diff options
Diffstat (limited to 'net')
66 files changed, 1146 insertions, 329 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 9ee5787634e5..953b6728bd00 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -626,11 +626,18 @@ static netdev_features_t vlan_dev_fix_features(struct net_device *dev, { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; netdev_features_t old_features = features; + netdev_features_t lower_features; - features = netdev_intersect_features(features, real_dev->vlan_features); - features |= NETIF_F_RXCSUM; - features = netdev_intersect_features(features, real_dev->features); + lower_features = netdev_intersect_features((real_dev->vlan_features | + NETIF_F_RXCSUM), + real_dev->features); + /* Add HW_CSUM setting to preserve user ability to control + * checksum offload on the vlan device. + */ + if (lower_features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) + lower_features |= NETIF_F_HW_CSUM; + features = netdev_intersect_features(features, lower_features); features |= old_features & (NETIF_F_SOFT_FEATURES | NETIF_F_GSO_SOFTWARE); features |= NETIF_F_LLTX; diff --git a/net/9p/Kconfig b/net/9p/Kconfig index a75174a33723..e6014e0e51f7 100644 --- a/net/9p/Kconfig +++ b/net/9p/Kconfig @@ -22,6 +22,15 @@ config NET_9P_VIRTIO This builds support for a transports between guest partitions and a host partition. +config NET_9P_XEN + depends on XEN + select XEN_XENBUS_FRONTEND + tristate "9P Xen Transport" + help + This builds support for a transport for 9pfs between + two Xen domains. + + config NET_9P_RDMA depends on INET && INFINIBAND && INFINIBAND_ADDR_TRANS tristate "9P RDMA Transport (Experimental)" diff --git a/net/9p/Makefile b/net/9p/Makefile index a0874cc1f718..697ea7caf466 100644 --- a/net/9p/Makefile +++ b/net/9p/Makefile @@ -1,4 +1,5 @@ obj-$(CONFIG_NET_9P) := 9pnet.o +obj-$(CONFIG_NET_9P_XEN) += 9pnet_xen.o obj-$(CONFIG_NET_9P_VIRTIO) += 9pnet_virtio.o obj-$(CONFIG_NET_9P_RDMA) += 9pnet_rdma.o @@ -14,5 +15,8 @@ obj-$(CONFIG_NET_9P_RDMA) += 9pnet_rdma.o 9pnet_virtio-objs := \ trans_virtio.o \ +9pnet_xen-objs := \ + trans_xen.o \ + 9pnet_rdma-objs := \ trans_rdma.o \ diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c new file mode 100644 index 000000000000..71e85643b3f9 --- /dev/null +++ b/net/9p/trans_xen.c @@ -0,0 +1,545 @@ +/* + * linux/fs/9p/trans_xen + * + * Xen transport layer. + * + * Copyright (C) 2017 by Stefano Stabellini <stefano@aporeto.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#include <xen/events.h> +#include <xen/grant_table.h> +#include <xen/xen.h> +#include <xen/xenbus.h> +#include <xen/interface/io/9pfs.h> + +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/rwlock.h> +#include <net/9p/9p.h> +#include <net/9p/client.h> +#include <net/9p/transport.h> + +#define XEN_9PFS_NUM_RINGS 2 +#define XEN_9PFS_RING_ORDER 6 +#define XEN_9PFS_RING_SIZE XEN_FLEX_RING_SIZE(XEN_9PFS_RING_ORDER) + +struct xen_9pfs_header { + uint32_t size; + uint8_t id; + uint16_t tag; + + /* uint8_t sdata[]; */ +} __attribute__((packed)); + +/* One per ring, more than one per 9pfs share */ +struct xen_9pfs_dataring { + struct xen_9pfs_front_priv *priv; + + struct xen_9pfs_data_intf *intf; + grant_ref_t ref; + int evtchn; + int irq; + /* protect a ring from concurrent accesses */ + spinlock_t lock; + + struct xen_9pfs_data data; + wait_queue_head_t wq; + struct work_struct work; +}; + +/* One per 9pfs share */ +struct xen_9pfs_front_priv { + struct list_head list; + struct xenbus_device *dev; + char *tag; + struct p9_client *client; + + int num_rings; + struct xen_9pfs_dataring *rings; +}; + +static LIST_HEAD(xen_9pfs_devs); +static DEFINE_RWLOCK(xen_9pfs_lock); + +/* We don't currently allow canceling of requests */ +static int p9_xen_cancel(struct p9_client *client, struct p9_req_t *req) +{ + return 1; +} + +static int p9_xen_create(struct p9_client *client, const char *addr, char *args) +{ + struct xen_9pfs_front_priv *priv; + + read_lock(&xen_9pfs_lock); + list_for_each_entry(priv, &xen_9pfs_devs, list) { + if (!strcmp(priv->tag, addr)) { + priv->client = client; + read_unlock(&xen_9pfs_lock); + return 0; + } + } + read_unlock(&xen_9pfs_lock); + return -EINVAL; +} + +static void p9_xen_close(struct p9_client *client) +{ + struct xen_9pfs_front_priv *priv; + + read_lock(&xen_9pfs_lock); + list_for_each_entry(priv, &xen_9pfs_devs, list) { + if (priv->client == client) { + priv->client = NULL; + read_unlock(&xen_9pfs_lock); + return; + } + } + read_unlock(&xen_9pfs_lock); +} + +static bool p9_xen_write_todo(struct xen_9pfs_dataring *ring, RING_IDX size) +{ + RING_IDX cons, prod; + + cons = ring->intf->out_cons; + prod = ring->intf->out_prod; + virt_mb(); + + return XEN_9PFS_RING_SIZE - + xen_9pfs_queued(prod, cons, XEN_9PFS_RING_SIZE) >= size; +} + +static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req) +{ + struct xen_9pfs_front_priv *priv = NULL; + RING_IDX cons, prod, masked_cons, masked_prod; + unsigned long flags; + u32 size = p9_req->tc->size; + struct xen_9pfs_dataring *ring; + int num; + + read_lock(&xen_9pfs_lock); + list_for_each_entry(priv, &xen_9pfs_devs, list) { + if (priv->client == client) + break; + } + read_unlock(&xen_9pfs_lock); + if (!priv || priv->client != client) + return -EINVAL; + + num = p9_req->tc->tag % priv->num_rings; + ring = &priv->rings[num]; + +again: + while (wait_event_interruptible(ring->wq, + p9_xen_write_todo(ring, size)) != 0) + ; + + spin_lock_irqsave(&ring->lock, flags); + cons = ring->intf->out_cons; + prod = ring->intf->out_prod; + virt_mb(); + + if (XEN_9PFS_RING_SIZE - xen_9pfs_queued(prod, cons, + XEN_9PFS_RING_SIZE) < size) { + spin_unlock_irqrestore(&ring->lock, flags); + goto again; + } + + masked_prod = xen_9pfs_mask(prod, XEN_9PFS_RING_SIZE); + masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE); + + xen_9pfs_write_packet(ring->data.out, p9_req->tc->sdata, size, + &masked_prod, masked_cons, XEN_9PFS_RING_SIZE); + + p9_req->status = REQ_STATUS_SENT; + virt_wmb(); /* write ring before updating pointer */ + prod += size; + ring->intf->out_prod = prod; + spin_unlock_irqrestore(&ring->lock, flags); + notify_remote_via_irq(ring->irq); + + return 0; +} + +static void p9_xen_response(struct work_struct *work) +{ + struct xen_9pfs_front_priv *priv; + struct xen_9pfs_dataring *ring; + RING_IDX cons, prod, masked_cons, masked_prod; + struct xen_9pfs_header h; + struct p9_req_t *req; + int status; + + ring = container_of(work, struct xen_9pfs_dataring, work); + priv = ring->priv; + + while (1) { + cons = ring->intf->in_cons; + prod = ring->intf->in_prod; + virt_rmb(); + + if (xen_9pfs_queued(prod, cons, XEN_9PFS_RING_SIZE) < + sizeof(h)) { + notify_remote_via_irq(ring->irq); + return; + } + + masked_prod = xen_9pfs_mask(prod, XEN_9PFS_RING_SIZE); + masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE); + + /* First, read just the header */ + xen_9pfs_read_packet(&h, ring->data.in, sizeof(h), + masked_prod, &masked_cons, + XEN_9PFS_RING_SIZE); + + req = p9_tag_lookup(priv->client, h.tag); + if (!req || req->status != REQ_STATUS_SENT) { + dev_warn(&priv->dev->dev, "Wrong req tag=%x\n", h.tag); + cons += h.size; + virt_mb(); + ring->intf->in_cons = cons; + continue; + } + + memcpy(req->rc, &h, sizeof(h)); + req->rc->offset = 0; + + masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE); + /* Then, read the whole packet (including the header) */ + xen_9pfs_read_packet(req->rc->sdata, ring->data.in, h.size, + masked_prod, &masked_cons, + XEN_9PFS_RING_SIZE); + + virt_mb(); + cons += h.size; + ring->intf->in_cons = cons; + + status = (req->status != REQ_STATUS_ERROR) ? + REQ_STATUS_RCVD : REQ_STATUS_ERROR; + + p9_client_cb(priv->client, req, status); + } +} + +static irqreturn_t xen_9pfs_front_event_handler(int irq, void *r) +{ + struct xen_9pfs_dataring *ring = r; + + if (!ring || !ring->priv->client) { + /* ignore spurious interrupt */ + return IRQ_HANDLED; + } + + wake_up_interruptible(&ring->wq); + schedule_work(&ring->work); + + return IRQ_HANDLED; +} + +static struct p9_trans_module p9_xen_trans = { + .name = "xen", + .maxsize = 1 << (XEN_9PFS_RING_ORDER + XEN_PAGE_SHIFT), + .def = 1, + .create = p9_xen_create, + .close = p9_xen_close, + .request = p9_xen_request, + .cancel = p9_xen_cancel, + .owner = THIS_MODULE, +}; + +static const struct xenbus_device_id xen_9pfs_front_ids[] = { + { "9pfs" }, + { "" } +}; + +static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) +{ + int i, j; + + write_lock(&xen_9pfs_lock); + list_del(&priv->list); + write_unlock(&xen_9pfs_lock); + + for (i = 0; i < priv->num_rings; i++) { + if (!priv->rings[i].intf) + break; + if (priv->rings[i].irq > 0) + unbind_from_irqhandler(priv->rings[i].irq, priv->dev); + if (priv->rings[i].data.in) { + for (j = 0; j < (1 << XEN_9PFS_RING_ORDER); j++) { + grant_ref_t ref; + + ref = priv->rings[i].intf->ref[j]; + gnttab_end_foreign_access(ref, 0, 0); + } + free_pages((unsigned long)priv->rings[i].data.in, + XEN_9PFS_RING_ORDER - + (PAGE_SHIFT - XEN_PAGE_SHIFT)); + } + gnttab_end_foreign_access(priv->rings[i].ref, 0, 0); + free_page((unsigned long)priv->rings[i].intf); + } + kfree(priv->rings); + kfree(priv->tag); + kfree(priv); +} + +static int xen_9pfs_front_remove(struct xenbus_device *dev) +{ + struct