >= 4) { + err = decode_pg_upmap(p, end, map); + if (err) + goto bad; + + err = decode_pg_upmap_items(p, end, map); + if (err) + goto bad; + } else { + WARN_ON(!RB_EMPTY_ROOT(&map->pg_upmap)); + WARN_ON(!RB_EMPTY_ROOT(&map->pg_upmap_items)); + } + /* ignore the rest */ *p = end; @@ -1314,7 +1607,7 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end) * new_up_client: { osd=6, addr=... } # set osd_state and addr * new_state: { osd=6, xorstate=EXISTS } # clear osd_state */ -static int decode_new_up_state_weight(void **p, void *end, +static int decode_new_up_state_weight(void **p, void *end, u8 struct_v, struct ceph_osdmap *map) { void *new_up_client; @@ -1330,7 +1623,7 @@ static int decode_new_up_state_weight(void **p, void *end, new_state = *p; ceph_decode_32_safe(p, end, len, e_inval); - len *= sizeof(u32) + sizeof(u8); + len *= sizeof(u32) + (struct_v >= 5 ? sizeof(u32) : sizeof(u8)); ceph_decode_need(p, end, len, e_inval); *p += len; @@ -1366,11 +1659,14 @@ static int decode_new_up_state_weight(void **p, void *end, len = ceph_decode_32(p); while (len--) { s32 osd; - u8 xorstate; + u32 xorstate; int ret; osd = ceph_decode_32(p); - xorstate = ceph_decode_8(p); + if (struct_v >= 5) + xorstate = ceph_decode_32(p); + else + xorstate = ceph_decode_8(p); if (xorstate == 0) xorstate = CEPH_OSD_UP; BUG_ON(osd >= map->max_osd); @@ -1504,7 +1800,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, } /* new_up_client, new_state, new_weight */ - err = decode_new_up_state_weight(p, end, map); + err = decode_new_up_state_weight(p, end, struct_v, map); if (err) goto bad; @@ -1527,6 +1823,32 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, goto bad; } + if (struct_v >= 3) { + /* new_erasure_code_profiles */ + ceph_decode_skip_map_of_map(p, end, string, string, string, + e_inval); + /* old_erasure_code_profiles */ + ceph_decode_skip_set(p, end, string, e_inval); + } + + if (struct_v >= 4) { + err = decode_new_pg_upmap(p, end, map); + if (err) + goto bad; + + err = decode_old_pg_upmap(p, end, map); + if (err) + goto bad; + + err = decode_new_pg_upmap_items(p, end, map); + if (err) + goto bad; + + err = decode_old_pg_upmap_items(p, end, map); + if (err) + goto bad; + } + /* ignore the rest */ *p = end; @@ -1547,12 +1869,13 @@ bad: void ceph_oloc_copy(struct ceph_object_locator *dest, const struct ceph_object_locator *src) { - WARN_ON(!ceph_oloc_empty(dest)); - WARN_ON(dest->pool_ns); /* empty() only covers ->pool */ + ceph_oloc_destroy(dest); dest->pool = src->pool; if (src->pool_ns) dest->pool_ns = ceph_get_string(src->pool_ns); + else + dest->pool_ns = NULL; } EXPORT_SYMBOL(ceph_oloc_copy); @@ -1565,14 +1888,15 @@ EXPORT_SYMBOL(ceph_oloc_destroy); void ceph_oid_copy(struct ceph_object_id *dest, const struct ceph_object_id *src) { - WARN_ON(!ceph_oid_empty(dest)); + ceph_oid_destroy(dest); if (src->name != src->inline_name) { /* very rare, see ceph_object_id definition */ dest->name = kmalloc(src->name_len + 1, GFP_NOIO | __GFP_NOFAIL); + } else { + dest->name = dest->inline_name; } - memcpy(dest->name, src->name, src->name_len + 1); dest->name_len = src->name_len; } @@ -1714,9 +2038,8 @@ void ceph_osds_copy(struct ceph_osds *dest, const struct ceph_osds *src) dest->primary = src->primary; } -static bool is_split(const struct ceph_pg *pgid, - u32 old_pg_num, - u32 new_pg_num) +bool ceph_pg_is_split(const struct ceph_pg *pgid, u32 old_pg_num, + u32 new_pg_num) { int old_bits = calc_bits_of(old_pg_num); int old_mask = (1 << old_bits) - 1; @@ -1761,7 +2084,7 @@ bool ceph_is_new_interval(const struct ceph_osds *old_acting, !osds_equal(old_up, new_up) || old_size != new_size || old_min_size != new_min_size || - is_split(pgid, old_pg_num, new_pg_num) || + ceph_pg_is_split(pgid, old_pg_num, new_pg_num) || old_sort_bitwise != new_sort_bitwise; } @@ -1885,16 +2208,12 @@ EXPORT_SYMBOL(ceph_calc_file_object_mapping); * Should only be called with target_oid and target_oloc (as opposed to * base_oid and base_oloc), since tiering isn't taken into account. */ -int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap, - struct ceph_object_id *oid, - struct ceph_object_locator *oloc, - struct ceph_pg *raw_pgid) +int __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi, + const struct ceph_object_id *oid, + const struct ceph_object_locator *oloc, + struct ceph_pg *raw_pgid) { - struct ceph_pg_pool_info *pi; - - pi = ceph_pg_pool_by_id(osdmap, oloc->pool); - if (!pi) - return -ENOENT; + WARN_ON(pi->id != oloc->pool); if (!oloc->pool_ns) { raw_pgid->pool = oloc->pool; @@ -1926,6 +2245,20 @@ int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap, } return 0; } + +int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap, + const struct ceph_object_id *oid, + const struct ceph_object_locator *oloc, + struct ceph_pg *raw_pgid) +{ + struct ceph_pg_pool_info *pi; + + pi = ceph_pg_pool_by_id(osdmap, oloc->pool); + if (!pi) + return -ENOENT; + + return __ceph_object_locator_to_pg(pi, oid, oloc, raw_pgid); +} EXPORT_SYMBOL(ceph_object_locator_to_pg); /* @@ -1970,23 +2303,57 @@ static u32 raw_pg_to_pps(struct ceph_pg_pool_info *pi, static int do_crush(struct ceph_osdmap *map, int ruleno, int x, int *result, int result_max, - const __u32 *weight, int weight_max) + const __u32 *weight, int weight_max, + u64 choose_args_index) { + struct crush_choose_arg_map *arg_map; int r; BUG_ON(result_max > CEPH_PG_MAX_SIZE); + arg_map = lookup_choose_arg_map(&map->crush->choose_args, + choose_args_index); + mutex_lock(&map->crush_workspace_mutex); r = crush_do_rule(map->crush, ruleno, x, result, result_max, - weight, weight_max, map->crush_workspace); + weight, weight_max, map->crush_workspace, + arg_map ? arg_map->args : NULL); mutex_unlock(&map->crush_workspace_mutex); return r; } +static void remove_nonexistent_osds(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, + struct ceph_osds *set) +{ + int i; + + if (ceph_can_shift_osds(pi)) { + int removed = 0; + + /* shift left */ + for (i = 0; i < set->size; i++) { + if (!ceph_osd_exists(osdmap, set->osds[i])) { + removed++; + continue; + } + if (removed) + set->osds[i - removed] = set->osds[i]; + } + set->size -= removed; + } else { + /* set dne devices to NONE */ + for (i = 0; i < set->size; i++) { + if (!ceph_osd_exists(osdmap, set->osds[i])) + set->osds[i] = CRUSH_ITEM_NONE; + } + } +} + /* - * Calculate raw set (CRUSH output) for given PG. The result may - * contain nonexistent OSDs. ->primary is undefined for a raw set. + * Calculate raw set (CRUSH output) for given PG and filter out + * nonexistent OSDs. ->primary is undefined for a raw set. * * Placement seed (CRUSH input) is returned through @ppps. */ @@ -2020,7 +2387,7 @@ static void pg_to_raw_osds(struct ceph_osdmap *osdmap, } len = do_crush(osdmap, ruleno, pps, raw->osds, pi->size, - osdmap->osd_weight, osdmap->max_osd); + osdmap->osd_weight, osdmap->max_osd, pi->id); if (len < 0) { pr_err("error %d from crush rule %d: pool %lld ruleset %d type %d size %d\n", len, ruleno, pi->id, pi->crush_ruleset, pi->type, @@ -2029,6 +2396,70 @@ static void pg_to_raw_osds(struct ceph_osdmap *osdmap, } raw->size = len; + remove_nonexistent_osds(osdmap, pi, raw); +} + +/* apply pg_upmap[_items] mappings */ +static void apply_upmap(struct ceph_osdmap *osdmap, + const struct ceph_pg *pgid, + struct ceph_osds *raw) +{ + struct ceph_pg_mapping *pg; + int i, j; + + pg = lookup_pg_mapping(&osdmap->pg_upmap, pgid); + if (pg) { + /* make sure targets aren't marked out */ + for (i = 0; i < pg->pg_upmap.len; i++) { + int osd = pg->pg_upmap.osds[i]; + + if (osd != CRUSH_ITEM_NONE && + osd < osdmap->max_osd && + osdmap->osd_weight[osd] == 0) { + /* reject/ignore explicit mapping */ + return; + } + } + for (i = 0; i < pg->pg_upmap.len; i++) + raw->osds[i] = pg->pg_upmap.osds[i]; + raw->size = pg->pg_upmap.len; + return; + } + + pg = lookup_pg_mapping(&osdmap->pg_upmap_items, pgid); + if (pg) { + /* + * Note: this approach does not allow a bidirectional swap, + * e.g., [[1,2],[2,1]] applied to [0,1,2] -> [0,2,1]. + */ + for (i = 0; i < pg->pg_upmap_items.len; i++) { + int from = pg->pg_upmap_items.from_to[i][0]; + int to = pg->pg_upmap_items.from_to[i][1]; + int pos = -1; + bool exists = false; + + /* make sure replacement doesn't already appear */ + for (j = 0; j < raw->size; j++) { + int osd = raw->osds[j]; + + if (osd == to) { + exists = true; + break; + } + /* ignore mapping if target is marked out */ + if (osd == from && pos < 0 && + !(to != CRUSH_ITEM_NONE && + to < osdmap->max_osd && + osdmap->osd_weight[to] == 0)) { + pos = j; + } + } + if (!exists && pos >= 0) { + raw->osds[pos] = to; + return; + } + } + } } /* @@ -2151,18 +2582,16 @@ static void apply_primary_affinity(struct ceph_osdmap *osdmap, */ static void get_temp_osds(struct ceph_osdmap *osdmap, struct ceph_pg_pool_info *pi, - const struct ceph_pg *raw_pgid, + const struct ceph_pg *pgid, struct ceph_osds *temp) { - struct ceph_pg pgid; struct ceph_pg_mapping *pg; int i; - raw_pg_to_pg(pi, raw_pgid, &pgid); ceph_osds_init(temp); /* pg_temp? */ - pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid); + pg = lookup_pg_mapping(&osdmap->pg_temp, pgid); if (pg) { for (i = 0; i < pg->pg_temp.len; i++) { if (ceph_osd_is_down(osdmap, pg->pg_temp.osds[i])) { @@ -2185,7 +2614,7 @@ static void get_temp_osds(struct ceph_osdmap *osdmap, } /* primary_temp? */ - pg = __lookup_pg_mapping(&osdmap->primary_temp, pgid); + pg = lookup_pg_mapping(&osdmap->primary_temp, pgid); if (pg) temp->primary = pg->primary_temp.osd; } @@ -2198,43 +2627,75 @@ static void get_temp_osds(struct ceph_osdmap *osdmap, * resend a request. */ void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, const struct ceph_pg *raw_pgid, struct ceph_osds *up, struct ceph_osds *acting) { - struct ceph_pg_pool_info *pi; + struct ceph_pg pgid; u32 pps; - pi = ceph_pg_pool_by_id(osdmap, raw_pgid->pool); - if (!pi) { - ceph_osds_init(up); - ceph_osds_init(acting); - goto out; - } + WARN_ON(pi->id != raw_pgid->pool); + raw_pg_to_pg(pi, raw_pgid, &pgid); pg_to_raw_osds(osdmap, pi, raw_pgid, up, &pps); + apply_upmap(osdmap, &pgid, up); raw_to_up_osds(osdmap, pi, up); apply_primary_affinity(osdmap, pi, pps, up); - get_temp_osds(osdmap, pi, raw_pgid, acting); + get_temp_osds(osdmap, pi, &pgid, acting); if (!acting->size) { memcpy(acting->osds, up->osds, up->size * sizeof(up->osds[0])); acting->size = up->size; if (acting->primary == -1) acting->primary = up->primary; } -out: WARN_ON(!osds_valid(up) || !osds_valid(acting)); } +bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, + const struct ceph_pg *raw_pgid, + struct ceph_spg *spgid) +{ + struct ceph_pg pgid; + struct ceph_osds up, acting; + int i; + + WARN_ON(pi->id != raw_pgid->pool); + raw_pg_to_pg(pi, raw_pgid, &pgid); + + if (ceph_can_shift_osds(pi)) { + spgid->pgid = pgid; /* struct */ + spgid->shard = CEPH_SPG_NOSHARD; + return true; + } + + ceph_pg_to_up_acting_osds(osdmap, pi, &pgid, &up, &acting); + for (i = 0; i < acting.size; i++) { + if (acting.osds[i] == acting.primary) { + spgid->pgid = pgid; /* struct */ + spgid->shard = i; + return true; + } + } + + return false; +} + /* * Return acting primary for given PG, or -1 if none. */ int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap, const struct ceph_pg *raw_pgid) { + struct ceph_pg_pool_info *pi; struct ceph_osds up, acting; - ceph_pg_to_up_acting_osds(osdmap, raw_pgid, &up, &acting); + pi = ceph_pg_pool_by_id(osdmap, raw_pgid->pool); + if (!pi) + return -1; + + ceph_pg_to_up_acting_osds(osdmap, pi, raw_pgid, &up, &acting); return acting.primary; } EXPORT_SYMBOL(ceph_pg_to_acting_primary); diff --git a/net/compat.c b/net/compat.c index aba929e5250f..6ded6c821d7a 100644 --- a/net/compat.c +++ b/net/compat.c @@ -37,21 +37,16 @@ int get_compat_msghdr(struct msghdr *kmsg, struct sockaddr __user **save_addr, struct iovec **iov) { - compat_uptr_t uaddr, uiov, tmp3; - compat_size_t nr_segs; + struct compat_msghdr msg; ssize_t err; - if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) || - __get_user(uaddr, &umsg->msg_name) || - __get_user(kmsg->msg_namelen, &umsg->msg_namelen) || - __get_user(uiov, &umsg->msg_iov) || - __get_user(nr_segs, &umsg->msg_iovlen) || - __get_user(tmp3, &umsg->msg_control) || - __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || - __get_user(kmsg->msg_flags, &umsg->msg_flags)) + if (copy_from_user(&msg, umsg, sizeof(*umsg))) return -EFAULT; - if (!uaddr) + kmsg->msg_flags = msg.msg_flags; + kmsg->msg_namelen = msg.msg_namelen; + + if (!msg.msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) @@ -59,14 +54,16 @@ int get_compat_msghdr(struct msghdr *kmsg, if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); - kmsg->msg_control = compat_ptr(tmp3); + + kmsg->msg_control = compat_ptr(msg.msg_control); + kmsg->msg_controllen = msg.msg_controllen; if (save_addr) - *save_addr = compat_ptr(uaddr); + *save_addr = compat_ptr(msg.msg_name); - if (uaddr && kmsg->msg_namelen) { + if (msg.msg_name && kmsg->msg_namelen) { if (!save_addr) { - err = move_addr_to_kernel(compat_ptr(uaddr), + err = move_addr_to_kernel(compat_ptr(msg.msg_name), kmsg->msg_namelen, kmsg->msg_name); if (err < 0) @@ -77,13 +74,13 @@ int get_compat_msghdr(struct msghdr *kmsg, kmsg->msg_namelen = 0; } - if (nr_segs > UIO_MAXIOV) + if (msg.msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; return compat_import_iovec(save_addr ? READ : WRITE, - compat_ptr(uiov), nr_segs, + compat_ptr(msg.msg_iov), msg.msg_iovlen, UIO_FASTIOV, iov, &kmsg->msg_iter); } @@ -316,15 +313,15 @@ struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval) { struct compat_sock_fprog __user *fprog32 = (struct compat_sock_fprog __user *)optval; struct sock_fprog __user *kfprog = compat_alloc_user_space(sizeof(struct sock_fprog)); - compat_uptr_t ptr; - u16 len; - - if (!access_ok(VERIFY_READ, fprog32, sizeof(*fprog32)) || - !access_ok(VERIFY_WRITE, kfprog, sizeof(struct sock_fprog)) || - __get_user(len, &fprog32->len) || - __get_user(ptr, &fprog32->filter) || - __put_user(len, &kfprog->len) || - __put_user(compat_ptr(ptr), &kfprog->filter)) + struct compat_sock_fprog f32; + struct sock_fprog f; + + if (copy_from_user(&f32, fprog32, sizeof(*fprog32))) + return NULL; + memset(&f, 0, sizeof(f)); + f.len = f32.len; + f.filter = compat_ptr(f32.filter); + if (copy_to_user(kfprog, &f, sizeof(struct sock_fprog))) return NULL; return kfprog; diff --git a/net/core/datagram.c b/net/core/datagram.c index db1866f2ffcf..ee5647bd91b3 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -68,7 +68,7 @@ static inline int connection_based(struct sock *sk) return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM; } -static int receiver_wake_function(wait_queue_t *wait, unsigned int mode, int sync, +static int receiver_wake_function(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key) { unsigned long bits = (unsigned long)key; @@ -161,10 +161,49 @@ done: return skb; } +struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, + struct sk_buff_head *queue, + unsigned int flags, + void (*destructor)(struct sock *sk, + struct sk_buff *skb), + int *peeked, int *off, int *err, + struct sk_buff **last) +{ + struct sk_buff *skb; + int _off = *off; + + *last = queue->prev; + skb_queue_walk(queue, skb) { + if (flags & MSG_PEEK) { + if (_off >= skb->len && (skb->len || _off || + skb->peeked)) { + _off -= skb->len; + continue; + } + if (!skb->len) { + skb = skb_set_peeked(skb); + if (unlikely(IS_ERR(skb))) { + *err = PTR_ERR(skb); + return NULL; + } + } + *peeked = 1; + refcount_inc(&skb->users); + } else { + __skb_unlink(skb, queue); + if (destructor) + destructor(sk, skb); + } + *off = _off; + return skb; + } + return NULL; +} + /** * __skb_try_recv_datagram - Receive a datagram skbuff * @sk: socket - * @flags: MSG_ flags + * @flags: MSG\_ flags * @destructor: invoked under the receive lock on successful dequeue * @peeked: returns non-zero if this packet has been seen before * @off: an offset in bytes to peek skb from. Returns an offset @@ -181,7 +220,7 @@ done: * * This function will lock the socket if a skb is returned, so * the caller needs to unlock the socket in that case (usually by - * calling skb_free_datagram). Returns NULL with *err set to + * calling skb_free_datagram). Returns NULL with @err set to * -EAGAIN if no data was available or to some other value if an * error was detected. * @@ -222,40 +261,14 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, * Look at current nfs client by the way... * However, this function was correct in any case. 8) */ - int _off = *off; - - *last = (struct sk_buff *)queue; spin_lock_irqsave(&queue->lock, cpu_flags); - skb_queue_walk(queue, skb) { - *last = skb; - if (flags & MSG_PEEK) { - if (_off >= skb->len && (skb->len || _off || - skb->peeked)) { - _off -= skb->len; - continue; - } - if (!skb->len) { - skb = skb_set_peeked(skb); - if (IS_ERR(skb)) { - error = PTR_ERR(skb); - spin_unlock_irqrestore(&queue->lock, - cpu_flags); - goto no_packet; - } - } - *peeked = 1; - atomic_inc(&skb->users); - } else { - __skb_unlink(skb, queue); - if (destructor) - destructor(sk, skb); - } - spin_unlock_irqrestore(&queue->lock, cpu_flags); - *off = _off; - return skb; - } - + skb = __skb_try_recv_from_queue(sk, queue, flags, destructor, + peeked, off, &error, last); spin_unlock_irqrestore(&queue->lock, cpu_flags); + if (error) + goto no_packet; + if (skb) + return skb; if (!sk_can_busy_loop(sk)) break; @@ -317,9 +330,7 @@ void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len) { bool slow; - if (likely(atomic_read(&skb->users) == 1)) - smp_rmb(); - else if (likely(!atomic_dec_and_test(&skb->users))) { + if (!skb_unref(skb)) { sk_peek_offset_bwd(sk, len); return; } @@ -335,8 +346,8 @@ void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len) } EXPORT_SYMBOL(__skb_free_datagram_locked); -int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb, - unsigned int flags, +int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, + struct sk_buff *skb, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb)) { @@ -344,15 +355,15 @@ int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb, if (flags & MSG_PEEK) { err = -ENOENT; - spin_lock_bh(&sk->sk_receive_queue.lock); - if (skb == skb_peek(&sk->sk_receive_queue)) { - __skb_unlink(skb, &sk->sk_receive_queue); - atomic_dec(&skb->users); + spin_lock_bh(&sk_queue->lock); + if (skb == skb_peek(sk_queue)) { + __skb_unlink(skb, sk_queue); + refcount_dec(&skb->users); if (destructor) destructor(sk, skb); err = 0; } - spin_unlock_bh(&sk->sk_receive_queue.lock); + spin_unlock_bh(&sk_queue->lock); } atomic_inc(&sk->sk_drops); @@ -364,7 +375,7 @@ EXPORT_SYMBOL(__sk_queue_drop_skb); * skb_kill_datagram - Free a datagram skbuff forcibly * @sk: socket * @skb: datagram skbuff - * @flags: MSG_ flags + * @flags: MSG\_ flags * * This function frees a datagram skbuff that was received by * skb_recv_datagram. The flags argument must match the one @@ -383,7 +394,8 @@ EXPORT_SYMBOL(__sk_queue_drop_skb); int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags) { - int err = __sk_queue_drop_skb(sk, skb, flags, NULL); + int err = __sk_queue_drop_skb(sk, &sk->sk_receive_queue, skb, flags, + NULL); kfree_skb(skb); sk_mem_reclaim_partial(sk); @@ -602,7 +614,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) skb->data_len += copied; skb->len += copied; skb->truesize += truesize; - atomic_add(truesize, &skb->sk->sk_wmem_alloc); + refcount_add(truesize, &skb->sk->sk_wmem_alloc); while (copied) { int size = min_t(int, copied, PAGE_SIZE - start); skb_fill_page_desc(skb, frag++, pages[n], start, size); @@ -797,7 +809,7 @@ EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg); * sequenced packet sockets providing the socket receive queue * is only ever holding data ready to receive. * - * Note: when you _don't_ use this routine for this protocol, + * Note: when you *don't* use this routine for this protocol, * and you use a different write policy from sock_writeable() * then please supply your own write_space callback. */ diff --git a/net/core/dev.c b/net/core/dev.c index 416137c64bf8..8515f8fe0460 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -105,6 +105,7 @@ #include <net/dst.h> #include <net/dst_metadata.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <net/checksum.h> #include <net/xfrm.h> #include <linux/highmem.h> @@ -142,6 +143,7 @@ #include <linux/hrtimer.h> #include <linux/netfilter_ingress.h> #include <linux/crash_dump.h> +#include <linux/sctp.h> #include "net-sysfs.h" @@ -161,6 +163,7 @@ static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev, struct netdev_notifier_info *info); +static struct napi_struct *napi_by_id(unsigned int napi_id); /* * The @dev_base_head list is protected by @dev_base_lock and the rtnl @@ -865,6 +868,31 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex) EXPORT_SYMBOL(dev_get_by_index); /** + * dev_get_by_napi_id - find a device by napi_id + * @napi_id: ID of the NAPI struct + * + * Search for an interface by NAPI ID. Returns %NULL if the device + * is not found or a pointer to the device. The device has not had + * its reference counter increased so the caller must be careful + * about locking. The caller must hold RCU lock. + */ + +struct net_device *dev_get_by_napi_id(unsigned int napi_id) +{ + struct napi_struct *napi; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (napi_id < MIN_NAPI_ID) + return NULL; + + napi = napi_by_id(napi_id); + + return napi ? napi->dev : NULL; +} +EXPORT_SYMBOL(dev_get_by_napi_id); + +/** * netdev_get_name - get a netdevice name, knowing its ifindex. * @net: network namespace * @name: a pointer to the buffer where the name will be stored. @@ -1834,7 +1862,7 @@ static inline int deliver_skb(struct sk_buff *skb, { if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) return -ENOMEM; - atomic_inc(&skb->users); + refcount_inc(&skb->users); return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } @@ -2456,10 +2484,10 @@ void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason) if (unlikely(!skb)) return; - if (likely(atomic_read(&skb->users) == 1)) { + if (likely(refcount_read(&skb->users) == 1)) { smp_rmb(); - atomic_set(&skb->users, 0); - } else if (likely(!atomic_dec_and_test(&skb->users))) { + refcount_set(&skb->users, 0); + } else if (likely(!refcount_dec_and_test(&skb->users))) { return; } get_kfree_skb_cb(skb)->reason = reason; @@ -2612,6 +2640,47 @@ out: } EXPORT_SYMBOL(skb_checksum_help); +int skb_crc32c_csum_help(struct sk_buff *skb) +{ + __le32 crc32c_csum; + int ret = 0, offset, start; + + if (skb->ip_summed != CHECKSUM_PARTIAL) + goto out; + + if (unlikely(skb_is_gso(skb))) + goto out; + + /* Before computing a checksum, we should make sure no frag could + * be modified by an external entity : checksum could be wrong. + */ + if (unlikely(skb_has_shared_frag(skb))) { + ret = __skb_linearize(skb); + if (ret) + goto out; + } + start = skb_checksum_start_offset(skb); + offset = start + offsetof(struct sctphdr, checksum); + if (WARN_ON_ONCE(offset >= skb_headlen(skb))) { + ret = -EINVAL; + goto out; + } + if (skb_cloned(skb) && + !skb_clone_writable(skb, offset + sizeof(__le32))) { + ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + if (ret) + goto out; + } + crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start, + skb->len - start, ~(__u32)0, + crc32c_csum_stub)); + *(__le32 *)(skb->data + offset) = crc32c_csum; + skb->ip_summed = CHECKSUM_NONE; + skb->csum_not_inet = 0; +out: + return ret; +} + __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; @@ -2954,6 +3023,17 @@ static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, return skb; } +int skb_csum_hwoffload_help(struct sk_buff *skb, + const netdev_features_t features) +{ + if (unlikely(skb->csum_not_inet)) + return !!(features & NETIF_F_SCTP_CRC) ? 0 : + skb_crc32c_csum_help(skb); + + return !!(features & NETIF_F_CSUM_MASK) ? 0 : skb_checksum_help(skb); +} +EXPORT_SYMBOL(skb_csum_hwoffload_help); + static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev) { netdev_features_t features; @@ -2992,8 +3072,7 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device else skb_set_transport_header(skb, skb_checksum_start_offset(skb)); - if (!(features & NETIF_F_CSUM_MASK) && - skb_checksum_help(skb)) + if (skb_csum_hwoffload_help(skb, features)) goto out_kfree_skb; } } @@ -3179,7 +3258,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ qdisc_bstats_cpu_update(cl->q, skb); - switch (tc_classify(skb, cl, &cl_res, false)) { + switch (tcf_classify(skb, cl, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); @@ -3191,6 +3270,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) return NULL; case TC_ACT_STOLEN: case TC_ACT_QUEUED: + case TC_ACT_TRAP: *ret = NET_XMIT_SUCCESS; consume_skb(skb); return NULL; @@ -3875,7 +3955,7 @@ static __latent_entropy void net_tx_action(struct softirq_action *h) clist = clist->next; - WARN_ON(atomic_read(&skb->users)); + WARN_ON(refcount_read(&skb->users)); if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED)) trace_consume_skb(skb); else @@ -3949,7 +4029,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, skb->tc_at_ingress = 1; qdisc_bstats_cpu_update(cl->q, skb); - switch (tc_classify(skb, cl, &cl_res, false)) { + switch (tcf_classify(skb, cl, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); @@ -3960,6 +4040,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, return NULL; case TC_ACT_STOLEN: case TC_ACT_QUEUED: + case TC_ACT_TRAP: consume_skb(skb); return NULL; case TC_ACT_REDIRECT: @@ -4261,13 +4342,12 @@ static struct static_key generic_xdp_needed __read_mostly; static int generic_xdp_install(struct net_device *dev, struct netdev_xdp *xdp) { + struct bpf_prog *old = rtnl_dereference(dev->xdp_prog); struct bpf_prog *new = xdp->prog; int ret = 0; switch (xdp->command) { - case XDP_SETUP_PROG: { - struct bpf_prog *old = rtnl_dereference(dev->xdp_prog); - + case XDP_SETUP_PROG: rcu_assign_pointer(dev->xdp_prog, new); if (old) bpf_prog_put(old); @@ -4279,10 +4359,10 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_xdp *xdp) dev_disable_lro(dev); } break; - } case XDP_QUERY_PROG: - xdp->prog_attached = !!rcu_access_pointer(dev->xdp_prog); + xdp->prog_attached = !!old; + xdp->prog_id = old ? old->aux->id : 0; break; default: @@ -4637,9 +4717,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (netif_elide_gro(skb->dev)) goto normal; - if (skb->csum_bad) - goto normal; - gro_list_prepare(napi, skb); rcu_read_lock(); @@ -6688,7 +6765,7 @@ int dev_change_flags(struct net_device *dev, unsigned int flags) } EXPORT_SYMBOL(dev_change_flags); -static int __dev_set_mtu(struct net_device *dev, int new_mtu) +int __dev_set_mtu(struct net_device *dev, int new_mtu) { const struct net_device_ops *ops = dev->netdev_ops; @@ -6698,6 +6775,7 @@ static int __dev_set_mtu(struct net_device *dev, int new_mtu) dev->mtu = new_mtu; return 0; } +EXPORT_SYMBOL(__dev_set_mtu); /** * dev_set_mtu - Change maximum transfer unit @@ -6867,7 +6945,7 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down) } EXPORT_SYMBOL(dev_change_proto_down); -bool __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op) +u8 __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op, u32 *prog_id) { struct netdev_xdp xdp; @@ -6876,18 +6954,25 @@ bool __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op) /* Query must always succeed. */ WARN_ON(xdp_op(dev, &xdp) < 0); + if (prog_id) + *prog_id = xdp.prog_id; + return xdp.prog_attached; } static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op, - struct netlink_ext_ack *extack, + struct netlink_ext_ack *extack, u32 flags, struct bpf_prog *prog) { struct netdev_xdp xdp; memset(&xdp, 0, sizeof(xdp)); - xdp.command = XDP_SETUP_PROG; + if (flags & XDP_FLAGS_HW_MODE) + xdp.command = XDP_SETUP_PROG_HW; + else + xdp.command = XDP_SETUP_PROG; xdp.extack = extack; + xdp.flags = flags; xdp.prog = prog; return xdp_op(dev, &xdp); @@ -6913,7 +6998,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, ASSERT_RTNL(); xdp_op = xdp_chk = ops->ndo_xdp; - if (!xdp_op && (flags & XDP_FLAGS_DRV_MODE)) + if (!xdp_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) return -EOPNOTSUPP; if (!xdp_op || (flags & XDP_FLAGS_SKB_MODE)) xdp_op = generic_xdp_install; @@ -6921,10 +7006,10 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, xdp_chk = generic_xdp_install; if (fd >= 0) { - if (xdp_chk && __dev_xdp_attached(dev, xdp_chk)) + if (xdp_chk && __dev_xdp_attached(dev, xdp_chk, NULL)) return -EEXIST; if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && - __dev_xdp_attached(dev, xdp_op)) + __dev_xdp_attached(dev, xdp_op, NULL)) return -EBUSY; prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); @@ -6932,7 +7017,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, return PTR_ERR(prog); } - err = dev_xdp_install(dev, xdp_op, extack, prog); + err = dev_xdp_install(dev, xdp_op, extack, flags, prog); if (err < 0 && prog) bpf_prog_put(prog); @@ -7023,7 +7108,7 @@ static void rollback_registered_many(struct list_head *head) if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, + skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, GFP_KERNEL); /* @@ -7299,7 +7384,7 @@ static int netif_alloc_rx_queues(struct net_device *dev) BUG_ON(count < 1); - rx = kvzalloc(sz, GFP_KERNEL | __GFP_REPEAT); + rx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!rx) return -ENOMEM; @@ -7339,7 +7424,7 @@ static int netif_alloc_netdev_queues(struct net_device *dev) if (count < 1 || count > 0xffff) return -EINVAL; - tx = kvzalloc(sz, GFP_KERNEL | __GFP_REPEAT); + tx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!tx) return -ENOMEM; @@ -7751,7 +7836,7 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, { #if BITS_PER_LONG == 64 BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats)); - memcpy(stats64, netdev_stats, sizeof(*stats64)); + memcpy(stats64, netdev_stats, sizeof(*netdev_stats)); /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + sizeof(*netdev_stats), 0, sizeof(*stats64) - sizeof(*netdev_stats)); @@ -7880,7 +7965,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, /* ensure 32-byte alignment of whole construct */ alloc_size += NETDEV_ALIGN - 1; - p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_REPEAT); + p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!p) return NULL; @@ -8608,7 +8693,6 @@ static int __init net_dev_init(void) rc = cpuhp_setup_state_nocalls(CPUHP_NET_DEV_DEAD, "net/dev:dead", NULL, dev_cpu_dead); WARN_ON(rc < 0); - dst_subsys_init(); rc = 0; out: return rc; diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 27fad31784a8..06b147d7d9e2 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -28,6 +28,7 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg) if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) return -EFAULT; + ifr.ifr_name[IFNAMSIZ-1] = 0; error = netdev_get_name(net, ifr.ifr_name, ifr.ifr_ifindex); if (error) @@ -225,6 +226,7 @@ static int net_hwtstamp_validate(struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_NTP_ALL: rx_filter_valid = 1; break; } @@ -423,6 +425,8 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (copy_from_user(&iwr, arg, sizeof(iwr))) return -EFAULT; + iwr.ifr_name[sizeof(iwr.ifr_name) - 1] = 0; + return wext_handle_ioctl(net, &iwr, cmd, arg); } diff --git a/net/core/dst.c b/net/core/dst.c index 13ba4a090c41..00aa972ad1a1 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -42,108 +42,6 @@ * to dirty as few cache lines as possible in __dst_free(). * As this is not a very strong hint, we dont force an alignment on SMP. */ -static struct { - spinlock_t lock; - struct dst_entry *list; - unsigned long timer_inc; - unsigned long timer_expires; -} dst_garbage = { - .lock = __SPIN_LOCK_UNLOCKED(dst_garbage.lock), - .timer_inc = DST_GC_MAX, -}; -static void dst_gc_task(struct work_struct *work); -static void ___dst_free(struct dst_entry *dst); - -static DECLARE_DELAYED_WORK(dst_gc_work, dst_gc_task); - -static DEFINE_MUTEX(dst_gc_mutex); -/* - * long lived entries are maintained in this list, guarded by dst_gc_mutex - */ -static struct dst_entry *dst_busy_list; - -static void dst_gc_task(struct work_struct *work) -{ - int delayed = 0; - int work_performed = 0; - unsigned long expires = ~0L; - struct dst_entry *dst, *next, head; - struct dst_entry *last = &head; - - mutex_lock(&dst_gc_mutex); - next = dst_busy_list; - -loop: - while ((dst = next) != NULL) { - next = dst->next; - prefetch(&next->next); - cond_resched(); - if (likely(atomic_read(&dst->__refcnt))) { - last->next = dst; - last = dst; - delayed++; - continue; - } - work_performed++; - - dst = dst_destroy(dst); - if (dst) { - /* NOHASH and still referenced. Unless it is already - * on gc list, invalidate it and add to gc list. - * - * Note: this is temporary. Actually, NOHASH dst's - * must be obsoleted when parent is obsoleted. - * But we do not have state "obsoleted, but - * referenced by parent", so it is right. - */ - if (dst->obsolete > 0) - continue; - - ___dst_free(dst); - dst->next = next; - next = dst; - } - } - - spin_lock_bh(&dst_garbage.lock); - next = dst_garbage.list; - if (next) { - dst_garbage.list = NULL; - spin_unlock_bh(&dst_garbage.lock); - goto loop; - } - last->next = NULL; - dst_busy_list = head.next; - if (!dst_busy_list) - dst_garbage.timer_inc = DST_GC_MAX; - else { - /* - * if we freed less than 1/10 of delayed entries, - * we can sleep longer. - */ - if (work_performed <= delayed/10) { - dst_garbage.timer_expires += dst_garbage.timer_inc; - if (dst_garbage.timer_expires > DST_GC_MAX) - dst_garbage.timer_expires = DST_GC_MAX; - dst_garbage.timer_inc += DST_GC_INC; - } else { - dst_garbage.timer_inc = DST_GC_INC; - dst_garbage.timer_expires = DST_GC_MIN; - } - expires = dst_garbage.timer_expires; - /* - * if the next desired timer is more than 4 seconds in the - * future then round the timer to whole seconds - */ - if (expires > 4*HZ) - expires = round_jiffies_relative(expires); - schedule_delayed_work(&dst_gc_work, expires); - } - - spin_unlock_bh(&dst_garbage.lock); - mutex_unlock(&dst_gc_mutex); -} - int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); @@ -216,41 +114,12 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, } EXPORT_SYMBOL(dst_alloc); -static void ___dst_free(struct dst_entry *dst) -{ - /* The first case (dev==NULL) is required, when - protocol module is unloaded. - */ - if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) { - dst->input = dst_discard; - dst->output = dst_discard_out; - } - dst->obsolete = DST_OBSOLETE_DEAD; -} - -void __dst_free(struct dst_entry *dst) -{ - spin_lock_bh(&dst_garbage.lock); - ___dst_free(dst); - dst->next = dst_garbage.list; - dst_garbage.list = dst; - if (dst_garbage.timer_inc > DST_GC_INC) { - dst_garbage.timer_inc = DST_GC_INC; - dst_garbage.timer_expires = DST_GC_MIN; - mod_delayed_work(system_wq, &dst_gc_work, - dst_garbage.timer_expires); - } - spin_unlock_bh(&dst_garbage.lock); -} -EXPORT_SYMBOL(__dst_free); - struct dst_entry *dst_destroy(struct dst_entry * dst) { struct dst_entry *child; smp_rmb(); -again: child = dst->child; if (!(dst->flags & DST_NOCOUNT)) @@ -269,20 +138,8 @@ again: kmem_cache_free(dst->ops->kmem_cachep, dst); dst = child; - if (dst) { - int nohash = dst->flags & DST_NOHASH; - - if (atomic_dec_and_test(&dst->__refcnt)) { - /* We were real parent of this dst, so kill child. */ - if (nohash) - goto again; - } else { - /* Child is still referenced, return it for freeing. */ - if (nohash) - return dst; - /* Child is still in his hash table */ - } - } + if (dst) + dst_release_immediate(dst); return NULL; } EXPORT_SYMBOL(dst_destroy); @@ -292,26 +149,62 @@ static void dst_destroy_rcu(struct rcu_head *head) struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); dst = dst_destroy(dst); - if (dst) - __dst_free(dst); } +/* Operations to mark dst as DEAD and clean up the net device referenced + * by dst: + * 1. put the dst under loopback interface and discard all tx/rx packets + * on this route. + * 2. release the net_device + * This function should be called when removing routes from the fib tree + * in preparation for a NETDEV_DOWN/NETDEV_UNREGISTER event and also to + * make the next dst_ops->check() fail. + */ +void dst_dev_put(struct dst_entry *dst) +{ + struct net_device *dev = dst->dev; + + dst->obsolete = DST_OBSOLETE_DEAD; + if (dst->ops->ifdown) + dst->ops->ifdown(dst, dev, true); + dst->input = dst_discard; + dst->output = dst_discard_out; + dst->dev = dev_net(dst->dev)->loopback_dev; + dev_hold(dst->dev); + dev_put(dev); +} +EXPORT_SYMBOL(dst_dev_put); + void dst_release(struct dst_entry *dst) { if (dst) { int newrefcnt; - unsigned short nocache = dst->flags & DST_NOCACHE; newrefcnt = atomic_dec_return(&dst->__refcnt); if (unlikely(newrefcnt < 0)) net_warn_ratelimited("%s: dst:%p refcnt:%d\n", __func__, dst, newrefcnt); - if (!newrefcnt && unlikely(nocache)) + if (!newrefcnt) call_rcu(&dst->rcu_head, dst_destroy_rcu); } } EXPORT_SYMBOL(dst_release); +void dst_release_immediate(struct dst_entry *dst) +{ + if (dst) { + int newrefcnt; + + newrefcnt = atomic_dec_return(&dst->__refcnt); + if (unlikely(newrefcnt < 0)) + net_warn_ratelimited("%s: dst:%p refcnt:%d\n", + __func__, dst, newrefcnt); + if (!newrefcnt) + dst_destroy(dst); + } +} +EXPORT_SYMBOL(dst_release_immediate); + u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) { struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC); @@ -371,21 +264,25 @@ static int dst_md_discard(struct sk_buff *skb) return 0; } -static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen) +static void __metadata_dst_init(struct metadata_dst *md_dst, + enum metadata_type type, u8 optslen) + { struct dst_entry *dst; dst = &md_dst->dst; dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE, - DST_METADATA | DST_NOCACHE | DST_NOCOUNT); + DST_METADATA | DST_NOCOUNT); dst->input = dst_md_discard; dst->output = dst_md_discard_out; memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst)); + md_dst->type = type; } -struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags) +struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, + gfp_t flags) { struct metadata_dst *md_dst; @@ -393,7 +290,7 @@ struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags) if (!md_dst) return NULL; - __metadata_dst_init(md_dst, optslen); + __metadata_dst_init(md_dst, type, optslen); return md_dst; } @@ -407,7 +304,8 @@ void metadata_dst_free(struct metadata_dst *md_dst) kfree(md_dst); } -struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags) +struct metadata_dst __percpu * +metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags) { int cpu; struct metadata_dst __percpu *md_dst; @@ -418,91 +316,8 @@ struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags) return NULL; for_each_possible_cpu(cpu) - __metadata_dst_init(per_cpu_ptr(md_dst, cpu), optslen); + __metadata_dst_init(per_cpu_ptr(md_dst, cpu), type, optslen); return md_dst; } EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu); - -/* Dirty hack. We did it in 2.2 (in __dst_free), - * we have _very_ good reasons not to repeat - * this mistake in 2.3, but we have no choice - * now. _It_ _is_ _explicit_ _deliberate_ - * _race_ _condition_. - * - * Commented and originally written by Alexey. - */ -static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, - int unregister) -{ - if (dst->ops->ifdown) - dst->ops->ifdown(dst, dev, unregister); - - if (dev != dst->dev) - return; - - if (!unregister) { - dst->input = dst_discard; - dst->output = dst_discard_out; - } else { - dst->dev = dev_net(dst->dev)->loopback_dev; - dev_hold(dst->dev); - dev_put(dev); - } -} - -static int dst_dev_event(struct notifier_block *this, unsigned long event, - void *ptr) -{ - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct dst_entry *dst, *last = NULL; - - switch (event) { - case NETDEV_UNREGISTER_FINAL: - case NETDEV_DOWN: - mutex_lock(&dst_gc_mutex); - for (dst = dst_busy_list; dst; dst = dst->next) { - last = dst; - dst_ifdown(dst, dev, event != NETDEV_DOWN); - } - - spin_lock_bh(&dst_garbage.lock); - dst = dst_garbage.list; - dst_garbage.list = NULL; - /* The code in dst_ifdown places a hold on the loopback device. - * If the gc entry processing is set to expire after a lengthy - * interval, this hold can cause netdev_wait_allrefs() to hang - * out and wait for a long time -- until the the loopback - * interface is released. If we're really unlucky, it'll emit - * pr_emerg messages to console too. Reset the interval here, - * so dst cleanups occur in a more timely fashion. - */ - if (dst_garbage.timer_inc > DST_GC_INC) { - dst_garbage.timer_inc = DST_GC_INC; - dst_garbage.timer_expires = DST_GC_MIN; - mod_delayed_work(system_wq, &dst_gc_work, - dst_garbage.timer_expires); - } - spin_unlock_bh(&dst_garbage.lock); - - if (last) - last->next = dst; - else - dst_busy_list = dst; - for (; dst; dst = dst->next) - dst_ifdown(dst, dev, event != NETDEV_DOWN); - mutex_unlock(&dst_gc_mutex); - break; - } - return NOTIFY_DONE; -} - -static struct notifier_block dst_dev_notifier = { - .notifier_call = dst_dev_event, - .priority = -10, /* must be called after other network notifiers */ -}; - -void __init dst_subsys_init(void) -{ - register_netdevice_notifier(&dst_dev_notifier); -} diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 03111a2d6653..674b6c9cec18 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -2322,16 +2322,12 @@ static int ethtool_set_tunable(struct net_device *dev, void __user *useraddr) ret = ethtool_tunable_valid(&tuna); if (ret) return ret; - data = kmalloc(tuna.len, GFP_USER); - if (!data) - return -ENOMEM; useraddr += sizeof(tuna); - ret = -EFAULT; - if (copy_from_user(data, useraddr, tuna.len)) - goto out; + data = memdup_user(useraddr, tuna.len); + if (IS_ERR(data)) + return PTR_ERR(data); ret = ops->set_tunable(dev, &tuna, data); -out: kfree(data); return ret; } @@ -2507,18 +2503,14 @@ static int set_phy_tunable(struct net_device *dev, void __user *useraddr) ret = ethtool_phy_tunable_valid(&tuna); if (ret) return ret; - data = kmalloc(tuna.len, GFP_USER); - if (!data) - return -ENOMEM; useraddr += sizeof(tuna); - ret = -EFAULT; - if (copy_from_user(data, useraddr, tuna.len)) - goto out; + data = memdup_user(useraddr, tuna.len); + if (IS_ERR(data)) + return PTR_ERR(data); mutex_lock(&phydev->lock); ret = phydev->drv->set_tunable(phydev, &tuna, data); mutex_unlock(&phydev->lock); -out: kfree(data); return ret; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 3bba291c6c32..fdcb1bcd2afa 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -46,7 +46,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, if (r == NULL) return -ENOMEM; - atomic_set(&r->refcnt, 1); + refcount_set(&r->refcnt, 1); r->action = FR_ACT_TO_TBL; r->pref = pref; r->table = table; @@ -283,7 +283,7 @@ jumped: if (err != -EAGAIN) { if ((arg->flags & FIB_LOOKUP_NOREF) || - likely(atomic_inc_not_zero(&rule->refcnt))) { + likely(refcount_inc_not_zero(&rule->refcnt))) { arg->rule = rule; goto out; } @@ -400,6 +400,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, err = -ENOMEM; goto errout; } + refcount_set(&rule->refcnt, 1); rule->fr_net = net; rule->pref = tb[FRA_PRIORITY] ? nla_get_u32(tb[FRA_PRIORITY]) @@ -517,8 +518,6 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, last = r; } - fib_rule_get(rule); - if (last) list_add_rcu(&rule->list, &last->list); else diff --git a/net/core/filter.c b/net/core/filter.c index a6bb95fa87b2..f44fc22fd45a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -54,6 +54,7 @@ #include <net/dst.h> #include <net/sock_reuseport.h> #include <net/busy_poll.h> +#include <net/tcp.h> /** * sk_filter_trim_cap - run a packet through a socket filter @@ -352,7 +353,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, * bpf_convert_filter - convert filter program * @prog: the user passed filter program * @len: the length of the user passed filter program - * @new_prog: buffer where converted program will be stored + * @new_prog: allocated 'struct bpf_prog' or NULL * @new_len: pointer to store length of converted program * * Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn' @@ -364,14 +365,13 @@ static bool convert_bpf_extensions(struct sock_filter *fp, * * 2) 2nd pass to remap in two passes: 1st pass finds new * jump offsets, 2nd pass remapping: - * new_prog = kmalloc(sizeof(struct bpf_insn) * new_len); * bpf_convert_filter(old_prog, old_len, new_prog, &new_len); */ static int bpf_convert_filter(struct sock_filter *prog, int len, - struct bpf_insn *new_prog, int *new_len) + struct bpf_prog *new_prog, int *new_len) { - int new_flen = 0, pass = 0, target, i; - struct bpf_insn *new_insn; + int new_flen = 0, pass = 0, target, i, stack_off; + struct bpf_insn *new_insn, *first_insn = NULL; struct sock_filter *fp; int *addrs = NULL; u8 bpf_src; @@ -383,6 +383,7 @@ static int bpf_convert_filter(struct sock_filter *prog, int len, return -EINVAL; if (new_prog) { + first_insn = new_prog->insnsi; addrs = kcalloc(len, sizeof(*addrs), GFP_KERNEL | __GFP_NOWARN); if (!addrs) @@ -390,11 +391,11 @@ static int bpf_convert_filter(struct sock_filter *prog, int len, } do_pass: - new_insn = new_prog; + new_insn = first_insn; fp = prog; /* Classic BPF related prologue emission. */ - if (new_insn) { + if (new_prog) { /* Classic BPF expects A and X to be reset first. These need * to be guaranteed to be the first two instructions. */ @@ -415,7 +416,7 @@ do_pass: struct bpf_insn *insn = tmp_insns; if (addrs) - addrs[i] = new_insn - new_prog; + addrs[i] = new_insn - first_insn; switch (fp->code) { /* All arithmetic insns and skb loads map as-is. */ @@ -561,17 +562,25 @@ do_pass: /* Store to stack. */ case BPF_ST: case BPF_STX: + stack_off = fp->k * 4 + 4; *insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) == BPF_ST ? BPF_REG_A : BPF_REG_X, - -(BPF_MEMWORDS - fp->k) * 4); + -stack_off); + /* check_load_and_stores() verifies that classic BPF can + * load from stack only after write, so tracking + * stack_depth for ST|STX insns is enough + */ + if (new_prog && new_prog->aux->stack_depth < stack_off) + new_prog->aux->stack_depth = stack_off; break; /* Load from stack. */ case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: + stack_off = fp->k * 4 + 4; *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, BPF_REG_FP, - -(BPF_MEMWORDS - fp->k) * 4); + -stack_off); break; /* A = K or X = K */ @@ -619,13 +628,13 @@ do_pass: if (!new_prog) { /* Only calculating new length. */ - *new_len = new_insn - new_prog; + *new_len = new_insn - first_insn; return 0; } pass++; - if (new_flen != new_insn - new_prog) { - new_flen = new_insn - new_prog; + if (new_flen != new_insn - first_insn) { + new_flen = new_insn - first_insn; if (pass > 2) goto err; goto do_pass; @@ -1017,7 +1026,7 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) fp->len = new_len; /* 2nd pass: remap sock_filter insns into bpf_insn insns. */ - err = bpf_convert_filter(old_prog, old_len, fp->insnsi, &new_len); + err = bpf_convert_filter(old_prog, old_len, fp, &new_len); if (err) /* 2nd bpf_convert_filter() can fail only if it fails * to allocate memory, remapping must succeed. Note, @@ -1866,6 +1875,24 @@ static const struct bpf_func_proto bpf_set_hash_invalid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_2(bpf_set_hash, struct sk_buff *, skb, u32, hash) +{ + /* Set user specified hash as L4(+), so that it gets returned + * on skb_get_hash() call unless BPF prog later on triggers a + * skb_clear_hash(). + */ + __skb_set_sw_hash(skb, hash, true); + return 0; +} + +static const struct bpf_func_proto bpf_set_hash_proto = { + .func = bpf_set_hash, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, u16, vlan_tci) { @@ -1985,7 +2012,7 @@ static int bpf_skb_net_hdr_pop(struct sk_buff *skb, u32 off, u32 len) static int bpf_skb_proto_4_to_6(struct sk_buff *skb) { const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); - u32 off = skb->network_header - skb->mac_header; + u32 off = skb_mac_header_len(skb); int ret; ret = skb_cow(skb, len_diff); @@ -2021,7 +2048,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) static int bpf_skb_proto_6_to_4(struct sk_buff *skb) { const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); - u32 off = skb->network_header - skb->mac_header; + u32 off = skb_mac_header_len(skb); int ret; ret = skb_unclone(skb, GFP_ATOMIC); @@ -2127,6 +2154,124 @@ static const struct bpf_func_proto bpf_skb_change_type_proto = { .arg2_type = ARG_ANYTHING, }; +static u32 bpf_skb_net_base_len(const struct sk_buff *skb) +{ + switch (skb->protocol) { + case htons(ETH_P_IP): + return sizeof(struct iphdr); + case htons(ETH_P_IPV6): + return sizeof(struct ipv6hdr); + default: + return ~0U; + } +} + +static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) +{ + u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); + int ret; + + ret = skb_cow(skb, len_diff); + if (unlikely(ret < 0)) + return ret; + + ret = bpf_skb_net_hdr_push(skb, off, len_diff); + if (unlikely(ret < 0)) + return ret; + + if (skb_is_gso(skb)) { + /* Due to header grow, MSS needs to be downgraded. */ + skb_shinfo(skb)->gso_size -= len_diff; + /* Header must be checked, and gso_segs recomputed. */ + skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; + skb_shinfo(skb)->gso_segs = 0; + } + + return 0; +} + +static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) +{ + u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); + int ret; + + ret = skb_unclone(skb, GFP_ATOMIC); + if (unlikely(ret < 0)) + return ret; + + ret = bpf_skb_net_hdr_pop(skb, off, len_diff); + if (unlikely(ret < 0)) + return ret; + + if (skb_is_gso(skb)) { + /* Due to header shrink, MSS can be upgraded. */ + skb_shinfo(skb)->gso_size += len_diff; + /* Header must be checked, and gso_segs recomputed. */ + skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; + skb_shinfo(skb)->gso_segs = 0; + } + + return 0; +} + +static u32 __bpf_skb_max_len(const struct sk_buff *skb) +{ + return skb->dev->mtu + skb->dev->hard_header_len; +} + +static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff) +{ + bool trans_same = skb->transport_header == skb->network_header; + u32 len_cur, len_diff_abs = abs(len_diff); + u32 len_min = bpf_skb_net_base_len(skb); + u32 len_max = __bpf_skb_max_len(skb); + __be16 proto = skb->protocol; + bool shrink = len_diff < 0; + int ret; + + if (unlikely(len_diff_abs > 0xfffU)) + return -EFAULT; + if (unlikely(proto != htons(ETH_P_IP) && + proto != htons(ETH_P_IPV6))) + return -ENOTSUPP; + + len_cur = skb->len - skb_network_offset(skb); + if (skb_transport_header_was_set(skb) && !trans_same) + len_cur = skb_network_header_len(skb); + if ((shrink && (len_diff_abs >= len_cur || + len_cur - len_diff_abs < len_min)) || + (!shrink && (skb->len + len_diff_abs > len_max && + !skb_is_gso(skb)))) + return -ENOTSUPP; + + ret = shrink ? bpf_skb_net_shrink(skb, len_diff_abs) : + bpf_skb_net_grow(skb, len_diff_abs); + + bpf_compute_data_end(skb); + return ret; +} + +BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, + u32, mode, u64, flags) +{ + if (unlikely(flags)) + return -EINVAL; + if (likely(mode == BPF_ADJ_ROOM_NET)) + return bpf_skb_adjust_net(skb, len_diff); + + return -ENOTSUPP; +} + +static const struct bpf_func_proto bpf_skb_adjust_room_proto = { + .func = bpf_skb_adjust_room, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, +}; + static u32 __bpf_skb_min_len(const struct sk_buff *skb) { u32 min_len = skb_network_offset(skb); @@ -2139,11 +2284,6 @@ static u32 __bpf_skb_min_len(const struct sk_buff *skb) return min_len; } -static u32 __bpf_skb_max_len(const struct sk_buff *skb) -{ - return skb->dev->mtu + skb->dev->hard_header_len; -} - static int bpf_skb_grow_rcsum(struct sk_buff *skb, unsigned int new_len) { unsigned int old_len = skb->len; @@ -2280,6 +2420,7 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_skb_change_proto || func == bpf_skb_change_head || func == bpf_skb_change_tail || + func == bpf_skb_adjust_room || func == bpf_skb_pull_data || func == bpf_clone_redirect || func == bpf_l3_csum_replace || @@ -2539,6 +2680,7 @@ bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) * that is holding verifier mutex. */ md_dst = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, + METADATA_IP_TUNNEL, GFP_KERNEL); if (!md_dst) return NULL; @@ -2645,6 +2787,110 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, + int, level, int, optname, char *, optval, int, optlen) +{ + struct sock *sk = bpf_sock->sk; + int ret = 0; + int val; + + if (!sk_fullsock(sk)) + return -EINVAL; + + if (level == SOL_SOCKET) { + if (optlen != sizeof(int)) + return -EINVAL; + val = *((int *)optval); + + /* Only some socketops are supported */ + switch (optname) { + case SO_RCVBUF: + sk->sk_userlocks |= SOCK_RCVBUF_LOCK; + sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); + break; + case SO_SNDBUF: + sk->sk_userlocks |= SOCK_SNDBUF_LOCK; + sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); + break; + case SO_MAX_PACING_RATE: + sk->sk_max_pacing_rate = val; + sk->sk_pacing_rate = min(sk->sk_pacing_rate, + sk->sk_max_pacing_rate); + break; + case SO_PRIORITY: + sk->sk_priority = val; + break; + case SO_RCVLOWAT: + if (val < 0) + val = INT_MAX; + sk->sk_rcvlowat = val ? : 1; + break; + case SO_MARK: + sk->sk_mark = val; + break; + default: + ret = -EINVAL; + } +#ifdef CONFIG_INET + } else if (level == SOL_TCP && + sk->sk_prot->setsockopt == tcp_setsockopt) { + if (optname == TCP_CONGESTION) { + char name[TCP_CA_NAME_MAX]; + + strncpy(name, optval, min_t(long, optlen, + TCP_CA_NAME_MAX-1)); + name[TCP_CA_NAME_MAX-1] = 0; + ret = tcp_set_congestion_control(sk, name, false); + if (!ret && bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN) + /* replacing an existing ca */ + tcp_reinit_congestion_control(sk, + inet_csk(sk)->icsk_ca_ops); + } else { + struct tcp_sock *tp = tcp_sk(sk); + + if (optlen != sizeof(int)) + return -EINVAL; + + val = *((int *)optval); + /* Only some options are supported */ + switch (optname) { + case TCP_BPF_IW: + if (val <= 0 || tp->data_segs_out > 0) + ret = -EINVAL; + else + tp->snd_cwnd = val; + break; + case TCP_BPF_SNDCWND_CLAMP: + if (val <= 0) { + ret = -EINVAL; + } else { + tp->snd_cwnd_clamp = val; + tp->snd_ssthresh = val; + } + break; + default: + ret = -EINVAL; + } + } + ret = -EINVAL; +#endif + } else { + ret = -EINVAL; + } + return ret; +} + +static const struct bpf_func_proto bpf_setsockopt_proto = { + .func = bpf_setsockopt, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE, +}; + static const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id) { @@ -2718,6 +2964,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_skb_change_proto_proto; case BPF_FUNC_skb_change_type: return &bpf_skb_change_type_proto; + case BPF_FUNC_skb_adjust_room: + return &bpf_skb_adjust_room_proto; case BPF_FUNC_skb_change_tail: return &bpf_skb_change_tail_proto; case BPF_FUNC_skb_get_tunnel_key: @@ -2736,6 +2984,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_get_hash_recalc_proto; case BPF_FUNC_set_hash_invalid: return &bpf_set_hash_invalid_proto; + case BPF_FUNC_set_hash: + return &bpf_set_hash_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; case BPF_FUNC_get_smp_processor_id: @@ -2767,12 +3017,6 @@ xdp_func_proto(enum bpf_func_id func_id) } static const struct bpf_func_proto * -cg_skb_func_proto(enum bpf_func_id func_id) -{ - return sk_filter_func_proto(func_id); -} - -static const struct bpf_func_proto * lwt_inout_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -2800,6 +3044,17 @@ lwt_inout_func_proto(enum bpf_func_id func_id) } static const struct bpf_func_proto * + sock_ops_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_setsockopt: + return &bpf_setsockopt_proto; + default: + return bpf_base_func_proto(func_id); + } +} + +static const struct bpf_func_proto * lwt_xmit_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -2834,8 +3089,11 @@ lwt_xmit_func_proto(enum bpf_func_id func_id) } } -static bool __is_valid_access(int off, int size) +static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info) { + const int size_default = sizeof(__u32); + if (off < 0 || off >= sizeof(struct __sk_buff)) return false; @@ -2844,15 +3102,25 @@ static bool __is_valid_access(int off, int size) return false; switch (off) { - case offsetof(struct __sk_buff, cb[0]) ... - offsetof(struct __sk_buff, cb[4]) + sizeof(__u32) - 1: - if (off + size > - offsetof(struct __sk_buff, cb[4]) + sizeof(__u32)) + case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): + if (off + size > offsetofend(struct __sk_buff, cb[4])) return false; break; - default: - if (size != sizeof(__u32)) + case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_end): + if (size != size_default) return false; + break; + default: + /* Only narrow read access allowed for now. */ + if (type == BPF_WRITE) { + if (size != size_default) + return false; + } else { + bpf_ctx_record_field_size(info, size_default); + if (!bpf_ctx_narrow_access_ok(off, size, size_default)) + return false; + } } return true; @@ -2860,43 +3128,41 @@ static bool __is_valid_access(int off, int size) static bool sk_filter_is_valid_access(int off, int size, enum bpf_access_type type, - enum bpf_reg_type *reg_type) + struct bpf_insn_access_aux *info) { switch (off) { - case offsetof(struct __sk_buff, tc_classid): - case offsetof(struct __sk_buff, data): - case offsetof(struct __sk_buff, data_end): + case bpf_ctx_range(struct __sk_buff, tc_classid): + case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_end): return false; } if (type == BPF_WRITE) { switch (off) { - case offsetof(struct __sk_buff, cb[0]) ... - offsetof(struct __sk_buff, cb[4]) + sizeof(__u32) - 1: + case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; default: return false; } } - return __is_valid_access(off, size); + return bpf_skb_is_valid_access(off, size, type, info); } static bool lwt_is_valid_access(int off, int size, enum bpf_access_type type, - enum bpf_reg_type *reg_type) + struct bpf_insn_access_aux *info) { switch (off) { - case offsetof(struct __sk_buff, tc_classid): + case bpf_ctx_range(struct __sk_buff, tc_classid): return false; } if (type == BPF_WRITE) { switch (off) { - case offsetof(struct __sk_buff, mark): - case offsetof(struct __sk_buff, priority): - case offsetof(struct __sk_buff, cb[0]) ... - offsetof(struct __sk_buff, cb[4]) + sizeof(__u32) - 1: + case bpf_ctx_range(struct __sk_buff, mark): + case bpf_ctx_range(struct __sk_buff, priority): + case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; default: return false; @@ -2904,20 +3170,20 @@ static bool lwt_is_valid_access(int off, int size, } switch (off) { - case offsetof(struct __sk_buff, data): - *reg_type = PTR_TO_PACKET; + case bpf_ctx_range(struct __sk_buff, data): + info->reg_type = PTR_TO_PACKET; break; - case offsetof(struct __sk_buff, data_end): - *reg_type = PTR_TO_PACKET_END; + case bpf_ctx_range(struct __sk_buff, data_end): + info->reg_type = PTR_TO_PACKET_END; break; } - return __is_valid_access(off, size); + return bpf_skb_is_valid_access(off, size, type, info); } static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type type, - enum bpf_reg_type *reg_type) + struct bpf_insn_access_aux *info) { if (type == BPF_WRITE) { switch (off) { @@ -2980,16 +3246,15 @@ static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type, - enum bpf_reg_type *reg_type) + struct bpf_insn_access_aux *info) { if (type == BPF_WRITE) { switch (off) { - case offsetof(struct __sk_buff, mark): - case offsetof(struct __sk_buff, tc_index): - case offsetof(struct __sk_buff, priority): - case offsetof(struct __sk_buff, cb[0]) ... - offsetof(struct __sk_buff, cb[4]) + sizeof(__u32) - 1: - case offsetof(struct __sk_buff, tc_classid): + case bpf_ctx_range(struct __sk_buff, mark): + case bpf_ctx_range(struct __sk_buff, tc_index): + case bpf_ctx_range(struct __sk_buff, priority): + case bpf_ctx_range(struct __sk_buff, tc_classid): + case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; default: return false; @@ -2997,15 +3262,15 @@ static bool tc_cls_act_is_valid_access(int off, int size, } switch (off) { - case offsetof(struct __sk_buff, data): - *reg_type = PTR_TO_PACKET; + case bpf_ctx_range(struct __sk_buff, data): + info->reg_type = PTR_TO_PACKET; break; - case offsetof(struct __sk_buff, data_end): - *reg_type = PTR_TO_PACKET_END; + case bpf_ctx_range(struct __sk_buff, data_end): + info->reg_type = PTR_TO_PACKET_END; break; } - return __is_valid_access(off, size); + return bpf_skb_is_valid_access(off, size, type, info); } static bool __is_valid_xdp_access(int off, int size) @@ -3022,17 +3287,17 @@ static bool __is_valid_xdp_access(int off, int size) static bool xdp_is_valid_access(int off, int size, enum bpf_access_type type, - enum bpf_reg_type *reg_type) + struct bpf_insn_access_aux *info) { if (type == BPF_WRITE) return false; switch (off) { case offsetof(struct xdp_md, data): - *reg_type = PTR_TO_PACKET; + info->reg_type = PTR_TO_PACKET; break; case offsetof(struct xdp_md, data_end): - *reg_type = PTR_TO_PACKET_END; + info->reg_type = PTR_TO_PACKET_END; break; } @@ -3045,101 +3310,141 @@ void bpf_warn_invalid_xdp_action(u32 act) } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); +static bool __is_valid_sock_ops_access(int off, int size) +{ + if (off < 0 || off >= sizeof(struct bpf_sock_ops)) + return false; + /* The verifier guarantees that size > 0. */ + if (off % size != 0) + return false; + if (size != sizeof(__u32)) + return false; + + return true; +} + +static bool sock_ops_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + if (type == BPF_WRITE) { + switch (off) { + case offsetof(struct bpf_sock_ops, op) ... + offsetof(struct bpf_sock_ops, replylong[3]): + break; + default: + return false; + } + } + + return __is_valid_sock_ops_access(off, size); +} + static u32 bpf_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, - struct bpf_prog *prog) + struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct __sk_buff, len): - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); - *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, - offsetof(struct sk_buff, len)); + bpf_target_off(struct sk_buff, len, 4, + target_size)); break; case offsetof(struct __sk_buff, protocol): - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); - *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, - offsetof(struct sk_buff, protocol)); + bpf_target_off(struct sk_buff, protocol, 2, + target_size)); break; case offsetof(struct __sk_buff, vlan_proto): - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2); - *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, - offsetof(struct sk_buff, vlan_proto)); + bpf_target_off(struct sk_buff, vlan_proto, 2, + target_size)); break; case offsetof(struct __sk_buff, priority): - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, priority) != 4); - if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, - offsetof(struct sk_buff, priority)); + bpf_target_off(struct sk_buff, priority, 4, + target_size)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, - offsetof(struct sk_buff, priority)); + bpf_target_off(struct sk_buff, priority, 4, + target_size)); break; case offsetof(struct __sk_buff, ingress_ifindex): - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, skb_iif) != 4); - *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, - offsetof(struct sk_buff, skb_iif)); + bpf_target_off(struct sk_buff, skb_iif, 4, + target_size)); break; case offsetof(struct __sk_buff, ifindex): - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), si->dst_reg, si->src_reg, offsetof(struct sk_buff, dev)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, - offsetof(struct net_device, ifindex)); + bpf_target_off(struct net_device, ifindex, 4, + target_size)); break; case offsetof(struct __sk_buff, hash): - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); - *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, - offsetof(struct sk_buff, hash)); + bpf_target_off(struct sk_buff, hash, 4, + target_size)); break; case offsetof(struct __sk_buff, mark): - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); - if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, - offsetof(struct sk_buff, mark)); + bpf_target_off(struct sk_buff, mark, 4, + target_size)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, - offsetof(struct sk_buff, mark)); + bpf_target_off(struct sk_buff, mark, 4, + target_size)); break; case offsetof(struct __sk_buff, pkt_type): - return convert_skb_access(SKF_AD_PKTTYPE, si->dst_reg, - si->src_reg, insn); + *target_size = 1; + *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->src_reg, + PKT_TYPE_OFFSET()); + *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, PKT_TYPE_MAX); +#ifdef __BIG_ENDIAN_BITFIELD + *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, 5); +#endif + break; case offsetof(struct __sk_buff, queue_mapping): - return convert_skb_access(SKF_AD_QUEUE, si->dst_reg, - si->src_reg, insn); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, + bpf_target_off(struct sk_buff, queue_mapping, 2, + target_size)); + break; case offsetof(struct __sk_buff, vlan_present): - return convert_skb_access(SKF_AD_VLAN_TAG_PRESENT, - si->dst_reg, si->src_reg, insn); - case offsetof(struct __sk_buff, vlan_tci): - return convert_skb_access(SKF_AD_VLAN_TAG, - si->dst_reg, si->src_reg, insn); + BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); + + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, + bpf_target_off(struct sk_buff, vlan_tci, 2, + target_size)); + if (si->off == offsetof(struct __sk_buff, vlan_tci)) { + *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, + ~VLAN_TAG_PRESENT); + } else { + *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, 12); + *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, 1); + } + break; case offsetof(struct __sk_buff, cb[0]) ... - offsetof(struct __sk_buff, cb[4]) + sizeof(__u32) - 1: + offsetofend(struct __sk_buff, cb[4]) - 1: BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, data)) % @@ -3165,6 +3470,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, off -= offsetof(struct __sk_buff, tc_classid); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, tc_classid); + *target_size = 2; if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_H, si->dst_reg, si->src_reg, off); @@ -3190,14 +3496,14 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, tc_index): #ifdef CONFIG_NET_SCHED - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tc_index) != 2); - if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_H, si->dst_reg, si->src_reg, - offsetof(struct sk_buff, tc_index)); + bpf_target_off(struct sk_buff, tc_index, 2, + target_size)); else *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, - offsetof(struct sk_buff, tc_index)); + bpf_target_off(struct sk_buff, tc_index, 2, + target_size)); #else if (type == BPF_WRITE) *insn++ = BPF_MOV64_REG(si->dst_reg, si->dst_reg); @@ -3208,10 +3514,9 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, napi_id): #if defined(CONFIG_NET_RX_BUSY_POLL) - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, napi_id) != 4); - *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, - offsetof(struct sk_buff, napi_id)); + bpf_target_off(struct sk_buff, napi_id, 4, + target_size)); *insn++ = BPF_JMP_IMM(BPF_JGE, si->dst_reg, MIN_NAPI_ID, 1); *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #else @@ -3226,7 +3531,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, static u32 sock_filter_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, - struct bpf_prog *prog) + struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; @@ -3270,22 +3575,22 @@ static u32 sock_filter_convert_ctx_access(enum bpf_access_type type, static u32 tc_cls_act_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, - struct bpf_prog *prog) + struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct __sk_buff, ifindex): - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), si->dst_reg, si->src_reg, offsetof(struct sk_buff, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, - offsetof(struct net_device, ifindex)); + bpf_target_off(struct net_device, ifindex, 4, + target_size)); break; default: - return bpf_convert_ctx_access(type, si, insn_buf, prog); + return bpf_convert_ctx_access(type, si, insn_buf, prog, + target_size); } return insn - insn_buf; @@ -3294,7 +3599,7 @@ static u32 tc_cls_act_convert_ctx_access(enum bpf_access_type type, static u32 xdp_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, - struct bpf_prog *prog) + struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; @@ -3314,6 +3619,139 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } +static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size) +{ + struct bpf_insn *insn = insn_buf; + int off; + + switch (si->off) { + case offsetof(struct bpf_sock_ops, op) ... + offsetof(struct bpf_sock_ops, replylong[3]): + BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, op) != + FIELD_SIZEOF(struct bpf_sock_ops_kern, op)); + BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, reply) != + FIELD_SIZEOF(struct bpf_sock_ops_kern, reply)); + BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, replylong) != + FIELD_SIZEOF(struct bpf_sock_ops_kern, replylong)); + off = si->off; + off -= offsetof(struct bpf_sock_ops, op); + off += offsetof(struct bpf_sock_ops_kern, op); + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, + off); + else + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + off); + break; + + case offsetof(struct bpf_sock_ops, family): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, skc_family)); + break; + + case offsetof(struct bpf_sock_ops, remote_ip4): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, skc_daddr)); + break; + + case offsetof(struct bpf_sock_ops, local_ip4): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_rcv_saddr) != 4); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, + skc_rcv_saddr)); + break; + + case offsetof(struct bpf_sock_ops, remote_ip6[0]) ... + offsetof(struct bpf_sock_ops, remote_ip6[3]): +#if IS_ENABLED(CONFIG_IPV6) + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + skc_v6_daddr.s6_addr32[0]) != 4); + + off = si->off; + off -= offsetof(struct bpf_sock_ops, remote_ip6[0]); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, + skc_v6_daddr.s6_addr32[0]) + + off); +#else + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); +#endif + break; + + case offsetof(struct bpf_sock_ops, local_ip6[0]) ... + offsetof(struct bpf_sock_ops, local_ip6[3]): +#if IS_ENABLED(CONFIG_IPV6) + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + skc_v6_rcv_saddr.s6_addr32[0]) != 4); + + off = si->off; + off -= offsetof(struct bpf_sock_ops, local_ip6[0]); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, + skc_v6_rcv_saddr.s6_addr32[0]) + + off); +#else + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); +#endif + break; + + case offsetof(struct bpf_sock_ops, remote_port): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, skc_dport)); +#ifndef __BIG_ENDIAN_BITFIELD + *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); +#endif + break; + + case offsetof(struct bpf_sock_ops, local_port): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, skc_num)); + break; + } + return insn - insn_buf; +} + const struct bpf_verifier_ops sk_filter_prog_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, @@ -3336,7 +3774,7 @@ const struct bpf_verifier_ops xdp_prog_ops = { }; const struct bpf_verifier_ops cg_skb_prog_ops = { - .get_func_proto = cg_skb_func_proto, + .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .test_run = bpf_prog_test_run_skb, @@ -3363,6 +3801,12 @@ const struct bpf_verifier_ops cg_sock_prog_ops = { .convert_ctx_access = sock_filter_convert_ctx_access, }; +const struct bpf_verifier_ops sock_ops_prog_ops = { + .get_func_proto = sock_ops_func_proto, + .is_valid_access = sock_ops_is_valid_access, + .convert_ctx_access = sock_ops_convert_ctx_access, +}; + int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 28d94bce4df8..fc5fc4594c90 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -18,6 +18,7 @@ #include <linux/stddef.h> #include <linux/if_ether.h> #include <linux/mpls.h> +#include <linux/tcp.h> #include <net/flow_dissector.h> #include <scsi/fc/fc_fcoe.h> @@ -342,6 +343,64 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, return FLOW_DISSECT_RET_OUT_PROTO_AGAIN; } +static void +__skb_flow_dissect_tcp(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, int thoff, int hlen) +{ + struct flow_dissector_key_tcp *key_tcp; + struct tcphdr *th, _th; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TCP)) + return; + + th = __skb_header_pointer(skb, thoff, sizeof(_th), data, hlen, &_th); + if (!th) + return; + + if (unlikely(__tcp_hdrlen(th) < sizeof(_th))) + return; + + key_tcp = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_TCP, + target_container); + key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF)); +} + +static void +__skb_flow_dissect_ipv4(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, const struct iphdr *iph) +{ + struct flow_dissector_key_ip *key_ip; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) + return; + + key_ip = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IP, + target_container); + key_ip->tos = iph->tos; + key_ip->ttl = iph->ttl; +} + +static void +__skb_flow_dissect_ipv6(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, const struct ipv6hdr *iph) +{ + struct flow_dissector_key_ip *key_ip; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) + return; + + key_ip = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IP, + target_container); + key_ip->tos = ipv6_get_dsfield(iph); + key_ip->ttl = iph->hop_limit; +} + /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified @@ -444,6 +503,9 @@ ip: } } + __skb_flow_dissect_ipv4(skb, flow_dissector, + target_container, data, iph); + if (flags & FLOW_DISSECTOR_F_STOP_AT_L3) goto out_good; @@ -489,6 +551,9 @@ ipv6: goto out_good; } + __skb_flow_dissect_ipv6(skb, flow_dissector, + target_container, data, iph); + if (flags & FLOW_DISSECTOR_F_STOP_AT_L3) goto out_good; @@ -683,6 +748,10 @@ ip_proto_again: case IPPROTO_MPLS: proto = htons(ETH_P_MPLS_UC); goto mpls; + case IPPROTO_TCP: + __skb_flow_dissect_tcp(skb, flow_dissector, target_container, + data, nhoff, hlen); + break; default: break; } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index b3bc0a31af9f..1307731ddfe4 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -240,7 +240,8 @@ static const struct nla_policy bpf_nl_policy[LWT_BPF_MAX + 1] = { static int bpf_build_state(struct nlattr *nla, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct nlattr *tb[LWT_BPF_MAX + 1]; struct lwtunnel_state *newts; @@ -250,7 +251,7 @@ static int bpf_build_state(struct nlattr *nla, if (family != AF_INET && family != AF_INET6) return -EAFNOSUPPORT; - ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy, NULL); + ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy, extack); if (ret < 0) return ret; diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index cfae3d5fe11f..d9cb3532f1dd 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -103,37 +103,53 @@ EXPORT_SYMBOL(lwtunnel_encap_del_ops); int lwtunnel_build_state(u16 encap_type, struct nlattr *encap, unsigned int family, - const void *cfg, struct lwtunnel_state **lws) + const void *cfg, struct lwtunnel_state **lws, + struct netlink_ext_ack *extack) { const struct lwtunnel_encap_ops *ops; + bool found = false; int ret = -EINVAL; if (encap_type == LWTUNNEL_ENCAP_NONE || - encap_type > LWTUNNEL_ENCAP_MAX) + encap_type > LWTUNNEL_ENCAP_MAX) { + NL_SET_ERR_MSG_ATTR(extack, encap, + "Unknown LWT encapsulation type"); return ret; + } ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); if (likely(ops && ops->build_state && try_module_get(ops->owner))) { - ret = ops->build_state(encap, family, cfg, lws); + found = true; + ret = ops->build_state(encap, family, cfg, lws, extack); if (ret) module_put(ops->owner); } rcu_read_unlock(); + /* don't rely on -EOPNOTSUPP to detect match as build_state + * handlers could return it + */ + if (!found) { + NL_SET_ERR_MSG_ATTR(extack, encap, + "LWT encapsulation type not supported"); + } + return ret; } EXPORT_SYMBOL(lwtunnel_build_state); -int lwtunnel_valid_encap_type(u16 encap_type) +int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) { const struct lwtunnel_encap_ops *ops; int ret = -EINVAL; if (encap_type == LWTUNNEL_ENCAP_NONE || - encap_type > LWTUNNEL_ENCAP_MAX) + encap_type > LWTUNNEL_ENCAP_MAX) { + NL_SET_ERR_MSG(extack, "Unknown lwt encapsulation type"); return ret; + } rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); @@ -153,11 +169,16 @@ int lwtunnel_valid_encap_type(u16 encap_type) } } #endif - return ops ? 0 : -EOPNOTSUPP; + ret = ops ? 0 : -EOPNOTSUPP; + if (ret < 0) + NL_SET_ERR_MSG(extack, "lwt encapsulation type not supported"); + + return ret; } EXPORT_SYMBOL(lwtunnel_valid_encap_type); -int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) +int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining, + struct netlink_ext_ack *extack) { struct rtnexthop *rtnh = (struct rtnexthop *)attr; struct nlattr *nla_entype; @@ -174,7 +195,8 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) if (nla_entype) { encap_type = nla_get_u16(nla_entype); - if (lwtunnel_valid_encap_type(encap_type) != 0) + if (lwtunnel_valid_encap_type(encap_type, + extack) != 0) return -EOPNOTSUPP; } } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index d274f81fcc2c..d0713627deb6 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -118,6 +118,50 @@ unsigned long neigh_rand_reach_time(unsigned long base) EXPORT_SYMBOL(neigh_rand_reach_time); +static bool neigh_del(struct neighbour *n, __u8 state, + struct neighbour __rcu **np, struct neigh_table *tbl) +{ + bool retval = false; + + write_lock(&n->lock); + if (refcount_read(&n->refcnt) == 1 && !(n->nud_state & state)) { + struct neighbour *neigh; + + neigh = rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock)); + rcu_assign_pointer(*np, neigh); + n->dead = 1; + retval = true; + } + write_unlock(&n->lock); + if (retval) + neigh_cleanup_and_release(n); + return retval; +} + +bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl) +{ + struct neigh_hash_table *nht; + void *pkey = ndel->primary_key; + u32 hash_val; + struct neighbour *n; + struct neighbour __rcu **np; + + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); + hash_val = tbl->hash(pkey, ndel->dev, nht->hash_rnd); + hash_val = hash_val >> (32 - nht->hash_shift); + + np = &nht->hash_buckets[hash_val]; + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock)))) { + if (n == ndel) + return neigh_del(n, 0, np, tbl); + np = &n->next; + } + return false; +} + static int neigh_forced_gc(struct neigh_table *tbl) { int shrunk = 0; @@ -140,19 +184,10 @@ static int neigh_forced_gc(struct neigh_table *tbl) * - nobody refers to it. * - it is not permanent */ - write_lock(&n->lock); - if (atomic_read(&n->refcnt) == 1 && - !(n->nud_state & NUD_PERMANENT)) { - rcu_assign_pointer(*np, - rcu_dereference_protected(n->next, - lockdep_is_held(&tbl->lock))); - n->dead = 1; - shrunk = 1; - write_unlock(&n->lock); - neigh_cleanup_and_release(n); + if (neigh_del(n, NUD_PERMANENT, np, tbl)) { + shrunk = 1; continue; } - write_unlock(&n->lock); np = &n->next; } } @@ -219,7 +254,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) neigh_del_timer(n); n->dead = 1; - if (atomic_read(&n->refcnt) != 1) { + if (refcount_read(&n->refcnt) != 1) { /* The most unpleasant situation. We must destroy neighbour entry, but someone still uses it. @@ -300,7 +335,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device NEIGH_CACHE_STAT_INC(tbl, allocs); n->tbl = tbl; - atomic_set(&n->refcnt, 1); + refcount_set(&n->refcnt, 1); n->dead = 1; out: return n; @@ -312,8 +347,7 @@ out_entries: static void neigh_get_hash_rnd(u32 *x) { - get_random_bytes(x, sizeof(*x)); - *x |= 1; + *x = get_random_u32() | 1; } static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) @@ -409,7 +443,7 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, rcu_read_lock_bh(); n = __neigh_lookup_noref(tbl, pkey, dev); if (n) { - if (!atomic_inc_not_zero(&n->refcnt)) + if (!refcount_inc_not_zero(&n->refcnt)) n = NULL; NEIGH_CACHE_STAT_INC(tbl, hits); } @@ -438,7 +472,7 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, n = rcu_dereference_bh(n->next)) { if (!memcmp(n->primary_key, pkey, key_len) && net_eq(dev_net(n->dev), net)) { - if (!atomic_inc_not_zero(&n->refcnt)) + if (!refcount_inc_not_zero(&n->refcnt)) n = NULL; NEIGH_CACHE_STAT_INC(tbl, hits); break; @@ -674,7 +708,7 @@ static void neigh_parms_destroy(struct neigh_parms *parms); static inline void neigh_parms_put(struct neigh_parms *parms) { - if (atomic_dec_and_test(&parms->refcnt)) + if (refcount_dec_and_test(&parms->refcnt)) neigh_parms_destroy(parms); } @@ -786,7 +820,7 @@ static void neigh_periodic_work(struct work_struct *work) if (time_before(n->used, n->confirmed)) n->used = n->confirmed; - if (atomic_read(&n->refcnt) == 1 && + if (refcount_read(&n->refcnt) == 1 && (state == NUD_FAILED || time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { *np = n->next; @@ -1444,7 +1478,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL); if (p) { p->tbl = tbl; - atomic_set(&p->refcnt, 1); + refcount_set(&p->refcnt, 1); p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); dev_hold(dev); @@ -1507,7 +1541,7 @@ void neigh_table_init(int index, struct neigh_table *tbl) INIT_LIST_HEAD(&tbl->parms_list); list_add(&tbl->parms.list, &tbl->parms_list); write_pnet(&tbl->parms.net, &init_net); - atomic_set(&tbl->parms.refcnt, 1); + refcount_set(&tbl->parms.refcnt, 1); tbl->parms.reachable_time = neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME)); @@ -1649,7 +1683,10 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN, NETLINK_CB(skb).portid); + write_lock_bh(&tbl->lock); neigh_release(neigh); + neigh_remove_one(neigh, tbl); + write_unlock_bh(&tbl->lock); out: return err; @@ -1758,7 +1795,7 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) if ((parms->dev && nla_put_u32(skb, NDTPA_IFINDEX, parms->dev->ifindex)) || - nla_put_u32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)) || + nla_put_u32(skb, NDTPA_REFCNT, refcount_read(&parms->refcnt)) || nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, NEIGH_VAR(parms, QUEUE_LEN_BYTES)) || /* approximative value for deprecated QUEUE_LEN (in packets) */ @@ -2196,7 +2233,7 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, ci.ndm_used = jiffies_to_clock_t(now - neigh->used); ci.ndm_confirmed = jiffies_to_clock_t(now - neigh->confirmed); ci.ndm_updated = jiffies_to_clock_t(now - neigh->updated); - ci.ndm_refcnt = atomic_read(&neigh->refcnt) - 1; + ci.ndm_refcnt = refcount_read(&neigh->refcnt) - 1; read_unlock_bh(&neigh->lock); if (nla_put_u32(skb, NDA_PROBES, atomic_read(&neigh->probes)) || diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index 14d09345f00d..4847964931df 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -363,15 +363,10 @@ static int dev_mc_seq_show(struct seq_file *seq, void *v) netif_addr_lock_bh(dev); netdev_for_each_mc_addr(ha, dev) { - int i; - - seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex, - dev->name, ha->refcount, ha->global_use); - - for (i = 0; i < dev->addr_len; i++) - seq_printf(seq, "%02x", ha->addr[i]); - - seq_putc(seq, '\n'); + seq_printf(seq, "%-4d %-15s %-5d %-5d %*phN\n", + dev->ifindex, dev->name, + ha->refcount, ha->global_use, + (int)dev->addr_len, ha->addr); } netif_addr_unlock_bh(dev); return 0; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 65ea0ff4017c..b4f9922b6f23 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -323,7 +323,11 @@ NETDEVICE_SHOW_RW(flags, fmt_hex); static int change_tx_queue_len(struct net_device *dev, unsigned long new_len) { - int res, orig_len = dev->tx_queue_len; + unsigned int orig_len = dev->tx_queue_len; + int res; + + if (new_len != (unsigned int)new_len) + return -ERANGE; if (new_len != orig_len) { dev->tx_queue_len = new_len; @@ -349,7 +353,7 @@ static ssize_t tx_queue_len_store(struct device *dev, return netdev_store(dev, attr, buf, len, change_tx_queue_len); } -NETDEVICE_SHOW_RW(tx_queue_len, fmt_ulong); +NETDEVICE_SHOW_RW(tx_queue_len, fmt_dec); static int change_gro_flush_timeout(struct net_device *dev, unsigned long val) { @@ -622,7 +626,7 @@ static struct attribute *netstat_attrs[] = { }; -static struct attribute_group netstat_group = { +static const struct attribute_group netstat_group = { .name = "statistics", .attrs = netstat_attrs, }; @@ -632,7 +636,7 @@ static struct attribute *wireless_attrs[] = { NULL }; -static struct attribute_group wireless_group = { +static const struct attribute_group wireless_group = { .name = "wireless", .attrs = wireless_attrs, }; @@ -1200,7 +1204,7 @@ static struct attribute *dql_attrs[] = { NULL }; -static struct attribute_group dql_group = { +static const struct attribute_group dql_group = { .name = "byte_queue_limits", .attrs = dql_attrs, }; @@ -1444,7 +1448,7 @@ static void *net_grab_current_ns(void) struct net *ns = current->nsproxy->net_ns; #ifdef CONFIG_NET_NS if (ns) - atomic_inc(&ns->passive); + refcount_inc(&ns->passive); #endif return ns; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 26bbfababff2..8726d051f31d 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -284,7 +284,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) LIST_HEAD(net_exit_list); atomic_set(&net->count, 1); - atomic_set(&net->passive, 1); + refcount_set(&net->passive, 1); net->dev_base_seq = 1; net->user_ns = user_ns; idr_init(&net->netns_ids); @@ -380,7 +380,7 @@ static void net_free(struct net *net) void net_drop_ns(void *p) { struct net *ns = p; - if (ns && atomic_dec_and_test(&ns->passive)) + if (ns && refcount_dec_and_test(&ns->passive)) net_free(ns); } @@ -501,6 +501,23 @@ static void cleanup_net(struct work_struct *work) net_drop_ns(net); } } + +/** + * net_ns_barrier - wait until concurrent net_cleanup_work is done + * + * cleanup_net runs from work queue and will first remove namespaces + * from the global list, then run net exit functions. + * + * Call this in module exit path to make sure that all netns + * ->exit ops have been invoked before the function is removed. + */ +void net_ns_barrier(void) +{ + mutex_lock(&net_mutex); + mutex_unlock(&net_mutex); +} +EXPORT_SYMBOL(net_ns_barrier); + static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) @@ -596,6 +613,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, { struct net *net = sock_net(skb->sk); struct nlattr *tb[NETNSA_MAX + 1]; + struct nlattr *nla; struct net *peer; int nsid, err; @@ -603,23 +621,35 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, rtnl_net_policy, extack); if (err < 0) return err; - if (!tb[NETNSA_NSID]) + if (!tb[NETNSA_NSID]) { + NL_SET_ERR_MSG(extack, "nsid is missing"); return -EINVAL; + } nsid = nla_get_s32(tb[NETNSA_NSID]); - if (tb[NETNSA_PID]) + if (tb[NETNSA_PID]) { peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID])); - else if (tb[NETNSA_FD]) + nla = tb[NETNSA_PID]; + } else if (tb[NETNSA_FD]) { peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD])); - else + nla = tb[NETNSA_FD]; + } else { + NL_SET_ERR_MSG(extack, "Peer netns reference is missing"); return -EINVAL; - if (IS_ERR(peer)) + } + if (IS_ERR(peer)) { + NL_SET_BAD_ATTR(extack, nla); + NL_SET_ERR_MSG(extack, "Peer netns reference is invalid"); return PTR_ERR(peer); + } spin_lock_bh(&net->nsid_lock); if (__peernet2id(net, peer) >= 0) { spin_unlock_bh(&net->nsid_lock); err = -EEXIST; + NL_SET_BAD_ATTR(extack, nla); + NL_SET_ERR_MSG(extack, + "Peer netns already has a nsid assigned"); goto out; } @@ -628,6 +658,10 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, if (err >= 0) { rtnl_net_notifyid(net, RTM_NEWNSID, err); err = 0; + } else if (err == -ENOSPC && nsid >= 0) { + err = -EEXIST; + NL_SET_BAD_ATTR(extack, tb[NETNSA_NSID]); + NL_SET_ERR_MSG(extack, "The specified nsid is already used"); } out: put_net(peer); @@ -670,6 +704,7 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh, { struct net *net = sock_net(skb->sk); struct nlattr *tb[NETNSA_MAX + 1]; + struct nlattr *nla; struct sk_buff *msg; struct net *peer; int err, id; @@ -678,15 +713,22 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh, rtnl_net_policy, extack); if (err < 0) return err; - if (tb[NETNSA_PID]) + if (tb[NETNSA_PID]) { peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID])); - else if (tb[NETNSA_FD]) + nla = tb[NETNSA_PID]; + } else if (tb[NETNSA_FD]) { peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD])); - else + nla = tb[NETNSA_FD]; + } else { + NL_SET_ERR_MSG(extack, "Peer netns reference is missing"); return -EINVAL; + } - if (IS_ERR(peer)) + if (IS_ERR(peer)) { + NL_SET_BAD_ATTR(extack, nla); + NL_SET_ERR_MSG(extack, "Peer netns reference is invalid"); return PTR_ERR(peer); + } msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL); if (!msg) { diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 29be2466970c..8357f164c660 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -277,7 +277,7 @@ static void zap_completion_queue(void) struct sk_buff *skb = clist; clist = clist->next; if (!skb_irq_freeable(skb)) { - atomic_inc(&skb->users); + refcount_set(&skb->users, 1); dev_kfree_skb_any(skb); /* put this one back */ } else { __kfree_skb(skb); @@ -309,7 +309,7 @@ repeat: return NULL; } - atomic_set(&skb->users, 1); + refcount_set(&skb->users, 1); skb_reserve(skb, reserve); return skb; } @@ -441,7 +441,7 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) ip6h->saddr = np->local_ip.in6; ip6h->daddr = np->remote_ip.in6; - eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); + eth = skb_push(skb, ETH_HLEN); skb_reset_mac_header(skb); skb->protocol = eth->h_proto = htons(ETH_P_IPV6); } else { @@ -470,7 +470,7 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) put_unaligned(np->remote_ip.ip, &(iph->daddr)); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); - eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); + eth = skb_push(skb, ETH_HLEN); skb_reset_mac_header(skb); skb->protocol = eth->h_proto = htons(ETH_P_IP); } @@ -632,7 +632,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) skb_queue_head_init(&npinfo->txq); INIT_DELAYED_WORK(&npinfo->tx_work, queue_process); - atomic_set(&npinfo->refcnt, 1); + refcount_set(&npinfo->refcnt, 1); ops = np->dev->netdev_ops; if (ops->ndo_netpoll_setup) { @@ -642,7 +642,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) } } else { npinfo = rtnl_dereference(ndev->npinfo); - atomic_inc(&npinfo->refcnt); + refcount_inc(&npinfo->refcnt); } npinfo->netpoll = np; @@ -821,7 +821,7 @@ void __netpoll_cleanup(struct netpoll *np) synchronize_srcu(&netpoll_srcu); - if (atomic_dec_and_test(&npinfo->refcnt)) { + if (refcount_dec_and_test(&npinfo->refcnt)) { const struct net_device_ops *ops; ops = np->dev->netdev_ops; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 96947f5d41e4..6e1e10ff433a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2675,7 +2675,7 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, goto err; } /* restore ll */ - eth = (struct ethhdr *)skb_push(skb, ETH_HLEN); + eth = skb_push(skb, ETH_HLEN); memcpy(eth, pkt_dev->hh, 2 * ETH_ALEN); eth->h_proto = protocol; @@ -2714,11 +2714,11 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, struct timeval timestamp; struct pktgen_hdr *pgh; - pgh = (struct pktgen_hdr *)skb_put(skb, sizeof(*pgh)); + pgh = skb_put(skb, sizeof(*pgh)); datalen -= sizeof(*pgh); if (pkt_dev->nfrags <= 0) { - memset(skb_put(skb, datalen), 0, datalen); + skb_put_zero(skb, datalen); } else { int frags = pkt_dev->nfrags; int i, len; @@ -2729,7 +2729,7 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, frags = MAX_SKB_FRAGS; len = datalen - frags * PAGE_SIZE; if (len > 0) { - memset(skb_put(skb, len), 0, len); + skb_put_zero(skb, len); datalen = frags * PAGE_SIZE; } @@ -2844,34 +2844,35 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, skb_reserve(skb, 16); /* Reserve for ethernet and IP header */ - eth = (__u8 *) skb_push(skb, 14); - mpls = (__be32 *)skb_put(skb, pkt_dev->nr_labels*sizeof(__u32)); + eth = skb_push(skb, 14); + mpls = skb_put(skb, pkt_dev->nr_labels * sizeof(__u32)); if (pkt_dev->nr_labels) mpls_push(mpls, pkt_dev); if (pkt_dev->vlan_id != 0xffff) { if (pkt_dev->svlan_id != 0xffff) { - svlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + svlan_tci = skb_put(skb, sizeof(__be16)); *svlan_tci = build_tci(pkt_dev->svlan_id, pkt_dev->svlan_cfi, pkt_dev->svlan_p); - svlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + svlan_encapsulated_proto = skb_put(skb, + sizeof(__be16)); *svlan_encapsulated_proto = htons(ETH_P_8021Q); } - vlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + vlan_tci = skb_put(skb, sizeof(__be16)); *vlan_tci = build_tci(pkt_dev->vlan_id, pkt_dev->vlan_cfi, pkt_dev->vlan_p); - vlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + vlan_encapsulated_proto = skb_put(skb, sizeof(__be16)); *vlan_encapsulated_proto = htons(ETH_P_IP); } skb_reset_mac_header(skb); skb_set_network_header(skb, skb->len); - iph = (struct iphdr *) skb_put(skb, sizeof(struct iphdr)); + iph = skb_put(skb, sizeof(struct iphdr)); skb_set_transport_header(skb, skb->len); - udph = (struct udphdr *) skb_put(skb, sizeof(struct udphdr)); + udph = skb_put(skb, sizeof(struct udphdr)); skb_set_queue_mapping(skb, queue_map); skb->priority = pkt_dev->skb_priority; @@ -2971,34 +2972,35 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, skb_reserve(skb, 16); /* Reserve for ethernet and IP header */ - eth = (__u8 *) skb_push(skb, 14); - mpls = (__be32 *)skb_put(skb, pkt_dev->nr_labels*sizeof(__u32)); + eth = skb_push(skb, 14); + mpls = skb_put(skb, pkt_dev->nr_labels * sizeof(__u32)); if (pkt_dev->nr_labels) mpls_push(mpls, pkt_dev); if (pkt_dev->vlan_id != 0xffff) { if (pkt_dev->svlan_id != 0xffff) { - svlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + svlan_tci = skb_put(skb, sizeof(__be16)); *svlan_tci = build_tci(pkt_dev->svlan_id, pkt_dev->svlan_cfi, pkt_dev->svlan_p); - svlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + svlan_encapsulated_proto = skb_put(skb, + sizeof(__be16)); *svlan_encapsulated_proto = htons(ETH_P_8021Q); } - vlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + vlan_tci = skb_put(skb, sizeof(__be16)); *vlan_tci = build_tci(pkt_dev->vlan_id, pkt_dev->vlan_cfi, pkt_dev->vlan_p); - vlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + vlan_encapsulated_proto = skb_put(skb, sizeof(__be16)); *vlan_encapsulated_proto = htons(ETH_P_IPV6); } skb_reset_mac_header(skb); skb_set_network_header(skb, skb->len); - iph = (struct ipv6hdr *) skb_put(skb, sizeof(struct ipv6hdr)); + iph = skb_put(skb, sizeof(struct ipv6hdr)); skb_set_transport_header(skb, skb->len); - udph = (struct udphdr *) skb_put(skb, sizeof(struct udphdr)); + udph = skb_put(skb, sizeof(struct udphdr)); skb_set_queue_mapping(skb, queue_map); skb->priority = pkt_dev->skb_priority; @@ -3361,7 +3363,7 @@ static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev) { ktime_t idle_start = ktime_get(); - while (atomic_read(&(pkt_dev->skb->users)) != 1) { + while (refcount_read(&(pkt_dev->skb->users)) != 1) { if (signal_pending(current)) break; @@ -3418,7 +3420,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) if (pkt_dev->xmit_mode == M_NETIF_RECEIVE) { skb = pkt_dev->skb; skb->protocol = eth_type_trans(skb, skb->dev); - atomic_add(burst, &skb->users); + refcount_add(burst, &skb->users); local_bh_disable(); do { ret = netif_receive_skb(skb); @@ -3426,11 +3428,11 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) pkt_dev->errors++; pkt_dev->sofar++; pkt_dev->seq_num++; - if (atomic_read(&skb->users) != burst) { + if (refcount_read(&skb->users) != burst) { /* skb was queued by rps/rfs or taps, * so cannot reuse this skb */ - atomic_sub(burst - 1, &skb->users); + WARN_ON(refcount_sub_and_test(burst - 1, &skb->users)); /* get out of the loop and wait * until skb is consumed */ @@ -3444,7 +3446,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) goto out; /* Skips xmit_mode M_START_XMIT */ } else if (pkt_dev->xmit_mode == M_QUEUE_XMIT) { local_bh_disable(); - atomic_inc(&pkt_dev->skb->users); + refcount_inc(&pkt_dev->skb->users); ret = dev_queue_xmit(pkt_dev->skb); switch (ret) { @@ -3485,7 +3487,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) pkt_dev->last_ok = 0; goto unlock; } - atomic_add(burst, &pkt_dev->skb->users); + refcount_add(burst, &pkt_dev->skb->users); xmit_more: ret = netdev_start_xmit(pkt_dev->skb, odev, txq, --burst > 0); @@ -3511,11 +3513,11 @@ xmit_more: /* fallthru */ case NETDEV_TX_BUSY: /* Retry it next time */ - atomic_dec(&(pkt_dev->skb->users)); + refcount_dec(&(pkt_dev->skb->users)); pkt_dev->last_ok = 0; } if (unlikely(burst)) - atomic_sub(burst, &pkt_dev->skb->users); + WARN_ON(refcount_sub_and_test(burst, &pkt_dev->skb->users)); unlock: HARD_TX_UNLOCK(odev, txq); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 467a2f4510a7..9201e3621351 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -16,6 +16,7 @@ * Vitaly E. Lavrov RTA_OK arithmetics was wrong. */ +#include <linux/bitops.h> #include <linux/errno.h> #include <linux/module.h> #include <linux/types.h> @@ -39,6 +40,7 @@ #include <linux/if_vlan.h> #include <linux/pci.h> #include <linux/etherdevice.h> +#include <linux/bpf.h> #include <linux/uaccess.h> @@ -647,7 +649,7 @@ int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int g NETLINK_CB(skb).dst_group = group; if (echo) - atomic_inc(&skb->users); + refcount_inc(&skb->users); netlink_broadcast(rtnl, skb, pid, group, GFP_KERNEL); if (echo) err = netlink_unicast(rtnl, skb, pid, MSG_DONTWAIT); @@ -899,7 +901,8 @@ static size_t rtnl_port_size(const struct net_device *dev, static size_t rtnl_xdp_size(void) { size_t xdp_size = nla_total_size(0) + /* nest IFLA_XDP */ - nla_total_size(1); /* XDP_ATTACHED */ + nla_total_size(1) + /* XDP_ATTACHED */ + nla_total_size(4); /* XDP_PROG_ID */ return xdp_size; } @@ -942,6 +945,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */ + rtnl_xdp_size() /* IFLA_XDP */ + + nla_total_size(4) /* IFLA_EVENT */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ } @@ -1248,23 +1252,29 @@ static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) return 0; } -static u8 rtnl_xdp_attached_mode(struct net_device *dev) +static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id) { const struct net_device_ops *ops = dev->netdev_ops; + const struct bpf_prog *generic_xdp_prog; ASSERT_RTNL(); - if (rcu_access_pointer(dev->xdp_prog)) + *prog_id = 0; + generic_xdp_prog = rtnl_dereference(dev->xdp_prog); + if (generic_xdp_prog) { + *prog_id = generic_xdp_prog->aux->id; return XDP_ATTACHED_SKB; - if (ops->ndo_xdp && __dev_xdp_attached(dev, ops->ndo_xdp)) - return XDP_ATTACHED_DRV; + } + if (!ops->ndo_xdp) + return XDP_ATTACHED_NONE; - return XDP_ATTACHED_NONE; + return __dev_xdp_attached(dev, ops->ndo_xdp, prog_id); } static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) { struct nlattr *xdp; + u32 prog_id; int err; xdp = nla_nest_start(skb, IFLA_XDP); @@ -1272,10 +1282,16 @@ static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) return -EMSGSIZE; err = nla_put_u8(skb, IFLA_XDP_ATTACHED, - rtnl_xdp_attached_mode(dev)); + rtnl_xdp_attached_mode(dev, &prog_id)); if (err) goto err_cancel; + if (prog_id) { + err = nla_put_u32(skb, IFLA_XDP_PROG_ID, prog_id); + if (err) + goto err_cancel; + } + nla_nest_end(skb, xdp); return 0; @@ -1284,9 +1300,40 @@ err_cancel: return err; } +static u32 rtnl_get_event(unsigned long event) +{ + u32 rtnl_event_type = IFLA_EVENT_NONE; + + switch (event) { + case NETDEV_REBOOT: + rtnl_event_type = IFLA_EVENT_REBOOT; + break; + case NETDEV_FEAT_CHANGE: + rtnl_event_type = IFLA_EVENT_FEATURES; + break; + case NETDEV_BONDING_FAILOVER: + rtnl_event_type = IFLA_EVENT_BONDING_FAILOVER; + break; + case NETDEV_NOTIFY_PEERS: + rtnl_event_type = IFLA_EVENT_NOTIFY_PEERS; + break; + case NETDEV_RESEND_IGMP: + rtnl_event_type = IFLA_EVENT_IGMP_RESEND; + break; + case NETDEV_CHANGEINFODATA: + rtnl_event_type = IFLA_EVENT_BONDING_OPTIONS; + break; + default: + break; + } + + return rtnl_event_type; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, - unsigned int flags, u32 ext_filter_mask) + unsigned int flags, u32 ext_filter_mask, + u32 event) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -1335,6 +1382,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down)) goto nla_put_failure; + if (event != IFLA_EVENT_NONE) { + if (nla_put_u32(skb, IFLA_EVENT, event)) + goto nla_put_failure; + } + if (rtnl_fill_link_ifmap(skb, dev)) goto nla_put_failure; @@ -1469,6 +1521,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_LINK_NETNSID] = { .type = NLA_S32 }, [IFLA_PROTO_DOWN] = { .type = NLA_U8 }, [IFLA_XDP] = { .type = NLA_NESTED }, + [IFLA_EVENT] = { .type = NLA_U32 }, [IFLA_GROUP] = { .type = NLA_U32 }, }; @@ -1517,6 +1570,7 @@ static const struct nla_policy ifla_xdp_policy[IFLA_XDP_MAX + 1] = { [IFLA_XDP_FD] = { .type = NLA_S32 }, [IFLA_XDP_ATTACHED] = { .type = NLA_U8 }, [IFLA_XDP_FLAGS] = { .type = NLA_U32 }, + [IFLA_XDP_PROG_ID] = { .type = NLA_U32 }, }; static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla) @@ -1629,7 +1683,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, 0, flags, - ext_filter_mask); + ext_filter_mask, 0); if (err < 0) { if (likely(skb->len)) @@ -1977,7 +2031,8 @@ static int do_setlink(const struct sk_buff *skb, struct sockaddr *sa; int len; - len = sizeof(sa_family_t) + dev->addr_len; + len = sizeof(sa_family_t) + max_t(size_t, dev->addr_len, + sizeof(*sa)); sa = kmalloc(len, GFP_KERNEL); if (!sa) { err = -ENOMEM; @@ -2051,8 +2106,8 @@ static int do_setlink(const struct sk_buff *skb, } if (tb[IFLA_TXQLEN]) { - unsigned long value = nla_get_u32(tb[IFLA_TXQLEN]); - unsigned long orig_len = dev->tx_queue_len; + unsigned int value = nla_get_u32(tb[IFLA_TXQLEN]); + unsigned int orig_len = dev->tx_queue_len; if (dev->tx_queue_len ^ value) { dev->tx_queue_len = value; @@ -2189,7 +2244,7 @@ static int do_setlink(const struct sk_buff *skb, if (err < 0) goto errout; - if (xdp[IFLA_XDP_ATTACHED]) { + if (xdp[IFLA_XDP_ATTACHED] || xdp[IFLA_XDP_PROG_ID]) { err = -EINVAL; goto errout; } @@ -2200,8 +2255,7 @@ static int do_setlink(const struct sk_buff *skb, err = -EINVAL; goto errout; } - if ((xdp_flags & XDP_FLAGS_SKB_MODE) && - (xdp_flags & XDP_FLAGS_DRV_MODE)) { + if (hweight32(xdp_flags & XDP_FLAGS_MODES) > 1) { err = -EINVAL; goto errout; } @@ -2529,7 +2583,7 @@ replay: data = attr; } if (ops->validate) { - err = ops->validate(tb, data); + err = ops->validate(tb, data, extack); if (err < 0) return err; } @@ -2548,7 +2602,8 @@ replay: slave_data = slave_attr; } if (m_ops->slave_validate) { - err = m_ops->slave_validate(tb, slave_data); + err = m_ops->slave_validate(tb, slave_data, + extack); if (err < 0) return err; } @@ -2567,7 +2622,7 @@ replay: !ops->changelink) return -EOPNOTSUPP; - err = ops->changelink(dev, tb, data); + err = ops->changelink(dev, tb, data, extack); if (err < 0) return err; status |= DO_SETLINK_NOTIFY; @@ -2578,7 +2633,8 @@ replay: return -EOPNOTSUPP; err = m_ops->slave_changelink(master_dev, dev, - tb, slave_data); + tb, slave_data, + extack); if (err < 0) return err; status |= DO_SETLINK_NOTIFY; @@ -2652,7 +2708,8 @@ replay: dev->ifindex = ifm->ifi_index; if (ops->newlink) { - err = ops->newlink(link_net ? : net, dev, tb, data); + err = ops->newlink(link_net ? : net, dev, tb, data, + extack); /* Drivers should call free_netdev() in ->destructor * and unregister it on failure after registration * so that device could be finally freed in rtnl_unlock. @@ -2739,7 +2796,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, return -ENOBUFS; err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, 0, 0, ext_filter_mask); + nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); @@ -2811,7 +2868,8 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) } struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, - unsigned int change, gfp_t flags) + unsigned int change, + u32 event, gfp_t flags) { struct net *net = dev_net(dev); struct sk_buff *skb; @@ -2822,7 +2880,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, if (skb == NULL) goto errout; - err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0); + err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -2843,18 +2901,25 @@ void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags) rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags); } -void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, - gfp_t flags) +static void rtmsg_ifinfo_event(int type, struct net_device *dev, + unsigned int change, u32 event, + gfp_t flags) { struct sk_buff *skb; if (dev->reg_state != NETREG_REGISTERED) return; - skb = rtmsg_ifinfo_build_skb(type, dev, change, flags); + skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags); if (skb) rtmsg_ifinfo_send(skb, dev, flags); } + +void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, + gfp_t flags) +{ + rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags); +} EXPORT_SYMBOL(rtmsg_ifinfo); static int nlmsg_populate_fdb_fill(struct sk_buff *skb, @@ -4159,19 +4224,33 @@ static void rtnetlink_rcv(struct sk_buff *skb) rtnl_unlock(); } +static int rtnetlink_bind(struct net *net, int group) +{ + switch (group) { + case RTNLGRP_IPV4_MROUTE_R: + case RTNLGRP_IPV6_MROUTE_R: + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + break; + } + return 0; +} + static int rtnetlink_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_REBOOT: + case NETDEV_CHANGEADDR: case NETDEV_CHANGENAME: case NETDEV_FEAT_CHANGE: case NETDEV_BONDING_FAILOVER: case NETDEV_NOTIFY_PEERS: case NETDEV_RESEND_IGMP: case NETDEV_CHANGEINFODATA: - rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); + rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event), + GFP_KERNEL); break; default: break; @@ -4192,6 +4271,7 @@ static int __net_init rtnetlink_net_init(struct net *net) .input = rtnetlink_rcv, .cb_mutex = &rtnl_mutex, .flags = NL_CFG_F_NONROOT_RECV, + .bind = rtnetlink_bind, }; sk = netlink_kernel_create(net, NETLINK_ROUTE, &cfg); diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index ae35cce3a40d..7232274de334 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -51,7 +51,8 @@ static u32 seq_scale(u32 seq) #endif #if IS_ENABLED(CONFIG_IPV6) -u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr) +u32 secure_tcpv6_ts_off(const struct net *net, + const __be32 *saddr, const __be32 *daddr) { const struct { struct in6_addr saddr; @@ -61,7 +62,7 @@ u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr) .daddr = *(struct in6_addr *)daddr, }; - if (sysctl_tcp_timestamps != 1) + if (net->ipv4.sysctl_tcp_timestamps != 1) return 0; ts_secret_init(); @@ -113,9 +114,9 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET -u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr) +u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr) { - if (sysctl_tcp_timestamps != 1) + if (net->ipv4.sysctl_tcp_timestamps != 1) return 0; ts_secret_init(); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b1be7c01efe2..f990eb8b30a9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -176,7 +176,7 @@ struct sk_buff *__alloc_skb_head(gfp_t gfp_mask, int node) memset(skb, 0, offsetof(struct sk_buff, tail)); skb->head = NULL; skb->truesize = sizeof(struct sk_buff); - atomic_set(&skb->users, 1); + refcount_set(&skb->users, 1); skb->mac_header = (typeof(skb->mac_header))~0U; out: @@ -247,7 +247,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, /* Account for allocated memory : skb + skb->head */ skb->truesize = SKB_TRUESIZE(size); skb->pfmemalloc = pfmemalloc; - atomic_set(&skb->users, 1); + refcount_set(&skb->users, 1); skb->head = data; skb->data = data; skb_reset_tail_pointer(skb); @@ -268,7 +268,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, kmemcheck_annotate_bitfield(&fclones->skb2, flags1); skb->fclone = SKB_FCLONE_ORIG; - atomic_set(&fclones->fclone_ref, 1); + refcount_set(&fclones->fclone_ref, 1); fclones->skb2.fclone = SKB_FCLONE_CLONE; } @@ -314,7 +314,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size) memset(skb, 0, offsetof(struct sk_buff, tail)); skb->truesize = SKB_TRUESIZE(size); - atomic_set(&skb->users, 1); + refcount_set(&skb->users, 1); skb->head = data; skb->data = data; skb_reset_tail_pointer(skb); @@ -629,7 +629,7 @@ static void kfree_skbmem(struct sk_buff *skb) * This test would have no chance to be true for the clone, * while here, branch prediction will be good. */ - if (atomic_read(&fclones->fclone_ref) == 1) + if (refcount_read(&fclones->fclone_ref) == 1) goto fastpath; break; @@ -637,18 +637,16 @@ static void kfree_skbmem(struct sk_buff *skb) fclones = container_of(skb, struct sk_buff_fclones, skb2); break; } - if (!atomic_dec_and_test(&fclones->fclone_ref)) + if (!refcount_dec_and_test(&fclones->fclone_ref)) return; fastpath: kmem_cache_free(skbuff_fclone_cache, fclones); } -static void skb_release_head_state(struct sk_buff *skb) +void skb_release_head_state(struct sk_buff *skb) { skb_dst_drop(skb); -#ifdef CONFIG_XFRM - secpath_put(skb->sp); -#endif + secpath_reset(skb); if (skb->destructor) { WARN_ON(in_irq()); skb->destructor(skb); @@ -694,12 +692,9 @@ EXPORT_SYMBOL(__kfree_skb); */ void kfree_skb(struct sk_buff *skb) { - if (unlikely(!skb)) - return; - if (likely(atomic_read(&skb->users) == 1)) - smp_rmb(); - else if (likely(!atomic_dec_and_test(&skb->users))) + if (!skb_unref(skb)) return; + trace_kfree_skb(skb, __builtin_return_address(0)); __kfree_skb(skb); } @@ -746,17 +741,32 @@ EXPORT_SYMBOL(skb_tx_error); */ void consume_skb(struct sk_buff *skb) { - if (unlikely(!skb)) - return; - if (likely(atomic_read(&skb->users) == 1)) - smp_rmb(); - else if (likely(!atomic_dec_and_test(&skb->users))) + if (!skb_unref(skb)) return; + trace_consume_skb(skb); __kfree_skb(skb); } EXPORT_SYMBOL(consume_skb); +/** + * consume_stateless_skb - free an skbuff, assuming it is stateless + * @skb: buffer to free + * + * Works like consume_skb(), but this variant assumes that all the head + * states have been already dropped. + */ +void consume_stateless_skb(struct sk_buff *skb) +{ + if (!skb_unref(skb)) + return; + + trace_consume_skb(skb); + if (likely(skb->head)) + skb_release_data(skb); + kfree_skbmem(skb); +} + void __kfree_skb_flush(void) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); @@ -807,10 +817,9 @@ void napi_consume_skb(struct sk_buff *skb, int budget) return; } - if (likely(atomic_read(&skb->users) == 1)) - smp_rmb(); - else if (likely(!atomic_dec_and_test(&skb->users))) + if (!skb_unref(skb)) return; + /* if reaching here SKB is ready to free */ trace_consume_skb(skb); @@ -906,7 +915,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) C(head_frag); C(data); C(truesize); - atomic_set(&n->users, 1); + refcount_set(&n->users, 1); atomic_inc(&(skb_shinfo(skb)->dataref)); skb->cloned = 1; @@ -1018,9 +1027,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) return NULL; if (skb->fclone == SKB_FCLONE_ORIG && - atomic_read(&fclones->fclone_ref) == 1) { + refcount_read(&fclones->fclone_ref) == 1) { n = &fclones->skb2; - atomic_set(&fclones->fclone_ref, 2); + refcount_set(&fclones->fclone_ref, 2); } else { if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; @@ -1412,7 +1421,7 @@ EXPORT_SYMBOL(skb_pad); * returned. */ -unsigned char *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len) +void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len) { if (tail != skb) { skb->data_len += len; @@ -1431,9 +1440,9 @@ EXPORT_SYMBOL_GPL(pskb_put); * exceed the total buffer size the kernel will panic. A pointer to the * first byte of the extra data is returned. */ -unsigned char *skb_put(struct sk_buff *skb, unsigned int len) +void *skb_put(struct sk_buff *skb, unsigned int len) { - unsigned char *tmp = skb_tail_pointer(skb); + void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; @@ -1452,7 +1461,7 @@ EXPORT_SYMBOL(skb_put); * start. If this would exceed the total buffer headroom the kernel will * panic. A pointer to the first byte of the extra data is returned. */ -unsigned char *skb_push(struct sk_buff *skb, unsigned int len) +void *skb_push(struct sk_buff *skb, unsigned int len) { skb->data -= len; skb->len += len; @@ -1472,7 +1481,7 @@ EXPORT_SYMBOL(skb_push); * is returned. Once the data has been pulled future pushes will overwrite * the old data. */ -unsigned char *skb_pull(struct sk_buff *skb, unsigned int len) +void *skb_pull(struct sk_buff *skb, unsigned int len) { return skb_pull_inline(skb, len); } @@ -1607,7 +1616,7 @@ EXPORT_SYMBOL(___pskb_trim); * * It is pretty complicated. Luckily, it is called only in exceptional cases. */ -unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta) +void *__pskb_pull_tail(struct sk_buff *skb, int delta) { /* If skb has not enough free space at tail, get new one * plus 128 bytes for future expansions. If we have enough @@ -2243,6 +2252,32 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, } EXPORT_SYMBOL(skb_copy_and_csum_bits); +static __wsum warn_crc32c_csum_update(const void *buff, int len, __wsum sum) +{ + net_warn_ratelimited( + "%s: attempt to compute crc32c without libcrc32c.ko\n", + __func__); + return 0; +} + +static __wsum warn_crc32c_csum_combine(__wsum csum, __wsum csum2, + int offset, int len) +{ + net_warn_ratelimited( + "%s: attempt to compute crc32c without libcrc32c.ko\n", + __func__); + return 0; +} + +static const struct skb_checksum_ops default_crc32c_ops = { + .update = warn_crc32c_csum_update, + .combine = warn_crc32c_csum_combine, +}; + +const struct skb_checksum_ops *crc32c_csum_stub __read_mostly = + &default_crc32c_ops; +EXPORT_SYMBOL(crc32c_csum_stub); + /** * skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy() * @from: source buffer @@ -2620,7 +2655,8 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); - skb_shinfo(skb1)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; + skb_shinfo(skb1)->tx_flags |= skb_shinfo(skb)->tx_flags & + SKBTX_SHARED_FRAG; if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ @@ -2988,7 +3024,7 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, get_page(pfrag->page); skb->truesize += copy; - atomic_add(copy, &sk->sk_wmem_alloc); + refcount_add(copy, &sk->sk_wmem_alloc); skb->len += copy; skb->data_len += copy; offset += copy; @@ -3029,7 +3065,7 @@ EXPORT_SYMBOL_GPL(skb_append_pagefrags); * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ -unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) +void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) { unsigned char *data = skb->data; @@ -3235,8 +3271,8 @@ normal: skb_copy_from_linear_data_offset(head_skb, offset, skb_put(nskb, hsize), hsize); - skb_shinfo(nskb)->tx_flags = skb_shinfo(head_skb)->tx_flags & - SKBTX_SHARED_FRAG; + skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags & + SKBTX_SHARED_FRAG; while (pos < offset + len) { if (i >= nfrags) { @@ -3482,24 +3518,18 @@ void __init skb_init(void) NULL); } -/** - * skb_to_sgvec - Fill a scatter-gather list from a socket buffer - * @skb: Socket buffer containing the buffers to be mapped - * @sg: The scatter-gather list to map into - * @offset: The offset into the buffer's contents to start mapping - * @len: Length of buffer space to be mapped - * - * Fill the specified scatter-gather list with mappings/pointers into a - * region of the buffer space attached to a socket buffer. - */ static int -__skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) +__skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len, + unsigned int recursion_level) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int elt = 0; + if (unlikely(recursion_level >= 24)) + return -EMSGSIZE; + if (copy > 0) { if (copy > len) copy = len; @@ -3518,6 +3548,8 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + if (unlikely(elt && sg_is_last(&sg[elt - 1]))) + return -EMSGSIZE; if (copy > len) copy = len; @@ -3532,16 +3564,22 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) } skb_walk_frags(skb, frag_iter) { - int end; + int end, ret; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { + if (unlikely(elt && sg_is_last(&sg[elt - 1]))) + return -EMSGSIZE; + if (copy > len) copy = len; - elt += __skb_to_sgvec(frag_iter, sg+elt, offset - start, - copy); + ret = __skb_to_sgvec(frag_iter, sg+elt, offset - start, + copy, recursion_level + 1); + if (unlikely(ret < 0)) + return ret; + elt += ret; if ((len -= copy) == 0) return elt; offset += copy; @@ -3552,6 +3590,31 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) return elt; } +/** + * skb_to_sgvec - Fill a scatter-gather list from a socket buffer + * @skb: Socket buffer containing the buffers to be mapped + * @sg: The scatter-gather list to map into + * @offset: The offset into the buffer's contents to start mapping + * @len: Length of buffer space to be mapped + * + * Fill the specified scatter-gather list with mappings/pointers into a + * region of the buffer space attached to a socket buffer. Returns either + * the number of scatterlist items used, or -EMSGSIZE if the contents + * could not fit. + */ +int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) +{ + int nsg = __skb_to_sgvec(skb, sg, offset, len, 0); + + if (nsg <= 0) + return nsg; + + sg_mark_end(&sg[nsg - 1]); + + return nsg; +} +EXPORT_SYMBOL_GPL(skb_to_sgvec); + /* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given * sglist without mark the sg which contain last skb data as the end. * So the caller can mannipulate sg list as will when padding new data after @@ -3574,19 +3637,11 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { - return __skb_to_sgvec(skb, sg, offset, len); + return __skb_to_sgvec(skb, sg, offset, len, 0); } EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark); -int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) -{ - int nsg = __skb_to_sgvec(skb, sg, offset, len); - sg_mark_end(&sg[nsg - 1]); - - return nsg; -} -EXPORT_SYMBOL_GPL(skb_to_sgvec); /** * skb_cow_data - Check that a socket buffer's data buffers are writable @@ -3789,7 +3844,7 @@ struct sk_buff *skb_clone_sk(struct sk_buff *skb) struct sock *sk = skb->sk; struct sk_buff *clone; - if (!sk || !atomic_inc_not_zero(&sk->sk_refcnt)) + if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; clone = skb_clone(skb, GFP_ATOMIC); @@ -3860,7 +3915,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. */ - if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) { + if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) { *skb_hwtstamps(skb) = *hwtstamps; __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false); sock_put(sk); @@ -3878,6 +3933,10 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, if (!sk) return; + if (!hwtstamps && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) && + skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS) + return; + tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY; if (!skb_may_tx_timestamp(sk, tsonly)) return; @@ -3899,7 +3958,8 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, return; if (tsonly) { - skb_shinfo(skb)->tx_flags = skb_shinfo(orig_skb)->tx_flags; + skb_shinfo(skb)->tx_flags |= skb_shinfo(orig_skb)->tx_flags & + SKBTX_ANY_TSTAMP; skb_shinfo(skb)->tskey = skb_shinfo(orig_skb)->tskey; } @@ -3937,7 +3997,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. */ - if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) { + if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) { err = sock_queue_err_skb(sk, skb); sock_put(sk); } @@ -4687,7 +4747,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, gfp_head = gfp_mask; if (gfp_head & __GFP_DIRECT_RECLAIM) - gfp_head |= __GFP_REPEAT; + gfp_head |= __GFP_RETRY_MAYFAIL; *errcode = -ENOBUFS; skb = alloc_skb(header_len, gfp_head); diff --git a/net/core/sock.c b/net/core/sock.c index 727f924b7f91..ac2a404c73eb 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1038,6 +1038,10 @@ set_rcvbuf: #endif case SO_MAX_PACING_RATE: + if (val != ~0U) + cmpxchg(&sk->sk_pacing_status, + SK_PACING_NONE, + SK_PACING_NEEDED); sk->sk_max_pacing_rate = val; sk->sk_pacing_rate = min(sk->sk_pacing_rate, sk->sk_max_pacing_rate); @@ -1074,6 +1078,18 @@ static void cred_to_ucred(struct pid *pid, const struct cred *cred, } } +static int groups_to_user(gid_t __user *dst, const struct group_info *src) +{ + struct user_namespace *user_ns = current_user_ns(); + int i; + + for (i = 0; i < src->ngroups; i++) + if (put_user(from_kgid_munged(user_ns, src->gid[i]), dst + i)) + return -EFAULT; + + return 0; +} + int sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { @@ -1227,6 +1243,27 @@ int sock_getsockopt(struct socket *sock, int level, int optname, goto lenout; } + case SO_PEERGROUPS: + { + int ret, n; + + if (!sk->sk_peer_cred) + return -ENODATA; + + n = sk->sk_peer_cred->group_info->ngroups; + if (len < n * sizeof(gid_t)) { + len = n * sizeof(gid_t); + return put_user(len, optlen) ? -EFAULT : -ERANGE; + } + len = n * sizeof(gid_t); + + ret = groups_to_user((gid_t __user *)optval, + sk->sk_peer_cred->group_info); + if (ret) + return ret; + goto lenout; + } + case SO_PEERNAME: { char address[128]; @@ -1491,7 +1528,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, if (likely(sk->sk_net_refcnt)) get_net(net); sock_net_set(sk, net); - atomic_set(&sk->sk_wmem_alloc, 1); + refcount_set(&sk->sk_wmem_alloc, 1); mem_cgroup_sk_alloc(sk); cgroup_sk_alloc(&sk->sk_cgrp_data); @@ -1515,7 +1552,7 @@ static void __sk_destruct(struct rcu_head *head) sk->sk_destruct(sk); filter = rcu_dereference_check(sk->sk_filter, - atomic_read(&sk->sk_wmem_alloc) == 0); + refcount_read(&sk->sk_wmem_alloc) == 0); if (filter) { sk_filter_uncharge(sk, filter); RCU_INIT_POINTER(sk->sk_filter, NULL); @@ -1565,7 +1602,7 @@ void sk_free(struct sock *sk) * some packets are still in some tx queue. * If not null, sock_wfree() will call __sk_free(sk) later */ - if (atomic_dec_and_test(&sk->sk_wmem_alloc)) + if (refcount_dec_and_test(&sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sk_free); @@ -1622,7 +1659,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) /* * sk_wmem_alloc set to one (see sk_free() and sock_wfree()) */ - atomic_set(&newsk->sk_wmem_alloc, 1); + refcount_set(&newsk->sk_wmem_alloc, 1); atomic_set(&newsk->sk_omem_alloc, 0); sk_init_common(newsk); @@ -1671,7 +1708,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) * (Documentation/RCU/rculist_nulls.txt for details) */ smp_wmb(); - atomic_set(&newsk->sk_refcnt, 2); + refcount_set(&newsk->sk_refcnt, 2); /* * Increment the counter in the same struct proto as the master @@ -1750,7 +1787,7 @@ void sock_wfree(struct sk_buff *skb) * Keep a reference on sk_wmem_alloc, this will be released * after sk_write_space() call */ - atomic_sub(len - 1, &sk->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(len - 1, &sk->sk_wmem_alloc)); sk->sk_write_space(sk); len = 1; } @@ -1758,7 +1795,7 @@ void sock_wfree(struct sk_buff *skb) * if sk_wmem_alloc reaches 0, we must finish what sk_free() * could not do because of in-flight packets */ - if (atomic_sub_and_test(len, &sk->sk_wmem_alloc)) + if (refcount_sub_and_test(len, &sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sock_wfree); @@ -1770,7 +1807,7 @@ void __sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; - if (atomic_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)) + if (refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)) __sk_free(sk); } @@ -1792,7 +1829,7 @@ void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) * is enough to guarantee sk_free() wont free this sock until * all in-flight packets are completed */ - atomic_add(skb->truesize, &sk->sk_wmem_alloc); + refcount_add(skb->truesize, &sk->sk_wmem_alloc); } EXPORT_SYMBOL(skb_set_owner_w); @@ -1814,8 +1851,8 @@ void skb_orphan_partial(struct sk_buff *skb) ) { struct sock *sk = skb->sk; - if (atomic_inc_not_zero(&sk->sk_refcnt)) { - atomic_sub(skb->truesize, &sk->sk_wmem_alloc); + if (refcount_inc_not_zero(&sk->sk_refcnt)) { + WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)); skb->destructor = sock_efree; } } else { @@ -1875,7 +1912,7 @@ EXPORT_SYMBOL(sock_i_ino); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority) { - if (force || atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { + if (force || refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { struct sk_buff *skb = alloc_skb(size, priority); if (skb) { skb_set_owner_w(skb, sk); @@ -1950,7 +1987,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) + if (refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) break; if (sk->sk_shutdown & SEND_SHUTDOWN) break; @@ -2072,6 +2109,26 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg, } EXPORT_SYMBOL(sock_cmsg_send); +static void sk_enter_memory_pressure(struct sock *sk) +{ + if (!sk->sk_prot->enter_memory_pressure) + return; + + sk->sk_prot->enter_memory_pressure(sk); +} + +static void sk_leave_memory_pressure(struct sock *sk) +{ + if (sk->sk_prot->leave_memory_pressure) { + sk->sk_prot->leave_memory_pressure(sk); + } else { + unsigned long *memory_pressure = sk->sk_prot->memory_pressure; + + if (memory_pressure && *memory_pressure) + *memory_pressure = 0; + } +} + /* On 32bit arches, an skb frag is limited to 2^15 */ #define SKB_FRAG_PAGE_ORDER get_order(32768) @@ -2253,7 +2310,7 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) if (sk->sk_type == SOCK_STREAM) { if (sk->sk_wmem_queued < prot->sysctl_wmem[0]) return 1; - } else if (atomic_read(&sk->sk_wmem_alloc) < + } else if (refcount_read(&sk->sk_wmem_alloc) < prot->sysctl_wmem[0]) return 1; } @@ -2520,7 +2577,7 @@ static void sock_def_write_space(struct sock *sk) /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ - if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { + if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, POLLOUT | @@ -2630,7 +2687,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) * (Documentation/RCU/rculist_nulls.txt for details) */ smp_wmb(); - atomic_set(&sk->sk_refcnt, 1); + refcount_set(&sk->sk_refcnt, 1); atomic_set(&sk->sk_drops, 0); } EXPORT_SYMBOL(sock_init_data); @@ -2675,9 +2732,12 @@ EXPORT_SYMBOL(release_sock); * @sk: socket * * This version should be used for very small section, where process wont block - * return false if fast path is taken + * return false if fast path is taken: + * * sk_lock.slock locked, owned = 0, BH disabled - * return true if slow path is taken + * + * return true if slow path is taken: + * * sk_lock.slock unlocked, owned = 1, BH enabled */ bool lock_sock_fast(struct sock *sk) diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 93106120f987..733f523707ac 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -178,10 +178,6 @@ static const struct nla_policy dcbnl_ieee_policy[DCB_ATTR_IEEE_MAX + 1] = { [DCB_ATTR_IEEE_QCN_STATS] = {.len = sizeof(struct ieee_qcn_stats)}, }; -static const struct nla_policy dcbnl_ieee_app[DCB_ATTR_IEEE_APP_MAX + 1] = { - [DCB_ATTR_IEEE_APP] = {.len = sizeof(struct dcb_app)}, -}; - /* DCB number of traffic classes nested attributes. */ static const struct nla_policy dcbnl_featcfg_nest[DCB_FEATCFG_ATTR_MAX + 1] = { [DCB_FEATCFG_ATTR_ALL] = {.type = NLA_FLAG}, @@ -1463,8 +1459,15 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, nla_for_each_nested(attr, ieee[DCB_ATTR_IEEE_APP_TABLE], rem) { struct dcb_app *app_data; + if (nla_type(attr) != DCB_ATTR_IEEE_APP) continue; + + if (nla_len(attr) < sizeof(struct dcb_app)) { + err = -ERANGE; + goto err; + } + app_data = nla_data(attr); if (ops->ieee_setapp) err = ops->ieee_setapp(netdev, app_data); diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index 5e3a7302f774..e1295d5f2c56 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -233,7 +233,7 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len) { struct dccp_sock *dp = dccp_sk(sk); struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - const u32 now = ccid2_time_stamp; + const u32 now = ccid2_jiffies32; struct ccid2_seq *next; /* slow-start after idle periods (RFC 2581, RFC 2861) */ @@ -466,7 +466,7 @@ static void ccid2_new_ack(struct sock *sk, struct ccid2_seq *seqp, * The cleanest solution is to not use the ccid2s_sent field at all * and instead use DCCP timestamps: requires changes in other places. */ - ccid2_rtt_estimator(sk, ccid2_time_stamp - seqp->ccid2s_sent); + ccid2_rtt_estimator(sk, ccid2_jiffies32 - seqp->ccid2s_sent); } static void ccid2_congestion_event(struct sock *sk, struct ccid2_seq *seqp) @@ -478,7 +478,7 @@ static void ccid2_congestion_event(struct sock *sk, struct ccid2_seq *seqp) return; } - hc->tx_last_cong = ccid2_time_stamp; + hc->tx_last_cong = ccid2_jiffies32; hc->tx_cwnd = hc->tx_cwnd / 2 ? : 1U; hc->tx_ssthresh = max(hc->tx_cwnd, 2U); @@ -731,7 +731,7 @@ static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) hc->tx_rto = DCCP_TIMEOUT_INIT; hc->tx_rpdupack = -1; - hc->tx_last_cong = hc->tx_lsndtime = hc->tx_cwnd_stamp = ccid2_time_stamp; + hc->tx_last_cong = hc->tx_lsndtime = hc->tx_cwnd_stamp = ccid2_jiffies32; hc->tx_cwnd_used = 0; setup_timer(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire, (unsigned long)sk); diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h index 18c97543e522..6e50ef2898fb 100644 --- a/net/dccp/ccids/ccid2.h +++ b/net/dccp/ccids/ccid2.h @@ -27,7 +27,7 @@ * CCID-2 timestamping faces the same issues as TCP timestamping. * Hence we reuse/share as much of the code as possible. */ -#define ccid2_time_stamp tcp_time_stamp +#define ccid2_jiffies32 ((u32)jiffies) /* NUMDUPACK parameter from RFC 4341, p. 6 */ #define NUMDUPACK 3 diff --git a/net/dccp/input.c b/net/dccp/input.c index 4a05d7876850..fa6be9750bb4 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -126,7 +126,7 @@ static int dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb) static u16 dccp_reset_code_convert(const u8 code) { - const u16 error_code[] = { + static const u16 error_code[] = { [DCCP_RESET_CODE_CLOSED] = 0, /* normal termination */ [DCCP_RESET_CODE_UNSPECIFIED] = 0, /* nothing known */ [DCCP_RESET_CODE_ABORTED] = ECONNRESET, diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index f75482bdee9a..f85d901f4e3f 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -1033,33 +1033,34 @@ static int __init dccp_v4_init(void) { int err = proto_register(&dccp_v4_prot, 1); - if (err != 0) + if (err) goto out; - err = inet_add_protocol(&dccp_v4_protocol, IPPROTO_DCCP); - if (err != 0) - goto out_proto_unregister; - inet_register_protosw(&dccp_v4_protosw); err = register_pernet_subsys(&dccp_v4_ops); if (err) goto out_destroy_ctl_sock; + + err = inet_add_protocol(&dccp_v4_protocol, IPPROTO_DCCP); + if (err) + goto out_proto_unregister; + out: return err; +out_proto_unregister: + unregister_pernet_subsys(&dccp_v4_ops); out_destroy_ctl_sock: inet_unregister_protosw(&dccp_v4_protosw); - inet_del_protocol(&dccp_v4_protocol, IPPROTO_DCCP); -out_proto_unregister: proto_unregister(&dccp_v4_prot); goto out; } static void __exit dccp_v4_exit(void) { + inet_del_protocol(&dccp_v4_protocol, IPPROTO_DCCP); unregister_pernet_subsys(&dccp_v4_ops); inet_unregister_protosw(&dccp_v4_protosw); - inet_del_protocol(&dccp_v4_protocol, IPPROTO_DCCP); proto_unregister(&dccp_v4_prot); } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 992621172220..c376af5bfdfb 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -353,7 +353,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { - atomic_inc(&skb->users); + refcount_inc(&skb->users); ireq->pktopts = skb; } ireq->ir_iif = sk->sk_bound_dev_if; @@ -1098,33 +1098,33 @@ static int __init dccp_v6_init(void) { int err = proto_register(&dccp_v6_prot, 1); - if (err != 0) + if (err) goto out; - err = inet6_add_protocol(&dccp_v6_protocol, IPPROTO_DCCP); - if (err != 0) - goto out_unregister_proto; - inet6_register_protosw(&dccp_v6_protosw); err = register_pernet_subsys(&dccp_v6_ops); - if (err != 0) + if (err) goto out_destroy_ctl_sock; + + err = inet6_add_protocol(&dccp_v6_protocol, IPPROTO_DCCP); + if (err) + goto out_unregister_proto; + out: return err; - +out_unregister_proto: + unregister_pernet_subsys(&dccp_v6_ops); out_destroy_ctl_sock: - inet6_del_protocol(&dccp_v6_protocol, IPPROTO_DCCP); inet6_unregister_protosw(&dccp_v6_protosw); -out_unregister_proto: proto_unregister(&dccp_v6_prot); goto out; } static void __exit dccp_v6_exit(void) { - unregister_pernet_subsys(&dccp_v6_ops); inet6_del_protocol(&dccp_v6_protocol, IPPROTO_DCCP); + unregister_pernet_subsys(&dccp_v6_ops); inet6_unregister_protosw(&dccp_v6_protosw); proto_unregister(&dccp_v6_prot); } diff --git a/net/dccp/options.c b/net/dccp/options.c index 74d29c56c367..51cdfc3bd8ca 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -484,7 +484,7 @@ int dccp_insert_option_mandatory(struct sk_buff *skb) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len++; - *skb_push(skb, 1) = DCCPO_MANDATORY; + *(u8 *)skb_push(skb, 1) = DCCPO_MANDATORY; return 0; } diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 405483a07efc..73a0399dc7a2 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -447,7 +447,7 @@ static void dn_destruct(struct sock *sk) dst_release(rcu_dereference_check(sk->sk_dst_cache, 1)); } -static int dn_memory_pressure; +static unsigned long dn_memory_pressure; static void dn_enter_memory_pressure(struct sock *sk) { diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 9017a9a73ab5..fa0110b57ca1 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -846,7 +846,7 @@ static void dn_send_endnode_hello(struct net_device *dev, struct dn_ifaddr *ifa) skb->dev = dev; - msg = (struct endnode_hello_message *)skb_put(skb,sizeof(*msg)); + msg = skb_put(skb, sizeof(*msg)); msg->msgflg = 0x0D; memcpy(msg->tiver, dn_eco_version, 3); @@ -867,7 +867,7 @@ static void dn_send_endnode_hello(struct net_device *dev, struct dn_ifaddr *ifa) msg->datalen = 0x02; memset(msg->data, 0xAA, 2); - pktlen = (__le16 *)skb_push(skb,2); + pktlen = skb_push(skb, 2); *pktlen = cpu_to_le16(skb->len - 2); skb_reset_network_header(skb); @@ -959,7 +959,7 @@ static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) skb_trim(skb, (27 + *i2)); - pktlen = (__le16 *)skb_push(skb, 2); + pktlen = skb_push(skb, 2); *pktlen = cpu_to_le16(skb->len - 2); skb_reset_network_header(skb); diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index f9058ebeb635..f9f6fb3f3c5b 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -389,7 +389,7 @@ link_it: } fi->fib_treeref++; - atomic_inc(&fi->fib_clntref); + refcount_set(&fi->fib_clntref, 1); spin_lock(&dn_fib_info_lock); fi->fib_next = dn_fib_info_list; fi->fib_prev = NULL; @@ -425,7 +425,7 @@ int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowidn switch (type) { case RTN_NAT: DN_FIB_RES_RESET(*res); - atomic_inc(&fi->fib_clntref); + refcount_inc(&fi->fib_clntref); return 0; case RTN_UNICAST: case RTN_LOCAL: @@ -438,7 +438,7 @@ int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowidn } if (nhsel < fi->fib_nhs) { res->nh_sel = nhsel; - atomic_inc(&fi->fib_clntref); + refcount_inc(&fi->fib_clntref); return 0; } endfor_nexthops(fi); diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index eeb5fc561f80..21dedf6fd0f7 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -559,7 +559,7 @@ static inline void dn_neigh_format_entry(struct seq_file *seq, (dn->flags&DN_NDFLAG_R2) ? "2" : "-", (dn->flags&DN_NDFLAG_P3) ? "3" : "-", dn->n.nud_state, - atomic_read(&dn->n.refcnt), + refcount_read(&dn->n.refcnt), dn->blksize, (dn->n.dev) ? dn->n.dev->name : "?"); read_unlock(&n->lock); diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index 849805e7af52..66f035e476ea 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -484,7 +484,7 @@ void dn_send_conn_ack (struct sock *sk) if ((skb = dn_alloc_skb(sk, 3, sk->sk_allocation)) == NULL) return; - msg = (struct nsp_conn_ack_msg *)skb_put(skb, 3); + msg = skb_put(skb, 3); msg->msgflg = 0x24; msg->dstaddr = scp->addrrem; @@ -522,7 +522,7 @@ void dn_send_conn_conf(struct sock *sk, gfp_t gfp) if ((skb = dn_alloc_skb(sk, 50 + len, gfp)) == NULL) return; - msg = (struct nsp_conn_init_msg *)skb_put(skb, sizeof(*msg)); + msg = skb_put(skb, sizeof(*msg)); msg->msgflg = 0x28; msg->dstaddr = scp->addrrem; msg->srcaddr = scp->addrloc; @@ -530,10 +530,10 @@ void dn_send_conn_conf(struct sock *sk, gfp_t gfp) msg->info = scp->info_loc; msg->segsize = cpu_to_le16(scp->segsize_loc); - *skb_put(skb,1) = len; + skb_put_u8(skb, len); if (len > 0) - memcpy(skb_put(skb, len), scp->conndata_out.opt_data, len); + skb_put_data(skb, scp->conndata_out.opt_data, len); dn_nsp_send(skb); @@ -662,7 +662,7 @@ void dn_nsp_send_conninit(struct sock *sk, unsigned char msgflg) return; cb = DN_SKB_CB(skb); - msg = (struct nsp_conn_init_msg *)skb_put(skb,sizeof(*msg)); + msg = skb_put(skb, sizeof(*msg)); msg->msgflg = msgflg; msg->dstaddr = 0x0000; /* Remote Node will assign it*/ @@ -686,27 +686,27 @@ void dn_nsp_send_conninit(struct sock *sk, unsigned char msgflg) if (scp->peer.sdn_flags & SDF_UICPROXY) menuver |= DN_MENUVER_UIC; - *skb_put(skb, 1) = menuver; /* Menu Version */ + skb_put_u8(skb, menuver); /* Menu Version */ aux = scp->accessdata.acc_userl; - *skb_put(skb, 1) = aux; + skb_put_u8(skb, aux); if (aux > 0) - memcpy(skb_put(skb, aux), scp->accessdata.acc_user, aux); + skb_put_data(skb, scp->accessdata.acc_user, aux); aux = scp->accessdata.acc_passl; - *skb_put(skb, 1) = aux; + skb_put_u8(skb, aux); if (aux > 0) - memcpy(skb_put(skb, aux), scp->accessdata.acc_pass, aux); + skb_put_data(skb, scp->accessdata.acc_pass, aux); aux = scp->accessdata.acc_accl; - *skb_put(skb, 1) = aux; + skb_put_u8(skb, aux); if (aux > 0) - memcpy(skb_put(skb, aux), scp->accessdata.acc_acc, aux); + skb_put_data(skb, scp->accessdata.acc_acc, aux); aux = (__u8)le16_to_cpu(scp->conndata_out.opt_optl); - *skb_put(skb, 1) = aux; + skb_put_u8(skb, aux); if (aux > 0) - memcpy(skb_put(skb, aux), scp->conndata_out.opt_data, aux); + skb_put_data(skb, scp->conndata_out.opt_data, aux); scp->persist = dn_nsp_persist(sk); scp->persist_fxn = dn_nsp_retrans_conninit; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 6f95612b4d32..bcbe548f8854 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -183,11 +183,6 @@ static __inline__ unsigned int dn_hash(__le16 src, __le16 dst) return dn_rt_hash_mask & (unsigned int)tmp; } -static inline void dnrt_free(struct dn_route *rt) -{ - call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free); -} - static void dn_dst_check_expire(unsigned long dummy) { int i; @@ -202,14 +197,15 @@ static void dn_dst_check_expire(unsigned long dummy) spin_lock(&dn_rt_hash_table[i].lock); while ((rt = rcu_dereference_protected(*rtp, lockdep_is_held(&dn_rt_hash_table[i].lock))) != NULL) { - if (atomic_read(&rt->dst.__refcnt) || - (now - rt->dst.lastuse) < expire) { + if (atomic_read(&rt->dst.__refcnt) > 1 || + (now - rt->dst.lastuse) < expire) { rtp = &rt->dst.dn_next; continue; } *rtp = rt->dst.dn_next; rt->dst.dn_next = NULL; - dnrt_free(rt); + dst_dev_put(&rt->dst); + dst_release(&rt->dst); } spin_unlock(&dn_rt_hash_table[i].lock); @@ -235,14 +231,15 @@ static int dn_dst_gc(struct dst_ops *ops) while ((rt = rcu_dereference_protected(*rtp, lockdep_is_held(&dn_rt_hash_table[i].lock))) != NULL) { - if (atomic_read(&rt->dst.__refcnt) || - (now - rt->dst.lastuse) < expire) { + if (atomic_read(&rt->dst.