diff options
author | Ingo Molnar <mingo@kernel.org> | 2019-12-25 10:41:37 +0100 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2019-12-25 10:41:37 +0100 |
commit | 1e5f8a308551b9816588e12bb795aeadebe37c4a (patch) | |
tree | bd71fc796fed24a3b7cc99df4a1d1bdaecc2b387 /net | |
parent | stop_machine: remove try_stop_cpus helper (diff) | |
parent | Linux 5.5-rc3 (diff) | |
download | linux-1e5f8a308551b9816588e12bb795aeadebe37c4a.tar.xz linux-1e5f8a308551b9816588e12bb795aeadebe37c4a.zip |
Merge tag 'v5.5-rc3' into sched/core, to pick up fixes
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'net')
134 files changed, 1766 insertions, 1263 deletions
diff --git a/net/802/mrp.c b/net/802/mrp.c index 2cfdfbfbb2ed..bea6e43d45a0 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -523,7 +523,7 @@ int mrp_request_join(const struct net_device *dev, struct mrp_attr *attr; if (sizeof(struct mrp_skb_cb) + len > - FIELD_SIZEOF(struct sk_buff, cb)) + sizeof_field(struct sk_buff, cb)) return -ENOMEM; spin_lock_bh(&app->lock); @@ -548,7 +548,7 @@ void mrp_request_leave(const struct net_device *dev, struct mrp_attr *attr; if (sizeof(struct mrp_skb_cb) + len > - FIELD_SIZEOF(struct sk_buff, cb)) + sizeof_field(struct sk_buff, cb)) return; spin_lock_bh(&app->lock); @@ -692,7 +692,7 @@ static int mrp_pdu_parse_vecattr(struct mrp_applicant *app, * advance to the next event in its Vector. */ if (sizeof(struct mrp_skb_cb) + mrp_cb(skb)->mh->attrlen > - FIELD_SIZEOF(struct sk_buff, cb)) + sizeof_field(struct sk_buff, cb)) return -1; if (skb_copy_bits(skb, *offset, mrp_cb(skb)->attrvalue, mrp_cb(skb)->mh->attrlen) < 0) diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 4a89177def64..4811ec65bc43 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -548,7 +548,7 @@ static void batadv_recv_handler_init(void) BUILD_BUG_ON(sizeof(struct batadv_tvlv_tt_change) != 12); BUILD_BUG_ON(sizeof(struct batadv_tvlv_roam_adv) != 8); - i = FIELD_SIZEOF(struct sk_buff, cb); + i = sizeof_field(struct sk_buff, cb); BUILD_BUG_ON(sizeof(struct batadv_skb_cb) > i); /* broadcast packet */ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 915c2d6f7fb9..f79205d4444f 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -253,21 +253,21 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) /* priority is allowed */ if (!range_is_zero(__skb, offsetof(struct __sk_buff, priority) + - FIELD_SIZEOF(struct __sk_buff, priority), + sizeof_field(struct __sk_buff, priority), offsetof(struct __sk_buff, cb))) return -EINVAL; /* cb is allowed */ if (!range_is_zero(__skb, offsetof(struct __sk_buff, cb) + - FIELD_SIZEOF(struct __sk_buff, cb), + sizeof_field(struct __sk_buff, cb), offsetof(struct __sk_buff, tstamp))) return -EINVAL; /* tstamp is allowed */ if (!range_is_zero(__skb, offsetof(struct __sk_buff, tstamp) + - FIELD_SIZEOF(struct __sk_buff, tstamp), + sizeof_field(struct __sk_buff, tstamp), sizeof(struct __sk_buff))) return -EINVAL; @@ -438,7 +438,7 @@ static int verify_user_bpf_flow_keys(struct bpf_flow_keys *ctx) /* flags is allowed */ if (!range_is_zero(ctx, offsetof(struct bpf_flow_keys, flags) + - FIELD_SIZEOF(struct bpf_flow_keys, flags), + sizeof_field(struct bpf_flow_keys, flags), sizeof(struct bpf_flow_keys))) return -EINVAL; diff --git a/net/bridge/br.c b/net/bridge/br.c index 8a8f9e5f264f..b6fe30e3768f 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -312,7 +312,7 @@ static int __init br_init(void) { int err; - BUILD_BUG_ON(sizeof(struct br_input_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct br_input_skb_cb) > sizeof_field(struct sk_buff, cb)); err = stp_proto_register(&br_stp_proto); if (err < 0) { diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 434effde02c3..fb38add21b37 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -245,6 +245,12 @@ static int br_set_mac_address(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; + /* dev_set_mac_addr() can be called by a master device on bridge's + * NETDEV_UNREGISTER, but since it's being destroyed do nothing + */ + if (dev->reg_state != NETREG_REGISTERED) + return -EBUSY; + spin_lock_bh(&br->lock); if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) { /* Mac address will be changed in br_stp_change_bridge_id(). */ diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index af7800103e51..59980ecfc962 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -662,6 +662,9 @@ static unsigned int br_nf_forward_arp(void *priv, nf_bridge_pull_encap_header(skb); } + if (unlikely(!pskb_may_pull(skb, sizeof(struct arphdr)))) + return NF_DROP; + if (arp_hdr(skb)->ar_pln != 4) { if (is_vlan_arp(skb, state->net)) nf_bridge_push_encap_header(skb); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index de09b0a65791..f7587428febd 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -423,9 +423,9 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct j1939_sock *jsk = j1939_sk(sock->sk); - struct j1939_priv *priv = jsk->priv; - struct sock *sk = sock->sk; - struct net *net = sock_net(sk); + struct j1939_priv *priv; + struct sock *sk; + struct net *net; int ret = 0; ret = j1939_sk_sanity_check(addr, len); @@ -434,6 +434,10 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) lock_sock(sock->sk); + priv = jsk->priv; + sk = sock->sk; + net = sock_net(sk); + /* Already bound to an interface? */ if (jsk->state & J1939_SOCK_BOUND) { /* A re-bind() to a different interface is not diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 2d568246803f..a9d6c97b5b0d 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -11,7 +11,7 @@ #include <linux/module.h> #include <linux/mount.h> #include <linux/nsproxy.h> -#include <linux/parser.h> +#include <linux/fs_parser.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/seq_file.h> @@ -254,58 +254,77 @@ enum { Opt_mount_timeout, Opt_osd_idle_ttl, Opt_osd_request_timeout, - Opt_last_int, /* int args above */ Opt_fsid, Opt_name, Opt_secret, Opt_key, Opt_ip, - Opt_last_string, /* string args above */ Opt_share, - Opt_noshare, Opt_crc, - Opt_nocrc, Opt_cephx_require_signatures, - Opt_nocephx_require_signatures, Opt_cephx_sign_messages, - Opt_nocephx_sign_messages, Opt_tcp_nodelay, - Opt_notcp_nodelay, Opt_abort_on_full, }; -static match_table_t opt_tokens = { - {Opt_osdtimeout, "osdtimeout=%d"}, - {Opt_osdkeepalivetimeout, "osdkeepalive=%d"}, - {Opt_mount_timeout, "mount_timeout=%d"}, - {Opt_osd_idle_ttl, "osd_idle_ttl=%d"}, - {Opt_osd_request_timeout, "osd_request_timeout=%d"}, - /* int args above */ - {Opt_fsid, "fsid=%s"}, - {Opt_name, "name=%s"}, - {Opt_secret, "secret=%s"}, - {Opt_key, "key=%s"}, - {Opt_ip, "ip=%s"}, - /* string args above */ - {Opt_share, "share"}, - {Opt_noshare, "noshare"}, - {Opt_crc, "crc"}, - {Opt_nocrc, "nocrc"}, - {Opt_cephx_require_signatures, "cephx_require_signatures"}, - {Opt_nocephx_require_signatures, "nocephx_require_signatures"}, - {Opt_cephx_sign_messages, "cephx_sign_messages"}, - {Opt_nocephx_sign_messages, "nocephx_sign_messages"}, - {Opt_tcp_nodelay, "tcp_nodelay"}, - {Opt_notcp_nodelay, "notcp_nodelay"}, - {Opt_abort_on_full, "abort_on_full"}, - {-1, NULL} +static const struct fs_parameter_spec ceph_param_specs[] = { + fsparam_flag ("abort_on_full", Opt_abort_on_full), + fsparam_flag_no ("cephx_require_signatures", Opt_cephx_require_signatures), + fsparam_flag_no ("cephx_sign_messages", Opt_cephx_sign_messages), + fsparam_flag_no ("crc", Opt_crc), + fsparam_string ("fsid", Opt_fsid), + fsparam_string ("ip", Opt_ip), + fsparam_string ("key", Opt_key), + fsparam_u32 ("mount_timeout", Opt_mount_timeout), + fsparam_string ("name", Opt_name), + fsparam_u32 ("osd_idle_ttl", Opt_osd_idle_ttl), + fsparam_u32 ("osd_request_timeout", Opt_osd_request_timeout), + fsparam_u32 ("osdkeepalive", Opt_osdkeepalivetimeout), + __fsparam (fs_param_is_s32, "osdtimeout", Opt_osdtimeout, + fs_param_deprecated), + fsparam_string ("secret", Opt_secret), + fsparam_flag_no ("share", Opt_share), + fsparam_flag_no ("tcp_nodelay", Opt_tcp_nodelay), + {} +}; + +static const struct fs_parameter_description ceph_parameters = { + .name = "libceph", + .specs = ceph_param_specs, }; +struct ceph_options *ceph_alloc_options(void) +{ + struct ceph_options *opt; + + opt = kzalloc(sizeof(*opt), GFP_KERNEL); + if (!opt) + return NULL; + + opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr), + GFP_KERNEL); + if (!opt->mon_addr) { + kfree(opt); + return NULL; + } + + opt->flags = CEPH_OPT_DEFAULT; + opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; + opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; + opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; + opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT; + return opt; +} +EXPORT_SYMBOL(ceph_alloc_options); + void ceph_destroy_options(struct ceph_options *opt) { dout("destroy_options %p\n", opt); + if (!opt) + return; + kfree(opt->name); if (opt->key) { ceph_crypto_key_destroy(opt->key); @@ -317,7 +336,9 @@ void ceph_destroy_options(struct ceph_options *opt) EXPORT_SYMBOL(ceph_destroy_options); /* get secret from key store */ -static int get_secret(struct ceph_crypto_key *dst, const char *name) { +static int get_secret(struct ceph_crypto_key *dst, const char *name, + struct fs_context *fc) +{ struct key *ukey; int key_err; int err = 0; @@ -330,20 +351,20 @@ static int get_secret(struct ceph_crypto_key *dst, const char *name) { key_err = PTR_ERR(ukey); switch (key_err) { case -ENOKEY: - pr_warn("ceph: Mount failed due to key not found: %s\n", - name); + errorf(fc, "libceph: Failed due to key not found: %s", + name); break; case -EKEYEXPIRED: - pr_warn("ceph: Mount failed due to expired key: %s\n", - name); + errorf(fc, "libceph: Failed due to expired key: %s", + name); break; case -EKEYREVOKED: - pr_warn("ceph: Mount failed due to revoked key: %s\n", - name); + errorf(fc, "libceph: Failed due to revoked key: %s", + name); break; default: - pr_warn("ceph: Mount failed due to unknown key error %d: %s\n", - key_err, name); + errorf(fc, "libceph: Failed due to key error %d: %s", + key_err, name); } err = -EPERM; goto out; @@ -361,217 +382,157 @@ out: return err; } -struct ceph_options * -ceph_parse_options(char *options, const char *dev_name, - const char *dev_name_end, - int (*parse_extra_token)(char *c, void *private), - void *private) +int ceph_parse_mon_ips(const char *buf, size_t len, struct ceph_options *opt, + struct fs_context *fc) { - struct ceph_options *opt; - const char *c; - int err = -ENOMEM; - substring_t argstr[MAX_OPT_ARGS]; - - opt = kzalloc(sizeof(*opt), GFP_KERNEL); - if (!opt) - return ERR_PTR(-ENOMEM); - opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr), - GFP_KERNEL); - if (!opt->mon_addr) - goto out; - - dout("parse_options %p options '%s' dev_name '%s'\n", opt, options, - dev_name); - - /* start with defaults */ - opt->flags = CEPH_OPT_DEFAULT; - opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; - opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; - opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; - opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT; + int ret; - /* get mon ip(s) */ /* ip1[:port1][,ip2[:port2]...] */ - err = ceph_parse_ips(dev_name, dev_name_end, opt->mon_addr, - CEPH_MAX_MON, &opt->num_mon); - if (err < 0) - goto out; + ret = ceph_parse_ips(buf, buf + len, opt->mon_addr, CEPH_MAX_MON, + &opt->num_mon); + if (ret) { + errorf(fc, "libceph: Failed to parse monitor IPs: %d", ret); + return ret; + } - /* parse mount options */ - while ((c = strsep(&options, ",")) != NULL) { - int token, intval; - if (!*c) - continue; - err = -EINVAL; - token = match_token((char *)c, opt_tokens, argstr); - if (token < 0 && parse_extra_token) { - /* extra? */ - err = parse_extra_token((char *)c, private); - if (err < 0) { - pr_err("bad option at '%s'\n", c); - goto out; - } - continue; - } - if (token < Opt_last_int) { - err = match_int(&argstr[0], &intval); - if (err < 0) { - pr_err("bad option arg (not int) at '%s'\n", c); - goto out; - } - dout("got int token %d val %d\n", token, intval); - } else if (token > Opt_last_int && token < Opt_last_string) { - dout("got string token %d val %s\n", token, - argstr[0].from); - } else { - dout("got token %d\n", token); + return 0; +} +EXPORT_SYMBOL(ceph_parse_mon_ips); + +int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, + struct fs_context *fc) +{ + struct fs_parse_result result; + int token, err; + + token = fs_parse(fc, &ceph_parameters, param, &result); + dout("%s fs_parse '%s' token %d\n", __func__, param->key, token); + if (token < 0) + return token; + + switch (token) { + case Opt_ip: + err = ceph_parse_ips(param->string, + param->string + param->size, + &opt->my_addr, + 1, NULL); + if (err) { + errorf(fc, "libceph: Failed to parse ip: %d", err); + return err; } - switch (token) { - case Opt_ip: - err = ceph_parse_ips(argstr[0].from, - argstr[0].to, - &opt->my_addr, - 1, NULL); - if (err < 0) - goto out; - opt->flags |= CEPH_OPT_MYIP; - break; + opt->flags |= CEPH_OPT_MYIP; + break; - case Opt_fsid: - err = parse_fsid(argstr[0].from, &opt->fsid); - if (err == 0) - opt->flags |= CEPH_OPT_FSID; - break; - case Opt_name: - kfree(opt->name); - opt->name = kstrndup(argstr[0].from, - argstr[0].to-argstr[0].from, - GFP_KERNEL); - if (!opt->name) { - err = -ENOMEM; - goto out; - } - break; - case Opt_secret: - ceph_crypto_key_destroy(opt->key); - kfree(opt->key); - - opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); - if (!opt->key) { - err = -ENOMEM; - goto out; - } - err = ceph_crypto_key_unarmor(opt->key, argstr[0].from); - if (err < 0) - goto out; - break; - case Opt_key: - ceph_crypto_key_destroy(opt->key); - kfree(opt->key); - - opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); - if (!opt->key) { - err = -ENOMEM; - goto out; - } - err = get_secret(opt->key, argstr[0].from); - if (err < 0) - goto out; - break; + case Opt_fsid: + err = parse_fsid(param->string, &opt->fsid); + if (err) { + errorf(fc, "libceph: Failed to parse fsid: %d", err); + return err; + } + opt->flags |= CEPH_OPT_FSID; + break; + case Opt_name: + kfree(opt->name); + opt->name = param->string; + param->string = NULL; + break; + case Opt_secret: + ceph_crypto_key_destroy(opt->key); + kfree(opt->key); - /* misc */ - case Opt_osdtimeout: - pr_warn("ignoring deprecated osdtimeout option\n"); - break; - case Opt_osdkeepalivetimeout: - /* 0 isn't well defined right now, reject it */ - if (intval < 1 || intval > INT_MAX / 1000) { - pr_err("osdkeepalive out of range\n"); - err = -EINVAL; - goto out; - } - opt->osd_keepalive_timeout = - msecs_to_jiffies(intval * 1000); - break; - case Opt_osd_idle_ttl: - /* 0 isn't well defined right now, reject it */ - if (intval < 1 || intval > INT_MAX / 1000) { - pr_err("osd_idle_ttl out of range\n"); - err = -EINVAL; - goto out; - } - opt->osd_idle_ttl = msecs_to_jiffies(intval * 1000); - break; - case Opt_mount_timeout: - /* 0 is "wait forever" (i.e. infinite timeout) */ - if (intval < 0 || intval > INT_MAX / 1000) { - pr_err("mount_timeout out of range\n"); - err = -EINVAL; - goto out; - } - opt->mount_timeout = msecs_to_jiffies(intval * 1000); - break; - case Opt_osd_request_timeout: - /* 0 is "wait forever" (i.e. infinite timeout) */ - if (intval < 0 || intval > INT_MAX / 1000) { - pr_err("osd_request_timeout out of range\n"); - err = -EINVAL; - goto out; - } - opt->osd_request_timeout = msecs_to_jiffies(intval * 1000); - break; + opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); + if (!opt->key) + return -ENOMEM; + err = ceph_crypto_key_unarmor(opt->key, param->string); + if (err) { + errorf(fc, "libceph: Failed to parse secret: %d", err); + return err; + } + break; + case Opt_key: + ceph_crypto_key_destroy(opt->key); + kfree(opt->key); - case Opt_share: + opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); + if (!opt->key) + return -ENOMEM; + return get_secret(opt->key, param->string, fc); + + case Opt_osdtimeout: + warnf(fc, "libceph: Ignoring osdtimeout"); + break; + case Opt_osdkeepalivetimeout: + /* 0 isn't well defined right now, reject it */ + if (result.uint_32 < 1 || result.uint_32 > INT_MAX / 1000) + goto out_of_range; + opt->osd_keepalive_timeout = + msecs_to_jiffies(result.uint_32 * 1000); + break; + case Opt_osd_idle_ttl: + /* 0 isn't well defined right now, reject it */ + if (result.uint_32 < 1 || result.uint_32 > INT_MAX / 1000) + goto out_of_range; + opt->osd_idle_ttl = msecs_to_jiffies(result.uint_32 * 1000); + break; + case Opt_mount_timeout: + /* 0 is "wait forever" (i.e. infinite timeout) */ + if (result.uint_32 > INT_MAX / 1000) + goto out_of_range; + opt->mount_timeout = msecs_to_jiffies(result.uint_32 * 1000); + break; + case Opt_osd_request_timeout: + /* 0 is "wait forever" (i.e. infinite timeout) */ + if (result.uint_32 > INT_MAX / 1000) + goto out_of_range; + opt->osd_request_timeout = + msecs_to_jiffies(result.uint_32 * 1000); + break; + + case Opt_share: + if (!result.negated) opt->flags &= ~CEPH_OPT_NOSHARE; - break; - case Opt_noshare: + else opt->flags |= CEPH_OPT_NOSHARE; - break; - - case Opt_crc: + break; + case Opt_crc: + if (!result.negated) opt->flags &= ~CEPH_OPT_NOCRC; - break; - case Opt_nocrc: + else opt->flags |= CEPH_OPT_NOCRC; - break; - - case Opt_cephx_require_signatures: + break; + case Opt_cephx_require_signatures: + if (!result.negated) opt->flags &= ~CEPH_OPT_NOMSGAUTH; - break; - case Opt_nocephx_require_signatures: + else opt->flags |= CEPH_OPT_NOMSGAUTH; - break; - case Opt_cephx_sign_messages: + break; + case Opt_cephx_sign_messages: + if (!result.negated) opt->flags &= ~CEPH_OPT_NOMSGSIGN; - break; - case Opt_nocephx_sign_messages: + else opt->flags |= CEPH_OPT_NOMSGSIGN; - break; - - case Opt_tcp_nodelay: + break; + case Opt_tcp_nodelay: + if (!result.negated) opt->flags |= CEPH_OPT_TCP_NODELAY; - break; - case Opt_notcp_nodelay: + else opt->flags &= ~CEPH_OPT_TCP_NODELAY; - break; + break; - case Opt_abort_on_full: - opt->flags |= CEPH_OPT_ABORT_ON_FULL; - break; + case Opt_abort_on_full: + opt->flags |= CEPH_OPT_ABORT_ON_FULL; + break; - default: - BUG_ON(token); - } + default: + BUG(); } - /* success */ - return opt; + return 0; -out: - ceph_destroy_options(opt); - return ERR_PTR(err); +out_of_range: + return invalf(fc, "libceph: %s out of range", param->key); } -EXPORT_SYMBOL(ceph_parse_options); +EXPORT_SYMBOL(ceph_parse_param); int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, bool show_all) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index e4cb3db2ee77..5b4bd8261002 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2004,10 +2004,8 @@ int ceph_parse_ips(const char *c, const char *end, return 0; bad: - pr_err("parse_ips bad ip '%.*s'\n", (int)(end - c), c); return ret; } -EXPORT_SYMBOL(ceph_parse_ips); static int process_banner(struct ceph_connection *con) { diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 7256c402ebaa..9d9e4e4ea600 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -1233,9 +1233,6 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) struct ceph_mon_client *monc = con->private; int type = le16_to_cpu(msg->hdr.type); - if (!monc) - return; - switch (type) { case CEPH_MSG_AUTH_REPLY: handle_auth_reply(monc, msg); diff --git a/net/core/dev.c b/net/core/dev.c index de5f14bc639d..2ca5bf191ae5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8188,7 +8188,8 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu) if (ops->ndo_change_mtu) return ops->ndo_change_mtu(dev, new_mtu); - dev->mtu = new_mtu; + /* Pairs with all the lockless reads of dev->mtu in the stack */ + WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL(__dev_set_mtu); @@ -9246,7 +9247,7 @@ int register_netdevice(struct net_device *dev) if (ret) { if (ret > 0) ret = -EIO; - goto out; + goto err_free_name; } } @@ -9361,12 +9362,12 @@ out: return ret; err_uninit: - if (dev->name_node) - netdev_name_node_free(dev->name_node); if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); if (dev->priv_destructor) dev->priv_destructor(dev); +err_free_name: + netdev_name_node_free(dev->name_node); goto out; } EXPORT_SYMBOL(register_netdevice); @@ -10164,7 +10165,7 @@ static struct hlist_head * __net_init netdev_create_hash(void) static int __net_init netdev_init(struct net *net) { BUILD_BUG_ON(GRO_HASH_BUCKETS > - 8 * FIELD_SIZEOF(struct napi_struct, gro_bitmask)); + 8 * sizeof_field(struct napi_struct, gro_bitmask)); if (net != &init_net) INIT_LIST_HEAD(&net->dev_base_head); diff --git a/net/core/filter.c b/net/core/filter.c index f1e703eed3d2..28b3c258188c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -274,7 +274,7 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, switch (skb_field) { case SKF_AD_MARK: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + BUILD_BUG_ON(sizeof_field(struct sk_buff, mark) != 4); *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sk_buff, mark)); @@ -289,14 +289,14 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, break; case SKF_AD_QUEUE: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, queue_mapping) != 2); *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, queue_mapping)); break; case SKF_AD_VLAN_TAG: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_tci) != 2); /* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, @@ -322,7 +322,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, switch (fp->k) { case SKF_AD_OFF + SKF_AD_PROTOCOL: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, protocol) != 2); /* A = *(u16 *) (CTX + offsetof(protocol)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, @@ -338,8 +338,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, case SKF_AD_OFF + SKF_AD_IFINDEX: case SKF_AD_OFF + SKF_AD_HATYPE: - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); + BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4); + BUILD_BUG_ON(sizeof_field(struct net_device, type) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), BPF_REG_TMP, BPF_REG_CTX, @@ -361,7 +361,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, break; case SKF_AD_OFF + SKF_AD_RXHASH: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + BUILD_BUG_ON(sizeof_field(struct sk_buff, hash) != 4); *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, hash)); @@ -385,7 +385,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, break; case SKF_AD_OFF + SKF_AD_VLAN_TPID: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_proto) != 2); /* A = *(u16 *) (CTX + offsetof(vlan_proto)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, @@ -2055,6 +2055,7 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) } skb->dev = dev; + skb->tstamp = 0; dev_xmit_recursion_inc(); ret = dev_queue_xmit(skb); @@ -5589,8 +5590,8 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, #define BPF_TCP_SOCK_GET_COMMON(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, FIELD) > \ - FIELD_SIZEOF(struct bpf_tcp_sock, FIELD)); \ + BUILD_BUG_ON(sizeof_field(struct tcp_sock, FIELD) > \ + sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct tcp_sock, FIELD)); \ @@ -5598,9 +5599,9 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, #define BPF_INET_SOCK_GET_COMMON(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct inet_connection_sock, \ + BUILD_BUG_ON(sizeof_field(struct inet_connection_sock, \ FIELD) > \ - FIELD_SIZEOF(struct bpf_tcp_sock, FIELD)); \ + sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct inet_connection_sock, \ FIELD), \ @@ -5615,7 +5616,7 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, switch (si->off) { case offsetof(struct bpf_tcp_sock, rtt_min): - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, rtt_min) != + BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); @@ -5780,8 +5781,8 @@ u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, #define BPF_XDP_SOCK_GET(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_sock, FIELD) > \ - FIELD_SIZEOF(struct bpf_xdp_sock, FIELD)); \ + BUILD_BUG_ON(sizeof_field(struct xdp_sock, FIELD) > \ + sizeof_field(struct bpf_xdp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct xdp_sock, FIELD)); \ @@ -7344,7 +7345,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20); + BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, data)) % sizeof(__u64)); @@ -7363,7 +7364,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, tc_classid): - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, tc_classid) != 2); + BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, tc_classid) != 2); off = si->off; off -= offsetof(struct __sk_buff, tc_classid); @@ -7434,7 +7435,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, #endif break; case offsetof(struct __sk_buff, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7445,7 +7446,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, 2, target_size)); break; case offsetof(struct __sk_buff, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7456,7 +7457,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, 4, target_size)); break; case offsetof(struct __sk_buff, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), @@ -7470,7 +7471,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, remote_ip6[0]) ... offsetof(struct __sk_buff, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; @@ -7490,7 +7491,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, local_ip6[0]) ... offsetof(struct __sk_buff, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; @@ -7509,7 +7510,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7524,7 +7525,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7535,7 +7536,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, tstamp): - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tstamp) != 8); + BUILD_BUG_ON(sizeof_field(struct sk_buff, tstamp) != 8); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_DW, @@ -7573,7 +7574,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, target_size)); break; case offsetof(struct __sk_buff, wire_len): - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, pkt_len) != 4); + BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, pkt_len) != 4); off = si->off; off -= offsetof(struct __sk_buff, wire_len); @@ -7603,7 +7604,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, switch (si->off) { case offsetof(struct bpf_sock, bound_dev_if): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_bound_dev_if) != 4); + BUILD_BUG_ON(sizeof_field(struct sock, sk_bound_dev_if) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@ -7614,7 +7615,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock, mark): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_mark) != 4); + BUILD_BUG_ON(sizeof_field(struct sock, sk_mark) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@ -7625,7 +7626,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock, priority): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_priority) != 4); + BUILD_BUG_ON(sizeof_field(struct sock, sk_priority) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@ -7641,7 +7642,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_family, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_family), target_size)); break; @@ -7668,7 +7669,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_rcv_saddr), target_size)); break; @@ -7677,7 +7678,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_daddr, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_daddr), target_size)); break; @@ -7691,7 +7692,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, bpf_target_off( struct sock_common, skc_v6_rcv_saddr.s6_addr32[0], - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]), target_size) + off); #else @@ -7708,7 +7709,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_v6_daddr.s6_addr32[0], - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]), target_size) + off); #else @@ -7722,7 +7723,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct sock_common, skc_num), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_num, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_num), target_size)); break; @@ -7732,7 +7733,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct sock_common, skc_dport), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_dport, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_dport), target_size)); break; @@ -7742,7 +7743,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct sock_common, skc_state), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_state, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_state), target_size)); break; @@ -7837,7 +7838,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, si->src_reg, offsetof(S, F)); \ *insn++ = BPF_LDX_MEM( \ SIZE, si->dst_reg, si->dst_reg, \ - bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF), \ + bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF); \ } while (0) @@ -7868,7 +7869,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), tmp_reg, \ si->dst_reg, offsetof(S, F)); \ *insn++ = BPF_STX_MEM(SIZE, tmp_reg, si->src_reg, \ - bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF), \ + bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF); \ *insn++ = BPF_LDX_MEM(BPF_DW, tmp_reg, si->dst_reg, \ @@ -7930,8 +7931,8 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, */ BUILD_BUG_ON(offsetof(struct sockaddr_in, sin_port) != offsetof(struct sockaddr_in6, sin6_port)); - BUILD_BUG_ON(FIELD_SIZEOF(struct sockaddr_in, sin_port) != - FIELD_SIZEOF(struct sockaddr_in6, sin6_port)); + BUILD_BUG_ON(sizeof_field(struct sockaddr_in, sin_port) != + sizeof_field(struct sockaddr_in6, sin6_port)); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD(struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_port, tmp_reg); @@ -7997,8 +7998,8 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, /* Helper macro for adding read access to tcp_sock or sock fields. */ #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ - FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ + BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ + sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ @@ -8031,8 +8032,8 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, #define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int reg = BPF_REG_9; \ - BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ - FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ + BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ + sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ @@ -8073,12 +8074,12 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, 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)); + BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, op) != + sizeof_field(struct bpf_sock_ops_kern, op)); + BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) != + sizeof_field(struct bpf_sock_ops_kern, reply)); + BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) != + sizeof_field(struct bpf_sock_ops_kern, replylong)); off = si->off; off -= offsetof(struct bpf_sock_ops, op); off += offsetof(struct bpf_sock_ops_kern, op); @@ -8091,7 +8092,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8102,7 +8103,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8113,7 +8114,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( @@ -8128,7 +8129,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, 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, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; @@ -8149,7 +8150,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, 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, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; @@ -8168,7 +8169,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8182,7 +8183,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8202,7 +8203,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, state): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_state) != 1); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_state) != 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8213,7 +8214,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, rtt_min): - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, rtt_min) != + BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); @@ -8224,7 +8225,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct tcp_sock, rtt_min) + - FIELD_SIZEOF(struct minmax_sample, t)); + sizeof_field(struct minmax_sample, t)); break; case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags): @@ -8366,7 +8367,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, offsetof(struct sk_msg, data_end)); break; case offsetof(struct sk_msg_md, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8377,7 +8378,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8388,7 +8389,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( @@ -8403,7 +8404,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, case offsetof(struct sk_msg_md, remote_ip6[0]) ... offsetof(struct sk_msg_md, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; @@ -8424,7 +8425,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, case offsetof(struct sk_msg_md, local_ip6[0]) ... offsetof(struct sk_msg_md, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; @@ -8443,7 +8444,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8457,7 +8458,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8847,7 +8848,7 @@ sk_reuseport_is_valid_access(int off, int size, /* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): - if (size < FIELD_SIZEOF(struct sk_buff, protocol)) + if (size < sizeof_field(struct sk_buff, protocol)) return false; /* fall through */ case bpf_ctx_range(struct sk_reuseport_md, ip_protocol): @@ -8865,7 +8866,7 @@ sk_reuseport_is_valid_access(int off, int size, *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_reuseport_kern, F), \ si->dst_reg, si->src_reg, \ bpf_target_off(struct sk_reuseport_kern, F, \ - FIELD_SIZEOF(struct sk_reuseport_kern, F), \ + sizeof_field(struct sk_reuseport_kern, F), \ target_size)); \ }) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index ca871657a4c4..2dbbb030fbed 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -599,8 +599,8 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, offset += sizeof(struct gre_base_hdr); if (hdr->flags & GRE_CSUM) - offset += FIELD_SIZEOF(struct gre_full_hdr, csum) + - FIELD_SIZEOF(struct gre_full_hdr, reserved1); + offset += sizeof_field(struct gre_full_hdr, csum) + + sizeof_field(struct gre_full_hdr, reserved1); if (hdr->flags & GRE_KEY) { const __be32 *keyid; @@ -622,11 +622,11 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, else key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; } - offset += FIELD_SIZEOF(struct gre_full_hdr, key); + offset += sizeof_field(struct gre_full_hdr, key); } if (hdr->flags & GRE_SEQ) - offset += FIELD_SIZEOF(struct pptp_gre_header, seq); + offset += sizeof_field(struct pptp_gre_header, seq); if (gre_ver == 0) { if (*p_proto == htons(ETH_P_TEB)) { @@ -653,7 +653,7 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, u8 *ppp_hdr; if (hdr->flags & GRE_ACK) - offset += FIELD_SIZEOF(struct pptp_gre_header, ack); + offset += sizeof_field(struct pptp_gre_header, ack); ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_ppp_hdr), @@ -760,6 +760,31 @@ __skb_flow_dissect_tcp(const struct sk_buff *skb, } static void +__skb_flow_dissect_ports(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, int nhoff, + u8 ip_proto, int hlen) +{ + enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX; + struct flow_dissector_key_ports *key_ports; + + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) + dissector_ports = FLOW_DISSECTOR_KEY_PORTS; + else if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE)) + dissector_ports = FLOW_DISSECTOR_KEY_PORTS_RANGE; + + if (dissector_ports == FLOW_DISSECTOR_KEY_MAX) + return; + + key_ports = skb_flow_dissector_target(flow_dissector, + dissector_ports, + target_container); + key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, + data, hlen); +} + +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) @@ -928,7 +953,6 @@ bool __skb_flow_dissect(const struct net *net, struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; - struct flow_dissector_key_ports *key_ports; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; struct bpf_prog *attached = NULL; @@ -945,9 +969,10 @@ bool __skb_flow_dissect(const struct net *net, nhoff = skb_network_offset(skb); hlen = skb_headlen(skb); #if IS_ENABLED(CONFIG_NET_DSA) - if (unlikely(skb->dev && netdev_uses_dsa(skb->dev))) { + if (unlikely(skb->dev && netdev_uses_dsa(skb->dev) && + proto == htons(ETH_P_XDSA))) { const struct dsa_device_ops *ops; - int offset; + int offset = 0; ops = skb->dev->dsa_ptr->tag_ops; if (ops->flow_dissect && @@ -1383,14 +1408,9 @@ ip_proto_again: break; } - if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) && - !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) { - key_ports = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS, - target_container); - key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, - data, hlen); - } + if (!(key_control->flags & FLOW_DIS_IS_FRAGMENT)) + __skb_flow_dissect_ports(skb, flow_dissector, target_container, + data, nhoff, ip_proto, hlen); /* Process result of IP proto processing */ switch (fdret) { diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index cf52d9c422fa..45b6a59ac124 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -283,7 +283,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f, } EXPORT_SYMBOL(flow_block_cb_setup_simple); -static LIST_HEAD(block_ing_cb_list); +static LIST_HEAD(block_cb_list); static struct rhashtable indr_setup_block_ht; @@ -391,20 +391,19 @@ static void flow_indr_block_cb_del(struct flow_indr_block_cb *indr_block_cb) kfree(indr_block_cb); } -static DEFINE_MUTEX(flow_indr_block_ing_cb_lock); +static DEFINE_MUTEX(flow_indr_block_cb_lock); -static void flow_block_ing_cmd(struct net_device *dev, - flow_indr_block_bind_cb_t *cb, - void *cb_priv, - enum flow_block_command command) +static void flow_block_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, void *cb_priv, + enum flow_block_command command) { - struct flow_indr_block_ing_entry *entry; + struct flow_indr_block_entry *entry; - mutex_lock(&flow_indr_block_ing_cb_lock); - list_for_each_entry(entry, &block_ing_cb_list, list) { + mutex_lock(&flow_indr_block_cb_lock); + list_for_each_entry(entry, &block_cb_list, list) { entry->cb(dev, cb, cb_priv, command); } - mutex_unlock(&flow_indr_block_ing_cb_lock); + mutex_unlock(&flow_indr_block_cb_lock); } int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, @@ -424,8 +423,8 @@ int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, if (err) goto err_dev_put; - flow_block_ing_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, - FLOW_BLOCK_BIND); + flow_block_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, + FLOW_BLOCK_BIND); return 0; @@ -464,8 +463,8 @@ void __flow_indr_block_cb_unregister(struct net_device *dev, if (!indr_block_cb) return; - flow_block_ing_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, - FLOW_BLOCK_UNBIND); + flow_block_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, + FLOW_BLOCK_UNBIND); flow_indr_block_cb_del(indr_block_cb); flow_indr_block_dev_put(indr_dev); @@ -499,21 +498,21 @@ void flow_indr_block_call(struct net_device *dev, } EXPORT_SYMBOL_GPL(flow_indr_block_call); -void flow_indr_add_block_ing_cb(struct flow_indr_block_ing_entry *entry) +void flow_indr_add_block_cb(struct flow_indr_block_entry *entry) { - mutex_lock(&flow_indr_block_ing_cb_lock); - list_add_tail(&entry->list, &block_ing_cb_list); - mutex_unlock(&flow_indr_block_ing_cb_lock); + mutex_lock(&flow_indr_block_cb_lock); + list_add_tail(&entry->list, &block_cb_list); + mutex_unlock(&flow_indr_block_cb_lock); } -EXPORT_SYMBOL_GPL(flow_indr_add_block_ing_cb); +EXPORT_SYMBOL_GPL(flow_indr_add_block_cb); -void flow_indr_del_block_ing_cb(struct flow_indr_block_ing_entry *entry) +void flow_indr_del_block_cb(struct flow_indr_block_entry *entry) { - mutex_lock(&flow_indr_block_ing_cb_lock); + mutex_lock(&flow_indr_block_cb_lock); list_del(&entry->list); - mutex_unlock(&flow_indr_block_ing_cb_lock); + mutex_unlock(&flow_indr_block_cb_lock); } -EXPORT_SYMBOL_GPL(flow_indr_del_block_ing_cb); +EXPORT_SYMBOL_GPL(flow_indr_del_block_cb); static int __init init_flow_indr_rhashtable(void) { diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 74cfb8b5ab33..99a6de52b21d 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -230,9 +230,7 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb) fl6.daddr = iph6->daddr; fl6.saddr = iph6->saddr; - err = ipv6_stub->ipv6_dst_lookup(net, skb->sk, &dst, &fl6); - if (unlikely(err)) - goto err; + dst = ipv6_stub->ipv6_dst_lookup_flow(net, skb->sk, &fl6, NULL); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto err; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 652da6369037..920784a9b7ff 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -98,9 +98,6 @@ static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb) static void neigh_cleanup_and_release(struct neighbour *neigh) { - if (neigh->parms->neigh_cleanup) - neigh->parms->neigh_cleanup(neigh); - trace_neigh_cleanup_and_release(neigh, 0); __neigh_notify(neigh, RTM_DELNEIGH, 0, 0); call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index ae3bcb1540ec..4c826b8bf9b1 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -919,14 +919,17 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) struct kobject *kobj = &queue->kobj; int error = 0; + /* Kobject_put later will trigger rx_queue_release call which + * decreases dev refcount: Take that reference here + */ + dev_hold(queue->dev); + kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) goto err; - dev_hold(queue->dev); - if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) @@ -1459,14 +1462,17 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index) struct kobject *kobj = &queue->kobj; int error = 0; + /* Kobject_put later will trigger netdev_queue_release call + * which decreases dev refcount: Take that reference here + */ + dev_hold(queue->dev); + kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, "tx-%u", index); if (error) goto err; - dev_hold(queue->dev); - #ifdef CONFIG_BQL error = sysfs_create_group(kobj, &dql_group); if (error) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 0b5ccb7c9bc8..02916f43bf63 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1250,7 +1250,9 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, vf_spoofchk.vf = vf_linkstate.vf = vf_rss_query_en.vf = - vf_trust.vf = ivi.vf; + vf_trust.vf = + node_guid.vf = + port_guid.vf = ivi.vf; memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); memcpy(vf_broadcast.broadcast, dev->broadcast, dev->addr_len); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 867e61df00db..973a71f4bc89 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5484,7 +5484,7 @@ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, * Returns 0 on success, -errno otherwise. */ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, - int mac_len) + int mac_len, bool ethernet) { struct mpls_shim_hdr *lse; int err; @@ -5515,7 +5515,7 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, lse->label_stack_entry = mpls_lse; skb_postpush_rcsum(skb, lse, MPLS_HLEN); - if (skb->dev && skb->dev->type == ARPHRD_ETHER) + if (ethernet) skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto); skb->protocol = mpls_proto; @@ -5529,12 +5529,14 @@ EXPORT_SYMBOL_GPL(skb_mpls_push); * @skb: buffer * @next_proto: ethertype of header after popped MPLS header * @mac_len: length of the MAC header + * @ethernet: flag to indicate if ethernet header is present in packet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ -int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len) +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, + bool ethernet) { int err; @@ -5553,7 +5555,7 @@ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len) skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); - if (skb->dev && skb->dev->type == ARPHRD_ETHER) { + if (ethernet) { struct ethhdr *hdr; /* use mpls_hdr() to get ethertype to account for VLANs. */ diff --git a/net/core/sock.c b/net/core/sock.c index 043db3ce023e..8459ad579f73 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2916,7 +2916,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_max_pacing_rate = ~0UL; sk->sk_pacing_rate = ~0UL; - sk->sk_pacing_shift = 10; + WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; sk_rx_queue_clear(sk); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index eb29e5adc84d..9f9e00ba3ad7 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -288,6 +288,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write, return ret; } +# ifdef CONFIG_HAVE_EBPF_JIT static int proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -298,6 +299,7 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } +# endif /* CONFIG_HAVE_EBPF_JIT */ static int proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write, diff --git a/net/core/xdp.c b/net/core/xdp.c index e334fad0a6b8..8310714c47fd 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -36,7 +36,7 @@ static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed) const u32 *k = data; const u32 key = *k; - BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_mem_allocator, mem.id) + BUILD_BUG_ON(sizeof_field(struct xdp_mem_allocator, mem.id) != sizeof(u32)); /* Use cyclic increasing ID as direct hash key */ @@ -56,7 +56,7 @@ static const struct rhashtable_params mem_id_rht_params = { .nelem_hint = 64, .head_offset = offsetof(struct xdp_mem_allocator, node), .key_offset = offsetof(struct xdp_mem_allocator, mem.id), - .key_len = FIELD_SIZEOF(struct xdp_mem_allocator, mem.id), + .key_len = sizeof_field(struct xdp_mem_allocator, mem.id), .max_size = MEM_ID_MAX, .min_size = 8, .automatic_shrinking = true, @@ -80,12 +80,8 @@ static void mem_xa_remove(struct xdp_mem_allocator *xa) { trace_mem_disconnect(xa); - mutex_lock(&mem_id_lock); - if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); - - mutex_unlock(&mem_id_lock); } static void mem_allocator_disconnect(void *allocator) @@ -93,6 +89,8 @@ static void mem_allocator_disconnect(void *allocator) struct xdp_mem_allocator *xa; struct rhashtable_iter iter; + mutex_lock(&mem_id_lock); + rhashtable_walk_enter(mem_id_ht, &iter); do { rhashtable_walk_start(&iter); @@ -106,6 +104,8 @@ static void mem_allocator_disconnect(void *allocator) } while (xa == ERR_PTR(-EAGAIN)); rhashtable_walk_exit(&iter); + + mutex_unlock(&mem_id_lock); } static void mem_id_disconnect(int id) diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 25aab672fc99..1e5e08cc0bfc 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -210,7 +210,7 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; @@ -282,7 +282,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6)); /* sk = NULL, but it is safe for now. RST socket required. */ - dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); + dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(skb, dst); ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0, 0); @@ -912,7 +912,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(&fl6, opt, &final); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index a52e8ba1ced0..4af8a98fe784 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -1132,7 +1132,7 @@ static int __init dccp_init(void) int rc; BUILD_BUG_ON(sizeof(struct dccp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); rc = percpu_counter_init(&dccp_orphan_count, 0, GFP_KERNEL); if (rc) goto out_fail; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 9ef2caa13f27..c66abbed4daf 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -124,7 +124,8 @@ static struct dsa_port *dsa_tree_find_port_by_node(struct dsa_switch_tree *dst, return NULL; } -struct dsa_link *dsa_link_touch(struct dsa_port *dp, struct dsa_port *link_dp) +static struct dsa_link *dsa_link_touch(struct dsa_port *dp, + struct dsa_port *link_dp) { struct dsa_switch *ds = dp->ds; struct dsa_switch_tree *dst; diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 73605bcbb385..90d055c4df9e 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -84,8 +84,6 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, * (eg, 0x00=port1, 0x02=port3, 0x06=port7) */ -#define KSZ8795_INGRESS_TAG_LEN 1 - #define KSZ8795_TAIL_TAG_OVERRIDE BIT(6) #define KSZ8795_TAIL_TAG_LOOKUP BIT(7) @@ -96,12 +94,12 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) u8 *tag; u8 *addr; - nskb = ksz_common_xmit(skb, dev, KSZ8795_INGRESS_TAG_LEN); + nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN); if (!nskb) return NULL; /* Tag encoding */ - tag = skb_put(nskb, KSZ8795_INGRESS_TAG_LEN); + tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); addr = skb_mac_header(nskb); *tag = 1 << dp->index; @@ -124,7 +122,7 @@ static const struct dsa_device_ops ksz8795_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ8795, .xmit = ksz8795_xmit, .rcv = ksz8795_rcv, - .overhead = KSZ8795_INGRESS_TAG_LEN, + .overhead = KSZ_INGRESS_TAG_LEN, }; DSA_TAG_DRIVER(ksz8795_netdev_ops); diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index f509b495451a..b01e1bae4ddc 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -227,8 +227,13 @@ static int hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct hsr_port *master; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); - skb->dev = master->dev; - hsr_forward_skb(skb, master); + if (master) { + skb->dev = master->dev; + hsr_forward_skb(skb, master); + } else { + atomic_long_inc(&dev->tx_dropped); + dev_kfree_skb_any(skb); + } return NETDEV_TX_OK; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a4b5bd4d2c89..e4632bd2026d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1496,11 +1496,6 @@ skip: } } -static bool inetdev_valid_mtu(unsigned int mtu) -{ - return mtu >= IPV4_MIN_MTU; -} - static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 44bfeecac33e..5fd6e8ed02b5 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -127,7 +127,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (!pskb_may_pull(skb, nhs + hdr_len + sizeof(*ershdr))) return -EINVAL; - ershdr = (struct erspan_base_hdr *)options; + ershdr = (struct erspan_base_hdr *)(skb->data + nhs + hdr_len); tpi->key = cpu_to_be32(get_session_id(ershdr)); } diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index af154977904c..f11e997e517b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -911,11 +911,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, for (i = s_i; i < INET_LHTABLE_SIZE; i++) { struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; num = 0; ilb = &hashinfo->listening_hash[i]; spin_lock(&ilb->lock); - sk_for_each(sk, &ilb->head) { + sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 83fb00153018..2bbaaf0c7176 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -516,10 +516,11 @@ static int inet_reuseport_add_sock(struct sock *sk, struct inet_listen_hashbucket *ilb) { struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash; + const struct hlist_nulls_node *node; struct sock *sk2; kuid_t uid = sock_i_uid(sk); - sk_for_each_rcu(sk2, &ilb->head) { + sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) { if (sk2 != sk && sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && @@ -555,9 +556,9 @@ int __inet_hash(struct sock *sk, struct sock *osk) } if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) - hlist_add_tail_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head); else - hlist_add_head_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_rcu(sk, &ilb->nulls_head); inet_hash2(hashinfo, sk); ilb->count++; sock_set_flag(sk, SOCK_RCU_FREE); @@ -606,11 +607,9 @@ void inet_unhash(struct sock *sk) reuseport_detach_sock(sk); if (ilb) { inet_unhash2(hashinfo, sk); - __sk_del_node_init(sk); - ilb->count--; - } else { - __sk_nulls_del_node_init_rcu(sk); + ilb->count--; } + __sk_nulls_del_node_init_rcu(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); unlock: spin_unlock_bh(lock); @@ -750,7 +749,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h) for (i = 0; i < INET_LHTABLE_SIZE; i++) { spin_lock_init(&h->listening_hash[i].lock); - INIT_HLIST_HEAD(&h->listening_hash[i].head); + INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head, + i + LISTENING_NULLS_BASE); h->listening_hash[i].count = 0; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 572b6307a2df..8274f98c511c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1464,8 +1464,8 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, - [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, - [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, + [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_TOS] = { .type = NLA_U8 }, [IFLA_GRE_PMTUDISC] = { .type = NLA_U8 }, diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9d83cb320dcb..14db1e0b8a6e 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1258,15 +1258,18 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->addr = ipc->addr; } - /* - * We steal reference to this route, caller should not release it - */ - *rtp = NULL; cork->fragsize = ip_sk_use_pmtu(sk) ? - dst_mtu(&rt->dst) : rt->dst.dev->mtu; + dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + + if (!inetdev_valid_mtu(cork->fragsize)) + return -ENETUNREACH; cork->gso_size = ipc->gso_size; + cork->dst = &rt->dst; + /* We stole this route, caller should not release it. */ + *rtp = NULL; + cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index cfb025606793..9b153c7fcbb4 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -580,8 +580,8 @@ static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = { [IFLA_VTI_LINK] = { .type = NLA_U32 }, [IFLA_VTI_IKEY] = { .type = NLA_U32 }, [IFLA_VTI_OKEY] = { .type = NLA_U32 }, - [IFLA_VTI_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, - [IFLA_VTI_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_VTI_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, + [IFLA_VTI_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VTI_FWMARK] = { .type = NLA_U32 }, }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8a39ee794891..d885ba868822 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1087,8 +1087,7 @@ do_error: goto out; out_err: /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } @@ -1419,8 +1418,7 @@ out_err: sock_zerocopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } @@ -3949,7 +3947,7 @@ void __init tcp_init(void) BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE); BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 32772d6ded4e..a6545ef0d27b 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -306,7 +306,8 @@ static u32 bbr_tso_segs_goal(struct sock *sk) /* Sort of tcp_tso_autosize() but ignoring * driver provided sk_gso_max_size. */ - bytes = min_t(unsigned long, sk->sk_pacing_rate >> sk->sk_pacing_shift, + bytes = min_t(unsigned long, + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), GSO_MAX_SIZE - 1 - MAX_TCP_HEADER); segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk)); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 92282f98dc82..1c7326e04f9b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2147,13 +2147,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur) struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; struct sock *sk = cur; if (!sk) { get_head: ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock(&ilb->lock); - sk = sk_head(&ilb->head); + sk = sk_nulls_head(&ilb->nulls_head); st->offset = 0; goto get_sk; } @@ -2161,9 +2162,9 @@ get_head: ++st->num; ++st->offset; - sk = sk_next(sk); + sk = sk_nulls_next(sk); get_sk: - sk_for_each_from(sk) { + sk_nulls_for_each_from(sk, node) { if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_family == afinfo->family) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index be6d22b8190f..1f7735ca8f22 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -755,8 +755,9 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb min_t(unsigned int, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); - size += TCPOLEN_SACK_BASE_ALIGNED + - opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; + if (likely(opts->num_sack_blocks)) + size += TCPOLEN_SACK_BASE_ALIGNED + + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } return size; @@ -1724,7 +1725,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, u32 bytes, segs; bytes = min_t(unsigned long, - sk->sk_pacing_rate >> sk->sk_pacing_shift, + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), sk->sk_gso_max_size - 1 - MAX_TCP_HEADER); /* Goal is to send at least one packet per ms, @@ -2259,7 +2260,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit = max_t(unsigned long, 2 * skb->truesize, - sk->sk_pacing_rate >> sk->sk_pacing_shift); + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift)); if (sk->sk_pacing_status == SK_PACING_NONE) limit = min_t(unsigned long, limit, sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes); @@ -2437,6 +2438,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (tcp_small_queue_check(sk, skb, 0)) break; + /* Argh, we hit an empty skb(), presumably a thread + * is sleeping in sendmsg()/sk_stream_wait_memory(). + * We do not want to send a pure-ack packet and have + * a strange looking rtx queue with empty packet(s). + */ + if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) + break; + if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; @@ -3120,7 +3129,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size) */ void tcp_send_fin(struct sock *sk) { - struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); + struct sk_buff *skb, *tskb, *tail = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); /* Optimization, tack on the FIN if we have one skb in write queue and @@ -3128,6 +3137,7 @@ void tcp_send_fin(struct sock *sk) * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ + tskb = tail; if (!tskb && tcp_under_memory_pressure(sk)) tskb = skb_rb_last(&sk->tcp_rtx_queue); @@ -3135,7 +3145,7 @@ void tcp_send_fin(struct sock *sk) TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; - if (tcp_write_queue_empty(sk)) { + if (!tail) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index dd5a6317a801..1097b438befe 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -434,6 +434,7 @@ void tcp_retransmit_timer(struct sock *sk) struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock *req; + struct sk_buff *skb; req = rcu_dereference_protected(tp->fastopen_rsk, lockdep_sock_is_held(sk)); @@ -446,7 +447,12 @@ void tcp_retransmit_timer(struct sock *sk) */ return; } - if (!tp->packets_out || WARN_ON_ONCE(tcp_rtx_queue_empty(sk))) + + if (!tp->packets_out) + return; + + skb = tcp_rtx_queue_head(sk); + if (WARN_ON_ONCE(!skb)) return; tp->tlp_high_seq = 0; @@ -480,7 +486,7 @@ void tcp_retransmit_timer(struct sock *sk) goto out; } tcp_enter_loss(sk); - tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1); + tcp_retransmit_skb(sk, skb, 1); __sk_dst_reset(sk); goto out_reset_timer; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 98d82305d6de..39d861d00377 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5231,16 +5231,16 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb, return -EINVAL; } + if (!netlink_strict_get_check(skb)) + return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, + ifa_ipv6_policy, extack); + ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request"); return -EINVAL; } - if (!netlink_strict_get_check(skb)) - return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, - ifa_ipv6_policy, extack); - err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err) diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 2fc079284ca4..ea00ce3d4117 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -129,11 +129,12 @@ int inet6addr_validator_notifier_call_chain(unsigned long val, void *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) +static struct dst_entry *eafnosupport_ipv6_dst_lookup_flow(struct net *net, + const struct sock *sk, + struct flowi6 *fl6, + const struct in6_addr *final_dst) { - return -EAFNOSUPPORT; + return ERR_PTR(-EAFNOSUPPORT); } static int eafnosupport_ipv6_route_input(struct sk_buff *skb) @@ -190,7 +191,7 @@ static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt) } const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { - .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup, + .ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow, .ipv6_route_input = eafnosupport_ipv6_route_input, .fib6_get_table = eafnosupport_fib6_get_table, .fib6_table_lookup = eafnosupport_fib6_table_lookup, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 60e2ff91a5b3..d727c3b41495 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -765,7 +765,7 @@ int inet6_sk_rebuild_header(struct sock *sk) &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { sk->sk_route_caps = 0; sk->sk_err_soft = -PTR_ERR(dst); @@ -946,7 +946,7 @@ static int ipv6_route_input(struct sk_buff *skb) static const struct ipv6_stub ipv6_stub_impl = { .ipv6_sock_mc_join = ipv6_sock_mc_join, .ipv6_sock_mc_drop = ipv6_sock_mc_drop, - .ipv6_dst_lookup = ip6_dst_lookup, + .ipv6_dst_lookup_flow = ip6_dst_lookup_flow, .ipv6_route_input = ipv6_route_input, .fib6_get_table = fib6_get_table, .fib6_table_lookup = fib6_table_lookup, diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 96f939248d2f..390bedde21a5 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -85,7 +85,7 @@ int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr) final_p = fl6_update_dst(&fl6, opt, &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 0a0945a5b30d..fe9cb8d1adca 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -48,7 +48,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk, fl6->flowi6_uid = sk->sk_uid; security_req_classify_flow(req, flowi6_to_flowi(fl6)); - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (IS_ERR(dst)) return NULL; @@ -103,7 +103,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk, dst = __inet6_csk_dst_check(sk, np->dst_cookie); if (!dst) { - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (!IS_ERR(dst)) ip6_dst_store(sk, dst, NULL, NULL); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 923034c52ce4..9d0965252ddf 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -2170,8 +2170,8 @@ static const struct nla_policy ip6gre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, - [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct ipv6hdr, saddr) }, - [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct ipv6hdr, daddr) }, + [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct ipv6hdr, saddr) }, + [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct ipv6hdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_ENCAP_LIMIT] = { .type = NLA_U8 }, [IFLA_GRE_FLOWINFO] = { .type = NLA_U32 }, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 945508a7cb0f..087304427bbb 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1144,19 +1144,19 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup); * It returns a valid dst pointer on success, or a pointer encoded * error code. */ -struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst) { struct dst_entry *dst = NULL; int err; - err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6); + err = ip6_dst_lookup_tail(net, sk, &dst, fl6); if (err) return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst; - return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(net, dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); @@ -1188,7 +1188,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (dst) return dst; - dst = ip6_dst_lookup_flow(sk, fl6, final_dst); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_dst); if (connected && !IS_ERR(dst)) ip6_sk_dst_store_flow(sk, dst_clone(dst), fl6); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a77f6b7d3a7c..dfe5e603ffe1 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -925,7 +925,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 16632e02e9b0..30915f6f31e3 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -235,7 +235,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) fl6.flowi6_uid = sk->sk_uid; security_req_classify_flow(req, flowi6_to_flowi(&fl6)); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) goto out_free; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 81f51335e326..df5fd9109696 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -275,7 +275,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; @@ -906,7 +906,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 * Underlying function will use this to retrieve the network * namespace */ - dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); + dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index ebb62a4ebe30..c4bdcbc84b07 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -50,7 +50,7 @@ static struct iucv_interface *pr_iucv; static const u8 iprm_shutdown[8] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}; -#define TRGCLS_SIZE FIELD_SIZEOF(struct iucv_message, class) +#define TRGCLS_SIZE sizeof_field(struct iucv_message, class) #define __iucv_sock_wait(sk, condition, timeo, ret) \ do { \ diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 802f19aba7e3..d148766f40d1 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -615,7 +615,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c index 204a8351efff..c29170e767a8 100644 --- a/net/llc/llc_station.c +++ b/net/llc/llc_station.c @@ -32,7 +32,7 @@ static int llc_stat_ev_rx_null_dsap_xid_c(struct sk_buff *skb) return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_XID && - !pdu->dsap ? 0 : 1; /* NULL DSAP value */ + !pdu->dsap; /* NULL DSAP value */ } static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) @@ -42,7 +42,7 @@ static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_TEST && - !pdu->dsap ? 0 : 1; /* NULL DSAP */ + !pdu->dsap; /* NULL DSAP */ } static int llc_station_ac_send_xid_r(struct sk_buff *skb) diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index 63cb0028b02d..9fc2968856c0 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -442,7 +442,7 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, return 0; sband = hw->wiphy->bands[status->band]; - if (!sband || status->rate_idx > sband->n_bitrates) + if (!sband || status->rate_idx >= sband->n_bitrates) return 0; rate = &sband->bitrates[status->rate_idx]; diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index b3c9001d1f43..c80b1e163ea4 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -201,8 +201,6 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; u64 rx_airtime = 0, tx_airtime = 0; s64 deficit[IEEE80211_NUM_ACS]; - u32 q_depth[IEEE80211_NUM_ACS]; - u32 q_limit_l[IEEE80211_NUM_ACS], q_limit_h[IEEE80211_NUM_ACS]; ssize_t rv; int ac; @@ -214,6 +212,56 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, rx_airtime += sta->airtime[ac].rx_airtime; tx_airtime += sta->airtime[ac].tx_airtime; deficit[ac] = sta->airtime[ac].deficit; + spin_unlock_bh(&local->active_txq_lock[ac]); + } + + p += scnprintf(p, bufsz + buf - p, + "RX: %llu us\nTX: %llu us\nWeight: %u\n" + "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n", + rx_airtime, tx_airtime, sta->airtime_weight, + deficit[0], deficit[1], deficit[2], deficit[3]); + + rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + kfree(buf); + return rv; +} + +static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->sdata->local; + int ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->active_txq_lock[ac]); + sta->airtime[ac].rx_airtime = 0; + sta->airtime[ac].tx_airtime = 0; + sta->airtime[ac].deficit = sta->airtime_weight; + spin_unlock_bh(&local->active_txq_lock[ac]); + } + + return count; +} +STA_OPS_RW(airtime); + +static ssize_t sta_aql_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->sdata->local; + size_t bufsz = 400; + char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; + u32 q_depth[IEEE80211_NUM_ACS]; + u32 q_limit_l[IEEE80211_NUM_ACS], q_limit_h[IEEE80211_NUM_ACS]; + ssize_t rv; + int ac; + + if (!buf) + return -ENOMEM; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->active_txq_lock[ac]); q_limit_l[ac] = sta->airtime[ac].aql_limit_low; q_limit_h[ac] = sta->airtime[ac].aql_limit_high; spin_unlock_bh(&local->active_txq_lock[ac]); @@ -221,12 +269,8 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, } p += scnprintf(p, bufsz + buf - p, - "RX: %llu us\nTX: %llu us\nWeight: %u\n" - "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n" "Q depth: VO: %u us VI: %u us BE: %u us BK: %u us\n" "Q limit[low/high]: VO: %u/%u VI: %u/%u BE: %u/%u BK: %u/%u\n", - rx_airtime, tx_airtime, sta->airtime_weight, - deficit[0], deficit[1], deficit[2], deficit[3], q_depth[0], q_depth[1], q_depth[2], q_depth[3], q_limit_l[0], q_limit_h[0], q_limit_l[1], q_limit_h[1], q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]), @@ -236,11 +280,10 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, return rv; } -static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, +static ssize_t sta_aql_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; - struct ieee80211_local *local = sta->sdata->local; u32 ac, q_limit_l, q_limit_h; char _buf[100] = {}, *buf = _buf; @@ -251,7 +294,7 @@ static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, return -EFAULT; buf[sizeof(_buf) - 1] = '\0'; - if (sscanf(buf, "queue limit %u %u %u", &ac, &q_limit_l, &q_limit_h) + if (sscanf(buf, "limit %u %u %u", &ac, &q_limit_l, &q_limit_h) != 3) return -EINVAL; @@ -261,17 +304,10 @@ static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, sta->airtime[ac].aql_limit_low = q_limit_l; sta->airtime[ac].aql_limit_high = q_limit_h; - for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - spin_lock_bh(&local->active_txq_lock[ac]); - sta->airtime[ac].rx_airtime = 0; - sta->airtime[ac].tx_airtime = 0; - sta->airtime[ac].deficit = sta->airtime_weight; - spin_unlock_bh(&local->active_txq_lock[ac]); - } - return count; } -STA_OPS_RW(airtime); +STA_OPS_RW(aql); + static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) @@ -996,6 +1032,10 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) DEBUGFS_ADD(airtime); + if (wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AQL)) + DEBUGFS_ADD(aql); + debugfs_create_xul("driver_buffered_tids", 0400, sta->debugfs_dir, &sta->driver_buffered_tids); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 6cca0853f183..4c2b5ba3ac09 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -672,9 +672,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, IEEE80211_DEFAULT_AQL_TXQ_LIMIT_H; } - local->airtime_flags = AIRTIME_USE_TX | - AIRTIME_USE_RX | - AIRTIME_USE_AQL; + local->airtime_flags = AIRTIME_USE_TX | AIRTIME_USE_RX; local->aql_threshold = IEEE80211_AQL_THRESHOLD; atomic_set(&local->aql_total_pending_airtime, 0); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 8eafd81e97b4..0f5f40678885 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1916,6 +1916,9 @@ void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local, { int tx_pending; + if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) + return; + if (!tx_completed) { if (sta) atomic_add(tx_airtime, diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index ad5d8a4ae56d..c00e28585f9d 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -127,7 +127,6 @@ enum ieee80211_agg_stop_reason { /* Debugfs flags to enable/disable use of RX/TX airtime in scheduler */ #define AIRTIME_USE_TX BIT(0) #define AIRTIME_USE_RX BIT(1) -#define AIRTIME_USE_AQL BIT(2) struct airtime_info { u64 rx_airtime; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index b696b9136f4c..a8a7306a1f56 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2256,6 +2256,15 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, payload[7]); } + /* + * Initialize skb->priority for QoS frames. This is put in the TID field + * of the frame before passing it to the driver. + */ + if (ieee80211_is_data_qos(hdr->frame_control)) { + u8 *p = ieee80211_get_qos_ctl(hdr); + skb->priority = *p & IEEE80211_QOS_CTL_TAG1D_MASK; + } + memset(info, 0, sizeof(*info)); info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS | @@ -3668,7 +3677,7 @@ begin: IEEE80211_SKB_CB(skb)->control.vif = vif; - if (local->airtime_flags & AIRTIME_USE_AQL) { + if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { u32 airtime; airtime = ieee80211_calc_expected_tx_airtime(hw, vif, txq->sta, @@ -3790,7 +3799,7 @@ bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct sta_info *sta; struct ieee80211_local *local = hw_to_local(hw); - if (!(local->airtime_flags & AIRTIME_USE_AQL)) + if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) return true; if (!txq->sta) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index c312741df2ce..4701edffb1f7 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -617,16 +617,15 @@ static struct net_device *inet6_fib_lookup_dev(struct net *net, struct net_device *dev; struct dst_entry *dst; struct flowi6 fl6; - int err; if (!ipv6_stub) return ERR_PTR(-EAFNOSUPPORT); memset(&fl6, 0, sizeof(fl6)); memcpy(&fl6.daddr, addr, sizeof(struct in6_addr)); - err = ipv6_stub->ipv6_dst_lookup(net, NULL, &dst, &fl6); - if (err) - return ERR_PTR(err); + dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL); + if (IS_ERR(dst)) + return ERR_CAST(dst); dev = dst->dev; dev_hold(dev); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0af1898af2b8..f475fec84536 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -895,9 +895,10 @@ static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo, } /* Resolve race on insertion if this protocol allows this. */ -static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - struct nf_conntrack_tuple_hash *h) +static __cold noinline int +nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + struct nf_conntrack_tuple_hash *h) { /* This is the conntrack entry already in hashes that won race. */ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d8d33ef52ce0..6a1c8f1f6171 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -3626,6 +3626,9 @@ static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list) list_for_each_entry(net, net_exit_list, exit_list) ctnetlink_net_exit(net); + + /* wait for other cpus until they are done with ctnl_notifiers */ + synchronize_rcu(); } static struct pernet_operations ctnetlink_net_ops = { diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index c54c9a6cc981..de7a0d1e15c8 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -28,6 +28,7 @@ struct nf_flow_key { struct flow_dissector_key_basic basic; union { struct flow_dissector_key_ipv4_addrs ipv4; + struct flow_dissector_key_ipv6_addrs ipv6; }; struct flow_dissector_key_tcp tcp; struct flow_dissector_key_ports tp; @@ -57,6 +58,7 @@ static int nf_flow_rule_match(struct nf_flow_match *match, NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_CONTROL, control); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_BASIC, basic); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_TCP, tcp); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_PORTS, tp); @@ -69,9 +71,18 @@ static int nf_flow_rule_match(struct nf_flow_match *match, key->ipv4.dst = tuple->dst_v4.s_addr; mask->ipv4.dst = 0xffffffff; break; + case AF_INET6: + key->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + key->basic.n_proto = htons(ETH_P_IPV6); + key->ipv6.src = tuple->src_v6; + memset(&mask->ipv6.src, 0xff, sizeof(mask->ipv6.src)); + key->ipv6.dst = tuple->dst_v6; + memset(&mask->ipv6.dst, 0xff, sizeof(mask->ipv6.dst)); + break; default: return -EOPNOTSUPP; } + match->dissector.used_keys |= BIT(key->control.addr_type); mask->basic.n_proto = 0xffff; switch (tuple->l4proto) { @@ -96,14 +107,13 @@ static int nf_flow_rule_match(struct nf_flow_match *match, match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | BIT(FLOW_DISSECTOR_KEY_PORTS); return 0; } static void flow_offload_mangle(struct flow_action_entry *entry, - enum flow_action_mangle_base htype, - u32 offset, u8 *value, u8 *mask) + enum flow_action_mangle_base htype, u32 offset, + const __be32 *value, const __be32 *mask) { entry->id = FLOW_ACTION_MANGLE; entry->mangle.htype = htype; @@ -140,12 +150,12 @@ static int flow_offload_eth_src(struct net *net, memcpy(&val16, dev->dev_addr, 2); val = val16 << 16; flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, - (u8 *)&val, (u8 *)&mask); + &val, &mask); mask = ~0xffffffff; memcpy(&val, dev->dev_addr + 2, 4); flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 8, - (u8 *)&val, (u8 *)&mask); + &val, &mask); dev_put(dev); return 0; @@ -170,13 +180,13 @@ static int flow_offload_eth_dst(struct net *net, mask = ~0xffffffff; memcpy(&val, n->ha, 4); flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 0, - (u8 *)&val, (u8 *)&mask); + &val, &mask); mask = ~0x0000ffff; memcpy(&val16, n->ha + 4, 2); val = val16; flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, - (u8 *)&val, (u8 *)&mask); + &val, &mask); neigh_release(n); return 0; @@ -206,7 +216,7 @@ static void flow_offload_ipv4_snat(struct net *net, } flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset, - (u8 *)&addr, (u8 *)&mask); + &addr, &mask); } static void flow_offload_ipv4_dnat(struct net *net, @@ -233,12 +243,12 @@ static void flow_offload_ipv4_dnat(struct net *net, } flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset, - (u8 *)&addr, (u8 *)&mask); + &addr, &mask); } static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule, unsigned int offset, - u8 *addr, u8 *mask) + const __be32 *addr, const __be32 *mask) { struct flow_action_entry *entry; int i; @@ -246,8 +256,7 @@ static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule, for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i += sizeof(u32)) { entry = flow_action_entry_next(flow_rule); flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP6, - offset + i, - &addr[i], mask); + offset + i, &addr[i], mask); } } @@ -257,23 +266,23 @@ static void flow_offload_ipv6_snat(struct net *net, struct nf_flow_rule *flow_rule) { u32 mask = ~htonl(0xffffffff); - const u8 *addr; + const __be32 *addr; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6.s6_addr32; offset = offsetof(struct ipv6hdr, saddr); break; case FLOW_OFFLOAD_DIR_REPLY: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6.s6_addr32; offset = offsetof(struct ipv6hdr, daddr); break; default: return; } - flow_offload_ipv6_mangle(flow_rule, offset, (u8 *)addr, (u8 *)&mask); + flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask); } static void flow_offload_ipv6_dnat(struct net *net, @@ -282,23 +291,23 @@ static void flow_offload_ipv6_dnat(struct net *net, struct nf_flow_rule *flow_rule) { u32 mask = ~htonl(0xffffffff); - const u8 *addr; + const __be32 *addr; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6.s6_addr32; offset = offsetof(struct ipv6hdr, daddr); break; case FLOW_OFFLOAD_DIR_REPLY: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6.s6_addr32; offset = offsetof(struct ipv6hdr, saddr); break; default: return; } - flow_offload_ipv6_mangle(flow_rule, offset, (u8 *)addr, (u8 *)&mask); + flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask); } static int flow_offload_l4proto(const struct flow_offload *flow) @@ -326,25 +335,24 @@ static void flow_offload_port_snat(struct net *net, struct nf_flow_rule *flow_rule) { struct flow_action_entry *entry = flow_action_entry_next(flow_rule); - u32 mask = ~htonl(0xffff0000); - __be16 port; + u32 mask = ~htonl(0xffff0000), port; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port); offset = 0; /* offsetof(struct tcphdr, source); */ break; case FLOW_OFFLOAD_DIR_REPLY: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port); offset = 0; /* offsetof(struct tcphdr, dest); */ break; default: - break; + return; } - + port = htonl(port << 16); flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, - (u8 *)&port, (u8 *)&mask); + &port, &mask); } static void flow_offload_port_dnat(struct net *net, @@ -353,25 +361,24 @@ static void flow_offload_port_dnat(struct net *net, struct nf_flow_rule *flow_rule) { struct flow_action_entry *entry = flow_action_entry_next(flow_rule); - u32 mask = ~htonl(0xffff); - __be16 port; + u32 mask = ~htonl(0xffff), port; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port); offset = 0; /* offsetof(struct tcphdr, source); */ break; case FLOW_OFFLOAD_DIR_REPLY: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port); offset = 0; /* offsetof(struct tcphdr, dest); */ break; default: - break; + return; } - + port = htonl(port); flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, - (u8 *)&port, (u8 *)&mask); + &port, &mask); } static void flow_offload_ipv4_checksum(struct net *net, @@ -574,7 +581,7 @@ static int flow_offload_tuple_add(struct flow_offload_work *offload, cls_flow.rule = flow_rule->rule; list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) { - err = block_cb->cb(TC_SETUP_FT, &cls_flow, + err = block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); if (err < 0) continue; @@ -599,7 +606,7 @@ static void flow_offload_tuple_del(struct flow_offload_work *offload, &offload->flow->tuplehash[dir].tuple, &extack); list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) - block_cb->cb(TC_SETUP_FT, &cls_flow, block_cb->cb_priv); + block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); offload->flow->flags |= FLOW_OFFLOAD_HW_DEAD; } @@ -656,7 +663,7 @@ static void flow_offload_tuple_stats(struct flow_offload_work *offload, &offload->flow->tuplehash[dir].tuple, &extack); list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) - block_cb->cb(TC_SETUP_FT, &cls_flow, block_cb->cb_priv); + block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); memcpy(stats, &cls_flow.stats, sizeof(*stats)); } @@ -822,7 +829,7 @@ int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, bo.extack = &extack; INIT_LIST_HEAD(&bo.cb_list); - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, &bo); if (err < 0) return err; diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index a2b58de82600..f8f52ff99cfb 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -189,7 +189,7 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, goto err; } - if (!skb_dst_force(skb) && state->hook != NF_INET_PRE_ROUTING) { + if (skb_dst(skb) && !skb_dst_force(skb)) { status = -ENETDOWN; goto err; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 062b73a83af0..273f3838318b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4519,8 +4519,10 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; err = -EINVAL; - if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) + if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) { + nft_data_release(&elem.key.val, desc.type); return err; + } priv = set->ops->get(ctx->net, set, &elem, flags); if (IS_ERR(priv)) @@ -4756,14 +4758,20 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_DATA] == NULL && !(flags & NFT_SET_ELEM_INTERVAL_END)) return -EINVAL; - if (nla[NFTA_SET_ELEM_DATA] != NULL && - flags & NFT_SET_ELEM_INTERVAL_END) - return -EINVAL; } else { if (nla[NFTA_SET_ELEM_DATA] != NULL) return -EINVAL; } + if ((flags & NFT_SET_ELEM_INTERVAL_END) && + (nla[NFTA_SET_ELEM_DATA] || + nla[NFTA_SET_ELEM_OBJREF] || + nla[NFTA_SET_ELEM_TIMEOUT] || + nla[NFTA_SET_ELEM_EXPIRATION] || + nla[NFTA_SET_ELEM_USERDATA] || + nla[NFTA_SET_ELEM_EXPR])) + return -EINVAL; + timeout = 0; if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) @@ -5476,7 +5484,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - type = nft_obj_type_get(net, objtype); + type = __nft_obj_type_get(objtype); nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); return nf_tables_updobj(&ctx, type, nla[NFTA_OBJ_DATA], obj); @@ -7595,7 +7603,7 @@ int nft_validate_register_load(enum nft_registers reg, unsigned int len) return -EINVAL; if (len == 0) return -EINVAL; - if (reg * NFT_REG32_SIZE + len > FIELD_SIZEOF(struct nft_regs, data)) + if (reg * NFT_REG32_SIZE + len > sizeof_field(struct nft_regs, data)) return -ERANGE; return 0; @@ -7643,7 +7651,7 @@ int nft_validate_register_store(const struct nft_ctx *ctx, if (len == 0) return -EINVAL; if (reg * NFT_REG32_SIZE + len > - FIELD_SIZEOF(struct nft_regs, data)) + sizeof_field(struct nft_regs, data)) return -ERANGE; if (data != NULL && type != NFT_DATA_VALUE) diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 68f17a6921d8..a9ea29afb09f 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -44,6 +44,9 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net, expr = nft_expr_next(expr); } + if (num_actions == 0) + return ERR_PTR(-EOPNOTSUPP); + flow = nft_flow_rule_alloc(num_actions); if (!flow) return ERR_PTR(-ENOMEM); @@ -577,6 +580,9 @@ static int nft_offload_netdev_event(struct notifier_block *this, struct net *net = dev_net(dev); struct nft_chain *chain; + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + mutex_lock(&net->nft.commit_mutex); chain = __nft_offload_get_chain(dev); if (chain) @@ -588,7 +594,7 @@ static int nft_offload_netdev_event(struct notifier_block *this, return NOTIFY_DONE; } -static struct flow_indr_block_ing_entry block_ing_entry = { +static struct flow_indr_block_entry block_ing_entry = { .cb = nft_indr_block_cb, .list = LIST_HEAD_INIT(block_ing_entry.list), }; @@ -605,13 +611,13 @@ int nft_offload_init(void) if (err < 0) return err; - flow_indr_add_block_ing_cb(&block_ing_entry); + flow_indr_add_block_cb(&block_ing_entry); return 0; } void nft_offload_exit(void) { - flow_indr_del_block_ing_cb(&block_ing_entry); + flow_indr_del_block_cb(&block_ing_entry); unregister_netdevice_notifier(&nft_offload_netdev_notifier); } diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 7525063c25f5..de3a9596b7f1 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -236,7 +236,7 @@ nfnl_cthelper_create(const struct nlattr * const tb[], nla_strlcpy(helper->name, tb[NFCTH_NAME], NF_CT_HELPER_NAME_LEN); size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN])); - if (size > FIELD_SIZEOF(struct nf_conn_help, data)) { + if (size > sizeof_field(struct nf_conn_help, data)) { ret = -ENOMEM; goto err2; } diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 02afa752dd2e..10e9d50e4e19 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -80,7 +80,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, tb[NFTA_BITWISE_MASK]); if (err < 0) return err; - if (d1.len != priv->len) { + if (d1.type != NFT_DATA_VALUE || d1.len != priv->len) { err = -EINVAL; goto err1; } @@ -89,7 +89,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, tb[NFTA_BITWISE_XOR]); if (err < 0) goto err1; - if (d2.len != priv->len) { + if (d2.type != NFT_DATA_VALUE || d2.len != priv->len) { err = -EINVAL; goto err2; } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index b8092069f868..8a28c127effc 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -81,6 +81,12 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (err < 0) return err; + if (desc.type != NFT_DATA_VALUE) { + err = -EINVAL; + nft_data_release(&priv->data, desc.type); + return err; + } + priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]); err = nft_validate_register_load(priv->sreg, desc.len); if (err < 0) diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 46ca8bcca1bd..faea72c2df32 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -440,12 +440,12 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, switch (ctx->family) { case NFPROTO_IPV4: - len = FIELD_SIZEOF(struct nf_conntrack_tuple, + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip); break; case NFPROTO_IPV6: case NFPROTO_INET: - len = FIELD_SIZEOF(struct nf_conntrack_tuple, + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip6); break; default: @@ -457,20 +457,20 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, if (tb[NFTA_CT_DIRECTION] == NULL) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conntrack_tuple, src.u3.ip); + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip); break; case NFT_CT_SRC_IP6: case NFT_CT_DST_IP6: if (tb[NFTA_CT_DIRECTION] == NULL) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conntrack_tuple, src.u3.ip6); + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip6); break; case NFT_CT_PROTO_SRC: case NFT_CT_PROTO_DST: if (tb[NFTA_CT_DIRECTION] == NULL) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conntrack_tuple, src.u.all); + len = sizeof_field(struct nf_conntrack_tuple, src.u.all); break; case NFT_CT_BYTES: case NFT_CT_PKTS: @@ -551,7 +551,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, case NFT_CT_MARK: if (tb[NFTA_CT_DIRECTION]) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conn, mark); + len = sizeof_field(struct nf_conn, mark); break; #endif #ifdef CONFIG_NF_CONNTRACK_LABELS diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 39dc94f2491e..bc9fd98c5d6d 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -43,7 +43,7 @@ static int nft_masq_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { - u32 plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); + u32 plen = sizeof_field(struct nf_nat_range, min_addr.all); struct nft_masq *priv = nft_expr_priv(expr); int err; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index c3c93e95b46e..8b44a4de5329 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -141,10 +141,10 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, switch (family) { case NFPROTO_IPV4: - alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip); + alen = sizeof_field(struct nf_nat_range, min_addr.ip); break; case NFPROTO_IPV6: - alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip6); + alen = sizeof_field(struct nf_nat_range, min_addr.ip6); break; default: return -EAFNOSUPPORT; @@ -171,7 +171,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, } } - plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); + plen = sizeof_field(struct nf_nat_range, min_addr.all); if (tb[NFTA_NAT_REG_PROTO_MIN]) { priv->sreg_proto_min = nft_parse_register(tb[NFTA_NAT_REG_PROTO_MIN]); diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index 4701fa8a45e7..89efcc5a533d 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -66,11 +66,21 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr if (err < 0) return err; + if (desc_from.type != NFT_DATA_VALUE) { + err = -EINVAL; + goto err1; + } + err = nft_data_init(NULL, &priv->data_to, sizeof(priv->data_to), &desc_to, tb[NFTA_RANGE_TO_DATA]); if (err < 0) goto err1; + if (desc_to.type != NFT_DATA_VALUE) { + err = -EINVAL; + goto err2; + } + if (desc_from.len != desc_to.len) { err = -EINVAL; goto err2; diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 43eeb1f609f1..5b779171565c 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -48,7 +48,7 @@ static int nft_redir_init(const struct nft_ctx *ctx, unsigned int plen; int err; - plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); + plen = sizeof_field(struct nf_nat_range, min_addr.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { priv->sreg_proto_min = nft_parse_register(tb[NFTA_REDIR_REG_PROTO_MIN]); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 57123259452f..a9f804f7a04a 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -74,8 +74,13 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set parent = rcu_dereference_raw(parent->rb_left); continue; } - if (nft_rbtree_interval_end(rbe)) - goto out; + if (nft_rbtree_interval_end(rbe)) { + if (nft_set_is_anonymous(set)) + return false; + parent = rcu_dereference_raw(parent->rb_left); + interval = NULL; + continue; + } *ext = &rbe->ext; return true; @@ -88,7 +93,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set *ext = &interval->ext; return true; } -out: + return false; } @@ -139,8 +144,10 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, if (flags & NFT_SET_ELEM_INTERVAL_END) interval = rbe; } else { - if (!nft_set_elem_active(&rbe->ext, genmask)) + if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = rcu_dereference_raw(parent->rb_left); + continue; + } if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) || (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) == @@ -148,7 +155,11 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, *elem = rbe; return true; } - return false; + + if (nft_rbtree_interval_end(rbe)) + interval = NULL; + + parent = rcu_dereference_raw(parent->rb_left); } } diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index f92a82c73880..4c33dfc9dab5 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -218,14 +218,14 @@ static int nft_tproxy_init(const struct nft_ctx *ctx, switch (priv->family) { case NFPROTO_IPV4: - alen = FIELD_SIZEOF(union nf_inet_addr, in); + alen = sizeof_field(union nf_inet_addr, in); err = nf_defrag_ipv4_enable(ctx->net); if (err) return err; break; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: - alen = FIELD_SIZEOF(union nf_inet_addr, in6); + alen = sizeof_field(union nf_inet_addr, in6); err = nf_defrag_ipv6_enable(ctx->net); if (err) return err; diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 2236455b10a3..37253d399c6b 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -30,7 +30,7 @@ static unsigned int jhash_rnd __read_mostly; static unsigned int xt_rateest_hash(const char *name) { - return jhash(name, FIELD_SIZEOF(struct xt_rateest, name), jhash_rnd) & + return jhash(name, sizeof_field(struct xt_rateest, name), jhash_rnd) & (RATEEST_HSIZE - 1); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 90b2ab9dd449..4e31721e7293 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2755,7 +2755,7 @@ static int __init netlink_proto_init(void) if (err != 0) goto out; - BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof_field(struct sk_buff, cb)); nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL); if (!nl_table) diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c index 9dd8a1096916..7d8e10e27c20 100644 --- a/net/nfc/nci/spi.c +++ b/net/nfc/nci/spi.c @@ -44,7 +44,8 @@ static int __nci_spi_send(struct nci_spi *nspi, struct sk_buff *skb, t.len = 0; } t.cs_change = cs_change; - t.delay_usecs = nspi->xfer_udelay; + t.delay.value = nspi->xfer_udelay; + t.delay.unit = SPI_DELAY_UNIT_USECS; t.speed_hz = nspi->xfer_speed_hz; spi_message_init(&m); @@ -216,7 +217,8 @@ static struct sk_buff *__nci_spi_read(struct nci_spi *nspi) rx.rx_buf = skb_put(skb, rx_len); rx.len = rx_len; rx.cs_change = 0; - rx.delay_usecs = nspi->xfer_udelay; + rx.delay.value = nspi->xfer_udelay; + rx.delay.unit = SPI_DELAY_UNIT_USECS; rx.speed_hz = nspi->xfer_speed_hz; spi_message_add_tail(&rx, &m); diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index 78fe622eba65..11b554ce07ff 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -346,7 +346,7 @@ static int nci_uart_default_recv_buf(struct nci_uart *nu, const u8 *data, nu->rx_packet_len = -1; nu->rx_skb = nci_skb_alloc(nu->ndev, NCI_MAX_PACKET_SIZE, - GFP_KERNEL); + GFP_ATOMIC); if (!nu->rx_skb) return -ENOMEM; } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 12936c151cc0..4c8395462303 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -166,7 +166,8 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, int err; err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype, - skb->mac_len); + skb->mac_len, + ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET); if (err) return err; @@ -179,7 +180,8 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key, { int err; - err = skb_mpls_pop(skb, ethertype, skb->mac_len); + err = skb_mpls_pop(skb, ethertype, skb->mac_len, + ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET); if (err) return err; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index df9c80bf621d..e726159cfcfa 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -903,6 +903,17 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, } err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype); + if (err == NF_ACCEPT && + ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, + maniptype); + } + /* Mark NAT done if successful and update the flow key. */ if (err == NF_ACCEPT) ovs_nat_update_key(key, skb, maniptype); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 1047e8043084..e3a37d22539c 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2497,7 +2497,7 @@ static int __init dp_init(void) { int err; - BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof_field(struct sk_buff, cb)); pr_info("Open vSwitch switching datapath\n"); diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index fd8ed766bdd1..758a8c77f736 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -37,7 +37,7 @@ enum sw_flow_mac_proto { * matching for small options. */ #define TUN_METADATA_OFFSET(opt_len) \ - (FIELD_SIZEOF(struct sw_flow_key, tun_opts) - opt_len) + (sizeof_field(struct sw_flow_key, tun_opts) - opt_len) #define TUN_METADATA_OPTS(flow_key, opt_len) \ ((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len))) @@ -52,7 +52,7 @@ struct vlan_head { #define OVS_SW_FLOW_KEY_METADATA_SIZE \ (offsetof(struct sw_flow_key, recirc_id) + \ - FIELD_SIZEOF(struct sw_flow_key, recirc_id)) + sizeof_field(struct sw_flow_key, recirc_id)) struct ovs_key_nsh { struct ovs_nsh_key_base base; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 53c1d41fb1c9..118cd66b7516 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -544,7 +544,8 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po, msec = 1; div = ecmd.base.speed / 1000; } - } + } else + return DEFAULT_PRB_RETIRE_TOV; mbits = (blk_size_in_bytes * 8) / (1024 * 1024); diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 461d75274fb3..971c73c7d34c 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1002,10 +1002,13 @@ static void rfkill_sync_work(struct work_struct *work) int __must_check rfkill_register(struct rfkill *rfkill) { static unsigned long rfkill_no; - struct device *dev = &rfkill->dev; + struct device *dev; int error; - BUG_ON(!rfkill); + if (!rfkill) + return -EINVAL; + + dev = &rfkill->dev; mutex_lock(&rfkill_global_mutex); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index d72ddb67bb74..9d3c4d2d893a 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -972,7 +972,7 @@ static int __init af_rxrpc_init(void) int ret = -1; unsigned int tmp; - BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb)); get_random_bytes(&tmp, sizeof(tmp)); tmp &= 0x3fffffff; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index ae0de372b1c8..f685c0d73708 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -312,7 +312,7 @@ static void tcf_ct_act_set_labels(struct nf_conn *ct, u32 *labels_m) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) - size_t labels_sz = FIELD_SIZEOF(struct tcf_ct_params, labels); + size_t labels_sz = sizeof_field(struct tcf_ct_params, labels); if (!memchr_inv(labels_m, 0, labels_sz)) return; @@ -329,6 +329,7 @@ static int tcf_ct_act_nat(struct sk_buff *skb, bool commit) { #if IS_ENABLED(CONFIG_NF_NAT) + int err; enum nf_nat_manip_type maniptype; if (!(ct_action & TCA_CT_ACT_NAT)) @@ -359,7 +360,17 @@ static int tcf_ct_act_nat(struct sk_buff *skb, return NF_ACCEPT; } - return ct_nat_execute(skb, ct, ctinfo, range, maniptype); + err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); + if (err == NF_ACCEPT && + ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); + } + return err; #else return NF_ACCEPT; #endif @@ -925,7 +936,7 @@ static struct tc_action_ops act_ct_ops = { static __net_init int ct_init_net(struct net *net) { - unsigned int n_bits = FIELD_SIZEOF(struct tcf_ct_params, labels) * 8; + unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8; struct tc_ct_action_net *tn = net_generic(net, ct_net_id); if (nf_connlabels_get(net, n_bits - 1)) { diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 325eddcc6621..be3f215cd027 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2019 Netronome Systems, Inc. */ +#include <linux/if_arp.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> @@ -76,12 +77,14 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, switch (p->tcfm_action) { case TCA_MPLS_ACT_POP: - if (skb_mpls_pop(skb, p->tcfm_proto, mac_len)) + if (skb_mpls_pop(skb, p->tcfm_proto, mac_len, + skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; break; case TCA_MPLS_ACT_PUSH: new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol)); - if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len)) + if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len, + skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; break; case TCA_MPLS_ACT_MODIFY: diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 20d60b8fcb70..6a0eacafdb19 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -626,15 +626,15 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) static int tcf_block_setup(struct tcf_block *block, struct flow_block_offload *bo); -static void tc_indr_block_ing_cmd(struct net_device *dev, - struct tcf_block *block, - flow_indr_block_bind_cb_t *cb, - void *cb_priv, - enum flow_block_command command) +static void tc_indr_block_cmd(struct net_device *dev, struct tcf_block *block, + flow_indr_block_bind_cb_t *cb, void *cb_priv, + enum flow_block_command command, bool ingress) { struct flow_block_offload bo = { .command = command, - .binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS, + .binder_type = ingress ? + FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS : + FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS, .net = dev_net(dev), .block_shared = tcf_block_non_null_shared(block), }; @@ -652,9 +652,10 @@ static void tc_indr_block_ing_cmd(struct net_device *dev, up_write(&block->cb_lock); } -static struct tcf_block *tc_dev_ingress_block(struct net_device *dev) +static struct tcf_block *tc_dev_block(struct net_device *dev, bool ingress) { const struct Qdisc_class_ops *cops; + const struct Qdisc_ops *ops; struct Qdisc *qdisc; if (!dev_ingress_queue(dev)) @@ -664,24 +665,37 @@ static struct tcf_block *tc_dev_ingress_block(struct net_device *dev) if (!qdisc) return NULL; - cops = qdisc->ops->cl_ops; + ops = qdisc->ops; + if (!ops) + return NULL; + + if (!ingress && !strcmp("ingress", ops->id)) + return NULL; + + cops = ops->cl_ops; if (!cops) return NULL; if (!cops->tcf_block) return NULL; - return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL); + return cops->tcf_block(qdisc, + ingress ? TC_H_MIN_INGRESS : TC_H_MIN_EGRESS, + NULL); } -static void tc_indr_block_get_and_ing_cmd(struct net_device *dev, - flow_indr_block_bind_cb_t *cb, - void *cb_priv, - enum flow_block_command command) +static void tc_indr_block_get_and_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command) { - struct tcf_block *block = tc_dev_ingress_block(dev); + struct tcf_block *block; + + block = tc_dev_block(dev, true); + tc_indr_block_cmd(dev, block, cb, cb_priv, command, true); - tc_indr_block_ing_cmd(dev, block, cb, cb_priv, command); + block = tc_dev_block(dev, false); + tc_indr_block_cmd(dev, block, cb, cb_priv, command, false); } static void tc_indr_block_call(struct tcf_block *block, @@ -2721,13 +2735,19 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, struct netlink_ext_ack *extack) { const struct tcf_proto_ops *ops; + char name[IFNAMSIZ]; void *tmplt_priv; /* If kind is not set, user did not specify template. */ if (!tca[TCA_KIND]) return 0; - ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), true, extack); + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC chain template name too long"); + return -EINVAL; + } + + ops = tcf_proto_lookup_ops(name, true, extack); if (IS_ERR(ops)) return PTR_ERR(ops); if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) { @@ -3626,9 +3646,9 @@ static struct pernet_operations tcf_net_ops = { .size = sizeof(struct tcf_net), }; -static struct flow_indr_block_ing_entry block_ing_entry = { - .cb = tc_indr_block_get_and_ing_cmd, - .list = LIST_HEAD_INIT(block_ing_entry.list), +static struct flow_indr_block_entry block_entry = { + .cb = tc_indr_block_get_and_cmd, + .list = LIST_HEAD_INIT(block_entry.list), }; static int __init tc_filter_init(void) @@ -3643,7 +3663,7 @@ static int __init tc_filter_init(void) if (err) goto err_register_pernet_subsys; - flow_indr_add_block_ing_cb(&block_ing_entry); + flow_indr_add_block_cb(&block_entry); rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, RTNL_FLAG_DOIT_UNLOCKED); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index c307ee1d6ca6..0d125de54285 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -56,8 +56,13 @@ struct fl_flow_key { struct flow_dissector_key_ip ip; struct flow_dissector_key_ip enc_ip; struct flow_dissector_key_enc_opts enc_opts; - struct flow_dissector_key_ports tp_min; - struct flow_dissector_key_ports tp_max; + union { + struct flow_dissector_key_ports tp; + struct { + struct flow_dissector_key_ports tp_min; + struct flow_dissector_key_ports tp_max; + }; + } tp_range; struct flow_dissector_key_ct ct; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ @@ -200,19 +205,19 @@ static bool fl_range_port_dst_cmp(struct cls_fl_filter *filter, { __be16 min_mask, max_mask, min_val, max_val; - min_mask = htons(filter->mask->key.tp_min.dst); - max_mask = htons(filter->mask->key.tp_max.dst); - min_val = htons(filter->key.tp_min.dst); - max_val = htons(filter->key.tp_max.dst); + min_mask = htons(filter->mask->key.tp_range.tp_min.dst); + max_mask = htons(filter->mask->key.tp_range.tp_max.dst); + min_val = htons(filter->key.tp_range.tp_min.dst); + max_val = htons(filter->key.tp_range.tp_max.dst); if (min_mask && max_mask) { - if (htons(key->tp.dst) < min_val || - htons(key->tp.dst) > max_val) + if (htons(key->tp_range.tp.dst) < min_val || + htons(key->tp_range.tp.dst) > max_val) return false; /* skb does not have min and max values */ - mkey->tp_min.dst = filter->mkey.tp_min.dst; - mkey->tp_max.dst = filter->mkey.tp_max.dst; + mkey->tp_range.tp_min.dst = filter->mkey.tp_range.tp_min.dst; + mkey->tp_range.tp_max.dst = filter->mkey.tp_range.tp_max.dst; } return true; } @@ -223,19 +228,19 @@ static bool fl_range_port_src_cmp(struct cls_fl_filter *filter, { __be16 min_mask, max_mask, min_val, max_val; - min_mask = htons(filter->mask->key.tp_min.src); - max_mask = htons(filter->mask->key.tp_max.src); - min_val = htons(filter->key.tp_min.src); - max_val = htons(filter->key.tp_max.src); + min_mask = htons(filter->mask->key.tp_range.tp_min.src); + max_mask = htons(filter->mask->key.tp_range.tp_max.src); + min_val = htons(filter->key.tp_range.tp_min.src); + max_val = htons(filter->key.tp_range.tp_max.src); if (min_mask && max_mask) { - if (htons(key->tp.src) < min_val || - htons(key->tp.src) > max_val) + if (htons(key->tp_range.tp.src) < min_val || + htons(key->tp_range.tp.src) > max_val) return false; /* skb does not have min and max values */ - mkey->tp_min.src = filter->mkey.tp_min.src; - mkey->tp_max.src = filter->mkey.tp_max.src; + mkey->tp_range.tp_min.src = filter->mkey.tp_range.tp_min.src; + mkey->tp_range.tp_max.src = filter->mkey.tp_range.tp_max.src; } return true; } @@ -734,23 +739,25 @@ static void fl_set_key_val(struct nlattr **tb, static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask) { - fl_set_key_val(tb, &key->tp_min.dst, - TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_min.dst, - TCA_FLOWER_UNSPEC, sizeof(key->tp_min.dst)); - fl_set_key_val(tb, &key->tp_max.dst, - TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_max.dst, - TCA_FLOWER_UNSPEC, sizeof(key->tp_max.dst)); - fl_set_key_val(tb, &key->tp_min.src, - TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_min.src, - TCA_FLOWER_UNSPEC, sizeof(key->tp_min.src)); - fl_set_key_val(tb, &key->tp_max.src, - TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_max.src, - TCA_FLOWER_UNSPEC, sizeof(key->tp_max.src)); - - if ((mask->tp_min.dst && mask->tp_max.dst && - htons(key->tp_max.dst) <= htons(key->tp_min.dst)) || - (mask->tp_min.src && mask->tp_max.src && - htons(key->tp_max.src) <= htons(key->tp_min.src))) + fl_set_key_val(tb, &key->tp_range.tp_min.dst, + TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_range.tp_min.dst, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_min.dst)); + fl_set_key_val(tb, &key->tp_range.tp_max.dst, + TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_range.tp_max.dst, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.dst)); + fl_set_key_val(tb, &key->tp_range.tp_min.src, + TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_range.tp_min.src, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_min.src)); + fl_set_key_val(tb, &key->tp_range.tp_max.src, + TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_range.tp_max.src, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.src)); + + if ((mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst && + htons(key->tp_range.tp_max.dst) <= + htons(key->tp_range.tp_min.dst)) || + (mask->tp_range.tp_min.src && mask->tp_range.tp_max.src && + htons(key->tp_range.tp_max.src) <= + htons(key->tp_range.tp_min.src))) return -EINVAL; return 0; @@ -1474,7 +1481,7 @@ static int fl_init_mask_hashtable(struct fl_flow_mask *mask) } #define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member) -#define FL_KEY_MEMBER_SIZE(member) FIELD_SIZEOF(struct fl_flow_key, member) +#define FL_KEY_MEMBER_SIZE(member) sizeof_field(struct fl_flow_key, member) #define FL_KEY_IS_MASKED(mask, member) \ memchr_inv(((char *)mask) + FL_KEY_MEMBER_OFFSET(member), \ @@ -1509,9 +1516,10 @@ static void fl_init_dissector(struct flow_dissector *dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); - if (FL_KEY_IS_MASKED(mask, tp) || - FL_KEY_IS_MASKED(mask, tp_min) || FL_KEY_IS_MASKED(mask, tp_max)) - FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_PORTS, tp); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_PORTS, tp); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_PORTS_RANGE, tp_range); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_IP, ip); FL_KEY_SET_IF_MASKED(mask, keys, cnt, @@ -1560,8 +1568,10 @@ static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head, fl_mask_copy(newmask, mask); - if ((newmask->key.tp_min.dst && newmask->key.tp_max.dst) || - (newmask->key.tp_min.src && newmask->key.tp_max.src)) + if ((newmask->key.tp_range.tp_min.dst && + newmask->key.tp_range.tp_max.dst) || + (newmask->key.tp_range.tp_min.src && + newmask->key.tp_range.tp_max.src)) newmask->flags |= TCA_FLOWER_MASK_FLAGS_RANGE; err = fl_init_mask_hashtable(newmask); @@ -2159,18 +2169,22 @@ static int fl_dump_key_val(struct sk_buff *skb, static int fl_dump_key_port_range(struct sk_buff *skb, struct fl_flow_key *key, struct fl_flow_key *mask) { - if (fl_dump_key_val(skb, &key->tp_min.dst, TCA_FLOWER_KEY_PORT_DST_MIN, - &mask->tp_min.dst, TCA_FLOWER_UNSPEC, - sizeof(key->tp_min.dst)) || - fl_dump_key_val(skb, &key->tp_max.dst, TCA_FLOWER_KEY_PORT_DST_MAX, - &mask->tp_max.dst, TCA_FLOWER_UNSPEC, - sizeof(key->tp_max.dst)) || - fl_dump_key_val(skb, &key->tp_min.src, TCA_FLOWER_KEY_PORT_SRC_MIN, - &mask->tp_min.src, TCA_FLOWER_UNSPEC, - sizeof(key->tp_min.src)) || - fl_dump_key_val(skb, &key->tp_max.src, TCA_FLOWER_KEY_PORT_SRC_MAX, - &mask->tp_max.src, TCA_FLOWER_UNSPEC, - sizeof(key->tp_max.src))) + if (fl_dump_key_val(skb, &key->tp_range.tp_min.dst, + TCA_FLOWER_KEY_PORT_DST_MIN, + &mask->tp_range.tp_min.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_min.dst)) || + fl_dump_key_val(skb, &key->tp_range.tp_max.dst, + TCA_FLOWER_KEY_PORT_DST_MAX, + &mask->tp_range.tp_max.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_max.dst)) || + fl_dump_key_val(skb, &key->tp_range.tp_min.src, + TCA_FLOWER_KEY_PORT_SRC_MIN, + &mask->tp_range.tp_min.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_min.src)) || + fl_dump_key_val(skb, &key->tp_range.tp_max.src, + TCA_FLOWER_KEY_PORT_SRC_MAX, + &mask->tp_range.tp_max.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_max.src))) return -1; return 0; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index a0e6fac613de..66c6bcec16cb 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1108,10 +1108,33 @@ erridr: return err; } +static bool u32_hnode_empty(struct tc_u_hnode *ht, bool *non_root_ht) +{ + int i; + + if (!ht) + return true; + if (!ht->is_root) { + *non_root_ht = true; + return false; + } + if (*non_root_ht) + return false; + if (ht->refcnt < 2) + return true; + + for (i = 0; i <= ht->divisor; i++) { + if (rtnl_dereference(ht->ht[i])) + return false; + } + return true; +} + static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held) { struct tc_u_common *tp_c = tp->data; + bool non_root_ht = false; struct tc_u_hnode *ht; struct tc_u_knode *n; unsigned int h; @@ -1124,6 +1147,8 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, ht = rtnl_dereference(ht->next)) { if (ht->prio != tp->prio) continue; + if (u32_hnode_empty(ht, &non_root_ht)) + return; if (arg->count >= arg->skip) { if (arg->fn(tp, ht, arg) < 0) { arg->stop = 1; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 53a80bc6b13a..e0f40400f679 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2184,6 +2184,7 @@ static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = { [TCA_CAKE_MPU] = { .type = NLA_U32 }, [TCA_CAKE_INGRESS] = { .type = NLA_U32 }, [TCA_CAKE_ACK_FILTER] = { .type = NLA_U32 }, + [TCA_CAKE_SPLIT_GSO] = { .type = NLA_U32 }, [TCA_CAKE_FWMARK] = { .type = NLA_U32 }, }; diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 278c0b2dc523..e79f1afe0cfd 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -153,6 +153,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) __gnet_stats_copy_queue(&sch->qstats, qdisc->cpu_qstats, &qdisc->qstats, qlen); + sch->q.qlen += qlen; } else { sch->q.qlen += qdisc->q.qlen; sch->bstats.bytes += qdisc->bstats.bytes; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 0d0113a24962..8766ab5b8788 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -411,6 +411,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) __gnet_stats_copy_queue(&sch->qstats, qdisc->cpu_qstats, &qdisc->qstats, qlen); + sch->q.qlen += qlen; } else { sch->q.qlen += qdisc->q.qlen; sch->bstats.bytes += qdisc->bstats.bytes; @@ -433,7 +434,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.offset[tc] = dev->tc_to_txq[tc].offset; } - if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt)) + if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; if ((priv->flags & TC_MQPRIO_F_MODE) && diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index dd860fea0148..bc734cfaa29e 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -275,7 +275,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (!asoc || saddr) goto out; @@ -328,7 +328,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, fl6->saddr = laddr->a.v6.sin6_addr; fl6->fl6_sport = laddr->a.v6.sin6_port; final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); - bdst = ip6_dst_lookup_flow(sk, fl6, final_p); + bdst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (IS_ERR(bdst)) continue; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index fbbf19128c2d..78af2fcf90cc 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -227,6 +227,7 @@ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb, sa->sin_port = sh->dest; sa->sin_addr.s_addr = ip_hdr(skb)->daddr; } + memset(sa->sin_zero, 0, sizeof(sa->sin_zero)); } /* Initialize an sctp_addr from a socket. */ @@ -235,6 +236,7 @@ static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk) addr->v4.sin_family = AF_INET; addr->v4.sin_port = 0; addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ @@ -257,6 +259,7 @@ static void sctp_v4_from_addr_param(union sctp_addr *addr, addr->v4.sin_family = AF_INET; addr->v4.sin_port = port; addr->v4.sin_addr.s_addr = param->v4.addr.s_addr; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize an address parameter from a sctp_addr and return the length @@ -281,6 +284,7 @@ static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4, saddr->v4.sin_family = AF_INET; saddr->v4.sin_port = port; saddr->v4.sin_addr.s_addr = fl4->saddr; + memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero)); } /* Compare two addresses exactly. */ @@ -303,6 +307,7 @@ static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port) addr->v4.sin_family = AF_INET; addr->v4.sin_addr.s_addr = htonl(INADDR_ANY); addr->v4.sin_port = port; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Is this a wildcard address? */ diff --git a/net/sctp/stream.c b/net/sctp/stream.c index e83cdaa2ab76..6a30392068a0 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -84,8 +84,10 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, return 0; ret = genradix_prealloc(&stream->out, outcnt, gfp); - if (ret) + if (ret) { + genradix_free(&stream->out); return ret; + } stream->outcnt = outcnt; return 0; @@ -100,8 +102,10 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, return 0; ret = genradix_prealloc(&stream->in, incnt, gfp); - if (ret) + if (ret) { + genradix_free(&stream->in); return ret; + } stream->incnt = incnt; return 0; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index b997072c72e5..cee5bf4a9bb9 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -857,6 +857,8 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, goto out; sock_hold(&smc->sk); /* sock put in passive closing */ + if (smc->use_fallback) + goto out; if (flags & O_NONBLOCK) { if (schedule_work(&smc->connect_work)) smc->connect_nonblock = 1; @@ -1721,8 +1723,6 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_err = smc->clcsock->sk->sk_err; sk->sk_error_report(sk); } - if (rc) - return rc; if (optlen < sizeof(int)) return -EINVAL; @@ -1730,6 +1730,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; lock_sock(sk); + if (rc || smc->use_fallback) + goto out; switch (optname) { case TCP_ULP: case TCP_FASTOPEN: @@ -1741,15 +1743,14 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { - if (!smc->use_fallback) - rc = -EINVAL; + rc = -EINVAL; } break; case TCP_NODELAY: if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (val && !smc->use_fallback) + if (val) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } @@ -1758,7 +1759,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (!val && !smc->use_fallback) + if (!val) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } @@ -1769,6 +1770,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, default: break; } +out: release_sock(sk); return rc; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index bb92c7c6214c..e419ff277e55 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1287,7 +1287,7 @@ static int smc_core_reboot_event(struct notifier_block *this, unsigned long event, void *ptr) { smc_lgrs_shutdown(); - + smc_ib_unregister_client(); return 0; } diff --git a/net/socket.c b/net/socket.c index ea28cbb9e2e7..50623218747f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -957,7 +957,7 @@ static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) .msg_iocb = iocb}; ssize_t res; - if (file->f_flags & O_NONBLOCK) + if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (iocb->ki_pos != 0) @@ -982,7 +982,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_pos != 0) return -ESPIPE; - if (file->f_flags & O_NONBLOCK) + if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (sock->type == SOCK_SEQPACKET) @@ -1826,26 +1826,22 @@ SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr, * include the -EINPROGRESS status for such sockets. */ -int __sys_connect_file(struct file *file, struct sockaddr __user *uservaddr, +int __sys_connect_file(struct file *file, struct sockaddr_storage *address, int addrlen, int file_flags) { struct socket *sock; - struct sockaddr_storage address; int err; sock = sock_from_file(file, &err); if (!sock) goto out; - err = move_addr_to_kernel(uservaddr, addrlen, &address); - if (err < 0) - goto out; err = - security_socket_connect(sock, (struct sockaddr *)&address, addrlen); + security_socket_connect(sock, (struct sockaddr *)address, addrlen); if (err) goto out; - err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen, + err = sock->ops->connect(sock, (struct sockaddr *)address, addrlen, sock->file->f_flags | file_flags); out: return err; @@ -1858,7 +1854,11 @@ int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) f = fdget(fd); if (f.file) { - ret = __sys_connect_file(f.file, uservaddr, addrlen, 0); + struct sockaddr_storage address; + + ret = move_addr_to_kernel(uservaddr, addrlen, &address); + if (!ret) + ret = __sys_connect_file(f.file, &address, addrlen, 0); if (f.flags) fput(f.file); } @@ -2346,9 +2346,9 @@ out: return err; } -static int sendmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct iovec **iov) +int sendmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct iovec **iov) { int err; @@ -2390,27 +2390,14 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, /* * BSD sendmsg interface */ -long __sys_sendmsg_sock(struct socket *sock, struct user_msghdr __user *umsg, +long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg, unsigned int flags) { - struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; - struct sockaddr_storage address; - struct msghdr msg = { .msg_name = &address }; - ssize_t err; - - err = sendmsg_copy_msghdr(&msg, umsg, flags, &iov); - if (err) - return err; /* disallow ancillary data requests from this path */ - if (msg.msg_control || msg.msg_controllen) { - err = -EINVAL; - goto out; - } + if (msg->msg_control || msg->msg_controllen) + return -EINVAL; - err = ____sys_sendmsg(sock, &msg, flags, NULL, 0); -out: - kfree(iov); - return err; + return ____sys_sendmsg(sock, msg, flags, NULL, 0); } long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, @@ -2516,10 +2503,10 @@ SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, return __sys_sendmmsg(fd, mmsg, vlen, flags, true); } -static int recvmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct sockaddr __user **uaddr, - struct iovec **iov) +int recvmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct sockaddr __user **uaddr, + struct iovec **iov) { ssize_t err; @@ -2559,7 +2546,12 @@ static int ____sys_recvmsg(struct socket *sock, struct msghdr *msg_sys, if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; - err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys, flags); + + if (unlikely(nosec)) + err = sock_recvmsg_nosec(sock, msg_sys, flags); + else + err = sock_recvmsg(sock, msg_sys, flags); + if (err < 0) goto out; len = err; @@ -2609,28 +2601,15 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, * BSD recvmsg interface */ -long __sys_recvmsg_sock(struct socket *sock, struct user_msghdr __user *umsg, - unsigned int flags) +long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, + struct user_msghdr __user *umsg, + struct sockaddr __user *uaddr, unsigned int flags) { - struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; - struct sockaddr_storage address; - struct msghdr msg = { .msg_name = &address }; - struct sockaddr __user *uaddr; - ssize_t err; - - err = recvmsg_copy_msghdr(&msg, umsg, flags, &uaddr, &iov); - if (err) - return err; /* disallow ancillary data requests from this path */ - if (msg.msg_control || msg.msg_controllen) { - err = -EINVAL; - goto out; - } + if (msg->msg_control || msg->msg_controllen) + return -EINVAL; - err = ____sys_recvmsg(sock, &msg, umsg, uaddr, flags, 0); -out: - kfree(iov); - return err; + return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); } long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 82060099a429..30b7de6f3d76 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -20,6 +20,7 @@ #include <linux/sunrpc/sched.h> #include <linux/sunrpc/gss_api.h> #include <linux/sunrpc/clnt.h> +#include <trace/events/rpcgss.h> #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH @@ -158,7 +159,6 @@ struct gss_api_mech *gss_mech_get_by_OID(struct rpcsec_gss_oid *obj) if (sprint_oid(obj->data, obj->len, buf, sizeof(buf)) < 0) return NULL; - dprintk("RPC: %s(%s)\n", __func__, buf); request_module("rpc-auth-gss-%s", buf); rcu_read_lock(); @@ -172,6 +172,8 @@ struct gss_api_mech *gss_mech_get_by_OID(struct rpcsec_gss_oid *obj) } } rcu_read_unlock(); + if (!gm) + trace_rpcgss_oid_to_mech(buf); return gm; } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 8be2f209982b..c62d1f10978b 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -49,6 +49,9 @@ #include <linux/sunrpc/svcauth.h> #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/cache.h> + +#include <trace/events/rpcgss.h> + #include "gss_rpc_upcall.h" @@ -1075,24 +1078,32 @@ gss_read_verf(struct rpc_gss_wire_cred *gc, return 0; } -/* Ok this is really heavily depending on a set of semantics in - * how rqstp is set up by svc_recv and pages laid down by the - * server when reading a request. We are basically guaranteed that - * the token lays all down linearly across a set of pages, starting - * at iov_base in rq_arg.head[0] which happens to be the first of a - * set of pages stored in rq_pages[]. - * rq_arg.head[0].iov_base will provide us the page_base to pass - * to the upcall. - */ -static inline int -gss_read_proxy_verf(struct svc_rqst *rqstp, - struct rpc_gss_wire_cred *gc, __be32 *authp, - struct xdr_netobj *in_handle, - struct gssp_in_token *in_token) +static void gss_free_in_token_pages(struct gssp_in_token *in_token) { - struct kvec *argv = &rqstp->rq_arg.head[0]; u32 inlen; - int res; + int i; + + i = 0; + inlen = in_token->page_len; + while (inlen) { + if (in_token->pages[i]) + put_page(in_token->pages[i]); + inlen -= inlen > PAGE_SIZE ? PAGE_SIZE : inlen; + } + + kfree(in_token->pages); + in_token->pages = NULL; +} + +static int gss_read_proxy_verf(struct svc_rqst *rqstp, + struct rpc_gss_wire_cred *gc, __be32 *authp, + struct xdr_netobj *in_handle, + struct gssp_in_token *in_token) +{ + struct kvec *argv = &rqstp->rq_arg.head[0]; + unsigned int page_base, length; + int pages, i, res; + size_t inlen; res = gss_read_common_verf(gc, argv, authp, in_handle); if (res) @@ -1102,10 +1113,36 @@ gss_read_proxy_verf(struct svc_rqst *rqstp, if (inlen > (argv->iov_len + rqstp->rq_arg.page_len)) return SVC_DENIED; - in_token->pages = rqstp->rq_pages; - in_token->page_base = (ulong)argv->iov_base & ~PAGE_MASK; + pages = DIV_ROUND_UP(inlen, PAGE_SIZE); + in_token->pages = kcalloc(pages, sizeof(struct page *), GFP_KERNEL); + if (!in_token->pages) + return SVC_DENIED; + in_token->page_base = 0; in_token->page_len = inlen; + for (i = 0; i < pages; i++) { + in_token->pages[i] = alloc_page(GFP_KERNEL); + if (!in_token->pages[i]) { + gss_free_in_token_pages(in_token); + return SVC_DENIED; + } + } + length = min_t(unsigned int, inlen, argv->iov_len); + memcpy(page_address(in_token->pages[0]), argv->iov_base, length); + inlen -= length; + + i = 1; + page_base = rqstp->rq_arg.page_base; + while (inlen) { + length = min_t(unsigned int, inlen, PAGE_SIZE); + memcpy(page_address(in_token->pages[i]), + page_address(rqstp->rq_arg.pages[i]) + page_base, + length); + + inlen -= length; + page_base = 0; + i++; + } return 0; } @@ -1270,9 +1307,8 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, if (status) goto out; - dprintk("RPC: svcauth_gss: gss major status = %d " - "minor status = %d\n", - ud.major_status, ud.minor_status); + trace_rpcgss_accept_upcall(rqstp->rq_xid, ud.major_status, + ud.minor_status); switch (ud.major_status) { case GSS_S_CONTINUE_NEEDED: @@ -1280,8 +1316,11 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, break; case GSS_S_COMPLETE: status = gss_proxy_save_rsc(sn->rsc_cache, &ud, &handle); - if (status) + if (status) { + pr_info("%s: gss_proxy_save_rsc failed (%d)\n", + __func__, status); goto out; + } cli_handle.data = (u8 *)&handle; cli_handle.len = sizeof(handle); break; @@ -1292,15 +1331,20 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, /* Got an answer to the upcall; use it: */ if (gss_write_init_verf(sn->rsc_cache, rqstp, - &cli_handle, &ud.major_status)) + &cli_handle, &ud.major_status)) { + pr_info("%s: gss_write_init_verf failed\n", __func__); goto out; + } if (gss_write_resv(resv, PAGE_SIZE, &cli_handle, &ud.out_token, - ud.major_status, ud.minor_status)) + ud.major_status, ud.minor_status)) { + pr_info("%s: gss_write_resv failed\n", __func__); goto out; + } ret = SVC_COMPLETE; out: + gss_free_in_token_pages(&ud.in_token); gssp_free_upcall_data(&ud); return ret; } diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index a349094f6fb7..f740cb51802a 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -53,9 +53,6 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail) h->last_refresh = now; } -static inline int cache_is_valid(struct cache_head *h); -static void cache_fresh_locked(struct cache_head *head, time_t expiry, - struct cache_detail *detail); static void cache_fresh_unlocked(struct cache_head *head, struct cache_detail *detail); @@ -105,9 +102,6 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, if (cache_is_expired(detail, tmp)) { hlist_del_init_rcu(&tmp->cache_list); detail->entries --; - if (cache_is_valid(tmp) == -EAGAIN) - set_bit(CACHE_NEGATIVE, &tmp->flags); - cache_fresh_locked(tmp, 0, detail); freeme = tmp; break; } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f7f78566be46..a3379765605d 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -591,6 +591,9 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) xprt->resvport = 1; if (args->flags & RPC_CLNT_CREATE_NONPRIVPORT) xprt->resvport = 0; + xprt->reuseport = 0; + if (args->flags & RPC_CLNT_CREATE_REUSEPORT) + xprt->reuseport = 1; clnt = rpc_create_xprt(args, xprt); if (IS_ERR(clnt) || args->nconnect <= 1) @@ -1676,8 +1679,6 @@ call_reserveresult(struct rpc_task *task) return; } - printk(KERN_ERR "%s: status=%d, but no request slot, exiting\n", - __func__, status); rpc_call_rpcerror(task, -EIO); return; } @@ -1686,11 +1687,8 @@ call_reserveresult(struct