xen_9pfs_front_priv *priv = dev_get_drvdata(&dev->dev); + + dev_set_drvdata(&dev->dev, NULL); + xen_9pfs_front_free(priv); + return 0; +} + +static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev, + struct xen_9pfs_dataring *ring) +{ + int i = 0; + int ret = -ENOMEM; + void *bytes = NULL; + + init_waitqueue_head(&ring->wq); + spin_lock_init(&ring->lock); + INIT_WORK(&ring->work, p9_xen_response); + + ring->intf = (struct xen_9pfs_data_intf *)get_zeroed_page(GFP_KERNEL); + if (!ring->intf) + return ret; + ret = gnttab_grant_foreign_access(dev->otherend_id, + virt_to_gfn(ring->intf), 0); + if (ret < 0) + goto out; + ring->ref = ret; + bytes = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + XEN_9PFS_RING_ORDER - (PAGE_SHIFT - XEN_PAGE_SHIFT)); + if (!bytes) { + ret = -ENOMEM; + goto out; + } + for (; i < (1 << XEN_9PFS_RING_ORDER); i++) { + ret = gnttab_grant_foreign_access( + dev->otherend_id, virt_to_gfn(bytes) + i, 0); + if (ret < 0) + goto out; + ring->intf->ref[i] = ret; + } + ring->intf->ring_order = XEN_9PFS_RING_ORDER; + ring->data.in = bytes; + ring->data.out = bytes + XEN_9PFS_RING_SIZE; + + ret = xenbus_alloc_evtchn(dev, &ring->evtchn); + if (ret) + goto out; + ring->irq = bind_evtchn_to_irqhandler(ring->evtchn, + xen_9pfs_front_event_handler, + 0, "xen_9pfs-frontend", ring); + if (ring->irq >= 0) + return 0; + + xenbus_free_evtchn(dev, ring->evtchn); + ret = ring->irq; +out: + if (bytes) { + for (i--; i >= 0; i--) + gnttab_end_foreign_access(ring->intf->ref[i], 0, 0); + free_pages((unsigned long)bytes, + XEN_9PFS_RING_ORDER - + (PAGE_SHIFT - XEN_PAGE_SHIFT)); + } + gnttab_end_foreign_access(ring->ref, 0, 0); + free_page((unsigned long)ring->intf); + return ret; +} + +static int xen_9pfs_front_probe(struct xenbus_device *dev, + const struct xenbus_device_id *id) +{ + int ret, i; + struct xenbus_transaction xbt; + struct xen_9pfs_front_priv *priv = NULL; + char *versions; + unsigned int max_rings, max_ring_order, len = 0; + + versions = xenbus_read(XBT_NIL, dev->otherend, "versions", &len); + if (!len) + return -EINVAL; + if (strcmp(versions, "1")) { + kfree(versions); + return -EINVAL; + } + kfree(versions); + max_rings = xenbus_read_unsigned(dev->otherend, "max-rings", 0); + if (max_rings < XEN_9PFS_NUM_RINGS) + return -EINVAL; + max_ring_order = xenbus_read_unsigned(dev->otherend, + "max-ring-page-order", 0); + if (max_ring_order < XEN_9PFS_RING_ORDER) + return -EINVAL; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->dev = dev; + priv->num_rings = XEN_9PFS_NUM_RINGS; + priv->rings = kcalloc(priv->num_rings, sizeof(*priv->rings), + GFP_KERNEL); + if (!priv->rings) { + kfree(priv); + return -ENOMEM; + } + + for (i = 0; i < priv->num_rings; i++) { + priv->rings[i].priv = priv; + ret = xen_9pfs_front_alloc_dataring(dev, &priv->rings[i]); + if (ret < 0) + goto error; + } + + again: + ret = xenbus_transaction_start(&xbt); + if (ret) { + xenbus_dev_fatal(dev, ret, "starting transaction"); + goto error; + } + ret = xenbus_printf(xbt, dev->nodename, "version", "%u", 1); + if (ret) + goto error_xenbus; + ret = xenbus_printf(xbt, dev->nodename, "num-rings", "%u", + priv->num_rings); + if (ret) + goto error_xenbus; + for (i = 0; i < priv->num_rings; i++) { + char str[16]; + + BUILD_BUG_ON(XEN_9PFS_NUM_RINGS > 9); + sprintf(str, "ring-ref%u", i); + ret = xenbus_printf(xbt, dev->nodename, str, "%d", + priv->rings[i].ref); + if (ret) + goto error_xenbus; + + sprintf(str, "event-channel-%u", i); + ret = xenbus_printf(xbt, dev->nodename, str, "%u", + priv->rings[i].evtchn); + if (ret) + goto error_xenbus; + } + priv->tag = xenbus_read(xbt, dev->nodename, "tag", NULL); + if (!priv->tag) { + ret = -EINVAL; + goto error_xenbus; + } + ret = xenbus_transaction_end(xbt, 0); + if (ret) { + if (ret == -EAGAIN) + goto again; + xenbus_dev_fatal(dev, ret, "completing transaction"); + goto error; + } + + write_lock(&xen_9pfs_lock); + list_add_tail(&priv->list, &xen_9pfs_devs); + write_unlock(&xen_9pfs_lock); + dev_set_drvdata(&dev->dev, priv); + xenbus_switch_state(dev, XenbusStateInitialised); + + return 0; + + error_xenbus: + xenbus_transaction_end(xbt, 1); + xenbus_dev_fatal(dev, ret, "writing xenstore"); + error: + dev_set_drvdata(&dev->dev, NULL); + xen_9pfs_front_free(priv); + return ret; +} + +static int xen_9pfs_front_resume(struct xenbus_device *dev) +{ + dev_warn(&dev->dev, "suspsend/resume unsupported\n"); + return 0; +} + +static void xen_9pfs_front_changed(struct xenbus_device *dev, + enum xenbus_state backend_state) +{ + switch (backend_state) { + case XenbusStateReconfiguring: + case XenbusStateReconfigured: + case XenbusStateInitialising: + case XenbusStateInitialised: + case XenbusStateUnknown: + break; + + case XenbusStateInitWait: + break; + + case XenbusStateConnected: + xenbus_switch_state(dev, XenbusStateConnected); + break; + + case XenbusStateClosed: + if (dev->state == XenbusStateClosed) + break; + /* Missed the backend's CLOSING state -- fallthrough */ + case XenbusStateClosing: + xenbus_frontend_closed(dev); + break; + } +} + +static struct xenbus_driver xen_9pfs_front_driver = { + .ids = xen_9pfs_front_ids, + .probe = xen_9pfs_front_probe, + .remove = xen_9pfs_front_remove, + .resume = xen_9pfs_front_resume, + .otherend_changed = xen_9pfs_front_changed, +}; + +int p9_trans_xen_init(void) +{ + if (!xen_domain()) + return -ENODEV; + + pr_info("Initialising Xen transport for 9pfs\n"); + + v9fs_register_trans(&p9_xen_trans); + return xenbus_register_frontend(&xen_9pfs_front_driver); +} +module_init(p9_trans_xen_init); + +void p9_trans_xen_exit(void) +{ + v9fs_unregister_trans(&p9_xen_trans); + return xenbus_unregister_driver(&xen_9pfs_front_driver); +} +module_exit(p9_trans_xen_exit); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index a572db710d4e..c5ce7745b230 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -133,6 +133,8 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_MCAST_TO_UCAST */ + nla_total_size(1) /* IFLA_BRPORT_LEARNING */ + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */ + + nla_total_size(1) /* IFLA_BRPORT_MCAST_FLOOD */ + + nla_total_size(1) /* IFLA_BRPORT_BCAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */ @@ -633,6 +635,8 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 }, [IFLA_BRPORT_MULTICAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 }, + [IFLA_BRPORT_MCAST_FLOOD] = { .type = NLA_U8 }, + [IFLA_BRPORT_BCAST_FLOOD] = { .type = NLA_U8 }, }; /* Change the state of the port and notify spanning tree */ diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index 4e0b0c359325..e0bb624c3845 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -9,6 +9,7 @@ */ #include <linux/module.h> #include <net/sock.h> +#include "../br_private.h" #include <linux/netfilter.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_bridge/ebtables.h> @@ -18,11 +19,30 @@ static unsigned int ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; + struct net_device *dev; if (!skb_make_writable(skb, 0)) return EBT_DROP; ether_addr_copy(eth_hdr(skb)->h_dest, info->mac); + + if (is_multicast_ether_addr(info->mac)) { + if (is_broadcast_ether_addr(info->mac)) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_MULTICAST; + } else { + if (xt_hooknum(par) != NF_BR_BROUTING) + dev = br_port_get_rcu(xt_in(par))->br->dev; + else + dev = xt_in(par); + + if (ether_addr_equal(info->mac, dev->dev_addr)) + skb->pkt_type = PACKET_HOST; + else + skb->pkt_type = PACKET_OTHERHOST; + } + return info->target; } diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 108533859a53..4fd02831beed 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -45,6 +45,17 @@ bool libceph_compatible(void *data) } EXPORT_SYMBOL(libceph_compatible); +static int param_get_supported_features(char *buffer, + const struct kernel_param *kp) +{ + return sprintf(buffer, "0x%llx", CEPH_FEATURES_SUPPORTED_DEFAULT); +} +static const struct kernel_param_ops param_ops_supported_features = { + .get = param_get_supported_features, +}; +module_param_cb(supported_features, ¶m_ops_supported_features, NULL, + S_IRUGO); + /* * find filename portion of a path (/foo/bar/baz -> baz) */ @@ -187,7 +198,7 @@ void *ceph_kvmalloc(size_t size, gfp_t flags) return ptr; } - return __vmalloc(size, flags | __GFP_HIGHMEM, PAGE_KERNEL); + return __vmalloc(size, flags, PAGE_KERNEL); } @@ -596,9 +607,7 @@ EXPORT_SYMBOL(ceph_client_gid); /* * create a fresh client instance */ -struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, - u64 supported_features, - u64 required_features) +struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private) { struct ceph_client *client; struct ceph_entity_addr *myaddr = NULL; @@ -615,14 +624,12 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, init_waitqueue_head(&client->auth_wq); client->auth_err = 0; - if (!ceph_test_opt(client, NOMSGAUTH)) - required_features |= CEPH_FEATURE_MSG_AUTH; - client->extra_mon_dispatch = NULL; - client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT | - supported_features; - client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT | - required_features; + client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT; + client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT; + + if (!ceph_test_opt(client, NOMSGAUTH)) + client->required_features |= CEPH_FEATURE_MSG_AUTH; /* msgr */ if (ceph_test_opt(client, MYIP)) diff --git a/net/ceph/cls_lock_client.c b/net/ceph/cls_lock_client.c index b9233b990399..08ada893f01e 100644 --- a/net/ceph/cls_lock_client.c +++ b/net/ceph/cls_lock_client.c @@ -179,6 +179,57 @@ int ceph_cls_break_lock(struct ceph_osd_client *osdc, } EXPORT_SYMBOL(ceph_cls_break_lock); +int ceph_cls_set_cookie(struct ceph_osd_client *osdc, + struct ceph_object_id *oid, + struct ceph_object_locator *oloc, + char *lock_name, u8 type, char *old_cookie, + char *tag, char *new_cookie) +{ + int cookie_op_buf_size; + int name_len = strlen(lock_name); + int old_cookie_len = strlen(old_cookie); + int tag_len = strlen(tag); + int new_cookie_len = strlen(new_cookie); + void *p, *end; + struct page *cookie_op_page; + int ret; + + cookie_op_buf_size = name_len + sizeof(__le32) + + old_cookie_len + sizeof(__le32) + + tag_len + sizeof(__le32) + + new_cookie_len + sizeof(__le32) + + sizeof(u8) + CEPH_ENCODING_START_BLK_LEN; + if (cookie_op_buf_size > PAGE_SIZE) + return -E2BIG; + + cookie_op_page = alloc_page(GFP_NOIO); + if (!cookie_op_page) + return -ENOMEM; + + p = page_address(cookie_op_page); + end = p + cookie_op_buf_size; + + /* encode cls_lock_set_cookie_op struct */ + ceph_start_encoding(&p, 1, 1, + cookie_op_buf_size - CEPH_ENCODING_START_BLK_LEN); + ceph_encode_string(&p, end, lock_name, name_len); + ceph_encode_8(&p, type); + ceph_encode_string(&p, end, old_cookie, old_cookie_len); + ceph_encode_string(&p, end, tag, tag_len); + ceph_encode_string(&p, end, new_cookie, new_cookie_len); + + dout("%s lock_name %s type %d old_cookie %s tag %s new_cookie %s\n", + __func__, lock_name, type, old_cookie, tag, new_cookie); + ret = ceph_osdc_call(osdc, oid, oloc, "lock", "set_cookie", + CEPH_OSD_FLAG_WRITE, cookie_op_page, + cookie_op_buf_size, NULL, NULL); + + dout("%s: status %d\n", __func__, ret); + __free_page(cookie_op_page); + return ret; +} +EXPORT_SYMBOL(ceph_cls_set_cookie); + void ceph_free_lockers(struct ceph_locker *lockers, u32 num_lockers) { int i; diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c index c62b2b029a6e..71ba13927b3d 100644 --- a/net/ceph/debugfs.c +++ b/net/ceph/debugfs.c @@ -62,7 +62,8 @@ static int osdmap_show(struct seq_file *s, void *p) return 0; down_read(&osdc->lock); - seq_printf(s, "epoch %d flags 0x%x\n", map->epoch, map->flags); + seq_printf(s, "epoch %u barrier %u flags 0x%x\n", map->epoch, + osdc->epoch_barrier, map->flags); for (n = rb_first(&map->pg_pools); n; n = rb_next(n)) { struct ceph_pg_pool_info *pi = @@ -177,9 +178,7 @@ static void dump_request(struct seq_file *s, struct ceph_osd_request *req) seq_printf(s, "%llu\t", req->r_tid); dump_target(s, &req->r_t); - seq_printf(s, "\t%d\t%u'%llu", req->r_attempts, - le32_to_cpu(req->r_replay_version.epoch), - le64_to_cpu(req->r_replay_version.version)); + seq_printf(s, "\t%d", req->r_attempts); for (i = 0; i < req->r_num_ops; i++) { struct ceph_osd_req_op *op = &req->r_ops[i]; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index f76bb3332613..5766a6c896c4 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1386,8 +1386,9 @@ static void prepare_write_keepalive(struct ceph_connection *con) dout("prepare_write_keepalive %p\n", con); con_out_kvec_reset(con); if (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2) { - struct timespec now = CURRENT_TIME; + struct timespec now; + ktime_get_real_ts(&now); con_out_kvec_add(con, sizeof(tag_keepalive2), &tag_keepalive2); ceph_encode_timespec(&con->out_temp_keepalive2, &now); con_out_kvec_add(con, sizeof(con->out_temp_keepalive2), @@ -3176,8 +3177,9 @@ bool ceph_con_keepalive_expired(struct ceph_connection *con, { if (interval > 0 && (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2)) { - struct timespec now = CURRENT_TIME; + struct timespec now; struct timespec ts; + ktime_get_real_ts(&now); jiffies_to_timespec(interval, &ts); ts = timespec_add(con->last_keepalive_ack, ts); return timespec_compare(&now, &ts) >= 0; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index e15ea9e4c495..924f07c36ddb 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -961,6 +961,7 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, truncate_size, truncate_seq); } + req->r_abort_on_full = true; req->r_flags = flags; req->r_base_oloc.pool = layout->pool_id; req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns); @@ -1005,7 +1006,7 @@ static bool osd_registered(struct ceph_osd *osd) */ static void osd_init(struct ceph_osd *osd) { - atomic_set(&osd->o_ref, 1); + refcount_set(&osd->o_ref, 1); RB_CLEAR_NODE(&osd->o_node); osd->o_requests = RB_ROOT; osd->o_linger_requests = RB_ROOT; @@ -1050,9 +1051,9 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum) static struct ceph_osd *get_osd(struct ceph_osd *osd) { - if (atomic_inc_not_zero(&osd->o_ref)) { - dout("get_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref)-1, - atomic_read(&osd->o_ref)); + if (refcount_inc_not_zero(&osd->o_ref)) { + dout("get_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref)-1, + refcount_read(&osd->o_ref)); return osd; } else { dout("get_osd %p FAIL\n", osd); @@ -1062,9 +1063,9 @@ static struct ceph_osd *get_osd(struct ceph_osd *osd) static void put_osd(struct ceph_osd *osd) { - dout("put_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref), - atomic_read(&osd->o_ref) - 1); - if (atomic_dec_and_test(&osd->o_ref)) { + dout("put_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref), + refcount_read(&osd->o_ref) - 1); + if (refcount_dec_and_test(&osd->o_ref)) { osd_cleanup(osd); kfree(osd); } @@ -1297,8 +1298,9 @@ static bool target_should_be_paused(struct ceph_osd_client *osdc, __pool_full(pi); WARN_ON(pi->id != t->base_oloc.pool); - return (t->flags & CEPH_OSD_FLAG_READ && pauserd) || - (t->flags & CEPH_OSD_FLAG_WRITE && pausewr); + return ((t->flags & CEPH_OSD_FLAG_READ) && pauserd) || + ((t->flags & CEPH_OSD_FLAG_WRITE) && pausewr) || + (osdc->osdmap->epoch < osdc->epoch_barrier); } enum calc_target_result { @@ -1503,9 +1505,10 @@ static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg) ceph_encode_32(&p, req->r_flags); ceph_encode_timespec(p, &req->r_mtime); p += sizeof(struct ceph_timespec); - /* aka reassert_version */ - memcpy(p, &req->r_replay_version, sizeof(req->r_replay_version)); - p += sizeof(req->r_replay_version); + + /* reassert_version */ + memset(p, 0, sizeof(struct ceph_eversion)); + p += sizeof(struct ceph_eversion); /* oloc */ ceph_start_encoding(&p, 5, 4, @@ -1626,6 +1629,7 @@ static void maybe_request_map(struct ceph_osd_client *osdc) ceph_monc_renew_subs(&osdc->client->monc); } +static void complete_request(struct ceph_osd_request *req, int err); static void send_map_check(struct ceph_osd_request *req); static void __submit_request(struct ceph_osd_request *req, bool wrlocked) @@ -1635,6 +1639,7 @@ static void __submit_request(struct ceph_osd_request *req, bool wrlocked) enum calc_target_result ct_res; bool need_send = false; bool promoted = false; + bool need_abort = false; WARN_ON(req->r_tid); dout("%s req %p wrlocked %d\n", __func__, req, wrlocked); @@ -1650,8 +1655,13 @@ again: goto promote; } - if ((req->r_flags & CEPH_OSD_FLAG_WRITE) && - ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) { + if (osdc->osdmap->epoch < osdc->epoch_barrier) { + dout("req %p epoch %u barrier %u\n", req, osdc->osdmap->epoch, + osdc->epoch_barrier); + req->r_t.paused = true; + maybe_request_map(osdc); + } else if ((req->r_flags & CEPH_OSD_FLAG_WRITE) && + ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) { dout("req %p pausewr\n", req); req->r_t.paused = true; maybe_request_map(osdc); @@ -1669,6 +1679,8 @@ again: pr_warn_ratelimited("FULL or reached pool quota\n"); req->r_t.paused = true; maybe_request_map(osdc); + if (req->r_abort_on_full) + need_abort = true; } else if (!osd_homeless(osd)) { need_send = true; } else { @@ -1685,6 +1697,8 @@ again: link_request(osd, req); if (need_send) send_request(req); + else if (need_abort) + complete_request(req, -ENOSPC); mutex_unlock(&osd->lock); if (ct_res == CALC_TARGET_POOL_DNE) @@ -1799,6 +1813,97 @@ static void abort_request(struct ceph_osd_request *req, int err) complete_request(req, err); } +static void update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb) +{ + if (likely(eb > osdc->epoch_barrier)) { + dout("updating epoch_barrier from %u to %u\n", + osdc->epoch_barrier, eb); + osdc->epoch_barrier = eb; + /* Request map if we're not to the barrier yet */ + if (eb > osdc->osdmap->epoch) + maybe_request_map(osdc); + } +} + +void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb) +{ + down_read(&osdc->lock); + if (unlikely(eb > osdc->epoch_barrier)) { + up_read(&osdc->lock); + down_write(&osdc->lock); + update_epoch_barrier(osdc, eb); + up_write(&osdc->lock); + } else { + up_read(&osdc->lock); + } +} +EXPORT_SYMBOL(ceph_osdc_update_epoch_barrier); + +/* + * Drop all pending requests that are stalled waiting on a full condition to + * clear, and complete them with ENOSPC as the return code. Set the + * osdc->epoch_barrier to the latest map epoch that we've seen if any were + * cancelled. + */ +static void ceph_osdc_abort_on_full(struct ceph_osd_client *osdc) +{ + struct rb_node *n; + bool victims = false; + + dout("enter abort_on_full\n"); + + if (!ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) && !have_pool_full(osdc)) + goto out; + + /* Scan list and see if there is anything to abort */ + for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { + struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); + struct rb_node *m; + + m = rb_first(&osd->o_requests); + while (m) { + struct ceph_osd_request *req = rb_entry(m, + struct ceph_osd_request, r_node); + m = rb_next(m); + + if (req->r_abort_on_full) { + victims = true; + break; + } + } + if (victims) + break; + } + + if (!victims) + goto out; + + /* + * Update the barrier to current epoch if it's behind that point, + * since we know we have some calls to be aborted in the tree. + */ + update_epoch_barrier(osdc, osdc->osdmap->epoch); + + for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { + struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); + struct rb_node *m; + + m = rb_first(&osd->o_requests); + while (m) { + struct ceph_osd_request *req = rb_entry(m, + struct ceph_osd_request, r_node); + m = rb_next(m); + + if (req->r_abort_on_full && + (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || + pool_full(osdc, req->r_t.target_oloc.pool))) + abort_request(req, -ENOSPC); + } + } +out: + dout("return abort_on_full barrier=%u\n", osdc->epoch_barrier); +} + static void check_pool_dne(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; @@ -3252,11 +3357,13 @@ done: pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || have_pool_full(osdc); - if (was_pauserd || was_pausewr || pauserd || pausewr) + if (was_pauserd || was_pausewr || pauserd || pausewr || + osdc->osdmap->epoch < osdc->epoch_barrier) maybe_request_map(osdc); kick_requests(osdc, &need_resend, &need_resend_linger); + ceph_osdc_abort_on_full(osdc); ceph_monc_got_map(&osdc->client->monc, CEPH_SUB_OSDMAP, osdc->osdmap->epoch); up_write(&osdc->lock); @@ -3574,7 +3681,7 @@ ceph_osdc_watch(struct ceph_osd_client *osdc, ceph_oid_copy(&lreq->t.base_oid, oid); ceph_oloc_copy(&lreq->t.base_oloc, oloc); lreq->t.flags = CEPH_OSD_FLAG_WRITE; - lreq->mtime = CURRENT_TIME; + ktime_get_real_ts(&lreq->mtime); lreq->reg_req = alloc_linger_request(lreq); if (!lreq->reg_req) { @@ -3632,7 +3739,7 @@ int ceph_osdc_unwatch(struct ceph_osd_client *osdc, ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid); ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); req->r_flags = CEPH_OSD_FLAG_WRITE; - req->r_mtime = CURRENT_TIME; + ktime_get_real_ts(&req->r_mtime); osd_req_op_watch_init(req, 0, lreq->linger_id, CEPH_OSD_WATCH_OP_UNWATCH); @@ -4126,7 +4233,7 @@ void ceph_osdc_stop(struct ceph_osd_client *osdc) close_osd(osd); } up_write(&osdc->lock); - WARN_ON(atomic_read(&osdc->homeless_osd.o_ref) != 1); + WARN_ON(refcount_read(&osdc->homeless_osd.o_ref) != 1); osd_cleanup(&osdc->homeless_osd); WARN_ON(!list_empty(&osdc->osd_lru)); diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c index 6864007e64fc..ce09f73be759 100644 --- a/net/ceph/pagelist.c +++ b/net/ceph/pagelist.c @@ -16,7 +16,7 @@ static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl) void ceph_pagelist_release(struct ceph_pagelist *pl) { - if (!atomic_dec_and_test(&pl->refcnt)) + if (!refcount_dec_and_test(&pl->refcnt)) return; ceph_pagelist_unmap_tail(pl); while (!list_empty(&pl->head)) { diff --git a/net/ceph/snapshot.c b/net/ceph/snapshot.c index 705414e78ae0..e14a5d038656 100644 --- a/net/ceph/snapshot.c +++ b/net/ceph/snapshot.c @@ -49,7 +49,7 @@ struct ceph_snap_context *ceph_create_snap_context(u32 snap_count, if (!snapc) return NULL; - atomic_set(&snapc->nref, 1); + refcount_set(&snapc->nref, 1); snapc->num_snaps = snap_count; return snapc; @@ -59,7 +59,7 @@ EXPORT_SYMBOL(ceph_create_snap_context); struct ceph_snap_context *ceph_get_snap_context(struct ceph_snap_context *sc) { if (sc) - atomic_inc(&sc->nref); + refcount_inc(&sc->nref); return sc; } EXPORT_SYMBOL(ceph_get_snap_context); @@ -68,7 +68,7 @@ void ceph_put_snap_context(struct ceph_snap_context *sc) { if (!sc) return; - if (atomic_dec_and_test(&sc->nref)) { + if (refcount_dec_and_test(&sc->nref)) { /*printk(" deleting snap_context %p\n", sc);*/ kfree(sc); } diff --git a/net/core/dev.c b/net/core/dev.c index d07aa5ffb511..96cf83da0d66 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -81,6 +81,7 @@ #include <linux/hash.h> #include <linux/slab.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/mutex.h> #include <linux/string.h> #include <linux/mm.h> @@ -4235,7 +4236,7 @@ static int __netif_receive_skb(struct sk_buff *skb) int ret; if (sk_memalloc_socks() && skb_pfmemalloc(skb)) { - unsigned long pflags = current->flags; + unsigned int noreclaim_flag; /* * PFMEMALLOC skbs are special, they should @@ -4246,9 +4247,9 @@ static int __netif_receive_skb(struct sk_buff *skb) * Use PF_MEMALLOC as this saves us from propagating the allocation * context down to all allocation sites. */ - current->flags |= PF_MEMALLOC; + noreclaim_flag = memalloc_noreclaim_save(); ret = __netif_receive_skb_core(skb, true); - current_restore_flags(pflags, PF_MEMALLOC); + memalloc_noreclaim_restore(noreclaim_flag); } else ret = __netif_receive_skb_core(skb, false); @@ -7264,12 +7265,10 @@ static int netif_alloc_rx_queues(struct net_device *dev) BUG_ON(count < 1); - rx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); - if (!rx) { - rx = vzalloc(sz); - if (!rx) - return -ENOMEM; - } + rx = kvzalloc(sz, GFP_KERNEL | __GFP_REPEAT); + if (!rx) + return -ENOMEM; + dev->_rx = rx; for (i = 0; i < count; i++) @@ -7306,12 +7305,10 @@ static int netif_alloc_netdev_queues(struct net_device *dev) if (count < 1 || count > 0xffff) return -EINVAL; - tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); - if (!tx) { - tx = vzalloc(sz); - if (!tx) - return -ENOMEM; - } + tx = kvzalloc(sz, GFP_KERNEL | __GFP_REPEAT); + if (!tx) + return -ENOMEM; + dev->_tx = tx; netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); @@ -7845,9 +7842,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, /* ensure 32-byte alignment of whole construct */ alloc_size += NETDEV_ALIGN - 1; - p = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); - if (!p) - p = vzalloc(alloc_size); + p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_REPEAT); if (!p) return NULL; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 6e67315ec368..bcb0f610ee42 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1054,7 +1054,7 @@ static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev) return err; } - if (nla_put(skb, IFLA_PHYS_PORT_NAME, strlen(name), name)) + if (nla_put_string(skb, IFLA_PHYS_PORT_NAME, name)) return -EMSGSIZE; return 0; diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 6bd2f8fb0476..ae35cce3a40d 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -24,9 +24,13 @@ static siphash_key_t ts_secret __read_mostly; static __always_inline void net_secret_init(void) { - net_get_random_once(&ts_secret, sizeof(ts_secret)); net_get_random_once(&net_secret, sizeof(net_secret)); } + +static __always_inline void ts_secret_init(void) +{ + net_get_random_once(&ts_secret, sizeof(ts_secret)); +} #endif #ifdef CONFIG_INET @@ -47,7 +51,7 @@ static u32 seq_scale(u32 seq) #endif #if IS_ENABLED(CONFIG_IPV6) -static u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr) +u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr) { const struct { struct in6_addr saddr; @@ -60,12 +64,14 @@ static u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr) if (sysctl_tcp_timestamps != 1) return 0; + ts_secret_init(); return siphash(&combined, offsetofend(typeof(combined), daddr), &ts_secret); } +EXPORT_SYMBOL(secure_tcpv6_ts_off); -u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport, u32 *tsoff) +u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, + __be16 sport, __be16 dport) { const struct { struct in6_addr saddr; @@ -78,14 +84,14 @@ u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr, .sport = sport, .dport = dport }; - u64 hash; + u32 hash; + net_secret_init(); hash = siphash(&combined, offsetofend(typeof(combined), dport), &net_secret); - *tsoff = secure_tcpv6_ts_off(saddr, daddr); return seq_scale(hash); } -EXPORT_SYMBOL(secure_tcpv6_seq_and_tsoff); +EXPORT_SYMBOL(secure_tcpv6_seq); u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) @@ -107,11 +113,12 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET -static u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr) +u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr) { if (sysctl_tcp_timestamps != 1) return 0; + ts_secret_init(); return siphash_2u32((__force u32)saddr, (__force u32)daddr, &ts_secret); } @@ -121,15 +128,15 @@ static u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr) * it would be easy enough to have the former function use siphash_4u32, passing * the arguments as separate u32. */ -u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport, u32 *tsoff) +u32 secure_tcp_seq(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) { - u64 hash; + u32 hash; + net_secret_init(); hash = siphash_3u32((__force u32)saddr, (__force u32)daddr, (__force u32)sport << 16 | (__force u32)dport, &net_secret); - *tsoff = secure_tcp_ts_off(saddr, daddr); return seq_scale(hash); } diff --git a/net/core/sock.c b/net/core/sock.c index b5baeb9cb0fb..79c6aee6af9b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -102,6 +102,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> @@ -372,14 +373,14 @@ EXPORT_SYMBOL_GPL(sk_clear_memalloc); int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { int ret; - unsigned long pflags = current->flags; + unsigned int noreclaim_flag; /* these should have been dropped before queueing */ BUG_ON(!sock_flag(sk, SOCK_MEMALLOC)); - current->flags |= PF_MEMALLOC; + noreclaim_flag = memalloc_noreclaim_save(); ret = sk->sk_backlog_rcv(sk, skb); - current_restore_flags(pflags, PF_MEMALLOC); + memalloc_noreclaim_restore(noreclaim_flag); return ret; } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b99168b0fabf..f75482bdee9a 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -951,7 +951,7 @@ static struct proto dccp_v4_prot = { .orphan_count = &dccp_orphan_count, .