__refcnt) > 1 || + (now - rt->dst.lastuse) < expire) { rtp = &rt->dst.dn_next; continue; } *rtp = rt->dst.dn_next; rt->dst.dn_next = NULL; - dnrt_free(rt); + dst_dev_put(&rt->dst); + dst_release(&rt->dst); break; } spin_unlock_bh(&dn_rt_hash_table[i].lock); @@ -344,7 +341,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou dst_use(&rth->dst, now); spin_unlock_bh(&dn_rt_hash_table[hash].lock); - dst_free(&rt->dst); + dst_release_immediate(&rt->dst); *rp = rth; return 0; } @@ -374,7 +371,8 @@ static void dn_run_flush(unsigned long dummy) for(; rt; rt = next) { next = rcu_dereference_raw(rt->dst.dn_next); RCU_INIT_POINTER(rt->dst.dn_next, NULL); - dnrt_free(rt); + dst_dev_put(&rt->dst); + dst_release(&rt->dst); } nothing_to_declare: @@ -1215,6 +1213,7 @@ make_route: goto e_neighbour; hash = dn_hash(rt->fld.saddr, rt->fld.daddr); + /* dn_insert_route() increments dst->__refcnt */ dn_insert_route(rt, hash, (struct dn_route **)pprt); done: @@ -1237,7 +1236,7 @@ e_nobufs: err = -ENOBUFS; goto done; e_neighbour: - dst_free(&rt->dst); + dst_release_immediate(&rt->dst); goto e_nobufs; } @@ -1445,7 +1444,7 @@ static int dn_route_input_slow(struct sk_buff *skb) } make_route: - rt = dst_alloc(&dn_dst_ops, out_dev, 0, DST_OBSOLETE_NONE, DST_HOST); + rt = dst_alloc(&dn_dst_ops, out_dev, 1, DST_OBSOLETE_NONE, DST_HOST); if (rt == NULL) goto e_nobufs; @@ -1491,6 +1490,7 @@ make_route: goto e_neighbour; hash = dn_hash(rt->fld.saddr, rt->fld.daddr); + /* dn_insert_route() increments dst->__refcnt */ dn_insert_route(rt, hash, &rt); skb_dst_set(skb, &rt->dst); @@ -1514,7 +1514,7 @@ e_nobufs: goto done; e_neighbour: - dst_free(&rt->dst); + dst_release_immediate(&rt->dst); goto done; } diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 81a0868edb1d..cc5f8f971689 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -25,16 +25,19 @@ config NET_DSA_TAG_DSA config NET_DSA_TAG_EDSA bool -config NET_DSA_TAG_TRAILER +config NET_DSA_TAG_KSZ bool -config NET_DSA_TAG_QCA +config NET_DSA_TAG_LAN9303 bool config NET_DSA_TAG_MTK bool -config NET_DSA_TAG_LAN9303 +config NET_DSA_TAG_TRAILER + bool + +config NET_DSA_TAG_QCA bool endif diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 0b747d75e65a..fcce25da937c 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -1,12 +1,13 @@ # the core obj-$(CONFIG_NET_DSA) += dsa_core.o -dsa_core-y += dsa.o slave.o dsa2.o switch.o legacy.o +dsa_core-y += dsa.o dsa2.o legacy.o port.o slave.o switch.o # tagging formats dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o -dsa_core-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o -dsa_core-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o -dsa_core-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o +dsa_core-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o dsa_core-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o +dsa_core-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o +dsa_core-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o +dsa_core-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 90038d45a547..416ac4ef9ba9 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -24,7 +24,7 @@ #include <linux/phy_fixed.h> #include <linux/gpio/consumer.h> #include <linux/etherdevice.h> -#include <net/dsa.h> + #include "dsa_priv.h" static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb, @@ -40,26 +40,29 @@ static const struct dsa_device_ops none_ops = { }; const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { +#ifdef CONFIG_NET_DSA_TAG_BRCM + [DSA_TAG_PROTO_BRCM] = &brcm_netdev_ops, +#endif #ifdef CONFIG_NET_DSA_TAG_DSA [DSA_TAG_PROTO_DSA] = &dsa_netdev_ops, #endif #ifdef CONFIG_NET_DSA_TAG_EDSA [DSA_TAG_PROTO_EDSA] = &edsa_netdev_ops, #endif -#ifdef CONFIG_NET_DSA_TAG_TRAILER - [DSA_TAG_PROTO_TRAILER] = &trailer_netdev_ops, -#endif -#ifdef CONFIG_NET_DSA_TAG_BRCM - [DSA_TAG_PROTO_BRCM] = &brcm_netdev_ops, +#ifdef CONFIG_NET_DSA_TAG_KSZ + [DSA_TAG_PROTO_KSZ] = &ksz_netdev_ops, #endif -#ifdef CONFIG_NET_DSA_TAG_QCA - [DSA_TAG_PROTO_QCA] = &qca_netdev_ops, +#ifdef CONFIG_NET_DSA_TAG_LAN9303 + [DSA_TAG_PROTO_LAN9303] = &lan9303_netdev_ops, #endif #ifdef CONFIG_NET_DSA_TAG_MTK [DSA_TAG_PROTO_MTK] = &mtk_netdev_ops, #endif -#ifdef CONFIG_NET_DSA_TAG_LAN9303 - [DSA_TAG_PROTO_LAN9303] = &lan9303_netdev_ops, +#ifdef CONFIG_NET_DSA_TAG_QCA + [DSA_TAG_PROTO_QCA] = &qca_netdev_ops, +#endif +#ifdef CONFIG_NET_DSA_TAG_TRAILER + [DSA_TAG_PROTO_TRAILER] = &trailer_netdev_ops, #endif [DSA_TAG_PROTO_NONE] = &none_ops, }; @@ -109,23 +112,22 @@ const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol) return ops; } -int dsa_cpu_port_ethtool_setup(struct dsa_switch *ds) +int dsa_cpu_port_ethtool_setup(struct dsa_port *cpu_dp) { + struct dsa_switch *ds = cpu_dp->ds; struct net_device *master; struct ethtool_ops *cpu_ops; - master = ds->dst->master_netdev; - if (ds->master_netdev) - master = ds->master_netdev; + master = cpu_dp->netdev; cpu_ops = devm_kzalloc(ds->dev, sizeof(*cpu_ops), GFP_KERNEL); if (!cpu_ops) return -ENOMEM; - memcpy(&ds->dst->master_ethtool_ops, master->ethtool_ops, + memcpy(&cpu_dp->ethtool_ops, master->ethtool_ops, sizeof(struct ethtool_ops)); - ds->dst->master_orig_ethtool_ops = master->ethtool_ops; - memcpy(cpu_ops, &ds->dst->master_ethtool_ops, + cpu_dp->orig_ethtool_ops = master->ethtool_ops; + memcpy(cpu_ops, &cpu_dp->ethtool_ops, sizeof(struct ethtool_ops)); dsa_cpu_port_ethtool_init(cpu_ops); master->ethtool_ops = cpu_ops; @@ -133,15 +135,9 @@ int dsa_cpu_port_ethtool_setup(struct dsa_switch *ds) return 0; } -void dsa_cpu_port_ethtool_restore(struct dsa_switch *ds) +void dsa_cpu_port_ethtool_restore(struct dsa_port *cpu_dp) { - struct net_device *master; - - master = ds->dst->master_netdev; - if (ds->master_netdev) - master = ds->master_netdev; - - master->ethtool_ops = ds->dst->master_orig_ethtool_ops; + cpu_dp->netdev->ethtool_ops = cpu_dp->orig_ethtool_ops; } void dsa_cpu_dsa_destroy(struct dsa_port *port) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 7796580e99ee..56e46090526b 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -18,7 +18,7 @@ #include <linux/rtnetlink.h> #include <linux/of.h> #include <linux/of_net.h> -#include <net/dsa.h> + #include "dsa_priv.h" static LIST_HEAD(dsa_switch_trees); @@ -214,66 +214,59 @@ static int dsa_dst_complete(struct dsa_switch_tree *dst) return 0; } -static int dsa_dsa_port_apply(struct dsa_port *port, u32 index, - struct dsa_switch *ds) +static int dsa_dsa_port_apply(struct dsa_port *port) { + struct dsa_switch *ds = port->ds; int err; - err = dsa_cpu_dsa_setup(ds, ds->dev, port, index); + err = dsa_cpu_dsa_setup(ds, ds->dev, port, port->index); if (err) { dev_warn(ds->dev, "Failed to setup dsa port %d: %d\n", - index, err); + port->index, err); return err; } - memset(&ds->ports[index].devlink_port, 0, - sizeof(ds->ports[index].devlink_port)); + memset(&port->devlink_port, 0, sizeof(port->devlink_port)); - return devlink_port_register(ds->devlink, - &ds->ports[index].devlink_port, - index); + return devlink_port_register(ds->devlink, &port->devlink_port, + port->index); } -static void dsa_dsa_port_unapply(struct dsa_port *port, u32 index, - struct dsa_switch *ds) +static void dsa_dsa_port_unapply(struct dsa_port *port) { - devlink_port_unregister(&ds->ports[index].devlink_port); + devlink_port_unregister(&port->devlink_port); dsa_cpu_dsa_destroy(port); } -static int dsa_cpu_port_apply(struct dsa_port *port, u32 index, - struct dsa_switch *ds) +static int dsa_cpu_port_apply(struct dsa_port *port) { + struct dsa_switch *ds = port->ds; int err; - err = dsa_cpu_dsa_setup(ds, ds->dev, port, index); + err = dsa_cpu_dsa_setup(ds, ds->dev, port, port->index); if (err) { dev_warn(ds->dev, "Failed to setup cpu port %d: %d\n", - index, err); + port->index, err); return err; } - ds->cpu_port_mask |= BIT(index); - - memset(&ds->ports[index].devlink_port, 0, - sizeof(ds->ports[index].devlink_port)); - err = devlink_port_register(ds->devlink, &ds->ports[index].devlink_port, - index); + memset(&port->devlink_port, 0, sizeof(port->devlink_port)); + err = devlink_port_register(ds->devlink, &port->devlink_port, + port->index); return err; } -static void dsa_cpu_port_unapply(struct dsa_port *port, u32 index, - struct dsa_switch *ds) +static void dsa_cpu_port_unapply(struct dsa_port *port) { - devlink_port_unregister(&ds->ports[index].devlink_port); + devlink_port_unregister(&port->devlink_port); dsa_cpu_dsa_destroy(port); - ds->cpu_port_mask &= ~BIT(index); + port->ds->cpu_port_mask &= ~BIT(port->index); } -static int dsa_user_port_apply(struct dsa_port *port, u32 index, - struct dsa_switch *ds) +static int dsa_user_port_apply(struct dsa_port *port) { + struct dsa_switch *ds = port->ds; const char *name = port->name; int err; @@ -282,35 +275,32 @@ static int dsa_user_port_apply(struct dsa_port *port, u32 index, if (!name) name = "eth%d"; - err = dsa_slave_create(ds, ds->dev, index, name); + err = dsa_slave_create(ds, ds->dev, port->index, name); if (err) { dev_warn(ds->dev, "Failed to create slave %d: %d\n", - index, err); - ds->ports[index].netdev = NULL; + port->index, err); + port->netdev = NULL; return err; } - memset(&ds->ports[index].devlink_port, 0, - sizeof(ds->ports[index].devlink_port)); - err = devlink_port_register(ds->devlink, &ds->ports[index].devlink_port, - index); + memset(&port->devlink_port, 0, sizeof(port->devlink_port)); + err = devlink_port_register(ds->devlink, &port->devlink_port, + port->index); if (err) return err; - devlink_port_type_eth_set(&ds->ports[index].devlink_port, - ds->ports[index].netdev); + devlink_port_type_eth_set(&port->devlink_port, port->netdev); return 0; } -static void dsa_user_port_unapply(struct dsa_port *port, u32 index, - struct dsa_switch *ds) +static void dsa_user_port_unapply(struct dsa_port *port) { - devlink_port_unregister(&ds->ports[index].devlink_port); - if (ds->ports[index].netdev) { - dsa_slave_destroy(ds->ports[index].netdev); - ds->ports[index].netdev = NULL; - ds->enabled_port_mask &= ~(1 << index); + devlink_port_unregister(&port->devlink_port); + if (port->netdev) { + dsa_slave_destroy(port->netdev); + port->netdev = NULL; + port->ds->enabled_port_mask &= ~(1 << port->index); } } @@ -347,7 +337,7 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds) return err; if (ds->ops->set_addr) { - err = ds->ops->set_addr(ds, dst->master_netdev->dev_addr); + err = ds->ops->set_addr(ds, dst->cpu_dp->netdev->dev_addr); if (err < 0) return err; } @@ -370,20 +360,20 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds) continue; if (dsa_port_is_dsa(port)) { - err = dsa_dsa_port_apply(port, index, ds); + err = dsa_dsa_port_apply(port); if (err) return err; continue; } if (dsa_port_is_cpu(port)) { - err = dsa_cpu_port_apply(port, index, ds); + err = dsa_cpu_port_apply(port); if (err) return err; continue; } - err = dsa_user_port_apply(port, index, ds); + err = dsa_user_port_apply(port); if (err) continue; } @@ -402,16 +392,16 @@ static void dsa_ds_unapply(struct dsa_switch_tree *dst, struct dsa_switch *ds) continue; if (dsa_port_is_dsa(port)) { - dsa_dsa_port_unapply(port, index, ds); + dsa_dsa_port_unapply(port); continue; } if (dsa_port_is_cpu(port)) { - dsa_cpu_port_unapply(port, index, ds); + dsa_cpu_port_unapply(port); continue; } - dsa_user_port_unapply(port, index, ds); + dsa_user_port_unapply(port); } if (ds->slave_mii_bus && ds->ops->phy_read) @@ -443,8 +433,8 @@ static int dsa_dst_apply(struct dsa_switch_tree *dst) return err; } - if (dst->cpu_switch) { - err = dsa_cpu_port_ethtool_setup(dst->cpu_switch); + if (dst->cpu_dp) { + err = dsa_cpu_port_ethtool_setup(dst->cpu_dp); if (err) return err; } @@ -454,7 +444,7 @@ static int dsa_dst_apply(struct dsa_switch_tree *dst) * sent to the tag format's receive function. */ wmb(); - dst->master_netdev->dsa_ptr = (void *)dst; + dst->cpu_dp->netdev->dsa_ptr = dst; dst->applied = true; return 0; @@ -468,7 +458,7 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst) if (!dst->applied) return; - dst->master_netdev->dsa_ptr = NULL; + dst->cpu_dp->netdev->dsa_ptr = NULL; /* If we used a tagging format that doesn't have an ethertype * field, make sure that all packets from this point get sent @@ -484,9 +474,9 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst) dsa_ds_unapply(dst, ds); } - if (dst->cpu_switch) { - dsa_cpu_port_ethtool_restore(dst->cpu_switch); - dst->cpu_switch = NULL; + if (dst->cpu_dp) { + dsa_cpu_port_ethtool_restore(dst->cpu_dp); + dst->cpu_dp = NULL; } pr_info("DSA: tree %d unapplied\n", dst->tree); @@ -514,15 +504,9 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, if (!ethernet_dev) return -EPROBE_DEFER; - if (!ds->master_netdev) - ds->master_netdev = ethernet_dev; - - if (!dst->master_netdev) - dst->master_netdev = ethernet_dev; - - if (!dst->cpu_switch) { - dst->cpu_switch = ds; - dst->cpu_port = index; + if (!dst->cpu_dp) { + dst->cpu_dp = port; + dst->cpu_dp->netdev = ethernet_dev; } tag_protocol = ds->ops->get_tag_protocol(ds); @@ -534,6 +518,12 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, dst->rcv = dst->tag_ops->rcv; + /* Initialize cpu_port_mask now for drv->setup() + * to have access to a correct value, just like what + * net/dsa/dsa.c::dsa_switch_setup_one does. + */ + ds->cpu_port_mask |= BIT(index); + return 0; } @@ -545,14 +535,22 @@ static int dsa_ds_parse(struct dsa_switch_tree *dst, struct dsa_switch *ds) for (index = 0; index < ds->num_ports; index++) { port = &ds->ports[index]; - if (!dsa_port_is_valid(port)) + if (!dsa_port_is_valid(port) || + dsa_port_is_dsa(port)) continue; if (dsa_port_is_cpu(port)) { err = dsa_cpu_parse(port, index, dst, ds); if (err) return err; + } else { + /* Initialize enabled_port_mask now for drv->setup() + * to have access to a correct value, just like what + * net/dsa/dsa.c::dsa_switch_setup_one does. + */ + ds->enabled_port_mask |= BIT(index); } + } pr_info("DSA: switch %d %d parsed\n", dst->tree, ds->index); @@ -563,7 +561,9 @@ static int dsa_ds_parse(struct dsa_switch_tree *dst, struct dsa_switch *ds) static int dsa_dst_parse(struct dsa_switch_tree *dst) { struct dsa_switch *ds; + struct dsa_port *dp; u32 index; + int port; int err; for (index = 0; index < DSA_MAX_SWITCHES; index++) { @@ -576,11 +576,28 @@ static int dsa_dst_parse(struct dsa_switch_tree *dst) return err; } - if (!dst->master_netdev) { + if (!dst->cpu_dp->netdev) { pr_warn("Tree has no master device\n"); return -EINVAL; } + /* Assign the default CPU port to all ports of the fabric */ + for (index = 0; index < DSA_MAX_SWITCHES; index++) { + ds = dst->ds[index]; + if (!ds) + continue; + + for (port = 0; port < ds->num_ports; port++) { + dp = &ds->ports[port]; + if (!dsa_port_is_valid(dp) || + dsa_port_is_dsa(dp) || + dsa_port_is_cpu(dp)) + continue; + + dp->cpu_dp = dst->cpu_dp; + } + } + pr_info("DSA: tree %d parsed\n", dst->tree); return 0; @@ -601,13 +618,6 @@ static int dsa_parse_ports_dn(struct device_node *ports, struct dsa_switch *ds) return -EINVAL; ds->ports[reg].dn = port; - - /* Initialize enabled_port_mask now for ops->setup() - * to have access to a correct value, just like what - * net/dsa/dsa.c::dsa_switch_setup_one does. - */ - if (!dsa_port_is_cpu(&ds->ports[reg])) - ds->enabled_port_mask |= 1 << reg; } return 0; @@ -623,14 +633,6 @@ static int dsa_parse_ports(struct dsa_chip_data *cd, struct dsa_switch *ds) continue; ds->ports[i].name = cd->port_names[i]; - - /* Initialize enabled_port_mask now for drv->setup() - * to have access to a correct value, just like what - * net/dsa/dsa.c::dsa_switch_setup_one does. - */ - if (!dsa_port_is_cpu(&ds->ports[i])) - ds->enabled_port_mask |= 1 << i; - valid_name_found = true; } @@ -690,10 +692,10 @@ static struct device_node *dsa_get_ports(struct dsa_switch *ds, return ports; } -static int _dsa_register_switch(struct dsa_switch *ds, struct device *dev) +static int _dsa_register_switch(struct dsa_switch *ds) { - struct dsa_chip_data *pdata = dev->platform_data; - struct device_node *np = dev->of_node; + struct dsa_chip_data *pdata = ds->dev->platform_data; + struct device_node *np = ds->dev->of_node; struct dsa_switch_tree *dst; struct device_node *ports; u32 tree, index; @@ -807,12 +809,12 @@ struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n) } EXPORT_SYMBOL_GPL(dsa_switch_alloc); -int dsa_register_switch(struct dsa_switch *ds, struct device *dev) +int dsa_register_switch(struct dsa_switch *ds) { int err; mutex_lock(&dsa2_mutex); - err = _dsa_register_switch(ds, dev); + err = _dsa_register_switch(ds); mutex_unlock(&dsa2_mutex); return err; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index f4a88e485213..55982cc39b24 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -14,6 +14,56 @@ #include <linux/phy.h> #include <linux/netdevice.h> #include <linux/netpoll.h> +#include <net/dsa.h> + +enum { + DSA_NOTIFIER_AGEING_TIME, + DSA_NOTIFIER_BRIDGE_JOIN, + DSA_NOTIFIER_BRIDGE_LEAVE, + DSA_NOTIFIER_FDB_ADD, + DSA_NOTIFIER_FDB_DEL, + DSA_NOTIFIER_MDB_ADD, + DSA_NOTIFIER_MDB_DEL, + DSA_NOTIFIER_VLAN_ADD, + DSA_NOTIFIER_VLAN_DEL, +}; + +/* DSA_NOTIFIER_AGEING_TIME */ +struct dsa_notifier_ageing_time_info { + struct switchdev_trans *trans; + unsigned int ageing_time; +}; + +/* DSA_NOTIFIER_BRIDGE_* */ +struct dsa_notifier_bridge_info { + struct net_device *br; + int sw_index; + int port; +}; + +/* DSA_NOTIFIER_FDB_* */ +struct dsa_notifier_fdb_info { + const struct switchdev_obj_port_fdb *fdb; + struct switchdev_trans *trans; + int sw_index; + int port; +}; + +/* DSA_NOTIFIER_MDB_* */ +struct dsa_notifier_mdb_info { + const struct switchdev_obj_port_mdb *mdb; + struct switchdev_trans *trans; + int sw_index; + int port; +}; + +/* DSA_NOTIFIER_VLAN_* */ +struct dsa_notifier_vlan_info { + const struct switchdev_obj_port_vlan *vlan; + struct switchdev_trans *trans; + int sw_index; + int port; +}; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); @@ -23,6 +73,7 @@ struct dsa_device_ops { }; struct dsa_slave_priv { + /* Copy of dp->ds->dst->tag_ops->xmit for faster access in hot path */ struct sk_buff * (*xmit)(struct sk_buff *skb, struct net_device *dev); @@ -52,13 +103,46 @@ int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev, struct dsa_port *dport, int port); void dsa_cpu_dsa_destroy(struct dsa_port *dport); const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol); -int dsa_cpu_port_ethtool_setup(struct dsa_switch *ds); -void dsa_cpu_port_ethtool_restore(struct dsa_switch *ds); +int dsa_cpu_port_ethtool_setup(struct dsa_port *cpu_dp); +void dsa_cpu_port_ethtool_restore(struct dsa_port *cpu_dp); /* legacy.c */ int dsa_legacy_register(void); void dsa_legacy_unregister(void); +/* port.c */ +int dsa_port_set_state(struct dsa_port *dp, u8 state, + struct switchdev_trans *trans); +void dsa_port_set_state_now(struct dsa_port *dp, u8 state); +int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br); +void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br); +int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, + struct switchdev_trans *trans); +int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock, + struct switchdev_trans *trans); +int dsa_port_fdb_add(struct dsa_port *dp, + const struct switchdev_obj_port_fdb *fdb, + struct switchdev_trans *trans); +int dsa_port_fdb_del(struct dsa_port *dp, + const struct switchdev_obj_port_fdb *fdb); +int dsa_port_fdb_dump(struct dsa_port *dp, struct switchdev_obj_port_fdb *fdb, + switchdev_obj_dump_cb_t *cb); +int dsa_port_mdb_add(struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb, + struct switchdev_trans *trans); +int dsa_port_mdb_del(struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); +int dsa_port_mdb_dump(struct dsa_port *dp, struct switchdev_obj_port_mdb *mdb, + switchdev_obj_dump_cb_t *cb); +int dsa_port_vlan_add(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, + struct switchdev_trans *trans); +int dsa_port_vlan_del(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan); +int dsa_port_vlan_dump(struct dsa_port *dp, + struct switchdev_obj_port_vlan *vlan, + switchdev_obj_dump_cb_t *cb); + /* slave.c */ extern const struct dsa_device_ops notag_netdev_ops; void dsa_slave_mii_bus_init(struct dsa_switch *ds); @@ -75,25 +159,38 @@ void dsa_slave_unregister_notifier(void); int dsa_switch_register_notifier(struct dsa_switch *ds); void dsa_switch_unregister_notifier(struct dsa_switch *ds); +/* tag_brcm.c */ +extern const struct dsa_device_ops brcm_netdev_ops; + /* tag_dsa.c */ extern const struct dsa_device_ops dsa_netdev_ops; /* tag_edsa.c */ extern const struct dsa_device_ops edsa_netdev_ops; -/* tag_trailer.c */ -extern const struct dsa_device_ops trailer_netdev_ops; +/* tag_ksz.c */ +extern const struct dsa_device_ops ksz_netdev_ops; -/* tag_brcm.c */ -extern const struct dsa_device_ops brcm_netdev_ops; +/* tag_lan9303.c */ +extern const struct dsa_device_ops lan9303_netdev_ops; + +/* tag_mtk.c */ +extern const struct dsa_device_ops mtk_netdev_ops; /* tag_qca.c */ extern const struct dsa_device_ops qca_netdev_ops; -/* tag_mtk.c */ -extern const struct dsa_device_ops mtk_netdev_ops; +/* tag_trailer.c */ +extern const struct dsa_device_ops trailer_netdev_ops; -/* tag_lan9303.c */ -extern const struct dsa_device_ops lan9303_netdev_ops; +static inline struct net_device *dsa_master_netdev(struct dsa_slave_priv *p) +{ + return p->dp->cpu_dp->netdev; +} + +static inline struct dsa_port *dsa_get_cpu_port(struct dsa_switch_tree *dst) +{ + return dst->cpu_dp; +} #endif diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 7281098df04e..1d7a3282f2a7 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -22,7 +22,7 @@ #include <linux/sysfs.h> #include <linux/phy_fixed.h> #include <linux/etherdevice.h> -#include <net/dsa.h> + #include "dsa_priv.h" /* switch driver registration ***********************************************/ @@ -95,7 +95,8 @@ static int dsa_cpu_dsa_setups(struct dsa_switch *ds, struct device *dev) return 0; } -static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) +static int dsa_switch_setup_one(struct dsa_switch *ds, struct net_device *master, + struct device *parent) { const struct dsa_switch_ops *ops = ds->ops; struct dsa_switch_tree *dst = ds->dst; @@ -115,13 +116,13 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) continue; if (!strcmp(name, "cpu")) { - if (dst->cpu_switch) { - netdev_err(dst->master_netdev, + if (dst->cpu_dp) { + netdev_err(master, "multiple cpu ports?!\n"); return -EINVAL; } - dst->cpu_switch = ds; - dst->cpu_port = i; + dst->cpu_dp = &ds->ports[i]; + dst->cpu_dp->netdev = master; ds->cpu_port_mask |= 1 << i; } else if (!strcmp(name, "dsa")) { ds->dsa_port_mask |= 1 << i; @@ -144,7 +145,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) * tagging protocol to the preferred tagging format of this * switch. */ - if (dst->cpu_switch == ds) { + if (dst->cpu_dp->ds == ds) { enum dsa_tag_protocol tag_protocol; tag_protocol = ops->get_tag_protocol(ds); @@ -169,7 +170,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) return ret; if (ops->set_addr) { - ret = ops->set_addr(ds, dst->master_netdev->dev_addr); + ret = ops->set_addr(ds, master->dev_addr); if (ret < 0) return ret; } @@ -190,23 +191,24 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) */ for (i = 0; i < ds->num_ports; i++) { ds->ports[i].dn = cd->port_dn[i]; + ds->ports[i].cpu_dp = dst->cpu_dp; if (!(ds->enabled_port_mask & (1 << i))) continue; ret = dsa_slave_create(ds, parent, i, cd->port_names[i]); if (ret < 0) - netdev_err(dst->master_netdev, "[%d]: can't create dsa slave device for port %d(%s): %d\n", + netdev_err(master, "[%d]: can't create dsa slave device for port %d(%s): %d\n", index, i, cd->port_names[i], ret); } /* Perform configuration of the CPU and DSA ports */ ret = dsa_cpu_dsa_setups(ds, parent); if (ret < 0) - netdev_err(dst->master_netdev, "[%d] : can't configure CPU and DSA ports\n", + netdev_err(master, "[%d] : can't configure CPU and DSA ports\n", index); - ret = dsa_cpu_port_ethtool_setup(ds); + ret = dsa_cpu_port_ethtool_setup(ds->dst->cpu_dp); if (ret) return ret; @@ -214,8 +216,8 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) } static struct dsa_switch * -dsa_switch_setup(struct dsa_switch_tree *dst, int index, - struct device *parent, struct device *host_dev) +dsa_switch_setup(struct dsa_switch_tree *dst, struct net_device *master, + int index, struct device *parent, struct device *host_dev) { struct dsa_chip_data *cd = dst->pd->chip + index; const struct dsa_switch_ops *ops; @@ -229,11 +231,11 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, */ ops = dsa_switch_probe(parent, host_dev, cd->sw_addr, &name, &priv); if (!ops) { - netdev_err(dst->master_netdev, "[%d]: could not detect attached switch\n", + netdev_err(master, "[%d]: could not detect attached switch\n", index); return ERR_PTR(-EINVAL); } - netdev_info(dst->master_netdev, "[%d]: detected a %s switch\n", + netdev_info(master, "[%d]: detected a %s switch\n", index, name); @@ -250,7 +252,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, ds->ops = ops; ds->priv = priv; - ret = dsa_switch_setup_one(ds, parent); + ret = dsa_switch_setup_one(ds, master, parent); if (ret) return ERR_PTR(ret); @@ -576,13 +578,11 @@ static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, unsigned configured = 0; dst->pd = pd; - dst->master_netdev = dev; - dst->cpu_port = -1; for (i = 0; i < pd->nr_chips; i++) { struct dsa_switch *ds; - ds = dsa_switch_setup(dst, i, parent, pd->chip[i].host_dev); + ds = dsa_switch_setup(dst, dev, i, parent, pd->chip[i].host_dev); if (IS_ERR(ds)) { netdev_err(dev, "[%d]: couldn't create dsa switch instance (error %ld)\n", i, PTR_ERR(ds)); @@ -606,7 +606,7 @@ static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, * sent to the tag format's receive function. */ wmb(); - dev->dsa_ptr = (void *)dst; + dev->dsa_ptr = dst; return 0; } @@ -673,7 +673,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) { int i; - dst->master_netdev->dsa_ptr = NULL; + dst->cpu_dp->netdev->dsa_ptr = NULL; /* If we used a tagging format that doesn't have an ethertype * field, make sure that all packets from this point get sent @@ -688,9 +688,9 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) dsa_switch_destroy(ds); } - dsa_cpu_port_ethtool_restore(dst->cpu_switch); + dsa_cpu_port_ethtool_restore(dst->cpu_dp); - dev_put(dst->master_netdev); + dev_put(dst->cpu_dp->netdev); } static int dsa_remove(struct platform_device *pdev) diff --git a/net/dsa/port.c b/net/dsa/port.c new file mode 100644 index 000000000000..efc3bce3a89d --- /dev/null +++ b/net/dsa/port.c @@ -0,0 +1,259 @@ +/* + * Handling of a single switch port + * + * Copyright (c) 2017 Savoir-faire Linux Inc. + * Vivien Didelot <vivien.didelot@savoirfairelinux.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/if_bridge.h> +#include <linux/notifier.h> + +#include "dsa_priv.h" + +static int dsa_port_notify(struct dsa_port *dp, unsigned long e, void *v) +{ + struct raw_notifier_head *nh = &dp->ds->dst->nh; + int err; + + err = raw_notifier_call_chain(nh, e, v); + + return notifier_to_errno(err); +} + +int dsa_port_set_state(struct dsa_port *dp, u8 state, + struct switchdev_trans *trans) +{ + struct dsa_switch *ds = dp->ds; + int port = dp->index; + + if (switchdev_trans_ph_prepare(trans)) + return ds->ops->port_stp_state_set ? 0 : -EOPNOTSUPP; + + if (ds->ops->port_stp_state_set) + ds->ops->port_stp_state_set(ds, port, state); + + if (ds->ops->port_fast_age) { + /* Fast age FDB entries or flush appropriate forwarding database + * for the given port, if we are moving it from Learning or + * Forwarding state, to Disabled or Blocking or Listening state. + */ + + if ((dp->stp_state == BR_STATE_LEARNING || + dp->stp_state == BR_STATE_FORWARDING) && + (state == BR_STATE_DISABLED || + state == BR_STATE_BLOCKING || + state == BR_STATE_LISTENING)) + ds->ops->port_fast_age(ds, port); + } + + dp->stp_state = state; + + return 0; +} + +void dsa_port_set_state_now(struct dsa_port *dp, u8 state) +{ + int err; + + err = dsa_port_set_state(dp, state, NULL); + if (err) + pr_err("DSA: failed to set STP state %u (%d)\n", state, err); +} + +int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br) +{ + struct dsa_notifier_bridge_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .br = br, + }; + int err; + + /* Here the port is already bridged. Reflect the current configuration + * so that drivers can program their chips accordingly. + */ + dp->bridge_dev = br; + + err = dsa_port_notify(dp, DSA_NOTIFIER_BRIDGE_JOIN, &info); + + /* The bridging is rolled back on error */ + if (err) + dp->bridge_dev = NULL; + + return err; +} + +void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) +{ + struct dsa_notifier_bridge_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .br = br, + }; + int err; + + /* Here the port is already unbridged. Reflect the current configuration + * so that drivers can program their chips accordingly. + */ + dp->bridge_dev = NULL; + + err = dsa_port_notify(dp, DSA_NOTIFIER_BRIDGE_LEAVE, &info); + if (err) + pr_err("DSA: failed to notify DSA_NOTIFIER_BRIDGE_LEAVE\n"); + + /* Port left the bridge, put in BR_STATE_DISABLED by the bridge layer, + * so allow it to be in BR_STATE_FORWARDING to be kept functional + */ + dsa_port_set_state_now(dp, BR_STATE_FORWARDING); +} + +int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, + struct switchdev_trans *trans) +{ + struct dsa_switch *ds = dp->ds; + + /* bridge skips -EOPNOTSUPP, so skip the prepare phase */ + if (switchdev_trans_ph_prepare(trans)) + return 0; + + if (ds->ops->port_vlan_filtering) + return ds->ops->port_vlan_filtering(ds, dp->index, + vlan_filtering); + + return 0; +} + +int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock, + struct switchdev_trans *trans) +{ + unsigned long ageing_jiffies = clock_t_to_jiffies(ageing_clock); + unsigned int ageing_time = jiffies_to_msecs(ageing_jiffies); + struct dsa_notifier_ageing_time_info info = { + .ageing_time = ageing_time, + .trans = trans, + }; + + if (switchdev_trans_ph_prepare(trans)) + return dsa_port_notify(dp, DSA_NOTIFIER_AGEING_TIME, &info); + + dp->ageing_time = ageing_time; + + return dsa_port_notify(dp, DSA_NOTIFIER_AGEING_TIME, &info); +} + +int dsa_port_fdb_add(struct dsa_port *dp, + const struct switchdev_obj_port_fdb *fdb, + struct switchdev_trans *trans) +{ + struct dsa_notifier_fdb_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .trans = trans, + .fdb = fdb, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_FDB_ADD, &info); +} + +int dsa_port_fdb_del(struct dsa_port *dp, + const struct switchdev_obj_port_fdb *fdb) +{ + struct dsa_notifier_fdb_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .fdb = fdb, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_FDB_DEL, &info); +} + +int dsa_port_fdb_dump(struct dsa_port *dp, struct switchdev_obj_port_fdb *fdb, + switchdev_obj_dump_cb_t *cb) +{ + struct dsa_switch *ds = dp->ds; + + if (ds->ops->port_fdb_dump) + return ds->ops->port_fdb_dump(ds, dp->index, fdb, cb); + + return -EOPNOTSUPP; +} + +int dsa_port_mdb_add(struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb, + struct switchdev_trans *trans) +{ + struct dsa_notifier_mdb_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .trans = trans, + .mdb = mdb, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_MDB_ADD, &info); +} + +int dsa_port_mdb_del(struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb) +{ + struct dsa_notifier_mdb_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .mdb = mdb, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_MDB_DEL, &info); +} + +int dsa_port_mdb_dump(struct dsa_port *dp, struct switchdev_obj_port_mdb *mdb, + switchdev_obj_dump_cb_t *cb) +{ + struct dsa_switch *ds = dp->ds; + + if (ds->ops->port_mdb_dump) + return ds->ops->port_mdb_dump(ds, dp->index, mdb, cb); + + return -EOPNOTSUPP; +} + +int dsa_port_vlan_add(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, + struct switchdev_trans *trans) +{ + struct dsa_notifier_vlan_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .trans = trans, + .vlan = vlan, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_ADD, &info); +} + +int dsa_port_vlan_del(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan) +{ + struct dsa_notifier_vlan_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .vlan = vlan, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info); +} + +int dsa_port_vlan_dump(struct dsa_port *dp, + struct switchdev_obj_port_vlan *vlan, + switchdev_obj_dump_cb_t *cb) +{ + struct dsa_switch *ds = dp->ds; + + if (ds->ops->port_vlan_dump) + return ds->ops->port_vlan_dump(ds, dp->index, vlan, cb); + + return -EOPNOTSUPP; +} diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 7693182df81e..9507bd38cf04 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -17,28 +17,16 @@ #include <linux/of_mdio.h> #include <linux/mdio.h> #include <linux/list.h> -#include <net/dsa.h> #include <net/rtnetlink.h> -#include <net/switchdev.h> #include <net/pkt_cls.h> #include <net/tc_act/tc_mirred.h> #include <linux/if_bridge.h> #include <linux/netpoll.h> + #include "dsa_priv.h" static bool dsa_slave_dev_check(struct net_device *dev); -static int dsa_slave_notify(struct net_device *dev, unsigned long e, void *v) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct raw_notifier_head *nh = &p->dp->ds->dst->nh; - int err; - - err = raw_notifier_call_chain(nh, e, v); - - return notifier_to_errno(err); -} - /* slave mii_bus handling ***************************************************/ static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg) { @@ -78,48 +66,16 @@ static int dsa_slave_get_iflink(const struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); - return p->dp->ds->dst->master_netdev->ifindex; -} - -static inline bool dsa_port_is_bridged(struct dsa_port *dp) -{ - return !!dp->bridge_dev; + return dsa_master_netdev(p)->ifindex; } -static void dsa_slave_set_state(struct net_device *dev, u8 state) +static int dsa_slave_open(struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_port *dp = p->dp; struct dsa_switch *ds = dp->ds; - int port = dp->index; - - if (ds->ops->port_stp_state_set) - ds->ops->port_stp_state_set(ds, port, state); - - if (ds->ops->port_fast_age) { - /* Fast age FDB entries or flush appropriate forwarding database - * for the given port, if we are moving it from Learning or - * Forwarding state, to Disabled or Blocking or Listening state. - */ - - if ((dp->stp_state == BR_STATE_LEARNING || - dp->stp_state == BR_STATE_FORWARDING) && - (state == BR_STATE_DISABLED || - state == BR_STATE_BLOCKING || - state == BR_STATE_LISTENING)) - ds->ops->port_fast_age(ds, port); - } - - dp->stp_state = state; -} - -static int dsa_slave_open(struct net_device *dev) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = p->dp->ds->dst->master_netdev; - struct dsa_switch *ds = p->dp->ds; - u8 stp_state = dsa_port_is_bridged(p->dp) ? - BR_STATE_BLOCKING : BR_STATE_FORWARDING; + struct net_device *master = dsa_master_netdev(p); + u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING; int err; if (!(master->flags & IFF_UP)) @@ -148,7 +104,7 @@ static int dsa_slave_open(struct net_device *dev) goto clear_promisc; } - dsa_slave_set_state(dev, stp_state); + dsa_port_set_state_now(p->dp, stp_state); if (p->phy) phy_start(p->phy); @@ -171,7 +127,7 @@ out: static int dsa_slave_close(struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = p->dp->ds->dst->master_netdev; + struct net_device *master = dsa_master_netdev(p); struct dsa_switch *ds = p->dp->ds; if (p->phy) @@ -190,7 +146,7 @@ static int dsa_slave_close(struct net_device *dev) if (ds->ops->port_disable) ds->ops->port_disable(ds, p->dp->index, p->phy); - dsa_slave_set_state(dev, BR_STATE_DISABLED); + dsa_port_set_state_now(p->dp, BR_STATE_DISABLED); return 0; } @@ -198,7 +154,7 @@ static int dsa_slave_close(struct net_device *dev) static void dsa_slave_change_rx_flags(struct net_device *dev, int change) { struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = p->dp->ds->dst->master_netdev; + struct net_device *master = dsa_master_netdev(p); if (change & IFF_ALLMULTI) dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1); @@ -209,7 +165,7 @@ static void dsa_slave_change_rx_flags(struct net_device *dev, int change) static void dsa_slave_set_rx_mode(struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = p->dp->ds->dst->master_netdev; + struct net_device *master = dsa_master_netdev(p); dev_mc_sync(master, dev); dev_uc_sync(master, dev); @@ -218,7 +174,7 @@ static void dsa_slave_set_rx_mode(struct net_device *dev) static int dsa_slave_set_mac_address(struct net_device *dev, void *a) { struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = p->dp->ds->dst->master_netdev; + struct net_device *master = dsa_master_netdev(p); struct sockaddr *addr = a; int err; @@ -243,140 +199,6 @@ out: return 0; } -static int dsa_slave_port_vlan_add(struct net_device *dev, - const struct switchdev_obj_port_vlan *vlan, - struct switchdev_trans *trans) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; - struct dsa_switch *ds = dp->ds; - - if (switchdev_trans_ph_prepare(trans)) { - if (!ds->ops->port_vlan_prepare || !ds->ops->port_vlan_add) - return -EOPNOTSUPP; - - return ds->ops->port_vlan_prepare(ds, dp->index, vlan, trans); - } - - ds->ops->port_vlan_add(ds, dp->index, vlan, trans); - - return 0; -} - -static int dsa_slave_port_vlan_del(struct net_device *dev, - const struct switchdev_obj_port_vlan *vlan) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - - if (!ds->ops->port_vlan_del) - return -EOPNOTSUPP; - - return ds->ops->port_vlan_del(ds, p->dp->index, vlan); -} - -static int dsa_slave_port_vlan_dump(struct net_device *dev, - struct switchdev_obj_port_vlan *vlan, - switchdev_obj_dump_cb_t *cb) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - - if (ds->ops->port_vlan_dump) - return ds->ops->port_vlan_dump(ds, p->dp->index, vlan, cb); - - return -EOPNOTSUPP; -} - -static int dsa_slave_port_fdb_add(struct net_device *dev, - const struct switchdev_obj_port_fdb *fdb, - struct switchdev_trans *trans) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - - if (switchdev_trans_ph_prepare(trans)) { - if (!ds->ops->port_fdb_prepare || !ds->ops->port_fdb_add) - return -EOPNOTSUPP; - - return ds->ops->port_fdb_prepare(ds, p->dp->index, fdb, trans); - } - - ds->ops->port_fdb_add(ds, p->dp->index, fdb, trans); - - return 0; -} - -static int dsa_slave_port_fdb_del(struct net_device *dev, - const struct switchdev_obj_port_fdb *fdb) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - int ret = -EOPNOTSUPP; - - if (ds->ops->port_fdb_del) - ret = ds->ops->port_fdb_del(ds, p->dp->index, fdb); - - return ret; -} - -static int dsa_slave_port_fdb_dump(struct net_device *dev, - struct switchdev_obj_port_fdb *fdb, - switchdev_obj_dump_cb_t *cb) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - - if (ds->ops->port_fdb_dump) - return ds->ops->port_fdb_dump(ds, p->dp->index, fdb, cb); - - return -EOPNOTSUPP; -} - -static int dsa_slave_port_mdb_add(struct net_device *dev, - const struct switchdev_obj_port_mdb *mdb, - struct switchdev_trans *trans) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - - if (switchdev_trans_ph_prepare(trans)) { - if (!ds->ops->port_mdb_prepare || !ds->ops->port_mdb_add) - return -EOPNOTSUPP; - - return ds->ops->port_mdb_prepare(ds, p->dp->index, mdb, trans); - } - - ds->ops->port_mdb_add(ds, p->dp->index, mdb, trans); - - return 0; -} - -static int dsa_slave_port_mdb_del(struct net_device *dev, - const struct switchdev_obj_port_mdb *mdb) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - - if (ds->ops->port_mdb_del) - return ds->ops->port_mdb_del(ds, p->dp->index, mdb); - - return -EOPNOTSUPP; -} - -static int dsa_slave_port_mdb_dump(struct net_device *dev, - struct switchdev_obj_port_mdb *mdb, - switchdev_obj_dump_cb_t *cb) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - - if (ds->ops->port_mdb_dump) - return ds->ops->port_mdb_dump(ds, p->dp->index, mdb, cb); - - return -EOPNOTSUPP; -} - static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -387,96 +209,24 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return -EOPNOTSUPP; } -static int dsa_slave_stp_state_set(struct net_device *dev, - const struct switchdev_attr *attr, - struct switchdev_trans *trans) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - - if (switchdev_trans_ph_prepare(trans)) - return ds->ops->port_stp_state_set ? 0 : -EOPNOTSUPP; - - dsa_slave_set_state(dev, attr->u.stp_state); - - return 0; -} - -static int dsa_slave_vlan_filtering(struct net_device *dev, - const struct switchdev_attr *attr, - struct switchdev_trans *trans) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - - /* bridge skips -EOPNOTSUPP, so skip the prepare phase */ - if (switchdev_trans_ph_prepare(trans)) - return 0; - - if (ds->ops->port_vlan_filtering) - return ds->ops->port_vlan_filtering(ds, p->dp->index, - attr->u.vlan_filtering); - - return 0; -} - -static unsigned int dsa_fastest_ageing_time(struct dsa_switch *ds, - unsigned int ageing_time) -{ - int i; - - for (i = 0; i < ds->num_ports; ++i) { - struct dsa_port *dp = &ds->ports[i]; - - if (dp && dp->ageing_time && dp->ageing_time < ageing_time) - ageing_time = dp->ageing_time; - } - - return ageing_time; -} - -static int dsa_slave_ageing_time(struct net_device *dev, - const struct switchdev_attr *attr, - struct switchdev_trans *trans) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - unsigned long ageing_jiffies = clock_t_to_jiffies(attr->u.ageing_time); - unsigned int ageing_time = jiffies_to_msecs(ageing_jiffies); - - if (switchdev_trans_ph_prepare(trans)) { - if (ds->ageing_time_min && ageing_time < ds->ageing_time_min) - return -ERANGE; - if (ds->ageing_time_max && ageing_time > ds->ageing_time_max) - return -ERANGE; - return 0; - } - - /* Keep the fastest ageing time in case of multiple bridges */ - p->dp->ageing_time = ageing_time; - ageing_time = dsa_fastest_ageing_time(ds, ageing_time); - - if (ds->ops->set_ageing_time) - return ds->ops->set_ageing_time(ds, ageing_time); - - return 0; -} - static int dsa_slave_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct switchdev_trans *trans) { + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = p->dp; int ret; switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: - ret = dsa_slave_stp_state_set(dev, attr, trans); + ret = dsa_port_set_state(dp, attr->u.stp_state, trans); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: - ret = dsa_slave_vlan_filtering(dev, attr, trans); + ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering, + trans); break; case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: - ret = dsa_slave_ageing_time(dev, attr, trans); + ret = dsa_port_ageing_time(dp, attr->u.ageing_time, trans); break; default: ret = -EOPNOTSUPP; @@ -490,6 +240,8 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct switchdev_trans *trans) { + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = p->dp; int err; /* For the prepare phase, ensure the full set of changes is feasable in @@ -499,18 +251,14 @@ static int dsa_slave_port_obj_add(struct net_device *dev, switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_FDB: - err = dsa_slave_port_fdb_add(dev, - SWITCHDEV_OBJ_PORT_FDB(obj), - trans); + err = dsa_port_fdb_add(dp, SWITCHDEV_OBJ_PORT_FDB(obj), trans); break; case SWITCHDEV_OBJ_ID_PORT_MDB: - err = dsa_slave_port_mdb_add(dev, SWITCHDEV_OBJ_PORT_MDB(obj), - trans); + err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj), trans); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = dsa_slave_port_vlan_add(dev, - SWITCHDEV_OBJ_PORT_VLAN(obj), - trans); + err = dsa_port_vlan_add(dp, SWITCHDEV_OBJ_PORT_VLAN(obj), + trans); break; default: err = -EOPNOTSUPP; @@ -523,19 +271,19 @@ static int dsa_slave_port_obj_add(struct net_device *dev, static int dsa_slave_port_obj_del(struct net_device *dev, const struct switchdev_obj *obj) { + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = p->dp; int err; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_FDB: - err = dsa_slave_port_fdb_del(dev, - SWITCHDEV_OBJ_PORT_FDB(obj)); + err = dsa_port_fdb_del(dp, SWITCHDEV_OBJ_PORT_FDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_MDB: - err = dsa_slave_port_mdb_del(dev, SWITCHDEV_OBJ_PORT_MDB(obj)); + err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = dsa_slave_port_vlan_del(dev, - SWITCHDEV_OBJ_PORT_VLAN(obj)); + err = dsa_port_vlan_del(dp, SWITCHDEV_OBJ_PORT_VLAN(obj)); break; default: err = -EOPNOTSUPP; @@ -549,22 +297,19 @@ static int dsa_slave_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, switchdev_obj_dump_cb_t *cb) { + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = p->dp; int err; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_FDB: - err = dsa_slave_port_fdb_dump(dev, - SWITCHDEV_OBJ_PORT_FDB(obj), - cb); + err = dsa_port_fdb_dump(dp, SWITCHDEV_OBJ_PORT_FDB(obj), cb); break; case SWITCHDEV_OBJ_ID_PORT_MDB: - err = dsa_slave_port_mdb_dump(dev, SWITCHDEV_OBJ_PORT_MDB(obj), - cb); + err = dsa_port_mdb_dump(dp, SWITCHDEV_OBJ_PORT_MDB(obj), cb); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = dsa_slave_port_vlan_dump(dev, - SWITCHDEV_OBJ_PORT_VLAN(obj), - cb); + err = dsa_port_vlan_dump(dp, SWITCHDEV_OBJ_PORT_VLAN(obj), cb); break; default: err = -EOPNOTSUPP; @@ -574,57 +319,6 @@ static int dsa_slave_port_obj_dump(struct net_device *dev, return err; } -static int dsa_slave_bridge_port_join(struct net_device *dev, - struct net_device *br) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_notifier_bridge_info info = { - .sw_index = p->dp->ds->index, - .port = p->dp->index, - .br = br, - }; - int err; - - /* Here the port is already bridged. Reflect the current configuration - * so that drivers can program their chips accordingly. - */ - p->dp->bridge_dev = br; - - err = dsa_slave_notify(dev, DSA_NOTIFIER_BRIDGE_JOIN, &info); - - /* The bridging is rolled back on error */ - if (err) - p->dp->bridge_dev = NULL; - - return err; -} - -static void dsa_slave_bridge_port_leave(struct net_device *dev, - struct net_device *br) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_notifier_bridge_info info = { - .sw_index = p->dp->ds->index, - .port = p->dp->index, - .br = br, - }; - int err; - - /* Here the port is already unbridged. Reflect the current configuration - * so that drivers can program their chips accordingly. - */ - p->dp->bridge_dev = NULL; - - err = dsa_slave_notify(dev, DSA_NOTIFIER_BRIDGE_LEAVE, &info); - if (err) - netdev_err(dev, "failed to notify DSA_NOTIFIER_BRIDGE_LEAVE\n"); - - /* Port left the bridge, put in BR_STATE_DISABLED by the bridge layer, - * so allow it to be in BR_STATE_FORWARDING to be kept functional - */ - dsa_slave_set_state(dev, BR_STATE_FORWARDING); -} - static int dsa_slave_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) { @@ -663,10 +357,14 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; - /* Transmit function may have to reallocate the original SKB */ + /* Transmit function may have to reallocate the original SKB, + * in which case it must have freed it. Only free it here on error. + */ nskb = p->xmit(skb, dev); - if (!nskb) + if (!nskb) { + kfree_skb(skb); return NETDEV_TX_OK; + } /* SKB for netpoll still need to be mangled with the protocol-specific * tag to be successfully transmitted @@ -677,7 +375,7 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) /* Queue the SKB for transmission on the parent interface, but * do not modify its EtherType */ - nskb->dev = p->dp->ds->dst->master_netdev; + nskb->dev = dsa_master_netdev(p); dev_queue_xmit(nskb); return NETDEV_TX_OK; @@ -689,12 +387,13 @@ dsa_slave_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct dsa_slave_priv *p = netdev_priv(dev); - int err = -EOPNOTSUPP; - if (p->phy != NULL) - err = phy_ethtool_ksettings_get(p->phy, cmd); + if (!p->phy) + return -EOPNOTSUPP; - return err; + phy_ethtool_ksettings_get(p->phy, cmd); + + return 0; } static int @@ -821,14 +520,14 @@ static void dsa_cpu_port_get_ethtool_stats(struct net_device *dev, uint64_t *data) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds = dst->cpu_switch; - s8 cpu_port = dst->cpu_port; + struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); + struct dsa_switch *ds = cpu_dp->ds; + s8 cpu_port = cpu_dp->index; int count = 0; - if (dst->master_ethtool_ops.get_sset_count) { - count = dst->master_ethtool_ops.get_sset_count(dev, - ETH_SS_STATS); - dst->master_ethtool_ops.get_ethtool_stats(dev, stats, data); + if (cpu_dp->ethtool_ops.get_sset_count) { + count = cpu_dp->ethtool_ops.get_sset_count(dev, ETH_SS_STATS); + cpu_dp->ethtool_ops.get_ethtool_stats(dev, stats, data); } if (ds->ops->get_ethtool_stats) @@ -838,11 +537,12 @@ static void dsa_cpu_port_get_ethtool_stats(struct net_device *dev, static int dsa_cpu_port_get_sset_count(struct net_device *dev, int sset) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds = dst->cpu_switch; + struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); + struct dsa_switch *ds = cpu_dp->ds; int count = 0; - if (dst->master_ethtool_ops.get_sset_count) - count += dst->master_ethtool_ops.get_sset_count(dev, sset); + if (cpu_dp->ethtool_ops.get_sset_count) + count += cpu_dp->ethtool_ops.get_sset_count(dev, sset); if (sset == ETH_SS_STATS && ds->ops->get_sset_count) count += ds->ops->get_sset_count(ds); @@ -854,8 +554,9 @@ static void dsa_cpu_port_get_strings(struct net_device *dev, uint32_t stringset, uint8_t *data) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds = dst->cpu_switch; - s8 cpu_port = dst->cpu_port; + struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); + struct dsa_switch *ds = cpu_dp->ds; + s8 cpu_port = cpu_dp->index; int len = ETH_GSTRING_LEN; int mcount = 0, count; unsigned int i; @@ -866,10 +567,9 @@ static void dsa_cpu_port_get_strings(struct net_device *dev, /* We do not want to be NULL-terminated, since this is a prefix */ pfx[sizeof(pfx) - 1] = '_'; - if (dst->master_ethtool_ops.get_sset_count) { - mcount = dst->master_ethtool_ops.get_sset_count(dev, - ETH_SS_STATS); - dst->master_ethtool_ops.get_strings(dev, stringset, data); + if (cpu_dp->ethtool_ops.get_sset_count) { + mcount = cpu_dp->ethtool_ops.get_sset_count(dev, ETH_SS_STATS); + cpu_dp->ethtool_ops.get_strings(dev, stringset, data); } if (stringset == ETH_SS_STATS && ds->ops->get_strings) { @@ -985,8 +685,7 @@ static int dsa_slave_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) { struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - struct net_device *master = ds->dst->master_netdev; + struct net_device *master = dsa_master_netdev(p); struct netpoll *netpoll; int err = 0; @@ -1138,10 +837,13 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev, } static int dsa_slave_setup_tc(struct net_device *dev, u32 handle, - __be16 protocol, struct tc_to_netdev *tc) + u32 chain_index, __be16 protocol, + struct tc_to_netdev *tc) { bool ingress = TC_H_MAJ(handle) == TC_H_MAJ(TC_H_INGRESS); - int ret = -EOPNOTSUPP; + + if (chain_index) + return -EOPNOTSUPP; switch (tc->type) { case TC_SETUP_MATCHALL: @@ -1155,10 +857,8 @@ static int dsa_slave_setup_tc(struct net_device *dev, u32 handle, return 0; } default: - break; + return -EOPNOTSUPP; } - - return ret; } void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops) @@ -1441,11 +1141,11 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, struct net_device *master; struct net_device *slave_dev; struct dsa_slave_priv *p; + struct dsa_port *cpu_dp; int ret; - master = ds->dst->master_netdev; - if (ds->master_netdev) - master = ds->master_netdev; + cpu_dp = ds->dst->cpu_dp; + master = cpu_dp->netdev; slave_dev = alloc_netdev(sizeof(struct dsa_slave_priv), name, NET_NAME_UNKNOWN, ether_setup); @@ -1528,14 +1228,16 @@ static bool dsa_slave_dev_check(struct net_device *dev) static int dsa_slave_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = p->dp; int err = NOTIFY_DONE; if (netif_is_bridge_master(info->upper_dev)) { if (info->linking) { - err = dsa_slave_bridge_port_join(dev, info->upper_dev); + err = dsa_port_bridge_join(dp, info->upper_dev); err = notifier_from_errno(err); } else { - dsa_slave_bridge_port_leave(dev, info->upper_dev); + dsa_port_bridge_leave(dp, info->upper_dev); err = NOTIFY_OK; } } diff --git a/net/dsa/switch.c b/net/dsa/switch.c index ca6e26e514f0..97e2e9c8cf3f 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -12,7 +12,47 @@ #include <linux/netdevice.h> #include <linux/notifier.h> -#include <net/dsa.h> +#include <net/switchdev.h> + +#include "dsa_priv.h" + +static unsigned int dsa_switch_fastest_ageing_time(struct dsa_switch *ds, + unsigned int ageing_time) +{ + int i; + + for (i = 0; i < ds->num_ports; ++i) { + struct dsa_port *dp = &ds->ports[i]; + + if (dp->ageing_time && dp->ageing_time < ageing_time) + ageing_time = dp->ageing_time; + } + + return ageing_time; +} + +static int dsa_switch_ageing_time(struct dsa_switch *ds, + struct dsa_notifier_ageing_time_info *info) +{ + unsigned int ageing_time = info->ageing_time; + struct switchdev_trans *trans = info->trans; + + if (switchdev_trans_ph_prepare(trans)) { + if (ds->ageing_time_min && ageing_time < ds->ageing_time_min) + return -ERANGE; + if (ds->ageing_time_max && ageing_time > ds->ageing_time_max) + return -ERANGE; + return 0; + } + + /* Program the fastest ageing time in case of multiple bridges */ + ageing_time = dsa_switch_fastest_ageing_time(ds, ageing_time); + + if (ds->ops->set_ageing_time) + return ds->ops->set_ageing_time(ds, ageing_time); + + return 0; +} static int dsa_switch_bridge_join(struct dsa_switch *ds, struct dsa_notifier_bridge_info *info) @@ -40,6 +80,137 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, return 0; } +static int dsa_switch_fdb_add(struct dsa_switch *ds, + struct dsa_notifier_fdb_info *info) +{ + const struct switchdev_obj_port_fdb *fdb = info->fdb; + struct switchdev_trans *trans = info->trans; + + /* Do not care yet about other switch chips of the fabric */ + if (ds->index != info->sw_index) + return 0; + + if (switchdev_trans_ph_prepare(trans)) { + if (!ds->ops->port_fdb_prepare || !ds->ops->port_fdb_add) + return -EOPNOTSUPP; + + return ds->ops->port_fdb_prepare(ds, info->port, fdb, trans); + } + + ds->ops->port_fdb_add(ds, info->port, fdb, trans); + + return 0; +} + +static int dsa_switch_fdb_del(struct dsa_switch *ds, + struct dsa_notifier_fdb_info *info) +{ + const struct switchdev_obj_port_fdb *fdb = info->fdb; + + /* Do not care yet about other switch chips of the fabric */ + if (ds->index != info->sw_index) + return 0; + + if (!ds->ops->port_fdb_del) + return -EOPNOTSUPP; + + return ds->ops->port_fdb_del(ds, info->port, fdb); +} + +static int dsa_switch_mdb_add(struct dsa_switch *ds, + struct dsa_notifier_mdb_info *info) +{ + const struct switchdev_obj_port_mdb *mdb = info->mdb; + struct switchdev_trans *trans = info->trans; + DECLARE_BITMAP(group, ds->num_ports); + int port, err; + + /* Build a mask of Multicast group members */ + bitmap_zero(group, ds->num_ports); + if (ds->index == info->sw_index) + set_bit(info->port, group); + for (port = 0; port < ds->num_ports; port++) + if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) + set_bit(port, group); + + if (switchdev_trans_ph_prepare(trans)) { + if (!ds->ops->port_mdb_prepare || !ds->ops->port_mdb_add) + return -EOPNOTSUPP; + + for_each_set_bit(port, group, ds->num_ports) { + err = ds->ops->port_mdb_prepare(ds, port, mdb, trans); + if (err) + return err; + } + } + + for_each_set_bit(port, group, ds->num_ports) + ds->ops->port_mdb_add(ds, port, mdb, trans); + + return 0; +} + +static int dsa_switch_mdb_del(struct dsa_switch *ds, + struct dsa_notifier_mdb_info *info) +{ + const struct switchdev_obj_port_mdb *mdb = info->mdb; + + if (!ds->ops->port_mdb_del) + return -EOPNOTSUPP; + + if (ds->index == info->sw_index) + return ds->ops->port_mdb_del(ds, info->port, mdb); + + return 0; +} + +static int dsa_switch_vlan_add(struct dsa_switch *ds, + struct dsa_notifier_vlan_info *info) +{ + const struct switchdev_obj_port_vlan *vlan = info->vlan; + struct switchdev_trans *trans = info->trans; + DECLARE_BITMAP(members, ds->num_ports); + int port, err; + + /* Build a mask of VLAN members */ + bitmap_zero(members, ds->num_ports); + if (ds->index == info->sw_index) + set_bit(info->port, members); + for (port = 0; port < ds->num_ports; port++) + if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) + set_bit(port, members); + + if (switchdev_trans_ph_prepare(trans)) { + if (!ds->ops->port_vlan_prepare || !ds->ops->port_vlan_add) + return -EOPNOTSUPP; + + for_each_set_bit(port, members, ds->num_ports) { + err = ds->ops->port_vlan_prepare(ds, port, vlan, trans); + if (err) + return err; + } + } + + for_each_set_bit(port, members, ds->num_ports) + ds->ops->port_vlan_add(ds, port, vlan, trans); + + return 0; +} + +static int dsa_switch_vlan_del(struct dsa_switch *ds, + struct dsa_notifier_vlan_info *info) +{ + const struct switchdev_obj_port_vlan *vlan = info->vlan; + + if (!ds->ops->port_vlan_del) + return -EOPNOTSUPP; + + if (ds->index == info->sw_index) + return ds->ops->port_vlan_del(ds, info->port, vlan); + + return 0; +} + static int dsa_switch_event(struct notifier_block *nb, unsigned long event, void *info) { @@ -47,12 +218,33 @@ static int dsa_switch_event(struct notifier_block *nb, int err; switch (event) { + case DSA_NOTIFIER_AGEING_TIME: + err = dsa_switch_ageing_time(ds, info); + break; case DSA_NOTIFIER_BRIDGE_JOIN: err = dsa_switch_bridge_join(ds, info); break; case DSA_NOTIFIER_BRIDGE_LEAVE: err = dsa_switch_bridge_leave(ds, info); break; + case DSA_NOTIFIER_FDB_ADD: + err = dsa_switch_fdb_add(ds, info); + break; + case DSA_NOTIFIER_FDB_DEL: + err = dsa_switch_fdb_del(ds, info); + break; + case DSA_NOTIFIER_MDB_ADD: + err = dsa_switch_mdb_add(ds, info); + break; + case DSA_NOTIFIER_MDB_DEL: + err = dsa_switch_mdb_del(ds, info); + break; + case DSA_NOTIFIER_VLAN_ADD: + err = dsa_switch_vlan_add(ds, info); + break; + case DSA_NOTIFIER_VLAN_DEL: + err = dsa_switch_vlan_del(ds, info); + break; default: err = -EOPNOTSUPP; break; diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 2a9b52c5af86..c697d9815177 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -12,7 +12,7 @@ #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/slab.h> -#include <net/dsa.h> + #include "dsa_priv.h" /* This tag length is 4 bytes, older ones were 6 bytes, we do not @@ -65,7 +65,7 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev u8 *brcm_tag; if (skb_cow_head(skb, BRCM_TAG_LEN) < 0) - goto out_free; + return NULL; skb_push(skb, BRCM_TAG_LEN); @@ -86,10 +86,6 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev brcm_tag[3] = (1 << p->dp->index) & BRCM_IG_DSTMAP1_MASK; return skb; - -out_free: - kfree_skb(skb); - return NULL; } static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, @@ -97,34 +93,33 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, struct net_device *orig_dev) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds; + struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); + struct dsa_switch *ds = cpu_dp->ds; int source_port; u8 *brcm_tag; - ds = dst->cpu_switch; - if (unlikely(!pskb_may_pull(skb, BRCM_TAG_LEN))) - goto out_drop; + return NULL; /* skb->data points to the EtherType, the tag is right before it */ brcm_tag = skb->data - 2; /* The opcode should never be different than 0b000 */ if (unlikely((brcm_tag[0] >> BRCM_OPCODE_SHIFT) & BRCM_OPCODE_MASK)) - goto out_drop; + return NULL; /* We should never see a reserved reason code without knowing how to * handle it */ if (unlikely(brcm_tag[2] & BRCM_EG_RC_RSVD)) - goto out_drop; + return NULL; /* Locate which port this is coming from */ source_port = brcm_tag[3] & BRCM_EG_PID_MASK; /* Validate port against switch setup, either the port is totally */ if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) - goto out_drop; + return NULL; /* Remove Broadcom tag and update checksum */ skb_pull_rcsum(skb, BRCM_TAG_LEN); @@ -137,9 +132,6 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, skb->dev = ds->ports[source_port].netdev; return skb; - -out_drop: - return NULL; } const struct dsa_device_ops brcm_netdev_ops = { diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 1c6633f0de01..12867a4b458f 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -11,7 +11,7 @@ #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/slab.h> -#include <net/dsa.h> + #include "dsa_priv.h" #define DSA_HLEN 4 @@ -28,7 +28,7 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) */ if (skb->protocol == htons(ETH_P_8021Q)) { if (skb_cow_head(skb, 0) < 0) - goto out_free; + return NULL; /* * Construct tagged FROM_CPU DSA tag from 802.1q tag. @@ -46,7 +46,7 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) } } else { if (skb_cow_head(skb, DSA_HLEN) < 0) - goto out_free; + return NULL; skb_push(skb, DSA_HLEN); memmove(skb->data, skb->data + DSA_HLEN, 2 * ETH_ALEN); @@ -62,10 +62,6 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) } return skb; - -out_free: - kfree_skb(skb); - return NULL; } static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, @@ -79,7 +75,7 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, int source_port; if (unlikely(!pskb_may_pull(skb, DSA_HLEN))) - goto out_drop; + return NULL; /* * The ethertype field is part of the DSA header. @@ -90,7 +86,7 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, * Check that frame type is either TO_CPU or FORWARD. */ if ((dsa_header[0] & 0xc0) != 0x00 && (dsa_header[0] & 0xc0) != 0xc0) - goto out_drop; + return NULL; /* * Determine source device and port. @@ -103,14 +99,14 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, * port is a registered DSA port. */ if (source_device >= DSA_MAX_SWITCHES) - goto out_drop; + return NULL; ds = dst->ds[source_device]; if (!ds) - goto out_drop; + return NULL; if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) - goto out_drop; + return NULL; /* * Convert the DSA header to an 802.1q header if the 'tagged' @@ -161,9 +157,6 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, skb->dev = ds->ports[source_port].netdev; return skb; - -out_drop: - return NULL; } const struct dsa_device_ops dsa_netdev_ops = { diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index d9c668aa5e54..67a9d26f9075 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -11,7 +11,7 @@ #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/slab.h> -#include <net/dsa.h> + #include "dsa_priv.h" #define DSA_HLEN 4 @@ -30,7 +30,7 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) */ if (skb->protocol == htons(ETH_P_8021Q)) { if (skb_cow_head(skb, DSA_HLEN) < 0) - goto out_free; + return NULL; skb_push(skb, DSA_HLEN); memmove(skb->data, skb->data + DSA_HLEN, 2 * ETH_ALEN); @@ -55,7 +55,7 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) } } else { if (skb_cow_head(skb, EDSA_HLEN) < 0) - goto out_free; + return NULL; skb_push(skb, EDSA_HLEN); memmove(skb->data, skb->data + EDSA_HLEN, 2 * ETH_ALEN); @@ -75,10 +75,6 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) } return skb; - -out_free: - kfree_skb(skb); - return NULL; } static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, @@ -92,7 +88,7 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, int source_port; if (unlikely(!pskb_may_pull(skb, EDSA_HLEN))) - goto out_drop; + return NULL; /* * Skip the two null bytes after the ethertype. @@ -103,7 +99,7 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, * Check that frame type is either TO_CPU or FORWARD. */ if ((edsa_header[0] & 0xc0) != 0x00 && (edsa_header[0] & 0xc0) != 0xc0) - goto out_drop; + return NULL; /* * Determine source device and port. @@ -116,14 +112,14 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, * port is a registered DSA port. */ if (source_device >= DSA_MAX_SWITCHES) - goto out_drop; + return NULL; ds = dst->ds[source_device]; if (!ds) - goto out_drop; + return NULL; if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) - goto out_drop; + return NULL; /* * If the 'tagged' bit is set, convert the DSA tag to a 802.1q @@ -180,9 +176,6 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, skb->dev = ds->ports[source_port].netdev; return skb; - -out_drop: - return NULL; } const struct dsa_device_ops edsa_netdev_ops = { diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c new file mode 100644 index 000000000000..fab41de8e983 --- /dev/null +++ b/net/dsa/tag_ksz.c @@ -0,0 +1,99 @@ +/* + * net/dsa/tag_ksz.c - Microchip KSZ Switch tag format handling + * Copyright (c) 2017 Microchip Technology + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/etherdevice.h> +#include <linux/list.h> +#include <linux/slab.h> +#include <net/dsa.h> +#include "dsa_priv.h" + +/* For Ingress (Host -> KSZ), 2 bytes are added before FCS. + * --------------------------------------------------------------------------- + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|tag1(1byte)|FCS(4bytes) + * --------------------------------------------------------------------------- + * tag0 : Prioritization (not used now) + * tag1 : each bit represents port (eg, 0x01=port1, 0x02=port2, 0x10=port5) + * + * For Egress (KSZ -> Host), 1 byte is added before FCS. + * --------------------------------------------------------------------------- + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes) + * --------------------------------------------------------------------------- + * tag0 : zero-based value represents port + * (eg, 0x00=port1, 0x02=port3, 0x06=port7) + */ + +#define KSZ_INGRESS_TAG_LEN 2 +#define KSZ_EGRESS_TAG_LEN 1 + +static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct sk_buff *nskb; + int padlen; + u8 *tag; + + padlen = (skb->len >= ETH_ZLEN) ? 0 : ETH_ZLEN - skb->len; + + if (skb_tailroom(skb) >= padlen + KSZ_INGRESS_TAG_LEN) { + nskb = skb; + } else { + nskb = alloc_skb(NET_IP_ALIGN + skb->len + + padlen + KSZ_INGRESS_TAG_LEN, GFP_ATOMIC); + if (!nskb) + return NULL; + skb_reserve(nskb, NET_IP_ALIGN); + + skb_reset_mac_header(nskb); + skb_set_network_header(nskb, + skb_network_header(skb) - skb->head); + skb_set_transport_header(nskb, + skb_transport_header(skb) - skb->head); + skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len)); + kfree_skb(skb); + } + + /* skb is freed when it fails */ + if (skb_put_padto(nskb, nskb->len + padlen)) + return NULL; + + tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); + tag[0] = 0; + tag[1] = 1 << p->dp->index; /* destination port */ + + return nskb; +} + +static struct sk_buff *ksz_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, + struct net_device *orig_dev) +{ + struct dsa_switch_tree *dst = dev->dsa_ptr; + struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); + struct dsa_switch *ds = cpu_dp->ds; + u8 *tag; + int source_port; + + tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; + + source_port = tag[0] & 7; + if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) + return NULL; + + pskb_trim_rcsum(skb, skb->len - KSZ_EGRESS_TAG_LEN); + + skb->dev = ds->ports[source_port].netdev; + + return skb; +} + +const struct dsa_device_ops ksz_netdev_ops = { + .xmit = ksz_xmit, + .rcv = ksz_rcv, +}; diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index 70130ed5c21a..247774d149f9 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -14,7 +14,7 @@ #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/slab.h> -#include <net/dsa.h> + #include "dsa_priv.h" /* To define the outgoing port and to discover the incoming port a regular @@ -52,7 +52,7 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) if (skb_cow_head(skb, LAN9303_TAG_LEN) < 0) { dev_dbg(&dev->dev, "Cannot make room for the special tag. Dropping packet\n"); - goto out_free; + return NULL; } /* provide 'LAN9303_TAG_LEN' bytes additional space */ @@ -66,9 +66,6 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) lan9303_tag[1] = htons(p->dp->index | BIT(4)); return skb; -out_free: - kfree_skb(skb); - return NULL; } static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index 837cdddb53f0..2f32b7ea3365 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -13,7 +13,7 @@ */ #include <linux/etherdevice.h> -#include <net/dsa.h> + #include "dsa_priv.h" #define MTK_HDR_LEN 4 @@ -27,7 +27,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, u8 *mtk_tag; if (skb_cow_head(skb, MTK_HDR_LEN) < 0) - goto out_free; + return NULL; skb_push(skb, MTK_HDR_LEN); @@ -41,10 +41,6 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, mtk_tag[3] = 0; return skb; - -out_free: - kfree_skb(skb); - return NULL; } static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, @@ -57,7 +53,7 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, __be16 *phdr, hdr; if (unlikely(!pskb_may_pull(skb, MTK_HDR_LEN))) - goto out_drop; + return NULL; /* The MTK header is added by the switch between src addr * and ethertype at this point, skb->data points to 2 bytes @@ -79,19 +75,16 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, */ ds = dst->ds[0]; if (!ds) - goto out_drop; + return NULL; /* Get source port information */ port = (hdr & MTK_HDR_RECV_SOURCE_PORT_MASK); if (!ds->ports[port].netdev) - goto out_drop; + return NULL; skb->dev = ds->ports[port].netdev; return skb; - -out_drop: - return NULL; } const struct dsa_device_ops mtk_netdev_ops = { diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 3ba3f59f7a34..1867a3d11f28 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -12,7 +12,7 @@ */ #include <linux/etherdevice.h> -#include <net/dsa.h> + #include "dsa_priv.h" #define QCA_HDR_LEN 2 @@ -45,7 +45,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_bytes += skb->len; if (skb_cow_head(skb, 0) < 0) - goto out_free; + return NULL; skb_push(skb, QCA_HDR_LEN); @@ -60,10 +60,6 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) *phdr = htons(hdr); return skb; - -out_free: - kfree_skb(skb); - return NULL; } static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, @@ -71,13 +67,14 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, struct net_device *orig_dev) { struct dsa_switch_tree *dst = dev->dsa_ptr; + struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); struct dsa_switch *ds; u8 ver; int port; __be16 *phdr, hdr; if (unlikely(!pskb_may_pull(skb, QCA_HDR_LEN))) - goto out_drop; + return NULL; /* The QCA header is added by the switch between src addr and Ethertype * At this point, skb->data points to ethertype so header should be @@ -89,7 +86,7 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, /* Make sure the version is correct */ ver = (hdr & QCA_HDR_RECV_VERSION_MASK) >> QCA_HDR_RECV_VERSION_S; if (unlikely(ver != QCA_HDR_VERSION)) - goto out_drop; + return NULL; /* Remove QCA tag and recalculate checksum */ skb_pull_rcsum(skb, QCA_HDR_LEN); @@ -99,22 +96,19 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, /* This protocol doesn't support cascading multiple switches so it's * safe to assume the switch is first in the tree */ - ds = dst->cpu_switch; + ds = cpu_dp->ds; if (!ds) - goto out_drop; + return NULL; /* Get source port information */ port = (hdr & QCA_HDR_RECV_SOURCE_PORT_MASK); if (!ds->ports[port].netdev) - goto out_drop; + return NULL; /* Update skb & forward the frame accordingly */ skb->dev = ds->ports[port].netdev; return skb; - -out_drop: - return NULL; } const struct dsa_device_ops qca_netdev_ops = { diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index aafc2fc74c30..b09e56214005 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -11,7 +11,7 @@ #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/slab.h> -#include <net/dsa.h> + #include "dsa_priv.h" static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) @@ -32,10 +32,8 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) padlen = 60 - skb->len; nskb = alloc_skb(NET_IP_ALIGN + skb->len + padlen + 4, GFP_ATOMIC); - if (nskb == NULL) { - kfree_skb(skb); + if (!nskb) return NULL; - } skb_reserve(nskb, NET_IP_ALIGN); skb_reset_mac_header(nskb); @@ -45,8 +43,7 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) kfree_skb(skb); if (padlen) { - u8 *pad = skb_put(nskb, padlen); - memset(pad, 0, padlen); + skb_put_zero(nskb, padlen); } trailer = skb_put(nskb, 4); @@ -63,32 +60,28 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, struct net_device *orig_dev) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds; + struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); + struct dsa_switch *ds = cpu_dp->ds; u8 *trailer; int source_port; - ds = dst->cpu_switch; - if (skb_linearize(skb)) - goto out_drop; + return NULL; trailer = skb_tail_pointer(skb) - 4; if (trailer[0] != 0x80 || (trailer[1] & 0xf8) != 0x00 || (trailer[2] & 0xef) != 0x00 || trailer[3] != 0x00) - goto out_drop; + return NULL; source_port = trailer[1] & 7; if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) - goto out_drop; + return NULL; pskb_trim_rcsum(skb, skb->len - 4); skb->dev = ds->ports[source_port].netdev; return skb; - -out_drop: - return NULL; } const struct dsa_device_ops trailer_netdev_ops = { diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 1446810047f5..eaeba9b99a73 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -83,7 +83,7 @@ int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { - struct ethhdr *eth = (struct ethhdr *)skb_push(skb, ETH_HLEN); + struct ethhdr *eth = skb_push(skb, ETH_HLEN); if (type != ETH_P_802_3 && type != ETH_P_802_2) eth->h_proto = htons(type); diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 0a0a392dc2bd..4e7bdb213cd0 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -284,12 +284,12 @@ static void send_hsr_supervision_frame(struct hsr_port *master, skb_reset_mac_header(skb); if (hsrVer > 0) { - hsr_tag = (typeof(hsr_tag)) skb_put(skb, sizeof(struct hsr_tag)); + hsr_tag = skb_put(skb, sizeof(struct hsr_tag)); hsr_tag->encap_proto = htons(ETH_P_PRP); set_hsr_tag_LSDU_size(hsr_tag, HSR_V1_SUP_LSDUSIZE); } - hsr_stag = (typeof(hsr_stag)) skb_put(skb, sizeof(struct hsr_sup_tag)); + hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsrVer ? 0x0 : 0xf)); set_hsr_stag_HSR_Ver(hsr_stag, hsrVer); @@ -311,7 +311,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr_stag->HSR_TLV_Length = hsrVer ? sizeof(struct hsr_sup_payload) : 12; /* Payload: MacAddressA */ - hsr_sp = (typeof(hsr_sp)) skb_put(skb, sizeof(struct hsr_sup_payload)); + hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->MacAddressA, master->dev->dev_addr); skb_put_padto(skb, ETH_ZLEN + HSR_HLEN); diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 81dac16933fc..b9cce0fd5696 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -33,7 +33,8 @@ static const struct nla_policy hsr_policy[IFLA_HSR_MAX + 1] = { * hsr_dev_setup routine has been executed. Nice! */ static int hsr_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net_device *link[2]; unsigned char multicast_spec, hsr_version; diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 0a866f332290..de2661cd0328 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -111,7 +111,8 @@ static void lowpan_setup(struct net_device *ldev) ldev->features |= NETIF_F_NETNS_LOCAL; } -static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[]) +static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != IEEE802154_ADDR_LEN) @@ -121,7 +122,8 @@ static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[]) } static int lowpan_newlink(struct net *src_net, struct net_device *ldev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net_device *wdev; int ret; diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c index dbb476d7d38f..e6ff5128e61a 100644 --- a/net/ieee802154/6lowpan/tx.c +++ b/net/ieee802154/6lowpan/tx.c @@ -121,8 +121,7 @@ lowpan_alloc_frag(struct sk_buff *skb, int size, *mac_cb(frag) = *mac_cb(skb); if (frag1) { - memcpy(skb_put(frag, skb->mac_len), - skb_mac_header(skb), skb->mac_len); + skb_put_data(frag, skb_mac_header(skb), skb->mac_len); } else { rc = wpan_dev_hard_header(frag, wdev, &master_hdr->dest, @@ -152,8 +151,8 @@ lowpan_xmit_fragment(struct sk_buff *skb, const struct ieee802154_hdr *wpan_hdr, if (IS_ERR(frag)) return PTR_ERR(frag); - memcpy(skb_put(frag, frag_hdrlen), frag_hdr, frag_hdrlen); - memcpy(skb_put(frag, len), skb_network_header(skb) + offset, len); + skb_put_data(frag, frag_hdr, frag_hdrlen); + skb_put_data(frag, skb_network_header(skb) + offset, len); raw_dump_table(__func__, " fragment dump", frag->data, frag->len); diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index eedba7670b51..a60658c85a9a 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -301,15 +301,14 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) goto out_skb; skb->dev = dev; - skb->sk = sk; skb->protocol = htons(ETH_P_IEEE802154); - dev_put(dev); - err = dev_queue_xmit(skb); if (err > 0) err = net_xmit_errno(err); + dev_put(dev); + return err ?: size; out_skb: @@ -690,15 +689,14 @@ static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) goto out_skb; skb->dev = dev; - skb->sk = sk; skb->protocol = htons(ETH_P_IEEE802154); - dev_put(dev); - err = dev_queue_xmit(skb); if (err > 0) err = net_xmit_errno(err); + dev_put(dev); + return err ?: size; out_skb: diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index f83de23a30e7..afcb435adfbe 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -8,7 +8,7 @@ obj-y := route.o inetpeer.o protocol.o \ inet_timewait_sock.o inet_connection_sock.o \ tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \ tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \ - tcp_rate.o tcp_recovery.o \ + tcp_rate.o tcp_recovery.o tcp_ulp.o \ tcp_offload.o datagram.o raw.o udp.o udplite.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 58925b6597de..76c2077c3f5b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -150,7 +150,7 @@ void inet_sock_destruct(struct sock *sk) } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); - WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(sk->sk_wmem_queued); WARN_ON(sk->sk_forward_alloc); diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 22377c8ff14b..37db44f60718 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -1,5 +1,6 @@ #define pr_fmt(fmt) "IPsec: " fmt +#include <crypto/algapi.h> #include <crypto/hash.h> #include <linux/err.h> #include <linux/module.h> @@ -220,7 +221,9 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); sg_init_table(sg, nfrags + sglists); - skb_to_sgvec_nomark(skb, sg, 0, skb->len); + err = skb_to_sgvec_nomark(skb, sg, 0, skb->len); + if (unlikely(err < 0)) + goto out_free; if (x->props.flags & XFRM_STATE_ESN) { /* Attach seqhi sg right after packet payload */ @@ -277,7 +280,7 @@ static void ah_input_done(struct crypto_async_request *base, int err) auth_data = ah_tmp_auth(work_iph, ihl); icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len); - err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0; + err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0; if (err) goto out; @@ -393,7 +396,9 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, ihl); sg_init_table(sg, nfrags + sglists); - skb_to_sgvec_nomark(skb, sg, 0, skb->len); + err = skb_to_sgvec_nomark(skb, sg, 0, skb->len); + if (unlikely(err < 0)) + goto out_free; if (x->props.flags & XFRM_STATE_ESN) { /* Attach seqhi sg right after packet payload */ @@ -413,7 +418,7 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) goto out_free; } - err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0; + err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0; if (err) goto out_free; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index e9f3386a528b..8b52179ddc6e 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -539,7 +539,7 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, skb_reserve(skb, hlen); skb_reset_network_header(skb); - arp = (struct arphdr *) skb_put(skb, arp_hdr_len(dev)); + arp = skb_put(skb, arp_hdr_len(dev)); skb->dev = dev; skb->protocol = htons(ETH_P_ARP); if (!src_hw) @@ -1113,13 +1113,17 @@ static int arp_invalidate(struct net_device *dev, __be32 ip) { struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev); int err = -ENXIO; + struct neigh_table *tbl = &arp_tbl; if (neigh) { if (neigh->nud_state & ~NUD_NOARP) err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_ADMIN, 0); + write_lock_bh(&tbl->lock); neigh_release(neigh); + neigh_remove_one(neigh, tbl); + write_unlock_bh(&tbl->lock); } return err; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index ae206163c273..c4c6e1969ed0 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -265,7 +265,7 @@ static int cipso_v4_cache_check(const unsigned char *key, entry->key_len == key_len && memcmp(entry->key, key, key_len) == 0) { entry->activity += 1; - atomic_inc(&entry->lsm_data->refcount); + refcount_inc(&entry->lsm_data->refcount); secattr->cache = entry->lsm_data; secattr->flags |= NETLBL_SECATTR_CACHE; secattr->type = NETLBL_NLTYPE_CIPSOV4; @@ -332,7 +332,7 @@ int cipso_v4_cache_add(const unsigned char *cipso_ptr, } entry->key_len = cipso_ptr_len; entry->hash = cipso_v4_map_cache_hash(cipso_ptr, cipso_ptr_len); - atomic_inc(&secattr->cache->refcount); + refcount_inc(&secattr->cache->refcount); entry->lsm_data = secattr->cache; bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETS - 1); @@ -375,7 +375,7 @@ static struct cipso_v4_doi *cipso_v4_doi_search(u32 doi) struct cipso_v4_doi *iter; list_for_each_entry_rcu(iter, &cipso_v4_doi_list, list) - if (iter->doi == doi && atomic_read(&iter->refcount)) + if (iter->doi == doi && refcount_read(&iter->refcount)) return iter; return NULL; } @@ -429,7 +429,7 @@ int cipso_v4_doi_add(struct cipso_v4_doi *doi_def, } } - atomic_set(&doi_def->refcount, 1); + refcount_set(&doi_def->refcount, 1); spin_lock(&cipso_v4_doi_list_lock); if (cipso_v4_doi_search(doi_def->doi)) { @@ -533,7 +533,7 @@ int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info) ret_val = -ENOENT; goto doi_remove_return; } - if (!atomic_dec_and_test(&doi_def->refcount)) { + if (!refcount_dec_and_test(&doi_def->refcount)) { spin_unlock(&cipso_v4_doi_list_lock); ret_val = -EBUSY; goto doi_remove_return; @@ -576,7 +576,7 @@ struct cipso_v4_doi *cipso_v4_doi_getdef(u32 doi) doi_def = cipso_v4_doi_search(doi); if (!doi_def) goto doi_getdef_return; - if (!atomic_inc_not_zero(&doi_def->refcount)) + if (!refcount_inc_not_zero(&doi_def->refcount)) doi_def = NULL; doi_getdef_return: @@ -597,7 +597,7 @@ void cipso_v4_doi_putdef(struct cipso_v4_doi *doi_def) if (!doi_def) return; - if (!atomic_dec_and_test(&doi_def->refcount)) + if (!refcount_dec_and_test(&doi_def->refcount)) return; spin_lock(&cipso_v4_doi_list_lock); list_del_rcu(&doi_def->list); @@ -630,7 +630,7 @@ int cipso_v4_doi_walk(u32 *skip_cnt, rcu_read_lock(); list_for_each_entry_rcu(iter_doi, &cipso_v4_doi_list, list) - if (atomic_read(&iter_doi->refcount) > 0) { + if (refcount_read(&iter_doi->refcount) > 0) { if (doi_cnt++ < *skip_cnt) continue; ret_val = callback(iter_doi, cb_arg); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index df14815a3b8c..38d9af9b917c 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -176,6 +176,7 @@ EXPORT_SYMBOL(__ip_dev_find); static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); +static BLOCKING_NOTIFIER_HEAD(inetaddr_validator_chain); static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, int destroy); #ifdef CONFIG_SYSCTL @@ -251,7 +252,7 @@ static struct in_device *inetdev_init(struct net_device *dev) /* Reference in_dev->dev */ dev_hold(dev); /* Account for reference dev->ip_ptr (below) */ - in_dev_hold(in_dev); + refcount_set(&in_dev->refcnt, 1); err = devinet_sysctl_register(in_dev); if (err) { @@ -441,6 +442,8 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, { struct in_device *in_dev = ifa->ifa_dev; struct in_ifaddr *ifa1, **ifap, **last_primary; + struct in_validator_info ivi; + int ret; ASSERT_RTNL(); @@ -471,6 +474,23 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, } } + /* Allow any devices that wish to register ifaddr validtors to weigh + * in now, before changes are committed. The rntl lock is serializing + * access here, so the state should not change between a validator call + * and a final notify on commit. This isn't invoked on promotion under + * the assumption that validators are checking the address itself, and + * not the flags. + */ + ivi.ivi_addr = ifa->ifa_address; + ivi.ivi_dev = ifa->ifa_dev; + ret = blocking_notifier_call_chain(&inetaddr_validator_chain, + NETDEV_UP, &ivi); + ret = notifier_to_errno(ret); + if (ret) { + inet_free_ifa(ifa); + return ret; + } + if (!(ifa->ifa_flags & IFA_F_SECONDARY)) { prandom_seed((__force u32) ifa->ifa_local); ifap = last_primary; @@ -1356,6 +1376,19 @@ int unregister_inetaddr_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_inetaddr_notifier); +int register_inetaddr_validator_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&inetaddr_validator_chain, nb); +} +EXPORT_SYMBOL(register_inetaddr_validator_notifier); + +int unregister_inetaddr_validator_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&inetaddr_validator_chain, + nb); +} +EXPORT_SYMBOL(unregister_inetaddr_validator_notifier); + /* Rename ifa_labels for a device name change. Make some effort to preserve * existing alias numbering and to create unique labels if possible. */ diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 93322f895eab..0cbee0a666ff 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -307,7 +307,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * skb->data_len += tailen; skb->truesize += tailen; if (sk) - atomic_add(tailen, &sk->sk_wmem_alloc); + refcount_add(tailen, &sk->sk_wmem_alloc); goto out; } @@ -377,9 +377,11 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * esp->esph = esph; sg_init_table(sg, esp->nfrags); - skb_to_sgvec(skb, sg, - (unsigned char *)esph - skb->data, - assoclen + ivlen + esp->clen + alen); + err = skb_to_sgvec(skb, sg, + (unsigned char *)esph - skb->data, + assoclen + ivlen + esp->clen + alen); + if (unlikely(err < 0)) + goto error; if (!esp->inplace) { int allocsize; @@ -403,9 +405,11 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * spin_unlock_bh(&x->lock); sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1); - skb_to_sgvec(skb, dsg, - (unsigned char *)esph - skb->data, - assoclen + ivlen + esp->clen + alen); + err = skb_to_sgvec(skb, dsg, + (unsigned char *)esph - skb->data, + assoclen + ivlen + esp->clen + alen); + if (unlikely(err < 0)) + goto error; } if ((x->props.flags & XFRM_STATE_ESN)) @@ -605,7 +609,7 @@ static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi) * decryption. */ if ((x->props.flags & XFRM_STATE_ESN)) { - esph = (void *)skb_push(skb, 4); + esph = skb_push(skb, 4); *seqhi = esph->spi; esph->spi = esph->seq_no; esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; @@ -690,7 +694,9 @@ skip_cow: esp_input_set_header(skb, seqhi); sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + err = skb_to_sgvec(skb, sg, 0, skb->len); + if (unlikely(err < 0)) + goto out; skb->ip_summed = CHECKSUM_NONE; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 83e3ed258467..044d2a159a3c 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -588,13 +588,15 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (cmd == SIOCDELRT) { tb = fib_get_table(net, cfg.fc_table); if (tb) - err = fib_table_delete(net, tb, &cfg); + err = fib_table_delete(net, tb, &cfg, + NULL); else err = -ESRCH; } else { tb = fib_new_table(net, cfg.fc_table); if (tb) - err = fib_table_insert(net, tb, &cfg); + err = fib_table_insert(net, tb, + &cfg, NULL); else err = -ENOBUFS; } @@ -626,14 +628,15 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, - struct nlmsghdr *nlh, struct fib_config *cfg) + struct nlmsghdr *nlh, struct fib_config *cfg, + struct netlink_ext_ack *extack) { struct nlattr *attr; int err, remaining; struct rtmsg *rtm; err = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy, - NULL); + extack); if (err < 0) goto errout; @@ -654,6 +657,7 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, cfg->fc_nlinfo.nl_net = net; if (cfg->fc_type > RTN_MAX) { + NL_SET_ERR_MSG(extack, "Invalid route type"); err = -EINVAL; goto errout; } @@ -681,7 +685,8 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, break; case RTA_MULTIPATH: err = lwtunnel_valid_encap_type_attr(nla_data(attr), - nla_len(attr)); + nla_len(attr), + extack); if (err < 0) goto errout; cfg->fc_mp = nla_data(attr); @@ -698,7 +703,8 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, break; case RTA_ENCAP_TYPE: cfg->fc_encap_type = nla_get_u16(attr); - err = lwtunnel_valid_encap_type(cfg->fc_encap_type); + err = lwtunnel_valid_encap_type(cfg->fc_encap_type, + extack); if (err < 0) goto errout; break; @@ -718,17 +724,18 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib_table *tb; int err; - err = rtm_to_fib_config(net, skb, nlh, &cfg); + err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; tb = fib_get_table(net, cfg.fc_table); if (!tb) { + NL_SET_ERR_MSG(extack, "FIB table does not exist"); err = -ESRCH; goto errout; } - err = fib_table_delete(net, tb, &cfg); + err = fib_table_delete(net, tb, &cfg, extack); errout: return err; } @@ -741,7 +748,7 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib_table *tb; int err; - err = rtm_to_fib_config(net, skb, nlh, &cfg); + err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; @@ -751,7 +758,7 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; } - err = fib_table_insert(net, tb, &cfg); + err = fib_table_insert(net, tb, &cfg, extack); errout: return err; } @@ -845,9 +852,9 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad cfg.fc_scope = RT_SCOPE_HOST; if (cmd == RTM_NEWROUTE) - fib_table_insert(net, tb, &cfg); + fib_table_insert(net, tb, &cfg, NULL); else - fib_table_delete(net, tb, &cfg); + fib_table_delete(net, tb, &cfg, NULL); } void fib_add_ifaddr(struct in_ifaddr *ifa) @@ -1327,13 +1334,14 @@ static struct pernet_operations fib_net_ops = { void __init ip_fib_init(void) { - rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL); - rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL); - rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL); + fib_trie_init(); register_pernet_subsys(&fib_net_ops); + register_netdevice_notifier(&fib_netdev_notifier); register_inetaddr_notifier(&fib_inetaddr_notifier); - fib_trie_init(); + rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL); + rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL); + rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL); } diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 9c02920725db..769ab87ebc4b 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -28,8 +28,10 @@ static inline void fib_alias_accessed(struct fib_alias *fa) /* Exported by fib_semantics.c */ void fib_release_info(struct fib_info *); -struct fib_info *fib_create_info(struct fib_config *cfg); -int fib_nh_match(struct fib_config *cfg, struct fib_info *fi); +struct fib_info *fib_create_info(struct fib_config *cfg, + struct netlink_ext_ack *extack); +int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, + struct netlink_ext_ack *extack); int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index ad9ad4aab5da..222100103808 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -32,6 +32,7 @@ #include <linux/skbuff.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/netlink.h> #include <net/arp.h> #include <net/ip.h> @@ -151,7 +152,8 @@ static void rt_fibinfo_free(struct rtable __rcu **rtp) * free_fib_info_rcu() */ - dst_free(&rt->dst); + dst_dev_put(&rt->dst); + dst_release_immediate(&rt->dst); } static void free_nh_exceptions(struct fib_nh *nh) @@ -193,8 +195,10 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp) struct rtable *rt; rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1); - if (rt) - dst_free(&rt->dst); + if (rt) { + dst_dev_put(&rt->dst); + dst_release_immediate(&rt->dst); + } } free_percpu(rtp); } @@ -456,7 +460,8 @@ static int fib_detect_death(struct fib_info *fi, int order, #ifdef CONFIG_IP_ROUTE_MULTIPATH -static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining) +static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining, + struct netlink_ext_ack *extack) { int nhs = 0; @@ -466,22 +471,35 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining) } /* leftover implies invalid nexthop configuration, discard it */ - return remaining > 0 ? 0 : nhs; + if (remaining > 0) { + NL_SET_ERR_MSG(extack, + "Invalid nexthop configuration - extra data after nexthops"); + nhs = 0; + } + + return nhs; } static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, - int remaining, struct fib_config *cfg) + int remaining, struct fib_config *cfg, + struct netlink_ext_ack *extack) { int ret; change_nexthops(fi) { int attrlen; - if (!rtnh_ok(rtnh, remaining)) + if (!rtnh_ok(rtnh, remaining)) { + NL_SET_ERR_MSG(extack, + "Invalid nexthop configuration - extra data after nexthop"); return -EINVAL; + } - if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) { + NL_SET_ERR_MSG(extack, + "Invalid flags for nexthop - can not contain DEAD or LINKDOWN"); return -EINVAL; + } nexthop_nh->nh_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; @@ -507,13 +525,17 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); - if (!nla_entype) + if (!nla_entype) { + NL_SET_BAD_ATTR(extack, nla); + NL_SET_ERR_MSG(extack, + "Encap type is missing"); goto err_inval; + } ret = lwtunnel_build_state(nla_get_u16( nla_entype), nla, AF_INET, cfg, - &lwtstate); + &lwtstate, extack); if (ret) goto errout; nexthop_nh->nh_lwtstate = @@ -595,7 +617,8 @@ static inline void fib_add_weight(struct fib_info *fi, static int fib_encap_match(u16 encap_type, struct nlattr *encap, const struct fib_nh *nh, - const struct fib_config *cfg) + const struct fib_config *cfg, + struct netlink_ext_ack *extack) { struct lwtunnel_state *lwtstate; int ret, result = 0; @@ -603,8 +626,8 @@ static int fib_encap_match(u16 encap_type, if (encap_type == LWTUNNEL_ENCAP_NONE) return 0; - ret = lwtunnel_build_state(encap_type, encap, - AF_INET, cfg, &lwtstate); + ret = lwtunnel_build_state(encap_type, encap, AF_INET, + cfg, &lwtstate, extack); if (!ret) { result = lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate); lwtstate_free(lwtstate); @@ -613,7 +636,8 @@ static int fib_encap_match(u16 encap_type, return result; } -int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) +int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, + struct netlink_ext_ack *extack) { #ifdef CONFIG_IP_ROUTE_MULTIPATH struct rtnexthop *rtnh; @@ -625,9 +649,9 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) if (cfg->fc_oif || cfg->fc_gw) { if (cfg->fc_encap) { - if (fib_encap_match(cfg->fc_encap_type, - cfg->fc_encap, fi->fib_nh, cfg)) - return 1; + if (fib_encap_match(cfg->fc_encap_type, cfg->fc_encap, + fi->fib_nh, cfg, extack)) + return 1; } if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) && (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw)) @@ -716,7 +740,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) * |-> {local prefix} (terminal node) */ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, - struct fib_nh *nh) + struct fib_nh *nh, struct netlink_ext_ack *extack) { int err = 0; struct net *net; @@ -729,16 +753,25 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, if (nh->nh_flags & RTNH_F_ONLINK) { unsigned int addr_type; - if (cfg->fc_scope >= RT_SCOPE_LINK) + if (cfg->fc_scope >= RT_SCOPE_LINK) { + NL_SET_ERR_MSG(extack, + "Nexthop has invalid scope"); return -EINVAL; + } dev = __dev_get_by_index(net, nh->nh_oif); if (!dev) return -ENODEV; - if (!(dev->flags & IFF_UP)) + if (!(dev->flags & IFF_UP)) { + NL_SET_ERR_MSG(extack, + "Nexthop device is not up"); return -ENETDOWN; + } addr_type = inet_addr_type_dev_table(net, dev, nh->nh_gw); - if (addr_type != RTN_UNICAST) + if (addr_type != RTN_UNICAST) { + NL_SET_ERR_MSG(extack, + "Nexthop has invalid gateway"); return -EINVAL; + } if (!netif_carrier_ok(dev)) nh->nh_flags |= RTNH_F_LINKDOWN; nh->nh_dev = dev; @@ -778,18 +811,25 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, } if (err) { + NL_SET_ERR_MSG(extack, + "Nexthop has invalid gateway"); rcu_read_unlock(); return err; } } err = -EINVAL; - if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) + if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) { + NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway"); goto out; + } nh->nh_scope = res.scope; nh->nh_oif = FIB_RES_OIF(res); nh->nh_dev = dev = FIB_RES_DEV(res); - if (!dev) + if (!dev) { + NL_SET_ERR_MSG(extack, + "No egress device for nexthop gateway"); goto out; + } dev_hold(dev); if (!netif_carrier_ok(dev)) nh->nh_flags |= RTNH_F_LINKDOWN; @@ -797,17 +837,21 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, } else { struct in_device *in_dev; - if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) + if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) { + NL_SET_ERR_MSG(extack, + "Invalid flags for nexthop - PERVASIVE and ONLINK can not be set"); return -EINVAL; - + } rcu_read_lock(); err = -ENODEV; in_dev = inetdev_by_index(net, nh->nh_oif); if (!in_dev) goto out; err = -ENETDOWN; - if (!(in_dev->dev->flags & IFF_UP)) + if (!(in_dev->dev->flags & IFF_UP)) { + NL_SET_ERR_MSG(extack, "Device for nexthop is not up"); goto out; + } nh->nh_dev = in_dev->dev; dev_hold(nh->nh_dev); nh->nh_scope = RT_SCOPE_HOST; @@ -982,7 +1026,8 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg) return 0; } -struct fib_info *fib_create_info(struct fib_config *cfg) +struct fib_info *fib_create_info(struct fib_config *cfg, + struct netlink_ext_ack *extack) { int err; struct fib_info *fi = NULL; @@ -994,15 +1039,20 @@ struct fib_info *fib_create_info(struct fib_config *cfg) goto err_inval; /* Fast check to catch the most weird cases */ - if (fib_props[cfg->fc_type].scope > cfg->fc_scope) + if (fib_props[cfg->fc_type].scope > cfg->fc_scope) { + NL_SET_ERR_MSG(extack, "Invalid scope"); goto err_inval; + } - if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) { + NL_SET_ERR_MSG(extack, + "Invalid rtm_flags - can not contain DEAD or LINKDOWN"); goto err_inval; + } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (cfg->fc_mp) { - nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len); + nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len, extack); if (nhs == 0) goto err_inval; } @@ -1065,18 +1115,29 @@ struct fib_info *fib_create_info(struct fib_config *cfg) if (cfg->fc_mp) { #ifdef CONFIG_IP_ROUTE_MULTIPATH - err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg); + err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg, extack); if (err != 0) goto failure; - if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif) + if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif) { + NL_SET_ERR_MSG(extack, + "Nexthop device index does not match RTA_OIF"); goto err_inval; - if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw) + } + if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw) { + NL_SET_ERR_MSG(extack, + "Nexthop gateway does not match RTA_GATEWAY"); goto err_inval; + } #ifdef CONFIG_IP_ROUTE_CLASSID - if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) + if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) { + NL_SET_ERR_MSG(extack, + "Nexthop class id does not match RTA_FLOW"); goto err_inval; + } #endif #else + NL_SET_ERR_MSG(extack, + "Multipath support not enabled in kernel"); goto err_inval; #endif } else { @@ -1085,11 +1146,14 @@ struct fib_info *fib_create_info(struct fib_config *cfg) if (cfg->fc_encap) { struct lwtunnel_state *lwtstate; - if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE) + if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE) { + NL_SET_ERR_MSG(extack, + "LWT encap type not specified"); goto err_inval; + } err = lwtunnel_build_state(cfg->fc_encap_type, cfg->fc_encap, AF_INET, cfg, - &lwtstate); + &lwtstate, extack); if (err) goto failure; @@ -1109,8 +1173,11 @@ struct fib_info *fib_create_info(struct fib_config *cfg) } if (fib_props[cfg->fc_type].error) { - if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp) + if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp) { + NL_SET_ERR_MSG(extack, + "Gateway, device and multipath can not be specified for this route type"); goto err_inval; + } goto link_it; } else { switch (cfg->fc_type) { @@ -1121,19 +1188,30 @@ struct fib_info *fib_create_info(struct fib_config *cfg) case RTN_MULTICAST: break; default: + NL_SET_ERR_MSG(extack, "Invalid route type"); goto err_inval; } } - if (cfg->fc_scope > RT_SCOPE_HOST) + if (cfg->fc_scope > RT_SCOPE_HOST) { + NL_SET_ERR_MSG(extack, "Invalid scope"); goto err_inval; + } if (cfg->fc_scope == RT_SCOPE_HOST) { struct fib_nh *nh = fi->fib_nh; /* Local address is added. */ - if (nhs != 1 || nh->nh_gw) + if (nhs != 1) { + NL_SET_ERR_MSG(extack, + "Route with host scope can not have multiple nexthops"); goto err_inval; + } + if (nh->nh_gw) { + NL_SET_ERR_MSG(extack, + "Route with host scope can not have a gateway"); + goto err_inval; + } nh->nh_scope = RT_SCOPE_NOWHERE; nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif); err = -ENODEV; @@ -1143,7 +1221,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) int linkdown = 0; change_nexthops(fi) { - err = fib_check_nh(cfg, fi, nexthop_nh); + err = fib_check_nh(cfg, fi, nexthop_nh, extack); if (err != 0) goto failure; if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN) @@ -1153,8 +1231,10 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_flags |= RTNH_F_LINKDOWN; } - if (fi->fib_prefsrc && !fib_valid_prefsrc(cfg, fi->fib_prefsrc)) + if (fi->fib_prefsrc && !fib_valid_prefsrc(cfg, fi->fib_prefsrc)) { + NL_SET_ERR_MSG(extack, "Invalid prefsrc address"); goto err_inval; + } change_nexthops(fi) { fib_info_update_nh_saddr(net, nexthop_nh); @@ -1173,7 +1253,7 @@ link_it: } fi->fib_treeref++; - atomic_inc(&fi->fib_clntref); + refcount_set(&fi->fib_clntref, 1); spin_lock_bh(&fib_info_lock); hlist_add_head(&fi->fib_hash, &fib_info_hash[fib_info_hashfn(fi)]); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 51182ff2b441..64668c69dda6 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1099,9 +1099,25 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp, return 0; } +static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) +{ + if (plen > KEYLENGTH) { + NL_SET_ERR_MSG(extack, "Invalid prefix length"); + return false; + } + + if ((plen < KEYLENGTH) && (key << plen)) { + NL_SET_ERR_MSG(extack, + "Invalid prefix for given prefix length"); + return false; + } + + return true; +} + /* Caller must hold RTNL. */ int fib_table_insert(struct net *net, struct fib_table *tb, - struct fib_config *cfg) + struct fib_config *cfg, struct netlink_ext_ack *extack) { enum fib_event_type event = FIB_EVENT_ENTRY_ADD; struct trie *t = (struct trie *)tb->tb_data; @@ -1115,17 +1131,14 @@ int fib_table_insert(struct net *net, struct fib_table *tb, u32 key; int err; - if (plen > KEYLENGTH) - return -EINVAL; - key = ntohl(cfg->fc_dst); - pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); - - if ((plen < KEYLENGTH) && (key << plen)) + if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; - fi = fib_create_info(cfg); + pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); + + fi = fib_create_info(cfg, extack); if (IS_ERR(fi)) { err = PTR_ERR(fi); goto err; @@ -1450,8 +1463,9 @@ found: } if (!(fib_flags & FIB_LOOKUP_NOREF)) - atomic_inc(&fi->fib_clntref); + refcount_inc(&fi->fib_clntref); + res->prefix = htonl(n->key); res->prefixlen = KEYLENGTH - fa->fa_slen; res->nh_sel = nhsel; res->type = fa->fa_type; @@ -1507,7 +1521,7 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp, /* Caller must hold RTNL. */ int fib_table_delete(struct net *net, struct fib_table *tb, - struct fib_config *cfg) + struct fib_config *cfg, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *) tb->tb_data; struct fib_alias *fa, *fa_to_delete; @@ -1517,12 +1531,9 @@ int fib_table_delete(struct net *net, struct fib_table *tb, u8 tos = cfg->fc_tos; u32 key; - if (plen > KEYLENGTH) - return -EINVAL; - key = ntohl(cfg->fc_dst); - if ((plen < KEYLENGTH) && (key << plen)) + if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; l = fib_find_node(t, &tp, key); @@ -1551,7 +1562,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, fi->fib_prefsrc == cfg->fc_prefsrc) && (!cfg->fc_protocol || fi->fib_protocol == cfg->fc_protocol) && - fib_nh_match(cfg, fi) == 0) { + fib_nh_match(cfg, fi, extack) == 0) { fa_to_delete = fa; break; } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 805f6607f8d9..8e0257d01200 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -8,6 +8,7 @@ #include <linux/kernel.h> #include <net/genetlink.h> #include <net/gue.h> +#include <net/fou.h> #include <net/ip.h> #include <net/protocol.h> #include <net/udp.h> @@ -859,25 +860,6 @@ size_t gue_encap_hlen(struct ip_tunnel_encap *e) } EXPORT_SYMBOL(gue_encap_hlen); -static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e, - struct flowi4 *fl4, u8 *protocol, __be16 sport) -{ - struct udphdr *uh; - - skb_push(skb, sizeof(struct udphdr)); - skb_reset_transport_header(skb); - - uh = udp_hdr(skb); - - uh->dest = e->dport; - uh->source = sport; - uh->len = htons(skb->len); - udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb, - fl4->saddr, fl4->daddr, skb->len); - - *protocol = IPPROTO_UDP; -} - int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, __be16 *sport, int type) { @@ -894,24 +876,6 @@ int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, } EXPORT_SYMBOL(__fou_build_header); -int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, - u8 *protocol, struct flowi4 *fl4) -{ - int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM : - SKB_GSO_UDP_TUNNEL; - __be16 sport; - int err; - - err = __fou_build_header(skb, e, protocol, &sport, type); - if (err) - return err; - - fou_build_udp(skb, e, fl4, protocol, sport); - - return 0; -} -EXPORT_SYMBOL(fou_build_header); - int __gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, __be16 *sport, int type) { @@ -985,8 +949,46 @@ int __gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, } EXPORT_SYMBOL(__gue_build_header); -int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, - u8 *protocol, struct flowi4 *fl4) +#ifdef CONFIG_NET_FOU_IP_TUNNELS + +static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e, + struct flowi4 *fl4, u8 *protocol, __be16 sport) +{ + struct udphdr *uh; + + skb_push(skb, sizeof(struct udphdr)); + skb_reset_transport_header(skb); + + uh = udp_hdr(skb); + + uh->dest = e->dport; + uh->source = sport; + uh->len = htons(skb->len); + udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb, + fl4->saddr, fl4->daddr, skb->len); + + *protocol = IPPROTO_UDP; +} + +static int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, + u8 *protocol, struct flowi4 *fl4) +{ + int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM : + SKB_GSO_UDP_TUNNEL; + __be16 sport; + int err; + + err = __fou_build_header(skb, e, protocol, &sport, type); + if (err) + return err; + + fou_build_udp(skb, e, fl4, protocol, sport); + + return 0; +} + +static int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, + u8 *protocol, struct flowi4 *fl4) { int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; @@ -1001,9 +1003,7 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, return 0; } -EXPORT_SYMBOL(gue_build_header); -#ifdef CONFIG_NET_FOU_IP_TUNNELS static const struct ip_tunnel_encap_ops fou_iptun_ops = { .encap_hlen = fou_encap_hlen, diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 9144fa7df2ad..c2be26b98b5f 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -489,7 +489,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); - rt = __ip_route_output_key_hash(net, fl4, skb_in); + rt = ip_route_output_key_hash(net, fl4, skb_in); if (IS_ERR(rt)) return rt; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index ec9a396fa466..28f14afd0dd3 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -173,7 +173,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, static void ip_ma_put(struct ip_mc_list *im) { - if (atomic_dec_and_test(&im->refcnt)) { + if (refcount_dec_and_test(&im->refcnt)) { in_dev_put(im->interface); kfree_rcu(im, rcu); } @@ -199,7 +199,7 @@ static void igmp_stop_timer(struct ip_mc_list *im) { spin_lock_bh(&im->lock); if (del_timer(&im->timer)) - atomic_dec(&im->refcnt); + refcount_dec(&im->refcnt); im->tm_running = 0; im->reporter = 0; im->unsolicit_count = 0; @@ -213,7 +213,7 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) im->tm_running = 1; if (!mod_timer(&im->timer, jiffies+tv+2)) - atomic_inc(&im->refcnt); + refcount_inc(&im->refcnt); } static void igmp_gq_start_timer(struct in_device *in_dev) @@ -249,7 +249,7 @@ static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) spin_unlock_bh(&im->lock); return; } - atomic_dec(&im->refcnt); + refcount_dec(&im->refcnt); } igmp_start_timer(im, max_delay); spin_unlock_bh(&im->lock); @@ -414,7 +414,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, skb = igmpv3_newpack(dev, dev->mtu); if (!skb) return NULL; - pgr = (struct igmpv3_grec *)skb_put(skb, sizeof(struct igmpv3_grec)); + pgr = skb_put(skb, sizeof(struct igmpv3_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; @@ -508,7 +508,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, } if (!skb) return NULL; - psrc = (__be32 *)skb_put(skb, sizeof(__be32)); + psrc = skb_put(skb, sizeof(__be32)); *psrc = psf->sf_inaddr; scount++; stotal++; if ((type == IGMPV3_ALLOW_NEW_SOURCES || @@ -742,7 +742,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, ((u8 *)&iph[1])[2] = 0; ((u8 *)&iph[1])[3] = 0; - ih = (struct igmphdr *)skb_put(skb, sizeof(struct igmphdr)); + ih = skb_put(skb, sizeof(struct igmphdr)); ih->type = type; ih->code = 0; ih->csum = 0; @@ -1374,7 +1374,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) /* initial mode is (EX, empty) */ im->sfmode = MCAST_EXCLUDE; im->sfcount[MCAST_EXCLUDE] = 1; - atomic_set(&im->refcnt, 1); + refcount_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST setup_timer(&im->timer, igmp_timer_expire, (unsigned long)im); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 1054d330bf9d..4089c013cb03 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -25,6 +25,7 @@ #include <net/xfrm.h> #include <net/tcp.h> #include <net/sock_reuseport.h> +#include <net/addrconf.h> #ifdef INET_CSK_DEBUG const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n"; @@ -755,7 +756,7 @@ static void reqsk_queue_hash_req(struct request_sock *req, * are committed to memory and refcnt initialized. */ smp_wmb(); - atomic_set(&req->rsk_refcnt, 2 + 1); + refcount_set(&req->rsk_refcnt, 2 + 1); } void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, @@ -789,7 +790,6 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port; inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num; inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num); - newsk->sk_write_space = sk_stream_write_space; /* listeners have SOCK_RCU_FREE, not the children */ sock_reset_flag(newsk, SOCK_RCU_FREE); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index b5e9317eaf9e..96e95e83cc61 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -276,11 +276,11 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f) void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) { if (del_timer(&fq->timer)) - atomic_dec(&fq->refcnt); + refcount_dec(&fq->refcnt); if (!(fq->flags & INET_FRAG_COMPLETE)) { fq_unlink(fq, f); - atomic_dec(&fq->refcnt); + refcount_dec(&fq->refcnt); } } EXPORT_SYMBOL(inet_frag_kill); @@ -329,7 +329,7 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, */ hlist_for_each_entry(qp, &hb->chain, list) { if (qp->net == nf && f->match(qp, arg)) { - atomic_inc(&qp->refcnt); + refcount_inc(&qp->refcnt); spin_unlock(&hb->chain_lock); qp_in->flags |= INET_FRAG_COMPLETE; inet_frag_put(qp_in, f); @@ -339,9 +339,9 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, #endif qp = qp_in; if (!mod_timer(&qp->timer, jiffies + nf->timeout)) - atomic_inc(&qp->refcnt); + refcount_inc(&qp->refcnt); - atomic_inc(&qp->refcnt); + refcount_inc(&qp->refcnt); hlist_add_head(&qp->list, &hb->chain); spin_unlock(&hb->chain_lock); @@ -370,7 +370,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, setup_timer(&q->timer, f->frag_expire, (unsigned long)q); spin_lock_init(&q->lock); - atomic_set(&q->refcnt, 1); + refcount_set(&q->refcnt, 1); return q; } @@ -405,7 +405,7 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, spin_lock(&hb->chain_lock); hlist_for_each_entry(q, &hb->chain, list) { if (q->net == nf && f->match(q, key)) { - atomic_inc(&q->refcnt); + refcount_inc(&q->refcnt); spin_unlock(&hb->chain_lock); return q; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e9a59d2d91d4..2e3389d614d1 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -43,7 +43,7 @@ static u32 inet_ehashfn(const struct net *net, const __be32 laddr, /* This function handles inet_sock, but also timewait and request sockets * for IPv4/IPv6. */ -u32 sk_ehashfn(const struct sock *sk) +static u32 sk_ehashfn(const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6 && @@ -246,7 +246,7 @@ EXPORT_SYMBOL_GPL(__inet_lookup_listener); /* All sockets share common refcount, but have different destructors */ void sock_gen_put(struct sock *sk) { - if (!atomic_dec_and_test(&sk->sk_refcnt)) + if (!refcount_dec_and_test(&sk->sk_refcnt)) return; if (sk->sk_state == TCP_TIME_WAIT) @@ -287,7 +287,7 @@ begin: continue; if (likely(INET_MATCH(sk, net, acookie, saddr, daddr, ports, dif))) { - if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; if (unlikely(!INET_MATCH(sk, net, acookie, saddr, daddr, ports, dif))) { diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index f8aff2c71cde..5b039159e67a 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -76,7 +76,7 @@ void inet_twsk_free(struct inet_timewait_sock *tw) void inet_twsk_put(struct inet_timewait_sock *tw) { - if (atomic_dec_and_test(&tw->tw_refcnt)) + if (refcount_dec_and_test(&tw->tw_refcnt)) inet_twsk_free(tw); } EXPORT_SYMBOL_GPL(inet_twsk_put); @@ -131,7 +131,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, * We can use atomic_set() because prior spin_lock()/spin_unlock() * committed into memory all tw fields. */ - atomic_set(&tw->tw_refcnt, 4); + refcount_set(&tw->tw_refcnt, 4); inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ @@ -195,7 +195,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, * to a non null value before everything is setup for this * timewait socket. */ - atomic_set(&tw->tw_refcnt, 0); + refcount_set(&tw->tw_refcnt, 0); __module_get(tw->tw_prot->owner); } @@ -278,7 +278,7 @@ restart: atomic_read(&twsk_net(tw)->count)) continue; - if (unlikely(!atomic_inc_not_zero(&tw->tw_refcnt))) + if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) continue; if (unlikely((tw->tw_family != family) || diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 86fa45809540..c5a117cc6619 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -115,7 +115,7 @@ static void inetpeer_gc_worker(struct work_struct *work) n = list_entry(p->gc_list.next, struct inet_peer, gc_list); - if (!atomic_read(&p->refcnt)) { + if (refcount_read(&p->refcnt) == 1) { list_del(&p->gc_list); kmem_cache_free(peer_cachep, p); } @@ -202,10 +202,11 @@ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr, int cmp = inetpeer_addr_cmp(daddr, &u->daddr); if (cmp == 0) { /* Before taking a reference, check if this entry was - * deleted (refcnt=-1) + * deleted (refcnt=0) */ - if (!atomic_add_unless(&u->refcnt, 1, -1)) + if (!refcount_inc_not_zero(&u->refcnt)) { u = NULL; + } return u; } if (cmp == -1) @@ -382,11 +383,10 @@ static int inet_peer_gc(struct inet_peer_base *base, while (stackptr > stack) { stackptr--; p = rcu_deref_locked(**stackptr, base); - if (atomic_read(&p->refcnt) == 0) { + if (refcount_read(&p->refcnt) == 1) { smp_rmb(); delta = (__u32)jiffies - p->dtime; - if (delta >= ttl && - atomic_cmpxchg(&p->refcnt, 0, -1) == 0) { + if (delta >= ttl && refcount_dec_if_one(&p->refcnt)) { p->gc_next = gchead; gchead = p; } @@ -432,7 +432,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, relookup: p = lookup(daddr, stack, base); if (p != peer_avl_empty) { - atomic_inc(&p->refcnt); + refcount_inc(&p->refcnt); write_sequnlock_bh(&base->lock); return p; } @@ -444,7 +444,7 @@ relookup: p = create ? kmem_cache_alloc(peer_cachep, GFP_ATOMIC) : NULL; if (p) { p->daddr = *daddr; - atomic_set(&p->refcnt, 1); + refcount_set(&p->refcnt, 2); atomic_set(&p->rid, 0); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; @@ -468,7 +468,7 @@ void inet_putpeer(struct inet_peer *p) { p->dtime = (__u32)jiffies; smp_mb__before_atomic(); - atomic_dec(&p->refcnt); + refcount_dec(&p->refcnt); } EXPORT_SYMBOL_GPL(inet_putpeer); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b3cdeec85f1f..9a8cfac503dc 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -312,7 +312,7 @@ static int ip_frag_reinit(struct ipq *qp) unsigned int sum_truesize = 0; if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) { - atomic_inc(&qp->q.refcnt); + refcount_inc(&qp->q.refcnt); return -ETIMEDOUT; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index e90c80a548ad..7a7829e839c2 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -592,7 +592,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, struct iphdr *iph; struct gre_base_hdr *greh; - iph = (struct iphdr *)skb_push(skb, t->hlen + sizeof(*iph)); + iph = skb_push(skb, t->hlen + sizeof(*iph)); greh = (struct gre_base_hdr *)(iph+1); greh->flags = gre_tnl_flags_to_gre_flags(t->parms.o_flags); greh->protocol = htons(type); @@ -779,7 +779,8 @@ static struct pernet_operations ipgre_net_ops = { .size = sizeof(struct ip_tunnel_net), }; -static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { __be16 flags; @@ -802,7 +803,8 @@ static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } -static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { __be32 daddr; @@ -823,7 +825,7 @@ static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) } out: - return ipgre_tunnel_validate(tb, data); + return ipgre_tunnel_validate(tb, data, extack); } static int ipgre_netlink_parms(struct net_device *dev, @@ -957,7 +959,8 @@ static void ipgre_tap_setup(struct net_device *dev) } static int ipgre_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; @@ -979,7 +982,8 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, } static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; @@ -1155,7 +1159,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, t = netdev_priv(dev); t->collect_md = true; - err = ipgre_newlink(net, dev, tb, NULL); + err = ipgre_newlink(net, dev, tb, NULL, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 532b36e9ce2a..50c74cd890bc 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -173,7 +173,8 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, } skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + if (!skb->mark) + skb->mark = sk->sk_mark; /* Send it out. */ return ip_local_out(net, skb->sk, skb); @@ -598,6 +599,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, hlen = iph->ihl * 4; mtu = mtu - hlen; /* Size of data space */ IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE; + ll_rs = LL_RESERVED_SPACE(rt->dst.dev); /* When frag_list is given, use it. First, check its validity: * some transformers could create wrong frag_list or break existing @@ -613,14 +615,15 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (first_len - hlen > mtu || ((first_len - hlen) & 7) || ip_is_fragment(iph) || - skb_cloned(skb)) + skb_cloned(skb) || + skb_headroom(skb) < ll_rs) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || - skb_headroom(frag) < hlen) + skb_headroom(frag) < hlen + ll_rs) goto slow_path_clean; /* Partially cloned skb? */ @@ -710,8 +713,6 @@ slow_path: left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ - ll_rs = LL_RESERVED_SPACE(rt->dst.dev); - /* * Fragment the datagram. */ @@ -1037,7 +1038,7 @@ alloc_new_skb: (flags & MSG_DONTWAIT), &err); } else { skb = NULL; - if (atomic_read(&sk->sk_wmem_alloc) <= + if (refcount_read(&sk->sk_wmem_alloc) <= 2 * sk->sk_sndbuf) skb = sock_wmalloc(sk, alloclen + hh_len + 15, 1, @@ -1145,7 +1146,7 @@ alloc_new_skb: skb->len += copy; skb->data_len += copy; skb->truesize += copy; - atomic_add(copy, &sk->sk_wmem_alloc); + refcount_add(copy, &sk->sk_wmem_alloc); } offset += copy; length -= copy; @@ -1369,7 +1370,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, skb->len += len; skb->data_len += len; skb->truesize += len; - atomic_add(len, &sk->sk_wmem_alloc); + refcount_add(len, &sk->sk_wmem_alloc); offset += len; size -= len; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index ec4fe3d4b5c9..ecc4b4a2413e 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -934,14 +934,9 @@ static int do_ip_setsockopt(struct sock *sk, int level, err = -ENOBUFS; break; } - msf = kmalloc(optlen, GFP_KERNEL); - if (!msf) { - err = -ENOBUFS; - break; - } - err = -EFAULT; - if (copy_from_user(msf, optval, optlen)) { - kfree(msf); + msf = memdup_user(optval, optlen); + if (IS_ERR(msf)) { + err = PTR_ERR(msf); break; } /* numsrc >= (1G-4) overflow in 32 bits */ @@ -1090,14 +1085,11 @@ static int do_ip_setsockopt(struct sock *sk, int level, err = -ENOBUFS; break; } - gsf = kmalloc(optlen, GFP_KERNEL); - if (!gsf) { - err = -ENOBUFS; + gsf = memdup_user(optval, optlen); + if (IS_ERR(gsf)) { + err = PTR_ERR(gsf); break; } - err = -EFAULT; - if (copy_from_user(gsf, optval, optlen)) - goto mc_msf_out; /* numsrc >= (4G-140)/128 overflow in 32 bits */ if (gsf->gf_numsrc >= 0x1ffffff || diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index baf196eaf1d8..2f39479be92f 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -134,10 +134,12 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, struct metadata_dst *res; struct ip_tunnel_info *dst, *src; - if (!md || md->u.tun_info.mode & IP_TUNNEL_INFO_TX) + if (!md || md->type != METADATA_IP_TUNNEL || + md->u.tun_info.mode & IP_TUNNEL_INFO_TX) + return NULL; - res = metadata_dst_alloc(0, flags); + res = metadata_dst_alloc(0, METADATA_IP_TUNNEL, flags); if (!res) return NULL; @@ -228,14 +230,16 @@ static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = { static int ip_tun_build_state(struct nlattr *attr, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct ip_tunnel_info *tun_info; struct lwtunnel_state *new_state; struct nlattr *tb[LWTUNNEL_IP_MAX + 1]; int err; - err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy, NULL); + err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy, + extack); if (err < 0) return err; @@ -325,7 +329,8 @@ static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { static int ip6_tun_build_state(struct nlattr *attr, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct ip_tunnel_info *tun_info; struct lwtunnel_state *new_state; @@ -333,7 +338,7 @@ static int ip6_tun_build_state(struct nlattr *attr, int err; err = nla_parse_nested(tb, LWTUNNEL_IP6_MAX, attr, ip6_tun_policy, - NULL); + extack); if (err < 0) return err; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 4ec9affb2252..0192c255e508 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -465,7 +465,8 @@ static struct pernet_operations vti_net_ops = { .size = sizeof(struct ip_tunnel_net), }; -static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { return 0; } @@ -503,7 +504,8 @@ static void vti_netlink_parms(struct nlattr *data[], } static int vti_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel_parm parms; __u32 fwmark = 0; @@ -513,7 +515,8 @@ static int vti_newlink(struct net *src_net, struct net_device *dev, } static int vti_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); __u32 fwmark = t->fwmark; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index c3b12b1c7162..4c5dfe6bd34d 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -813,8 +813,7 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d if (!skb) return; skb_reserve(skb, hlen); - b = (struct bootp_pkt *) skb_put(skb, sizeof(struct bootp_pkt)); - memset(b, 0, sizeof(struct bootp_pkt)); + b = skb_put_zero(skb, sizeof(struct bootp_pkt)); /* Construct IP header */ skb_reset_network_header(skb); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 1e441c6f2160..fb1ad22b5e29 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -375,7 +375,8 @@ static int ipip_tunnel_init(struct net_device *dev) return ip_tunnel_init(dev); } -static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { u8 proto; @@ -469,7 +470,8 @@ static bool ipip_netlink_encap_parms(struct nlattr *data[], } static int ipip_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; @@ -488,7 +490,8 @@ static int ipip_newlink(struct net *src_net, struct net_device *dev, } static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 8ae425cad818..06863ea3fc5b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -109,6 +109,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm); static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, int cmd); +static void igmpmsg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt); static void mroute_clean_tables(struct mr_table *mrt, bool all); static void ipmr_expire_process(unsigned long arg); @@ -669,7 +670,8 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { - struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr)); + struct nlmsghdr *nlh = skb_pull(skb, + sizeof(struct iphdr)); nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); @@ -972,7 +974,8 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, /* Play the pending entries through our router */ while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { - struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr)); + struct nlmsghdr *nlh = skb_pull(skb, + sizeof(struct iphdr)); if (__ipmr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - @@ -993,8 +996,7 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, } } -/* Bounce a cache query up to mrouted. We could use netlink for this but mrouted - * expects the following bizarre scheme. +/* Bounce a cache query up to mrouted and netlink. * * Called under mrt_lock. */ @@ -1044,7 +1046,7 @@ static int ipmr_cache_report(struct mr_table *mrt, msg->im_vif = vifi; skb_dst_set(skb, dst_clone(skb_dst(pkt))); /* Add our header */ - igmp = (struct igmphdr *)skb_put(skb, sizeof(struct igmphdr)); + igmp = skb_put(skb, sizeof(struct igmphdr)); igmp->type = assert; msg->im_msgtype = assert; igmp->code = 0; @@ -1060,6 +1062,8 @@ static int ipmr_cache_report(struct mr_table *mrt, return -EINVAL; } + igmpmsg_netlink_event(mrt, skb); + /* Deliver to mrouted */ ret = sock_queue_rcv_skb(mroute_sk, skb); rcu_read_unlock(); @@ -2339,6 +2343,130 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err); } +static size_t igmpmsg_netlink_msgsize(size_t payloadlen) +{ + size_t len = + NLMSG_ALIGN(sizeof(struct rtgenmsg)) + + nla_total_size(1) /* IPMRA_CREPORT_MSGTYPE */ + + nla_total_size(4) /* IPMRA_CREPORT_VIF_ID */ + + nla_total_size(4) /* IPMRA_CREPORT_SRC_ADDR */ + + nla_total_size(4) /* IPMRA_CREPORT_DST_ADDR */ + /* IPMRA_CREPORT_PKT */ + + nla_total_size(payloadlen) + ; + + return len; +} + +static void igmpmsg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt) +{ + struct net *net = read_pnet(&mrt->net); + struct nlmsghdr *nlh; + struct rtgenmsg *rtgenm; + struct igmpmsg *msg; + struct sk_buff *skb; + struct nlattr *nla; + int payloadlen; + + payloadlen = pkt->len - sizeof(struct igmpmsg); + msg = (struct igmpmsg *)skb_network_header(pkt); + + skb = nlmsg_new(igmpmsg_netlink_msgsize(payloadlen), GFP_ATOMIC); + if (!skb) + goto errout; + + nlh = nlmsg_put(skb, 0, 0, RTM_NEWCACHEREPORT, + sizeof(struct rtgenmsg), 0); + if (!nlh) + goto errout; + rtgenm = nlmsg_data(nlh); + rtgenm->rtgen_family = RTNL_FAMILY_IPMR; + if (nla_put_u8(skb, IPMRA_CREPORT_MSGTYPE, msg->im_msgtype) || + nla_put_u32(skb, IPMRA_CREPORT_VIF_ID, msg->im_vif) || + nla_put_in_addr(skb, IPMRA_CREPORT_SRC_ADDR, + msg->im_src.s_addr) || + nla_put_in_addr(skb, IPMRA_CREPORT_DST_ADDR, + msg->im_dst.s_addr)) + goto nla_put_failure; + + nla = nla_reserve(skb, IPMRA_CREPORT_PKT, payloadlen); + if (!nla || skb_copy_bits(pkt, sizeof(struct igmpmsg), + nla_data(nla), payloadlen)) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + + rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MROUTE_R, NULL, GFP_ATOMIC); + return; + +nla_put_failure: + nlmsg_cancel(skb, nlh); +errout: + kfree_skb(skb); + rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE_R, -ENOBUFS); +} + +static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(in_skb->sk); + struct nlattr *tb[RTA_MAX + 1]; + struct sk_buff *skb = NULL; + struct mfc_cache *cache; + struct mr_table *mrt; + struct rtmsg *rtm; + __be32 src, grp; + u32 tableid; + int err; + + err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, + rtm_ipv4_policy, extack); + if (err < 0) + goto errout; + + rtm = nlmsg_data(nlh); + + src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0; + grp = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0; + tableid = tb[RTA_TABLE] ? nla_get_u32(tb[RTA_TABLE]) : 0; + + mrt = ipmr_get_table(net, tableid ? tableid : RT_TABLE_DEFAULT); + if (!mrt) { + err = -ENOENT; + goto errout_free; + } + + /* entries are added/deleted only under RTNL */ + rcu_read_lock(); + cache = ipmr_cache_find(mrt, src, grp); + rcu_read_unlock(); + if (!cache) { + err = -ENOENT; + goto errout_free; + } + + skb = nlmsg_new(mroute_msgsize(false, mrt->maxvif), GFP_KERNEL); + if (!skb) { + err = -ENOBUFS; + goto errout_free; + } + + err = ipmr_fill_mroute(mrt, skb, NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, cache, + RTM_NEWROUTE, 0); + if (err < 0) + goto errout_free; + + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); + +errout: + return err; + +errout_free: + kfree_skb(skb); + goto errout; +} + static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -2526,6 +2654,129 @@ static int ipmr_rtm_route(struct sk_buff *skb, struct nlmsghdr *nlh, return ipmr_mfc_delete(tbl, &mfcc, parent); } +static bool ipmr_fill_table(struct mr_table *mrt, struct sk_buff *skb) +{ + u32 queue_len = atomic_read(&mrt->cache_resolve_queue_len); + + if (nla_put_u32(skb, IPMRA_TABLE_ID, mrt->id) || + nla_put_u32(skb, IPMRA_TABLE_CACHE_RES_QUEUE_LEN, queue_len) || + nla_put_s32(skb, IPMRA_TABLE_MROUTE_REG_VIF_NUM, + mrt->mroute_reg_vif_num) || + nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_ASSERT, + mrt->mroute_do_assert) || + nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM, mrt->mroute_do_pim)) + return false; + + return true; +} + +static bool ipmr_fill_vif(struct mr_table *mrt, u32 vifid, struct sk_buff *skb) +{ + struct nlattr *vif_nest; + struct vif_device *vif; + + /* if the VIF doesn't exist just continue */ + if (!VIF_EXISTS(mrt, vifid)) + return true; + + vif = &mrt->vif_table[vifid]; + vif_nest = nla_nest_start(skb, IPMRA_VIF); + if (!vif_nest) + return false; + if (nla_put_u32(skb, IPMRA_VIFA_IFINDEX, vif->dev->ifindex) || + nla_put_u32(skb, IPMRA_VIFA_VIF_ID, vifid) || + nla_put_u16(skb, IPMRA_VIFA_FLAGS, vif->flags) || + nla_put_u64_64bit(skb, IPMRA_VIFA_BYTES_IN, vif->bytes_in, + IPMRA_VIFA_PAD) || + nla_put_u64_64bit(skb, IPMRA_VIFA_BYTES_OUT, vif->bytes_out, + IPMRA_VIFA_PAD) || + nla_put_u64_64bit(skb, IPMRA_VIFA_PACKETS_IN, vif->pkt_in, + IPMRA_VIFA_PAD) || + nla_put_u64_64bit(skb, IPMRA_VIFA_PACKETS_OUT, vif->pkt_out, + IPMRA_VIFA_PAD) || + nla_put_be32(skb, IPMRA_VIFA_LOCAL_ADDR, vif->local) || + nla_put_be32(skb, IPMRA_VIFA_REMOTE_ADDR, vif->remote)) { + nla_nest_cancel(skb, vif_nest); + return false; + } + nla_nest_end(skb, vif_nest); + + return true; +} + +static int ipmr_rtm_dumplink(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct nlmsghdr *nlh = NULL; + unsigned int t = 0, s_t; + unsigned int e = 0, s_e; + struct mr_table *mrt; + + s_t = cb->args[0]; + s_e = cb->args[1]; + + ipmr_for_each_table(mrt, net) { + struct nlattr *vifs, *af; + struct ifinfomsg *hdr; + u32 i; + + if (t < s_t) + goto skip_table; + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWLINK, + sizeof(*hdr), NLM_F_MULTI); + if (!nlh) + break; + + hdr = nlmsg_data(nlh); + memset(hdr, 0, sizeof(*hdr)); + hdr->ifi_family = RTNL_FAMILY_IPMR; + + af = nla_nest_start(skb, IFLA_AF_SPEC); + if (!af) { + nlmsg_cancel(skb, nlh); + goto out; + } + + if (!ipmr_fill_table(mrt, skb)) { + nlmsg_cancel(skb, nlh); + goto out; + } + + vifs = nla_nest_start(skb, IPMRA_TABLE_VIFS); + if (!vifs) { + nla_nest_end(skb, af); + nlmsg_end(skb, nlh); + goto out; + } + for (i = 0; i < mrt->maxvif; i++) { + if (e < s_e) + goto skip_entry; + if (!ipmr_fill_vif(mrt, i, skb)) { + nla_nest_end(skb, vifs); + nla_nest_end(skb, af); + nlmsg_end(skb, nlh); + goto out; + } +skip_entry: + e++; + } + s_e = 0; + e = 0; + nla_nest_end(skb, vifs); + nla_nest_end(skb, af); + nlmsg_end(skb, nlh); +skip_table: + t++; + } + +out: + cb->args[1] = e; + cb->args[0] = t; + + return skb->len; +} + #ifdef CONFIG_PROC_FS /* The /proc interfaces to multicast routing : * /proc/net/ip_mr_cache & /proc/net/ip_mr_vif @@ -2863,11 +3114,14 @@ int __init ip_mr_init(void) } #endif rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, - NULL, ipmr_rtm_dumproute, NULL); + ipmr_rtm_getroute, ipmr_rtm_dumproute, NULL); rtnl_register(RTNL_FAMILY_IPMR, RTM_NEWROUTE, ipmr_rtm_route, NULL, NULL); rtnl_register(RTNL_FAMILY_IPMR, RTM_DELROUTE, ipmr_rtm_route, NULL, NULL); + + rtnl_register(RTNL_FAMILY_IPMR, RTM_GETLINK, + NULL, ipmr_rtm_dumplink, NULL); return 0; #ifdef CONFIG_IP_PIMSM_V2 diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 038f293c2376..7d72decb80f9 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -47,7 +47,7 @@ struct clusterip_config { __be32 clusterip; /* the IP address */ u_int8_t clustermac[ETH_ALEN]; /* the MAC address */ - struct net_device *dev; /* device */ + int ifindex; /* device ifindex */ u_int16_t num_total_nodes; /* total number of nodes */ unsigned long local_nodes; /* node number array */ @@ -57,6 +57,9 @@ struct clusterip_config { enum clusterip_hashmode hash_mode; /* which hashing mode */ u_int32_t hash_initval; /* hash initialization */ struct rcu_head rcu; + + char ifname[IFNAMSIZ]; /* device ifname */ + struct notifier_block notifier; /* refresh c->ifindex in it */ }; #ifdef CONFIG_PROC_FS @@ -98,9 +101,8 @@ clusterip_config_put(struct clusterip_config *c) * entry(rule) is removed, remove the config from lists, but don't free it * yet, since proc-files could still be holding references */ static inline void -clusterip_config_entry_put(struct clusterip_config *c) +clusterip_config_entry_put(struct net *net, struct clusterip_config *c) { - struct net *net = dev_net(c->dev); struct clusterip_net *cn = net_generic(net, clusterip_net_id); local_bh_disable(); @@ -109,8 +111,7 @@ clusterip_config_entry_put(struct clusterip_config *c) spin_unlock(&cn->lock); local_bh_enable(); - dev_mc_del(c->dev, c->clustermac); - dev_put(c->dev); + unregister_netdevice_notifier(&c->notifier); /* In case anyone still accesses the file, the open/close * functions are also incrementing the refcount on their own, @@ -170,19 +171,55 @@ clusterip_config_init_nodelist(struct clusterip_config *c, set_bit(i->local_nodes[n] - 1, &c->local_nodes); } -static struct clusterip_config * -clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip, - struct net_device *dev) +static int +clusterip_netdev_event(struct notifier_block *this, unsigned long event, + void *ptr) { - struct net *net = dev_net(dev); + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct clusterip_config *c; + + c = container_of(this, struct clusterip_config, notifier); + switch (event) { + case NETDEV_REGISTER: + if (!strcmp(dev->name, c->ifname)) { + c->ifindex = dev->ifindex; + dev_mc_add(dev, c->clustermac); + } + break; + case NETDEV_UNREGISTER: + if (dev->ifindex == c->ifindex) { + dev_mc_del(dev, c->clustermac); + c->ifindex = -1; + } + break; + case NETDEV_CHANGENAME: + if (!strcmp(dev->name, c->ifname)) { + c->ifindex = dev->ifindex; + dev_mc_add(dev, c->clustermac); + } else if (dev->ifindex == c->ifindex) { + dev_mc_del(dev, c->clustermac); + c->ifindex = -1; + } + break; + } + + return NOTIFY_DONE; +} + +static struct clusterip_config * +clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, + __be32 ip, const char *iniface) +{ struct clusterip_net *cn = net_generic(net, clusterip_net_id); + struct clusterip_config *c; + int err; c = kzalloc(sizeof(*c), GFP_ATOMIC); if (!c) return ERR_PTR(-ENOMEM); - c->dev = dev; + strcpy(c->ifname, iniface); + c->ifindex = -1; c->clusterip = ip; memcpy(&c->clustermac, &i->clustermac, ETH_ALEN); c->num_total_nodes = i->num_total_nodes; @@ -213,17 +250,27 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip, cn->procdir, &clusterip_proc_fops, c); if (!c->pde) { - spin_lock_bh(&cn->lock); - list_del_rcu(&c->list); - spin_unlock_bh(&cn->lock); - kfree(c); - - return ERR_PTR(-ENOMEM); + err = -ENOMEM; + goto err; } } #endif - return c; + c->notifier.notifier_call = clusterip_netdev_event; + err = register_netdevice_notifier(&c->notifier); + if (!err) + return c; + +#ifdef CONFIG_PROC_FS + proc_remove(c->pde); +err: +#endif + spin_lock_bh(&cn->lock); + list_del_rcu(&c->list); + spin_unlock_bh(&cn->lock); + kfree(c); + + return ERR_PTR(err); } #ifdef CONFIG_PROC_FS @@ -425,14 +472,13 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) e->ip.iniface); return -ENOENT; } + dev_put(dev); - config = clusterip_config_init(cipinfo, - e->ip.dst.s_addr, dev); - if (IS_ERR(config)) { - dev_put(dev); + config = clusterip_config_init(par->net, cipinfo, + e->ip.dst.s_addr, + e->ip.iniface); + if (IS_ERR(config)) return PTR_ERR(config); - } - dev_mc_add(config->dev, config->clustermac); } } cipinfo->config = config; @@ -458,7 +504,7 @@ static void clusterip_tg_destroy(const struct xt_tgdtor_param *par) /* if no more entries are referencing the config, remove it * from the list and destroy the proc entry */ - clusterip_config_entry_put(cipinfo->config); + clusterip_config_entry_put(par->net, cipinfo->config); clusterip_config_put(cipinfo->config); @@ -558,10 +604,9 @@ arp_mangle(void *priv, * addresses on different interfacs. However, in the CLUSTERIP case * this wouldn't work, since we didn't subscribe the mcast group on * other interfaces */ - if (c->dev != state->out) { - pr_debug("not mangling arp reply on different " - "interface: cip'%s'-skb'%s'\n", - c->dev->name, state->out->name); + if (c->ifindex != state->out->ifindex) { + pr_debug("not mangling arp reply on different interface: cip'%d'-skb'%d'\n", + c->ifindex, state->out->ifindex); clusterip_config_put(c); return NF_ACCEPT; } @@ -743,14 +788,20 @@ static const struct file_operations clusterip_proc_fops = { static int clusterip_net_init(struct net *net) { struct clusterip_net *cn = net_generic(net, clusterip_net_id); + int ret; INIT_LIST_HEAD(&cn->configs); spin_lock_init(&cn->lock); + ret = nf_register_net_hook(net, &cip_arp_ops); + if (ret < 0) + return ret; + #ifdef CONFIG_PROC_FS cn->procdir = proc_mkdir("ipt_CLUSTERIP", net->proc_net); if (!cn->procdir) { + nf_unregister_net_hook(net, &cip_arp_ops); pr_err("Unable to proc dir entry\n"); return -ENOMEM; } @@ -765,6 +816,7 @@ static void clusterip_net_exit(struct net *net) struct clusterip_net *cn = net_generic(net, clusterip_net_id); proc_remove(cn->procdir); #endif + nf_unregister_net_hook(net, &cip_arp_ops); } static struct pernet_operations clusterip_net_ops = { @@ -786,17 +838,11 @@ static int __init clusterip_tg_init(void) if (ret < 0) goto cleanup_subsys; - ret = nf_register_hook(&cip_arp_ops); - if (ret < 0) - goto cleanup_target; - pr_info("ClusterIP Version %s loaded successfully\n", CLUSTERIP_VERSION); return 0; -cleanup_target: - xt_unregister_target(&clusterip_tg_reg); cleanup_subsys: unregister_pernet_subsys(&clusterip_net_ops); return ret; @@ -806,7 +852,6 @@ static void __exit clusterip_tg_exit(void) { pr_info("ClusterIP Version %s unloading\n", CLUSTERIP_VERSION); - nf_unregister_hook(&cip_arp_ops); xt_unregister_target(&clusterip_tg_reg); unregister_pernet_subsys(&clusterip_net_ops); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index af2b69b6895f..f1528f7175a8 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -24,7 +24,7 @@ synproxy_build_ip(struct net *net, struct sk_buff *skb, __be32 saddr, struct iphdr *iph; skb_reset_network_header(skb); - iph = (struct iphdr *)skb_put(skb, sizeof(*iph)); + iph = skb_put(skb, sizeof(*iph)); iph->version = 4; iph->ihl = sizeof(*iph) / 4; iph->tos = 0; @@ -91,7 +91,7 @@ synproxy_send_client_synack(struct net *net, niph = synproxy_build_ip(net, nskb, iph->daddr, iph->saddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->dest; nth->dest = th->source; nth->seq = htonl(__cookie_v4_init_sequence(iph, th, &mss)); @@ -133,7 +133,7 @@ synproxy_send_server_syn(struct net *net, niph = synproxy_build_ip(net, nskb, iph->saddr, iph->daddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->source; nth->dest = th->dest; nth->seq = htonl(recv_seq - 1); @@ -178,7 +178,7 @@ synproxy_send_server_ack(struct net *net, niph = synproxy_build_ip(net, nskb, iph->daddr, iph->saddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->dest; nth->dest = th->source; nth->seq = htonl(ntohl(th->ack_seq)); @@ -216,7 +216,7 @@ synproxy_send_client_ack(struct net *net, niph = synproxy_build_ip(net, nskb, iph->saddr, iph->daddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->source; nth->dest = th->dest; nth->seq = htonl(ntohl(th->seq) + 1); diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c index dc1dea15c1b4..f39037fca923 100644 --- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c @@ -98,8 +98,8 @@ static int masq_device_event(struct notifier_block *this, */ NF_CT_ASSERT(dev->ifindex != 0); - nf_ct_iterate_cleanup(net, device_cmp, - (void *)(long)dev->ifindex, 0, 0); + nf_ct_iterate_cleanup_net(net, device_cmp, + (void *)(long)dev->ifindex, 0, 0); } return NOTIFY_DONE; diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 7cd8d0d918f8..eeacbdaf7cdf 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -51,7 +51,7 @@ struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, struct iphdr *niph, *oiph = ip_hdr(oldskb); skb_reset_network_header(nskb); - niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr)); + niph = skb_put(nskb, sizeof(struct iphdr)); niph->version = 4; niph->ihl = sizeof(struct iphdr) / 4; niph->tos = 0; @@ -76,8 +76,7 @@ void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, struct tcphdr *tcph; skb_reset_transport_header(nskb); - tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); - memset(tcph, 0, sizeof(*tcph)); + tcph = skb_put_zero(nskb, sizeof(struct tcphdr)); tcph->source = oth->dest; tcph->dest = oth->source; tcph->doff = sizeof(struct tcphdr) / 4; @@ -172,7 +171,7 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook) struct iphdr *iph = ip_hdr(skb_in); u8 proto; - if (skb_in->csum_bad || iph->frag_off & htons(IP_OFFSET)) + if (iph->frag_off & htons(IP_OFFSET)) return; if (skb_csum_unnecessary(skb_in)) { diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c index 805c8ddfe860..4bbc273b45e8 100644 --- a/net/ipv4/netfilter/nf_tables_arp.c +++ b/net/ipv4/netfilter/nf_tables_arp.c @@ -72,8 +72,7 @@ static const struct nf_chain_type filter_arp = { .family = NFPROTO_ARP, .owner = THIS_MODULE, .hook_mask = (1 << NF_ARP_IN) | - (1 << NF_ARP_OUT) | - (1 << NF_ARP_FORWARD), + (1 << NF_ARP_OUT), }; static int __init nf_tables_arp_init(void) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index ccfbce13a633..b8f0db54b197 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -290,7 +290,7 @@ void ping_close(struct sock *sk, long timeout) { pr_debug("ping_close(sk=%p,sk->num=%u)\n", inet_sk(sk), inet_sk(sk)->inet_num); - pr_debug("isk->refcnt = %d\n", sk->sk_refcnt.counter); + pr_debug("isk->refcnt = %d\n", refcount_read(&sk->sk_refcnt)); sk_common_release(sk); } @@ -1127,7 +1127,7 @@ static void ping_v4_format_sock(struct sock *sp, struct seq_file *f, 0, 0L, 0, from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, + refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index fa44e752a9a3..43eb6567b3a0 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -250,6 +250,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPAbortOnLinger", LINUX_MIB_TCPABORTONLINGER), SNMP_MIB_ITEM("TCPAbortFailed", LINUX_MIB_TCPABORTFAILED), SNMP_MIB_ITEM("TCPMemoryPressures", LINUX_MIB_TCPMEMORYPRESSURES), + SNMP_MIB_ITEM("TCPMemoryPressuresChrono", LINUX_MIB_TCPMEMORYPRESSURESCHRONO), SNMP_MIB_ITEM("TCPSACKDiscard", LINUX_MIB_TCPSACKDISCARD), SNMP_MIB_ITEM("TCPDSACKIgnoredOld", LINUX_MIB_TCPDSACKIGNOREDOLD), SNMP_MIB_ITEM("TCPDSACKIgnoredNoUndo", LINUX_MIB_TCPDSACKIGNOREDNOUNDO), diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index bdffad875691..b0bb5d0a30bd 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -1063,7 +1063,7 @@ static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) 0, 0L, 0, from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); + refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } static int raw_seq_show(struct seq_file *seq, void *v) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6883b3d4ba8f..0383e66f59bc 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -114,6 +114,8 @@ #include <net/ip_tunnels.h> #include <net/l3mdev.h> +#include "fib_lookup.h" + #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) @@ -587,11 +589,6 @@ static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk, build_sk_flow_key(fl4, sk); } -static inline void rt_free(struct rtable *rt) -{ - call_rcu(&rt->dst.rcu_head, dst_rcu_free); -} - static DEFINE_SPINLOCK(fnhe_lock); static void fnhe_flush_routes(struct fib_nh_exception *fnhe) @@ -601,12 +598,14 @@ static void fnhe_flush_routes(struct fib_nh_exception *fnhe) rt = rcu_dereference(fnhe->fnhe_rth_input); if (rt) { RCU_INIT_POINTER(fnhe->fnhe_rth_input, NULL); - rt_free(rt); + dst_dev_put(&rt->dst); + dst_release(&rt->dst); } rt = rcu_dereference(fnhe->fnhe_rth_output); if (rt) { RCU_INIT_POINTER(fnhe->fnhe_rth_output, NULL); - rt_free(rt); + dst_dev_put(&rt->dst); + dst_release(&rt->dst); } } @@ -1300,7 +1299,7 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) } static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, - __be32 daddr) + __be32 daddr, const bool do_cache) { bool ret = false; @@ -1329,10 +1328,13 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, if (!rt->rt_gateway) rt->rt_gateway = daddr; - if (!