rpc_task *task) * Even though there was an error, we may have acquired * a request slot somehow. Make sure not to leak it. */ - if (task->tk_rqstp) { - printk(KERN_ERR "%s: status=%d, request allocated anyway\n", - __func__, status); + if (task->tk_rqstp) xprt_release(task); - } switch (status) { case -ENOMEM: @@ -1699,14 +1697,9 @@ call_reserveresult(struct rpc_task *task) case -EAGAIN: /* woken up; retry */ task->tk_action = call_retry_reserve; return; - case -EIO: /* probably a shutdown */ - break; default: - printk(KERN_ERR "%s: unrecognized error %d, exiting\n", - __func__, status); - break; + rpc_call_rpcerror(task, status); } - rpc_call_rpcerror(task, status); } /* @@ -2906,7 +2899,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt; unsigned long connect_timeout; unsigned long reconnect_timeout; - unsigned char resvport; + unsigned char resvport, reuseport; int ret = 0; rcu_read_lock(); @@ -2918,6 +2911,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, return -EAGAIN; } resvport = xprt->resvport; + reuseport = xprt->reuseport; connect_timeout = xprt->connect_timeout; reconnect_timeout = xprt->max_reconnect_timeout; rcu_read_unlock(); @@ -2928,6 +2922,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, goto out_put_switch; } xprt->resvport = resvport; + xprt->reuseport = reuseport; if (xprt->ops->set_connect_timeout != NULL) xprt->ops->set_connect_timeout(xprt, connect_timeout, diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index b71a39ded930..39e14d5edaf1 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -51,7 +51,7 @@ static BLOCKING_NOTIFIER_HEAD(rpc_pipefs_notifier_list); int rpc_pipefs_notifier_register(struct notifier_block *nb) { - return blocking_notifier_chain_cond_register(&rpc_pipefs_notifier_list, nb); + return blocking_notifier_chain_register(&rpc_pipefs_notifier_list, nb); } EXPORT_SYMBOL_GPL(rpc_pipefs_notifier_register); diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 360afe153193..9c79548c6847 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -260,7 +260,7 @@ static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const c rpc_reset_waitqueue_priority(queue); queue->qlen = 0; queue->timer_list.expires = 0; - INIT_DEFERRABLE_WORK(&queue->timer_list.dwork, __rpc_queue_timer_fn); + INIT_DELAYED_WORK(&queue->timer_list.dwork, __rpc_queue_timer_fn); INIT_LIST_HEAD(&queue->timer_list.list); rpc_assign_waitqueue_name(queue, qname); } @@ -824,6 +824,7 @@ rpc_reset_task_statistics(struct rpc_task *task) */ void rpc_exit_task(struct rpc_task *task) { + trace_rpc_task_end(task, task->tk_action); task->tk_action = NULL; if (task->tk_ops->rpc_count_stats) task->tk_ops->rpc_count_stats(task, task->tk_calldata); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index d11b70552c33..187dd4e73d64 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1337,6 +1337,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) auth_stat = rpc_autherr_badcred; auth_res = progp->pg_authenticate(rqstp); } + if (auth_res != SVC_OK) + trace_svc_authenticate(rqstp, auth_res, auth_stat); switch (auth_res) { case SVC_OK: break; diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 550b214cb001..552617e3467b 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -19,6 +19,8 @@ #include <linux/err.h> #include <linux/hash.h> +#include <trace/events/sunrpc.h> + #define RPCDBG_FACILITY RPCDBG_AUTH diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 14ba9e72a204..f3104be8ff5d 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -436,13 +436,12 @@ xdr_shrink_bufhead(struct xdr_buf *buf, size_t len) } /** - * xdr_shrink_pagelen + * xdr_shrink_pagelen - shrinks buf->pages by up to @len bytes * @buf: xdr_buf * @len: bytes to remove from buf->pages * - * Shrinks XDR buffer's page array buf->pages by - * 'len' bytes. The extra data is not lost, but is instead - * moved into the tail. + * The extra data is not lost, but is instead moved into buf->tail. + * Returns the actual number of bytes moved. */ static unsigned int xdr_shrink_pagelen(struct xdr_buf *buf, size_t len) @@ -455,8 +454,8 @@ xdr_shrink_pagelen(struct xdr_buf *buf, size_t len) result = 0; tail = buf->tail; - BUG_ON (len > pglen); - + if (len > buf->page_len) + len = buf-> page_len; tailbuf_len = buf->buflen - buf->head->iov_len - buf->page_len; /* Shift the tail first */ diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 41df4c507193..1aafe8d3f3f4 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -205,20 +205,20 @@ int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task) if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) { if (task == xprt->snd_task) - return 1; + goto out_locked; goto out_sleep; } if (test_bit(XPRT_WRITE_SPACE, &xprt->state)) goto out_unlock; xprt->snd_task = task; +out_locked: + trace_xprt_reserve_xprt(xprt, task); return 1; out_unlock: xprt_clear_locked(xprt); out_sleep: - dprintk("RPC: %5u failed to lock transport %p\n", - task->tk_pid, xprt); task->tk_status = -EAGAIN; if (RPC_IS_SOFT(task)) rpc_sleep_on_timeout(&xprt->sending, task, NULL, @@ -269,23 +269,22 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) { if (task == xprt->snd_task) - return 1; + goto out_locked; goto out_sleep; } if (req == NULL) { xprt->snd_task = task; - return 1; + goto out_locked; } if (test_bit(XPRT_WRITE_SPACE, &xprt->state)) goto out_unlock; if (!xprt_need_congestion_window_wait(xprt)) { xprt->snd_task = task; - return 1; + goto out_locked; } out_unlock: xprt_clear_locked(xprt); out_sleep: - dprintk("RPC: %5u failed to lock transport %p\n", task->tk_pid, xprt); task->tk_status = -EAGAIN; if (RPC_IS_SOFT(task)) rpc_sleep_on_timeout(&xprt->sending, task, NULL, @@ -293,6 +292,9 @@ out_sleep: else rpc_sleep_on(&xprt->sending, task, NULL); return 0; +out_locked: + trace_xprt_reserve_cong(xprt, task); + return 1; } EXPORT_SYMBOL_GPL(xprt_reserve_xprt_cong); @@ -357,6 +359,7 @@ void xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task) xprt_clear_locked(xprt); __xprt_lock_write_next(xprt); } + trace_xprt_release_xprt(xprt, task); } EXPORT_SYMBOL_GPL(xprt_release_xprt); @@ -374,6 +377,7 @@ void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) xprt_clear_locked(xprt); __xprt_lock_write_next_cong(xprt); } + trace_xprt_release_cong(xprt, task); } EXPORT_SYMBOL_GPL(xprt_release_xprt_cong); @@ -395,8 +399,7 @@ __xprt_get_cong(struct rpc_xprt *xprt, struct rpc_rqst *req) { if (req->rq_cong) return 1; - dprintk("RPC: %5u xprt_cwnd_limited cong = %lu cwnd = %lu\n", - req->rq_task->tk_pid, xprt->cong, xprt->cwnd); + trace_xprt_get_cong(xprt, req->rq_task); if (RPCXPRT_CONGESTED(xprt)) { xprt_set_congestion_window_wait(xprt); return 0; @@ -418,6 +421,7 @@ __xprt_put_cong(struct rpc_xprt *xprt, struct rpc_rqst *req) req->rq_cong = 0; xprt->cong -= RPC_CWNDSCALE; xprt_test_and_clear_congestion_window_wait(xprt); + trace_xprt_put_cong(xprt, req->rq_task); __xprt_lock_write_next_cong(xprt); } diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index b458bf53ca69..9d02eae353c6 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -79,7 +79,7 @@ static int rpcrdma_bc_marshal_reply(struct rpc_rqst *rqst) *p = xdr_zero; if (rpcrdma_prepare_send_sges(r_xprt, req, RPCRDMA_HDRLEN_MIN, - &rqst->rq_snd_buf, rpcrdma_noch)) + &rqst->rq_snd_buf, rpcrdma_noch_pullup)) return -EIO; trace_xprtrdma_cb_reply(rqst); diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 30065a28628c..523722be6a16 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -36,8 +36,8 @@ * connect worker from running concurrently. * * When the underlying transport disconnects, MRs that are in flight - * are flushed and are likely unusable. Thus all flushed MRs are - * destroyed. New MRs are created on demand. + * are flushed and are likely unusable. Thus all MRs are destroyed. + * New MRs are created on demand. */ #include <linux/sunrpc/rpc_rdma.h> @@ -88,8 +88,10 @@ void frwr_release_mr(struct rpcrdma_mr *mr) kfree(mr); } -static void frwr_mr_recycle(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr) +static void frwr_mr_recycle(struct rpcrdma_mr *mr) { + struct rpcrdma_xprt *r_xprt = mr->mr_xprt; + trace_xprtrdma_mr_recycle(mr); if (mr->mr_dir != DMA_NONE) { @@ -107,32 +109,6 @@ static void frwr_mr_recycle(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr) frwr_release_mr(mr); } -/* MRs are dynamically allocated, so simply clean up and release the MR. - * A replacement MR will subsequently be allocated on demand. - */ -static void -frwr_mr_recycle_worker(struct work_struct *work) -{ - struct rpcrdma_mr *mr = container_of(work, struct rpcrdma_mr, - mr_recycle); - - frwr_mr_recycle(mr->mr_xprt, mr); -} - -/* frwr_recycle - Discard MRs - * @req: request to reset - * - * Used after a reconnect. These MRs could be in flight, we can't - * tell. Safe thing to do is release them. - */ -void frwr_recycle(struct rpcrdma_req *req) -{ - struct rpcrdma_mr *mr; - - while ((mr = rpcrdma_mr_pop(&req->rl_registered))) - frwr_mr_recycle(mr->mr_xprt, mr); -} - /* frwr_reset - Place MRs back on the free list * @req: request to reset * @@ -166,9 +142,6 @@ int frwr_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr) struct ib_mr *frmr; int rc; - /* NB: ib_alloc_mr and device drivers typically allocate - * memory with GFP_KERNEL. - */ frmr = ib_alloc_mr(ia->ri_pd, ia->ri_mrtype, depth); if (IS_ERR(frmr)) goto out_mr_err; @@ -180,7 +153,6 @@ int frwr_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr) mr->frwr.fr_mr = frmr; mr->mr_dir = DMA_NONE; INIT_LIST_HEAD(&mr->mr_list); - INIT_WORK(&mr->mr_recycle, frwr_mr_recycle_worker); init_completion(&mr->frwr.fr_linv_done); sg_init_table(sg, depth); @@ -424,7 +396,7 @@ int frwr_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req) struct ib_send_wr *post_wr; struct rpcrdma_mr *mr; - post_wr = &req->rl_sendctx->sc_wr; + post_wr = &req->rl_wr; list_for_each_entry(mr, &req->rl_registered, mr_list) { struct rpcrdma_frwr *frwr; @@ -440,9 +412,6 @@ int frwr_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req) post_wr = &frwr->fr_regwr.wr; } - /* If ib_post_send fails, the next ->send_request for - * @req will queue these MRs for recovery. - */ return ib_post_send(ia->ri_id->qp, post_wr, NULL); } @@ -468,7 +437,7 @@ void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs) static void __frwr_release_mr(struct ib_wc *wc, struct rpcrdma_mr *mr) { if (wc->status != IB_WC_SUCCESS) - rpcrdma_mr_recycle(mr); + frwr_mr_recycle(mr); else rpcrdma_mr_put(mr); } @@ -570,7 +539,6 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) */ bad_wr = NULL; rc = ib_post_send(r_xprt->rx_ia.ri_id->qp, first, &bad_wr); - trace_xprtrdma_post_send(req, rc); /* The final LOCAL_INV WR in the chain is supposed to * do the wake. If it was never posted, the wake will @@ -583,6 +551,7 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) /* Recycle MRs in the LOCAL_INV chain that did not get posted. */ + trace_xprtrdma_post_linv(req, rc); while (bad_wr) { frwr = container_of(bad_wr, struct rpcrdma_frwr, fr_invwr); @@ -590,7 +559,7 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) bad_wr = bad_wr->next; list_del_init(&mr->mr_list); - rpcrdma_mr_recycle(mr); + frwr_mr_recycle(mr); } } @@ -673,18 +642,18 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) */ bad_wr = NULL; rc = ib_post_send(r_xprt->rx_ia.ri_id->qp, first, &bad_wr); - trace_xprtrdma_post_send(req, rc); if (!rc) return; /* Recycle MRs in the LOCAL_INV chain that did not get posted. */ + trace_xprtrdma_post_linv(req, rc); while (bad_wr) { frwr = container_of(bad_wr, struct rpcrdma_frwr, fr_invwr); mr = container_of(frwr, struct rpcrdma_mr, frwr); bad_wr = bad_wr->next; - rpcrdma_mr_recycle(mr); + frwr_mr_recycle(mr); } /* The final LOCAL_INV WR in the chain is supposed to diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index b86b5fd62d9f..aec3beb93b25 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -78,8 +78,6 @@ static unsigned int rpcrdma_max_call_header_size(unsigned int maxsegs) size += rpcrdma_segment_maxsz * sizeof(__be32); size += sizeof(__be32); /* list discriminator */ - dprintk("RPC: %s: max call header size = %u\n", - __func__, size); return size; } @@ -100,8 +98,6 @@ static unsigned int rpcrdma_max_reply_header_size(unsigned int maxsegs) size += maxsegs * rpcrdma_segment_maxsz * sizeof(__be32); size += sizeof(__be32); /* list discriminator */ - dprintk("RPC: %s: max reply header size = %u\n", - __func__, size); return size; } @@ -363,8 +359,7 @@ static struct rpcrdma_mr_seg *rpcrdma_mr_prepare(struct rpcrdma_xprt *r_xprt, out_getmr_err: trace_xprtrdma_nomrs(req); xprt_wait_for_buffer_space(&r_xprt->rx_xprt); - if (r_xprt->rx_ep.rep_connected != -ENODEV) - schedule_work(&r_xprt->rx_buf.rb_refresh_worker); + rpcrdma_mrs_refresh(r_xprt); return ERR_PTR(-EAGAIN); } @@ -393,7 +388,7 @@ static int rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, unsigned int pos; int nsegs; - if (rtype == rpcrdma_noch) + if (rtype == rpcrdma_noch_pullup || rtype == rpcrdma_noch_mapped) goto done; pos = rqst->rq_snd_buf.head[0].iov_len; @@ -565,6 +560,7 @@ static void rpcrdma_sendctx_done(struct kref *kref) */ void rpcrdma_sendctx_unmap(struct rpcrdma_sendctx *sc) { + struct rpcrdma_regbuf *rb = sc->sc_req->rl_sendbuf; struct ib_sge *sge; if (!sc->sc_unmap_count) @@ -576,7 +572,7 @@ void rpcrdma_sendctx_unmap(struct rpcrdma_sendctx *sc) */ for (sge = &sc->sc_sges[2]; sc->sc_unmap_count; ++sge, --sc->sc_unmap_count) - ib_dma_unmap_page(sc->sc_device, sge->addr, sge->length, + ib_dma_unmap_page(rdmab_device(rb), sge->addr, sge->length, DMA_TO_DEVICE); kref_put(&sc->sc_req->rl_kref, rpcrdma_sendctx_done); @@ -589,149 +585,228 @@ static bool rpcrdma_prepare_hdr_sge(struct rpcrdma_xprt *r_xprt, { struct rpcrdma_sendctx *sc = req->rl_sendctx; struct rpcrdma_regbuf *rb = req->rl_rdmabuf; - struct ib_sge *sge = sc->sc_sges; + struct ib_sge *sge = &sc->sc_sges[req->rl_wr.num_sge++]; if (!rpcrdma_regbuf_dma_map(r_xprt, rb)) - goto out_regbuf; + return false; sge->addr = rdmab_addr(rb); sge->length = len; sge->lkey = rdmab_lkey(rb); ib_dma_sync_single_for_device(rdmab_device(rb), sge->addr, sge->length, DMA_TO_DEVICE); - sc->sc_wr.num_sge++; return true; - -out_regbuf: - pr_err("rpcrdma: failed to DMA map a Send buffer\n"); - return false; } -/* Prepare the Send SGEs. The head and tail iovec, and each entry - * in the page list, gets its own SGE. +/* The head iovec is straightforward, as it is usually already + * DMA-mapped. Sync the content that has changed. */ -static bool rpcrdma_prepare_msg_sges(struct rpcrdma_xprt *r_xprt, - struct rpcrdma_req *req, - struct xdr_buf *xdr, - enum rpcrdma_chunktype rtype) +static bool rpcrdma_prepare_head_iov(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, unsigned int len) { struct rpcrdma_sendctx *sc = req->rl_sendctx; - unsigned int sge_no, page_base, len, remaining; + struct ib_sge *sge = &sc->sc_sges[req->rl_wr.num_sge++]; struct rpcrdma_regbuf *rb = req->rl_sendbuf; - struct ib_sge *sge = sc->sc_sges; - struct page *page, **ppages; - /* The head iovec is straightforward, as it is already - * DMA-mapped. Sync the content that has changed. - */ if (!rpcrdma_regbuf_dma_map(r_xprt, rb)) - goto out_regbuf; - sc->sc_device = rdmab_device(rb); - sge_no = 1; - sge[sge_no].addr = rdmab_addr(rb); - sge[sge_no].length = xdr->head[0].iov_len; - sge[sge_no].lkey = rdmab_lkey(rb); - ib_dma_sync_single_for_device(rdmab_device(rb), sge[sge_no].addr, - sge[sge_no].length, DMA_TO_DEVICE); - - /* If there is a Read chunk, the page list is being handled - * via explicit RDMA, and thus is skipped here. However, the - * tail iovec may include an XDR pad for the page list, as - * well as additional content, and may not reside in the - * same page as the head iovec. - */ - if (rtype == rpcrdma_readch) { - len = xdr->tail[0].iov_len; + return false; - /* Do not include the tail if it is only an XDR pad */ - if (len < 4) - goto out; + sge->addr = rdmab_addr(rb); + sge->length = len; + sge->lkey = rdmab_lkey(rb); - page = virt_to_page(xdr->tail[0].iov_base); - page_base = offset_in_page(xdr->tail[0].iov_base); + ib_dma_sync_single_for_device(rdmab_device(rb), sge->addr, sge->length, + DMA_TO_DEVICE); + return true; +} - /* If the content in the page list is an odd length, - * xdr_write_pages() has added a pad at the beginning - * of the tail iovec. Force the tail's non-pad content - * to land at the next XDR position in the Send message. - */ - page_base += len & 3; - len -= len & 3; - goto map_tail; - } +/* If there is a page list present, DMA map and prepare an + * SGE for each page to be sent. + */ +static bool rpcrdma_prepare_pagelist(struct rpcrdma_req *req, + struct xdr_buf *xdr) +{ + struct rpcrdma_sendctx *sc = req->rl_sendctx; + struct rpcrdma_regbuf *rb = req->rl_sendbuf; + unsigned int page_base, len, remaining; + struct page **ppages; + struct ib_sge *sge; - /* If there is a page list present, temporarily DMA map - * and prepare an SGE for each page to be sent. - */ - if (xdr->page_len) { - ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT); - page_base = offset_in_page(xdr->page_base); - remaining = xdr->page_len; - while (remaining) { - sge_no++; - if (sge_no > RPCRDMA_MAX_SEND_SGES - 2) - goto out_mapping_overflow; - - len = min_t(u32, PAGE_SIZE - page_base, remaining); - sge[sge_no].addr = - ib_dma_map_page(rdmab_device(rb), *ppages, - page_base, len, DMA_TO_DEVICE); - if (ib_dma_mapping_error(rdmab_device(rb), - sge[sge_no].addr)) - goto out_mapping_err; - sge[sge_no].length = len; - sge[sge_no].lkey = rdmab_lkey(rb); - - sc->sc_unmap_count++; - ppages++; - remaining -= len; - page_base = 0; - } - } + ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT); + page_base = offset_in_page(xdr->page_base); + remaining = xdr->page_len; + while (remaining) { + sge = &sc->sc_sges[req->rl_wr.num_sge++]; + len = min_t(unsigned int, PAGE_SIZE - page_base, remaining); + sge->addr = ib_dma_map_page(rdmab_device(rb), *ppages, + page_base, len, DMA_TO_DEVICE); + if (ib_dma_mapping_error(rdmab_device(rb), sge->addr)) + goto out_mapping_err; - /* The tail iovec is not always constructed in the same - * page where the head iovec resides (see, for example, - * gss_wrap_req_priv). To neatly accommodate that case, - * DMA map it separately. - */ - if (xdr->tail[0].iov_len) { - page = virt_to_page(xdr->tail[0].iov_base); - page_base = offset_in_page(xdr->tail[0].iov_base); - len = xdr->tail[0].iov_len; + sge->length = len; + sge->lkey = rdmab_lkey(rb); -map_tail: - sge_no++; - sge[sge_no].addr = - ib_dma_map_page(rdmab_device(rb), page, page_base, len, - DMA_TO_DEVICE); - if (ib_dma_mapping_error(rdmab_device(rb), sge[sge_no].addr)) - goto out_mapping_err; - sge[sge_no].length = len; - sge[sge_no].lkey = rdmab_lkey(rb); sc->sc_unmap_count++; + ppages++; + remaining -= len; + page_base = 0; } -out: - sc->sc_wr.num_sge += sge_no; - if (sc->sc_unmap_count) - kref_get(&req->rl_kref); return true; -out_regbuf: - pr_err("rpcrdma: failed to DMA map a Send buffer\n"); +out_mapping_err: + trace_xprtrdma_dma_maperr(sge->addr); return false; +} -out_mapping_overflow: - rpcrdma_sendctx_unmap(sc); - pr_err("rpcrdma: too many Send SGEs (%u)\n", sge_no); - return false; +/* The tail iovec may include an XDR pad for the page list, + * as well as additional content, and may not reside in the + * same page as the head iovec. + */ +static bool rpcrdma_prepare_tail_iov(struct rpcrdma_req *req, + struct xdr_buf *xdr, + unsigned int page_base, unsigned int len) +{ + struct rpcrdma_sendctx *sc = req->rl_sendctx; + struct ib_sge *sge = &sc->sc_sges[req->rl_wr.num_sge++]; + struct rpcrdma_regbuf *rb = req->rl_sendbuf; + struct page *page = virt_to_page(xdr->tail[0].iov_base); + + sge->addr = ib_dma_map_page(rdmab_device(rb), page, page_base, len, + DMA_TO_DEVICE); + if (ib_dma_mapping_error(rdmab_device(rb), sge->addr)) + goto out_mapping_err; + + sge->length = len; + sge->lkey = rdmab_lkey(rb); + ++sc->sc_unmap_count; + return true; out_mapping_err: - rpcrdma_sendctx_unmap(sc); - trace_xprtrdma_dma_maperr(sge[sge_no].addr); + trace_xprtrdma_dma_maperr(sge->addr); return false; } +/* Copy the tail to the end of the head buffer. + */ +static void rpcrdma_pullup_tail_iov(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, + struct xdr_buf *xdr) +{ + unsigned char *dst; + + dst = (unsigned char *)xdr->head[0].iov_base; + dst += xdr->head[0].iov_len + xdr->page_len; + memmove(dst, xdr->tail[0].iov_base, xdr->tail[0].iov_len); + r_xprt->rx_stats.pullup_copy_count += xdr->tail[0].iov_len; +} + +/* Copy pagelist content into the head buffer. + */ +static void rpcrdma_pullup_pagelist(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, + struct xdr_buf *xdr) +{ + unsigned int len, page_base, remaining; + struct page **ppages; + unsigned char *src, *dst; + + dst = (unsigned char *)xdr->head[0].iov_base; + dst += xdr->head[0].iov_len; + ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT); + page_base = offset_in_page(xdr->page_base); + remaining = xdr->page_len; + while (remaining) { + src = page_address(*ppages); + src += page_base; + len = min_t(unsigned int, PAGE_SIZE - page_base, remaining); + memcpy(dst, src, len); + r_xprt->rx_stats.pullup_copy_count += len; + + ppages++; + dst += len; + remaining -= len; + page_base = 0; + } +} + +/* Copy the contents of @xdr into @rl_sendbuf and DMA sync it. + * When the head, pagelist, and tail are small, a pull-up copy + * is considerably less costly than DMA mapping the components + * of @xdr. + * + * Assumptions: + * - the caller has already verified that the total length + * of the RPC Call body will fit into @rl_sendbuf. + */ +static bool rpcrdma_prepare_noch_pullup(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, + struct xdr_buf *xdr) +{ + if (unlikely(xdr->tail[0].iov_len)) + rpcrdma_pullup_tail_iov(r_xprt, req, xdr); + + if (unlikely(xdr->page_len)) + rpcrdma_pullup_pagelist(r_xprt, req, xdr); + + /* The whole RPC message resides in the head iovec now */ + return rpcrdma_prepare_head_iov(r_xprt, req, xdr->len); +} + +static bool rpcrdma_prepare_noch_mapped(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, + struct xdr_buf *xdr) +{ + struct kvec *tail = &xdr->tail[0]; + + if (!rpcrdma_prepare_head_iov(r_xprt, req, xdr->head[0].iov_len)) + return false; + if (xdr->page_len) + if (!rpcrdma_prepare_pagelist(req, xdr)) + return false; + if (tail->iov_len) + if (!rpcrdma_prepare_tail_iov(req, xdr, + offset_in_page(tail->iov_base), + tail->iov_len)) + return false; + + if (req->rl_sendctx->sc_unmap_count) + kref_get(&req->rl_kref); + return true; +} + +static bool rpcrdma_prepare_readch(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, + struct xdr_buf *xdr) +{ + if (!rpcrdma_prepare_head_iov(r_xprt, req, xdr->head[0].iov_len)) + return false; + + /* If there is a Read chunk, the page list is being handled + * via explicit RDMA, and thus is skipped here. + */ + + /* Do not include the tail if it is only an XDR pad */ + if (xdr->tail[0].iov_len > 3) { + unsigned int page_base, len; + + /* If the content in the page list is an odd length, + * xdr_write_pages() adds a pad at the beginning of + * the tail iovec. Force the tail's non-pad content to + * land at the next XDR position in the Send message. + */ + page_base = offset_in_page(xdr->tail[0].iov_base); + len = xdr->tail[0].iov_len; + page_base += len & 3; + len -= len & 3; + if (!rpcrdma_prepare_tail_iov(req, xdr, page_base, len)) + return false; + kref_get(&req->rl_kref); + } + + return true; +} + /** * rpcrdma_prepare_send_sges - Construct SGEs for a Send WR * @r_xprt: controlling transport @@ -742,31 +817,53 @@ out_mapping_err: * * Returns 0 on success; otherwise a negative errno is returned. */ -int -rpcrdma_prepare_send_sges(struct rpcrdma_xprt *r_xprt, - struct rpcrdma_req *req, u32 hdrlen, - struct xdr_buf *xdr, enum rpcrdma_chunktype rtype) +inline int rpcrdma_prepare_send_sges(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, u32 hdrlen, + struct xdr_buf *xdr, + enum rpcrdma_chunktype rtype) { int ret; ret = -EAGAIN; req->rl_sendctx = rpcrdma_sendctx_get_locked(r_xprt); if (!req->rl_sendctx) - goto err; - req->rl_sendctx->sc_wr.num_sge = 0; + goto out_nosc; req->rl_sendctx->sc_unmap_count = 0; req->rl_sendctx->sc_req = req; kref_init(&req->rl_kref); + req->rl_wr.wr_cqe = &req->rl_sendctx->sc_cqe; + req->rl_wr.sg_list = req->rl_sendctx->sc_sges; + req->rl_wr.num_sge = 0; + req->rl_wr.opcode = IB_WR_SEND; ret = -EIO; if (!rpcrdma_prepare_hdr_sge(r_xprt, req, hdrlen)) - goto err; - if (rtype != rpcrdma_areadch) - if (!rpcrdma_prepare_msg_sges(r_xprt, req, xdr, rtype)) - goto err; + goto out_unmap; + + switch (rtype) { + case rpcrdma_noch_pullup: + if (!rpcrdma_prepare_noch_pullup(r_xprt, req, xdr)) + goto out_unmap; + break; + case rpcrdma_noch_mapped: + if (!rpcrdma_prepare_noch_mapped(r_xprt, req, xdr)) + goto out_unmap; + break; + case rpcrdma_readch: + if (!rpcrdma_prepare_readch(r_xprt, req, xdr)) + goto out_unmap; + break; + case rpcrdma_areadch: + break; + default: + goto out_unmap; + } + return 0; -err: +out_unmap: + rpcrdma_sendctx_unmap(req->rl_sendctx); +out_nosc: trace_xprtrdma_prepsend_failed(&req->rl_slot, ret); return ret; } @@ -796,6 +893,7 @@ rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst) struct rpcrdma_req *req = rpcr_to_rdmar(rqst); struct xdr_stream *xdr = &req->rl_stream; enum rpcrdma_chunktype rtype, wtype; + struct xdr_buf *buf = &rqst->rq_snd_buf; bool ddp_allowed; __be32 *p; int ret; @@ -853,8 +951,9 @@ rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst) */ if (rpcrdma_args_inline(r_xprt, rqst)) { *p++ = rdma_msg; - rtype = rpcrdma_noch; - } else if (ddp_allowed && rqst->rq_snd_buf.flags & XDRBUF_WRITE) { + rtype = buf->len < rdmab_length(req->rl_sendbuf) ? + rpcrdma_noch_pullup : rpcrdma_noch_mapped; + } else if (ddp_allowed && buf->flags & XDRBUF_WRITE) { *p++ = rdma_msg; rtype = rpcrdma_readch; } else { @@ -863,12 +962,6 @@ rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst) rtype = rpcrdma_areadch; } - /* If this is a retransmit, discard previously registered - * chunks. Very likely the connection has been replaced, - * so these registrations are invalid and unusable. - */ - frwr_recycle(req); - /* This implementation supports the following combinations * of chunk lists in one RPC-over-RDMA Call message: * @@ -902,7 +995,7 @@ rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst) goto out_err; ret = rpcrdma_prepare_send_sges(r_xprt, req, req->rl_hdrbuf.len, - &rqst->rq_snd_buf, rtype); + buf, rtype); if (ret) goto out_err; @@ -916,6 +1009,40 @@ out_err: return ret; } +static void __rpcrdma_update_cwnd_locked(struct rpc_xprt *xprt, + struct rpcrdma_buffer *buf, + u32 grant) +{ + buf->rb_credits = grant; + xprt->cwnd = grant << RPC_CWNDSHIFT; +} + +static void rpcrdma_update_cwnd(struct rpcrdma_xprt *r_xprt, u32 grant) +{ + struct rpc_xprt *xprt = &r_xprt->rx_xprt; + + spin_lock(&xprt->transport_lock); + __rpcrdma_update_cwnd_locked(xprt, &r_xprt->rx_buf, grant); + spin_unlock(&xprt->transport_lock); +} + +/** + * rpcrdma_reset_cwnd - Reset the xprt's congestion window + * @r_xprt: controlling transport instance + * + * Prepare @r_xprt for the next connection by reinitializing + * its credit grant to one (see RFC 8166, Section 3.3.3). + */ +void rpcrdma_reset_cwnd(struct rpcrdma_xprt *r_xprt) +{ + struct rpc_xprt *xprt = &r_xprt->rx_xprt; + + spin_lock(&xprt->transport_lock); + xprt->cong = 0; + __rpcrdma_update_cwnd_locked(xprt, &r_xprt->rx_buf, 1); + spin_unlock(&xprt->transport_lock); +} + /** * rpcrdma_inline_fixup - Scatter inline received data into rqst's iovecs * @rqst: controlling RPC request @@ -955,7 +1082,6 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) curlen = rqst->rq_rcv_buf.head[0].iov_len; if (curlen > copy_len) curlen = copy_len; - trace_xprtrdma_fixup(rqst, copy_len, curlen); srcp += curlen; copy_len -= curlen; @@ -975,8 +1101,6 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) if (curlen > pagelist_len) curlen = pagelist_len; - trace_xprtrdma_fixup_pg(rqst, i, srcp, - copy_len, curlen); destp = kmap_atomic(ppages[i]); memcpy(destp + page_base, srcp, curlen); flush_dcache_page(ppages[i]); @@ -1008,6 +1132,8 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) rqst->rq_private_buf.tail[0].iov_base = srcp; } + if (fixup_copy_count) + trace_xprtrdma_fixup(rqst, fixup_copy_count); return fixup_copy_count; } @@ -1356,12 +1482,9 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) credits = 1; /* don't deadlock */ else if (credits > buf->rb_max_requests) credits = buf->rb_max_requests; - if (buf->rb_credits != credits) { - spin_lock(&xprt->transport_lock); - buf->rb_credits = credits; - xprt->cwnd = credits << RPC_CWNDSHIFT; - spin_unlock(&xprt->transport_lock); - } + if (buf->rb_credits != credits) + rpcrdma_update_cwnd(r_xprt, credits); + rpcrdma_post_recvs(r_xprt, false); req = rpcr_to_rdmar(rqst); if (req->rl_reply) { diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index d1fcc41d5eb5..908e78bb87c6 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -195,6 +195,7 @@ rpcrdma_bc_send_request(struct svcxprt_rdma *rdma, struct rpc_rqst *rqst) pr_info("%s: %*ph\n", __func__, 64, rqst->rq_buffer); #endif + rqst->rq_xtime = ktime_get(); rc = svc_rdma_bc_sendto(rdma, rqst, ctxt); if (rc) { svc_rdma_send_ctxt_put(rdma, ctxt); diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 6fdba72f89f4..f3f108090aa4 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -233,11 +233,15 @@ void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma, /* The first SGE contains the transport header, which * remains mapped until @ctxt is destroyed. */ - for (i = 1; i < ctxt->sc_send_wr.num_sge; i++) + for (i = 1; i < ctxt->sc_send_wr.num_sge; i++) { ib_dma_unmap_page(device, ctxt->sc_sges[i].addr, ctxt->sc_sges[i].length, DMA_TO_DEVICE); + trace_svcrdma_dma_unmap_page(rdma, + ctxt->sc_sges[i].addr, + ctxt->sc_sges[i].length); + } for (i = 0; i < ctxt->sc_page_count; ++i) put_page(ctxt->sc_pages[i]); @@ -490,6 +494,7 @@ static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma, dma_addr_t dma_addr; dma_addr = ib_dma_map_page(dev, page, offset, len, DMA_TO_DEVICE); + trace_svcrdma_dma_map_page(rdma, dma_addr, len); if (ib_dma_mapping_error(dev, dma_addr)) goto out_maperr; @@ -499,7 +504,6 @@ static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma, return 0; out_maperr: - trace_svcrdma_dma_map_page(rdma, page); return -EIO; } diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 160558b4135e..7395eb2cfdeb 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -243,16 +243,13 @@ xprt_rdma_connect_worker(struct work_struct *work) rc = rpcrdma_ep_connect(&r_xprt->rx_ep, &r_xprt->rx_ia); xprt_clear_connecting(xprt); if (r_xprt->rx_ep.rep_connected > 0) { - if (!xprt_test_and_set_connected(xprt)) { - xprt->stat.connect_count++; - xprt->stat.connect_time += (long)jiffies - - xprt->stat.connect_start; - xprt_wake_pending_tasks(xprt, -EAGAIN); - } - } else { - if (xprt_test_and_clear_connected(xprt)) - xprt_wake_pending_tasks(xprt, rc); + xprt->stat.connect_count++; + xprt->stat.connect_time += (long)jiffies - + xprt->stat.connect_start; + xprt_set_connected(xprt); + rc = -EAGAIN; } + xprt_wake_pending_tasks(xprt, rc); } /** @@ -425,12 +422,6 @@ void xprt_rdma_close(struct rpc_xprt *xprt) return; rpcrdma_ep_disconnect(ep, ia); - /* Prepare @xprt for the next connection by reinitializing - * its credit grant to one (see RFC 8166, Section 3.3.3). - */ - r_xprt->rx_buf.rb_credits = 1; - xprt->cwnd = RPC_CWNDSHIFT; - out: xprt->reestablish_timeout = 0; ++xprt->connect_cookie; @@ -450,12 +441,6 @@ xprt_rdma_set_port(struct rpc_xprt *xprt, u16 port) struct sockaddr *sap = (struct sockaddr *)&xprt->addr; char buf[8]; - dprintk("RPC: %s: setting port for xprt %p (%s:%s) to %u\n", - __func__, xprt, - xprt->address_strings[RPC_DISPLAY_ADDR], - xprt->address_strings[RPC_DISPLAY_PORT], - port); - rpc_set_port(sap, port); kfree(xprt->address_strings[RPC_DISPLAY_PORT]); @@ -465,6 +450,9 @@ xprt_rdma_set_port(struct rpc_xprt *xprt, u16 port) kfree(xprt->address_strings[RPC_DISPLAY_HEX_PORT]); snprintf(buf, sizeof(buf), "%4hx", port); xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); + + trace_xprtrdma_op_setport(container_of(xprt, struct rpcrdma_xprt, + rx_xprt)); } /** @@ -536,13 +524,12 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task) struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); unsigned long delay; - trace_xprtrdma_op_connect(r_xprt); - delay = 0; if (r_xprt->rx_ep.rep_connected != 0) { delay = xprt_reconnect_delay(xprt); xprt_reconnect_backoff(xprt, RPCRDMA_INIT_REEST_TO); } + trace_xprtrdma_op_connect(r_xprt, delay); queue_delayed_work(xprtiod_workqueue, &r_xprt->rx_connect_worker, delay); } diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 3a907537e2cf..77c7dd7f05e8 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -74,17 +74,17 @@ /* * internal functions */ -static void rpcrdma_sendctx_put_locked(struct rpcrdma_sendctx *sc); +static void rpcrdma_sendctx_put_locked(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_sendctx *sc); +static void rpcrdma_reqs_reset(struct rpcrdma_xprt *r_xprt); static void rpcrdma_reps_destroy(struct rpcrdma_buffer *buf); static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt); -static void rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf); -static void rpcrdma_mr_free(struct rpcrdma_mr *mr); +static void rpcrdma_mrs_destroy(struct rpcrdma_xprt *r_xprt); static struct rpcrdma_regbuf * rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction, gfp_t flags); static void rpcrdma_regbuf_dma_unmap(struct rpcrdma_regbuf *rb); static void rpcrdma_regbuf_free(struct rpcrdma_regbuf *rb); -static void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp); /* Wait for outstanding transport work to finish. ib_drain_qp * handles the drains in the wrong order for us, so open code @@ -125,7 +125,7 @@ rpcrdma_qp_event_handler(struct ib_event *event, void *context) /** * rpcrdma_wc_send - Invoked by RDMA provider for each polled Send WC - * @cq: completion queue (ignored) + * @cq: completion queue * @wc: completed WR * */ @@ -138,7 +138,7 @@ rpcrdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) /* WARNING: Only wr_cqe and status are reliable at this point */ trace_xprtrdma_wc_send(sc, wc); - rpcrdma_sendctx_put_locked(sc); + rpcrdma_sendctx_put_locked((struct rpcrdma_xprt *)cq->cq_context, sc); } /** @@ -170,7 +170,6 @@ rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) rdmab_addr(rep->rr_rdmabuf), wc->byte_len, DMA_FROM_DEVICE); - rpcrdma_post_recvs(r_xprt, false); rpcrdma_reply_handler(rep); return; @@ -178,11 +177,11 @@ out_flushed: rpcrdma_recv_buffer_put(rep); } -static void -rpcrdma_update_connect_private(struct rpcrdma_xprt *r_xprt, - struct rdma_conn_param *param) +static void rpcrdma_update_cm_private(struct rpcrdma_xprt *r_xprt, + struct rdma_conn_param *param) { const struct rpcrdma_connect_private *pmsg = param->private_data; + struct rpcrdma_ep *ep = &r_xprt->rx_ep; unsigned int rsize, wsize; /* Default settings for RPC-over-RDMA Version One */ @@ -198,13 +197,11 @@ rpcrdma_update_connect_private(struct rpcrdma_xprt *r_xprt, wsize = rpcrdma_decode_buffer_size(pmsg->cp_recv_size); } - if (rsize < r_xprt->rx_ep.rep_inline_recv) - r_xprt->rx_ep.rep_inline_recv = rsize; - if (wsize < r_xprt->rx_ep.rep_inline_send) - r_xprt->rx_ep.rep_inline_send = wsize; - dprintk("RPC: %s: max send %u, max recv %u\n", __func__, - r_xprt->rx_ep.rep_inline_send, - r_xprt->rx_ep.rep_inline_recv); + if (rsize < ep->rep_inline_recv) + ep->rep_inline_recv = rsize; + if (wsize < ep->rep_inline_send) + ep->rep_inline_send = wsize; + rpcrdma_set_max_header_sizes(r_xprt); } @@ -258,7 +255,8 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) case RDMA_CM_EVENT_ESTABLISHED: ++xprt->connect_cookie; ep->rep_connected = 1; - rpcrdma_update_connect_private(r_xprt, &event->param.conn); + rpcrdma_update_cm_private(r_xprt, &event->param.conn); + trace_xprtrdma_inline_thresh(r_xprt); wake_up_all(&ep->rep_connect_wait); break; case RDMA_CM_EVENT_CONNECT_ERROR: @@ -298,8 +296,6 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia) struct rdma_cm_id *id; int rc; - trace_xprtrdma_conn_start(xprt); - init_completion(&ia->ri_done); init_completion(&ia->ri_remove_done); @@ -315,10 +311,8 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia) if (rc) goto out; rc = wait_for_completion_interruptible_timeout(&ia->ri_done, wtimeout); - if (rc < 0) { - trace_xprtrdma_conn_tout(xprt); + if (rc < 0) goto out; - } rc = ia->ri_async_rc; if (rc) @@ -329,10 +323,8 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia) if (rc) goto out; rc = wait_for_completion_interruptible_timeout(&ia->ri_done, wtimeout); - if (rc < 0) { - trace_xprtrdma_conn_tout(xprt); + if (rc < 0) goto out; - } rc = ia->ri_async_rc; if (rc) goto out; @@ -409,8 +401,6 @@ rpcrdma_ia_remove(struct rpcrdma_ia *ia) struct rpcrdma_buffer *buf = &r_xprt->rx_buf; struct rpcrdma_req *req; - cancel_work_sync(&buf->rb_refresh_worker); - /* This is similar to rpcrdma_ep_destroy, but: * - Don't cancel the connect worker. * - Don't call rpcrdma_ep_disconnect, which waits @@ -437,7 +427,7 @@ rpcrdma_ia_remove(struct rpcrdma_ia *ia) rpcrdma_regbuf_dma_unmap(req->rl_sendbuf); rpcrdma_regbuf_dma_unmap(req->rl_recvbuf); } - rpcrdma_mrs_destroy(buf); + rpcrdma_mrs_destroy(r_xprt); ib_dealloc_pd(ia->ri_pd); ia->ri_pd = NULL; @@ -522,7 +512,7 @@ int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) init_waitqueue_head(&ep->rep_connect_wait); ep->rep_receive_count = 0; - sendcq = ib_alloc_cq_any(ia->ri_id->device, NULL, + sendcq = ib_alloc_cq_any(ia->ri_id->device, r_xprt, ep->rep_attr.cap.max_send_wr + 1, IB_POLL_WORKQUEUE); if (IS_ERR(sendcq)) { @@ -630,8 +620,6 @@ static int rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt, pr_err("rpcrdma: rdma_create_qp returned %d\n", err); goto out3; } - - rpcrdma_mrs_create(r_xprt); return 0; out3: @@ -649,8 +637,6 @@ static int rpcrdma_ep_reconnect(struct rpcrdma_xprt *r_xprt, struct rdma_cm_id *id, *old; int err, rc; - trace_xprtrdma_reconnect(r_xprt); - rpcrdma_ep_disconnect(&r_xprt->rx_ep, ia); rc = -EHOSTUNREACH; @@ -705,7 +691,6 @@ retry: memcpy(&qp_init_attr, &ep->rep_attr, sizeof(qp_init_attr)); switch (ep->rep_connected) { case 0: - dprintk("RPC: %s: connecting...\n", __func__); rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &qp_init_attr); if (rc) { rc = -ENETUNREACH; @@ -726,6 +711,7 @@ retry: ep->rep_connected = 0; xprt_clear_connected(xprt); + rpcrdma_reset_cwnd(r_xprt); rpcrdma_post_recvs(r_xprt, true); rc = rdma_connect(ia->ri_id, &ep->rep_remote_cma); @@ -742,13 +728,14 @@ retry: goto out; } - dprintk("RPC: %s: connected\n", __func__); + rpcrdma_mrs_create(r_xprt); out: if (rc) ep->rep_connected = rc; out_noupdate: + trace_xprtrdma_connect(r_xprt, rc); return rc; } @@ -757,11 +744,8 @@ out_noupdate: * @ep: endpoint to disconnect * @ia: associated interface adapter * - * This is separate from destroy to facilitate the ability - * to reconnect without recreating the endpoint. - * - * This call is not reentrant, and must not be made in parallel - * on the same endpoint. + * Caller serializes. Either the transport send lock is held, + * or we're being called to destroy the transport. */ void rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) @@ -780,6 +764,8 @@ rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) trace_xprtrdma_disconnect(r_xprt, rc); rpcrdma_xprt_drain(r_xprt); + rpcrdma_reqs_reset(r_xprt); + rpcrdma_mrs_destroy(r_xprt); } /* Fixed-size circular FIFO queue. This implementation is wait-free and @@ -817,9 +803,6 @@ static struct rpcrdma_sendctx *rpcrdma_sendctx_create(struct rpcrdma_ia *ia) if (!sc) return NULL; - sc->sc_wr.wr_cqe = &sc->sc_cqe; - sc->sc_wr.sg_list = sc->sc_sges; - sc->sc_wr.opcode = IB_WR_SEND; sc->sc_cqe.done = rpcrdma_wc_send; return sc; } @@ -847,7 +830,6 @@ static int rpcrdma_sendctxs_create(struct rpcrdma_xprt *r_xprt) if (!sc) return -ENOMEM; - sc->sc_xprt = r_xprt; buf->rb_sc_ctxs[i] = sc; } @@ -910,6 +892,7 @@ out_emptyq: /** * rpcrdma_sendctx_put_locked - Release a send context + * @r_xprt: controlling transport instance * @sc: send context to release * * Usage: Called from Send completion to return a sendctxt @@ -917,10 +900,10 @@ out_emptyq: * * The caller serializes calls to this function (per transport). */ -static void -rpcrdma_sendctx_put_locked(struct rpcrdma_sendctx *sc) +static void rpcrdma_sendctx_put_locked(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_sendctx *sc) { - struct rpcrdma_buffer *buf = &sc->sc_xprt->rx_buf; + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; unsigned long next_tail; /* Unmap SGEs of previously completed but unsignaled @@ -938,7 +921,7 @@ rpcrdma_sendctx_put_locked(struct rpcrdma_sendctx *sc) /* Paired with READ_ONCE */ smp_store_release(&buf->rb_sc_tail, next_tail); - xprt_write_space(&sc->sc_xprt->rx_xprt); + xprt_write_space(&r_xprt->rx_xprt); } static void @@ -965,7 +948,7 @@ rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt) mr->mr_xprt = r_xprt; spin_lock(&buf->rb_lock); - list_add(&mr->mr_list, &buf->rb_mrs); + rpcrdma_mr_push(mr, &buf->rb_mrs); list_add(&mr->mr_all, &buf->rb_all_mrs); spin_unlock(&buf->rb_lock); } @@ -987,6 +970,28 @@ rpcrdma_mr_refresh_worker(struct work_struct *work) } /** + * rpcrdma_mrs_refresh - Wake the MR refresh worker + * @r_xprt: controlling transport instance + * + */ +void rpcrdma_mrs_refresh(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpcrdma_ep *ep = &r_xprt->rx_ep; + + /* If there is no underlying device, it's no use to + * wake the refresh worker. + */ + if (ep->rep_connected != -ENODEV) { + /* The work is scheduled on a WQ_MEM_RECLAIM + * workqueue in order to prevent MR allocation + * from recursing into NFS during direct reclaim. + */ + queue_work(xprtiod_workqueue, &buf->rb_refresh_worker); + } +} + +/** * rpcrdma_req_create - Allocate an rpcrdma_req object * @r_xprt: controlling r_xprt * @size: initial size, in bytes, of send and receive buffers @@ -1042,6 +1047,26 @@ out1: return NULL; } +/** + * rpcrdma_reqs_reset - Reset all reqs owned by a transport + * @r_xprt: controlling transport instance + * + * ASSUMPTION: the rb_allreqs list is stable for the duration, + * and thus can be walked without holding rb_lock. Eg. the + * caller is holding the transport send lock to exclude + * device removal or disconnection. + */ +static void rpcrdma_reqs_reset(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpcrdma_req *req; + + list_for_each_entry(req, &buf->rb_allreqs, rl_all) { + /* Credits are valid only for one connection */ + req->rl_slot.rq_cong = 0; + } +} + static struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, bool temp) { @@ -1125,8 +1150,6 @@ int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) INIT_LIST_HEAD(&buf->rb_all_mrs); INIT_WORK(&buf->rb_refresh_worker, rpcrdma_mr_refresh_worker); - rpcrdma_mrs_create(r_xprt); - INIT_LIST_HEAD(&buf->rb_send_bufs); INIT_LIST_HEAD(&buf->rb_allreqs); @@ -1134,14 +1157,13 @@ int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) for (i = 0; i < buf->rb_max_requests; i++) { struct rpcrdma_req *req; - req = rpcrdma_req_create(r_xprt, RPCRDMA_V1_DEF_INLINE_SIZE, + req = rpcrdma_req_create(r_xprt, RPCRDMA_V1_DEF_INLINE_SIZE * 2, GFP_KERNEL); if (!req) goto out; list_add(&req->rl_list, &buf->rb_send_bufs); } - buf->rb_credits = 1; init_llist_head(&buf->rb_free_reps); rc = rpcrdma_sendctxs_create(r_xprt); @@ -1158,15 +1180,24 @@ out: * rpcrdma_req_destroy - Destroy an rpcrdma_req object * @req: unused object to be destroyed * - * This function assumes that the caller prevents concurrent device - * unload and transport tear-down. + * Relies on caller holding the transport send lock to protect + * removing req->rl_all from buf->rb_all_reqs safely. */ void rpcrdma_req_destroy(struct rpcrdma_req *req) { + struct rpcrdma_mr *mr; + list_del(&req->rl_all); - while (!list_empty(&req->rl_free_mrs)) - rpcrdma_mr_free(rpcrdma_mr_pop(&req->rl_free_mrs)); + while ((mr = rpcrdma_mr_pop(&req->rl_free_mrs))) { + struct rpcrdma_buffer *buf = &mr->mr_xprt->rx_buf; + + spin_lock(&buf->rb_lock); + list_del(&mr->mr_all); + spin_unlock(&buf->rb_lock); + + frwr_release_mr(mr); + } rpcrdma_regbuf_free(req->rl_recvbuf); rpcrdma_regbuf_free(req->rl_sendbuf); @@ -1174,28 +1205,33 @@ void rpcrdma_req_destroy(struct rpcrdma_req *req) kfree(req); } -static void -rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf) +/** + * rpcrdma_mrs_destroy - Release all of a transport's MRs + * @r_xprt: controlling transport instance + * + * Relies on caller holding the transport send lock to protect + * removing mr->mr_list from req->rl_free_mrs safely. + */ +static void rpcrdma_mrs_destroy(struct rpcrdma_xprt *r_xprt) { - struct rpcrdma_xprt *r_xprt = container_of(buf, struct rpcrdma_xprt, - rx_buf); + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; struct rpcrdma_mr *mr; - unsigned int count; - count = 0; + cancel_work_sync(&buf->rb_refresh_worker); + spin_lock(&buf->rb_lock); while ((mr = list_first_entry_or_null(&buf->rb_all_mrs, struct rpcrdma_mr, mr_all)) != NULL) { + list_del(&mr->mr_list); list_del(&mr->mr_all); spin_unlock(&buf->rb_lock); frwr_release_mr(mr); - count++; + spin_lock(&buf->rb_lock); } spin_unlock(&buf->rb_lock); - r_xprt->rx_stats.mrs_allocated = 0; } /** @@ -1209,8 +1245,6 @@ rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf) void rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) { - cancel_work_sync(&buf->rb_refresh_worker); - rpcrdma_sendctxs_destroy(buf); rpcrdma_reps_destroy(buf); @@ -1222,8 +1256,6 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) list_del(&req->rl_list); rpcrdma_req_destroy(req); } - - rpcrdma_mrs_destroy(buf); } /** @@ -1264,17 +1296,6 @@ void rpcrdma_mr_put(struct rpcrdma_mr *mr) rpcrdma_mr_push(mr, &mr->mr_req->rl_free_mrs); } -static void rpcrdma_mr_free(struct rpcrdma_mr *mr) -{ - struct rpcrdma_xprt *r_xprt = mr->mr_xprt; - struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - - mr->mr_req = NULL; - spin_lock(&buf->rb_lock); - rpcrdma_mr_push(mr, &buf->rb_mrs); - spin_unlock(&buf->rb_lock); -} - /** * rpcrdma_buffer_get - Get a request buffer * @buffers: Buffer pool from which to obtain a buffer @@ -1437,7 +1458,7 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct rpcrdma_req *req) { - struct ib_send_wr *send_wr = &req->rl_sendctx->sc_wr; + struct ib_send_wr *send_wr = &req->rl_wr; int rc; if (!ep->rep_send_count || kref_read(&req->rl_kref) > 1) { @@ -1455,8 +1476,13 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, return 0; } -static void -rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) +/** + * rpcrdma_post_recvs - Refill the Receive Queue + * @r_xprt: controlling transport instance + * @temp: mark Receive buffers to be deleted after use + * + */ +void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) { struct rpcrdma_buffer *buf = &r_xprt->rx_buf; struct rpcrdma_ep *ep = &r_xprt->rx_ep; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 65e6b0eb862e..5d15140a0266 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -218,12 +218,8 @@ enum { /* struct rpcrdma_sendctx - DMA mapped SGEs to unmap after Send completes */ struct rpcrdma_req; -struct rpcrdma_xprt; struct rpcrdma_sendctx { - struct ib_send_wr sc_wr; struct ib_cqe sc_cqe; - struct ib_device *sc_device; - struct rpcrdma_xprt *sc_xprt; struct rpcrdma_req *sc_req; unsigned int sc_unmap_count; struct ib_sge sc_sges[]; @@ -257,7 +253,6 @@ struct rpcrdma_mr { u32 mr_handle; u32 mr_length; u64 mr_offset; - struct work_struct mr_recycle; struct list_head mr_all; }; @@ -318,6 +313,7 @@ struct rpcrdma_req { struct rpcrdma_rep *rl_reply; struct xdr_stream rl_stream; struct xdr_buf rl_hdrbuf; + struct ib_send_wr rl_wr; struct rpcrdma_sendctx *rl_sendctx; struct rpcrdma_regbuf *rl_rdmabuf; /* xprt header */ struct rpcrdma_regbuf *rl_sendbuf; /* rq_snd_buf */ @@ -474,6 +470,7 @@ void rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *); int rpcrdma_ep_post(struct rpcrdma_ia *, struct rpcrdma_ep *, struct rpcrdma_req *); +void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp); /* * Buffer calls - xprtrdma/verbs.c @@ -487,12 +484,7 @@ struct rpcrdma_sendctx *rpcrdma_sendctx_get_locked(struct rpcrdma_xprt *r_xprt); struct rpcrdma_mr *rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt); void rpcrdma_mr_put(struct rpcrdma_mr *mr); - -static inline void -rpcrdma_mr_recycle(struct rpcrdma_mr *mr) -{ - schedule_work(&mr->mr_recycle); -} +void rpcrdma_mrs_refresh(struct rpcrdma_xprt *r_xprt); struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *); void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, @@ -542,7 +534,6 @@ rpcrdma_data_dir(bool writing) /* Memory registration calls xprtrdma/frwr_ops.c */ bool frwr_is_supported(struct ib_device *device); -void frwr_recycle(struct rpcrdma_req *req); void frwr_reset(struct rpcrdma_req *req); int frwr_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep); int frwr_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr); @@ -563,6 +554,8 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req); enum rpcrdma_chunktype { rpcrdma_noch = 0, + rpcrdma_noch_pullup, + rpcrdma_noch_mapped, rpcrdma_readch, rpcrdma_areadch, rpcrdma_writech, @@ -576,6 +569,7 @@ int rpcrdma_prepare_send_sges(struct rpcrdma_xprt *r_xprt, void rpcrdma_sendctx_unmap(struct rpcrdma_sendctx *sc); int rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst); void rpcrdma_set_max_header_sizes(struct rpcrdma_xprt *); +void rpcrdma_reset_cwnd(struct rpcrdma_xprt *r_xprt); void rpcrdma_complete_rqst(struct rpcrdma_rep *rep); void rpcrdma_reply_handler(struct rpcrdma_rep *rep); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 70e52f567b2a..d86c664ea6af 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1752,7 +1752,7 @@ static void xs_set_port(struct rpc_xprt *xprt, unsigned short port) static void xs_set_srcport(struct sock_xprt *transport, struct socket *sock) { - if (transport->srcport == 0) + if (transport->srcport == 0 && transport->xprt.reuseport) transport->srcport = xs_sock_getport(sock); } @@ -2659,6 +2659,8 @@ static int bc_sendto(struct rpc_rqst *req) .iov_len = sizeof(marker), }; + req->rq_xtime = ktime_get(); + len = kernel_sendmsg(transport->sock, &msg, &iov, 1, iov.iov_len); if (len != iov.iov_len) return -EAGAIN; @@ -2684,7 +2686,6 @@ static int bc_send_request(struct rpc_rqst *req) struct svc_xprt *xprt; int len; - dprintk("sending request with xid: %08x\n", ntohl(req->rq_xid)); /* * Get the server socket associated with this callback xprt */ diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 55aeba681cf4..656ebc79c64e 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -305,17 +305,17 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, * @skb: socket buffer to copy * @method: send method to be used * @dests: destination nodes for message. - * @cong_link_cnt: returns number of encountered congested destination links * Returns 0 if success, otherwise errno */ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, struct tipc_mc_method *method, - struct tipc_nlist *dests, - u16 *cong_link_cnt) + struct tipc_nlist *dests) { struct tipc_msg *hdr, *_hdr; struct sk_buff_head tmpq; struct sk_buff *_skb; + u16 cong_link_cnt; + int rc = 0; /* Is a cluster supporting with new capabilities ? */ if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL)) @@ -343,18 +343,19 @@ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, _hdr = buf_msg(_skb); msg_set_size(_hdr, MCAST_H_SIZE); msg_set_is_rcast(_hdr, !msg_is_rcast(hdr)); + msg_set_errcode(_hdr, TIPC_ERR_NO_PORT); __skb_queue_head_init(&tmpq); __skb_queue_tail(&tmpq, _skb); if (method->rcast) - tipc_bcast_xmit(net, &tmpq, cong_link_cnt); + rc = tipc_bcast_xmit(net, &tmpq, &cong_link_cnt); else - tipc_rcast_xmit(net, &tmpq, dests, cong_link_cnt); + rc = tipc_rcast_xmit(net, &tmpq, dests, &cong_link_cnt); /* This queue should normally be empty by now */ __skb_queue_purge(&tmpq); - return 0; + return rc; } /* tipc_mcast_xmit - deliver message to indicated destination nodes @@ -396,9 +397,14 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, msg_set_is_rcast(hdr, method->rcast); /* Switch method ? */ - if (rcast != method->rcast) - tipc_mcast_send_sync(net, skb, method, - dests, cong_link_cnt); + if (rcast != method->rcast) { + rc = tipc_mcast_send_sync(net, skb, method, dests); + if (unlikely(rc)) { + pr_err("Unable to send SYN: method %d, rc %d\n", + rcast, rc); + goto exit; + } + } if (method->rcast) rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt); diff --git a/net/tipc/core.c b/net/tipc/core.c index 7532a00ac73d..4f6dc74adf45 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -148,14 +148,6 @@ static int __init tipc_init(void) sysctl_tipc_rmem[1] = RCVBUF_DEF; sysctl_tipc_rmem[2] = RCVBUF_MAX; - err = tipc_netlink_start(); - if (err) - goto out_netlink; - - err = tipc_netlink_compat_start(); - if (err) - goto out_netlink_compat; - err = tipc_register_sysctl(); if (err) goto out_sysctl; @@ -180,8 +172,21 @@ static int __init tipc_init(void) if (err) goto out_bearer; + err = tipc_netlink_start(); + if (err) + goto out_netlink; + + err = tipc_netlink_compat_start(); + if (err) + goto out_netlink_compat; + pr_info("Started in single node mode\n"); return 0; + +out_netlink_compat: + tipc_netlink_stop(); +out_netlink: + tipc_bearer_cleanup(); out_bearer: unregister_pernet_subsys(&tipc_pernet_pre_exit_ops); out_register_pernet_subsys: @@ -193,23 +198,19 @@ out_socket: out_pernet: tipc_unregister_sysctl(); out_sysctl: - tipc_netlink_compat_stop(); -out_netlink_compat: - tipc_netlink_stop(); -out_netlink: pr_err("Unable to start in single node mode\n"); return err; } static void __exit tipc_exit(void) { + tipc_netlink_compat_stop(); + tipc_netlink_stop(); tipc_bearer_cleanup(); unregister_pernet_subsys(&tipc_pernet_pre_exit_ops); unregister_pernet_device(&tipc_topsrv_net_ops); tipc_socket_stop(); unregister_pernet_device(&tipc_net_ops); - tipc_netlink_stop(); - tipc_netlink_compat_stop(); tipc_unregister_sysctl(); pr_info("Deactivated\n"); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index b043e8c6397a..bfe43da127c0 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -194,6 +194,7 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, { struct tipc_net *tn = tipc_net(net); struct tipc_msg *hdr = buf_msg(skb); + u32 pnet_hash = msg_peer_net_hash(hdr); u16 caps = msg_node_capabilities(hdr); bool legacy = tn->legacy_addr_format; u32 sugg = msg_sugg_node_addr(hdr); @@ -242,9 +243,8 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, return; if (!tipc_in_scope(legacy, b->domain, src)) return; - tipc_node_check_dest(net, src, peer_id, b, caps, signature, - msg_peer_net_hash(hdr), &maddr, &respond, - &dupl_addr); + tipc_node_check_dest(net, src, peer_id, b, caps, signature, pnet_hash, + &maddr, &respond, &dupl_addr); if (dupl_addr) disc_dupl_alert(b, src, &maddr); if (!respond) diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 92d04dc2a44b..359b2bc888cf 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -36,6 +36,7 @@ #include <net/sock.h> #include <linux/list_sort.h> +#include <linux/rbtree_augmented.h> #include "core.h" #include "netlink.h" #include "name_table.h" @@ -51,6 +52,7 @@ * @lower: service range lower bound * @upper: service range upper bound * @tree_node: member of service range RB tree + * @max: largest 'upper' in this node subtree * @local_publ: list of identical publications made from this node * Used by closest_first lookup and multicast lookup algorithm * @all_publ: all publications identical to this one, whatever node and scope @@ -60,6 +62,7 @@ struct service_range { u32 lower; u32 upper; struct rb_node tree_node; + u32 max; struct list_head local_publ; struct list_head all_publ; }; @@ -84,6 +87,130 @@ struct tipc_service { struct rcu_head rcu; }; +#define service_range_upper(sr) ((sr)->upper) +RB_DECLARE_CALLBACKS_MAX(static, sr_callbacks, + struct service_range, tree_node, u32, max, + service_range_upper) + +#define service_range_entry(rbtree_node) \ + (container_of(rbtree_node, struct service_range, tree_node)) + +#define service_range_overlap(sr, start, end) \ + ((sr)->lower <= (end) && (sr)->upper >= (start)) + +/** + * service_range_foreach_match - iterate over tipc service rbtree for each + * range match + * @sr: the service range pointer as a loop cursor + * @sc: the pointer to tipc service which holds the service range rbtree + * @start, end: the range (end >= start) for matching + */ +#define service_range_foreach_match(sr, sc, start, end) \ + for (sr = service_range_match_first((sc)->ranges.rb_node, \ + start, \ + end); \ + sr; \ + sr = service_range_match_next(&(sr)->tree_node, \ + start, \ + end)) + +/** + * service_range_match_first - find first service range matching a range + * @n: the root node of service range rbtree for searching + * @start, end: the range (end >= start) for matching + * + * Return: the leftmost service range node in the rbtree that overlaps the + * specific range if any. Otherwise, returns NULL. + */ +static struct service_range *service_range_match_first(struct rb_node *n, + u32 start, u32 end) +{ + struct service_range *sr; + struct rb_node *l, *r; + + /* Non overlaps in tree at all? */ + if (!n || service_range_entry(n)->max < start) + return NULL; + + while (n) { + l = n->rb_left; + if (l && service_range_entry(l)->max >= start) { + /* A leftmost overlap range node must be one in the left + * subtree. If not, it has lower > end, then nodes on + * the right side cannot satisfy the condition either. + */ + n = l; + continue; + } + + /* No one in the left subtree can match, return if this node is + * an overlap i.e. leftmost. + */ + sr = service_range_entry(n); + if (service_range_overlap(sr, start, end)) + return sr; + + /* Ok, try to lookup on the right side */ + r = n->rb_right; + if (sr->lower <= end && + r && service_range_entry(r)->max >= start) { + n = r; + continue; + } + break; + } + + return NULL; +} + +/** + * service_range_match_next - find next service range matching a range + * @n: a node in service range rbtree from which the searching starts + * @start, end: the range (end >= start) for matching + * + * Return: the next service range node to the given node in the rbtree that + * overlaps the specific range if any. Otherwise, returns NULL. + */ +static struct service_range *service_range_match_next(struct rb_node *n, + u32 start, u32 end) +{ + struct service_range *sr; + struct rb_node *p, *r; + + while (n) { + r = n->rb_right; + if (r && service_range_entry(r)->max >= start) + /* A next overlap range node must be one in the right + * subtree. If not, it has lower > end, then any next + * successor (- an ancestor) of this node cannot + * satisfy the condition either. + */ + return service_range_match_first(r, start, end); + + /* No one in the right subtree can match, go up to find an + * ancestor of this node which is parent of a left-hand child. + */ + while ((p = rb_parent(n)) && n == p->rb_right) + n = p; + if (!p) + break; + + /* Return if this ancestor is an overlap */ + sr = service_range_entry(p); + if (service_range_overlap(sr, start, end)) + return sr; + + /* Ok, try to lookup more from this ancestor */ + if (sr->lower <= end) { + n = p; + continue; + } + break; + } + + return NULL; +} + static int hash(int x) { return x & (TIPC_NAMETBL_SIZE - 1); @@ -139,84 +266,51 @@ static struct tipc_service *tipc_service_create(u32 type, struct hlist_head *hd) return service; } -/** - * tipc_service_first_range - find first service range in tree matching instance - * - * Very time-critical, so binary search through range rb tree - */ -static struct service_range *tipc_service_first_range(struct tipc_service *sc, - u32 instance) -{ - struct rb_node *n = sc->ranges.rb_node; - struct service_range *sr; - - while (n) { - sr = container_of(n, struct service_range, tree_node); - if (sr->lower > instance) - n = n->rb_left; - else if (sr->upper < instance) - n = n->rb_right; - else - return sr; - } - return NULL; -} - /* tipc_service_find_range - find service range matching publication parameters */ static struct service_range *tipc_service_find_range(struct tipc_service *sc, u32 lower, u32 upper) { - struct rb_node *n = sc->ranges.rb_node; struct service_range *sr; - sr = tipc_service_first_range(sc, lower); - if (!sr) - return NULL; - - /* Look for exact match */ - for (n = &sr->tree_node; n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->upper == upper) - break; + service_range_foreach_match(sr, sc, lower, upper) { + /* Look for exact match */ + if (sr->lower == lower && sr->upper == upper) + return sr; } - if (!n || sr->lower != lower || sr->upper != upper) - return NULL; - return sr; + return NULL; } static struct service_range *tipc_service_create_range(struct tipc_service *sc, u32 lower, u32 upper) { struct rb_node **n, *parent = NULL; - struct service_range *sr, *tmp; + struct service_range *sr; n = &sc->ranges.rb_node; while (*n) { - tmp = container_of(*n, struct service_range, tree_node); parent = *n; - tmp = container_of(parent, struct service_range, tree_node); - if (lower < tmp->lower) - n = &(*n)->rb_left; - else if (lower > tmp->lower) - n = &(*n)->rb_right; - else if (upper < tmp->upper) - n = &(*n)->rb_left; - else if (upper > tmp->upper) - n = &(*n)->rb_right; + sr = service_range_entry(parent); + if (lower == sr->lower && upper == sr->upper) + return sr; + if (sr->max < upper) + sr->max = upper; + if (lower <= sr->lower) + n = &parent->rb_left; else - return tmp; + n = &parent->rb_right; } sr = kzalloc(sizeof(*sr), GFP_ATOMIC); if (!sr) return NULL; sr->lower = lower; sr->upper = upper; + sr->max = upper; INIT_LIST_HEAD(&sr->local_publ); INIT_LIST_HEAD(&sr->all_publ); rb_link_node(&sr->tree_node, parent, n); - rb_insert_color(&sr->tree_node, &sc->ranges); + rb_insert_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); return sr; } @@ -310,7 +404,6 @@ static void tipc_service_subscribe(struct tipc_service *service, struct list_head publ_list; struct service_range *sr; struct tipc_name_seq ns; - struct rb_node *n; u32 filter; ns.type = tipc_sub_read(sb, seq.type); @@ -325,13 +418,7 @@ static void tipc_service_subscribe(struct tipc_service *service, return; INIT_LIST_HEAD(&publ_list); - for (n = rb_first(&service->ranges); n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->lower > ns.upper) - break; - if (!tipc_sub_check_overlap(&ns, sr->lower, sr->upper)) - continue; - + service_range_foreach_match(sr, service, ns.lower, ns.upper) { first = NULL; list_for_each_entry(p, &sr->all_publ, all_publ) { if (filter & TIPC_SUB_PORTS) @@ -425,7 +512,7 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, /* Remove service range item if this was its last publication */ if (list_empty(&sr->all_publ)) { - rb_erase(&sr->tree_node, &sc->ranges); + rb_erase_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); kfree(sr); } @@ -473,34 +560,39 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *dnode) rcu_read_lock(); sc = tipc_service_find(net, type); if (unlikely(!sc)) - goto not_found; + goto exit; spin_lock_bh(&sc->lock); - sr = tipc_service_first_range(sc, instance); - if (unlikely(!sr)) - goto no_match; - - /* Select lookup algorithm: local, closest-first or round-robin */ - if (*dnode == self) { - list = &sr->local_publ; - if (list_empty(list)) - goto no_match; - p = list_first_entry(list, struct publication, local_publ); - list_move_tail(&p->local_publ, &sr->local_publ); - } else if (legacy && !*dnode && !list_empty(&sr->local_publ)) { - list = &sr->local_publ; - p = list_first_entry(list, struct publication, local_publ); - list_move_tail(&p->local_publ, &sr->local_publ); - } else { - list = &sr->all_publ; - p = list_first_entry(list, struct publication, all_publ); - list_move_tail(&p->all_publ, &sr->all_publ); + service_range_foreach_match(sr, sc, instance, instance) { + /* Select lookup algo: local, closest-first or round-robin */ + if (*dnode == self) { + list = &sr->local_publ; + if (list_empty(list)) + continue; + p = list_first_entry(list, struct publication, + local_publ); + list_move_tail(&p->local_publ, &sr->local_publ); + } else if (legacy && !*dnode && !list_empty(&sr->local_publ)) { + list = &sr->local_publ; + p = list_first_entry(list, struct publication, + local_publ); + list_move_tail(&p->local_publ, &sr->local_publ); + } else { + list = &sr->all_publ; + p = list_first_entry(list, struct publication, + all_publ); + list_move_tail(&p->all_publ, &sr->all_publ); + } + port = p->port; + node = p->node; + /* Todo: as for legacy, pick the first matching range only, a + * "true" round-robin will be performed as needed. + */ + break; } - port = p->port; - node = p->node; -no_match: spin_unlock_bh(&sc->lock); -not_found: + +exit: rcu_read_unlock(); *dnode = node; return port; @@ -523,7 +615,8 @@ bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 scope, spin_lock_bh(&sc->lock); - sr = tipc_service_first_range(sc, instance); + /* Todo: a full search i.e. service_range_foreach_match() instead? */ + sr = service_range_match_first(sc->ranges.rb_node, instance, instance); if (!sr) goto no_match; @@ -552,7 +645,6 @@ void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper, struct service_range *sr; struct tipc_service *sc; struct publication *p; - struct rb_node *n; rcu_read_lock(); sc = tipc_service_find(net, type); @@ -560,13 +652,7 @@ void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper, goto exit; spin_lock_bh(&sc->lock); - - for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->upper < lower) - continue; - if (sr->lower > upper) - break; + service_range_foreach_match(sr, sc, lower, upper) { list_for_each_entry(p, &sr->local_publ, local_publ) { if (p->scope == scope || (!exact && p->scope < scope)) tipc_dest_push(dports, 0, p->port); @@ -587,7 +673,6 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, struct service_range *sr; struct tipc_service *sc; struct publication *p; - struct rb_node *n; rcu_read_lock(); sc = tipc_service_find(net, type); @@ -595,13 +680,7 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, goto exit; spin_lock_bh(&sc->lock); - - for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->upper < lower) - continue; - if (sr->lower > upper) - break; + service_range_foreach_match(sr, sc, lower, upper) { list_for_each_entry(p, &sr->all_publ, all_publ) { tipc_nlist_add(nodes, p->node); } @@ -799,7 +878,7 @@ static void tipc_service_delete(struct net *net, struct tipc_service *sc) tipc_service_remove_publ(sr, p->node, p->key); kfree_rcu(p, rcu); } - rb_erase(&sr->tree_node, &sc->ranges); + rb_erase_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); kfree(sr); } hlist_del_init_rcu(&sc->service_list); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 41688da233ab..6552f986774c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1364,8 +1364,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) struct tipc_msg *hdr = &tsk->phdr; struct tipc_name_seq *seq; struct sk_buff_head pkts; - u32 dport, dnode = 0; - u32 type, inst; + u32 dport = 0, dnode = 0; + u32 type = 0, inst = 0; int mtu, rc; if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE)) @@ -1418,23 +1418,11 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) type = dest->addr.name.name.type; inst = dest->addr.name.name.instance; dnode = dest->addr.name.domain; - msg_set_type(hdr, TIPC_NAMED_MSG); - msg_set_hdr_sz(hdr, NAMED_H_SIZE); - msg_set_nametype(hdr, type); - msg_set_nameinst(hdr, inst); - msg_set_lookup_scope(hdr, tipc_node2scope(dnode)); dport = tipc_nametbl_translate(net, type, inst, &dnode); - msg_set_destnode(hdr, dnode); - msg_set_destport(hdr, dport); if (unlikely(!dport && !dnode)) return -EHOSTUNREACH; } else if (dest->addrtype == TIPC_ADDR_ID) { dnode = dest->addr.id.node; - msg_set_type(hdr, TIPC_DIRECT_MSG); - msg_set_lookup_scope(hdr, 0); - msg_set_destnode(hdr, dnode); - msg_set_destport(hdr, dest->addr.id.ref); - msg_set_hdr_sz(hdr, BASIC_H_SIZE); } else { return -EINVAL; } @@ -1445,6 +1433,22 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(rc)) return rc; + if (dest->addrtype == TIPC_ADDR_NAME) { + msg_set_type(hdr, TIPC_NAMED_MSG); + msg_set_hdr_sz(hdr, NAMED_H_SIZE); + msg_set_nametype(hdr, type); + msg_set_nameinst(hdr, inst); + msg_set_lookup_scope(hdr, tipc_node2scope(dnode)); + msg_set_destnode(hdr, dnode); + msg_set_destport(hdr, dport); + } else { /* TIPC_ADDR_ID */ + msg_set_type(hdr, TIPC_DIRECT_MSG); + msg_set_lookup_scope(hdr, 0); + msg_set_destnode(hdr, dnode); + msg_set_destport(hdr, dest->addr.id.ref); + msg_set_hdr_sz(hdr, BASIC_H_SIZE); + } + __skb_queue_head_init(&pkts); mtu = tipc_node_get_mtu(net, dnode, tsk->portid, false); rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 86aaa4d3e781..ed113735c019 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -195,10 +195,13 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb, .saddr = src->ipv6, .flowi6_proto = IPPROTO_UDP }; - err = ipv6_stub->ipv6_dst_lookup(net, ub->ubsock->sk, - &ndst, &fl6); - if (err) + ndst = ipv6_stub->ipv6_dst_lookup_flow(net, + ub->ubsock->sk, + &fl6, NULL); + if (IS_ERR(ndst)) { + err = PTR_ERR(ndst); goto tx_error; + } dst_cache_set_ip6(cache, ndst, &fl6.saddr); } ttl = ip6_dst_hoplimit(ndst); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 0683788bbef0..cd91ad812291 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -429,7 +429,7 @@ static int tls_push_data(struct sock *sk, if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST)) - return -ENOTSUPP; + return -EOPNOTSUPP; if (unlikely(sk->sk_err)) return -sk->sk_err; @@ -571,7 +571,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, lock_sock(sk); if (flags & MSG_OOB) { - rc = -ENOTSUPP; + rc = -EOPNOTSUPP; goto out; } @@ -1023,7 +1023,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) } if (!(netdev->features & NETIF_F_HW_TLS_TX)) { - rc = -ENOTSUPP; + rc = -EOPNOTSUPP; goto release_netdev; } @@ -1098,7 +1098,7 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) } if (!(netdev->features & NETIF_F_HW_TLS_RX)) { - rc = -ENOTSUPP; + rc = -EOPNOTSUPP; goto release_netdev; } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index b3da6c5ab999..dac24c7aa7d4 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -487,7 +487,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, /* check version */ if (crypto_info->version != TLS_1_2_VERSION && crypto_info->version != TLS_1_3_VERSION) { - rc = -ENOTSUPP; + rc = -EINVAL; goto err_crypto_info; } @@ -714,7 +714,7 @@ static int tls_init(struct sock *sk) * share the ulp context. */ if (sk->sk_state != TCP_ESTABLISHED) - return -ENOTSUPP; + return -ENOTCONN; /* allocate tls context */ write_lock_bh(&sk->sk_callback_lock); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 2b2d0bae14a9..c6803a82b769 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -905,7 +905,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) int ret = 0; if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) - return -ENOTSUPP; + return -EOPNOTSUPP; mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); @@ -1220,7 +1220,7 @@ int tls_sw_sendpage_locked(struct sock *sk, struct page *page, if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY | MSG_NO_SHARED_FRAGS)) - return -ENOTSUPP; + return -EOPNOTSUPP; return tls_sw_do_sendpage(sk, page, offset, size, flags); } @@ -1233,7 +1233,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY)) - return -ENOTSUPP; + return -EOPNOTSUPP; mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); @@ -1932,7 +1932,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, /* splice does not support reading control messages */ if (ctx->control != TLS_RECORD_TYPE_DATA) { - err = -ENOTSUPP; + err = -EINVAL; goto splice_read_end; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 7cfdce10de36..774babbee045 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2865,7 +2865,7 @@ static int __init af_unix_init(void) { int rc = -1; - BUILD_BUG_ON(sizeof(struct unix_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof_field(struct sk_buff, cb)); rc = proto_register(&unix_proto, 1); if (rc != 0) { diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index e5ea29c6bca7..6abec3fc81d1 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -34,6 +34,9 @@ virtio_transport_get_ops(struct vsock_sock *vsk) { const struct vsock_transport *t = vsock_core_get_transport(vsk); + if (WARN_ON(!t)) + return NULL; + return container_of(t, struct virtio_transport, transport); } @@ -161,15 +164,25 @@ void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt) } EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt); +/* This function can only be used on connecting/connected sockets, + * since a socket assigned to a transport is required. + * + * Do not use on listener sockets! + */ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, struct virtio_vsock_pkt_info *info) { u32 src_cid, src_port, dst_cid, dst_port; + const struct virtio_transport *t_ops; struct virtio_vsock_sock *vvs; struct virtio_vsock_pkt *pkt; u32 pkt_len = info->pkt_len; - src_cid = virtio_transport_get_ops(vsk)->transport.get_local_cid(); + t_ops = virtio_transport_get_ops(vsk); + if (unlikely(!t_ops)) + return -EFAULT; + + src_cid = t_ops->transport.get_local_cid(); src_port = vsk->local_addr.svm_port; if (!info->remote_cid) { dst_cid = vsk->remote_addr.svm_cid; @@ -202,7 +215,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, virtio_transport_inc_tx_pkt(vvs, pkt); - return virtio_transport_get_ops(vsk)->send_pkt(pkt); + return t_ops->send_pkt(pkt); } static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, @@ -1021,18 +1034,18 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, int ret; if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -EINVAL; } if (sk_acceptq_is_full(sk)) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -ENOMEM; } child = vsock_create_connected(sk); if (!child) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -ENOMEM; } @@ -1054,7 +1067,7 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, */ if (ret || vchild->transport != &t->transport) { release_sock(child); - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); sock_put(child); return ret; } diff --git a/net/wireless/core.c b/net/wireless/core.c index 350513744575..3e25229a059d 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1102,6 +1102,7 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync) #ifdef CONFIG_CFG80211_WEXT kzfree(wdev->wext.keys); + wdev->wext.keys = NULL; #endif /* only initialized if we have a netdev */ if (wdev->netdev) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index c34f7d077604..2efe44a34644 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -659,6 +659,12 @@ static int x25_release(struct socket *sock) sock_set_flag(sk, SOCK_DEAD); sock_set_flag(sk, SOCK_DESTROY); break; + + case X25_STATE_5: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25_disconnect(sk, 0, 0, 0); + __x25_destroy_socket(sk); + goto out; } sock_orphan(sk); @@ -1054,6 +1060,8 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, if (test_bit(X25_ACCPT_APPRV_FLAG, &makex25->flags)) { x25_write_internal(make, X25_CALL_ACCEPTED); makex25->state = X25_STATE_3; + } else { + makex25->state = X25_STATE_5; } /* diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index f97c43344e95..4d3bb46aaae0 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -382,6 +382,35 @@ out_clear: return 0; } +/* + * State machine for state 5, Call Accepted / Call Connected pending (X25_ACCPT_APPRV_FLAG). + * The handling of the timer(s) is in file x25_timer.c + * Handling of state 0 and connection release is in af_x25.c. + */ +static int x25_state5_machine(struct sock *sk, struct sk_buff *skb, int frametype) +{ + struct x25_sock *x25 = x25_sk(sk); + + switch (frametype) { + case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) { + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25->state = X25_STATE_2; + x25_start_t23timer(sk); + return 0; + } + + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); + x25_disconnect(sk, 0, skb->data[3], skb->data[4]); + break; + + default: + break; + } + + return 0; +} + /* Higher level upcall for a LAPB frame */ int x25_process_rx_frame(struct sock *sk, struct sk_buff *skb) { @@ -406,6 +435,9 @@ int x25_process_rx_frame(struct sock *sk, struct sk_buff *skb) case X25_STATE_4: queued = x25_state4_machine(sk, skb, frametype); break; + case X25_STATE_5: + queued = x25_state5_machine(sk, skb, frametype); + break; } x25_kick(sk); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 956793893c9d..328f661b83b2 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -334,12 +334,21 @@ out: } EXPORT_SYMBOL(xsk_umem_consume_tx); -static int xsk_zc_xmit(struct xdp_sock *xs) +static int xsk_wakeup(struct xdp_sock *xs, u8 flags) { struct net_device *dev = xs->dev; + int err; + + rcu_read_lock(); + err = dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags); + rcu_read_unlock(); + + return err; +} - return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, - XDP_WAKEUP_TX); +static int xsk_zc_xmit(struct xdp_sock *xs) +{ + return xsk_wakeup(xs, XDP_WAKEUP_TX); } static void xsk_destruct_skb(struct sk_buff *skb) @@ -453,19 +462,16 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); - struct net_device *dev; struct xdp_umem *umem; if (unlikely(!xsk_is_bound(xs))) return mask; - dev = xs->dev; umem = xs->umem; if (umem->need_wakeup) { - if (dev->netdev_ops->ndo_xsk_wakeup) - dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, - umem->need_wakeup); + if (xs->zc) + xsk_wakeup(xs, umem->need_wakeup); else /* Poll needs to drive Tx also in copy mode */ __xsk_sendmsg(sk); |