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, + .slab_flags = SLAB_TYPESAFE_BY_RCU, .rsk_prot = &dccp_request_sock_ops, .twsk_prot = &dccp_timewait_sock_ops, .h.hashinfo = &dccp_hashinfo, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index d9b6a4e403e7..840f14aaa016 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1014,7 +1014,7 @@ static struct proto dccp_v6_prot = { .orphan_count = &dccp_orphan_count, .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp6_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, + .slab_flags = SLAB_TYPESAFE_BY_RCU, .rsk_prot = &dccp6_request_sock_ops, .twsk_prot = &dccp6_timewait_sock_ops, .h.hashinfo = &dccp_hashinfo, diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 9afa2a5030b2..405483a07efc 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -2361,7 +2361,8 @@ MODULE_AUTHOR("Linux DECnet Project Team"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_DECnet); -static char banner[] __initdata = KERN_INFO "NET4: DECnet for Linux: V.2.5.68s (C) 1995-2003 Linux DECnet Project Team\n"; +static const char banner[] __initconst = KERN_INFO +"NET4: DECnet for Linux: V.2.5.68s (C) 1995-2003 Linux DECnet Project Team\n"; static int __init decnet_init(void) { diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 482730cd8a56..eeb5fc561f80 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -110,7 +110,7 @@ struct neigh_table dn_neigh_table = { static int dn_neigh_construct(struct neighbour *neigh) { struct net_device *dev = neigh->dev; - struct dn_neigh *dn = (struct dn_neigh *)neigh; + struct dn_neigh *dn = container_of(neigh, struct dn_neigh, n); struct dn_dev *dn_db; struct neigh_parms *parms; @@ -339,7 +339,7 @@ int dn_to_neigh_output(struct net *net, struct sock *sk, struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *) dst; struct neighbour *neigh = rt->n; - struct dn_neigh *dn = (struct dn_neigh *)neigh; + struct dn_neigh *dn = container_of(neigh, struct dn_neigh, n); struct dn_dev *dn_db; bool use_long; @@ -391,7 +391,7 @@ int dn_neigh_router_hello(struct net *net, struct sock *sk, struct sk_buff *skb) neigh = __neigh_lookup(&dn_neigh_table, &src, skb->dev, 1); - dn = (struct dn_neigh *)neigh; + dn = container_of(neigh, struct dn_neigh, n); if (neigh) { write_lock(&neigh->lock); @@ -451,7 +451,7 @@ int dn_neigh_endnode_hello(struct net *net, struct sock *sk, struct sk_buff *skb neigh = __neigh_lookup(&dn_neigh_table, &src, skb->dev, 1); - dn = (struct dn_neigh *)neigh; + dn = container_of(neigh, struct dn_neigh, n); if (neigh) { write_lock(&neigh->lock); @@ -510,7 +510,7 @@ static void neigh_elist_cb(struct neighbour *neigh, void *_info) if (neigh->dev != s->dev) return; - dn = (struct dn_neigh *) neigh; + dn = container_of(neigh, struct dn_neigh, n); if (!(dn->flags & (DN_NDFLAG_R1|DN_NDFLAG_R2))) return; @@ -549,7 +549,7 @@ int dn_neigh_elist(struct net_device *dev, unsigned char *ptr, int n) static inline void dn_neigh_format_entry(struct seq_file *seq, struct neighbour *n) { - struct dn_neigh *dn = (struct dn_neigh *) n; + struct dn_neigh *dn = container_of(n, struct dn_neigh, n); char buf[DN_ASCBUF_LEN]; read_lock(&n->lock); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 5e313c1ac94f..1054d330bf9d 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -794,6 +794,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, /* listeners have SOCK_RCU_FREE, not the children */ sock_reset_flag(newsk, SOCK_RCU_FREE); + inet_sk(newsk)->mc_list = NULL; + newsk->sk_mark = inet_rsk(req)->ir_mark; atomic64_set(&newsk->sk_cookie, atomic64_read(&inet_rsk(req)->ir_cookie)); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 8bea74298173..e9a59d2d91d4 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -678,11 +678,7 @@ int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo) /* no more locks than number of hash buckets */ nblocks = min(nblocks, hashinfo->ehash_mask + 1); - hashinfo->ehash_locks = kmalloc_array(nblocks, locksz, - GFP_KERNEL | __GFP_NOWARN); - if (!hashinfo->ehash_locks) - hashinfo->ehash_locks = vmalloc(nblocks * locksz); - + hashinfo->ehash_locks = kvmalloc_array(nblocks, locksz, GFP_KERNEL); if (!hashinfo->ehash_locks) return -ENOMEM; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 40977413fd48..4ec9affb2252 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -546,12 +546,13 @@ static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev) struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm *p = &t->parms; - nla_put_u32(skb, IFLA_VTI_LINK, p->link); - nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key); - nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key); - nla_put_in_addr(skb, IFLA_VTI_LOCAL, p->iph.saddr); - nla_put_in_addr(skb, IFLA_VTI_REMOTE, p->iph.daddr); - nla_put_u32(skb, IFLA_VTI_FWMARK, t->fwmark); + if (nla_put_u32(skb, IFLA_VTI_LINK, p->link) || + nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key) || + nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key) || + nla_put_in_addr(skb, IFLA_VTI_LOCAL, p->iph.saddr) || + nla_put_in_addr(skb, IFLA_VTI_REMOTE, p->iph.daddr) || + nla_put_u32(skb, IFLA_VTI_FWMARK, t->fwmark)) + return -EMSGSIZE; return 0; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 9d943974de2b..bdffad875691 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -358,6 +358,9 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, rt->dst.dev->mtu); return -EMSGSIZE; } + if (length < sizeof(struct iphdr)) + return -EINVAL; + if (flags&MSG_PROBE) goto out; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 496b97e17aaf..0257d965f111 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -16,6 +16,7 @@ #include <linux/siphash.h> #include <linux/kernel.h> #include <linux/export.h> +#include <net/secure_seq.h> #include <net/tcp.h> #include <net/route.h> @@ -203,7 +204,7 @@ EXPORT_SYMBOL_GPL(__cookie_v4_check); struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct dst_entry *dst) + struct dst_entry *dst, u32 tsoff) { struct inet_connection_sock *icsk = inet_csk(sk); struct sock *child; @@ -213,6 +214,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, NULL, &own_req); if (child) { atomic_set(&req->rsk_refcnt, 1); + tcp_sk(child)->tsoffset = tsoff; sock_rps_save_rxhash(child, skb); inet_csk_reqsk_queue_add(sk, req, child); } else { @@ -292,6 +294,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) struct rtable *rt; __u8 rcv_wscale; struct flowi4 fl4; + u32 tsoff = 0; if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst) goto out; @@ -311,6 +314,11 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) memset(&tcp_opt, 0, sizeof(tcp_opt)); tcp_parse_options(skb, &tcp_opt, 0, NULL); + if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { + tsoff = secure_tcp_ts_off(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); + tcp_opt.rcv_tsecr -= tsoff; + } + if (!cookie_timestamp_decode(&tcp_opt)) goto out; @@ -381,7 +389,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), &rt->dst); - ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst); + ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst, tsoff); /* ip_queue_xmit() depends on our flow being setup * Normal sockets get it right from inet_csk_route_child_sock() */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9739962bfb3f..5a3ad09e2786 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -85,7 +85,6 @@ int sysctl_tcp_dsack __read_mostly = 1; int sysctl_tcp_app_win __read_mostly = 31; int sysctl_tcp_adv_win_scale __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); -EXPORT_SYMBOL(sysctl_tcp_timestamps); /* rfc5961 challenge ack rate limiting */ int sysctl_tcp_challenge_ack_limit = 1000; @@ -6347,8 +6346,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (security_inet_conn_request(sk, skb, req)) goto drop_and_free; - if (isn && tmp_opt.tstamp_ok) - af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off); + if (tmp_opt.tstamp_ok) + tcp_rsk(req)->ts_off = af_ops->init_ts_off(skb); if (!want_cookie && !isn) { /* Kill the following clause, if you dislike this way. */ @@ -6368,7 +6367,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_release; } - isn = af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off); + isn = af_ops->init_seq(skb); } if (!dst) { dst = af_ops->route_req(sk, &fl, req); @@ -6380,7 +6379,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (want_cookie) { isn = cookie_init_sequence(af_ops, sk, skb, &req->mss); - tcp_rsk(req)->ts_off = 0; req->cookie_ts = tmp_opt.tstamp_ok; if (!tmp_opt.tstamp_ok) inet_rsk(req)->ecn_ok = 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index cbbafe546c0f..5ab2aac5ca19 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -94,12 +94,18 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, struct inet_hashinfo tcp_hashinfo; EXPORT_SYMBOL(tcp_hashinfo); -static u32 tcp_v4_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff) +static u32 tcp_v4_init_seq(const struct sk_buff *skb) { - return secure_tcp_seq_and_tsoff(ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source, tsoff); + return secure_tcp_seq(ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); +} + +static u32 tcp_v4_init_ts_off(const struct sk_buff *skb) +{ + return secure_tcp_ts_off(ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) @@ -145,7 +151,6 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct flowi4 *fl4; struct rtable *rt; int err; - u32 seq; struct ip_options_rcu *inet_opt; struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; @@ -232,13 +237,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) rt = NULL; if (likely(!tp->repair)) { - seq = secure_tcp_seq_and_tsoff(inet->inet_saddr, - inet->inet_daddr, - inet->inet_sport, - usin->sin_port, - &tp->tsoffset); if (!tp->write_seq) - tp->write_seq = seq; + tp->write_seq = secure_tcp_seq(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port); + tp->tsoffset = secure_tcp_ts_off(inet->inet_saddr, + inet->inet_daddr); } inet->inet_id = tp->write_seq ^ jiffies; @@ -1239,7 +1244,8 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .cookie_init_seq = cookie_v4_init_sequence, #endif .route_req = tcp_v4_route_req, - .init_seq_tsoff = tcp_v4_init_seq_and_tsoff, + .init_seq = tcp_v4_init_seq, + .init_ts_off = tcp_v4_init_ts_off, .send_synack = tcp_v4_send_synack, }; @@ -2389,7 +2395,7 @@ struct proto tcp_prot = { .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, + .slab_flags = SLAB_TYPESAFE_BY_RCU, .twsk_prot = &tcp_timewait_sock_ops, .rsk_prot = &tcp_request_sock_ops, .h.hashinfo = &tcp_hashinfo, diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 9d0d4f39e42b..653bbd67e3a3 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -1011,10 +1011,7 @@ static int __net_init tcp_net_metrics_init(struct net *net) tcp_metrics_hash_log = order_base_2(slots); size = sizeof(struct tcpm_hash_bucket) << tcp_metrics_hash_log; - tcp_metrics_hash = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); - if (!tcp_metrics_hash) - tcp_metrics_hash = vzalloc(size); - + tcp_metrics_hash = kvzalloc(size, GFP_KERNEL); if (!tcp_metrics_hash) return -ENOMEM; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 8f6373b0cd77..717be4de5324 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -523,6 +523,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; newtp->rx_opt.mss_clamp = req->mss; tcp_ecn_openreq_child(newtp, req); + newtp->fastopen_req = NULL; newtp->fastopen_rsk = NULL; newtp->syn_data_acked = 0; newtp->rack.mstamp.v64 = 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 60111a0fc201..4858e190f6ac 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1514,6 +1514,7 @@ static void tcp_cwnd_application_limited(struct sock *sk) static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) { + const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; struct tcp_sock *tp = tcp_sk(sk); /* Track the maximum number of outstanding packets in each @@ -1536,7 +1537,8 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) tp->snd_cwnd_used = tp->packets_out; if (sysctl_tcp_slow_start_after_idle && - (s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto) + (s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && + !ca_ops->cong_control) tcp_cwnd_application_limited(sk); /* The following conditions together indicate the starvation diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b09ac38d8dc4..8d297a79b568 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3328,7 +3328,8 @@ static int fixup_permanent_addr(struct inet6_dev *idev, idev->dev, 0, 0); } - addrconf_dad_start(ifp); + if (ifp->state == INET6_IFADDR_STATE_PREDAD) + addrconf_dad_start(ifp); return 0; } @@ -3547,6 +3548,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, */ static struct notifier_block ipv6_dev_notf = { .notifier_call = addrconf_notify, + .priority = ADDRCONF_NOTIFY_PRIORITY, }; static void addrconf_type_change(struct net_device *dev, unsigned long event) @@ -3683,7 +3685,7 @@ restart: if (keep) { /* set state to skip the notifier below */ state = INET6_IFADDR_STATE_DEAD; - ifa->state = 0; + ifa->state = INET6_IFADDR_STATE_PREDAD; if (!(ifa->flags & IFA_F_NODAD)) ifa->flags |= IFA_F_TENTATIVE; @@ -6572,6 +6574,8 @@ int __init addrconf_init(void) goto errlo; } + ip6_route_init_special_entries(); + for (i = 0; i < IN6_ADDR_HSIZE; i++) INIT_HLIST_HEAD(&inet6_addr_lst[i]); diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index af8f52ee7180..2fd5ca151dcf 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -41,13 +41,7 @@ static int alloc_ila_locks(struct ila_net *ilan) size = roundup_pow_of_two(nr_pcpus * LOCKS_PER_CPU); if (sizeof(spinlock_t) != 0) { -#ifdef CONFIG_NUMA - if (size * sizeof(spinlock_t) > PAGE_SIZE) - ilan->locks = vmalloc(size * sizeof(spinlock_t)); - else -#endif - ilan->locks = kmalloc_array(size, sizeof(spinlock_t), - GFP_KERNEL); + ilan->locks = kvmalloc(size * sizeof(spinlock_t), GFP_KERNEL); if (!ilan->locks) return -ENOMEM; for (i = 0; i < size; i++) diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index bf3ad3e7b647..b2b4f031b3a1 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -235,7 +235,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, inside->icmp6.icmp6_cksum = csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len - hdrlen, IPPROTO_ICMPV6, - csum_partial(&inside->icmp6, + skb_checksum(skb, hdrlen, skb->len - hdrlen, 0)); } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 0da6a12b5472..1f992d9e261d 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -632,6 +632,8 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu); return -EMSGSIZE; } + if (length < sizeof(struct ipv6hdr)) + return -EINVAL; if (flags&MSG_PROBE) goto out; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a1bf426c959b..dc61b0b5e64e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3709,7 +3709,10 @@ static int ip6_route_dev_notify(struct notifier_block *this, struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); - if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) { + if (!(dev->flags & IFF_LOOPBACK)) + return NOTIFY_OK; + + if (event == NETDEV_REGISTER) { net->ipv6.ip6_null_entry->dst.dev = dev; net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES @@ -3718,6 +3721,12 @@ static int ip6_route_dev_notify(struct notifier_block *this, net->ipv6.ip6_blk_hole_entry->dst.dev = dev; net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev); #endif + } else if (event == NETDEV_UNREGISTER) { + in6_dev_put(net->ipv6.ip6_null_entry->rt6i_idev); +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + in6_dev_put(net->ipv6.ip6_prohibit_entry->rt6i_idev); + in6_dev_put(net->ipv6.ip6_blk_hole_entry->rt6i_idev); +#endif } return NOTIFY_OK; @@ -4024,9 +4033,24 @@ static struct pernet_operations ip6_route_net_late_ops = { static struct notifier_block ip6_route_dev_notifier = { .notifier_call = ip6_route_dev_notify, - .priority = 0, + .priority = ADDRCONF_NOTIFY_PRIORITY - 10, }; +void __init ip6_route_init_special_entries(void) +{ + /* Registering of the loopback is done before this portion of code, + * the loopback reference in rt6_info will not be taken, do it + * manually for init_net */ + init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); + #ifdef CONFIG_IPV6_MULTIPLE_TABLES + init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); + init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); + #endif +} + int __init ip6_route_init(void) { int ret; @@ -4053,17 +4077,6 @@ int __init ip6_route_init(void) ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep; - /* Registering of the loopback is done before this portion of code, - * the loopback reference in rt6_info will not be taken, do it - * manually for init_net */ - init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev; - init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); - #ifdef CONFIG_IPV6_MULTIPLE_TABLES - init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev; - init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); - init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev; - init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); - #endif ret = fib6_init(); if (ret) goto out_register_subsys; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 895ff650db43..5abc3692b901 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -18,6 +18,7 @@ #include <linux/random.h> #include <linux/siphash.h> #include <linux/kernel.h> +#include <net/secure_seq.h> #include <net/ipv6.h> #include <net/tcp.h> @@ -143,6 +144,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) int mss; struct dst_entry *dst; __u8 