(rt->dst.flags & DST_NOCACHE)) { + if (do_cache) { + dst_hold(&rt->dst); rcu_assign_pointer(*porig, rt); - if (orig) - rt_free(orig); + if (orig) { + dst_dev_put(&orig->dst); + dst_release(&orig->dst); + } ret = true; } @@ -1355,12 +1357,20 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt) } orig = *p; + /* hold dst before doing cmpxchg() to avoid race condition + * on this dst + */ + dst_hold(&rt->dst); prev = cmpxchg(p, orig, rt); if (prev == orig) { - if (orig) - rt_free(orig); - } else + if (orig) { + dst_dev_put(&orig->dst); + dst_release(&orig->dst); + } + } else { + dst_release(&rt->dst); ret = false; + } return ret; } @@ -1431,7 +1441,8 @@ static bool rt_cache_valid(const struct rtable *rt) static void rt_set_nexthop(struct rtable *rt, __be32 daddr, const struct fib_result *res, struct fib_nh_exception *fnhe, - struct fib_info *fi, u16 type, u32 itag) + struct fib_info *fi, u16 type, u32 itag, + const bool do_cache) { bool cached = false; @@ -1452,8 +1463,8 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, #endif rt->dst.lwtstate = lwtstate_get(nh->nh_lwtstate); if (unlikely(fnhe)) - cached = rt_bind_exception(rt, fnhe, daddr); - else if (!(rt->dst.flags & DST_NOCACHE)) + cached = rt_bind_exception(rt, fnhe, daddr, do_cache); + else if (do_cache) cached = rt_cache_route(nh, rt); if (unlikely(!cached)) { /* Routes we intend to cache in nexthop exception or @@ -1461,7 +1472,6 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, * However, if we are unsuccessful at storing this * route into the cache we really need to set it. */ - rt->dst.flags |= DST_NOCACHE; if (!rt->rt_gateway) rt->rt_gateway = daddr; rt_add_uncached_list(rt); @@ -1484,7 +1494,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev, struct rtable *rt; rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, - (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) | + (will_cache ? 0 : DST_HOST) | (nopolicy ? DST_NOPOLICY : 0) | (noxfrm ? DST_NOXFRM : 0)); @@ -1728,7 +1738,8 @@ rt_cache: rth->dst.input = ip_forward; - rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag); + rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag, + do_cache); set_lwt_redirect(rth); skb_dst_set(skb, &rth->dst); out: @@ -1860,9 +1871,9 @@ static int ip_mkroute_input(struct sk_buff *skb, */ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev) + u8 tos, struct net_device *dev, + struct fib_result *res) { - struct fib_result res; struct in_device *in_dev = __in_dev_get_rcu(dev); struct ip_tunnel_info *tun_info; struct flowi4 fl4; @@ -1892,8 +1903,8 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; - res.fi = NULL; - res.table = NULL; + res->fi = NULL; + res->table = NULL; if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; @@ -1929,17 +1940,17 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); - err = fib_lookup(net, &fl4, &res, 0); + err = fib_lookup(net, &fl4, res, 0); if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) err = -EHOSTUNREACH; goto no_route; } - if (res.type == RTN_BROADCAST) + if (res->type == RTN_BROADCAST) goto brd_input; - if (res.type == RTN_LOCAL) { + if (res->type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &itag); if (err < 0) @@ -1951,10 +1962,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, err = -EHOSTUNREACH; goto no_route; } - if (res.type != RTN_UNICAST) + if (res->type != RTN_UNICAST) goto martian_destination; - err = ip_mkroute_input(skb, &res, in_dev, daddr, saddr, tos); + err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos); out: return err; brd_input: @@ -1968,14 +1979,14 @@ brd_input: goto martian_source; } flags |= RTCF_BROADCAST; - res.type = RTN_BROADCAST; + res->type = RTN_BROADCAST; RT_CACHE_STAT_INC(in_brd); local_input: do_cache = false; - if (res.fi) { + if (res->fi) { if (!itag) { - rth = rcu_dereference(FIB_RES_NH(res).nh_rth_input); + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); err = 0; @@ -1986,7 +1997,7 @@ local_input: } rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev, - flags | RTCF_LOCAL, res.type, + flags | RTCF_LOCAL, res->type, IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache); if (!rth) goto e_nobufs; @@ -1996,18 +2007,18 @@ local_input: rth->dst.tclassid = itag; #endif rth->rt_is_input = 1; - if (res.table) - rth->rt_table_id = res.table->tb_id; + if (res->table) + rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(in_slow_tot); - if (res.type == RTN_UNREACHABLE) { + if (res->type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } if (do_cache) { - struct fib_nh *nh = &FIB_RES_NH(res); + struct fib_nh *nh = &FIB_RES_NH(*res); rth->dst.lwtstate = lwtstate_get(nh->nh_lwtstate); if (lwtunnel_input_redirect(rth->dst.lwtstate)) { @@ -2016,10 +2027,8 @@ local_input: rth->dst.input = lwtunnel_input; } - if (unlikely(!rt_cache_route(nh, rth))) { - rth->dst.flags |= DST_NOCACHE; + if (unlikely(!rt_cache_route(nh, rth))) rt_add_uncached_list(rth); - } } skb_dst_set(skb, &rth->dst); err = 0; @@ -2027,9 +2036,9 @@ local_input: no_route: RT_CACHE_STAT_INC(in_no_route); - res.type = RTN_UNREACHABLE; - res.fi = NULL; - res.table = NULL; + res->type = RTN_UNREACHABLE; + res->fi = NULL; + res->table = NULL; goto local_input; /* @@ -2059,11 +2068,22 @@ martian_source: int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev) { - int res; + struct fib_result res; + int err; tos &= IPTOS_RT_MASK; rcu_read_lock(); + err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res); + rcu_read_unlock(); + return err; +} +EXPORT_SYMBOL(ip_route_input_noref); + +/* called with rcu_read_lock held */ +int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, struct fib_result *res) +{ /* Multicast recognition logic is moved from route cache to here. The problem was that too many Ethernet cards have broken/missing hardware multicast filters :-( As result the host on multicasting @@ -2078,6 +2098,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_multicast(daddr)) { struct in_device *in_dev = __in_dev_get_rcu(dev); int our = 0; + int err = -EINVAL; if (in_dev) our = ip_check_mc_rcu(in_dev, daddr, saddr, @@ -2093,7 +2114,6 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, ip_hdr(skb)->protocol); } - res = -EINVAL; if (our #ifdef CONFIG_IP_MROUTE || @@ -2101,17 +2121,14 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, IN_DEV_MFORWARD(in_dev)) #endif ) { - res = ip_route_input_mc(skb, daddr, saddr, + err = ip_route_input_mc(skb, daddr, saddr, tos, dev, our); } - rcu_read_unlock(); - return res; + return err; } - res = ip_route_input_slow(skb, daddr, saddr, tos, dev); - rcu_read_unlock(); - return res; + + return ip_route_input_slow(skb, daddr, saddr, tos, dev, res); } -EXPORT_SYMBOL(ip_route_input_noref); /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, @@ -2207,10 +2224,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rth = rcu_dereference(*prth); rt_cache: - if (rt_cache_valid(rth)) { - dst_hold(&rth->dst); + if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst)) return rth; - } } add: @@ -2244,7 +2259,7 @@ add: #endif } - rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0); + rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0, do_cache); set_lwt_redirect(rth); return rth; @@ -2254,29 +2269,40 @@ add: * Major route resolver routine. */ -struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, - const struct sk_buff *skb) +struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, + const struct sk_buff *skb) { - struct net_device *dev_out = NULL; __u8 tos = RT_FL_TOS(fl4); - unsigned int flags = 0; struct fib_result res; struct rtable *rth; - int orig_oif; - int err = -ENETUNREACH; res.tclassid = 0; res.fi = NULL; res.table = NULL; - orig_oif = fl4->flowi4_oif; - fl4->flowi4_iif = LOOPBACK_IFINDEX; fl4->flowi4_tos = tos & IPTOS_RT_MASK; fl4->flowi4_scope = ((tos & RTO_ONLINK) ? RT_SCOPE_LINK : RT_SCOPE_UNIVERSE); rcu_read_lock(); + rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); + rcu_read_unlock(); + + return rth; +} +EXPORT_SYMBOL_GPL(ip_route_output_key_hash); + +struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, + struct fib_result *res, + const struct sk_buff *skb) +{ + struct net_device *dev_out = NULL; + int orig_oif = fl4->flowi4_oif; + unsigned int flags = 0; + struct rtable *rth; + int err = -ENETUNREACH; + if (fl4->saddr) { rth = ERR_PTR(-EINVAL); if (ipv4_is_multicast(fl4->saddr) || @@ -2362,15 +2388,15 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK); dev_out = net->loopback_dev; fl4->flowi4_oif = LOOPBACK_IFINDEX; - res.type = RTN_LOCAL; + res->type = RTN_LOCAL; flags |= RTCF_LOCAL; goto make_route; } - err = fib_lookup(net, fl4, &res, 0); + err = fib_lookup(net, fl4, res, 0); if (err) { - res.fi = NULL; - res.table = NULL; + res->fi = NULL; + res->table = NULL; if (fl4->flowi4_oif && (ipv4_is_multicast(fl4->daddr) || !netif_index_is_l3_master(net, fl4->flowi4_oif))) { @@ -2395,43 +2421,41 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, if (fl4->saddr == 0) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); - res.type = RTN_UNICAST; + res->type = RTN_UNICAST; goto make_route; } rth = ERR_PTR(err); goto out; } - if (res.type == RTN_LOCAL) { + if (res->type == RTN_LOCAL) { if (!fl4->saddr) { - if (res.fi->fib_prefsrc) - fl4->saddr = res.fi->fib_prefsrc; + if (res->fi->fib_prefsrc) + fl4->saddr = res->fi->fib_prefsrc; else fl4->saddr = fl4->daddr; } /* L3 master device is the loopback for that domain */ - dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? : + dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) ? : net->loopback_dev; fl4->flowi4_oif = dev_out->ifindex; flags |= RTCF_LOCAL; goto make_route; } - fib_select_path(net, &res, fl4, skb); + fib_select_path(net, res, fl4, skb); - dev_out = FIB_RES_DEV(res); + dev_out = FIB_RES_DEV(*res); fl4->flowi4_oif = dev_out->ifindex; make_route: - rth = __mkroute_output(&res, fl4, orig_oif, dev_out, flags); + rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags); out: - rcu_read_unlock(); return rth; } -EXPORT_SYMBOL_GPL(__ip_route_output_key_hash); static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) { @@ -2485,7 +2509,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or new->input = dst_discard; new->output = dst_discard_out; - new->dev = ort->dst.dev; + new->dev = net->loopback_dev; if (new->dev) dev_hold(new->dev); @@ -2500,7 +2524,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_uses_gateway = ort->rt_uses_gateway; INIT_LIST_HEAD(&rt->rt_uncached); - dst_free(new); } dst_release(dst_orig); @@ -2525,9 +2548,10 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, } EXPORT_SYMBOL_GPL(ip_route_output_flow); +/* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, struct flowi4 *fl4, struct sk_buff *skb, u32 portid, - u32 seq, int event) + u32 seq) { struct rtable *rt = skb_rtable(skb); struct rtmsg *r; @@ -2536,7 +2560,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, u32 error; u32 metrics[RTAX_MAX]; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*r), 0); + nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), 0); if (!nlh) return -EMSGSIZE; @@ -2644,6 +2668,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct net *net = sock_net(in_skb->sk); struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; + struct fib_result res = {}; struct rtable *rt = NULL; struct flowi4 fl4; __be32 dst = 0; @@ -2700,10 +2725,12 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; + rcu_read_lock(); + if (iif) { struct net_device *dev; - dev = __dev_get_by_index(net, iif); + dev = dev_get_by_index_rcu(net, iif); if (!dev) { err = -ENODEV; goto errout_free; @@ -2712,14 +2739,14 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, skb->protocol = htons(ETH_P_IP); skb->dev = dev; skb->mark = mark; - err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev); + err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos, + dev, &res); rt = skb_rtable(skb); if (err == 0 && rt->dst.error) err = -rt->dst.error; } else { - rt = ip_route_output_key(net, &fl4); - + rt = ip_route_output_key_hash_rcu(net, &fl4, &res, skb); err = 0; if (IS_ERR(rt)) err = PTR_ERR(rt); @@ -2735,17 +2762,25 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE) table_id = rt->rt_table_id; - err = rt_fill_info(net, dst, src, table_id, &fl4, skb, - NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, - RTM_NEWROUTE); + if (rtm->rtm_flags & RTM_F_FIB_MATCH) + err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, RTM_NEWROUTE, table_id, + rt->rt_type, res.prefix, res.prefixlen, + fl4.flowi4_tos, res.fi, 0); + else + err = rt_fill_info(net, dst, src, table_id, &fl4, skb, + NETLINK_CB(in_skb).portid, nlh->nlmsg_seq); if (err < 0) goto errout_free; + rcu_read_unlock(); + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; errout_free: + rcu_read_unlock(); kfree_skb(skb); goto errout; } @@ -2944,8 +2979,7 @@ static __net_init int rt_genid_init(struct net *net) { atomic_set(&net->ipv4.rt_genid, 0); atomic_set(&net->fnhe_genid, 0); - get_random_bytes(&net->ipv4.dev_addr_genid, - sizeof(net->ipv4.dev_addr_genid)); + atomic_set(&net->ipv4.dev_addr_genid, get_random_int()); return 0; } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 0257d965f111..03ad8778c395 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -66,10 +66,10 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, * Since subsequent timestamps use the normal tcp_time_stamp value, we * must make sure that the resulting initial timestamp is <= tcp_time_stamp. */ -__u32 cookie_init_timestamp(struct request_sock *req) +u64 cookie_init_timestamp(struct request_sock *req) { struct inet_request_sock *ireq; - u32 ts, ts_now = tcp_time_stamp; + u32 ts, ts_now = tcp_time_stamp_raw(); u32 options = 0; ireq = inet_rsk(req); @@ -88,7 +88,7 @@ __u32 cookie_init_timestamp(struct request_sock *req) ts <<= TSBITS; ts |= options; } - return ts; + return (u64)ts * (USEC_PER_SEC / TCP_TS_HZ); } @@ -213,7 +213,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst, NULL, &own_req); if (child) { - atomic_set(&req->rsk_refcnt, 1); + refcount_set(&req->rsk_refcnt, 1); tcp_sk(child)->tsoffset = tsoff; sock_rps_save_rxhash(child, skb); inet_csk_reqsk_queue_add(sk, req, child); @@ -232,7 +232,8 @@ EXPORT_SYMBOL(tcp_get_cookie_sock); * return false if we decode a tcp option that is disabled * on the host. */ -bool cookie_timestamp_decode(struct tcp_options_received *tcp_opt) +bool cookie_timestamp_decode(const struct net *net, + struct tcp_options_received *tcp_opt) { /* echoed timestamp, lowest bits contain options */ u32 options = tcp_opt->rcv_tsecr; @@ -242,12 +243,12 @@ bool cookie_timestamp_decode(struct tcp_options_received *tcp_opt) return true; } - if (!sysctl_tcp_timestamps) + if (!net->ipv4.sysctl_tcp_timestamps) return false; tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0; - if (tcp_opt->sack_ok && !sysctl_tcp_sack) + if (tcp_opt->sack_ok && !net->ipv4.sysctl_tcp_sack) return false; if ((options & TS_OPT_WSCALE_MASK) == TS_OPT_WSCALE_MASK) @@ -256,7 +257,7 @@ bool cookie_timestamp_decode(struct tcp_options_received *tcp_opt) tcp_opt->wscale_ok = 1; tcp_opt->snd_wscale = options & TS_OPT_WSCALE_MASK; - return sysctl_tcp_window_scaling != 0; + return net->ipv4.sysctl_tcp_window_scaling != 0; } EXPORT_SYMBOL(cookie_timestamp_decode); @@ -312,14 +313,16 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, 0, NULL); + tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcp_ts_off(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); + tsoff = secure_tcp_ts_off(sock_net(sk), + ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr); tcp_opt.rcv_tsecr -= tsoff; } - if (!cookie_timestamp_decode(&tcp_opt)) + if (!cookie_timestamp_decode(sock_net(sk), &tcp_opt)) goto out; ret = NULL; @@ -332,6 +335,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; treq->ts_off = 0; + treq->txhash = net_tx_rndhash(); req->mss = mss; ireq->ir_num = ntohs(th->dest); ireq->ir_rmt_port = th->source; @@ -343,7 +347,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack.v64 = 0; + treq->snt_synack = 0; treq->tfo_listener = false; ireq->ir_iif = inet_request_bound_dev_if(sk, skb); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 86957e9cd6c6..9bf809726066 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -360,32 +360,30 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) tcp_fastopen_active_timeout_reset(); + + return ret; +} + +static int proc_tcp_available_ulp(struct ctl_table *ctl, + int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct ctl_table tbl = { .maxlen = TCP_ULP_BUF_MAX, }; + int ret; + + tbl.data = kmalloc(tbl.maxlen, GFP_USER); + if (!tbl.data) + return -ENOMEM; + tcp_get_available_ulp(tbl.data, TCP_ULP_BUF_MAX); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); + kfree(tbl.data); + return ret; } static struct ctl_table ipv4_table[] = { { - .procname = "tcp_timestamps", - .data = &sysctl_tcp_timestamps, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_window_scaling", - .data = &sysctl_tcp_window_scaling, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_sack", - .data = &sysctl_tcp_sack, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "tcp_retrans_collapse", .data = &sysctl_tcp_retrans_collapse, .maxlen = sizeof(int), @@ -707,6 +705,12 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec_ms_jiffies, }, { + .procname = "tcp_available_ulp", + .maxlen = TCP_ULP_BUF_MAX, + .mode = 0444, + .proc_handler = proc_tcp_available_ulp, + }, + { .procname = "icmp_msgs_per_sec", .data = &sysctl_icmp_msgs_per_sec, .maxlen = sizeof(int), @@ -1116,6 +1120,27 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = &one, }, #endif + { + .procname = "tcp_sack", + .data = &init_net.ipv4.sysctl_tcp_sack, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_window_scaling", + .data = &init_net.ipv4.sysctl_tcp_window_scaling, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_timestamps", + .data = &init_net.ipv4.sysctl_tcp_timestamps, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 40aca7803cf2..71ce33decd97 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -320,17 +320,36 @@ struct tcp_splice_state { * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ -int tcp_memory_pressure __read_mostly; -EXPORT_SYMBOL(tcp_memory_pressure); +unsigned long tcp_memory_pressure __read_mostly; +EXPORT_SYMBOL_GPL(tcp_memory_pressure); void tcp_enter_memory_pressure(struct sock *sk) { - if (!tcp_memory_pressure) { + unsigned long val; + + if (tcp_memory_pressure) + return; + val = jiffies; + + if (!val) + val--; + if (!cmpxchg(&tcp_memory_pressure, 0, val)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES); - tcp_memory_pressure = 1; - } } -EXPORT_SYMBOL(tcp_enter_memory_pressure); +EXPORT_SYMBOL_GPL(tcp_enter_memory_pressure); + +void tcp_leave_memory_pressure(struct sock *sk) +{ + unsigned long val; + + if (!tcp_memory_pressure) + return; + val = xchg(&tcp_memory_pressure, 0); + if (val) + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURESCHRONO, + jiffies_to_msecs(jiffies - val)); +} +EXPORT_SYMBOL_GPL(tcp_leave_memory_pressure); /* Convert seconds to retransmits based on initial and max timeout */ static u8 secs_to_retrans(int seconds, int timeout, int rto_max) @@ -386,7 +405,7 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); - minmax_reset(&tp->rtt_min, tcp_time_stamp, ~0U); + minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control @@ -645,7 +664,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, return skb->len < size_goal && sysctl_tcp_autocorking && skb != tcp_write_queue_head(sk) && - atomic_read(&sk->sk_wmem_alloc) > skb->truesize; + refcount_read(&sk->sk_wmem_alloc) > skb->truesize; } static void tcp_push(struct sock *sk, int flags, int mss_now, @@ -673,7 +692,7 @@ static void tcp_push(struct sock *sk, int flags, int mss_now, /* It is possible TX completion already happened * before we set TSQ_THROTTLED. */ - if (atomic_read(&sk->sk_wmem_alloc) > skb->truesize) + if (refcount_read(&sk->sk_wmem_alloc) > skb->truesize) return; } @@ -882,8 +901,8 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags) return mss_now; } -static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, - size_t size, int flags) +ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, + size_t size, int flags) { struct tcp_sock *tp = tcp_sk(sk); int mss_now, size_goal; @@ -1013,6 +1032,7 @@ out_err: } return sk_stream_error(sk, flags, err); } +EXPORT_SYMBOL_GPL(do_tcp_sendpages); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) @@ -2186,7 +2206,7 @@ adjudge_to_death: /* Now socket is owned by kernel and we acquire BH lock - to finish close. No need to check for user refs. + * to finish close. No need to check for user refs. */ local_bh_disable(); bh_lock_sock(sk); @@ -2461,7 +2481,25 @@ static int do_tcp_setsockopt(struct sock *sk, int level, name[val] = 0; lock_sock(sk); - err = tcp_set_congestion_control(sk, name); + err = tcp_set_congestion_control(sk, name, true); + release_sock(sk); + return err; + } + case TCP_ULP: { + char name[TCP_ULP_NAME_MAX]; + + if (optlen < 1) + return -EINVAL; + + val = strncpy_from_user(name, optval, + min_t(long, TCP_ULP_NAME_MAX - 1, + optlen)); + if (val < 0) + return -EFAULT; + name[val] = 0; + + lock_sock(sk); + err = tcp_set_ulp(sk, name); release_sock(sk); return err; } @@ -2482,7 +2520,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_MAXSEG: /* Values greater than interface MTU won't take effect. However * at the point when this call is done we typically don't yet - * know which interface is going to be used */ + * know which interface is going to be used + */ if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) { err = -EINVAL; break; @@ -2677,8 +2716,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: + case TCP_MD5SIG_EXT: /* Read the IP->Key mappings from userspace */ - err = tp->af_specific->md5_parse(sk, optval, optlen); + err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif case TCP_USER_TIMEOUT: @@ -2717,7 +2757,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, if (!tp->repair) err = -EPERM; else - tp->tsoffset = val - tcp_time_stamp; + tp->tsoffset = val - tcp_time_stamp_raw(); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); @@ -2768,7 +2808,7 @@ static void tcp_get_info_chrono_stats(const struct tcp_sock *tp, for (i = TCP_CHRONO_BUSY; i < __TCP_CHRONO_MAX; ++i) { stats[i] = tp->chrono_stat[i - 1]; if (i == tp->chrono_type) - stats[i] += tcp_time_stamp - tp->chrono_start; + stats[i] += tcp_jiffies32 - tp->chrono_start; stats[i] *= USEC_PER_SEC / HZ; total += stats[i]; } @@ -2852,7 +2892,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_retrans = tp->retrans_out; info->tcpi_fackets = tp->fackets_out; - now = tcp_time_stamp; + now = tcp_jiffies32; info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime); info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime); info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp); @@ -3020,6 +3060,21 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return -EFAULT; return 0; + case TCP_ULP: + if (get_user(len, optlen)) + return -EFAULT; + len = min_t(unsigned int, len, TCP_ULP_NAME_MAX); + if (!icsk->icsk_ulp_ops) { + if (put_user(0, optlen)) + return -EFAULT; + return 0; + } + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, icsk->icsk_ulp_ops->name, len)) + return -EFAULT; + return 0; + case TCP_THIN_LINEAR_TIMEOUTS: val = tp->thin_lto; break; @@ -3083,7 +3138,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TIMESTAMP: - val = tcp_time_stamp + tp->tsoffset; + val = tcp_time_stamp_raw() + tp->tsoffset; break; case TCP_NOTSENT_LOWAT: val = tp->notsent_lowat; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index b89bce4c721e..69ee877574d0 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -52,10 +52,9 @@ * There is a public e-mail list for discussing BBR development and testing: * https://groups.google.com/forum/#!forum/bbr-dev * - * NOTE: BBR *must* be used with the fq qdisc ("man tc-fq") with pacing enabled, - * since pacing is integral to the BBR design and implementation. - * BBR without pacing would not function properly, and may incur unnecessary - * high packet loss rates. + * NOTE: BBR might be used with the fq qdisc ("man tc-fq") with pacing enabled, + * otherwise TCP stack falls back to an internal pacing using one high + * resolution timer per TCP socket and may use more resources. */ #include <linux/module.h> #include <net/tcp.h> @@ -92,7 +91,7 @@ struct bbr { struct minmax bw; /* Max recent delivery rate in pkts/uS << 24 */ u32 rtt_cnt; /* count of packet-timed rounds elapsed */ u32 next_rtt_delivered; /* scb->tx.delivered at end of round */ - struct skb_mstamp cycle_mstamp; /* time of this cycle phase start */ + u64 cycle_mstamp; /* time of this cycle phase start */ u32 mode:3, /* current bbr_mode in state machine */ prev_ca_state:3, /* CA state on previous ACK */ packet_conservation:1, /* use packet conservation? */ @@ -113,7 +112,8 @@ struct bbr { cwnd_gain:10, /* current gain for setting cwnd */ full_bw_cnt:3, /* number of rounds without large bw gains */ cycle_idx:3, /* current index in pacing_gain cycle array */ - unused_b:6; + has_seen_rtt:1, /* have we seen an RTT sample yet? */ + unused_b:5; u32 prior_cwnd; /* prior cwnd upon entering loss recovery */ u32 full_bw; /* recent bw, to estimate if pipe is full */ }; @@ -212,6 +212,35 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) return rate >> BW_SCALE; } +/* Convert a BBR bw and gain factor to a pacing rate in bytes per second. */ +static u32 bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain) +{ + u64 rate = bw; + + rate = bbr_rate_bytes_per_sec(sk, rate, gain); + rate = min_t(u64, rate, sk->sk_max_pacing_rate); + return rate; +} + +/* Initialize pacing rate to: high_gain * init_cwnd / RTT. */ +static void bbr_init_pacing_rate_from_rtt(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u64 bw; + u32 rtt_us; + + if (tp->srtt_us) { /* any RTT sample yet? */ + rtt_us = max(tp->srtt_us >> 3, 1U); + bbr->has_seen_rtt = 1; + } else { /* no RTT sample yet */ + rtt_us = USEC_PER_MSEC; /* use nominal default RTT */ + } + bw = (u64)tp->snd_cwnd * BW_UNIT; + do_div(bw, rtt_us); + sk->sk_pacing_rate = bbr_bw_to_pacing_rate(sk, bw, bbr_high_gain); +} + /* Pace using current bw estimate and a gain factor. In order to help drive the * network toward lower queues while maintaining high utilization and low * latency, the average pacing rate aims to be slightly (~1%) lower than the @@ -221,12 +250,13 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) */ static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain) { + struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); - u64 rate = bw; + u32 rate = bbr_bw_to_pacing_rate(sk, bw, gain); - rate = bbr_rate_bytes_per_sec(sk, rate, gain); - rate = min_t(u64, rate, sk->sk_max_pacing_rate); - if (bbr->mode != BBR_STARTUP || rate > sk->sk_pacing_rate) + if (unlikely(!bbr->has_seen_rtt && tp->srtt_us)) + bbr_init_pacing_rate_from_rtt(sk); + if (bbr_full_bw_reached(sk) || rate > sk->sk_pacing_rate) sk->sk_pacing_rate = rate; } @@ -412,7 +442,7 @@ static bool bbr_is_next_cycle_phase(struct sock *sk, struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); bool is_full_length = - skb_mstamp_us_delta(&tp->delivered_mstamp, &bbr->cycle_mstamp) > + tcp_stamp_us_delta(tp->delivered_mstamp, bbr->cycle_mstamp) > bbr->min_rtt_us; u32 inflight, bw; @@ -498,7 +528,7 @@ static void bbr_reset_lt_bw_sampling_interval(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); - bbr->lt_last_stamp = tp->delivered_mstamp.stamp_jiffies; + bbr->lt_last_stamp = div_u64(tp->delivered_mstamp, USEC_PER_MSEC); bbr->lt_last_delivered = tp->delivered; bbr->lt_last_lost = tp->lost; bbr->lt_rtt_cnt = 0; @@ -552,7 +582,7 @@ static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs) struct bbr *bbr = inet_csk_ca(sk); u32 lost, delivered; u64 bw; - s32 t; + u32 t; if (bbr->lt_use_bw) { /* already using long-term rate, lt_bw? */ if (bbr->mode == BBR_PROBE_BW && bbr->round_start && @@ -604,15 +634,15 @@ static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs) return; /* Find average delivery rate in this sampling interval. */ - t = (s32)(tp->delivered_mstamp.stamp_jiffies - bbr->lt_last_stamp); - if (t < 1) - return; /* interval is less than one jiffy, so wait */ - t = jiffies_to_usecs(t); - /* Interval long enough for jiffies_to_usecs() to return a bogus 0? */ - if (t < 1) { + t = div_u64(tp->delivered_mstamp, USEC_PER_MSEC) - bbr->lt_last_stamp; + if ((s32)t < 1) + return; /* interval is less than one ms, so wait */ + /* Check if can multiply without overflow */ + if (t >= ~0U / USEC_PER_MSEC) { bbr_reset_lt_bw_sampling(sk); /* interval too long; reset */ return; } + t *= USEC_PER_MSEC; bw = (u64)delivered * BW_UNIT; do_div(bw, t); bbr_lt_bw_interval_done(sk, bw); @@ -731,12 +761,12 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) bool filter_expired; /* Track min RTT seen in the min_rtt_win_sec filter window: */ - filter_expired = after(tcp_time_stamp, + filter_expired = after(tcp_jiffies32, bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ); if (rs->rtt_us >= 0 && (rs->rtt_us <= bbr->min_rtt_us || filter_expired)) { bbr->min_rtt_us = rs->rtt_us; - bbr->min_rtt_stamp = tcp_time_stamp; + bbr->min_rtt_stamp = tcp_jiffies32; } if (bbr_probe_rtt_mode_ms > 0 && filter_expired && @@ -755,7 +785,7 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) /* Maintain min packets in flight for max(200 ms, 1 round). */ if (!bbr->probe_rtt_done_stamp && tcp_packets_in_flight(tp) <= bbr_cwnd_min_target) { - bbr->probe_rtt_done_stamp = tcp_time_stamp + + bbr->probe_rtt_done_stamp = tcp_jiffies32 + msecs_to_jiffies(bbr_probe_rtt_mode_ms); bbr->probe_rtt_round_done = 0; bbr->next_rtt_delivered = tp->delivered; @@ -763,8 +793,8 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) if (bbr->round_start) bbr->probe_rtt_round_done = 1; if (bbr->probe_rtt_round_done && - after(tcp_time_stamp, bbr->probe_rtt_done_stamp)) { - bbr->min_rtt_stamp = tcp_time_stamp; + after(tcp_jiffies32, bbr->probe_rtt_done_stamp)) { + bbr->min_rtt_stamp = tcp_jiffies32; bbr->restore_cwnd = 1; /* snap to prior_cwnd */ bbr_reset_mode(sk); } @@ -799,7 +829,6 @@ static void bbr_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); - u64 bw; bbr->prior_cwnd = 0; bbr->tso_segs_goal = 0; /* default segs per skb until first ACK */ @@ -811,25 +840,24 @@ static void bbr_init(struct sock *sk) bbr->probe_rtt_done_stamp = 0; bbr->probe_rtt_round_done = 0; bbr->min_rtt_us = tcp_min_rtt(tp); - bbr->min_rtt_stamp = tcp_time_stamp; + bbr->min_rtt_stamp = tcp_jiffies32; minmax_reset(&bbr->bw, bbr->rtt_cnt, 0); /* init max bw to 0 */ - /* Initialize pacing rate to: high_gain * init_cwnd / RTT. */ - bw = (u64)tp->snd_cwnd * BW_UNIT; - do_div(bw, (tp->srtt_us >> 3) ? : USEC_PER_MSEC); - sk->sk_pacing_rate = 0; /* force an update of sk_pacing_rate */ - bbr_set_pacing_rate(sk, bw, bbr_high_gain); + bbr->has_seen_rtt = 0; + bbr_init_pacing_rate_from_rtt(sk); bbr->restore_cwnd = 0; bbr->round_start = 0; bbr->idle_restart = 0; bbr->full_bw = 0; bbr->full_bw_cnt = 0; - bbr->cycle_mstamp.v64 = 0; + bbr->cycle_mstamp = 0; bbr->cycle_idx = 0; bbr_reset_lt_bw_sampling(sk); bbr_reset_startup_mode(sk); + + cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); } static u32 bbr_sndbuf_expand(struct sock *sk) diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index 36087bca9f48..609965f0e298 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -84,14 +84,14 @@ static void bictcp_init(struct sock *sk) static inline void bictcp_update(struct bictcp *ca, u32 cwnd) { if (ca->last_cwnd == cwnd && - (s32)(tcp_time_stamp - ca->last_time) <= HZ / 32) + (s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32) return; ca->last_cwnd = cwnd; - ca->last_time = tcp_time_stamp; + ca->last_time = tcp_jiffies32; if (ca->epoch_start == 0) /* record the beginning of an epoch */ - ca->epoch_start = tcp_time_stamp; + ca->epoch_start = tcp_jiffies32; /* start off normal */ if (cwnd <= low_window) { diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 324c9bcc5456..fde983f6376b 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -189,8 +189,8 @@ void tcp_init_congestion_control(struct sock *sk) INET_ECN_dontxmit(sk); } -static void tcp_reinit_congestion_control(struct sock *sk, - const struct tcp_congestion_ops *ca) +void tcp_reinit_congestion_control(struct sock *sk, + const struct tcp_congestion_ops *ca) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -333,8 +333,12 @@ out: return ret; } -/* Change congestion control for socket */ -int tcp_set_congestion_control(struct sock *sk, const char *name) +/* Change congestion control for socket. If load is false, then it is the + * responsibility of the caller to call tcp_init_congestion_control or + * tcp_reinit_congestion_control (if the current congestion control was + * already initialized. + */ +int tcp_set_congestion_control(struct sock *sk, const char *name, bool load) { struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; @@ -344,21 +348,29 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) return -EPERM; rcu_read_lock(); - ca = __tcp_ca_find_autoload(name); + if (!load) + ca = tcp_ca_find(name); + else + ca = __tcp_ca_find_autoload(name); /* No change asking for existing value */ if (ca == icsk->icsk_ca_ops) { icsk->icsk_ca_setsockopt = 1; goto out; } - if (!ca) + if (!ca) { err = -ENOENT; - else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || - ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) + } else if (!load) { + icsk->icsk_ca_ops = ca; + if (!try_module_get(ca->owner)) + err = -EBUSY; + } else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || + ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) { err = -EPERM; - else if (!try_module_get(ca->owner)) + } else if (!try_module_get(ca->owner)) { err = -EBUSY; - else + } else { tcp_reinit_congestion_control(sk, ca); + } out: rcu_read_unlock(); return err; diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 0683ba447d77..57ae5b5ae643 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -155,7 +155,7 @@ static void bictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_TX_START) { struct bictcp *ca = inet_csk_ca(sk); - u32 now = tcp_time_stamp; + u32 now = tcp_jiffies32; s32 delta; delta = now - tcp_sk(sk)->lsndtime; @@ -231,21 +231,21 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked) ca->ack_cnt += acked; /* count the number of ACKed packets */ if (ca->last_cwnd == cwnd && - (s32)(tcp_time_stamp - ca->last_time) <= HZ / 32) + (s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32) return; /* The CUBIC function can update ca->cnt at most once per jiffy. * On all cwnd reduction events, ca->epoch_start is set to 0, * which will force a recalculation of ca->cnt. */ - if (ca->epoch_start && tcp_time_stamp == ca->last_time) + if (ca->epoch_start && tcp_jiffies32 == ca->last_time) goto tcp_friendliness; ca->last_cwnd = cwnd; - ca->last_time = tcp_time_stamp; + ca->last_time = tcp_jiffies32; if (ca->epoch_start == 0) { - ca->epoch_start = tcp_time_stamp; /* record beginning */ + ca->epoch_start = tcp_jiffies32; /* record beginning */ ca->ack_cnt = acked; /* start counting */ ca->tcp_cwnd = cwnd; /* syn with cubic */ @@ -276,7 +276,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked) * if the cwnd < 1 million packets !!! */ - t = (s32)(tcp_time_stamp - ca->epoch_start); + t = (s32)(tcp_jiffies32 - ca->epoch_start); t += msecs_to_jiffies(ca->delay_min >> 3); /* change the unit from HZ to bictcp_HZ */ t <<= BICTCP_HZ; @@ -448,7 +448,7 @@ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample) return; /* Discard delay samples right after fast recovery */ - if (ca->epoch_start && (s32)(tcp_time_stamp - ca->epoch_start) < HZ) + if (ca->epoch_start && (s32)(tcp_jiffies32 - ca->epoch_start) < HZ) return; delay = (sample->rtt_us << 3) / USEC_PER_MSEC; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 4af82b914dd4..ce9c7fef200f 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -214,13 +214,14 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, TCP_TIMEOUT_INIT, TCP_RTO_MAX); - atomic_set(&req->rsk_refcnt, 2); + refcount_set(&req->rsk_refcnt, 2); /* Now finish processing the fastopen child socket. */ inet_csk(child)->icsk_af_ops->rebuild_header(child); tcp_init_congestion_control(child); tcp_mtup_init(child); tcp_init_metrics(child); + tcp_call_bpf(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); tcp_init_buffer_space(child); tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 4a4d8e76738f..3eb78cde6ff0 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -104,7 +104,7 @@ static void measure_achieved_throughput(struct sock *sk, const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); struct htcp *ca = inet_csk_ca(sk); - u32 now = tcp_time_stamp; + u32 now = tcp_jiffies32; if (icsk->icsk_ca_state == TCP_CA_Open) ca->pkts_acked = sample->pkts_acked; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 174d4376baa5..2920e0cb09f8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -76,9 +76,6 @@ #include <asm/unaligned.h> #include <linux/errqueue.h> -int sysctl_tcp_timestamps __read_mostly = 1; -int sysctl_tcp_window_scaling __read_mostly = 1; -int sysctl_tcp_sack __read_mostly = 1; int sysctl_tcp_fack __read_mostly; int sysctl_tcp_max_reordering __read_mostly = 300; int sysctl_tcp_dsack __read_mostly = 1; @@ -112,6 +109,7 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */ #define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */ #define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */ +#define FLAG_NO_CHALLENGE_ACK 0x8000 /* do not call tcp_send_challenge_ack() */ #define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED) #define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED) @@ -441,7 +439,7 @@ void tcp_init_buffer_space(struct sock *sk) tcp_sndbuf_expand(sk); tp->rcvq_space.space = tp->rcv_wnd; - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); tp->rcvq_space.time = tp->tcp_mstamp; tp->rcvq_space.seq = tp->copied_seq; @@ -463,7 +461,7 @@ void tcp_init_buffer_space(struct sock *sk) tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss); tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp); - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; } /* 5. Recalculate window clamp after socket hit its memory bounds. */ @@ -555,11 +553,11 @@ static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp) { u32 delta_us; - if (tp->rcv_rtt_est.time.v64 == 0) + if (tp->rcv_rtt_est.time == 0) goto new_measure; if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq)) return; - delta_us = skb_mstamp_us_delta(&tp->tcp_mstamp, &tp->rcv_rtt_est.time); + delta_us = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcv_rtt_est.time); tcp_rcv_rtt_update(tp, delta_us, 1); new_measure: @@ -571,13 +569,15 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + if (tp->rx_opt.rcv_tsecr && (TCP_SKB_CB(skb)->end_seq - - TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) - tcp_rcv_rtt_update(tp, - jiffies_to_usecs(tcp_time_stamp - - tp->rx_opt.rcv_tsecr), - 0); + TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) { + u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; + u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + + tcp_rcv_rtt_update(tp, delta_us, 0); + } } /* @@ -590,7 +590,7 @@ void tcp_rcv_space_adjust(struct sock *sk) int time; int copied; - time = skb_mstamp_us_delta(&tp->tcp_mstamp, &tp->rcvq_space.time); + time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time); if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0) return; @@ -672,7 +672,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) tcp_rcv_rtt_measure(tp); - now = tcp_time_stamp; + now = tcp_jiffies32; if (!icsk->icsk_ack.ato) { /* The _first_ data packet received, initialize @@ -885,6 +885,9 @@ static void tcp_update_reordering(struct sock *sk, const int metric, struct tcp_sock *tp = tcp_sk(sk); int mib_idx; + if (WARN_ON_ONCE(metric < 0)) + return; + if (metric > tp->reordering) { tp->reordering = min(sysctl_tcp_max_reordering, metric); @@ -1134,8 +1137,8 @@ struct tcp_sacktag_state { * that was SACKed. RTO needs the earliest RTT to stay conservative, * but congestion control should still get an accurate delay signal. */ - struct skb_mstamp first_sackt; - struct skb_mstamp last_sackt; + u64 first_sackt; + u64 last_sackt; struct rate_sample *rate; int flag; }; @@ -1200,7 +1203,7 @@ 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, - const struct skb_mstamp *xmit_time) + u64 xmit_time) { struct tcp_sock *tp = tcp_sk(sk); int fack_count = state->fack_count; @@ -1242,9 +1245,9 @@ static u8 tcp_sacktag_one(struct sock *sk, state->reord); if (!after(end_seq, tp->high_seq)) state->flag |= FLAG_ORIG_SACK_ACKED; - if (state->first_sackt.v64 == 0) - state->first_sackt = *xmit_time; - state->last_sackt = *xmit_time; + if (state->first_sackt == 0) + state->first_sackt = xmit_time; + state->last_sackt = xmit_time; } if (sacked & TCPCB_LOST) { @@ -1304,7 +1307,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, */ tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, start_seq, end_seq, dup_sack, pcount, - &skb->skb_mstamp); + skb->skb_mstamp); tcp_rate_skb_delivered(sk, skb, state->rate); if (skb == tp->lost_skb_hint) @@ -1356,8 +1359,8 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tcp_advance_highest_sack(sk, skb); tcp_skb_collapse_tstamp(prev, skb); - if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp.v64)) - TCP_SKB_CB(prev)->tx.delivered_mstamp.v64 = 0; + if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp)) + TCP_SKB_CB(prev)->tx.delivered_mstamp = 0; tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); @@ -1587,7 +1590,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, TCP_SKB_CB(skb)->end_seq, dup_sack, tcp_skb_pcount(skb), - &skb->skb_mstamp); + skb->skb_mstamp); tcp_rate_skb_delivered(sk, skb, state->rate); if (!before(TCP_SKB_CB(skb)->seq, @@ -1954,7 +1957,7 @@ void tcp_enter_loss(struct sock *sk) } tp->snd_cwnd = 1; tp->snd_cwnd_cnt = 0; - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; tp->retrans_out = 0; tp->lost_out = 0; @@ -2383,7 +2386,7 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) tcp_ecn_withdraw_cwr(tp); } } - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; tp->undo_marker = 0; } @@ -2520,7 +2523,7 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk) if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) { tp->snd_cwnd = tp->snd_ssthresh; - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; } tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); } @@ -2590,7 +2593,7 @@ static void tcp_mtup_probe_success(struct sock *sk) tcp_mss_to_mtu(sk, tp->mss_cache) / icsk->icsk_mtup.probe_size; tp->snd_cwnd_cnt = 0; - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; tp->snd_ssthresh = tcp_current_ssthresh(sk); icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size; @@ -2911,13 +2914,13 @@ static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us) struct tcp_sock *tp = tcp_sk(sk); u32 wlen = sysctl_tcp_min_rtt_wlen * HZ; - minmax_running_min(&tp->rtt_min, wlen, tcp_time_stamp, + minmax_running_min(&tp->rtt_min, wlen, tcp_jiffies32, rtt_us ? : jiffies_to_usecs(1)); } -static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, - long seq_rtt_us, long sack_rtt_us, - long ca_rtt_us) +static bool tcp_ack_update_rtt(struct sock *sk, const int flag, + long seq_rtt_us, long sack_rtt_us, + long ca_rtt_us, struct rate_sample *rs) { const struct tcp_sock *tp = tcp_sk(sk); @@ -2936,9 +2939,13 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * See draft-ietf-tcplw-high-performance-00, section 3.3. */ if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && - flag & FLAG_ACKED) - seq_rtt_us = ca_rtt_us = jiffies_to_usecs(tcp_time_stamp - - tp->rx_opt.rcv_tsecr); + flag & FLAG_ACKED) { + u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; + u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + + seq_rtt_us = ca_rtt_us = delta_us; + } + rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */ if (seq_rtt_us < 0) return false; @@ -2958,16 +2965,13 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, /* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req) { + struct rate_sample rs; long rtt_us = -1L; - if (req && !req->num_retrans && tcp_rsk(req)->snt_synack.v64) { - struct skb_mstamp now; + if (req && !req->num_retrans && tcp_rsk(req)->snt_synack) + rtt_us = tcp_stamp_us_delta(tcp_clock_us(), tcp_rsk(req)->snt_synack); - skb_mstamp_get(&now); - rtt_us = skb_mstamp_us_delta(&now, &tcp_rsk(req)->snt_synack); - } - - tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L, rtt_us); + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L, rtt_us, &rs); } @@ -2976,7 +2980,7 @@ static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) const struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_ca_ops->cong_avoid(sk, ack, acked); - tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp; + tcp_sk(sk)->snd_cwnd_stamp = tcp_jiffies32; } /* Restart timer after forward progress on connection. @@ -3001,14 +3005,14 @@ void tcp_rearm_rto(struct sock *sk) if (icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { struct sk_buff *skb = tcp_write_queue_head(sk); - const u32 rto_time_stamp = - tcp_skb_timestamp(skb) + rto; - s32 delta = (s32)(rto_time_stamp - tcp_time_stamp); - /* delta may not be positive if the socket is locked + u64 rto_time_stamp = skb->skb_mstamp + + jiffies_to_usecs(rto); + s64 delta_us = rto_time_stamp - tp->tcp_mstamp; + /* delta_us may not be positive if the socket is locked * when the retrans timer fires and is rescheduled. */ - if (delta > 0) - rto = delta; + if (delta_us > 0) + rto = usecs_to_jiffies(delta_us); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto, TCP_RTO_MAX); @@ -3060,9 +3064,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, struct tcp_sacktag_state *sack) { const struct inet_connection_sock *icsk = inet_csk(sk); - struct skb_mstamp first_ackt, last_ackt; + u64 first_ackt, last_ackt; struct tcp_sock *tp = tcp_sk(sk); - struct skb_mstamp *now = &tp->tcp_mstamp; u32 prior_sacked = tp->sacked_out; u32 reord = tp->packets_out; bool fully_acked = true; @@ -3075,7 +3078,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, bool rtt_update; int flag = 0; - first_ackt.v64 = 0; + first_ackt = 0; while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); @@ -3106,8 +3109,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, flag |= FLAG_RETRANS_DATA_ACKED; } else if (!(sacked & TCPCB_SACKED_ACKED)) { last_ackt = skb->skb_mstamp; - WARN_ON_ONCE(last_ackt.v64 == 0); - if (!first_ackt.v64) + WARN_ON_ONCE(last_ackt == 0); + if (!first_ackt) first_ackt = last_ackt; last_in_flight = TCP_SKB_CB(skb)->tx.in_flight; @@ -3122,7 +3125,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->delivered += acked_pcount; if (!tcp_skb_spurious_retrans(tp, skb)) tcp_rack_advance(tp, sacked, scb->end_seq, - &skb->skb_mstamp); + skb->skb_mstamp); } if (sacked & TCPCB_LOST) tp->lost_out -= acked_pcount; @@ -3165,17 +3168,16 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; - if (likely(first_ackt.v64) && !(flag & FLAG_RETRANS_DATA_ACKED)) { - seq_rtt_us = skb_mstamp_us_delta(now, &first_ackt); - ca_rtt_us = skb_mstamp_us_delta(now, &last_ackt); + if (likely(first_ackt) && !(flag & FLAG_RETRANS_DATA_ACKED)) { + seq_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, first_ackt); + ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, last_ackt); } - if (sack->first_sackt.v64) { - sack_rtt_us = skb_mstamp_us_delta(now, &sack->first_sackt); - ca_rtt_us = skb_mstamp_us_delta(now, &sack->last_sackt); + if (sack->first_sackt) { + sack_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->first_sackt); + ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->last_sackt); } - sack->rate->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet, or -1 */ rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us, - ca_rtt_us); + ca_rtt_us, sack->rate); if (flag & FLAG_ACKED) { tcp_rearm_rto(sk); @@ -3201,7 +3203,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->fackets_out -= min(pkts_acked, tp->fackets_out); } else if (skb && rtt_update && sack_rtt_us >= 0 && - sack_rtt_us > skb_mstamp_us_delta(now, &skb->skb_mstamp)) { + sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp)) { /* Do not re-arm RTO if the sack RTT is measured from data sent * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. @@ -3211,7 +3213,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (icsk->icsk_ca_ops->pkts_acked) { struct ack_sample sample = { .pkts_acked = pkts_acked, - .rtt_us = ca_rtt_us, + .rtt_us = sack->rate->rtt_us, .in_flight = last_in_flight }; icsk->icsk_ca_ops->pkts_acked(sk, &sample); @@ -3390,7 +3392,7 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, u32 *last_oow_ack_time) { if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); + s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time); if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { NET_INC_STATS(net, mib_idx); @@ -3398,7 +3400,7 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, } } - *last_oow_ack_time = tcp_time_stamp; + *last_oow_ack_time = tcp_jiffies32; return false; /* not rate-limited: go ahead, send dupack now! */ } @@ -3553,7 +3555,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) int acked = 0; /* Number of packets newly acked */ int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */ - sack_state.first_sackt.v64 = 0; + sack_state.first_sackt = 0; sack_state.rate = &rs; /* We very likely will need to access write queue head. */ @@ -3565,7 +3567,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (before(ack, prior_snd_una)) { /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ if (before(ack, prior_snd_una - tp->max_window)) { - tcp_send_challenge_ack(sk, skb); + if (!(flag & FLAG_NO_CHALLENGE_ACK)) + tcp_send_challenge_ack(sk, skb); return -1; } goto old_ack; @@ -3636,7 +3639,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) */ sk->sk_err_soft = 0; icsk->icsk_probes_out = 0; - tp->rcv_tstamp = tcp_time_stamp; + tp->rcv_tstamp = tcp_jiffies32; if (!prior_packets) goto no_queue; @@ -3718,7 +3721,8 @@ static void tcp_parse_fastopen_option(int len, const unsigned char *cookie, * But, this can also be called on packets in the established flow when * the fast version below fails. */ -void tcp_parse_options(const struct sk_buff *skb, +void tcp_parse_options(const struct net *net, + const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc) { @@ -3759,7 +3763,7 @@ void tcp_parse_options(const struct sk_buff *skb, break; case TCPOPT_WINDOW: if (opsize == TCPOLEN_WINDOW && th->syn && - !estab && sysctl_tcp_window_scaling) { + !estab && net->ipv4.sysctl_tcp_window_scaling) { __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; if (snd_wscale > TCP_MAX_WSCALE) { @@ -3775,7 +3779,7 @@ void tcp_parse_options(const struct sk_buff *skb, case TCPOPT_TIMESTAMP: if ((opsize == TCPOLEN_TIMESTAMP) && ((estab && opt_rx->tstamp_ok) || - (!estab && sysctl_tcp_timestamps))) { + (!estab && net->ipv4.sysctl_tcp_timestamps))) { opt_rx->saw_tstamp = 1; opt_rx->rcv_tsval = get_unaligned_be32(ptr); opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4); @@ -3783,7 +3787,7 @@ void tcp_parse_options(const struct sk_buff *skb, break; case TCPOPT_SACK_PERM: if (opsize == TCPOLEN_SACK_PERM && th->syn && - !estab && sysctl_tcp_sack) { + !estab && net->ipv4.sysctl_tcp_sack) { opt_rx->sack_ok = TCP_SACK_SEEN; tcp_sack_reset(opt_rx); } @@ -3852,7 +3856,8 @@ static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr /* Fast parse options. This hopes to only see timestamps. * If it is wrong it falls back on tcp_parse_options(). */ -static bool tcp_fast_parse_options(const struct sk_buff *skb, +static bool tcp_fast_parse_options(const struct net *net, + const struct sk_buff *skb, const struct tcphdr *th, struct tcp_sock *tp) { /* In the spirit of fast parsing, compare doff directly to constant @@ -3867,7 +3872,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb, return true; } - tcp_parse_options(skb, &tp->rx_opt, 1, NULL); + tcp_parse_options(net, skb, &tp->rx_opt, 1, NULL); if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) tp->rx_opt.rcv_tsecr -= tp->tsoffset; @@ -5019,7 +5024,7 @@ static void tcp_new_space(struct sock *sk) if (tcp_should_expand_sndbuf(sk)) { tcp_sndbuf_expand(sk); - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; } sk->sk_write_space(sk); @@ -5228,7 +5233,8 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, bool rst_seq_match = false; /* RFC1323: H1. Apply PAWS check first. */ - if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp && + if (tcp_fast_parse_options(sock_net(sk), skb, th, tp) && + tp->rx_opt.saw_tstamp && tcp_paws_discard(sk, skb)) { if (!th->rst) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); @@ -5356,7 +5362,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); if (unlikely(!sk->sk_rx_dst)) inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); /* @@ -5554,7 +5560,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) struct inet_connection_sock *icsk = inet_csk(sk); tcp_set_state(sk, TCP_ESTABLISHED); - icsk->icsk_ack.lrcvtime = tcp_time_stamp; + icsk->icsk_ack.lrcvtime = tcp_jiffies32; if (skb) { icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); @@ -5565,13 +5571,13 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) icsk->icsk_af_ops->rebuild_header(sk); tcp_init_metrics(sk); - + tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); tcp_init_congestion_control(sk); /* Prevent spurious tcp_cwnd_restart() on first data * packet. */ - tp->lsndtime = tcp_time_stamp; + tp->lsndtime = tcp_jiffies32; tcp_init_buffer_space(sk); @@ -5599,7 +5605,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, /* Get original SYNACK MSS value if user MSS sets mss_clamp */ tcp_clear_options(&opt); opt.user_mss = opt.mss_clamp = 0; - tcp_parse_options(synack, &opt, 0, NULL); + tcp_parse_options(sock_net(sk), synack, &opt, 0, NULL); mss = opt.mss_clamp; } @@ -5653,7 +5659,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, int saved_clamp = tp->rx_opt.mss_clamp; bool fastopen_fail; - tcp_parse_options(skb, &tp->rx_opt, 0, &foc); + tcp_parse_options(sock_net(sk), skb, &tp->rx_opt, 0, &foc); if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) tp->rx_opt.rcv_tsecr -= tp->tsoffset; @@ -5672,7 +5678,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && !between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp, - tcp_time_stamp)) { + tcp_time_stamp(tp))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSACTIVEREJECTED); goto reset_and_undo; @@ -5917,7 +5923,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_SYN_SENT: tp->rx_opt.saw_tstamp = 0; - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); queued = tcp_rcv_synsent_state_process(sk, skb, th); if (queued >= 0) return queued; @@ -5929,7 +5935,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) return 0; } - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); tp->rx_opt.saw_tstamp = 0; req = tp->fastopen_rsk; if (req) { @@ -5948,13 +5954,17 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) /* step 5: check the ACK field */ acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH | - FLAG_UPDATE_TS_RECENT) > 0; + FLAG_UPDATE_TS_RECENT | + FLAG_NO_CHALLENGE_ACK) > 0; + if (!acceptable) { + if (sk->sk_state == TCP_SYN_RECV) + return 1; /* send one RST */ + tcp_send_challenge_ack(sk, skb); + goto discard; + } switch (sk->sk_state) { case TCP_SYN_RECV: - if (!acceptable) - return 1; - if (!tp->srtt_us) tcp_synack_rtt_meas(sk, req); @@ -5967,6 +5977,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) } else { /* Make sure socket is routed, for correct metrics. */ icsk->icsk_af_ops->rebuild_header(sk); + tcp_call_bpf(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); tcp_init_congestion_control(sk); tcp_mtup_init(sk); @@ -6008,7 +6019,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_update_pacing_rate(sk); /* Prevent spurious tcp_cwnd_restart() on first data packet */ - tp->lsndtime = tcp_time_stamp; + tp->lsndtime = tcp_jiffies32; tcp_initialize_rcv_mss(sk); tcp_fast_path_on(tp); @@ -6023,14 +6034,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) * our SYNACK so stop the SYNACK timer. */ if (req) { - /* Return RST if ack_seq is invalid. - * Note that RFC793 only says to generate a - * DUPACK for it but for TCP Fast Open it seems - * better to treat this case like TCP_SYN_RECV - * above. - */ - if (!acceptable) - return 1; /* We no longer need the request sock. */ reqsk_fastopen_remove(sk, req, false); tcp_rearm_rto(sk); @@ -6188,7 +6191,8 @@ static void tcp_ecn_create_request(struct request_sock *req, ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst; if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk) || - (ecn_ok_dst & DST_FEATURE_ECN_CA)) + (ecn_ok_dst & DST_FEATURE_ECN_CA) || + tcp_bpf_ca_needs_ecn((struct sock *)req)) inet_rsk(req)->ecn_ok = 1; } @@ -6202,7 +6206,7 @@ static void tcp_openreq_init(struct request_sock *req, req->cookie_ts = 0; tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - skb_mstamp_get(&tcp_rsk(req)->snt_synack); + tcp_rsk(req)->snt_synack = tcp_clock_us(); tcp_rsk(req)->last_oow_ack_time = 0; req->mss = rx_opt->mss_clamp; req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; @@ -6330,7 +6334,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = af_ops->mss_clamp; tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc); + tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, + want_cookie ? NULL : &foc); if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); @@ -6348,7 +6353,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_free; if (tmp_opt.tstamp_ok) - tcp_rsk(req)->ts_off = af_ops->init_ts_off(skb); + tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb); if (!want_cookie && !isn) { /* Kill the following clause, if you dislike this way. */ @@ -6403,7 +6408,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, } else { tcp_rsk(req)->tfo_listener = false; if (!want_cookie) - inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); + inet_csk_reqsk_queue_hash_add(sk, req, + tcp_timeout_init((struct sock *)req)); af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie ? TCP_SYNACK_NORMAL : TCP_SYNACK_COOKIE); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5ab2aac5ca19..a20e7f03d5f7 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -80,6 +80,7 @@ #include <linux/stddef.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/inetdevice.h> #include <crypto/hash.h> #include <linux/scatterlist.h> @@ -102,10 +103,9 @@ static u32 tcp_v4_init_seq(const struct sk_buff *skb) tcp_hdr(skb)->source); } -static u32 tcp_v4_init_ts_off(const struct sk_buff *skb) +static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) { - return secure_tcp_ts_off(ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr); + return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) @@ -242,7 +242,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, usin->sin_port); - tp->tsoffset = secure_tcp_ts_off(inet->inet_saddr, + tp->tsoffset = secure_tcp_ts_off(sock_net(sk), + inet->inet_saddr, inet->inet_daddr); } @@ -376,8 +377,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) struct sock *sk; struct sk_buff *skb; struct request_sock *fastopen; - __u32 seq, snd_una; - __u32 remaining; + u32 seq, snd_una; + s32 remaining; + u32 delta_us; int err; struct net *net = dev_net(icmp_skb->dev); @@ -483,11 +485,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) skb = tcp_write_queue_head(sk); BUG_ON(!skb); + tcp_mstamp_refresh(tp); + delta_us = (u32)(tp->tcp_mstamp - skb->skb_mstamp); remaining = icsk->icsk_rto - - min(icsk->icsk_rto, - tcp_time_stamp - tcp_skb_timestamp(skb)); + usecs_to_jiffies(delta_us); - if (remaining) { + if (remaining > 0) { inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, remaining, TCP_RTO_MAX); } else { @@ -811,7 +814,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v4_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcp_time_stamp + tcptw->tw_ts_offset, + tcp_time_stamp_raw() + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), @@ -839,7 +842,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, - tcp_time_stamp + tcp_rsk(req)->ts_off, + tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, 0, tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, @@ -904,6 +907,48 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, { const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; + const struct tcp_md5sig_info *md5sig; + __be32 mask; + struct tcp_md5sig_key *best_match = NULL; + bool match; + + /* caller either holds rcu_read_lock() or socket lock */ + md5sig = rcu_dereference_check(tp->md5sig_info, + lockdep_sock_is_held(sk)); + if (!md5sig) + return NULL; + + hlist_for_each_entry_rcu(key, &md5sig->head, node) { + if (key->family != family) + continue; + + if (family == AF_INET) { + mask = inet_make_mask(key->prefixlen); + match = (key->addr.a4.s_addr & mask) == + (addr->a4.s_addr & mask); +#if IS_ENABLED(CONFIG_IPV6) + } else if (family == AF_INET6) { + match = ipv6_prefix_equal(&key->addr.a6, &addr->a6, + key->prefixlen); +#endif + } else { + match = false; + } + + if (match && (!best_match || + key->prefixlen > best_match->prefixlen)) + best_match = key; + } + return best_match; +} +EXPORT_SYMBOL(tcp_md5_do_lookup); + +static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, + const union tcp_md5_addr *addr, + int family, u8 prefixlen) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct tcp_md5sig_key *key; unsigned int size = sizeof(struct in_addr); const struct tcp_md5sig_info *md5sig; @@ -919,12 +964,12 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, hlist_for_each_entry_rcu(key, &md5sig->head, node) { if (key->family != family) continue; - if (!memcmp(&key->addr, addr, size)) + if (!memcmp(&key->addr, addr, size) && + key->prefixlen == prefixlen) return key; } return NULL; } -EXPORT_SYMBOL(tcp_md5_do_lookup); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk) @@ -938,14 +983,15 @@ EXPORT_SYMBOL(tcp_v4_md5_lookup); /* This can be called on a newly created socket, from other files */ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, - int family, const u8 *newkey, u8 newkeylen, gfp_t gfp) + int family, u8 prefixlen, const u8 *newkey, u8 newkeylen, + gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_info *md5sig; - key = tcp_md5_do_lookup(sk, addr, family); + key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); if (key) { /* Pre-existing entry - just update that one. */ memcpy(key->key, newkey, newkeylen); @@ -976,6 +1022,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, memcpy(key->key, newkey, newkeylen); key->keylen = newkeylen; key->family = family; + key->prefixlen = prefixlen; memcpy(&key->addr, addr, (family == AF_INET6) ? sizeof(struct in6_addr) : sizeof(struct in_addr)); @@ -984,11 +1031,12 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, } EXPORT_SYMBOL(tcp_md5_do_add); -int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family) +int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, + u8 prefixlen) { struct tcp_md5sig_key *key; - key = tcp_md5_do_lookup(sk, addr, family); + key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); if (!key) return -ENOENT; hlist_del_rcu(&key->node); @@ -1014,11 +1062,12 @@ static void tcp_clear_md5_list(struct sock *sk) } } -static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, - int optlen) +static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, + char __user *optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr; + u8 prefixlen = 32; if (optlen < sizeof(cmd)) return -EINVAL; @@ -1029,15 +1078,22 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, if (sin->sin_family != AF_INET) return -EINVAL; + if (optname == TCP_MD5SIG_EXT && + cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { + prefixlen = cmd.tcpm_prefixlen; + if (prefixlen > 32) + return -EINVAL; + } + if (!cmd.tcpm_keylen) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, - AF_INET); + AF_INET, prefixlen); if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, - AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, + AF_INET, prefixlen, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); } @@ -1340,7 +1396,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, * across. Shucks. */ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr, - AF_INET, key->key, key->keylen, GFP_ATOMIC); + AF_INET, 32, key->key, key->keylen, GFP_ATOMIC); sk_nocaps_add(newsk, NETIF_F_GSO_MASK); } #endif @@ -1673,6 +1729,8 @@ process: } if (nsk == sk) { reqsk_put(req); + } else if (tcp_filter(sk, skb)) { + goto discard_and_relse; } else if (tcp_child_process(sk, nsk, skb)) { tcp_v4_send_reset(nsk, skb); goto discard_and_relse; @@ -1858,6 +1916,8 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_cleanup_congestion_control(sk); + tcp_cleanup_ulp(sk); + /* Cleanup up the write buffer. */ tcp_write_queue_purge(sk); @@ -2263,7 +2323,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) from_kuid_munged(seq_user_ns(f), sock_i_uid(sk)), icsk->icsk_probes_out, sock_i_ino(sk), - atomic_read(&sk->sk_refcnt), sk, + refcount_read(&sk->sk_refcnt), sk, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, @@ -2289,7 +2349,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw, " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK", i, src, srcp, dest, destp, tw->tw_substate, 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, - atomic_read(&tw->tw_refcnt), tw); + refcount_read(&tw->tw_refcnt), tw); } #define TMPSZ 150 @@ -2385,6 +2445,7 @@ struct proto tcp_prot = { .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .orphan_count = &tcp_orphan_count, @@ -2463,6 +2524,9 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256); + net->ipv4.sysctl_tcp_sack = 1; + net->ipv4.sysctl_tcp_window_scaling = 1; + net->ipv4.sysctl_tcp_timestamps = 1; return 0; fail: diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index d6fb6c067af4..ae10ed64fe13 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -37,7 +37,7 @@ #include <net/tcp.h> /* resolution of owd */ -#define LP_RESOL 1000 +#define LP_RESOL TCP_TS_HZ /** * enum tcp_lp_state @@ -147,9 +147,9 @@ static u32 tcp_lp_remote_hz_estimator(struct sock *sk) tp->rx_opt.rcv_tsecr == lp->local_ref_time) goto out; - m = HZ * (tp->rx_opt.rcv_tsval - - lp->remote_ref_time) / (tp->rx_opt.rcv_tsecr - - lp->local_ref_time); + m = TCP_TS_HZ * + (tp->rx_opt.rcv_tsval - lp->remote_ref_time) / + (tp->rx_opt.rcv_tsecr - lp->local_ref_time); if (m < 0) m = -m; @@ -194,7 +194,7 @@ static u32 tcp_lp_owd_calculator(struct sock *sk) if (lp->flag & LP_VALID_RHZ) { owd = tp->rx_opt.rcv_tsval * (LP_RESOL / lp->remote_hz) - - tp->rx_opt.rcv_tsecr * (LP_RESOL / HZ); + tp->rx_opt.rcv_tsecr * (LP_RESOL / TCP_TS_HZ); if (owd < 0) owd = -owd; } @@ -264,18 +264,19 @@ static void tcp_lp_pkts_acked(struct sock *sk, const struct ack_sample *sample) { struct tcp_sock *tp = tcp_sk(sk); struct lp *lp = inet_csk_ca(sk); + u32 now = tcp_time_stamp(tp); u32 delta; if (sample->rtt_us > 0) tcp_lp_rtt_sample(sk, sample->rtt_us); /* calc inference */ - delta = tcp_time_stamp - tp->rx_opt.rcv_tsecr; + delta = now - tp->rx_opt.rcv_tsecr; if ((s32)delta > 0) lp->inference = 3 * delta; /* test if within inference */ - if (lp->last_drop && (tcp_time_stamp - lp->last_drop < lp->inference)) + if (lp->last_drop && (now - lp->last_drop < lp->inference)) lp->flag |= LP_WITHIN_INF; else lp->flag &= ~LP_WITHIN_INF; @@ -312,7 +313,7 @@ static void tcp_lp_pkts_acked(struct sock *sk, const struct ack_sample *sample) tp->snd_cwnd = max(tp->snd_cwnd >> 1U, 1U); /* record this drop time */ - lp->last_drop = tcp_time_stamp; + lp->last_drop = now; } static struct tcp_congestion_ops tcp_lp __read_mostly = { diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 653bbd67e3a3..102b2c90bb80 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -524,7 +524,7 @@ reset: tp->snd_cwnd = 1; else tp->snd_cwnd = tcp_init_cwnd(tp, dst); - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; } bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 717be4de5324..0ff83c1637d8 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -98,7 +98,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { - tcp_parse_options(skb, &tmp_opt, 0, NULL); + tcp_parse_options(twsk_net(tw), skb, &tmp_opt, 0, NULL); if (tmp_opt.saw_tstamp) { if (tmp_opt.rcv_tsecr) @@ -351,6 +351,7 @@ void tcp_openreq_init_rwin(struct request_sock *req, int full_space = tcp_full_space(sk_listener); u32 window_clamp; __u8 rcv_wscale; + u32 rcv_wnd; int mss; mss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); @@ -363,6 +364,12 @@ void tcp_openreq_init_rwin(struct request_sock *req, (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) req->rsk_window_clamp = full_space; + rcv_wnd = tcp_rwnd_init_bpf((struct sock *)req); + if (rcv_wnd == 0) + rcv_wnd = dst_metric(dst, RTAX_INITRWND); + else if (full_space < rcv_wnd * mss) + full_space = rcv_wnd * mss; + /* tcp_full_space because it is guaranteed to be the first packet */ tcp_select_initial_window(full_space, mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), @@ -370,7 +377,7 @@ void tcp_openreq_init_rwin(struct request_sock *req, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, - dst_metric(dst, RTAX_INITRWND)); + rcv_wnd); ireq->rcv_wscale = rcv_wscale; } EXPORT_SYMBOL(tcp_openreq_init_rwin); @@ -445,9 +452,9 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->srtt_us = 0; newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); - minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U); + minmax_reset(&newtp->rtt_min, tcp_jiffies32, ~0U); newicsk->icsk_rto = TCP_TIMEOUT_INIT; - newicsk->icsk_ack.lrcvtime = tcp_time_stamp; + newicsk->icsk_ack.lrcvtime = tcp_jiffies32; newtp->packets_out = 0; newtp->retrans_out = 0; @@ -455,7 +462,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->fackets_out = 0; newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; newtp->tlp_high_seq = 0; - newtp->lsndtime = treq->snt_synack.stamp_jiffies; + newtp->lsndtime = tcp_jiffies32; newsk->sk_txhash = treq->txhash; newtp->last_oow_ack_time = 0; newtp->total_retrans = req->num_retrans; @@ -526,7 +533,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->fastopen_req = NULL; newtp->fastopen_rsk = NULL; newtp->syn_data_acked = 0; - newtp->rack.mstamp.v64 = 0; + newtp->rack.mstamp = 0; newtp->rack.advanced = 0; __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); @@ -559,7 +566,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(struct tcphdr)>>2)) { - tcp_parse_options(skb, &tmp_opt, 0, NULL); + tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = req->ts_recent; diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c index 5de82a8d4d87..6d650ed3cb59 100644 --- a/net/ipv4/tcp_nv.c +++ b/net/ipv4/tcp_nv.c @@ -424,8 +424,8 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample) } /* Extract info for Tcp socket info provided via netlink */ -size_t tcpnv_get_info(struct sock *sk, u32 ext, int *attr, - union tcp_cc_info *info) +static size_t tcpnv_get_info(struct sock *sk, u32 ext, int *attr, + union tcp_cc_info *info) { const struct tcpnv *ca = inet_csk_ca(sk); @@ -440,7 +440,6 @@ size_t tcpnv_get_info(struct sock *sk, u32 ext, int *attr, } return 0; } -EXPORT_SYMBOL_GPL(tcpnv_get_info); static struct tcp_congestion_ops tcpnv __read_mostly = { .init = tcpnv_init, diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index bc68da38ea86..11f69bbf9307 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -152,7 +152,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, swap(gso_skb->sk, skb->sk); swap(gso_skb->destructor, skb->destructor); sum_truesize += skb->truesize; - atomic_add(sum_truesize - gso_skb->truesize, + refcount_add(sum_truesize - gso_skb->truesize, &skb->sk->sk_wmem_alloc); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4858e190f6ac..4e985dea1dd2 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -151,7 +151,7 @@ void tcp_cwnd_restart(struct sock *sk, s32 delta) while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd) cwnd >>= 1; tp->snd_cwnd = max(cwnd, restart_cwnd); - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; tp->snd_cwnd_used = 0; } @@ -160,7 +160,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp, struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - const u32 now = tcp_time_stamp; + const u32 now = tcp_jiffies32; if (tcp_packets_in_flight(tp) == 0) tcp_ca_event(sk, CA_EVENT_TX_START); @@ -316,7 +316,8 @@ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR; if (!(tp->ecn_flags & TCP_ECN_OK)) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; - else if (tcp_ca_needs_ecn(sk)) + else if (tcp_ca_needs_ecn(sk) || + tcp_bpf_ca_needs_ecn(sk)) INET_ECN_xmit(sk); } @@ -324,8 +325,9 @@ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk); bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 || - tcp_ca_needs_ecn(sk); + tcp_ca_needs_ecn(sk) || bpf_needs_ecn; if (!use_ecn) { const struct dst_entry *dst = __sk_dst_get(sk); @@ -339,7 +341,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) if (use_ecn) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; tp->ecn_flags = TCP_ECN_OK; - if (tcp_ca_needs_ecn(sk)) + if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn) INET_ECN_xmit(sk); } } @@ -569,18 +571,18 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; - if (likely(sysctl_tcp_timestamps && !*md5)) { + if (likely(sock_net(sk)->ipv4.sysctl_tcp_timestamps && !*md5)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } - if (likely(sysctl_tcp_window_scaling)) { + if (likely(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } - if (likely(sysctl_tcp_sack)) { + if (likely(sock_net(sk)->ipv4.sysctl_tcp_sack)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) remaining -= TCPOLEN_SACKPERM_ALIGNED; @@ -861,12 +863,11 @@ void tcp_wfree(struct sk_buff *skb) struct sock *sk = skb->sk; struct tcp_sock *tp = tcp_sk(sk); unsigned long flags, nval, oval; - int wmem; /* Keep one reference on sk_wmem_alloc. * Will be released by sk_free() from here or tcp_tasklet_func() */ - wmem = atomic_sub_return(skb->truesize - 1, &sk->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(skb->truesize - 1, &sk->sk_wmem_alloc)); /* If this softirq is serviced by ksoftirqd, we are likely under stress. * Wait until our queues (qdisc + devices) are drained. @@ -875,7 +876,7 @@ void tcp_wfree(struct sk_buff *skb) * - chance for incoming ACK (processed by another cpu maybe) * to migrate this flow (skb->ooo_okay will be eventually set) */ - if (wmem >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current) + if (refcount_read(&sk->sk_wmem_alloc) >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current) goto out; for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) { @@ -904,6 +905,72 @@ out: sk_free(sk); } +/* Note: Called under hard irq. + * We can not call TCP stack right away. + */ +enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) +{ + struct tcp_sock *tp = container_of(timer, struct tcp_sock, pacing_timer); + struct sock *sk = (struct sock *)tp; + unsigned long nval, oval; + + for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) { + struct tsq_tasklet *tsq; + bool empty; + + if (oval & TSQF_QUEUED) + break; + + nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED | TCPF_TSQ_DEFERRED; + nval = cmpxchg(&sk->sk_tsq_flags, oval, nval); + if (nval != oval) + continue; + + if (!refcount_inc_not_zero(&sk->sk_wmem_alloc)) + break; + /* queue this socket to tasklet queue */ + tsq = this_cpu_ptr(&tsq_tasklet); + empty = list_empty(&tsq->head); + list_add(&tp->tsq_node, &tsq->head); + if (empty) + tasklet_schedule(&tsq->tasklet); + break; + } + return HRTIMER_NORESTART; +} + +/* BBR congestion control needs pacing. + * Same remark for SO_MAX_PACING_RATE. + * sch_fq packet scheduler is efficiently handling pacing, + * but is not always installed/used. + * Return true if TCP stack should pace packets itself. + */ +static bool tcp_needs_internal_pacing(const struct sock *sk) +{ + return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; +} + +static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) +{ + u64 len_ns; + u32 rate; + + if (!tcp_needs_internal_pacing(sk)) + return; + rate = sk->sk_pacing_rate; + if (!rate || rate == ~0U) + return; + + /* Should account for header sizes as sch_fq does, + * but lets make things simple. + */ + len_ns = (u64)skb->len * NSEC_PER_SEC; + do_div(len_ns, rate); + hrtimer_start(&tcp_sk(sk)->pacing_timer, + ktime_add_ns(ktime_get(), len_ns), + HRTIMER_MODE_ABS_PINNED); +} + /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. @@ -931,8 +998,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, BUG_ON(!skb || !tcp_skb_pcount(skb)); tp = tcp_sk(sk); + skb->skb_mstamp = tp->tcp_mstamp; if (clone_it) { - skb_mstamp_get(&skb->skb_mstamp); TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq - tp->snd_una; tcp_rate_skb_sent(sk, skb); @@ -979,7 +1046,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb->sk = sk; skb->destructor = skb_is_tcp_pure_ack(skb) ? __sock_wfree : tcp_wfree; skb_set_hash_from_sk(skb, sk); - atomic_add(skb->truesize, &sk->sk_wmem_alloc); + refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm); @@ -1034,6 +1101,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); tp->data_segs_out += tcp_skb_pcount(skb); + tcp_internal_pacing(sk, skb); } if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) @@ -1261,9 +1329,8 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, return 0; } -/* This is similar to __pskb_pull_head() (it will go to core/skbuff.c - * eventually). The difference is that pulled data not copied, but - * immediately discarded. +/* This is similar to __pskb_pull_tail(). The difference is that pulled + * data is not copied, but immediately discarded. */ static int __pskb_trim_head(struct sk_buff *skb, int len) { @@ -1298,7 +1365,6 @@ static int __pskb_trim_head(struct sk_buff *skb, int len) } shinfo->nr_frags = k; - skb_reset_tail_pointer(skb); skb->data_len -= len; skb->len = skb->data_len; return len; @@ -1408,7 +1474,7 @@ void tcp_mtup_init(struct sock *sk) icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss); icsk->icsk_mtup.probe_size = 0; if (icsk->icsk_mtup.enabled) - icsk->icsk_mtup.probe_timestamp = tcp_time_stamp; + icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } EXPORT_SYMBOL(tcp_mtup_init); @@ -1509,7 +1575,7 @@ static void tcp_cwnd_application_limited(struct sock *sk) } tp->snd_cwnd_used = 0; } - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; } static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) @@ -1530,14 +1596,14 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) if (tcp_is_cwnd_limited(sk)) { /* Network is feed fully. */ tp->snd_cwnd_used = 0; - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; } else { /* Network starves. */ if (tp->packets_out > tp->snd_cwnd_used) tp->snd_cwnd_used = tp->packets_out; if (sysctl_tcp_slow_start_after_idle && - (s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && + (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && !ca_ops->cong_control) tcp_cwnd_application_limited(sk); @@ -1839,7 +1905,6 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, const struct inet_connection_sock *icsk = inet_csk(sk); u32 age, send_win, cong_win, limit, in_flight; struct tcp_sock *tp = tcp_sk(sk); - struct skb_mstamp now; struct sk_buff *head; int win_divisor; @@ -1852,7 +1917,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, /* Avoid bursty behavior by allowing defer * only if the last write was recent. */ - if ((s32)(tcp_time_stamp - tp->lsndtime) > 0) + if ((s32)(tcp_jiffies32 - tp->lsndtime) > 0) goto send_now; in_flight = tcp_packets_in_flight(tp); @@ -1895,8 +1960,8 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, } head = tcp_write_queue_head(sk); - skb_mstamp_get(&now); - age = skb_mstamp_us_delta(&now, &head->skb_mstamp); + + age = tcp_stamp_us_delta(tp->tcp_mstamp, head->skb_mstamp); /* If next ACK is likely to come too late (half srtt), do not defer */ if (age < (tp->srtt_us >> 4)) goto send_now; @@ -1921,7 +1986,7 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk) s32 delta; interval = net->ipv4.sysctl_tcp_probe_interval; - delta = tcp_time_stamp - icsk->icsk_mtup.probe_timestamp; + delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp; if (unlikely(delta >= interval * HZ)) { int mss = tcp_current_mss(sk); @@ -1933,7 +1998,7 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk) icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); /* Update probe time stamp */ - icsk->icsk_mtup.probe_timestamp = tcp_time_stamp; + icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } } @@ -2086,6 +2151,12 @@ static int tcp_mtu_probe(struct sock *sk) return -1; } +static bool tcp_pacing_check(const struct sock *sk) +{ + return tcp_needs_internal_pacing(sk) && + hrtimer_active(&tcp_sk(sk)->pacing_timer); +} + /* TCP Small Queues : * Control number of packets in qdisc/devices to two packets / or ~1 ms. * (These limits are doubled for retransmits) @@ -2106,7 +2177,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes); limit <<= factor; - if (atomic_read(&sk->sk_wmem_alloc) > limit) { + if (refcount_read(&sk->sk_wmem_alloc) > limit) { /* Always send the 1st or 2nd skb in write queue. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. @@ -2122,7 +2193,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, * test again the condition. */ smp_mb__after_atomic(); - if (atomic_read(&sk->sk_wmem_alloc) > limit) + if (refcount_read(&sk->sk_wmem_alloc) > limit) return true; } return false; @@ -2130,7 +2201,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, static void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new) { - const u32 now = tcp_time_stamp; + const u32 now = tcp_jiffies32; if (tp->chrono_type > TCP_CHRONO_UNSPEC) tp->chrono_stat[tp->chrono_type - 1] += now - tp->chrono_start; @@ -2207,15 +2278,19 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, } max_segs = tcp_tso_segs(sk, mss_now); + tcp_mstamp_refresh(tp); while ((skb = tcp_send_head(sk))) { unsigned int limit; + if (tcp_pacing_check(sk)) + break; + tso_segs = tcp_init_tso_segs(skb, mss_now); BUG_ON(!tso_segs); if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp" is used as a start point for the retransmit timer */ - skb_mstamp_get(&skb->skb_mstamp); + skb->skb_mstamp = tp->tcp_mstamp; goto repair; /* Skip network transmission */ } @@ -2342,10 +2417,10 @@ bool tcp_schedule_loss_probe(struct sock *sk) timeout = max_t(u32, timeout, msecs_to_jiffies(10)); /* If RTO is shorter, just schedule TLP in its place. */ - tlp_time_stamp = tcp_time_stamp + timeout; + tlp_time_stamp = tcp_jiffies32 + timeout; rto_time_stamp = (u32)inet_csk(sk)->icsk_timeout; if ((s32)(tlp_time_stamp - rto_time_stamp) > 0) { - s32 delta = rto_time_stamp - tcp_time_stamp; + s32 delta = rto_time_stamp - tcp_jiffies32; if (delta > 0) timeout = delta; } @@ -2738,7 +2813,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) /* Do not sent more than we queued. 1/4 is reserved for possible * copying overhead: fragmentation, tunneling, mangling etc. */ - if (atomic_read(&sk->sk_wmem_alloc) > + if (refcount_read(&sk->sk_wmem_alloc) > min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf)) return -EAGAIN; @@ -2803,7 +2878,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb; - skb_mstamp_get(&skb->skb_mstamp); + skb->skb_mstamp = tp->tcp_mstamp; nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : -ENOBUFS; @@ -2878,6 +2953,10 @@ void tcp_xmit_retransmit_queue(struct sock *sk) if (skb == tcp_send_head(sk)) break; + + if (tcp_pacing_check(sk)) + break; + /* we could do better than to assign each time */ if (!hole) tp->retransmit_skb_hint = skb; @@ -3015,7 +3094,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) skb_reserve(skb, MAX_TCP_HEADER); tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), TCPHDR_ACK | TCPHDR_RST); - skb_mstamp_get(&skb->skb_mstamp); + tcp_mstamp_refresh(tcp_sk(sk)); /* Send it off. */ if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); @@ -3111,10 +3190,10 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, memset(&opts, 0, sizeof(opts)); #ifdef CONFIG_SYN_COOKIES if (unlikely(req->cookie_ts)) - skb->skb_mstamp.stamp_jiffies = cookie_init_timestamp(req); + skb->skb_mstamp = cookie_init_timestamp(req); else #endif - skb_mstamp_get(&skb->skb_mstamp); + skb->skb_mstamp = tcp_clock_us(); #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); @@ -3134,6 +3213,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, tcp_ecn_make_synack(req, th); th->source = htons(ireq->ir_num); th->dest = ireq->ir_rmt_port; + skb->mark = ireq->ir_mark; /* Setting of flags are superfluous here for callers (and ECE is * not even correctly set) */ @@ -3189,12 +3269,14 @@ static void tcp_connect_init(struct sock *sk) const struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); __u8 rcv_wscale; + u32 rcv_wnd; /* We'll fix this up when we get a response from the other end. * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ - tp->tcp_header_len = sizeof(struct tcphdr) + - (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0); + tp->tcp_header_len = sizeof(struct tcphdr); + if (sock_net(sk)->ipv4.sysctl_tcp_timestamps) + tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG if (tp->af_specific->md5_lookup(sk, sk)) @@ -3221,13 +3303,17 @@ static void tcp_connect_init(struct sock *sk) (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0)) tp->window_clamp = tcp_full_space(sk); + rcv_wnd = tcp_rwnd_init_bpf(sk); + if (rcv_wnd == 0) + rcv_wnd = dst_metric(dst, RTAX_INITRWND); + tcp_select_initial_window(tcp_full_space(sk), tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, - sysctl_tcp_window_scaling, + sock_net(sk)->ipv4.sysctl_tcp_window_scaling, &rcv_wscale, - dst_metric(dst, RTAX_INITRWND)); + rcv_wnd); tp->rx_opt.rcv_wscale = rcv_wscale; tp->rcv_ssthresh = tp->rcv_wnd; @@ -3244,11 +3330,11 @@ static void tcp_connect_init(struct sock *sk) if (likely(!tp->repair)) tp->rcv_nxt = 0; else - tp->rcv_tstamp = tcp_time_stamp; + tp->rcv_tstamp = tcp_jiffies32; tp->rcv_wup = tp->rcv_nxt; tp->copied_seq = tp->rcv_nxt; - inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT; + inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); inet_csk(sk)->icsk_retransmits = 0; tcp_clear_retrans(tp); } @@ -3361,6 +3447,7 @@ int tcp_connect(struct sock *sk) struct sk_buff *buff; int err; + tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB); tcp_connect_init(sk); if (unlikely(tp->repair)) { @@ -3373,7 +3460,8 @@ int tcp_connect(struct sock *sk) return -ENOBUFS; tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); - tp->retrans_stamp = tcp_time_stamp; + tcp_mstamp_refresh(tp); + tp->retrans_stamp = tcp_time_stamp(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); @@ -3492,7 +3580,6 @@ void tcp_send_ack(struct sock *sk) skb_set_tcp_pure_ack(buff); /* Send it off, this clears delayed acks for us. */ - skb_mstamp_get(&buff->skb_mstamp); tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0); } EXPORT_SYMBOL_GPL(tcp_send_ack); @@ -3526,15 +3613,16 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) * send it. */ tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK); - skb_mstamp_get(&skb->skb_mstamp); NET_INC_STATS(sock_net(sk), mib); return tcp_transmit_skb(sk, skb, 0, (__force gfp_t)0); } +/* Called from setsockopt( ... TCP_REPAIR ) */ void tcp_send_window_probe(struct sock *sk) { if (sk->sk_state == TCP_ESTABLISHED) { tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; + tcp_mstamp_refresh(tcp_sk(sk)); tcp_xmit_probe_skb(sk, 0, LINUX_MIB_TCPWINPROBE); } } diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index c6a9fa894646..3330a370d306 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -78,7 +78,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *scb = TCP_SKB_CB(skb); - if (!scb->tx.delivered_mstamp.v64) + if (!scb->tx.delivered_mstamp) return; if (!rs->prior_delivered || @@ -89,9 +89,9 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, rs->is_retrans = scb->sacked & TCPCB_RETRANS; /* Find the duration of the "send phase" of this window: */ - rs->interval_us = skb_mstamp_us_delta( - &skb->skb_mstamp, - &scb->tx.first_tx_mstamp); + rs->interval_us = tcp_stamp_us_delta( + skb->skb_mstamp, + scb->tx.first_tx_mstamp); /* Record send time of most recently ACKed packet: */ tp->first_tx_mstamp = skb->skb_mstamp; @@ -101,7 +101,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, * we don't need to reset since it'll be freed soon. */ if (scb->sacked & TCPCB_SACKED_ACKED) - scb->tx.delivered_mstamp.v64 = 0; + scb->tx.delivered_mstamp = 0; } /* Update the connection delivery information and generate a rate sample. */ @@ -125,7 +125,7 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, rs->acked_sacked = delivered; /* freshly ACKed or SACKed */ rs->losses = lost; /* freshly marked lost */ /* Return an invalid sample if no timing information is available. */ - if (!rs->prior_mstamp.v64) { + if (!rs->prior_mstamp) { rs->delivered = -1; rs->interval_us = -1; return; @@ -138,8 +138,8 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, * longer phase. */ snd_us = rs->interval_us; /* send phase */ - ack_us = skb_mstamp_us_delta(&tp->tcp_mstamp, - &rs->prior_mstamp); /* ack phase */ + ack_us = tcp_stamp_us_delta(tp->tcp_mstamp, + rs->prior_mstamp); /* ack phase */ rs->interval_us = max(snd_us, ack_us); /* Normally we expect interval_us >= min-rtt. @@ -185,3 +185,4 @@ void tcp_rate_check_app_limited(struct sock *sk) tp->app_limited = (tp->delivered + tcp_packets_in_flight(tp)) ? : 1; } +EXPORT_SYMBOL_GPL(tcp_rate_check_app_limited); diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 362b8c75bfab..fe9a493d0208 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -17,12 +17,9 @@ static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb) } } -static bool tcp_rack_sent_after(const struct skb_mstamp *t1, - const struct skb_mstamp *t2, - u32 seq1, u32 seq2) +static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) { - return skb_mstamp_after(t1, t2) || - (t1->v64 == t2->v64 && after(seq1, seq2)); + return t1 > t2 || (t1 == t2 && after(seq1, seq2)); } /* RACK loss detection (IETF draft draft-ietf-tcpm-rack-01): @@ -72,14 +69,14 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) scb->sacked & TCPCB_SACKED_ACKED) continue; - if (tcp_rack_sent_after(&tp->rack.mstamp, &skb->skb_mstamp, + if (tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp, tp->rack.end_seq, scb->end_seq)) { /* Step 3 in draft-cheng-tcpm-rack-00.txt: * A packet is lost if its elapsed time is beyond * the recent RTT plus the reordering window. */ - u32 elapsed = skb_mstamp_us_delta(&tp->tcp_mstamp, - &skb->skb_mstamp); + u32 elapsed = tcp_stamp_us_delta(tp->tcp_mstamp, + skb->skb_mstamp); s32 remaining = tp->rack.rtt_us + reo_wnd - elapsed; if (remaining < 0) { @@ -127,16 +124,16 @@ void tcp_rack_mark_lost(struct sock *sk) * draft-cheng-tcpm-rack-00.txt */ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, - const struct skb_mstamp *xmit_time) + u64 xmit_time) { u32 rtt_us; - if (tp->rack.mstamp.v64 && - !tcp_rack_sent_after(xmit_time, &tp->rack.mstamp, + if (tp->rack.mstamp && + !tcp_rack_sent_after(xmit_time, tp->rack.mstamp, end_seq, tp->rack.end_seq)) return; - rtt_us = skb_mstamp_us_delta(&tp->tcp_mstamp, xmit_time); + rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, xmit_time); if (sacked & TCPCB_RETRANS) { /* If the sacked packet was retransmitted, it's ambiguous * whether the retransmission or the original (or the prior @@ -152,7 +149,7 @@ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, return; } tp->rack.rtt_us = rtt_us; - tp->rack.mstamp = *xmit_time; + tp->rack.mstamp = xmit_time; tp->rack.end_seq = end_seq; tp->rack.advanced = 1; } @@ -166,7 +163,6 @@ void tcp_rack_reo_timeout(struct sock *sk) u32 timeout, prior_inflight; prior_inflight = tcp_packets_in_flight(tp); - skb_mstamp_get(&tp->tcp_mstamp); tcp_rack_detect_loss(sk, &timeout); if (prior_inflight != tcp_packets_in_flight(tp)) { if (inet_csk(sk)->icsk_ca_state != TCP_CA_Recovery) { diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 14672543cf0b..c0feeeef962a 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -63,7 +63,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) /* If peer does not open window for long time, or did not transmit * anything for long time, penalize it. */ - if ((s32)(tcp_time_stamp - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset) + if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset) shift++; /* If some dubious ICMP arrived, penalize even more. */ @@ -73,7 +73,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) 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 || + if ((s32)(tcp_jiffies32 - tp->lsndtime) <= TCP_TIMEWAIT_LEN || /* 2. Window is closed. */ (!tp->snd_wnd && !tp->packets_out)) do_reset = true; @@ -115,7 +115,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) if (net->ipv4.sysctl_tcp_mtu_probing) { if (!icsk->icsk_mtup.enabled) { icsk->icsk_mtup.enabled = 1; - icsk->icsk_mtup.probe_timestamp = tcp_time_stamp; + icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } else { struct net *net = sock_net(sk); @@ -139,22 +139,18 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) * @timeout: A custom timeout value. * If set to 0 the default timeout is calculated and used. * Using TCP_RTO_MIN and the number of unsuccessful retransmits. - * @syn_set: true if the SYN Bit was set. * * The default "timeout" value this function can calculate and use * is equivalent to the timeout of a TCP Connection * after "boundary" unsuccessful, exponentially backed-off - * retransmissions with an initial RTO of TCP_RTO_MIN or TCP_TIMEOUT_INIT if - * syn_set flag is set. - * + * retransmissions with an initial RTO of TCP_RTO_MIN. */ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, - unsigned int timeout, - bool syn_set) + unsigned int timeout) { + const unsigned int rto_base = TCP_RTO_MIN; unsigned int linear_backoff_thresh, start_ts; - unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN; if (!inet_csk(sk)->icsk_retransmits) return false; @@ -172,7 +168,7 @@ static bool retransmits_timed_out(struct sock *sk, timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + (boundary - linear_backoff_thresh) * TCP_RTO_MAX; } - return (tcp_time_stamp - start_ts) >= timeout; + return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= jiffies_to_msecs(timeout); } /* A write timeout has occurred. Process the after effects. */ @@ -181,8 +177,8 @@ static int tcp_write_timeout(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); + bool expired, do_reset; int retry_until; - bool do_reset, syn_set = false; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) { @@ -196,9 +192,9 @@ static int tcp_write_timeout(struct sock *sk) sk_rethink_txhash(sk); } retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; - syn_set = true; + expired = icsk->icsk_retransmits >= retry_until; } else { - if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0, 0)) { + if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0)) { /* Some middle-boxes may black-hole Fast Open _after_ * the handshake. Therefore we conservatively disable * Fast Open on this path on recurring timeouts after @@ -224,15 +220,15 @@ static int tcp_write_timeout(struct sock *sk) retry_until = tcp_orphan_retries(sk, alive); do_reset = alive || - !retransmits_timed_out(sk, retry_until, 0, 0); + !retransmits_timed_out(sk, retry_until, 0); if (tcp_out_of_resources(sk, do_reset)) return 1; } + expired = retransmits_timed_out(sk, retry_until, + icsk->icsk_user_timeout); } - - if (retransmits_timed_out(sk, retry_until, - syn_set ? 0 : icsk->icsk_user_timeout, syn_set)) { + if (expired) { /* Has it gone just too far? */ tcp_write_err(sk); return 1; @@ -339,9 +335,10 @@ static void tcp_probe_timer(struct sock *sk) */ start_ts = tcp_skb_timestamp(tcp_send_head(sk)); if (!start_ts) - skb_mstamp_get(&tcp_send_head(sk)->skb_mstamp); + tcp_send_head(sk)->skb_mstamp = tp->tcp_mstamp; else if (icsk->icsk_user_timeout && - (s32)(tcp_time_stamp - start_ts) > icsk->icsk_user_timeout) + (s32)(tcp_time_stamp(tp) - start_ts) > + jiffies_to_msecs(icsk->icsk_user_timeout)) goto abort; max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2; @@ -451,7 +448,7 @@ void tcp_retransmit_timer(struct sock *sk) tp->snd_una, tp->snd_nxt); } #endif - if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) { + if (tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX) { tcp_write_err(sk); goto out; } @@ -539,7 +536,7 @@ out_reset_timer: icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX); - if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0, 0)) + if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0)) __sk_dst_reset(sk); out:; @@ -561,6 +558,7 @@ void tcp_write_timer_handler(struct sock *sk) goto out; } + tcp_mstamp_refresh(tcp_sk(sk)); event = icsk->icsk_pending; switch (event) { @@ -710,4 +708,7 @@ void tcp_init_xmit_timers(struct sock *sk) { inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); + hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_PINNED); + tcp_sk(sk)->pacing_timer.function = tcp_pace_kick; } diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c new file mode 100644 index 000000000000..2417f55374c5 --- /dev/null +++ b/net/ipv4/tcp_ulp.c @@ -0,0 +1,135 @@ +/* + * Pluggable TCP upper layer protocol support. + * + * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. + * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved. + * + */ + +#include<linux/module.h> +#include <linux/mm.h> +#include <linux/types.h> +#include <linux/list.h> +#include <linux/gfp.h> +#include <net/tcp.h> + +static DEFINE_SPINLOCK(tcp_ulp_list_lock); +static LIST_HEAD(tcp_ulp_list); + +/* Simple linear search, don't expect many entries! */ +static struct tcp_ulp_ops *tcp_ulp_find(const char *name) +{ + struct tcp_ulp_ops *e; + + list_for_each_entry_rcu(e, &tcp_ulp_list, list) { + if (strcmp(e->name, name) == 0) + return e; + } + + return NULL; +} + +static const struct tcp_ulp_ops *__tcp_ulp_find_autoload(const char *name) +{ + const struct tcp_ulp_ops *ulp = NULL; + + rcu_read_lock(); + ulp = tcp_ulp_find(name); + +#ifdef CONFIG_MODULES + if (!ulp && capable(CAP_NET_ADMIN)) { + rcu_read_unlock(); + request_module("%s", name); + rcu_read_lock(); + ulp = tcp_ulp_find(name); + } +#endif + if (!ulp || !try_module_get(ulp->owner)) + ulp = NULL; + + rcu_read_unlock(); + return ulp; +} + +/* Attach new upper layer protocol to the list + * of available protocols. + */ +int tcp_register_ulp(struct tcp_ulp_ops *ulp) +{ + int ret = 0; + + spin_lock(&tcp_ulp_list_lock); + if (tcp_ulp_find(ulp->name)) { + pr_notice("%s already registered or non-unique name\n", + ulp->name); + ret = -EEXIST; + } else { + list_add_tail_rcu(&ulp->list, &tcp_ulp_list); + } + spin_unlock(&tcp_ulp_list_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(tcp_register_ulp); + +void tcp_unregister_ulp(struct tcp_ulp_ops *ulp) +{ + spin_lock(&tcp_ulp_list_lock); + list_del_rcu(&ulp->list); + spin_unlock(&tcp_ulp_list_lock); + + synchronize_rcu(); +} +EXPORT_SYMBOL_GPL(tcp_unregister_ulp); + +/* Build string with list of available upper layer protocl values */ +void tcp_get_available_ulp(char *buf, size_t maxlen) +{ + struct tcp_ulp_ops *ulp_ops; + size_t offs = 0; + + *buf = '\0'; + rcu_read_lock(); + list_for_each_entry_rcu(ulp_ops, &tcp_ulp_list, list) { + offs += snprintf(buf + offs, maxlen - offs, + "%s%s", + offs == 0 ? "" : " ", ulp_ops->name); + } + rcu_read_unlock(); +} + +void tcp_cleanup_ulp(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (!icsk->icsk_ulp_ops) + return; + + if (icsk->icsk_ulp_ops->release) + icsk->icsk_ulp_ops->release(sk); + module_put(icsk->icsk_ulp_ops->owner); +} + +/* Change upper layer protocol for socket */ +int tcp_set_ulp(struct sock *sk, const char *name) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcp_ulp_ops *ulp_ops; + int err = 0; + + if (icsk->icsk_ulp_ops) + return -EEXIST; + + ulp_ops = __tcp_ulp_find_autoload(name); + if (!ulp_ops) + err = -ENOENT; + else + err = ulp_ops->init(sk); + + if (err) + goto out; + + icsk->icsk_ulp_ops = ulp_ops; + out: + return err; +} diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c index 9775453b8d17..bec9cafbe3f9 100644 --- a/net/ipv4/tcp_westwood.c +++ b/net/ipv4/tcp_westwood.c @@ -68,7 +68,7 @@ static void tcp_westwood_init(struct sock *sk) w->cumul_ack = 0; w->reset_rtt_min = 1; w->rtt_min = w->rtt = TCP_WESTWOOD_INIT_RTT; - w->rtt_win_sx = tcp_time_stamp; + w->rtt_win_sx = tcp_jiffies32; w->snd_una = tcp_sk(sk)->snd_una; w->first_ack = 1; } @@ -116,7 +116,7 @@ static void tcp_westwood_pkts_acked(struct sock *sk, static void westwood_update_window(struct sock *sk) { struct westwood *w = inet_csk_ca(sk); - s32 delta = tcp_time_stamp - w->rtt_win_sx; + s32 delta = tcp_jiffies32 - w->rtt_win_sx; /* Initialize w->snd_una with the first acked sequence number in order * to fix mismatch between tp->snd_una and w->snd_una for the first @@ -140,7 +140,7 @@ static void westwood_update_window(struct sock *sk) westwood_filter(w, delta); w->bk = 0; - w->rtt_win_sx = tcp_time_stamp; + w->rtt_win_sx = tcp_jiffies32; } } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1d6219bf2d6b..b057653ceca9 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -577,7 +577,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table, NULL); - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } @@ -1163,23 +1163,62 @@ out: return ret; } +#if BITS_PER_LONG == 64 +static void udp_set_dev_scratch(struct sk_buff *skb) +{ + struct udp_dev_scratch *scratch; + + BUILD_BUG_ON(sizeof(struct udp_dev_scratch) > sizeof(long)); + scratch = (struct udp_dev_scratch *)&skb->dev_scratch; + scratch->truesize = skb->truesize; + scratch->len = skb->len; + scratch->csum_unnecessary = !!skb_csum_unnecessary(skb); + scratch->is_linear = !skb_is_nonlinear(skb); +} + +static int udp_skb_truesize(struct sk_buff *skb) +{ + return ((struct udp_dev_scratch *)&skb->dev_scratch)->truesize; +} +#else +static void udp_set_dev_scratch(struct sk_buff *skb) +{ + skb->dev_scratch = skb->truesize; +} + +static int udp_skb_truesize(struct sk_buff *skb) +{ + return skb->dev_scratch; +} +#endif + /* fully reclaim rmem/fwd memory allocated for skb */ -static void udp_rmem_release(struct sock *sk, int size, int partial) +static void udp_rmem_release(struct sock *sk, int size, int partial, + bool rx_queue_lock_held) { struct udp_sock *up = udp_sk(sk); + struct sk_buff_head *sk_queue; int amt; if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; if (size < (sk->sk_rcvbuf >> 2) && - !skb_queue_empty(&sk->sk_receive_queue)) + !skb_queue_empty(&up->reader_queue)) return; } else { size += up->forward_deficit; } up->forward_deficit = 0; + /* acquire the sk_receive_queue for fwd allocated memory scheduling, + * if the called don't held it already + */ + sk_queue = &sk->sk_receive_queue; + if (!rx_queue_lock_held) + spin_lock(&sk_queue->lock); + + sk->sk_forward_alloc += size; amt = (sk->sk_forward_alloc - partial) & ~(SK_MEM_QUANTUM - 1); sk->sk_forward_alloc -= amt; @@ -1188,19 +1227,33 @@ static void udp_rmem_release(struct sock *sk, int size, int partial) __sk_mem_reduce_allocated(sk, amt >> SK_MEM_QUANTUM_SHIFT); atomic_sub(size, &sk->sk_rmem_alloc); + + /* this can save us from acquiring the rx queue lock on next receive */ + skb_queue_splice_tail_init(sk_queue, &up->reader_queue); + + if (!rx_queue_lock_held) + spin_unlock(&sk_queue->lock); } -/* Note: called with sk_receive_queue.lock held. +/* Note: called with reader_queue.lock held. * Instead of using skb->truesize here, find a copy of it in skb->dev_scratch * This avoids a cache line miss while receive_queue lock is held. * Look at __udp_enqueue_schedule_skb() to find where this copy is done. */ void udp_skb_destructor(struct sock *sk, struct sk_buff *skb) { - udp_rmem_release(sk, skb->dev_scratch, 1); + prefetch(&skb->data); + udp_rmem_release(sk, udp_skb_truesize(skb), 1, false); } EXPORT_SYMBOL(udp_skb_destructor); +/* as above, but the caller held the rx queue lock, too */ +static void udp_skb_dtor_locked(struct sock *sk, struct sk_buff *skb) +{ + prefetch(&skb->data); + udp_rmem_release(sk, udp_skb_truesize(skb), 1, true); +} + /* Idea of busylocks is to let producers grab an extra spinlock * to relieve pressure on the receive_queue spinlock shared by consumer. * Under flood, this means that only one producer can be in line @@ -1252,10 +1305,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) busy = busylock_acquire(sk); } size = skb->truesize; - /* Copy skb->truesize into skb->dev_scratch to avoid a cache line miss - * in udp_skb_destructor() - */ - skb->dev_scratch = size; + udp_set_dev_scratch(skb); /* we drop only if the receive buf is full and the receive * queue contains some other skb @@ -1306,14 +1356,16 @@ EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb); void udp_destruct_sock(struct sock *sk) { /* reclaim completely the forward allocated memory */ + struct udp_sock *up = udp_sk(sk); unsigned int total = 0; struct sk_buff *skb; - while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { + skb_queue_splice_tail_init(&sk->sk_receive_queue, &up->reader_queue); + while ((skb = __skb_dequeue(&up->reader_queue)) != NULL) { total += skb->truesize; kfree_skb(skb); } - udp_rmem_release(sk, total, 0); + udp_rmem_release(sk, total, 0, true); inet_sock_destruct(sk); } @@ -1321,6 +1373,7 @@ EXPORT_SYMBOL_GPL(udp_destruct_sock); int udp_init_sock(struct sock *sk) { + skb_queue_head_init(&udp_sk(sk)->reader_queue); sk->sk_destruct = udp_destruct_sock; return 0; } @@ -1334,10 +1387,43 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) sk_peek_offset_bwd(sk, len); unlock_sock_fast(sk, slow); } - consume_skb(skb); + + /* we cleared the head states previously only if the skb lacks any IP + * options, see __udp_queue_rcv_skb(). + */ + if (unlikely(IPCB(skb)->opt.optlen > 0)) + skb_release_head_state(skb); + consume_stateless_skb(skb); } EXPORT_SYMBOL_GPL(skb_consume_udp); +static struct sk_buff *__first_packet_length(struct sock *sk, + struct sk_buff_head *rcvq, + int *total) +{ + struct sk_buff *skb; + + while ((skb = skb_peek(rcvq)) != NULL) { + if (udp_lib_checksum_complete(skb)) { + __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, + IS_UDPLITE(sk)); + __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + atomic_inc(&sk->sk_drops); + __skb_unlink(skb, rcvq); + *total += skb->truesize; + kfree_skb(skb); + } else { + /* the csum related bits could be changed, refresh + * the scratch area + */ + udp_set_dev_scratch(skb); + break; + } + } + return skb; +} + /** * first_packet_length - return length of first packet in receive queue * @sk: socket @@ -1347,26 +1433,24 @@ EXPORT_SYMBOL_GPL(skb_consume_udp); */ static int first_packet_length(struct sock *sk) { - struct sk_buff_head *rcvq = &sk->sk_receive_queue; + struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue; + struct sk_buff_head *sk_queue = &sk->sk_receive_queue; struct sk_buff *skb; int total = 0; int res; spin_lock_bh(&rcvq->lock); - while ((skb = skb_peek(rcvq)) != NULL && - udp_lib_checksum_complete(skb)) { - __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, - IS_UDPLITE(sk)); - __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, - IS_UDPLITE(sk)); - atomic_inc(&sk->sk_drops); - __skb_unlink(skb, rcvq); - total += skb->truesize; - kfree_skb(skb); + skb = __first_packet_length(sk, rcvq, &total); + if (!skb && !skb_queue_empty(sk_queue)) { + spin_lock(&sk_queue->lock); + skb_queue_splice_tail_init(sk_queue, rcvq); + spin_unlock(&sk_queue->lock); + + skb = __first_packet_length(sk, rcvq, &total); } res = skb ? skb->len : -1; if (total) - udp_rmem_release(sk, total, 1); + udp_rmem_release(sk, total, 1, false); spin_unlock_bh(&rcvq->lock); return res; } @@ -1400,6 +1484,77 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) } EXPORT_SYMBOL(udp_ioctl); +struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, + int noblock, int *peeked, int *off, int *err) +{ + struct sk_buff_head *sk_queue = &sk->sk_receive_queue; + struct sk_buff_head *queue; + struct sk_buff *last; + long timeo; + int error; + + queue = &udp_sk(sk)->reader_queue; + flags |= noblock ? MSG_DONTWAIT : 0; + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + do { + struct sk_buff *skb; + + error = sock_error(sk); + if (error) + break; + + error = -EAGAIN; + *peeked = 0; + do { + spin_lock_bh(&queue->lock); + skb = __skb_try_recv_from_queue(sk, queue, flags, + udp_skb_destructor, + peeked, off, err, + &last); + if (skb) { + spin_unlock_bh(&queue->lock); + return skb; + } + + if (skb_queue_empty(sk_queue)) { + spin_unlock_bh(&queue->lock); + goto busy_check; + } + + /* refill the reader queue and walk it again + * keep both queues locked to avoid re-acquiring + * the sk_receive_queue lock if fwd memory scheduling + * is needed. + */ + spin_lock(&sk_queue->lock); + skb_queue_splice_tail_init(sk_queue, queue); + + skb = __skb_try_recv_from_queue(sk, queue, flags, + udp_skb_dtor_locked, + peeked, off, err, + &last); + spin_unlock(&sk_queue->lock); + spin_unlock_bh(&queue->lock); + if (skb) + return skb; + +busy_check: + if (!sk_can_busy_loop(sk)) + break; + + sk_busy_loop(sk, flags & MSG_DONTWAIT); + } while (!skb_queue_empty(sk_queue)); + + /* sk_queue is empty, reader_queue may contain peeked packets */ + } while (timeo && + !__skb_wait_for_more_packets(sk, &error, &timeo, + (struct sk_buff *)sk_queue)); + + *err = error; + return NULL; +} +EXPORT_SYMBOL_GPL(__skb_recv_udp); + /* * This should be easy, if there is something there we * return it, otherwise we block. @@ -1426,7 +1581,7 @@ try_again: if (!skb) return err; - ulen = skb->len; + ulen = udp_skb_len(skb); copied = len; if (copied > ulen - off) copied = ulen - off; @@ -1441,14 +1596,18 @@ try_again: if (copied < ulen || peeking || (is_udplite && UDP_SKB_CB(skb)->partial_cov)) { - checksum_valid = !udp_lib_checksum_complete(skb); + checksum_valid = udp_skb_csum_unnecessary(skb) || + !__udp_lib_checksum_complete(skb); if (!checksum_valid) goto csum_copy_err; } - if (checksum_valid || skb_csum_unnecessary(skb)) - err = skb_copy_datagram_msg(skb, off, msg, copied); - else { + if (checksum_valid || udp_skb_csum_unnecessary(skb)) { + if (udp_skb_is_linear(skb)) + err = copy_linear_skb(skb, copied, off, &msg->msg_iter); + else + err = skb_copy_datagram_msg(skb, off, msg, copied); + } else { err = skb_copy_and_csum_datagram_msg(skb, off, msg); if (err == -EINVAL) @@ -1490,7 +1649,8 @@ try_again: return err; csum_copy_err: - if (!__sk_queue_drop_skb(sk, skb, flags, udp_skb_destructor)) { + if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags, + udp_skb_destructor)) { UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } @@ -1624,6 +1784,13 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) sk_mark_napi_id_once(sk, skb); } + /* At recvmsg() time we need skb->dst to process IP options-related + * cmsg, elsewhere can we clear all pending head states while they are + * hot in the cache + */ + if (likely(IPCB(skb)->opt.optlen == 0)) + skb_release_head_state(skb); + rc = __udp_enqueue_schedule_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); @@ -1738,6 +1905,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } } + prefetch(&sk->sk_rmem_alloc); if (rcu_access_pointer(sk->sk_filter) && udp_lib_checksum_complete(skb)) goto csum_error; @@ -1766,9 +1934,10 @@ static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old; - dst_hold(dst); - old = xchg(&sk->sk_rx_dst, dst); - dst_release(old); + if (dst_hold_safe(dst)) { + old = xchg(&sk->sk_rx_dst, dst); + dst_release(old); + } } /* @@ -2082,7 +2251,7 @@ void udp_v4_early_demux(struct sk_buff *skb) uh->source, iph->saddr, dif); } - if (!sk || !atomic_inc_not_zero_hint(&sk->sk_refcnt, 2)) + if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return; skb->sk = sk; @@ -2092,13 +2261,11 @@ void udp_v4_early_demux(struct sk_buff *skb) if (dst) dst = dst_check(dst, 0); if (dst) { - /* DST_NOCACHE can not be used without taking a reference */ - if (dst->flags & DST_NOCACHE) { - if (likely(atomic_inc_not_zero(&dst->__refcnt))) - skb_dst_set(skb, dst); - } else { - skb_dst_set_noref(skb, dst); - } + /* set noref for now. + * any place which wants to hold dst has to call + * dst_hold_safe() + */ + skb_dst_set_noref(skb, dst); } } @@ -2325,6 +2492,9 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) unsigned int mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; + if (!skb_queue_empty(&udp_sk(sk)->reader_queue)) + mask |= POLLIN | POLLRDNORM; + sock_rps_record_flow(sk); /* Check for false positives due to checksum errors */ @@ -2530,7 +2700,7 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f, 0, 0L, 0, from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, + refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 9a89c10a55f0..4515836d2a3a 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -55,7 +55,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, req->id.idiag_dport, req->id.idiag_if, tbl, NULL); #endif - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; rcu_read_unlock(); err = -ENOENT; @@ -206,7 +206,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb, return -EINVAL; } - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; rcu_read_unlock(); diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c index 71acd0014f2d..856d2dfdb44b 100644 --- a/net/ipv4/xfrm4_mode_beet.c +++ b/net/ipv4/xfrm4_mode_beet.c @@ -57,8 +57,7 @@ static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb) xfrm4_beet_make_header(skb); - ph = (struct ip_beet_phdr *) - __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdrlen); + ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdrlen); top_iph = ip_hdr(skb); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 1d2dbace42ff..3c46e9513a31 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -426,7 +426,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) } /* One reference from device. */ - in6_dev_hold(ndev); + refcount_set(&ndev->refcnt, 1); if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) ndev->cnf.accept_dad = -1; @@ -963,6 +963,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, struct net *net = dev_net(idev->dev); struct inet6_ifaddr *ifa = NULL; struct rt6_info *rt; + struct in6_validator_info i6vi; unsigned int hash; int err = 0; int addr_type = ipv6_addr_type(addr); @@ -974,6 +975,9 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, return ERR_PTR(-EADDRNOTAVAIL); rcu_read_lock_bh(); + + in6_dev_hold(idev); + if (idev->dead) { err = -ENODEV; /*XXX*/ goto out2; @@ -984,6 +988,17 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, goto out2; } + i6vi.i6vi_addr = *addr; + i6vi.i6vi_dev = idev; + rcu_read_unlock_bh(); + + err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi); + + rcu_read_lock_bh(); + err = notifier_to_errno(err); + if (err) + goto out2; + spin_lock(&addrconf_hash_lock); /* Ignore adding duplicate addresses on an interface */ @@ -1034,9 +1049,8 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifa->rt = rt; ifa->idev = idev; - in6_dev_hold(idev); /* For caller */ - in6_ifa_hold(ifa); + refcount_set(&ifa->refcnt, 1); /* Add to big hash table */ hash = inet6_addr_hash(addr); @@ -1062,6 +1076,7 @@ out2: inet6addr_notifier_call_chain(NETDEV_UP, ifa); else { kfree(ifa); + in6_dev_put(idev); ifa = ERR_PTR(err); } @@ -1912,15 +1927,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) if (dad_failed) ifp->flags |= IFA_F_DADFAILED; - if (ifp->flags&IFA_F_PERMANENT) { - spin_lock_bh(&ifp->lock); - addrconf_del_dad_work(ifp); - ifp->flags |= IFA_F_TENTATIVE; - spin_unlock_bh(&ifp->lock); - if (dad_failed) - ipv6_ifa_notify(0, ifp); - in6_ifa_put(ifp); - } else if (ifp->flags&IFA_F_TEMPORARY) { + if (ifp->flags&IFA_F_TEMPORARY) { struct inet6_ifaddr *ifpub; spin_lock_bh(&ifp->lock); ifpub = ifp->ifpub; @@ -1933,6 +1940,14 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) spin_unlock_bh(&ifp->lock); } ipv6_del_addr(ifp); + } else if (ifp->flags&IFA_F_PERMANENT || !dad_failed) { + spin_lock_bh(&ifp->lock); + addrconf_del_dad_work(ifp); + ifp->flags |= IFA_F_TENTATIVE; + spin_unlock_bh(&ifp->lock); + if (dad_failed) + ipv6_ifa_notify(0, ifp); + in6_ifa_put(ifp); } else { ipv6_del_addr(ifp); } @@ -2280,7 +2295,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, cfg.fc_flags |= RTF_NONEXTHOP; #endif - ip6_route_add(&cfg); + ip6_route_add(&cfg, NULL); } @@ -2335,7 +2350,7 @@ static void addrconf_add_mroute(struct net_device *dev) ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); - ip6_route_add(&cfg); + ip6_route_add(&cfg, NULL); } static struct inet6_dev *addrconf_add_dev(struct net_device *dev) @@ -5562,8 +5577,8 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) ip6_del_rt(rt); } if (ifp->rt) { - dst_hold(&ifp->rt->dst); - ip6_del_rt(ifp->rt); + if (dst_hold_safe(&ifp->rt->dst)) + ip6_del_rt(ifp->rt); } rt_genid_bump_ipv6(net); break; diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index bfa941fc1165..9e3488d50b15 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -88,6 +88,7 @@ int __ipv6_addr_type(const struct in6_addr *addr) EXPORT_SYMBOL(__ipv6_addr_type); static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); +static ATOMIC_NOTIFIER_HEAD(inet6addr_validator_chain); int register_inet6addr_notifier(struct notifier_block *nb) { @@ -107,6 +108,24 @@ int inet6addr_notifier_call_chain(unsigned long val, void *v) } EXPORT_SYMBOL(inet6addr_notifier_call_chain); +int register_inet6addr_validator_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&inet6addr_validator_chain, nb); +} +EXPORT_SYMBOL(register_inet6addr_validator_notifier); + +int unregister_inet6addr_validator_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&inet6addr_validator_chain, nb); +} +EXPORT_SYMBOL(unregister_inet6addr_validator_notifier); + +int inet6addr_validator_notifier_call_chain(unsigned long val, void *v) +{ + return atomic_notifier_call_chain(&inet6addr_validator_chain, val, v); +} +EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain); + static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1, struct dst_entry **u2, struct flowi6 *u3) diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 07cd7d248bb6..7a428f65c7ec 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -18,6 +18,7 @@ #include <linux/if_addrlabel.h> #include <linux/netlink.h> #include <linux/rtnetlink.h> +#include <linux/refcount.h> #if 0 #define ADDRLABEL(x...) printk(x) @@ -36,7 +37,7 @@ struct ip6addrlbl_entry { int addrtype; u32 label; struct hlist_node list; - atomic_t refcnt; + refcount_t refcnt; struct rcu_head rcu; }; @@ -137,12 +138,12 @@ static void ip6addrlbl_free_rcu(struct rcu_head *h) static bool ip6addrlbl_hold(struct ip6addrlbl_entry *p) { - return atomic_inc_not_zero(&p->refcnt); + return refcount_inc_not_zero(&p->refcnt); } static inline void ip6addrlbl_put(struct ip6addrlbl_entry *p) { - if (atomic_dec_and_test(&p->refcnt)) + if (refcount_dec_and_test(&p->refcnt)) call_rcu(&p->rcu, ip6addrlbl_free_rcu); } @@ -236,7 +237,7 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, newp->label = label; INIT_HLIST_NODE(&newp->list); write_pnet(&newp->lbl_net, net); - atomic_set(&newp->refcnt, 1); + refcount_set(&newp->refcnt, 1); return newp; } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index dda6035e3b84..7802b72196f3 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -25,6 +25,7 @@ #define pr_fmt(fmt) "IPv6: " fmt +#include <crypto/algapi.h> #include <crypto/hash.h> #include <linux/module.h> #include <linux/slab.h> @@ -423,7 +424,9 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); sg_init_table(sg, nfrags + sglists); - skb_to_sgvec_nomark(skb, sg, 0, skb->len); + err = skb_to_sgvec_nomark(skb, sg, 0, skb->len); + if (unlikely(err < 0)) + goto out_free; if (x->props.flags & XFRM_STATE_ESN) { /* Attach seqhi sg right after packet payload */ @@ -481,7 +484,7 @@ static void ah6_input_done(struct crypto_async_request *base, int err) auth_data = ah_tmp_auth(work_iph, hdr_len); icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len); - err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0; + err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0; if (err) goto out; @@ -606,7 +609,9 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) ip6h->hop_limit = 0; sg_init_table(sg, nfrags + sglists); - skb_to_sgvec_nomark(skb, sg, 0, skb->len); + err = skb_to_sgvec_nomark(skb, sg, 0, skb->len); + if (unlikely(err < 0)) + goto out_free; if (x->props.flags & XFRM_STATE_ESN) { /* Attach seqhi sg right after packet payload */ @@ -627,7 +632,7 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) goto out_free; } - err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0; + err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0; if (err) goto out_free; diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 514ac259f543..0bbab8a4b5d8 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -203,12 +203,12 @@ void ipv6_sock_ac_close(struct sock *sk) static void aca_get(struct ifacaddr6 *aca) { - atomic_inc(&aca->aca_refcnt); + refcount_inc(&aca->aca_refcnt); } static void aca_put(struct ifacaddr6 *ac) { - if (atomic_dec_and_test(&ac->aca_refcnt)) { + if (refcount_dec_and_test(&ac->aca_refcnt)) { in6_dev_put(ac->aca_idev); dst_release(&ac->aca_rt->dst); kfree(ac); @@ -232,7 +232,7 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt, aca->aca_users = 1; /* aca_tstamp should be updated upon changes */ aca->aca_cstamp = aca->aca_tstamp = jiffies; - atomic_set(&aca->aca_refcnt, 1); + refcount_set(&aca->aca_refcnt, 1); return aca; } diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 8d772fea1dde..1323b9679cf7 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -227,7 +227,7 @@ static int calipso_cache_check(const unsigned char *key, entry->key_len == key_len && memcmp(entry->key, key, key_len) == 0) { entry->activity += 1; - atomic_inc(&entry->lsm_data->refcount); + refcount_inc(&entry->lsm_data->refcount); secattr->cache = entry->lsm_data; secattr->flags |= NETLBL_SECATTR_CACHE; secattr->type = NETLBL_NLTYPE_CALIPSO; @@ -296,7 +296,7 @@ static int calipso_cache_add(const unsigned char *calipso_ptr, } entry->key_len = calipso_ptr_len; entry->hash = calipso_map_cache_hash(calipso_ptr, calipso_ptr_len); - atomic_inc(&secattr->cache->refcount); + refcount_inc(&secattr->cache->refcount); entry->lsm_data = secattr->cache; bkt = entry->hash & (CALIPSO_CACHE_BUCKETS - 1); @@ -338,7 +338,7 @@ static struct calipso_doi *calipso_doi_search(u32 doi) struct calipso_doi *iter; list_for_each_entry_rcu(iter, &calipso_doi_list, list) - if (iter->doi == doi && atomic_read(&iter->refcount)) + if (iter->doi == doi && refcount_read(&iter->refcount)) return iter; return NULL; } @@ -370,7 +370,7 @@ static int calipso_doi_add(struct calipso_doi *doi_def, if (doi_def->doi == CALIPSO_DOI_UNKNOWN) goto doi_add_return; - atomic_set(&doi_def->refcount, 1); + refcount_set(&doi_def->refcount, 1); spin_lock(&calipso_doi_list_lock); if (calipso_doi_search(doi_def->doi)) { @@ -458,7 +458,7 @@ static int calipso_doi_remove(u32 doi, struct netlbl_audit *audit_info) ret_val = -ENOENT; goto doi_remove_return; } - if (!atomic_dec_and_test(&doi_def->refcount)) { + if (!refcount_dec_and_test(&doi_def->refcount)) { spin_unlock(&calipso_doi_list_lock); ret_val = -EBUSY; goto doi_remove_return; @@ -499,7 +499,7 @@ static struct calipso_doi *calipso_doi_getdef(u32 doi) doi_def = calipso_doi_search(doi); if (!doi_def) goto doi_getdef_return; - if (!atomic_inc_not_zero(&doi_def->refcount)) + if (!refcount_inc_not_zero(&doi_def->refcount)) doi_def = NULL; doi_getdef_return: @@ -520,7 +520,7 @@ static void calipso_doi_putdef(struct calipso_doi *doi_def) if (!doi_def) return; - if (!atomic_dec_and_test(&doi_def->refcount)) + if (!refcount_dec_and_test(&doi_def->refcount)) return; spin_lock(&calipso_doi_list_lock); list_del_rcu(&doi_def->list); @@ -553,7 +553,7 @@ static int calipso_doi_walk(u32 *skip_cnt, rcu_read_lock(); list_for_each_entry_rcu(iter_doi, &calipso_doi_list, list) - if (atomic_read(&iter_doi->refcount) > 0) { + if (refcount_read(&iter_doi->refcount) > 0) { if (doi_cnt++ < *skip_cnt) continue; ret_val = callback(iter_doi, cb_arg); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 5c786f5ab961..a1f918713006 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -1041,6 +1041,6 @@ void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, + refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 1fe99ba8066c..9ed35473dcb5 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -118,7 +118,6 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, static void esp_ssg_unref(struct xfrm_state *x, void *tmp) { - __be32 *seqhi; struct crypto_aead *aead = x->data; int seqhilen = 0; u8 *iv; @@ -128,7 +127,6 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) if (x->props.flags & XFRM_STATE_ESN) seqhilen += sizeof(__be32); - seqhi = esp_tmp_seqhi(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); req = esp_tmp_req(aead, iv); @@ -224,12 +222,9 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info u8 *vaddr; int nfrags; struct page *page; - struct ip_esp_hdr *esph; struct sk_buff *trailer; int tailen = esp->tailen; - esph = ip_esp_hdr(skb); - if (!skb_cloned(skb)) { if (tailen <= skb_availroom(skb)) { nfrags = 1; @@ -280,7 +275,7 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info skb->data_len += tailen; skb->truesize += tailen; if (sk) - atomic_add(tailen, &sk->sk_wmem_alloc); + refcount_add(tailen, &sk->sk_wmem_alloc); goto out; } @@ -346,9 +341,11 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info esph = esp_output_set_esn(skb, x, ip_esp_hdr(skb), seqhi); sg_init_table(sg, esp->nfrags); - skb_to_sgvec(skb, sg, - (unsigned char *)esph - skb->data, - assoclen + ivlen + esp->clen + alen); + err = skb_to_sgvec(skb, sg, + (unsigned char *)esph - skb->data, + assoclen + ivlen + esp->clen + alen); + if (unlikely(err < 0)) + goto error; if (!esp->inplace) { int allocsize; @@ -372,9 +369,11 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info spin_unlock_bh(&x->lock); sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1); - skb_to_sgvec(skb, dsg, - (unsigned char *)esph - skb->data, - assoclen + ivlen + esp->clen + alen); + err = skb_to_sgvec(skb, dsg, + (unsigned char *)esph - skb->data, + assoclen + ivlen + esp->clen + alen); + if (unlikely(err < 0)) + goto error; } if ((x->props.flags & XFRM_STATE_ESN)) @@ -534,7 +533,7 @@ static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi) * decryption. */ if ((x->props.flags & XFRM_STATE_ESN)) { - esph = (void *)skb_push(skb, 4); + esph = skb_push(skb, 4); *seqhi = esph->spi; esph->spi = esph->seq_no; esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; @@ -618,7 +617,9 @@ skip_cow: esp_input_set_header(skb, seqhi); sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + ret = skb_to_sgvec(skb, sg, 0, skb->len); + if (unlikely(ret < 0)) + goto out; skb->ip_summed = CHECKSUM_NONE; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index b636f1da9aec..4996d734f1d2 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -847,7 +847,7 @@ static void ipv6_push_rthdr0(struct sk_buff *skb, u8 *proto, ihdr = (struct rt0_hdr *) opt; - phdr = (struct rt0_hdr *) skb_push(skb, (ihdr->rt_hdr.hdrlen + 1) << 3); + phdr = skb_push(skb, (ihdr->rt_hdr.hdrlen + 1) << 3); memcpy(phdr, ihdr, sizeof(struct rt0_hdr)); hops = ihdr->rt_hdr.hdrlen >> 1; @@ -873,7 +873,7 @@ static void ipv6_push_rthdr4(struct sk_buff *skb, u8 *proto, sr_ihdr = (struct ipv6_sr_hdr *)opt; plen = (sr_ihdr->hdrlen + 1) << 3; - sr_phdr = (struct ipv6_sr_hdr *)skb_push(skb, plen); + sr_phdr = skb_push(skb, plen); memcpy(sr_phdr, sr_ihdr, sizeof(struct ipv6_sr_hdr)); hops = sr_ihdr->first_segment + 1; @@ -923,7 +923,7 @@ static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto, static void ipv6_push_exthdr(struct sk_buff *skb, u8 *proto, u8 type, struct ipv6_opt_hdr *opt) { - struct ipv6_opt_hdr *h = (struct ipv6_opt_hdr *)skb_push(skb, ipv6_optlen(opt)); + struct ipv6_opt_hdr *h = skb_push(skb, ipv6_optlen(opt)); memcpy(h, opt, ipv6_optlen(opt)); h->nexthdr = *proto; @@ -971,7 +971,7 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) *((char **)&opt2->dst1opt) += dif; if (opt2->srcrt) *((char **)&opt2->srcrt) += dif; - atomic_set(&opt2->refcnt, 1); + refcount_set(&opt2->refcnt, 1); } return opt2; } @@ -1056,7 +1056,7 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, return ERR_PTR(-ENOBUFS); memset(opt2, 0, tot_len); - atomic_set(&opt2->refcnt, 1); + refcount_set(&opt2->refcnt, 1); opt2->tot_len = tot_len; p = (char *)(opt2 + 1); diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c index 9ea249b9451e..6de3c04b0f30 100644 --- a/net/ipv6/fou6.c +++ b/net/ipv6/fou6.c @@ -14,6 +14,8 @@ #include <net/udp.h> #include <net/udp_tunnel.h> +#if IS_ENABLED(CONFIG_IPV6_FOU_TUNNEL) + static void fou6_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e, struct flowi6 *fl6, u8 *protocol, __be16 sport) { @@ -33,8 +35,8 @@ static void fou6_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e, *protocol = IPPROTO_UDP; } -int fou6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, - u8 *protocol, struct flowi6 *fl6) +static int fou6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, + u8 *protocol, struct flowi6 *fl6) { __be16 sport; int err; @@ -49,10 +51,9 @@ int fou6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, return 0; } -EXPORT_SYMBOL(fou6_build_header); -int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, - u8 *protocol, struct flowi6 *fl6) +static int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, + u8 *protocol, struct flowi6 *fl6) { __be16 sport; int err; @@ -67,9 +68,6 @@ int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, return 0; } -EXPORT_SYMBOL(gue6_build_header); - -#if IS_ENABLED(CONFIG_IPV6_FOU_TUNNEL) static const struct ip6_tnl_encap_ops fou_ip6tun_ops = { .encap_hlen = fou_encap_hlen, diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index b3df03e3faa0..0c02a09bc351 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -91,7 +91,7 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) drop: kfree_skb(skb); - return -EINVAL; + return err; } static int ila_input(struct sk_buff *skb) @@ -117,7 +117,8 @@ static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { static int ila_build_state(struct nlattr *nla, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct ila_lwt *ilwt; struct ila_params *p; @@ -146,7 +147,7 @@ static int ila_build_state(struct nlattr *nla, return -EINVAL; } - ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, NULL); + ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, extack); if (ret < 0) return ret; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index d0900918a19e..b13b8f93079d 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -75,7 +75,7 @@ begin: continue; if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif)) continue; - if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif))) { @@ -172,7 +172,7 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, ntohs(dport), dif, &refcounted); - if (sk && !refcounted && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index e6b78ba0e636..ebb299cf72b7 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -153,11 +153,6 @@ static void node_free(struct fib6_node *fn) kmem_cache_free(fib6_node_kmem, fn); } -static void rt6_rcu_free(struct rt6_info *rt) -{ - call_rcu(&rt->dst.rcu_head, dst_rcu_free); -} - static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) { int cpu; @@ -172,7 +167,8 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu); pcpu_rt = *ppcpu_rt; if (pcpu_rt) { - rt6_rcu_free(pcpu_rt); + dst_dev_put(&pcpu_rt->dst); + dst_release(&pcpu_rt->dst); *ppcpu_rt = NULL; } } @@ -185,7 +181,8 @@ static void rt6_release(struct rt6_info *rt) { if (atomic_dec_and_test(&rt->rt6i_ref)) { rt6_free_pcpu(rt); - rt6_rcu_free(rt); + dst_dev_put(&rt->dst); + dst_release(&rt->dst); } } @@ -472,7 +469,8 @@ out: static struct fib6_node *fib6_add_1(struct fib6_node *root, struct in6_addr *addr, int plen, int offset, int allow_create, - int replace_required, int sernum) + int replace_required, int sernum, + struct netlink_ext_ack *extack) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; @@ -496,6 +494,8 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) { if (!allow_create) { if (replace_required) { + NL_SET_ERR_MSG(extack, + "Can not replace route - no match found"); pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } @@ -542,6 +542,8 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, * That would keep IPv6 consistent with IPv4 */ if (replace_required) { + NL_SET_ERR_MSG(extack, + "Can not replace route - no match found"); pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } @@ -784,10 +786,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, goto next_iter; } - if (iter->dst.dev == rt->dst.dev && - iter->rt6i_idev == rt->rt6i_idev && - ipv6_addr_equal(&iter->rt6i_gateway, - &rt->rt6i_gateway)) { + if (rt6_duplicate_nexthop(iter, rt)) { if (rt->rt6i_nsiblings) rt->rt6i_nsiblings = 0; if (!(iter->rt6i_flags & RTF_EXPIRES)) @@ -963,7 +962,8 @@ void fib6_force_start_gc(struct net *net) */ int fib6_add(struct fib6_node *root, struct rt6_info *rt, - struct nl_info *info, struct mx6_config *mxc) + struct nl_info *info, struct mx6_config *mxc, + struct netlink_ext_ack *extack) { struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; @@ -971,8 +971,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, int replace_required = 0; int sernum = fib6_new_sernum(info->nl_net); - if (WARN_ON_ONCE((rt->dst.flags & DST_NOCACHE) && - !atomic_read(&rt->dst.__refcnt))) + if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt))) return -EINVAL; if (info->nlh) { @@ -986,7 +985,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), allow_create, - replace_required, sernum); + replace_required, sernum, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); fn = NULL; @@ -1027,7 +1026,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, sn = fib6_add_1(sfn, &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum); + allow_create, replace_required, sernum, + extack); if (IS_ERR(sn)) { /* If it is failed, discard just allocated @@ -1046,7 +1046,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum); + allow_create, replace_required, sernum, + extack); if (IS_ERR(sn)) { err = PTR_ERR(sn); @@ -1067,7 +1068,6 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, fib6_start_gc(info->nl_net, rt); if (!(rt->rt6i_flags & RTF_CACHE)) fib6_prune_clones(info->nl_net, pn); - rt->dst.flags &= ~DST_NOCACHE; } out: @@ -1092,8 +1092,10 @@ out: atomic_inc(&pn->leaf->rt6i_ref); } #endif - if (!(rt->dst.flags & DST_NOCACHE)) - dst_free(&rt->dst); + /* Always release dst as dst->__refcnt is guaranteed + * to be taken before entering this function + */ + dst_release_immediate(&rt->dst); } return err; @@ -1104,8 +1106,10 @@ out: st_failure: if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT))) fib6_repair_tree(info->nl_net, fn); - if (!(rt->dst.flags & DST_NOCACHE)) - dst_free(&rt->dst); + /* Always release dst as dst->__refcnt is guaranteed + * to be taken before entering this function + */ + dst_release_immediate(&rt->dst); return err; #endif } @@ -1774,7 +1778,7 @@ static int fib6_age(struct rt6_info *rt, void *arg) } gc_args->more++; } else if (rt->rt6i_flags & RTF_CACHE) { - if (atomic_read(&rt->dst.__refcnt) == 0 && + if (atomic_read(&rt->dst.__refcnt) == 1 && time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { RT6_TRACE("aging clone %p\n", rt); return -1; @@ -1812,8 +1816,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force) } gc_args.timeout = expires ? (int)expires : net->ipv6.sysctl.ip6_rt_gc_interval; - - gc_args.more = icmp6_dst_gc(); + gc_args.more = 0; fib6_clean_all(net, fib6_age, &gc_args); now = jiffies; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 64eea3962733..67ff2aaf5dcb 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -942,7 +942,7 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, const void *daddr, const void *saddr, unsigned int len) { struct ip6_tnl *t = netdev_priv(dev); - struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb_push(skb, t->hlen); + struct ipv6hdr *ipv6h = skb_push(skb, t->hlen); __be16 *p = (__be16 *)(ipv6h+1); ip6_flow_hdr(ipv6h, 0, @@ -1170,7 +1170,8 @@ static struct pernet_operations ip6gre_net_ops = { .size = sizeof(struct ip6gre_net), }; -static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { __be16 flags; @@ -1188,7 +1189,8 @@ static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } -static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct in6_addr daddr; @@ -1209,7 +1211,7 @@ static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) } out: - return ip6gre_tunnel_validate(tb, data); + return ip6gre_tunnel_validate(tb, data, extack); } @@ -1342,7 +1344,8 @@ static bool ip6gre_netlink_encap_parms(struct nlattr *data[], } static int ip6gre_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip6_tnl *nt; struct net *net = dev_net(dev); @@ -1403,7 +1406,8 @@ out: } static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip6_tnl *t, *nt = netdev_priv(dev); struct net *net = nt->net; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 1699acb2fa2c..1422d6c08377 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -67,9 +67,6 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * struct in6_addr *nexthop; int ret; - skb->protocol = htons(ETH_P_IPV6); - skb->dev = dev; - if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); @@ -154,6 +151,9 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) struct net_device *dev = skb_dst(skb)->dev; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); + skb->protocol = htons(ETH_P_IPV6); + skb->dev = dev; + if (unlikely(idev->cnf.disable_ipv6)) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); @@ -682,7 +682,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, skb_frag_list_init(skb); __skb_pull(skb, hlen); - fh = (struct frag_hdr *)__skb_push(skb, sizeof(struct frag_hdr)); + fh = __skb_push(skb, sizeof(struct frag_hdr)); __skb_push(skb, hlen); skb_reset_network_header(skb); memcpy(skb_network_header(skb), tmp_hdr, hlen); @@ -698,15 +698,13 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); - dst_hold(&rt->dst); - for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (frag) { frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); - fh = (struct frag_hdr *)__skb_push(frag, sizeof(struct frag_hdr)); + fh = __skb_push(frag, sizeof(struct frag_hdr)); __skb_push(frag, hlen); skb_reset_network_header(frag); memcpy(skb_network_header(frag), tmp_hdr, @@ -742,7 +740,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); - ip6_rt_put(rt); return 0; } @@ -750,7 +747,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); - ip6_rt_put(rt); return err; slow_path_clean: @@ -869,7 +865,6 @@ fail_toobig: if (skb->sk && dst_allfrag(skb_dst(skb))) sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK); - skb->dev = skb_dst(skb)->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); err = -EMSGSIZE; @@ -1477,7 +1472,7 @@ alloc_new_skb: (flags & MSG_DONTWAIT), &err); } else { skb = NULL; - if (atomic_read(&sk->sk_wmem_alloc) <= + if (refcount_read(&sk->sk_wmem_alloc) <= 2 * sk->sk_sndbuf) skb = sock_wmalloc(sk, alloclen + hh_len, 1, @@ -1586,7 +1581,7 @@ alloc_new_skb: skb->len += copy; skb->data_len += copy; skb->truesize += copy; - atomic_add(copy, &sk->sk_wmem_alloc); + refcount_add(copy, &sk->sk_wmem_alloc); } offset += copy; length -= copy; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 8c6c3c8e7eef..3a0ba2ae4b0f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1885,7 +1885,8 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) return 0; } -static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { u8 proto; @@ -1974,7 +1975,8 @@ static bool ip6_tnl_netlink_encap_parms(struct nlattr *data[], } static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); @@ -2005,7 +2007,8 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, } static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm p; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 837ea1eefe7f..486c2305f53c 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -907,7 +907,8 @@ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev) return 0; } -static int vti6_validate(struct nlattr *tb[], struct nlattr *data[]) +static int vti6_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { return 0; } @@ -940,7 +941,8 @@ static void vti6_netlink_parms(struct nlattr *data[], } static int vti6_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip6_tnl *nt; @@ -966,7 +968,8 @@ static void vti6_dellink(struct net_device *dev, struct list_head *head) } static int vti6_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip6_tnl *t; struct __ip6_tnl_parm p; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 2ecb39b943b5..7454850f2098 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -116,6 +116,7 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm); static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, int cmd); +static void mrt6msg_netlink_event(struct mr6_table *mrt, struct sk_buff *pkt); static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb); static void mroute_clean_tables(struct mr6_table *mrt, bool all); @@ -846,7 +847,8 @@ static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c) while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) { if (ipv6_hdr(skb)->version == 0) { - struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr)); + struct nlmsghdr *nlh = skb_pull(skb, + sizeof(struct ipv6hdr)); nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); @@ -1106,7 +1108,8 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) { if (ipv6_hdr(skb)->version == 0) { - struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr)); + struct nlmsghdr *nlh = skb_pull(skb, + sizeof(struct ipv6hdr)); if (__ip6mr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; @@ -1123,8 +1126,7 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, } /* - * Bounce a cache query up to pim6sd. We could use netlink for this but pim6sd - * expects the following bizarre scheme. + * Bounce a cache query up to pim6sd and netlink. * * Called under mrt_lock. */ @@ -1206,6 +1208,8 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, return -EINVAL; } + mrt6msg_netlink_event(mrt, skb); + /* * Deliver to user space multicast routing algorithms */ @@ -2455,6 +2459,71 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err); } +static size_t mrt6msg_netlink_msgsize(size_t payloadlen) +{ + size_t len = + NLMSG_ALIGN(sizeof(struct rtgenmsg)) + + nla_total_size(1) /* IP6MRA_CREPORT_MSGTYPE */ + + nla_total_size(4) /* IP6MRA_CREPORT_MIF_ID */ + /* IP6MRA_CREPORT_SRC_ADDR */ + + nla_total_size(sizeof(struct in6_addr)) + /* IP6MRA_CREPORT_DST_ADDR */ + + nla_total_size(sizeof(struct in6_addr)) + /* IP6MRA_CREPORT_PKT */ + + nla_total_size(payloadlen) + ; + + return len; +} + +static void mrt6msg_netlink_event(struct mr6_table *mrt, struct sk_buff *pkt) +{ + struct net *net = read_pnet(&mrt->net); + struct nlmsghdr *nlh; + struct rtgenmsg *rtgenm; + struct mrt6msg *msg; + struct sk_buff *skb; + struct nlattr *nla; + int payloadlen; + + payloadlen = pkt->len - sizeof(struct mrt6msg); + msg = (struct mrt6msg *)skb_transport_header(pkt); + + skb = nlmsg_new(mrt6msg_netlink_msgsize(payloadlen), GFP_ATOMIC); + if (!skb) + goto errout; + + nlh = nlmsg_put(skb, 0, 0, RTM_NEWCACHEREPORT, + sizeof(struct rtgenmsg), 0); + if (!nlh) + goto errout; + rtgenm = nlmsg_data(nlh); + rtgenm->rtgen_family = RTNL_FAMILY_IP6MR; + if (nla_put_u8(skb, IP6MRA_CREPORT_MSGTYPE, msg->im6_msgtype) || + nla_put_u32(skb, IP6MRA_CREPORT_MIF_ID, msg->im6_mif) || + nla_put_in6_addr(skb, IP6MRA_CREPORT_SRC_ADDR, + &msg->im6_src) || + nla_put_in6_addr(skb, IP6MRA_CREPORT_DST_ADDR, + &msg->im6_dst)) + goto nla_put_failure; + + nla = nla_reserve(skb, IP6MRA_CREPORT_PKT, payloadlen); + if (!nla || skb_copy_bits(pkt, sizeof(struct mrt6msg), + nla_data(nla), payloadlen)) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MROUTE_R, NULL, GFP_ATOMIC); + return; + +nla_put_failure: + nlmsg_cancel(skb, nlh); +errout: + kfree_skb(skb); + rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE_R, -ENOBUFS); +} + static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a531ba032b85..02d795fe3d7f 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -505,7 +505,7 @@ sticky_done: break; memset(opt, 0, sizeof(*opt)); - atomic_set(&opt->refcnt, 1); + refcount_set(&opt->refcnt, 1); opt->tot_len = sizeof(*opt) + optlen; retv = -EFAULT; if (copy_from_user(opt+1, optval, optlen)) @@ -735,14 +735,9 @@ done: retv = -ENOBUFS; break; } - gsf = kmalloc(optlen, GFP_KERNEL); - if (!gsf) { - retv = -ENOBUFS; - break; - } - retv = -EFAULT; - if (copy_from_user(gsf, optval, optlen)) { - kfree(gsf); + gsf = memdup_user(optval, optlen); + if (IS_ERR(gsf)) { + retv = PTR_ERR(gsf); break; } /* numsrc >= (4G-140)/128 overflow in 32 bits */ diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 07403fa164e1..12b7c27ce5ce 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -701,7 +701,7 @@ static void igmp6_group_dropped(struct ifmcaddr6 *mc) spin_lock_bh(&mc->mca_lock); if (del_timer(&mc->mca_timer)) - atomic_dec(&mc->mca_refcnt); + refcount_dec(&mc->mca_refcnt); spin_unlock_bh(&mc->mca_lock); } @@ -819,12 +819,12 @@ static void mld_clear_delrec(struct inet6_dev *idev) static void mca_get(struct ifmcaddr6 *mc) { - atomic_inc(&mc->mca_refcnt); + refcount_inc(&mc->mca_refcnt); } static void ma_put(struct ifmcaddr6 *mc) { - if (atomic_dec_and_test(&mc->mca_refcnt)) { + if (refcount_dec_and_test(&mc->mca_refcnt)) { in6_dev_put(mc->idev); kfree(mc); } @@ -846,7 +846,7 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, mc->mca_users = 1; /* mca_stamp should be updated upon changes */ mc->mca_cstamp = mc->mca_tstamp = jiffies; - atomic_set(&mc->mca_refcnt, 1); + refcount_set(&mc->mca_refcnt, 1); spin_lock_init(&mc->mca_lock); /* initial mode is (EX, empty) */ @@ -1065,7 +1065,7 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) return; if (del_timer(&ma->mca_timer)) { - atomic_dec(&ma->mca_refcnt); + refcount_dec(&ma->mca_refcnt); delay = ma->mca_timer.expires - jiffies; } @@ -1074,7 +1074,7 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) ma->mca_timer.expires = jiffies + delay; if (!mod_timer(&ma->mca_timer, jiffies + delay)) - atomic_inc(&ma->mca_refcnt); + refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING; } @@ -1469,7 +1469,7 @@ int igmp6_event_report(struct sk_buff *skb) if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) { spin_lock(&ma->mca_lock); if (del_timer(&ma->mca_timer)) - atomic_dec(&ma->mca_refcnt); + refcount_dec(&ma->mca_refcnt); ma->mca_flags &= ~(MAF_LAST_REPORTER|MAF_TIMER_RUNNING); spin_unlock(&ma->mca_lock); break; @@ -1602,7 +1602,7 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) ip6_mc_hdr(sk, skb, dev, saddr, &mld2_all_mcr, NEXTHDR_HOP, 0); - memcpy(skb_put(skb, sizeof(ra)), ra, sizeof(ra)); + skb_put_data(skb, ra, sizeof(ra)); skb_set_transport_header(skb, skb_tail_pointer(skb) - skb->data); skb_put(skb, sizeof(*pmr)); @@ -1692,7 +1692,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, skb = mld_newpack(pmc->idev, dev->mtu); if (!skb) return NULL; - pgr = (struct mld2_grec *)skb_put(skb, sizeof(struct mld2_grec)); + pgr = skb_put(skb, sizeof(struct mld2_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; @@ -1784,7 +1784,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, } if (!skb) return NULL; - psrc = (struct in6_addr *)skb_put(skb, sizeof(*psrc)); + psrc = skb_put(skb, sizeof(*psrc)); *psrc = psf->sf_addr; scount++; stotal++; if ((type == MLD2_ALLOW_NEW_SOURCES || @@ -2006,10 +2006,9 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) ip6_mc_hdr(sk, skb, dev, saddr, snd_addr, NEXTHDR_HOP, payload_len); - memcpy(skb_put(skb, sizeof(ra)), ra, sizeof(ra)); + skb_put_data(skb, ra, sizeof(ra)); - hdr = (struct mld_msg *) skb_put(skb, sizeof(struct mld_msg)); - memset(hdr, 0, sizeof(struct mld_msg)); + hdr = skb_put_zero(skb, sizeof(struct mld_msg)); hdr->mld_type = type; hdr->mld_mca = *addr; @@ -2392,12 +2391,12 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) spin_lock_bh(&ma->mca_lock); if (del_timer(&ma->mca_timer)) { - atomic_dec(&ma->mca_refcnt); + refcount_dec(&ma->mca_refcnt); delay = ma->mca_timer.expires - jiffies; } if (!mod_timer(&ma->mca_timer, jiffies + delay)) - atomic_inc(&ma->mca_refcnt); + refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING | MAF_LAST_REPORTER; spin_unlock_bh(&ma->mca_lock); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index d310dc41209a..0327c1f2e6fc 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -528,7 +528,7 @@ void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, if (!skb) return; - msg = (struct nd_msg *)skb_put(skb, sizeof(*msg)); + msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, @@ -597,7 +597,7 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, if (!skb) return; - msg = (struct nd_msg *)skb_put(skb, sizeof(*msg)); + msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_SOLICITATION, @@ -657,7 +657,7 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, if (!skb) return; - msg = (struct rs_msg *)skb_put(skb, sizeof(*msg)); + msg = skb_put(skb, sizeof(*msg)); *msg = (struct rs_msg) { .icmph = { .icmp6_type = NDISC_ROUTER_SOLICITATION, @@ -1633,7 +1633,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) if (!buff) goto release; - msg = (struct rd_msg *)skb_put(buff, sizeof(*msg)); + msg = skb_put(buff, sizeof(*msg)); *msg = (struct rd_msg) { .icmph = { .icmp6_type = NDISC_REDIRECT, diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index d3c4daa708b9..ce203dd729e0 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -27,7 +27,7 @@ synproxy_build_ip(struct net *net, struct sk_buff *skb, struct ipv6hdr *iph; skb_reset_network_header(skb); - iph = (struct ipv6hdr *)skb_put(skb, sizeof(*iph)); + iph = skb_put(skb, sizeof(*iph)); ip6_flow_hdr(iph, 0, 0); iph->hop_limit = net->ipv6.devconf_all->hop_limit; iph->nexthdr = IPPROTO_TCP; @@ -105,7 +105,7 @@ synproxy_send_client_synack(struct net *net, niph = synproxy_build_ip(net, nskb, &iph->daddr, &iph->saddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->dest; nth->dest = th->source; nth->seq = htonl(__cookie_v6_init_sequence(iph, th, &mss)); @@ -147,7 +147,7 @@ synproxy_send_server_syn(struct net *net, niph = synproxy_build_ip(net, nskb, &iph->saddr, &iph->daddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->source; nth->dest = th->dest; nth->seq = htonl(recv_seq - 1); @@ -192,7 +192,7 @@ synproxy_send_server_ack(struct net *net, niph = synproxy_build_ip(net, nskb, &iph->daddr, &iph->saddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->dest; nth->dest = th->source; nth->seq = htonl(ntohl(th->ack_seq)); @@ -230,7 +230,7 @@ synproxy_send_client_ack(struct net *net, niph = synproxy_build_ip(net, nskb, &iph->saddr, &iph->daddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->source; nth->dest = th->dest; nth->seq = htonl(ntohl(th->seq) + 1); diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 2297c9f073ba..d7b679037bae 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -75,8 +75,8 @@ static int masq_device_event(struct notifier_block *this, struct net *net = dev_net(dev); if (event == NETDEV_DOWN) - nf_ct_iterate_cleanup(net, device_cmp, - (void *)(long)dev->ifindex, 0, 0); + nf_ct_iterate_cleanup_net(net, device_cmp, + (void *)(long)dev->ifindex, 0, 0); return NOTIFY_DONE; } @@ -99,7 +99,7 @@ static void iterate_cleanup_work(struct work_struct *work) w = container_of(work, struct masq_dev_work, work); index = w->ifindex; - nf_ct_iterate_cleanup(w->net, device_cmp, (void *)index, 0, 0); + nf_ct_iterate_cleanup_net(w->net, device_cmp, (void *)index, 0, 0); put_net(w->net); kfree(w); @@ -110,12 +110,12 @@ static void iterate_cleanup_work(struct work_struct *work) /* ipv6 inet notifier is an atomic notifier, i.e. we cannot * schedule. * - * Unfortunately, nf_ct_iterate_cleanup can run for a long + * Unfortunately, nf_ct_iterate_cleanup_net can run for a long * time if there are lots of conntracks and the system * handles high softirq load, so it frequently calls cond_resched * while iterating the conntrack table. * - * So we defer nf_ct_iterate_cleanup walk to the system workqueue. + * So we defer nf_ct_iterate_cleanup_net walk to the system workqueue. * * As we can have 'a lot' of inet_events (depending on amount * of ipv6 addresses being deleted), we also need to add an upper diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index eedee5d108d9..24858402e374 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -95,7 +95,7 @@ void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb, int needs_ack; skb_reset_transport_header(nskb); - tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); + tcph = skb_put(nskb, sizeof(struct tcphdr)); /* Truncate to length (no data) */ tcph->doff = sizeof(struct tcphdr)/4; tcph->source = oth->dest; @@ -220,9 +220,6 @@ static bool reject6_csum_ok(struct sk_buff *skb, int hook) __be16 fo; u8 proto; - if (skb->csum_bad) - return false; - if (skb_csum_unnecessary(skb)) return true; diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index e9065b8d3af8..abb2c307fbe8 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -78,7 +78,7 @@ EXPORT_SYMBOL(ipv6_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { - u16 offset = sizeof(struct ipv6hdr); + unsigned int offset = sizeof(struct ipv6hdr); unsigned int packet_len = skb_tail_pointer(skb) - skb_network_header(skb); int found_rhdr = 0; @@ -86,6 +86,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) while (offset <= packet_len) { struct ipv6_opt_hdr *exthdr; + unsigned int len; switch (**nexthdr) { @@ -111,7 +112,10 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + offset); - offset += ipv6_optlen(exthdr); + len = ipv6_optlen(exthdr); + if (len + offset >= IPV6_MAXPLEN) + return -EINVAL; + offset += len; *nexthdr = &exthdr->nexthdr; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 322bd62e688b..4d30c96a819d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -128,7 +128,6 @@ static void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); - rt->dst.flags |= DST_NOCACHE; rt->rt6i_uncached_list = ul; spin_lock_bh(&ul->lock); @@ -354,7 +353,7 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net, int flags) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, - 0, DST_OBSOLETE_FORCE_CHK, flags); + 1, DST_OBSOLETE_FORCE_CHK, flags); if (rt) rt6_info_init(rt); @@ -381,7 +380,7 @@ struct rt6_info *ip6_dst_alloc(struct net *net, *p = NULL; } } else { - dst_destroy((struct dst_entry *)rt); + dst_release_immediate(&rt->dst); return NULL; } } @@ -932,20 +931,21 @@ struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, EXPORT_SYMBOL(rt6_lookup); /* ip6_ins_rt is called with FREE table->tb6_lock. - It takes new route entry, the addition fails by any reason the - route is freed. In any case, if caller does not hold it, it may - be destroyed. + * It takes new route entry, the addition fails by any reason the + * route is released. + * Caller must hold dst before calling it. */ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, - struct mx6_config *mxc) + struct mx6_config *mxc, + struct netlink_ext_ack *extack) { int err; struct fib6_table *table; table = rt->rt6i_table; write_lock_bh(&table->tb6_lock); - err = fib6_add(&table->tb6_root, rt, info, mxc); + err = fib6_add(&table->tb6_root, rt, info, mxc, extack); write_unlock_bh(&table->tb6_lock); return err; @@ -956,7 +956,9 @@ int ip6_ins_rt(struct rt6_info *rt) struct nl_info info = { .nl_net = dev_net(rt->dst.dev), }; struct mx6_config mxc = { .mx = NULL, }; - return __ip6_ins_rt(rt, &info, &mxc); + /* Hold dst to account for the reference from the fib6 tree */ + dst_hold(&rt->dst); + return __ip6_ins_rt(rt, &info, &mxc, NULL); } static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort, @@ -1048,7 +1050,7 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) prev = cmpxchg(p, NULL, pcpu_rt); if (prev) { /* If someone did it before us, return prev instead */ - dst_destroy(&pcpu_rt->dst); + dst_release_immediate(&pcpu_rt->dst); pcpu_rt = prev; } } else { @@ -1058,7 +1060,7 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) * since rt is going away anyway. The next * dst_check() will trigger a re-lookup. */ - dst_destroy(&pcpu_rt->dst); + dst_release_immediate(&pcpu_rt->dst); pcpu_rt = rt; } dst_hold(&pcpu_rt->dst); @@ -1128,12 +1130,15 @@ redo_rt6_select: uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL); dst_release(&rt->dst); - if (uncached_rt) + if (uncached_rt) { + /* Uncached_rt's refcnt is taken during ip6_rt_cache_alloc() + * No need for another dst_hold() + */ rt6_uncached_list_add(uncached_rt); - else + } else { uncached_rt = net->ipv6.ip6_null_entry; - - dst_hold(&uncached_rt->dst); + dst_hold(&uncached_rt->dst); + } trace_fib6_table_lookup(net, uncached_rt, table->tb6_id, fl6); return uncached_rt; @@ -1244,9 +1249,11 @@ EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig; + struct net_device *loopback_dev = net->loopback_dev; struct dst_entry *new = NULL; - rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, DST_OBSOLETE_NONE, 0); + rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, 1, + DST_OBSOLETE_NONE, 0); if (rt) { rt6_info_init(rt); @@ -1256,10 +1263,8 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori new->output = dst_discard_out; dst_copy_metrics(new, &ort->dst); - rt->rt6i_idev = ort->rt6i_idev; - if (rt->rt6i_idev) - in6_dev_hold(rt->rt6i_idev); + rt->rt6i_idev = in6_dev_get(loopback_dev); rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU; rt->rt6i_metric = 0; @@ -1268,8 +1273,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori #ifdef CONFIG_IPV6_SUBTREES memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); #endif - - dst_free(new); } dst_release(dst_orig); @@ -1322,7 +1325,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt6_dst_from_metrics_check(rt); if (rt->rt6i_flags & RTF_PCPU || - (unlikely(dst->flags & DST_NOCACHE) && rt->dst.from)) + (unlikely(!list_empty(&rt->rt6i_uncached)) && rt->dst.from)) return rt6_dst_from_check(rt, cookie); else return rt6_check(rt, cookie); @@ -1355,8 +1358,8 @@ static void ip6_link_failure(struct sk_buff *skb) rt = (struct rt6_info *) skb_dst(skb); if (rt) { if (rt->rt6i_flags & RTF_CACHE) { - dst_hold(&rt->dst); - ip6_del_rt(rt); + if (dst_hold_safe(&rt->dst)) + ip6_del_rt(rt); } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) { rt->rt6i_node->fn_sernum = -1; } @@ -1420,6 +1423,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, * invalidate the sk->sk_dst_cache. */ ip6_ins_rt(nrt6); + /* Release the reference taken in + * ip6_rt_cache_alloc() + */ + dst_release(&nrt6->dst); } } } @@ -1648,9 +1655,6 @@ out: return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } -static struct dst_entry *icmp6_dst_gc_list; -static DEFINE_SPINLOCK(icmp6_dst_lock); - struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6) { @@ -1671,19 +1675,16 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; - atomic_set(&rt->dst.__refcnt, 1); rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 0); - spin_lock_bh(&icmp6_dst_lock); - rt->dst.next = icmp6_dst_gc_list; - icmp6_dst_gc_list = &rt->dst; - spin_unlock_bh(&icmp6_dst_lock); - - fib6_force_start_gc(net); + /* Add this dst into uncached_list so that rt6_ifdown() can + * do proper release of the net_device + */ + rt6_uncached_list_add(rt); dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0); @@ -1691,48 +1692,6 @@ out: return dst; } -int icmp6_dst_gc(void) -{ - struct dst_entry *dst, **pprev; - int more = 0; - - spin_lock_bh(&icmp6_dst_lock); - pprev = &icmp6_dst_gc_list; - - while ((dst = *pprev) != NULL) { - if (!atomic_read(&dst->__refcnt)) { - *pprev = dst->next; - dst_free(dst); - } else { - pprev = &dst->next; - ++more; - } - } - - spin_unlock_bh(&icmp6_dst_lock); - - return more; -} - -static void icmp6_clean_all(int (*func)(struct rt6_info *rt, void *arg), - void *arg) -{ - struct dst_entry *dst, **pprev; - - spin_lock_bh(&icmp6_dst_lock); - pprev = &icmp6_dst_gc_list; - while ((dst = *pprev) != NULL) { - struct rt6_info *rt = (struct rt6_info *) dst; - if (func(rt, arg)) { - *pprev = dst->next; - dst_free(dst); - } else { - pprev = &dst->next; - } - } - spin_unlock_bh(&icmp6_dst_lock); -} - static int ip6_dst_gc(struct dst_ops *ops) { struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); @@ -1844,7 +1803,8 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net, return rt; } -static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) +static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct net *net = cfg->fc_nlinfo.nl_net; struct rt6_info *rt = NULL; @@ -1855,14 +1815,25 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) int err = -EINVAL; /* RTF_PCPU is an internal flag; can not be set by userspace */ - if (cfg->fc_flags & RTF_PCPU) + if (cfg->fc_flags & RTF_PCPU) { + NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU"); goto out; + } - if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) + if (cfg->fc_dst_len > 128) { + NL_SET_ERR_MSG(extack, "Invalid prefix length"); + goto out; + } + if (cfg->fc_src_len > 128) { + NL_SET_ERR_MSG(extack, "Invalid source address length"); goto out; + } #ifndef CONFIG_IPV6_SUBTREES - if (cfg->fc_src_len) + if (cfg->fc_src_len) { + NL_SET_ERR_MSG(extack, + "Specifying source address requires IPV6_SUBTREES to be enabled"); goto out; + } #endif if (cfg->fc_ifindex) { err = -ENODEV; @@ -1926,7 +1897,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) err = lwtunnel_build_state(cfg->fc_encap_type, cfg->fc_encap, AF_INET6, cfg, - &lwtstate); + &lwtstate, extack); if (err) goto out; rt->dst.lwtstate = lwtstate_get(lwtstate); @@ -2013,9 +1984,10 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) err = -EINVAL; if (ipv6_chk_addr_and_flags(net, gw_addr, gwa_type & IPV6_ADDR_LINKLOCAL ? - dev : NULL, 0, 0)) + dev : NULL, 0, 0)) { + NL_SET_ERR_MSG(extack, "Invalid gateway address"); goto out; - + } rt->rt6i_gateway = *gw_addr; if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) { @@ -2031,8 +2003,11 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) addressing */ if (!(gwa_type & (IPV6_ADDR_UNICAST | - IPV6_ADDR_MAPPED))) + IPV6_ADDR_MAPPED))) { + NL_SET_ERR_MSG(extack, + "Invalid gateway address"); goto out; + } if (cfg->fc_table) { grt = ip6_nh_lookup_table(net, cfg, gw_addr); @@ -2072,8 +2047,14 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) goto out; } err = -EINVAL; - if (!dev || (dev->flags & IFF_LOOPBACK)) + if (!dev) { + NL_SET_ERR_MSG(extack, "Egress device not specified"); + goto out; + } else if (dev->flags & IFF_LOOPBACK) { + NL_SET_ERR_MSG(extack, + "Egress device can not be loopback device for this route"); goto out; + } } err = -ENODEV; @@ -2082,6 +2063,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) if (!ipv6_addr_any(&cfg->fc_prefsrc)) { if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) { + NL_SET_ERR_MSG(extack, "Invalid source address"); err = -EINVAL; goto out; } @@ -2106,18 +2088,19 @@ out: if (idev) in6_dev_put(idev); if (rt) - dst_free(&rt->dst); + dst_release_immediate(&rt->dst); return ERR_PTR(err); } -int ip6_route_add(struct fib6_config *cfg) +int ip6_route_add(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct mx6_config mxc = { .mx = NULL, }; struct rt6_info *rt; int err; - rt = ip6_route_info_create(cfg); + rt = ip6_route_info_create(cfg, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; @@ -2128,14 +2111,14 @@ int ip6_route_add(struct fib6_config *cfg) if (err) goto out; - err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc); + err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc, extack); kfree(mxc.mx); return err; out: if (rt) - dst_free(&rt->dst); + dst_release_immediate(&rt->dst); return err; } @@ -2146,8 +2129,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) struct fib6_table *table; struct net *net = dev_net(rt->dst.dev); - if (rt == net->ipv6.ip6_null_entry || - rt->dst.flags & DST_NOCACHE) { + if (rt == net->ipv6.ip6_null_entry) { err = -ENOENT; goto out; } @@ -2222,7 +2204,8 @@ out_put: return err; } -static int ip6_route_del(struct fib6_config *cfg) +static int ip6_route_del(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct fib6_table *table; struct fib6_node *fn; @@ -2230,8 +2213,10 @@ static int ip6_route_del(struct fib6_config *cfg) int err = -ESRCH; table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table); - if (!table) + if (!table) { + NL_SET_ERR_MSG(extack, "FIB table does not exist"); return err; + } read_lock_bh(&table->tb6_lock); @@ -2369,7 +2354,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; if (ip6_ins_rt(nrt)) - goto out; + goto out_release; netevent.old = &rt->dst; netevent.new = &nrt->dst; @@ -2382,6 +2367,12 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu ip6_del_rt(rt); } +out_release: + /* Release the reference taken in + * ip6_rt_cache_alloc() + */ + dst_release(&nrt->dst); + out: neigh_release(neigh); } @@ -2483,7 +2474,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, if (!prefixlen) cfg.fc_flags |= RTF_DEFAULT; - ip6_route_add(&cfg); + ip6_route_add(&cfg, NULL); return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev); } @@ -2529,7 +2520,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, cfg.fc_gateway = *gwaddr; - if (!ip6_route_add(&cfg)) { + if (!ip6_route_add(&cfg, NULL)) { struct fib6_table *table; table = fib6_get_table(dev_net(dev), cfg.fc_table); @@ -2622,10 +2613,10 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) rtnl_lock(); switch (cmd) { case SIOCADDRT: - err = ip6_route_add(&cfg); + err = ip6_route_add(&cfg, NULL); break; case SIOCDELRT: - err = ip6_route_del(&cfg); + err = ip6_route_del(&cfg, NULL); break; default: err = -EINVAL; @@ -2729,9 +2720,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->rt6i_dst.plen = 128; tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL; rt->rt6i_table = fib6_get_table(net, tb_id); - rt->dst.flags |= DST_NOCACHE; - - atomic_set(&rt->dst.__refcnt, 1); return rt; } @@ -2819,7 +2807,6 @@ void rt6_ifdown(struct net *net, struct net_device *dev) }; fib6_clean_all(net, fib6_ifdown, &adn); - icmp6_clean_all(fib6_ifdown, &adn); if (dev) rt6_uncached_list_flush_dev(net, dev); } @@ -2904,7 +2891,8 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, - struct fib6_config *cfg) + struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; @@ -2988,7 +2976,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); err = lwtunnel_valid_encap_type_attr(cfg->fc_mp, - cfg->fc_mp_len); + cfg->fc_mp_len, extack); if (err < 0) goto errout; } @@ -3007,7 +2995,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_ENCAP_TYPE]) { cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); - err = lwtunnel_valid_encap_type(cfg->fc_encap_type); + err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack); if (err < 0) goto errout; } @@ -3048,17 +3036,11 @@ static int ip6_route_info_append(struct list_head *rt6_nh_list, struct rt6_info *rt, struct fib6_config *r_cfg) { struct rt6_nh *nh; - struct rt6_info *rtnh; int err = -EEXIST; list_for_each_entry(nh, rt6_nh_list, next) { /* check if rt6_info already exists */ - rtnh = nh->rt6_info; - - if (rtnh->dst.dev == rt->dst.dev && - rtnh->rt6i_idev == rt->rt6i_idev && - ipv6_addr_equal(&rtnh->rt6i_gateway, - &rt->rt6i_gateway)) + if (rt6_duplicate_nexthop(nh->rt6_info, rt)) return err; } @@ -3098,7 +3080,8 @@ static void ip6_route_mpath_notify(struct rt6_info *rt, inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); } -static int ip6_route_multipath_add(struct fib6_config *cfg) +static int ip6_route_multipath_add(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct rt6_info *rt_notif = NULL, *rt_last = NULL; struct nl_info *info = &cfg->fc_nlinfo; @@ -3146,7 +3129,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg) r_cfg.fc_encap_type = nla_get_u16(nla); } - rt = ip6_route_info_create(&r_cfg); + rt = ip6_route_info_create(&r_cfg, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; @@ -3155,7 +3138,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg) err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg); if (err) { - dst_free(&rt->dst); + dst_release_immediate(&rt->dst); goto cleanup; } @@ -3171,7 +3154,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg) err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { rt_last = nh->rt6_info; - err = __ip6_ins_rt(nh->rt6_info, info, &nh->mxc); + err = __ip6_ins_rt(nh->rt6_info, info, &nh->mxc, extack); /* save reference to first route for notification */ if (!rt_notif && !err) rt_notif = nh->rt6_info; @@ -3213,13 +3196,13 @@ add_errout: list_for_each_entry(nh, &rt6_nh_list, next) { if (err_nh == nh) break; - ip6_route_del(&nh->r_cfg); + ip6_route_del(&nh->r_cfg, extack); } cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { if (nh->rt6_info) - dst_free(&nh->rt6_info->dst); + dst_release_immediate(&nh->rt6_info->dst); kfree(nh->mxc.mx); list_del(&nh->next); kfree(nh); @@ -3228,7 +3211,8 @@ cleanup: return err; } -static int ip6_route_multipath_del(struct fib6_config *cfg) +static int ip6_route_multipath_del(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct fib6_config r_cfg; struct rtnexthop *rtnh; @@ -3255,7 +3239,7 @@ static int ip6_route_multipath_del(struct fib6_config *cfg) r_cfg.fc_flags |= RTF_GATEWAY; } } - err = ip6_route_del(&r_cfg); + err = ip6_route_del(&r_cfg, extack); if (err) last_err = err; @@ -3271,15 +3255,15 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib6_config cfg; int err; - err = rtm_to_fib6_config(skb, nlh, &cfg); + err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_mp) - return ip6_route_multipath_del(&cfg); + return ip6_route_multipath_del(&cfg, extack); else { cfg.fc_delete_all_nh = 1; - return ip6_route_del(&cfg); + return ip6_route_del(&cfg, extack); } } @@ -3289,14 +3273,14 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib6_config cfg; int err; - err = rtm_to_fib6_config(skb, nlh, &cfg); + err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_mp) - return ip6_route_multipath_add(&cfg); + return ip6_route_multipath_add(&cfg, extack); else - return ip6_route_add(&cfg); + return ip6_route_add(&cfg, extack); } static size_t rt6_nlmsg_size(struct rt6_info *rt) @@ -3577,11 +3561,13 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; + int err, iif = 0, oif = 0; + struct dst_entry *dst; struct rt6_info *rt; struct sk_buff *skb; struct rtmsg *rtm; struct flowi6 fl6; - int err, iif = 0, oif = 0; + bool fibmatch; err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); @@ -3592,6 +3578,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, memset(&fl6, 0, sizeof(fl6)); rtm = nlmsg_data(nlh); fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0); + fibmatch = !!(rtm->rtm_flags & RTM_F_FIB_MATCH); if (tb[RTA_SRC]) { if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr)) @@ -3637,12 +3624,23 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (!ipv6_addr_any(&fl6.saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; - rt = (struct rt6_info *)ip6_route_input_lookup(net, dev, &fl6, - flags); + if (!fibmatch) + dst = ip6_route_input_lookup(net, dev, &fl6, flags); } else { fl6.flowi6_oif = oif; - rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6); + if (!fibmatch) + dst = ip6_route_output(net, NULL, &fl6); + } + + if (fibmatch) + dst = ip6_route_lookup(net, &fl6, 0); + + rt = container_of(dst, struct rt6_info, dst); + if (rt->dst.error) { + err = rt->dst.error; + ip6_rt_put(rt); + goto errout; } if (rt == net->ipv6.ip6_null_entry) { @@ -3659,10 +3657,14 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, } skb_dst_set(skb, &rt->dst); - - err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif, - RTM_NEWROUTE, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0); + if (fibmatch) + err = rt6_fill_node(net, skb, rt, NULL, NULL, iif, + RTM_NEWROUTE, NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, 0); + else + err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif, + RTM_NEWROUTE, NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, 0); if (err < 0) { kfree_skb(skb); goto errout; diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 5f44ffed2576..15fba55e3da8 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -303,13 +303,9 @@ static int seg6_genl_dumphmac_done(struct netlink_callback *cb) static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb) { struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; - struct net *net = sock_net(skb->sk); - struct seg6_pernet_data *sdata; struct seg6_hmac_info *hinfo; int ret; - sdata = seg6_pernet(net); - ret = rhashtable_walk_start(iter); if (ret && ret != -EAGAIN) goto done; diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 6a495490d43e..264d772d3c7d 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -326,7 +326,8 @@ drop: static int seg6_build_state(struct nlattr *nla, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct nlattr *tb[SEG6_IPTUNNEL_MAX + 1]; struct seg6_iptunnel_encap *tuninfo; @@ -336,7 +337,7 @@ static int seg6_build_state(struct nlattr *nla, int err; err = nla_parse_nested(tb, SEG6_IPTUNNEL_MAX, nla, - seg6_iptunnel_policy, NULL); + seg6_iptunnel_policy, extack); if (err < 0) return err; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index f8ad15891cd7..ac912bb21747 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1406,7 +1406,8 @@ static void __net_init ipip6_fb_tunnel_init(struct net_device *dev) rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); } -static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { u8 proto; @@ -1537,7 +1538,8 @@ static bool ipip6_netlink_6rd_parms(struct nlattr *data[], #endif static int ipip6_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip_tunnel *nt; @@ -1573,7 +1575,8 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev, } static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 5abc3692b901..4e7817abc0b9 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -162,15 +162,16 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, 0, NULL); + tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcpv6_ts_off(ipv6_hdr(skb)->daddr.s6_addr32, + tsoff = secure_tcpv6_ts_off(sock_net(sk), + ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32); tcp_opt.rcv_tsecr -= tsoff; } - if (!cookie_timestamp_decode(&tcp_opt)) + if (!cookie_timestamp_decode(sock_net(sk), &tcp_opt)) goto out; ret = NULL; @@ -193,7 +194,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { - atomic_inc(&skb->users); + refcount_inc(&skb->users); ireq->pktopts = skb; } @@ -211,10 +212,11 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack.v64 = 0; + treq->snt_synack = 0; treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; treq->ts_off = 0; + treq->txhash = net_tx_rndhash(); /* * We need to lookup the dst_entry to get the correct window size. diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4f4310a36a04..2521690d62d6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -109,9 +109,9 @@ static u32 tcp_v6_init_seq(const struct sk_buff *skb) tcp_hdr(skb)->source); } -static u32 tcp_v6_init_ts_off(const struct sk_buff *skb) +static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb) { - return secure_tcpv6_ts_off(ipv6_hdr(skb)->daddr.s6_addr32, + return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32); } @@ -292,7 +292,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport); - tp->tsoffset = secure_tcpv6_ts_off(np->saddr.s6_addr32, + tp->tsoffset = secure_tcpv6_ts_off(sock_net(sk), + np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32); } @@ -514,11 +515,12 @@ static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk, return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr); } -static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, - int optlen) +static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, + char __user *optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; + u8 prefixlen; if (optlen < sizeof(cmd)) return -EINVAL; @@ -529,12 +531,22 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, if (sin6->sin6_family != AF_INET6) return -EINVAL; + if (optname == TCP_MD5SIG_EXT && + cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { + prefixlen = cmd.tcpm_prefixlen; + if (prefixlen > 128 || (ipv6_addr_v4mapped(&sin6->sin6_addr) && + prefixlen > 32)) + return -EINVAL; + } else { + prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128; + } + if (!cmd.tcpm_keylen) { if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], - AF_INET); + AF_INET, prefixlen); return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr, - AF_INET6); + AF_INET6, prefixlen); } if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) @@ -542,10 +554,12 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], - AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); + AF_INET, prefixlen, cmd.tcpm_key, + cmd.tcpm_keylen, GFP_KERNEL); return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr, - AF_INET6, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); + AF_INET6, prefixlen, cmd.tcpm_key, + cmd.tcpm_keylen, GFP_KERNEL); } static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp, @@ -720,7 +734,7 @@ static void tcp_v6_init_req(struct request_sock *req, np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim || np->repflow)) { - atomic_inc(&skb->users); + refcount_inc(&skb->users); ireq->pktopts = skb; } } @@ -788,7 +802,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len); - t1 = (struct tcphdr *) skb_push(buff, tot_len); + t1 = skb_push(buff, tot_len); skb_reset_transport_header(buff); /* Swap the send and the receive. */ @@ -949,7 +963,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcp_time_stamp + tcptw->tw_ts_offset, + tcp_time_stamp_raw() + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel)); @@ -971,7 +985,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, - tcp_time_stamp + tcp_rsk(req)->ts_off, + tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0, 0); @@ -1185,7 +1199,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * * across. Shucks. */ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, - AF_INET6, key->key, key->keylen, + AF_INET6, 128, key->key, key->keylen, sk_gfp_mask(sk, GFP_ATOMIC)); } #endif @@ -1248,9 +1262,6 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_do_rcv(sk, skb); - if (tcp_filter(sk, skb)) - goto discard; - /* * socket locking is here for SMP purposes as backlog rcv * is currently called with bh processing disabled. @@ -1453,6 +1464,8 @@ process: if (nsk == sk) { reqsk_put(req); tcp_v6_restore_cb(skb); + } else if (tcp_filter(sk, skb)) { + goto discard_and_relse; } else if (tcp_child_process(sk, nsk, skb)) { tcp_v6_send_reset(nsk, skb); goto discard_and_relse; @@ -1796,7 +1809,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), icsk->icsk_probes_out, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, + refcount_read(&sp->sk_refcnt), sp, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, @@ -1829,7 +1842,7 @@ static void get_timewait6_sock(struct seq_file *seq, dest->s6_addr32[2], dest->s6_addr32[3], destp, tw->tw_substate, 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, - atomic_read(&tw->tw_refcnt), tw); + refcount_read(&tw->tw_refcnt), tw); } static int tcp6_seq_show(struct seq_file *seq, void *v) @@ -1909,6 +1922,7 @@ struct proto tcpv6_prot = { .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 75703fda23e7..4a3e65626e8b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -325,7 +325,7 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table, NULL); - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } @@ -362,7 +362,7 @@ try_again: if (!skb) return err; - ulen = skb->len; + ulen = udp_skb_len(skb); copied = len; if (copied > ulen - off) copied = ulen - off; @@ -379,14 +379,18 @@ try_again: if (copied < ulen || peeking || (is_udplite && UDP_SKB_CB(skb)->partial_cov)) { - checksum_valid = !udp_lib_checksum_complete(skb); + checksum_valid = udp_skb_csum_unnecessary(skb) || + !__udp_lib_checksum_complete(skb); if (!checksum_valid) goto csum_copy_err; } - if (checksum_valid || skb_csum_unnecessary(skb)) - err = skb_copy_datagram_msg(skb, off, msg, copied); - else { + if (checksum_valid || udp_skb_csum_unnecessary(skb)) { + if (udp_skb_is_linear(skb)) + err = copy_linear_skb(skb, copied, off, &msg->msg_iter); + else + err = skb_copy_datagram_msg(skb, off, msg, copied); + } else { err = skb_copy_and_csum_datagram_msg(skb, off, msg); if (err == -EINVAL) goto csum_copy_err; @@ -455,7 +459,8 @@ try_again: return err; csum_copy_err: - if (!__sk_queue_drop_skb(sk, skb, flags, udp_skb_destructor)) { + if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags, + udp_skb_destructor)) { if (is_udp4) { UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); @@ -629,6 +634,7 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } } + prefetch(&sk->sk_rmem_alloc); if (rcu_access_pointer(sk->sk_filter) && udp_lib_checksum_complete(skb)) goto csum_error; @@ -910,7 +916,7 @@ static void udp_v6_early_demux(struct sk_buff *skb) else return; - if (!sk || !atomic_inc_not_zero_hint(&sk->sk_refcnt, 2)) + if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return; skb->sk = sk; @@ -920,12 +926,11 @@ static void udp_v6_early_demux(struct sk_buff *skb) if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); if (dst) { - if (dst->flags & DST_NOCACHE) { - if (likely(atomic_inc_not_zero(&dst->__refcnt))) - skb_dst_set(skb, dst); - } else { - skb_dst_set_noref(skb, dst); - } + /* set noref for now. + * any place which wants to hold dst has to call + * dst_hold_safe() + */ + skb_dst_set_noref(skb, dst); } } diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index 1e205c3253ac..57fd314ec2b8 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -54,7 +54,7 @@ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) skb->mac_header = skb->network_header + offsetof(struct ipv6hdr, nexthdr); skb->transport_header = skb->network_header + sizeof(*top_iph); - ph = (struct ip_beet_phdr *)__skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl-hdr_len); + ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdr_len); xfrm6_beet_make_header(skb); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index d7b731a78d09..4e438bc7ee87 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -59,7 +59,7 @@ struct xfrm6_tunnel_spi { struct hlist_node list_byspi; xfrm_address_t addr; u32 spi; - atomic_t refcnt; + refcount_t refcnt; struct rcu_head rcu_head; }; @@ -160,7 +160,7 @@ alloc_spi: memcpy(&x6spi->addr, saddr, sizeof(x6spi->addr)); x6spi->spi = spi; - atomic_set(&x6spi->refcnt, 1); + refcount_set(&x6spi->refcnt, 1); hlist_add_head_rcu(&x6spi->list_byspi, &xfrm6_tn->spi_byspi[index]); @@ -178,7 +178,7 @@ __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr) spin_lock_bh(&xfrm6_tunnel_spi_lock); x6spi = __xfrm6_tunnel_spi_lookup(net, saddr); if (x6spi) { - atomic_inc(&x6spi->refcnt); + refcount_inc(&x6spi->refcnt); spi = x6spi->spi; } else spi = __xfrm6_tunnel_alloc_spi(net, saddr); @@ -207,7 +207,7 @@ static void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr) list_byaddr) { if (xfrm6_addr_equal(&x6spi->addr, saddr)) { - if (atomic_dec_and_test(&x6spi->refcnt)) { + if (refcount_dec_and_test(&x6spi->refcnt)) { hlist_del_rcu(&x6spi->list_byaddr); hlist_del_rcu(&x6spi->list_byspi); call_rcu(&x6spi->rcu_head, x6spi_destroy_rcu); diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index fa31ef29e3fa..ac598ec90589 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -308,7 +308,7 @@ void ipxitf_down(struct ipx_interface *intrfc) static void __ipxitf_put(struct ipx_interface *intrfc) { - if (atomic_dec_and_test(&intrfc->refcnt)) + if (refcount_dec_and_test(&intrfc->refcnt)) __ipxitf_down(intrfc); } @@ -876,7 +876,7 @@ static struct ipx_interface *ipxitf_alloc(struct net_device *dev, __be32 netnum, intrfc->if_ipx_offset = ipx_offset; intrfc->if_sknum = IPX_MIN_EPHEMERAL_SOCKET; INIT_HLIST_HEAD(&intrfc->if_sklist); - atomic_set(&intrfc->refcnt, 1); + refcount_set(&intrfc->refcnt, 1); spin_lock_init(&intrfc->if_sklist_lock); } @@ -1105,7 +1105,7 @@ static struct ipx_interface *ipxitf_auto_create(struct net_device *dev, memcpy((char *)&(intrfc->if_node[IPX_NODE_LEN-dev->addr_len]), dev->dev_addr, dev->addr_len); spin_lock_init(&intrfc->if_sklist_lock); - atomic_set(&intrfc->refcnt, 1); + refcount_set(&intrfc->refcnt, 1); ipxitf_insert(intrfc); dev_hold(dev); } diff --git a/net/ipx/ipx_proc.c b/net/ipx/ipx_proc.c index c1d247ebe916..7d75e4c5c75d 100644 --- a/net/ipx/ipx_proc.c +++ b/net/ipx/ipx_proc.c @@ -53,7 +53,7 @@ static int ipx_seq_interface_show(struct seq_file *seq, void *v) seq_printf(seq, "%-11s", ipx_device_name(i)); seq_printf(seq, "%-9s", ipx_frame_name(i->if_dlink_type)); #ifdef IPX_REFCNT_DEBUG - seq_printf(seq, "%6d", atomic_read(&i->refcnt)); + seq_printf(seq, "%6d", refcount_read(&i->refcnt)); #endif seq_puts(seq, "\n"); out: diff --git a/net/ipx/ipx_route.c b/net/ipx/ipx_route.c index 3e2a32a9f3bd..b5d91447f3dc 100644 --- a/net/ipx/ipx_route.c +++ b/net/ipx/ipx_route.c @@ -59,7 +59,7 @@ int ipxrtr_add_route(__be32 network, struct ipx_interface *intrfc, if (!rt) goto out; - atomic_set(&rt->refcnt, 1); + refcount_set(&rt->refcnt, 1); ipxrtr_hold(rt); write_lock_bh(&ipx_routes_lock); list_add(&rt->node, &ipx_routes); diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 8d77ad5cadaf..2e6990f8b80b 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1901,16 +1901,10 @@ static int irda_setsockopt(struct socket *sock, int level, int optname, goto out; } - ias_opt = kmalloc(sizeof(struct irda_ias_set), GFP_ATOMIC); - if (ias_opt == NULL) { - err = -ENOMEM; - goto out; - } - /* Copy query to the driver. */ - if (copy_from_user(ias_opt, optval, optlen)) { - kfree(ias_opt); - err = -EFAULT; + ias_opt = memdup_user(optval, optlen); + if (IS_ERR(ias_opt)) { + err = PTR_ERR(ias_opt); goto out; } @@ -2032,16 +2026,10 @@ static int irda_setsockopt(struct socket *sock, int level, int optname, goto out; } - ias_opt = kmalloc(sizeof(struct irda_ias_set), GFP_ATOMIC); - if (ias_opt == NULL) { - err = -ENOMEM; - goto out; - } - /* Copy query to the driver. */ - if (copy_from_user(ias_opt, optval, optlen)) { - kfree(ias_opt); - err = -EFAULT; + ias_opt = memdup_user(optval, optlen); + if (IS_ERR(ias_opt)) { + err = PTR_ERR(ias_opt); goto out; } @@ -2317,16 +2305,10 @@ bed: goto out; } - ias_opt = kmalloc(sizeof(struct irda_ias_set), GFP_ATOMIC); - if (ias_opt == NULL) { - err = -ENOMEM; - goto out; - } - /* Copy query to the driver. */ - if (copy_from_user(ias_opt, optval, len)) { - kfree(ias_opt); - err = -EFAULT; + ias_opt = memdup_user(optval, len); + if (IS_ERR(ias_opt)) { + err = PTR_ERR(ias_opt); goto out; } @@ -2381,16 +2363,10 @@ bed: goto out; } - ias_opt = kmalloc(sizeof(struct irda_ias_set), GFP_ATOMIC); - if (ias_opt == NULL) { - err = -ENOMEM; - goto out; - } - /* Copy query to the driver. */ - if (copy_from_user(ias_opt, optval, len)) { - kfree(ias_opt); - err = -EFAULT; + ias_opt = memdup_user(optval, len); + if (IS_ERR(ias_opt)) { + err = PTR_ERR(ias_opt); goto out; } diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index f6061c4bb0a8..ec157c3419b5 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -690,7 +690,7 @@ static int ircomm_tty_write(struct tty_struct *tty, } /* Copy data */ - memcpy(skb_put(skb,size), buf + len, size); + skb_put_data(skb, buf + len, size); count -= size; len += size; diff --git a/net/irda/ircomm/ircomm_tty_ioctl.c b/net/irda/ircomm/ircomm_tty_ioctl.c index f18070118d05..171c3dee760e 100644 --- a/net/irda/ircomm/ircomm_tty_ioctl.c +++ b/net/irda/ircomm/ircomm_tty_ioctl.c @@ -97,33 +97,7 @@ static void ircomm_tty_change_speed(struct ircomm_tty_cb *self, self->settings.flow_control &= ~IRCOMM_RTS_CTS_IN; } tty_port_set_check_carrier(&self->port, ~cflag & CLOCAL); -#if 0 - /* - * Set up parity check flag - */ - - if (I_INPCK(self->tty)) - driver->read_status_mask |= LSR_FE | LSR_PE; - if (I_BRKINT(driver->tty) || I_PARMRK(driver->tty)) - driver->read_status_mask |= LSR_BI; - - /* - * Characters to ignore - */ - driver->ignore_status_mask = 0; - if (I_IGNPAR(driver->tty)) - driver->ignore_status_mask |= LSR_PE | LSR_FE; - - if (I_IGNBRK(self->tty)) { - self->ignore_status_mask |= LSR_BI; - /* - * If we're ignore parity and break indicators, ignore - * overruns too. (For real raw support). - */ - if (I_IGNPAR(self->tty)) - self->ignore_status_mask |= LSR_OE; - } -#endif + self->settings.data_format = cval; ircomm_param_request(self, IRCOMM_DATA_FORMAT, FALSE); @@ -271,67 +245,6 @@ static int ircomm_tty_get_serial_info(struct ircomm_tty_cb *self, static int ircomm_tty_set_serial_info(struct ircomm_tty_cb *self, struct serial_struct __user *new_info) { -#if 0 - struct serial_struct new_serial; - struct ircomm_tty_cb old_state, *state; - - if (copy_from_user(&new_serial,new_info,sizeof(new_serial))) - return -EFAULT; - - - state = self - old_state = *self; - - if (!capable(CAP_SYS_ADMIN)) { - if ((new_serial.baud_base != state->settings.data_rate) || - (new_serial.close_delay != state->close_delay) || - ((new_serial.flags & ~ASYNC_USR_MASK) != - (self->flags & ~ASYNC_USR_MASK))) - return -EPERM; - state->flags = ((state->flags & ~ASYNC_USR_MASK) | - (new_serial.flags & ASYNC_USR_MASK)); - self->flags = ((self->flags & ~ASYNC_USR_MASK) | - (new_serial.flags & ASYNC_USR_MASK)); - /* self->custom_divisor = new_serial.custom_divisor; */ - goto check_and_exit; - } - - /* - * OK, past this point, all the error checking has been done. - * At this point, we start making changes..... - */ - - if (self->settings.data_rate != new_serial.baud_base) { - self->settings.data_rate = new_serial.baud_base; - ircomm_param_request(self, IRCOMM_DATA_RATE, TRUE); - } - - self->close_delay = new_serial.close_delay * HZ/100; - self->closing_wait = new_serial.closing_wait * HZ/100; - /* self->custom_divisor = new_serial.custom_divisor; */ - - self->flags = ((self->flags & ~ASYNC_FLAGS) | - (new_serial.flags & ASYNC_FLAGS)); - self->tty->low_latency = (self->flags & ASYNC_LOW_LATENCY) ? 1 : 0; - - check_and_exit: - - if (tty_port_initialized(self)) { - if (((old_state.flags & ASYNC_SPD_MASK) != - (self->flags & ASYNC_SPD_MASK)) || - (old_driver.custom_divisor != driver->custom_divisor)) { - if ((driver->flags & ASYNC_SPD_MASK) == ASYNC_SPD_HI) - driver->tty->alt_speed = 57600; - if ((driver->flags & ASYNC_SPD_MASK) == ASYNC_SPD_VHI) - driver->tty->alt_speed = 115200; - if ((driver->flags & ASYNC_SPD_MASK) == ASYNC_SPD_SHI) - driver->tty->alt_speed = 230400; - if ((driver->flags & ASYNC_SPD_MASK) == ASYNC_SPD_WARP) - driver->tty->alt_speed = 460800; - ircomm_tty_change_speed(driver); - } - } -#endif return 0; } @@ -367,24 +280,6 @@ int ircomm_tty_ioctl(struct tty_struct *tty, case TIOCGICOUNT: pr_debug("%s(), TIOCGICOUNT not impl!\n", __func__); -#if 0 - save_flags(flags); cli(); - cnow = driver->icount; - restore_flags(flags); - p_cuser = (struct serial_icounter_struct __user *) arg; - if (put_user(cnow.cts, &p_cuser->cts) || - put_user(cnow.dsr, &p_cuser->dsr) || - put_user(cnow.rng, &p_cuser->rng) || - put_user(cnow.dcd, &p_cuser->dcd) || - put_user(cnow.rx, &p_cuser->rx) || - put_user(cnow.tx, &p_cuser->tx) || - put_user(cnow.frame, &p_cuser->frame) || - put_user(cnow.overrun, &p_cuser->overrun) || - put_user(cnow.parity, &p_cuser->parity) || - put_user(cnow.brk, &p_cuser->brk) || - put_user(cnow.buf_overrun, &p_cuser->buf_overrun)) - return -EFAULT; -#endif return 0; default: ret = -ENOIOCTLCMD; /* ioctls which we must ignore */ diff --git a/net/irda/irlap_frame.c b/net/irda/irlap_frame.c index b936b1251a66..debda3de4726 100644 --- a/net/irda/irlap_frame.c +++ b/net/irda/irlap_frame.c @@ -133,7 +133,7 @@ void irlap_send_snrm_frame(struct irlap_cb *self, struct qos_info *qos) if (!tx_skb) return; - frame = (struct snrm_frame *) skb_put(tx_skb, 2); + frame = skb_put(tx_skb, 2); /* Insert connection address field */ if (qos) @@ -228,7 +228,7 @@ void irlap_send_ua_response_frame(struct irlap_cb *self, struct qos_info *qos) if (!tx_skb) return; - frame = (struct ua_frame *) skb_put(tx_skb, 10); + frame = skb_put(tx_skb, 10); /* Build UA response */ frame->caddr = self->caddr; @@ -268,7 +268,7 @@ void irlap_send_dm_frame( struct irlap_cb *self) if (!tx_skb) return; - frame = (struct dm_frame *)skb_put(tx_skb, 2); + frame = skb_put(tx_skb, 2); if (self->state == LAP_NDM) frame->caddr = CBROADCAST; @@ -298,7 +298,7 @@ void irlap_send_disc_frame(struct irlap_cb *self) if (!tx_skb) return; - frame = (struct disc_frame *)skb_put(tx_skb, 2); + frame = skb_put(tx_skb, 2); frame->caddr = self->caddr | CMD_FRAME; frame->control = DISC_CMD | PF_BIT; @@ -392,8 +392,7 @@ void irlap_send_discovery_xid_frame(struct irlap_cb *self, int S, __u8 s, info[0] = discovery->data.charset; len = IRDA_MIN(discovery->name_len, skb_tailroom(tx_skb)); - info = skb_put(tx_skb, len); - memcpy(info, discovery->data.info, len); + skb_put_data(tx_skb, discovery->data.info, len); } irlap_queue_xmit(self, tx_skb); } @@ -588,7 +587,7 @@ void irlap_send_rr_frame(struct irlap_cb *self, int command) if (!tx_skb) return; - frame = (struct rr_frame *)skb_put(tx_skb, 2); + frame = skb_put(tx_skb, 2); frame->caddr = self->caddr; frame->caddr |= (command) ? CMD_FRAME : 0; @@ -613,7 +612,7 @@ void irlap_send_rd_frame(struct irlap_cb *self) if (!tx_skb) return; - frame = (struct rd_frame *)skb_put(tx_skb, 2); + frame = skb_put(tx_skb, 2); frame->caddr = self->caddr; frame->control = RD_RSP | PF_BIT; @@ -1195,7 +1194,6 @@ void irlap_send_test_frame(struct irlap_cb *self, __u8 caddr, __u32 daddr, { struct sk_buff *tx_skb; struct test_frame *frame; - __u8 *info; tx_skb = alloc_skb(cmd->len + sizeof(struct test_frame), GFP_ATOMIC); if (!tx_skb) @@ -1203,21 +1201,19 @@ void irlap_send_test_frame(struct irlap_cb *self, __u8 caddr, __u32 daddr, /* Broadcast frames must include saddr and daddr fields */ if (caddr == CBROADCAST) { - frame = (struct test_frame *) - skb_put(tx_skb, sizeof(struct test_frame)); + frame = skb_put(tx_skb, sizeof(struct test_frame)); /* Insert the swapped addresses */ frame->saddr = cpu_to_le32(self->saddr); frame->daddr = cpu_to_le32(daddr); } else - frame = (struct test_frame *) skb_put(tx_skb, LAP_ADDR_HEADER + LAP_CTRL_HEADER); + frame = skb_put(tx_skb, LAP_ADDR_HEADER + LAP_CTRL_HEADER); frame->caddr = caddr; frame->control = TEST_RSP | PF_BIT; /* Copy info */ - info = skb_put(tx_skb, cmd->len); - memcpy(info, cmd->data, cmd->len); + skb_put_data(tx_skb, cmd->data, cmd->len); /* Return to sender */ irlap_wait_min_turn_around(self, &self->qos_tx); diff --git a/net/irda/irnet/irnet_irda.c b/net/irda/irnet/irnet_irda.c index 7f17a8020e8a..e390bceeb2f8 100644 --- a/net/irda/irnet/irnet_irda.c +++ b/net/irda/irnet/irnet_irda.c @@ -1065,7 +1065,7 @@ irnet_data_indication(void * instance, if(p[0] & 1) { /* protocol is compressed */ - skb_push(skb, 1)[0] = 0; + *(u8 *)skb_push(skb, 1) = 0; } else if(skb->len < 2) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 84de7b6326dc..148533169b1d 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -322,8 +322,7 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, int err, confirm_recv = 0; memset(skb->head, 0, ETH_HLEN); - phs_hdr = (struct af_iucv_trans_hdr *)skb_push(skb, - sizeof(struct af_iucv_trans_hdr)); + phs_hdr = skb_push(skb, sizeof(struct af_iucv_trans_hdr)); skb_reset_mac_header(skb); skb_reset_network_header(skb); skb_push(skb, ETH_HLEN); @@ -363,7 +362,7 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, else skb_trim(skb, skb->dev->mtu); } - skb->protocol = ETH_P_AF_IUCV; + skb->protocol = cpu_to_be16(ETH_P_AF_IUCV); nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; @@ -403,7 +402,7 @@ static void iucv_sock_destruct(struct sock *sk) } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); - WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(sk->sk_wmem_queued); WARN_ON(sk->sk_forward_alloc); } @@ -716,10 +715,8 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, char uid[9]; /* Verify the input sockaddr */ - if (!addr || addr->sa_family != AF_IUCV) - return -EINVAL; - - if (addr_len < sizeof(struct sockaddr_iucv)) + if (addr_len < sizeof(struct sockaddr_iucv) || + addr->sa_family != AF_IUCV) return -EINVAL; lock_sock(sk); @@ -863,7 +860,7 @@ static int iucv_sock_connect(struct socket *sock, struct sockaddr *addr, struct iucv_sock *iucv = iucv_sk(sk); int err; - if (addr->sa_family != AF_IUCV || alen < sizeof(struct sockaddr_iucv)) + if (alen < sizeof(struct sockaddr_iucv) || addr->sa_family != AF_IUCV) return -EINVAL; if (sk->sk_state != IUCV_OPEN && sk->sk_state != IUCV_BOUND) diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c index bf75c9231cca..c343ac60bf50 100644 --- a/net/kcm/kcmproc.c +++ b/net/kcm/kcmproc.c @@ -162,7 +162,7 @@ static void kcm_format_psock(struct kcm_psock *psock, struct seq_file *seq, psock->sk->sk_receive_queue.qlen, atomic_read(&psock->sk->sk_rmem_alloc), psock->sk->sk_write_queue.qlen, - atomic_read(&psock->sk->sk_wmem_alloc)); + refcount_read(&psock->sk->sk_wmem_alloc)); if (psock->done) seq_puts(seq, "Done "); diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index deca20fb2ce2..da49191f7ad0 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1985,7 +1985,7 @@ static int kcm_create(struct net *net, struct socket *sock, return 0; } -static struct net_proto_family kcm_family_ops = { +static const struct net_proto_family kcm_family_ops = { .family = PF_KCM, .create = kcm_create, .owner = THIS_MODULE, diff --git a/net/key/af_key.c b/net/key/af_key.c index b1432b668033..ca9d3ae665e7 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -109,7 +109,7 @@ static void pfkey_sock_destruct(struct sock *sk) } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); - WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(refcount_read(&sk->sk_wmem_alloc)); atomic_dec(&net_pfkey->socks_nr); } @@ -203,11 +203,11 @@ static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2, sock_hold(sk); if (*skb2 == NULL) { - if (atomic_read(&skb->users) != 1) { + if (refcount_read(&skb->users) != 1) { *skb2 = skb_clone(skb, allocation); } else { *skb2 = skb; - atomic_inc(&skb->users); + refcount_inc(&skb->users); } } if (*skb2 != NULL) { @@ -349,7 +349,7 @@ static int pfkey_error(const struct sadb_msg *orig, int err, struct sock *sk) err = EINVAL; BUG_ON(err <= 0 || err >= 256); - hdr = (struct sadb_msg *) skb_put(skb, sizeof(struct sadb_msg)); + hdr = skb_put(skb, sizeof(struct sadb_msg)); pfkey_hdr_dup(hdr, orig); hdr->sadb_msg_errno = (uint8_t) err; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / @@ -810,12 +810,12 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, return ERR_PTR(-ENOBUFS); /* call should fill header later */ - hdr = (struct sadb_msg *) skb_put(skb, sizeof(struct sadb_msg)); + hdr = skb_put(skb, sizeof(struct sadb_msg)); memset(hdr, 0, size); /* XXX do we need this ? */ hdr->sadb_msg_len = size / sizeof(uint64_t); /* sa */ - sa = (struct sadb_sa *) skb_put(skb, sizeof(struct sadb_sa)); + sa = skb_put(skb, sizeof(struct sadb_sa)); sa->sadb_sa_len = sizeof(struct sadb_sa)/sizeof(uint64_t); sa->sadb_sa_exttype = SADB_EXT_SA; sa->sadb_sa_spi = x->id.spi; @@ -862,8 +862,7 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, /* hard time */ if (hsc & 2) { - lifetime = (struct sadb_lifetime *) skb_put(skb, - sizeof(struct sadb_lifetime)); + lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_HARD; @@ -874,8 +873,7 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, } /* soft time */ if (hsc & 1) { - lifetime = (struct sadb_lifetime *) skb_put(skb, - sizeof(struct sadb_lifetime)); + lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_SOFT; @@ -885,8 +883,7 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, lifetime->sadb_lifetime_usetime = x->lft.soft_use_expires_seconds; } /* current time */ - lifetime = (struct sadb_lifetime *) skb_put(skb, - sizeof(struct sadb_lifetime)); + lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_CURRENT; @@ -895,8 +892,7 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, lifetime->sadb_lifetime_addtime = x->curlft.add_time; lifetime->sadb_lifetime_usetime = x->curlft.use_time; /* src address */ - addr = (struct sadb_address*) skb_put(skb, - sizeof(struct sadb_address)+sockaddr_size); + addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); @@ -915,8 +911,7 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, BUG(); /* dst address */ - addr = (struct sadb_address*) skb_put(skb, - sizeof(struct sadb_address)+sockaddr_size); + addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); @@ -933,8 +928,8 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, if (!xfrm_addr_equal(&x->sel.saddr, &x->props.saddr, x->props.family)) { - addr = (struct sadb_address*) skb_put(skb, - sizeof(struct sadb_address)+sockaddr_size); + addr = skb_put(skb, + sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); @@ -951,8 +946,7 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, /* auth key */ if (add_keys && auth_key_size) { - key = (struct sadb_key *) skb_put(skb, - sizeof(struct sadb_key)+auth_key_size); + key = skb_put(skb, sizeof(struct sadb_key) + auth_key_size); key->sadb_key_len = (sizeof(struct sadb_key) + auth_key_size) / sizeof(uint64_t); key->sadb_key_exttype = SADB_EXT_KEY_AUTH; @@ -962,8 +956,7 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, } /* encrypt key */ if (add_keys && encrypt_key_size) { - key = (struct sadb_key *) skb_put(skb, - sizeof(struct sadb_key)+encrypt_key_size); + key = skb_put(skb, sizeof(struct sadb_key) + encrypt_key_size); key->sadb_key_len = (sizeof(struct sadb_key) + encrypt_key_size) / sizeof(uint64_t); key->sadb_key_exttype = SADB_EXT_KEY_ENCRYPT; @@ -974,7 +967,7 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, } /* sa */ - sa2 = (struct sadb_x_sa2 *) skb_put(skb, sizeof(struct sadb_x_sa2)); + sa2 = skb_put(skb, sizeof(struct sadb_x_sa2)); sa2->sadb_x_sa2_len = sizeof(struct sadb_x_sa2)/sizeof(uint64_t); sa2->sadb_x_sa2_exttype = SADB_X_EXT_SA2; if ((mode = pfkey_mode_from_xfrm(x->props.mode)) < 0) { @@ -992,7 +985,7 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, struct sadb_x_nat_t_port *n_port; /* type */ - n_type = (struct sadb_x_nat_t_type*) skb_put(skb, sizeof(*n_type)); + n_type = skb_put(skb, sizeof(*n_type)); n_type->sadb_x_nat_t_type_len = sizeof(*n_type)/sizeof(uint64_t); n_type->sadb_x_nat_t_type_exttype = SADB_X_EXT_NAT_T_TYPE; n_type->sadb_x_nat_t_type_type = natt->encap_type; @@ -1001,14 +994,14 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, n_type->sadb_x_nat_t_type_reserved[2] = 0; /* source port */ - n_port = (struct sadb_x_nat_t_port*) skb_put(skb, sizeof (*n_port)); + n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_SPORT; n_port->sadb_x_nat_t_port_port = natt->encap_sport; n_port->sadb_x_nat_t_port_reserved = 0; /* dest port */ - n_port = (struct sadb_x_nat_t_port*) skb_put(skb, sizeof (*n_port)); + n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_DPORT; n_port->sadb_x_nat_t_port_port = natt->encap_dport; @@ -1017,8 +1010,8 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, /* security context */ if (xfrm_ctx) { - sec_ctx = (struct sadb_x_sec_ctx *) skb_put(skb, - sizeof(struct sadb_x_sec_ctx) + ctx_size); + sec_ctx = skb_put(skb, + sizeof(struct sadb_x_sec_ctx) + ctx_size); sec_ctx->sadb_x_sec_len = (sizeof(struct sadb_x_sec_ctx) + ctx_size) / sizeof(uint64_t); sec_ctx->sadb_x_sec_exttype = SADB_X_EXT_SEC_CTX; @@ -1626,7 +1619,7 @@ static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig, if (!skb) goto out_put_algs; - hdr = (struct sadb_msg *) skb_put(skb, sizeof(*hdr)); + hdr = skb_put(skb, sizeof(*hdr)); pfkey_hdr_dup(hdr, orig); hdr->sadb_msg_errno = 0; hdr->sadb_msg_len = len / sizeof(uint64_t); @@ -1635,7 +1628,7 @@ static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig, struct sadb_supported *sp; struct sadb_alg *ap; - sp = (struct sadb_supported *) skb_put(skb, auth_len); + sp = skb_put(skb, auth_len); ap = (struct sadb_alg *) (sp + 1); sp->sadb_supported_len = auth_len / sizeof(uint64_t); @@ -1656,7 +1649,7 @@ static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig, struct sadb_supported *sp; struct sadb_alg *ap; - sp = (struct sadb_supported *) skb_put(skb, enc_len); + sp = skb_put(skb, enc_len); ap = (struct sadb_alg *) (sp + 1); sp->sadb_supported_len = enc_len / sizeof(uint64_t); @@ -1715,8 +1708,7 @@ static int unicast_flush_resp(struct sock *sk, const struct sadb_msg *ihdr) if (!skb) return -ENOBUFS; - hdr = (struct sadb_msg *) skb_put(skb, sizeof(struct sadb_msg)); - memcpy(hdr, ihdr, sizeof(struct sadb_msg)); + hdr = skb_put_data(skb, ihdr, sizeof(struct sadb_msg)); hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); @@ -1731,7 +1723,7 @@ static int key_notify_sa_flush(const struct km_event *c) skb = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); if (!skb) return -ENOBUFS; - hdr = (struct sadb_msg *) skb_put(skb, sizeof(struct sadb_msg)); + hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_satype = pfkey_proto2satype(c->data.proto); hdr->sadb_msg_type = SADB_FLUSH; hdr->sadb_msg_seq = c->seq; @@ -2056,12 +2048,11 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy * size = pfkey_xfrm_policy2msg_size(xp); /* call should fill header later */ - hdr = (struct sadb_msg *) skb_put(skb, sizeof(struct sadb_msg)); + hdr = skb_put(skb, sizeof(struct sadb_msg)); memset(hdr, 0, size); /* XXX do we need this ? */ /* src address */ - addr = (struct sadb_address*) skb_put(skb, - sizeof(struct sadb_address)+sockaddr_size); + addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); @@ -2076,8 +2067,7 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy * BUG(); /* dst address */ - addr = (struct sadb_address*) skb_put(skb, - sizeof(struct sadb_address)+sockaddr_size); + addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); @@ -2091,8 +2081,7 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy * xp->family); /* hard time */ - lifetime = (struct sadb_lifetime *) skb_put(skb, - sizeof(struct sadb_lifetime)); + lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_HARD; @@ -2101,8 +2090,7 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy * lifetime->sadb_lifetime_addtime = xp->lft.hard_add_expires_seconds; lifetime->sadb_lifetime_usetime = xp->lft.hard_use_expires_seconds; /* soft time */ - lifetime = (struct sadb_lifetime *) skb_put(skb, - sizeof(struct sadb_lifetime)); + lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_SOFT; @@ -2111,8 +2099,7 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy * lifetime->sadb_lifetime_addtime = xp->lft.soft_add_expires_seconds; lifetime->sadb_lifetime_usetime = xp->lft.soft_use_expires_seconds; /* current time */ - lifetime = (struct sadb_lifetime *) skb_put(skb, - sizeof(struct sadb_lifetime)); + lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_CURRENT; @@ -2121,7 +2108,7 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy * lifetime->sadb_lifetime_addtime = xp->curlft.add_time; lifetime->sadb_lifetime_usetime = xp->curlft.use_time; - pol = (struct sadb_x_policy *) skb_put(skb, sizeof(struct sadb_x_policy)); + pol = skb_put(skb, sizeof(struct sadb_x_policy)); pol->sadb_x_policy_len = sizeof(struct sadb_x_policy)/sizeof(uint64_t); pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_DISCARD; @@ -2149,7 +2136,7 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy * } else { size -= 2*socklen; } - rq = (void*)skb_put(skb, req_size); + rq = skb_put(skb, req_size); pol->sadb_x_policy_len += req_size/8; memset(rq, 0, sizeof(*rq)); rq->sadb_x_ipsecrequest_len = req_size; @@ -2179,7 +2166,7 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy * if ((xfrm_ctx = xp->security)) { int ctx_size = pfkey_xfrm_policy2sec_ctx_size(xp); - sec_ctx = (struct sadb_x_sec_ctx *) skb_put(skb, ctx_size); + sec_ctx = skb_put(skb, ctx_size); sec_ctx->sadb_x_sec_len = ctx_size / sizeof(uint64_t); sec_ctx->sadb_x_sec_exttype = SADB_X_EXT_SEC_CTX; sec_ctx->sadb_x_ctx_doi = xfrm_ctx->ctx_doi; @@ -2190,7 +2177,7 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy * } hdr->sadb_msg_len = size / sizeof(uint64_t); - hdr->sadb_msg_reserved = atomic_read(&xp->refcnt); + hdr->sadb_msg_reserved = refcount_read(&xp->refcnt); return 0; } @@ -2611,7 +2598,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb, } return xfrm_migrate(&sel, dir, XFRM_POLICY_TYPE_MAIN, m, i, - kma ? &k : NULL, net); + kma ? &k : NULL, net, NULL); out: return err; @@ -2743,7 +2730,7 @@ static int key_notify_policy_flush(const struct km_event *c) skb_out = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); if (!skb_out) return -ENOBUFS; - hdr = (struct sadb_msg *) skb_put(skb_out, sizeof(struct sadb_msg)); + hdr = skb_put(skb_out, sizeof(struct sadb_msg)); hdr->sadb_msg_type = SADB_X_SPDFLUSH; hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->portid; @@ -2929,7 +2916,7 @@ static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) struct sadb_prop *p; int i; - p = (struct sadb_prop*)skb_put(skb, sizeof(struct sadb_prop)); + p = skb_put(skb, sizeof(struct sadb_prop)); p->sadb_prop_len = sizeof(struct sadb_prop)/8; p->sadb_prop_exttype = SADB_EXT_PROPOSAL; p->sadb_prop_replay = 32; @@ -2945,8 +2932,7 @@ static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) if (aalg_tmpl_set(t, aalg) && aalg->available) { struct sadb_comb *c; - c = (struct sadb_comb*)skb_put(skb, sizeof(struct sadb_comb)); - memset(c, 0, sizeof(*c)); + c = skb_put_zero(skb, sizeof(struct sadb_comb)); p->sadb_prop_len += sizeof(struct sadb_comb)/8; c->sadb_comb_auth = aalg->desc.sadb_alg_id; c->sadb_comb_auth_minbits = aalg->desc.sadb_alg_minbits; @@ -2964,7 +2950,7 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) struct sadb_prop *p; int i, k; - p = (struct sadb_prop*)skb_put(skb, sizeof(struct sadb_prop)); + p = skb_put(skb, sizeof(struct sadb_prop)); p->sadb_prop_len = sizeof(struct sadb_prop)/8; p->sadb_prop_exttype = SADB_EXT_PROPOSAL; p->sadb_prop_replay = 32; @@ -2990,7 +2976,7 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) continue; if (!(aalg_tmpl_set(t, aalg) && aalg->available)) continue; - c = (struct sadb_comb*)skb_put(skb, sizeof(struct sadb_comb)); + c = skb_put(skb, sizeof(struct sadb_comb)); memset(c, 0, sizeof(*c)); p->sadb_prop_len += sizeof(struct sadb_comb)/8; c->sadb_comb_auth = aalg->desc.sadb_alg_id; @@ -3157,7 +3143,7 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct if (skb == NULL) return -ENOMEM; - hdr = (struct sadb_msg *) skb_put(skb, sizeof(struct sadb_msg)); + hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = SADB_ACQUIRE; hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); @@ -3168,8 +3154,7 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct hdr->sadb_msg_pid = 0; /* src address */ - addr = (struct sadb_address*) skb_put(skb, - sizeof(struct sadb_address)+sockaddr_size); + addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); @@ -3184,8 +3169,7 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct BUG(); /* dst address */ - addr = (struct sadb_address*) skb_put(skb, - sizeof(struct sadb_address)+sockaddr_size); + addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); @@ -3199,7 +3183,7 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct if (!addr->sadb_address_prefixlen) BUG(); - pol = (struct sadb_x_policy *) skb_put(skb, sizeof(struct sadb_x_policy)); + pol = skb_put(skb, sizeof(struct sadb_x_policy)); pol->sadb_x_policy_len = sizeof(struct sadb_x_policy)/sizeof(uint64_t); pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; @@ -3216,8 +3200,8 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct /* security context */ if (xfrm_ctx) { - sec_ctx = (struct sadb_x_sec_ctx *) skb_put(skb, - sizeof(struct sadb_x_sec_ctx) + ctx_size); + sec_ctx = skb_put(skb, + sizeof(struct sadb_x_sec_ctx) + ctx_size); sec_ctx->sadb_x_sec_len = (sizeof(struct sadb_x_sec_ctx) + ctx_size) / sizeof(uint64_t); sec_ctx->sadb_x_sec_exttype = SADB_X_EXT_SEC_CTX; @@ -3359,7 +3343,7 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, if (skb == NULL) return -ENOMEM; - hdr = (struct sadb_msg *) skb_put(skb, sizeof(struct sadb_msg)); + hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = SADB_X_NAT_T_NEW_MAPPING; hdr->sadb_msg_satype = satype; @@ -3370,7 +3354,7 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, hdr->sadb_msg_pid = 0; /* SA */ - sa = (struct sadb_sa *) skb_put(skb, sizeof(struct sadb_sa)); + sa = skb_put(skb, sizeof(struct sadb_sa)); sa->sadb_sa_len = sizeof(struct sadb_sa)/sizeof(uint64_t); sa->sadb_sa_exttype = SADB_EXT_SA; sa->sadb_sa_spi = x->id.spi; @@ -3381,8 +3365,7 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, sa->sadb_sa_flags = 0; /* ADDRESS_SRC (old addr) */ - addr = (struct sadb_address*) - skb_put(skb, sizeof(struct sadb_address)+sockaddr_size); + addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); @@ -3397,15 +3380,14 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, BUG(); /* NAT_T_SPORT (old port) */ - n_port = (struct sadb_x_nat_t_port*) skb_put(skb, sizeof (*n_port)); + n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_SPORT; n_port->sadb_x_nat_t_port_port = natt->encap_sport; n_port->sadb_x_nat_t_port_reserved = 0; /* ADDRESS_DST (new addr) */ - addr = (struct sadb_address*) - skb_put(skb, sizeof(struct sadb_address)+sockaddr_size); + addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); @@ -3420,7 +3402,7 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, BUG(); /* NAT_T_DPORT (new port) */ - n_port = (struct sadb_x_nat_t_port*) skb_put(skb, sizeof (*n_port)); + n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_DPORT; n_port->sadb_x_nat_t_port_port = sport; @@ -3434,7 +3416,7 @@ static int set_sadb_address(struct sk_buff *skb, int sasize, int type, const struct xfrm_selector *sel) { struct sadb_address *addr; - addr = (struct sadb_address *)skb_put(skb, sizeof(struct sadb_address) + sasize); + addr = skb_put(skb, sizeof(struct sadb_address) + sasize); addr->sadb_address_len = (sizeof(struct sadb_address) + sasize)/8; addr->sadb_address_exttype = type; addr->sadb_address_proto = sel->proto; @@ -3472,8 +3454,7 @@ static int set_sadb_kmaddress(struct sk_buff *skb, const struct xfrm_kmaddress * size_req = (sizeof(struct sadb_x_kmaddress) + pfkey_sockaddr_pair_size(family)); - kma = (struct sadb_x_kmaddress *)skb_put(skb, size_req); - memset(kma, 0, size_req); + kma = skb_put_zero(skb, size_req); kma->sadb_x_kmaddress_len = size_req / 8; kma->sadb_x_kmaddress_exttype = SADB_X_EXT_KMADDRESS; kma->sadb_x_kmaddress_reserved = k->reserved; @@ -3499,8 +3480,7 @@ static int set_ipsecrequest(struct sk_buff *skb, size_req = sizeof(struct sadb_x_ipsecrequest) + pfkey_sockaddr_pair_size(family); - rq = (struct sadb_x_ipsecrequest *)skb_put(skb, size_req); - memset(rq, 0, size_req); + rq = skb_put_zero(skb, size_req); rq->sadb_x_ipsecrequest_len = size_req; rq->sadb_x_ipsecrequest_proto = proto; rq->sadb_x_ipsecrequest_mode = mode; @@ -3519,7 +3499,8 @@ static int set_ipsecrequest(struct sk_buff *skb, #ifdef CONFIG_NET_KEY_MIGRATE static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, - const struct xfrm_kmaddress *k) + const struct xfrm_kmaddress *k, + const struct xfrm_encap_tmpl *encap) { int i; int sasize_sel; @@ -3568,7 +3549,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, if (skb == NULL) return -ENOMEM; - hdr = (struct sadb_msg *)skb_put(skb, sizeof(struct sadb_msg)); + hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = SADB_X_MIGRATE; hdr->sadb_msg_satype = pfkey_proto2satype(m->proto); @@ -3589,7 +3570,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, set_sadb_address(skb, sasize_sel, SADB_EXT_ADDRESS_DST, sel); /* policy information */ - pol = (struct sadb_x_policy *)skb_put(skb, sizeof(struct sadb_x_policy)); + pol = skb_put(skb, sizeof(struct sadb_x_policy)); pol->sadb_x_policy_len = size_pol / 8; pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; @@ -3629,7 +3610,8 @@ err: #else static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, - const struct xfrm_kmaddress *k) + const struct xfrm_kmaddress *k, + const struct xfrm_encap_tmpl *encap) { return -ENOPROTOOPT; } @@ -3757,7 +3739,7 @@ static int pfkey_seq_show(struct seq_file *f, void *v) else seq_printf(f, "%pK %-6d %-6u %-6u %-6u %-6lu\n", s, - atomic_read(&s->sk_refcnt), + refcount_read(&s->sk_refcnt), sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), from_kuid_munged(seq_user_ns(f), sock_i_uid(s)), diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index fa0342574b89..b0c2d4ae781d 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -132,12 +132,12 @@ static inline struct l2tp_net *l2tp_pernet(const struct net *net) */ static inline void l2tp_tunnel_inc_refcount_1(struct l2tp_tunnel *tunnel) { - atomic_inc(&tunnel->ref_count); + refcount_inc(&tunnel->ref_count); } static inline void l2tp_tunnel_dec_refcount_1(struct l2tp_tunnel *tunnel) { - if (atomic_dec_and_test(&tunnel->ref_count)) + if (refcount_dec_and_test(&tunnel->ref_count)) l2tp_tunnel_free(tunnel); } #ifdef L2TP_REFCNT_DEBUG @@ -145,14 +145,14 @@ static inline void l2tp_tunnel_dec_refcount_1(struct l2tp_tunnel *tunnel) do { \ pr_debug("l2tp_tunnel_inc_refcount: %s:%d %s: cnt=%d\n", \ __func__, __LINE__, (_t)->name, \ - atomic_read(&_t->ref_count)); \ + refcount_read(&_t->ref_count)); \ l2tp_tunnel_inc_refcount_1(_t); \ } while (0) #define l2tp_tunnel_dec_refcount(_t) \ do { \ pr_debug("l2tp_tunnel_dec_refcount: %s:%d %s: cnt=%d\n", \ __func__, __LINE__, (_t)->name, \ - atomic_read(&_t->ref_count)); \ + refcount_read(&_t->ref_count)); \ l2tp_tunnel_dec_refcount_1(_t); \ } while (0) #else @@ -1353,7 +1353,7 @@ static void l2tp_udp_encap_destroy(struct sock *sk) */ static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { - BUG_ON(atomic_read(&tunnel->ref_count) != 0); + BUG_ON(refcount_read(&tunnel->ref_count) != 0); BUG_ON(tunnel->sock != NULL); l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: free...\n", tunnel->name); kfree_rcu(tunnel, rcu); @@ -1667,7 +1667,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 /* Bump the reference count. The tunnel context is deleted * only when this drops to zero. Must be done before list insertion */ - l2tp_tunnel_inc_refcount(tunnel); + refcount_set(&tunnel->ref_count, 1); spin_lock_bh(&pn->l2tp_tunnel_list_lock); list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list); spin_unlock_bh(&pn->l2tp_tunnel_list_lock); @@ -1706,7 +1706,7 @@ void l2tp_session_free(struct l2tp_session *session) { struct l2tp_tunnel *tunnel = session->tunnel; - BUG_ON(atomic_read(&session->ref_count) != 0); + BUG_ON(refcount_read(&session->ref_count) != 0); if (tunnel) { BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC); @@ -1854,7 +1854,7 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn /* Bump the reference count. The session context is deleted * only when this drops to zero. */ - l2tp_session_inc_refcount(session); + refcount_set(&session->ref_count, 1); l2tp_tunnel_inc_refcount(tunnel); /* Ensure tunnel socket isn't deleted */ diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index eec5ad2ebb93..cdb6e3327f74 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -7,6 +7,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include <linux/refcount.h> #ifndef _L2TP_CORE_H_ #define _L2TP_CORE_H_ @@ -98,7 +99,7 @@ struct l2tp_session { int nr_oos_count; /* For OOS recovery */ int nr_oos_count_max; struct hlist_node hlist; /* Hash list node */ - atomic_t ref_count; + refcount_t ref_count; char name[32]; /* for logging */ char ifname[IFNAMSIZ]; @@ -177,7 +178,7 @@ struct l2tp_tunnel { struct list_head list; /* Keep a list of all tunnels */ struct net *l2tp_net; /* the net we belong to */ - atomic_t ref_count; + refcount_t ref_count; #ifdef CONFIG_DEBUG_FS void (*show)(struct seq_file *m, void *arg); #endif @@ -273,12 +274,12 @@ int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg); */ static inline void l2tp_session_inc_refcount_1(struct l2tp_session *session) { - atomic_inc(&session->ref_count); + refcount_inc(&session->ref_count); } static inline void l2tp_session_dec_refcount_1(struct l2tp_session *session) { - if (atomic_dec_and_test(&session->ref_count)) + if (refcount_dec_and_test(&session->ref_count)) l2tp_session_free(session); } @@ -287,14 +288,14 @@ static inline void l2tp_session_dec_refcount_1(struct l2tp_session *session) do { \ pr_debug("l2tp_session_inc_refcount: %s:%d %s: cnt=%d\n", \ __func__, __LINE__, (_s)->name, \ - atomic_read(&_s->ref_count)); \ + refcount_read(&_s->ref_count)); \ l2tp_session_inc_refcount_1(_s); \ } while (0) #define l2tp_session_dec_refcount(_s) \ do { \ pr_debug("l2tp_session_dec_refcount: %s:%d %s: cnt=%d\n", \ __func__, __LINE__, (_s)->name, \ - atomic_read(&_s->ref_count)); \ + refcount_read(&_s->ref_count)); \ l2tp_session_dec_refcount_1(_s); \ } while (0) #else diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index d100aed3d06f..53bae54c4d6e 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -144,9 +144,8 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) tunnel->encap == L2TP_ENCAPTYPE_IP ? "IP" : ""); seq_printf(m, " %d sessions, refcnt %d/%d\n", session_count, - tunnel->sock ? atomic_read(&tunnel->sock->sk_refcnt) : 0, - atomic_read(&tunnel->ref_count)); - + tunnel->sock ? refcount_read(&tunnel->sock->sk_refcnt) : 0, + refcount_read(&tunnel->ref_count)); seq_printf(m, " %08x rx %ld/%ld/%ld rx %ld/%ld/%ld\n", tunnel->debug, atomic_long_read(&tunnel->stats.tx_packets), @@ -171,7 +170,7 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v) ""); if (session->send_seq || session->recv_seq) seq_printf(m, " nr %hu, ns %hu\n", session->nr, session->ns); - seq_printf(m, " refcnt %d\n", atomic_read(&session->ref_count)); + seq_printf(m, " refcnt %d\n", refcount_read(&session->ref_count)); seq_printf(m, " config %d/%d/%c/%c/%s/%s %08x %u\n", session->mtu, session->mru, session->recv_seq ? 'R' : '-', diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 32ea0f3d868c..f0edb7209079 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1616,7 +1616,7 @@ static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v) seq_printf(m, "\nTUNNEL '%s', %c %d\n", tunnel->name, (tunnel == tunnel->sock->sk_user_data) ? 'Y' : 'N', - atomic_read(&tunnel->ref_count) - 1); + refcount_read(&tunnel->ref_count) - 1); seq_printf(m, " %08x %ld/%ld/%ld %ld/%ld/%ld\n", tunnel->debug, atomic_long_read(&tunnel->stats.tx_packets), diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index b50b64ac8815..e15314e3b464 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -54,12 +54,12 @@ static void lapb_free_cb(struct lapb_cb *lapb) static __inline__ void lapb_hold(struct lapb_cb *lapb) { - atomic_inc(&lapb->refcnt); + refcount_inc(&lapb->refcnt); } static __inline__ void lapb_put(struct lapb_cb *lapb) { - if (atomic_dec_and_test(&lapb->refcnt)) + if (refcount_dec_and_test(&lapb->refcnt)) lapb_free_cb(lapb); } @@ -136,7 +136,7 @@ static struct lapb_cb *lapb_create_cb(void) lapb->mode = LAPB_DEFAULT_MODE; lapb->window = LAPB_DEFAULT_WINDOW; lapb->state = LAPB_STATE_0; - atomic_set(&lapb->refcnt, 1); + refcount_set(&lapb->refcnt, 1); out: return lapb; } diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 9b02c13d258b..5e91b47f0d2a 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -507,7 +507,7 @@ again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_estab_match(sap, daddr, laddr, rc)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ - if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || !llc_estab_match(sap, daddr, laddr, rc))) { @@ -566,7 +566,7 @@ again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_listener_match(sap, laddr, rc)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ - if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || !llc_listener_match(sap, laddr, rc))) { @@ -973,9 +973,9 @@ void llc_sk_free(struct sock *sk) skb_queue_purge(&sk->sk_write_queue); skb_queue_purge(&llc->pdu_unack_q); #ifdef LLC_REFCNT_DEBUG - if (atomic_read(&sk->sk_refcnt) != 1) { + if (refcount_read(&sk->sk_refcnt) != 1) { printk(KERN_DEBUG "Destruction of LLC sock %p delayed in %s, cnt=%d\n", - sk, __func__, atomic_read(&sk->sk_refcnt)); + sk, __func__, refcount_read(&sk->sk_refcnt)); printk(KERN_DEBUG "%d LLC sockets are still alive\n", atomic_read(&llc_sock_nr)); } else { diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index 842851cef698..89041260784c 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -41,7 +41,7 @@ static struct llc_sap *llc_sap_alloc(void) spin_lock_init(&sap->sk_lock); for (i = 0; i < LLC_SK_LADDR_HASH_ENTRIES; i++) INIT_HLIST_NULLS_HEAD(&sap->sk_laddr_hash[i], i); - atomic_set(&sap->refcnt, 1); + refcount_set(&sap->refcnt, 1); } return sap; } diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index 63b6ab056370..d90928f50226 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -329,7 +329,7 @@ again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_dgram_match(sap, laddr, rc)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ - if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || !llc_dgram_match(sap, laddr, rc))) { diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 1b7a4daf283c..8708cbe8af5b 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -213,8 +213,7 @@ static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *d return; skb_reserve(skb, local->hw.extra_tx_headroom); - mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24); - memset(mgmt, 0, 24); + mgmt = skb_put_zero(skb, 24); memcpy(mgmt->da, da, ETH_ALEN); memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); if (sdata->vif.type == NL80211_IFTYPE_AP || @@ -449,44 +448,21 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, buf_size, true, false); } -void ieee80211_start_rx_ba_session_offl(struct ieee80211_vif *vif, - const u8 *addr, u16 tid) +void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, + const u8 *addr, unsigned int bit) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; - struct ieee80211_rx_agg *rx_agg; - struct sk_buff *skb = dev_alloc_skb(0); - - if (unlikely(!skb)) - return; - - rx_agg = (struct ieee80211_rx_agg *) &skb->cb; - memcpy(&rx_agg->addr, addr, ETH_ALEN); - rx_agg->tid = tid; - - skb->pkt_type = IEEE80211_SDATA_QUEUE_RX_AGG_START; - skb_queue_tail(&sdata->skb_queue, skb); - ieee80211_queue_work(&local->hw, &sdata->work); -} -EXPORT_SYMBOL(ieee80211_start_rx_ba_session_offl); - -void ieee80211_stop_rx_ba_session_offl(struct ieee80211_vif *vif, - const u8 *addr, u16 tid) -{ - struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); - struct ieee80211_local *local = sdata->local; - struct ieee80211_rx_agg *rx_agg; - struct sk_buff *skb = dev_alloc_skb(0); - - if (unlikely(!skb)) - return; + struct sta_info *sta; - rx_agg = (struct ieee80211_rx_agg *) &skb->cb; - memcpy(&rx_agg->addr, addr, ETH_ALEN); - rx_agg->tid = tid; + rcu_read_lock(); + sta = sta_info_get_bss(sdata, addr); + if (!sta) + goto unlock; - skb->pkt_type = IEEE80211_SDATA_QUEUE_RX_AGG_STOP; - skb_queue_tail(&sdata->skb_queue, skb); - ieee80211_queue_work(&local->hw, &sdata->work); + set_bit(bit, sta->ampdu_mlme.tid_rx_manage_offl); + ieee80211_queue_work(&local->hw, &sta->ampdu_mlme.work); + unlock: + rcu_read_unlock(); } -EXPORT_SYMBOL(ieee80211_stop_rx_ba_session_offl); +EXPORT_SYMBOL(ieee80211_manage_rx_ba_offl); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index cf2392b2ac71..cbd48762256c 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -76,8 +76,7 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata, return; skb_reserve(skb, local->hw.extra_tx_headroom); - mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24); - memset(mgmt, 0, 24); + mgmt = skb_put_zero(skb, 24); memcpy(mgmt->da, da, ETH_ALEN); memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); if (sdata->vif.type == NL80211_IFTYPE_AP || @@ -125,8 +124,7 @@ void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn) return; skb_reserve(skb, local->hw.extra_tx_headroom); - bar = (struct ieee80211_bar *)skb_put(skb, sizeof(*bar)); - memset(bar, 0, sizeof(*bar)); + bar = skb_put_zero(skb, sizeof(*bar)); bar->frame_control = cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK_REQ); memcpy(bar->ra, ra, ETH_ALEN); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 4a388fe8c2d1..a354f1939e49 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1107,7 +1107,7 @@ static void ieee80211_send_layer2_update(struct sta_info *sta) skb = dev_alloc_skb(sizeof(*msg)); if (!skb) return; - msg = (struct iapp_layer2_update *)skb_put(skb, sizeof(*msg)); + msg = skb_put(skb, sizeof(*msg)); /* 802.2 Type 1 Logical Link Control (LLC) Exchange Identifier (XID) * Update response frame; IEEE Std 802.2-1998, 5.4.1.2.1 */ @@ -1876,6 +1876,7 @@ static int copy_mesh_setup(struct ieee80211_if_mesh *ifmsh, ifmsh->user_mpm = setup->user_mpm; ifmsh->mesh_auth_id = setup->auth_id; ifmsh->security = IEEE80211_MESH_SEC_NONE; + ifmsh->userspace_handles_dfs = setup->userspace_handles_dfs; if (setup->is_authenticated) ifmsh->security |= IEEE80211_MESH_SEC_AUTHED; if (setup->is_secure) @@ -3413,7 +3414,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, skb_reserve(skb, local->hw.extra_tx_headroom); - nullfunc = (void *) skb_put(skb, size); + nullfunc = skb_put(skb, size); nullfunc->frame_control = fc; nullfunc->duration_id = 0; memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN); diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 8f5fff8b2040..c813207bb123 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -330,8 +330,7 @@ static ssize_t ieee80211_if_parse_tkip_mic_test( return -ENOMEM; skb_reserve(skb, local->hw.extra_tx_headroom); - hdr = (struct ieee80211_hdr *) skb_put(skb, 24); - memset(hdr, 0, 24); + hdr = skb_put_zero(skb, 24); fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA); switch (sdata->vif.type) { @@ -367,7 +366,7 @@ static ssize_t ieee80211_if_parse_tkip_mic_test( * The exact contents does not matter since the recipient is required * to drop this because of the Michael MIC failure. */ - memset(skb_put(skb, 50), 0, 50); + skb_put_zero(skb, 50); IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_TKIP_MIC_FAILURE; diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 42601820db20..b15412c21ac9 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -154,6 +154,12 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, p += scnprintf(p, bufsz+buf-p, + "target %uus interval %uus ecn %s\n", + codel_time_to_us(sta->cparams.target), + codel_time_to_us(sta->cparams.interval), + sta->cparams.ecn ? "yes" : "no"); + p += scnprintf(p, + bufsz+buf-p, "tid ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets\n"); for (i = 0; i < IEEE80211_NUM_TIDS; i++) { diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 6ca5442b1e03..c92df492e898 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -331,6 +331,18 @@ void ieee80211_ba_session_work(struct work_struct *work) sta, tid, WLAN_BACK_RECIPIENT, WLAN_REASON_UNSPECIFIED, true); + if (test_and_clear_bit(tid, + sta->ampdu_mlme.tid_rx_manage_offl)) + __ieee80211_start_rx_ba_session(sta, 0, 0, 0, 1, tid, + IEEE80211_MAX_AMPDU_BUF, + false, true); + + if (test_and_clear_bit(tid + IEEE80211_NUM_TIDS, + sta->ampdu_mlme.tid_rx_manage_offl)) + ___ieee80211_stop_rx_ba_session( + sta, tid, WLAN_BACK_RECIPIENT, + 0, false); + spin_lock_bh(&sta->lock); tid_tx = sta->ampdu_mlme.tid_start_tx[tid]; @@ -382,8 +394,7 @@ void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata, return; skb_reserve(skb, local->hw.extra_tx_headroom); - mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24); - memset(mgmt, 0, 24); + mgmt = skb_put_zero(skb, 24); memcpy(mgmt->da, da, ETH_ALEN); memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); if (sdata->vif.type == NL80211_IFTYPE_AP || @@ -448,7 +459,7 @@ int ieee80211_send_smps_action(struct ieee80211_sub_if_data *sdata, return -ENOMEM; skb_reserve(skb, local->hw.extra_tx_headroom); - action_frame = (void *)skb_put(skb, 27); + action_frame = skb_put(skb, 27); memcpy(action_frame->da, da, ETH_ALEN); memcpy(action_frame->sa, sdata->dev->dev_addr, ETH_ALEN); memcpy(action_frame->bssid, bssid, ETH_ALEN); diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 364d4e137649..e9c6aa3ed05b 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -808,7 +808,6 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, } memset(¶ms, 0, sizeof(params)); - memset(&csa_ie, 0, sizeof(csa_ie)); err = ieee80211_parse_ch_switch_ie(sdata, elems, ifibss->chandef.chan->band, sta_flags, ifibss->bssid, &csa_ie); @@ -1570,7 +1569,7 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata, return; skb_reserve(skb, local->tx_headroom); - memcpy(skb_put(skb, presp->head_len), presp->head, presp->head_len); + skb_put_data(skb, presp->head, presp->head_len); memcpy(((struct ieee80211_mgmt *) skb->data)->da, mgmt->sa, ETH_ALEN); ibss_dbg(sdata, "Sending ProbeResp to %pM\n", mgmt->sa); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 5e002f62c235..2197c62a0a6e 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -643,6 +643,8 @@ struct ieee80211_if_mesh { unsigned long wrkq_flags; unsigned long mbss_changed; + bool userspace_handles_dfs; + u8 mesh_id[IEEE80211_MAX_MESH_ID_LEN]; size_t mesh_id_len; /* Active Path Selection Protocol Identifier */ @@ -1029,17 +1031,6 @@ ieee80211_vif_get_shift(struct ieee80211_vif *vif) return shift; } -struct ieee80211_rx_agg { - u8 addr[ETH_ALEN]; - u16 tid; -}; - -enum sdata_queue_type { - IEEE80211_SDATA_QUEUE_TYPE_FRAME = 0, - IEEE80211_SDATA_QUEUE_RX_AGG_START = 3, - IEEE80211_SDATA_QUEUE_RX_AGG_STOP = 4, -}; - enum { IEEE80211_RX_MSG = 1, IEEE80211_TX_STATUS_MSG = 2, @@ -1432,6 +1423,7 @@ struct ieee80211_csa_ie { u8 count; u8 ttl; u16 pre_value; + u16 reason_code; }; /* Parsed Information Elements */ @@ -2057,6 +2049,8 @@ u8 *ieee80211_ie_build_ht_cap(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, const struct cfg80211_chan_def *chandef, u16 prot_mode, bool rifs_mode); +void ieee80211_ie_build_wide_bw_cs(u8 *pos, + const struct cfg80211_chan_def *chandef); u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, u32 cap); u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index f5f50150ba1c..9228ac73c429 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1237,7 +1237,6 @@ static void ieee80211_iface_work(struct work_struct *work) struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct sta_info *sta; - struct ieee80211_rx_agg *rx_agg; if (!ieee80211_sdata_running(sdata)) return; @@ -1252,28 +1251,8 @@ static void ieee80211_iface_work(struct work_struct *work) while ((skb = skb_dequeue(&sdata->skb_queue))) { struct ieee80211_mgmt *mgmt = (void *)skb->data; - if (skb->pkt_type == IEEE80211_SDATA_QUEUE_RX_AGG_START) { - rx_agg = (void *)&skb->cb; - mutex_lock(&local->sta_mtx); - sta = sta_info_get_bss(sdata, rx_agg->addr); - if (sta) - __ieee80211_start_rx_ba_session(sta, - 0, 0, 0, 1, rx_agg->tid, - IEEE80211_MAX_AMPDU_BUF, - false, true); - mutex_unlock(&local->sta_mtx); - } else if (skb->pkt_type == IEEE80211_SDATA_QUEUE_RX_AGG_STOP) { - rx_agg = (void *)&skb->cb; - mutex_lock(&local->sta_mtx); - sta = sta_info_get_bss(sdata, rx_agg->addr); - if (sta) - __ieee80211_stop_rx_ba_session(sta, - rx_agg->tid, - WLAN_BACK_RECIPIENT, 0, - false); - mutex_unlock(&local->sta_mtx); - } else if (ieee80211_is_action(mgmt->frame_control) && - mgmt->u.action.category == WLAN_CATEGORY_BACK) { + if (ieee80211_is_action(mgmt->frame_control) && + mgmt->u.action.category == WLAN_CATEGORY_BACK) { int len = skb->len; mutex_lock(&local->sta_mtx); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 737e1f082b0d..a550c707cd8a 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -345,7 +345,7 @@ int mesh_add_vendor_ies(struct ieee80211_sub_if_data *sdata, data = ifmsh->ie + offset; if (skb_tailroom(skb) < len) return -ENOMEM; - memcpy(skb_put(skb, len), data, len); + skb_put_data(skb, data, len); } return 0; @@ -369,7 +369,7 @@ int mesh_add_rsn_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) if (skb_tailroom(skb) < len) return -ENOMEM; - memcpy(skb_put(skb, len), data, len); + skb_put_data(skb, data, len); return 0; } @@ -690,6 +690,9 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) 2 + sizeof(struct ieee80211_channel_sw_ie) + /* Mesh Channel Switch Parameters */ 2 + sizeof(struct ieee80211_mesh_chansw_params_ie) + + /* Channel Switch Wrapper + Wide Bandwidth CSA IE */ + 2 + 2 + sizeof(struct ieee80211_wide_bw_chansw_ie) + + 2 + sizeof(struct ieee80211_sec_chan_offs_ie) + 2 + 8 + /* supported rates */ 2 + 3; /* DS params */ tail_len = 2 + (IEEE80211_MAX_SUPP_RATES - 8) + @@ -716,8 +719,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) bcn->head = ((u8 *) bcn) + sizeof(*bcn); /* fill in the head */ - mgmt = (struct ieee80211_mgmt *) skb_put(skb, hdr_len); - memset(mgmt, 0, hdr_len); + mgmt = skb_put_zero(skb, hdr_len); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON); eth_broadcast_addr(mgmt->da); @@ -736,8 +738,12 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) rcu_read_lock(); csa = rcu_dereference(ifmsh->csa); if (csa) { - pos = skb_put(skb, 13); - memset(pos, 0, 13); + enum nl80211_channel_type ct; + struct cfg80211_chan_def *chandef; + int ie_len = 2 + sizeof(struct ieee80211_channel_sw_ie) + + 2 + sizeof(struct ieee80211_mesh_chansw_params_ie); + + pos = skb_put_zero(skb, ie_len); *pos++ = WLAN_EID_CHANNEL_SWITCH; *pos++ = 3; *pos++ = 0x0; @@ -760,6 +766,37 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) pos += 2; put_unaligned_le16(ifmsh->pre_value, pos); pos += 2; + + switch (csa->settings.chandef.width) { + case NL80211_CHAN_WIDTH_40: + ie_len = 2 + sizeof(struct ieee80211_sec_chan_offs_ie); + pos = skb_put_zero(skb, ie_len); + + *pos++ = WLAN_EID_SECONDARY_CHANNEL_OFFSET; /* EID */ + *pos++ = 1; /* len */ + ct = cfg80211_get_chandef_type(&csa->settings.chandef); + if (ct == NL80211_CHAN_HT40PLUS) + *pos++ = IEEE80211_HT_PARAM_CHA_SEC_ABOVE; + else + *pos++ = IEEE80211_HT_PARAM_CHA_SEC_BELOW; + break; + case NL80211_CHAN_WIDTH_80: + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_160: + /* Channel Switch Wrapper + Wide Bandwidth CSA IE */ + ie_len = 2 + 2 + + sizeof(struct ieee80211_wide_bw_chansw_ie); + pos = skb_put_zero(skb, ie_len); + + *pos++ = WLAN_EID_CHANNEL_SWITCH_WRAPPER; /* EID */ + *pos++ = 5; /* len */ + /* put sub IE */ + chandef = &csa->settings.chandef; + ieee80211_ie_build_wide_bw_cs(pos, chandef); + break; + default: + break; + } } rcu_read_unlock(); @@ -916,6 +953,21 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) ieee80211_configure_filter(local); } +static void ieee80211_mesh_csa_mark_radar(struct ieee80211_sub_if_data *sdata) +{ + int err; + + /* if the current channel is a DFS channel, mark the channel as + * unavailable. + */ + err = cfg80211_chandef_dfs_required(sdata->local->hw.wiphy, + &sdata->vif.bss_conf.chandef, + NL80211_IFTYPE_MESH_POINT); + if (err > 0) + cfg80211_radar_event(sdata->local->hw.wiphy, + &sdata->vif.bss_conf.chandef, GFP_ATOMIC); +} + static bool ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems, bool beacon) @@ -933,19 +985,20 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, if (!sband) return false; - sta_flags = IEEE80211_STA_DISABLE_VHT; + sta_flags = 0; switch (sdata->vif.bss_conf.chandef.width) { case NL80211_CHAN_WIDTH_20_NOHT: sta_flags |= IEEE80211_STA_DISABLE_HT; case NL80211_CHAN_WIDTH_20: sta_flags |= IEEE80211_STA_DISABLE_40MHZ; + case NL80211_CHAN_WIDTH_40: + sta_flags |= IEEE80211_STA_DISABLE_VHT; break; default: break; } memset(¶ms, 0, sizeof(params)); - memset(&csa_ie, 0, sizeof(csa_ie)); err = ieee80211_parse_ch_switch_ie(sdata, elems, sband->band, sta_flags, sdata->vif.addr, &csa_ie); @@ -954,11 +1007,19 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, if (err) return false; + /* Mark the channel unavailable if the reason for the switch is + * regulatory. + */ + if (csa_ie.reason_code == WLAN_REASON_MESH_CHAN_REGULATORY) + ieee80211_mesh_csa_mark_radar(sdata); + params.chandef = csa_ie.chandef; params.count = csa_ie.count; if (!cfg80211_chandef_usable(sdata->local->hw.wiphy, ¶ms.chandef, - IEEE80211_CHAN_DISABLED)) { + IEEE80211_CHAN_DISABLED) || + !cfg80211_reg_can_beacon(sdata->local->hw.wiphy, ¶ms.chandef, + NL80211_IFTYPE_MESH_POINT)) { sdata_info(sdata, "mesh STA %pM switches to unsupported channel (%d MHz, width:%d, CF1/2: %d/%d MHz), aborting\n", sdata->vif.addr, @@ -974,9 +1035,16 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, NL80211_IFTYPE_MESH_POINT); if (err < 0) return false; - if (err > 0) - /* TODO: DFS not (yet) supported */ + if (err > 0 && !ifmsh->userspace_handles_dfs) { + sdata_info(sdata, + "mesh STA %pM switches to channel requiring DFS (%d MHz, width:%d, CF1/2: %d/%d MHz), aborting\n", + sdata->vif.addr, + params.chandef.chan->center_freq, + params.chandef.width, + params.chandef.center_freq1, + params.chandef.center_freq2); return false; + } params.radar_required = err; @@ -1057,8 +1125,8 @@ ieee80211_mesh_rx_probe_req(struct ieee80211_sub_if_data *sdata, goto out; skb_reserve(presp, local->tx_headroom); - memcpy(skb_put(presp, bcn->head_len), bcn->head, bcn->head_len); - memcpy(skb_put(presp, bcn->tail_len), bcn->tail, bcn->tail_len); + skb_put_data(presp, bcn->head, bcn->head_len); + skb_put_data(presp, bcn->tail, bcn->tail_len); hdr = (struct ieee80211_mgmt *) presp->data; hdr->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_RESP); @@ -1197,7 +1265,7 @@ static int mesh_fwd_csa_frame(struct ieee80211_sub_if_data *sdata, if (!skb) return -ENOMEM; skb_reserve(skb, local->tx_headroom); - mgmt_fwd = (struct ieee80211_mgmt *) skb_put(skb, len); + mgmt_fwd = skb_put(skb, len); /* offset_ttl is based on whether the secondary channel * offset is available or not. Subtract 1 from the mesh TTL @@ -1233,7 +1301,7 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata, pos = mgmt->u.action.u.chan_switch.variable; baselen = offsetof(struct ieee80211_mgmt, u.action.u.chan_switch.variable); - ieee802_11_parse_elems(pos, len - baselen, false, &elems); + ieee802_11_parse_elems(pos, len - baselen, true, &elems); ifmsh->chsw_ttl = elems.mesh_chansw_params_ie->mesh_ttl; if (!--ifmsh->chsw_ttl) diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 4005edd71fe8..d8bbd0d2225a 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -120,8 +120,7 @@ static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags, if (!skb) return -1; skb_reserve(skb, local->tx_headroom); - mgmt = (struct ieee80211_mgmt *) skb_put(skb, hdr_len); - memset(mgmt, 0, hdr_len); + mgmt = skb_put_zero(skb, hdr_len); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); @@ -257,8 +256,7 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, if (!skb) return -1; skb_reserve(skb, local->tx_headroom + sdata->encrypt_headroom); - mgmt = (struct ieee80211_mgmt *) skb_put(skb, hdr_len); - memset(mgmt, 0, hdr_len); + mgmt = skb_put_zero(skb, hdr_len); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 1131cd504a15..f69c6c38ca43 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -242,8 +242,7 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, return err; info = IEEE80211_SKB_CB(skb); skb_reserve(skb, local->tx_headroom); - mgmt = (struct ieee80211_mgmt *) skb_put(skb, hdr_len); - memset(mgmt, 0, hdr_len); + mgmt = skb_put_zero(skb, hdr_len); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); memcpy(mgmt->da, da, ETH_ALEN); @@ -264,8 +263,7 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, band = sband->band; /* capability info */ - pos = skb_put(skb, 2); - memset(pos, 0, 2); + pos = skb_put_zero(skb, 2); if (action == WLAN_SP_MESH_PEERING_CONFIRM) { /* AID */ pos = skb_put(skb, 2); diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c index 90a268abea17..d8cd91424175 100644 --- a/net/mac80211/mesh_ps.c +++ b/net/mac80211/mesh_ps.c @@ -30,7 +30,7 @@ static struct sk_buff *mps_qos_null_get(struct sta_info *sta) return NULL; skb_reserve(skb, local->hw.extra_tx_headroom); - nullfunc = (struct ieee80211_hdr *) skb_put(skb, size); + nullfunc = skb_put(skb, size); fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC); ieee80211_fill_mesh_addresses(nullfunc, &fc, sta->sta.addr, sdata->vif.addr); @@ -39,7 +39,7 @@ static struct sk_buff *mps_qos_null_get(struct sta_info *sta) nullfunc->seq_ctrl = 0; /* no address resolution for this frame -> set addr 1 immediately */ memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN); - memset(skb_put(skb, 2), 0, 2); /* append QoS control field */ + skb_put_zero(skb, 2); /* append QoS control field */ ieee80211_mps_set_frame_flags(sdata, sta, nullfunc); return skb; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index cc8e6ea1b27e..b588e593b0ec 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -674,8 +674,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) if (ifmgd->flags & IEEE80211_STA_ENABLE_RRM) capab |= WLAN_CAPABILITY_RADIO_MEASURE; - mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24); - memset(mgmt, 0, 24); + mgmt = skb_put_zero(skb, 24); memcpy(mgmt->da, assoc_data->bss->bssid, ETH_ALEN); memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); memcpy(mgmt->bssid, assoc_data->bss->bssid, ETH_ALEN); @@ -797,8 +796,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) after_ric, ARRAY_SIZE(after_ric), offset); - pos = skb_put(skb, noffset - offset); - memcpy(pos, assoc_data->ie + offset, noffset - offset); + skb_put_data(skb, assoc_data->ie + offset, noffset - offset); offset = noffset; } @@ -835,8 +833,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) noffset = ieee80211_ie_split(assoc_data->ie, assoc_data->ie_len, before_vht, ARRAY_SIZE(before_vht), offset); - pos = skb_put(skb, noffset - offset); - memcpy(pos, assoc_data->ie + offset, noffset - offset); + skb_put_data(skb, assoc_data->ie + offset, noffset - offset); offset = noffset; } @@ -849,8 +846,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) noffset = ieee80211_ie_split_vendor(assoc_data->ie, assoc_data->ie_len, offset); - pos = skb_put(skb, noffset - offset); - memcpy(pos, assoc_data->ie + offset, noffset - offset); + skb_put_data(skb, assoc_data->ie + offset, noffset - offset); offset = noffset; } @@ -869,8 +865,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) /* add any remaining custom (i.e. vendor specific here) IEs */ if (assoc_data->ie_len) { noffset = assoc_data->ie_len; - pos = skb_put(skb, noffset - offset); - memcpy(pos, assoc_data->ie + offset, noffset - offset); + skb_put_data(skb, assoc_data->ie + offset, noffset - offset); } if (assoc_data->fils_kek_len && @@ -949,8 +944,7 @@ static void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, skb_reserve(skb, local->hw.extra_tx_headroom); - nullfunc = (struct ieee80211_hdr *) skb_put(skb, 30); - memset(nullfunc, 0, 30); + nullfunc = skb_put_zero(skb, 30); fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC | IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS); nullfunc->frame_control = fc; @@ -1122,7 +1116,6 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, return; current_band = cbss->channel->band; - memset(&csa_ie, 0, sizeof(csa_ie)); res = ieee80211_parse_ch_switch_ie(sdata, elems, current_band, ifmgd->flags, ifmgd->associated->bssid, &csa_ie); diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index eede5c6db8d5..f8e7a8bbc618 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -885,8 +885,7 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, } skb_reserve(skb, local->hw.extra_tx_headroom); - data = skb_put(skb, params->len); - memcpy(data, params->buf, params->len); + data = skb_put_data(skb, params->buf, params->len); /* Update CSA counters */ if (sdata->vif.csa_active && diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index ea1f4315c521..76f303fda3ed 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -943,6 +943,8 @@ int rate_control_set_rates(struct ieee80211_hw *hw, drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta); + ieee80211_sta_set_expected_throughput(pubsta, sta_get_expected_throughput(sta)); + return 0; } EXPORT_SYMBOL(rate_control_set_rates); @@ -991,4 +993,3 @@ void rate_control_deinitialize(struct ieee80211_local *local) local->rate_ctrl = NULL; rate_control_free(local, ref); } - diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3674fe3d67dc..70e9d2ca8bbe 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -237,7 +237,6 @@ static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata, if (!skb) return; - skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME; skb_queue_tail(&sdata->skb_queue, skb); ieee80211_queue_work(&sdata->local->hw, &sdata->work); } @@ -274,7 +273,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, if (!(has_fcs && ieee80211_hw_check(&local->hw, RX_INCLUDES_FCS))) mpdulen += FCS_LEN; - rthdr = (struct ieee80211_radiotap_header *)skb_push(skb, rtap_len); + rthdr = skb_push(skb, rtap_len); memset(rthdr, 0, rtap_len - rtap.len - rtap.pad); it_present = &rthdr->it_present; @@ -1217,7 +1216,6 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, /* if this mpdu is fragmented - terminate rx aggregation session */ sc = le16_to_cpu(hdr->seq_ctrl); if (sc & IEEE80211_SCTL_FRAG) { - skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME; skb_queue_tail(&rx->sdata->skb_queue, skb); ieee80211_queue_work(&local->hw, &rx->sdata->work); return; @@ -2100,7 +2098,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) } } while ((skb = __skb_dequeue(&entry->skb_list))) { - memcpy(skb_put(rx->skb, skb->len), skb->data, skb->len); + skb_put_data(rx->skb, skb->data, skb->len); dev_kfree_skb(skb); } @@ -2762,8 +2760,7 @@ static void ieee80211_process_sa_query_req(struct ieee80211_sub_if_data *sdata, return; skb_reserve(skb, local->hw.extra_tx_headroom); - resp = (struct ieee80211_mgmt *) skb_put(skb, 24); - memset(resp, 0, 24); + resp = skb_put_zero(skb, 24); memcpy(resp->da, mgmt->sa, ETH_ALEN); memcpy(resp->sa, sdata->vif.addr, ETH_ALEN); memcpy(resp->bssid, sdata->u.mgd.bssid, ETH_ALEN); @@ -3104,7 +3101,6 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) return RX_QUEUED; queue: - rx->skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME; skb_queue_tail(&sdata->skb_queue, rx->skb); ieee80211_queue_work(&local->hw, &sdata->work); if (rx->sta) @@ -3250,7 +3246,6 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx) } /* queue up frame and kick off work to process it */ - rx->skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME; skb_queue_tail(&sdata->skb_queue, rx->skb); ieee80211_queue_work(&rx->local->hw, &sdata->work); if (rx->sta) diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index 0782e486fe89..ee0181778a42 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -36,6 +36,8 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, const struct ieee80211_wide_bw_chansw_ie *wide_bw_chansw_ie; int secondary_channel_offset = -1; + memset(csa_ie, 0, sizeof(*csa_ie)); + sec_chan_offs = elems->sec_chan_offs; wide_bw_chansw_ie = elems->wide_bw_chansw_ie; @@ -76,6 +78,11 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, csa_ie->mode = elems->mesh_chansw_params_ie->mesh_flags; csa_ie->pre_value = le16_to_cpu( elems->mesh_chansw_params_ie->mesh_pre_value); + + if (elems->mesh_chansw_params_ie->mesh_flags & + WLAN_EID_CHAN_SWITCH_PARAM_REASON) + csa_ie->reason_code = le16_to_cpu( + elems->mesh_chansw_params_ie->mesh_reason); } new_freq = ieee80211_channel_to_frequency(new_chan_no, new_band); @@ -186,8 +193,7 @@ static void ieee80211_send_refuse_measurement_request(struct ieee80211_sub_if_da return; skb_reserve(skb, local->hw.extra_tx_headroom); - msr_report = (struct ieee80211_mgmt *)skb_put(skb, 24); - memset(msr_report, 0, 24); + msr_report = skb_put_zero(skb, 24); memcpy(msr_report->da, da, ETH_ALEN); memcpy(msr_report->sa, sdata->vif.addr, ETH_ALEN); memcpy(msr_report->bssid, bssid, ETH_ALEN); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 403e3cc58b57..69615016d5bf 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -20,6 +20,7 @@ #include <linux/timer.h> #include <linux/rtnetlink.h> +#include <net/codel.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "driver-ops.h" @@ -425,6 +426,11 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->sta.max_rc_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_BA; + sta->cparams.ce_threshold = CODEL_DISABLED_THRESHOLD; + sta->cparams.target = MS2TIME(20); + sta->cparams.interval = MS2TIME(100); + sta->cparams.ecn = true; + sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr); return sta; @@ -1306,7 +1312,7 @@ static void ieee80211_send_null_response(struct sta_info *sta, int tid, skb_reserve(skb, local->hw.extra_tx_headroom); - nullfunc = (void *) skb_put(skb, size); + nullfunc = skb_put(skb, size); nullfunc->frame_control = fc; nullfunc->duration_id = 0; memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN); @@ -2310,3 +2316,27 @@ unsigned long ieee80211_sta_last_active(struct sta_info *sta) return stats->last_rx; return sta->status_stats.last_ack; } + +static void sta_update_codel_params(struct sta_info *sta, u32 thr) +{ + if (!sta->sdata->local->ops->wake_tx_queue) + return; + + if (thr && thr < STA_SLOW_THRESHOLD * sta->local->num_sta) { + sta->cparams.target = MS2TIME(50); + sta->cparams.interval = MS2TIME(300); + sta->cparams.ecn = false; + } else { + sta->cparams.target = MS2TIME(20); + sta->cparams.interval = MS2TIME(100); + sta->cparams.ecn = true; + } +} + +void ieee80211_sta_set_expected_throughput(struct ieee80211_sta *pubsta, + u32 thr) +{ + struct sta_info *sta = container_of(pubsta, struct sta_info, sta); + + sta_update_codel_params(sta, thr); +} diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index ea0747d6a6da..3acbdfa9f649 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -233,6 +233,8 @@ struct tid_ampdu_rx { * RX timer expired until the work for it runs * @tid_rx_stop_requested: bitmap indicating which BA sessions per TID the * driver requested to close until the work for it runs + * @tid_rx_manage_offl: bitmap indicating which BA sessions were requested + * to be treated as started/stopped due to offloading * @agg_session_valid: bitmap indicating which TID has a rx BA session open on * @unexpected_agg: bitmap indicating which TID already sent a delBA due to * unexpected aggregation related frames outside a session @@ -250,6 +252,7 @@ struct sta_ampdu_mlme { u8 tid_rx_token[IEEE80211_NUM_TIDS]; unsigned long tid_rx_timer_expired[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; unsigned long tid_rx_stop_requested[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; + unsigned long tid_rx_manage_offl[BITS_TO_LONGS(2 * IEEE80211_NUM_TIDS)]; unsigned long agg_session_valid[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; unsigned long unexpected_agg[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; /* tx */ @@ -396,6 +399,14 @@ struct ieee80211_sta_rx_stats { }; /** + * The bandwidth threshold below which the per-station CoDel parameters will be + * scaled to be more lenient (to prevent starvation of slow stations). This + * value will be scaled by the number of active stations when it is being + * applied. + */ +#define STA_SLOW_THRESHOLD 6000 /* 6 Mbps */ + +/** * struct sta_info - STA information * * This structure collects information about a station that @@ -448,6 +459,7 @@ struct ieee80211_sta_rx_stats { * @known_smps_mode: the smps_mode the client thinks we are in. Relevant for * AP only. * @cipher_scheme: optional cipher scheme for this station + * @cparams: CoDel parameters for this station. * @reserved_tid: reserved TID (if any, otherwise IEEE80211_TID_UNRESERVED) * @fast_tx: TX fastpath information * @fast_rx: RX fastpath information @@ -551,6 +563,8 @@ struct sta_info { enum ieee80211_smps_mode known_smps_mode; const struct ieee80211_cipher_scheme *cipher_scheme; + struct codel_params cparams; + u8 reserved_tid; struct cfg80211_chan_def tdls_chandef; diff --git a/net/mac80211/status.c b/net/mac80211/status.c index be47ac5cd8c8..da7427a41529 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -288,7 +288,7 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, unsigned char *pos; u16 txflags; - rthdr = (struct ieee80211_radiotap_header *) skb_push(skb, rtap_len); + rthdr = skb_push(skb, rtap_len); memset(rthdr, 0, rtap_len); rthdr->it_len = cpu_to_le16(rtap_len); @@ -546,6 +546,8 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, skb->wifi_acked_valid = 1; skb->wifi_acked = acked; } + + ieee80211_led_tx(local); } /* @@ -823,8 +825,6 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, } } - ieee80211_led_tx(local); - /* SNMP counters * Fragments are passed to low-level drivers as separate skbs, so these * are actually fragments, not frames. Update frame counters only for diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index f20dcf1b1830..91093d4a2f84 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -49,7 +49,7 @@ static void ieee80211_tdls_add_ext_capab(struct ieee80211_sub_if_data *sdata, !ifmgd->tdls_wider_bw_prohibited; struct ieee80211_supported_band *sband = ieee80211_get_sband(sdata); bool vht = sband && sband->vht_cap.vht_supported; - u8 *pos = (void *)skb_put(skb, 10); + u8 *pos = skb_put(skb, 10); *pos++ = WLAN_EID_EXT_CAPABILITY; *pos++ = 8; /* len */ @@ -168,7 +168,7 @@ static void ieee80211_tdls_add_oper_classes(struct ieee80211_sub_if_data *sdata, static void ieee80211_tdls_add_bss_coex_ie(struct sk_buff *skb) { - u8 *pos = (void *)skb_put(skb, 3); + u8 *pos = skb_put(skb, 3); *pos++ = WLAN_EID_BSS_COEX_2040; *pos++ = 1; /* len */ @@ -209,7 +209,7 @@ static void ieee80211_tdls_add_link_ie(struct ieee80211_sub_if_data *sdata, rsp_addr = sdata->vif.addr; } - lnkid = (void *)skb_put(skb, sizeof(struct ieee80211_tdls_lnkie)); + lnkid = skb_put(skb, sizeof(struct ieee80211_tdls_lnkie)); lnkid->ie_type = WLAN_EID_LINK_ID; lnkid->ie_len = sizeof(struct ieee80211_tdls_lnkie) - 2; @@ -223,7 +223,7 @@ static void ieee80211_tdls_add_aid(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - u8 *pos = (void *)skb_put(skb, 4); + u8 *pos = skb_put(skb, 4); *pos++ = WLAN_EID_AID; *pos++ = 2; /* len */ @@ -271,8 +271,7 @@ static void ieee80211_tdls_add_wmm_param_ie(struct ieee80211_sub_if_data *sdata, struct ieee80211_tx_queue_params *txq; int i; - wmm = (void *)skb_put(skb, sizeof(*wmm)); - memset(wmm, 0, sizeof(*wmm)); + wmm = skb_put_zero(skb, sizeof(*wmm)); wmm->element_id = WLAN_EID_VENDOR_SPECIFIC; wmm->len = sizeof(*wmm) - 2; @@ -389,8 +388,7 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, before_ext_cap, ARRAY_SIZE(before_ext_cap), offset); - pos = skb_put(skb, noffset - offset); - memcpy(pos, extra_ies + offset, noffset - offset); + skb_put_data(skb, extra_ies + offset, noffset - offset); offset = noffset; } @@ -419,8 +417,7 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, before_ht_cap, ARRAY_SIZE(before_ht_cap), offset); - pos = skb_put(skb, noffset - offset); - memcpy(pos, extra_ies + offset, noffset - offset); + skb_put_data(skb, extra_ies + offset, noffset - offset); offset = noffset; } @@ -491,8 +488,7 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, before_vht_cap, ARRAY_SIZE(before_vht_cap), offset); - pos = skb_put(skb, noffset - offset); - memcpy(pos, extra_ies + offset, noffset - offset); + skb_put_data(skb, extra_ies + offset, noffset - offset); offset = noffset; } @@ -533,8 +529,7 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, /* add any remaining IEs */ if (extra_ies_len) { noffset = extra_ies_len; - pos = skb_put(skb, noffset - offset); - memcpy(pos, extra_ies + offset, noffset - offset); + skb_put_data(skb, extra_ies + offset, noffset - offset); } } @@ -576,8 +571,7 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata, before_qos, ARRAY_SIZE(before_qos), offset); - pos = skb_put(skb, noffset - offset); - memcpy(pos, extra_ies + offset, noffset - offset); + skb_put_data(skb, extra_ies + offset, noffset - offset); offset = noffset; } @@ -597,8 +591,7 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata, before_ht_op, ARRAY_SIZE(before_ht_op), offset); - pos = skb_put(skb, noffset - offset); - memcpy(pos, extra_ies + offset, noffset - offset); + skb_put_data(skb, extra_ies + offset, noffset - offset); offset = noffset; } @@ -639,8 +632,7 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata, /* add any remaining IEs */ if (extra_ies_len) { noffset = extra_ies_len; - pos = skb_put(skb, noffset - offset); - memcpy(pos, extra_ies + offset, noffset - offset); + skb_put_data(skb, extra_ies + offset, noffset - offset); } } @@ -653,7 +645,6 @@ ieee80211_tdls_add_chan_switch_req_ies(struct ieee80211_sub_if_data *sdata, { struct ieee80211_tdls_data *tf; size_t offset = 0, noffset; - u8 *pos; if (WARN_ON_ONCE(!chandef)) return; @@ -671,8 +662,7 @@ ieee80211_tdls_add_chan_switch_req_ies(struct ieee80211_sub_if_data *sdata, before_lnkie, ARRAY_SIZE(before_lnkie), offset); - pos = skb_put(skb, noffset - offset); - memcpy(pos, extra_ies + offset, noffset - offset); + skb_put_data(skb, extra_ies + offset, noffset - offset); offset = noffset; } @@ -681,8 +671,7 @@ ieee80211_tdls_add_chan_switch_req_ies(struct ieee80211_sub_if_data *sdata, /* add any remaining IEs */ if (extra_ies_len) { noffset = extra_ies_len; - pos = skb_put(skb, noffset - offset); - memcpy(pos, extra_ies + offset, noffset - offset); + skb_put_data(skb, extra_ies + offset, noffset - offset); } } @@ -697,7 +686,7 @@ ieee80211_tdls_add_chan_switch_resp_ies(struct ieee80211_sub_if_data *sdata, ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator); if (extra_ies_len) - memcpy(skb_put(skb, extra_ies_len), extra_ies, extra_ies_len); + skb_put_data(skb, extra_ies, extra_ies_len); } static void ieee80211_tdls_add_ies(struct ieee80211_sub_if_data *sdata, @@ -727,8 +716,7 @@ static void ieee80211_tdls_add_ies(struct ieee80211_sub_if_data *sdata, case WLAN_TDLS_TEARDOWN: case WLAN_TDLS_DISCOVERY_REQUEST: if (extra_ies_len) - memcpy(skb_put(skb, extra_ies_len), extra_ies, - extra_ies_len); + skb_put_data(skb, extra_ies, extra_ies_len); if (status_code == 0 || action_code == WLAN_TDLS_TEARDOWN) ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator); break; @@ -756,7 +744,7 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_tdls_data *tf; - tf = (void *)skb_put(skb, offsetof(struct ieee80211_tdls_data, u)); + tf = skb_put(skb, offsetof(struct ieee80211_tdls_data, u)); memcpy(tf->da, peer, ETH_ALEN); memcpy(tf->sa, sdata->vif.addr, ETH_ALEN); @@ -838,8 +826,7 @@ ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_mgmt *mgmt; - mgmt = (void *)skb_put(skb, 24); - memset(mgmt, 0, 24); + mgmt = skb_put_zero(skb, 24); memcpy(mgmt->da, peer, ETH_ALEN); memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); memcpy(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN); diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 0d645bc148d0..3d9ac17af407 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -92,16 +92,19 @@ __field(u16, ssn) \ __field(u8, buf_size) \ __field(bool, amsdu) \ - __field(u16, timeout) + __field(u16, timeout) \ + __field(u16, action) #define AMPDU_ACTION_ASSIGN STA_NAMED_ASSIGN(params->sta); \ __entry->tid = params->tid; \ __entry->ssn = params->ssn; \ __entry->buf_size = params->buf_size; \ __entry->amsdu = params->amsdu; \ - __entry->timeout = params->timeout; -#define AMPDU_ACTION_PR_FMT STA_PR_FMT " tid %d, ssn %d, buf_size %u, amsdu %d, timeout %d" + __entry->timeout = params->timeout; \ + __entry->action = params->action; +#define AMPDU_ACTION_PR_FMT STA_PR_FMT " tid %d, ssn %d, buf_size %u, amsdu %d, timeout %d action %d" #define AMPDU_ACTION_PR_ARG STA_PR_ARG, __entry->tid, __entry->ssn, \ - __entry->buf_size, __entry->amsdu, __entry->timeout + __entry->buf_size, __entry->amsdu, __entry->timeout, \ + __entry->action /* * Tracing for driver callbacks. diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 04b22f8982fe..8858f4f185e9 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -903,8 +903,8 @@ static int ieee80211_fragment(struct ieee80211_tx_data *tx, tmp->dev = skb->dev; /* copy header and data */ - memcpy(skb_put(tmp, hdrlen), skb->data, hdrlen); - memcpy(skb_put(tmp, fraglen), skb->data + pos, fraglen); + skb_put_data(tmp, skb->data, hdrlen); + skb_put_data(tmp, skb->data + pos, fraglen); pos += fraglen; } @@ -1340,9 +1340,16 @@ static struct sk_buff *fq_tin_dequeue_func(struct fq *fq, local = container_of(fq, struct ieee80211_local, fq); txqi = container_of(tin, struct txq_info, tin); - cparams = &local->cparams; cstats = &txqi->cstats; + if (txqi->txq.sta) { + struct sta_info *sta = container_of(txqi->txq.sta, + struct sta_info, sta); + cparams = &sta->cparams; + } else { + cparams = &local->cparams; + } + if (flow == &txqi->def_flow) cvars = &txqi->def_cvars; else @@ -2701,7 +2708,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, if (ieee80211_is_data_qos(fc)) { __le16 *qos_control; - qos_control = (__le16 *) skb_push(skb, 2); + qos_control = skb_push(skb, 2); memcpy(skb_push(skb, hdrlen - 2), &hdr, hdrlen - 2); /* * Maybe we could actually set some fields here, for now just @@ -3037,7 +3044,7 @@ static bool ieee80211_amsdu_realloc_pad(struct ieee80211_local *local, if (padding) { *subframe_len += padding; - memset(skb_put(skb, padding), 0, padding); + skb_put_zero(skb, padding); } return true; @@ -3340,7 +3347,7 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, } memcpy(ð, skb->data, ETH_HLEN - 2); - hdr = (void *)skb_push(skb, extra_head); + hdr = skb_push(skb, extra_head); memcpy(skb->data, fast_tx->hdr, fast_tx->hdr_len); memcpy(skb->data + fast_tx->da_offs, eth.h_dest, ETH_ALEN); memcpy(skb->data + fast_tx->sa_offs, eth.h_source, ETH_ALEN); @@ -3867,7 +3874,7 @@ static void __ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, ps->dtim_count--; } - tim = pos = (u8 *) skb_put(skb, 6); + tim = pos = skb_put(skb, 6); *pos++ = WLAN_EID_TIM; *pos++ = 4; *pos++ = ps->dtim_count; @@ -4125,8 +4132,7 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, goto out; skb_reserve(skb, local->tx_headroom); - memcpy(skb_put(skb, beacon->head_len), beacon->head, - beacon->head_len); + skb_put_data(skb, beacon->head, beacon->head_len); ieee80211_beacon_add_tim(sdata, &ap->ps, skb, is_template); @@ -4140,8 +4146,8 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, } if (beacon->tail) - memcpy(skb_put(skb, beacon->tail_len), - beacon->tail, beacon->tail_len); + skb_put_data(skb, beacon->tail, + beacon->tail_len); } else goto out; } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { @@ -4164,8 +4170,7 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (!skb) goto out; skb_reserve(skb, local->tx_headroom); - memcpy(skb_put(skb, beacon->head_len), beacon->head, - beacon->head_len); + skb_put_data(skb, beacon->head, beacon->head_len); hdr = (struct ieee80211_hdr *) skb->data; hdr->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | @@ -4200,8 +4205,7 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (!skb) goto out; skb_reserve(skb, local->tx_headroom); - memcpy(skb_put(skb, beacon->head_len), beacon->head, - beacon->head_len); + skb_put_data(skb, beacon->head, beacon->head_len); ieee80211_beacon_add_tim(sdata, &ifmsh->ps, skb, is_template); if (offs) { @@ -4209,8 +4213,7 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, offs->tim_length = skb->len - beacon->head_len; } - memcpy(skb_put(skb, beacon->tail_len), beacon->tail, - beacon->tail_len); + skb_put_data(skb, beacon->tail, beacon->tail_len); } else { WARN_ON(1); goto out; @@ -4330,7 +4333,7 @@ struct sk_buff *ieee80211_proberesp_get(struct ieee80211_hw *hw, if (!skb) goto out; - memcpy(skb_put(skb, presp->len), presp->data, presp->len); + skb_put_data(skb, presp->data, presp->len); hdr = (struct ieee80211_hdr *) skb->data; memset(hdr->addr1, 0, sizeof(hdr->addr1)); @@ -4363,8 +4366,7 @@ struct sk_buff *ieee80211_pspoll_get(struct ieee80211_hw *hw, skb_reserve(skb, local->hw.extra_tx_headroom); - pspoll = (struct ieee80211_pspoll *) skb_put(skb, sizeof(*pspoll)); - memset(pspoll, 0, sizeof(*pspoll)); + pspoll = skb_put_zero(skb, sizeof(*pspoll)); pspoll->frame_control = cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_PSPOLL); pspoll->aid = cpu_to_le16(ifmgd->aid); @@ -4401,9 +4403,7 @@ struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw, skb_reserve(skb, local->hw.extra_tx_headroom); - nullfunc = (struct ieee80211_hdr_3addr *) skb_put(skb, - sizeof(*nullfunc)); - memset(nullfunc, 0, sizeof(*nullfunc)); + nullfunc = skb_put_zero(skb, sizeof(*nullfunc)); nullfunc->frame_control = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC | IEEE80211_FCTL_TODS); @@ -4435,8 +4435,7 @@ struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw, skb_reserve(skb, local->hw.extra_tx_headroom); - hdr = (struct ieee80211_hdr_3addr *) skb_put(skb, sizeof(*hdr)); - memset(hdr, 0, sizeof(*hdr)); + hdr = skb_put_zero(skb, sizeof(*hdr)); hdr->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_REQ); eth_broadcast_addr(hdr->addr1); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index ac9ac6c35594..259698de569f 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1242,8 +1242,7 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, skb_reserve(skb, local->hw.extra_tx_headroom + IEEE80211_WEP_IV_LEN); - mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24 + 6); - memset(mgmt, 0, 24 + 6); + mgmt = skb_put_zero(skb, 24 + 6); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_AUTH); memcpy(mgmt->da, da, ETH_ALEN); @@ -1253,7 +1252,7 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, mgmt->u.auth.auth_transaction = cpu_to_le16(transaction); mgmt->u.auth.status_code = cpu_to_le16(status); if (extra) - memcpy(skb_put(skb, extra_len), extra, extra_len); + skb_put_data(skb, extra, extra_len); if (auth_alg == WLAN_AUTH_SHARED_KEY && transaction == 3) { mgmt->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); @@ -1293,8 +1292,7 @@ void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, skb_reserve(skb, local->hw.extra_tx_headroom); /* copy in frame */ - memcpy(skb_put(skb, IEEE80211_DEAUTH_FRAME_LEN), - mgmt, IEEE80211_DEAUTH_FRAME_LEN); + skb_put_data(skb, mgmt, IEEE80211_DEAUTH_FRAME_LEN); if (sdata->vif.type != NL80211_IFTYPE_STATION || !