rcv_wscale; + u32 tsoff = 0; if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst) goto out; @@ -162,6 +164,12 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) memset(&tcp_opt, 0, sizeof(tcp_opt)); tcp_parse_options(skb, &tcp_opt, 0, NULL); + if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { + tsoff = secure_tcpv6_ts_off(ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32); + tcp_opt.rcv_tsecr -= tsoff; + } + if (!cookie_timestamp_decode(&tcp_opt)) goto out; @@ -242,7 +250,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), dst); - ret = tcp_get_cookie_sock(sk, skb, req, dst); + ret = tcp_get_cookie_sock(sk, skb, req, dst, tsoff); out: return ret; out_free: diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 8e42e8f54b70..7a8237acd210 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -101,12 +101,18 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) } } -static u32 tcp_v6_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff) +static u32 tcp_v6_init_seq(const struct sk_buff *skb) { - return secure_tcpv6_seq_and_tsoff(ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source, tsoff); + return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); +} + +static u32 tcp_v6_init_ts_off(const struct sk_buff *skb) +{ + return secure_tcpv6_ts_off(ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32); } static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, @@ -122,7 +128,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct flowi6 fl6; struct dst_entry *dst; int addr_type; - u32 seq; int err; struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; @@ -282,13 +287,13 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk_set_txhash(sk); if (likely(!tp->repair)) { - seq = secure_tcpv6_seq_and_tsoff(np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32, - inet->inet_sport, - inet->inet_dport, - &tp->tsoffset); if (!tp->write_seq) - tp->write_seq = seq; + tp->write_seq = secure_tcpv6_seq(np->saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport); + tp->tsoffset = secure_tcpv6_ts_off(np->saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32); } if (tcp_fastopen_defer_connect(sk, &err)) @@ -749,7 +754,8 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .cookie_init_seq = cookie_v6_init_sequence, #endif .route_req = tcp_v6_route_req, - .init_seq_tsoff = tcp_v6_init_seq_and_tsoff, + .init_seq = tcp_v6_init_seq, + .init_ts_off = tcp_v6_init_ts_off, .send_synack = tcp_v6_send_synack, }; @@ -1911,7 +1917,7 @@ struct proto tcpv6_prot = { .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, + .slab_flags = SLAB_TYPESAFE_BY_RCU, .twsk_prot = &tcp6_timewait_sock_ops, .rsk_prot = &tcp6_request_sock_ops, .h.hashinfo = &tcp_hashinfo, diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index cb4fff785cbf..8364fe5b59e4 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -142,7 +142,7 @@ static struct proto llc_proto = { .name = "LLC", .owner = THIS_MODULE, .obj_size = sizeof(struct llc_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, + .slab_flags = SLAB_TYPESAFE_BY_RCU, }; /** diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 8bc5a1bd2d45..9b02c13d258b 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -506,7 +506,7 @@ static struct sock *__llc_lookup_established(struct llc_sap *sap, again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_estab_match(sap, daddr, laddr, rc)) { - /* Extra checks required by SLAB_DESTROY_BY_RCU */ + /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || @@ -565,7 +565,7 @@ static struct sock *__llc_lookup_listener(struct llc_sap *sap, again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_listener_match(sap, laddr, rc)) { - /* Extra checks required by SLAB_DESTROY_BY_RCU */ + /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index 5404d0d195cc..63b6ab056370 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -328,7 +328,7 @@ static struct sock *llc_lookup_dgram(struct llc_sap *sap, again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_dgram_match(sap, laddr, rc)) { - /* Extra checks required by SLAB_DESTROY_BY_RCU */ + /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 6db09fa18269..364d4e137649 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -66,6 +66,8 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata, 2 + (IEEE80211_MAX_SUPP_RATES - 8) + 2 + sizeof(struct ieee80211_ht_cap) + 2 + sizeof(struct ieee80211_ht_operation) + + 2 + sizeof(struct ieee80211_vht_cap) + + 2 + sizeof(struct ieee80211_vht_operation) + ifibss->ie_len; presp = kzalloc(sizeof(*presp) + frame_len, GFP_KERNEL); if (!presp) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 89dff563b1ec..0ea9712bd99e 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4382,6 +4382,10 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, if (WARN_ON(!ifmgd->auth_data && !ifmgd->assoc_data)) return -EINVAL; + /* If a reconfig is happening, bail out */ + if (local->in_reconfig) + return -EBUSY; + if (assoc) { rcu_read_lock(); have_sta = sta_info_get(sdata, cbss->bssid); diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 088e2b459d0f..257ec66009da 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -2005,10 +2005,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) unsigned index; if (size) { - labels = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); - if (!labels) - labels = vzalloc(size); - + labels = kvzalloc(size, GFP_KERNEL); if (!labels) goto nolabels; } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 668d9643f0cc..1fa3c2307b6e 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3078,6 +3078,17 @@ nla_put_failure: return skb->len; } +static bool ip_vs_is_af_valid(int af) +{ + if (af == AF_INET) + return true; +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6 && ipv6_mod_enabled()) + return true; +#endif + return false; +} + static int ip_vs_genl_parse_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *usvc, struct nlattr *nla, int full_entry, @@ -3105,11 +3116,7 @@ static int ip_vs_genl_parse_service(struct netns_ipvs *ipvs, memset(usvc, 0, sizeof(*usvc)); usvc->af = nla_get_u16(nla_af); -#ifdef CONFIG_IP_VS_IPV6 - if (usvc->af != AF_INET && usvc->af != AF_INET6) -#else - if (usvc->af != AF_INET) -#endif + if (!ip_vs_is_af_valid(usvc->af)) return -EAFNOSUPPORT; if (nla_fwmark) { @@ -3612,6 +3619,11 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) if (udest.af == 0) udest.af = svc->af; + if (!ip_vs_is_af_valid(udest.af)) { + ret = -EAFNOSUPPORT; + goto out; + } + if (udest.af != svc->af && cmd != IPVS_CMD_DEL_DEST) { /* The synchronization protocol is incompatible * with mixed family services diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index f9245dbfe435..e847dbaa0c6b 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -911,7 +911,7 @@ static unsigned int early_drop_list(struct net *net, continue; /* kill only if still in same netns -- might have moved due to - * SLAB_DESTROY_BY_RCU rules. + * SLAB_TYPESAFE_BY_RCU rules. * * We steal the timer reference. If that fails timer has * already fired or someone else deleted it. Just drop ref @@ -1114,7 +1114,7 @@ __nf_conntrack_alloc(struct net *net, /* * Do not use kmem_cache_zalloc(), as this cache uses - * SLAB_DESTROY_BY_RCU. + * SLAB_TYPESAFE_BY_RCU. */ ct = kmem_cache_alloc(nf_conntrack_cachep, gfp); if (ct == NULL) @@ -1159,7 +1159,7 @@ void nf_conntrack_free(struct nf_conn *ct) struct net *net = nf_ct_net(ct); /* A freed object has refcnt == 0, that's - * the golden rule for SLAB_DESTROY_BY_RCU + * the golden rule for SLAB_TYPESAFE_BY_RCU */ NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0); @@ -1853,7 +1853,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize); module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, &nf_conntrack_htable_size, 0600); -static unsigned int total_extension_size(void) +static __always_inline unsigned int total_extension_size(void) { /* remember to add new extensions below */ BUILD_BUG_ON(NF_CT_EXT_NUM > 9); @@ -1929,7 +1929,7 @@ int nf_conntrack_init_start(void) nf_conntrack_cachep = kmem_cache_create("nf_conntrack", sizeof(struct nf_conn), NFCT_INFOMASK + 1, - SLAB_DESTROY_BY_RCU | SLAB_HWCACHE_ALIGN, NULL); + SLAB_TYPESAFE_BY_RCU | SLAB_HWCACHE_ALIGN, NULL); if (!nf_conntrack_cachep) goto err_cachep; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 4b9dfe3eef62..3a60efa7799b 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -385,7 +385,7 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) struct nf_conntrack_tuple_mask mask = { .src.u.all = htons(0xFFFF) }; unsigned int h = helper_hash(&me->tuple); struct nf_conntrack_helper *cur; - int ret = 0; + int ret = 0, i; BUG_ON(me->expect_policy == NULL); BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES); @@ -395,10 +395,26 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) return -EINVAL; mutex_lock(&nf_ct_helper_mutex); - hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) { - if (nf_ct_tuple_src_mask_cmp(&cur->tuple, &me->tuple, &mask)) { - ret = -EEXIST; - goto out; + for (i = 0; i < nf_ct_helper_hsize; i++) { + hlist_for_each_entry(cur, &nf_ct_helper_hash[i], hnode) { + if (!strcmp(cur->name, me->name) && + (cur->tuple.src.l3num == NFPROTO_UNSPEC || + cur->tuple.src.l3num == me->tuple.src.l3num) && + cur->tuple.dst.protonum == me->tuple.dst.protonum) { + ret = -EEXIST; + goto out; + } + } + } + + /* avoid unpredictable behaviour for auto_assign_helper */ + if (!