(sdata->u.mgd.flags & IEEE80211_STA_MFP_ENABLED)) @@ -2414,6 +2412,35 @@ u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, return pos + sizeof(struct ieee80211_ht_operation); } +void ieee80211_ie_build_wide_bw_cs(u8 *pos, + const struct cfg80211_chan_def *chandef) +{ + *pos++ = WLAN_EID_WIDE_BW_CHANNEL_SWITCH; /* EID */ + *pos++ = 3; /* IE length */ + /* New channel width */ + switch (chandef->width) { + case NL80211_CHAN_WIDTH_80: + *pos++ = IEEE80211_VHT_CHANWIDTH_80MHZ; + break; + case NL80211_CHAN_WIDTH_160: + *pos++ = IEEE80211_VHT_CHANWIDTH_160MHZ; + break; + case NL80211_CHAN_WIDTH_80P80: + *pos++ = IEEE80211_VHT_CHANWIDTH_80P80MHZ; + break; + default: + *pos++ = IEEE80211_VHT_CHANWIDTH_USE_HT; + } + + /* new center frequency segment 0 */ + *pos++ = ieee80211_frequency_to_channel(chandef->center_freq1); + /* new center frequency segment 1 */ + if (chandef->center_freq2) + *pos++ = ieee80211_frequency_to_channel(chandef->center_freq2); + else + *pos++ = 0; +} + u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, const struct cfg80211_chan_def *chandef) { @@ -2964,13 +2991,13 @@ int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata, skb = dev_alloc_skb(local->tx_headroom + hdr_len + 5 + /* channel switch announcement element */ 3 + /* secondary channel offset element */ + 5 + /* wide bandwidth channel switch announcement */ 8); /* mesh channel switch parameters element */ if (!skb) return -ENOMEM; skb_reserve(skb, local->tx_headroom); - mgmt = (struct ieee80211_mgmt *)skb_put(skb, hdr_len); - memset(mgmt, 0, hdr_len); + mgmt = skb_put_zero(skb, hdr_len); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); @@ -3022,6 +3049,13 @@ int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata, pos += 2; } + if (csa_settings->chandef.width == NL80211_CHAN_WIDTH_80 || + csa_settings->chandef.width == NL80211_CHAN_WIDTH_80P80 || + csa_settings->chandef.width == NL80211_CHAN_WIDTH_160) { + skb_put(skb, 5); + ieee80211_ie_build_wide_bw_cs(pos, &csa_settings->chandef); + } + ieee80211_tx_skb(sdata, skb); return 0; } diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index cc19614ff4e6..0d722ea98a1b 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -949,7 +949,7 @@ ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx) if (WARN_ON(skb_tailroom(skb) < sizeof(*mmie))) return TX_DROP; - mmie = (struct ieee80211_mmie *) skb_put(skb, sizeof(*mmie)); + mmie = skb_put(skb, sizeof(*mmie)); mmie->element_id = WLAN_EID_MMIE; mmie->length = sizeof(*mmie) - 2; mmie->key_id = cpu_to_le16(key->conf.keyidx); @@ -993,7 +993,7 @@ ieee80211_crypto_aes_cmac_256_encrypt(struct ieee80211_tx_data *tx) if (WARN_ON(skb_tailroom(skb) < sizeof(*mmie))) return TX_DROP; - mmie = (struct ieee80211_mmie_16 *)skb_put(skb, sizeof(*mmie)); + mmie = skb_put(skb, sizeof(*mmie)); mmie->element_id = WLAN_EID_MMIE; mmie->length = sizeof(*mmie) - 2; mmie->key_id = cpu_to_le16(key->conf.keyidx); @@ -1138,7 +1138,7 @@ ieee80211_crypto_aes_gmac_encrypt(struct ieee80211_tx_data *tx) if (WARN_ON(skb_tailroom(skb) < sizeof(*mmie))) return TX_DROP; - mmie = (struct ieee80211_mmie_16 *)skb_put(skb, sizeof(*mmie)); + mmie = skb_put(skb, sizeof(*mmie)); mmie->element_id = WLAN_EID_MMIE; mmie->length = sizeof(*mmie) - 2; mmie->key_id = cpu_to_le16(key->conf.keyidx); diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 7b05fd1497ce..ea4f481839dd 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -684,6 +684,54 @@ errout: return err; } +static int nla_get_via(const struct nlattr *nla, u8 *via_alen, u8 *via_table, + u8 via_addr[], struct netlink_ext_ack *extack) +{ + struct rtvia *via = nla_data(nla); + int err = -EINVAL; + int alen; + + if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) { + NL_SET_ERR_MSG_ATTR(extack, nla, + "Invalid attribute length for RTA_VIA"); + goto errout; + } + alen = nla_len(nla) - + offsetof(struct rtvia, rtvia_addr); + if (alen > MAX_VIA_ALEN) { + NL_SET_ERR_MSG_ATTR(extack, nla, + "Invalid address length for RTA_VIA"); + goto errout; + } + + /* Validate the address family */ + switch (via->rtvia_family) { + case AF_PACKET: + *via_table = NEIGH_LINK_TABLE; + break; + case AF_INET: + *via_table = NEIGH_ARP_TABLE; + if (alen != 4) + goto errout; + break; + case AF_INET6: + *via_table = NEIGH_ND_TABLE; + if (alen != 16) + goto errout; + break; + default: + /* Unsupported address family */ + goto errout; + } + + memcpy(via_addr, via->rtvia_addr, alen); + *via_alen = alen; + err = 0; + +errout: + return err; +} + static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg, struct mpls_route *rt) { @@ -695,8 +743,6 @@ static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg, if (!nh) return -ENOMEM; - err = -EINVAL; - nh->nh_labels = cfg->rc_output_labels; for (i = 0; i < nh->nh_labels; i++) nh->nh_label[i] = cfg->rc_output_label[i]; @@ -720,7 +766,8 @@ errout: static int mpls_nh_build(struct net *net, struct mpls_route *rt, struct mpls_nh *nh, int oif, struct nlattr *via, - struct nlattr *newdst, u8 max_labels) + struct nlattr *newdst, u8 max_labels, + struct netlink_ext_ack *extack) { int err = -ENOMEM; @@ -728,15 +775,15 @@ static int mpls_nh_build(struct net *net, struct mpls_route *rt, goto errout; if (newdst) { - err = nla_get_labels(newdst, max_labels, - &nh->nh_labels, nh->nh_label); + err = nla_get_labels(newdst, max_labels, &nh->nh_labels, + nh->nh_label, extack); if (err) goto errout; } if (via) { err = nla_get_via(via, &nh->nh_via_alen, &nh->nh_via_table, - __mpls_nh_via(rt, nh)); + __mpls_nh_via(rt, nh), extack); if (err) goto errout; } else { @@ -782,7 +829,8 @@ static u8 mpls_count_nexthops(struct rtnexthop *rtnh, int len, nla = nla_find(attrs, attrlen, RTA_NEWDST); if (nla && - nla_get_labels(nla, MAX_NEW_LABELS, &n_labels, NULL) != 0) + nla_get_labels(nla, MAX_NEW_LABELS, &n_labels, + NULL, NULL) != 0) return 0; *max_labels = max_t(u8, *max_labels, n_labels); @@ -802,7 +850,8 @@ static u8 mpls_count_nexthops(struct rtnexthop *rtnh, int len, } static int mpls_nh_build_multi(struct mpls_route_config *cfg, - struct mpls_route *rt, u8 max_labels) + struct mpls_route *rt, u8 max_labels, + struct netlink_ext_ack *extack) { struct rtnexthop *rtnh = cfg->rc_mp; struct nlattr *nla_via, *nla_newdst; @@ -836,7 +885,7 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg, err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh, rtnh->rtnh_ifindex, nla_via, nla_newdst, - max_labels); + max_labels, extack); if (err) goto errout; @@ -855,7 +904,28 @@ errout: return err; } -static int mpls_route_add(struct mpls_route_config *cfg) +static bool mpls_label_ok(struct net *net, unsigned int index, + struct netlink_ext_ack *extack) +{ + /* Reserved labels may not be set */ + if (index < MPLS_LABEL_FIRST_UNRESERVED) { + NL_SET_ERR_MSG(extack, + "Invalid label - must be MPLS_LABEL_FIRST_UNRESERVED or higher"); + return false; + } + + /* The full 20 bit range may not be supported. */ + if (index >= net->mpls.platform_labels) { + NL_SET_ERR_MSG(extack, + "Label >= configured maximum in platform_labels"); + return false; + } + + return true; +} + +static int mpls_route_add(struct mpls_route_config *cfg, + struct netlink_ext_ack *extack) { struct mpls_route __rcu **platform_label; struct net *net = cfg->rc_nlinfo.nl_net; @@ -874,18 +944,15 @@ static int mpls_route_add(struct mpls_route_config *cfg) index = find_free_label(net); } - /* Reserved labels may not be set */ - if (index < MPLS_LABEL_FIRST_UNRESERVED) - goto errout; - - /* The full 20 bit range may not be supported. */ - if (index >= net->mpls.platform_labels) + if (!mpls_label_ok(net, index, extack)) goto errout; /* Append makes no sense with mpls */ err = -EOPNOTSUPP; - if (cfg->rc_nlflags & NLM_F_APPEND) + if (cfg->rc_nlflags & NLM_F_APPEND) { + NL_SET_ERR_MSG(extack, "MPLS does not support route append"); goto errout; + } err = -EEXIST; platform_label = rtnl_dereference(net->mpls.platform_label); @@ -912,8 +979,10 @@ static int mpls_route_add(struct mpls_route_config *cfg) nhs = 1; } - if (nhs == 0) + if (nhs == 0) { + NL_SET_ERR_MSG(extack, "Route does not contain a nexthop"); goto errout; + } err = -ENOMEM; rt = mpls_rt_alloc(nhs, max_via_alen, max_labels); @@ -927,7 +996,7 @@ static int mpls_route_add(struct mpls_route_config *cfg) rt->rt_ttl_propagate = cfg->rc_ttl_propagate; if (cfg->rc_mp) - err = mpls_nh_build_multi(cfg, rt, max_labels); + err = mpls_nh_build_multi(cfg, rt, max_labels, extack); else err = mpls_nh_build_from_cfg(cfg, rt); if (err) @@ -943,7 +1012,8 @@ errout: return err; } -static int mpls_route_del(struct mpls_route_config *cfg) +static int mpls_route_del(struct mpls_route_config *cfg, + struct netlink_ext_ack *extack) { struct net *net = cfg->rc_nlinfo.nl_net; unsigned index; @@ -951,12 +1021,7 @@ static int mpls_route_del(struct mpls_route_config *cfg) index = cfg->rc_label; - /* Reserved labels may not be removed */ - if (index < MPLS_LABEL_FIRST_UNRESERVED) - goto errout; - - /* The full 20 bit range may not be supported */ - if (index >= net->mpls.platform_labels) + if (!mpls_label_ok(net, index, extack)) goto errout; mpls_route_update(net, index, NULL, &cfg->rc_nlinfo); @@ -1541,8 +1606,8 @@ int nla_put_labels(struct sk_buff *skb, int attrtype, } EXPORT_SYMBOL_GPL(nla_put_labels); -int nla_get_labels(const struct nlattr *nla, - u8 max_labels, u8 *labels, u32 label[]) +int nla_get_labels(const struct nlattr *nla, u8 max_labels, u8 *labels, + u32 label[], struct netlink_ext_ack *extack) { unsigned len = nla_len(nla); struct mpls_shim_hdr *nla_label; @@ -1553,13 +1618,18 @@ int nla_get_labels(const struct nlattr *nla, /* len needs to be an even multiple of 4 (the label size). Number * of labels is a u8 so check for overflow. */ - if (len & 3 || len / 4 > 255) + if (len & 3 || len / 4 > 255) { + NL_SET_ERR_MSG_ATTR(extack, nla, + "Invalid length for labels attribute"); return -EINVAL; + } /* Limit the number of new labels allowed */ nla_labels = len/4; - if (nla_labels > max_labels) + if (nla_labels > max_labels) { + NL_SET_ERR_MSG(extack, "Too many labels"); return -EINVAL; + } /* when label == NULL, caller wants number of labels */ if (!label) @@ -1574,8 +1644,29 @@ int nla_get_labels(const struct nlattr *nla, /* Ensure the bottom of stack flag is properly set * and ttl and tc are both clear. */ - if ((dec.bos != bos) || dec.ttl || dec.tc) + if (dec.ttl) { + NL_SET_ERR_MSG_ATTR(extack, nla, + "TTL in label must be 0"); return -EINVAL; + } + + if (dec.tc) { + NL_SET_ERR_MSG_ATTR(extack, nla, + "Traffic class in label must be 0"); + return -EINVAL; + } + + if (dec.bos != bos) { + NL_SET_BAD_ATTR(extack, nla); + if (bos) { + NL_SET_ERR_MSG(extack, + "BOS bit must be set in first label"); + } else { + NL_SET_ERR_MSG(extack, + "BOS bit can only be set in first label"); + } + return -EINVAL; + } switch (dec.label) { case MPLS_LABEL_IMPLNULL: @@ -1583,6 +1674,8 @@ int nla_get_labels(const struct nlattr *nla, * assign and distribute, but which never * actually appears in the encapsulation. */ + NL_SET_ERR_MSG_ATTR(extack, nla, + "Implicit NULL Label (3) can not be used in encapsulation"); return -EINVAL; } @@ -1594,50 +1687,10 @@ out: } EXPORT_SYMBOL_GPL(nla_get_labels); -int nla_get_via(const struct nlattr *nla, u8 *via_alen, - u8 *via_table, u8 via_addr[]) -{ - struct rtvia *via = nla_data(nla); - int err = -EINVAL; - int alen; - - if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) - goto errout; - alen = nla_len(nla) - - offsetof(struct rtvia, rtvia_addr); - if (alen > MAX_VIA_ALEN) - goto errout; - - /* Validate the address family */ - switch (via->rtvia_family) { - case AF_PACKET: - *via_table = NEIGH_LINK_TABLE; - break; - case AF_INET: - *via_table = NEIGH_ARP_TABLE; - if (alen != 4) - goto errout; - break; - case AF_INET6: - *via_table = NEIGH_ND_TABLE; - if (alen != 16) - goto errout; - break; - default: - /* Unsupported address family */ - goto errout; - } - - memcpy(via_addr, via->rtvia_addr, alen); - *via_alen = alen; - err = 0; - -errout: - return err; -} - -static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, - struct mpls_route_config *cfg) +static int rtm_to_route_config(struct sk_buff *skb, + struct nlmsghdr *nlh, + struct mpls_route_config *cfg, + struct netlink_ext_ack *extack) { struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; @@ -1645,35 +1698,54 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, int err; err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy, - NULL); + extack); if (err < 0) goto errout; err = -EINVAL; rtm = nlmsg_data(nlh); - if (rtm->rtm_family != AF_MPLS) + if (rtm->rtm_family != AF_MPLS) { + NL_SET_ERR_MSG(extack, "Invalid address family in rtmsg"); goto errout; - if (rtm->rtm_dst_len != 20) + } + if (rtm->rtm_dst_len != 20) { + NL_SET_ERR_MSG(extack, "rtm_dst_len must be 20 for MPLS"); goto errout; - if (rtm->rtm_src_len != 0) + } + if (rtm->rtm_src_len != 0) { + NL_SET_ERR_MSG(extack, "rtm_src_len must be 0 for MPLS"); goto errout; - if (rtm->rtm_tos != 0) + } + if (rtm->rtm_tos != 0) { + NL_SET_ERR_MSG(extack, "rtm_tos must be 0 for MPLS"); goto errout; - if (rtm->rtm_table != RT_TABLE_MAIN) + } + if (rtm->rtm_table != RT_TABLE_MAIN) { + NL_SET_ERR_MSG(extack, + "MPLS only supports the main route table"); goto errout; + } /* Any value is acceptable for rtm_protocol */ /* As mpls uses destination specific addresses * (or source specific address in the case of multicast) * all addresses have universal scope. */ - if (rtm->rtm_scope != RT_SCOPE_UNIVERSE) + if (rtm->rtm_scope != RT_SCOPE_UNIVERSE) { + NL_SET_ERR_MSG(extack, + "Invalid route scope - MPLS only supports UNIVERSE"); goto errout; - if (rtm->rtm_type != RTN_UNICAST) + } + if (rtm->rtm_type != RTN_UNICAST) { + NL_SET_ERR_MSG(extack, + "Invalid route type - MPLS only supports UNICAST"); goto errout; - if (rtm->rtm_flags != 0) + } + if (rtm->rtm_flags != 0) { + NL_SET_ERR_MSG(extack, "rtm_flags must be 0 for MPLS"); goto errout; + } cfg->rc_label = LABEL_NOT_SPECIFIED; cfg->rc_protocol = rtm->rtm_protocol; @@ -1696,26 +1768,26 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, case RTA_NEWDST: if (nla_get_labels(nla, MAX_NEW_LABELS, &cfg->rc_output_labels, - cfg->rc_output_label)) + cfg->rc_output_label, extack)) goto errout; break; case RTA_DST: { u8 label_count; if (nla_get_labels(nla, 1, &label_count, - &cfg->rc_label)) + &cfg->rc_label, extack)) goto errout; - /* Reserved labels may not be set */ - if (cfg->rc_label < MPLS_LABEL_FIRST_UNRESERVED) + if (!mpls_label_ok(cfg->rc_nlinfo.nl_net, + cfg->rc_label, extack)) goto errout; - break; } case RTA_VIA: { if (nla_get_via(nla, &cfg->rc_via_alen, - &cfg->rc_via_table, cfg->rc_via)) + &cfg->rc_via_table, cfg->rc_via, + extack)) goto errout; break; } @@ -1729,14 +1801,18 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, { u8 ttl_propagate = nla_get_u8(nla); - if (ttl_propagate > 1) + if (ttl_propagate > 1) { + NL_SET_ERR_MSG_ATTR(extack, nla, + "RTA_TTL_PROPAGATE can only be 0 or 1"); goto errout; + } cfg->rc_ttl_propagate = ttl_propagate ? MPLS_TTL_PROP_ENABLED : MPLS_TTL_PROP_DISABLED; break; } default: + NL_SET_ERR_MSG_ATTR(extack, nla, "Unknown attribute"); /* Unsupported attribute */ goto errout; } @@ -1757,11 +1833,11 @@ static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, if (!cfg) return -ENOMEM; - err = rtm_to_route_config(skb, nlh, cfg); + err = rtm_to_route_config(skb, nlh, cfg, extack); if (err < 0) goto out; - err = mpls_route_del(cfg); + err = mpls_route_del(cfg, extack); out: kfree(cfg); @@ -1779,11 +1855,11 @@ static int mpls_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, if (!cfg) return -ENOMEM; - err = rtm_to_route_config(skb, nlh, cfg); + err = rtm_to_route_config(skb, nlh, cfg, extack); if (err < 0) goto out; - err = mpls_route_add(cfg); + err = mpls_route_add(cfg, extack); out: kfree(cfg); @@ -1995,6 +2071,170 @@ errout: rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err); } +static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(in_skb->sk); + u32 portid = NETLINK_CB(in_skb).portid; + u32 in_label = LABEL_NOT_SPECIFIED; + struct nlattr *tb[RTA_MAX + 1]; + u32 labels[MAX_NEW_LABELS]; + struct mpls_shim_hdr *hdr; + unsigned int hdr_size = 0; + struct net_device *dev; + struct mpls_route *rt; + struct rtmsg *rtm, *r; + struct nlmsghdr *nlh; + struct sk_buff *skb; + struct mpls_nh *nh; + u8 n_labels; + int err; + + err = nlmsg_parse(in_nlh, sizeof(*rtm), tb, RTA_MAX, + rtm_mpls_policy, extack); + if (err < 0) + goto errout; + + rtm = nlmsg_data(in_nlh); + + if (tb[RTA_DST]) { + u8 label_count; + + if (nla_get_labels(tb[RTA_DST], 1, &label_count, + &in_label, extack)) { + err = -EINVAL; + goto errout; + } + + if (!mpls_label_ok(net, in_label, extack)) { + err = -EINVAL; + goto errout; + } + } + + rt = mpls_route_input_rcu(net, in_label); + if (!rt) { + err = -ENETUNREACH; + goto errout; + } + + if (rtm->rtm_flags & RTM_F_FIB_MATCH) { + skb = nlmsg_new(lfib_nlmsg_size(rt), GFP_KERNEL); + if (!skb) { + err = -ENOBUFS; + goto errout; + } + + err = mpls_dump_route(skb, portid, in_nlh->nlmsg_seq, + RTM_NEWROUTE, in_label, rt, 0); + if (err < 0) { + /* -EMSGSIZE implies BUG in lfib_nlmsg_size */ + WARN_ON(err == -EMSGSIZE); + goto errout_free; + } + + return rtnl_unicast(skb, net, portid); + } + + if (tb[RTA_NEWDST]) { + if (nla_get_labels(tb[RTA_NEWDST], MAX_NEW_LABELS, &n_labels, + labels, extack) != 0) { + err = -EINVAL; + goto errout; + } + + hdr_size = n_labels * sizeof(struct mpls_shim_hdr); + } + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) { + err = -ENOBUFS; + goto errout; + } + + skb->protocol = htons(ETH_P_MPLS_UC); + + if (hdr_size) { + bool bos; + int i; + + if (skb_cow(skb, hdr_size)) { + err = -ENOBUFS; + goto errout_free; + } + + skb_reserve(skb, hdr_size); + skb_push(skb, hdr_size); + skb_reset_network_header(skb); + + /* Push new labels */ + hdr = mpls_hdr(skb); + bos = true; + for (i = n_labels - 1; i >= 0; i--) { + hdr[i] = mpls_entry_encode(labels[i], + 1, 0, bos); + bos = false; + } + } + + nh = mpls_select_multipath(rt, skb); + if (!nh) { + err = -ENETUNREACH; + goto errout_free; + } + + if (hdr_size) { + skb_pull(skb, hdr_size); + skb_reset_network_header(skb); + } + + nlh = nlmsg_put(skb, portid, in_nlh->nlmsg_seq, + RTM_NEWROUTE, sizeof(*r), 0); + if (!nlh) { + err = -EMSGSIZE; + goto errout_free; + } + + r = nlmsg_data(nlh); + r->rtm_family = AF_MPLS; + r->rtm_dst_len = 20; + r->rtm_src_len = 0; + r->rtm_table = RT_TABLE_MAIN; + r->rtm_type = RTN_UNICAST; + r->rtm_scope = RT_SCOPE_UNIVERSE; + r->rtm_protocol = rt->rt_protocol; + r->rtm_flags = 0; + + if (nla_put_labels(skb, RTA_DST, 1, &in_label)) + goto nla_put_failure; + + if (nh->nh_labels && + nla_put_labels(skb, RTA_NEWDST, nh->nh_labels, + nh->nh_label)) + goto nla_put_failure; + + if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC && + nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), + nh->nh_via_alen)) + goto nla_put_failure; + dev = rtnl_dereference(nh->nh_dev); + if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + + err = rtnl_unicast(skb, net, portid); +errout: + return err; + +nla_put_failure: + nlmsg_cancel(skb, nlh); + err = -EMSGSIZE; +errout_free: + kfree_skb(skb); + return err; +} + static int resize_platform_label_table(struct net *net, size_t limit) { size_t size = sizeof(struct mpls_route *) * limit; @@ -2241,7 +2481,8 @@ static int __init mpls_init(void) rtnl_register(PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, NULL); rtnl_register(PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, NULL); - rtnl_register(PF_MPLS, RTM_GETROUTE, NULL, mpls_dump_routes, NULL); + rtnl_register(PF_MPLS, RTM_GETROUTE, mpls_getroute, mpls_dump_routes, + NULL); rtnl_register(PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf, mpls_netconf_dump_devconf, NULL); err = 0; diff --git a/net/mpls/internal.h b/net/mpls/internal.h index 4db6a5971322..cf65aec2e551 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -203,9 +203,7 @@ static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev) int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels, const u32 label[]); int nla_get_labels(const struct nlattr *nla, u8 max_labels, u8 *labels, - u32 label[]); -int nla_get_via(const struct nlattr *nla, u8 *via_alen, u8 *via_table, - u8 via[]); + u32 label[], struct netlink_ext_ack *extack); bool mpls_output_possible(const struct net_device *dev); unsigned int mpls_dev_mtu(const struct net_device *dev); bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu); diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 369c7a23c86c..6e558a419f60 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -159,7 +159,8 @@ drop: static int mpls_build_state(struct nlattr *nla, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct mpls_iptunnel_encap *tun_encap_info; struct nlattr *tb[MPLS_IPTUNNEL_MAX + 1]; @@ -168,17 +169,18 @@ static int mpls_build_state(struct nlattr *nla, int ret; ret = nla_parse_nested(tb, MPLS_IPTUNNEL_MAX, nla, - mpls_iptunnel_policy, NULL); + mpls_iptunnel_policy, extack); if (ret < 0) return ret; - if (!tb[MPLS_IPTUNNEL_DST]) + if (!tb[MPLS_IPTUNNEL_DST]) { + NL_SET_ERR_MSG(extack, "MPLS_IPTUNNEL_DST attribute is missing"); return -EINVAL; - + } /* determine number of labels */ - if (nla_get_labels(tb[MPLS_IPTUNNEL_DST], - MAX_NEW_LABELS, &n_labels, NULL)) + if (nla_get_labels(tb[MPLS_IPTUNNEL_DST], MAX_NEW_LABELS, + &n_labels, NULL, extack)) return -EINVAL; newts = lwtunnel_state_alloc(sizeof(*tun_encap_info) + @@ -188,7 +190,8 @@ static int mpls_build_state(struct nlattr *nla, tun_encap_info = mpls_lwtunnel_encap(newts); ret = nla_get_labels(tb[MPLS_IPTUNNEL_DST], n_labels, - &tun_encap_info->labels, tun_encap_info->label); + &tun_encap_info->labels, tun_encap_info->label, + extack); if (ret) goto errout; diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c index db7083bfd476..5e03ed190e18 100644 --- a/net/ncsi/ncsi-cmd.c +++ b/net/ncsi/ncsi-cmd.c @@ -66,8 +66,7 @@ static int ncsi_cmd_handler_default(struct sk_buff *skb, { struct ncsi_cmd_pkt *cmd; - cmd = (struct ncsi_cmd_pkt *)skb_put(skb, sizeof(*cmd)); - memset(cmd, 0, sizeof(*cmd)); + cmd = skb_put_zero(skb, sizeof(*cmd)); ncsi_cmd_build_header(&cmd->cmd.common, nca); return 0; @@ -78,8 +77,7 @@ static int ncsi_cmd_handler_sp(struct sk_buff *skb, { struct ncsi_cmd_sp_pkt *cmd; - cmd = (struct ncsi_cmd_sp_pkt *)skb_put(skb, sizeof(*cmd)); - memset(cmd, 0, sizeof(*cmd)); + cmd = skb_put_zero(skb, sizeof(*cmd)); cmd->hw_arbitration = nca->bytes[0]; ncsi_cmd_build_header(&cmd->cmd.common, nca); @@ -91,8 +89,7 @@ static int ncsi_cmd_handler_dc(struct sk_buff *skb, { struct ncsi_cmd_dc_pkt *cmd; - cmd = (struct ncsi_cmd_dc_pkt *)skb_put(skb, sizeof(*cmd)); - memset(cmd, 0, sizeof(*cmd)); + cmd = skb_put_zero(skb, sizeof(*cmd)); cmd->ald = nca->bytes[0]; ncsi_cmd_build_header(&cmd->cmd.common, nca); @@ -104,8 +101,7 @@ static int ncsi_cmd_handler_rc(struct sk_buff *skb, { struct ncsi_cmd_rc_pkt *cmd; - cmd = (struct ncsi_cmd_rc_pkt *)skb_put(skb, sizeof(*cmd)); - memset(cmd, 0, sizeof(*cmd)); + cmd = skb_put_zero(skb, sizeof(*cmd)); ncsi_cmd_build_header(&cmd->cmd.common, nca); return 0; @@ -116,8 +112,7 @@ static int ncsi_cmd_handler_ae(struct sk_buff *skb, { struct ncsi_cmd_ae_pkt *cmd; - cmd = (struct ncsi_cmd_ae_pkt *)skb_put(skb, sizeof(*cmd)); - memset(cmd, 0, sizeof(*cmd)); + cmd = skb_put_zero(skb, sizeof(*cmd)); cmd->mc_id = nca->bytes[0]; cmd->mode = htonl(nca->dwords[1]); ncsi_cmd_build_header(&cmd->cmd.common, nca); @@ -130,8 +125,7 @@ static int ncsi_cmd_handler_sl(struct sk_buff *skb, { struct ncsi_cmd_sl_pkt *cmd; - cmd = (struct ncsi_cmd_sl_pkt *)skb_put(skb, sizeof(*cmd)); - memset(cmd, 0, sizeof(*cmd)); + cmd = skb_put_zero(skb, sizeof(*cmd)); cmd->mode = htonl(nca->dwords[0]); cmd->oem_mode = htonl(nca->dwords[1]); ncsi_cmd_build_header(&cmd->cmd.common, nca); @@ -144,8 +138,7 @@ static int ncsi_cmd_handler_svf(struct sk_buff *skb, { struct ncsi_cmd_svf_pkt *cmd; - cmd = (struct ncsi_cmd_svf_pkt *)skb_put(skb, sizeof(*cmd)); - memset(cmd, 0, sizeof(*cmd)); + cmd = skb_put_zero(skb, sizeof(*cmd)); cmd->vlan = htons(nca->words[0]); cmd->index = nca->bytes[2]; cmd->enable = nca->bytes[3]; @@ -159,8 +152,7 @@ static int ncsi_cmd_handler_ev(struct sk_buff *skb, { struct ncsi_cmd_ev_pkt *cmd; - cmd = (struct ncsi_cmd_ev_pkt *)skb_put(skb, sizeof(*cmd)); - memset(cmd, 0, sizeof(*cmd)); + cmd = skb_put_zero(skb, sizeof(*cmd)); cmd->mode = nca->bytes[0]; ncsi_cmd_build_header(&cmd->cmd.common, nca); @@ -173,8 +165,7 @@ static int ncsi_cmd_handler_sma(struct sk_buff *skb, struct ncsi_cmd_sma_pkt *cmd; int i; - cmd = (struct ncsi_cmd_sma_pkt *)skb_put(skb, sizeof(*cmd)); - memset(cmd, 0, sizeof(*cmd)); + cmd = skb_put_zero(skb, sizeof(*cmd)); for (i = 0; i < 6; i++) cmd->mac[i] = nca->bytes[i]; cmd->index = nca->bytes[6]; @@ -189,8 +180,7 @@ static int ncsi_cmd_handler_ebf(struct sk_buff *skb, { struct ncsi_cmd_ebf_pkt *cmd; - cmd = (struct ncsi_cmd_ebf_pkt *)skb_put(skb, sizeof(*cmd)); - memset(cmd, 0, sizeof(*cmd)); + cmd = skb_put_zero(skb, sizeof(*cmd)); cmd->mode = htonl(nca->dwords[0]); ncsi_cmd_build_header(&cmd->cmd.common, nca); @@ -202,8 +192,7 @@ static int ncsi_cmd_handler_egmf(struct sk_buff *skb, { struct ncsi_cmd_egmf_pkt *cmd; - cmd = (struct ncsi_cmd_egmf_pkt *)skb_put(skb, sizeof(*cmd)); - memset(cmd, 0, sizeof(*cmd)); + cmd = skb_put_zero(skb, sizeof(*cmd)); cmd->mode = htonl(nca->dwords[0]); ncsi_cmd_build_header(&cmd->cmd.common, nca); @@ -215,8 +204,7 @@ static int ncsi_cmd_handler_snfc(struct sk_buff *skb, { struct ncsi_cmd_snfc_pkt *cmd; - cmd = (struct ncsi_cmd_snfc_pkt *)skb_put(skb, sizeof(*cmd)); - memset(cmd, 0, sizeof(*cmd)); + cmd = skb_put_zero(skb, sizeof(*cmd)); cmd->mode = nca->bytes[0]; ncsi_cmd_build_header(&cmd->cmd.common, nca); @@ -343,7 +331,7 @@ int ncsi_xmit_cmd(struct ncsi_cmd_arg *nca) } /* Fill the ethernet header */ - eh = (struct ethhdr *)skb_push(nr->cmd, sizeof(*eh)); + eh = skb_push(nr->cmd, sizeof(*eh)); eh->h_proto = htons(ETH_P_NCSI); eth_broadcast_addr(eh->h_dest); eth_broadcast_addr(eh->h_source); diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index c9b78e7b342f..913380919301 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -70,10 +70,9 @@ obj-$(CONFIG_NETFILTER_SYNPROXY) += nf_synproxy_core.o obj-$(CONFIG_NF_DUP_NETDEV) += nf_dup_netdev.o # nf_tables -nf_tables-objs += nf_tables_core.o nf_tables_api.o nf_tables_trace.o -nf_tables-objs += nft_immediate.o nft_cmp.o nft_range.o -nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o -nf_tables-objs += nft_lookup.o nft_dynset.o +nf_tables-objs := nf_tables_core.o nf_tables_api.o nf_tables_trace.o \ + nft_immediate.o nft_cmp.o nft_range.o nft_bitwise.o \ + nft_byteorder.o nft_payload.o nft_lookup.o nft_dynset.o obj-$(CONFIG_NF_TABLES) += nf_tables.o obj-$(CONFIG_NF_TABLES_INET) += nf_tables_inet.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 552d606e57ca..974cf2a3795a 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -227,114 +227,6 @@ void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, } EXPORT_SYMBOL(nf_unregister_net_hooks); -static LIST_HEAD(nf_hook_list); - -static int _nf_register_hook(struct nf_hook_ops *reg) -{ - struct net *net, *last; - int ret; - - for_each_net(net) { - ret = nf_register_net_hook(net, reg); - if (ret && ret != -ENOENT) - goto rollback; - } - list_add_tail(®->list, &nf_hook_list); - - return 0; -rollback: - last = net; - for_each_net(net) { - if (net == last) - break; - nf_unregister_net_hook(net, reg); - } - return ret; -} - -int nf_register_hook(struct nf_hook_ops *reg) -{ - int ret; - - rtnl_lock(); - ret = _nf_register_hook(reg); - rtnl_unlock(); - - return ret; -} -EXPORT_SYMBOL(nf_register_hook); - -static void _nf_unregister_hook(struct nf_hook_ops *reg) -{ - struct net *net; - - list_del(®->list); - for_each_net(net) - nf_unregister_net_hook(net, reg); -} - -void nf_unregister_hook(struct nf_hook_ops *reg) -{ - rtnl_lock(); - _nf_unregister_hook(reg); - rtnl_unlock(); -} -EXPORT_SYMBOL(nf_unregister_hook); - -int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n) -{ - unsigned int i; - int err = 0; - - for (i = 0; i < n; i++) { - err = nf_register_hook(®[i]); - if (err) - goto err; - } - return err; - -err: - if (i > 0) - nf_unregister_hooks(reg, i); - return err; -} -EXPORT_SYMBOL(nf_register_hooks); - -/* Caller MUST take rtnl_lock() */ -int _nf_register_hooks(struct nf_hook_ops *reg, unsigned int n) -{ - unsigned int i; - int err = 0; - - for (i = 0; i < n; i++) { - err = _nf_register_hook(®[i]); - if (err) - goto err; - } - return err; - -err: - if (i > 0) - _nf_unregister_hooks(reg, i); - return err; -} -EXPORT_SYMBOL(_nf_register_hooks); - -void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) -{ - while (n-- > 0) - nf_unregister_hook(®[n]); -} -EXPORT_SYMBOL(nf_unregister_hooks); - -/* Caller MUST take rtnl_lock */ -void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) -{ - while (n-- > 0) - _nf_unregister_hook(®[n]); -} -EXPORT_SYMBOL(_nf_unregister_hooks); - /* Returns 1 if okfn() needs to be executed by the caller, * -EPERM for NF_DROP, 0 otherwise. Caller must hold rcu_read_lock. */ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, @@ -450,40 +342,9 @@ void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); EXPORT_SYMBOL(nf_nat_decode_session_hook); #endif -static int nf_register_hook_list(struct net *net) -{ - struct nf_hook_ops *elem; - int ret; - - rtnl_lock(); - list_for_each_entry(elem, &nf_hook_list, list) { - ret = nf_register_net_hook(net, elem); - if (ret && ret != -ENOENT) - goto out_undo; - } - rtnl_unlock(); - return 0; - -out_undo: - list_for_each_entry_continue_reverse(elem, &nf_hook_list, list) - nf_unregister_net_hook(net, elem); - rtnl_unlock(); - return ret; -} - -static void nf_unregister_hook_list(struct net *net) -{ - struct nf_hook_ops *elem; - - rtnl_lock(); - list_for_each_entry(elem, &nf_hook_list, list) - nf_unregister_net_hook(net, elem); - rtnl_unlock(); -} - static int __net_init netfilter_net_init(struct net *net) { - int i, h, ret; + int i, h; for (i = 0; i < ARRAY_SIZE(net->nf.hooks); i++) { for (h = 0; h < NF_MAX_HOOKS; h++) @@ -500,16 +361,12 @@ static int __net_init netfilter_net_init(struct net *net) return -ENOMEM; } #endif - ret = nf_register_hook_list(net); - if (ret) - remove_proc_entry("netfilter", net->proc_net); - return ret; + return 0; } static void __net_exit netfilter_net_exit(struct net *net) { - nf_unregister_hook_list(net); remove_proc_entry("netfilter", net->proc_net); } diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index ba6a5516dc7c..e495b5e484b1 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -841,14 +841,16 @@ find_free_id(struct ip_set_net *inst, const char *name, ip_set_id_t *index, static int ip_set_none(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } static int ip_set_create(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *set, *clash = NULL; @@ -989,7 +991,8 @@ ip_set_destroy_set(struct ip_set *set) static int ip_set_destroy(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *s; @@ -1067,7 +1070,8 @@ ip_set_flush_set(struct ip_set *set) static int ip_set_flush(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *s; @@ -1106,7 +1110,8 @@ ip_set_setname2_policy[IPSET_ATTR_CMD_MAX + 1] = { static int ip_set_rename(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *set, *s; @@ -1155,7 +1160,8 @@ out: static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *from, *to; @@ -1428,7 +1434,8 @@ out: static int ip_set_dump(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { if (unlikely(protocol_failed(attr))) return -IPSET_ERR_PROTOCOL; @@ -1513,7 +1520,8 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, static int ip_set_uadd(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *set; @@ -1567,7 +1575,8 @@ static int ip_set_uadd(struct net *net, struct sock *ctnl, struct sk_buff *skb, static int ip_set_udel(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *set; @@ -1621,7 +1630,8 @@ static int ip_set_udel(struct net *net, struct sock *ctnl, struct sk_buff *skb, static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *set; @@ -1656,7 +1666,8 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb, static int ip_set_header(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); const struct ip_set *set; @@ -1712,7 +1723,8 @@ static const struct nla_policy ip_set_type_policy[IPSET_ATTR_CMD_MAX + 1] = { static int ip_set_type(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct sk_buff *skb2; struct nlmsghdr *nlh2; @@ -1770,7 +1782,8 @@ ip_set_protocol_policy[IPSET_ATTR_CMD_MAX + 1] = { static int ip_set_protocol(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct sk_buff *skb2; struct nlmsghdr *nlh2; diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c index 42c3e3ba1b94..3f09cdb42562 100644 --- a/net/netfilter/ipset/ip_set_getport.c +++ b/net/netfilter/ipset/ip_set_getport.c @@ -38,8 +38,8 @@ get_port(const struct sk_buff *skb, int protocol, unsigned int protooff, break; } case IPPROTO_SCTP: { - sctp_sctphdr_t _sh; - const sctp_sctphdr_t *sh; + struct sctphdr _sh; + const struct sctphdr *sh; sh = skb_header_pointer(skb, protooff, sizeof(_sh), &_sh); if (!sh) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index ad99c1ceea6f..e31956b58aba 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1037,9 +1037,9 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, */ static inline int is_sctp_abort(const struct sk_buff *skb, int nh_len) { - sctp_chunkhdr_t *sch, schunk; - sch = skb_header_pointer(skb, nh_len + sizeof(sctp_sctphdr_t), - sizeof(schunk), &schunk); + struct sctp_chunkhdr *sch, schunk; + sch = skb_header_pointer(skb, nh_len + sizeof(struct sctphdr), + sizeof(schunk), &schunk); if (sch == NULL) return 0; if (sch->type == SCTP_CID_ABORT) @@ -1070,9 +1070,9 @@ static inline bool is_new_conn(const struct sk_buff *skb, return th->syn; } case IPPROTO_SCTP: { - sctp_chunkhdr_t *sch, schunk; + struct sctp_chunkhdr *sch, schunk; - sch = skb_header_pointer(skb, iph->len + sizeof(sctp_sctphdr_t), + sch = skb_header_pointer(skb, iph->len + sizeof(struct sctphdr), sizeof(schunk), &schunk); if (sch == NULL) return false; diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 56f8e4b204ff..3ffad4adaddf 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -15,16 +15,15 @@ sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_service *svc; - sctp_chunkhdr_t _schunkh, *sch; - sctp_sctphdr_t *sh, _sctph; + struct sctp_chunkhdr _schunkh, *sch; + struct sctphdr *sh, _sctph; __be16 _ports[2], *ports = NULL; if (likely(!ip_vs_iph_icmp(iph))) { sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph); if (sh) { - sch = skb_header_pointer( - skb, iph->len + sizeof(sctp_sctphdr_t), - sizeof(_schunkh), &_schunkh); + sch = skb_header_pointer(skb, iph->len + sizeof(_sctph), + sizeof(_schunkh), &_schunkh); if (sch && (sch->type == SCTP_CID_INIT || sysctl_sloppy_sctp(ipvs))) ports = &sh->source; @@ -77,7 +76,7 @@ sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, return 1; } -static void sctp_nat_csum(struct sk_buff *skb, sctp_sctphdr_t *sctph, +static void sctp_nat_csum(struct sk_buff *skb, struct sctphdr *sctph, unsigned int sctphoff) { sctph->checksum = sctp_compute_cksum(skb, sctphoff); @@ -88,7 +87,7 @@ static int sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { - sctp_sctphdr_t *sctph; + struct sctphdr *sctph; unsigned int sctphoff = iph->len; bool payload_csum = false; @@ -135,7 +134,7 @@ static int sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { - sctp_sctphdr_t *sctph; + struct sctphdr *sctph; unsigned int sctphoff = iph->len; bool payload_csum = false; @@ -378,7 +377,7 @@ static inline void set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, int direction, const struct sk_buff *skb) { - sctp_chunkhdr_t _sctpch, *sch; + struct sctp_chunkhdr _sctpch, *sch; unsigned char chunk_type; int event, next_state; int ihl, cofs; @@ -389,7 +388,7 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, ihl = ip_hdrlen(skb); #endif - cofs = ihl + sizeof(sctp_sctphdr_t); + cofs = ihl + sizeof(struct sctphdr); sch = skb_header_pointer(skb, cofs, sizeof(_sctpch), &_sctpch); if (sch == NULL) return; @@ -410,7 +409,7 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, (sch->type == SCTP_CID_COOKIE_ACK)) { int clen = ntohs(sch->length); - if (clen >= sizeof(sctp_chunkhdr_t)) { + if (clen >= sizeof(_sctpch)) { sch = skb_header_pointer(skb, cofs + ALIGN(clen, 4), sizeof(_sctpch), &_sctpch); if (sch && sch->type == SCTP_CID_ABORT) diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c index 03d2ccffa9fa..20edd589fe06 100644 --- a/net/netfilter/nf_conntrack_amanda.c +++ b/net/netfilter/nf_conntrack_amanda.c @@ -197,8 +197,8 @@ static void __exit nf_conntrack_amanda_fini(void) { int i; - nf_conntrack_helper_unregister(&amanda_helper[0]); - nf_conntrack_helper_unregister(&amanda_helper[1]); + nf_conntrack_helpers_unregister(amanda_helper, + ARRAY_SIZE(amanda_helper)); for (i = 0; i < ARRAY_SIZE(search); i++) textsearch_destroy(search[i].ts); } @@ -218,16 +218,12 @@ static int __init nf_conntrack_amanda_init(void) goto err1; } } - ret = nf_conntrack_helper_register(&amanda_helper[0]); + ret = nf_conntrack_helpers_register(amanda_helper, + ARRAY_SIZE(amanda_helper)); if (ret < 0) goto err1; - ret = nf_conntrack_helper_register(&amanda_helper[1]); - if (ret < 0) - goto err2; return 0; -err2: - nf_conntrack_helper_unregister(&amanda_helper[0]); err1: while (--i >= 0) textsearch_destroy(search[i].ts); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index e847dbaa0c6b..9979f46c81dc 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1586,13 +1586,12 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb) /* Bring out ya dead! */ static struct nf_conn * -get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), +get_next_corpse(int (*iter)(struct nf_conn *i, void *data), void *data, unsigned int *bucket) { struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct hlist_nulls_node *n; - int cpu; spinlock_t *lockp; for (; *bucket < nf_conntrack_htable_size; (*bucket)++) { @@ -1604,8 +1603,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) continue; ct = nf_ct_tuplehash_to_ctrack(h); - if (net_eq(nf_ct_net(ct), net) && - iter(ct, data)) + if (iter(ct, data)) goto found; } } @@ -1614,51 +1612,150 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), cond_resched(); } + return NULL; +found: + atomic_inc(&ct->ct_general.use); + spin_unlock(lockp); + local_bh_enable(); + return ct; +} + +static void nf_ct_iterate_cleanup(int (*iter)(struct nf_conn *i, void *data), + void *data, u32 portid, int report) +{ + unsigned int bucket = 0, sequence; + struct nf_conn *ct; + + might_sleep(); + + for (;;) { + sequence = read_seqcount_begin(&nf_conntrack_generation); + + while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) { + /* Time to push up daises... */ + + nf_ct_delete(ct, portid, report); + nf_ct_put(ct); + cond_resched(); + } + + if (!read_seqcount_retry(&nf_conntrack_generation, sequence)) + break; + bucket = 0; + } +} + +struct iter_data { + int (*iter)(struct nf_conn *i, void *data); + void *data; + struct net *net; +}; + +static int iter_net_only(struct nf_conn *i, void *data) +{ + struct iter_data *d = data; + + if (!net_eq(d->net, nf_ct_net(i))) + return 0; + + return d->iter(i, d->data); +} + +static void +__nf_ct_unconfirmed_destroy(struct net *net) +{ + int cpu; + for_each_possible_cpu(cpu) { - struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + struct nf_conntrack_tuple_hash *h; + struct hlist_nulls_node *n; + struct ct_pcpu *pcpu; + + pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); spin_lock_bh(&pcpu->lock); hlist_nulls_for_each_entry(h, n, &pcpu->unconfirmed, hnnode) { + struct nf_conn *ct; + ct = nf_ct_tuplehash_to_ctrack(h); - if (iter(ct, data)) - set_bit(IPS_DYING_BIT, &ct->status); + + /* we cannot call iter() on unconfirmed list, the + * owning cpu can reallocate ct->ext at any time. + */ + set_bit(IPS_DYING_BIT, &ct->status); } spin_unlock_bh(&pcpu->lock); cond_resched(); } - return NULL; -found: - atomic_inc(&ct->ct_general.use); - spin_unlock(lockp); - local_bh_enable(); - return ct; } -void nf_ct_iterate_cleanup(struct net *net, - int (*iter)(struct nf_conn *i, void *data), - void *data, u32 portid, int report) +void nf_ct_iterate_cleanup_net(struct net *net, + int (*iter)(struct nf_conn *i, void *data), + void *data, u32 portid, int report) { - struct nf_conn *ct; - unsigned int bucket = 0; + struct iter_data d; might_sleep(); if (atomic_read(&net->ct.count) == 0) return; - while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) { - /* Time to push up daises... */ + __nf_ct_unconfirmed_destroy(net); - nf_ct_delete(ct, portid, report); - nf_ct_put(ct); - cond_resched(); + d.iter = iter; + d.data = data; + d.net = net; + + synchronize_net(); + + nf_ct_iterate_cleanup(iter_net_only, &d, portid, report); +} +EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup_net); + +/** + * nf_ct_iterate_destroy - destroy unconfirmed conntracks and iterate table + * @iter: callback to invoke for each conntrack + * @data: data to pass to @iter + * + * Like nf_ct_iterate_cleanup, but first marks conntracks on the + * unconfirmed list as dying (so they will not be inserted into + * main table). + * + * Can only be called in module exit path. + */ +void +nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data) +{ + struct net *net; + + rtnl_lock(); + for_each_net(net) { + if (atomic_read(&net->ct.count) == 0) + continue; + __nf_ct_unconfirmed_destroy(net); } + rtnl_unlock(); + + /* Need to wait for netns cleanup worker to finish, if its + * running -- it might have deleted a net namespace from + * the global list, so our __nf_ct_unconfirmed_destroy() might + * not have affected all namespaces. + */ + net_ns_barrier(); + + /* a conntrack could have been unlinked from unconfirmed list + * before we grabbed pcpu lock in __nf_ct_unconfirmed_destroy(). + * This makes sure its inserted into conntrack table. + */ + synchronize_net(); + + nf_ct_iterate_cleanup(iter, data, 0, 0); } -EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup); +EXPORT_SYMBOL_GPL(nf_ct_iterate_destroy); static int kill_all(struct nf_conn *i, void *data) { - return 1; + return net_eq(nf_ct_net(i), data); } void nf_ct_free_hashtable(void *hash, unsigned int size) @@ -1723,7 +1820,7 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list) i_see_dead_people: busy = 0; list_for_each_entry(net, net_exit_list, exit_list) { - nf_ct_iterate_cleanup(net, kill_all, NULL, 0, 0); + nf_ct_iterate_cleanup(kill_all, net, 0, 0); if (atomic_read(&net->ct.count) != 0) busy = 1; } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index e03d16ed550d..899c2c36da13 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -422,7 +422,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) h = nf_ct_expect_dst_hash(net, &expect->tuple); hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) { if (expect_matches(i, expect)) { - if (nf_ct_remove_expect(expect)) + if (nf_ct_remove_expect(i)) break; } else if (expect_clash(i, expect)) { ret = -EBUSY; diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 3bcdc718484e..f71f0d2558fd 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -1815,14 +1815,44 @@ static struct nf_conntrack_helper nf_conntrack_helper_ras[] __read_mostly = { }, }; +static int __init h323_helper_init(void) +{ + int ret; + + ret = nf_conntrack_helper_register(&nf_conntrack_helper_h245); + if (ret < 0) + return ret; + ret = nf_conntrack_helpers_register(nf_conntrack_helper_q931, + ARRAY_SIZE(nf_conntrack_helper_q931)); + if (ret < 0) + goto err1; + ret = nf_conntrack_helpers_register(nf_conntrack_helper_ras, + ARRAY_SIZE(nf_conntrack_helper_ras)); + if (ret < 0) + goto err2; + + return 0; +err2: + nf_conntrack_helpers_unregister(nf_conntrack_helper_q931, + ARRAY_SIZE(nf_conntrack_helper_q931)); +err1: + nf_conntrack_helper_unregister(&nf_conntrack_helper_h245); + return ret; +} + +static void __exit h323_helper_exit(void) +{ + nf_conntrack_helpers_unregister(nf_conntrack_helper_ras, + ARRAY_SIZE(nf_conntrack_helper_ras)); + nf_conntrack_helpers_unregister(nf_conntrack_helper_q931, + ARRAY_SIZE(nf_conntrack_helper_q931)); + nf_conntrack_helper_unregister(&nf_conntrack_helper_h245); +} + /****************************************************************************/ static void __exit nf_conntrack_h323_fini(void) { - nf_conntrack_helper_unregister(&nf_conntrack_helper_ras[1]); - nf_conntrack_helper_unregister(&nf_conntrack_helper_ras[0]); - nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[1]); - nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[0]); - nf_conntrack_helper_unregister(&nf_conntrack_helper_h245); + h323_helper_exit(); kfree(h323_buffer); pr_debug("nf_ct_h323: fini\n"); } @@ -1837,32 +1867,11 @@ static int __init nf_conntrack_h323_init(void) h323_buffer = kmalloc(65536, GFP_KERNEL); if (!h323_buffer) return -ENOMEM; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_h245); + ret = h323_helper_init(); if (ret < 0) goto err1; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[0]); - if (ret < 0) - goto err2; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[1]); - if (ret < 0) - goto err3; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[0]); - if (ret < 0) - goto err4; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[1]); - if (ret < 0) - goto err5; pr_debug("nf_ct_h323: init success\n"); return 0; - -err5: - nf_conntrack_helper_unregister(&nf_conntrack_helper_ras[0]); -err4: - nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[1]); -err3: - nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[0]); -err2: - nf_conntrack_helper_unregister(&nf_conntrack_helper_h245); err1: kfree(h323_buffer); return ret; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 7f6100ca63be..9129bb3b5153 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -285,16 +285,16 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper); /* appropriate ct lock protecting must be taken by caller */ -static inline int unhelp(struct nf_conntrack_tuple_hash *i, - const struct nf_conntrack_helper *me) +static int unhelp(struct nf_conn *ct, void *me) { - struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i); struct nf_conn_help *help = nfct_help(ct); if (help && rcu_dereference_raw(help->helper) == me) { nf_conntrack_event(IPCT_HELPER, ct); RCU_INIT_POINTER(help->helper, NULL); } + + /* We are not intended to delete this conntrack. */ return 0; } @@ -437,33 +437,10 @@ out: } EXPORT_SYMBOL_GPL(nf_conntrack_helper_register); -static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, - struct net *net) -{ - struct nf_conntrack_tuple_hash *h; - const struct hlist_nulls_node *nn; - int cpu; - - /* Get rid of expecteds, set helpers to NULL. */ - for_each_possible_cpu(cpu) { - struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); - - spin_lock_bh(&pcpu->lock); - hlist_nulls_for_each_entry(h, nn, &pcpu->unconfirmed, hnnode) - unhelp(h, me); - spin_unlock_bh(&pcpu->lock); - } -} - void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) { - struct nf_conntrack_tuple_hash *h; struct nf_conntrack_expect *exp; const struct hlist_node *next; - const struct hlist_nulls_node *nn; - unsigned int last_hsize; - spinlock_t *lock; - struct net *net; unsigned int i; mutex_lock(&nf_ct_helper_mutex); @@ -491,26 +468,7 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) } spin_unlock_bh(&nf_conntrack_expect_lock); - rtnl_lock(); - for_each_net(net) - __nf_conntrack_helper_unregister(me, net); - rtnl_unlock(); - - local_bh_disable(); -restart: - last_hsize = nf_conntrack_htable_size; - for (i = 0; i < last_hsize; i++) { - lock = &nf_conntrack_locks[i % CONNTRACK_LOCKS]; - nf_conntrack_lock(lock); - if (last_hsize != nf_conntrack_htable_size) { - spin_unlock(lock); - goto restart; - } - hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode) - unhelp(h, me); - spin_unlock(lock); - } - local_bh_enable(); + nf_ct_iterate_destroy(unhelp, me); } EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index a8be9b72e6cd..7999e70c3bfb 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -636,11 +636,11 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) if (events & (1 << IPCT_DESTROY)) { type = IPCTNL_MSG_CT_DELETE; group = NFNLGRP_CONNTRACK_DESTROY; - } else if (events & ((1 << IPCT_NEW) | (1 << IPCT_RELATED))) { + } else if (events & ((1 << IPCT_NEW) | (1 << IPCT_RELATED))) { type = IPCTNL_MSG_CT_NEW; flags = NLM_F_CREATE|NLM_F_EXCL; group = NFNLGRP_CONNTRACK_NEW; - } else if (events) { + } else if (events) { type = IPCTNL_MSG_CT_NEW; group = NFNLGRP_CONNTRACK_UPDATE; } else @@ -1122,8 +1122,8 @@ static int ctnetlink_flush_conntrack(struct net *net, return PTR_ERR(filter); } - nf_ct_iterate_cleanup(net, ctnetlink_filter_match, filter, - portid, report); + nf_ct_iterate_cleanup_net(net, ctnetlink_filter_match, filter, + portid, report); kfree(filter); return 0; @@ -1132,7 +1132,8 @@ static int ctnetlink_flush_conntrack(struct net *net, static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; @@ -1184,7 +1185,8 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, static int ctnetlink_get_conntrack(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; @@ -1345,7 +1347,8 @@ ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb) static int ctnetlink_get_ct_dying(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { @@ -1367,7 +1370,8 @@ ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb) static int ctnetlink_get_ct_unconfirmed(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { @@ -1906,7 +1910,8 @@ err1: static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; @@ -2071,7 +2076,8 @@ ctnetlink_ct_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) static int ctnetlink_stat_ct_cpu(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { @@ -2116,7 +2122,8 @@ nlmsg_failure: static int ctnetlink_stat_ct(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct sk_buff *skb2; int err; @@ -2778,7 +2785,8 @@ out: static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { int err; struct nfgenmsg *nfmsg = nlmsg_data(nlh); @@ -2822,7 +2830,8 @@ static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl, static int ctnetlink_get_expect(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; @@ -2834,7 +2843,8 @@ static int ctnetlink_get_expect(struct net *net, struct sock *ctnl, if (nlh->nlmsg_flags & NLM_F_DUMP) { if (cda[CTA_EXPECT_MASTER]) - return ctnetlink_dump_exp_ct(net, ctnl, skb, nlh, cda); + return ctnetlink_dump_exp_ct(net, ctnl, skb, nlh, cda, + extack); else { struct netlink_dump_control c = { .dump = ctnetlink_exp_dump_table, @@ -2902,7 +2912,8 @@ out: static int ctnetlink_del_expect(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; @@ -3190,7 +3201,8 @@ err_ct: static int ctnetlink_new_expect(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; @@ -3296,7 +3308,8 @@ ctnetlink_exp_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) static int ctnetlink_stat_exp_cpu(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 2de6c1fe3261..1dcad229c3cc 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -28,8 +28,8 @@ #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_core.h> -static struct nf_conntrack_l4proto __rcu **nf_ct_protos[PF_MAX] __read_mostly; -struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX] __read_mostly; +static struct nf_conntrack_l4proto __rcu **nf_ct_protos[NFPROTO_NUMPROTO] __read_mostly; +struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[NFPROTO_NUMPROTO] __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_l3protos); static DEFINE_MUTEX(nf_ct_proto_mutex); @@ -68,7 +68,7 @@ nf_ct_unregister_sysctl(struct ctl_table_header **header, struct nf_conntrack_l4proto * __nf_ct_l4proto_find(u_int16_t l3proto, u_int8_t l4proto) { - if (unlikely(l3proto >= AF_MAX || nf_ct_protos[l3proto] == NULL)) + if (unlikely(l3proto >= NFPROTO_NUMPROTO || nf_ct_protos[l3proto] == NULL)) return &nf_conntrack_l4proto_generic; return rcu_dereference(nf_ct_protos[l3proto][l4proto]); @@ -212,7 +212,7 @@ int nf_ct_l3proto_register(struct nf_conntrack_l3proto *proto) int ret = 0; struct nf_conntrack_l3proto *old; - if (proto->l3proto >= AF_MAX) + if (proto->l3proto >= NFPROTO_NUMPROTO) return -EBUSY; if (proto->tuple_to_nlattr && !proto->nlattr_tuple_size) @@ -254,7 +254,7 @@ EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_register); void nf_ct_l3proto_unregister(struct nf_conntrack_l3proto *proto) { - BUG_ON(proto->l3proto >= AF_MAX); + BUG_ON(proto->l3proto >= NFPROTO_NUMPROTO); mutex_lock(&nf_ct_proto_mutex); BUG_ON(rcu_dereference_protected(nf_ct_l3protos[proto->l3proto], @@ -265,6 +265,8 @@ void nf_ct_l3proto_unregister(struct nf_conntrack_l3proto *proto) mutex_unlock(&nf_ct_proto_mutex); synchronize_rcu(); + /* Remove all contrack entries for this protocol */ + nf_ct_iterate_destroy(kill_l3proto, proto); } EXPORT_SYMBOL_GPL(nf_ct_l3proto_unregister); @@ -280,9 +282,6 @@ void nf_ct_l3proto_pernet_unregister(struct net *net, */ if (proto->net_ns_put) proto->net_ns_put(net); - - /* Remove all contrack entries for this protocol */ - nf_ct_iterate_cleanup(net, kill_l3proto, proto, 0, 0); } EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_unregister); @@ -342,7 +341,7 @@ int nf_ct_l4proto_register_one(struct nf_conntrack_l4proto *l4proto) { int ret = 0; - if (l4proto->l3proto >= PF_MAX) + if (l4proto->l3proto >= ARRAY_SIZE(nf_ct_protos)) return -EBUSY; if ((l4proto->to_nlattr && !l4proto->nlattr_size) || @@ -421,17 +420,23 @@ out: } EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register_one); -void nf_ct_l4proto_unregister_one(struct nf_conntrack_l4proto *l4proto) +static void __nf_ct_l4proto_unregister_one(struct nf_conntrack_l4proto *l4proto) + { - BUG_ON(l4proto->l3proto >= PF_MAX); + BUG_ON(l4proto->l3proto >= ARRAY_SIZE(nf_ct_protos)); - mutex_lock(&nf_ct_proto_mutex); BUG_ON(rcu_dereference_protected( nf_ct_protos[l4proto->l3proto][l4proto->l4proto], lockdep_is_held(&nf_ct_proto_mutex) ) != l4proto); rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto], &nf_conntrack_l4proto_generic); +} + +void nf_ct_l4proto_unregister_one(struct nf_conntrack_l4proto *l4proto) +{ + mutex_lock(&nf_ct_proto_mutex); + __nf_ct_l4proto_unregister_one(l4proto); mutex_unlock(&nf_ct_proto_mutex); synchronize_rcu(); @@ -448,9 +453,6 @@ void nf_ct_l4proto_pernet_unregister_one(struct net *net, pn->users--; nf_ct_l4proto_unregister_sysctl(net, pn, l4proto); - - /* Remove all contrack entries for this protocol */ - nf_ct_iterate_cleanup(net, kill_l4proto, l4proto, 0, 0); } EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister_one); @@ -500,8 +502,14 @@ EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register); void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *l4proto[], unsigned int num_proto) { + mutex_lock(&nf_ct_proto_mutex); while (num_proto-- != 0) - nf_ct_l4proto_unregister_one(l4proto[num_proto]); + __nf_ct_l4proto_unregister_one(l4proto[num_proto]); + mutex_unlock(&nf_ct_proto_mutex); + + synchronize_net(); + /* Remove all contrack entries for this protocol */ + nf_ct_iterate_destroy(kill_l4proto, l4proto); } EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister); @@ -548,7 +556,7 @@ void nf_conntrack_proto_pernet_fini(struct net *net) int nf_conntrack_proto_init(void) { unsigned int i; - for (i = 0; i < AF_MAX; i++) + for (i = 0; i < NFPROTO_NUMPROTO; i++) rcu_assign_pointer(nf_ct_l3protos[i], &nf_conntrack_l3proto_generic); return 0; @@ -558,6 +566,6 @@ void nf_conntrack_proto_fini(void) { unsigned int i; /* free l3proto protocol tables */ - for (i = 0; i < PF_MAX; i++) + for (i = 0; i < ARRAY_SIZE(nf_ct_protos); i++) kfree(nf_ct_protos[i]); } diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index b553fdd68816..4707d997558a 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -872,6 +872,11 @@ static int dccp_init_net(struct net *net, u_int16_t proto) return dccp_kmemdup_sysctl_table(net, pn, dn); } +static struct nf_proto_net *dccp_get_net_proto(struct net *net) +{ + return &net->ct.nf_ct_proto.dccp.pn; +} + struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 __read_mostly = { .l3proto = AF_INET, .l4proto = IPPROTO_DCCP, @@ -904,6 +909,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 __read_mostly = { }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ .init_net = dccp_init_net, + .get_net_proto = dccp_get_net_proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_dccp4); @@ -939,5 +945,6 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 __read_mostly = { }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ .init_net = dccp_init_net, + .get_net_proto = dccp_get_net_proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_dccp6); diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 1c5b14a6cab3..6eef29d2eec4 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -190,7 +190,7 @@ static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) } #define for_each_sctp_chunk(skb, sch, _sch, offset, dataoff, count) \ -for ((offset) = (dataoff) + sizeof(sctp_sctphdr_t), (count) = 0; \ +for ((offset) = (dataoff) + sizeof(struct sctphdr), (count) = 0; \ (offset) < (skb)->len && \ ((sch) = skb_header_pointer((skb), (offset), sizeof(_sch), &(_sch))); \ (offset) += (ntohs((sch)->length) + 3) & ~3, (count)++) @@ -202,7 +202,7 @@ static int do_basic_checks(struct nf_conn *ct, unsigned long *map) { u_int32_t offset, count; - sctp_chunkhdr_t _sch, *sch; + struct sctp_chunkhdr _sch, *sch; int flag; flag = 0; @@ -395,9 +395,9 @@ static int sctp_packet(struct nf_conn *ct, /* If it is an INIT or an INIT ACK note down the vtag */ if (sch->type == SCTP_CID_INIT || sch->type == SCTP_CID_INIT_ACK) { - sctp_inithdr_t _inithdr, *ih; + struct sctp_inithdr _inithdr, *ih; - ih = skb_header_pointer(skb, offset + sizeof(sctp_chunkhdr_t), + ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(_inithdr), &_inithdr); if (ih == NULL) goto out_unlock; @@ -471,23 +471,20 @@ static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb, /* Copy the vtag into the state info */ if (sch->type == SCTP_CID_INIT) { - if (sh->vtag == 0) { - sctp_inithdr_t _inithdr, *ih; + struct sctp_inithdr _inithdr, *ih; + /* Sec 8.5.1 (A) */ + if (sh->vtag) + return false; - ih = skb_header_pointer(skb, offset + sizeof(sctp_chunkhdr_t), - sizeof(_inithdr), &_inithdr); - if (ih == NULL) - return false; + ih = skb_header_pointer(skb, offset + sizeof(_sch), + sizeof(_inithdr), &_inithdr); + if (!ih) + return false; - pr_debug("Setting vtag %x for new conn\n", - ih->init_tag); + pr_debug("Setting vtag %x for new conn\n", + ih->init_tag); - ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = - ih->init_tag; - } else { - /* Sec 8.5.1 (A) */ - return false; - } + ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = ih->init_tag; } else if (sch->type == SCTP_CID_HEARTBEAT) { pr_debug("Setting vtag %x for secondary conntrack\n", sh->vtag); @@ -786,6 +783,11 @@ static int sctp_init_net(struct net *net, u_int16_t proto) return sctp_kmemdup_sysctl_table(pn, sn); } +static struct nf_proto_net *sctp_get_net_proto(struct net *net) +{ + return &net->ct.nf_ct_proto.sctp.pn; +} + struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = { .l3proto = PF_INET, .l4proto = IPPROTO_SCTP, @@ -819,6 +821,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = { }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ .init_net = sctp_init_net, + .get_net_proto = sctp_get_net_proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_sctp4); @@ -855,5 +858,6 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = { #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #endif .init_net = sctp_init_net, + .get_net_proto = sctp_get_net_proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_sctp6); diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c index c9d7f95768ab..f4a566e67213 100644 --- a/net/netfilter/nf_dup_netdev.c +++ b/net/netfilter/nf_dup_netdev.c @@ -13,6 +13,7 @@ #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_dup_netdev.h> static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev) { diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 6c72922d20ca..eb541786ccb7 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -222,20 +222,21 @@ find_appropriate_src(struct net *net, .tuple = tuple, .zone = zone }; - struct rhlist_head *hl; + struct rhlist_head *hl, *h; hl = rhltable_lookup(&nf_nat_bysource_table, &key, nf_nat_bysource_params); - if (!hl) - return 0; - ct = container_of(hl, typeof(*ct), nat_bysource); + rhl_for_each_entry_rcu(ct, h, hl, nat_bysource) { + nf_ct_invert_tuplepr(result, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + result->dst = tuple->dst; - nf_ct_invert_tuplepr(result, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); - result->dst = tuple->dst; + if (in_range(l3proto, l4proto, result, range)) + return 1; + } - return in_range(l3proto, l4proto, result, range); + return 0; } /* For [FUTURE] fragmentation handling, we want the least-used @@ -582,12 +583,8 @@ static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) .l3proto = l3proto, .l4proto = l4proto, }; - struct net *net; - rtnl_lock(); - for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean, 0, 0); - rtnl_unlock(); + nf_ct_iterate_destroy(nf_nat_proto_remove, &clean); } static void nf_nat_l3proto_clean(u8 l3proto) @@ -595,13 +592,8 @@ static void nf_nat_l3proto_clean(u8 l3proto) struct nf_nat_proto_clean clean = { .l3proto = l3proto, }; - struct net *net; - - rtnl_lock(); - for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean, 0, 0); - rtnl_unlock(); + nf_ct_iterate_destroy(nf_nat_proto_remove, &clean); } /* Protocol registration. */ @@ -822,17 +814,6 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, } #endif -static void __net_exit nf_nat_net_exit(struct net *net) -{ - struct nf_nat_proto_clean clean = {}; - - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean, 0, 0); -} - -static struct pernet_operations nf_nat_net_ops = { - .exit = nf_nat_net_exit, -}; - static struct nf_ct_helper_expectfn follow_master_nat = { .name = "nat-follow-master", .expectfn = nf_nat_follow_master, @@ -853,10 +834,6 @@ static int __init nf_nat_init(void) return ret; } - ret = register_pernet_subsys(&nf_nat_net_ops); - if (ret < 0) - goto cleanup_extend; - nf_ct_helper_expectfn_register(&follow_master_nat); BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); @@ -867,18 +844,15 @@ static int __init nf_nat_init(void) RCU_INIT_POINTER(nf_nat_decode_session_hook, __nf_nat_decode_session); #endif return 0; - - cleanup_extend: - rhltable_destroy(&nf_nat_bysource_table); - nf_ct_extend_unregister(&nat_extend); - return ret; } static void __exit nf_nat_cleanup(void) { + struct nf_nat_proto_clean clean = {}; unsigned int i; - unregister_pernet_subsys(&nf_nat_net_ops); + nf_ct_iterate_destroy(nf_nat_proto_clean, &clean); + nf_ct_extend_unregister(&nat_extend); nf_ct_helper_expectfn_unregister(&follow_master_nat); RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c index 804e8a0ab36e..c57ee3240b1d 100644 --- a/net/netfilter/nf_nat_proto_sctp.c +++ b/net/netfilter/nf_nat_proto_sctp.c @@ -32,7 +32,7 @@ sctp_manip_pkt(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { - sctp_sctphdr_t *hdr; + struct sctphdr *hdr; int hdrsize = 8; /* This could be an inner header returned in imcp packet; in such diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index a504e87c6ddf..49bd8bb16b18 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -152,7 +152,7 @@ void synproxy_init_timestamp_cookie(const struct xt_synproxy_info *info, struct synproxy_options *opts) { opts->tsecr = opts->tsval; - opts->tsval = tcp_time_stamp & ~0x3f; + opts->tsval = tcp_time_stamp_raw() & ~0x3f; if (opts->options & XT_SYNPROXY_OPT_WSCALE) { opts->tsval |= opts->wscale; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index da314be0c048..7843efa33c59 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -13,6 +13,7 @@ #include <linux/list.h> #include <linux/skbuff.h> #include <linux/netlink.h> +#include <linux/vmalloc.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nf_tables.h> @@ -386,7 +387,7 @@ static inline u64 nf_tables_alloc_handle(struct nft_table *table) return ++table->hgenerator; } -static const struct nf_chain_type *chain_type[AF_MAX][NFT_CHAIN_T_MAX]; +static const struct nf_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX]; static const struct nf_chain_type * __nf_tables_chain_type_lookup(int family, const struct nlattr *nla) @@ -534,7 +535,8 @@ done: static int nf_tables_gettable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_cur(net); @@ -677,7 +679,8 @@ err: static int nf_tables_newtable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -830,7 +833,8 @@ out: static int nf_tables_deltable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -869,6 +873,9 @@ int nft_register_chain_type(const struct nf_chain_type *ctype) { int err = 0; + if (WARN_ON(ctype->family >= NFPROTO_NUMPROTO)) + return -EINVAL; + nfnl_lock(NFNL_SUBSYS_NFTABLES); if (chain_type[ctype->family][ctype->type] != NULL) { err = -EBUSY; @@ -1123,7 +1130,8 @@ done: static int nf_tables_getchain(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_cur(net); @@ -1319,7 +1327,8 @@ static void nft_chain_release_hook(struct nft_chain_hook *hook) static int nf_tables_newchain(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nlattr * uninitialized_var(name); @@ -1557,7 +1566,8 @@ err1: static int nf_tables_delchain(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -2038,7 +2048,8 @@ static int nf_tables_dump_rules_done(struct netlink_callback *cb) static int nf_tables_getrule(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_cur(net); @@ -2131,7 +2142,8 @@ static struct nft_expr_info *info; static int nf_tables_newrule(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -2313,7 +2325,8 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net, static int nf_tables_delrule(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -2377,64 +2390,77 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, * Sets */ -static LIST_HEAD(nf_tables_set_ops); +static LIST_HEAD(nf_tables_set_types); -int nft_register_set(struct nft_set_ops *ops) +int nft_register_set(struct nft_set_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_add_tail_rcu(&ops->list, &nf_tables_set_ops); + list_add_tail_rcu(&type->list, &nf_tables_set_types); nfnl_unlock(NFNL_SUBSYS_NFTABLES); return 0; } EXPORT_SYMBOL_GPL(nft_register_set); -void nft_unregister_set(struct nft_set_ops *ops) +void nft_unregister_set(struct nft_set_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_del_rcu(&ops->list); + list_del_rcu(&type->list); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_set); +#define NFT_SET_FEATURES (NFT_SET_INTERVAL | NFT_SET_MAP | \ + NFT_SET_TIMEOUT | NFT_SET_OBJECT) + +static bool nft_set_ops_candidate(const struct nft_set_ops *ops, u32 flags) +{ + return (flags & ops->features) == (flags & NFT_SET_FEATURES); +} + /* * Select a set implementation based on the data characteristics and the * given policy. The total memory use might not be known if no size is * given, in that case the amount of memory per element is used. */ static const struct nft_set_ops * -nft_select_set_ops(const struct nlattr * const nla[], +nft_select_set_ops(const struct nft_ctx *ctx, + const struct nlattr * const nla[], const struct nft_set_desc *desc, enum nft_set_policies policy) { const struct nft_set_ops *ops, *bops; struct nft_set_estimate est, best; - u32 features; + const struct nft_set_type *type; + u32 flags = 0; #ifdef CONFIG_MODULES - if (list_empty(&nf_tables_set_ops)) { + if (list_empty(&nf_tables_set_types)) { nfnl_unlock(NFNL_SUBSYS_NFTABLES); request_module("nft-set"); nfnl_lock(NFNL_SUBSYS_NFTABLES); - if (!list_empty(&nf_tables_set_ops)) + if (!list_empty(&nf_tables_set_types)) return ERR_PTR(-EAGAIN); } #endif - features = 0; - if (nla[NFTA_SET_FLAGS] != NULL) { - features = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS])); - features &= NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_TIMEOUT | - NFT_SET_OBJECT; - } + if (nla[NFTA_SET_FLAGS] != NULL) + flags = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS])); bops = NULL; best.size = ~0; best.lookup = ~0; best.space = ~0; - list_for_each_entry(ops, &nf_tables_set_ops, list) { - if ((ops->features & features) != features) + list_for_each_entry(type, &nf_tables_set_types, list) { + if (!type->select_ops) + ops = type->ops; + else + ops = type->select_ops(ctx, desc, flags); + if (!ops) + continue; + + if (!nft_set_ops_candidate(ops, flags)) continue; - if (!ops->estimate(desc, features, &est)) + if (!ops->estimate(desc, flags, &est)) continue; switch (policy) { @@ -2465,10 +2491,10 @@ nft_select_set_ops(const struct nlattr * const nla[], break; } - if (!try_module_get(ops->owner)) + if (!try_module_get(type->owner)) continue; if (bops != NULL) - module_put(bops->owner); + module_put(bops->type->owner); bops = ops; best = est; @@ -2816,7 +2842,8 @@ static int nf_tables_dump_sets_done(struct netlink_callback *cb) static int nf_tables_getset(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { u8 genmask = nft_genmask_cur(net); const struct nft_set *set; @@ -2892,7 +2919,8 @@ static int nf_tables_set_desc_parse(const struct nft_ctx *ctx, static int nf_tables_newset(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -3029,7 +3057,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (!(nlh->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; - ops = nft_select_set_ops(nla, &desc, policy); + ops = nft_select_set_ops(&ctx, nla, &desc, policy); if (IS_ERR(ops)) return PTR_ERR(ops); @@ -3039,12 +3067,13 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, size = 0; if (ops->privsize != NULL) - size = ops->privsize(nla); + size = ops->privsize(nla, &desc); - err = -ENOMEM; - set = kzalloc(sizeof(*set) + size + udlen, GFP_KERNEL); - if (set == NULL) + set = kvzalloc(sizeof(*set) + size + udlen, GFP_KERNEL); + if (!set) { + err = -ENOMEM; goto err1; + } nla_strlcpy(name, nla[NFTA_SET_NAME], sizeof(set->name)); err = nf_tables_set_alloc_name(&ctx, set, name); @@ -3087,17 +3116,17 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, err3: ops->destroy(set); err2: - kfree(set); + kvfree(set); err1: - module_put(ops->owner); + module_put(ops->type->owner); return err; } static void nft_set_destroy(struct nft_set *set) { set->ops->destroy(set); - module_put(set->ops->owner); - kfree(set); + module_put(set->ops->type->owner); + kvfree(set); } static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) @@ -3109,7 +3138,8 @@ static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set static int nf_tables_delset(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -3469,7 +3499,8 @@ static int nf_tables_dump_set_done(struct netlink_callback *cb) static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { u8 genmask = nft_genmask_cur(net); const struct nft_set *set; @@ -3870,7 +3901,8 @@ err1: static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { u8 genmask = nft_genmask_next(net); const struct nlattr *attr; @@ -4067,7 +4099,8 @@ err1: static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { u8 genmask = nft_genmask_next(net); const struct nlattr *attr; @@ -4277,7 +4310,8 @@ static const struct nft_object_type *nft_obj_type_get(u32 objtype) static int nf_tables_newobj(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nft_object_type *type; @@ -4471,7 +4505,8 @@ nft_obj_filter_alloc(const struct nlattr * const nla[]) static int nf_tables_getobj(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_cur(net); @@ -4549,8 +4584,9 @@ static void nft_obj_destroy(struct nft_object *obj) } static int nf_tables_delobj(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + struct sk_buff *skb, const struct nlmsghdr *nlh, + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -4680,7 +4716,8 @@ err: static int nf_tables_getgen(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { struct sk_buff *skb2; int err; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 80f5ecf2c3d7..733d3e4a30d8 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -201,7 +201,8 @@ replay: if (nc->call_rcu) { err = nc->call_rcu(net, net->nfnl, skb, nlh, - (const struct nlattr **)cda); + (const struct nlattr **)cda, + extack); rcu_read_unlock(); } else { rcu_read_unlock(); @@ -211,7 +212,8 @@ replay: err = -EAGAIN; else if (nc->call) err = nc->call(net, net->nfnl, skb, nlh, - (const struct nlattr **)cda); + (const struct nlattr **)cda, + extack); else err = -EINVAL; nfnl_unlock(subsys_id); @@ -226,9 +228,11 @@ struct nfnl_err { struct list_head head; struct nlmsghdr *nlh; int err; + struct netlink_ext_ack extack; }; -static int nfnl_err_add(struct list_head *list, struct nlmsghdr *nlh, int err) +static int nfnl_err_add(struct list_head *list, struct nlmsghdr *nlh, int err, + const struct netlink_ext_ack *extack) { struct nfnl_err *nfnl_err; @@ -238,6 +242,7 @@ static int nfnl_err_add(struct list_head *list, struct nlmsghdr *nlh, int err) nfnl_err->nlh = nlh; nfnl_err->err = err; + nfnl_err->extack = *extack; list_add_tail(&nfnl_err->head, list); return 0; @@ -262,7 +267,8 @@ static void nfnl_err_deliver(struct list_head *err_list, struct sk_buff *skb) struct nfnl_err *nfnl_err, *next; list_for_each_entry_safe(nfnl_err, next, err_list, head) { - netlink_ack(skb, nfnl_err->nlh, nfnl_err->err, NULL); + netlink_ack(skb, nfnl_err->nlh, nfnl_err->err, + &nfnl_err->extack); nfnl_err_del(nfnl_err); } } @@ -280,6 +286,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); const struct nfnetlink_subsystem *ss; const struct nfnl_callback *nc; + struct netlink_ext_ack extack; LIST_HEAD(err_list); u32 status; int err; @@ -325,6 +332,7 @@ replay: while (skb->len >= nlmsg_total_size(0)) { int msglen, type; + memset(&extack, 0, sizeof(extack)); nlh = nlmsg_hdr(skb); err = 0; @@ -384,7 +392,8 @@ replay: if (nc->call_batch) { err = nc->call_batch(net, net->nfnl, skb, nlh, - (const struct nlattr **)cda); + (const struct nlattr **)cda, + &extack); } /* The lock was released to autoload some module, we @@ -402,7 +411,7 @@ ack: * processed, this avoids that the same error is * reported several times when replaying the batch. */ - if (nfnl_err_add(&err_list, nlh, err) < 0) { + if (nfnl_err_add(&err_list, nlh, err, &extack) < 0) { /* We failed to enqueue an error, reset the * list of errors and send OOM to userspace * pointing to the batch header. @@ -463,8 +472,7 @@ static void nfnetlink_rcv_skb_batch(struct sk_buff *skb, struct nlmsghdr *nlh) if (msglen > skb->len) msglen = skb->len; - if (nlh->nlmsg_len < NLMSG_HDRLEN || - skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg)) + if (skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg)) return; err = nla_parse(cda, NFNL_BATCH_MAX, attr, attrlen, nfnl_batch_policy, @@ -491,7 +499,8 @@ static void nfnetlink_rcv(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); - if (nlh->nlmsg_len < NLMSG_HDRLEN || + if (skb->len < NLMSG_HDRLEN || + nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) return; diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 9898fb4d0512..c45e6d4358ab 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -49,7 +49,8 @@ struct nfacct_filter { static int nfnl_acct_new(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { struct nf_acct *nfacct, *matching = NULL; char *acct_name; @@ -264,7 +265,8 @@ nfacct_filter_alloc(const struct nlattr * const attr) static int nfnl_acct_get(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { int ret = -ENOENT; struct nf_acct *cur; @@ -343,7 +345,8 @@ static int nfnl_acct_try_del(struct nf_acct *cur) static int nfnl_acct_del(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { struct nf_acct *cur, *tmp; int ret = -ENOENT; diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index be678a323598..41628b393673 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -398,7 +398,8 @@ nfnl_cthelper_update(const struct nlattr * const tb[], static int nfnl_cthelper_new(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { const char *helper_name; struct nf_conntrack_helper *cur, *helper = NULL; @@ -599,7 +600,8 @@ out: static int nfnl_cthelper_get(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { int ret = -ENOENT; struct nf_conntrack_helper *cur; @@ -666,7 +668,8 @@ static int nfnl_cthelper_get(struct net *net, struct sock *nfnl, static int nfnl_cthelper_del(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { char *helper_name = NULL; struct nf_conntrack_helper *cur; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index a3e7bb54d96a..400e9ae97153 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -69,7 +69,8 @@ ctnl_timeout_parse_policy(void *timeouts, struct nf_conntrack_l4proto *l4proto, static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { __u16 l3num; __u8 l4num; @@ -239,7 +240,8 @@ ctnl_timeout_dump(struct sk_buff *skb, struct netlink_callback *cb) static int cttimeout_get_timeout(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { int ret = -ENOENT; char *name; @@ -287,49 +289,20 @@ static int cttimeout_get_timeout(struct net *net, struct sock *ctnl, return ret; } -static void untimeout(struct nf_conntrack_tuple_hash *i, - struct ctnl_timeout *timeout) +static int untimeout(struct nf_conn *ct, void *timeout) { - struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i); struct nf_conn_timeout *timeout_ext = nf_ct_timeout_find(ct); if (timeout_ext && (!timeout || timeout_ext->timeout == timeout)) RCU_INIT_POINTER(timeout_ext->timeout, NULL); + + /* We are not intended to delete this conntrack. */ + return 0; } static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout) { - struct nf_conntrack_tuple_hash *h; - const struct hlist_nulls_node *nn; - unsigned int last_hsize; - spinlock_t *lock; - int i, cpu; - - for_each_possible_cpu(cpu) { - struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); - - spin_lock_bh(&pcpu->lock); - hlist_nulls_for_each_entry(h, nn, &pcpu->unconfirmed, hnnode) - untimeout(h, timeout); - spin_unlock_bh(&pcpu->lock); - } - - local_bh_disable(); -restart: - last_hsize = nf_conntrack_htable_size; - for (i = 0; i < last_hsize; i++) { - lock = &nf_conntrack_locks[i % CONNTRACK_LOCKS]; - nf_conntrack_lock(lock); - if (last_hsize != nf_conntrack_htable_size) { - spin_unlock(lock); - goto restart; - } - - hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode) - untimeout(h, timeout); - spin_unlock(lock); - } - local_bh_enable(); + nf_ct_iterate_cleanup_net(net, untimeout, timeout, 0, 0); } /* try to delete object, fail if it is still in use. */ @@ -355,7 +328,8 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) static int cttimeout_del_timeout(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct ctnl_timeout *cur, *tmp; int ret = -ENOENT; @@ -386,7 +360,8 @@ static int cttimeout_del_timeout(struct net *net, struct sock *ctnl, static int cttimeout_default_set(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { __u16 l3num; __u8 l4num; @@ -475,7 +450,8 @@ nla_put_failure: static int cttimeout_default_get(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { __u16 l3num; __u8 l4num; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index da9704971a83..c684ba95dbb4 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -590,7 +590,7 @@ __build_packet_message(struct nfnl_log_net *log, if (skb_tailroom(inst->skb) < nla_total_size(data_len)) goto nla_put_failure; - nla = (struct nlattr *)skb_put(inst->skb, nla_total_size(data_len)); + nla = skb_put(inst->skb, nla_total_size(data_len)); nla->nla_type = NFULA_PAYLOAD; nla->nla_len = size; @@ -795,7 +795,8 @@ static struct notifier_block nfulnl_rtnl_notifier = { static int nfulnl_recv_unsupp(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[]) + const struct nlattr * const nfqa[], + struct netlink_ext_ack *extack) { return -ENOTSUPP; } @@ -818,7 +819,8 @@ static const struct nla_policy nfula_cfg_policy[NFULA_CFG_MAX+1] = { static int nfulnl_recv_config(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfula[]) + const struct nlattr * const nfula[], + struct netlink_ext_ack *extack) { struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int16_t group_num = ntohs(nfmsg->res_id); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 8a0f218b7938..16fa04086880 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -589,7 +589,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, if (skb_tailroom(skb) < sizeof(*nla) + hlen) goto nla_put_failure; - nla = (struct nlattr *)skb_put(skb, sizeof(*nla)); + nla = skb_put(skb, sizeof(*nla)); nla->nla_type = NFQA_PAYLOAD; nla->nla_len = nla_attr_size(data_len); @@ -1032,7 +1032,8 @@ static int nfq_id_after(unsigned int id, unsigned int max) static int nfqnl_recv_verdict_batch(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[]) + const struct nlattr * const nfqa[], + struct netlink_ext_ack *extack) { struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nf_queue_entry *entry, *tmp; @@ -1136,7 +1137,8 @@ static int nfqa_parse_bridge(struct nf_queue_entry *entry, static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[]) + const struct nlattr * const nfqa[], + struct netlink_ext_ack *extack) { struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int16_t queue_num = ntohs(nfmsg->res_id); @@ -1200,7 +1202,8 @@ static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl, static int nfqnl_recv_unsupp(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[]) + const struct nlattr * const nfqa[], + struct netlink_ext_ack *extack) { return -ENOTSUPP; } @@ -1217,7 +1220,8 @@ static const struct nf_queue_handler nfqh = { static int nfqnl_recv_config(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[]) + const struct nlattr * const nfqa[], + struct netlink_ext_ack *extack) { struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int16_t queue_num = ntohs(nfmsg->res_id); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index f753ec69f790..f5a7cb68694e 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -530,7 +530,8 @@ nla_put_failure: static int nfnl_compat_get(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { int ret = 0, target; struct nfgenmsg *nfmsg; diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index d3eb640bc784..c7383d8f88d0 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -23,9 +23,9 @@ struct nft_rt { enum nft_registers dreg:8; }; -void nft_rt_get_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static void nft_rt_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_rt *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; @@ -72,9 +72,9 @@ const struct nla_policy nft_rt_policy[NFTA_RT_MAX + 1] = { [NFTA_RT_KEY] = { .type = NLA_U32 }, }; -int nft_rt_get_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_rt_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { struct nft_rt *priv = nft_expr_priv(expr); unsigned int len; @@ -103,8 +103,8 @@ int nft_rt_get_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, len); } -int nft_rt_get_dump(struct sk_buff *skb, - const struct nft_expr *expr) +static int nft_rt_get_dump(struct sk_buff *skb, + const struct nft_expr *expr) { const struct nft_rt *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index b988162b5b15..734989c40579 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -236,7 +236,8 @@ static inline u32 nft_bitmap_total_size(u32 klen) return sizeof(struct nft_bitmap) + nft_bitmap_size(klen); } -static unsigned int nft_bitmap_privsize(const struct nlattr * const nla[]) +static unsigned int nft_bitmap_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) { u32 klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN])); @@ -278,7 +279,9 @@ static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, return true; } +static struct nft_set_type nft_bitmap_type; static struct nft_set_ops nft_bitmap_ops __read_mostly = { + .type = &nft_bitmap_type, .privsize = nft_bitmap_privsize, .elemsize = offsetof(struct nft_bitmap_elem, ext), .estimate = nft_bitmap_estimate, @@ -291,17 +294,21 @@ static struct nft_set_ops nft_bitmap_ops __read_mostly = { .activate = nft_bitmap_activate, .lookup = nft_bitmap_lookup, .walk = nft_bitmap_walk, +}; + +static struct nft_set_type nft_bitmap_type __read_mostly = { + .ops = &nft_bitmap_ops, .owner = THIS_MODULE, }; static int __init nft_bitmap_module_init(void) { - return nft_register_set(&nft_bitmap_ops); + return nft_register_set(&nft_bitmap_type); } static void __exit nft_bitmap_module_exit(void) { - nft_unregister_set(&nft_bitmap_ops); + nft_unregister_set(&nft_bitmap_type); } module_init(nft_bitmap_module_init); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 3d3a6df4ce70..0fa01d772c5e 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -22,45 +22,43 @@ #include <net/netfilter/nf_tables.h> /* We target a hash table size of 4, element hint is 75% of final size */ -#define NFT_HASH_ELEMENT_HINT 3 +#define NFT_RHASH_ELEMENT_HINT 3 -struct nft_hash { +struct nft_rhash { struct rhashtable ht; struct delayed_work gc_work; }; -struct nft_hash_elem { +struct nft_rhash_elem { struct rhash_head node; struct nft_set_ext ext; }; -struct nft_hash_cmp_arg { +struct nft_rhash_cmp_arg { const struct nft_set *set; const u32 *key; u8 genmask; }; -static const struct rhashtable_params nft_hash_params; - -static inline u32 nft_hash_key(const void *data, u32 len, u32 seed) +static inline u32 nft_rhash_key(const void *data, u32 len, u32 seed) { - const struct nft_hash_cmp_arg *arg = data; + const struct nft_rhash_cmp_arg *arg = data; return jhash(arg->key, len, seed); } -static inline u32 nft_hash_obj(const void *data, u32 len, u32 seed) +static inline u32 nft_rhash_obj(const void *data, u32 len, u32 seed) { - const struct nft_hash_elem *he = data; + const struct nft_rhash_elem *he = data; return jhash(nft_set_ext_key(&he->ext), len, seed); } -static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg, - const void *ptr) +static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) { - const struct nft_hash_cmp_arg *x = arg->key; - const struct nft_hash_elem *he = ptr; + const struct nft_rhash_cmp_arg *x = arg->key; + const struct nft_rhash_elem *he = ptr; if (memcmp(nft_set_ext_key(&he->ext), x->key, x->set->klen)) return 1; @@ -71,41 +69,49 @@ static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg, return 0; } -static bool nft_hash_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +static const struct rhashtable_params nft_rhash_params = { + .head_offset = offsetof(struct nft_rhash_elem, node), + .hashfn = nft_rhash_key, + .obj_hashfn = nft_rhash_obj, + .obj_cmpfn = nft_rhash_cmp, + .automatic_shrinking = true, +}; + +static bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { - struct nft_hash *priv = nft_set_priv(set); - const struct nft_hash_elem *he; - struct nft_hash_cmp_arg arg = { + struct nft_rhash *priv = nft_set_priv(set); + const struct nft_rhash_elem *he; + struct nft_rhash_cmp_arg arg = { .genmask = nft_genmask_cur(net), .set = set, .key = key, }; - he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_rhash_params); if (he != NULL) *ext = &he->ext; return !!he; } -static bool nft_hash_update(struct nft_set *set, const u32 *key, - void *(*new)(struct nft_set *, - const struct nft_expr *, - struct nft_regs *regs), - const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_set_ext **ext) +static bool nft_rhash_update(struct nft_set *set, const u32 *key, + void *(*new)(struct nft_set *, + const struct nft_expr *, + struct nft_regs *regs), + const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_set_ext **ext) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he, *prev; - struct nft_hash_cmp_arg arg = { + struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_elem *he, *prev; + struct nft_rhash_cmp_arg arg = { .genmask = NFT_GENMASK_ANY, .set = set, .key = key, }; - he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_rhash_params); if (he != NULL) goto out; @@ -114,7 +120,7 @@ static bool nft_hash_update(struct nft_set *set, const u32 *key, goto err1; prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node, - nft_hash_params); + nft_rhash_params); if (IS_ERR(prev)) goto err2; @@ -134,21 +140,21 @@ err1: return false; } -static int nft_hash_insert(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem, - struct nft_set_ext **ext) +static int nft_rhash_insert(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, + struct nft_set_ext **ext) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he = elem->priv; - struct nft_hash_cmp_arg arg = { + struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_elem *he = elem->priv; + struct nft_rhash_cmp_arg arg = { .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, }; - struct nft_hash_elem *prev; + struct nft_rhash_elem *prev; prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node, - nft_hash_params); + nft_rhash_params); if (IS_ERR(prev)) return PTR_ERR(prev); if (prev) { @@ -158,19 +164,19 @@ static int nft_hash_insert(const struct net *net, const struct nft_set *set, return 0; } -static void nft_hash_activate(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) +static void nft_rhash_activate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) { - struct nft_hash_elem *he = elem->priv; + struct nft_rhash_elem *he = elem->priv; nft_set_elem_change_active(net, set, &he->ext); nft_set_elem_clear_busy(&he->ext); } -static bool nft_hash_flush(const struct net *net, - const struct nft_set *set, void *priv) +static bool nft_rhash_flush(const struct net *net, + const struct nft_set *set, void *priv) { - struct nft_hash_elem *he = priv; + struct nft_rhash_elem *he = priv; if (!nft_set_elem_mark_busy(&he->ext) || !nft_is_active(net, &he->ext)) { @@ -180,22 +186,22 @@ static bool nft_hash_flush(const struct net *net, return false; } -static void *nft_hash_deactivate(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static void *nft_rhash_deactivate(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he; - struct nft_hash_cmp_arg arg = { + struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_elem *he; + struct nft_rhash_cmp_arg arg = { .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, }; rcu_read_lock(); - he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_rhash_params); if (he != NULL && - !nft_hash_flush(net, set, he)) + !nft_rhash_flush(net, set, he)) he = NULL; rcu_read_unlock(); @@ -203,21 +209,21 @@ static void *nft_hash_deactivate(const struct net *net, return he; } -static void nft_hash_remove(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static void nft_rhash_remove(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he = elem->priv; + struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_elem *he = elem->priv; - rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params); + rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params); } -static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_iter *iter) +static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, + struct nft_set_iter *iter) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he; + struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_elem *he; struct rhashtable_iter hti; struct nft_set_elem elem; int err; @@ -266,16 +272,16 @@ out: rhashtable_walk_exit(&hti); } -static void nft_hash_gc(struct work_struct *work) +static void nft_rhash_gc(struct work_struct *work) { struct nft_set *set; - struct nft_hash_elem *he; - struct nft_hash *priv; + struct nft_rhash_elem *he; + struct nft_rhash *priv; struct nft_set_gc_batch *gcb = NULL; struct rhashtable_iter hti; int err; - priv = container_of(work, struct nft_hash, gc_work.work); + priv = container_of(work, struct nft_rhash, gc_work.work); set = nft_set_container_of(priv); err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL); @@ -301,7 +307,7 @@ static void nft_hash_gc(struct work_struct *work) gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); if (gcb == NULL) goto out; - rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params); + rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params); atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, he); } @@ -315,82 +321,290 @@ schedule: nft_set_gc_interval(set)); } -static unsigned int nft_hash_privsize(const struct nlattr * const nla[]) +static unsigned int nft_rhash_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) { - return sizeof(struct nft_hash); + return sizeof(struct nft_rhash); } -static const struct rhashtable_params nft_hash_params = { - .head_offset = offsetof(struct nft_hash_elem, node), - .hashfn = nft_hash_key, - .obj_hashfn = nft_hash_obj, - .obj_cmpfn = nft_hash_cmp, - .automatic_shrinking = true, -}; - -static int nft_hash_init(const struct nft_set *set, - const struct nft_set_desc *desc, - const struct nlattr * const tb[]) +static int nft_rhash_init(const struct nft_set *set, + const struct nft_set_desc *desc, + const struct nlattr * const tb[]) { - struct nft_hash *priv = nft_set_priv(set); - struct rhashtable_params params = nft_hash_params; + struct nft_rhash *priv = nft_set_priv(set); + struct rhashtable_params params = nft_rhash_params; int err; - params.nelem_hint = desc->size ?: NFT_HASH_ELEMENT_HINT; + params.nelem_hint = desc->size ?: NFT_RHASH_ELEMENT_HINT; params.key_len = set->klen; err = rhashtable_init(&priv->ht, ¶ms); if (err < 0) return err; - INIT_DEFERRABLE_WORK(&priv->gc_work, nft_hash_gc); + INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rhash_gc); if (set->flags & NFT_SET_TIMEOUT) queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); return 0; } -static void nft_hash_elem_destroy(void *ptr, void *arg) +static void nft_rhash_elem_destroy(void *ptr, void *arg) { nft_set_elem_destroy(arg, ptr, true); } -static void nft_hash_destroy(const struct nft_set *set) +static void nft_rhash_destroy(const struct nft_set *set) { - struct nft_hash *priv = nft_set_priv(set); + struct nft_rhash *priv = nft_set_priv(set); cancel_delayed_work_sync(&priv->gc_work); - rhashtable_free_and_destroy(&priv->ht, nft_hash_elem_destroy, + rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, (void *)set); } -static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, - struct nft_set_estimate *est) +static u32 nft_hash_buckets(u32 size) { - unsigned int esize; + return roundup_pow_of_two(size * 4 / 3); +} - esize = sizeof(struct nft_hash_elem); - if (desc->size) { - est->size = sizeof(struct nft_hash) + - roundup_pow_of_two(desc->size * 4 / 3) * - sizeof(struct nft_hash_elem *) + - desc->size * esize; - } else { - /* Resizing happens when the load drops below 30% or goes - * above 75%. The average of 52.5% load (approximated by 50%) - * is used for the size estimation of the hash buckets, - * meaning we calculate two buckets per element. - */ - est->size = esize + 2 * sizeof(struct nft_hash_elem *); +static bool nft_rhash_estimate(const struct nft_set_desc *desc, u32 features, + struct nft_set_estimate *est) +{ + est->size = ~0; + est->lookup = NFT_SET_CLASS_O_1; + est->space = NFT_SET_CLASS_O_N; + + return true; +} + +struct nft_hash { + u32 seed; + u32 buckets; + struct hlist_head table[]; +}; + +struct nft_hash_elem { + struct hlist_node node; + struct nft_set_ext ext; +}; + +static bool nft_hash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) +{ + struct nft_hash *priv = nft_set_priv(set); + u8 genmask = nft_genmask_cur(net); + const struct nft_hash_elem *he; + u32 hash; + + hash = jhash(key, set->klen, priv->seed); + hash = reciprocal_scale(hash, priv->buckets); + hlist_for_each_entry_rcu(he, &priv->table[hash], node) { + if (!memcmp(nft_set_ext_key(&he->ext), key, set->klen) && + nft_set_elem_active(&he->ext, genmask)) { + *ext = &he->ext; + return true; + } + } + return false; +} + +/* nft_hash_select_ops() makes sure key size can be either 2 or 4 bytes . */ +static inline u32 nft_hash_key(const u32 *key, u32 klen) +{ + if (klen == 4) + return *key; + + return *(u16 *)key; +} + +static bool nft_hash_lookup_fast(const struct net *net, + const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) +{ + struct nft_hash *priv = nft_set_priv(set); + u8 genmask = nft_genmask_cur(net); + const struct nft_hash_elem *he; + u32 hash, k1, k2; + + k1 = nft_hash_key(key, set->klen); + hash = jhash_1word(k1, priv->seed); + hash = reciprocal_scale(hash, priv->buckets); + hlist_for_each_entry_rcu(he, &priv->table[hash], node) { + k2 = nft_hash_key(nft_set_ext_key(&he->ext)->data, set->klen); + if (k1 == k2 && + nft_set_elem_active(&he->ext, genmask)) { + *ext = &he->ext; + return true; + } + } + return false; +} + +static int nft_hash_insert(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, + struct nft_set_ext **ext) +{ + struct nft_hash_elem *this = elem->priv, *he; + struct nft_hash *priv = nft_set_priv(set); + u8 genmask = nft_genmask_next(net); + u32 hash; + + hash = jhash(nft_set_ext_key(&this->ext), set->klen, priv->seed); + hash = reciprocal_scale(hash, priv->buckets); + hlist_for_each_entry(he, &priv->table[hash], node) { + if (!memcmp(nft_set_ext_key(&this->ext), + nft_set_ext_key(&he->ext), set->klen) && + nft_set_elem_active(&he->ext, genmask)) { + *ext = &he->ext; + return -EEXIST; + } + } + hlist_add_head_rcu(&this->node, &priv->table[hash]); + return 0; +} + +static void nft_hash_activate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_hash_elem *he = elem->priv; + + nft_set_elem_change_active(net, set, &he->ext); +} + +static bool nft_hash_flush(const struct net *net, + const struct nft_set *set, void *priv) +{ + struct nft_hash_elem *he = priv; + + nft_set_elem_change_active(net, set, &he->ext); + return true; +} + +static void *nft_hash_deactivate(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *this = elem->priv, *he; + u8 genmask = nft_genmask_next(net); + u32 hash; + + hash = jhash(nft_set_ext_key(&this->ext), set->klen, priv->seed); + hash = reciprocal_scale(hash, priv->buckets); + hlist_for_each_entry(he, &priv->table[hash], node) { + if (!memcmp(nft_set_ext_key(&this->ext), &elem->key.val, + set->klen) || + nft_set_elem_active(&he->ext, genmask)) { + nft_set_elem_change_active(net, set, &he->ext); + return he; + } } + return NULL; +} + +static void nft_hash_remove(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_hash_elem *he = elem->priv; + + hlist_del_rcu(&he->node); +} + +static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set, + struct nft_set_iter *iter) +{ + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he; + struct nft_set_elem elem; + int i; + + for (i = 0; i < priv->buckets; i++) { + hlist_for_each_entry_rcu(he, &priv->table[i], node) { + if (iter->count < iter->skip) + goto cont; + if (!nft_set_elem_active(&he->ext, iter->genmask)) + goto cont; + + elem.priv = he; + + iter->err = iter->fn(ctx, set, iter, &elem); + if (iter->err < 0) + return; +cont: + iter->count++; + } + } +} + +static unsigned int nft_hash_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) +{ + return sizeof(struct nft_hash) + + nft_hash_buckets(desc->size) * sizeof(struct hlist_head); +} +static int nft_hash_init(const struct nft_set *set, + const struct nft_set_desc *desc, + const struct nlattr * const tb[]) +{ + struct nft_hash *priv = nft_set_priv(set); + + priv->buckets = nft_hash_buckets(desc->size); + get_random_bytes(&priv->seed, sizeof(priv->seed)); + + return 0; +} + +static void nft_hash_destroy(const struct nft_set *set) +{ + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he; + struct hlist_node *next; + int i; + + for (i = 0; i < priv->buckets; i++) { + hlist_for_each_entry_safe(he, next, &priv->table[i], node) { + hlist_del_rcu(&he->node); + nft_set_elem_destroy(set, he, true); + } + } +} + +static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, + struct nft_set_estimate *est) +{ + est->size = sizeof(struct nft_hash) + + nft_hash_buckets(desc->size) * sizeof(struct hlist_head) + + desc->size * sizeof(struct nft_hash_elem); est->lookup = NFT_SET_CLASS_O_1; est->space = NFT_SET_CLASS_O_N; return true; } +static struct nft_set_type nft_hash_type; +static struct nft_set_ops nft_rhash_ops __read_mostly = { + .type = &nft_hash_type, + .privsize = nft_rhash_privsize, + .elemsize = offsetof(struct nft_rhash_elem, ext), + .estimate = nft_rhash_estimate, + .init = nft_rhash_init, + .destroy = nft_rhash_destroy, + .insert = nft_rhash_insert, + .activate = nft_rhash_activate, + .deactivate = nft_rhash_deactivate, + .flush = nft_rhash_flush, + .remove = nft_rhash_remove, + .lookup = nft_rhash_lookup, + .update = nft_rhash_update, + .walk = nft_rhash_walk, + .features = NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, +}; + static struct nft_set_ops nft_hash_ops __read_mostly = { + .type = &nft_hash_type, .privsize = nft_hash_privsize, .elemsize = offsetof(struct nft_hash_elem, ext), .estimate = nft_hash_estimate, @@ -402,20 +616,57 @@ static struct nft_set_ops nft_hash_ops __read_mostly = { .flush = nft_hash_flush, .remove = nft_hash_remove, .lookup = nft_hash_lookup, - .update = nft_hash_update, .walk = nft_hash_walk, - .features = NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, + .features = NFT_SET_MAP | NFT_SET_OBJECT, +}; + +static struct nft_set_ops nft_hash_fast_ops __read_mostly = { + .type = &nft_hash_type, + .privsize = nft_hash_privsize, + .elemsize = offsetof(struct nft_hash_elem, ext), + .estimate = nft_hash_estimate, + .init = nft_hash_init, + .destroy = nft_hash_destroy, + .insert = nft_hash_insert, + .activate = nft_hash_activate, + .deactivate = nft_hash_deactivate, + .flush = nft_hash_flush, + .remove = nft_hash_remove, + .lookup = nft_hash_lookup_fast, + .walk = nft_hash_walk, + .features = NFT_SET_MAP | NFT_SET_OBJECT, +}; + +static const struct nft_set_ops * +nft_hash_select_ops(const struct nft_ctx *ctx, const struct nft_set_desc *desc, + u32 flags) +{ + if (desc->size) { + switch (desc->klen) { + case 2: + case 4: + return &nft_hash_fast_ops; + default: + return &nft_hash_ops; + } + } + + return &nft_rhash_ops; +} + +static struct nft_set_type nft_hash_type __read_mostly = { + .select_ops = nft_hash_select_ops, .owner = THIS_MODULE, }; static int __init nft_hash_module_init(void) { - return nft_register_set(&nft_hash_ops); + return nft_register_set(&nft_hash_type); } static void __exit nft_hash_module_exit(void) { - nft_unregister_set(&nft_hash_ops); + nft_unregister_set(&nft_hash_type); } module_init(nft_hash_module_init); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index fbdbaa00dd5f..bce5382f1d49 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -251,7 +251,8 @@ cont: read_unlock_bh(&priv->lock); } -static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[]) +static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) { return sizeof(struct nft_rbtree); } @@ -283,13 +284,11 @@ static void nft_rbtree_destroy(const struct nft_set *set) static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est) { - unsigned int nsize; - - nsize = sizeof(struct nft_rbtree_elem); if (desc->size) - est->size = sizeof(struct nft_rbtree) + desc->size * nsize; + est->size = sizeof(struct nft_rbtree) + + desc->size * sizeof(struct nft_rbtree_elem); else - est->size = nsize; + est->size = ~0; est->lookup = NFT_SET_CLASS_O_LOG_N; est->space = NFT_SET_CLASS_O_N; @@ -297,7 +296,9 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, return true; } +static struct nft_set_type nft_rbtree_type; static struct nft_set_ops nft_rbtree_ops __read_mostly = { + .type = &nft_rbtree_type, .privsize = nft_rbtree_privsize, .elemsize = offsetof(struct nft_rbtree_elem, ext), .estimate = nft_rbtree_estimate, @@ -311,17 +312,21 @@ static struct nft_set_ops nft_rbtree_ops __read_mostly = { .lookup = nft_rbtree_lookup, .walk = nft_rbtree_walk, .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT, +}; + +static struct nft_set_type nft_rbtree_type __read_mostly = { + .ops = &nft_rbtree_ops, .owner = THIS_MODULE, }; static int __init nft_rbtree_module_init(void) { - return nft_register_set(&nft_rbtree_ops); + return nft_register_set(&nft_rbtree_type); } static void __exit nft_rbtree_module_exit(void) { - nft_unregister_set(&nft_rbtree_ops); + nft_unregister_set(&nft_rbtree_type); } module_init(nft_rbtree_module_init); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 1770c1d9b37f..e1648238a9c9 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1003,14 +1003,10 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size) if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > totalram_pages) return NULL; - if (sz <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) - info = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); - if (!info) { - info = __vmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY, - PAGE_KERNEL); - if (!info) - return NULL; - } + info = kvmalloc(sz, GFP_KERNEL); + if (!info) + return NULL; + memset(info, 0, sizeof(*info)); info->size = size; return info; diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index df7f1df00330..d767e35fff6b 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -127,7 +127,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, daddr, dport, in->ifindex); - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in @@ -197,7 +197,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, daddr, ntohs(dport), in->ifindex); - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index c05fefcec238..71cfa9551d08 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -63,7 +63,8 @@ static const struct nla_policy xt_osf_policy[OSF_ATTR_MAX + 1] = { static int xt_osf_add_callback(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const osf_attrs[]) + const struct nlattr * const osf_attrs[], + struct netlink_ext_ack *extack) { struct xt_osf_user_finger *f; struct xt_osf_finger *kf = NULL, *sf; @@ -107,7 +108,8 @@ static int xt_osf_add_callback(struct net *net, struct sock *ctnl, static int xt_osf_remove_callback(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const osf_attrs[]) + const struct nlattr * const osf_attrs[], + struct netlink_ext_ack *extack) { struct xt_osf_user_finger *f; struct xt_osf_finger *sf; diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c index 4dedb96d1a06..2d2fa1d53ea6 100644 --- a/net/netfilter/xt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -42,8 +42,8 @@ match_packet(const struct sk_buff *skb, bool *hotdrop) { u_int32_t chunkmapcopy[256 / sizeof (u_int32_t)]; - const sctp_chunkhdr_t *sch; - sctp_chunkhdr_t _sch; + const struct sctp_chunkhdr *sch; + struct sctp_chunkhdr _sch; int chunk_match_type = info->chunk_match_type; const struct xt_sctp_flag_info *flag_info = info->flag_info; int flag_count = info->flag_count; @@ -118,8 +118,8 @@ static bool sctp_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_sctp_info *info = par->matchinfo; - const sctp_sctphdr_t *sh; - sctp_sctphdr_t _sh; + const struct sctphdr *sh; + struct sctphdr _sh; if (par->fragoff != 0) { pr_debug("Dropping non-first fragment.. FIXME\n"); @@ -136,13 +136,13 @@ sctp_mt(const struct sk_buff *skb, struct xt_action_param *par) return SCCHECK(ntohs(sh->source) >= info->spts[0] && ntohs(sh->source) <= info->spts[1], - XT_SCTP_SRC_PORTS, info->flags, info->invflags) - && SCCHECK(ntohs(sh->dest) >= info->dpts[0] + XT_SCTP_SRC_PORTS, info->flags, info->invflags) && + SCCHECK(ntohs(sh->dest) >= info->dpts[0] && ntohs(sh->dest) <= info->dpts[1], - XT_SCTP_DEST_PORTS, info->flags, info->invflags) - && SCCHECK(match_packet(skb, par->thoff + sizeof(sctp_sctphdr_t), - info, &par->hotdrop), - XT_SCTP_CHUNK_TYPES, info->flags, info->invflags); + XT_SCTP_DEST_PORTS, info->flags, info->invflags) && + SCCHECK(match_packet(skb, par->thoff + sizeof(_sh), + info, &par->hotdrop), + XT_SCTP_CHUNK_TYPES, info->flags, info->invflags); } static int sctp_mt_check(const struct xt_mtchk_param *par) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 7586d446d7dc..5acee49db90b 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -170,7 +170,7 @@ static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group; NETLINK_CB(new).creds = NETLINK_CB(skb).creds; - memcpy(skb_put(new, len), skb->data, len); + skb_put_data(new, skb->data, len); return new; } @@ -372,7 +372,7 @@ static void netlink_sock_destruct(struct sock *sk) } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); - WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(nlk_sk(sk)->groups); } @@ -575,7 +575,7 @@ static void netlink_remove(struct sock *sk) table = &nl_table[sk->sk_protocol]; if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node, netlink_rhashtable_params)) { - WARN_ON(atomic_read(&sk->sk_refcnt) == 1); + WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } @@ -691,7 +691,7 @@ static void deferred_put_nlk_sk(struct rcu_head *head) struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu); struct sock *sk = &nlk->sk; - if (!atomic_dec_and_test(&sk->sk_refcnt)) + if (!refcount_dec_and_test(&sk->sk_refcnt)) return; if (nlk->cb_running && nlk->cb.done) { @@ -1848,7 +1848,7 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } if (dst_group) { - atomic_inc(&skb->users); + refcount_inc(&skb->users); netlink_broadcast(sk, skb, dst_portid, dst_group, GFP_KERNEL); } err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags&MSG_DONTWAIT); @@ -2104,7 +2104,7 @@ __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int fla struct nlmsghdr *nlh; int size = nlmsg_msg_size(len); - nlh = (struct nlmsghdr *)skb_put(skb, NLMSG_ALIGN(size)); + nlh = skb_put(skb, NLMSG_ALIGN(size)); nlh->nlmsg_type = type; nlh->nlmsg_len = size; nlh->nlmsg_flags = flags; @@ -2226,7 +2226,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, struct netlink_sock *nlk; int ret; - atomic_inc(&skb->users); + refcount_inc(&skb->users); sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid); if (sk == NULL) { @@ -2431,7 +2431,7 @@ int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, int exclude_portid = 0; if (report) { - atomic_inc(&skb->users); + refcount_inc(&skb->users); exclude_portid = portid; } @@ -2568,7 +2568,7 @@ static int netlink_seq_show(struct seq_file *seq, void *v) sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), nlk->cb_running, - atomic_read(&s->sk_refcnt), + refcount_read(&s->sk_refcnt), atomic_read(&s->sk_drops), sock_i_ino(s) ); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index d72a4f1558f2..0c59354e280e 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -149,7 +149,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, nr_neigh->count = 0; nr_neigh->number = nr_neigh_no++; nr_neigh->failed = 0; - atomic_set(&nr_neigh->refcount, 1); + refcount_set(&nr_neigh->refcount, 1); if (ax25_digi != NULL && ax25_digi->ndigi > 0) { nr_neigh->digipeat = kmemdup(ax25_digi, @@ -184,7 +184,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, nr_node->which = 0; nr_node->count = 1; - atomic_set(&nr_node->refcount, 1); + refcount_set(&nr_node->refcount, 1); spin_lock_init(&nr_node->node_lock); nr_node->routes[0].quality = quality; @@ -431,7 +431,7 @@ static int __must_check nr_add_neigh(ax25_address *callsign, nr_neigh->count = 0; nr_neigh->number = nr_neigh_no++; nr_neigh->failed = 0; - atomic_set(&nr_neigh->refcount, 1); + refcount_set(&nr_neigh->refcount, 1); if (ax25_digi != NULL && ax25_digi->ndigi > 0) { nr_neigh->digipeat = kmemdup(ax25_digi, sizeof(*ax25_digi), diff --git a/net/nfc/af_nfc.c b/net/nfc/af_nfc.c index 54e40fa47822..d3e594eb36d0 100644 --- a/net/nfc/af_nfc.c +++ b/net/nfc/af_nfc.c @@ -48,7 +48,7 @@ static int nfc_sock_create(struct net *net, struct socket *sock, int proto, return rc; } -static struct net_proto_family nfc_sock_family_ops = { +static const struct net_proto_family nfc_sock_family_ops = { .owner = THIS_MODULE, .family = PF_NFC, .create = nfc_sock_create, diff --git a/net/nfc/core.c b/net/nfc/core.c index 122bb81da918..5cf33df888c3 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -982,6 +982,8 @@ static void nfc_release(struct device *d) kfree(se); } + ida_simple_remove(&nfc_index_ida, dev->idx); + kfree(dev); } @@ -1056,6 +1058,7 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, int tx_headroom, int tx_tailroom) { struct nfc_dev *dev; + int rc; if (!ops->start_poll || !ops->stop_poll || !ops->activate_target || !ops->deactivate_target || !ops->im_transceive) @@ -1068,6 +1071,15 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, if (!dev) return NULL; + rc = ida_simple_get(&nfc_index_ida, 0, 0, GFP_KERNEL); + if (rc < 0) + goto err_free_dev; + dev->idx = rc; + + dev->dev.class = &nfc_class; + dev_set_name(&dev->dev, "nfc%d", dev->idx); + device_initialize(&dev->dev); + dev->ops = ops; dev->supported_protocols = supported_protocols; dev->tx_headroom = tx_headroom; @@ -1090,6 +1102,11 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, } return dev; + +err_free_dev: + kfree(dev); + + return ERR_PTR(rc); } EXPORT_SYMBOL(nfc_allocate_device); @@ -1104,14 +1121,6 @@ int nfc_register_device(struct nfc_dev *dev) pr_debug("dev_name=%s\n", dev_name(&dev->dev)); - dev->idx = ida_simple_get(&nfc_index_ida, 0, 0, GFP_KERNEL); - if (dev->idx < 0) - return dev->idx; - - dev->dev.class = &nfc_class; - dev_set_name(&dev->dev, "nfc%d", dev->idx); - device_initialize(&dev->dev); - mutex_lock(&nfc_devlist_mutex); nfc_devlist_generation++; rc = device_add(&dev->dev); @@ -1149,12 +1158,10 @@ EXPORT_SYMBOL(nfc_register_device); */ void nfc_unregister_device(struct nfc_dev *dev) { - int rc, id; + int rc; pr_debug("dev_name=%s\n", dev_name(&dev->dev)); - id = dev->idx; - if (dev->rfkill) { rfkill_unregister(dev->rfkill); rfkill_destroy(dev->rfkill); @@ -1179,8 +1186,6 @@ void nfc_unregister_device(struct nfc_dev *dev) nfc_devlist_generation++; device_del(&dev->dev); mutex_unlock(&nfc_devlist_mutex); - - ida_simple_remove(&nfc_index_ida, id); } EXPORT_SYMBOL(nfc_unregister_device); diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index 0fd5518bf252..de6dd37d04c7 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -74,8 +74,8 @@ void digital_skb_add_crc(struct sk_buff *skb, crc_func_t crc_func, u16 init, if (msb_first) crc = __fswab16(crc); - *skb_put(skb, 1) = crc & 0xFF; - *skb_put(skb, 1) = (crc >> 8) & 0xFF; + skb_put_u8(skb, crc & 0xFF); + skb_put_u8(skb, (crc >> 8) & 0xFF); } int digital_skb_check_crc(struct sk_buff *skb, crc_func_t crc_func, @@ -240,7 +240,7 @@ int digital_send_cmd(struct nfc_digital_dev *ddev, u8 cmd_type, { struct digital_cmd *cmd; - cmd = kzalloc(sizeof(struct digital_cmd), GFP_KERNEL); + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); if (!cmd) return -ENOMEM; @@ -287,7 +287,7 @@ static int digital_tg_listen_mdaa(struct nfc_digital_dev *ddev, u8 rf_tech) { struct digital_tg_mdaa_params *params; - params = kzalloc(sizeof(struct digital_tg_mdaa_params), GFP_KERNEL); + params = kzalloc(sizeof(*params), GFP_KERNEL); if (!params) return -ENOMEM; @@ -706,11 +706,9 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target, struct digital_data_exch *data_exch; int rc; - data_exch = kzalloc(sizeof(struct digital_data_exch), GFP_KERNEL); - if (!data_exch) { - pr_err("Failed to allocate data_exch struct\n"); + data_exch = kzalloc(sizeof(*data_exch), GFP_KERNEL); + if (!data_exch) return -ENOMEM; - } data_exch->cb = cb; data_exch->cb_context = cb_context; @@ -764,7 +762,7 @@ struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops, !ops->switch_rf || (ops->tg_listen_md && !ops->tg_get_rf_tech)) return NULL; - ddev = kzalloc(sizeof(struct nfc_digital_dev), GFP_KERNEL); + ddev = kzalloc(sizeof(*ddev), GFP_KERNEL); if (!ddev) return NULL; diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c index f864ce19e13d..4f9a973988b2 100644 --- a/net/nfc/digital_dep.c +++ b/net/nfc/digital_dep.c @@ -151,7 +151,7 @@ static const u8 digital_payload_bits_map[4] = { * 0 <= wt <= 14 (given by the target by the TO field of ATR_RES response) */ #define DIGITAL_NFC_DEP_IN_MAX_WT 14 -#define DIGITAL_NFC_DEP_TG_MAX_WT 8 +#define DIGITAL_NFC_DEP_TG_MAX_WT 14 static const u16 digital_rwt_map[DIGITAL_NFC_DEP_IN_MAX_WT + 1] = { 100, 101, 101, 102, 105, 110, 119, 139, 177, 255, @@ -185,7 +185,7 @@ static void digital_skb_push_dep_sod(struct nfc_digital_dev *ddev, skb->data[0] = skb->len; if (ddev->curr_rf_tech == NFC_DIGITAL_RF_TECH_106A) - *skb_push(skb, sizeof(u8)) = DIGITAL_NFC_DEP_NFCA_SOD_SB; + *(u8 *)skb_push(skb, sizeof(u8)) = DIGITAL_NFC_DEP_NFCA_SOD_SB; } static int digital_skb_pull_dep_sod(struct nfc_digital_dev *ddev, @@ -226,8 +226,7 @@ digital_send_dep_data_prep(struct nfc_digital_dev *ddev, struct sk_buff *skb, return ERR_PTR(-ENOMEM); } - memcpy(skb_put(new_skb, ddev->remote_payload_max), skb->data, - ddev->remote_payload_max); + skb_put_data(new_skb, skb->data, ddev->remote_payload_max); skb_pull(skb, ddev->remote_payload_max); ddev->chaining_skb = skb; @@ -277,8 +276,7 @@ digital_recv_dep_data_gather(struct nfc_digital_dev *ddev, u8 pfb, ddev->chaining_skb = new_skb; } - memcpy(skb_put(ddev->chaining_skb, resp->len), resp->data, - resp->len); + skb_put_data(ddev->chaining_skb, resp->data, resp->len); kfree_skb(resp); resp = NULL; @@ -525,7 +523,7 @@ int digital_in_send_atr_req(struct nfc_digital_dev *ddev, if (gb_len) { atr_req->pp |= DIGITAL_GB_BIT; - memcpy(skb_put(skb, gb_len), gb, gb_len); + skb_put_data(skb, gb, gb_len); } digital_skb_push_dep_sod(ddev, skb); @@ -656,7 +654,7 @@ static int digital_in_send_rtox(struct nfc_digital_dev *ddev, if (!skb) return -ENOMEM; - *skb_put(skb, 1) = rtox; + skb_put_u8(skb, rtox); skb_push(skb, sizeof(struct digital_dep_req_res)); @@ -1012,8 +1010,7 @@ static int digital_tg_send_ack(struct nfc_digital_dev *ddev, if (ddev->did) { dep_res->pfb |= DIGITAL_NFC_DEP_PFB_DID_BIT; - memcpy(skb_put(skb, sizeof(ddev->did)), &ddev->did, - sizeof(ddev->did)); + skb_put_data(skb, &ddev->did, sizeof(ddev->did)); } ddev->curr_nfc_dep_pni = @@ -1057,8 +1054,7 @@ static int digital_tg_send_atn(struct nfc_digital_dev *ddev) if (ddev->did) { dep_res->pfb |= DIGITAL_NFC_DEP_PFB_DID_BIT; - memcpy(skb_put(skb, sizeof(ddev->did)), &ddev->did, - sizeof(ddev->did)); + skb_put_data(skb, &ddev->did, sizeof(ddev->did)); } digital_skb_push_dep_sod(ddev, skb); @@ -1325,8 +1321,7 @@ int digital_tg_send_dep_res(struct nfc_digital_dev *ddev, struct sk_buff *skb) if (ddev->did) { dep_res->pfb |= DIGITAL_NFC_DEP_PFB_DID_BIT; - memcpy(skb_put(skb, sizeof(ddev->did)), &ddev->did, - sizeof(ddev->did)); + skb_put_data(skb, &ddev->did, sizeof(ddev->did)); } ddev->curr_nfc_dep_pni = diff --git a/net/nfc/digital_technology.c b/net/nfc/digital_technology.c index d9080dec5d27..2021d1d58a75 100644 --- a/net/nfc/digital_technology.c +++ b/net/nfc/digital_technology.c @@ -27,6 +27,7 @@ #define DIGITAL_SDD_RES_CT 0x88 #define DIGITAL_SDD_RES_LEN 5 +#define DIGITAL_SEL_RES_LEN 1 #define DIGITAL_SEL_RES_NFCID1_COMPLETE(sel_res) (!((sel_res) & 0x04)) #define DIGITAL_SEL_RES_IS_T2T(sel_res) (!((sel_res) & 0x60)) @@ -266,8 +267,8 @@ static int digital_in_send_rats(struct nfc_digital_dev *ddev, if (!skb) return -ENOMEM; - *skb_put(skb, 1) = DIGITAL_RATS_BYTE1; - *skb_put(skb, 1) = DIGITAL_RATS_PARAM; + skb_put_u8(skb, DIGITAL_RATS_BYTE1); + skb_put_u8(skb, DIGITAL_RATS_PARAM); rc = digital_in_send_cmd(ddev, skb, 30, digital_in_recv_ats, target); @@ -299,7 +300,7 @@ static void digital_in_recv_sel_res(struct nfc_digital_dev *ddev, void *arg, } } - if (!resp->len) { + if (resp->len != DIGITAL_SEL_RES_LEN) { rc = -EIO; goto exit; } @@ -470,8 +471,8 @@ static int digital_in_send_sdd_req(struct nfc_digital_dev *ddev, else sel_cmd = DIGITAL_CMD_SEL_REQ_CL3; - *skb_put(skb, sizeof(u8)) = sel_cmd; - *skb_put(skb, sizeof(u8)) = DIGITAL_SDD_REQ_SEL_PAR; + skb_put_u8(skb, sel_cmd); + skb_put_u8(skb, DIGITAL_SDD_REQ_SEL_PAR); return digital_in_send_cmd(ddev, skb, 30, digital_in_recv_sdd_res, target); @@ -541,7 +542,7 @@ int digital_in_send_sens_req(struct nfc_digital_dev *ddev, u8 rf_tech) if (!skb) return -ENOMEM; - *skb_put(skb, sizeof(u8)) = DIGITAL_CMD_SENS_REQ; + skb_put_u8(skb, DIGITAL_CMD_SENS_REQ); rc = digital_in_send_cmd(ddev, skb, 30, digital_in_recv_sens_res, NULL); if (rc) @@ -625,8 +626,7 @@ static int digital_in_send_attrib_req(struct nfc_digital_dev *ddev, if (!skb) return -ENOMEM; - attrib_req = (struct digital_attrib_req *)skb_put(skb, - sizeof(*attrib_req)); + attrib_req = skb_put(skb, sizeof(*attrib_req)); attrib_req->cmd = DIGITAL_CMD_ATTRIB_REQ; memcpy(attrib_req->nfcid0, sensb_res->nfcid0, @@ -730,8 +730,7 @@ int digital_in_send_sensb_req(struct nfc_digital_dev *ddev, u8 rf_tech) if (!skb) return -ENOMEM; - sensb_req = (struct digital_sensb_req *)skb_put(skb, - sizeof(*sensb_req)); + sensb_req = skb_put(skb, sizeof(*sensb_req)); sensb_req->cmd = DIGITAL_CMD_SENSB_REQ; sensb_req->afi = 0x00; /* All families and sub-families */ @@ -830,7 +829,7 @@ int digital_in_send_sensf_req(struct nfc_digital_dev *ddev, u8 rf_tech) sensf_req->rc = 0; sensf_req->tsn = 0; - *skb_push(skb, 1) = size + 1; + *(u8 *)skb_push(skb, 1) = size + 1; if (!DIGITAL_DRV_CAPS_IN_CRC(ddev)) digital_skb_add_crc_f(skb); @@ -939,7 +938,7 @@ static int digital_tg_send_sel_res(struct nfc_digital_dev *ddev) if (!skb) return -ENOMEM; - *skb_put(skb, 1) = DIGITAL_SEL_RES_NFC_DEP; + skb_put_u8(skb, DIGITAL_SEL_RES_NFC_DEP); if (!DIGITAL_DRV_CAPS_TG_CRC(ddev)) digital_skb_add_crc_a(skb); @@ -1163,7 +1162,7 @@ static int digital_tg_send_sensf_res(struct nfc_digital_dev *ddev, break; } - *skb_push(skb, sizeof(u8)) = size + 1; + *(u8 *)skb_push(skb, sizeof(u8)) = size + 1; if (!DIGITAL_DRV_CAPS_TG_CRC(ddev)) digital_skb_add_crc_f(skb); diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index 2b0f0ac498d2..b740fef0acc5 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -727,7 +727,7 @@ static int hci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target, break; } - *skb_push(skb, 1) = 0; /* CTR, see spec:10.2.2.1 */ + *(u8 *)skb_push(skb, 1) = 0; /* CTR, see spec:10.2.2.1 */ hdev->async_cb_type = HCI_CB_TYPE_TRANSCEIVE; hdev->async_cb = cb; @@ -874,13 +874,13 @@ static void nfc_hci_recv_from_llc(struct nfc_hci_dev *hdev, struct sk_buff *skb) return; } - *skb_put(hcp_skb, NFC_HCI_HCP_PACKET_HEADER_LEN) = pipe; + skb_put_u8(hcp_skb, pipe); skb_queue_walk(&hdev->rx_hcp_frags, frag_skb) { msg_len = frag_skb->len - NFC_HCI_HCP_PACKET_HEADER_LEN; - memcpy(skb_put(hcp_skb, msg_len), - frag_skb->data + NFC_HCI_HCP_PACKET_HEADER_LEN, - msg_len); + skb_put_data(hcp_skb, + frag_skb->data + NFC_HCI_HCP_PACKET_HEADER_LEN, + msg_len); } skb_queue_purge(&hdev->rx_hcp_frags); diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index 401c7e255273..17e59a009ce6 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -160,7 +160,7 @@ static int llc_shdlc_send_s_frame(struct llc_shdlc *shdlc, if (skb == NULL) return -ENOMEM; - *skb_push(skb, 1) = SHDLC_CONTROL_HEAD_S | (sframe_type << 3) | nr; + *(u8 *)skb_push(skb, 1) = SHDLC_CONTROL_HEAD_S | (sframe_type << 3) | nr; r = shdlc->xmit_to_drv(shdlc->hdev, skb); @@ -178,7 +178,7 @@ static int llc_shdlc_send_u_frame(struct llc_shdlc *shdlc, pr_debug("uframe_modifier=%d\n", uframe_modifier); - *skb_push(skb, 1) = SHDLC_CONTROL_HEAD_U | uframe_modifier; + *(u8 *)skb_push(skb, 1) = SHDLC_CONTROL_HEAD_U | uframe_modifier; r = shdlc->xmit_to_drv(shdlc->hdev, skb); @@ -382,8 +382,8 @@ static int llc_shdlc_connect_initiate(struct llc_shdlc *shdlc) if (skb == NULL) return -ENOMEM; - *skb_put(skb, 1) = SHDLC_MAX_WINDOW; - *skb_put(skb, 1) = SHDLC_SREJ_SUPPORT ? 1 : 0; + skb_put_u8(skb, SHDLC_MAX_WINDOW); + skb_put_u8(skb, SHDLC_SREJ_SUPPORT ? 1 : 0); return llc_shdlc_send_u_frame(shdlc, skb, U_FRAME_RSET); } @@ -551,8 +551,8 @@ static void llc_shdlc_handle_send_queue(struct llc_shdlc *shdlc) skb = skb_dequeue(&shdlc->send_q); - *skb_push(skb, 1) = SHDLC_CONTROL_HEAD_I | (shdlc->ns << 3) | - shdlc->nr; + *(u8 *)skb_push(skb, 1) = SHDLC_CONTROL_HEAD_I | (shdlc->ns << 3) | + shdlc->nr; pr_debug("Sending I-Frame %d, waiting to rcv %d\n", shdlc->ns, shdlc->nr); diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index c5959ce503e6..367d8c027101 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -298,7 +298,7 @@ static struct sk_buff *llcp_add_header(struct sk_buff *pdu, pr_debug("header 0x%x 0x%x\n", header[0], header[1]); - memcpy(skb_put(pdu, LLCP_HEADER_SIZE), header, LLCP_HEADER_SIZE); + skb_put_data(pdu, header, LLCP_HEADER_SIZE); return pdu; } @@ -311,7 +311,7 @@ static struct sk_buff *llcp_add_tlv(struct sk_buff *pdu, u8 *tlv, if (tlv == NULL) return NULL; - memcpy(skb_put(pdu, tlv_length), tlv, tlv_length); + skb_put_data(pdu, tlv, tlv_length); return pdu; } @@ -549,7 +549,7 @@ int nfc_llcp_send_snl_sdres(struct nfc_llcp_local *local, return PTR_ERR(skb); hlist_for_each_entry_safe(sdp, n, tlv_list, node) { - memcpy(skb_put(skb, sdp->tlv_len), sdp->tlv, sdp->tlv_len); + skb_put_data(skb, sdp->tlv, sdp->tlv_len); hlist_del(&sdp->node); @@ -581,8 +581,7 @@ int nfc_llcp_send_snl_sdreq(struct nfc_llcp_local *local, hlist_for_each_entry_safe(sdreq, n, tlv_list, node) { pr_debug("tid %d for %s\n", sdreq->tid, sdreq->uri); - memcpy(skb_put(skb, sdreq->tlv_len), sdreq->tlv, - sdreq->tlv_len); + skb_put_data(skb, sdreq->tlv, sdreq->tlv_len); hlist_del(&sdreq->node); @@ -622,7 +621,7 @@ int nfc_llcp_send_dm(struct nfc_llcp_local *local, u8 ssap, u8 dsap, u8 reason) skb = llcp_add_header(skb, dsap, ssap, LLCP_PDU_DM); - memcpy(skb_put(skb, 1), &reason, 1); + skb_put_data(skb, &reason, 1); skb_queue_head(&local->tx_queue, skb); @@ -693,7 +692,7 @@ int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock, skb_put(pdu, LLCP_SEQUENCE_SIZE); if (likely(frag_len > 0)) - memcpy(skb_put(pdu, frag_len), msg_ptr, frag_len); + skb_put_data(pdu, msg_ptr, frag_len); skb_queue_tail(&sock->tx_queue, pdu); @@ -759,7 +758,7 @@ int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap, pdu = llcp_add_header(pdu, dsap, ssap, LLCP_PDU_UI); if (likely(frag_len > 0)) - memcpy(skb_put(pdu, frag_len), msg_ptr, frag_len); + skb_put_data(pdu, msg_ptr, frag_len); /* No need to check for the peer RW for UI frames */ skb_queue_tail(&local->tx_queue, pdu); diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index e69786c6804c..02eef5cf3cce 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -1390,7 +1390,7 @@ static void nfc_llcp_recv_agf(struct nfc_llcp_local *local, struct sk_buff *skb) return; } - memcpy(skb_put(new_skb, pdu_len), skb->data, pdu_len); + skb_put_data(new_skb, skb->data, pdu_len); nfc_llcp_rx_skb(local, new_skb); diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 2ffb18e73df6..fb7afcaa3004 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -77,7 +77,8 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) struct sockaddr_nfc_llcp llcp_addr; int len, ret = 0; - if (!addr || addr->sa_family != AF_NFC) + if (!addr || alen < offsetofend(struct sockaddr, sa_family) || + addr->sa_family != AF_NFC) return -EINVAL; pr_debug("sk %p addr %p family %d\n", sk, addr, addr->sa_family); @@ -151,7 +152,8 @@ static int llcp_raw_sock_bind(struct socket *sock, struct sockaddr *addr, struct sockaddr_nfc_llcp llcp_addr; int len, ret = 0; - if (!addr || addr->sa_family != AF_NFC) + if (!addr || alen < offsetofend(struct sockaddr, sa_family) || + addr->sa_family != AF_NFC) return -EINVAL; pr_debug("sk %p addr %p family %d\n", sk, addr, addr->sa_family); @@ -662,8 +664,7 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, pr_debug("sock %p sk %p flags 0x%x\n", sock, sk, flags); - if (!addr || len < sizeof(struct sockaddr_nfc) || - addr->sa_family != AF_NFC) + if (!addr || len < sizeof(*addr) || addr->sa_family != AF_NFC) return -EINVAL; if (addr->service_name_len == 0 && addr->dsap == 0) diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 61fff422424f..c25e9b4179c3 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -73,11 +73,10 @@ int nci_get_conn_info_by_dest_type_params(struct nci_dev *ndev, u8 dest_type, if (conn_info->dest_type == dest_type) { if (!params) return conn_info->conn_id; - if (conn_info) { - if (params->id == conn_info->dest_params->id && - params->protocol == conn_info->dest_params->protocol) - return conn_info->conn_id; - } + + if (params->id == conn_info->dest_params->id && + params->protocol == conn_info->dest_params->protocol) + return conn_info->conn_id; } } @@ -462,7 +461,7 @@ int nci_nfcc_loopback(struct nci_dev *ndev, void *data, size_t data_len, return -ENOMEM; skb_reserve(skb, NCI_DATA_HDR_SIZE); - memcpy(skb_put(skb, data_len), data, data_len); + skb_put_data(skb, data, data_len); loopback_data.conn_id = conn_id; loopback_data.data = skb; @@ -1173,8 +1172,7 @@ struct nci_dev *nci_allocate_device(struct nci_ops *ops, return ndev; free_nfc: - kfree(ndev->nfc_dev); - + nfc_free_device(ndev->nfc_dev); free_nci: kfree(ndev); return NULL; @@ -1341,7 +1339,7 @@ int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload) return -ENOMEM; } - hdr = (struct nci_ctrl_hdr *) skb_put(skb, NCI_CTRL_HDR_SIZE); + hdr = skb_put(skb, NCI_CTRL_HDR_SIZE); hdr->gid = nci_opcode_gid(opcode); hdr->oid = nci_opcode_oid(opcode); hdr->plen = plen; @@ -1350,7 +1348,7 @@ int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload) nci_pbf_set((__u8 *)hdr, NCI_PBF_LAST); if (plen) - memcpy(skb_put(skb, plen), payload, plen); + skb_put_data(skb, payload, plen); skb_queue_tail(&ndev->cmd_q, skb); queue_work(ndev->cmd_wq, &ndev->cmd_work); diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index dbd24254412a..908f25e3773e 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -81,7 +81,7 @@ static inline void nci_push_data_hdr(struct nci_dev *ndev, struct nci_data_hdr *hdr; int plen = skb->len; - hdr = (struct nci_data_hdr *) skb_push(skb, NCI_DATA_HDR_SIZE); + hdr = skb_push(skb, NCI_DATA_HDR_SIZE); hdr->conn_id = conn_id; hdr->rfu = 0; hdr->plen = plen; @@ -138,7 +138,7 @@ static int nci_queue_tx_data_frags(struct nci_dev *ndev, skb_reserve(skb_frag, NCI_DATA_HDR_SIZE); /* first, copy the data */ - memcpy(skb_put(skb_frag, frag_len), data, frag_len); + skb_put_data(skb_frag, data, frag_len); /* second, set the header */ nci_push_data_hdr(ndev, conn_id, skb_frag, diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index a0ab26d535dc..ddfc52ac1f9b 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -170,7 +170,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, return -ENOMEM; skb_reserve(skb, NCI_DATA_HDR_SIZE + 2); - *skb_push(skb, 1) = data_type; + *(u8 *)skb_push(skb, 1) = data_type; do { len = conn_info->max_pkt_payload_len; @@ -184,10 +184,10 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, len = conn_info->max_pkt_payload_len - skb->len - 1; } - *skb_push(skb, 1) = cb; + *(u8 *)skb_push(skb, 1) = cb; if (len > 0) - memcpy(skb_put(skb, len), data + i, len); + skb_put_data(skb, data + i, len); r = nci_send_data(ndev, conn_info->conn_id, skb); if (r < 0) @@ -472,12 +472,13 @@ void nci_hci_data_received_cb(void *context, return; } - *skb_put(hcp_skb, NCI_HCI_HCP_PACKET_HEADER_LEN) = pipe; + skb_put_u8(hcp_skb, pipe); skb_queue_walk(&ndev->hci_dev->rx_hcp_frags, frag_skb) { msg_len = frag_skb->len - NCI_HCI_HCP_PACKET_HEADER_LEN; - memcpy(skb_put(hcp_skb, msg_len), frag_skb->data + - NCI_HCI_HCP_PACKET_HEADER_LEN, msg_len); + skb_put_data(hcp_skb, + frag_skb->data + NCI_HCI_HCP_PACKET_HEADER_LEN, + msg_len); } skb_queue_purge(&ndev->hci_dev->rx_hcp_frags); diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c index d904cd2f1442..452f4c16b7a9 100644 --- a/net/nfc/nci/spi.c +++ b/net/nfc/nci/spi.c @@ -86,8 +86,8 @@ int nci_spi_send(struct nci_spi *nspi, u16 crc; crc = crc_ccitt(CRC_INIT, skb->data, skb->len); - *skb_put(skb, 1) = crc >> 8; - *skb_put(skb, 1) = crc & 0xFF; + skb_put_u8(skb, crc >> 8); + skb_put_u8(skb, crc & 0xFF); } if (write_handshake_completion) { @@ -172,8 +172,8 @@ static int send_acknowledge(struct nci_spi *nspi, u8 acknowledge) hdr[3] = 0; crc = crc_ccitt(CRC_INIT, skb->data, skb->len); - *skb_put(skb, 1) = crc >> 8; - *skb_put(skb, 1) = crc & 0xFF; + skb_put_u8(skb, crc >> 8); + skb_put_u8(skb, crc & 0xFF); ret = __nci_spi_send(nspi, skb, 0); @@ -238,8 +238,8 @@ static struct sk_buff *__nci_spi_read(struct nci_spi *nspi) goto receive_error; if (nspi->acknowledge_mode == NCI_SPI_CRC_ENABLED) { - *skb_push(skb, 1) = resp_hdr[1]; - *skb_push(skb, 1) = resp_hdr[0]; + *(u8 *)skb_push(skb, 1) = resp_hdr[1]; + *(u8 *)skb_push(skb, 1) = resp_hdr[0]; } return skb; diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index c468eabd6943..8d104c1db628 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -355,7 +355,7 @@ static int nci_uart_default_recv_buf(struct nci_uart *nu, const u8 *data, /* Eat byte after byte till full packet header is received */ if (nu->rx_skb->len < NCI_CTRL_HDR_SIZE) { - *skb_put(nu->rx_skb, 1) = *data++; + skb_put_u8(nu->rx_skb, *data++); --count; continue; } @@ -371,7 +371,7 @@ static int nci_uart_default_recv_buf(struct nci_uart *nu, const u8 *data, chunk_len = nu->rx_packet_len - nu->rx_skb->len; if (count < chunk_len) chunk_len = count; - memcpy(skb_put(nu->rx_skb, chunk_len), data, chunk_len); + skb_put_data(nu->rx_skb, data, chunk_len); data += chunk_len; count -= chunk_len; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 6b0850e63e09..b251fb936a27 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -907,7 +907,9 @@ static int nfc_genl_activate_target(struct sk_buff *skb, struct genl_info *info) u32 device_idx, target_idx, protocol; int rc; - if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || + !info->attrs[NFC_ATTR_TARGET_INDEX] || + !info->attrs[NFC_ATTR_PROTOCOLS]) return -EINVAL; device_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index e386e6c90b17..e2188deb08dc 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -142,7 +142,7 @@ error: static int rawsock_add_header(struct sk_buff *skb) { - *skb_push(skb, NFC_HEADER_SIZE) = 0; + *(u8 *)skb_push(skb, NFC_HEADER_SIZE) = 0; return 0; } diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 08679ebb3068..e3c4c6c3fef7 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -629,6 +629,34 @@ ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, return ct; } +static +struct nf_conn *ovs_ct_executed(struct net *net, + const struct sw_flow_key *key, + const struct ovs_conntrack_info *info, + struct sk_buff *skb, + bool *ct_executed) +{ + struct nf_conn *ct = NULL; + + /* If no ct, check if we have evidence that an existing conntrack entry + * might be found for this skb. This happens when we lose a skb->_nfct + * due to an upcall, or if the direction is being forced. If the + * connection was not confirmed, it is not cached and needs to be run + * through conntrack again. + */ + *ct_executed = (key->ct_state & OVS_CS_F_TRACKED) && + !(key->ct_state & OVS_CS_F_INVALID) && + (key->ct_zone == info->zone.id); + + if (*ct_executed || (!key->ct_state && info->force)) { + ct = ovs_ct_find_existing(net, &info->zone, info->family, skb, + !!(key->ct_state & + OVS_CS_F_NAT_MASK)); + } + + return ct; +} + /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */ static bool skb_nfct_cached(struct net *net, const struct sw_flow_key *key, @@ -637,24 +665,17 @@ static bool skb_nfct_cached(struct net *net, { enum ip_conntrack_info ctinfo; struct nf_conn *ct; + bool ct_executed = true; ct = nf_ct_get(skb, &ctinfo); - /* If no ct, check if we have evidence that an existing conntrack entry - * might be found for this skb. This happens when we lose a skb->_nfct - * due to an upcall. If the connection was not confirmed, it is not - * cached and needs to be run through conntrack again. - */ - if (!ct && key->ct_state & OVS_CS_F_TRACKED && - !(key->ct_state & OVS_CS_F_INVALID) && - key->ct_zone == info->zone.id) { - ct = ovs_ct_find_existing(net, &info->zone, info->family, skb, - !!(key->ct_state - & OVS_CS_F_NAT_MASK)); - if (ct) - nf_ct_get(skb, &ctinfo); - } if (!ct) + ct = ovs_ct_executed(net, key, info, skb, &ct_executed); + + if (ct) + nf_ct_get(skb, &ctinfo); + else return false; + if (!net_eq(net, read_pnet(&ct->ct_net))) return false; if (!nf_ct_zone_equal_any(info->ct, nf_ct_zone(ct))) @@ -679,7 +700,7 @@ static bool skb_nfct_cached(struct net *net, return false; } - return true; + return ct_executed; } #ifdef CONFIG_NF_NAT_NEEDED diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 7b17da9a94a0..45fe8c8a884d 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -413,7 +413,7 @@ static void pad_packet(struct datapath *dp, struct sk_buff *skb) size_t plen = NLA_ALIGN(skb->len) - skb->len; if (plen > 0) - memset(skb_put(skb, plen), 0, plen); + skb_put_zero(skb, plen); } } @@ -453,7 +453,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, /* Complete checksum if needed */ if (skb->ip_summed == CHECKSUM_PARTIAL && - (err = skb_checksum_help(skb))) + (err = skb_csum_hwoffload_help(skb, 0))) goto out; /* Older versions of OVS user space enforce alignment of the last @@ -1090,6 +1090,58 @@ static struct sw_flow_actions *get_flow_actions(struct net *net, return acts; } +/* Factor out match-init and action-copy to avoid + * "Wframe-larger-than=1024" warning. Because mask is only + * used to get actions, we new a function to save some + * stack space. + * + * If there are not key and action attrs, we return 0 + * directly. In the case, the caller will also not use the + * match as before. If there is action attr, we try to get + * actions and save them to *acts. Before returning from + * the function, we reset the match->mask pointer. Because + * we should not to return match object with dangling reference + * to mask. + * */ +static int ovs_nla_init_match_and_action(struct net *net, + struct sw_flow_match *match, + struct sw_flow_key *key, + struct nlattr **a, + struct sw_flow_actions **acts, + bool log) +{ + struct sw_flow_mask mask; + int error = 0; + + if (a[OVS_FLOW_ATTR_KEY]) { + ovs_match_init(match, key, true, &mask); + error = ovs_nla_get_match(net, match, a[OVS_FLOW_ATTR_KEY], + a[OVS_FLOW_ATTR_MASK], log); + if (error) + goto error; + } + + if (a[OVS_FLOW_ATTR_ACTIONS]) { + if (!a[OVS_FLOW_ATTR_KEY]) { + OVS_NLERR(log, + "Flow key attribute not present in set flow."); + return -EINVAL; + } + + *acts = get_flow_actions(net, a[OVS_FLOW_ATTR_ACTIONS], key, + &mask, log); + if (IS_ERR(*acts)) { + error = PTR_ERR(*acts); + goto error; + } + } + + /* On success, error is 0. */ +error: + match->mask = NULL; + return error; +} + static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); @@ -1097,7 +1149,6 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) struct ovs_header *ovs_header = info->userhdr; struct sw_flow_key key; struct sw_flow *flow; - struct sw_flow_mask mask; struct sk_buff *reply = NULL; struct datapath *dp; struct sw_flow_actions *old_acts = NULL, *acts = NULL; @@ -1109,34 +1160,18 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) bool ufid_present; ufid_present = ovs_nla_get_ufid(&sfid, a[OVS_FLOW_ATTR_UFID], log); - if (a[OVS_FLOW_ATTR_KEY]) { - ovs_match_init(&match, &key, true, &mask); - error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], - a[OVS_FLOW_ATTR_MASK], log); - } else if (!ufid_present) { + if (!a[OVS_FLOW_ATTR_KEY] && !ufid_present) { OVS_NLERR(log, "Flow set message rejected, Key attribute missing."); - error = -EINVAL; + return -EINVAL; } + + error = ovs_nla_init_match_and_action(net, &match, &key, a, + &acts, log); if (error) goto error; - /* Validate actions. */ - if (a[OVS_FLOW_ATTR_ACTIONS]) { - if (!a[OVS_FLOW_ATTR_KEY]) { - OVS_NLERR(log, - "Flow key attribute not present in set flow."); - error = -EINVAL; - goto error; - } - - acts = get_flow_actions(net, a[OVS_FLOW_ATTR_ACTIONS], &key, - &mask, log); - if (IS_ERR(acts)) { - error = PTR_ERR(acts); - goto error; - } - + if (acts) { /* Can allocate before locking if have acts. */ reply = ovs_flow_cmd_alloc_info(acts, &sfid, info, false, ufid_flags); diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index da931bdef8a7..5d8dcd88815f 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -98,8 +98,8 @@ struct datapath { * @input_vport: The original vport packet came in on. This value is cached * when a packet is received by OVS. * @mru: The maximum received fragement size; 0 if the packet is not - * @cutlen: The number of bytes from the packet end to be removed. * fragmented. + * @cutlen: The number of bytes from the packet end to be removed. */ struct ovs_skb_cb { struct vport *input_vport; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 7e1d8a2afa63..f07d10ac35d8 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2202,7 +2202,9 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, if (start < 0) return start; - tun_dst = metadata_dst_alloc(key.tun_opts_len, GFP_KERNEL); + tun_dst = metadata_dst_alloc(key.tun_opts_len, METADATA_IP_TUNNEL, + GFP_KERNEL); + if (!tun_dst) return -ENOMEM; diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 869acb3b3d3f..7e6301b2ec4d 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -40,14 +40,14 @@ static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb) if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port))) return -EMSGSIZE; - if (vxlan->flags & VXLAN_F_GBP) { + if (vxlan->cfg.flags & VXLAN_F_GBP) { struct nlattr *exts; exts = nla_nest_start(skb, OVS_TUNNEL_ATTR_EXTENSION); if (!exts) return -EMSGSIZE; - if (vxlan->flags & VXLAN_F_GBP && + if (vxlan->cfg.flags & VXLAN_F_GBP && nla_put_flag(skb, OVS_VXLAN_EXT_GBP)) return -EMSGSIZE; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e3eeed19cc7a..008bb34ee324 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -188,7 +188,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, #define BLOCK_PRIV(x) ((void *)((char *)(x) + BLOCK_O2PRIV(x))) struct packet_sock; -static int tpacket_snd(struct packet_sock *po, struct msghdr *msg); static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); @@ -196,8 +195,7 @@ static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status); static void packet_increment_head(struct packet_ring_buffer *buff); -static int prb_curr_blk_in_use(struct tpacket_kbdq_core *, - struct tpacket_block_desc *); +static int prb_curr_blk_in_use(struct tpacket_block_desc *); static void *prb_dispatch_next_block(struct tpacket_kbdq_core *, struct packet_sock *); static void prb_retire_current_block(struct tpacket_kbdq_core *, @@ -216,6 +214,7 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *, static void prb_fill_vlan_info(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); +static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb); struct packet_skb_cb { union { @@ -262,6 +261,7 @@ static int packet_direct_xmit(struct sk_buff *skb) if (skb != orig_skb) goto drop; + packet_pick_tx_queue(dev, skb); txq = skb_get_tx_queue(dev, skb); local_bh_disable(); @@ -721,7 +721,7 @@ static void prb_retire_rx_blk_timer_expired(unsigned long data) /* Case 1. Queue was frozen because user-space was * lagging behind. */ - if (prb_curr_blk_in_use(pkc, pbd)) { + if (prb_curr_blk_in_use(pbd)) { /* * Ok, user-space is still behind. * So just refresh the timer. @@ -972,8 +972,7 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, } } -static int prb_curr_blk_in_use(struct tpacket_kbdq_core *pkc, - struct tpacket_block_desc *pbd) +static int prb_curr_blk_in_use(struct tpacket_block_desc *pbd) { return TP_STATUS_USER & BLOCK_STATUS(pbd); } @@ -1064,7 +1063,7 @@ static void *__packet_lookup_frame_in_block(struct packet_sock *po, * Check if that last block which caused the queue to freeze, * is still in_use by user-space. */ - if (prb_curr_blk_in_use(pkc, pbd)) { + if (prb_curr_blk_in_use(pbd)) { /* Can't record this packet */ return NULL; } else { @@ -1320,7 +1319,7 @@ static void packet_sock_destruct(struct sock *sk) skb_queue_purge(&sk->sk_error_queue); WARN_ON(atomic_read(&sk->sk_rmem_alloc)); - WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(refcount_read(&sk->sk_wmem_alloc)); if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive packet socket: %p\n", sk); @@ -1742,7 +1741,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) match->flags = flags; INIT_LIST_HEAD(&match->list); spin_lock_init(&match->lock); - atomic_set(&match->sk_ref, 0); + refcount_set(&match->sk_ref, 0); fanout_init_data(match); match->prot_hook.type = po->prot_hook.type; match->prot_hook.dev = po->prot_hook.dev; @@ -1756,10 +1755,10 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) match->prot_hook.type == po->prot_hook.type && match->prot_hook.dev == po->prot_hook.dev) { err = -ENOSPC; - if (atomic_read(&match->sk_ref) < PACKET_FANOUT_MAX) { + if (refcount_read(&match->sk_ref) < PACKET_FANOUT_MAX) { __dev_remove_pack(&po->prot_hook); po->fanout = match; - atomic_inc(&match->sk_ref); + refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1); __fanout_link(sk, po); err = 0; } @@ -1788,7 +1787,7 @@ static struct packet_fanout *fanout_release(struct sock *sk) if (f) { po->fanout = NULL; - if (atomic_dec_and_test(&f->sk_ref)) + if (refcount_dec_and_test(&f->sk_ref)) list_del(&f->list); else f = NULL; @@ -2526,7 +2525,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->data_len = to_write; skb->len += to_write; skb->truesize += to_write; - atomic_add(to_write, &po->sk.sk_wmem_alloc); + refcount_add(to_write, &po->sk.sk_wmem_alloc); while (likely(to_write)) { nr_frags = skb_shinfo(skb)->nr_frags; @@ -2750,8 +2749,6 @@ tpacket_error: goto tpacket_error; } - packet_pick_tx_queue(dev, skb); - skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); packet_inc_pending(&po->tx_ring); @@ -2934,8 +2931,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->priority = sk->sk_priority; skb->mark = sockc.mark; - packet_pick_tx_queue(dev, skb); - if (po->has_vnet_hdr) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) @@ -4498,7 +4493,7 @@ static int packet_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%pK %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n", s, - atomic_read(&s->sk_refcnt), + refcount_read(&s->sk_refcnt), s->sk_type, ntohs(po->num), po->ifindex, diff --git a/net/packet/internal.h b/net/packet/internal.h index 9ee46314b7d7..94d1d405a116 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -1,6 +1,8 @@ #ifndef __PACKET_INTERNAL_H__ #define __PACKET_INTERNAL_H__ +#include <linux/refcount.h> + struct packet_mclist { struct packet_mclist *next; int ifindex; @@ -86,7 +88,7 @@ struct packet_fanout { struct list_head list; struct sock *arr[PACKET_FANOUT_MAX]; spinlock_t lock; - atomic_t sk_ref; + refcount_t sk_ref; struct packet_type prot_hook ____cacheline_aligned_in_smp; }; diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 64634e3ec2fc..1b050dd17393 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -360,7 +360,7 @@ static unsigned int pn_socket_poll(struct file *file, struct socket *sock, return POLLHUP; if (sk->sk_state == TCP_ESTABLISHED && - atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf && + refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf && atomic_read(&pn->tx_credits)) mask |= POLLOUT | POLLWRNORM | POLLWRBAND; @@ -614,7 +614,7 @@ static int pn_sock_seq_show(struct seq_file *seq, void *v) sk_wmem_alloc_get(sk), sk_rmem_alloc_get(sk), from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)), sock_i_ino(sk), - atomic_read(&sk->sk_refcnt), sk, + refcount_read(&sk->sk_refcnt), sk, atomic_read(&sk->sk_drops)); } seq_pad(seq, '\n'); diff --git a/net/psample/psample.c b/net/psample/psample.c index 8aa58a918783..3a6ad0f438dc 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -264,7 +264,7 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, int nla_len = nla_total_size(data_len); struct nlattr *nla; - nla = (struct nlattr *)skb_put(nl_skb, nla_len); + nla = skb_put(nl_skb, nla_len); nla->nla_type = PSAMPLE_ATTR_DATA; nla->nla_len = nla_attr_size(data_len); diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index a9a8c7d5a4a9..5586609afa27 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -111,6 +111,9 @@ struct qrtr_node { struct list_head item; }; +static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb); +static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb); + /* Release node resources and free the node. * * Do not call directly, use qrtr_node_release. To be used with @@ -236,7 +239,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) return -ENOMEM; skb_reset_transport_header(skb); - memcpy(skb_put(skb, len), data, len); + skb_put_data(skb, data, len); skb_queue_tail(&node->rx_queue, skb); schedule_work(&node->work); @@ -245,23 +248,20 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) } EXPORT_SYMBOL_GPL(qrtr_endpoint_post); -/* Allocate and construct a resume-tx packet. */ -static struct sk_buff *qrtr_alloc_resume_tx(u32 src_node, - u32 dst_node, u32 port) +static struct sk_buff *qrtr_alloc_ctrl_packet(u32 type, size_t pkt_len, + u32 src_node, u32 dst_node) { - const int pkt_len = 20; struct qrtr_hdr *hdr; struct sk_buff *skb; - __le32 *buf; skb = alloc_skb(QRTR_HDR_SIZE + pkt_len, GFP_KERNEL); if (!skb) return NULL; skb_reset_transport_header(skb); - hdr = (struct qrtr_hdr *)skb_put(skb, QRTR_HDR_SIZE); + hdr = skb_put(skb, QRTR_HDR_SIZE); hdr->version = cpu_to_le32(QRTR_PROTO_VER); - hdr->type = cpu_to_le32(QRTR_TYPE_RESUME_TX); + hdr->type = cpu_to_le32(type); hdr->src_node_id = cpu_to_le32(src_node); hdr->src_port_id = cpu_to_le32(QRTR_PORT_CTRL); hdr->confirm_rx = cpu_to_le32(0); @@ -269,8 +269,23 @@ static struct sk_buff *qrtr_alloc_resume_tx(u32 src_node, hdr->dst_node_id = cpu_to_le32(dst_node); hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL); - buf = (__le32 *)skb_put(skb, pkt_len); - memset(buf, 0, pkt_len); + return skb; +} + +/* Allocate and construct a resume-tx packet. */ +static struct sk_buff *qrtr_alloc_resume_tx(u32 src_node, + u32 dst_node, u32 port) +{ + const int pkt_len = 20; + struct sk_buff *skb; + __le32 *buf; + + skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_RESUME_TX, pkt_len, + src_node, dst_node); + if (!skb) + return NULL; + + buf = skb_put_zero(skb, pkt_len); buf[0] = cpu_to_le32(QRTR_TYPE_RESUME_TX); buf[1] = cpu_to_le32(src_node); buf[2] = cpu_to_le32(port); @@ -278,6 +293,43 @@ static struct sk_buff *qrtr_alloc_resume_tx(u32 src_node, return skb; } +/* Allocate and construct a BYE message to signal remote termination */ +static struct sk_buff *qrtr_alloc_local_bye(u32 src_node) +{ + const int pkt_len = 20; + struct sk_buff *skb; + __le32 *buf; + + skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_BYE, pkt_len, + src_node, qrtr_local_nid); + if (!skb) + return NULL; + + buf = skb_put_zero(skb, pkt_len); + buf[0] = cpu_to_le32(QRTR_TYPE_BYE); + + return skb; +} + +static struct sk_buff *qrtr_alloc_del_client(struct sockaddr_qrtr *sq) +{ + const int pkt_len = 20; + struct sk_buff *skb; + __le32 *buf; + + skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_DEL_CLIENT, pkt_len, + sq->sq_node, QRTR_NODE_BCAST); + if (!skb) + return NULL; + + buf = skb_put_zero(skb, pkt_len); + buf[0] = cpu_to_le32(QRTR_TYPE_DEL_CLIENT); + buf[1] = cpu_to_le32(sq->sq_node); + buf[2] = cpu_to_le32(sq->sq_port); + + return skb; +} + static struct qrtr_sock *qrtr_port_lookup(int port); static void qrtr_port_put(struct qrtr_sock *ipc); @@ -369,11 +421,17 @@ EXPORT_SYMBOL_GPL(qrtr_endpoint_register); void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) { struct qrtr_node *node = ep->node; + struct sk_buff *skb; mutex_lock(&node->ep_lock); node->ep = NULL; mutex_unlock(&node->ep_lock); + /* Notify the local controller about the event */ + skb = qrtr_alloc_local_bye(node->nid); + if (skb) + qrtr_local_enqueue(NULL, skb); + qrtr_node_release(node); ep->node = NULL; } @@ -408,8 +466,15 @@ static void qrtr_port_put(struct qrtr_sock *ipc) /* Remove port assignment. */ static void qrtr_port_remove(struct qrtr_sock *ipc) { + struct sk_buff *skb; int port = ipc->us.sq_port; + skb = qrtr_alloc_del_client(&ipc->us); + if (skb) { + skb_set_owner_w(skb, &ipc->sk); + qrtr_bcast_enqueue(NULL, skb); + } + if (port == QRTR_PORT_CTRL) port = 0; @@ -462,6 +527,26 @@ static int qrtr_port_assign(struct qrtr_sock *ipc, int *port) return 0; } +/* Reset all non-control ports */ +static void qrtr_reset_ports(void) +{ + struct qrtr_sock *ipc; + int id; + + mutex_lock(&qrtr_port_lock); + idr_for_each_entry(&qrtr_ports, ipc, id) { + /* Don't reset control port */ + if (id == 0) + continue; + + sock_hold(&ipc->sk); + ipc->sk.sk_err = ENETRESET; + wake_up_interruptible(sk_sleep(&ipc->sk)); + sock_put(&ipc->sk); + } + mutex_unlock(&qrtr_port_lock); +} + /* Bind socket to address. * * Socket should be locked upon call. @@ -490,6 +575,10 @@ static int __qrtr_bind(struct socket *sock, sock_reset_flag(sk, SOCK_ZAPPED); + /* Notify all open ports about the new controller */ + if (port == QRTR_PORT_CTRL) + qrtr_reset_ports(); + return 0; } diff --git a/net/rds/connection.c b/net/rds/connection.c index 6a5ebdea7d2e..50a3789ac23e 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -124,11 +124,6 @@ static void __rds_conn_path_init(struct rds_connection *conn, cp->cp_conn = conn; atomic_set(&cp->cp_state, RDS_CONN_DOWN); cp->cp_send_gen = 0; - /* cp_outgoing is per-path. So we can only set it here - * for the single-path transports. - */ - if (!conn->c_trans->t_mp_capable) - cp->cp_outgoing = (is_outgoing ? 1 : 0); cp->cp_reconnect_jiffies = 0; INIT_DELAYED_WORK(&cp->cp_send_w, rds_send_worker); INIT_DELAYED_WORK(&cp->cp_recv_w, rds_recv_worker); @@ -417,6 +412,7 @@ void rds_conn_destroy(struct rds_connection *conn) "%pI4\n", conn, &conn->c_laddr, &conn->c_faddr); + conn->c_destroy_in_prog = 1; /* Ensure conn will not be scheduled for reconnect */ spin_lock_irq(&rds_conn_lock); hlist_del_init_rcu(&conn->c_hash_node); diff --git a/net/rds/ib.c b/net/rds/ib.c index 7a64c8db81ab..a0954ace3774 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -118,8 +118,8 @@ static void rds_ib_dev_free(struct work_struct *work) void rds_ib_dev_put(struct rds_ib_device *rds_ibdev) { - BUG_ON(atomic_read(&rds_ibdev->refcount) <= 0); - if (atomic_dec_and_test(&rds_ibdev->refcount)) + BUG_ON(refcount_read(&rds_ibdev->refcount) == 0); + if (refcount_dec_and_test(&rds_ibdev->refcount)) queue_work(rds_wq, &rds_ibdev->free_work); } @@ -137,7 +137,7 @@ static void rds_ib_add_one(struct ib_device *device) return; spin_lock_init(&rds_ibdev->spinlock); - atomic_set(&rds_ibdev->refcount, 1); + refcount_set(&rds_ibdev->refcount, 1); INIT_WORK(&rds_ibdev->free_work, rds_ib_dev_free); rds_ibdev->max_wrs = device->attrs.max_qp_wr; @@ -205,10 +205,10 @@ static void rds_ib_add_one(struct ib_device *device) down_write(&rds_ib_devices_lock); list_add_tail_rcu(&rds_ibdev->list, &rds_ib_devices); up_write(&rds_ib_devices_lock); - atomic_inc(&rds_ibdev->refcount); + refcount_inc(&rds_ibdev->refcount); ib_set_client_data(device, &rds_ib_client, rds_ibdev); - atomic_inc(&rds_ibdev->refcount); + refcount_inc(&rds_ibdev->refcount); rds_ib_nodev_connect(); @@ -239,7 +239,7 @@ struct rds_ib_device *rds_ib_get_client_data(struct ib_device *device) rcu_read_lock(); rds_ibdev = ib_get_client_data(device, &rds_ib_client); if (rds_ibdev) - atomic_inc(&rds_ibdev->refcount); + refcount_inc(&rds_ibdev->refcount); rcu_read_unlock(); return rds_ibdev; } diff --git a/net/rds/ib.h b/net/rds/ib.h index ec550626e221..bf4822407567 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -230,7 +230,7 @@ struct rds_ib_device { unsigned int max_initiator_depth; unsigned int max_responder_resources; spinlock_t spinlock; /* protect the above */ - atomic_t refcount; + refcount_t refcount; struct work_struct free_work; int *vector_load; }; diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 977f69886c00..9a3c54e659e9 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -52,7 +52,7 @@ static struct rds_ib_device *rds_ib_get_device(__be32 ipaddr) list_for_each_entry_rcu(rds_ibdev, &rds_ib_devices, list) { list_for_each_entry_rcu(i_ipaddr, &rds_ibdev->ipaddr_list, list) { if (i_ipaddr->ipaddr == ipaddr) { - atomic_inc(&rds_ibdev->refcount); + refcount_inc(&rds_ibdev->refcount); rcu_read_unlock(); return rds_ibdev; } @@ -134,7 +134,7 @@ void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *con spin_unlock_irq(&ib_nodev_conns_lock); ic->rds_ibdev = rds_ibdev; - atomic_inc(&rds_ibdev->refcount); + refcount_inc(&rds_ibdev->refcount); } void rds_ib_remove_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn) diff --git a/net/rds/message.c b/net/rds/message.c index 49bfb512d808..4318cc9b78f7 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -48,8 +48,8 @@ static unsigned int rds_exthdr_size[__RDS_EXTHDR_MAX] = { void rds_message_addref(struct rds_message *rm) { - rdsdebug("addref rm %p ref %d\n", rm, atomic_read(&rm->m_refcount)); - atomic_inc(&rm->m_refcount); + rdsdebug("addref rm %p ref %d\n", rm, refcount_read(&rm->m_refcount)); + refcount_inc(&rm->m_refcount); } EXPORT_SYMBOL_GPL(rds_message_addref); @@ -83,9 +83,9 @@ static void rds_message_purge(struct rds_message *rm) void rds_message_put(struct rds_message *rm) { - rdsdebug("put rm %p ref %d\n", rm, atomic_read(&rm->m_refcount)); - WARN(!atomic_read(&rm->m_refcount), "danger refcount zero on %p\n", rm); - if (atomic_dec_and_test(&rm->m_refcount)) { + rdsdebug("put rm %p ref %d\n", rm, refcount_read(&rm->m_refcount)); + WARN(!refcount_read(&rm->m_refcount), "danger refcount zero on %p\n", rm); + if (refcount_dec_and_test(&rm->m_refcount)) { BUG_ON(!list_empty(&rm->m_sock_item)); BUG_ON(!list_empty(&rm->m_conn_item)); rds_message_purge(rm); @@ -206,7 +206,7 @@ struct rds_message *rds_message_alloc(unsigned int extra_len, gfp_t gfp) rm->m_used_sgs = 0; rm->m_total_sgs = extra_len / sizeof(struct scatterlist); - atomic_set(&rm->m_refcount, 1); + refcount_set(&rm->m_refcount, 1); INIT_LIST_HEAD(&rm->m_sock_item); INIT_LIST_HEAD(&rm->m_conn_item); spin_lock_init(&rm->m_rs_lock); diff --git a/net/rds/rdma.c b/net/rds/rdma.c index f06fac4886b0..8886f15abe90 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -84,7 +84,7 @@ static struct rds_mr *rds_mr_tree_walk(struct rb_root *root, u64 key, if (insert) { rb_link_node(&insert->r_rb_node, parent, p); rb_insert_color(&insert->r_rb_node, root); - atomic_inc(&insert->r_refcount); + refcount_inc(&insert->r_refcount); } return NULL; } @@ -99,7 +99,7 @@ static void rds_destroy_mr(struct rds_mr *mr) unsigned long flags; rdsdebug("RDS: destroy mr key is %x refcnt %u\n", - mr->r_key, atomic_read(&mr->r_refcount)); + mr->r_key, refcount_read(&mr->r_refcount)); if (test_and_set_bit(RDS_MR_DEAD, &mr->r_state)) return; @@ -223,7 +223,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, goto out; } - atomic_set(&mr->r_refcount, 1); + refcount_set(&mr->r_refcount, 1); RB_CLEAR_NODE(&mr->r_rb_node); mr->r_trans = rs->rs_transport; mr->r_sock = rs; @@ -307,7 +307,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, rdsdebug("RDS: get_mr key is %x\n", mr->r_key); if (mr_ret) { - atomic_inc(&mr->r_refcount); + refcount_inc(&mr->r_refcount); *mr_ret = mr; } @@ -756,7 +756,7 @@ int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, if (!mr) err = -EINVAL; /* invalid r_key */ else - atomic_inc(&mr->r_refcount); + refcount_inc(&mr->r_refcount); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (mr) { diff --git a/net/rds/rds.h b/net/rds/rds.h index 82d38ccf5e8b..516bcc89b46f 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -8,6 +8,7 @@ #include <linux/mutex.h> #include <linux/rds.h> #include <linux/rhashtable.h> +#include <linux/refcount.h> #include "info.h" @@ -92,6 +93,8 @@ enum { #define RDS_MPATH_HASH(rs, n) (jhash_1word((rs)->rs_bound_port, \ (rs)->rs_hash_initval) & ((n) - 1)) +#define IS_CANONICAL(laddr, faddr) (htonl(laddr) < htonl(faddr)) + /* Per mpath connection state */ struct rds_conn_path { struct rds_connection *cp_conn; @@ -125,8 +128,6 @@ struct rds_conn_path { unsigned int cp_unacked_packets; unsigned int cp_unacked_bytes; - unsigned int cp_outgoing:1, - cp_pad_to_32:31; unsigned int cp_index; }; @@ -137,7 +138,8 @@ struct rds_connection { __be32 c_faddr; unsigned int c_loopback:1, c_ping_triggered:1, - c_pad_to_32:30; + c_destroy_in_prog:1, + c_pad_to_32:29; int c_npaths; struct rds_connection *c_passive; struct rds_transport *c_trans; @@ -260,7 +262,7 @@ struct rds_ext_header_rdma_dest { #define RDS_MSG_RX_CMSG 3 struct rds_incoming { - atomic_t i_refcount; + refcount_t i_refcount; struct list_head i_item; struct rds_connection *i_conn; struct rds_conn_path *i_conn_path; @@ -275,7 +277,7 @@ struct rds_incoming { struct rds_mr { struct rb_node r_rb_node; - atomic_t r_refcount; + refcount_t r_refcount; u32 r_key; /* A copy of the creation flags */ @@ -354,7 +356,7 @@ static inline u32 rds_rdma_cookie_offset(rds_rdma_cookie_t cookie) #define RDS_MSG_FLUSH 8 struct rds_message { - atomic_t m_refcount; + refcount_t m_refcount; struct list_head m_sock_item; struct list_head m_conn_item; struct rds_incoming m_inc; @@ -827,6 +829,7 @@ void rds_send_drop_acked(struct rds_connection *conn, u64 ack, is_acked_func is_acked); void rds_send_path_drop_acked(struct rds_conn_path *cp, u64 ack, is_acked_func is_acked); +void rds_send_ping(struct rds_connection *conn, int cp_index); int rds_send_pong(struct rds_conn_path *cp, __be16 dport); /* rdma.c */ @@ -854,7 +857,7 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, void __rds_put_mr_final(struct rds_mr *mr); static inline void rds_mr_put(struct rds_mr *mr) { - if (atomic_dec_and_test(&mr->r_refcount)) + if (refcount_dec_and_test(&mr->r_refcount)) __rds_put_mr_final(mr); } diff --git a/net/rds/recv.c b/net/rds/recv.c index c70c32cb05f5..b25bcfe411ca 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -45,7 +45,7 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, { int i; - atomic_set(&inc->i_refcount, 1); + refcount_set(&inc->i_refcount, 1); INIT_LIST_HEAD(&inc->i_item); inc->i_conn = conn; inc->i_saddr = saddr; @@ -61,7 +61,7 @@ EXPORT_SYMBOL_GPL(rds_inc_init); void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *cp, __be32 saddr) { - atomic_set(&inc->i_refcount, 1); + refcount_set(&inc->i_refcount, 1); INIT_LIST_HEAD(&inc->i_item); inc->i_conn = cp->cp_conn; inc->i_conn_path = cp; @@ -74,14 +74,14 @@ EXPORT_SYMBOL_GPL(rds_inc_path_init); static void rds_inc_addref(struct rds_incoming *inc) { - rdsdebug("addref inc %p ref %d\n", inc, atomic_read(&inc->i_refcount)); - atomic_inc(&inc->i_refcount); + rdsdebug("addref inc %p ref %d\n", inc, refcount_read(&inc->i_refcount)); + refcount_inc(&inc->i_refcount); } void rds_inc_put(struct rds_incoming *inc) { - rdsdebug("put inc %p ref %d\n", inc, atomic_read(&inc->i_refcount)); - if (atomic_dec_and_test(&inc->i_refcount)) { + rdsdebug("put inc %p ref %d\n", inc, refcount_read(&inc->i_refcount)); + if (refcount_dec_and_test(&inc->i_refcount)) { BUG_ON(!list_empty(&inc->i_item)); inc->i_conn->c_trans->inc_free(inc); @@ -215,10 +215,10 @@ static void rds_recv_hs_exthdrs(struct rds_header *hdr, switch (type) { case RDS_EXTHDR_NPATHS: conn->c_npaths = min_t(int, RDS_MPATH_WORKERS, - buffer.rds_npaths); + be16_to_cpu(buffer.rds_npaths)); break; case RDS_EXTHDR_GEN_NUM: - new_peer_gen_num = buffer.rds_gen_num; + new_peer_gen_num = be32_to_cpu(buffer.rds_gen_num); break; default: pr_warn_ratelimited("ignoring unknown exthdr type " @@ -227,6 +227,7 @@ static void rds_recv_hs_exthdrs(struct rds_header *hdr, } /* if RDS_EXTHDR_NPATHS was not found, default to a single-path */ conn->c_npaths = max_t(int, conn->c_npaths, 1); + conn->c_ping_triggered = 0; rds_conn_peer_gen_update(conn, new_peer_gen_num); } @@ -244,8 +245,7 @@ static void rds_recv_hs_exthdrs(struct rds_header *hdr, * called after reception of the probe-pong on all mprds_paths. * Otherwise (sender of probe-ping is not the smaller ip addr): just call * rds_conn_path_connect_if_down on the hashed path. (see rule 4) - * 4. when cp_index > 0, rds_connect_worker must only trigger - * a connection if laddr < faddr. + * 4. rds_connect_worker must only trigger a connection if laddr < faddr. * 5. sender may end up queuing the packet on the cp. will get sent out later. * when connection is completed. */ @@ -254,8 +254,9 @@ static void rds_start_mprds(struct rds_connection *conn) int i; struct rds_conn_path *cp; - if (conn->c_npaths > 1 && conn->c_laddr < conn->c_faddr) { - for (i = 1; i < conn->c_npaths; i++) { + if (conn->c_npaths > 1 && + IS_CANONICAL(conn->c_laddr, conn->c_faddr)) { + for (i = 0; i < conn->c_npaths; i++) { cp = &conn->c_path[i]; rds_conn_path_connect_if_down(cp); } @@ -339,14 +340,15 @@ void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr, rds_stats_inc(s_recv_ping); rds_send_pong(cp, inc->i_hdr.h_sport); /* if this is a handshake ping, start multipath if necessary */ - if (RDS_HS_PROBE(inc->i_hdr.h_sport, inc->i_hdr.h_dport)) { + if (RDS_HS_PROBE(be16_to_cpu(inc->i_hdr.h_sport), + be16_to_cpu(inc->i_hdr.h_dport))) { rds_recv_hs_exthdrs(&inc->i_hdr, cp->cp_conn); rds_start_mprds(cp->cp_conn); } goto out; } - if (inc->i_hdr.h_dport == RDS_FLAG_PROBE_PORT && + if (be16_to_cpu(inc->i_hdr.h_dport) == RDS_FLAG_PROBE_PORT && inc->i_hdr.h_sport == 0) { rds_recv_hs_exthdrs(&inc->i_hdr, cp->cp_conn); /* if this is a handshake pong, start multipath if necessary */ diff --git a/net/rds/send.c b/net/rds/send.c index 5cc64039caf7..41b9f0f5bb9c 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -170,8 +170,8 @@ restart: * The acquire_in_xmit() check above ensures that only one * caller can increment c_send_gen at any time. */ - cp->cp_send_gen++; - send_gen = cp->cp_send_gen; + send_gen = READ_ONCE(cp->cp_send_gen) + 1; + WRITE_ONCE(cp->cp_send_gen, send_gen); /* * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT, @@ -431,7 +431,7 @@ over_batch: smp_mb(); if ((test_bit(0, &conn->c_map_queued) || !list_empty(&cp->cp_send_queue)) && - send_gen == cp->cp_send_gen) { + send_gen == READ_ONCE(cp->cp_send_gen)) { rds_stats_inc(s_send_lock_queue_raced); if (batch_count < send_batch_count) goto restart; @@ -971,8 +971,6 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, return ret; } -static void rds_send_ping(struct rds_connection *conn); - static int rds_send_mprds_hash(struct rds_sock *rs, struct rds_connection *conn) { int hash; @@ -982,7 +980,7 @@ static int rds_send_mprds_hash(struct rds_sock *rs, struct rds_connection *conn) else hash = RDS_MPATH_HASH(rs, conn->c_npaths); if (conn->c_npaths == 0 && hash != 0) { - rds_send_ping(conn); + rds_send_ping(conn, 0); if (conn->c_npaths == 0) { wait_event_interruptible(conn->c_hs_waitq, @@ -1246,15 +1244,17 @@ rds_send_probe(struct rds_conn_path *cp, __be16 sport, rm->m_inc.i_hdr.h_flags |= h_flags; cp->cp_next_tx_seq++; - if (RDS_HS_PROBE(sport, dport) && cp->cp_conn->c_trans->t_mp_capable) { - u16 npaths = RDS_MPATH_WORKERS; + if (RDS_HS_PROBE(be16_to_cpu(sport), be16_to_cpu(dport)) && + cp->cp_conn->c_trans->t_mp_capable) { + u16 npaths = cpu_to_be16(RDS_MPATH_WORKERS); + u32 my_gen_num = cpu_to_be32(cp->cp_conn->c_my_gen_num); rds_message_add_extension(&rm->m_inc.i_hdr, RDS_EXTHDR_NPATHS, &npaths, sizeof(npaths)); rds_message_add_extension(&rm->m_inc.i_hdr, RDS_EXTHDR_GEN_NUM, - &cp->cp_conn->c_my_gen_num, + &my_gen_num, sizeof(u32)); } spin_unlock_irqrestore(&cp->cp_lock, flags); @@ -1280,11 +1280,11 @@ rds_send_pong(struct rds_conn_path *cp, __be16 dport) return rds_send_probe(cp, 0, dport, 0); } -static void -rds_send_ping(struct rds_connection *conn) +void +rds_send_ping(struct rds_connection *conn, int cp_index) { unsigned long flags; - struct rds_conn_path *cp = &conn->c_path[0]; + struct rds_conn_path *cp = &conn->c_path[cp_index]; spin_lock_irqsave(&cp->cp_lock, flags); if (conn->c_ping_triggered) { @@ -1293,5 +1293,6 @@ rds_send_ping(struct rds_connection *conn) } conn->c_ping_triggered = 1; spin_unlock_irqrestore(&cp->cp_lock, flags); - rds_send_probe(&conn->c_path[0], RDS_FLAG_PROBE_PORT, 0, 0); + rds_send_probe(cp, cpu_to_be16(RDS_FLAG_PROBE_PORT), 0, 0); } +EXPORT_SYMBOL_GPL(rds_send_ping); diff --git a/net/rds/tcp.h b/net/rds/tcp.h index 56ea6620fcf9..f8800b7ce79c 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -71,6 +71,7 @@ void rds_tcp_listen_data_ready(struct sock *sk); int rds_tcp_accept_one(struct socket *sock); int rds_tcp_keepalive(struct socket *sock); void *rds_tcp_listen_sock_def_readable(struct net *net); +void rds_tcp_set_linger(struct socket *sock); /* tcp_recv.c */ int rds_tcp_recv_init(void); diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index d6839d96d539..cbe08a1fa4c7 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -66,7 +66,7 @@ void rds_tcp_state_change(struct sock *sk) * RDS connection as RDS_CONN_UP until the reconnect, * to avoid RDS datagram loss. */ - if (cp->cp_conn->c_laddr > cp->cp_conn->c_faddr && + if (!IS_CANONICAL(cp->cp_conn->c_laddr, cp->cp_conn->c_faddr) && rds_conn_path_transition(cp, RDS_CONN_CONNECTING, RDS_CONN_ERROR)) { rds_conn_path_drop(cp); @@ -135,7 +135,6 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp) ret = sock->ops->connect(sock, (struct sockaddr *)&dest, sizeof(dest), O_NONBLOCK); - cp->cp_outgoing = 1; rdsdebug("connect to address %pI4 returned %d\n", &conn->c_faddr, ret); if (ret == -EINPROGRESS) ret = 0; @@ -171,6 +170,8 @@ void rds_tcp_conn_path_shutdown(struct rds_conn_path *cp) cp->cp_conn, tc, sock); if (sock) { + if (cp->cp_conn->c_destroy_in_prog) + rds_tcp_set_linger(sock); sock->ops->shutdown(sock, RCV_SHUTDOWN | SEND_SHUTDOWN); lock_sock(sock->sk); rds_tcp_restore_callbacks(sock, tc); /* tc->tc_sock = NULL */ diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 507678853e6c..c061d6eb465d 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -83,7 +83,7 @@ static struct rds_tcp_connection *rds_tcp_accept_one_path(struct rds_connection *conn) { int i; - bool peer_is_smaller = (conn->c_faddr < conn->c_laddr); + bool peer_is_smaller = IS_CANONICAL(conn->c_faddr, conn->c_laddr); int npaths = max_t(int, 1, conn->c_npaths); /* for mprds, all paths MUST be initiated by the peer @@ -112,6 +112,17 @@ struct rds_tcp_connection *rds_tcp_accept_one_path(struct rds_connection *conn) return NULL; } +void rds_tcp_set_linger(struct socket *sock) +{ + struct linger no_linger = { + .l_onoff = 1, + .l_linger = 0, + }; + + kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER, + (char *)&no_linger, sizeof(no_linger)); +} + int rds_tcp_accept_one(struct socket *sock) { struct socket *new_sock = NULL; @@ -125,7 +136,7 @@ int rds_tcp_accept_one(struct socket *sock) if (!sock) /* module unload or netns delete in progress */ return -ENETUNREACH; - ret = sock_create_kern(sock_net(sock->sk), sock->sk->sk_family, + ret = sock_create_lite(sock->sk->sk_family, sock->sk->sk_type, sock->sk->sk_protocol, &new_sock); if (ret) @@ -171,30 +182,27 @@ int rds_tcp_accept_one(struct socket *sock) if (conn_state != RDS_CONN_CONNECTING && conn_state != RDS_CONN_ERROR) goto rst_nsk; if (rs_tcp->t_sock) { - /* Need to resolve a duelling SYN between peers. - * We have an outstanding SYN to this peer, which may - * potentially have transitioned to the RDS_CONN_UP state, - * so we must quiesce any send threads before resetting - * c_transport_data. - */ - if (ntohl(inet->inet_saddr) < ntohl(inet->inet_daddr) || - !cp->cp_outgoing) { - goto rst_nsk; - } else { - rds_tcp_reset_callbacks(new_sock, cp); - cp->cp_outgoing = 0; - /* rds_connect_path_complete() marks RDS_CONN_UP */ - rds_connect_path_complete(cp, RDS_CONN_RESETTING); - } + /* Duelling SYN has been handled in rds_tcp_accept_one() */ + rds_tcp_reset_callbacks(new_sock, cp); + /* rds_connect_path_complete() marks RDS_CONN_UP */ + rds_connect_path_complete(cp, RDS_CONN_RESETTING); } else { rds_tcp_set_callbacks(new_sock, cp); rds_connect_path_complete(cp, RDS_CONN_CONNECTING); } new_sock = NULL; ret = 0; + if (conn->c_npaths == 0) + rds_send_ping(cp->cp_conn, cp->cp_index); goto out; rst_nsk: - /* reset the newly returned accept sock and bail */ + /* reset the newly returned accept sock and bail. + * It is safe to set linger on new_sock because the RDS connection + * has not been brought up on new_sock, so no RDS-level data could + * be pending on it. By setting linger, we achieve the side-effect + * of avoiding TIME_WAIT state on new_sock. + */ + rds_tcp_set_linger(new_sock); kernel_sock_shutdown(new_sock, SHUT_RDWR); ret = 0; out: diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c index 52d11d7725c8..0d8616aa5bad 100644 --- a/net/rds/tcp_send.c +++ b/net/rds/tcp_send.c @@ -202,7 +202,7 @@ void rds_tcp_write_space(struct sock *sk) tc->t_last_seen_una = rds_tcp_snd_una(tc); rds_send_path_drop_acked(cp, rds_tcp_snd_una(tc), rds_tcp_is_acked); - if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) + if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) queue_delayed_work(rds_wq, &cp->cp_send_w, 0); out: diff --git a/net/rds/threads.c b/net/rds/threads.c index 3e447d056d09..2852bc1d37d4 100644 --- a/net/rds/threads.c +++ b/net/rds/threads.c @@ -127,7 +127,7 @@ void rds_queue_reconnect(struct rds_conn_path *cp) /* let peer with smaller addr initiate reconnect, to avoid duels */ if (conn->c_trans->t_type == RDS_TRANS_TCP && - conn->c_laddr > conn->c_faddr) + !IS_CANONICAL(conn->c_laddr, conn->c_faddr)) return; set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); @@ -156,7 +156,8 @@ void rds_connect_worker(struct work_struct *work) struct rds_connection *conn = cp->cp_conn; int ret; - if (cp->cp_index > 0 && cp->cp_conn->c_laddr > cp->cp_conn->c_faddr) + if (cp->cp_index > 0 && + !IS_CANONICAL(cp->cp_conn->c_laddr, cp->cp_conn->c_faddr)) return; clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); ret = rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_CONNECTING); diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 76c01cbd56e3..41bd496531d4 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -81,8 +81,7 @@ static int rfkill_gpio_acpi_probe(struct device *dev, rfkill->type = (unsigned)id->driver_data; - return acpi_dev_add_driver_gpios(ACPI_COMPANION(dev), - acpi_rfkill_default_gpios); + return devm_acpi_dev_add_driver_gpios(dev, acpi_rfkill_default_gpios); } static int rfkill_gpio_probe(struct platform_device *pdev) @@ -154,8 +153,6 @@ static int rfkill_gpio_remove(struct platform_device *pdev) rfkill_unregister(rfkill->rfkill_dev); rfkill_destroy(rfkill->rfkill_dev); - acpi_dev_remove_driver_gpios(ACPI_COMPANION(&pdev->dev)); - return 0; } diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index b9da4d6b914f..9c68d2f8ba39 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -19,6 +19,7 @@ rxrpc-y := \ local_event.o \ local_object.o \ misc.o \ + net_ns.o \ output.o \ peer_event.o \ peer_object.o \ diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 7fb59c3f1542..a2ad4482376f 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -38,9 +38,6 @@ MODULE_PARM_DESC(debug, "RxRPC debugging mask"); static struct proto rxrpc_proto; static const struct proto_ops rxrpc_rpc_ops; -/* local epoch for detecting local-end reset */ -u32 rxrpc_epoch; - /* current debugging ID */ atomic_t rxrpc_debug_id; @@ -56,7 +53,7 @@ static void rxrpc_sock_destructor(struct sock *); */ static inline int rxrpc_writable(struct sock *sk) { - return atomic_read(&sk->sk_wmem_alloc) < (size_t) sk->sk_sndbuf; + return refcount_read(&sk->sk_wmem_alloc) < (size_t) sk->sk_sndbuf; } /* @@ -134,9 +131,8 @@ static int rxrpc_validate_address(struct rxrpc_sock *rx, static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) { struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)saddr; - struct sock *sk = sock->sk; struct rxrpc_local *local; - struct rxrpc_sock *rx = rxrpc_sk(sk); + struct rxrpc_sock *rx = rxrpc_sk(sock->sk); u16 service_id = srx->srx_service; int ret; @@ -148,31 +144,48 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) lock_sock(&rx->sk); - if (rx->sk.sk_state != RXRPC_UNBOUND) { - ret = -EINVAL; - goto error_unlock; - } - - memcpy(&rx->srx, srx, sizeof(rx->srx)); + switch (rx->sk.sk_state) { + case RXRPC_UNBOUND: + rx->srx = *srx; + local = rxrpc_lookup_local(sock_net(&rx->sk), &rx->srx); + if (IS_ERR(local)) { + ret = PTR_ERR(local); + goto error_unlock; + } - local = rxrpc_lookup_local(&rx->srx); - if (IS_ERR(local)) { - ret = PTR_ERR(local); - goto error_unlock; - } + if (service_id) { + write_lock(&local->services_lock); + if (rcu_access_pointer(local->service)) + goto service_in_use; + rx->local = local; + rcu_assign_pointer(local->service, rx); + write_unlock(&local->services_lock); + + rx->sk.sk_state = RXRPC_SERVER_BOUND; + } else { + rx->local = local; + rx->sk.sk_state = RXRPC_CLIENT_BOUND; + } + break; - if (service_id) { - write_lock(&local->services_lock); - if (rcu_access_pointer(local->service)) - goto service_in_use; - rx->local = local; - rcu_assign_pointer(local->service, rx); - write_unlock(&local->services_lock); + case RXRPC_SERVER_BOUND: + ret = -EINVAL; + if (service_id == 0) + goto error_unlock; + ret = -EADDRINUSE; + if (service_id == rx->srx.srx_service) + goto error_unlock; + ret = -EINVAL; + srx->srx_service = rx->srx.srx_service; + if (memcmp(srx, &rx->srx, sizeof(*srx)) != 0) + goto error_unlock; + rx->second_service = service_id; + rx->sk.sk_state = RXRPC_SERVER_BOUND2; + break; - rx->sk.sk_state = RXRPC_SERVER_BOUND; - } else { - rx->local = local; - rx->sk.sk_state = RXRPC_CLIENT_BOUND; + default: + ret = -EINVAL; + goto error_unlock; } release_sock(&rx->sk); @@ -209,6 +222,7 @@ static int rxrpc_listen(struct socket *sock, int backlog) ret = -EADDRNOTAVAIL; break; case RXRPC_SERVER_BOUND: + case RXRPC_SERVER_BOUND2: ASSERT(rx->local != NULL); max = READ_ONCE(rxrpc_max_backlog); ret = -EINVAL; @@ -248,6 +262,7 @@ static int rxrpc_listen(struct socket *sock, int backlog) * @srx: The address of the peer to contact * @key: The security context to use (defaults to socket setting) * @user_call_ID: The ID to use + * @tx_total_len: Total length of data to transmit during the call (or -1) * @gfp: The allocation constraints * @notify_rx: Where to send notifications instead of socket queue * @@ -262,6 +277,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, struct sockaddr_rxrpc *srx, struct key *key, unsigned long user_call_ID, + s64 tx_total_len, gfp_t gfp, rxrpc_notify_rx_t notify_rx) { @@ -289,7 +305,8 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, cp.security_level = 0; cp.exclusive = false; cp.service_id = srx->srx_service; - call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, gfp); + call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, tx_total_len, + gfp); /* The socket has been unlocked. */ if (!IS_ERR(call)) call->notify_rx = notify_rx; @@ -434,7 +451,7 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len) ret = -EAFNOSUPPORT; goto error_unlock; } - local = rxrpc_lookup_local(&rx->srx); + local = rxrpc_lookup_local(sock_net(sock->sk), &rx->srx); if (IS_ERR(local)) { ret = PTR_ERR(local); goto error_unlock; @@ -476,6 +493,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, { struct rxrpc_sock *rx = rxrpc_sk(sock->sk); unsigned int min_sec_level; + u16 service_upgrade[2]; int ret; _enter(",%d,%d,,%d", level, optname, optlen); @@ -532,6 +550,28 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, rx->min_sec_level = min_sec_level; goto success; + case RXRPC_UPGRADEABLE_SERVICE: + ret = -EINVAL; + if (optlen != sizeof(service_upgrade) || + rx->service_upgrade.from != 0) + goto error; + ret = -EISCONN; + if (rx->sk.sk_state != RXRPC_SERVER_BOUND2) + goto error; + ret = -EFAULT; + if (copy_from_user(service_upgrade, optval, + sizeof(service_upgrade)) != 0) + goto error; + ret = -EINVAL; + if ((service_upgrade[0] != rx->srx.srx_service || + service_upgrade[1] != rx->second_service) && + (service_upgrade[0] != rx->second_service || + service_upgrade[1] != rx->srx.srx_service)) + goto error; + rx->service_upgrade.from = service_upgrade[0]; + rx->service_upgrade.to = service_upgrade[1]; + goto success; + default: break; } @@ -545,6 +585,34 @@ error: } /* + * Get socket options. + */ +static int rxrpc_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *_optlen) +{ + int optlen; + + if (level != SOL_RXRPC) + return -EOPNOTSUPP; + + if (get_user(optlen, _optlen)) + return -EFAULT; + + switch (optname) { + case RXRPC_SUPPORTED_CMSG: + if (optlen < sizeof(int)) + return -ETOOSMALL; + if (put_user(RXRPC__SUPPORTED - 1, (int __user *)optval) || + put_user(sizeof(int), _optlen)) + return -EFAULT; + return 0; + + default: + return -EOPNOTSUPP; + } +} + +/* * permit an RxRPC socket to be polled */ static unsigned int rxrpc_poll(struct file *file, struct socket *sock, @@ -582,9 +650,6 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol, _enter("%p,%d", sock, protocol); - if (!net_eq(net, &init_net)) - return -EAFNOSUPPORT; - /* we support transport protocol UDP/UDP6 only */ if (protocol != PF_INET && IS_ENABLED(CONFIG_AF_RXRPC_IPV6) && protocol != PF_INET6) @@ -665,7 +730,7 @@ static void rxrpc_sock_destructor(struct sock *sk) rxrpc_purge_queue(&sk->sk_receive_queue); - WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(!sk_unhashed(sk)); WARN_ON(sk->sk_socket); @@ -682,7 +747,7 @@ static int rxrpc_release_sock(struct sock *sk) { struct rxrpc_sock *rx = rxrpc_sk(sk); - _enter("%p{%d,%d}", sk, sk->sk_state, atomic_read(&sk->sk_refcnt)); + _enter("%p{%d,%d}", sk, sk->sk_state, refcount_read(&sk->sk_refcnt)); /* declare the socket closed for business */ sock_orphan(sk); @@ -750,7 +815,7 @@ static const struct proto_ops rxrpc_rpc_ops = { .listen = rxrpc_listen, .shutdown = rxrpc_shutdown, .setsockopt = rxrpc_setsockopt, - .getsockopt = sock_no_getsockopt, + .getsockopt = rxrpc_getsockopt, .sendmsg = rxrpc_sendmsg, .recvmsg = rxrpc_recvmsg, .mmap = sock_no_mmap, @@ -780,8 +845,6 @@ static int __init af_rxrpc_init(void) BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > FIELD_SIZEOF(struct sk_buff, cb)); - get_random_bytes(&rxrpc_epoch, sizeof(rxrpc_epoch)); - rxrpc_epoch |= RXRPC_RANDOM_EPOCH; get_random_bytes(&tmp, sizeof(tmp)); tmp &= 0x3fffffff; if (tmp == 0) @@ -809,6 +872,10 @@ static int __init af_rxrpc_init(void) goto error_security; } + ret = register_pernet_subsys(&rxrpc_net_ops); + if (ret) + goto error_pernet; + ret = proto_register(&rxrpc_proto, 1); if (ret < 0) { pr_crit("Cannot register protocol\n"); @@ -839,11 +906,6 @@ static int __init af_rxrpc_init(void) goto error_sysctls; } -#ifdef CONFIG_PROC_FS - proc_create("rxrpc_calls", 0, init_net.proc_net, &rxrpc_call_seq_fops); - proc_create("rxrpc_conns", 0, init_net.proc_net, - &rxrpc_connection_seq_fops); -#endif return 0; error_sysctls: @@ -855,6 +917,8 @@ error_key_type: error_sock: proto_unregister(&rxrpc_proto); error_proto: + unregister_pernet_subsys(&rxrpc_net_ops); +error_pernet: rxrpc_exit_security(); error_security: destroy_workqueue(rxrpc_workqueue); @@ -875,14 +939,16 @@ static void __exit af_rxrpc_exit(void) unregister_key_type(&key_type_rxrpc); sock_unregister(PF_RXRPC); proto_unregister(&rxrpc_proto); - rxrpc_destroy_all_calls(); - rxrpc_destroy_all_connections(); + unregister_pernet_subsys(&rxrpc_net_ops); ASSERTCMP(atomic_read(&rxrpc_n_tx_skbs), ==, 0); ASSERTCMP(atomic_read(&rxrpc_n_rx_skbs), ==, 0); - rxrpc_destroy_all_locals(); - remove_proc_entry("rxrpc_conns", init_net.proc_net); - remove_proc_entry("rxrpc_calls", init_net.proc_net); + /* Make sure the local and peer records pinned by any dying connections + * are released. + */ + rcu_barrier(); + rxrpc_destroy_client_conn_ids(); + destroy_workqueue(rxrpc_workqueue); rxrpc_exit_security(); kmem_cache_destroy(rxrpc_call_jar); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 7486926e60a8..69b97339ff9d 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -11,6 +11,8 @@ #include <linux/atomic.h> #include <linux/seqlock.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include <rxrpc/packet.h> @@ -59,12 +61,44 @@ enum { RXRPC_CLIENT_UNBOUND, /* Unbound socket used as client */ RXRPC_CLIENT_BOUND, /* client local address bound */ RXRPC_SERVER_BOUND, /* server local address bound */ + RXRPC_SERVER_BOUND2, /* second server local address bound */ RXRPC_SERVER_LISTENING, /* server listening for connections */ RXRPC_SERVER_LISTEN_DISABLED, /* server listening disabled */ RXRPC_CLOSE, /* socket is being closed */ }; /* + * Per-network namespace data. + */ +struct rxrpc_net { + struct proc_dir_entry *proc_net; /* Subdir in /proc/net */ + u32 epoch; /* Local epoch for detecting local-end reset */ + struct list_head calls; /* List of calls active in this namespace */ + rwlock_t call_lock; /* Lock for ->calls */ + + struct list_head conn_proc_list; /* List of conns in this namespace for proc */ + struct list_head service_conns; /* Service conns in this namespace */ + rwlock_t conn_lock; /* Lock for ->conn_proc_list, ->service_conns */ + struct delayed_work service_conn_reaper; + + unsigned int nr_client_conns; + unsigned int nr_active_client_conns; + bool kill_all_client_conns; + spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */ + spinlock_t client_conn_discard_lock; /* Prevent multiple discarders */ + struct list_head waiting_client_conns; + struct list_head active_client_conns; + struct list_head idle_client_conns; + struct delayed_work client_conn_reaper; + + struct list_head local_endpoints; + struct mutex local_mutex; /* Lock for ->local_endpoints */ + + spinlock_t peer_hash_lock; /* Lock for ->peer_hash */ + DECLARE_HASHTABLE (peer_hash, 10); +}; + +/* * Service backlog preallocation. * * This contains circular buffers of preallocated peers, connections and calls @@ -109,8 +143,14 @@ struct rxrpc_sock { u32 min_sec_level; /* minimum security level */ #define RXRPC_SECURITY_MAX RXRPC_SECURITY_ENCRYPT bool exclusive; /* Exclusive connection for a client socket */ + u16 second_service; /* Additional service bound to the endpoint */ + struct { + /* Service upgrade information */ + u16 from; /* Service ID to upgrade (if not 0) */ + u16 to; /* service ID to upgrade to */ + } service_upgrade; sa_family_t family; /* Protocol family created with */ - struct sockaddr_rxrpc srx; /* local address */ + struct sockaddr_rxrpc srx; /* Primary Service/local addresses */ struct sockaddr_rxrpc connect_srx; /* Default client address from connect() */ }; @@ -211,6 +251,7 @@ struct rxrpc_security { struct rxrpc_local { struct rcu_head rcu; atomic_t usage; + struct rxrpc_net *rxnet; /* The network ns in which this resides */ struct list_head link; struct socket *socket; /* my UDP socket */ struct work_struct processor; @@ -259,6 +300,8 @@ struct rxrpc_peer { u64 rtt_cache[RXRPC_RTT_CACHE_SIZE]; /* Determined RTT cache */ u8 rtt_cursor; /* next entry at which to insert */ u8 rtt_usage; /* amount of cache actually used */ + + u8 cong_cwnd; /* Congestion window size */ }; /* @@ -279,6 +322,7 @@ struct rxrpc_conn_parameters { struct rxrpc_peer *peer; /* Remote endpoint */ struct key *key; /* Security details */ bool exclusive; /* T if conn is exclusive */ + bool upgrade; /* T if service ID can be upgraded */ u16 service_id; /* Service ID for this connection */ u32 security_level; /* Security level selected */ }; @@ -293,6 +337,7 @@ enum rxrpc_conn_flag { RXRPC_CONN_EXPOSED, /* Conn has extra ref for exposure */ RXRPC_CONN_DONT_REUSE, /* Don't reuse this connection */ RXRPC_CONN_COUNTED, /* Counted by rxrpc_nr_client_conns */ + RXRPC_CONN_PROBING_FOR_UPGRADE, /* Probing for service upgrade */ }; /* @@ -309,6 +354,7 @@ enum rxrpc_conn_cache_state { RXRPC_CONN_CLIENT_INACTIVE, /* Conn is not yet listed */ RXRPC_CONN_CLIENT_WAITING, /* Conn is on wait list, waiting for capacity */ RXRPC_CONN_CLIENT_ACTIVE, /* Conn is on active list, doing calls */ + RXRPC_CONN_CLIENT_UPGRADE, /* Conn is on active list, probing for upgrade */ RXRPC_CONN_CLIENT_CULLED, /* Conn is culled and delisted, doing calls */ RXRPC_CONN_CLIENT_IDLE, /* Conn is on idle list, doing mostly nothing */ RXRPC_CONN__NR_CACHE_STATES @@ -352,7 +398,6 @@ struct rxrpc_connection { u32 call_counter; /* Call ID counter */ u32 last_call; /* ID of last call */ u8 last_type; /* Type of last packet */ - u16 last_service_id; union { u32 last_seq; u32 last_abort; @@ -383,6 +428,7 @@ struct rxrpc_connection { atomic_t serial; /* packet serial number counter */ unsigned int hi_serial; /* highest serial number received */ u32 security_nonce; /* response re-use preventer */ + u16 service_id; /* Service ID, possibly upgraded */ u8 size_align; /* data size alignment (for security) */ u8 security_size; /* security header size */ u8 security_ix; /* security type */ @@ -484,6 +530,7 @@ struct rxrpc_call { struct rb_node sock_node; /* Node in rx->calls */ struct sk_buff *tx_pending; /* Tx socket buffer being filled */ wait_queue_head_t waitq; /* Wait queue for channel or Tx */ + s64 tx_total_len; /* Total length left to be transmitted (or -1) */ __be32 crypto_buf[2]; /* Temporary packet crypto buffer */ unsigned long user_call_ID; /* user-defined call ID */ unsigned long flags; @@ -601,7 +648,6 @@ struct rxrpc_ack_summary { * af_rxrpc.c */ extern atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs; -extern u32 rxrpc_epoch; extern atomic_t rxrpc_debug_id; extern struct workqueue_struct *rxrpc_workqueue; @@ -634,15 +680,13 @@ extern const char *const rxrpc_call_states[]; extern const char *const rxrpc_call_completions[]; extern unsigned int rxrpc_max_call_lifetime; extern struct kmem_cache *rxrpc_call_jar; -extern struct list_head rxrpc_calls; -extern rwlock_t rxrpc_call_lock; struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long); struct rxrpc_call *rxrpc_alloc_call(gfp_t); struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *, - unsigned long, gfp_t); + unsigned long, s64, gfp_t); void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); @@ -653,7 +697,7 @@ void rxrpc_see_call(struct rxrpc_call *); void rxrpc_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_put_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_cleanup_call(struct rxrpc_call *); -void __exit rxrpc_destroy_all_calls(void); +void rxrpc_destroy_all_calls(struct rxrpc_net *); static inline bool rxrpc_is_service_call(const struct rxrpc_call *call) { @@ -773,7 +817,8 @@ int rxrpc_connect_call(struct rxrpc_call *, struct rxrpc_conn_parameters *, void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_call *); void rxrpc_put_client_conn(struct rxrpc_connection *); -void __exit rxrpc_destroy_all_client_connections(void); +void rxrpc_discard_expired_client_conns(struct work_struct *); +void rxrpc_destroy_all_client_connections(struct rxrpc_net *); /* * conn_event.c @@ -784,9 +829,6 @@ void rxrpc_process_connection(struct work_struct *); * conn_object.c */ extern unsigned int rxrpc_connection_expiry; -extern struct list_head rxrpc_connections; -extern struct list_head rxrpc_connection_proc_list; -extern rwlock_t rxrpc_connection_lock; int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *); struct rxrpc_connection *rxrpc_alloc_connection(gfp_t); @@ -800,7 +842,8 @@ void rxrpc_see_connection(struct rxrpc_connection *); void rxrpc_get_connection(struct rxrpc_connection *); struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *); void rxrpc_put_service_conn(struct rxrpc_connection *); -void __exit rxrpc_destroy_all_connections(void); +void rxrpc_service_connection_reaper(struct work_struct *); +void rxrpc_destroy_all_connections(struct rxrpc_net *); static inline bool rxrpc_conn_is_client(const struct rxrpc_connection *conn) { @@ -828,8 +871,9 @@ static inline void rxrpc_put_connection(struct rxrpc_connection *conn) */ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *, struct sk_buff *); -struct rxrpc_connection *rxrpc_prealloc_service_connection(gfp_t); -void rxrpc_new_incoming_connection(struct rxrpc_connection *, struct sk_buff *); +struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *, gfp_t); +void rxrpc_new_incoming_connection(struct rxrpc_sock *, + struct rxrpc_connection *, struct sk_buff *); void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* @@ -861,9 +905,9 @@ extern void rxrpc_process_local_events(struct rxrpc_local *); /* * local_object.c */ -struct rxrpc_local *rxrpc_lookup_local(const struct sockaddr_rxrpc *); +struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc *); void __rxrpc_put_local(struct rxrpc_local *); -void __exit rxrpc_destroy_all_locals(void); +void rxrpc_destroy_all_locals(struct rxrpc_net *); static inline void rxrpc_get_local(struct rxrpc_local *local) { @@ -902,6 +946,17 @@ extern unsigned int rxrpc_resend_timeout; extern const s8 rxrpc_ack_priority[]; /* + * net_ns.c + */ +extern unsigned int rxrpc_net_id; +extern struct pernet_operations rxrpc_net_ops; + +static inline struct rxrpc_net *rxrpc_net(struct net *net) +{ + return net_generic(net, rxrpc_net_id); +} + +/* * output.c */ int rxrpc_send_ack_packet(struct rxrpc_call *, bool); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 1752fcf8e8f1..dd30d74824b0 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -38,6 +38,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, { const void *here = __builtin_return_address(0); struct rxrpc_call *call; + struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); int max, tmp; unsigned int size = RXRPC_BACKLOG_MAX; unsigned int head, tail, call_head, call_tail; @@ -79,7 +80,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, if (CIRC_CNT(head, tail, size) < max) { struct rxrpc_connection *conn; - conn = rxrpc_prealloc_service_connection(gfp); + conn = rxrpc_prealloc_service_connection(rxnet, gfp); if (!conn) return -ENOMEM; b->conn_backlog[head] = conn; @@ -136,9 +137,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, write_unlock(&rx->call_lock); - write_lock(&rxrpc_call_lock); - list_add_tail(&call->link, &rxrpc_calls); - write_unlock(&rxrpc_call_lock); + write_lock(&rxnet->call_lock); + list_add_tail(&call->link, &rxnet->calls); + write_unlock(&rxnet->call_lock); b->call_backlog[call_head] = call; smp_store_release(&b->call_backlog_head, (call_head + 1) & (size - 1)); @@ -185,6 +186,7 @@ int rxrpc_service_prealloc(struct rxrpc_sock *rx, gfp_t gfp) void rxrpc_discard_prealloc(struct rxrpc_sock *rx) { struct rxrpc_backlog *b = rx->backlog; + struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); unsigned int size = RXRPC_BACKLOG_MAX, head, tail; if (!b) @@ -209,10 +211,10 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) tail = b->conn_backlog_tail; while (CIRC_CNT(head, tail, size) > 0) { struct rxrpc_connection *conn = b->conn_backlog[tail]; - write_lock(&rxrpc_connection_lock); + write_lock(&rxnet->conn_lock); list_del(&conn->link); list_del(&conn->proc_link); - write_unlock(&rxrpc_connection_lock); + write_unlock(&rxnet->conn_lock); kfree(conn); tail = (tail + 1) & (size - 1); } @@ -294,7 +296,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, conn->params.local = local; conn->params.peer = peer; rxrpc_see_connection(conn); - rxrpc_new_incoming_connection(conn, skb); + rxrpc_new_incoming_connection(rx, conn, skb); } else { rxrpc_get_connection(conn); } @@ -308,6 +310,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, rxrpc_see_call(call); call->conn = conn; call->peer = rxrpc_get_peer(conn->params.peer); + call->cong_cwnd = call->peer->cong_cwnd; return call; } @@ -339,7 +342,8 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, /* Get the socket providing the service */ rx = rcu_dereference(local->service); - if (rx && service_id == rx->srx.srx_service) + if (rx && (service_id == rx->srx.srx_service || + service_id == rx->second_service)) goto found_service; trace_rxrpc_abort("INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 47f7f4205653..d7809a0620b4 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -44,8 +44,6 @@ const char *const rxrpc_call_completions[NR__RXRPC_CALL_COMPLETIONS] = { }; struct kmem_cache *rxrpc_call_jar; -LIST_HEAD(rxrpc_calls); -DEFINE_RWLOCK(rxrpc_call_lock); static void rxrpc_call_timer_expired(unsigned long _call) { @@ -129,6 +127,7 @@ struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) rwlock_init(&call->state_lock); atomic_set(&call->usage, 1); call->debug_id = atomic_inc_return(&rxrpc_debug_id); + call->tx_total_len = -1; memset(&call->sock_node, 0xed, sizeof(call->sock_node)); @@ -137,12 +136,7 @@ struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) call->tx_winsize = 16; call->rx_expect_next = 1; - if (RXRPC_TX_SMSS > 2190) - call->cong_cwnd = 2; - else if (RXRPC_TX_SMSS > 1095) - call->cong_cwnd = 3; - else - call->cong_cwnd = 4; + call->cong_cwnd = 2; call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1; return call; @@ -203,10 +197,12 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, struct rxrpc_conn_parameters *cp, struct sockaddr_rxrpc *srx, unsigned long user_call_ID, + s64 tx_total_len, gfp_t gfp) __releases(&rx->sk.sk_lock.slock) { struct rxrpc_call *call, *xcall; + struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); struct rb_node *parent, **pp; const void *here = __builtin_return_address(0); int ret; @@ -220,6 +216,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, return call; } + call->tx_total_len = tx_total_len; trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage), here, (const void *)user_call_ID); @@ -255,9 +252,9 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, write_unlock(&rx->call_lock); - write_lock(&rxrpc_call_lock); - list_add_tail(&call->link, &rxrpc_calls); - write_unlock(&rxrpc_call_lock); + write_lock(&rxnet->call_lock); + list_add_tail(&call->link, &rxnet->calls); + write_unlock(&rxnet->call_lock); /* From this point on, the call is protected by its own lock. */ release_sock(&rx->sk); @@ -508,6 +505,7 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) */ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) { + struct rxrpc_net *rxnet; const void *here = __builtin_return_address(0); int n; @@ -520,9 +518,12 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) _debug("call %d dead", call->debug_id); ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); - write_lock(&rxrpc_call_lock); - list_del_init(&call->link); - write_unlock(&rxrpc_call_lock); + if (!list_empty(&call->link)) { + rxnet = rxrpc_net(sock_net(&call->socket->sk)); + write_lock(&rxnet->call_lock); + list_del_init(&call->link); + write_unlock(&rxnet->call_lock); + } rxrpc_cleanup_call(call); } @@ -570,21 +571,23 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) } /* - * Make sure that all calls are gone. + * Make sure that all calls are gone from a network namespace. To reach this + * point, any open UDP sockets in that namespace must have been closed, so any + * outstanding calls cannot be doing I/O. */ -void __exit rxrpc_destroy_all_calls(void) +void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet) { struct rxrpc_call *call; _enter(""); - if (list_empty(&rxrpc_calls)) + if (list_empty(&rxnet->calls)) return; - write_lock(&rxrpc_call_lock); + write_lock(&rxnet->call_lock); - while (!list_empty(&rxrpc_calls)) { - call = list_entry(rxrpc_calls.next, struct rxrpc_call, link); + while (!list_empty(&rxnet->calls)) { + call = list_entry(rxnet->calls.next, struct rxrpc_call, link); _debug("Zapping call %p", call); rxrpc_see_call(call); @@ -595,10 +598,10 @@ void __exit rxrpc_destroy_all_calls(void) rxrpc_call_states[call->state], call->flags, call->events); - write_unlock(&rxrpc_call_lock); + write_unlock(&rxnet->call_lock); cond_resched(); - write_lock(&rxrpc_call_lock); + write_lock(&rxnet->call_lock); } - write_unlock(&rxrpc_call_lock); + write_unlock(&rxnet->call_lock); } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index e8dea0d49e7f..eb2157680399 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -31,22 +31,25 @@ * may freely grant available channels to new calls and calls may be * waiting on it for channels to become available. * - * The connection is on the rxrpc_active_client_conns list which is kept + * The connection is on the rxnet->active_client_conns list which is kept * in activation order for culling purposes. * * rxrpc_nr_active_client_conns is held incremented also. * - * (4) CULLED - The connection got summarily culled to try and free up + * (4) UPGRADE - As for ACTIVE, but only one call may be in progress and is + * being used to probe for service upgrade. + * + * (5) CULLED - The connection got summarily culled to try and free up * capacity. Calls currently in progress on the connection are allowed to * continue, but new calls will have to wait. There can be no waiters in * this state - the conn would have to go to the WAITING state instead. * - * (5) IDLE - The connection has no calls in progress upon it and must have + * (6) IDLE - The connection has no calls in progress upon it and must have * been exposed to the world (ie. the EXPOSED flag must be set). When it * expires, the EXPOSED flag is cleared and the connection transitions to * the INACTIVE state. * - * The connection is on the rxrpc_idle_client_conns list which is kept in + * The connection is on the rxnet->idle_client_conns list which is kept in * order of how soon they'll expire. * * There are flags of relevance to the cache: @@ -85,27 +88,13 @@ __read_mostly unsigned int rxrpc_reap_client_connections = 900; __read_mostly unsigned int rxrpc_conn_idle_client_expiry = 2 * 60 * HZ; __read_mostly unsigned int rxrpc_conn_idle_client_fast_expiry = 2 * HZ; -static unsigned int rxrpc_nr_client_conns; -static unsigned int rxrpc_nr_active_client_conns; -static __read_mostly bool rxrpc_kill_all_client_conns; - -static DEFINE_SPINLOCK(rxrpc_client_conn_cache_lock); -static DEFINE_SPINLOCK(rxrpc_client_conn_discard_mutex); -static LIST_HEAD(rxrpc_waiting_client_conns); -static LIST_HEAD(rxrpc_active_client_conns); -static LIST_HEAD(rxrpc_idle_client_conns); - /* * We use machine-unique IDs for our client connections. */ DEFINE_IDR(rxrpc_client_conn_ids); static DEFINE_SPINLOCK(rxrpc_conn_id_lock); -static void rxrpc_cull_active_client_conns(void); -static void rxrpc_discard_expired_client_conns(struct work_struct *); - -static DECLARE_DELAYED_WORK(rxrpc_client_conn_reap, - rxrpc_discard_expired_client_conns); +static void rxrpc_cull_active_client_conns(struct rxrpc_net *); /* * Get a connection ID and epoch for a client connection from the global pool. @@ -116,6 +105,7 @@ static DECLARE_DELAYED_WORK(rxrpc_client_conn_reap, static int rxrpc_get_client_connection_id(struct rxrpc_connection *conn, gfp_t gfp) { + struct rxrpc_net *rxnet = conn->params.local->rxnet; int id; _enter(""); @@ -131,7 +121,7 @@ static int rxrpc_get_client_connection_id(struct rxrpc_connection *conn, spin_unlock(&rxrpc_conn_id_lock); idr_preload_end(); - conn->proto.epoch = rxrpc_epoch; + conn->proto.epoch = rxnet->epoch; conn->proto.cid = id << RXRPC_CIDSHIFT; set_bit(RXRPC_CONN_HAS_IDR, &conn->flags); _leave(" [CID %x]", conn->proto.cid); @@ -183,6 +173,7 @@ static struct rxrpc_connection * rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) { struct rxrpc_connection *conn; + struct rxrpc_net *rxnet = cp->local->rxnet; int ret; _enter(""); @@ -196,10 +187,13 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) atomic_set(&conn->usage, 1); if (cp->exclusive) __set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); + if (cp->upgrade) + __set_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags); conn->params = *cp; conn->out_clientflag = RXRPC_CLIENT_INITIATED; conn->state = RXRPC_CONN_CLIENT; + conn->service_id = cp->service_id; ret = rxrpc_get_client_connection_id(conn, gfp); if (ret < 0) @@ -213,9 +207,9 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) if (ret < 0) goto error_2; - write_lock(&rxrpc_connection_lock); - list_add_tail(&conn->proc_link, &rxrpc_connection_proc_list); - write_unlock(&rxrpc_connection_lock); + write_lock(&rxnet->conn_lock); + list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); + write_unlock(&rxnet->conn_lock); /* We steal the caller's peer ref. */ cp->peer = NULL; @@ -243,12 +237,13 @@ error_0: */ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn) { + struct rxrpc_net *rxnet = conn->params.local->rxnet; int id_cursor, id, distance, limit; if (test_bit(RXRPC_CONN_DONT_REUSE, &conn->flags)) goto dont_reuse; - if (conn->proto.epoch != rxrpc_epoch) + if (conn->proto.epoch != rxnet->epoch) goto mark_dont_reuse; /* The IDR tree gets very expensive on memory if the connection IDs are @@ -297,6 +292,12 @@ static int rxrpc_get_client_conn(struct rxrpc_call *call, if (!cp->peer) goto error; + call->cong_cwnd = cp->peer->cong_cwnd; + if (call->cong_cwnd >= call->cong_ssthresh) + call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; + else + call->cong_mode = RXRPC_CALL_SLOW_START; + /* If the connection is not meant to be exclusive, search the available * connections to see if the connection we want to use already exists. */ @@ -310,7 +311,8 @@ static int rxrpc_get_client_conn(struct rxrpc_call *call, #define cmp(X) ((long)conn->params.X - (long)cp->X) diff = (cmp(peer) ?: cmp(key) ?: - cmp(security_level)); + cmp(security_level) ?: + cmp(upgrade)); #undef cmp if (diff < 0) { p = p->rb_left; @@ -354,6 +356,7 @@ static int rxrpc_get_client_conn(struct rxrpc_call *call, if (cp->exclusive) { call->conn = candidate; call->security_ix = candidate->security_ix; + call->service_id = candidate->service_id; _leave(" = 0 [exclusive %d]", candidate->debug_id); return 0; } @@ -374,7 +377,8 @@ static int rxrpc_get_client_conn(struct rxrpc_call *call, #define cmp(X) ((long)conn->params.X - (long)candidate->params.X) diff = (cmp(peer) ?: cmp(key) ?: - cmp(security_level)); + cmp(security_level) ?: + cmp(upgrade)); #undef cmp if (diff < 0) { pp = &(*pp)->rb_left; @@ -403,6 +407,7 @@ candidate_published: set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags); call->conn = candidate; call->security_ix = candidate->security_ix; + call->service_id = candidate->service_id; spin_unlock(&local->client_conns_lock); _leave(" = 0 [new %d]", candidate->debug_id); return 0; @@ -424,6 +429,7 @@ found_extant_conn: spin_lock(&conn->channel_lock); call->conn = conn; call->security_ix = conn->security_ix; + call->service_id = conn->service_id; list_add(&call->chan_wait_link, &conn->waiting_calls); spin_unlock(&conn->channel_lock); _leave(" = 0 [extant %d]", conn->debug_id); @@ -440,12 +446,18 @@ error: /* * Activate a connection. */ -static void rxrpc_activate_conn(struct rxrpc_connection *conn) +static void rxrpc_activate_conn(struct rxrpc_net *rxnet, + struct rxrpc_connection *conn) { - trace_rxrpc_client(conn, -1, rxrpc_client_to_active); - conn->cache_state = RXRPC_CONN_CLIENT_ACTIVE; - rxrpc_nr_active_client_conns++; - list_move_tail(&conn->cache_link, &rxrpc_active_client_conns); + if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) { + trace_rxrpc_client(conn, -1, rxrpc_client_to_upgrade); + conn->cache_state = RXRPC_CONN_CLIENT_UPGRADE; + } else { + trace_rxrpc_client(conn, -1, rxrpc_client_to_active); + conn->cache_state = RXRPC_CONN_CLIENT_ACTIVE; + } + rxnet->nr_active_client_conns++; + list_move_tail(&conn->cache_link, &rxnet->active_client_conns); } /* @@ -460,25 +472,28 @@ static void rxrpc_activate_conn(struct rxrpc_connection *conn) * channels if it has been culled to make space and then re-requested by a new * call. */ -static void rxrpc_animate_client_conn(struct rxrpc_connection *conn) +static void rxrpc_animate_client_conn(struct rxrpc_net *rxnet, + struct rxrpc_connection *conn) { unsigned int nr_conns; _enter("%d,%d", conn->debug_id, conn->cache_state); - if (conn->cache_state == RXRPC_CONN_CLIENT_ACTIVE) + if (conn->cache_state == RXRPC_CONN_CLIENT_ACTIVE || + conn->cache_state == RXRPC_CONN_CLIENT_UPGRADE) goto out; - spin_lock(&rxrpc_client_conn_cache_lock); + spin_lock(&rxnet->client_conn_cache_lock); - nr_conns = rxrpc_nr_client_conns; + nr_conns = rxnet->nr_client_conns; if (!test_and_set_bit(RXRPC_CONN_COUNTED, &conn->flags)) { trace_rxrpc_client(conn, -1, rxrpc_client_count); - rxrpc_nr_client_conns = nr_conns + 1; + rxnet->nr_client_conns = nr_conns + 1; } switch (conn->cache_state) { case RXRPC_CONN_CLIENT_ACTIVE: + case RXRPC_CONN_CLIENT_UPGRADE: case RXRPC_CONN_CLIENT_WAITING: break; @@ -494,21 +509,21 @@ static void rxrpc_animate_client_conn(struct rxrpc_connection *conn) } out_unlock: - spin_unlock(&rxrpc_client_conn_cache_lock); + spin_unlock(&rxnet->client_conn_cache_lock); out: _leave(" [%d]", conn->cache_state); return; activate_conn: _debug("activate"); - rxrpc_activate_conn(conn); + rxrpc_activate_conn(rxnet, conn); goto out_unlock; wait_for_capacity: _debug("wait"); trace_rxrpc_client(conn, -1, rxrpc_client_to_waiting); conn->cache_state = RXRPC_CONN_CLIENT_WAITING; - list_move_tail(&conn->cache_link, &rxrpc_waiting_client_conns); + list_move_tail(&conn->cache_link, &rxnet->waiting_client_conns); goto out_unlock; } @@ -582,6 +597,9 @@ static void rxrpc_activate_channels_locked(struct rxrpc_connection *conn) case RXRPC_CONN_CLIENT_ACTIVE: mask = RXRPC_ACTIVE_CHANS_MASK; break; + case RXRPC_CONN_CLIENT_UPGRADE: + mask = 0x01; + break; default: return; } @@ -660,18 +678,19 @@ int rxrpc_connect_call(struct rxrpc_call *call, struct sockaddr_rxrpc *srx, gfp_t gfp) { + struct rxrpc_net *rxnet = cp->local->rxnet; int ret; _enter("{%d,%lx},", call->debug_id, call->user_call_ID); - rxrpc_discard_expired_client_conns(NULL); - rxrpc_cull_active_client_conns(); + rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper.work); + rxrpc_cull_active_client_conns(rxnet); ret = rxrpc_get_client_conn(call, cp, srx, gfp); if (ret < 0) return ret; - rxrpc_animate_client_conn(call->conn); + rxrpc_animate_client_conn(rxnet, call->conn); rxrpc_activate_channels(call->conn); ret = rxrpc_wait_for_channel(call, gfp); @@ -729,6 +748,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) unsigned int channel = call->cid & RXRPC_CHANNELMASK; struct rxrpc_connection *conn = call->conn; struct rxrpc_channel *chan = &conn->channels[channel]; + struct rxrpc_net *rxnet = rxrpc_net(sock_net(&call->socket->sk)); trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect); call->conn = NULL; @@ -750,7 +770,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) /* We must deactivate or idle the connection if it's now * waiting for nothing. */ - spin_lock(&rxrpc_client_conn_cache_lock); + spin_lock(&rxnet->client_conn_cache_lock); if (conn->cache_state == RXRPC_CONN_CLIENT_WAITING && list_empty(&conn->waiting_calls) && !conn->active_chans) @@ -787,14 +807,23 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) * list. It might even get moved back to the active list whilst we're * waiting for the lock. */ - spin_lock(&rxrpc_client_conn_cache_lock); + spin_lock(&rxnet->client_conn_cache_lock); switch (conn->cache_state) { + case RXRPC_CONN_CLIENT_UPGRADE: + /* Deal with termination of a service upgrade probe. */ + if (test_bit(RXRPC_CONN_EXPOSED, &conn->flags)) { + clear_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags); + trace_rxrpc_client(conn, channel, rxrpc_client_to_active); + conn->cache_state = RXRPC_CONN_CLIENT_ACTIVE; + rxrpc_activate_channels_locked(conn); + } + /* fall through */ case RXRPC_CONN_CLIENT_ACTIVE: if (list_empty(&conn->waiting_calls)) { rxrpc_deactivate_one_channel(conn, channel); if (!conn->active_chans) { - rxrpc_nr_active_client_conns--; + rxnet->nr_active_client_conns--; goto idle_connection; } goto out; @@ -820,7 +849,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) } out: - spin_unlock(&rxrpc_client_conn_cache_lock); + spin_unlock(&rxnet->client_conn_cache_lock); out_2: spin_unlock(&conn->channel_lock); rxrpc_put_connection(conn); @@ -835,11 +864,11 @@ idle_connection: trace_rxrpc_client(conn, channel, rxrpc_client_to_idle); conn->idle_timestamp = jiffies; conn->cache_state = RXRPC_CONN_CLIENT_IDLE; - list_move_tail(&conn->cache_link, &rxrpc_idle_client_conns); - if (rxrpc_idle_client_conns.next == &conn->cache_link && - !rxrpc_kill_all_client_conns) + list_move_tail(&conn->cache_link, &rxnet->idle_client_conns); + if (rxnet->idle_client_conns.next == &conn->cache_link && + !rxnet->kill_all_client_conns) queue_delayed_work(rxrpc_workqueue, - &rxrpc_client_conn_reap, + &rxnet->client_conn_reaper, rxrpc_conn_idle_client_expiry); } else { trace_rxrpc_client(conn, channel, rxrpc_client_to_inactive); @@ -857,6 +886,7 @@ rxrpc_put_one_client_conn(struct rxrpc_connection *conn) { struct rxrpc_connection *next = NULL; struct rxrpc_local *local = conn->params.local; + struct rxrpc_net *rxnet = local->rxnet; unsigned int nr_conns; trace_rxrpc_client(conn, -1, rxrpc_client_cleanup); @@ -875,18 +905,18 @@ rxrpc_put_one_client_conn(struct rxrpc_connection *conn) if (test_bit(RXRPC_CONN_COUNTED, &conn->flags)) { trace_rxrpc_client(conn, -1, rxrpc_client_uncount); - spin_lock(&rxrpc_client_conn_cache_lock); - nr_conns = --rxrpc_nr_client_conns; + spin_lock(&rxnet->client_conn_cache_lock); + nr_conns = --rxnet->nr_client_conns; if (nr_conns < rxrpc_max_client_connections && - !list_empty(&rxrpc_waiting_client_conns)) { - next = list_entry(rxrpc_waiting_client_conns.next, + !list_empty(&rxnet->waiting_client_conns)) { + next = list_entry(rxnet->waiting_client_conns.next, struct rxrpc_connection, cache_link); rxrpc_get_connection(next); - rxrpc_activate_conn(next); + rxrpc_activate_conn(rxnet, next); } - spin_unlock(&rxrpc_client_conn_cache_lock); + spin_unlock(&rxnet->client_conn_cache_lock); } rxrpc_kill_connection(conn); @@ -921,10 +951,10 @@ void rxrpc_put_client_conn(struct rxrpc_connection *conn) /* * Kill the longest-active client connections to make room for new ones. */ -static void rxrpc_cull_active_client_conns(void) +static void rxrpc_cull_active_client_conns(struct rxrpc_net *rxnet) { struct rxrpc_connection *conn; - unsigned int nr_conns = rxrpc_nr_client_conns; + unsigned int nr_conns = rxnet->nr_client_conns; unsigned int nr_active, limit; _enter(""); @@ -936,14 +966,15 @@ static void rxrpc_cull_active_client_conns(void) } limit = rxrpc_reap_client_connections; - spin_lock(&rxrpc_client_conn_cache_lock); - nr_active = rxrpc_nr_active_client_conns; + spin_lock(&rxnet->client_conn_cache_lock); + nr_active = rxnet->nr_active_client_conns; while (nr_active > limit) { - ASSERT(!list_empty(&rxrpc_active_client_conns)); - conn = list_entry(rxrpc_active_client_conns.next, + ASSERT(!list_empty(&rxnet->active_client_conns)); + conn = list_entry(rxnet->active_client_conns.next, struct rxrpc_connection, cache_link); - ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_ACTIVE); + ASSERTIFCMP(conn->cache_state != RXRPC_CONN_CLIENT_ACTIVE, + conn->cache_state, ==, RXRPC_CONN_CLIENT_UPGRADE); if (list_empty(&conn->waiting_calls)) { trace_rxrpc_client(conn, -1, rxrpc_client_to_culled); @@ -953,14 +984,14 @@ static void rxrpc_cull_active_client_conns(void) trace_rxrpc_client(conn, -1, rxrpc_client_to_waiting); conn->cache_state = RXRPC_CONN_CLIENT_WAITING; list_move_tail(&conn->cache_link, - &rxrpc_waiting_client_conns); + &rxnet->waiting_client_conns); } nr_active--; } - rxrpc_nr_active_client_conns = nr_active; - spin_unlock(&rxrpc_client_conn_cache_lock); + rxnet->nr_active_client_conns = nr_active; + spin_unlock(&rxnet->client_conn_cache_lock); ASSERTCMP(nr_active, >=, 0); _leave(" [culled]"); } @@ -972,22 +1003,25 @@ static void rxrpc_cull_active_client_conns(void) * This may be called from conn setup or from a work item so cannot be * considered non-reentrant. */ -static void rxrpc_discard_expired_client_conns(struct work_struct *work) +void rxrpc_discard_expired_client_conns(struct work_struct *work) { struct rxrpc_connection *conn; + struct rxrpc_net *rxnet = + container_of(to_delayed_work(work), + struct rxrpc_net, client_conn_reaper); unsigned long expiry, conn_expires_at, now; unsigned int nr_conns; bool did_discard = false; - _enter("%c", work ? 'w' : 'n'); + _enter(""); - if (list_empty(&rxrpc_idle_client_conns)) { + if (list_empty(&rxnet->idle_client_conns)) { _leave(" [empty]"); return; } /* Don't double up on the discarding */ - if (!spin_trylock(&rxrpc_client_conn_discard_mutex)) { + if (!spin_trylock(&rxnet->client_conn_discard_lock)) { _leave(" [already]"); return; } @@ -995,19 +1029,19 @@ static void rxrpc_discard_expired_client_conns(struct work_struct *work) /* We keep an estimate of what the number of conns ought to be after * we've discarded some so that we don't overdo the discarding. */ - nr_conns = rxrpc_nr_client_conns; + nr_conns = rxnet->nr_client_conns; next: - spin_lock(&rxrpc_client_conn_cache_lock); + spin_lock(&rxnet->client_conn_cache_lock); - if (list_empty(&rxrpc_idle_client_conns)) + if (list_empty(&rxnet->idle_client_conns)) goto out; - conn = list_entry(rxrpc_idle_client_conns.next, + conn = list_entry(rxnet->idle_client_conns.next, struct rxrpc_connection, cache_link); ASSERT(test_bit(RXRPC_CONN_EXPOSED, &conn->flags)); - if (!rxrpc_kill_all_client_conns) { + if (!rxnet->kill_all_client_conns) { /* If the number of connections is over the reap limit, we * expedite discard by reducing the expiry timeout. We must, * however, have at least a short grace period to be able to do @@ -1030,7 +1064,7 @@ next: conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE; list_del_init(&conn->cache_link); - spin_unlock(&rxrpc_client_conn_cache_lock); + spin_unlock(&rxnet->client_conn_cache_lock); /* When we cleared the EXPOSED flag, we took on responsibility for the * reference that that had on the usage count. We deal with that here. @@ -1050,14 +1084,14 @@ not_yet_expired: * then things get messier. */ _debug("not yet"); - if (!rxrpc_kill_all_client_conns) + if (!rxnet->kill_all_client_conns) queue_delayed_work(rxrpc_workqueue, - &rxrpc_client_conn_reap, + &rxnet->client_conn_reaper, conn_expires_at - now); out: - spin_unlock(&rxrpc_client_conn_cache_lock); - spin_unlock(&rxrpc_client_conn_discard_mutex); + spin_unlock(&rxnet->client_conn_cache_lock); + spin_unlock(&rxnet->client_conn_discard_lock); _leave(""); } @@ -1065,17 +1099,17 @@ out: * Preemptively destroy all the client connection records rather than waiting * for them to time out */ -void __exit rxrpc_destroy_all_client_connections(void) +void rxrpc_destroy_all_client_connections(struct rxrpc_net *rxnet) { _enter(""); - spin_lock(&rxrpc_client_conn_cache_lock); - rxrpc_kill_all_client_conns = true; - spin_unlock(&rxrpc_client_conn_cache_lock); + spin_lock(&rxnet->client_conn_cache_lock); + rxnet->kill_all_client_conns = true; + spin_unlock(&rxnet->client_conn_cache_lock); - cancel_delayed_work(&rxrpc_client_conn_reap); + cancel_delayed_work(&rxnet->client_conn_reaper); - if (!queue_delayed_work(rxrpc_workqueue, &rxrpc_client_conn_reap, 0)) + if (!queue_delayed_work(rxrpc_workqueue, &rxnet->client_conn_reaper, 0)) _debug("destroy: queue failed"); _leave(""); diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 46babcf82ce8..59a51a56e7c8 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -74,7 +74,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, pkt.whdr.userStatus = 0; pkt.whdr.securityIndex = conn->security_ix; pkt.whdr._rsvd = 0; - pkt.whdr.serviceId = htons(chan->last_service_id); + pkt.whdr.serviceId = htons(conn->service_id); len = sizeof(pkt.whdr); switch (chan->last_type) { @@ -208,7 +208,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, whdr.userStatus = 0; whdr.securityIndex = conn->security_ix; whdr._rsvd = 0; - whdr.serviceId = htons(conn->params.service_id); + whdr.serviceId = htons(conn->service_id); word = htonl(conn->local_abort); diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index b0ecb770fdce..929b50d5afe8 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -22,13 +22,6 @@ */ unsigned int rxrpc_connection_expiry = 10 * 60; -static void rxrpc_connection_reaper(struct work_struct *work); - -LIST_HEAD(rxrpc_connections); -LIST_HEAD(rxrpc_connection_proc_list); -DEFINE_RWLOCK(rxrpc_connection_lock); -static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper); - static void rxrpc_destroy_connection(struct rcu_head *); /* @@ -174,7 +167,6 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, * through the channel, whilst disposing of the actual call record. */ trace_rxrpc_disconnect_call(call); - chan->last_service_id = call->service_id; if (call->abort_code) { chan->last_abort = call->abort_code; chan->last_type = RXRPC_PACKET_TYPE_ABORT; @@ -201,6 +193,8 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; + call->peer->cong_cwnd = call->cong_cwnd; + spin_lock_bh(&conn->params.peer->lock); hlist_del_init(&call->error_link); spin_unlock_bh(&conn->params.peer->lock); @@ -222,15 +216,17 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) */ void rxrpc_kill_connection(struct rxrpc_connection *conn) { + struct rxrpc_net *rxnet = conn->params.local->rxnet; + ASSERT(!rcu_access_pointer(conn->channels[0].call) && !rcu_access_pointer(conn->channels[1].call) && !rcu_access_pointer(conn->channels[2].call) && !rcu_access_pointer(conn->channels[3].call)); ASSERT(list_empty(&conn->cache_link)); - write_lock(&rxrpc_connection_lock); + write_lock(&rxnet->conn_lock); list_del_init(&conn->proc_link); - write_unlock(&rxrpc_connection_lock); + write_unlock(&rxnet->conn_lock); /* Drain the Rx queue. Note that even though we've unpublished, an * incoming packet could still be being added to our Rx queue, so we @@ -309,14 +305,17 @@ rxrpc_get_connection_maybe(struct rxrpc_connection *conn) */ void rxrpc_put_service_conn(struct rxrpc_connection *conn) { + struct rxrpc_net *rxnet; const void *here = __builtin_return_address(0); int n; n = atomic_dec_return(&conn->usage); trace_rxrpc_conn(conn, rxrpc_conn_put_service, n, here); ASSERTCMP(n, >=, 0); - if (n == 0) - rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); + if (n == 0) { + rxnet = conn->params.local->rxnet; + rxrpc_queue_delayed_work(&rxnet->service_conn_reaper, 0); + } } /* @@ -348,9 +347,12 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu) /* * reap dead service connections */ -static void rxrpc_connection_reaper(struct work_struct *work) +void rxrpc_service_connection_reaper(struct work_struct *work) { struct rxrpc_connection *conn, *_p; + struct rxrpc_net *rxnet = + container_of(to_delayed_work(work), + struct rxrpc_net, service_conn_reaper); unsigned long reap_older_than, earliest, idle_timestamp, now; LIST_HEAD(graveyard); @@ -361,8 +363,8 @@ static void rxrpc_connection_reaper(struct work_struct *work) reap_older_than = now - rxrpc_connection_expiry * HZ; earliest = ULONG_MAX; - write_lock(&rxrpc_connection_lock); - list_for_each_entry_safe(conn, _p, &rxrpc_connections, link) { + write_lock(&rxnet->conn_lock); + list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) { ASSERTCMP(atomic_read(&conn->usage), >, 0); if (likely(atomic_read(&conn->usage) > 1)) continue; @@ -393,12 +395,12 @@ static void rxrpc_connection_reaper(struct work_struct *work) list_move_tail(&conn->link, &graveyard); } - write_unlock(&rxrpc_connection_lock); + write_unlock(&rxnet->conn_lock); if (earliest != ULONG_MAX) { _debug("reschedule reaper %ld", (long) earliest - now); ASSERT(time_after(earliest, now)); - rxrpc_queue_delayed_work(&rxrpc_connection_reap, + rxrpc_queue_delayed_work(&rxnet->client_conn_reaper, earliest - now); } @@ -418,36 +420,30 @@ static void rxrpc_connection_reaper(struct work_struct *work) * preemptively destroy all the service connection records rather than * waiting for them to time out */ -void __exit rxrpc_destroy_all_connections(void) +void rxrpc_destroy_all_connections(struct rxrpc_net *rxnet) { struct rxrpc_connection *conn, *_p; bool leak = false; _enter(""); - rxrpc_destroy_all_client_connections(); + rxrpc_destroy_all_client_connections(rxnet); rxrpc_connection_expiry = 0; - cancel_delayed_work(&rxrpc_connection_reap); - rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); + cancel_delayed_work(&rxnet->client_conn_reaper); + rxrpc_queue_delayed_work(&rxnet->client_conn_reaper, 0); flush_workqueue(rxrpc_workqueue); - write_lock(&rxrpc_connection_lock); - list_for_each_entry_safe(conn, _p, &rxrpc_connections, link) { + write_lock(&rxnet->conn_lock); + list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) { pr_err("AF_RXRPC: Leaked conn %p {%d}\n", conn, atomic_read(&conn->usage)); leak = true; } - write_unlock(&rxrpc_connection_lock); + write_unlock(&rxnet->conn_lock); BUG_ON(leak); - ASSERT(list_empty(&rxrpc_connection_proc_list)); - - /* Make sure the local and peer records pinned by any dying connections - * are released. - */ - rcu_barrier(); - rxrpc_destroy_client_conn_ids(); + ASSERT(list_empty(&rxnet->conn_proc_list)); _leave(""); } diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index eef551f40dc2..e60fcd2a4a02 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -121,7 +121,8 @@ replace_old_connection: * Preallocate a service connection. The connection is placed on the proc and * reap lists so that we don't have to get the lock from BH context. */ -struct rxrpc_connection *rxrpc_prealloc_service_connection(gfp_t gfp) +struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxnet, + gfp_t gfp) { struct rxrpc_connection *conn = rxrpc_alloc_connection(gfp); @@ -132,10 +133,10 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(gfp_t gfp) conn->state = RXRPC_CONN_SERVICE_PREALLOC; atomic_set(&conn->usage, 2); - write_lock(&rxrpc_connection_lock); - list_add_tail(&conn->link, &rxrpc_connections); - list_add_tail(&conn->proc_link, &rxrpc_connection_proc_list); - write_unlock(&rxrpc_connection_lock); + write_lock(&rxnet->conn_lock); + list_add_tail(&conn->link, &rxnet->service_conns); + list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); + write_unlock(&rxnet->conn_lock); trace_rxrpc_conn(conn, rxrpc_conn_new_service, atomic_read(&conn->usage), @@ -149,7 +150,8 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(gfp_t gfp) * Set up an incoming connection. This is called in BH context with the RCU * read lock held. */ -void rxrpc_new_incoming_connection(struct rxrpc_connection *conn, +void rxrpc_new_incoming_connection(struct rxrpc_sock *rx, + struct rxrpc_connection *conn, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -159,6 +161,7 @@ void rxrpc_new_incoming_connection(struct rxrpc_connection *conn, conn->proto.epoch = sp->hdr.epoch; conn->proto.cid = sp->hdr.cid & RXRPC_CIDMASK; conn->params.service_id = sp->hdr.serviceId; + conn->service_id = sp->hdr.serviceId; conn->security_ix = sp->hdr.securityIndex; conn->out_clientflag = 0; if (conn->security_ix) @@ -166,6 +169,14 @@ void rxrpc_new_incoming_connection(struct rxrpc_connection *conn, else conn->state = RXRPC_CONN_SERVICE; + /* See if we should upgrade the service. This can only happen on the + * first packet on a new connection. Once done, it applies to all + * subsequent calls on that connection. + */ + if (sp->hdr.userStatus == RXRPC_USERSTATUS_SERVICE_UPGRADE && + conn->service_id == rx->service_upgrade.from) + conn->service_id = rx->service_upgrade.to; + /* Make the connection a target for incoming packets. */ rxrpc_publish_service_conn(conn->params.peer, conn); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 45dba732a3b4..e56e23ed2229 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1142,6 +1142,13 @@ void rxrpc_data_ready(struct sock *udp_sk) if (sp->hdr.securityIndex != conn->security_ix) goto wrong_security; + if (sp->hdr.serviceId != conn->service_id) { + if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) || + conn->service_id != conn->params.service_id) + goto reupgrade; + conn->service_id = sp->hdr.serviceId; + } + if (sp->hdr.callNumber == 0) { /* Connection-level packet */ _debug("CONN %p {%d}", conn, conn->debug_id); @@ -1194,6 +1201,9 @@ void rxrpc_data_ready(struct sock *udp_sk) rxrpc_input_implicit_end_call(conn, call); call = NULL; } + + if (call && sp->hdr.serviceId != call->service_id) + call->service_id = sp->hdr.serviceId; } else { skew = 0; call = NULL; @@ -1237,11 +1247,18 @@ wrong_security: skb->priority = RXKADINCONSISTENCY; goto post_abort; +reupgrade: + rcu_read_unlock(); + trace_rxrpc_abort("UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_PROTOCOL_ERROR, EBADMSG); + goto protocol_error; + bad_message_unlock: rcu_read_unlock(); bad_message: trace_rxrpc_abort("BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, RX_PROTOCOL_ERROR, EBADMSG); +protocol_error: skb->priority = RX_PROTOCOL_ERROR; post_abort: skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT; diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index ff4864d550b8..38b99db30e54 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -25,9 +25,6 @@ static void rxrpc_local_processor(struct work_struct *); static void rxrpc_local_rcu(struct rcu_head *); -static DEFINE_MUTEX(rxrpc_local_mutex); -static LIST_HEAD(rxrpc_local_endpoints); - /* * Compare a local to an address. Return -ve, 0 or +ve to indicate less than, * same or greater than. @@ -77,13 +74,15 @@ static long rxrpc_local_cmp_key(const struct rxrpc_local *local, /* * Allocate a new local endpoint. */ -static struct rxrpc_local *rxrpc_alloc_local(const struct sockaddr_rxrpc *srx) +static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, + const struct sockaddr_rxrpc *srx) { struct rxrpc_local *local; local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL); if (local) { atomic_set(&local->usage, 1); + local->rxnet = rxnet; INIT_LIST_HEAD(&local->link); INIT_WORK(&local->processor, rxrpc_local_processor); init_rwsem(&local->defrag_sem); @@ -95,6 +94,7 @@ static struct rxrpc_local *rxrpc_alloc_local(const struct sockaddr_rxrpc *srx) rwlock_init(&local->services_lock); local->debug_id = atomic_inc_return(&rxrpc_debug_id); memcpy(&local->srx, srx, sizeof(*srx)); + local->srx.srx_service = 0; } _leave(" = %p", local); @@ -105,7 +105,7 @@ static struct rxrpc_local *rxrpc_alloc_local(const struct sockaddr_rxrpc *srx) * create the local socket * - must be called with rxrpc_local_mutex locked */ -static int rxrpc_open_socket(struct rxrpc_local *local) +static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) { struct sock *sock; int ret, opt; @@ -114,7 +114,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local) local, local->srx.transport_type, local->srx.transport.family); /* create a socket to represent the local endpoint */ - ret = sock_create_kern(&init_net, local->srx.transport.family, + ret = sock_create_kern(net, local->srx.transport.family, local->srx.transport_type, 0, &local->socket); if (ret < 0) { _leave(" = %d [socket]", ret); @@ -172,9 +172,11 @@ error: /* * Look up or create a new local endpoint using the specified local address. */ -struct rxrpc_local *rxrpc_lookup_local(const struct sockaddr_rxrpc *srx) +struct rxrpc_local *rxrpc_lookup_local(struct net *net, + const struct sockaddr_rxrpc *srx) { struct rxrpc_local *local; + struct rxrpc_net *rxnet = rxrpc_net(net); struct list_head *cursor; const char *age; long diff; @@ -183,10 +185,10 @@ struct rxrpc_local *rxrpc_lookup_local(const struct sockaddr_rxrpc *srx) _enter("{%d,%d,%pISp}", srx->transport_type, srx->transport.family, &srx->transport); - mutex_lock(&rxrpc_local_mutex); + mutex_lock(&rxnet->local_mutex); - for (cursor = rxrpc_local_endpoints.next; - cursor != &rxrpc_local_endpoints; + for (cursor = rxnet->local_endpoints.next; + cursor != &rxnet->local_endpoints; cursor = cursor->next) { local = list_entry(cursor, struct rxrpc_local, link); @@ -220,11 +222,11 @@ struct rxrpc_local *rxrpc_lookup_local(const struct sockaddr_rxrpc *srx) goto found; } - local = rxrpc_alloc_local(srx); + local = rxrpc_alloc_local(rxnet, srx); if (!local) goto nomem; - ret = rxrpc_open_socket(local); + ret = rxrpc_open_socket(local, net); if (ret < 0) goto sock_error; @@ -232,7 +234,7 @@ struct rxrpc_local *rxrpc_lookup_local(const struct sockaddr_rxrpc *srx) age = "new"; found: - mutex_unlock(&rxrpc_local_mutex); + mutex_unlock(&rxnet->local_mutex); _net("LOCAL %s %d {%pISp}", age, local->debug_id, &local->srx.transport); @@ -243,13 +245,13 @@ found: nomem: ret = -ENOMEM; sock_error: - mutex_unlock(&rxrpc_local_mutex); + mutex_unlock(&rxnet->local_mutex); kfree(local); _leave(" = %d", ret); return ERR_PTR(ret); addr_in_use: - mutex_unlock(&rxrpc_local_mutex); + mutex_unlock(&rxnet->local_mutex); _leave(" = -EADDRINUSE"); return ERR_PTR(-EADDRINUSE); } @@ -273,6 +275,7 @@ void __rxrpc_put_local(struct rxrpc_local *local) static void rxrpc_local_destroyer(struct rxrpc_local *local) { struct socket *socket = local->socket; + struct rxrpc_net *rxnet = local->rxnet; _enter("%d", local->debug_id); @@ -286,9 +289,9 @@ static void rxrpc_local_destroyer(struct rxrpc_local *local) } local->dead = true; - mutex_lock(&rxrpc_local_mutex); + mutex_lock(&rxnet->local_mutex); list_del_init(&local->link); - mutex_unlock(&rxrpc_local_mutex); + mutex_unlock(&rxnet->local_mutex); ASSERT(RB_EMPTY_ROOT(&local->client_conns)); ASSERT(!local->service); @@ -357,7 +360,7 @@ static void rxrpc_local_rcu(struct rcu_head *rcu) /* * Verify the local endpoint list is empty by this point. */ -void __exit rxrpc_destroy_all_locals(void) +void rxrpc_destroy_all_locals(struct rxrpc_net *rxnet) { struct rxrpc_local *local; @@ -365,15 +368,13 @@ void __exit rxrpc_destroy_all_locals(void) flush_workqueue(rxrpc_workqueue); - if (!list_empty(&rxrpc_local_endpoints)) { - mutex_lock(&rxrpc_local_mutex); - list_for_each_entry(local, &rxrpc_local_endpoints, link) { + if (!list_empty(&rxnet->local_endpoints)) { + mutex_lock(&rxnet->local_mutex); + list_for_each_entry(local, &rxnet->local_endpoints, link) { pr_err("AF_RXRPC: Leaked local %p {%d}\n", local, atomic_read(&local->usage)); } - mutex_unlock(&rxrpc_local_mutex); + mutex_unlock(&rxnet->local_mutex); BUG(); } - - rcu_barrier(); } diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c new file mode 100644 index 000000000000..7edceb8522f5 --- /dev/null +++ b/net/rxrpc/net_ns.c @@ -0,0 +1,84 @@ +/* rxrpc network namespace handling. + * + * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/proc_fs.h> +#include "ar-internal.h" + +unsigned int rxrpc_net_id; + +/* + * Initialise a per-network namespace record. + */ +static __net_init int rxrpc_init_net(struct net *net) +{ + struct rxrpc_net *rxnet = rxrpc_net(net); + int ret; + + get_random_bytes(&rxnet->epoch, sizeof(rxnet->epoch)); + rxnet->epoch |= RXRPC_RANDOM_EPOCH; + + INIT_LIST_HEAD(&rxnet->calls); + rwlock_init(&rxnet->call_lock); + + INIT_LIST_HEAD(&rxnet->conn_proc_list); + INIT_LIST_HEAD(&rxnet->service_conns); + rwlock_init(&rxnet->conn_lock); + INIT_DELAYED_WORK(&rxnet->service_conn_reaper, + rxrpc_service_connection_reaper); + + rxnet->nr_client_conns = 0; + rxnet->nr_active_client_conns = 0; + rxnet->kill_all_client_conns = false; + spin_lock_init(&rxnet->client_conn_cache_lock); + spin_lock_init(&rxnet->client_conn_discard_lock); + INIT_LIST_HEAD(&rxnet->waiting_client_conns); + INIT_LIST_HEAD(&rxnet->active_client_conns); + INIT_LIST_HEAD(&rxnet->idle_client_conns); + INIT_DELAYED_WORK(&rxnet->client_conn_reaper, + rxrpc_discard_expired_client_conns); + + INIT_LIST_HEAD(&rxnet->local_endpoints); + mutex_init(&rxnet->local_mutex); + hash_init(rxnet->peer_hash); + spin_lock_init(&rxnet->peer_hash_lock); + + ret = -ENOMEM; + rxnet->proc_net = proc_net_mkdir(net, "rxrpc", net->proc_net); + if (!rxnet->proc_net) + goto err_proc; + + proc_create("calls", 0444, rxnet->proc_net, &rxrpc_call_seq_fops); + proc_create("conns", 0444, rxnet->proc_net, &rxrpc_connection_seq_fops); + return 0; + +err_proc: + return ret; +} + +/* + * Clean up a per-network namespace record. + */ +static __net_exit void rxrpc_exit_net(struct net *net) +{ + struct rxrpc_net *rxnet = rxrpc_net(net); + + rxrpc_destroy_all_calls(rxnet); + rxrpc_destroy_all_connections(rxnet); + rxrpc_destroy_all_locals(rxnet); + proc_remove(rxnet->proc_net); +} + +struct pernet_operations rxrpc_net_ops = { + .init = rxrpc_init_net, + .exit = rxrpc_exit_net, + .id = &rxrpc_net_id, + .size = sizeof(struct rxrpc_net), +}; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 5dab1ff3a6c2..5bd2d0fa4a03 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -292,6 +292,10 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, whdr._rsvd = htons(sp->hdr._rsvd); whdr.serviceId = htons(call->service_id); + if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) && + sp->hdr.seq == 1) + whdr.userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; + iov[0].iov_base = &whdr; iov[0].iov_len = sizeof(whdr); iov[1].iov_base = skb->head; diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 862eea6b266c..5787f97f5330 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -26,9 +26,6 @@ #include <net/ip6_route.h> #include "ar-internal.h" -static DEFINE_HASHTABLE(rxrpc_peer_hash, 10); -static DEFINE_SPINLOCK(rxrpc_peer_hash_lock); - /* * Hash a peer key. */ @@ -124,8 +121,9 @@ static struct rxrpc_peer *__rxrpc_lookup_peer_rcu( unsigned long hash_key) { struct rxrpc_peer *peer; + struct rxrpc_net *rxnet = local->rxnet; - hash_for_each_possible_rcu(rxrpc_peer_hash, peer, hash_link, hash_key) { + hash_for_each_possible_rcu(rxnet->peer_hash, peer, hash_link, hash_key) { if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0) { if (atomic_read(&peer->usage) == 0) return NULL; @@ -230,6 +228,13 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) seqlock_init(&peer->service_conn_lock); spin_lock_init(&peer->lock); peer->debug_id = atomic_inc_return(&rxrpc_debug_id); + + if (RXRPC_TX_SMSS > 2190) + peer->cong_cwnd = 2; + else if (RXRPC_TX_SMSS > 1095) + peer->cong_cwnd = 3; + else + peer->cong_cwnd = 4; } _leave(" = %p", peer); @@ -301,13 +306,14 @@ struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *prealloc) { struct rxrpc_peer *peer; + struct rxrpc_net *rxnet = local->rxnet; unsigned long hash_key; hash_key = rxrpc_peer_hash_key(local, &prealloc->srx); prealloc->local = local; rxrpc_init_peer(prealloc, hash_key); - spin_lock(&rxrpc_peer_hash_lock); + spin_lock(&rxnet->peer_hash_lock); /* Need to check that we aren't racing with someone else */ peer = __rxrpc_lookup_peer_rcu(local, &prealloc->srx, hash_key); @@ -315,10 +321,10 @@ struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local, peer = NULL; if (!peer) { peer = prealloc; - hash_add_rcu(rxrpc_peer_hash, &peer->hash_link, hash_key); + hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); } - spin_unlock(&rxrpc_peer_hash_lock); + spin_unlock(&rxnet->peer_hash_lock); return peer; } @@ -329,6 +335,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, struct sockaddr_rxrpc *srx, gfp_t gfp) { struct rxrpc_peer *peer, *candidate; + struct rxrpc_net *rxnet = local->rxnet; unsigned long hash_key = rxrpc_peer_hash_key(local, srx); _enter("{%pISp}", &srx->transport); @@ -350,17 +357,17 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, return NULL; } - spin_lock_bh(&rxrpc_peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); /* Need to check that we aren't racing with someone else */ peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); if (peer && !rxrpc_get_peer_maybe(peer)) peer = NULL; if (!peer) - hash_add_rcu(rxrpc_peer_hash, + hash_add_rcu(rxnet->peer_hash, &candidate->hash_link, hash_key); - spin_unlock_bh(&rxrpc_peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); if (peer) kfree(candidate); @@ -379,11 +386,13 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, */ void __rxrpc_put_peer(struct rxrpc_peer *peer) { + struct rxrpc_net *rxnet = peer->local->rxnet; + ASSERT(hlist_empty(&peer->error_targets)); - spin_lock_bh(&rxrpc_peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); hash_del_rcu(&peer->hash_link); - spin_unlock_bh(&rxrpc_peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); kfree_rcu(peer, rcu); } diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index b9bcfbfb095c..7421656963a9 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -30,19 +30,25 @@ static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = { */ static void *rxrpc_call_seq_start(struct seq_file *seq, loff_t *_pos) { + struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + rcu_read_lock(); - read_lock(&rxrpc_call_lock); - return seq_list_start_head(&rxrpc_calls, *_pos); + read_lock(&rxnet->call_lock); + return seq_list_start_head(&rxnet->calls, *_pos); } static void *rxrpc_call_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - return seq_list_next(v, &rxrpc_calls, pos); + struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + + return seq_list_next(v, &rxnet->calls, pos); } static void rxrpc_call_seq_stop(struct seq_file *seq, void *v) { - read_unlock(&rxrpc_call_lock); + struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + + read_unlock(&rxnet->call_lock); rcu_read_unlock(); } @@ -52,10 +58,11 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_sock *rx; struct rxrpc_peer *peer; struct rxrpc_call *call; + struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); rxrpc_seq_t tx_hard_ack, rx_hard_ack; char lbuff[50], rbuff[50]; - if (v == &rxrpc_calls) { + if (v == &rxnet->calls) { seq_puts(seq, "Proto Local " " Remote " @@ -113,7 +120,8 @@ static const struct seq_operations rxrpc_call_seq_ops = { static int rxrpc_call_seq_open(struct inode *inode, struct file *file) { - return seq_open(file, &rxrpc_call_seq_ops); + return seq_open_net(inode, file, &rxrpc_call_seq_ops, + sizeof(struct seq_net_private)); } const struct file_operations rxrpc_call_seq_fops = { @@ -129,27 +137,34 @@ const struct file_operations rxrpc_call_seq_fops = { */ static void *rxrpc_connection_seq_start(struct seq_file *seq, loff_t *_pos) { - read_lock(&rxrpc_connection_lock); - return seq_list_start_head(&rxrpc_connection_proc_list, *_pos); + struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + + read_lock(&rxnet->conn_lock); + return seq_list_start_head(&rxnet->conn_proc_list, *_pos); } static void *rxrpc_connection_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - return seq_list_next(v, &rxrpc_connection_proc_list, pos); + struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + + return seq_list_next(v, &rxnet->conn_proc_list, pos); } static void rxrpc_connection_seq_stop(struct seq_file *seq, void *v) { - read_unlock(&rxrpc_connection_lock); + struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + + read_unlock(&rxnet->conn_lock); } static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) { struct rxrpc_connection *conn; + struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); char lbuff[50], rbuff[50]; - if (v == &rxrpc_connection_proc_list) { + if (v == &rxnet->conn_proc_list) { seq_puts(seq, "Proto Local " " Remote " @@ -175,7 +190,7 @@ print: " %s %08x %08x %08x\n", lbuff, rbuff, - conn->params.service_id, + conn->service_id, conn->proto.cid, rxrpc_conn_is_service(conn) ? "Svc" : "Clt", atomic_read(&conn->usage), @@ -197,7 +212,8 @@ static const struct seq_operations rxrpc_connection_seq_ops = { static int rxrpc_connection_seq_open(struct inode *inode, struct file *file) { - return seq_open(file, &rxrpc_connection_seq_ops); + return seq_open_net(inode, file, &rxrpc_connection_seq_ops, + sizeof(struct seq_net_private)); } const struct file_operations rxrpc_connection_seq_fops = { diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index f9caf3b77509..bdece21f313d 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -522,8 +522,11 @@ try_again: } if (msg->msg_name) { - size_t len = sizeof(call->conn->params.peer->srx); - memcpy(msg->msg_name, &call->conn->params.peer->srx, len); + struct sockaddr_rxrpc *srx = msg->msg_name; + size_t len = sizeof(call->peer->srx); + + memcpy(msg->msg_name, &call->peer->srx, len); + srx->srx_service = call->service_id; msg->msg_namelen = len; } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 1bb9b2ccc267..46d1a1f0b55b 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -227,7 +227,9 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, len &= ~(call->conn->size_align - 1); sg_init_table(sg, nsg); - skb_to_sgvec(skb, sg, 0, len); + err = skb_to_sgvec(skb, sg, 0, len); + if (unlikely(err < 0)) + goto out; skcipher_request_set_crypt(req, sg, sg, len, iv.x); crypto_skcipher_encrypt(req); @@ -324,7 +326,7 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, bool aborted; u32 data_size, buf; u16 check; - int nsg; + int nsg, ret; _enter(""); @@ -342,7 +344,9 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, goto nomem; sg_init_table(sg, nsg); - skb_to_sgvec(skb, sg, offset, 8); + ret = skb_to_sgvec(skb, sg, offset, 8); + if (unlikely(ret < 0)) + return ret; /* start the decryption afresh */ memset(&iv, 0, sizeof(iv)); @@ -409,7 +413,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, bool aborted; u32 data_size, buf; u16 check; - int nsg; + int nsg, ret; _enter(",{%d}", skb->len); @@ -434,7 +438,12 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, } sg_init_table(sg, nsg); - skb_to_sgvec(skb, sg, offset, len); + ret = skb_to_sgvec(skb, sg, offset, len); + if (unlikely(ret < 0)) { + if (sg != _sg) + kfree(sg); + return ret; + } /* decrypt from the session key */ token = call->conn->params.key->payload.data[0]; @@ -640,7 +649,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) whdr.userStatus = 0; whdr.securityIndex = conn->security_ix; whdr._rsvd = 0; - whdr.serviceId = htons(conn->params.service_id); + whdr.serviceId = htons(conn->service_id); iov[0].iov_base = &whdr; iov[0].iov_len = sizeof(whdr); diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index 7d921e56e715..e9f428351293 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -121,7 +121,7 @@ int rxrpc_init_server_conn_security(struct rxrpc_connection *conn) _enter(""); - sprintf(kdesc, "%u:%u", conn->params.service_id, conn->security_ix); + sprintf(kdesc, "%u:%u", conn->service_id, conn->security_ix); sec = rxrpc_security_lookup(conn->security_ix); if (!sec) { @@ -133,7 +133,8 @@ int rxrpc_init_server_conn_security(struct rxrpc_connection *conn) read_lock(&local->services_lock); rx = rcu_dereference_protected(local->service, lockdep_is_held(&local->services_lock)); - if (rx && rx->srx.srx_service == conn->params.service_id) + if (rx && (rx->srx.srx_service == conn->service_id || + rx->second_service == conn->service_id)) goto found_service; /* the service appears to have died */ diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 96ffa5d5733b..b0d2cda6ec0a 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -28,6 +28,15 @@ enum rxrpc_command { RXRPC_CMD_REJECT_BUSY, /* [server] reject a call as busy */ }; +struct rxrpc_send_params { + s64 tx_total_len; /* Total Tx data length (if send data) */ + unsigned long user_call_ID; /* User's call ID */ + u32 abort_code; /* Abort code to Tx (if abort) */ + enum rxrpc_command command : 8; /* The command to implement */ + bool exclusive; /* Shared or exclusive call */ + bool upgrade; /* If the connection is upgradeable */ +}; + /* * wait for space to appear in the transmit/ACK window * - caller holds the socket locked @@ -199,6 +208,13 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, more = msg->msg_flags & MSG_MORE; + if (call->tx_total_len != -1) { + if (len > call->tx_total_len) + return -EMSGSIZE; + if (!more && len != call->tx_total_len) + return -EMSGSIZE; + } + skb = call->tx_pending; call->tx_pending = NULL; rxrpc_see_skb(skb, rxrpc_skb_tx_seen); @@ -291,6 +307,8 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, sp->remain -= copy; skb->mark += copy; copied += copy; + if (call->tx_total_len != -1) + call->tx_total_len -= copy; } /* check for the far side aborting the call or a network error @@ -312,7 +330,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, pad &= conn->size_align - 1; _debug("pad %zu", pad); if (pad) - memset(skb_put(skb, pad), 0, pad); + skb_put_zero(skb, pad); } seq = call->tx_top + 1; @@ -362,18 +380,12 @@ efault: /* * extract control messages from the sendmsg() control buffer */ -static int rxrpc_sendmsg_cmsg(struct msghdr *msg, - unsigned long *user_call_ID, - enum rxrpc_command *command, - u32 *abort_code, - bool *_exclusive) +static int rxrpc_sendmsg_cmsg(struct msghdr *msg, struct rxrpc_send_params *p) { struct cmsghdr *cmsg; bool got_user_ID = false; int len; - *command = RXRPC_CMD_SEND_DATA; - if (msg->msg_controllen == 0) return -EINVAL; @@ -393,42 +405,55 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, if (msg->msg_flags & MSG_CMSG_COMPAT) { if (len != sizeof(u32)) return -EINVAL; - *user_call_ID = *(u32 *) CMSG_DATA(cmsg); + p->user_call_ID = *(u32 *)CMSG_DATA(cmsg); } else { if (len != sizeof(unsigned long)) return -EINVAL; - *user_call_ID = *(unsigned long *) + p->user_call_ID = *(unsigned long *) CMSG_DATA(cmsg); } - _debug("User Call ID %lx", *user_call_ID); got_user_ID = true; break; case RXRPC_ABORT: - if (*command != RXRPC_CMD_SEND_DATA) + if (p->command != RXRPC_CMD_SEND_DATA) return -EINVAL; - *command = RXRPC_CMD_SEND_ABORT; - if (len != sizeof(*abort_code)) + p->command = RXRPC_CMD_SEND_ABORT; + if (len != sizeof(p->abort_code)) return -EINVAL; - *abort_code = *(unsigned int *) CMSG_DATA(cmsg); - _debug("Abort %x", *abort_code); - if (*abort_code == 0) + p->abort_code = *(unsigned int *)CMSG_DATA(cmsg); + if (p->abort_code == 0) return -EINVAL; break; case RXRPC_ACCEPT: - if (*command != RXRPC_CMD_SEND_DATA) + if (p->command != RXRPC_CMD_SEND_DATA) return -EINVAL; - *command = RXRPC_CMD_ACCEPT; + p->command = RXRPC_CMD_ACCEPT; if (len != 0) return -EINVAL; break; case RXRPC_EXCLUSIVE_CALL: - *_exclusive = true; + p->exclusive = true; + if (len != 0) + return -EINVAL; + break; + + case RXRPC_UPGRADE_SERVICE: + p->upgrade = true; if (len != 0) return -EINVAL; break; + + case RXRPC_TX_LENGTH: + if (p->tx_total_len != -1 || len != sizeof(__s64)) + return -EINVAL; + p->tx_total_len = *(__s64 *)CMSG_DATA(cmsg); + if (p->tx_total_len < 0) + return -EINVAL; + break; + default: return -EINVAL; } @@ -436,6 +461,8 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, if (!got_user_ID) return -EINVAL; + if (p->tx_total_len != -1 && p->command != RXRPC_CMD_SEND_DATA) + return -EINVAL; _leave(" = 0"); return 0; } @@ -447,7 +474,7 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, */ static struct rxrpc_call * rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, - unsigned long user_call_ID, bool exclusive) + struct rxrpc_send_params *p) __releases(&rx->sk.sk_lock.slock) { struct rxrpc_conn_parameters cp; @@ -471,9 +498,11 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, cp.local = rx->local; cp.key = rx->key; cp.security_level = rx->min_sec_level; - cp.exclusive = rx->exclusive | exclusive; + cp.exclusive = rx->exclusive | p->exclusive; + cp.upgrade = p->upgrade; cp.service_id = srx->srx_service; - call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, GFP_KERNEL); + call = rxrpc_new_client_call(rx, &cp, srx, p->user_call_ID, + p->tx_total_len, GFP_KERNEL); /* The socket is now unlocked */ _leave(" = %p\n", call); @@ -489,25 +518,29 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) __releases(&rx->sk.sk_lock.slock) { enum rxrpc_call_state state; - enum rxrpc_command cmd; struct rxrpc_call *call; - unsigned long user_call_ID = 0; - bool exclusive = false; - u32 abort_code = 0; int ret; + struct rxrpc_send_params p = { + .tx_total_len = -1, + .user_call_ID = 0, + .abort_code = 0, + .command = RXRPC_CMD_SEND_DATA, + .exclusive = false, + .upgrade = true, + }; + _enter(""); - ret = rxrpc_sendmsg_cmsg(msg, &user_call_ID, &cmd, &abort_code, - &exclusive); + ret = rxrpc_sendmsg_cmsg(msg, &p); if (ret < 0) goto error_release_sock; - if (cmd == RXRPC_CMD_ACCEPT) { + if (p.command == RXRPC_CMD_ACCEPT) { ret = -EINVAL; if (rx->sk.sk_state != RXRPC_SERVER_LISTENING) goto error_release_sock; - call = rxrpc_accept_call(rx, user_call_ID, NULL); + call = rxrpc_accept_call(rx, p.user_call_ID, NULL); /* The socket is now unlocked. */ if (IS_ERR(call)) return PTR_ERR(call); @@ -515,13 +548,12 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) return 0; } - call = rxrpc_find_call_by_user_ID(rx, user_call_ID); + call = rxrpc_find_call_by_user_ID(rx, p.user_call_ID); if (!call) { ret = -EBADSLT; - if (cmd != RXRPC_CMD_SEND_DATA) + if (p.command != RXRPC_CMD_SEND_DATA) goto error_release_sock; - call = rxrpc_new_client_call_for_sendmsg(rx, msg, user_call_ID, - exclusive); + call = rxrpc_new_client_call_for_sendmsg(rx, msg, &p); /* The socket is now unlocked... */ if (IS_ERR(call)) return PTR_ERR(call); @@ -545,6 +577,15 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) ret = -ERESTARTSYS; goto error_put; } + + if (p.tx_total_len != -1) { + ret = -EINVAL; + if (call->tx_total_len != -1 || + call->tx_pending || + call->tx_top != 0) + goto error_put; + call->tx_total_len = p.tx_total_len; + } } state = READ_ONCE(call->state); @@ -554,11 +595,11 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (state >= RXRPC_CALL_COMPLETE) { /* it's too late for this call */ ret = -ESHUTDOWN; - } else if (cmd == RXRPC_CMD_SEND_ABORT) { + } else if (p.command == RXRPC_CMD_SEND_ABORT) { ret = 0; - if (rxrpc_abort_call("CMD", call, 0, abort_code, -ECONNABORTED)) + if (rxrpc_abort_call("CMD", call, 0, p.abort_code, -ECONNABORTED)) ret = rxrpc_send_abort_packet(call); - } else if (cmd != RXRPC_CMD_SEND_DATA) { + } else if (p.command != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; } else if (rxrpc_is_client_call(call) && state != RXRPC_CALL_CLIENT_SEND_REQUEST) { @@ -662,5 +703,24 @@ bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call, mutex_unlock(&call->user_mutex); return aborted; } - EXPORT_SYMBOL(rxrpc_kernel_abort_call); + +/** + * rxrpc_kernel_set_tx_length - Set the total Tx length on a call + * @sock: The socket the call is on + * @call: The call to be informed + * @tx_total_len: The amount of data to be transmitted for this call + * + * Allow a kernel service to set the total transmit length on a call. This + * allows buffer-to-packet encrypt-and-copy to be performed. + * + * This function is primarily for use for setting the reply length since the + * request length can be set when beginning the call. + */ +void rxrpc_kernel_set_tx_length(struct socket *sock, struct rxrpc_call *call, + s64 tx_total_len) +{ + WARN_ON(call->tx_total_len != -1); + call->tx_total_len = tx_total_len; +} +EXPORT_SYMBOL(rxrpc_kernel_set_tx_length); diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index 67b02c45271b..b8985d01876a 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -27,7 +27,7 @@ void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(select_skb_count(op)); - trace_rxrpc_skb(skb, op, atomic_read(&skb->users), n, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); } /* @@ -38,7 +38,7 @@ void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) const void *here = __builtin_return_address(0); if (skb) { int n = atomic_read(select_skb_count(op)); - trace_rxrpc_skb(skb, op, atomic_read(&skb->users), n, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); } } @@ -49,7 +49,7 @@ void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(select_skb_count(op)); - trace_rxrpc_skb(skb, op, atomic_read(&skb->users), n, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); skb_get(skb); } @@ -63,7 +63,7 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) int n; CHECK_SLAB_OKAY(&skb->users); n = atomic_dec_return(select_skb_count(op)); - trace_rxrpc_skb(skb, op, atomic_read(&skb->users), n, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); kfree_skb(skb); } } @@ -78,7 +78,7 @@ void rxrpc_lose_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) int n; CHECK_SLAB_OKAY(&skb->users); n = atomic_dec_return(select_skb_count(op)); - trace_rxrpc_skb(skb, op, atomic_read(&skb->users), n, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); kfree_skb(skb); } } @@ -93,7 +93,7 @@ void rxrpc_purge_queue(struct sk_buff_head *list) while ((skb = skb_dequeue((list))) != NULL) { int n = atomic_dec_return(select_skb_count(rxrpc_skb_rx_purged)); trace_rxrpc_skb(skb, rxrpc_skb_rx_purged, - atomic_read(&skb->users), n, here); + refcount_read(&skb->users), n, here); kfree_skb(skb); } } diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 9fb84f0de6af..e70ed26485a2 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -649,6 +649,7 @@ config NET_EMATCH_IPSET config NET_CLS_ACT bool "Actions" + select NET_CLS ---help--- Say Y here if you want to use traffic control actions. Actions get attached to classifiers and are invoked after a successful diff --git a/net/sched/act_api.c b/net/sched/act_api.c index a90e8f355c00..f2e9ed34a963 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -28,6 +28,31 @@ #include <net/act_api.h> #include <net/netlink.h> +static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp) +{ + u32 chain_index = a->tcfa_action & TC_ACT_EXT_VAL_MASK; + + if (!tp) + return -EINVAL; + a->goto_chain = tcf_chain_get(tp->chain->block, chain_index, true); + if (!a->goto_chain) + return -ENOMEM; + return 0; +} + +static void tcf_action_goto_chain_fini(struct tc_action *a) +{ + tcf_chain_put(a->goto_chain); +} + +static void tcf_action_goto_chain_exec(const struct tc_action *a, + struct tcf_result *res) +{ + const struct tcf_chain *chain = a->goto_chain; + + res->goto_tp = rcu_dereference_bh(chain->filter_chain); +} + static void free_tcf(struct rcu_head *head) { struct tc_action *p = container_of(head, struct tc_action, tcfa_rcu); @@ -39,6 +64,8 @@ static void free_tcf(struct rcu_head *head) kfree(p->act_cookie->data); kfree(p->act_cookie); } + if (p->goto_chain) + tcf_action_goto_chain_fini(p); kfree(p); } @@ -465,6 +492,8 @@ repeat: else /* faulty graph, stop pipeline */ return TC_ACT_OK; } + } else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) { + tcf_action_goto_chain_exec(a, res); } if (ret != TC_ACT_PIPE) @@ -570,9 +599,9 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) return c; } -struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, - struct nlattr *est, char *name, int ovr, - int bind) +struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, + struct nlattr *nla, struct nlattr *est, + char *name, int ovr, int bind) { struct tc_action *a; struct tc_action_ops *a_o; @@ -657,6 +686,17 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, if (err != ACT_P_CREATED) module_put(a_o->owner); + if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) { + err = tcf_action_goto_chain_init(a, tp); + if (err) { + LIST_HEAD(actions); + + list_add_tail(&a->list, &actions); + tcf_action_destroy(&actions, bind); + return ERR_PTR(err); + } + } + return a; err_mod: @@ -680,8 +720,9 @@ static void cleanup_a(struct list_head *actions, int ovr) a->tcfa_refcnt--; } -int tcf_action_init(struct net *net, struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind, struct list_head *actions) +int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, + struct nlattr *est, char *name, int ovr, int bind, + struct list_head *actions) { struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; @@ -693,7 +734,7 @@ int tcf_action_init(struct net *net, struct nlattr *nla, struct nlattr *est, return err; for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_init_1(net, tb[i], est, name, ovr, bind); + act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind); if (IS_ERR(act)) { err = PTR_ERR(act); goto err; @@ -794,7 +835,7 @@ out_nlmsg_trim: } static int -act_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, +tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, struct list_head *actions, int event) { struct sk_buff *skb; @@ -977,7 +1018,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, } if (event == RTM_GETACTION) - ret = act_get_notify(net, portid, n, &actions, event); + ret = tcf_get_notify(net, portid, n, &actions, event); else { /* delete */ ret = tcf_del_notify(net, n, &actions, portid); if (ret) @@ -1020,7 +1061,7 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, int ret = 0; LIST_HEAD(actions); - ret = tcf_action_init(net, nla, NULL, NULL, ovr, 0, &actions); + ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions); if (ret) return ret; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index d33947d6e9d0..9afe1337cfd1 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -123,6 +123,9 @@ static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog, nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name)) return -EMSGSIZE; + if (nla_put_u32(skb, TCA_ACT_BPF_ID, prog->filter->aux->id)) + return -EMSGSIZE; + nla = nla_reserve(skb, TCA_ACT_BPF_TAG, sizeof(prog->filter->tag)); if (nla == NULL) return -EMSGSIZE; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index ab6fdbd34db7..3317a2f579da 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -350,6 +350,7 @@ static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl, sctph->checksum = sctp_compute_cksum(skb, skb_network_offset(skb) + ihl); skb->ip_summed = CHECKSUM_NONE; + skb->csum_not_inet = 0; return 1; } diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index b9a2f241a5b3..fd7e75679c69 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -67,6 +67,7 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_IPV6_DST] = { .len = sizeof(struct in6_addr) }, [TCA_TUNNEL_KEY_ENC_KEY_ID] = { .type = NLA_U32 }, [TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16}, + [TCA_TUNNEL_KEY_NO_CSUM] = { .type = NLA_U8 }, }; static int tunnel_key_init(struct net *net, struct nlattr *nla, @@ -83,6 +84,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, bool exists = false; __be16 dst_port = 0; __be64 key_id; + __be16 flags; int ret = 0; int err; @@ -113,6 +115,11 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, key_id = key32_to_tunnel_id(nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID])); + flags = TUNNEL_KEY | TUNNEL_CSUM; + if (tb[TCA_TUNNEL_KEY_NO_CSUM] && + nla_get_u8(tb[TCA_TUNNEL_KEY_NO_CSUM])) + flags &= ~TUNNEL_CSUM; + if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT]) dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]); @@ -125,7 +132,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, daddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]); metadata = __ip_tun_set_dst(saddr, daddr, 0, 0, - dst_port, TUNNEL_KEY, + dst_port, flags, key_id, 0); } else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] && tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) { @@ -136,7 +143,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]); metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, dst_port, - 0, TUNNEL_KEY, + 0, flags, key_id, 0); } @@ -266,7 +273,9 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) || tunnel_key_dump_addresses(skb, ¶ms->tcft_enc_metadata->u.tun_info) || - nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst)) + nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst) || + nla_put_u8(skb, TCA_TUNNEL_KEY_NO_CSUM, + !(key->tun_flags & TUNNEL_CSUM))) goto nla_put_failure; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 22f88b35a546..39da0c5801c9 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -106,13 +106,12 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, - struct tcf_proto __rcu **chain, int event) + struct tcf_chain *chain, int event) { - struct tcf_proto __rcu **it_chain; struct tcf_proto *tp; - for (it_chain = chain; (tp = rtnl_dereference(*it_chain)) != NULL; - it_chain = &tp->next) + for (tp = rtnl_dereference(chain->filter_chain); + tp; tp = rtnl_dereference(tp->next)) tfilter_notify(net, oskb, n, tp, 0, event, false); } @@ -125,11 +124,12 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) if (tp) first = tp->prio - 1; - return first; + return TC_H_MAJ(first); } static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, - u32 prio, u32 parent, struct Qdisc *q) + u32 prio, u32 parent, struct Qdisc *q, + struct tcf_chain *chain) { struct tcf_proto *tp; int err; @@ -165,6 +165,7 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, tp->prio = prio; tp->classid = parent; tp->q = q; + tp->chain = chain; err = tp->ops->init(tp); if (err) { @@ -185,16 +186,226 @@ static void tcf_proto_destroy(struct tcf_proto *tp) kfree_rcu(tp, rcu); } -void tcf_destroy_chain(struct tcf_proto __rcu **fl) +static struct tcf_chain *tcf_chain_create(struct tcf_block *block, + u32 chain_index) +{ + struct tcf_chain *chain; + + chain = kzalloc(sizeof(*chain), GFP_KERNEL); + if (!chain) + return NULL; + list_add_tail(&chain->list, &block->chain_list); + chain->block = block; + chain->index = chain_index; + chain->refcnt = 1; + return chain; +} + +static void tcf_chain_flush(struct tcf_chain *chain) { struct tcf_proto *tp; - while ((tp = rtnl_dereference(*fl)) != NULL) { - RCU_INIT_POINTER(*fl, tp->next); + if (*chain->p_filter_chain) + RCU_INIT_POINTER(*chain->p_filter_chain, NULL); + while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) { + RCU_INIT_POINTER(chain->filter_chain, tp->next); tcf_proto_destroy(tp); } } -EXPORT_SYMBOL(tcf_destroy_chain); + +static void tcf_chain_destroy(struct tcf_chain *chain) +{ + list_del(&chain->list); + tcf_chain_flush(chain); + kfree(chain); +} + +struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, + bool create) +{ + struct tcf_chain *chain; + + list_for_each_entry(chain, &block->chain_list, list) { + if (chain->index == chain_index) { + chain->refcnt++; + return chain; + } + } + if (create) + return tcf_chain_create(block, chain_index); + else + return NULL; +} +EXPORT_SYMBOL(tcf_chain_get); + +void tcf_chain_put(struct tcf_chain *chain) +{ + /* Destroy unused chain, with exception of chain 0, which is the + * default one and has to be always present. + */ + if (--chain->refcnt == 0 && !chain->filter_chain && chain->index != 0) + tcf_chain_destroy(chain); +} +EXPORT_SYMBOL(tcf_chain_put); + +static void +tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain, + struct tcf_proto __rcu **p_filter_chain) +{ + chain->p_filter_chain = p_filter_chain; +} + +int tcf_block_get(struct tcf_block **p_block, + struct tcf_proto __rcu **p_filter_chain) +{ + struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL); + struct tcf_chain *chain; + int err; + + if (!block) + return -ENOMEM; + INIT_LIST_HEAD(&block->chain_list); + /* Create chain 0 by default, it has to be always present. */ + chain = tcf_chain_create(block, 0); + if (!chain) { + err = -ENOMEM; + goto err_chain_create; + } + tcf_chain_filter_chain_ptr_set(chain, p_filter_chain); + *p_block = block; + return 0; + +err_chain_create: + kfree(block); + return err; +} +EXPORT_SYMBOL(tcf_block_get); + +void tcf_block_put(struct tcf_block *block) +{ + struct tcf_chain *chain, *tmp; + + if (!block) + return; + + list_for_each_entry_safe(chain, tmp, &block->chain_list, list) + tcf_chain_destroy(chain); + kfree(block); +} +EXPORT_SYMBOL(tcf_block_put); + +/* Main classifier routine: scans classifier chain attached + * to this qdisc, (optionally) tests for protocol and asks + * specific classifiers. + */ +int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res, bool compat_mode) +{ + __be16 protocol = tc_skb_protocol(skb); +#ifdef CONFIG_NET_CLS_ACT + const int max_reclassify_loop = 4; + const struct tcf_proto *orig_tp = tp; + const struct tcf_proto *first_tp; + int limit = 0; + +reclassify: +#endif + for (; tp; tp = rcu_dereference_bh(tp->next)) { + int err; + + if (tp->protocol != protocol && + tp->protocol != htons(ETH_P_ALL)) + continue; + + err = tp->classify(skb, tp, res); +#ifdef CONFIG_NET_CLS_ACT + if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) { + first_tp = orig_tp; + goto reset; + } else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) { + first_tp = res->goto_tp; + goto reset; + } +#endif + if (err >= 0) + return err; + } + + return TC_ACT_UNSPEC; /* signal: continue lookup */ +#ifdef CONFIG_NET_CLS_ACT +reset: + if (unlikely(limit++ >= max_reclassify_loop)) { + net_notice_ratelimited("%s: reclassify loop, rule prio %u, protocol %02x\n", + tp->q->ops->id, tp->prio & 0xffff, + ntohs(tp->protocol)); + return TC_ACT_SHOT; + } + + tp = first_tp; + protocol = tc_skb_protocol(skb); + goto reclassify; +#endif +} +EXPORT_SYMBOL(tcf_classify); + +struct tcf_chain_info { + struct tcf_proto __rcu **pprev; + struct tcf_proto __rcu *next; +}; + +static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain_info *chain_info) +{ + return rtnl_dereference(*chain_info->pprev); +} + +static void tcf_chain_tp_insert(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + struct tcf_proto *tp) +{ + if (chain->p_filter_chain && + *chain_info->pprev == chain->filter_chain) + rcu_assign_pointer(*chain->p_filter_chain, tp); + RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info)); + rcu_assign_pointer(*chain_info->pprev, tp); +} + +static void tcf_chain_tp_remove(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + struct tcf_proto *tp) +{ + struct tcf_proto *next = rtnl_dereference(chain_info->next); + + if (chain->p_filter_chain && tp == chain->filter_chain) + RCU_INIT_POINTER(*chain->p_filter_chain, next); + RCU_INIT_POINTER(*chain_info->pprev, next); +} + +static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + u32 protocol, u32 prio, + bool prio_allocate) +{ + struct tcf_proto **pprev; + struct tcf_proto *tp; + + /* Check the chain for existence of proto-tcf with this priority */ + for (pprev = &chain->filter_chain; + (tp = rtnl_dereference(*pprev)); pprev = &tp->next) { + if (tp->prio >= prio) { + if (tp->prio == prio) { + if (prio_allocate || + (tp->protocol != protocol && protocol)) + return ERR_PTR(-EINVAL); + } else { + tp = NULL; + } + break; + } + } + chain_info->pprev = pprev; + chain_info->next = tp ? tp->next : NULL; + return tp; +} /* Add/change/delete/get a filter node */ @@ -206,13 +417,14 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct tcmsg *t; u32 protocol; u32 prio; - u32 nprio; + bool prio_allocate; u32 parent; + u32 chain_index; struct net_device *dev; struct Qdisc *q; - struct tcf_proto __rcu **back; - struct tcf_proto __rcu **chain; - struct tcf_proto *next; + struct tcf_chain_info chain_info; + struct tcf_chain *chain = NULL; + struct tcf_block *block; struct tcf_proto *tp; const struct Qdisc_class_ops *cops; unsigned long cl; @@ -234,7 +446,7 @@ replay: t = nlmsg_data(n); protocol = TC_H_MIN(t->tcm_info); prio = TC_H_MAJ(t->tcm_info); - nprio = prio; + prio_allocate = false; parent = t->tcm_parent; cl = 0; @@ -250,6 +462,7 @@ replay: */ if (n->nlmsg_flags & NLM_F_CREATE) { prio = TC_H_MAKE(0x80000000U, 0U); + prio_allocate = true; break; } /* fall-through */ @@ -280,7 +493,7 @@ replay: if (!cops) return -EINVAL; - if (cops->tcf_chain == NULL) + if (!cops->tcf_block) return -EOPNOTSUPP; /* Do we search for filter, attached to class? */ @@ -291,34 +504,36 @@ replay: } /* And the last stroke */ - chain = cops->tcf_chain(q, cl); - if (chain == NULL) { + block = cops->tcf_block(q, cl); + if (!block) { err = -EINVAL; goto errout; } + + chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + if (chain_index > TC_ACT_EXT_VAL_MASK) { + err = -EINVAL; + goto errout; + } + chain = tcf_chain_get(block, chain_index, + n->nlmsg_type == RTM_NEWTFILTER); + if (!chain) { + err = n->nlmsg_type == RTM_NEWTFILTER ? -ENOMEM : -EINVAL; + goto errout; + } + if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) { tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER); - tcf_destroy_chain(chain); + tcf_chain_flush(chain); err = 0; goto errout; } - /* Check the chain for existence of proto-tcf with this priority */ - for (back = chain; - (tp = rtnl_dereference(*back)) != NULL; - back = &tp->next) { - if (tp->prio >= prio) { - if (tp->prio == prio) { - if (!nprio || - (tp->protocol != protocol && protocol)) { - err = -EINVAL; - goto errout; - } - } else { - tp = NULL; - } - break; - } + tp = tcf_chain_tp_find(chain, &chain_info, protocol, + prio, prio_allocate); + if (IS_ERR(tp)) { + err = PTR_ERR(tp); + goto errout; } if (tp == NULL) { @@ -335,11 +550,11 @@ replay: goto errout; } - if (!nprio) - nprio = TC_H_MAJ(tcf_auto_prio(rtnl_dereference(*back))); + if (prio_allocate) + prio = tcf_auto_prio(tcf_chain_tp_prev(&chain_info)); tp = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, nprio, parent, q); + protocol, prio, parent, q, chain); if (IS_ERR(tp)) { err = PTR_ERR(tp); goto errout; @@ -354,8 +569,7 @@ replay: if (fh == 0) { if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) { - next = rtnl_dereference(tp->next); - RCU_INIT_POINTER(*back, next); + tcf_chain_tp_remove(chain, &chain_info, tp); tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER, false); tcf_proto_destroy(tp); @@ -384,11 +598,10 @@ replay: err = tp->ops->delete(tp, fh, &last); if (err) goto errout; - next = rtnl_dereference(tp->next); tfilter_notify(net, skb, n, tp, t->tcm_handle, RTM_DELTFILTER, false); if (last) { - RCU_INIT_POINTER(*back, next); + tcf_chain_tp_remove(chain, &chain_info, tp); tcf_proto_destroy(tp); } goto errout; @@ -405,10 +618,8 @@ replay: err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE); if (err == 0) { - if (tp_created) { - RCU_INIT_POINTER(tp->next, rtnl_dereference(*back)); - rcu_assign_pointer(*back, tp); - } + if (tp_created) + tcf_chain_tp_insert(chain, &chain_info, tp); tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER, false); } else { if (tp_created) @@ -416,6 +627,8 @@ replay: } errout: + if (chain) + tcf_chain_put(chain); if (cl) cops->put(q, cl); if (err == -EAGAIN) @@ -444,6 +657,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); if (nla_put_string(skb, TCA_KIND, tp->ops->kind)) goto nla_put_failure; + if (nla_put_u32(skb, TCA_CHAIN, tp->chain->index)) + goto nla_put_failure; tcm->tcm_handle = fh; if (RTM_DELTFILTER != event) { tcm->tcm_handle = 0; @@ -500,22 +715,76 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n, RTM_NEWTFILTER); } +static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, + struct netlink_callback *cb, + long index_start, long *p_index) +{ + struct net *net = sock_net(skb->sk); + struct tcmsg *tcm = nlmsg_data(cb->nlh); + struct tcf_dump_args arg; + struct tcf_proto *tp; + + for (tp = rtnl_dereference(chain->filter_chain); + tp; tp = rtnl_dereference(tp->next), (*p_index)++) { + if (*p_index < index_start) + continue; + if (TC_H_MAJ(tcm->tcm_info) && + TC_H_MAJ(tcm->tcm_info) != tp->prio) + continue; + if (TC_H_MIN(tcm->tcm_info) && + TC_H_MIN(tcm->tcm_info) != tp->protocol) + continue; + if (*p_index > index_start) + memset(&cb->args[1], 0, + sizeof(cb->args) - sizeof(cb->args[0])); + if (cb->args[1] == 0) { + if (tcf_fill_node(net, skb, tp, 0, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + RTM_NEWTFILTER) <= 0) + return false; + + cb->args[1] = 1; + } + if (!tp->ops->walk) + continue; + arg.w.fn = tcf_node_dump; + arg.skb = skb; + arg.cb = cb; + arg.w.stop = 0; + arg.w.skip = cb->args[1] - 1; + arg.w.count = 0; + tp->ops->walk(tp, &arg.w); + cb->args[1] = arg.w.count + 1; + if (arg.w.stop) + return false; + } + return true; +} + /* called with RTNL */ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - int t; - int s_t; + struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; struct Qdisc *q; - struct tcf_proto *tp, __rcu **chain; + struct tcf_block *block; + struct tcf_chain *chain; struct tcmsg *tcm = nlmsg_data(cb->nlh); unsigned long cl = 0; const struct Qdisc_class_ops *cops; - struct tcf_dump_args arg; + long index_start; + long index; + int err; if (nlmsg_len(cb->nlh) < sizeof(*tcm)) return skb->len; + + err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL); + if (err) + return err; + dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return skb->len; @@ -529,56 +798,29 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) cops = q->ops->cl_ops; if (!cops) goto errout; - if (cops->tcf_chain == NULL) + if (!cops->tcf_block) goto errout; if (TC_H_MIN(tcm->tcm_parent)) { cl = cops->get(q, tcm->tcm_parent); if (cl == 0) goto errout; } - chain = cops->tcf_chain(q, cl); - if (chain == NULL) + block = cops->tcf_block(q, cl); + if (!block) goto errout; - s_t = cb->args[0]; - - for (tp = rtnl_dereference(*chain), t = 0; - tp; tp = rtnl_dereference(tp->next), t++) { - if (t < s_t) - continue; - if (TC_H_MAJ(tcm->tcm_info) && - TC_H_MAJ(tcm->tcm_info) != tp->prio) - continue; - if (TC_H_MIN(tcm->tcm_info) && - TC_H_MIN(tcm->tcm_info) != tp->protocol) - continue; - if (t > s_t) - memset(&cb->args[1], 0, - sizeof(cb->args)-sizeof(cb->args[0])); - if (cb->args[1] == 0) { - if (tcf_fill_node(net, skb, tp, 0, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER) <= 0) - break; + index_start = cb->args[0]; + index = 0; - cb->args[1] = 1; - } - if (tp->ops->walk == NULL) + list_for_each_entry(chain, &block->chain_list, list) { + if (tca[TCA_CHAIN] && + nla_get_u32(tca[TCA_CHAIN]) != chain->index) continue; - arg.w.fn = tcf_node_dump; - arg.skb = skb; - arg.cb = cb; - arg.w.stop = 0; - arg.w.skip = cb->args[1] - 1; - arg.w.count = 0; - tp->ops->walk(tp, &arg.w); - cb->args[1] = arg.w.count + 1; - if (arg.w.stop) + if (!tcf_chain_dump(chain, skb, cb, index_start, &index)) break; } - cb->args[0] = t; + cb->args[0] = index; errout: if (cl) @@ -608,8 +850,9 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct tc_action *act; if (exts->police && tb[exts->police]) { - act = tcf_action_init_1(net, tb[exts->police], rate_tlv, - "police", ovr, TCA_ACT_BIND); + act = tcf_action_init_1(net, tp, tb[exts->police], + rate_tlv, "police", ovr, + TCA_ACT_BIND); if (IS_ERR(act)) return PTR_ERR(act); @@ -620,8 +863,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, LIST_HEAD(actions); int err, i = 0; - err = tcf_action_init(net, tb[exts->action], rate_tlv, - NULL, ovr, TCA_ACT_BIND, + err = tcf_action_init(net, tp, tb[exts->action], + rate_tlv, NULL, ovr, TCA_ACT_BIND, &actions); if (err) return err; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 5ebeae996e63..f57bd531ba98 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -70,6 +70,7 @@ static int cls_bpf_exec_opcode(int code) case TC_ACT_OK: case TC_ACT_SHOT: case TC_ACT_STOLEN: + case TC_ACT_TRAP: case TC_ACT_REDIRECT: case TC_ACT_UNSPEC: return code; @@ -161,6 +162,7 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, bpf_offload.gen_flags = prog->gen_flags; err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, + tp->chain->index, tp->protocol, &offload); if (!err && (cmd == TC_CLSBPF_ADD || cmd == TC_CLSBPF_REPLACE)) @@ -564,6 +566,9 @@ static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog, nla_put_string(skb, TCA_BPF_NAME, prog->bpf_name)) return -EMSGSIZE; + if (nla_put_u32(skb, TCA_BPF_ID, prog->filter->aux->id)) + return -EMSGSIZE; + nla = nla_reserve(skb, TCA_BPF_TAG, sizeof(prog->filter->tag)); if (nla == NULL) return -EMSGSIZE; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index ca526c0881bd..7832eb93379b 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -49,6 +49,8 @@ struct fl_flow_key { }; struct flow_dissector_key_ports enc_tp; struct flow_dissector_key_mpls mpls; + struct flow_dissector_key_tcp tcp; + struct flow_dissector_key_ip ip; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct fl_flow_mask_range { @@ -237,7 +239,8 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f) tc->type = TC_SETUP_CLSFLOWER; tc->cls_flower = &offload; - dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, tc); + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->chain->index, + tp->protocol, tc); } static int fl_hw_replace_filter(struct tcf_proto *tp, @@ -273,8 +276,8 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, tc->type = TC_SETUP_CLSFLOWER; tc->cls_flower = &offload; - err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, - tc); + err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, + tp->chain->index, tp->protocol, tc); if (!err) f->flags |= TCA_CLS_FLAGS_IN_HW; @@ -300,7 +303,8 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) tc->type = TC_SETUP_CLSFLOWER; tc->cls_flower = &offload; - dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, tc); + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, + tp->chain->index, tp->protocol, tc); } static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f) @@ -424,6 +428,12 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_MPLS_BOS] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_MPLS_TC] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_MPLS_LABEL] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_TCP_FLAGS] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_TCP_FLAGS_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_IP_TOS] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_IP_TOS_MASK] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_IP_TTL] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_IP_TTL_MASK] = { .type = NLA_U8 }, }; static void fl_set_key_val(struct nlattr **tb, @@ -525,6 +535,19 @@ static int fl_set_key_flags(struct nlattr **tb, return 0; } +static void fl_set_key_ip(struct nlattr **tb, + struct flow_dissector_key_ip *key, + struct flow_dissector_key_ip *mask) +{ + fl_set_key_val(tb, &key->tos, TCA_FLOWER_KEY_IP_TOS, + &mask->tos, TCA_FLOWER_KEY_IP_TOS_MASK, + sizeof(key->tos)); + + fl_set_key_val(tb, &key->ttl, TCA_FLOWER_KEY_IP_TTL, + &mask->ttl, TCA_FLOWER_KEY_IP_TTL_MASK, + sizeof(key->ttl)); +} + static int fl_set_key(struct net *net, struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask) { @@ -567,6 +590,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, &mask->basic.ip_proto, TCA_FLOWER_UNSPEC, sizeof(key->basic.ip_proto)); + fl_set_key_ip(tb, &key->ip, &mask->ip); } if (tb[TCA_FLOWER_KEY_IPV4_SRC] || tb[TCA_FLOWER_KEY_IPV4_DST]) { @@ -596,6 +620,9 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST, &mask->tp.dst, TCA_FLOWER_KEY_TCP_DST_MASK, sizeof(key->tp.dst)); + fl_set_key_val(tb, &key->tcp.flags, TCA_FLOWER_KEY_TCP_FLAGS, + &mask->tcp.flags, TCA_FLOWER_KEY_TCP_FLAGS_MASK, + sizeof(key->tcp.flags)); } else if (key->basic.ip_proto == IPPROTO_UDP) { fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC, &mask->tp.src, TCA_FLOWER_KEY_UDP_SRC_MASK, @@ -767,6 +794,10 @@ static void fl_init_dissector(struct cls_fl_head *head, FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, FLOW_DISSECTOR_KEY_PORTS, tp); FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FLOW_DISSECTOR_KEY_IP, ip); + FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FLOW_DISSECTOR_KEY_TCP, tcp); + FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, FLOW_DISSECTOR_KEY_ICMP, icmp); FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, FLOW_DISSECTOR_KEY_ARP, arp); @@ -1074,6 +1105,19 @@ static int fl_dump_key_mpls(struct sk_buff *skb, return 0; } +static int fl_dump_key_ip(struct sk_buff *skb, + struct flow_dissector_key_ip *key, + struct flow_dissector_key_ip *mask) +{ + if (fl_dump_key_val(skb, &key->tos, TCA_FLOWER_KEY_IP_TOS, &mask->tos, + TCA_FLOWER_KEY_IP_TOS_MASK, sizeof(key->tos)) || + fl_dump_key_val(skb, &key->ttl, TCA_FLOWER_KEY_IP_TTL, &mask->ttl, + TCA_FLOWER_KEY_IP_TTL_MASK, sizeof(key->ttl))) + return -1; + + return 0; +} + static int fl_dump_key_vlan(struct sk_buff *skb, struct flow_dissector_key_vlan *vlan_key, struct flow_dissector_key_vlan *vlan_mask) @@ -1187,9 +1231,10 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, if ((key->basic.n_proto == htons(ETH_P_IP) || key->basic.n_proto == htons(ETH_P_IPV6)) && - fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, + (fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, &mask->basic.ip_proto, TCA_FLOWER_UNSPEC, - sizeof(key->basic.ip_proto))) + sizeof(key->basic.ip_proto)) || + fl_dump_key_ip(skb, &key->ip, &mask->ip))) goto nla_put_failure; if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS && @@ -1215,7 +1260,10 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, sizeof(key->tp.src)) || fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST, &mask->tp.dst, TCA_FLOWER_KEY_TCP_DST_MASK, - sizeof(key->tp.dst)))) + sizeof(key->tp.dst)) || + fl_dump_key_val(skb, &key->tcp.flags, TCA_FLOWER_KEY_TCP_FLAGS, + &mask->tcp.flags, TCA_FLOWER_KEY_TCP_FLAGS_MASK, + sizeof(key->tcp.flags)))) goto nla_put_failure; else if (key->basic.ip_proto == IPPROTO_UDP && (fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC, diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 51859b8edd7e..9dc26c32cf32 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -64,8 +64,9 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, offload.cls_mall->exts = &head->exts; offload.cls_mall->cookie = cookie; - err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, - &offload); + err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, + tp->chain->index, + tp->protocol, &offload); if (!err) head->flags |= TCA_CLS_FLAGS_IN_HW; @@ -86,8 +87,8 @@ static void mall_destroy_hw_filter(struct tcf_proto *tp, offload.cls_mall->exts = NULL; offload.cls_mall->cookie = cookie; - dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, - &offload); + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->chain->index, + tp->protocol, &offload); } static void mall_destroy(struct tcf_proto *tp) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index d20e72a095d5..2d01195153e6 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -441,7 +441,8 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) offload.cls_u32->command = TC_CLSU32_DELETE_KNODE; offload.cls_u32->knode.handle = handle; dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->protocol, &offload); + tp->chain->index, tp->protocol, + &offload); } } @@ -465,7 +466,8 @@ static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, offload.cls_u32->hnode.prio = h->prio; err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->protocol, &offload); + tp->chain->index, tp->protocol, + &offload); if (tc_skip_sw(flags)) return err; @@ -488,7 +490,8 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) offload.cls_u32->hnode.prio = h->prio; dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->protocol, &offload); + tp->chain->index, tp->protocol, + &offload); } } @@ -522,7 +525,8 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, offload.cls_u32->knode.link_handle = n->ht_down->handle; err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->protocol, &offload); + tp->chain->index, tp->protocol, + &offload); if (!err) n->flags |= TCA_CLS_FLAGS_IN_HW; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index eb0e9bab54c1..d6e97115500b 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -340,7 +340,7 @@ META_COLLECTOR(int_sk_refcnt) *err = -1; return; } - dst->value = atomic_read(&skb->sk->sk_refcnt); + dst->value = refcount_read(&skb->sk->sk_refcnt); } META_COLLECTOR(int_sk_rcvbuf) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index cfdbfa18a95e..bd24a550e0f9 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -163,7 +163,7 @@ int register_qdisc(struct Qdisc_ops *qops) if (!(cops->get && cops->put && cops->walk && cops->leaf)) goto out_einval; - if (cops->tcf_chain && !(cops->bind_tcf && cops->unbind_tcf)) + if (cops->tcf_block && !(cops->bind_tcf && cops->unbind_tcf)) goto out_einval; } @@ -839,7 +839,7 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, old = dev_graft_qdisc(dev_queue, new); if (new && i > 0) - atomic_inc(&new->refcnt); + refcount_inc(&new->refcnt); if (!ingress) qdisc_destroy(old); @@ -850,7 +850,7 @@ skip: notify_and_destroy(net, skb, n, classid, dev->qdisc, new); if (new && !new->ops->attach) - atomic_inc(&new->refcnt); + refcount_inc(&new->refcnt); dev->qdisc = new ? : &noop_qdisc; if (new && new->ops->attach) @@ -1259,7 +1259,7 @@ replay: if (q == p || (p && check_loop(q, p, 0))) return -ELOOP; - atomic_inc(&q->refcnt); + refcount_inc(&q->refcnt); goto graft; } else { if (!q) @@ -1374,7 +1374,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, tcm->tcm_ifindex = qdisc_dev(q)->ifindex; tcm->tcm_parent = clid; tcm->tcm_handle = q->handle; - tcm->tcm_info = atomic_read(&q->refcnt); + tcm->tcm_info = refcount_read(&q->refcnt); if (nla_put_string(skb, TCA_KIND, q->ops->id)) goto nla_put_failure; if (q->ops->dump && q->ops->dump(q, skb) < 0) @@ -1879,54 +1879,6 @@ done: return skb->len; } -/* Main classifier routine: scans classifier chain attached - * to this qdisc, (optionally) tests for protocol and asks - * specific classifiers. - */ -int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res, bool compat_mode) -{ - __be16 protocol = tc_skb_protocol(skb); -#ifdef CONFIG_NET_CLS_ACT - const int max_reclassify_loop = 4; - const struct tcf_proto *old_tp = tp; - int limit = 0; - -reclassify: -#endif - for (; tp; tp = rcu_dereference_bh(tp->next)) { - int err; - - if (tp->protocol != protocol && - tp->protocol != htons(ETH_P_ALL)) - continue; - - err = tp->classify(skb, tp, res); -#ifdef CONFIG_NET_CLS_ACT - if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) - goto reset; -#endif - if (err >= 0) - return err; - } - - return TC_ACT_UNSPEC; /* signal: continue lookup */ -#ifdef CONFIG_NET_CLS_ACT -reset: - if (unlikely(limit++ >= max_reclassify_loop)) { - net_notice_ratelimited("%s: reclassify loop, rule prio %u, protocol %02x\n", - tp->q->ops->id, tp->prio & 0xffff, - ntohs(tp->protocol)); - return TC_ACT_SHOT; - } - - tp = old_tp; - protocol = tc_skb_protocol(skb); - goto reclassify; -#endif -} -EXPORT_SYMBOL(tc_classify); - #ifdef CONFIG_PROC_FS static int psched_show(struct seq_file *seq, void *v) { diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 40cbceed4de8..572fe2584e48 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -43,6 +43,7 @@ struct atm_flow_data { struct Qdisc *q; /* FIFO, TBF, etc. */ struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */ void (*old_pop)(struct atm_vcc *vcc, struct sk_buff *skb); /* chaining */ @@ -143,7 +144,7 @@ static void atm_tc_put(struct Qdisc *sch, unsigned long cl) list_del_init(&flow->list); pr_debug("atm_tc_put: qdisc %p\n", flow->q); qdisc_destroy(flow->q); - tcf_destroy_chain(&flow->filter_list); + tcf_block_put(flow->block); if (flow->sock) { pr_debug("atm_tc_put: f_count %ld\n", file_count(flow->sock->file)); @@ -274,7 +275,13 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, error = -ENOBUFS; goto err_out; } - RCU_INIT_POINTER(flow->filter_list, NULL); + + error = tcf_block_get(&flow->block, &flow->filter_list); + if (error) { + kfree(flow); + goto err_out; + } + flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); if (!flow->q) flow->q = &noop_qdisc; @@ -346,14 +353,13 @@ static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static struct tcf_proto __rcu **atm_tc_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl) { struct atm_qdisc_data *p = qdisc_priv(sch); struct atm_flow_data *flow = (struct atm_flow_data *)cl; pr_debug("atm_tc_find_tcf(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - return flow ? &flow->filter_list : &p->link.filter_list; + return flow ? flow->block : p->link.block; } /* --------------------------- Qdisc operations ---------------------------- */ @@ -377,7 +383,7 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, list_for_each_entry(flow, &p->flows, list) { fl = rcu_dereference_bh(flow->filter_list); if (fl) { - result = tc_classify(skb, fl, &res, true); + result = tcf_classify(skb, fl, &res, true); if (result < 0) continue; flow = (struct atm_flow_data *)res.class; @@ -400,6 +406,7 @@ done: switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: + case TC_ACT_TRAP: __qdisc_drop(skb, to_free); return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: @@ -491,7 +498,7 @@ static void sch_atm_dequeue(unsigned long data) ATM_SKB(skb)->vcc = flow->vcc; memcpy(skb_push(skb, flow->hdr_len), flow->hdr, flow->hdr_len); - atomic_add(skb->truesize, + refcount_add(skb->truesize, &sk_atm(flow->vcc)->sk_wmem_alloc); /* atm.atm_options are already set by atm_tc_enqueue */ flow->vcc->send(flow->vcc, skb); @@ -524,6 +531,7 @@ static struct sk_buff *atm_tc_peek(struct Qdisc *sch) static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) { struct atm_qdisc_data *p = qdisc_priv(sch); + int err; pr_debug("atm_tc_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); INIT_LIST_HEAD(&p->flows); @@ -534,7 +542,11 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) if (!p->link.q) p->link.q = &noop_qdisc; pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - RCU_INIT_POINTER(p->link.filter_list, NULL); + + err = tcf_block_get(&p->link.block, &p->link.filter_list); + if (err) + return err; + p->link.vcc = NULL; p->link.sock = NULL; p->link.classid = sch->handle; @@ -561,7 +573,7 @@ static void atm_tc_destroy(struct Qdisc *sch) pr_debug("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p); list_for_each_entry(flow, &p->flows, list) - tcf_destroy_chain(&flow->filter_list); + tcf_block_put(flow->block); list_for_each_entry_safe(flow, tmp, &p->flows, list) { if (flow->ref > 1) @@ -646,7 +658,7 @@ static const struct Qdisc_class_ops atm_class_ops = { .change = atm_tc_change, .delete = atm_tc_delete, .walk = atm_tc_walk, - .tcf_chain = atm_tc_find_tcf, + .tcf_block = atm_tc_tcf_block, .bind_tcf = atm_tc_bind_filter, .unbind_tcf = atm_tc_put, .dump = atm_tc_dump_class, diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 7415859fd4c3..481036f6b54e 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -127,6 +127,7 @@ struct cbq_class { struct tc_cbq_xstats xstats; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; int refcnt; int filters; @@ -233,7 +234,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) /* * Step 2+n. Apply classifier. */ - result = tc_classify(skb, fl, &res, true); + result = tcf_classify(skb, fl, &res, true); if (!fl || result < 0) goto fallback; @@ -253,6 +254,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: + case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return NULL; @@ -1405,7 +1407,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) WARN_ON(cl->filters); - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); qdisc_destroy(cl->q); qdisc_put_rtab(cl->R_tab); gen_kill_estimator(&cl->rate_est); @@ -1430,7 +1432,7 @@ static void cbq_destroy(struct Qdisc *sch) */ for (h = 0; h < q->clhash.hashsize; h++) { hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); } for (h = 0; h < q->clhash.hashsize; h++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[h], @@ -1585,12 +1587,19 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (cl == NULL) goto failure; + err = tcf_block_get(&cl->block, &cl->filter_list); + if (err) { + kfree(cl); + return err; + } + if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) { + tcf_block_put(cl->block); kfree(cl); goto failure; } @@ -1688,8 +1697,7 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg) return 0; } -static struct tcf_proto __rcu **cbq_find_tcf(struct Qdisc *sch, - unsigned long arg) +static struct tcf_block *cbq_tcf_block(struct Qdisc *sch, unsigned long arg) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl = (struct cbq_class *)arg; @@ -1697,7 +1705,7 @@ static struct tcf_proto __rcu **cbq_find_tcf(struct Qdisc *sch, if (cl == NULL) cl = &q->link; - return &cl->filter_list; + return cl->block; } static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, @@ -1756,7 +1764,7 @@ static const struct Qdisc_class_ops cbq_class_ops = { .change = cbq_change_class, .delete = cbq_delete, .walk = cbq_walk, - .tcf_chain = cbq_find_tcf, + .tcf_block = cbq_tcf_block, .bind_tcf = cbq_bind_filter, .unbind_tcf = cbq_unbind_filter, .dump = cbq_dump_class, diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 58a8c32eab23..a413dc1c2098 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -36,6 +36,7 @@ struct drr_class { struct drr_sched { struct list_head active; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct Qdisc_class_hash clhash; }; @@ -190,15 +191,14 @@ static void drr_put_class(struct Qdisc *sch, unsigned long arg) drr_destroy_class(sch, cl); } -static struct tcf_proto __rcu **drr_tcf_chain(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *drr_tcf_block(struct Qdisc *sch, unsigned long cl) { struct drr_sched *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static unsigned long drr_bind_tcf(struct Qdisc *sch, unsigned long parent, @@ -333,12 +333,13 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); - result = tc_classify(skb, fl, &res, false); + result = tcf_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: + case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return NULL; @@ -431,6 +432,9 @@ static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt) struct drr_sched *q = qdisc_priv(sch); int err; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; err = qdisc_class_hash_init(&q->clhash); if (err < 0) return err; @@ -462,7 +466,7 @@ static void drr_destroy_qdisc(struct Qdisc *sch) struct hlist_node *next; unsigned int i; - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], @@ -477,7 +481,7 @@ static const struct Qdisc_class_ops drr_class_ops = { .delete = drr_delete_class, .get = drr_get_class, .put = drr_put_class, - .tcf_chain = drr_tcf_chain, + .tcf_block = drr_tcf_block, .bind_tcf = drr_bind_tcf, .unbind_tcf = drr_unbind_tcf, .graft = drr_graft_class, diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 1c0f877f673a..6d94fcc3592a 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -44,6 +44,7 @@ struct mask_value { struct dsmark_qdisc_data { struct Qdisc *q; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct mask_value *mv; u16 indices; u8 set_tc_index; @@ -183,11 +184,11 @@ ignore: } } -static inline struct tcf_proto __rcu **dsmark_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl) { struct dsmark_qdisc_data *p = qdisc_priv(sch); - return &p->filter_list; + + return p->block; } /* --------------------------- Qdisc operations ---------------------------- */ @@ -234,7 +235,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, else { struct tcf_result res; struct tcf_proto *fl = rcu_dereference_bh(p->filter_list); - int result = tc_classify(skb, fl, &res, false); + int result = tcf_classify(skb, fl, &res, false); pr_debug("result %d class 0x%04x\n", result, res.classid); @@ -242,6 +243,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, #ifdef CONFIG_NET_CLS_ACT case TC_ACT_QUEUED: case TC_ACT_STOLEN: + case TC_ACT_TRAP: __qdisc_drop(skb, to_free); return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; @@ -342,6 +344,10 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) goto errout; + err = tcf_block_get(&p->block, &p->filter_list); + if (err) + return err; + err = nla_parse_nested(tb, TCA_DSMARK_MAX, opt, dsmark_policy, NULL); if (err < 0) goto errout; @@ -400,7 +406,7 @@ static void dsmark_destroy(struct Qdisc *sch) pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - tcf_destroy_chain(&p->filter_list); + tcf_block_put(p->block); qdisc_destroy(p->q); if (p->mv != p->embedded) kfree(p->mv); @@ -468,7 +474,7 @@ static const struct Qdisc_class_ops dsmark_class_ops = { .change = dsmark_change, .delete = dsmark_delete, .walk = dsmark_walk, - .tcf_chain = dsmark_find_tcf, + .tcf_block = dsmark_tcf_block, .bind_tcf = dsmark_bind_filter, .unbind_tcf = dsmark_put, .dump = dsmark_dump_class, diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index b488721a0059..263d16e3219e 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -390,9 +390,17 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->stat_tcp_retrans++; qdisc_qstats_backlog_inc(sch, skb); if (fq_flow_is_detached(f)) { + struct sock *sk = skb->sk; + fq_flow_add_tail(&q->new_flows, f); if (time_after(jiffies, f->age + q->flow_refill_delay)) f->credit = max_t(u32, f->credit, q->quantum); + if (sk && q->rate_enable) { + if (unlikely(smp_load_acquire(&sk->sk_pacing_status) != + SK_PACING_FQ)) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); + } q->inactive_flows--; } @@ -640,7 +648,7 @@ static int fq_resize(struct Qdisc *sch, u32 log) return 0; /* If XPS was setup, we can allocate memory on right NUMA node */ - array = kvmalloc_node(sizeof(struct rb_root) << log, GFP_KERNEL | __GFP_REPEAT, + array = kvmalloc_node(sizeof(struct rb_root) << log, GFP_KERNEL | __GFP_RETRY_MAYFAIL, netdev_queue_numa_node_read(sch->dev_queue)); if (!array) return -ENOMEM; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 9201abce928c..337f2d6d81e4 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -55,6 +55,7 @@ struct fq_codel_flow { struct fq_codel_sched_data { struct tcf_proto __rcu *filter_list; /* optional external classifier */ + struct tcf_block *block; struct fq_codel_flow *flows; /* Flows table [flows_cnt] */ u32 *backlogs; /* backlog table [flows_cnt] */ u32 flows_cnt; /* number of flows */ @@ -96,12 +97,13 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch, return fq_codel_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tc_classify(skb, filter, &res, false); + result = tcf_classify(skb, filter, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: + case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return 0; @@ -450,7 +452,7 @@ static void fq_codel_destroy(struct Qdisc *sch) { struct fq_codel_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); kvfree(q->backlogs); kvfree(q->flows); } @@ -459,6 +461,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) { struct fq_codel_sched_data *q = qdisc_priv(sch); int i; + int err; sch->limit = 10*1024; q->flows_cnt = 1024; @@ -478,6 +481,10 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) return err; } + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + if (!q->flows) { q->flows = kvzalloc(q->flows_cnt * sizeof(struct fq_codel_flow), GFP_KERNEL); @@ -589,14 +596,13 @@ static void fq_codel_put(struct Qdisc *q, unsigned long cl) { } -static struct tcf_proto __rcu **fq_codel_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *fq_codel_tcf_block(struct Qdisc *sch, unsigned long cl) { struct fq_codel_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static int fq_codel_dump_class(struct Qdisc *sch, unsigned long cl, @@ -679,7 +685,7 @@ static const struct Qdisc_class_ops fq_codel_class_ops = { .leaf = fq_codel_leaf, .get = fq_codel_get, .put = fq_codel_put, - .tcf_chain = fq_codel_find_tcf, + .tcf_block = fq_codel_tcf_block, .bind_tcf = fq_codel_bind, .unbind_tcf = fq_codel_put, .dump = fq_codel_dump_class, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 52a2c55f6d9e..57ba406f1437 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -633,7 +633,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; dev_hold(dev); - atomic_set(&sch->refcnt, 1); + refcount_set(&sch->refcnt, 1); return sch; errout: @@ -701,7 +701,7 @@ void qdisc_destroy(struct Qdisc *qdisc) const struct Qdisc_ops *ops = qdisc->ops; if (qdisc->flags & TCQ_F_BUILTIN || - !atomic_dec_and_test(&qdisc->refcnt)) + !refcount_dec_and_test(&qdisc->refcnt)) return; #ifdef CONFIG_NET_SCHED @@ -739,7 +739,7 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, spin_lock_bh(root_lock); /* Prune old scheduler */ - if (oqdisc && atomic_read(&oqdisc->refcnt) <= 1) + if (oqdisc && refcount_read(&oqdisc->refcnt) <= 1) qdisc_reset(oqdisc); /* ... and graft new one */ @@ -785,7 +785,7 @@ static void attach_default_qdiscs(struct net_device *dev) dev->priv_flags & IFF_NO_QUEUE) { netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); dev->qdisc = txq->qdisc_sleeping; - atomic_inc(&dev->qdisc->refcnt); + refcount_inc(&dev->qdisc->refcnt); } else { qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT); if (qdisc) { diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 5cb82f6c1b06..b52f74610dc7 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -116,6 +116,7 @@ struct hfsc_class { struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct tcf_proto __rcu *filter_list; /* filter list */ + struct tcf_block *block; unsigned int filter_cnt; /* filter count */ unsigned int level; /* class level in hierarchy */ @@ -1040,12 +1041,19 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; + err = tcf_block_get(&cl->block, &cl->filter_list); + if (err) { + kfree(cl); + return err; + } + if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) { + tcf_block_put(cl->block); kfree(cl); return err; } @@ -1091,7 +1099,7 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl) { struct hfsc_sched *q = qdisc_priv(sch); - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); qdisc_destroy(cl->qdisc); gen_kill_estimator(&cl->rate_est); if (cl != &q->root) @@ -1142,11 +1150,12 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; head = &q->root; tcf = rcu_dereference_bh(q->root.filter_list); - while (tcf && (result = tc_classify(skb, tcf, &res, false)) >= 0) { + while (tcf && (result = tcf_classify(skb, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: + case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return NULL; @@ -1261,8 +1270,7 @@ hfsc_unbind_tcf(struct Qdisc *sch, unsigned long arg) cl->filter_cnt--; } -static struct tcf_proto __rcu ** -hfsc_tcf_chain(struct Qdisc *sch, unsigned long arg) +static struct tcf_block *hfsc_tcf_block(struct Qdisc *sch, unsigned long arg) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)arg; @@ -1270,7 +1278,7 @@ hfsc_tcf_chain(struct Qdisc *sch, unsigned long arg) if (cl == NULL) cl = &q->root; - return &cl->filter_list; + return cl->block; } static int @@ -1515,7 +1523,7 @@ hfsc_destroy_qdisc(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); } for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], @@ -1662,7 +1670,7 @@ static const struct Qdisc_class_ops hfsc_class_ops = { .put = hfsc_put_class, .bind_tcf = hfsc_bind_tcf, .unbind_tcf = hfsc_unbind_tcf, - .tcf_chain = hfsc_tcf_chain, + .tcf_block = hfsc_tcf_block, .dump = hfsc_dump_class, .dump_stats = hfsc_dump_class_stats, .walk = hfsc_walk diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 570ef3b0c09b..203286ab4427 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -105,6 +105,7 @@ struct htb_class { int quantum; /* but stored for parent-to-leaf return */ struct tcf_proto __rcu *filter_list; /* class attached filters */ + struct tcf_block *block; int filter_cnt; int refcnt; /* usage count of this class */ @@ -156,6 +157,7 @@ struct htb_sched { /* filters for qdisc itself */ struct tcf_proto __rcu *filter_list; + struct tcf_block *block; #define HTB_WARN_TOOMANYEVENTS 0x1 unsigned int warned; /* only one warning */ @@ -231,11 +233,12 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, } *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - while (tcf && (result = tc_classify(skb, tcf, &res, false)) >= 0) { + while (tcf && (result = tcf_classify(skb, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: + case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return NULL; @@ -1017,6 +1020,10 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) return -EINVAL; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + err = nla_parse_nested(tb, TCA_HTB_MAX, opt, htb_policy, NULL); if (err < 0) return err; @@ -1230,7 +1237,7 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) qdisc_destroy(cl->un.leaf.q); } gen_kill_estimator(&cl->rate_est); - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); kfree(cl); } @@ -1248,11 +1255,11 @@ static void htb_destroy(struct Qdisc *sch) * because filter need its target class alive to be able to call * unbind_filter on it (without Oops). */ - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); } for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], @@ -1396,6 +1403,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!cl) goto failure; + err = tcf_block_get(&cl->block, &cl->filter_list); + if (err) { + kfree(cl); + goto failure; + } if (htb_rate_est || tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, @@ -1403,6 +1415,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, qdisc_root_sleeping_running(sch), tca[TCA_RATE] ? : &est.nla); if (err) { + tcf_block_put(cl->block); kfree(cl); goto failure; } @@ -1521,14 +1534,12 @@ failure: return err; } -static struct tcf_proto __rcu **htb_find_tcf(struct Qdisc *sch, - unsigned long arg) +static struct tcf_block *htb_tcf_block(struct Qdisc *sch, unsigned long arg) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)arg; - struct tcf_proto __rcu **fl = cl ? &cl->filter_list : &q->filter_list; - return fl; + return cl ? cl->block : q->block; } static unsigned long htb_bind_filter(struct Qdisc *sch, unsigned long parent, @@ -1591,7 +1602,7 @@ static const struct Qdisc_class_ops htb_class_ops = { .change = htb_change_class, .delete = htb_delete, .walk = htb_walk, - .tcf_chain = htb_find_tcf, + .tcf_block = htb_tcf_block, .bind_tcf = htb_bind_filter, .unbind_tcf = htb_unbind_filter, .dump = htb_dump_class, diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 3bab5f66c392..d8a9bebcab90 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -18,6 +18,10 @@ #include <net/pkt_sched.h> #include <net/pkt_cls.h> +struct ingress_sched_data { + struct tcf_block *block; +}; + static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg) { return NULL; @@ -47,16 +51,23 @@ static void ingress_walk(struct Qdisc *sch, struct qdisc_walker *walker) { } -static struct tcf_proto __rcu **ingress_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *ingress_tcf_block(struct Qdisc *sch, unsigned long cl) { - struct net_device *dev = qdisc_dev(sch); + struct ingress_sched_data *q = qdisc_priv(sch); - return &dev->ingress_cl_list; + return q->block; } static int ingress_init(struct Qdisc *sch, struct nlattr *opt) { + struct ingress_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int err; + + err = tcf_block_get(&q->block, &dev->ingress_cl_list); + if (err) + return err; + net_inc_ingress_queue(); sch->flags |= TCQ_F_CPUSTATS; @@ -65,9 +76,9 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) static void ingress_destroy(struct Qdisc *sch) { - struct net_device *dev = qdisc_dev(sch); + struct ingress_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&dev->ingress_cl_list); + tcf_block_put(q->block); net_dec_ingress_queue(); } @@ -91,7 +102,7 @@ static const struct Qdisc_class_ops ingress_class_ops = { .get = ingress_get, .put = ingress_put, .walk = ingress_walk, - .tcf_chain = ingress_find_tcf, + .tcf_block = ingress_tcf_block, .tcf_cl_offload = ingress_cl_offload, .bind_tcf = ingress_bind_filter, .unbind_tcf = ingress_put, @@ -100,12 +111,18 @@ static const struct Qdisc_class_ops ingress_class_ops = { static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .cl_ops = &ingress_class_ops, .id = "ingress", + .priv_size = sizeof(struct ingress_sched_data), .init = ingress_init, .destroy = ingress_destroy, .dump = ingress_dump, .owner = THIS_MODULE, }; +struct clsact_sched_data { + struct tcf_block *ingress_block; + struct tcf_block *egress_block; +}; + static unsigned long clsact_get(struct Qdisc *sch, u32 classid) { switch (TC_H_MIN(classid)) { @@ -128,16 +145,15 @@ static unsigned long clsact_bind_filter(struct Qdisc *sch, return clsact_get(sch, classid); } -static struct tcf_proto __rcu **clsact_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *clsact_tcf_block(struct Qdisc *sch, unsigned long cl) { - struct net_device *dev = qdisc_dev(sch); + struct clsact_sched_data *q = qdisc_priv(sch); switch (cl) { case TC_H_MIN(TC_H_MIN_INGRESS): - return &dev->ingress_cl_list; + return q->ingress_block; case TC_H_MIN(TC_H_MIN_EGRESS): - return &dev->egress_cl_list; + return q->egress_block; default: return NULL; } @@ -145,6 +161,18 @@ static struct tcf_proto __rcu **clsact_find_tcf(struct Qdisc *sch, static int clsact_init(struct Qdisc *sch, struct nlattr *opt) { + struct clsact_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int err; + + err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list); + if (err) + return err; + + err = tcf_block_get(&q->egress_block, &dev->egress_cl_list); + if (err) + return err; + net_inc_ingress_queue(); net_inc_egress_queue(); @@ -155,10 +183,10 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) static void clsact_destroy(struct Qdisc *sch) { - struct net_device *dev = qdisc_dev(sch); + struct clsact_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&dev->ingress_cl_list); - tcf_destroy_chain(&dev->egress_cl_list); + tcf_block_put(q->egress_block); + tcf_block_put(q->ingress_block); net_dec_ingress_queue(); net_dec_egress_queue(); @@ -169,7 +197,7 @@ static const struct Qdisc_class_ops clsact_class_ops = { .get = clsact_get, .put = ingress_put, .walk = ingress_walk, - .tcf_chain = clsact_find_tcf, + .tcf_block = clsact_tcf_block, .tcf_cl_offload = clsact_cl_offload, .bind_tcf = clsact_bind_filter, .unbind_tcf = ingress_put, @@ -178,6 +206,7 @@ static const struct Qdisc_class_ops clsact_class_ops = { static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { .cl_ops = &clsact_class_ops, .id = "clsact", + .priv_size = sizeof(struct clsact_sched_data), .init = clsact_init, .destroy = clsact_destroy, .dump = ingress_dump, diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 0a4cf27ea54b..e0c02725cd48 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -43,7 +43,7 @@ static void mqprio_destroy(struct Qdisc *sch) struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO, { .mqprio = &offload } }; - dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc); + dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, 0, &tc); } else { netdev_set_num_tc(dev, 0); } @@ -152,7 +152,8 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO, { .mqprio = &offload } }; - err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc); + err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, + 0, 0, &tc); if (err) return err; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 43a3a10b3c81..f143b7bbaa0d 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -32,6 +32,7 @@ struct multiq_sched_data { u16 max_bands; u16 curband; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct Qdisc **queues; }; @@ -46,11 +47,12 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) int err; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - err = tc_classify(skb, fl, &res, false); + err = tcf_classify(skb, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: + case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return NULL; @@ -170,7 +172,7 @@ multiq_destroy(struct Qdisc *sch) int band; struct multiq_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (band = 0; band < q->bands; band++) qdisc_destroy(q->queues[band]); @@ -243,6 +245,10 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt) if (opt == NULL) return -EINVAL; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + q->max_bands = qdisc_dev(sch)->num_tx_queues; q->queues = kcalloc(q->max_bands, sizeof(struct Qdisc *), GFP_KERNEL); @@ -367,14 +373,13 @@ static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg) } } -static struct tcf_proto __rcu **multiq_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *multiq_tcf_block(struct Qdisc *sch, unsigned long cl) { struct multiq_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static const struct Qdisc_class_ops multiq_class_ops = { @@ -383,7 +388,7 @@ static const struct Qdisc_class_ops multiq_class_ops = { .get = multiq_get, .put = multiq_put, .walk = multiq_walk, - .tcf_chain = multiq_find_tcf, + .tcf_block = multiq_tcf_block, .bind_tcf = multiq_bind, .unbind_tcf = multiq_put, .dump = multiq_dump_class, diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 92c2e6d448d7..e3e364cc9a70 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -25,6 +25,7 @@ struct prio_sched_data { int bands; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; u8 prio2band[TC_PRIO_MAX+1]; struct Qdisc *queues[TCQ_PRIO_BANDS]; }; @@ -42,11 +43,12 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; if (TC_H_MAJ(skb->priority) != sch->handle) { fl = rcu_dereference_bh(q->filter_list); - err = tc_classify(skb, fl, &res, false); + err = tcf_classify(skb, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: + case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return NULL; @@ -145,7 +147,7 @@ prio_destroy(struct Qdisc *sch) int prio; struct prio_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (prio = 0; prio < q->bands; prio++) qdisc_destroy(q->queues[prio]); } @@ -204,9 +206,16 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) static int prio_init(struct Qdisc *sch, struct nlattr *opt) { + struct prio_sched_data *q = qdisc_priv(sch); + int err; + if (!opt) return -EINVAL; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + return prio_tune(sch, opt); } @@ -317,14 +326,13 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg) } } -static struct tcf_proto __rcu **prio_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *prio_tcf_block(struct Qdisc *sch, unsigned long cl) { struct prio_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static const struct Qdisc_class_ops prio_class_ops = { @@ -333,7 +341,7 @@ static const struct Qdisc_class_ops prio_class_ops = { .get = prio_get, .put = prio_put, .walk = prio_walk, - .tcf_chain = prio_find_tcf, + .tcf_block = prio_tcf_block, .bind_tcf = prio_bind, .unbind_tcf = prio_put, .dump = prio_dump_class, diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 041eba3006cc..0e16dfda0bd7 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -182,6 +182,7 @@ struct qfq_group { struct qfq_sched { struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct Qdisc_class_hash clhash; u64 oldV, V; /* Precise virtual times. */ @@ -582,15 +583,14 @@ static void qfq_put_class(struct Qdisc *sch, unsigned long arg) qfq_destroy_class(sch, cl); } -static struct tcf_proto __rcu **qfq_tcf_chain(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *qfq_tcf_block(struct Qdisc *sch, unsigned long cl) { struct qfq_sched *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static unsigned long qfq_bind_tcf(struct Qdisc *sch, unsigned long parent, @@ -720,12 +720,13 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); - result = tc_classify(skb, fl, &res, false); + result = tcf_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: + case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return NULL; @@ -1438,6 +1439,10 @@ static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt) int i, j, err; u32 max_cl_shift, maxbudg_shift, max_classes; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + err = qdisc_class_hash_init(&q->clhash); if (err < 0) return err; @@ -1492,7 +1497,7 @@ static void qfq_destroy_qdisc(struct Qdisc *sch) struct hlist_node *next; unsigned int i; - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], @@ -1508,7 +1513,7 @@ static const struct Qdisc_class_ops qfq_class_ops = { .delete = qfq_delete_class, .get = qfq_get_class, .put = qfq_put_class, - .tcf_chain = qfq_tcf_chain, + .tcf_block = qfq_tcf_block, .bind_tcf = qfq_bind_tcf, .unbind_tcf = qfq_unbind_tcf, .graft = qfq_graft_class, diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 0f777273ba29..11fb6ec878d6 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -56,6 +56,7 @@ struct sfb_bins { struct sfb_sched_data { struct Qdisc *qdisc; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; unsigned long rehash_interval; unsigned long warmup_time; /* double buffering warmup time in jiffies */ u32 max; @@ -259,12 +260,13 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl, struct tcf_result res; int result; - result = tc_classify(skb, fl, &res, false); + result = tcf_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: + case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return false; @@ -465,7 +467,7 @@ static void sfb_destroy(struct Qdisc *sch) { struct sfb_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); qdisc_destroy(q->qdisc); } @@ -549,6 +551,11 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt) static int sfb_init(struct Qdisc *sch, struct nlattr *opt) { struct sfb_sched_data *q = qdisc_priv(sch); + int err; + + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; q->qdisc = &noop_qdisc; return sfb_change(sch, opt); @@ -657,14 +664,13 @@ static void sfb_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static struct tcf_proto __rcu **sfb_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *sfb_tcf_block(struct Qdisc *sch, unsigned long cl) { struct sfb_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static unsigned long sfb_bind(struct Qdisc *sch, unsigned long parent, @@ -682,7 +688,7 @@ static const struct Qdisc_class_ops sfb_class_ops = { .change = sfb_change_class, .delete = sfb_delete, .walk = sfb_walk, - .tcf_chain = sfb_find_tcf, + .tcf_block = sfb_tcf_block, .bind_tcf = sfb_bind, .unbind_tcf = sfb_put, .dump = sfb_dump_class, diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 332d94be6e1c..f80ea2cc5f1f 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -126,6 +126,7 @@ struct sfq_sched_data { u8 flags; unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */ struct tcf_proto __rcu *filter_list; + struct tcf_block *block; sfq_index *ht; /* Hash table ('divisor' slots) */ struct sfq_slot *slots; /* Flows table ('maxflows' entries) */ @@ -180,12 +181,13 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, return sfq_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tc_classify(skb, fl, &res, false); + result = tcf_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: + case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return 0; @@ -697,7 +699,7 @@ static void sfq_destroy(struct Qdisc *sch) { struct sfq_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); q->perturb_period = 0; del_timer_sync(&q->perturb_timer); sfq_free(q->ht); @@ -709,6 +711,11 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) { struct sfq_sched_data *q = qdisc_priv(sch); int i; + int err; + + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; setup_deferrable_timer(&q->perturb_timer, sfq_perturbation, (unsigned long)sch); @@ -815,14 +822,13 @@ static void sfq_put(struct Qdisc *q, unsigned long cl) { } -static struct tcf_proto __rcu **sfq_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *sfq_tcf_block(struct Qdisc *sch, unsigned long cl) { struct sfq_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static int sfq_dump_class(struct Qdisc *sch, unsigned long cl, @@ -878,7 +884,7 @@ static const struct Qdisc_class_ops sfq_class_ops = { .leaf = sfq_leaf, .get = sfq_get, .put = sfq_put, - .tcf_chain = sfq_find_tcf, + .tcf_block = sfq_tcf_block, .bind_tcf = sfq_bind, .unbind_tcf = sfq_put, .dump = sfq_dump_class, diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 95238284c422..40ec83679d6e 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -71,7 +71,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a { struct net *net = sock_net(sk); struct sctp_sock *sp; - sctp_paramhdr_t *p; + struct sctp_paramhdr *p; int i; /* Retrieve the SCTP per socket area. */ @@ -88,7 +88,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->base.type = SCTP_EP_TYPE_ASSOCIATION; /* Initialize the object handling fields. */ - atomic_set(&asoc->base.refcnt, 1); + refcount_set(&asoc->base.refcnt, 1); /* Initialize the bind addr area. */ sctp_bind_addr_init(&asoc->base.bind_addr, ep->base.bind_addr.port); @@ -246,7 +246,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a if (!sctp_ulpq_init(&asoc->ulpq, asoc)) goto fail_init; - if (sctp_stream_new(asoc, gfp)) + if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, + 0, gfp)) goto fail_init; /* Assume that peer would support both address types unless we are @@ -283,15 +284,15 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a ntohs(ep->auth_chunk_list->param_hdr.length)); /* Get the AUTH random number for this association */ - p = (sctp_paramhdr_t *)asoc->c.auth_random; + p = (struct sctp_paramhdr *)asoc->c.auth_random; p->type = SCTP_PARAM_RANDOM; - p->length = htons(sizeof(sctp_paramhdr_t) + SCTP_AUTH_RANDOM_LENGTH); + p->length = htons(sizeof(*p) + SCTP_AUTH_RANDOM_LENGTH); get_random_bytes(p+1, SCTP_AUTH_RANDOM_LENGTH); return asoc; stream_free: - sctp_stream_free(asoc->stream); + sctp_stream_free(&asoc->stream); fail_init: sock_put(asoc->base.sk); sctp_endpoint_put(asoc->ep); @@ -365,7 +366,7 @@ void sctp_association_free(struct sctp_association *asoc) sctp_tsnmap_free(&asoc->peer.tsn_map); /* Free stream information. */ - sctp_stream_free(asoc->stream); + sctp_stream_free(&asoc->stream); if (asoc->strreset_chunk) sctp_chunk_free(asoc->strreset_chunk); @@ -872,7 +873,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, /* Hold a reference to an association. */ void sctp_association_hold(struct sctp_association *asoc) { - atomic_inc(&asoc->base.refcnt); + refcount_inc(&asoc->base.refcnt); } /* Release a reference to an association and cleanup @@ -880,7 +881,7 @@ void sctp_association_hold(struct sctp_association *asoc) */ void sctp_association_put(struct sctp_association *asoc) { - if (atomic_dec_and_test(&asoc->base.refcnt)) + if (refcount_dec_and_test(&asoc->base.refcnt)) sctp_association_destroy(asoc); } @@ -1111,8 +1112,8 @@ void sctp_assoc_migrate(struct sctp_association *assoc, struct sock *newsk) } /* Update an association (possibly from unexpected COOKIE-ECHO processing). */ -void sctp_assoc_update(struct sctp_association *asoc, - struct sctp_association *new) +int sctp_assoc_update(struct sctp_association *asoc, + struct sctp_association *new) { struct sctp_transport *trans; struct list_head *pos, *temp; @@ -1123,8 +1124,10 @@ void sctp_assoc_update(struct sctp_association *asoc, asoc->peer.sack_needed = new->peer.sack_needed; asoc->peer.auth_capable = new->peer.auth_capable; asoc->peer.i = new->peer.i; - sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, - asoc->peer.i.initial_tsn, GFP_ATOMIC); + + if (!sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, + asoc->peer.i.initial_tsn, GFP_ATOMIC)) + return -ENOMEM; /* Remove any peer addresses not present in the new association. */ list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { @@ -1151,7 +1154,7 @@ void sctp_assoc_update(struct sctp_association *asoc, /* Reinitialize SSN for both local streams * and peer's streams. */ - sctp_stream_clear(asoc->stream); + sctp_stream_clear(&asoc->stream); /* Flush the ULP reassembly and ordered queue. * Any data there will now be stale and will @@ -1168,27 +1171,21 @@ void sctp_assoc_update(struct sctp_association *asoc, } else { /* Add any peer addresses from the new association. */ list_for_each_entry(trans, &new->peer.transport_addr_list, - transports) { - if (!sctp_assoc_lookup_paddr(asoc, &trans->ipaddr)) - sctp_assoc_add_peer(asoc, &trans->ipaddr, - GFP_ATOMIC, trans->state); - } + transports) + if (!sctp_assoc_lookup_paddr(asoc, &trans->ipaddr) && + !sctp_assoc_add_peer(asoc, &trans->ipaddr, + GFP_ATOMIC, trans->state)) + return -ENOMEM; asoc->ctsn_ack_point = asoc->next_tsn - 1; asoc->adv_peer_ack_point = asoc->ctsn_ack_point; - if (sctp_state(asoc, COOKIE_WAIT)) { - sctp_stream_free(asoc->stream); - asoc->stream = new->stream; - new->stream = NULL; - } + if (sctp_state(asoc, COOKIE_WAIT)) + sctp_stream_update(&asoc->stream, &new->stream); - if (!asoc->assoc_id) { - /* get a new association id since we don't have one - * yet. - */ - sctp_assoc_set_id(asoc, GFP_ATOMIC); - } + /* get a new assoc id if we don't have one yet. */ + if (sctp_assoc_set_id(asoc, GFP_ATOMIC)) + return -ENOMEM; } /* SCTP-AUTH: Save the peer parameters from the new associations @@ -1206,7 +1203,7 @@ void sctp_assoc_update(struct sctp_association *asoc, asoc->peer.peer_hmacs = new->peer.peer_hmacs; new->peer.peer_hmacs = NULL; - sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC); + return sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC); } /* Update the retran path for sending a retransmitted packet. diff --git a/net/sctp/auth.c b/net/sctp/auth.c index f99d4855d3de..e001b01b0e68 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -63,7 +63,7 @@ void sctp_auth_key_put(struct sctp_auth_bytes *key) if (!key) return; - if (atomic_dec_and_test(&key->refcnt)) { + if (refcount_dec_and_test(&key->refcnt)) { kzfree(key); SCTP_DBG_OBJCNT_DEC(keys); } @@ -84,7 +84,7 @@ static struct sctp_auth_bytes *sctp_auth_create_key(__u32 key_len, gfp_t gfp) return NULL; key->len = key_len; - atomic_set(&key->refcnt, 1); + refcount_set(&key->refcnt, 1); SCTP_DBG_OBJCNT_INC(keys); return key; @@ -538,7 +538,8 @@ struct sctp_hmac *sctp_auth_asoc_get_hmac(const struct sctp_association *asoc) if (!hmacs) return NULL; - n_elt = (ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t)) >> 1; + n_elt = (ntohs(hmacs->param_hdr.length) - + sizeof(struct sctp_paramhdr)) >> 1; for (i = 0; i < n_elt; i++) { id = ntohs(hmacs->hmac_ids[i]); @@ -589,7 +590,8 @@ int sctp_auth_asoc_verify_hmac_id(const struct sctp_association *asoc, return 0; hmacs = (struct sctp_hmac_algo_param *)asoc->c.auth_hmacs; - n_elt = (ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t)) >> 1; + n_elt = (ntohs(hmacs->param_hdr.length) - + sizeof(struct sctp_paramhdr)) >> 1; return __sctp_auth_find_hmacid(hmacs->hmac_ids, n_elt, hmac_id); } @@ -612,8 +614,8 @@ void sctp_auth_asoc_set_default_hmac(struct sctp_association *asoc, if (asoc->default_hmac_id) return; - n_params = (ntohs(hmacs->param_hdr.length) - - sizeof(sctp_paramhdr_t)) >> 1; + n_params = (ntohs(hmacs->param_hdr.length) - + sizeof(struct sctp_paramhdr)) >> 1; ep = asoc->ep; for (i = 0; i < n_params; i++) { id = ntohs(hmacs->hmac_ids[i]); @@ -632,7 +634,7 @@ void sctp_auth_asoc_set_default_hmac(struct sctp_association *asoc, /* Check to see if the given chunk is supposed to be authenticated */ -static int __sctp_auth_cid(sctp_cid_t chunk, struct sctp_chunks_param *param) +static int __sctp_auth_cid(enum sctp_cid chunk, struct sctp_chunks_param *param) { unsigned short len; int found = 0; @@ -641,7 +643,7 @@ static int __sctp_auth_cid(sctp_cid_t chunk, struct sctp_chunks_param *param) if (!param || param->param_hdr.length == 0) return 0; - len = ntohs(param->param_hdr.length) - sizeof(sctp_paramhdr_t); + len = ntohs(param->param_hdr.length) - sizeof(struct sctp_paramhdr); /* SCTP-AUTH, Section 3.2 * The chunk types for INIT, INIT-ACK, SHUTDOWN-COMPLETE and AUTH @@ -668,7 +670,7 @@ static int __sctp_auth_cid(sctp_cid_t chunk, struct sctp_chunks_param *param) } /* Check if peer requested that this chunk is authenticated */ -int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc) +int sctp_auth_send_cid(enum sctp_cid chunk, const struct sctp_association *asoc) { if (!asoc) return 0; @@ -680,7 +682,7 @@ int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc) } /* Check if we requested that peer authenticate this chunk. */ -int sctp_auth_recv_cid(sctp_cid_t chunk, const struct sctp_association *asoc) +int sctp_auth_recv_cid(enum sctp_cid chunk, const struct sctp_association *asoc) { if (!asoc) return 0; @@ -775,7 +777,7 @@ int sctp_auth_ep_add_chunkid(struct sctp_endpoint *ep, __u8 chunk_id) /* Check if we can add this chunk to the array */ param_len = ntohs(p->param_hdr.length); - nchunks = param_len - sizeof(sctp_paramhdr_t); + nchunks = param_len - sizeof(struct sctp_paramhdr); if (nchunks == SCTP_NUM_CHUNK_TYPES) return -EINVAL; @@ -812,9 +814,11 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep, return -EINVAL; for (i = 0; i < hmacs->shmac_num_idents; i++) - ep->auth_hmacs_list->hmac_ids[i] = htons(hmacs->shmac_idents[i]); - ep->auth_hmacs_list->param_hdr.length = htons(sizeof(sctp_paramhdr_t) + - hmacs->shmac_num_idents * sizeof(__u16)); + ep->auth_hmacs_list->hmac_ids[i] = + htons(hmacs->shmac_idents[i]); + ep->auth_hmacs_list->param_hdr.length = + htons(sizeof(struct sctp_paramhdr) + + hmacs->shmac_num_idents * sizeof(__u16)); return 0; } diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 697721a7a3f1..1323d41e68b8 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -49,7 +49,7 @@ /* Initialize datamsg from memory. */ static void sctp_datamsg_init(struct sctp_datamsg *msg) { - atomic_set(&msg->refcnt, 1); + refcount_set(&msg->refcnt, 1); msg->send_failed = 0; msg->send_error = 0; msg->can_delay = 1; @@ -136,13 +136,13 @@ static void sctp_datamsg_destroy(struct sctp_datamsg *msg) /* Hold a reference. */ static void sctp_datamsg_hold(struct sctp_datamsg *msg) { - atomic_inc(&msg->refcnt); + refcount_inc(&msg->refcnt); } /* Release a reference. */ void sctp_datamsg_put(struct sctp_datamsg *msg) { - if (atomic_dec_and_test(&msg->refcnt)) + if (refcount_dec_and_test(&msg->refcnt)) sctp_datamsg_destroy(msg); } @@ -307,7 +307,7 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) && time_after(jiffies, chunk->msg->expires_at)) { struct sctp_stream_out *streamout = - &chunk->asoc->stream->out[chunk->sinfo.sinfo_stream]; + &chunk->asoc->stream.out[chunk->sinfo.sinfo_stream]; if (chunk->sent_count) { chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++; @@ -320,7 +320,7 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) } else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) && chunk->sent_count > chunk->sinfo.sinfo_timetolive) { struct sctp_stream_out *streamout = - &chunk->asoc->stream->out[chunk->sinfo.sinfo_stream]; + &chunk->asoc->stream.out[chunk->sinfo.sinfo_stream]; chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++; streamout->abandoned_sent[SCTP_PR_INDEX(RTX)]++; diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 3dcd0ecf3d99..0e86f988f836 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -90,12 +90,13 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, */ auth_hmacs->param_hdr.type = SCTP_PARAM_HMAC_ALGO; auth_hmacs->param_hdr.length = - htons(sizeof(sctp_paramhdr_t) + 2); + htons(sizeof(struct sctp_paramhdr) + 2); auth_hmacs->hmac_ids[0] = htons(SCTP_AUTH_HMAC_ID_SHA1); /* Initialize the CHUNKS parameter */ auth_chunks->param_hdr.type = SCTP_PARAM_CHUNKS; - auth_chunks->param_hdr.length = htons(sizeof(sctp_paramhdr_t)); + auth_chunks->param_hdr.length = + htons(sizeof(struct sctp_paramhdr)); /* If the Add-IP functionality is enabled, we must * authenticate, ASCONF and ASCONF-ACK chunks @@ -104,7 +105,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, auth_chunks->chunks[0] = SCTP_CID_ASCONF; auth_chunks->chunks[1] = SCTP_CID_ASCONF_ACK; auth_chunks->param_hdr.length = - htons(sizeof(sctp_paramhdr_t) + 2); + htons(sizeof(struct sctp_paramhdr) + 2); } } @@ -113,7 +114,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, ep->base.type = SCTP_EP_TYPE_SOCKET; /* Initialize the basic object fields. */ - atomic_set(&ep->base.refcnt, 1); + refcount_set(&ep->base.refcnt, 1); ep->base.dead = false; /* Create an input queue. */ @@ -268,16 +269,14 @@ static void sctp_endpoint_destroy(struct sctp_endpoint *ep) memset(ep->secret_key, 0, sizeof(ep->secret_key)); - /* Give up our hold on the sock. */ sk = ep->base.sk; - if (sk != NULL) { - /* Remove and free the port */ - if (sctp_sk(sk)->bind_hash) - sctp_put_port(sk); + /* Remove and free the port */ + if (sctp_sk(sk)->bind_hash) + sctp_put_port(sk); - sctp_sk(sk)->ep = NULL; - sock_put(sk); - } + sctp_sk(sk)->ep = NULL; + /* Give up our hold on the sock */ + sock_put(sk); kfree(ep); SCTP_DBG_OBJCNT_DEC(ep); @@ -286,7 +285,7 @@ static void sctp_endpoint_destroy(struct sctp_endpoint *ep) /* Hold a reference to an endpoint. */ void sctp_endpoint_hold(struct sctp_endpoint *ep) { - atomic_inc(&ep->base.refcnt); + refcount_inc(&ep->base.refcnt); } /* Release a reference to an endpoint and clean up if there are @@ -294,7 +293,7 @@ void sctp_endpoint_hold(struct sctp_endpoint *ep) */ void sctp_endpoint_put(struct sctp_endpoint *ep) { - if (atomic_dec_and_test(&ep->base.refcnt)) + if (refcount_dec_and_test(&ep->base.refcnt)) sctp_endpoint_destroy(ep); } diff --git a/net/sctp/input.c b/net/sctp/input.c index ba9ad32fc447..41eb2ec10460 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -663,19 +663,19 @@ out_unlock: */ static int sctp_rcv_ootb(struct sk_buff *skb) { - sctp_chunkhdr_t *ch, _ch; + struct sctp_chunkhdr *ch, _ch; int ch_end, offset = 0; /* Scan through all the chunks in the packet. */ do { /* Make sure we have at least the header there */ - if (offset + sizeof(sctp_chunkhdr_t) > skb->len) + if (offset + sizeof(_ch) > skb->len) break; ch = skb_header_pointer(skb, offset, sizeof(*ch), &_ch); /* Break out if chunk length is less then minimal. */ - if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t)) + if (ntohs(ch->length) < sizeof(_ch)) break; ch_end = offset + SCTP_PAD4(ntohs(ch->length)); @@ -1051,7 +1051,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, union sctp_addr *paddr = &addr; struct sctphdr *sh = sctp_hdr(skb); union sctp_params params; - sctp_init_chunk_t *init; + struct sctp_init_chunk *init; struct sctp_af *af; /* @@ -1070,7 +1070,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, /* Find the start of the TLVs and the end of the chunk. This is * the region we search for address parameters. */ - init = (sctp_init_chunk_t *)skb->data; + init = (struct sctp_init_chunk *)skb->data; /* Walk the parameters looking for embedded addresses. */ sctp_walk_params(params, init, init_hdr.params) { @@ -1106,7 +1106,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, */ static struct sctp_association *__sctp_rcv_asconf_lookup( struct net *net, - sctp_chunkhdr_t *ch, + struct sctp_chunkhdr *ch, const union sctp_addr *laddr, __be16 peer_port, struct sctp_transport **transportp) @@ -1144,7 +1144,7 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, struct sctp_transport **transportp) { struct sctp_association *asoc = NULL; - sctp_chunkhdr_t *ch; + struct sctp_chunkhdr *ch; int have_auth = 0; unsigned int chunk_num = 1; __u8 *ch_end; @@ -1152,10 +1152,10 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, /* Walk through the chunks looking for AUTH or ASCONF chunks * to help us find the association. */ - ch = (sctp_chunkhdr_t *) skb->data; + ch = (struct sctp_chunkhdr *)skb->data; do { /* Break out if chunk length is less then minimal. */ - if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t)) + if (ntohs(ch->length) < sizeof(*ch)) break; ch_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); @@ -1192,7 +1192,7 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, if (asoc) break; - ch = (sctp_chunkhdr_t *) ch_end; + ch = (struct sctp_chunkhdr *)ch_end; chunk_num++; } while (ch_end < skb_tail_pointer(skb)); @@ -1210,7 +1210,7 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, const union sctp_addr *laddr, struct sctp_transport **transportp) { - sctp_chunkhdr_t *ch; + struct sctp_chunkhdr *ch; /* We do not allow GSO frames here as we need to linearize and * then cannot guarantee frame boundaries. This shouldn't be an @@ -1220,7 +1220,7 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) return NULL; - ch = (sctp_chunkhdr_t *) skb->data; + ch = (struct sctp_chunkhdr *)skb->data; /* The code below will attempt to walk the chunk and extract * parameter information. Before we do that, we need to verify diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index f731de3e8428..48392552ee7c 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -99,7 +99,7 @@ void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *chunk) struct sctp_chunkhdr *sctp_inq_peek(struct sctp_inq *queue) { struct sctp_chunk *chunk; - sctp_chunkhdr_t *ch = NULL; + struct sctp_chunkhdr *ch = NULL; chunk = queue->in_progress; /* If there is no more chunks in this packet, say so */ @@ -108,7 +108,7 @@ struct sctp_chunkhdr *sctp_inq_peek(struct sctp_inq *queue) chunk->pdiscard) return NULL; - ch = (sctp_chunkhdr_t *)chunk->chunk_end; + ch = (struct sctp_chunkhdr *)chunk->chunk_end; return ch; } @@ -122,7 +122,7 @@ struct sctp_chunkhdr *sctp_inq_peek(struct sctp_inq *queue) struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) { struct sctp_chunk *chunk; - sctp_chunkhdr_t *ch = NULL; + struct sctp_chunkhdr *ch = NULL; /* The assumption is that we are safe to process the chunks * at this time. @@ -151,7 +151,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) chunk = queue->in_progress = NULL; } else { /* Nothing to do. Next chunk in the packet, please. */ - ch = (sctp_chunkhdr_t *) chunk->chunk_end; + ch = (struct sctp_chunkhdr *)chunk->chunk_end; /* Force chunk->skb->data to chunk->chunk_end. */ skb_pull(chunk->skb, chunk->chunk_end - chunk->skb->data); /* We are guaranteed to pull a SCTP header. */ @@ -195,7 +195,7 @@ next_chunk: new_skb: /* This is the first chunk in the packet. */ - ch = (sctp_chunkhdr_t *) chunk->skb->data; + ch = (struct sctp_chunkhdr *)chunk->skb->data; chunk->singleton = 1; chunk->data_accepted = 0; chunk->pdiscard = 0; @@ -214,11 +214,10 @@ new_skb: chunk->chunk_hdr = ch; chunk->chunk_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); - skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t)); + skb_pull(chunk->skb, sizeof(*ch)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ - if (chunk->chunk_end + sizeof(sctp_chunkhdr_t) < - skb_tail_pointer(chunk->skb)) { + if (chunk->chunk_end + sizeof(*ch) < skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index f5b45b8b8b16..2a186b201ad2 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -252,6 +252,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, fl6->flowi6_proto = IPPROTO_SCTP; if (ipv6_addr_type(&daddr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) fl6->flowi6_oif = daddr->v6.sin6_scope_id; + else if (asoc) + fl6->flowi6_oif = asoc->base.sk->sk_bound_dev_if; pr_debug("%s: dst=%pI6 ", __func__, &fl6->daddr); diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 4f5a2b580aa5..275925b93b29 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -35,6 +35,7 @@ static __le32 sctp_gso_make_checksum(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_NONE; + skb->csum_not_inet = 0; return sctp_compute_cksum(skb, skb_transport_offset(skb)); } @@ -98,6 +99,11 @@ static const struct net_offload sctp6_offload = { }, }; +static const struct skb_checksum_ops crc32c_csum_ops = { + .update = sctp_csum_update, + .combine = sctp_csum_combine, +}; + int __init sctp_offload_init(void) { int ret; @@ -110,6 +116,7 @@ int __init sctp_offload_init(void) if (ret) goto ipv4; + crc32c_csum_stub = &crc32c_csum_ops; return ret; ipv4: diff --git a/net/sctp/output.c b/net/sctp/output.c index 1409a875ad8e..9d8504985744 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -402,7 +402,7 @@ static void sctp_packet_set_owner_w(struct sk_buff *skb, struct sock *sk) * therefore only reserve a single byte to keep socket around until * the packet has been transmitted. */ - atomic_inc(&sk->sk_wmem_alloc); + refcount_inc(&sk->sk_wmem_alloc); } static int sctp_packet_pack(struct sctp_packet *packet, @@ -463,14 +463,13 @@ merge: padding = SCTP_PAD4(chunk->skb->len) - chunk->skb->len; if (padding) - memset(skb_put(chunk->skb, padding), 0, padding); + skb_put_zero(chunk->skb, padding); if (chunk == packet->auth) auth = (struct sctp_auth_chunk *) skb_tail_pointer(nskb); - memcpy(skb_put(nskb, chunk->skb->len), chunk->skb->data, - chunk->skb->len); + skb_put_data(nskb, chunk->skb->data, chunk->skb->len); pr_debug("*** Chunk:%p[%s] %s 0x%x, length:%d, chunk->skb->len:%d, rtt_in_progress:%d\n", chunk, @@ -538,6 +537,7 @@ merge: } else { chksum: head->ip_summed = CHECKSUM_PARTIAL; + head->csum_not_inet = 1; head->csum_start = skb_transport_header(head) - head->head; head->csum_offset = offsetof(struct sctphdr, checksum); } @@ -585,7 +585,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) sctp_packet_set_owner_w(head, sk); /* set sctp header */ - sh = (struct sctphdr *)skb_push(head, sizeof(struct sctphdr)); + sh = skb_push(head, sizeof(struct sctphdr)); skb_reset_transport_header(head); sh->source = htons(packet->source_port); sh->dest = htons(packet->destination_port); @@ -723,8 +723,8 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, /* Check whether this chunk and all the rest of pending data will fit * or delay in hopes of bundling a full sized packet. */ - if (chunk->skb->len + q->out_qlen > - transport->pathmtu - packet->overhead - sizeof(sctp_data_chunk_t) - 4) + if (chunk->skb->len + q->out_qlen > transport->pathmtu - + packet->overhead - sizeof(struct sctp_data_chunk) - 4) /* Enough data queued to fill a packet */ return SCTP_XMIT_OK; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index fe4c3d462f6e..e8762702a313 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -363,7 +363,7 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, sctp_insert_list(&asoc->outqueue.abandoned, &chk->transmitted_list); - streamout = &asoc->stream->out[chk->sinfo.sinfo_stream]; + streamout = &asoc->stream.out[chk->sinfo.sinfo_stream]; asoc->sent_cnt_removable--; asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; streamout->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; @@ -400,9 +400,9 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, q->out_qlen -= chk->skb->len; asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; - if (chk->sinfo.sinfo_stream < asoc->stream->outcnt) { + if (chk->sinfo.sinfo_stream < asoc->stream.outcnt) { struct sctp_stream_out *streamout = - &asoc->stream->out[chk->sinfo.sinfo_stream]; + &asoc->stream.out[chk->sinfo.sinfo_stream]; streamout->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; } @@ -1036,7 +1036,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) /* RFC 2960 6.5 Every DATA chunk MUST carry a valid * stream identifier. */ - if (chunk->sinfo.sinfo_stream >= asoc->stream->outcnt) { + if (chunk->sinfo.sinfo_stream >= asoc->stream.outcnt) { /* Mark as failed send. */ sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM); @@ -1054,7 +1054,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) continue; } - if (asoc->stream->out[sid].state == SCTP_STREAM_CLOSED) { + if (asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) { sctp_outq_head_data(q, chunk); goto sctp_flush_out; } @@ -1102,7 +1102,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk", ntohl(chunk->subh.data_hdr->tsn), chunk->skb ? chunk->skb->head : NULL, chunk->skb ? - atomic_read(&chunk->skb->users) : -1); + refcount_read(&chunk->skb->users) : -1); /* Add the chunk to the packet. */ status = sctp_packet_transmit_chunk(packet, chunk, 0, gfp); diff --git a/net/sctp/proc.c b/net/sctp/proc.c index a0b29d43627f..26b4be6b4172 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -218,8 +218,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) return -ENOMEM; head = &sctp_ep_hashtable[hash]; - local_bh_disable(); - read_lock(&head->lock); + read_lock_bh(&head->lock); sctp_for_each_hentry(epb, &head->chain) { ep = sctp_ep(epb); sk = epb->sk; @@ -234,8 +233,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) sctp_seq_dump_local_addrs(seq, epb); seq_printf(seq, "\n"); } - read_unlock(&head->lock); - local_bh_enable(); + read_unlock_bh(&head->lock); return 0; } @@ -361,11 +359,11 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) sctp_seq_dump_remote_addrs(seq, assoc); seq_printf(seq, "\t%8lu %5d %5d %4d %4d %4d %8d " "%8d %8d %8d %8d", - assoc->hbinterval, assoc->stream->incnt, - assoc->stream->outcnt, assoc->max_retrans, + assoc->hbinterval, assoc->stream.incnt, + assoc->stream.outcnt, assoc->max_retrans, assoc->init_retries, assoc->shutdown_retries, assoc->rtx_data_chunks, - atomic_read(&sk->sk_wmem_alloc), + refcount_read(&sk->sk_wmem_alloc), sk->sk_wmem_queued, sk->sk_sndbuf, sk->sk_rcvbuf); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 92e332e17391..6110447fe51d 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -217,7 +217,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, { struct net *net = sock_net(asoc->base.sk); struct sctp_endpoint *ep = asoc->ep; - sctp_inithdr_t init; + struct sctp_inithdr init; union sctp_params addrs; size_t chunksize; struct sctp_chunk *retval = NULL; @@ -228,8 +228,8 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, sctp_adaptation_ind_param_t aiparam; sctp_supported_ext_param_t ext_param; int num_ext = 0; - __u8 extensions[3]; - sctp_paramhdr_t *auth_chunks = NULL, + __u8 extensions[4]; + struct sctp_paramhdr *auth_chunks = NULL, *auth_hmacs = NULL; /* RFC 2960 3.3.2 Initiation (INIT) (1) @@ -286,14 +286,14 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, chunksize += sizeof(asoc->c.auth_random); /* Add HMACS parameter length if any were defined */ - auth_hmacs = (sctp_paramhdr_t *)asoc->c.auth_hmacs; + auth_hmacs = (struct sctp_paramhdr *)asoc->c.auth_hmacs; if (auth_hmacs->length) chunksize += SCTP_PAD4(ntohs(auth_hmacs->length)); else auth_hmacs = NULL; /* Add CHUNKS parameter length */ - auth_chunks = (sctp_paramhdr_t *)asoc->c.auth_chunks; + auth_chunks = (struct sctp_paramhdr *)asoc->c.auth_chunks; if (auth_chunks->length) chunksize += SCTP_PAD4(ntohs(auth_chunks->length)); else @@ -385,7 +385,7 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk, gfp_t gfp, int unkparam_len) { - sctp_inithdr_t initack; + struct sctp_inithdr initack; struct sctp_chunk *retval; union sctp_params addrs; struct sctp_sock *sp; @@ -396,8 +396,8 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, sctp_adaptation_ind_param_t aiparam; sctp_supported_ext_param_t ext_param; int num_ext = 0; - __u8 extensions[3]; - sctp_paramhdr_t *auth_chunks = NULL, + __u8 extensions[4]; + struct sctp_paramhdr *auth_chunks = NULL, *auth_hmacs = NULL, *auth_random = NULL; @@ -448,16 +448,16 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, chunksize += sizeof(aiparam); if (asoc->peer.auth_capable) { - auth_random = (sctp_paramhdr_t *)asoc->c.auth_random; + auth_random = (struct sctp_paramhdr *)asoc->c.auth_random; chunksize += ntohs(auth_random->length); - auth_hmacs = (sctp_paramhdr_t *)asoc->c.auth_hmacs; + auth_hmacs = (struct sctp_paramhdr *)asoc->c.auth_hmacs; if (auth_hmacs->length) chunksize += SCTP_PAD4(ntohs(auth_hmacs->length)); else auth_hmacs = NULL; - auth_chunks = (sctp_paramhdr_t *)asoc->c.auth_chunks; + auth_chunks = (struct sctp_paramhdr *)asoc->c.auth_chunks; if (auth_chunks->length) chunksize += SCTP_PAD4(ntohs(auth_chunks->length)); else @@ -1085,18 +1085,18 @@ struct sctp_chunk *sctp_make_abort_violation( struct sctp_chunk *retval; struct sctp_paramhdr phdr; - retval = sctp_make_abort(asoc, chunk, sizeof(sctp_errhdr_t) + paylen - + sizeof(sctp_paramhdr_t)); + retval = sctp_make_abort(asoc, chunk, sizeof(sctp_errhdr_t) + paylen + + sizeof(phdr)); if (!retval) goto end; - sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, paylen - + sizeof(sctp_paramhdr_t)); + sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, paylen + + sizeof(phdr)); phdr.type = htons(chunk->chunk_hdr->type); phdr.length = chunk->chunk_hdr->length; sctp_addto_chunk(retval, paylen, payload); - sctp_addto_param(retval, sizeof(sctp_paramhdr_t), &phdr); + sctp_addto_param(retval, sizeof(phdr), &phdr); end: return retval; @@ -1110,16 +1110,16 @@ struct sctp_chunk *sctp_make_violation_paramlen( struct sctp_chunk *retval; static const char error[] = "The following parameter had invalid length:"; size_t payload_len = sizeof(error) + sizeof(sctp_errhdr_t) + - sizeof(sctp_paramhdr_t); + sizeof(*param); retval = sctp_make_abort(asoc, chunk, payload_len); if (!retval) goto nodata; sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, - sizeof(error) + sizeof(sctp_paramhdr_t)); + sizeof(error) + sizeof(*param)); sctp_addto_chunk(retval, sizeof(error), error); - sctp_addto_param(retval, sizeof(sctp_paramhdr_t), param); + sctp_addto_param(retval, sizeof(*param), param); nodata: return retval; @@ -1296,8 +1296,7 @@ struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc) retval->subh.auth_hdr = sctp_addto_chunk(retval, sizeof(sctp_authhdr_t), &auth_hdr); - hmac = skb_put(retval->skb, hmac_desc->hmac_len); - memset(hmac, 0, hmac_desc->hmac_len); + hmac = skb_put_zero(retval->skb, hmac_desc->hmac_len); /* Adjust the chunk header to include the empty MAC */ retval->chunk_hdr->length = @@ -1346,7 +1345,7 @@ struct sctp_chunk *sctp_chunkify(struct sk_buff *skb, INIT_LIST_HEAD(&retval->transmitted_list); INIT_LIST_HEAD(&retval->frag_list); SCTP_DBG_OBJCNT_INC(chunk); - atomic_set(&retval->refcnt, 1); + refcount_set(&retval->refcnt, 1); nodata: return retval; @@ -1380,20 +1379,20 @@ static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc, gfp_t gfp) { struct sctp_chunk *retval; - sctp_chunkhdr_t *chunk_hdr; + struct sctp_chunkhdr *chunk_hdr; struct sk_buff *skb; struct sock *sk; /* No need to allocate LL here, as this is only a chunk. */ - skb = alloc_skb(SCTP_PAD4(sizeof(sctp_chunkhdr_t) + paylen), gfp); + skb = alloc_skb(SCTP_PAD4(sizeof(*chunk_hdr) + paylen), gfp); if (!skb) goto nodata; /* Make room for the chunk header. */ - chunk_hdr = (sctp_chunkhdr_t *)skb_put(skb, sizeof(sctp_chunkhdr_t)); + chunk_hdr = (struct sctp_chunkhdr *)skb_put(skb, sizeof(*chunk_hdr)); chunk_hdr->type = type; chunk_hdr->flags = flags; - chunk_hdr->length = htons(sizeof(sctp_chunkhdr_t)); + chunk_hdr->length = htons(sizeof(*chunk_hdr)); sk = asoc ? asoc->base.sk : NULL; retval = sctp_chunkify(skb, asoc, sk, gfp); @@ -1403,7 +1402,7 @@ static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc, } retval->chunk_hdr = chunk_hdr; - retval->chunk_end = ((__u8 *)chunk_hdr) + sizeof(struct sctp_chunkhdr); + retval->chunk_end = ((__u8 *)chunk_hdr) + sizeof(*chunk_hdr); /* Determine if the chunk needs to be authenticated */ if (sctp_auth_send_cid(type, asoc)) @@ -1459,13 +1458,13 @@ void sctp_chunk_free(struct sctp_chunk *chunk) /* Grab a reference to the chunk. */ void sctp_chunk_hold(struct sctp_chunk *ch) { - atomic_inc(&ch->refcnt); + refcount_inc(&ch->refcnt); } /* Release a reference to the chunk. */ void sctp_chunk_put(struct sctp_chunk *ch) { - if (atomic_dec_and_test(&ch->refcnt)) + if (refcount_dec_and_test(&ch->refcnt)) sctp_chunk_destroy(ch); } @@ -1475,15 +1474,11 @@ void sctp_chunk_put(struct sctp_chunk *ch) void *sctp_addto_chunk(struct sctp_chunk *chunk, int len, const void *data) { void *target; - void *padding; int chunklen = ntohs(chunk->chunk_hdr->length); int padlen = SCTP_PAD4(chunklen) - chunklen; - padding = skb_put(chunk->skb, padlen); - target = skb_put(chunk->skb, len); - - memset(padding, 0, padlen); - memcpy(target, data, len); + skb_put_zero(chunk->skb, padlen); + target = skb_put_data(chunk->skb, data, len); /* Adjust the chunk length field. */ chunk->chunk_hdr->length = htons(chunklen + padlen + len); @@ -1544,7 +1539,7 @@ void sctp_chunk_assign_ssn(struct sctp_chunk *chunk) /* All fragments will be on the same stream */ sid = ntohs(chunk->subh.data_hdr->stream); - stream = chunk->asoc->stream; + stream = &chunk->asoc->stream; /* Now assign the sequence number to the entire message. * All fragments must have the same stream sequence number. @@ -1619,7 +1614,7 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep, /* Header size is static data prior to the actual cookie, including * any padding. */ - headersize = sizeof(sctp_paramhdr_t) + + headersize = sizeof(struct sctp_paramhdr) + (sizeof(struct sctp_signed_cookie) - sizeof(struct sctp_cookie)); bodysize = sizeof(struct sctp_cookie) @@ -1715,7 +1710,7 @@ struct sctp_association *sctp_unpack_cookie( /* Header size is static data prior to the actual cookie, including * any padding. */ - headersize = sizeof(sctp_chunkhdr_t) + + headersize = sizeof(struct sctp_chunkhdr) + (sizeof(struct sctp_signed_cookie) - sizeof(struct sctp_cookie)); bodysize = ntohs(chunk->chunk_hdr->length) - headersize; @@ -1887,7 +1882,7 @@ struct __sctp_missing { * Report a missing mandatory parameter. */ static int sctp_process_missing_param(const struct sctp_association *asoc, - sctp_param_t paramtype, + enum sctp_param paramtype, struct sctp_chunk *chunk, struct sctp_chunk **errp) { @@ -1980,7 +1975,7 @@ static int sctp_process_hn_param(const struct sctp_association *asoc, static int sctp_verify_ext_param(struct net *net, union sctp_params param) { - __u16 num_ext = ntohs(param.p->length) - sizeof(sctp_paramhdr_t); + __u16 num_ext = ntohs(param.p->length) - sizeof(struct sctp_paramhdr); int have_auth = 0; int have_asconf = 0; int i; @@ -2015,7 +2010,7 @@ static void sctp_process_ext_param(struct sctp_association *asoc, union sctp_params param) { struct net *net = sock_net(asoc->base.sk); - __u16 num_ext = ntohs(param.p->length) - sizeof(sctp_paramhdr_t); + __u16 num_ext = ntohs(param.p->length) - sizeof(struct sctp_paramhdr); int i; for (i = 0; i < num_ext; i++) { @@ -2128,7 +2123,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, union sctp_params param, - sctp_cid_t cid, + enum sctp_cid cid, struct sctp_chunk *chunk, struct sctp_chunk **err_chunk) { @@ -2185,7 +2180,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net, * cause 'Protocol Violation'. */ if (SCTP_AUTH_RANDOM_LENGTH != - ntohs(param.p->length) - sizeof(sctp_paramhdr_t)) { + ntohs(param.p->length) - sizeof(struct sctp_paramhdr)) { sctp_process_inv_paramlength(asoc, param.p, chunk, err_chunk); retval = SCTP_IERROR_ABORT; @@ -2213,7 +2208,8 @@ static sctp_ierror_t sctp_verify_param(struct net *net, goto fallthrough; hmacs = (struct sctp_hmac_algo_param *)param.p; - n_elt = (ntohs(param.p->length) - sizeof(sctp_paramhdr_t)) >> 1; + n_elt = (ntohs(param.p->length) - + sizeof(struct sctp_paramhdr)) >> 1; /* SCTP-AUTH: Section 6.1 * The HMAC algorithm based on SHA-1 MUST be supported and @@ -2245,9 +2241,9 @@ fallthrough: /* Verify the INIT packet before we process it. */ int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, - const struct sctp_association *asoc, sctp_cid_t cid, - sctp_init_chunk_t *peer_init, struct sctp_chunk *chunk, - struct sctp_chunk **errp) + const struct sctp_association *asoc, enum sctp_cid cid, + struct sctp_init_chunk *peer_init, + struct sctp_chunk *chunk, struct sctp_chunk **errp) { union sctp_params param; bool has_cookie = false; @@ -2311,7 +2307,7 @@ int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, */ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, const union sctp_addr *peer_addr, - sctp_init_chunk_t *peer_init, gfp_t gfp) + struct sctp_init_chunk *peer_init, gfp_t gfp) { struct net *net = sock_net(asoc->base.sk); union sctp_params param; @@ -2454,7 +2450,8 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, * stream sequence number shall be set to 0. */ - if (sctp_stream_init(asoc, gfp)) + if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, + asoc->c.sinit_max_instreams, gfp)) goto clean_up; if (!asoc->temp && sctp_assoc_set_id(asoc, gfp)) @@ -2569,7 +2566,7 @@ do_addr_param: asoc->peer.ipv4_address = 1; /* Cycle through address types; avoid divide by 0. */ - sat = ntohs(param.p->length) - sizeof(sctp_paramhdr_t); + sat = ntohs(param.p->length) - sizeof(struct sctp_paramhdr); if (sat) sat /= sizeof(__u16); @@ -2596,7 +2593,7 @@ do_addr_param: case SCTP_PARAM_STATE_COOKIE: asoc->peer.cookie_len = - ntohs(param.p->length) - sizeof(sctp_paramhdr_t); + ntohs(param.p->length) - sizeof(struct sctp_paramhdr); asoc->peer.cookie = param.cookie->body; break; @@ -3180,7 +3177,7 @@ bool sctp_verify_asconf(const struct sctp_association *asoc, return false; length = ntohs(param.addip->param_hdr.length); if (length < sizeof(sctp_addip_param_t) + - sizeof(sctp_paramhdr_t)) + sizeof(**errp)) return false; break; case SCTP_PARAM_SUCCESS_REPORT: @@ -3222,7 +3219,8 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, int chunk_len; __u32 serial; - chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(sctp_chunkhdr_t); + chunk_len = ntohs(asconf->chunk_hdr->length) - + sizeof(struct sctp_chunkhdr); hdr = (sctp_addiphdr_t *)asconf->skb->data; serial = ntohl(hdr->serial); @@ -3368,7 +3366,7 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, err_code = SCTP_ERROR_REQ_REFUSED; asconf_ack_len = ntohs(asconf_ack->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t); + sizeof(struct sctp_chunkhdr); /* Skip the addiphdr from the asconf_ack chunk and store a pointer to * the first asconf_ack parameter. diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 25384fa82ba9..d6e5e9e0fd6d 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -647,7 +647,7 @@ static void sctp_cmd_assoc_failed(sctp_cmd_seq_t *commands, static int sctp_cmd_process_init(sctp_cmd_seq_t *commands, struct sctp_association *asoc, struct sctp_chunk *chunk, - sctp_init_chunk_t *peer_init, + struct sctp_init_chunk *peer_init, gfp_t gfp) { int error; @@ -818,6 +818,28 @@ static void sctp_cmd_setup_t2(sctp_cmd_seq_t *cmds, asoc->timeouts[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] = t->rto; } +static void sctp_cmd_assoc_update(sctp_cmd_seq_t *cmds, + struct sctp_association *asoc, + struct sctp_association *new) +{ + struct net *net = sock_net(asoc->base.sk); + struct sctp_chunk *abort; + + if (!sctp_assoc_update(asoc, new)) + return; + + abort = sctp_make_abort(asoc, NULL, sizeof(sctp_errhdr_t)); + if (abort) { + sctp_init_cause(abort, SCTP_ERROR_RSRC_LOW, 0); + sctp_add_cmd_sf(cmds, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); + } + sctp_add_cmd_sf(cmds, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNABORTED)); + sctp_add_cmd_sf(cmds, SCTP_CMD_ASSOC_FAILED, + SCTP_PERR(SCTP_ERROR_RSRC_LOW)); + SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); + SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); +} + /* Helper function to change the state of an association. */ static void sctp_cmd_new_state(sctp_cmd_seq_t *cmds, struct sctp_association *asoc, @@ -933,9 +955,10 @@ static void sctp_cmd_process_operr(sctp_cmd_seq_t *cmds, switch (err_hdr->cause) { case SCTP_ERROR_UNKNOWN_CHUNK: { - sctp_chunkhdr_t *unk_chunk_hdr; + struct sctp_chunkhdr *unk_chunk_hdr; - unk_chunk_hdr = (sctp_chunkhdr_t *)err_hdr->variable; + unk_chunk_hdr = (struct sctp_chunkhdr *) + err_hdr->variable; switch (unk_chunk_hdr->type) { /* ADDIP 4.1 A9) If the peer responds to an ASCONF with * an ERROR chunk reporting that it did not recognized @@ -1294,7 +1317,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, break; case SCTP_CMD_UPDATE_ASSOC: - sctp_assoc_update(asoc, cmd->obj.asoc); + sctp_cmd_assoc_update(commands, asoc, cmd->obj.asoc); break; case SCTP_CMD_PURGE_OUTQUEUE: @@ -1748,6 +1771,10 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, break; case SCTP_CMD_SET_ASOC: + if (asoc && local_cork) { + sctp_outq_uncork(&asoc->outqueue, gfp); + local_cork = 0; + } asoc = cmd->obj.asoc; break; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index f863b5573e42..b2a74c3823ee 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -235,7 +235,7 @@ sctp_disposition_t sctp_sf_do_4_C(struct net *net, return sctp_sf_violation_chunk(net, ep, asoc, type, arg, commands); /* Make sure that the SHUTDOWN_COMPLETE chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -345,7 +345,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, * error, but since we don't have an association, we'll * just discard the packet. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_init_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* If the INIT is coming toward a closing socket, we'll send back @@ -360,7 +360,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, /* Verify the INIT chunk before processing it. */ err_chunk = NULL; if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, - (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, + (struct sctp_init_chunk *)chunk->chunk_hdr, chunk, &err_chunk)) { /* This chunk contains fatal error. It is to be discarded. * Send an ABORT, with causes if there is any. @@ -368,9 +368,9 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, if (err_chunk) { packet = sctp_abort_pkt_new(net, ep, asoc, arg, (__u8 *)(err_chunk->chunk_hdr) + - sizeof(sctp_chunkhdr_t), + sizeof(struct sctp_chunkhdr), ntohs(err_chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t)); + sizeof(struct sctp_chunkhdr)); sctp_chunk_free(err_chunk); @@ -389,10 +389,10 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, } /* Grab the INIT header. */ - chunk->subh.init_hdr = (sctp_inithdr_t *)chunk->skb->data; + chunk->subh.init_hdr = (struct sctp_inithdr *)chunk->skb->data; /* Tag the variable length parameters. */ - chunk->param_hdr.v = skb_pull(chunk->skb, sizeof(sctp_inithdr_t)); + chunk->param_hdr.v = skb_pull(chunk->skb, sizeof(struct sctp_inithdr)); new_asoc = sctp_make_temp_asoc(ep, chunk, GFP_ATOMIC); if (!new_asoc) @@ -405,7 +405,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, /* The call, sctp_process_init(), can fail on memory allocation. */ if (!sctp_process_init(new_asoc, chunk, sctp_source(chunk), - (sctp_init_chunk_t *)chunk->chunk_hdr, + (struct sctp_init_chunk *)chunk->chunk_hdr, GFP_ATOMIC)) goto nomem_init; @@ -417,7 +417,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, len = 0; if (err_chunk) len = ntohs(err_chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t); + sizeof(struct sctp_chunkhdr); repl = sctp_make_init_ack(new_asoc, chunk, GFP_ATOMIC, len); if (!repl) @@ -437,7 +437,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, */ unk_param = (sctp_unrecognized_param_t *) ((__u8 *)(err_chunk->chunk_hdr) + - sizeof(sctp_chunkhdr_t)); + sizeof(struct sctp_chunkhdr)); /* Replace the cause code with the "Unrecognized parameter" * parameter type. */ @@ -503,7 +503,7 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net, sctp_cmd_seq_t *commands) { struct sctp_chunk *chunk = arg; - sctp_init_chunk_t *initchunk; + struct sctp_init_chunk *initchunk; struct sctp_chunk *err_chunk; struct sctp_packet *packet; @@ -522,12 +522,12 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net, return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* Grab the INIT header. */ - chunk->subh.init_hdr = (sctp_inithdr_t *) chunk->skb->data; + chunk->subh.init_hdr = (struct sctp_inithdr *)chunk->skb->data; /* Verify the INIT chunk before processing it. */ err_chunk = NULL; if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, - (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, + (struct sctp_init_chunk *)chunk->chunk_hdr, chunk, &err_chunk)) { sctp_error_t error = SCTP_ERROR_NO_RESOURCE; @@ -540,9 +540,9 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net, if (err_chunk) { packet = sctp_abort_pkt_new(net, ep, asoc, arg, (__u8 *)(err_chunk->chunk_hdr) + - sizeof(sctp_chunkhdr_t), + sizeof(struct sctp_chunkhdr), ntohs(err_chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t)); + sizeof(struct sctp_chunkhdr)); sctp_chunk_free(err_chunk); @@ -576,9 +576,9 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net, /* Tag the variable length parameters. Note that we never * convert the parameters in an INIT chunk. */ - chunk->param_hdr.v = skb_pull(chunk->skb, sizeof(sctp_inithdr_t)); + chunk->param_hdr.v = skb_pull(chunk->skb, sizeof(struct sctp_inithdr)); - initchunk = (sctp_init_chunk_t *) chunk->chunk_hdr; + initchunk = (struct sctp_init_chunk *)chunk->chunk_hdr; sctp_add_cmd_sf(commands, SCTP_CMD_PEER_INIT, SCTP_PEER_INIT(initchunk)); @@ -653,7 +653,7 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, { struct sctp_chunk *chunk = arg; struct sctp_association *new_asoc; - sctp_init_chunk_t *peer_init; + struct sctp_init_chunk *peer_init; struct sctp_chunk *repl; struct sctp_ulpevent *ev, *ai_ev = NULL; int error = 0; @@ -673,7 +673,7 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, * chunk header. More detailed verification is done * in sctp_unpack_cookie(). */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* If the endpoint is not listening or if the number of associations @@ -691,7 +691,7 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, chunk->subh.cookie_hdr = (struct sctp_signed_cookie *)chunk->skb->data; if (!pskb_pull(chunk->skb, ntohs(chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t))) + sizeof(struct sctp_chunkhdr))) goto nomem; /* 5.1 D) Upon reception of the COOKIE ECHO chunk, Endpoint @@ -770,9 +770,10 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, auth.skb = chunk->auth_chunk; auth.asoc = chunk->asoc; auth.sctp_hdr = chunk->sctp_hdr; - auth.chunk_hdr = (sctp_chunkhdr_t *)skb_push(chunk->auth_chunk, - sizeof(sctp_chunkhdr_t)); - skb_pull(chunk->auth_chunk, sizeof(sctp_chunkhdr_t)); + auth.chunk_hdr = (struct sctp_chunkhdr *) + skb_push(chunk->auth_chunk, + sizeof(struct sctp_chunkhdr)); + skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr)); auth.transport = chunk->transport; ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth); @@ -886,7 +887,7 @@ sctp_disposition_t sctp_sf_do_5_1E_ca(struct net *net, /* Verify that the chunk length for the COOKIE-ACK is OK. * If we don't do this, any bundled chunks may be junked. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -1080,7 +1081,7 @@ sctp_disposition_t sctp_sf_beat_8_3(struct net *net, void *arg, sctp_cmd_seq_t *commands) { - sctp_paramhdr_t *param_hdr; + struct sctp_paramhdr *param_hdr; struct sctp_chunk *chunk = arg; struct sctp_chunk *reply; size_t paylen = 0; @@ -1097,9 +1098,9 @@ sctp_disposition_t sctp_sf_beat_8_3(struct net *net, * respond with a HEARTBEAT ACK that contains the Heartbeat * Information field copied from the received HEARTBEAT chunk. */ - chunk->subh.hb_hdr = (sctp_heartbeathdr_t *) chunk->skb->data; - param_hdr = (sctp_paramhdr_t *) chunk->subh.hb_hdr; - paylen = ntohs(chunk->chunk_hdr->length) - sizeof(sctp_chunkhdr_t); + chunk->subh.hb_hdr = (sctp_heartbeathdr_t *)chunk->skb->data; + param_hdr = (struct sctp_paramhdr *)chunk->subh.hb_hdr; + paylen = ntohs(chunk->chunk_hdr->length) - sizeof(struct sctp_chunkhdr); if (ntohs(param_hdr->length) > paylen) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, @@ -1164,7 +1165,7 @@ sctp_disposition_t sctp_sf_backbeat_8_3(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the HEARTBEAT-ACK chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t) + + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr) + sizeof(sctp_sender_hb_info_t))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -1449,19 +1450,19 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( * In this case, we generate a protocol violation since we have * an association established. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_init_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* Grab the INIT header. */ - chunk->subh.init_hdr = (sctp_inithdr_t *) chunk->skb->data; + chunk->subh.init_hdr = (struct sctp_inithdr *)chunk->skb->data; /* Tag the variable length parameters. */ - chunk->param_hdr.v = skb_pull(chunk->skb, sizeof(sctp_inithdr_t)); + chunk->param_hdr.v = skb_pull(chunk->skb, sizeof(struct sctp_inithdr)); /* Verify the INIT chunk before processing it. */ err_chunk = NULL; if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, - (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, + (struct sctp_init_chunk *)chunk->chunk_hdr, chunk, &err_chunk)) { /* This chunk contains fatal error. It is to be discarded. * Send an ABORT, with causes if there is any. @@ -1469,9 +1470,9 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( if (err_chunk) { packet = sctp_abort_pkt_new(net, ep, asoc, arg, (__u8 *)(err_chunk->chunk_hdr) + - sizeof(sctp_chunkhdr_t), + sizeof(struct sctp_chunkhdr), ntohs(err_chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t)); + sizeof(struct sctp_chunkhdr)); if (packet) { sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, @@ -1508,7 +1509,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( * place (local tie-tag and per tie-tag) within the state cookie. */ if (!sctp_process_init(new_asoc, chunk, sctp_source(chunk), - (sctp_init_chunk_t *)chunk->chunk_hdr, + (struct sctp_init_chunk *)chunk->chunk_hdr, GFP_ATOMIC)) goto nomem; @@ -1535,7 +1536,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( len = 0; if (err_chunk) { len = ntohs(err_chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t); + sizeof(struct sctp_chunkhdr); } repl = sctp_make_init_ack(new_asoc, chunk, GFP_ATOMIC, len); @@ -1556,7 +1557,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( */ unk_param = (sctp_unrecognized_param_t *) ((__u8 *)(err_chunk->chunk_hdr) + - sizeof(sctp_chunkhdr_t)); + sizeof(struct sctp_chunkhdr)); /* Replace the cause code with the "Unrecognized parameter" * parameter type. */ @@ -1729,7 +1730,7 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(struct net *net, sctp_cmd_seq_t *commands, struct sctp_association *new_asoc) { - sctp_init_chunk_t *peer_init; + struct sctp_init_chunk *peer_init; struct sctp_ulpevent *ev; struct sctp_chunk *repl; struct sctp_chunk *err; @@ -1844,7 +1845,7 @@ static sctp_disposition_t sctp_sf_do_dupcook_b(struct net *net, sctp_cmd_seq_t *commands, struct sctp_association *new_asoc) { - sctp_init_chunk_t *peer_init; + struct sctp_init_chunk *peer_init; struct sctp_chunk *repl; /* new_asoc is a brand-new association, so these are not yet @@ -2044,7 +2045,7 @@ sctp_disposition_t sctp_sf_do_5_2_4_dupcook(struct net *net, * enough for the chunk header. Cookie length verification is * done later. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -2053,7 +2054,7 @@ sctp_disposition_t sctp_sf_do_5_2_4_dupcook(struct net *net, */ chunk->subh.cookie_hdr = (struct sctp_signed_cookie *)chunk->skb->data; if (!pskb_pull(chunk->skb, ntohs(chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t))) + sizeof(struct sctp_chunkhdr))) goto nomem; /* In RFC 2960 5.2.4 3, if both Verification Tags in the State Cookie @@ -2806,7 +2807,7 @@ sctp_disposition_t sctp_sf_do_9_2_reshutack(struct net *net, struct sctp_chunk *reply; /* Make sure that the chunk has a valid length */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -2989,7 +2990,7 @@ sctp_disposition_t sctp_sf_eat_data_6_2(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_data_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_data_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -3009,7 +3010,8 @@ sctp_disposition_t sctp_sf_eat_data_6_2(struct net *net, return SCTP_DISPOSITION_ABORT; case SCTP_IERROR_PROTO_VIOLATION: return sctp_sf_abort_violation(net, ep, asoc, chunk, commands, - (u8 *)chunk->subh.data_hdr, sizeof(sctp_datahdr_t)); + (u8 *)chunk->subh.data_hdr, + sizeof(struct sctp_datahdr)); default: BUG(); } @@ -3107,7 +3109,7 @@ sctp_disposition_t sctp_sf_eat_data_fast_4_4(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_data_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_data_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -3123,7 +3125,8 @@ sctp_disposition_t sctp_sf_eat_data_fast_4_4(struct net *net, return SCTP_DISPOSITION_ABORT; case SCTP_IERROR_PROTO_VIOLATION: return sctp_sf_abort_violation(net, ep, asoc, chunk, commands, - (u8 *)chunk->subh.data_hdr, sizeof(sctp_datahdr_t)); + (u8 *)chunk->subh.data_hdr, + sizeof(struct sctp_datahdr)); default: BUG(); } @@ -3358,7 +3361,7 @@ sctp_disposition_t sctp_sf_do_9_2_final(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the SHUTDOWN_ACK chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* 10.2 H) SHUTDOWN COMPLETE notification @@ -3435,7 +3438,7 @@ sctp_disposition_t sctp_sf_ootb(struct net *net, { struct sctp_chunk *chunk = arg; struct sk_buff *skb = chunk->skb; - sctp_chunkhdr_t *ch; + struct sctp_chunkhdr *ch; sctp_errhdr_t *err; __u8 *ch_end; int ootb_shut_ack = 0; @@ -3443,10 +3446,10 @@ sctp_disposition_t sctp_sf_ootb(struct net *net, SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES); - ch = (sctp_chunkhdr_t *) chunk->chunk_hdr; + ch = (struct sctp_chunkhdr *)chunk->chunk_hdr; do { /* Report violation if the chunk is less then minimal */ - if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t)) + if (ntohs(ch->length) < sizeof(*ch)) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -3487,7 +3490,7 @@ sctp_disposition_t sctp_sf_ootb(struct net *net, } } - ch = (sctp_chunkhdr_t *) ch_end; + ch = (struct sctp_chunkhdr *)ch_end; } while (ch_end < skb_tail_pointer(skb)); if (ootb_shut_ack) @@ -3560,7 +3563,7 @@ static sctp_disposition_t sctp_sf_shut_8_4_5(struct net *net, /* If the chunk length is invalid, we don't want to process * the reset of the packet. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* We need to discard the rest of the packet to prevent @@ -3591,7 +3594,7 @@ sctp_disposition_t sctp_sf_do_8_5_1_E_sa(struct net *net, struct sctp_chunk *chunk = arg; /* Make sure that the SHUTDOWN_ACK chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -3958,7 +3961,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn(struct net *net, /* Silently discard the chunk if stream-id is not valid */ sctp_walk_fwdtsn(skip, chunk) { - if (ntohs(skip->stream) >= asoc->stream->incnt) + if (ntohs(skip->stream) >= asoc->stream.incnt) goto discard_noforce; } @@ -4029,7 +4032,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn_fast( /* Silently discard the chunk if stream-id is not valid */ sctp_walk_fwdtsn(skip, chunk) { - if (ntohs(skip->stream) >= asoc->stream->incnt) + if (ntohs(skip->stream) >= asoc->stream.incnt) goto gen_shutdown; } @@ -4256,7 +4259,7 @@ sctp_disposition_t sctp_sf_unk_chunk(struct net *net, { struct sctp_chunk *unk_chunk = arg; struct sctp_chunk *err_chunk; - sctp_chunkhdr_t *hdr; + struct sctp_chunkhdr *hdr; pr_debug("%s: processing unknown chunk id:%d\n", __func__, type.chunk); @@ -4267,7 +4270,7 @@ sctp_disposition_t sctp_sf_unk_chunk(struct net *net, * Since we don't know the chunk type, we use a general * chunkhdr structure to make a comparison. */ - if (!sctp_chunk_length_valid(unk_chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(unk_chunk, sizeof(*hdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -4340,7 +4343,7 @@ sctp_disposition_t sctp_sf_discard_chunk(struct net *net, * Since we don't know the chunk type, we use a general * chunkhdr structure to make a comparison. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -4405,7 +4408,7 @@ sctp_disposition_t sctp_sf_violation(struct net *net, struct sctp_chunk *chunk = arg; /* Make sure that the chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -6121,9 +6124,9 @@ static struct sctp_packet *sctp_ootb_pkt_new(struct net *net, switch (chunk->chunk_hdr->type) { case SCTP_CID_INIT: { - sctp_init_chunk_t *init; + struct sctp_init_chunk *init; - init = (sctp_init_chunk_t *)chunk->chunk_hdr; + init = (struct sctp_init_chunk *)chunk->chunk_hdr; vtag = ntohl(init->init_hdr.init_tag); break; } @@ -6196,7 +6199,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, struct sctp_chunk *chunk, sctp_cmd_seq_t *commands) { - sctp_datahdr_t *data_hdr; + struct sctp_datahdr *data_hdr; struct sctp_chunk *err; size_t datalen; sctp_verb_t deliver; @@ -6209,8 +6212,9 @@ static int sctp_eat_data(const struct sctp_association *asoc, u16 sid; u8 ordered = 0; - data_hdr = chunk->subh.data_hdr = (sctp_datahdr_t *)chunk->skb->data; - skb_pull(chunk->skb, sizeof(sctp_datahdr_t)); + data_hdr = (struct sctp_datahdr *)chunk->skb->data; + chunk->subh.data_hdr = data_hdr; + skb_pull(chunk->skb, sizeof(*data_hdr)); tsn = ntohl(data_hdr->tsn); pr_debug("%s: TSN 0x%x\n", __func__, tsn); @@ -6258,7 +6262,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * Actually, allow a little bit of overflow (up to a MTU). */ datalen = ntohs(chunk->chunk_hdr->length); - datalen -= sizeof(sctp_data_chunk_t); + datalen -= sizeof(struct sctp_data_chunk); deliver = SCTP_CMD_CHUNK_ULP; @@ -6365,7 +6369,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * and discard the DATA chunk. */ sid = ntohs(data_hdr->stream); - if (sid >= asoc->stream->incnt) { + if (sid >= asoc->stream.incnt) { /* Mark tsn as received even though we drop it */ sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_TSN, SCTP_U32(tsn)); @@ -6387,7 +6391,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * and is invalid. */ ssn = ntohs(data_hdr->ssn); - if (ordered && SSN_lt(ssn, sctp_ssn_peek(asoc->stream, in, sid))) + if (ordered && SSN_lt(ssn, sctp_ssn_peek(&asoc->stream, in, sid))) return SCTP_IERROR_PROTO_VIOLATION; /* Send the data up to the user. Note: Schedule the diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index 419b18ebb056..3e958c1c4b95 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -53,7 +53,7 @@ static const sctp_sm_table_entry_t timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES]; static const sctp_sm_table_entry_t *sctp_chunk_event_lookup(struct net *net, - sctp_cid_t cid, + enum sctp_cid cid, sctp_state_t state); @@ -968,7 +968,7 @@ static const sctp_sm_table_entry_t timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][S }; static const sctp_sm_table_entry_t *sctp_chunk_event_lookup(struct net *net, - sctp_cid_t cid, + enum sctp_cid cid, sctp_state_t state) { if (state > SCTP_STATE_MAX) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 3a8318e518f1..1db478e34520 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -103,7 +103,7 @@ static int sctp_autobind(struct sock *sk); static void sctp_sock_migrate(struct sock *, struct sock *, struct sctp_association *, sctp_socket_type_t); -static int sctp_memory_pressure; +static unsigned long sctp_memory_pressure; static atomic_long_t sctp_memory_allocated; struct percpu_counter sctp_sockets_allocated; @@ -164,7 +164,7 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk) sizeof(struct sk_buff) + sizeof(struct sctp_chunk); - atomic_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); + refcount_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); sk->sk_wmem_queued += chunk->skb->truesize; sk_mem_charge(sk, chunk->skb->truesize); } @@ -1494,7 +1494,7 @@ static void sctp_close(struct sock *sk, long timeout) pr_debug("%s: sk:%p, timeout:%ld\n", __func__, sk, timeout); - lock_sock(sk); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); sk->sk_shutdown = SHUTDOWN_MASK; sk->sk_state = SCTP_SS_CLOSING; @@ -1544,7 +1544,7 @@ static void sctp_close(struct sock *sk, long timeout) * held and that should be grabbed before socket lock. */ spin_lock_bh(&net->sctp.addr_wq_lock); - bh_lock_sock(sk); + bh_lock_sock_nested(sk); /* Hold the sock, since sk_common_release() will put sock_put() * and we have just a little more cleanup. @@ -1920,7 +1920,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) } /* Check for invalid stream. */ - if (sinfo->sinfo_stream >= asoc->stream->outcnt) { + if (sinfo->sinfo_stream >= asoc->stream.outcnt) { err = -EINVAL; goto out_free; } @@ -4497,8 +4497,8 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, info->sctpi_rwnd = asoc->a_rwnd; info->sctpi_unackdata = asoc->unack_data; info->sctpi_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map); - info->sctpi_instrms = asoc->stream->incnt; - info->sctpi_outstrms = asoc->stream->outcnt; + info->sctpi_instrms = asoc->stream.incnt; + info->sctpi_outstrms = asoc->stream.outcnt; list_for_each(pos, &asoc->base.inqueue.in_chunk_list) info->sctpi_inqueue++; list_for_each(pos, &asoc->outqueue.out_chunk_list) @@ -4726,8 +4726,8 @@ static int sctp_getsockopt_sctp_status(struct sock *sk, int len, status.sstat_unackdata = asoc->unack_data; status.sstat_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map); - status.sstat_instrms = asoc->stream->incnt; - status.sstat_outstrms = asoc->stream->outcnt; + status.sstat_instrms = asoc->stream.incnt; + status.sstat_outstrms = asoc->stream.outcnt; status.sstat_fragmentation_point = asoc->frag_point; status.sstat_primary.spinfo_assoc_id = sctp_assoc2id(transport->asoc); memcpy(&status.sstat_primary.spinfo_address, &transport->ipaddr, @@ -4933,11 +4933,47 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) } EXPORT_SYMBOL(sctp_do_peeloff); +static int sctp_getsockopt_peeloff_common(struct sock *sk, sctp_peeloff_arg_t *peeloff, + struct file **newfile, unsigned flags) +{ + struct socket *newsock; + int retval; + + retval = sctp_do_peeloff(sk, peeloff->associd, &newsock); + if (retval < 0) + goto out; + + /* Map the socket to an unused fd that can be returned to the user. */ + retval = get_unused_fd_flags(flags & SOCK_CLOEXEC); + if (retval < 0) { + sock_release(newsock); + goto out; + } + + *newfile = sock_alloc_file(newsock, 0, NULL); + if (IS_ERR(*newfile)) { + put_unused_fd(retval); + sock_release(newsock); + retval = PTR_ERR(*newfile); + *newfile = NULL; + return retval; + } + + pr_debug("%s: sk:%p, newsk:%p, sd:%d\n", __func__, sk, newsock->sk, + retval); + + peeloff->sd = retval; + + if (flags & SOCK_NONBLOCK) + (*newfile)->f_flags |= O_NONBLOCK; +out: + return retval; +} + static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval, int __user *optlen) { sctp_peeloff_arg_t peeloff; - struct socket *newsock; - struct file *newfile; + struct file *newfile = NULL; int retval = 0; if (len < sizeof(sctp_peeloff_arg_t)) @@ -4946,26 +4982,44 @@ static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval if (copy_from_user(&peeloff, optval, len)) return -EFAULT; - retval = sctp_do_peeloff(sk, peeloff.associd, &newsock); + retval = sctp_getsockopt_peeloff_common(sk, &peeloff, &newfile, 0); if (retval < 0) goto out; - /* Map the socket to an unused fd that can be returned to the user. */ - retval = get_unused_fd_flags(0); - if (retval < 0) { - sock_release(newsock); - goto out; + /* Return the fd mapped to the new socket. */ + if (put_user(len, optlen)) { + fput(newfile); + put_unused_fd(retval); + return -EFAULT; } - newfile = sock_alloc_file(newsock, 0, NULL); - if (IS_ERR(newfile)) { + if (copy_to_user(optval, &peeloff, len)) { + fput(newfile); put_unused_fd(retval); - sock_release(newsock); - return PTR_ERR(newfile); + return -EFAULT; } + fd_install(retval, newfile); +out: + return retval; +} - pr_debug("%s: sk:%p, newsk:%p, sd:%d\n", __func__, sk, newsock->sk, - retval); +static int sctp_getsockopt_peeloff_flags(struct sock *sk, int len, + char __user *optval, int __user *optlen) +{ + sctp_peeloff_flags_arg_t peeloff; + struct file *newfile = NULL; + int retval = 0; + + if (len < sizeof(sctp_peeloff_flags_arg_t)) + return -EINVAL; + len = sizeof(sctp_peeloff_flags_arg_t); + if (copy_from_user(&peeloff, optval, len)) + return -EFAULT; + + retval = sctp_getsockopt_peeloff_common(sk, &peeloff.p_arg, + &newfile, peeloff.flags); + if (retval < 0) + goto out; /* Return the fd mapped to the new socket. */ if (put_user(len, optlen)) { @@ -4973,7 +5027,7 @@ static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval put_unused_fd(retval); return -EFAULT; } - peeloff.sd = retval; + if (copy_to_user(optval, &peeloff, len)) { fput(newfile); put_unused_fd(retval); @@ -6033,7 +6087,8 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, return -EACCES; hmacs = ep->auth_hmacs_list; - data_len = ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t); + data_len = ntohs(hmacs->param_hdr.length) - + sizeof(struct sctp_paramhdr); if (len < sizeof(struct sctp_hmacalgo) + data_len) return -EINVAL; @@ -6117,7 +6172,7 @@ static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, goto num; /* See if the user provided enough room for all the data */ - num_chunks = ntohs(ch->param_hdr.length) - sizeof(sctp_paramhdr_t); + num_chunks = ntohs(ch->param_hdr.length) - sizeof(struct sctp_paramhdr); if (len < num_chunks) return -EINVAL; @@ -6165,7 +6220,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, if (!ch) goto num; - num_chunks = ntohs(ch->param_hdr.length) - sizeof(sctp_paramhdr_t); + num_chunks = ntohs(ch->param_hdr.length) - sizeof(struct sctp_paramhdr); if (len < sizeof(struct sctp_authchunks) + num_chunks) return -EINVAL; @@ -6599,10 +6654,10 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, params.sprstat_assoc_id); - if (!asoc || params.sprstat_sid >= asoc->stream->outcnt) + if (!asoc || params.sprstat_sid >= asoc->stream.outcnt) goto out; - streamout = &asoc->stream->out[params.sprstat_sid]; + streamout = &asoc->stream.out[params.sprstat_sid]; if (policy == SCTP_PR_SCTP_NONE) { params.sprstat_abandoned_unsent = 0; params.sprstat_abandoned_sent = 0; @@ -6758,6 +6813,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, case SCTP_SOCKOPT_PEELOFF: retval = sctp_getsockopt_peeloff(sk, len, optval, optlen); break; + case SCTP_SOCKOPT_PEELOFF_FLAGS: + retval = sctp_getsockopt_peeloff_flags(sk, len, optval, optlen); + break; case SCTP_PEER_ADDR_PARAMS: retval = sctp_getsockopt_peer_addr_params(sk, len, optval, optlen); @@ -7563,7 +7621,7 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags, if (flags & MSG_PEEK) { skb = skb_peek(&sk->sk_receive_queue); if (skb) - atomic_inc(&skb->users); + refcount_inc(&skb->users); } else { skb = __skb_dequeue(&sk->sk_receive_queue); } @@ -7684,7 +7742,7 @@ static void sctp_wfree(struct sk_buff *skb) sizeof(struct sk_buff) + sizeof(struct sctp_chunk); - atomic_sub(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc)); /* * This undoes what is done via sctp_set_owner_w and sk_mem_charge diff --git a/net/sctp/stream.c b/net/sctp/stream.c index dda53a293986..63ea15503714 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -35,70 +35,43 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> -int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp) +int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, + gfp_t gfp) { - struct sctp_stream *stream; - int i; - - stream = kzalloc(sizeof(*stream), gfp); - if (!stream) - return -ENOMEM; - - stream->outcnt = asoc->c.sinit_num_ostreams; - stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp); - if (!stream->out) { - kfree(stream); - return -ENOMEM; - } - for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; - - asoc->stream = stream; - - return 0; -} - -int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp) -{ - struct sctp_stream *stream = asoc->stream; int i; /* Initial stream->out size may be very big, so free it and alloc * a new one with new outcnt to save memory. */ kfree(stream->out); - stream->outcnt = asoc->c.sinit_num_ostreams; - stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp); + + stream->out = kcalloc(outcnt, sizeof(*stream->out), gfp); if (!stream->out) - goto nomem; + return -ENOMEM; + stream->outcnt = outcnt; for (i = 0; i < stream->outcnt; i++) stream->out[i].state = SCTP_STREAM_OPEN; - stream->incnt = asoc->c.sinit_max_instreams; - stream->in = kcalloc(stream->incnt, sizeof(*stream->in), gfp); + if (!incnt) + return 0; + + stream->in = kcalloc(incnt, sizeof(*stream->in), gfp); if (!stream->in) { kfree(stream->out); - goto nomem; + stream->out = NULL; + return -ENOMEM; } - return 0; - -nomem: - asoc->stream = NULL; - kfree(stream); + stream->incnt = incnt; - return -ENOMEM; + return 0; } void sctp_stream_free(struct sctp_stream *stream) { - if (unlikely(!stream)) - return; - kfree(stream->out); kfree(stream->in); - kfree(stream); } void sctp_stream_clear(struct sctp_stream *stream) @@ -112,6 +85,19 @@ void sctp_stream_clear(struct sctp_stream *stream) stream->in[i].ssn = 0; } +void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) +{ + sctp_stream_free(stream); + + stream->out = new->out; + stream->in = new->in; + stream->outcnt = new->outcnt; + stream->incnt = new->incnt; + + new->out = NULL; + new->in = NULL; +} + static int sctp_send_reconf(struct sctp_association *asoc, struct sctp_chunk *chunk) { @@ -128,7 +114,7 @@ static int sctp_send_reconf(struct sctp_association *asoc, int sctp_send_reset_streams(struct sctp_association *asoc, struct sctp_reset_streams *params) { - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u16 i, str_nums, *str_list; struct sctp_chunk *chunk; int retval = -EINVAL; @@ -214,6 +200,7 @@ out: int sctp_send_reset_assoc(struct sctp_association *asoc) { + struct sctp_stream *stream = &asoc->stream; struct sctp_chunk *chunk = NULL; int retval; __u16 i; @@ -230,8 +217,8 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) return -ENOMEM; /* Block further xmit of data until this request is completed */ - for (i = 0; i < asoc->stream->outcnt; i++) - asoc->stream->out[i].state = SCTP_STREAM_CLOSED; + for (i = 0; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_CLOSED; asoc->strreset_chunk = chunk; sctp_chunk_hold(asoc->strreset_chunk); @@ -241,8 +228,8 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) sctp_chunk_put(asoc->strreset_chunk); asoc->strreset_chunk = NULL; - for (i = 0; i < asoc->stream->outcnt; i++) - asoc->stream->out[i].state = SCTP_STREAM_OPEN; + for (i = 0; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_OPEN; return retval; } @@ -255,7 +242,7 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) int sctp_send_add_streams(struct sctp_association *asoc, struct sctp_add_streams *params) { - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; struct sctp_chunk *chunk = NULL; int retval = -ENOMEM; __u32 outcnt, incnt; @@ -317,7 +304,7 @@ out: return retval; } -static sctp_paramhdr_t *sctp_chunk_lookup_strreset_param( +static struct sctp_paramhdr *sctp_chunk_lookup_strreset_param( struct sctp_association *asoc, __u32 resp_seq, __be16 type) { @@ -357,7 +344,7 @@ struct sctp_chunk *sctp_process_strreset_outreq( struct sctp_ulpevent **evp) { struct sctp_strreset_outreq *outreq = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u16 i, nums, flags = 0, *str_p = NULL; __u32 result = SCTP_STRRESET_DENIED; __u32 request_seq; @@ -449,7 +436,7 @@ struct sctp_chunk *sctp_process_strreset_inreq( struct sctp_ulpevent **evp) { struct sctp_strreset_inreq *inreq = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; struct sctp_chunk *chunk = NULL; __u16 i, nums, *str_p; @@ -523,7 +510,7 @@ struct sctp_chunk *sctp_process_strreset_tsnreq( { __u32 init_tsn = 0, next_tsn = 0, max_tsn_seen; struct sctp_strreset_tsnreq *tsnreq = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; __u32 request_seq; __u16 i; @@ -612,7 +599,7 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( struct sctp_ulpevent **evp) { struct sctp_strreset_addstrm *addstrm = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; struct sctp_stream_in *streamin; __u32 request_seq, incnt; @@ -687,7 +674,7 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in( struct sctp_ulpevent **evp) { struct sctp_strreset_addstrm *addstrm = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; struct sctp_stream_out *streamout; struct sctp_chunk *chunk = NULL; @@ -758,11 +745,11 @@ struct sctp_chunk *sctp_process_strreset_resp( union sctp_params param, struct sctp_ulpevent **evp) { + struct sctp_stream *stream = &asoc->stream; struct sctp_strreset_resp *resp = param.v; - struct sctp_stream *stream = asoc->stream; struct sctp_transport *t; __u16 i, nums, flags = 0; - sctp_paramhdr_t *req; + struct sctp_paramhdr *req; __u32 result; req = sctp_chunk_lookup_strreset_param(asoc, resp->response_seq, 0); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 721eeebfcd8a..80a97c8501a7 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -99,7 +99,7 @@ static struct sctp_transport *sctp_transport_init(struct net *net, /* Initialize the 64-bit random nonce sent with heartbeat. */ get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce)); - atomic_set(&peer->refcnt, 1); + refcount_set(&peer->refcnt, 1); return peer; } @@ -172,7 +172,7 @@ static void sctp_transport_destroy_rcu(struct rcu_head *head) */ static void sctp_transport_destroy(struct sctp_transport *transport) { - if (unlikely(atomic_read(&transport->refcnt))) { + if (unlikely(refcount_read(&transport->refcnt))) { WARN(1, "Attempt to destroy undead transport %p!\n", transport); return; } @@ -311,7 +311,7 @@ void sctp_transport_route(struct sctp_transport *transport, /* Hold a reference to a transport. */ int sctp_transport_hold(struct sctp_transport *transport) { - return atomic_add_unless(&transport->refcnt, 1, 0); + return refcount_inc_not_zero(&transport->refcnt); } /* Release a reference to a transport and clean up @@ -319,7 +319,7 @@ int sctp_transport_hold(struct sctp_transport *transport) */ void sctp_transport_put(struct sctp_transport *transport) { - if (atomic_dec_and_test(&transport->refcnt)) + if (refcount_dec_and_test(&transport->refcnt)) sctp_transport_destroy(transport); } @@ -405,14 +405,6 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport, TSN_lte(asoc->fast_recovery_exit, sack_ctsn)) asoc->fast_recovery = 0; - /* The appropriate cwnd increase algorithm is performed if, and only - * if the cumulative TSN whould advanced and the congestion window is - * being fully utilized. - */ - if (TSN_lte(sack_ctsn, transport->asoc->ctsn_ack_point) || - (flight_size < cwnd)) - return; - ssthresh = transport->ssthresh; pba = transport->partial_bytes_acked; pmtu = transport->asoc->pathmtu; @@ -435,6 +427,14 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport, if (asoc->fast_recovery) return; + /* The appropriate cwnd increase algorithm is performed + * if, and only if the congestion window is being fully + * utilized. Note that RFC4960 Errata 3.22 removed the + * other condition on ctsn moving. + */ + if (flight_size < cwnd) + return; + if (bytes_acked > pmtu) cwnd += pmtu; else @@ -446,23 +446,33 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport, flight_size, pba); } else { /* RFC 2960 7.2.2 Whenever cwnd is greater than ssthresh, - * upon each SACK arrival that advances the Cumulative TSN Ack - * Point, increase partial_bytes_acked by the total number of - * bytes of all new chunks acknowledged in that SACK including - * chunks acknowledged by the new Cumulative TSN Ack and by - * Gap Ack Blocks. + * upon each SACK arrival, increase partial_bytes_acked + * by the total number of bytes of all new chunks + * acknowledged in that SACK including chunks + * acknowledged by the new Cumulative TSN Ack and by Gap + * Ack Blocks. (updated by RFC4960 Errata 3.22) + * + * When partial_bytes_acked is greater than cwnd and + * before the arrival of the SACK the sender had less + * bytes of data outstanding than cwnd (i.e., before + * arrival of the SACK, flightsize was less than cwnd), + * reset partial_bytes_acked to cwnd. (RFC 4960 Errata + * 3.26) * - * When partial_bytes_acked is equal to or greater than cwnd - * and before the arrival of the SACK the sender had cwnd or - * more bytes of data outstanding (i.e., before arrival of the - * SACK, flightsize was greater than or equal to cwnd), - * increase cwnd by MTU, and reset partial_bytes_acked to - * (partial_bytes_acked - cwnd). + * When partial_bytes_acked is equal to or greater than + * cwnd and before the arrival of the SACK the sender + * had cwnd or more bytes of data outstanding (i.e., + * before arrival of the SACK, flightsize was greater + * than or equal to cwnd), partial_bytes_acked is reset + * to (partial_bytes_acked - cwnd). Next, cwnd is + * increased by MTU. (RFC 4960 Errata 3.12) */ pba += bytes_acked; - if (pba >= cwnd) { + if (pba > cwnd && flight_size < cwnd) + pba = cwnd; + if (pba >= cwnd && flight_size >= cwnd) { + pba = pba - cwnd; cwnd += pmtu; - pba = ((cwnd < pba) ? (pba - cwnd) : 0); } pr_debug("%s: congestion avoidance: transport:%p, " @@ -559,6 +569,8 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport, */ transport->cwnd = max(transport->cwnd/2, 4*asoc->pathmtu); + /* RFC 4960 Errata 3.27.2: also adjust sshthresh */ + transport->ssthresh = transport->cwnd; break; } diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index ec2b3e013c2f..5f86c5062a98 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -153,13 +153,12 @@ struct sctp_ulpevent *sctp_ulpevent_make_assoc_change( sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize); /* Include the notification structure */ - sac = (struct sctp_assoc_change *) - skb_push(skb, sizeof(struct sctp_assoc_change)); + sac = skb_push(skb, sizeof(struct sctp_assoc_change)); /* Trim the buffer to the right length. */ skb_trim(skb, sizeof(struct sctp_assoc_change) + ntohs(chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t)); + sizeof(struct sctp_chunkhdr)); } else { event = sctp_ulpevent_new(sizeof(struct sctp_assoc_change), MSG_NOTIFICATION, gfp); @@ -167,8 +166,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_assoc_change( goto fail; skb = sctp_event2skb(event); - sac = (struct sctp_assoc_change *) skb_put(skb, - sizeof(struct sctp_assoc_change)); + sac = skb_put(skb, sizeof(struct sctp_assoc_change)); } /* Socket Extensions for SCTP @@ -270,8 +268,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_peer_addr_change( goto fail; skb = sctp_event2skb(event); - spc = (struct sctp_paddr_change *) - skb_put(skb, sizeof(struct sctp_paddr_change)); + spc = skb_put(skb, sizeof(struct sctp_paddr_change)); /* Sockets API Extensions for SCTP * Section 5.3.1.2 SCTP_PEER_ADDR_CHANGE @@ -402,7 +399,7 @@ sctp_ulpevent_make_remote_error(const struct sctp_association *asoc, event = sctp_skb2event(skb); sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize); - sre = (struct sctp_remote_error *) skb_push(skb, sizeof(*sre)); + sre = skb_push(skb, sizeof(*sre)); /* Trim the buffer to the right length. */ skb_trim(skb, sizeof(*sre) + elen); @@ -453,8 +450,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_send_failed( event = sctp_skb2event(skb); sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize); - ssf = (struct sctp_send_failed *) - skb_push(skb, sizeof(struct sctp_send_failed)); + ssf = skb_push(skb, sizeof(struct sctp_send_failed)); /* Socket Extensions for SCTP * 5.3.1.4 SCTP_SEND_FAILED @@ -549,8 +545,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_shutdown_event( goto fail; skb = sctp_event2skb(event); - sse = (struct sctp_shutdown_event *) - skb_put(skb, sizeof(struct sctp_shutdown_event)); + sse = skb_put(skb, sizeof(struct sctp_shutdown_event)); /* Socket Extensions for SCTP * 5.3.1.5 SCTP_SHUTDOWN_EVENT @@ -612,8 +607,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_adaptation_indication( goto fail; skb = sctp_event2skb(event); - sai = (struct sctp_adaptation_event *) - skb_put(skb, sizeof(struct sctp_adaptation_event)); + sai = skb_put(skb, sizeof(struct sctp_adaptation_event)); sai->sai_type = SCTP_ADAPTATION_INDICATION; sai->sai_flags = 0; @@ -751,8 +745,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_pdapi( goto fail; skb = sctp_event2skb(event); - pd = (struct sctp_pdapi_event *) - skb_put(skb, sizeof(struct sctp_pdapi_event)); + pd = skb_put(skb, sizeof(struct sctp_pdapi_event)); /* pdapi_type * It should be SCTP_PARTIAL_DELIVERY_EVENT @@ -803,8 +796,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_authkey( goto fail; skb = sctp_event2skb(event); - ak = (struct sctp_authkey_event *) - skb_put(skb, sizeof(struct sctp_authkey_event)); + ak = skb_put(skb, sizeof(struct sctp_authkey_event)); ak->auth_type = SCTP_AUTHENTICATION_EVENT; ak->auth_flags = 0; @@ -842,8 +834,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_sender_dry_event( return NULL; skb = sctp_event2skb(event); - sdry = (struct sctp_sender_dry_event *) - skb_put(skb, sizeof(struct sctp_sender_dry_event)); + sdry = skb_put(skb, sizeof(struct sctp_sender_dry_event)); sdry->sender_dry_type = SCTP_SENDER_DRY_EVENT; sdry->sender_dry_flags = 0; @@ -869,7 +860,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event( return NULL; skb = sctp_event2skb(event); - sreset = (struct sctp_stream_reset_event *)skb_put(skb, length); + sreset = skb_put(skb, length); sreset->strreset_type = SCTP_STREAM_RESET_EVENT; sreset->strreset_flags = flags; @@ -897,8 +888,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event( return NULL; skb = sctp_event2skb(event); - areset = (struct sctp_assoc_reset_event *) - skb_put(skb, sizeof(struct sctp_assoc_reset_event)); + areset = skb_put(skb, sizeof(struct sctp_assoc_reset_event)); areset->assocreset_type = SCTP_ASSOC_RESET_EVENT; areset->assocreset_flags = flags; @@ -925,8 +915,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_stream_change_event( return NULL; skb = sctp_event2skb(event); - schange = (struct sctp_stream_change_event *) - skb_put(skb, sizeof(struct sctp_stream_change_event)); + schange = skb_put(skb, sizeof(struct sctp_stream_change_event)); schange->strchange_type = SCTP_STREAM_CHANGE_EVENT; schange->strchange_flags = flags; diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index aa3624d50278..0225d62a869f 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -764,7 +764,7 @@ static void sctp_ulpq_retrieve_ordered(struct sctp_ulpq *ulpq, __u16 sid, csid, cssn; sid = event->stream; - stream = ulpq->asoc->stream; + stream = &ulpq->asoc->stream; event_list = (struct sk_buff_head *) sctp_event2skb(event)->prev; @@ -858,7 +858,7 @@ static struct sctp_ulpevent *sctp_ulpq_order(struct sctp_ulpq *ulpq, /* Note: The stream ID must be verified before this routine. */ sid = event->stream; ssn = event->ssn; - stream = ulpq->asoc->stream; + stream = &ulpq->asoc->stream; /* Is this the expected SSN for this stream ID? */ if (ssn != sctp_ssn_peek(stream, in, sid)) { @@ -893,7 +893,7 @@ static void sctp_ulpq_reap_ordered(struct sctp_ulpq *ulpq, __u16 sid) struct sk_buff_head *lobby = &ulpq->lobby; __u16 csid, cssn; - stream = ulpq->asoc->stream; + stream = &ulpq->asoc->stream; /* We are holding the chunks by stream, by SSN. */ skb_queue_head_init(&temp); @@ -958,7 +958,7 @@ void sctp_ulpq_skip(struct sctp_ulpq *ulpq, __u16 sid, __u16 ssn) struct sctp_stream *stream; /* Note: The stream ID must be verified before this routine. */ - stream = ulpq->asoc->stream; + stream = &ulpq->asoc->stream; /* Is this an old SSN? If so ignore. */ if (SSN_lt(ssn, sctp_ssn_peek(stream, in, sid))) @@ -1090,7 +1090,7 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, if (chunk) { needed = ntohs(chunk->chunk_hdr->length); - needed -= sizeof(sctp_data_chunk_t); + needed -= sizeof(struct sctp_data_chunk); } else needed = SCTP_DEFAULT_MAXWINDOW; diff --git a/net/socket.c b/net/socket.c index c2564eb25c6b..bf2122691fba 100644 --- a/net/socket.c +++ b/net/socket.c @@ -461,7 +461,7 @@ EXPORT_SYMBOL(sock_from_file); * @err: pointer to an error code return * * The file handle passed in is locked and the socket it is bound - * too is returned. If an error occurs the err pointer is overwritten + * to is returned. If an error occurs the err pointer is overwritten * with a negative errno code and NULL is returned. The function checks * for both invalid handles and passing a handle which is not a socket. * @@ -662,6 +662,40 @@ static bool skb_is_err_queue(const struct sk_buff *skb) return skb->pkt_type == PACKET_OUTGOING; } +/* On transmit, software and hardware timestamps are returned independently. + * As the two skb clones share the hardware timestamp, which may be updated + * before the software timestamp is received, a hardware TX timestamp may be + * returned only if there is no software TX timestamp. Ignore false software + * timestamps, which may be made in the __sock_recv_timestamp() call when the + * option SO_TIMESTAMP(NS) is enabled on the socket, even when the skb has a + * hardware timestamp. + */ +static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp) +{ + return skb->tstamp && !false_tstamp && skb_is_err_queue(skb); +} + +static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb) +{ + struct scm_ts_pktinfo ts_pktinfo; + struct net_device *orig_dev; + + if (!skb_mac_header_was_set(skb)) + return; + + memset(&ts_pktinfo, 0, sizeof(ts_pktinfo)); + + rcu_read_lock(); + orig_dev = dev_get_by_napi_id(skb_napi_id(skb)); + if (orig_dev) + ts_pktinfo.if_index = orig_dev->ifindex; + rcu_read_unlock(); + + ts_pktinfo.pkt_length = skb->len - skb_mac_offset(skb); + put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_PKTINFO, + sizeof(ts_pktinfo), &ts_pktinfo); +} + /* * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP) */ @@ -670,14 +704,16 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, { int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); struct scm_timestamping tss; - int empty = 1; + int empty = 1, false_tstamp = 0; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); /* Race occurred between timestamp enabling and packet receiving. Fill in the current time for now. */ - if (need_software_tstamp && skb->tstamp == 0) + if (need_software_tstamp && skb->tstamp == 0) { __net_timestamp(skb); + false_tstamp = 1; + } if (need_software_tstamp) { if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) { @@ -699,8 +735,13 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, empty = 0; if (shhwtstamps && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && - ktime_to_timespec_cond(shhwtstamps->hwtstamp, tss.ts + 2)) + !skb_is_swtx_tstamp(skb, false_tstamp) && + ktime_to_timespec_cond(shhwtstamps->hwtstamp, tss.ts + 2)) { empty = 0; + if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && + !skb_is_err_queue(skb)) + put_ts_pktinfo(msg, skb); + } if (!empty) { put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING, sizeof(tss), &tss); @@ -950,8 +991,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = -EFAULT; if (get_user(pid, (int __user *)argp)) break; - f_setown(sock->file, pid, 1); - err = 0; + err = f_setown(sock->file, pid, 1); break; case FIOGETOWN: case SIOCGPGRP: @@ -1870,22 +1910,18 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, struct sockaddr __user **save_addr, struct iovec **iov) { - struct sockaddr __user *uaddr; - struct iovec __user *uiov; - size_t nr_segs; + struct user_msghdr msg; ssize_t err; - if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) || - __get_user(uaddr, &umsg->msg_name) || - __get_user(kmsg->msg_namelen, &umsg->msg_namelen) || - __get_user(uiov, &umsg->msg_iov) || - __get_user(nr_segs, &umsg->msg_iovlen) || - __get_user(kmsg->msg_control, &umsg->msg_control) || - __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || - __get_user(kmsg->msg_flags, &umsg->msg_flags)) + if (copy_from_user(&msg, umsg, sizeof(*umsg))) return -EFAULT; - if (!uaddr) + kmsg->msg_control = msg.msg_control; + kmsg->msg_controllen = msg.msg_controllen; + kmsg->msg_flags = msg.msg_flags; + + kmsg->msg_namelen = msg.msg_namelen; + if (!msg.msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) @@ -1895,11 +1931,11 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, kmsg->msg_namelen = sizeof(struct sockaddr_storage); if (save_addr) - *save_addr = uaddr; + *save_addr = msg.msg_name; - if (uaddr && kmsg->msg_namelen) { + if (msg.msg_name && kmsg->msg_namelen) { if (!save_addr) { - err = move_addr_to_kernel(uaddr, kmsg->msg_namelen, + err = move_addr_to_kernel(msg.msg_name, kmsg->msg_namelen, kmsg->msg_name); if (err < 0) return err; @@ -1909,12 +1945,13 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, kmsg->msg_namelen = 0; } - if (nr_segs > UIO_MAXIOV) + if (msg.msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; - return import_iovec(save_addr ? READ : WRITE, uiov, nr_segs, + return import_iovec(save_addr ? READ : WRITE, + msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV, iov, &kmsg->msg_iter); } diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 4f16953e4954..9463af4b32e8 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -117,14 +117,14 @@ static const struct rpc_pipe_ops gss_upcall_ops_v1; static inline struct gss_cl_ctx * gss_get_ctx(struct gss_cl_ctx *ctx) { - atomic_inc(&ctx->count); + refcount_inc(&ctx->count); return ctx; } static inline void gss_put_ctx(struct gss_cl_ctx *ctx) { - if (atomic_dec_and_test(&ctx->count)) + if (refcount_dec_and_test(&ctx->count)) gss_free_ctx(ctx); } @@ -200,7 +200,7 @@ gss_alloc_context(void) ctx->gc_proc = RPC_GSS_PROC_DATA; ctx->gc_seq = 1; /* NetApp 6.4R1 doesn't accept seq. no. 0 */ spin_lock_init(&ctx->gc_seq_lock); - atomic_set(&ctx->count,1); + refcount_set(&ctx->count,1); } return ctx; } @@ -287,7 +287,7 @@ err: #define UPCALL_BUF_LEN 128 struct gss_upcall_msg { - atomic_t count; + refcount_t count; kuid_t uid; struct rpc_pipe_msg msg; struct list_head list; @@ -328,7 +328,7 @@ static void gss_release_msg(struct gss_upcall_msg *gss_msg) { struct net *net = gss_msg->auth->net; - if (!atomic_dec_and_test(&gss_msg->count)) + if (!refcount_dec_and_test(&gss_msg->count)) return; put_pipe_version(net); BUG_ON(!list_empty(&gss_msg->list)); @@ -348,7 +348,7 @@ __gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid, const struct gss_auth *auth continue; if (auth && pos->auth->service != auth->service) continue; - atomic_inc(&pos->count); + refcount_inc(&pos->count); dprintk("RPC: %s found msg %p\n", __func__, pos); return pos; } @@ -369,7 +369,7 @@ gss_add_msg(struct gss_upcall_msg *gss_msg) spin_lock(&pipe->lock); old = __gss_find_upcall(pipe, gss_msg->uid, gss_msg->auth); if (old == NULL) { - atomic_inc(&gss_msg->count); + refcount_inc(&gss_msg->count); list_add(&gss_msg->list, &pipe->in_downcall); } else gss_msg = old; @@ -383,7 +383,7 @@ __gss_unhash_msg(struct gss_upcall_msg *gss_msg) list_del_init(&gss_msg->list); rpc_wake_up_status(&gss_msg->rpc_waitqueue, gss_msg->msg.errno); wake_up_all(&gss_msg->waitqueue); - atomic_dec(&gss_msg->count); + refcount_dec(&gss_msg->count); } static void @@ -506,7 +506,7 @@ gss_alloc_msg(struct gss_auth *gss_auth, INIT_LIST_HEAD(&gss_msg->list); rpc_init_wait_queue(&gss_msg->rpc_waitqueue, "RPCSEC_GSS upcall waitq"); init_waitqueue_head(&gss_msg->waitqueue); - atomic_set(&gss_msg->count, 1); + refcount_set(&gss_msg->count, 1); gss_msg->uid = uid; gss_msg->auth = gss_auth; switch (vers) { @@ -542,11 +542,11 @@ gss_setup_upcall(struct gss_auth *gss_auth, struct rpc_cred *cred) gss_msg = gss_add_msg(gss_new); if (gss_msg == gss_new) { int res; - atomic_inc(&gss_msg->count); + refcount_inc(&gss_msg->count); res = rpc_queue_upcall(gss_new->pipe, &gss_new->msg); if (res) { gss_unhash_msg(gss_new); - atomic_dec(&gss_msg->count); + refcount_dec(&gss_msg->count); gss_release_msg(gss_new); gss_msg = ERR_PTR(res); } @@ -595,7 +595,7 @@ gss_refresh_upcall(struct rpc_task *task) task->tk_timeout = 0; gss_cred->gc_upcall = gss_msg; /* gss_upcall_callback will release the reference to gss_upcall_msg */ - atomic_inc(&gss_msg->count); + refcount_inc(&gss_msg->count); rpc_sleep_on(&gss_msg->rpc_waitqueue, task, gss_upcall_callback); } else { gss_handle_downcall_result(gss_cred, gss_msg); @@ -815,7 +815,7 @@ restart: if (!list_empty(&gss_msg->msg.list)) continue; gss_msg->msg.errno = -EPIPE; - atomic_inc(&gss_msg->count); + refcount_inc(&gss_msg->count); __gss_unhash_msg(gss_msg); spin_unlock(&pipe->lock); gss_release_msg(gss_msg); @@ -834,7 +834,7 @@ gss_pipe_destroy_msg(struct rpc_pipe_msg *msg) if (msg->errno < 0) { dprintk("RPC: %s releasing msg %p\n", __func__, gss_msg); - atomic_inc(&gss_msg->count); + refcount_inc(&gss_msg->count); gss_unhash_msg(gss_msg); if (msg->errno == -ETIMEDOUT) warn_gssd(); diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index fb39284ec174..12649c9fedab 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -34,6 +34,7 @@ * WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE. */ +#include <crypto/algapi.h> #include <crypto/hash.h> #include <crypto/skcipher.h> #include <linux/err.h> @@ -927,7 +928,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, if (ret) goto out_err; - if (memcmp(pkt_hmac, our_hmac, kctx->gk5e->cksumlength) != 0) { + if (crypto_memneq(pkt_hmac, our_hmac, kctx->gk5e->cksumlength) != 0) { ret = GSS_S_BAD_SIG; goto out_err; } diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index f0c6a8c78a56..46b295e4f2b8 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -55,15 +55,15 @@ enum { #define PROC(proc, name) \ [GSSX_##proc] = { \ .p_proc = GSSX_##proc, \ - .p_encode = (kxdreproc_t)gssx_enc_##name, \ - .p_decode = (kxdrdproc_t)gssx_dec_##name, \ + .p_encode = gssx_enc_##name, \ + .p_decode = gssx_dec_##name, \ .p_arglen = GSSX_ARG_##name##_sz, \ .p_replen = GSSX_RES_##name##_sz, \ .p_statidx = GSSX_##proc, \ .p_name = #proc, \ } -static struct rpc_procinfo gssp_procedures[] = { +static const struct rpc_procinfo gssp_procedures[] = { PROC(INDICATE_MECHS, indicate_mechs), PROC(GET_CALL_CONTEXT, get_call_context), PROC(IMPORT_AND_CANON_NAME, import_and_canon_name), @@ -364,11 +364,12 @@ void gssp_free_upcall_data(struct gssp_upcall_data *data) /* * Initialization stuff */ - +static unsigned int gssp_version1_counts[ARRAY_SIZE(gssp_procedures)]; static const struct rpc_version gssp_version1 = { .number = GSSPROXY_VERS_1, .nrprocs = ARRAY_SIZE(gssp_procedures), .procs = gssp_procedures, + .counts = gssp_version1_counts, }; static const struct rpc_version *gssp_version[] = { diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index 25d9a9cf7b66..c4778cae58ef 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -44,7 +44,7 @@ static int gssx_dec_bool(struct xdr_stream *xdr, u32 *v) } static int gssx_enc_buffer(struct xdr_stream *xdr, - gssx_buffer *buf) + const gssx_buffer *buf) { __be32 *p; @@ -56,7 +56,7 @@ static int gssx_enc_buffer(struct xdr_stream *xdr, } static int gssx_enc_in_token(struct xdr_stream *xdr, - struct gssp_in_token *in) + const struct gssp_in_token *in) { __be32 *p; @@ -130,7 +130,7 @@ static int gssx_dec_option(struct xdr_stream *xdr, } static int dummy_enc_opt_array(struct xdr_stream *xdr, - struct gssx_option_array *oa) + const struct gssx_option_array *oa) { __be32 *p; @@ -348,7 +348,7 @@ static int gssx_dec_status(struct xdr_stream *xdr, } static int gssx_enc_call_ctx(struct xdr_stream *xdr, - struct gssx_call_ctx *ctx) + const struct gssx_call_ctx *ctx) { struct gssx_option opt; __be32 *p; @@ -733,8 +733,9 @@ static int gssx_enc_cb(struct xdr_stream *xdr, struct gssx_cb *cb) void gssx_enc_accept_sec_context(struct rpc_rqst *req, struct xdr_stream *xdr, - struct gssx_arg_accept_sec_context *arg) + const void *data) { + const struct gssx_arg_accept_sec_context *arg = data; int err; err = gssx_enc_call_ctx(xdr, &arg->call_ctx); @@ -789,8 +790,9 @@ done: int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct gssx_res_accept_sec_context *res) + void *data) { + struct gssx_res_accept_sec_context *res = data; u32 value_follows; int err; struct page *scratch; diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.h b/net/sunrpc/auth_gss/gss_rpc_xdr.h index 9d88c6239f01..146c31032917 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.h +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.h @@ -179,10 +179,10 @@ struct gssx_res_accept_sec_context { #define gssx_dec_init_sec_context NULL void gssx_enc_accept_sec_context(struct rpc_rqst *req, struct xdr_stream *xdr, - struct gssx_arg_accept_sec_context *args); + const void *data); int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct gssx_res_accept_sec_context *res); + void *data); #define gssx_enc_release_handle NULL #define gssx_dec_release_handle NULL #define gssx_enc_get_mic NULL diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index a54a7a3d28f5..7b1ee5a0b03c 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -838,6 +838,14 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g struct xdr_netobj mic; struct xdr_buf integ_buf; + /* NFS READ normally uses splice to send data in-place. However + * the data in cache can change after the reply's MIC is computed + * but before the RPC reply is sent. To prevent the client from + * rejecting the server-computed MIC in this somewhat rare case, + * do not use splice with the GSS integrity service. + */ + clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); + /* Did we already verify the signature on the original pass through? */ if (rqstp->rq_deferred) return 0; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index b5cb921775a0..2e49d1f892b7 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1517,14 +1517,16 @@ static void call_start(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; + int idx = task->tk_msg.rpc_proc->p_statidx; dprintk("RPC: %5u call_start %s%d proc %s (%s)\n", task->tk_pid, clnt->cl_program->name, clnt->cl_vers, rpc_proc_name(task), (RPC_IS_ASYNC(task) ? "async" : "sync")); - /* Increment call count */ - task->tk_msg.rpc_proc->p_count++; + /* Increment call count (version might not be valid for ping) */ + if (clnt->cl_program->version[clnt->cl_vers]) + clnt->cl_program->version[clnt->cl_vers]->counts[idx]++; clnt->cl_stats->rpccnt++; task->tk_action = call_reserve; } @@ -1672,7 +1674,7 @@ call_allocate(struct rpc_task *task) unsigned int slack = task->tk_rqstp->rq_cred->cr_auth->au_cslack; struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; - struct rpc_procinfo *proc = task->tk_msg.rpc_proc; + const struct rpc_procinfo *proc = task->tk_msg.rpc_proc; int status; dprint_status(task); @@ -2476,16 +2478,18 @@ out_overflow: goto out_garbage; } -static void rpcproc_encode_null(void *rqstp, struct xdr_stream *xdr, void *obj) +static void rpcproc_encode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + const void *obj) { } -static int rpcproc_decode_null(void *rqstp, struct xdr_stream *xdr, void *obj) +static int rpcproc_decode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + void *obj) { return 0; } -static struct rpc_procinfo rpcproc_null = { +static const struct rpc_procinfo rpcproc_null = { .p_encode = rpcproc_encode_null, .p_decode = rpcproc_decode_null, }; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 5b30603596d0..ea0676f199c8 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -128,13 +128,13 @@ struct rpcbind_args { int r_status; }; -static struct rpc_procinfo rpcb_procedures2[]; -static struct rpc_procinfo rpcb_procedures3[]; -static struct rpc_procinfo rpcb_procedures4[]; +static const struct rpc_procinfo rpcb_procedures2[]; +static const struct rpc_procinfo rpcb_procedures3[]; +static const struct rpc_procinfo rpcb_procedures4[]; struct rpcb_info { u32 rpc_vers; - struct rpc_procinfo * rpc_proc; + const struct rpc_procinfo *rpc_proc; }; static const struct rpcb_info rpcb_next_version[]; @@ -620,7 +620,8 @@ int rpcb_v4_register(struct net *net, const u32 program, const u32 version, return -EAFNOSUPPORT; } -static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbind_args *map, struct rpc_procinfo *proc) +static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, + struct rpcbind_args *map, const struct rpc_procinfo *proc) { struct rpc_message msg = { .rpc_proc = proc, @@ -671,7 +672,7 @@ static struct rpc_clnt *rpcb_find_transport_owner(struct rpc_clnt *clnt) void rpcb_getport_async(struct rpc_task *task) { struct rpc_clnt *clnt; - struct rpc_procinfo *proc; + const struct rpc_procinfo *proc; u32 bind_version; struct rpc_xprt *xprt; struct rpc_clnt *rpcb_clnt; @@ -843,8 +844,9 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) */ static void rpcb_enc_mapping(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct rpcbind_args *rpcb) + const void *data) { + const struct rpcbind_args *rpcb = data; __be32 *p; dprintk("RPC: %5u encoding PMAP_%s call (%u, %u, %d, %u)\n", @@ -860,8 +862,9 @@ static void rpcb_enc_mapping(struct rpc_rqst *req, struct xdr_stream *xdr, } static int rpcb_dec_getport(struct rpc_rqst *req, struct xdr_stream *xdr, - struct rpcbind_args *rpcb) + void *data) { + struct rpcbind_args *rpcb = data; unsigned long port; __be32 *p; @@ -882,8 +885,9 @@ static int rpcb_dec_getport(struct rpc_rqst *req, struct xdr_stream *xdr, } static int rpcb_dec_set(struct rpc_rqst *req, struct xdr_stream *xdr, - unsigned int *boolp) + void *data) { + unsigned int *boolp = data; __be32 *p; p = xdr_inline_decode(xdr, 4); @@ -917,8 +921,9 @@ static void encode_rpcb_string(struct xdr_stream *xdr, const char *string, } static void rpcb_enc_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct rpcbind_args *rpcb) + const void *data) { + const struct rpcbind_args *rpcb = data; __be32 *p; dprintk("RPC: %5u encoding RPCB_%s call (%u, %u, '%s', '%s')\n", @@ -937,8 +942,9 @@ static void rpcb_enc_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, } static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, - struct rpcbind_args *rpcb) + void *data) { + struct rpcbind_args *rpcb = data; struct sockaddr_storage address; struct sockaddr *sap = (struct sockaddr *)&address; __be32 *p; @@ -989,11 +995,11 @@ out_fail: * since the Linux kernel RPC code requires only these. */ -static struct rpc_procinfo rpcb_procedures2[] = { +static const struct rpc_procinfo rpcb_procedures2[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdreproc_t)rpcb_enc_mapping, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_encode = rpcb_enc_mapping, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -1002,8 +1008,8 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdreproc_t)rpcb_enc_mapping, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_encode = rpcb_enc_mapping, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -1012,8 +1018,8 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, [RPCBPROC_GETPORT] = { .p_proc = RPCBPROC_GETPORT, - .p_encode = (kxdreproc_t)rpcb_enc_mapping, - .p_decode = (kxdrdproc_t)rpcb_dec_getport, + .p_encode = rpcb_enc_mapping, + .p_decode = rpcb_dec_getport, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_getportres_sz, .p_statidx = RPCBPROC_GETPORT, @@ -1022,11 +1028,11 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, }; -static struct rpc_procinfo rpcb_procedures3[] = { +static const struct rpc_procinfo rpcb_procedures3[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_encode = rpcb_enc_getaddr, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -1035,8 +1041,8 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_encode = rpcb_enc_getaddr, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -1045,8 +1051,8 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, + .p_encode = rpcb_enc_getaddr, + .p_decode = rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, .p_statidx = RPCBPROC_GETADDR, @@ -1055,11 +1061,11 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, }; -static struct rpc_procinfo rpcb_procedures4[] = { +static const struct rpc_procinfo rpcb_procedures4[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_encode = rpcb_enc_getaddr, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -1068,8 +1074,8 @@ static struct rpc_procinfo rpcb_procedures4[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_encode = rpcb_enc_getaddr, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -1078,8 +1084,8 @@ static struct rpc_procinfo rpcb_procedures4[] = { }, [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, + .p_encode = rpcb_enc_getaddr, + .p_decode = rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, .p_statidx = RPCBPROC_GETADDR, @@ -1112,22 +1118,28 @@ static const struct rpcb_info rpcb_next_version6[] = { }, }; +static unsigned int rpcb_version2_counts[ARRAY_SIZE(rpcb_procedures2)]; static const struct rpc_version rpcb_version2 = { .number = RPCBVERS_2, .nrprocs = ARRAY_SIZE(rpcb_procedures2), - .procs = rpcb_procedures2 + .procs = rpcb_procedures2, + .counts = rpcb_version2_counts, }; +static unsigned int rpcb_version3_counts[ARRAY_SIZE(rpcb_procedures3)]; static const struct rpc_version rpcb_version3 = { .number = RPCBVERS_3, .nrprocs = ARRAY_SIZE(rpcb_procedures3), - .procs = rpcb_procedures3 + .procs = rpcb_procedures3, + .counts = rpcb_version3_counts, }; +static unsigned int rpcb_version4_counts[ARRAY_SIZE(rpcb_procedures4)]; static const struct rpc_version rpcb_version4 = { .number = RPCBVERS_4, .nrprocs = ARRAY_SIZE(rpcb_procedures4), - .procs = rpcb_procedures4 + .procs = rpcb_procedures4, + .counts = rpcb_version4_counts, }; static const struct rpc_version *rpcb_version[] = { diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index caeb01ad2b5a..1e671333c3d5 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -55,8 +55,7 @@ static int rpc_proc_show(struct seq_file *seq, void *v) { seq_printf(seq, "proc%u %u", vers->number, vers->nrprocs); for (j = 0; j < vers->nrprocs; j++) - seq_printf(seq, " %u", - vers->procs[j].p_count); + seq_printf(seq, " %u", vers->counts[j]); seq_putc(seq, '\n'); } return 0; @@ -78,9 +77,9 @@ static const struct file_operations rpc_proc_fops = { /* * Get RPC server stats */ -void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) { +void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) +{ const struct svc_program *prog = statp->program; - const struct svc_procedure *proc; const struct svc_version *vers; unsigned int i, j; @@ -99,11 +98,12 @@ void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) { statp->rpcbadclnt); for (i = 0; i < prog->pg_nvers; i++) { - if (!(vers = prog->pg_vers[i]) || !(proc = vers->vs_proc)) + vers = prog->pg_vers[i]; + if (!vers) continue; seq_printf(seq, "proc%d %u", i, vers->vs_nproc); - for (j = 0; j < vers->vs_nproc; j++, proc++) - seq_printf(seq, " %u", proc->pc_count); + for (j = 0; j < vers->vs_nproc; j++) + seq_printf(seq, " %u", vers->vs_count[j]); seq_putc(seq, '\n'); } } @@ -192,7 +192,7 @@ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) EXPORT_SYMBOL_GPL(rpc_count_iostats); static void _print_name(struct seq_file *seq, unsigned int op, - struct rpc_procinfo *procs) + const struct rpc_procinfo *procs) { if (procs[op].p_name) seq_printf(seq, "\t%12s: ", procs[op].p_name); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index bc0f5a0ecbdc..85ce0db5b0a6 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1008,7 +1008,7 @@ int svc_register(const struct svc_serv *serv, struct net *net, const unsigned short port) { struct svc_program *progp; - struct svc_version *vers; + const struct svc_version *vers; unsigned int i; int error = 0; @@ -1151,10 +1151,9 @@ static int svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) { struct svc_program *progp; - struct svc_version *versp = NULL; /* compiler food */ - struct svc_procedure *procp = NULL; + const struct svc_version *versp = NULL; /* compiler food */ + const struct svc_procedure *procp = NULL; struct svc_serv *serv = rqstp->rq_server; - kxdrproc_t xdr; __be32 *statp; u32 prog, vers, proc; __be32 auth_stat, rpc_stat; @@ -1166,7 +1165,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) if (argv->iov_len < 6*4) goto err_short_len; - /* Will be turned off only in gss privacy case: */ + /* Will be turned off by GSS integrity and privacy services */ set_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* Will be turned off only when NFSv4 Sessions are used */ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); @@ -1262,7 +1261,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) svc_putnl(resv, RPC_SUCCESS); /* Bump per-procedure stats counter */ - procp->pc_count++; + versp->vs_count[proc]++; /* Initialize storage for argp and resp */ memset(rqstp->rq_argp, 0, procp->pc_argsize); @@ -1276,28 +1275,30 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) /* Call the function that processes the request. */ if (!versp->vs_dispatch) { - /* Decode arguments */ - xdr = procp->pc_decode; - if (xdr && !xdr(rqstp, argv->iov_base, rqstp->rq_argp)) + /* + * Decode arguments + * XXX: why do we ignore the return value? + */ + if (procp->pc_decode && + !procp->pc_decode(rqstp, argv->iov_base)) goto err_garbage; - *statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp); + *statp = procp->pc_func(rqstp); /* Encode reply */ if (*statp == rpc_drop_reply || test_bit(RQ_DROPME, &rqstp->rq_flags)) { if (procp->pc_release) - procp->pc_release(rqstp, NULL, rqstp->rq_resp); + procp->pc_release(rqstp); goto dropit; } if (*statp == rpc_autherr_badcred) { if (procp->pc_release) - procp->pc_release(rqstp, NULL, rqstp->rq_resp); + procp->pc_release(rqstp); goto err_bad_auth; } - if (*statp == rpc_success && - (xdr = procp->pc_encode) && - !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) { + if (*statp == rpc_success && procp->pc_encode && + !procp->pc_encode(rqstp, resv->iov_base + resv->iov_len)) { dprintk("svc: failed to encode reply\n"); /* serv->sv_stats->rpcsystemerr++; */ *statp = rpc_system_err; @@ -1307,7 +1308,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) if (!versp->vs_dispatch(rqstp, statp)) { /* Release reply info */ if (procp->pc_release) - procp->pc_release(rqstp, NULL, rqstp->rq_resp); + procp->pc_release(rqstp); goto dropit; } } @@ -1318,7 +1319,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) /* Release reply info */ if (procp->pc_release) - procp->pc_release(rqstp, NULL, rqstp->rq_resp); + procp->pc_release(rqstp); if (procp->pc_encode == NULL) goto dropit; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 7bfe1fb42add..d16a8b423c20 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -659,11 +659,13 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) int i; /* now allocate needed pages. If we get a failure, sleep briefly */ - pages = (serv->sv_max_mesg + PAGE_SIZE) / PAGE_SIZE; - WARN_ON_ONCE(pages >= RPCSVC_MAXPAGES); - if (pages >= RPCSVC_MAXPAGES) + pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT; + if (pages > RPCSVC_MAXPAGES) { + pr_warn_once("svc: warning: pages=%u > RPCSVC_MAXPAGES=%lu\n", + pages, RPCSVC_MAXPAGES); /* use as many pages as possible */ - pages = RPCSVC_MAXPAGES - 1; + pages = RPCSVC_MAXPAGES; + } for (i = 0; i < pages ; i++) while (rqstp->rq_pages[i] == NULL) { struct page *p = alloc_page(GFP_KERNEL); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 3e63c5e97ebe..4654a9934269 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1047,13 +1047,15 @@ out: return ret; } -static struct rpc_rqst *xprt_dynamic_alloc_slot(struct rpc_xprt *xprt, gfp_t gfp_flags) +static struct rpc_rqst *xprt_dynamic_alloc_slot(struct rpc_xprt *xprt) { struct rpc_rqst *req = ERR_PTR(-EAGAIN); if (!atomic_add_unless(&xprt->num_reqs, 1, xprt->max_reqs)) goto out; - req = kzalloc(sizeof(struct rpc_rqst), gfp_flags); + spin_unlock(&xprt->reserve_lock); + req = kzalloc(sizeof(struct rpc_rqst), GFP_NOFS); + spin_lock(&xprt->reserve_lock); if (req != NULL) goto out; atomic_dec(&xprt->num_reqs); @@ -1081,7 +1083,7 @@ void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) list_del(&req->rq_list); goto out_init_req; } - req = xprt_dynamic_alloc_slot(xprt, GFP_NOWAIT|__GFP_NOWARN); + req = xprt_dynamic_alloc_slot(xprt); if (!IS_ERR(req)) goto out_init_req; switch (PTR_ERR(req)) { diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile index c1ae8142ab73..b8213ddce2f2 100644 --- a/net/sunrpc/xprtrdma/Makefile +++ b/net/sunrpc/xprtrdma/Makefile @@ -3,6 +3,6 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o rpcrdma-y := transport.o rpc_rdma.o verbs.o \ fmr_ops.o frwr_ops.o \ svc_rdma.o svc_rdma_backchannel.o svc_rdma_transport.o \ - svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o \ - svc_rdma_rw.o module.o + svc_rdma_sendto.o svc_rdma_recvfrom.o svc_rdma_rw.o \ + module.o rpcrdma-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel.o diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 59e64025ed96..d3f84bb1d443 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -91,7 +91,7 @@ __fmr_unmap(struct rpcrdma_mw *mw) list_add(&mw->fmr.fm_mr->list, &l); rc = ib_unmap_fmr(&l); - list_del_init(&mw->fmr.fm_mr->list); + list_del(&mw->fmr.fm_mr->list); return rc; } @@ -213,13 +213,11 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) break; } - mw->mw_nents = i; mw->mw_dir = rpcrdma_data_dir(writing); - if (i == 0) - goto out_dmamap_err; - if (!ib_dma_map_sg(r_xprt->rx_ia.ri_device, - mw->mw_sg, mw->mw_nents, mw->mw_dir)) + mw->mw_nents = ib_dma_map_sg(r_xprt->rx_ia.ri_device, + mw->mw_sg, i, mw->mw_dir); + if (!mw->mw_nents) goto out_dmamap_err; for (i = 0, dma_pages = mw->fmr.fm_physaddrs; i < mw->mw_nents; i++) @@ -237,16 +235,18 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, return mw->mw_nents; out_dmamap_err: - pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n", - mw->mw_sg, mw->mw_nents); - rpcrdma_defer_mr_recovery(mw); + pr_err("rpcrdma: failed to DMA map sg %p sg_nents %d\n", + mw->mw_sg, i); + rpcrdma_put_mw(r_xprt, mw); return -EIO; out_maperr: pr_err("rpcrdma: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n", len, (unsigned long long)dma_pages[0], pageoff, mw->mw_nents, rc); - rpcrdma_defer_mr_recovery(mw); + ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, + mw->mw_sg, mw->mw_nents, mw->mw_dir); + rpcrdma_put_mw(r_xprt, mw); return -EIO; } @@ -255,24 +255,26 @@ out_maperr: * Sleeps until it is safe for the host CPU to access the * previously mapped memory regions. * - * Caller ensures that req->rl_registered is not empty. + * Caller ensures that @mws is not empty before the call. This + * function empties the list. */ static void -fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) +fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mws) { - struct rpcrdma_mw *mw, *tmp; + struct rpcrdma_mw *mw; LIST_HEAD(unmap_list); int rc; - dprintk("RPC: %s: req %p\n", __func__, req); - /* ORDER: Invalidate all of the req's MRs first * * ib_unmap_fmr() is slow, so use a single call instead * of one call per mapped FMR. */ - list_for_each_entry(mw, &req->rl_registered, mw_list) + list_for_each_entry(mw, mws, mw_list) { + dprintk("RPC: %s: unmapping fmr %p\n", + __func__, &mw->fmr); list_add_tail(&mw->fmr.fm_mr->list, &unmap_list); + } r_xprt->rx_stats.local_inv_needed++; rc = ib_unmap_fmr(&unmap_list); if (rc) @@ -281,9 +283,11 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) /* ORDER: Now DMA unmap all of the req's MRs, and return * them to the free MW list. */ - list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) { - list_del_init(&mw->mw_list); - list_del_init(&mw->fmr.fm_mr->list); + while (!list_empty(mws)) { + mw = rpcrdma_pop_mw(mws); + dprintk("RPC: %s: DMA unmapping fmr %p\n", + __func__, &mw->fmr); + list_del(&mw->fmr.fm_mr->list); ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir); rpcrdma_put_mw(r_xprt, mw); @@ -294,8 +298,9 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) out_reset: pr_err("rpcrdma: ib_unmap_fmr failed (%i)\n", rc); - list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) { - list_del_init(&mw->fmr.fm_mr->list); + while (!list_empty(mws)) { + mw = rpcrdma_pop_mw(mws); + list_del(&mw->fmr.fm_mr->list); fmr_op_recover_mr(mw); } } diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index f81dd93176c0..6aea36a38bfd 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -277,7 +277,7 @@ __frwr_sendcompletion_flush(struct ib_wc *wc, const char *wr) } /** - * frwr_wc_fastreg - Invoked by RDMA provider for each polled FastReg WC + * frwr_wc_fastreg - Invoked by RDMA provider for a flushed FastReg WC * @cq: completion queue (ignored) * @wc: completed WR * @@ -298,7 +298,7 @@ frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc) } /** - * frwr_wc_localinv - Invoked by RDMA provider for each polled LocalInv WC + * frwr_wc_localinv - Invoked by RDMA provider for a flushed LocalInv WC * @cq: completion queue (ignored) * @wc: completed WR * @@ -319,7 +319,7 @@ frwr_wc_localinv(struct ib_cq *cq, struct ib_wc *wc) } /** - * frwr_wc_localinv - Invoked by RDMA provider for each polled LocalInv WC + * frwr_wc_localinv_wake - Invoked by RDMA provider for a signaled LocalInv WC * @cq: completion queue (ignored) * @wc: completed WR * @@ -355,7 +355,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, struct ib_mr *mr; struct ib_reg_wr *reg_wr; struct ib_send_wr *bad_wr; - int rc, i, n, dma_nents; + int rc, i, n; u8 key; mw = NULL; @@ -391,14 +391,10 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) break; } - mw->mw_nents = i; mw->mw_dir = rpcrdma_data_dir(writing); - if (i == 0) - goto out_dmamap_err; - dma_nents = ib_dma_map_sg(ia->ri_device, - mw->mw_sg, mw->mw_nents, mw->mw_dir); - if (!dma_nents) + mw->mw_nents = ib_dma_map_sg(ia->ri_device, mw->mw_sg, i, mw->mw_dir); + if (!mw->mw_nents) goto out_dmamap_err; n = ib_map_mr_sg(mr, mw->mw_sg, mw->mw_nents, NULL, PAGE_SIZE); @@ -436,13 +432,14 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, return mw->mw_nents; out_dmamap_err: - pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n", - mw->mw_sg, mw->mw_nents); - rpcrdma_defer_mr_recovery(mw); + pr_err("rpcrdma: failed to DMA map sg %p sg_nents %d\n", + mw->mw_sg, i); + frmr->fr_state = FRMR_IS_INVALID; + rpcrdma_put_mw(r_xprt, mw); return -EIO; out_mapmr_err: - pr_err("rpcrdma: failed to map mr %p (%u/%u)\n", + pr_err("rpcrdma: failed to map mr %p (%d/%d)\n", frmr->fr_mr, n, mw->mw_nents); rpcrdma_defer_mr_recovery(mw); return -EIO; @@ -458,21 +455,19 @@ out_senderr: * Sleeps until it is safe for the host CPU to access the * previously mapped memory regions. * - * Caller ensures that req->rl_registered is not empty. + * Caller ensures that @mws is not empty before the call. This + * function empties the list. */ static void -frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) +frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mws) { struct ib_send_wr *first, **prev, *last, *bad_wr; - struct rpcrdma_rep *rep = req->rl_reply; struct rpcrdma_ia *ia = &r_xprt->rx_ia; struct rpcrdma_frmr *f; struct rpcrdma_mw *mw; int count, rc; - dprintk("RPC: %s: req %p\n", __func__, req); - - /* ORDER: Invalidate all of the req's MRs first + /* ORDER: Invalidate all of the MRs first * * Chain the LOCAL_INV Work Requests and post them with * a single ib_post_send() call. @@ -480,11 +475,10 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) f = NULL; count = 0; prev = &first; - list_for_each_entry(mw, &req->rl_registered, mw_list) { + list_for_each_entry(mw, mws, mw_list) { mw->frmr.fr_state = FRMR_IS_INVALID; - if ((rep->rr_wc_flags & IB_WC_WITH_INVALIDATE) && - (mw->mw_handle == rep->rr_inv_rkey)) + if (mw->mw_flags & RPCRDMA_MW_F_RI) continue; f = &mw->frmr; @@ -524,18 +518,19 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) * unless ri_id->qp is a valid pointer. */ r_xprt->rx_stats.local_inv_needed++; + bad_wr = NULL; rc = ib_post_send(ia->ri_id->qp, first, &bad_wr); + if (bad_wr != first) + wait_for_completion(&f->fr_linv_done); if (rc) goto reset_mrs; - wait_for_completion(&f->fr_linv_done); - - /* ORDER: Now DMA unmap all of the req's MRs, and return + /* ORDER: Now DMA unmap all of the MRs, and return * them to the free MW list. */ unmap: - while (!list_empty(&req->rl_registered)) { - mw = rpcrdma_pop_mw(&req->rl_registered); + while (!list_empty(mws)) { + mw = rpcrdma_pop_mw(mws); dprintk("RPC: %s: DMA unmapping frmr %p\n", __func__, &mw->frmr); ib_dma_unmap_sg(ia->ri_device, @@ -546,17 +541,19 @@ unmap: reset_mrs: pr_err("rpcrdma: FRMR invalidate ib_post_send returned %i\n", rc); - rdma_disconnect(ia->ri_id); /* Find and reset the MRs in the LOCAL_INV WRs that did not - * get posted. This is synchronous, and slow. + * get posted. */ - list_for_each_entry(mw, &req->rl_registered, mw_list) { - f = &mw->frmr; - if (mw->mw_handle == bad_wr->ex.invalidate_rkey) { - __frwr_reset_mr(ia, mw); - bad_wr = bad_wr->next; - } + rpcrdma_init_cqcount(&r_xprt->rx_ep, -count); + while (bad_wr) { + f = container_of(bad_wr, struct rpcrdma_frmr, + fr_invwr); + mw = container_of(f, struct rpcrdma_mw, frmr); + + __frwr_reset_mr(ia, mw); + + bad_wr = bad_wr->next; } goto unmap; } diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 694e9b13ecf0..ca4d6e4528f3 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -141,7 +141,7 @@ static bool rpcrdma_args_inline(struct rpcrdma_xprt *r_xprt, if (xdr->page_len) { remaining = xdr->page_len; - offset = xdr->page_base & ~PAGE_MASK; + offset = offset_in_page(xdr->page_base); count = 0; while (remaining) { remaining -= min_t(unsigned int, @@ -222,7 +222,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf, len = xdrbuf->page_len; ppages = xdrbuf->pages + (xdrbuf->page_base >> PAGE_SHIFT); - page_base = xdrbuf->page_base & ~PAGE_MASK; + page_base = offset_in_page(xdrbuf->page_base); p = 0; while (len && n < RPCRDMA_MAX_SEGS) { if (!ppages[p]) { @@ -540,7 +540,7 @@ rpcrdma_prepare_msg_sges(struct rpcrdma_ia *ia, struct rpcrdma_req *req, goto out; page = virt_to_page(xdr->tail[0].iov_base); - page_base = (unsigned long)xdr->tail[0].iov_base & ~PAGE_MASK; + page_base = offset_in_page(xdr->tail[0].iov_base); /* If the content in the page list is an odd length, * xdr_write_pages() has added a pad at the beginning @@ -557,7 +557,7 @@ rpcrdma_prepare_msg_sges(struct rpcrdma_ia *ia, struct rpcrdma_req *req, */ if (xdr->page_len) { ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT); - page_base = xdr->page_base & ~PAGE_MASK; + page_base = offset_in_page(xdr->page_base); remaining = xdr->page_len; while (remaining) { sge_no++; @@ -587,7 +587,7 @@ rpcrdma_prepare_msg_sges(struct rpcrdma_ia *ia, struct rpcrdma_req *req, */ if (xdr->tail[0].iov_len) { page = virt_to_page(xdr->tail[0].iov_base); - page_base = (unsigned long)xdr->tail[0].iov_base & ~PAGE_MASK; + page_base = offset_in_page(xdr->tail[0].iov_base); len = xdr->tail[0].iov_len; map_tail: @@ -734,6 +734,9 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) rpclen = 0; } + req->rl_xid = rqst->rq_xid; + rpcrdma_insert_req(&r_xprt->rx_buf, req); + /* This implementation supports the following combinations * of chunk lists in one RPC-over-RDMA Call message: * @@ -875,9 +878,9 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) srcp += curlen; copy_len -= curlen; - page_base = rqst->rq_rcv_buf.page_base; - ppages = rqst->rq_rcv_buf.pages + (page_base >> PAGE_SHIFT); - page_base &= ~PAGE_MASK; + ppages = rqst->rq_rcv_buf.pages + + (rqst->rq_rcv_buf.page_base >> PAGE_SHIFT); + page_base = offset_in_page(rqst->rq_rcv_buf.page_base); fixup_copy_count = 0; if (copy_len && rqst->rq_rcv_buf.page_len) { int pagelist_len; @@ -928,6 +931,24 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) return fixup_copy_count; } +/* Caller must guarantee @rep remains stable during this call. + */ +static void +rpcrdma_mark_remote_invalidation(struct list_head *mws, + struct rpcrdma_rep *rep) +{ + struct rpcrdma_mw *mw; + + if (!(rep->rr_wc_flags & IB_WC_WITH_INVALIDATE)) + return; + + list_for_each_entry(mw, mws, mw_list) + if (mw->mw_handle == rep->rr_inv_rkey) { + mw->mw_flags = RPCRDMA_MW_F_RI; + break; /* only one invalidated MR per RPC */ + } +} + #if defined(CONFIG_SUNRPC_BACKCHANNEL) /* By convention, backchannel calls arrive via rdma_msg type * messages, and never populate the chunk lists. This makes @@ -969,14 +990,16 @@ rpcrdma_reply_handler(struct work_struct *work) { struct rpcrdma_rep *rep = container_of(work, struct rpcrdma_rep, rr_work); + struct rpcrdma_xprt *r_xprt = rep->rr_rxprt; + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpc_xprt *xprt = &r_xprt->rx_xprt; struct rpcrdma_msg *headerp; struct rpcrdma_req *req; struct rpc_rqst *rqst; - struct rpcrdma_xprt *r_xprt = rep->rr_rxprt; - struct rpc_xprt *xprt = &r_xprt->rx_xprt; __be32 *iptr; int rdmalen, status, rmerr; unsigned long cwnd; + struct list_head mws; dprintk("RPC: %s: incoming rep %p\n", __func__, rep); @@ -994,27 +1017,45 @@ rpcrdma_reply_handler(struct work_struct *work) /* Match incoming rpcrdma_rep to an rpcrdma_req to * get context for handling any incoming chunks. */ - spin_lock_bh(&xprt->transport_lock); - rqst = xprt_lookup_rqst(xprt, headerp->rm_xid); - if (!rqst) + spin_lock(&buf->rb_lock); + req = rpcrdma_lookup_req_locked(&r_xprt->rx_buf, + headerp->rm_xid); + if (!req) goto out_nomatch; - - req = rpcr_to_rdmar(rqst); if (req->rl_reply) goto out_duplicate; - /* Sanity checking has passed. We are now committed - * to complete this transaction. + list_replace_init(&req->rl_registered, &mws); + rpcrdma_mark_remote_invalidation(&mws, rep); + + /* Avoid races with signals and duplicate replies + * by marking this req as matched. */ - list_del_init(&rqst->rq_list); - spin_unlock_bh(&xprt->transport_lock); + req->rl_reply = rep; + spin_unlock(&buf->rb_lock); + dprintk("RPC: %s: reply %p completes request %p (xid 0x%08x)\n", __func__, rep, req, be32_to_cpu(headerp->rm_xid)); - /* from here on, the reply is no longer an orphan */ - req->rl_reply = rep; - xprt->reestablish_timeout = 0; + /* Invalidate and unmap the data payloads before waking the + * waiting application. This guarantees the memory regions + * are properly fenced from the server before the application + * accesses the data. It also ensures proper send flow control: + * waking the next RPC waits until this RPC has relinquished + * all its Send Queue entries. + */ + if (!list_empty(&mws)) + r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, &mws); + /* Perform XID lookup, reconstruction of the RPC reply, and + * RPC completion while holding the transport lock to ensure + * the rep, rqst, and rq_task pointers remain stable. + */ + spin_lock_bh(&xprt->transport_lock); + rqst = xprt_lookup_rqst(xprt, headerp->rm_xid); + if (!rqst) + goto out_norqst; + xprt->reestablish_timeout = 0; if (headerp->rm_vers != rpcrdma_version) goto out_badversion; @@ -1024,12 +1065,9 @@ rpcrdma_reply_handler(struct work_struct *work) case rdma_msg: /* never expect read chunks */ /* never expect reply chunks (two ways to check) */ - /* never expect write chunks without having offered RDMA */ if (headerp->rm_body.rm_chunks[0] != xdr_zero || (headerp->rm_body.rm_chunks[1] == xdr_zero && - headerp->rm_body.rm_chunks[2] != xdr_zero) || - (headerp->rm_body.rm_chunks[1] != xdr_zero && - list_empty(&req->rl_registered))) + headerp->rm_body.rm_chunks[2] != xdr_zero)) goto badheader; if (headerp->rm_body.rm_chunks[1] != xdr_zero) { /* count any expected write chunks in read reply */ @@ -1066,8 +1104,7 @@ rpcrdma_reply_handler(struct work_struct *work) /* never expect read or write chunks, always reply chunks */ if (headerp->rm_body.rm_chunks[0] != xdr_zero || headerp->rm_body.rm_chunks[1] != xdr_zero || - headerp->rm_body.rm_chunks[2] != xdr_one || - list_empty(&req->rl_registered)) + headerp->rm_body.rm_chunks[2] != xdr_one) goto badheader; iptr = (__be32 *)((unsigned char *)headerp + RPCRDMA_HDRLEN_MIN); @@ -1093,17 +1130,6 @@ badheader: } out: - /* Invalidate and flush the data payloads before waking the - * waiting application. This guarantees the memory region is - * properly fenced from the server before the application - * accesses the data. It also ensures proper send flow - * control: waking the next RPC waits until this RPC has - * relinquished all its Send Queue entries. - */ - if (!list_empty(&req->rl_registered)) - r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, req); - - spin_lock_bh(&xprt->transport_lock); cwnd = xprt->cwnd; xprt->cwnd = atomic_read(&r_xprt->rx_buf.rb_credits) << RPC_CWNDSHIFT; if (xprt->cwnd > cwnd) @@ -1112,7 +1138,7 @@ out: xprt_complete_rqst(rqst->rq_task, status); spin_unlock_bh(&xprt->transport_lock); dprintk("RPC: %s: xprt_complete_rqst(0x%p, 0x%p, %d)\n", - __func__, xprt, rqst, status); + __func__, xprt, rqst, status); return; out_badstatus: @@ -1161,26 +1187,37 @@ out_rdmaerr: r_xprt->rx_stats.bad_reply_count++; goto out; -/* If no pending RPC transaction was matched, post a replacement - * receive buffer before returning. +/* The req was still available, but by the time the transport_lock + * was acquired, the rqst and task had been released. Thus the RPC + * has already been terminated. */ +out_norqst: + spin_unlock_bh(&xprt->transport_lock); + rpcrdma_buffer_put(req); + dprintk("RPC: %s: race, no rqst left for req %p\n", + __func__, req); + return; + out_shortreply: dprintk("RPC: %s: short/invalid reply\n", __func__); goto repost; out_nomatch: - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&buf->rb_lock); dprintk("RPC: %s: no match for incoming xid 0x%08x len %d\n", __func__, be32_to_cpu(headerp->rm_xid), rep->rr_len); goto repost; out_duplicate: - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&buf->rb_lock); dprintk("RPC: %s: " "duplicate reply %p to RPC request %p: xid 0x%08x\n", __func__, rep, req, be32_to_cpu(headerp->rm_xid)); +/* If no pending RPC transaction was matched, post a replacement + * receive buffer before returning. + */ repost: r_xprt->rx_stats.bad_reply_count++; if (rpcrdma_ep_post_recv(&r_xprt->rx_ia, rep)) diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c deleted file mode 100644 index bdcf7d85a3dc..000000000000 --- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c +++ /dev/null @@ -1,168 +0,0 @@ -/* - * Copyright (c) 2016 Oracle. All rights reserved. - * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the BSD-type - * license below: - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * - * Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials provided - * with the distribution. - * - * Neither the name of the Network Appliance, Inc. nor the names of - * its contributors may be used to endorse or promote products - * derived from this software without specific prior written - * permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * Author: Tom Tucker <tom@opengridcomputing.com> - */ - -#include <linux/sunrpc/xdr.h> -#include <linux/sunrpc/debug.h> -#include <asm/unaligned.h> -#include <linux/sunrpc/rpc_rdma.h> -#include <linux/sunrpc/svc_rdma.h> - -#define RPCDBG_FACILITY RPCDBG_SVCXPRT - -static __be32 *xdr_check_read_list(__be32 *p, __be32 *end) -{ - __be32 *next; - - while (*p++ != xdr_zero) { - next = p + rpcrdma_readchunk_maxsz - 1; - if (next > end) - return NULL; - p = next; - } - return p; -} - -static __be32 *xdr_check_write_list(__be32 *p, __be32 *end) -{ - __be32 *next; - - while (*p++ != xdr_zero) { - next = p + 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz; - if (next > end) - return NULL; - p = next; - } - return p; -} - -static __be32 *xdr_check_reply_chunk(__be32 *p, __be32 *end) -{ - __be32 *next; - - if (*p++ != xdr_zero) { - next = p + 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz; - if (next > end) - return NULL; - p = next; - } - return p; -} - -/** - * svc_rdma_xdr_decode_req - Parse incoming RPC-over-RDMA header - * @rq_arg: Receive buffer - * - * On entry, xdr->head[0].iov_base points to first byte in the - * RPC-over-RDMA header. - * - * On successful exit, head[0] points to first byte past the - * RPC-over-RDMA header. For RDMA_MSG, this is the RPC message. - * The length of the RPC-over-RDMA header is returned. - */ -int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg) -{ - __be32 *p, *end, *rdma_argp; - unsigned int hdr_len; - - /* Verify that there's enough bytes for header + something */ - if (rq_arg->len <= RPCRDMA_HDRLEN_ERR) - goto out_short; - - rdma_argp = rq_arg->head[0].iov_base; - if (*(rdma_argp + 1) != rpcrdma_version) - goto out_version; - - switch (*(rdma_argp + 3)) { - case rdma_msg: - case rdma_nomsg: - break; - - case rdma_done: - goto out_drop; - - case rdma_error: - goto out_drop; - - default: - goto out_proc; - } - - end = (__be32 *)((unsigned long)rdma_argp + rq_arg->len); - p = xdr_check_read_list(rdma_argp + 4, end); - if (!p) - goto out_inval; - p = xdr_check_write_list(p, end); - if (!p) - goto out_inval; - p = xdr_check_reply_chunk(p, end); - if (!p) - goto out_inval; - if (p > end) - goto out_inval; - - rq_arg->head[0].iov_base = p; - hdr_len = (unsigned long)p - (unsigned long)rdma_argp; - rq_arg->head[0].iov_len -= hdr_len; - return hdr_len; - -out_short: - dprintk("svcrdma: header too short = %d\n", rq_arg->len); - return -EINVAL; - -out_version: - dprintk("svcrdma: bad xprt version: %u\n", - be32_to_cpup(rdma_argp + 1)); - return -EPROTONOSUPPORT; - -out_drop: - dprintk("svcrdma: dropping RDMA_DONE/ERROR message\n"); - return 0; - -out_proc: - dprintk("svcrdma: bad rdma procedure (%u)\n", - be32_to_cpup(rdma_argp + 3)); - return -EINVAL; - -out_inval: - dprintk("svcrdma: failed to parse transport header\n"); - return -EINVAL; -} diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 27a99bf5b1a6..ad4bd62eebf1 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -1,4 +1,5 @@ /* + * Copyright (c) 2016, 2017 Oracle. All rights reserved. * Copyright (c) 2014 Open Grid Computing, Inc. All rights reserved. * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved. * @@ -40,12 +41,66 @@ * Author: Tom Tucker <tom@opengridcomputing.com> */ -#include <linux/sunrpc/debug.h> -#include <linux/sunrpc/rpc_rdma.h> -#include <linux/spinlock.h> +/* Operation + * + * The main entry point is svc_rdma_recvfrom. This is called from + * svc_recv when the transport indicates there is incoming data to + * be read. "Data Ready" is signaled when an RDMA Receive completes, + * or when a set of RDMA Reads complete. + * + * An svc_rqst is passed in. This structure contains an array of + * free pages (rq_pages) that will contain the incoming RPC message. + * + * Short messages are moved directly into svc_rqst::rq_arg, and + * the RPC Call is ready to be processed by the Upper Layer. + * svc_rdma_recvfrom returns the length of the RPC Call message, + * completing the reception of the RPC Call. + * + * However, when an incoming message has Read chunks, + * svc_rdma_recvfrom must post RDMA Reads to pull the RPC Call's + * data payload from the client. svc_rdma_recvfrom sets up the + * RDMA Reads using pages in svc_rqst::rq_pages, which are + * transferred to an svc_rdma_op_ctxt for the duration of the + * I/O. svc_rdma_recvfrom then returns zero, since the RPC message + * is still not yet ready. + * + * When the Read chunk payloads have become available on the + * server, "Data Ready" is raised again, and svc_recv calls + * svc_rdma_recvfrom again. This second call may use a different + * svc_rqst than the first one, thus any information that needs + * to be preserved across these two calls is kept in an + * svc_rdma_op_ctxt. + * + * The second call to svc_rdma_recvfrom performs final assembly + * of the RPC Call message, using the RDMA Read sink pages kept in + * the svc_rdma_op_ctxt. The xdr_buf is copied from the + * svc_rdma_op_ctxt to the second svc_rqst. The second call returns + * the length of the completed RPC Call message. + * + * Page Management + * + * Pages under I/O must be transferred from the first svc_rqst to an + * svc_rdma_op_ctxt before the first svc_rdma_recvfrom call returns. + * + * The first svc_rqst supplies pages for RDMA Reads. These are moved + * from rqstp::rq_pages into ctxt::pages. The consumed elements of + * the rq_pages array are set to NULL and refilled with the first + * svc_rdma_recvfrom call returns. + * + * During the second svc_rdma_recvfrom call, RDMA Read sink pages + * are transferred from the svc_rdma_op_ctxt to the second svc_rqst + * (see rdma_read_complete() below). + */ + #include <asm/unaligned.h> #include <rdma/ib_verbs.h> #include <rdma/rdma_cm.h> + +#include <linux/spinlock.h> + +#include <linux/sunrpc/xdr.h> +#include <linux/sunrpc/debug.h> +#include <linux/sunrpc/rpc_rdma.h> #include <linux/sunrpc/svc_rdma.h> #define RPCDBG_FACILITY RPCDBG_SVCXPRT @@ -59,7 +114,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *ctxt, u32 byte_count) { - struct rpcrdma_msg *rmsgp; struct page *page; u32 bc; int sge_no; @@ -83,20 +137,12 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, rqstp->rq_arg.page_len = bc; rqstp->rq_arg.page_base = 0; - /* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */ - rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base; - if (rmsgp->rm_type == rdma_nomsg) - rqstp->rq_arg.pages = &rqstp->rq_pages[0]; - else - rqstp->rq_arg.pages = &rqstp->rq_pages[1]; - sge_no = 1; while (bc && sge_no < ctxt->count) { page = ctxt->pages[sge_no]; put_page(rqstp->rq_pages[sge_no]); rqstp->rq_pages[sge_no] = page; bc -= min_t(u32, bc, ctxt->sge[sge_no].length); - rqstp->rq_arg.buflen += ctxt->sge[sge_no].length; sge_no++; } rqstp->rq_respages = &rqstp->rq_pages[sge_no]; @@ -115,406 +161,208 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, rqstp->rq_arg.tail[0].iov_len = 0; } -/* Issue an RDMA_READ using the local lkey to map the data sink */ -int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt, - struct svc_rqst *rqstp, - struct svc_rdma_op_ctxt *head, - int *page_no, - u32 *page_offset, - u32 rs_handle, - u32 rs_length, - u64 rs_offset, - bool last) -{ - struct ib_rdma_wr read_wr; - int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT; - struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt); - int ret, read, pno; - u32 pg_off = *page_offset; - u32 pg_no = *page_no; - - ctxt->direction = DMA_FROM_DEVICE; - ctxt->read_hdr = head; - pages_needed = min_t(int, pages_needed, xprt->sc_max_sge_rd); - read = min_t(int, (pages_needed << PAGE_SHIFT) - *page_offset, - rs_length); - - for (pno = 0; pno < pages_needed; pno++) { - int len = min_t(int, rs_length, PAGE_SIZE - pg_off); - - head->arg.pages[pg_no] = rqstp->rq_arg.pages[pg_no]; - head->arg.page_len += len; - - head->arg.len += len; - if (!pg_off) - head->count++; - rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1]; - rqstp->rq_next_page = rqstp->rq_respages + 1; - ctxt->sge[pno].addr = - ib_dma_map_page(xprt->sc_cm_id->device, - head->arg.pages[pg_no], pg_off, - PAGE_SIZE - pg_off, - DMA_FROM_DEVICE); - ret = ib_dma_mapping_error(xprt->sc_cm_id->device, - ctxt->sge[pno].addr); - if (ret) - goto err; - svc_rdma_count_mappings(xprt, ctxt); - - ctxt->sge[pno].lkey = xprt->sc_pd->local_dma_lkey; - ctxt->sge[pno].length = len; - ctxt->count++; - - /* adjust offset and wrap to next page if needed */ - pg_off += len; - if (pg_off == PAGE_SIZE) { - pg_off = 0; - pg_no++; - } - rs_length -= len; - } - - if (last && rs_length == 0) - set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); - else - clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); - - memset(&read_wr, 0, sizeof(read_wr)); - ctxt->cqe.done = svc_rdma_wc_read; - read_wr.wr.wr_cqe = &ctxt->cqe; - read_wr.wr.opcode = IB_WR_RDMA_READ; - read_wr.wr.send_flags = IB_SEND_SIGNALED; - read_wr.rkey = rs_handle; - read_wr.remote_addr = rs_offset; - read_wr.wr.sg_list = ctxt->sge; - read_wr.wr.num_sge = pages_needed; - - ret = svc_rdma_send(xprt, &read_wr.wr); - if (ret) { - pr_err("svcrdma: Error %d posting RDMA_READ\n", ret); - set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); - goto err; - } +/* This accommodates the largest possible Write chunk, + * in one segment. + */ +#define MAX_BYTES_WRITE_SEG ((u32)(RPCSVC_MAXPAGES << PAGE_SHIFT)) - /* return current location in page array */ - *page_no = pg_no; - *page_offset = pg_off; - ret = read; - atomic_inc(&rdma_stat_read); - return ret; - err: - svc_rdma_unmap_dma(ctxt); - svc_rdma_put_context(ctxt, 0); - return ret; -} +/* This accommodates the largest possible Position-Zero + * Read chunk or Reply chunk, in one segment. + */ +#define MAX_BYTES_SPECIAL_SEG ((u32)((RPCSVC_MAXPAGES + 2) << PAGE_SHIFT)) -/* Issue an RDMA_READ using an FRMR to map the data sink */ -int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt, - struct svc_rqst *rqstp, - struct svc_rdma_op_ctxt *head, - int *page_no, - u32 *page_offset, - u32 rs_handle, - u32 rs_length, - u64 rs_offset, - bool last) +/* Sanity check the Read list. + * + * Implementation limits: + * - This implementation supports only one Read chunk. + * + * Sanity checks: + * - Read list does not overflow buffer. + * - Segment size limited by largest NFS data payload. + * + * The segment count is limited to how many segments can + * fit in the transport header without overflowing the + * buffer. That's about 40 Read segments for a 1KB inline + * threshold. + * + * Returns pointer to the following Write list. + */ +static __be32 *xdr_check_read_list(__be32 *p, const __be32 *end) { - struct ib_rdma_wr read_wr; - struct ib_send_wr inv_wr; - struct ib_reg_wr reg_wr; - u8 key; - int nents = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT; - struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt); - struct svc_rdma_fastreg_mr *frmr = svc_rdma_get_frmr(xprt); - int ret, read, pno, dma_nents, n; - u32 pg_off = *page_offset; - u32 pg_no = *page_no; - - if (IS_ERR(frmr)) - return -ENOMEM; - - ctxt->direction = DMA_FROM_DEVICE; - ctxt->frmr = frmr; - nents = min_t(unsigned int, nents, xprt->sc_frmr_pg_list_len); - read = min_t(int, (nents << PAGE_SHIFT) - *page_offset, rs_length); - - frmr->direction = DMA_FROM_DEVICE; - frmr->access_flags = (IB_ACCESS_LOCAL_WRITE|IB_ACCESS_REMOTE_WRITE); - frmr->sg_nents = nents; - - for (pno = 0; pno < nents; pno++) { - int len = min_t(int, rs_length, PAGE_SIZE - pg_off); - - head->arg.pages[pg_no] = rqstp->rq_arg.pages[pg_no]; - head->arg.page_len += len; - head->arg.len += len; - if (!pg_off) - head->count++; - - sg_set_page(&frmr->sg[pno], rqstp->rq_arg.pages[pg_no], - len, pg_off); - - rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1]; - rqstp->rq_next_page = rqstp->rq_respages + 1; - - /* adjust offset and wrap to next page if needed */ - pg_off += len; - if (pg_off == PAGE_SIZE) { - pg_off = 0; - pg_no++; + u32 position; + bool first; + + first = true; + while (*p++ != xdr_zero) { + if (first) { + position = be32_to_cpup(p++); + first = false; + } else if (be32_to_cpup(p++) != position) { + return NULL; } - rs_length -= len; - } + p++; /* handle */ + if (be32_to_cpup(p++) > MAX_BYTES_SPECIAL_SEG) + return NULL; + p += 2; /* offset */ - if (last && rs_length == 0) - set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); - else - clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); - - dma_nents = ib_dma_map_sg(xprt->sc_cm_id->device, - frmr->sg, frmr->sg_nents, - frmr->direction); - if (!dma_nents) { - pr_err("svcrdma: failed to dma map sg %p\n", - frmr->sg); - return -ENOMEM; + if (p > end) + return NULL; } + return p; +} - n = ib_map_mr_sg(frmr->mr, frmr->sg, frmr->sg_nents, NULL, PAGE_SIZE); - if (unlikely(n != frmr->sg_nents)) { - pr_err("svcrdma: failed to map mr %p (%d/%d elements)\n", - frmr->mr, n, frmr->sg_nents); - return n < 0 ? n : -EINVAL; - } +/* The segment count is limited to how many segments can + * fit in the transport header without overflowing the + * buffer. That's about 60 Write segments for a 1KB inline + * threshold. + */ +static __be32 *xdr_check_write_chunk(__be32 *p, const __be32 *end, + u32 maxlen) +{ + u32 i, segcount; - /* Bump the key */ - key = (u8)(frmr->mr->lkey & 0x000000FF); - ib_update_fast_reg_key(frmr->mr, ++key); - - ctxt->sge[0].addr = frmr->mr->iova; - ctxt->sge[0].lkey = frmr->mr->lkey; - ctxt->sge[0].length = frmr->mr->length; - ctxt->count = 1; - ctxt->read_hdr = head; - - /* Prepare REG WR */ - ctxt->reg_cqe.done = svc_rdma_wc_reg; - reg_wr.wr.wr_cqe = &ctxt->reg_cqe; - reg_wr.wr.opcode = IB_WR_REG_MR; - reg_wr.wr.send_flags = IB_SEND_SIGNALED; - reg_wr.wr.num_sge = 0; - reg_wr.mr = frmr->mr; - reg_wr.key = frmr->mr->lkey; - reg_wr.access = frmr->access_flags; - reg_wr.wr.next = &read_wr.wr; - - /* Prepare RDMA_READ */ - memset(&read_wr, 0, sizeof(read_wr)); - ctxt->cqe.done = svc_rdma_wc_read; - read_wr.wr.wr_cqe = &ctxt->cqe; - read_wr.wr.send_flags = IB_SEND_SIGNALED; - read_wr.rkey = rs_handle; - read_wr.remote_addr = rs_offset; - read_wr.wr.sg_list = ctxt->sge; - read_wr.wr.num_sge = 1; - if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_READ_W_INV) { - read_wr.wr.opcode = IB_WR_RDMA_READ_WITH_INV; - read_wr.wr.ex.invalidate_rkey = ctxt->frmr->mr->lkey; - } else { - read_wr.wr.opcode = IB_WR_RDMA_READ; - read_wr.wr.next = &inv_wr; - /* Prepare invalidate */ - memset(&inv_wr, 0, sizeof(inv_wr)); - ctxt->inv_cqe.done = svc_rdma_wc_inv; - inv_wr.wr_cqe = &ctxt->inv_cqe; - inv_wr.opcode = IB_WR_LOCAL_INV; - inv_wr.send_flags = IB_SEND_SIGNALED | IB_SEND_FENCE; - inv_wr.ex.invalidate_rkey = frmr->mr->lkey; - } + segcount = be32_to_cpup(p++); + for (i = 0; i < segcount; i++) { + p++; /* handle */ + if (be32_to_cpup(p++) > maxlen) + return NULL; + p += 2; /* offset */ - /* Post the chain */ - ret = svc_rdma_send(xprt, ®_wr.wr); - if (ret) { - pr_err("svcrdma: Error %d posting RDMA_READ\n", ret); - set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); - goto err; + if (p > end) + return NULL; } - /* return current location in page array */ - *page_no = pg_no; - *page_offset = pg_off; - ret = read; - atomic_inc(&rdma_stat_read); - return ret; - err: - svc_rdma_put_context(ctxt, 0); - svc_rdma_put_frmr(xprt, frmr); - return ret; -} - -static unsigned int -rdma_rcl_chunk_count(struct rpcrdma_read_chunk *ch) -{ - unsigned int count; - - for (count = 0; ch->rc_discrim != xdr_zero; ch++) - count++; - return count; + return p; } -/* If there was additional inline content, append it to the end of arg.pages. - * Tail copy has to be done after the reader function has determined how many - * pages are needed for RDMA READ. +/* Sanity check the Write list. + * + * Implementation limits: + * - This implementation supports only one Write chunk. + * + * Sanity checks: + * - Write list does not overflow buffer. + * - Segment size limited by largest NFS data payload. + * + * Returns pointer to the following Reply chunk. */ -static int -rdma_copy_tail(struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *head, - u32 position, u32 byte_count, u32 page_offset, int page_no) +static __be32 *xdr_check_write_list(__be32 *p, const __be32 *end) { - char *srcp, *destp; - - srcp = head->arg.head[0].iov_base + position; - byte_count = head->arg.head[0].iov_len - position; - if (byte_count > PAGE_SIZE) { - dprintk("svcrdma: large tail unsupported\n"); - return 0; - } - - /* Fit as much of the tail on the current page as possible */ - if (page_offset != PAGE_SIZE) { - destp = page_address(rqstp->rq_arg.pages[page_no]); - destp += page_offset; - while (byte_count--) { - *destp++ = *srcp++; - page_offset++; - if (page_offset == PAGE_SIZE && byte_count) - goto more; - } - goto done; + u32 chcount; + + chcount = 0; + while (*p++ != xdr_zero) { + p = xdr_check_write_chunk(p, end, MAX_BYTES_WRITE_SEG); + if (!p) + return NULL; + if (chcount++ > 1) + return NULL; } - -more: - /* Fit the rest on the next page */ - page_no++; - destp = page_address(rqstp->rq_arg.pages[page_no]); - while (byte_count--) - *destp++ = *srcp++; - - rqstp->rq_respages = &rqstp->rq_arg.pages[page_no+1]; - rqstp->rq_next_page = rqstp->rq_respages + 1; - -done: - byte_count = head->arg.head[0].iov_len - position; - head->arg.page_len += byte_count; - head->arg.len += byte_count; - head->arg.buflen += byte_count; - return 1; + return p; } -/* Returns the address of the first read chunk or <nul> if no read chunk - * is present +/* Sanity check the Reply chunk. + * + * Sanity checks: + * - Reply chunk does not overflow buffer. + * - Segment size limited by largest NFS data payload. + * + * Returns pointer to the following RPC header. */ -static struct rpcrdma_read_chunk * -svc_rdma_get_read_chunk(struct rpcrdma_msg *rmsgp) +static __be32 *xdr_check_reply_chunk(__be32 *p, const __be32 *end) { - struct rpcrdma_read_chunk *ch = - (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0]; - - if (ch->rc_discrim == xdr_zero) - return NULL; - return ch; + if (*p++ != xdr_zero) { + p = xdr_check_write_chunk(p, end, MAX_BYTES_SPECIAL_SEG); + if (!p) + return NULL; + } + return p; } -static int rdma_read_chunks(struct svcxprt_rdma *xprt, - struct rpcrdma_msg *rmsgp, - struct svc_rqst *rqstp, - struct svc_rdma_op_ctxt *head) +/* On entry, xdr->head[0].iov_base points to first byte in the + * RPC-over-RDMA header. + * + * On successful exit, head[0] points to first byte past the + * RPC-over-RDMA header. For RDMA_MSG, this is the RPC message. + * The length of the RPC-over-RDMA header is returned. + * + * Assumptions: + * - The transport header is entirely contained in the head iovec. + */ +static int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg) { - int page_no, ret; - struct rpcrdma_read_chunk *ch; - u32 handle, page_offset, byte_count; - u32 position; - u64 rs_offset; - bool last; - - /* If no read list is present, return 0 */ - ch = svc_rdma_get_read_chunk(rmsgp); - if (!ch) - return 0; + __be32 *p, *end, *rdma_argp; + unsigned int hdr_len; + char *proc; + + /* Verify that there's enough bytes for header + something */ + if (rq_arg->len <= RPCRDMA_HDRLEN_ERR) + goto out_short; + + rdma_argp = rq_arg->head[0].iov_base; + if (*(rdma_argp + 1) != rpcrdma_version) + goto out_version; + + switch (*(rdma_argp + 3)) { + case rdma_msg: + proc = "RDMA_MSG"; + break; + case rdma_nomsg: + proc = "RDMA_NOMSG"; + break; + + case rdma_done: + goto out_drop; - if (rdma_rcl_chunk_count(ch) > RPCSVC_MAXPAGES) - return -EINVAL; - - /* The request is completed when the RDMA_READs complete. The - * head context keeps all the pages that comprise the - * request. - */ - head->arg.head[0] = rqstp->rq_arg.head[0]; - head->arg.tail[0] = rqstp->rq_arg.tail[0]; - head->hdr_count = head->count; - head->arg.page_base = 0; - head->arg.page_len = 0; - head->arg.len = rqstp->rq_arg.len; - head->arg.buflen = rqstp->rq_arg.buflen; - - /* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */ - position = be32_to_cpu(ch->rc_position); - if (position == 0) { - head->arg.pages = &head->pages[0]; - page_offset = head->byte_len; - } else { - head->arg.pages = &head->pages[head->count]; - page_offset = 0; - } + case rdma_error: + goto out_drop; - ret = 0; - page_no = 0; - for (; ch->rc_discrim != xdr_zero; ch++) { - if (be32_to_cpu(ch->rc_position) != position) - goto err; - - handle = be32_to_cpu(ch->rc_target.rs_handle), - byte_count = be32_to_cpu(ch->rc_target.rs_length); - xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset, - &rs_offset); - - while (byte_count > 0) { - last = (ch + 1)->rc_discrim == xdr_zero; - ret = xprt->sc_reader(xprt, rqstp, head, - &page_no, &page_offset, - handle, byte_count, - rs_offset, last); - if (ret < 0) - goto err; - byte_count -= ret; - rs_offset += ret; - head->arg.buflen += ret; - } + default: + goto out_proc; } - /* Read list may need XDR round-up (see RFC 5666, s. 3.7) */ - if (page_offset & 3) { - u32 pad = 4 - (page_offset & 3); - - head->arg.tail[0].iov_len += pad; - head->arg.len += pad; - head->arg.buflen += pad; - page_offset += pad; - } + end = (__be32 *)((unsigned long)rdma_argp + rq_arg->len); + p = xdr_check_read_list(rdma_argp + 4, end); + if (!p) + goto out_inval; + p = xdr_check_write_list(p, end); + if (!p) + goto out_inval; + p = xdr_check_reply_chunk(p, end); + if (!p) + goto out_inval; + if (p > end) + goto out_inval; + + rq_arg->head[0].iov_base = p; + hdr_len = (unsigned long)p - (unsigned long)rdma_argp; + rq_arg->head[0].iov_len -= hdr_len; + rq_arg->len -= hdr_len; + dprintk("svcrdma: received %s request for XID 0x%08x, hdr_len=%u\n", + proc, be32_to_cpup(rdma_argp), hdr_len); + return hdr_len; + +out_short: + dprintk("svcrdma: header too short = %d\n", rq_arg->len); + return -EINVAL; + +out_version: + dprintk("svcrdma: bad xprt version: %u\n", + be32_to_cpup(rdma_argp + 1)); + return -EPROTONOSUPPORT; - ret = 1; - if (position && position < head->arg.head[0].iov_len) - ret = rdma_copy_tail(rqstp, head, position, - byte_count, page_offset, page_no); - head->arg.head[0].iov_len = position; - head->position = position; +out_drop: + dprintk("svcrdma: dropping RDMA_DONE/ERROR message\n"); + return 0; - err: - /* Detach arg pages. svc_recv will replenish them */ - for (page_no = 0; - &rqstp->rq_pages[page_no] < rqstp->rq_respages; page_no++) - rqstp->rq_pages[page_no] = NULL; +out_proc: + dprintk("svcrdma: bad rdma procedure (%u)\n", + be32_to_cpup(rdma_argp + 3)); + return -EINVAL; - return ret; +out_inval: + dprintk("svcrdma: failed to parse transport header\n"); + return -EINVAL; } static void rdma_read_complete(struct svc_rqst *rqstp, @@ -528,24 +376,9 @@ static void rdma_read_complete(struct svc_rqst *rqstp, rqstp->rq_pages[page_no] = head->pages[page_no]; } - /* Adjustments made for RDMA_NOMSG type requests */ - if (head->position == 0) { - if (head->arg.len <= head->sge[0].length) { - head->arg.head[0].iov_len = head->arg.len - - head->byte_len; - head->arg.page_len = 0; - } else { - head->arg.head[0].iov_len = head->sge[0].length - - head->byte_len; - head->arg.page_len = head->arg.len - - head->sge[0].length; - } - } - /* Point rq_arg.pages past header */ rqstp->rq_arg.pages = &rqstp->rq_pages[head->hdr_count]; rqstp->rq_arg.page_len = head->arg.page_len; - rqstp->rq_arg.page_base = head->arg.page_base; /* rq_respages starts after the last arg page */ rqstp->rq_respages = &rqstp->rq_pages[page_no]; @@ -642,21 +475,44 @@ static bool svc_rdma_is_backchannel_reply(struct svc_xprt *xprt, return true; } -/* - * Set up the rqstp thread context to point to the RQ buffer. If - * necessary, pull additional data from the client with an RDMA_READ - * request. +/** + * svc_rdma_recvfrom - Receive an RPC call + * @rqstp: request structure into which to receive an RPC Call + * + * Returns: + * The positive number of bytes in the RPC Call message, + * %0 if there were no Calls ready to return, + * %-EINVAL if the Read chunk data is too large, + * %-ENOMEM if rdma_rw context pool was exhausted, + * %-ENOTCONN if posting failed (connection is lost), + * %-EIO if rdma_rw initialization failed (DMA mapping, etc). + * + * Called in a loop when XPT_DATA is set. XPT_DATA is cleared only + * when there are no remaining ctxt's to process. + * + * The next ctxt is removed from the "receive" lists. + * + * - If the ctxt completes a Read, then finish assembling the Call + * message and return the number of bytes in the message. + * + * - If the ctxt completes a Receive, then construct the Call + * message from the contents of the Receive buffer. + * + * - If there are no Read chunks in this message, then finish + * assembling the Call message and return the number of bytes + * in the message. + * + * - If there are Read chunks in this message, post Read WRs to + * pull that payload and return 0. */ int svc_rdma_recvfrom(struct svc_rqst *rqstp) { struct svc_xprt *xprt = rqstp->rq_xprt; struct svcxprt_rdma *rdma_xprt = container_of(xprt, struct svcxprt_rdma, sc_xprt); - struct svc_rdma_op_ctxt *ctxt = NULL; - struct rpcrdma_msg *rmsgp; - int ret = 0; - - dprintk("svcrdma: rqstp=%p\n", rqstp); + struct svc_rdma_op_ctxt *ctxt; + __be32 *p; + int ret; spin_lock(&rdma_xprt->sc_rq_dto_lock); if (!list_empty(&rdma_xprt->sc_read_complete_q)) { @@ -671,22 +527,14 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) struct svc_rdma_op_ctxt, list); list_del(&ctxt->list); } else { - atomic_inc(&rdma_stat_rq_starve); + /* No new incoming requests, terminate the loop */ clear_bit(XPT_DATA, &xprt->xpt_flags); - ctxt = NULL; + spin_unlock(&rdma_xprt->sc_rq_dto_lock); + return 0; } spin_unlock(&rdma_xprt->sc_rq_dto_lock); - if (!ctxt) { - /* This is the EAGAIN path. The svc_recv routine will - * return -EAGAIN, the nfsd thread will go to call into - * svc_recv again and we shouldn't be on the active - * transport list - */ - if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) - goto defer; - goto out; - } - dprintk("svcrdma: processing ctxt=%p on xprt=%p, rqstp=%p\n", + + dprintk("svcrdma: recvfrom: ctxt=%p on xprt=%p, rqstp=%p\n", ctxt, rdma_xprt, rqstp); atomic_inc(&rdma_stat_recv); @@ -694,7 +542,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) rdma_build_arg_xdr(rqstp, ctxt, ctxt->byte_len); /* Decode the RDMA header. */ - rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base; + p = (__be32 *)rqstp->rq_arg.head[0].iov_base; ret = svc_rdma_xdr_decode_req(&rqstp->rq_arg); if (ret < 0) goto out_err; @@ -702,9 +550,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) goto out_drop; rqstp->rq_xprt_hlen = ret; - if (svc_rdma_is_backchannel_reply(xprt, &rmsgp->rm_xid)) { - ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, - &rmsgp->rm_xid, + if (svc_rdma_is_backchannel_reply(xprt, p)) { + ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, p, &rqstp->rq_arg); svc_rdma_put_context(ctxt, 0); if (ret) @@ -712,39 +559,34 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) return ret; } - /* Read read-list data. */ - ret = rdma_read_chunks(rdma_xprt, rmsgp, rqstp, ctxt); - if (ret > 0) { - /* read-list posted, defer until data received from client. */ - goto defer; - } else if (ret < 0) { - /* Post of read-list failed, free context. */ - svc_rdma_put_context(ctxt, 1); - return 0; - } + p += rpcrdma_fixed_maxsz; + if (*p != xdr_zero) + goto out_readchunk; complete: - ret = rqstp->rq_arg.head[0].iov_len - + rqstp->rq_arg.page_len - + rqstp->rq_arg.tail[0].iov_len; svc_rdma_put_context(ctxt, 0); - out: - dprintk("svcrdma: ret=%d, rq_arg.len=%u, " - "rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len=%zd\n", - ret, rqstp->rq_arg.len, - rqstp->rq_arg.head[0].iov_base, - rqstp->rq_arg.head[0].iov_len); + dprintk("svcrdma: recvfrom: xprt=%p, rqstp=%p, rq_arg.len=%u\n", + rdma_xprt, rqstp, rqstp->rq_arg.len); rqstp->rq_prot = IPPROTO_MAX; svc_xprt_copy_addrs(rqstp, xprt); - return ret; + return rqstp->rq_arg.len; + +out_readchunk: + ret = svc_rdma_recv_read_chunk(rdma_xprt, rqstp, ctxt, p); + if (ret < 0) + goto out_postfail; + return 0; out_err: - svc_rdma_send_error(rdma_xprt, &rmsgp->rm_xid, ret); + svc_rdma_send_error(rdma_xprt, p, ret); svc_rdma_put_context(ctxt, 0); return 0; -defer: - return 0; +out_postfail: + if (ret == -EINVAL) + svc_rdma_send_error(rdma_xprt, p, ret); + svc_rdma_put_context(ctxt, 1); + return ret; out_drop: svc_rdma_put_context(ctxt, 1); diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 0cf620277693..933f79bed270 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -12,6 +12,9 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT +static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc); +static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc); + /* Each R/W context contains state for one chain of RDMA Read or * Write Work Requests. * @@ -113,22 +116,20 @@ struct svc_rdma_chunk_ctxt { struct svcxprt_rdma *cc_rdma; struct list_head cc_rwctxts; int cc_sqecount; - enum dma_data_direction cc_dir; }; static void svc_rdma_cc_init(struct svcxprt_rdma *rdma, - struct svc_rdma_chunk_ctxt *cc, - enum dma_data_direction dir) + struct svc_rdma_chunk_ctxt *cc) { cc->cc_rdma = rdma; svc_xprt_get(&rdma->sc_xprt); INIT_LIST_HEAD(&cc->cc_rwctxts); cc->cc_sqecount = 0; - cc->cc_dir = dir; } -static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc) +static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc, + enum dma_data_direction dir) { struct svcxprt_rdma *rdma = cc->cc_rdma; struct svc_rdma_rw_ctxt *ctxt; @@ -138,7 +139,7 @@ static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc) rdma_rw_ctx_destroy(&ctxt->rw_ctx, rdma->sc_qp, rdma->sc_port_num, ctxt->rw_sg_table.sgl, - ctxt->rw_nents, cc->cc_dir); + ctxt->rw_nents, dir); svc_rdma_put_rw_ctxt(rdma, ctxt); } svc_xprt_put(&rdma->sc_xprt); @@ -176,13 +177,14 @@ svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma, __be32 *chunk) info->wi_seg_no = 0; info->wi_nsegs = be32_to_cpup(++chunk); info->wi_segs = ++chunk; - svc_rdma_cc_init(rdma, &info->wi_cc, DMA_TO_DEVICE); + svc_rdma_cc_init(rdma, &info->wi_cc); + info->wi_cc.cc_cqe.done = svc_rdma_write_done; return info; } static void svc_rdma_write_info_free(struct svc_rdma_write_info *info) { - svc_rdma_cc_release(&info->wi_cc); + svc_rdma_cc_release(&info->wi_cc, DMA_TO_DEVICE); kfree(info); } @@ -216,6 +218,76 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc) svc_rdma_write_info_free(info); } +/* State for pulling a Read chunk. + */ +struct svc_rdma_read_info { + struct svc_rdma_op_ctxt *ri_readctxt; + unsigned int ri_position; + unsigned int ri_pageno; + unsigned int ri_pageoff; + unsigned int ri_chunklen; + + struct svc_rdma_chunk_ctxt ri_cc; +}; + +static struct svc_rdma_read_info * +svc_rdma_read_info_alloc(struct svcxprt_rdma *rdma) +{ + struct svc_rdma_read_info *info; + + info = kmalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return info; + + svc_rdma_cc_init(rdma, &info->ri_cc); + info->ri_cc.cc_cqe.done = svc_rdma_wc_read_done; + return info; +} + +static void svc_rdma_read_info_free(struct svc_rdma_read_info *info) +{ + svc_rdma_cc_release(&info->ri_cc, DMA_FROM_DEVICE); + kfree(info); +} + +/** + * svc_rdma_wc_read_done - Handle completion of an RDMA Read ctx + * @cq: controlling Completion Queue + * @wc: Work Completion + * + */ +static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc) +{ + struct ib_cqe *cqe = wc->wr_cqe; + struct svc_rdma_chunk_ctxt *cc = + container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe); + struct svcxprt_rdma *rdma = cc->cc_rdma; + struct svc_rdma_read_info *info = + container_of(cc, struct svc_rdma_read_info, ri_cc); + + atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail); + wake_up(&rdma->sc_send_wait); + + if (unlikely(wc->status != IB_WC_SUCCESS)) { + set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags); + if (wc->status != IB_WC_WR_FLUSH_ERR) + pr_err("svcrdma: read ctx: %s (%u/0x%x)\n", + ib_wc_status_msg(wc->status), + wc->status, wc->vendor_err); + svc_rdma_put_context(info->ri_readctxt, 1); + } else { + spin_lock(&rdma->sc_rq_dto_lock); + list_add_tail(&info->ri_readctxt->list, + &rdma->sc_read_complete_q); + spin_unlock(&rdma->sc_rq_dto_lock); + + set_bit(XPT_DATA, &rdma->sc_xprt.xpt_flags); + svc_xprt_enqueue(&rdma->sc_xprt); + } + + svc_rdma_read_info_free(info); +} + /* This function sleeps when the transport's Send Queue is congested. * * Assumptions: @@ -232,6 +304,9 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc) struct ib_cqe *cqe; int ret; + if (cc->cc_sqecount > rdma->sc_sq_depth) + return -EINVAL; + first_wr = NULL; cqe = &cc->cc_cqe; list_for_each(tmp, &cc->cc_rwctxts) { @@ -295,8 +370,9 @@ static void svc_rdma_pagelist_to_sg(struct svc_rdma_write_info *info, struct scatterlist *sg; struct page **page; - page_off = (info->wi_next_off + xdr->page_base) & ~PAGE_MASK; - page_no = (info->wi_next_off + xdr->page_base) >> PAGE_SHIFT; + page_off = info->wi_next_off + xdr->page_base; + page_no = page_off >> PAGE_SHIFT; + page_off = offset_in_page(page_off); page = xdr->pages + page_no; info->wi_next_off += remaining; sg = ctxt->rw_sg_table.sgl; @@ -332,7 +408,6 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info, __be32 *seg; int ret; - cc->cc_cqe.done = svc_rdma_write_done; seg = info->wi_segs + info->wi_seg_no * rpcrdma_segment_maxsz; do { unsigned int write_len; @@ -425,6 +500,7 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info, * * Returns a non-negative number of bytes the chunk consumed, or * %-E2BIG if the payload was larger than the Write chunk, + * %-EINVAL if client provided too many segments, * %-ENOMEM if rdma_rw context pool was exhausted, * %-ENOTCONN if posting failed (connection is lost), * %-EIO if rdma_rw initialization failed (DMA mapping, etc). @@ -465,6 +541,7 @@ out_err: * * Returns a non-negative number of bytes the chunk consumed, or * %-E2BIG if the payload was larger than the Reply chunk, + * %-EINVAL if client provided too many segments, * %-ENOMEM if rdma_rw context pool was exhausted, * %-ENOTCONN if posting failed (connection is lost), * %-EIO if rdma_rw initialization failed (DMA mapping, etc). @@ -510,3 +587,353 @@ out_err: svc_rdma_write_info_free(info); return ret; } + +static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info, + struct svc_rqst *rqstp, + u32 rkey, u32 len, u64 offset) +{ + struct svc_rdma_op_ctxt *head = info->ri_readctxt; + struct svc_rdma_chunk_ctxt *cc = &info->ri_cc; + struct svc_rdma_rw_ctxt *ctxt; + unsigned int sge_no, seg_len; + struct scatterlist *sg; + int ret; + + sge_no = PAGE_ALIGN(info->ri_pageoff + len) >> PAGE_SHIFT; + ctxt = svc_rdma_get_rw_ctxt(cc->cc_rdma, sge_no); + if (!ctxt) + goto out_noctx; + ctxt->rw_nents = sge_no; + + dprintk("svcrdma: reading segment %u@0x%016llx:0x%08x (%u sges)\n", + len, offset, rkey, sge_no); + + sg = ctxt->rw_sg_table.sgl; + for (sge_no = 0; sge_no < ctxt->rw_nents; sge_no++) { + seg_len = min_t(unsigned int, len, + PAGE_SIZE - info->ri_pageoff); + + head->arg.pages[info->ri_pageno] = + rqstp->rq_pages[info->ri_pageno]; + if (!info->ri_pageoff) + head->count++; + + sg_set_page(sg, rqstp->rq_pages[info->ri_pageno], + seg_len, info->ri_pageoff); + sg = sg_next(sg); + + info->ri_pageoff += seg_len; + if (info->ri_pageoff == PAGE_SIZE) { + info->ri_pageno++; + info->ri_pageoff = 0; + } + len -= seg_len; + + /* Safety check */ + if (len && + &rqstp->rq_pages[info->ri_pageno + 1] > rqstp->rq_page_end) + goto out_overrun; + } + + ret = rdma_rw_ctx_init(&ctxt->rw_ctx, cc->cc_rdma->sc_qp, + cc->cc_rdma->sc_port_num, + ctxt->rw_sg_table.sgl, ctxt->rw_nents, + 0, offset, rkey, DMA_FROM_DEVICE); + if (ret < 0) + goto out_initerr; + + list_add(&ctxt->rw_list, &cc->cc_rwctxts); + cc->cc_sqecount += ret; + return 0; + +out_noctx: + dprintk("svcrdma: no R/W ctxs available\n"); + return -ENOMEM; + +out_overrun: + dprintk("svcrdma: request overruns rq_pages\n"); + return -EINVAL; + +out_initerr: + svc_rdma_put_rw_ctxt(cc->cc_rdma, ctxt); + pr_err("svcrdma: failed to map pagelist (%d)\n", ret); + return -EIO; +} + +static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, + struct svc_rdma_read_info *info, + __be32 *p) +{ + int ret; + + info->ri_chunklen = 0; + while (*p++ != xdr_zero) { + u32 rs_handle, rs_length; + u64 rs_offset; + + if (be32_to_cpup(p++) != info->ri_position) + break; + rs_handle = be32_to_cpup(p++); + rs_length = be32_to_cpup(p++); + p = xdr_decode_hyper(p, &rs_offset); + + ret = svc_rdma_build_read_segment(info, rqstp, + rs_handle, rs_length, + rs_offset); + if (ret < 0) + break; + + info->ri_chunklen += rs_length; + } + + return ret; +} + +/* If there is inline content following the Read chunk, append it to + * the page list immediately following the data payload. This has to + * be done after the reader function has determined how many pages + * were consumed for RDMA Read. + * + * On entry, ri_pageno and ri_pageoff point directly to the end of the + * page list. On exit, both have been updated to the new "next byte". + * + * Assumptions: + * - Inline content fits entirely in rq_pages[0] + * - Trailing content is only a handful of bytes + */ +static int svc_rdma_copy_tail(struct svc_rqst *rqstp, + struct svc_rdma_read_info *info) +{ + struct svc_rdma_op_ctxt *head = info->ri_readctxt; + unsigned int tail_length, remaining; + u8 *srcp, *destp; + + /* Assert that all inline content fits in page 0. This is an + * implementation limit, not a protocol limit. + */ + if (head->arg.head[0].iov_len > PAGE_SIZE) { + pr_warn_once("svcrdma: too much trailing inline content\n"); + return -EINVAL; + } + + srcp = head->arg.head[0].iov_base; + srcp += info->ri_position; + tail_length = head->arg.head[0].iov_len - info->ri_position; + remaining = tail_length; + + /* If there is room on the last page in the page list, try to + * fit the trailing content there. + */ + if (info->ri_pageoff > 0) { + unsigned int len; + + len = min_t(unsigned int, remaining, + PAGE_SIZE - info->ri_pageoff); + destp = page_address(rqstp->rq_pages[info->ri_pageno]); + destp += info->ri_pageoff; + + memcpy(destp, srcp, len); + srcp += len; + destp += len; + info->ri_pageoff += len; + remaining -= len; + + if (info->ri_pageoff == PAGE_SIZE) { + info->ri_pageno++; + info->ri_pageoff = 0; + } + } + + /* Otherwise, a fresh page is needed. */ + if (remaining) { + head->arg.pages[info->ri_pageno] = + rqstp->rq_pages[info->ri_pageno]; + head->count++; + + destp = page_address(rqstp->rq_pages[info->ri_pageno]); + memcpy(destp, srcp, remaining); + info->ri_pageoff += remaining; + } + + head->arg.page_len += tail_length; + head->arg.len += tail_length; + head->arg.buflen += tail_length; + return 0; +} + +/* Construct RDMA Reads to pull over a normal Read chunk. The chunk + * data lands in the page list of head->arg.pages. + * + * Currently NFSD does not look at the head->arg.tail[0] iovec. + * Therefore, XDR round-up of the Read chunk and trailing + * inline content must both be added at the end of the pagelist. + */ +static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp, + struct svc_rdma_read_info *info, + __be32 *p) +{ + struct svc_rdma_op_ctxt *head = info->ri_readctxt; + int ret; + + dprintk("svcrdma: Reading Read chunk at position %u\n", + info->ri_position); + + info->ri_pageno = head->hdr_count; + info->ri_pageoff = 0; + + ret = svc_rdma_build_read_chunk(rqstp, info, p); + if (ret < 0) + goto out; + + /* Read chunk may need XDR round-up (see RFC 5666, s. 3.7). + */ + if (info->ri_chunklen & 3) { + u32 padlen = 4 - (info->ri_chunklen & 3); + + info->ri_chunklen += padlen; + + /* NB: data payload always starts on XDR alignment, + * thus the pad can never contain a page boundary. + */ + info->ri_pageoff += padlen; + if (info->ri_pageoff == PAGE_SIZE) { + info->ri_pageno++; + info->ri_pageoff = 0; + } + } + + head->arg.page_len = info->ri_chunklen; + head->arg.len += info->ri_chunklen; + head->arg.buflen += info->ri_chunklen; + + if (info->ri_position < head->arg.head[0].iov_len) { + ret = svc_rdma_copy_tail(rqstp, info); + if (ret < 0) + goto out; + } + head->arg.head[0].iov_len = info->ri_position; + +out: + return ret; +} + +/* Construct RDMA Reads to pull over a Position Zero Read chunk. + * The start of the data lands in the first page just after + * the Transport header, and the rest lands in the page list of + * head->arg.pages. + * + * Assumptions: + * - A PZRC has an XDR-aligned length (no implicit round-up). + * - There can be no trailing inline content (IOW, we assume + * a PZRC is never sent in an RDMA_MSG message, though it's + * allowed by spec). + */ +static int svc_rdma_build_pz_read_chunk(struct svc_rqst *rqstp, + struct svc_rdma_read_info *info, + __be32 *p) +{ + struct svc_rdma_op_ctxt *head = info->ri_readctxt; + int ret; + + dprintk("svcrdma: Reading Position Zero Read chunk\n"); + + info->ri_pageno = head->hdr_count - 1; + info->ri_pageoff = offset_in_page(head->byte_len); + + ret = svc_rdma_build_read_chunk(rqstp, info, p); + if (ret < 0) + goto out; + + head->arg.len += info->ri_chunklen; + head->arg.buflen += info->ri_chunklen; + + if (head->arg.buflen <= head->sge[0].length) { + /* Transport header and RPC message fit entirely + * in page where head iovec resides. + */ + head->arg.head[0].iov_len = info->ri_chunklen; + } else { + /* Transport header and part of RPC message reside + * in the head iovec's page. + */ + head->arg.head[0].iov_len = + head->sge[0].length - head->byte_len; + head->arg.page_len = + info->ri_chunklen - head->arg.head[0].iov_len; + } + +out: + return ret; +} + +/** + * svc_rdma_recv_read_chunk - Pull a Read chunk from the client + * @rdma: controlling RDMA transport + * @rqstp: set of pages to use as Read sink buffers + * @head: pages under I/O collect here + * @p: pointer to start of Read chunk + * + * Returns: + * %0 if all needed RDMA Reads were posted successfully, + * %-EINVAL if client provided too many segments, + * %-ENOMEM if rdma_rw context pool was exhausted, + * %-ENOTCONN if posting failed (connection is lost), + * %-EIO if rdma_rw initialization failed (DMA mapping, etc). + * + * Assumptions: + * - All Read segments in @p have the same Position value. + */ +int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp, + struct svc_rdma_op_ctxt *head, __be32 *p) +{ + struct svc_rdma_read_info *info; + struct page **page; + int ret; + + /* The request (with page list) is constructed in + * head->arg. Pages involved with RDMA Read I/O are + * transferred there. + */ + head->hdr_count = head->count; + head->arg.head[0] = rqstp->rq_arg.head[0]; + head->arg.tail[0] = rqstp->rq_arg.tail[0]; + head->arg.pages = head->pages; + head->arg.page_base = 0; + head->arg.page_len = 0; + head->arg.len = rqstp->rq_arg.len; + head->arg.buflen = rqstp->rq_arg.buflen; + + info = svc_rdma_read_info_alloc(rdma); + if (!info) + return -ENOMEM; + info->ri_readctxt = head; + + info->ri_position = be32_to_cpup(p + 1); + if (info->ri_position) + ret = svc_rdma_build_normal_read_chunk(rqstp, info, p); + else + ret = svc_rdma_build_pz_read_chunk(rqstp, info, p); + + /* Mark the start of the pages that can be used for the reply */ + if (info->ri_pageoff > 0) + info->ri_pageno++; + rqstp->rq_respages = &rqstp->rq_pages[info->ri_pageno]; + rqstp->rq_next_page = rqstp->rq_respages + 1; + + if (ret < 0) + goto out; + + ret = svc_rdma_post_chunk_ctxt(&info->ri_cc); + +out: + /* Read sink pages have been moved from rqstp->rq_pages to + * head->arg.pages. Force svc_recv to refill those slots + * in rq_pages. + */ + for (page = rqstp->rq_pages; page < rqstp->rq_respages; page++) + *page = NULL; + + if (ret < 0) + svc_rdma_read_info_free(info); + return ret; +} diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 1736337f3a55..7c3a211e0e9a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -313,13 +313,17 @@ static int svc_rdma_dma_map_buf(struct svcxprt_rdma *rdma, dma_addr = ib_dma_map_page(dev, virt_to_page(base), offset, len, DMA_TO_DEVICE); if (ib_dma_mapping_error(dev, dma_addr)) - return -EIO; + goto out_maperr; ctxt->sge[sge_no].addr = dma_addr; ctxt->sge[sge_no].length = len; ctxt->sge[sge_no].lkey = rdma->sc_pd->local_dma_lkey; svc_rdma_count_mappings(rdma, ctxt); return 0; + +out_maperr: + pr_err("svcrdma: failed to map buffer\n"); + return -EIO; } static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma, @@ -334,13 +338,17 @@ static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma, dma_addr = ib_dma_map_page(dev, page, offset, len, DMA_TO_DEVICE); if (ib_dma_mapping_error(dev, dma_addr)) - return -EIO; + goto out_maperr; ctxt->sge[sge_no].addr = dma_addr; ctxt->sge[sge_no].length = len; ctxt->sge[sge_no].lkey = rdma->sc_pd->local_dma_lkey; svc_rdma_count_mappings(rdma, ctxt); return 0; + +out_maperr: + pr_err("svcrdma: failed to map page\n"); + return -EIO; } /** @@ -547,7 +555,6 @@ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma, return 0; err: - pr_err("svcrdma: failed to post Send WR (%d)\n", ret); svc_rdma_unmap_dma(ctxt); svc_rdma_put_context(ctxt, 1); return ret; @@ -677,7 +684,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) return 0; err2: - if (ret != -E2BIG) + if (ret != -E2BIG && ret != -EINVAL) goto err1; ret = svc_rdma_post_recv(rdma, GFP_KERNEL); diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index a9d9cb1ba4c6..e660d4965b18 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -202,7 +202,6 @@ struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) out: ctxt->count = 0; ctxt->mapped_sges = 0; - ctxt->frmr = NULL; return ctxt; out_empty: @@ -226,22 +225,13 @@ void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt) { struct svcxprt_rdma *xprt = ctxt->xprt; struct ib_device *device = xprt->sc_cm_id->device; - u32 lkey = xprt->sc_pd->local_dma_lkey; unsigned int i; - for (i = 0; i < ctxt->mapped_sges; i++) { - /* - * Unmap the DMA addr in the SGE if the lkey matches - * the local_dma_lkey, otherwise, ignore it since it is - * an FRMR lkey and will be unmapped later when the - * last WR that uses it completes. - */ - if (ctxt->sge[i].lkey == lkey) - ib_dma_unmap_page(device, - ctxt->sge[i].addr, - ctxt->sge[i].length, - ctxt->direction); - } + for (i = 0; i < ctxt->mapped_sges; i++) + ib_dma_unmap_page(device, + ctxt->sge[i].addr, + ctxt->sge[i].length, + ctxt->direction); ctxt->mapped_sges = 0; } @@ -346,36 +336,6 @@ out: svc_xprt_put(&xprt->sc_xprt); } -static void svc_rdma_send_wc_common(struct svcxprt_rdma *xprt, - struct ib_wc *wc, - const char *opname) -{ - if (wc->status != IB_WC_SUCCESS) - goto err; - -out: - atomic_inc(&xprt->sc_sq_avail); - wake_up(&xprt->sc_send_wait); - return; - -err: - set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); - if (wc->status != IB_WC_WR_FLUSH_ERR) - pr_err("svcrdma: %s: %s (%u/0x%x)\n", - opname, ib_wc_status_msg(wc->status), - wc->status, wc->vendor_err); - goto out; -} - -static void svc_rdma_send_wc_common_put(struct ib_cq *cq, struct ib_wc *wc, - const char *opname) -{ - struct svcxprt_rdma *xprt = cq->cq_context; - - svc_rdma_send_wc_common(xprt, wc, opname); - svc_xprt_put(&xprt->sc_xprt); -} - /** * svc_rdma_wc_send - Invoked by RDMA provider for each polled Send WC * @cq: completion queue @@ -384,73 +344,28 @@ static void svc_rdma_send_wc_common_put(struct ib_cq *cq, struct ib_wc *wc, */ void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) { - struct ib_cqe *cqe = wc->wr_cqe; - struct svc_rdma_op_ctxt *ctxt; - - svc_rdma_send_wc_common_put(cq, wc, "send"); - - ctxt = container_of(cqe, struct svc_rdma_op_ctxt, cqe); - svc_rdma_unmap_dma(ctxt); - svc_rdma_put_context(ctxt, 1); -} - -/** - * svc_rdma_wc_reg - Invoked by RDMA provider for each polled FASTREG WC - * @cq: completion queue - * @wc: completed WR - * - */ -void svc_rdma_wc_reg(struct ib_cq *cq, struct ib_wc *wc) -{ - svc_rdma_send_wc_common_put(cq, wc, "fastreg"); -} - -/** - * svc_rdma_wc_read - Invoked by RDMA provider for each polled Read WC - * @cq: completion queue - * @wc: completed WR - * - */ -void svc_rdma_wc_read(struct ib_cq *cq, struct ib_wc *wc) -{ struct svcxprt_rdma *xprt = cq->cq_context; struct ib_cqe *cqe = wc->wr_cqe; struct svc_rdma_op_ctxt *ctxt; - svc_rdma_send_wc_common(xprt, wc, "read"); + atomic_inc(&xprt->sc_sq_avail); + wake_up(&xprt->sc_send_wait); ctxt = container_of(cqe, struct svc_rdma_op_ctxt, cqe); svc_rdma_unmap_dma(ctxt); - svc_rdma_put_frmr(xprt, ctxt->frmr); - - if (test_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags)) { - struct svc_rdma_op_ctxt *read_hdr; - - read_hdr = ctxt->read_hdr; - spin_lock(&xprt->sc_rq_dto_lock); - list_add_tail(&read_hdr->list, - &xprt->sc_read_complete_q); - spin_unlock(&xprt->sc_rq_dto_lock); + svc_rdma_put_context(ctxt, 1); - set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags); - svc_xprt_enqueue(&xprt->sc_xprt); + if (unlikely(wc->status != IB_WC_SUCCESS)) { + set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); + if (wc->status != IB_WC_WR_FLUSH_ERR) + pr_err("svcrdma: Send: %s (%u/0x%x)\n", + ib_wc_status_msg(wc->status), + wc->status, wc->vendor_err); } - svc_rdma_put_context(ctxt, 0); svc_xprt_put(&xprt->sc_xprt); } -/** - * svc_rdma_wc_inv - Invoked by RDMA provider for each polled LOCAL_INV WC - * @cq: completion queue - * @wc: completed WR - * - */ -void svc_rdma_wc_inv(struct ib_cq *cq, struct ib_wc *wc) -{ - svc_rdma_send_wc_common_put(cq, wc, "localInv"); -} - static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, int listener) { @@ -462,14 +377,12 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, INIT_LIST_HEAD(&cma_xprt->sc_accept_q); INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q); INIT_LIST_HEAD(&cma_xprt->sc_read_complete_q); - INIT_LIST_HEAD(&cma_xprt->sc_frmr_q); INIT_LIST_HEAD(&cma_xprt->sc_ctxts); INIT_LIST_HEAD(&cma_xprt->sc_rw_ctxts); init_waitqueue_head(&cma_xprt->sc_send_wait); spin_lock_init(&cma_xprt->sc_lock); spin_lock_init(&cma_xprt->sc_rq_dto_lock); - spin_lock_init(&cma_xprt->sc_frmr_q_lock); spin_lock_init(&cma_xprt->sc_ctxt_lock); spin_lock_init(&cma_xprt->sc_rw_ctxt_lock); @@ -780,86 +693,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, return ERR_PTR(ret); } -static struct svc_rdma_fastreg_mr *rdma_alloc_frmr(struct svcxprt_rdma *xprt) -{ - struct ib_mr *mr; - struct scatterlist *sg; - struct svc_rdma_fastreg_mr *frmr; - u32 num_sg; - - frmr = kmalloc(sizeof(*frmr), GFP_KERNEL); - if (!frmr) - goto err; - - num_sg = min_t(u32, RPCSVC_MAXPAGES, xprt->sc_frmr_pg_list_len); - mr = ib_alloc_mr(xprt->sc_pd, IB_MR_TYPE_MEM_REG, num_sg); - if (IS_ERR(mr)) - goto err_free_frmr; - - sg = kcalloc(RPCSVC_MAXPAGES, sizeof(*sg), GFP_KERNEL); - if (!sg) - goto err_free_mr; - - sg_init_table(sg, RPCSVC_MAXPAGES); - - frmr->mr = mr; - frmr->sg = sg; - INIT_LIST_HEAD(&frmr->frmr_list); - return frmr; - - err_free_mr: - ib_dereg_mr(mr); - err_free_frmr: - kfree(frmr); - err: - return ERR_PTR(-ENOMEM); -} - -static void rdma_dealloc_frmr_q(struct svcxprt_rdma *xprt) -{ - struct svc_rdma_fastreg_mr *frmr; - - while (!list_empty(&xprt->sc_frmr_q)) { - frmr = list_entry(xprt->sc_frmr_q.next, - struct svc_rdma_fastreg_mr, frmr_list); - list_del_init(&frmr->frmr_list); - kfree(frmr->sg); - ib_dereg_mr(frmr->mr); - kfree(frmr); - } -} - -struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *rdma) -{ - struct svc_rdma_fastreg_mr *frmr = NULL; - - spin_lock(&rdma->sc_frmr_q_lock); - if (!list_empty(&rdma->sc_frmr_q)) { - frmr = list_entry(rdma->sc_frmr_q.next, - struct svc_rdma_fastreg_mr, frmr_list); - list_del_init(&frmr->frmr_list); - frmr->sg_nents = 0; - } - spin_unlock(&rdma->sc_frmr_q_lock); - if (frmr) - return frmr; - - return rdma_alloc_frmr(rdma); -} - -void svc_rdma_put_frmr(struct svcxprt_rdma *rdma, - struct svc_rdma_fastreg_mr *frmr) -{ - if (frmr) { - ib_dma_unmap_sg(rdma->sc_cm_id->device, - frmr->sg, frmr->sg_nents, frmr->direction); - spin_lock(&rdma->sc_frmr_q_lock); - WARN_ON_ONCE(!list_empty(&frmr->frmr_list)); - list_add(&frmr->frmr_list, &rdma->sc_frmr_q); - spin_unlock(&rdma->sc_frmr_q_lock); - } -} - /* * This is the xpo_recvfrom function for listening endpoints. Its * purpose is to accept incoming connections. The CMA callback handler @@ -908,8 +741,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) * capabilities of this particular device */ newxprt->sc_max_sge = min((size_t)dev->attrs.max_sge, (size_t)RPCSVC_MAXPAGES); - newxprt->sc_max_sge_rd = min_t(size_t, dev->attrs.max_sge_rd, - RPCSVC_MAXPAGES); newxprt->sc_max_req_size = svcrdma_max_req_size; newxprt->sc_max_requests = min_t(u32, dev->attrs.max_qp_wr, svcrdma_max_requests); @@ -952,7 +783,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) memset(&qp_attr, 0, sizeof qp_attr); qp_attr.event_handler = qp_event_handler; qp_attr.qp_context = &newxprt->sc_xprt; - qp_attr.port_num = newxprt->sc_cm_id->port_num; + qp_attr.port_num = newxprt->sc_port_num; qp_attr.cap.max_rdma_ctxs = newxprt->sc_max_requests; qp_attr.cap.max_send_wr = newxprt->sc_sq_depth; qp_attr.cap.max_recv_wr = newxprt->sc_rq_depth; @@ -976,47 +807,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) } newxprt->sc_qp = newxprt->sc_cm_id->qp; - /* - * Use the most secure set of MR resources based on the - * transport type and available memory management features in - * the device. Here's the table implemented below: - * - * Fast Global DMA Remote WR - * Reg LKEY MR Access - * Sup'd Sup'd Needed Needed - * - * IWARP N N Y Y - * N Y Y Y - * Y N Y N - * Y Y N - - * - * IB N N Y N - * N Y N - - * Y N Y N - * Y Y N - - * - * NB: iWARP requires remote write access for the data sink - * of an RDMA_READ. IB does not. - */ - newxprt->sc_reader = rdma_read_chunk_lcl; - if (dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) { - newxprt->sc_frmr_pg_list_len = - dev->attrs.max_fast_reg_page_list_len; - newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_FAST_REG; - newxprt->sc_reader = rdma_read_chunk_frmr; - } else + if (!(dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS)) newxprt->sc_snd_w_inv = false; - - /* - * Determine if a DMA MR is required and if so, what privs are required - */ - if (!rdma_protocol_iwarp(dev, newxprt->sc_cm_id->port_num) && - !rdma_ib_or_roce(dev, newxprt->sc_cm_id->port_num)) + if (!rdma_protocol_iwarp(dev, newxprt->sc_port_num) && + !rdma_ib_or_roce(dev, newxprt->sc_port_num)) goto errout; - if (rdma_protocol_iwarp(dev, newxprt->sc_cm_id->port_num)) - newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_READ_W_INV; - /* Post receive buffers */ for (i = 0; i < newxprt->sc_max_requests; i++) { ret = svc_rdma_post_recv(newxprt, GFP_KERNEL); @@ -1056,7 +852,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) sap = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr; dprintk(" remote address : %pIS:%u\n", sap, rpc_get_port(sap)); dprintk(" max_sge : %d\n", newxprt->sc_max_sge); - dprintk(" max_sge_rd : %d\n", newxprt->sc_max_sge_rd); dprintk(" sq_depth : %d\n", newxprt->sc_sq_depth); dprintk(" max_requests : %d\n", newxprt->sc_max_requests); dprintk(" ord : %d\n", newxprt->sc_ord); @@ -1117,12 +912,6 @@ static void __svc_rdma_free(struct work_struct *work) pr_err("svcrdma: sc_xprt still in use? (%d)\n", kref_read(&xprt->xpt_ref)); - /* - * Destroy queued, but not processed read completions. Note - * that this cleanup has to be done before destroying the - * cm_id because the device ptr is needed to unmap the dma in - * svc_rdma_put_context. - */ while (!list_empty(&rdma->sc_read_complete_q)) { struct svc_rdma_op_ctxt *ctxt; ctxt = list_first_entry(&rdma->sc_read_complete_q, @@ -1130,8 +919,6 @@ static void __svc_rdma_free(struct work_struct *work) list_del(&ctxt->list); svc_rdma_put_context(ctxt, 1); } - - /* Destroy queued, but not processed recv completions */ while (!list_empty(&rdma->sc_rq_dto_q)) { struct svc_rdma_op_ctxt *ctxt; ctxt = list_first_entry(&rdma->sc_rq_dto_q, @@ -1151,7 +938,6 @@ static void __svc_rdma_free(struct work_struct *work) xprt->xpt_bc_xprt = NULL; } - rdma_dealloc_frmr_q(rdma); svc_rdma_destroy_rw_ctxts(rdma); svc_rdma_destroy_ctxts(rdma); diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 62ecbccd9748..d1c458e5ec4d 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -684,7 +684,8 @@ xprt_rdma_free(struct rpc_task *task) dprintk("RPC: %s: called on 0x%p\n", __func__, req->rl_reply); - if (unlikely(!list_empty(&req->rl_registered))) + rpcrdma_remove_req(&r_xprt->rx_buf, req); + if (!list_empty(&req->rl_registered)) ia->ri_ops->ro_unmap_safe(r_xprt, req, !RPC_IS_ASYNC(task)); rpcrdma_unmap_sges(ia, req); rpcrdma_buffer_put(req); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 3dbce9ac4327..e4171f2abe37 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -243,8 +243,6 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct sockaddr *sap = (struct sockaddr *)&ep->rep_remote_addr; #endif - struct ib_qp_attr *attr = &ia->ri_qp_attr; - struct ib_qp_init_attr *iattr = &ia->ri_qp_init_attr; int connstate = 0; switch (event->event) { @@ -267,7 +265,8 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) break; case RDMA_CM_EVENT_DEVICE_REMOVAL: #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) - pr_info("rpcrdma: removing device for %pIS:%u\n", + pr_info("rpcrdma: removing device %s for %pIS:%u\n", + ia->ri_device->name, sap, rpc_get_port(sap)); #endif set_bit(RPCRDMA_IAF_REMOVING, &ia->ri_flags); @@ -282,13 +281,6 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) return 1; case RDMA_CM_EVENT_ESTABLISHED: connstate = 1; - ib_query_qp(ia->ri_id->qp, attr, - IB_QP_MAX_QP_RD_ATOMIC | IB_QP_MAX_DEST_RD_ATOMIC, - iattr); - dprintk("RPC: %s: %d responder resources" - " (%d initiator)\n", - __func__, attr->max_dest_rd_atomic, - attr->max_rd_atomic); rpcrdma_update_connect_private(xprt, &event->param.conn); goto connected; case RDMA_CM_EVENT_CONNECT_ERROR: @@ -298,11 +290,9 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) connstate = -ENETDOWN; goto connected; case RDMA_CM_EVENT_REJECTED: -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) - pr_info("rpcrdma: connection to %pIS:%u on %s rejected: %s\n", - sap, rpc_get_port(sap), ia->ri_device->name, + dprintk("rpcrdma: connection to %pIS:%u rejected: %s\n", + sap, rpc_get_port(sap), rdma_reject_msg(id, event->status)); -#endif connstate = -ECONNREFUSED; if (event->status == IB_CM_REJ_STALE_CONN) connstate = -EAGAIN; @@ -310,37 +300,19 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) case RDMA_CM_EVENT_DISCONNECTED: connstate = -ECONNABORTED; connected: - dprintk("RPC: %s: %sconnected\n", - __func__, connstate > 0 ? "" : "dis"); atomic_set(&xprt->rx_buf.rb_credits, 1); ep->rep_connected = connstate; rpcrdma_conn_func(ep); wake_up_all(&ep->rep_connect_wait); /*FALLTHROUGH*/ default: - dprintk("RPC: %s: %pIS:%u (ep 0x%p): %s\n", - __func__, sap, rpc_get_port(sap), ep, - rdma_event_msg(event->event)); + dprintk("RPC: %s: %pIS:%u on %s/%s (ep 0x%p): %s\n", + __func__, sap, rpc_get_port(sap), + ia->ri_device->name, ia->ri_ops->ro_displayname, + ep, rdma_event_msg(event->event)); break; } -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) - if (connstate == 1) { - int ird = attr->max_dest_rd_atomic; - int tird = ep->rep_remote_cma.responder_resources; - - pr_info("rpcrdma: connection to %pIS:%u on %s, memreg '%s', %d credits, %d responders%s\n", - sap, rpc_get_port(sap), - ia->ri_device->name, - ia->ri_ops->ro_displayname, - xprt->rx_buf.rb_max_requests, - ird, ird < 4 && ird < tird / 2 ? " (low!)" : ""); - } else if (connstate < 0) { - pr_info("rpcrdma: connection to %pIS:%u closed (%d)\n", - sap, rpc_get_port(sap), connstate); - } -#endif - return 0; } @@ -971,7 +943,6 @@ rpcrdma_create_req(struct rpcrdma_xprt *r_xprt) if (req == NULL) return ERR_PTR(-ENOMEM); - INIT_LIST_HEAD(&req->rl_free); spin_lock(&buffer->rb_reqslock); list_add(&req->rl_all, &buffer->rb_allreqs); spin_unlock(&buffer->rb_reqslock); @@ -1033,6 +1004,7 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) spin_lock_init(&buf->rb_recovery_lock); INIT_LIST_HEAD(&buf->rb_mws); INIT_LIST_HEAD(&buf->rb_all); + INIT_LIST_HEAD(&buf->rb_pending); INIT_LIST_HEAD(&buf->rb_stale_mrs); INIT_DELAYED_WORK(&buf->rb_refresh_worker, rpcrdma_mr_refresh_worker); @@ -1055,7 +1027,7 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) goto out; } req->rl_backchannel = false; - list_add(&req->rl_free, &buf->rb_send_bufs); + list_add(&req->rl_list, &buf->rb_send_bufs); } INIT_LIST_HEAD(&buf->rb_recv_bufs); @@ -1084,8 +1056,8 @@ rpcrdma_buffer_get_req_locked(struct rpcrdma_buffer *buf) struct rpcrdma_req *req; req = list_first_entry(&buf->rb_send_bufs, - struct rpcrdma_req, rl_free); - list_del(&req->rl_free); + struct rpcrdma_req, rl_list); + list_del_init(&req->rl_list); return req; } @@ -1187,6 +1159,7 @@ rpcrdma_get_mw(struct rpcrdma_xprt *r_xprt) if (!mw) goto out_nomws; + mw->mw_flags = 0; return mw; out_nomws: @@ -1267,7 +1240,7 @@ rpcrdma_buffer_put(struct rpcrdma_req *req) spin_lock(&buffers->rb_lock); buffers->rb_send_count--; - list_add_tail(&req->rl_free, &buffers->rb_send_bufs); + list_add_tail(&req->rl_list, &buffers->rb_send_bufs); if (rep) { buffers->rb_recv_count--; list_add_tail(&rep->rr_list, &buffers->rb_recv_bufs); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 1d66acf1a723..b282d3f8cdd8 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -271,6 +271,7 @@ struct rpcrdma_mw { struct scatterlist *mw_sg; int mw_nents; enum dma_data_direction mw_dir; + unsigned long mw_flags; union { struct rpcrdma_fmr fmr; struct rpcrdma_frmr frmr; @@ -282,6 +283,11 @@ struct rpcrdma_mw { struct list_head mw_all; }; +/* mw_flags */ +enum { + RPCRDMA_MW_F_RI = 1, +}; + /* * struct rpcrdma_req -- structure central to the request/reply sequence. * @@ -334,7 +340,8 @@ enum { struct rpcrdma_buffer; struct rpcrdma_req { - struct list_head rl_free; + struct list_head rl_list; + __be32 rl_xid; unsigned int rl_mapped_sges; unsigned int rl_connect_cookie; struct rpcrdma_buffer *rl_buffer; @@ -396,6 +403,7 @@ struct rpcrdma_buffer { int rb_send_count, rb_recv_count; struct list_head rb_send_bufs; struct list_head rb_recv_bufs; + struct list_head rb_pending; u32 rb_max_requests; atomic_t rb_credits; /* most recent credit grant */ @@ -461,7 +469,7 @@ struct rpcrdma_memreg_ops { struct rpcrdma_mr_seg *, int, bool, struct rpcrdma_mw **); void (*ro_unmap_sync)(struct rpcrdma_xprt *, - struct rpcrdma_req *); + struct list_head *); void (*ro_unmap_safe)(struct rpcrdma_xprt *, struct rpcrdma_req *, bool); void (*ro_recover_mr)(struct rpcrdma_mw *); @@ -544,6 +552,34 @@ void rpcrdma_destroy_req(struct rpcrdma_req *); int rpcrdma_buffer_create(struct rpcrdma_xprt *); void rpcrdma_buffer_destroy(struct rpcrdma_buffer *); +static inline void +rpcrdma_insert_req(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) +{ + spin_lock(&buffers->rb_lock); + if (list_empty(&req->rl_list)) + list_add_tail(&req->rl_list, &buffers->rb_pending); + spin_unlock(&buffers->rb_lock); +} + +static inline struct rpcrdma_req * +rpcrdma_lookup_req_locked(struct rpcrdma_buffer *buffers, __be32 xid) +{ + struct rpcrdma_req *pos; + + list_for_each_entry(pos, &buffers->rb_pending, rl_list) + if (pos->rl_xid == xid) + return pos; + return NULL; +} + +static inline void +rpcrdma_remove_req(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) +{ + spin_lock(&buffers->rb_lock); + list_del(&req->rl_list); + spin_unlock(&buffers->rb_lock); +} + struct rpcrdma_mw *rpcrdma_get_mw(struct rpcrdma_xprt *); void rpcrdma_put_mw(struct rpcrdma_xprt *, struct rpcrdma_mw *); struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index d5b54c020dec..4f154d388748 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1624,6 +1624,8 @@ static void xs_tcp_state_change(struct sock *sk) if (test_and_clear_bit(XPRT_SOCK_CONNECTING, &transport->sock_state)) xprt_clear_connecting(xprt); + if (sk->sk_err) + xprt_wake_pending_tasks(xprt, -sk->sk_err); xs_sock_mark_closed(xprt); } out: diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 8d40a7d31c99..25dc67ef9d37 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -571,24 +571,17 @@ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, } EXPORT_SYMBOL_GPL(switchdev_port_obj_dump); -static RAW_NOTIFIER_HEAD(switchdev_notif_chain); +static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain); /** * register_switchdev_notifier - Register notifier * @nb: notifier_block * - * Register switch device notifier. This should be used by code - * which needs to monitor events happening in particular device. - * Return values are same as for atomic_notifier_chain_register(). + * Register switch device notifier. */ int register_switchdev_notifier(struct notifier_block *nb) { - int err; - - rtnl_lock(); - err = raw_notifier_chain_register(&switchdev_notif_chain, nb); - rtnl_unlock(); - return err; + return atomic_notifier_chain_register(&switchdev_notif_chain, nb); } EXPORT_SYMBOL_GPL(register_switchdev_notifier); @@ -597,16 +590,10 @@ EXPORT_SYMBOL_GPL(register_switchdev_notifier); * @nb: notifier_block * * Unregister switch device notifier. - * Return values are same as for atomic_notifier_chain_unregister(). */ int unregister_switchdev_notifier(struct notifier_block *nb) { - int err; - - rtnl_lock(); - err = raw_notifier_chain_unregister(&switchdev_notif_chain, nb); - rtnl_unlock(); - return err; + return atomic_notifier_chain_unregister(&switchdev_notif_chain, nb); } EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); @@ -616,18 +603,13 @@ EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); * @dev: port device * @info: notifier information data * - * Call all network notifier blocks. This should be called by driver - * when it needs to propagate hardware event. - * Return values are same as for atomic_notifier_call_chain(). - * rtnl_lock must be held. + * Call all network notifier blocks. */ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info) { - ASSERT_RTNL(); - info->dev = dev; - return raw_notifier_call_chain(&switchdev_notif_chain, val, info); + return atomic_notifier_call_chain(&switchdev_notif_chain, val, info); } EXPORT_SYMBOL_GPL(call_switchdev_notifiers); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 1b92b72e812f..101e3597338f 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2313,7 +2313,7 @@ static void tipc_sk_remove(struct tipc_sock *tsk) struct tipc_net *tn = net_generic(sock_net(sk), tipc_net_id); if (!rhashtable_remove_fast(&tn->sk_rht, &tsk->node, tsk_rht_params)) { - WARN_ON(atomic_read(&sk->sk_refcnt) == 1); + WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } } diff --git a/net/tls/Kconfig b/net/tls/Kconfig new file mode 100644 index 000000000000..eb583038c67e --- /dev/null +++ b/net/tls/Kconfig @@ -0,0 +1,15 @@ +# +# TLS configuration +# +config TLS + tristate "Transport Layer Security support" + depends on INET + select CRYPTO + select CRYPTO_AES + select CRYPTO_GCM + default n + ---help--- + Enable kernel support for TLS protocol. This allows symmetric + encryption handling of the TLS protocol to be done in-kernel. + + If unsure, say N. diff --git a/net/tls/Makefile b/net/tls/Makefile new file mode 100644 index 000000000000..a930fd1c4f7b --- /dev/null +++ b/net/tls/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the TLS subsystem. +# + +obj-$(CONFIG_TLS) += tls.o + +tls-y := tls_main.o tls_sw.o diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c new file mode 100644 index 000000000000..60aff60e30ad --- /dev/null +++ b/net/tls/tls_main.c @@ -0,0 +1,489 @@ +/* + * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. + * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/module.h> + +#include <net/tcp.h> +#include <net/inet_common.h> +#include <linux/highmem.h> +#include <linux/netdevice.h> +#include <linux/sched/signal.h> + +#include <net/tls.h> + +MODULE_AUTHOR("Mellanox Technologies"); +MODULE_DESCRIPTION("Transport Layer Security Support"); +MODULE_LICENSE("Dual BSD/GPL"); + +static struct proto tls_base_prot; +static struct proto tls_sw_prot; + +int wait_on_pending_writer(struct sock *sk, long *timeo) +{ + int rc = 0; + DEFINE_WAIT_FUNC(wait, woken_wake_function); + + add_wait_queue(sk_sleep(sk), &wait); + while (1) { + if (!*timeo) { + rc = -EAGAIN; + break; + } + + if (signal_pending(current)) { + rc = sock_intr_errno(*timeo); + break; + } + + if (sk_wait_event(sk, timeo, !sk->sk_write_pending, &wait)) + break; + } + remove_wait_queue(sk_sleep(sk), &wait); + return rc; +} + +int tls_push_sg(struct sock *sk, + struct tls_context *ctx, + struct scatterlist *sg, + u16 first_offset, + int flags) +{ + int sendpage_flags = flags | MSG_SENDPAGE_NOTLAST; + int ret = 0; + struct page *p; + size_t size; + int offset = first_offset; + + size = sg->length - offset; + offset += sg->offset; + + while (1) { + if (sg_is_last(sg)) + sendpage_flags = flags; + + /* is sending application-limited? */ + tcp_rate_check_app_limited(sk); + p = sg_page(sg); +retry: + ret = do_tcp_sendpages(sk, p, offset, size, sendpage_flags); + + if (ret != size) { + if (ret > 0) { + offset += ret; + size -= ret; + goto retry; + } + + offset -= sg->offset; + ctx->partially_sent_offset = offset; + ctx->partially_sent_record = (void *)sg; + return ret; + } + + put_page(p); + sk_mem_uncharge(sk, sg->length); + sg = sg_next(sg); + if (!sg) + break; + + offset = sg->offset; + size = sg->length; + } + + clear_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags); + + return 0; +} + +static int tls_handle_open_record(struct sock *sk, int flags) +{ + struct tls_context *ctx = tls_get_ctx(sk); + + if (tls_is_pending_open_record(ctx)) + return ctx->push_pending_record(sk, flags); + + return 0; +} + +int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, + unsigned char *record_type) +{ + struct cmsghdr *cmsg; + int rc = -EINVAL; + + for_each_cmsghdr(cmsg, msg) { + if (!CMSG_OK(msg, cmsg)) + return -EINVAL; + if (cmsg->cmsg_level != SOL_TLS) + continue; + + switch (cmsg->cmsg_type) { + case TLS_SET_RECORD_TYPE: + if (cmsg->cmsg_len < CMSG_LEN(sizeof(*record_type))) + return -EINVAL; + + if (msg->msg_flags & MSG_MORE) + return -EINVAL; + + rc = tls_handle_open_record(sk, msg->msg_flags); + if (rc) + return rc; + + *record_type = *(unsigned char *)CMSG_DATA(cmsg); + rc = 0; + break; + default: + return -EINVAL; + } + } + + return rc; +} + +int tls_push_pending_closed_record(struct sock *sk, struct tls_context *ctx, + int flags, long *timeo) +{ + struct scatterlist *sg; + u16 offset; + + if (!tls_is_partially_sent_record(ctx)) + return ctx->push_pending_record(sk, flags); + + sg = ctx->partially_sent_record; + offset = ctx->partially_sent_offset; + + ctx->partially_sent_record = NULL; + return tls_push_sg(sk, ctx, sg, offset, flags); +} + +static void tls_write_space(struct sock *sk) +{ + struct tls_context *ctx = tls_get_ctx(sk); + + if (!sk->sk_write_pending && tls_is_pending_closed_record(ctx)) { + gfp_t sk_allocation = sk->sk_allocation; + int rc; + long timeo = 0; + + sk->sk_allocation = GFP_ATOMIC; + rc = tls_push_pending_closed_record(sk, ctx, + MSG_DONTWAIT | + MSG_NOSIGNAL, + &timeo); + sk->sk_allocation = sk_allocation; + + if (rc < 0) + return; + } + + ctx->sk_write_space(sk); +} + +static void tls_sk_proto_close(struct sock *sk, long timeout) +{ + struct tls_context *ctx = tls_get_ctx(sk); + long timeo = sock_sndtimeo(sk, 0); + void (*sk_proto_close)(struct sock *sk, long timeout); + + lock_sock(sk); + + if (!tls_complete_pending_work(sk, ctx, 0, &timeo)) + tls_handle_open_record(sk, 0); + + if (ctx->partially_sent_record) { + struct scatterlist *sg = ctx->partially_sent_record; + + while (1) { + put_page(sg_page(sg)); + sk_mem_uncharge(sk, sg->length); + + if (sg_is_last(sg)) + break; + sg++; + } + } + ctx->free_resources(sk); + kfree(ctx->rec_seq); + kfree(ctx->iv); + + sk_proto_close = ctx->sk_proto_close; + kfree(ctx); + + release_sock(sk); + sk_proto_close(sk, timeout); +} + +static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, + int __user *optlen) +{ + int rc = 0; + struct tls_context *ctx = tls_get_ctx(sk); + struct tls_crypto_info *crypto_info; + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + if (!optval || (len < sizeof(*crypto_info))) { + rc = -EINVAL; + goto out; + } + + if (!ctx) { + rc = -EBUSY; + goto out; + } + + /* get user crypto info */ + crypto_info = &ctx->crypto_send; + + if (!TLS_CRYPTO_INFO_READY(crypto_info)) { + rc = -EBUSY; + goto out; + } + + if (len == sizeof(*crypto_info)) { + if (copy_to_user(optval, crypto_info, sizeof(*crypto_info))) + rc = -EFAULT; + goto out; + } + + switch (crypto_info->cipher_type) { + case TLS_CIPHER_AES_GCM_128: { + struct tls12_crypto_info_aes_gcm_128 * + crypto_info_aes_gcm_128 = + container_of(crypto_info, + struct tls12_crypto_info_aes_gcm_128, + info); + + if (len != sizeof(*crypto_info_aes_gcm_128)) { + rc = -EINVAL; + goto out; + } + lock_sock(sk); + memcpy(crypto_info_aes_gcm_128->iv, ctx->iv, + TLS_CIPHER_AES_GCM_128_IV_SIZE); + release_sock(sk); + if (copy_to_user(optval, + crypto_info_aes_gcm_128, + sizeof(*crypto_info_aes_gcm_128))) + rc = -EFAULT; + break; + } + default: + rc = -EINVAL; + } + +out: + return rc; +} + +static int do_tls_getsockopt(struct sock *sk, int optname, + char __user *optval, int __user *optlen) +{ + int rc = 0; + + switch (optname) { + case TLS_TX: + rc = do_tls_getsockopt_tx(sk, optval, optlen); + break; + default: + rc = -ENOPROTOOPT; + break; + } + return rc; +} + +static int tls_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct tls_context *ctx = tls_get_ctx(sk); + + if (level != SOL_TLS) + return ctx->getsockopt(sk, level, optname, optval, optlen); + + return do_tls_getsockopt(sk, optname, optval, optlen); +} + +static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval, + unsigned int optlen) +{ + struct tls_crypto_info *crypto_info, tmp_crypto_info; + struct tls_context *ctx = tls_get_ctx(sk); + struct proto *prot = NULL; + int rc = 0; + + if (!optval || (optlen < sizeof(*crypto_info))) { + rc = -EINVAL; + goto out; + } + + rc = copy_from_user(&tmp_crypto_info, optval, sizeof(*crypto_info)); + if (rc) { + rc = -EFAULT; + goto out; + } + + /* check version */ + if (tmp_crypto_info.version != TLS_1_2_VERSION) { + rc = -ENOTSUPP; + goto out; + } + + /* get user crypto info */ + crypto_info = &ctx->crypto_send; + + /* Currently we don't support set crypto info more than one time */ + if (TLS_CRYPTO_INFO_READY(crypto_info)) + goto out; + + switch (tmp_crypto_info.cipher_type) { + case TLS_CIPHER_AES_GCM_128: { + if (optlen != sizeof(struct tls12_crypto_info_aes_gcm_128)) { + rc = -EINVAL; + goto out; + } + rc = copy_from_user( + crypto_info, + optval, + sizeof(struct tls12_crypto_info_aes_gcm_128)); + + if (rc) { + rc = -EFAULT; + goto err_crypto_info; + } + break; + } + default: + rc = -EINVAL; + goto out; + } + + ctx->sk_write_space = sk->sk_write_space; + sk->sk_write_space = tls_write_space; + + ctx->sk_proto_close = sk->sk_prot->close; + + /* currently SW is default, we will have ethtool in future */ + rc = tls_set_sw_offload(sk, ctx); + prot = &tls_sw_prot; + if (rc) + goto err_crypto_info; + + sk->sk_prot = prot; + goto out; + +err_crypto_info: + memset(crypto_info, 0, sizeof(*crypto_info)); +out: + return rc; +} + +static int do_tls_setsockopt(struct sock *sk, int optname, + char __user *optval, unsigned int optlen) +{ + int rc = 0; + + switch (optname) { + case TLS_TX: + lock_sock(sk); + rc = do_tls_setsockopt_tx(sk, optval, optlen); + release_sock(sk); + break; + default: + rc = -ENOPROTOOPT; + break; + } + return rc; +} + +static int tls_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen) +{ + struct tls_context *ctx = tls_get_ctx(sk); + + if (level != SOL_TLS) + return ctx->setsockopt(sk, level, optname, optval, optlen); + + return do_tls_setsockopt(sk, optname, optval, optlen); +} + +static int tls_init(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tls_context *ctx; + int rc = 0; + + /* allocate tls context */ + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) { + rc = -ENOMEM; + goto out; + } + icsk->icsk_ulp_data = ctx; + ctx->setsockopt = sk->sk_prot->setsockopt; + ctx->getsockopt = sk->sk_prot->getsockopt; + sk->sk_prot = &tls_base_prot; +out: + return rc; +} + +static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = { + .name = "tls", + .owner = THIS_MODULE, + .init = tls_init, +}; + +static int __init tls_register(void) +{ + tls_base_prot = tcp_prot; + tls_base_prot.setsockopt = tls_setsockopt; + tls_base_prot.getsockopt = tls_getsockopt; + + tls_sw_prot = tls_base_prot; + tls_sw_prot.sendmsg = tls_sw_sendmsg; + tls_sw_prot.sendpage = tls_sw_sendpage; + tls_sw_prot.close = tls_sk_proto_close; + + tcp_register_ulp(&tcp_tls_ulp_ops); + + return 0; +} + +static void __exit tls_unregister(void) +{ + tcp_unregister_ulp(&tcp_tls_ulp_ops); +} + +module_init(tls_register); +module_exit(tls_unregister); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c new file mode 100644 index 000000000000..fa596fa71ba7 --- /dev/null +++ b/net/tls/tls_sw.c @@ -0,0 +1,772 @@ +/* + * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. + * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved. + * Copyright (c) 2016-2017, Lance Chao <lancerchao@fb.com>. All rights reserved. + * Copyright (c) 2016, Fridolin Pokorny <fridolin.pokorny@gmail.com>. All rights reserved. + * Copyright (c) 2016, Nikos Mavrogiannopoulos <nmav@gnutls.org>. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/module.h> +#include <crypto/aead.h> + +#include <net/tls.h> + +static inline void tls_make_aad(int recv, + char *buf, + size_t size, + char *record_sequence, + int record_sequence_size, + unsigned char record_type) +{ + memcpy(buf, record_sequence, record_sequence_size); + + buf[8] = record_type; + buf[9] = TLS_1_2_VERSION_MAJOR; + buf[10] = TLS_1_2_VERSION_MINOR; + buf[11] = size >> 8; + buf[12] = size & 0xFF; +} + +static void trim_sg(struct sock *sk, struct scatterlist *sg, + int *sg_num_elem, unsigned int *sg_size, int target_size) +{ + int i = *sg_num_elem - 1; + int trim = *sg_size - target_size; + + if (trim <= 0) { + WARN_ON(trim < 0); + return; + } + + *sg_size = target_size; + while (trim >= sg[i].length) { + trim -= sg[i].length; + sk_mem_uncharge(sk, sg[i].length); + put_page(sg_page(&sg[i])); + i--; + + if (i < 0) + goto out; + } + + sg[i].length -= trim; + sk_mem_uncharge(sk, trim); + +out: + *sg_num_elem = i + 1; +} + +static void trim_both_sgl(struct sock *sk, int target_size) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + + trim_sg(sk, ctx->sg_plaintext_data, + &ctx->sg_plaintext_num_elem, + &ctx->sg_plaintext_size, + target_size); + + if (target_size > 0) + target_size += tls_ctx->overhead_size; + + trim_sg(sk, ctx->sg_encrypted_data, + &ctx->sg_encrypted_num_elem, + &ctx->sg_encrypted_size, + target_size); +} + +static int alloc_sg(struct sock *sk, int len, struct scatterlist *sg, + int *sg_num_elem, unsigned int *sg_size, + int first_coalesce) +{ + struct page_frag *pfrag; + unsigned int size = *sg_size; + int num_elem = *sg_num_elem, use = 0, rc = 0; + struct scatterlist *sge; + unsigned int orig_offset; + + len -= size; + pfrag = sk_page_frag(sk); + + while (len > 0) { + if (!sk_page_frag_refill(sk, pfrag)) { + rc = -ENOMEM; + goto out; + } + + use = min_t(int, len, pfrag->size - pfrag->offset); + + if (!sk_wmem_schedule(sk, use)) { + rc = -ENOMEM; + goto out; + } + + sk_mem_charge(sk, use); + size += use; + orig_offset = pfrag->offset; + pfrag->offset += use; + + sge = sg + num_elem - 1; + if (num_elem > first_coalesce && sg_page(sg) == pfrag->page && + sg->offset + sg->length == orig_offset) { + sg->length += use; + } else { + sge++; + sg_unmark_end(sge); + sg_set_page(sge, pfrag->page, use, orig_offset); + get_page(pfrag->page); + ++num_elem; + if (num_elem == MAX_SKB_FRAGS) { + rc = -ENOSPC; + break; + } + } + + len -= use; + } + goto out; + +out: + *sg_size = size; + *sg_num_elem = num_elem; + return rc; +} + +static int alloc_encrypted_sg(struct sock *sk, int len) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + int rc = 0; + + rc = alloc_sg(sk, len, ctx->sg_encrypted_data, + &ctx->sg_encrypted_num_elem, &ctx->sg_encrypted_size, 0); + + return rc; +} + +static int alloc_plaintext_sg(struct sock *sk, int len) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + int rc = 0; + + rc = alloc_sg(sk, len, ctx->sg_plaintext_data, + &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size, + tls_ctx->pending_open_record_frags); + + return rc; +} + +static void free_sg(struct sock *sk, struct scatterlist *sg, + int *sg_num_elem, unsigned int *sg_size) +{ + int i, n = *sg_num_elem; + + for (i = 0; i < n; ++i) { + sk_mem_uncharge(sk, sg[i].length); + put_page(sg_page(&sg[i])); + } + *sg_num_elem = 0; + *sg_size = 0; +} + +static void tls_free_both_sg(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + + free_sg(sk, ctx->sg_encrypted_data, &ctx->sg_encrypted_num_elem, + &ctx->sg_encrypted_size); + + free_sg(sk, ctx->sg_plaintext_data, &ctx->sg_plaintext_num_elem, + &ctx->sg_plaintext_size); +} + +static int tls_do_encryption(struct tls_context *tls_ctx, + struct tls_sw_context *ctx, size_t data_len, + gfp_t flags) +{ + unsigned int req_size = sizeof(struct aead_request) + + crypto_aead_reqsize(ctx->aead_send); + struct aead_request *aead_req; + int rc; + + aead_req = kmalloc(req_size, flags); + if (!aead_req) + return -ENOMEM; + + ctx->sg_encrypted_data[0].offset += tls_ctx->prepend_size; + ctx->sg_encrypted_data[0].length -= tls_ctx->prepend_size; + + aead_request_set_tfm(aead_req, ctx->aead_send); + aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); + aead_request_set_crypt(aead_req, ctx->sg_aead_in, ctx->sg_aead_out, + data_len, tls_ctx->iv); + rc = crypto_aead_encrypt(aead_req); + + ctx->sg_encrypted_data[0].offset -= tls_ctx->prepend_size; + ctx->sg_encrypted_data[0].length += tls_ctx->prepend_size; + + kfree(aead_req); + return rc; +} + +static int tls_push_record(struct sock *sk, int flags, + unsigned char record_type) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + int rc; + + sg_mark_end(ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem - 1); + sg_mark_end(ctx->sg_encrypted_data + ctx->sg_encrypted_num_elem - 1); + + tls_make_aad(0, ctx->aad_space, ctx->sg_plaintext_size, + tls_ctx->rec_seq, tls_ctx->rec_seq_size, + record_type); + + tls_fill_prepend(tls_ctx, + page_address(sg_page(&ctx->sg_encrypted_data[0])) + + ctx->sg_encrypted_data[0].offset, + ctx->sg_plaintext_size, record_type); + + tls_ctx->pending_open_record_frags = 0; + set_bit(TLS_PENDING_CLOSED_RECORD, &tls_ctx->flags); + + rc = tls_do_encryption(tls_ctx, ctx, ctx->sg_plaintext_size, + sk->sk_allocation); + if (rc < 0) { + /* If we are called from write_space and + * we fail, we need to set this SOCK_NOSPACE + * to trigger another write_space in the future. + */ + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + return rc; + } + + free_sg(sk, ctx->sg_plaintext_data, &ctx->sg_plaintext_num_elem, + &ctx->sg_plaintext_size); + + ctx->sg_encrypted_num_elem = 0; + ctx->sg_encrypted_size = 0; + + /* Only pass through MSG_DONTWAIT and MSG_NOSIGNAL flags */ + rc = tls_push_sg(sk, tls_ctx, ctx->sg_encrypted_data, 0, flags); + if (rc < 0 && rc != -EAGAIN) + tls_err_abort(sk); + + tls_advance_record_sn(sk, tls_ctx); + return rc; +} + +static int tls_sw_push_pending_record(struct sock *sk, int flags) +{ + return tls_push_record(sk, flags, TLS_RECORD_TYPE_DATA); +} + +static int zerocopy_from_iter(struct sock *sk, struct iov_iter *from, + int length) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct page *pages[MAX_SKB_FRAGS]; + + size_t offset; + ssize_t copied, use; + int i = 0; + unsigned int size = ctx->sg_plaintext_size; + int num_elem = ctx->sg_plaintext_num_elem; + int rc = 0; + int maxpages; + + while (length > 0) { + i = 0; + maxpages = ARRAY_SIZE(ctx->sg_plaintext_data) - num_elem; + if (maxpages == 0) { + rc = -EFAULT; + goto out; + } + copied = iov_iter_get_pages(from, pages, + length, + maxpages, &offset); + if (copied <= 0) { + rc = -EFAULT; + goto out; + } + + iov_iter_advance(from, copied); + + length -= copied; + size += copied; + while (copied) { + use = min_t(int, copied, PAGE_SIZE - offset); + + sg_set_page(&ctx->sg_plaintext_data[num_elem], + pages[i], use, offset); + sg_unmark_end(&ctx->sg_plaintext_data[num_elem]); + sk_mem_charge(sk, use); + + offset = 0; + copied -= use; + + ++i; + ++num_elem; + } + } + +out: + ctx->sg_plaintext_size = size; + ctx->sg_plaintext_num_elem = num_elem; + return rc; +} + +static int memcopy_from_iter(struct sock *sk, struct iov_iter *from, + int bytes) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct scatterlist *sg = ctx->sg_plaintext_data; + int copy, i, rc = 0; + + for (i = tls_ctx->pending_open_record_frags; + i < ctx->sg_plaintext_num_elem; ++i) { + copy = sg[i].length; + if (copy_from_iter( + page_address(sg_page(&sg[i])) + sg[i].offset, + copy, from) != copy) { + rc = -EFAULT; + goto out; + } + bytes -= copy; + + ++tls_ctx->pending_open_record_frags; + + if (!bytes) + break; + } + +out: + return rc; +} + +int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + int ret = 0; + int required_size; + long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + bool eor = !(msg->msg_flags & MSG_MORE); + size_t try_to_copy, copied = 0; + unsigned char record_type = TLS_RECORD_TYPE_DATA; + int record_room; + bool full_record; + int orig_size; + + if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) + return -ENOTSUPP; + + lock_sock(sk); + + if (tls_complete_pending_work(sk, tls_ctx, msg->msg_flags, &timeo)) + goto send_end; + + if (unlikely(msg->msg_controllen)) { + ret = tls_proccess_cmsg(sk, msg, &record_type); + if (ret) + goto send_end; + } + + while (msg_data_left(msg)) { + if (sk->sk_err) { + ret = sk->sk_err; + goto send_end; + } + + orig_size = ctx->sg_plaintext_size; + full_record = false; + try_to_copy = msg_data_left(msg); + record_room = TLS_MAX_PAYLOAD_SIZE - ctx->sg_plaintext_size; + if (try_to_copy >= record_room) { + try_to_copy = record_room; + full_record = true; + } + + required_size = ctx->sg_plaintext_size + try_to_copy + + tls_ctx->overhead_size; + + if (!sk_stream_memory_free(sk)) + goto wait_for_sndbuf; +alloc_encrypted: + ret = alloc_encrypted_sg(sk, required_size); + if (ret) { + if (ret != -ENOSPC) + goto wait_for_memory; + + /* Adjust try_to_copy according to the amount that was + * actually allocated. The difference is due + * to max sg elements limit + */ + try_to_copy -= required_size - ctx->sg_encrypted_size; + full_record = true; + } + + if (full_record || eor) { + ret = zerocopy_from_iter(sk, &msg->msg_iter, + try_to_copy); + if (ret) + goto fallback_to_reg_send; + + copied += try_to_copy; + ret = tls_push_record(sk, msg->msg_flags, record_type); + if (!ret) + continue; + if (ret == -EAGAIN) + goto send_end; + + copied -= try_to_copy; +fallback_to_reg_send: + iov_iter_revert(&msg->msg_iter, + ctx->sg_plaintext_size - orig_size); + trim_sg(sk, ctx->sg_plaintext_data, + &ctx->sg_plaintext_num_elem, + &ctx->sg_plaintext_size, + orig_size); + } + + required_size = ctx->sg_plaintext_size + try_to_copy; +alloc_plaintext: + ret = alloc_plaintext_sg(sk, required_size); + if (ret) { + if (ret != -ENOSPC) + goto wait_for_memory; + + /* Adjust try_to_copy according to the amount that was + * actually allocated. The difference is due + * to max sg elements limit + */ + try_to_copy -= required_size - ctx->sg_plaintext_size; + full_record = true; + + trim_sg(sk, ctx->sg_encrypted_data, + &ctx->sg_encrypted_num_elem, + &ctx->sg_encrypted_size, + ctx->sg_plaintext_size + + tls_ctx->overhead_size); + } + + ret = memcopy_from_iter(sk, &msg->msg_iter, try_to_copy); + if (ret) + goto trim_sgl; + + copied += try_to_copy; + if (full_record || eor) { +push_record: + ret = tls_push_record(sk, msg->msg_flags, record_type); + if (ret) { + if (ret == -ENOMEM) + goto wait_for_memory; + + goto send_end; + } + } + + continue; + +wait_for_sndbuf: + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); +wait_for_memory: + ret = sk_stream_wait_memory(sk, &timeo); + if (ret) { +trim_sgl: + trim_both_sgl(sk, orig_size); + goto send_end; + } + + if (tls_is_pending_closed_record(tls_ctx)) + goto push_record; + + if (ctx->sg_encrypted_size < required_size) + goto alloc_encrypted; + + goto alloc_plaintext; + } + +send_end: + ret = sk_stream_error(sk, msg->msg_flags, ret); + + release_sock(sk); + return copied ? copied : ret; +} + +int tls_sw_sendpage(struct sock *sk, struct page *page, + int offset, size_t size, int flags) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + int ret = 0; + long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); + bool eor; + size_t orig_size = size; + unsigned char record_type = TLS_RECORD_TYPE_DATA; + struct scatterlist *sg; + bool full_record; + int record_room; + + if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | + MSG_SENDPAGE_NOTLAST)) + return -ENOTSUPP; + + /* No MSG_EOR from splice, only look at MSG_MORE */ + eor = !(flags & (MSG_MORE | MSG_SENDPAGE_NOTLAST)); + + lock_sock(sk); + + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); + + if (tls_complete_pending_work(sk, tls_ctx, flags, &timeo)) + goto sendpage_end; + + /* Call the sk_stream functions to manage the sndbuf mem. */ + while (size > 0) { + size_t copy, required_size; + + if (sk->sk_err) { + ret = sk->sk_err; + goto sendpage_end; + } + + full_record = false; + record_room = TLS_MAX_PAYLOAD_SIZE - ctx->sg_plaintext_size; + copy = size; + if (copy >= record_room) { + copy = record_room; + full_record = true; + } + required_size = ctx->sg_plaintext_size + copy + + tls_ctx->overhead_size; + + if (!sk_stream_memory_free(sk)) + goto wait_for_sndbuf; +alloc_payload: + ret = alloc_encrypted_sg(sk, required_size); + if (ret) { + if (ret != -ENOSPC) + goto wait_for_memory; + + /* Adjust copy according to the amount that was + * actually allocated. The difference is due + * to max sg elements limit + */ + copy -= required_size - ctx->sg_plaintext_size; + full_record = true; + } + + get_page(page); + sg = ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem; + sg_set_page(sg, page, copy, offset); + ctx->sg_plaintext_num_elem++; + + sk_mem_charge(sk, copy); + offset += copy; + size -= copy; + ctx->sg_plaintext_size += copy; + tls_ctx->pending_open_record_frags = ctx->sg_plaintext_num_elem; + + if (full_record || eor || + ctx->sg_plaintext_num_elem == + ARRAY_SIZE(ctx->sg_plaintext_data)) { +push_record: + ret = tls_push_record(sk, flags, record_type); + if (ret) { + if (ret == -ENOMEM) + goto wait_for_memory; + + goto sendpage_end; + } + } + continue; +wait_for_sndbuf: + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); +wait_for_memory: + ret = sk_stream_wait_memory(sk, &timeo); + if (ret) { + trim_both_sgl(sk, ctx->sg_plaintext_size); + goto sendpage_end; + } + + if (tls_is_pending_closed_record(tls_ctx)) + goto push_record; + + goto alloc_payload; + } + +sendpage_end: + if (orig_size > size) + ret = orig_size - size; + else + ret = sk_stream_error(sk, flags, ret); + + release_sock(sk); + return ret; +} + +void tls_sw_free_resources(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + + if (ctx->aead_send) + crypto_free_aead(ctx->aead_send); + + tls_free_both_sg(sk); + + kfree(ctx); +} + +int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx) +{ + char keyval[TLS_CIPHER_AES_GCM_128_KEY_SIZE]; + struct tls_crypto_info *crypto_info; + struct tls12_crypto_info_aes_gcm_128 *gcm_128_info; + struct tls_sw_context *sw_ctx; + u16 nonce_size, tag_size, iv_size, rec_seq_size; + char *iv, *rec_seq; + int rc = 0; + + if (!ctx) { + rc = -EINVAL; + goto out; + } + + if (ctx->priv_ctx) { + rc = -EEXIST; + goto out; + } + + sw_ctx = kzalloc(sizeof(*sw_ctx), GFP_KERNEL); + if (!sw_ctx) { + rc = -ENOMEM; + goto out; + } + + ctx->priv_ctx = (struct tls_offload_context *)sw_ctx; + ctx->free_resources = tls_sw_free_resources; + + crypto_info = &ctx->crypto_send; + switch (crypto_info->cipher_type) { + case TLS_CIPHER_AES_GCM_128: { + nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; + tag_size = TLS_CIPHER_AES_GCM_128_TAG_SIZE; + iv_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; + iv = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->iv; + rec_seq_size = TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE; + rec_seq = + ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->rec_seq; + gcm_128_info = + (struct tls12_crypto_info_aes_gcm_128 *)crypto_info; + break; + } + default: + rc = -EINVAL; + goto out; + } + + ctx->prepend_size = TLS_HEADER_SIZE + nonce_size; + ctx->tag_size = tag_size; + ctx->overhead_size = ctx->prepend_size + ctx->tag_size; + ctx->iv_size = iv_size; + ctx->iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE, + GFP_KERNEL); + if (!ctx->iv) { + rc = -ENOMEM; + goto out; + } + memcpy(ctx->iv, gcm_128_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + memcpy(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size); + ctx->rec_seq_size = rec_seq_size; + ctx->rec_seq = kmalloc(rec_seq_size, GFP_KERNEL); + if (!ctx->rec_seq) { + rc = -ENOMEM; + goto free_iv; + } + memcpy(ctx->rec_seq, rec_seq, rec_seq_size); + + sg_init_table(sw_ctx->sg_encrypted_data, + ARRAY_SIZE(sw_ctx->sg_encrypted_data)); + sg_init_table(sw_ctx->sg_plaintext_data, + ARRAY_SIZE(sw_ctx->sg_plaintext_data)); + + sg_init_table(sw_ctx->sg_aead_in, 2); + sg_set_buf(&sw_ctx->sg_aead_in[0], sw_ctx->aad_space, + sizeof(sw_ctx->aad_space)); + sg_unmark_end(&sw_ctx->sg_aead_in[1]); + sg_chain(sw_ctx->sg_aead_in, 2, sw_ctx->sg_plaintext_data); + sg_init_table(sw_ctx->sg_aead_out, 2); + sg_set_buf(&sw_ctx->sg_aead_out[0], sw_ctx->aad_space, + sizeof(sw_ctx->aad_space)); + sg_unmark_end(&sw_ctx->sg_aead_out[1]); + sg_chain(sw_ctx->sg_aead_out, 2, sw_ctx->sg_encrypted_data); + + if (!sw_ctx->aead_send) { + sw_ctx->aead_send = crypto_alloc_aead("gcm(aes)", 0, 0); + if (IS_ERR(sw_ctx->aead_send)) { + rc = PTR_ERR(sw_ctx->aead_send); + sw_ctx->aead_send = NULL; + goto free_rec_seq; + } + } + + ctx->push_pending_record = tls_sw_push_pending_record; + + memcpy(keyval, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); + + rc = crypto_aead_setkey(sw_ctx->aead_send, keyval, + TLS_CIPHER_AES_GCM_128_KEY_SIZE); + if (rc) + goto free_aead; + + rc = crypto_aead_setauthsize(sw_ctx->aead_send, ctx->tag_size); + if (!rc) + goto out; + +free_aead: + crypto_free_aead(sw_ctx->aead_send); + sw_ctx->aead_send = NULL; +free_rec_seq: + kfree(ctx->rec_seq); + ctx->rec_seq = NULL; +free_iv: + kfree(ctx->iv); + ctx->iv = NULL; +out: + return rc; +} diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 1a0c961f4ffe..7b52a380d710 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -212,7 +212,7 @@ EXPORT_SYMBOL_GPL(unix_peer_get); static inline void unix_release_addr(struct unix_address *addr) { - if (atomic_dec_and_test(&addr->refcnt)) + if (refcount_dec_and_test(&addr->refcnt)) kfree(addr); } @@ -343,7 +343,7 @@ found: * are still connected to it and there's no way to inform "a polling * implementation" that it should let go of a certain wait queue * - * In order to propagate a wake up, a wait_queue_t of the client + * In order to propagate a wake up, a wait_queue_entry_t of the client * socket is enqueued on the peer_wait queue of the server socket * whose wake function does a wake_up on the ordinary client socket * wait queue. This connection is established whenever a write (or @@ -352,7 +352,7 @@ found: * was relayed. */ -static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags, +static int unix_dgram_peer_wake_relay(wait_queue_entry_t *q, unsigned mode, int flags, void *key) { struct unix_sock *u; @@ -442,7 +442,7 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) static int unix_writable(const struct sock *sk) { return sk->sk_state != TCP_LISTEN && - (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf; + (refcount_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf; } static void unix_write_space(struct sock *sk) @@ -487,7 +487,7 @@ static void unix_sock_destructor(struct sock *sk) skb_queue_purge(&sk->sk_receive_queue); - WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(!sk_unhashed(sk)); WARN_ON(sk->sk_socket); if (!sock_flag(sk, SOCK_DEAD)) { @@ -864,7 +864,7 @@ static int unix_autobind(struct socket *sock) goto out; addr->name->sun_family = AF_UNIX; - atomic_set(&addr->refcnt, 1); + refcount_set(&addr->refcnt, 1); retry: addr->len = sprintf(addr->name->sun_path+1, "%05x", ordernum) + 1 + sizeof(short); @@ -1040,7 +1040,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) memcpy(addr->name, sunaddr, addr_len); addr->len = addr_len; addr->hash = hash ^ sk->sk_type; - atomic_set(&addr->refcnt, 1); + refcount_set(&addr->refcnt, 1); if (sun_path[0]) { addr->hash = UNIX_HASH_SIZE; @@ -1335,7 +1335,7 @@ restart: /* copy address information from listening to new sock*/ if (otheru->addr) { - atomic_inc(&otheru->addr->refcnt); + refcount_inc(&otheru->addr->refcnt); newu->addr = otheru->addr; } if (otheru->path.dentry) { @@ -2033,7 +2033,7 @@ alloc_skb: skb->len += size; skb->data_len += size; skb->truesize += size; - atomic_add(size, &sk->sk_wmem_alloc); + refcount_add(size, &sk->sk_wmem_alloc); if (newskb) { err = unix_scm_to_skb(&scm, skb, false); @@ -2847,7 +2847,7 @@ static int unix_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%pK: %08X %08X %08X %04X %02X %5lu", s, - atomic_read(&s->sk_refcnt), + refcount_read(&s->sk_refcnt), 0, s->sk_state == TCP_LISTEN ? __SO_ACCEPTCON : 0, s->sk_type, diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 18e24793659f..edba7ab97563 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -90,7 +90,6 @@ out_pkt: static struct sk_buff *virtio_transport_build_skb(void *opaque) { struct virtio_vsock_pkt *pkt = opaque; - unsigned char *t_hdr, *payload; struct af_vsockmon_hdr *hdr; struct sk_buff *skb; @@ -99,7 +98,7 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) if (!skb) return NULL; - hdr = (struct af_vsockmon_hdr *)skb_put(skb, sizeof(*hdr)); + hdr = skb_put(skb, sizeof(*hdr)); /* pkt->hdr is little-endian so no need to byteswap here */ hdr->src_cid = pkt->hdr.src_cid; @@ -132,12 +131,10 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) break; } - t_hdr = skb_put(skb, sizeof(pkt->hdr)); - memcpy(t_hdr, &pkt->hdr, sizeof(pkt->hdr)); + skb_put_data(skb, &pkt->hdr, sizeof(pkt->hdr)); if (pkt->len) { - payload = skb_put(skb, pkt->len); - memcpy(payload, pkt->buf, pkt->len); + skb_put_data(skb, pkt->buf, pkt->len); } return skb; diff --git a/net/wireless/core.c b/net/wireless/core.c index 83ea164f16b3..7b33e8c366bc 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -711,6 +711,11 @@ int wiphy_register(struct wiphy *wiphy) (wiphy->bss_select_support & ~(BIT(__NL80211_BSS_SELECT_ATTR_AFTER_LAST) - 2)))) return -EINVAL; + if (WARN_ON(wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X) && + (!rdev->ops->set_pmk || !rdev->ops->del_pmk))) + return -EINVAL; + if (wiphy->addresses) memcpy(wiphy->perm_addr, wiphy->addresses[0].addr, ETH_ALEN); diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index ec0b1c20ac99..421a6b80ec62 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -174,6 +174,14 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, scan_width); } + err = cfg80211_chandef_dfs_required(&rdev->wiphy, + &setup->chandef, + NL80211_IFTYPE_MESH_POINT); + if (err < 0) + return err; + if (err > 0 && !setup->userspace_handles_dfs) + return -EINVAL; + if (!cfg80211_reg_can_beacon(&rdev->wiphy, &setup->chandef, NL80211_IFTYPE_MESH_POINT)) return -EINVAL; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c3bc9da30cff..8ce85420ecb0 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -291,8 +291,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 }, [NL80211_ATTR_PID] = { .type = NLA_U32 }, [NL80211_ATTR_4ADDR] = { .type = NLA_U8 }, - [NL80211_ATTR_PMKID] = { .type = NLA_BINARY, - .len = WLAN_PMKID_LEN }, + [NL80211_ATTR_PMKID] = { .len = WLAN_PMKID_LEN }, [NL80211_ATTR_DURATION] = { .type = NLA_U32 }, [NL80211_ATTR_COOKIE] = { .type = NLA_U64 }, [NL80211_ATTR_TX_RATES] = { .type = NLA_NESTED }, @@ -348,6 +347,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_SCAN_FLAGS] = { .type = NLA_U32 }, [NL80211_ATTR_P2P_CTWINDOW] = { .type = NLA_U8 }, [NL80211_ATTR_P2P_OPPPS] = { .type = NLA_U8 }, + [NL80211_ATTR_LOCAL_MESH_POWER_MODE] = {. type = NLA_U32 }, [NL80211_ATTR_ACL_POLICY] = {. type = NLA_U32 }, [NL80211_ATTR_MAC_ADDRS] = { .type = NLA_NESTED }, [NL80211_ATTR_STA_CAPABILITY] = { .type = NLA_U16 }, @@ -520,7 +520,7 @@ nl80211_bss_select_policy[NL80211_BSS_SELECT_ATTR_MAX + 1] = { static const struct nla_policy nl80211_nan_func_policy[NL80211_NAN_FUNC_ATTR_MAX + 1] = { [NL80211_NAN_FUNC_TYPE] = { .type = NLA_U8 }, - [NL80211_NAN_FUNC_SERVICE_ID] = { .type = NLA_BINARY, + [NL80211_NAN_FUNC_SERVICE_ID] = { .len = NL80211_NAN_FUNC_SERVICE_ID_LEN }, [NL80211_NAN_FUNC_PUBLISH_TYPE] = { .type = NLA_U8 }, [NL80211_NAN_FUNC_PUBLISH_BCAST] = { .type = NLA_FLAG }, @@ -6469,6 +6469,10 @@ static int validate_scan_freqs(struct nlattr *freqs) struct nlattr *attr1, *attr2; int n_channels = 0, tmp1, tmp2; + nla_for_each_nested(attr1, freqs, tmp1) + if (nla_len(attr1) != sizeof(u32)) + return 0; + nla_for_each_nested(attr1, freqs, tmp1) { n_channels++; /* @@ -7501,6 +7505,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) static struct nlattr *csa_attrs[NL80211_ATTR_MAX+1]; int err; bool need_new_beacon = false; + bool need_handle_dfs_flag = true; int len, i; u32 cs_count; @@ -7512,6 +7517,12 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: need_new_beacon = true; + /* For all modes except AP the handle_dfs flag needs to be + * supplied to tell the kernel that userspace will handle radar + * events when they happen. Otherwise a switch to a channel + * requiring DFS will be rejected. + */ + need_handle_dfs_flag = false; /* useless if AP is not running */ if (!wdev->beacon_interval) @@ -7634,8 +7645,13 @@ skip_beacons: if (err < 0) return err; - if (err > 0) + if (err > 0) { params.radar_required = true; + if (need_handle_dfs_flag && + !nla_get_flag(info->attrs[NL80211_ATTR_HANDLE_DFS])) { + return -EINVAL; + } + } if (info->attrs[NL80211_ATTR_CH_SWITCH_BLOCK_TX]) params.block_tx = true; @@ -8156,6 +8172,15 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, memcpy(settings->akm_suites, data, len); } + if (info->attrs[NL80211_ATTR_PMK]) { + if (nla_len(info->attrs[NL80211_ATTR_PMK]) != WLAN_PMK_LEN) + return -EINVAL; + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK)) + return -EINVAL; + settings->psk = nla_data(info->attrs[NL80211_ATTR_PMK]); + } + return 0; } @@ -8860,6 +8885,12 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) connect.privacy = info->attrs[NL80211_ATTR_PRIVACY]; + if (info->attrs[NL80211_ATTR_WANT_1X_4WAY_HS] && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X)) + return -EINVAL; + connect.want_1x = info->attrs[NL80211_ATTR_WANT_1X_4WAY_HS]; + err = nl80211_crypto_settings(rdev, info, &connect.crypto, NL80211_MAX_NR_CIPHER_SUITES); if (err) @@ -9962,6 +9993,9 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) return err; } + setup.userspace_handles_dfs = + nla_get_flag(info->attrs[NL80211_ATTR_HANDLE_DFS]); + return cfg80211_join_mesh(rdev, dev, &setup, &cfg); } @@ -11176,10 +11210,6 @@ static int nl80211_nan_add_func(struct sk_buff *skb, if (!info->attrs[NL80211_ATTR_NAN_FUNC]) return -EINVAL; - if (wdev->owner_nlportid && - wdev->owner_nlportid != info->snd_portid) - return -ENOTCONN; - err = nla_parse_nested(tb, NL80211_NAN_FUNC_ATTR_MAX, info->attrs[NL80211_ATTR_NAN_FUNC], nl80211_nan_func_policy, info->extack); @@ -11411,10 +11441,6 @@ static int nl80211_nan_del_func(struct sk_buff *skb, if (!info->attrs[NL80211_ATTR_COOKIE]) return -EINVAL; - if (wdev->owner_nlportid && - wdev->owner_nlportid != info->snd_portid) - return -ENOTCONN; - cookie = nla_get_u64(info->attrs[NL80211_ATTR_COOKIE]); rdev_del_nan_func(rdev, wdev, cookie); @@ -12241,6 +12267,90 @@ static int nl80211_set_multicast_to_unicast(struct sk_buff *skb, return rdev_set_multicast_to_unicast(rdev, dev, enabled); } +static int nl80211_set_pmk(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_pmk_conf pmk_conf = {}; + int ret; + + if (wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; + + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X)) + return -EOPNOTSUPP; + + if (!info->attrs[NL80211_ATTR_MAC] || !info->attrs[NL80211_ATTR_PMK]) + return -EINVAL; + + wdev_lock(wdev); + if (!wdev->current_bss) { + ret = -ENOTCONN; + goto out; + } + + pmk_conf.aa = nla_data(info->attrs[NL80211_ATTR_MAC]); + if (memcmp(pmk_conf.aa, wdev->current_bss->pub.bssid, ETH_ALEN)) { + ret = -EINVAL; + goto out; + } + + pmk_conf.pmk = nla_data(info->attrs[NL80211_ATTR_PMK]); + pmk_conf.pmk_len = nla_len(info->attrs[NL80211_ATTR_PMK]); + if (pmk_conf.pmk_len != WLAN_PMK_LEN && + pmk_conf.pmk_len != WLAN_PMK_LEN_SUITE_B_192) { + ret = -EINVAL; + goto out; + } + + if (info->attrs[NL80211_ATTR_PMKR0_NAME]) { + int r0_name_len = nla_len(info->attrs[NL80211_ATTR_PMKR0_NAME]); + + if (r0_name_len != WLAN_PMK_NAME_LEN) { + ret = -EINVAL; + goto out; + } + + pmk_conf.pmk_r0_name = + nla_data(info->attrs[NL80211_ATTR_PMKR0_NAME]); + } + + ret = rdev_set_pmk(rdev, dev, &pmk_conf); +out: + wdev_unlock(wdev); + return ret; +} + +static int nl80211_del_pmk(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + const u8 *aa; + int ret; + + if (wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; + + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X)) + return -EOPNOTSUPP; + + if (!info->attrs[NL80211_ATTR_MAC]) + return -EINVAL; + + wdev_lock(wdev); + aa = nla_data(info->attrs[NL80211_ATTR_MAC]); + ret = rdev_del_pmk(rdev, dev, aa); + wdev_unlock(wdev); + + return ret; +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -13116,6 +13226,21 @@ static const struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_SET_PMK, + .doit = nl80211_set_pmk, + .policy = nl80211_policy, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, + { + .cmd = NL80211_CMD_DEL_PMK, + .doit = nl80211_del_pmk, + .policy = nl80211_policy, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, + }; static struct genl_family nl80211_fam __ro_after_init = { @@ -13671,7 +13796,9 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, info->req_ie)) || (info->resp_ie && nla_put(msg, NL80211_ATTR_RESP_IE, info->resp_ie_len, - info->resp_ie))) + info->resp_ie)) || + (info->authorized && + nla_put_flag(msg, NL80211_ATTR_PORT_AUTHORIZED))) goto nla_put_failure; genlmsg_end(msg, hdr); diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 0598c1e5d0ad..ce23d7d49960 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1164,4 +1164,29 @@ rdev_set_coalesce(struct cfg80211_registered_device *rdev, trace_rdev_return_int(&rdev->wiphy, ret); return ret; } + +static inline int rdev_set_pmk(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_pmk_conf *pmk_conf) +{ + int ret = -EOPNOTSUPP; + + trace_rdev_set_pmk(&rdev->wiphy, dev, pmk_conf); + if (rdev->ops->set_pmk) + ret = rdev->ops->set_pmk(&rdev->wiphy, dev, pmk_conf); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_del_pmk(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *aa) +{ + int ret = -EOPNOTSUPP; + + trace_rdev_del_pmk(&rdev->wiphy, dev, aa); + if (rdev->ops->del_pmk) + ret = rdev->ops->del_pmk(&rdev->wiphy, dev, aa); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 532a0007ce82..0a49b88070d0 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -960,6 +960,7 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, ev->rm.resp_ie_len = info->resp_ie_len; memcpy((void *)ev->rm.resp_ie, info->resp_ie, info->resp_ie_len); ev->rm.bss = info->bss; + ev->rm.authorized = info->authorized; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index ca8b2059f92c..0f8db41eaddb 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2258,6 +2258,66 @@ TRACE_EVENT(rdev_tdls_cancel_channel_switch, WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(addr)) ); +TRACE_EVENT(rdev_set_pmk, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_pmk_conf *pmk_conf), + + TP_ARGS(wiphy, netdev, pmk_conf), + + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(aa) + __field(u8, pmk_len) + __field(u8, pmk_r0_name_len) + __dynamic_array(u8, pmk, pmk_conf->pmk_len) + __dynamic_array(u8, pmk_r0_name, WLAN_PMK_NAME_LEN) + ), + + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(aa, pmk_conf->aa); + __entry->pmk_len = pmk_conf->pmk_len; + __entry->pmk_r0_name_len = + pmk_conf->pmk_r0_name ? WLAN_PMK_NAME_LEN : 0; + memcpy(__get_dynamic_array(pmk), pmk_conf->pmk, + pmk_conf->pmk_len); + memcpy(__get_dynamic_array(pmk_r0_name), pmk_conf->pmk_r0_name, + pmk_conf->pmk_r0_name ? WLAN_PMK_NAME_LEN : 0); + ), + + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT + "pmk_len=%u, pmk: %s pmk_r0_name: %s", WIPHY_PR_ARG, + NETDEV_PR_ARG, MAC_PR_ARG(aa), __entry->pmk_len, + __print_array(__get_dynamic_array(pmk), + __get_dynamic_array_len(pmk), 1), + __entry->pmk_r0_name_len ? + __print_array(__get_dynamic_array(pmk_r0_name), + __get_dynamic_array_len(pmk_r0_name), 1) : "") +); + +TRACE_EVENT(rdev_del_pmk, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *aa), + + TP_ARGS(wiphy, netdev, aa), + + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(aa) + ), + + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(aa, aa); + ), + + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(aa)) +); + /************************************************************* * cfg80211 exported functions traces * *************************************************************/ diff --git a/net/wireless/util.c b/net/wireless/util.c index 4992f1025c9d..bcb1284c3415 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -522,7 +522,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, pskb_pull(skb, hdrlen); if (!ehdr) - ehdr = (struct ethhdr *) skb_push(skb, sizeof(struct ethhdr)); + ehdr = skb_push(skb, sizeof(struct ethhdr)); memcpy(ehdr, &tmp, sizeof(tmp)); return 0; @@ -1219,8 +1219,8 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) u32 bitrate; int idx; - if (WARN_ON_ONCE(rate->mcs > 9)) - return 0; + if (rate->mcs > 9) + goto warn; switch (rate->bw) { case RATE_INFO_BW_160: @@ -1235,8 +1235,7 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) case RATE_INFO_BW_5: case RATE_INFO_BW_10: default: - WARN_ON(1); - /* fall through */ + goto warn; case RATE_INFO_BW_20: idx = 0; } @@ -1249,6 +1248,10 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) /* do NOT round down here */ return (bitrate + 50000) / 100000; + warn: + WARN_ONCE(1, "invalid rate bw=%d, mcs=%d, nss=%d\n", + rate->bw, rate->mcs, rate->nss); + return 0; } u32 cfg80211_calculate_bitrate(struct rate_info *rate) diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c index bcaa180d6a3f..e0cd04d28352 100644 --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -266,7 +266,7 @@ void x25_link_device_up(struct net_device *dev) X25_MASK_PACKET_SIZE | X25_MASK_WINDOW_SIZE; nb->t20 = sysctl_x25_restart_request_timeout; - atomic_set(&nb->refcnt, 1); + refcount_set(&nb->refcnt, 1); write_lock_bh(&x25_neigh_list_lock); list_add(&nb->node, &x25_neigh_list); diff --git a/net/x25/x25_route.c b/net/x25/x25_route.c index 277c8d2448d6..b85b889596e5 100644 --- a/net/x25/x25_route.c +++ b/net/x25/x25_route.c @@ -55,7 +55,7 @@ static int x25_add_route(struct x25_address *address, unsigned int sigdigits, rt->sigdigits = sigdigits; rt->dev = dev; - atomic_set(&rt->refcnt, 1); + refcount_set(&rt->refcnt, 1); list_add(&rt->node, &x25_route_list); rc = 0; diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index 6b5af65f491f..db0b1315d577 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -188,17 +188,14 @@ void x25_write_internal(struct sock *sk, int frametype) *dptr++ = X25_CALL_REQUEST; len = x25_addr_aton(addresses, &x25->dest_addr, &x25->source_addr); - dptr = skb_put(skb, len); - memcpy(dptr, addresses, len); + skb_put_data(skb, addresses, len); len = x25_create_facilities(facilities, &x25->facilities, &x25->dte_facilities, x25->neighbour->global_facil_mask); - dptr = skb_put(skb, len); - memcpy(dptr, facilities, len); - dptr = skb_put(skb, x25->calluserdata.cudlength); - memcpy(dptr, x25->calluserdata.cuddata, - x25->calluserdata.cudlength); + skb_put_data(skb, facilities, len); + skb_put_data(skb, x25->calluserdata.cuddata, + x25->calluserdata.cudlength); x25->calluserdata.cudlength = 0; break; @@ -210,17 +207,15 @@ void x25_write_internal(struct sock *sk, int frametype) &x25->facilities, &x25->dte_facilities, x25->vc_facil_mask); - dptr = skb_put(skb, len); - memcpy(dptr, facilities, len); + skb_put_data(skb, facilities, len); /* fast select with no restriction on response allows call user data. Userland must ensure it is ours and not theirs */ if(x25->facilities.reverse & 0x80) { - dptr = skb_put(skb, - x25->calluserdata.cudlength); - memcpy(dptr, x25->calluserdata.cuddata, - x25->calluserdata.cudlength); + skb_put_data(skb, + x25->calluserdata.cuddata, + x25->calluserdata.cudlength); } x25->calluserdata.cudlength = 0; break; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 5aba03685d7d..5f7e8bfa0c2d 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -140,7 +140,7 @@ ok: EXPORT_SYMBOL_GPL(xfrm_dev_offload_ok); #endif -int xfrm_dev_register(struct net_device *dev) +static int xfrm_dev_register(struct net_device *dev) { if ((dev->features & NETIF_F_HW_ESP) && !dev->xfrmdev_ops) return NOTIFY_BAD; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 9de4b1dbc0ae..923205e279f7 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -116,7 +116,7 @@ struct sec_path *secpath_dup(struct sec_path *src) for (i = 0; i < sp->len; i++) xfrm_state_hold(sp->xvec[i]); } - atomic_set(&sp->refcnt, 1); + refcount_set(&sp->refcnt, 1); return sp; } EXPORT_SYMBOL(secpath_dup); @@ -126,7 +126,7 @@ int secpath_set(struct sk_buff *skb) struct sec_path *sp; /* Allocate new secpath or COW existing one. */ - if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) { + if (!skb->sp || refcount_read(&skb->sp->refcnt) != 1) { sp = secpath_dup(skb->sp); if (!sp) return -ENOMEM; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 643a18f72032..ff61d8557929 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -62,7 +62,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy) { - return atomic_inc_not_zero(&policy->refcnt); + return refcount_inc_not_zero(&policy->refcnt); } static inline bool @@ -292,7 +292,7 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) INIT_HLIST_NODE(&policy->bydst); INIT_HLIST_NODE(&policy->byidx); rwlock_init(&policy->lock); - atomic_set(&policy->refcnt, 1); + refcount_set(&policy->refcnt, 1); skb_queue_head_init(&policy->polq.hold_queue); setup_timer(&policy->timer, xfrm_policy_timer, (unsigned long)policy); @@ -1586,7 +1586,9 @@ static void xfrm_bundle_flo_delete(struct flow_cache_object *flo) struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo); struct dst_entry *dst = &xdst->u.dst; - dst_free(dst); + /* Mark DST_OBSOLETE_DEAD to fail the next xfrm_dst_check() */ + dst->obsolete = DST_OBSOLETE_DEAD; + dst_release_immediate(dst); } static const struct flow_cache_ops xfrm_bundle_fc_ops = { @@ -1616,7 +1618,7 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) default: BUG(); } - xdst = dst_alloc(dst_ops, NULL, 0, DST_OBSOLETE_NONE, 0); + xdst = dst_alloc(dst_ops, NULL, 1, DST_OBSOLETE_NONE, 0); if (likely(xdst)) { struct dst_entry *dst = &xdst->u.dst; @@ -1719,10 +1721,11 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, if (!dst_prev) dst0 = dst1; - else { - dst_prev->child = dst_clone(dst1); - dst1->flags |= DST_NOHASH; - } + else + /* Ref count is taken during xfrm_alloc_dst() + * No need to do dst_clone() on dst1 + */ + dst_prev->child = dst1; xdst->route = dst; dst_copy_metrics(dst1, dst); @@ -1788,7 +1791,7 @@ put_states: xfrm_state_put(xfrm[i]); free_dst: if (dst0) - dst_free(dst0); + dst_release_immediate(dst0); dst0 = ERR_PTR(err); goto out; } @@ -2069,7 +2072,11 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, pol_dead |= pols[i]->walk.dead; } if (pol_dead) { - dst_free(&xdst->u.dst); + /* Mark DST_OBSOLETE_DEAD to fail the next + * xfrm_dst_check() + */ + xdst->u.dst.obsolete = DST_OBSOLETE_DEAD; + dst_release_immediate(&xdst->u.dst); xdst = NULL; num_pols = 0; num_xfrms = 0; @@ -2116,11 +2123,12 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, if (xdst) { /* The policies were stolen for newly generated bundle */ xdst->num_pols = 0; - dst_free(&xdst->u.dst); + /* Mark DST_OBSOLETE_DEAD to fail the next xfrm_dst_check() */ + xdst->u.dst.obsolete = DST_OBSOLETE_DEAD; + dst_release_immediate(&xdst->u.dst); } - /* Flow cache does not have reference, it dst_free()'s, - * but we do need to return one reference for original caller */ + /* We do need to return one reference for original caller */ dst_hold(&new_xdst->u.dst); return &new_xdst->flo; @@ -2143,9 +2151,11 @@ make_dummy_bundle: inc_error: XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); error: - if (xdst != NULL) - dst_free(&xdst->u.dst); - else + if (xdst != NULL) { + /* Mark DST_OBSOLETE_DEAD to fail the next xfrm_dst_check() */ + xdst->u.dst.obsolete = DST_OBSOLETE_DEAD; + dst_release_immediate(&xdst->u.dst); + } else xfrm_pols_put(pols, num_pols); return ERR_PTR(err); } @@ -2217,7 +2227,6 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, } dst_hold(&xdst->u.dst); - xdst->u.dst.flags |= DST_NOCACHE; route = xdst->route; } } @@ -2632,10 +2641,12 @@ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) * notice. That's what we are validating here via the * stale_bundle() check. * - * When a policy's bundle is pruned, we dst_free() the XFRM - * dst which causes it's ->obsolete field to be set to - * DST_OBSOLETE_DEAD. If an XFRM dst has been pruned like - * this, we want to force a new route lookup. + * When an xdst is removed from flow cache, DST_OBSOLETE_DEAD will + * be marked on it. + * When a dst is removed from the fib tree, DST_OBSOLETE_DEAD will + * be marked on it. + * Both will force stable_bundle() to fail on any xdst bundle with + * this dst linked in it. */ if (dst->obsolete < 0 && !stale_bundle(dst)) return dst; @@ -3264,11 +3275,6 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) return -EINVAL; for (i = 0; i < num_migrate; i++) { - if (xfrm_addr_equal(&m[i].old_daddr, &m[i].new_daddr, - m[i].old_family) && - xfrm_addr_equal(&m[i].old_saddr, &m[i].new_saddr, - m[i].old_family)) - return -EINVAL; if (xfrm_addr_any(&m[i].new_daddr, m[i].new_family) || xfrm_addr_any(&m[i].new_saddr, m[i].new_family)) return -EINVAL; @@ -3292,7 +3298,8 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_migrate, - struct xfrm_kmaddress *k, struct net *net) + struct xfrm_kmaddress *k, struct net *net, + struct xfrm_encap_tmpl *encap) { int i, err, nx_cur = 0, nx_new = 0; struct xfrm_policy *pol = NULL; @@ -3315,7 +3322,8 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, if ((x = xfrm_migrate_state_find(mp, net))) { x_cur[nx_cur] = x; nx_cur++; - if ((xc = xfrm_state_migrate(x, mp))) { + xc = xfrm_state_migrate(x, mp, encap); + if (xc) { x_new[nx_new] = xc; nx_new++; } else { @@ -3336,7 +3344,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, } /* Stage 5 - announce */ - km_migrate(sel, dir, type, m, num_migrate, k); + km_migrate(sel, dir, type, m, num_migrate, k, encap); xfrm_pol_put(pol); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 2e291bc5f1fc..6c0956d10db6 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -48,7 +48,7 @@ static HLIST_HEAD(xfrm_state_gc_list); static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x) { - return atomic_inc_not_zero(&x->refcnt); + return refcount_inc_not_zero(&x->refcnt); } static inline unsigned int xfrm_dst_hash(struct net *net, @@ -558,7 +558,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) if (x) { write_pnet(&x->xs_net, net); - atomic_set(&x->refcnt, 1); + refcount_set(&x->refcnt, 1); atomic_set(&x->tunnel_users, 0); INIT_LIST_HEAD(&x->km.all); INIT_HLIST_NODE(&x->bydst); @@ -1309,7 +1309,8 @@ out: EXPORT_SYMBOL(xfrm_state_add); #ifdef CONFIG_XFRM_MIGRATE -static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig) +static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, + struct xfrm_encap_tmpl *encap) { struct net *net = xs_net(orig); struct xfrm_state *x = xfrm_state_alloc(net); @@ -1351,8 +1352,14 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig) } x->props.calgo = orig->props.calgo; - if (orig->encap) { - x->encap = kmemdup(orig->encap, sizeof(*x->encap), GFP_KERNEL); + if (encap || orig->encap) { + if (encap) + x->encap = kmemdup(encap, sizeof(*x->encap), + GFP_KERNEL); + else + x->encap = kmemdup(orig->encap, sizeof(*x->encap), + GFP_KERNEL); + if (!x->encap) goto error; } @@ -1442,11 +1449,12 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n EXPORT_SYMBOL(xfrm_migrate_state_find); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, - struct xfrm_migrate *m) + struct xfrm_migrate *m, + struct xfrm_encap_tmpl *encap) { struct xfrm_state *xc; - xc = xfrm_state_clone(x); + xc = xfrm_state_clone(x, encap); if (!xc) return NULL; @@ -1958,7 +1966,8 @@ EXPORT_SYMBOL(km_policy_expired); #ifdef CONFIG_XFRM_MIGRATE int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, - const struct xfrm_kmaddress *k) + const struct xfrm_kmaddress *k, + const struct xfrm_encap_tmpl *encap) { int err = -EINVAL; int ret; @@ -1967,7 +1976,8 @@ int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->migrate) { - ret = km->migrate(sel, dir, type, m, num_migrate, k); + ret = km->migrate(sel, dir, type, m, num_migrate, k, + encap); if (!ret) err = ret; } @@ -2025,13 +2035,9 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen if (optlen <= 0 || optlen > PAGE_SIZE) return -EMSGSIZE; - data = kmalloc(optlen, GFP_KERNEL); - if (!data) - return -ENOMEM; - - err = -EFAULT; - if (copy_from_user(data, optval, optlen)) - goto out; + data = memdup_user(optval, optlen); + if (IS_ERR(data)) + return PTR_ERR(data); err = -EINVAL; rcu_read_lock(); @@ -2049,7 +2055,6 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen err = 0; } -out: kfree(data); return err; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 86116e9aaf3d..2be4c6af008a 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2244,6 +2244,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, int err; int n = 0; struct net *net = sock_net(skb->sk); + struct xfrm_encap_tmpl *encap = NULL; if (attrs[XFRMA_MIGRATE] == NULL) return -EINVAL; @@ -2261,9 +2262,18 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, if (!n) return 0; - xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net); + if (attrs[XFRMA_ENCAP]) { + encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]), + sizeof(*encap), GFP_KERNEL); + if (!encap) + return 0; + } - return 0; + err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap); + + kfree(encap); + + return err; } #else static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2305,17 +2315,20 @@ static int copy_to_user_kmaddress(const struct xfrm_kmaddress *k, struct sk_buff return nla_put(skb, XFRMA_KMADDRESS, sizeof(uk), &uk); } -static inline size_t xfrm_migrate_msgsize(int num_migrate, int with_kma) +static inline size_t xfrm_migrate_msgsize(int num_migrate, int with_kma, + int with_encp) { return NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_id)) + (with_kma ? nla_total_size(sizeof(struct xfrm_kmaddress)) : 0) + + (with_encp ? nla_total_size(sizeof(struct xfrm_encap_tmpl)) : 0) + nla_total_size(sizeof(struct xfrm_user_migrate) * num_migrate) + userpolicy_type_attrsize(); } static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m, int num_migrate, const struct xfrm_kmaddress *k, - const struct xfrm_selector *sel, u8 dir, u8 type) + const struct xfrm_selector *sel, + const struct xfrm_encap_tmpl *encap, u8 dir, u8 type) { const struct xfrm_migrate *mp; struct xfrm_userpolicy_id *pol_id; @@ -2337,6 +2350,11 @@ static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m, if (err) goto out_cancel; } + if (encap) { + err = nla_put(skb, XFRMA_ENCAP, sizeof(*encap), encap); + if (err) + goto out_cancel; + } err = copy_to_user_policy_type(type, skb); if (err) goto out_cancel; @@ -2356,17 +2374,19 @@ out_cancel: static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, - const struct xfrm_kmaddress *k) + const struct xfrm_kmaddress *k, + const struct xfrm_encap_tmpl *encap) { struct net *net = &init_net; struct sk_buff *skb; - skb = nlmsg_new(xfrm_migrate_msgsize(num_migrate, !!k), GFP_ATOMIC); + skb = nlmsg_new(xfrm_migrate_msgsize(num_migrate, !!k, !!encap), + GFP_ATOMIC); if (skb == NULL) return -ENOMEM; /* build migrate */ - if (build_migrate(skb, m, num_migrate, k, sel, dir, type) < 0) + if (build_migrate(skb, m, num_migrate, k, sel, encap, dir, type) < 0) BUG(); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MIGRATE); @@ -2374,7 +2394,8 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, #else static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, - const struct xfrm_kmaddress *k) + const struct xfrm_kmaddress *k, + const struct xfrm_encap_tmpl *encap) { return -ENOPROTOOPT; } |