(me->flags & NF_CT_HELPER_F_USERSPACE)) { + hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) { + if (nf_ct_tuple_src_mask_cmp(&cur->tuple, &me->tuple, + &mask)) { + ret = -EEXIST; + goto out; + } } } hlist_add_head_rcu(&me->hnode, &nf_ct_helper_hash[h]); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 5f6f2f388928..dcf561b5c97a 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -417,8 +417,7 @@ nla_put_failure: return -1; } -static int ctnetlink_dump_ct_seq_adj(struct sk_buff *skb, - const struct nf_conn *ct) +static int ctnetlink_dump_ct_seq_adj(struct sk_buff *skb, struct nf_conn *ct) { struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); struct nf_ct_seqadj *seq; @@ -426,15 +425,20 @@ static int ctnetlink_dump_ct_seq_adj(struct sk_buff *skb, if (!(ct->status & IPS_SEQ_ADJUST) || !seqadj) return 0; + spin_lock_bh(&ct->lock); seq = &seqadj->seq[IP_CT_DIR_ORIGINAL]; if (dump_ct_seq_adj(skb, seq, CTA_SEQ_ADJ_ORIG) == -1) - return -1; + goto err; seq = &seqadj->seq[IP_CT_DIR_REPLY]; if (dump_ct_seq_adj(skb, seq, CTA_SEQ_ADJ_REPLY) == -1) - return -1; + goto err; + spin_unlock_bh(&ct->lock); return 0; +err: + spin_unlock_bh(&ct->lock); + return -1; } static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct) @@ -1417,6 +1421,24 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, } #endif +static void +__ctnetlink_change_status(struct nf_conn *ct, unsigned long on, + unsigned long off) +{ + unsigned int bit; + + /* Ignore these unchangable bits */ + on &= ~IPS_UNCHANGEABLE_MASK; + off &= ~IPS_UNCHANGEABLE_MASK; + + for (bit = 0; bit < __IPS_MAX_BIT; bit++) { + if (on & (1 << bit)) + set_bit(bit, &ct->status); + else if (off & (1 << bit)) + clear_bit(bit, &ct->status); + } +} + static int ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[]) { @@ -1436,10 +1458,7 @@ ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[]) /* ASSURED bit can only be set */ return -EBUSY; - /* Be careful here, modifying NAT bits can screw up things, - * so don't let users modify them directly if they don't pass - * nf_nat_range. */ - ct->status |= status & ~(IPS_NAT_DONE_MASK | IPS_NAT_MASK); + __ctnetlink_change_status(ct, status, 0); return 0; } @@ -1508,23 +1527,11 @@ static int ctnetlink_change_helper(struct nf_conn *ct, return 0; } + rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper == NULL) { -#ifdef CONFIG_MODULES - spin_unlock_bh(&nf_conntrack_expect_lock); - - if (request_module("nfct-helper-%s", helpname) < 0) { - spin_lock_bh(&nf_conntrack_expect_lock); - return -EOPNOTSUPP; - } - - spin_lock_bh(&nf_conntrack_expect_lock); - helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), - nf_ct_protonum(ct)); - if (helper) - return -EAGAIN; -#endif + rcu_read_unlock(); return -EOPNOTSUPP; } @@ -1533,13 +1540,16 @@ static int ctnetlink_change_helper(struct nf_conn *ct, /* update private helper data if allowed. */ if (helper->from_nlattr) helper->from_nlattr(helpinfo, ct); - return 0; + err = 0; } else - return -EBUSY; + err = -EBUSY; + } else { + /* we cannot set a helper for an existing conntrack */ + err = -EOPNOTSUPP; } - /* we cannot set a helper for an existing conntrack */ - return -EOPNOTSUPP; + rcu_read_unlock(); + return err; } static int ctnetlink_change_timeout(struct nf_conn *ct, @@ -1630,25 +1640,30 @@ ctnetlink_change_seq_adj(struct nf_conn *ct, if (!seqadj) return 0; + spin_lock_bh(&ct->lock); if (cda[CTA_SEQ_ADJ_ORIG]) { ret = change_seq_adj(&seqadj->seq[IP_CT_DIR_ORIGINAL], cda[CTA_SEQ_ADJ_ORIG]); if (ret < 0) - return ret; + goto err; - ct->status |= IPS_SEQ_ADJUST; + set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); } if (cda[CTA_SEQ_ADJ_REPLY]) { ret = change_seq_adj(&seqadj->seq[IP_CT_DIR_REPLY], cda[CTA_SEQ_ADJ_REPLY]); if (ret < 0) - return ret; + goto err; - ct->status |= IPS_SEQ_ADJUST; + set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); } + spin_unlock_bh(&ct->lock); return 0; +err: + spin_unlock_bh(&ct->lock); + return ret; } static int @@ -1959,9 +1974,7 @@ static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, err = -EEXIST; ct = nf_ct_tuplehash_to_ctrack(h); if (!(nlh->nlmsg_flags & NLM_F_EXCL)) { - spin_lock_bh(&nf_conntrack_expect_lock); err = ctnetlink_change_conntrack(ct, cda); - spin_unlock_bh(&nf_conntrack_expect_lock); if (err == 0) { nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | @@ -2294,10 +2307,10 @@ ctnetlink_update_status(struct nf_conn *ct, const struct nlattr * const cda[]) /* This check is less strict than ctnetlink_change_status() * because callers often flip IPS_EXPECTED bits when sending * an NFQA_CT attribute to the kernel. So ignore the - * unchangeable bits but do not error out. + * unchangeable bits but do not error out. Also user programs + * are allowed to clear the bits that they are allowed to change. */ - ct->status = (status & ~IPS_UNCHANGEABLE_MASK) | - (ct->status & IPS_UNCHANGEABLE_MASK); + __ctnetlink_change_status(ct, status, ~status); return 0; } @@ -2351,11 +2364,7 @@ ctnetlink_glue_parse(const struct nlattr *attr, struct nf_conn *ct) if (ret < 0) return ret; - spin_lock_bh(&nf_conntrack_expect_lock); - ret = ctnetlink_glue_parse_ct((const struct nlattr **)cda, ct); - spin_unlock_bh(&nf_conntrack_expect_lock); - - return ret; + return ctnetlink_glue_parse_ct((const struct nlattr **)cda, ct); } static int ctnetlink_glue_exp_parse(const struct nlattr * const *cda, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1c6482d2c4dc..559225029740 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3778,6 +3778,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = set->ops->insert(ctx->net, set, &elem, &ext2); if (err) { if (err == -EEXIST) { + if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) ^ + nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) || + nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) ^ + nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF)) + return -EBUSY; if ((nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) && memcmp(nft_set_ext_data(ext), diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 3948da380259..66221ad891a9 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -82,8 +82,7 @@ static void nft_dynset_eval(const struct nft_expr *expr, nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { timeout = priv->timeout ? : set->timeout; *nft_set_ext_expiration(ext) = jiffies + timeout; - } else if (sexpr == NULL) - goto out; + } if (sexpr != NULL) sexpr->ops->eval(sexpr, regs, pkt); @@ -92,7 +91,7 @@ static void nft_dynset_eval(const struct nft_expr *expr, regs->verdict.code = NFT_BREAK; return; } -out: + if (!priv->invert) regs->verdict.code = NFT_BREAK; } diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 8ebbc2940f4c..b988162b5b15 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -257,6 +257,11 @@ static int nft_bitmap_init(const struct nft_set *set, static void nft_bitmap_destroy(const struct nft_set *set) { + struct nft_bitmap *priv = nft_set_priv(set); + struct nft_bitmap_elem *be, *n; + + list_for_each_entry_safe(be, n, &priv->list, head) + nft_set_elem_destroy(set, be, true); } static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 14857afc9937..8876b7da6884 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -763,17 +763,8 @@ EXPORT_SYMBOL(xt_check_entry_offsets); */ unsigned int *xt_alloc_entry_offsets(unsigned int size) { - unsigned int *off; + return kvmalloc_array(size, sizeof(unsigned int), GFP_KERNEL | __GFP_ZERO); - off = kcalloc(size, sizeof(unsigned int), GFP_KERNEL | __GFP_NOWARN); - - if (off) - return off; - - if (size < (SIZE_MAX / sizeof(unsigned int))) - off = vmalloc(size * sizeof(unsigned int)); - - return off; } EXPORT_SYMBOL(xt_alloc_entry_offsets); @@ -1007,8 +998,7 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size) if (sz <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) info = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); if (!info) { - info = __vmalloc(sz, GFP_KERNEL | __GFP_NOWARN | - __GFP_NORETRY | __GFP_HIGHMEM, + info = __vmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY, PAGE_KERNEL); if (!info) return NULL; @@ -1051,8 +1041,10 @@ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, list_for_each_entry(t, &init_net.xt.tables[af], list) { if (strcmp(t->name, name)) continue; - if (!try_module_get(t->me)) + if (!try_module_get(t->me)) { + mutex_unlock(&xt[af].mutex); return NULL; + } mutex_unlock(&xt[af].mutex); if (t->table_init(net) != 0) { @@ -1114,7 +1106,7 @@ static int xt_jumpstack_alloc(struct xt_table_info *i) size = sizeof(void **) * nr_cpu_ids; if (size > PAGE_SIZE) - i->jumpstack = vzalloc(size); + i->jumpstack = kvzalloc(size, GFP_KERNEL); else i->jumpstack = kzalloc(size, GFP_KERNEL); if (i->jumpstack == NULL) @@ -1136,12 +1128,8 @@ static int xt_jumpstack_alloc(struct xt_table_info *i) */ size = sizeof(void *) * i->stacksize * 2u; for_each_possible_cpu(cpu) { - if (size > PAGE_SIZE) - i->jumpstack[cpu] = vmalloc_node(size, - cpu_to_node(cpu)); - else - i->jumpstack[cpu] = kmalloc_node(size, - GFP_KERNEL, cpu_to_node(cpu)); + i->jumpstack[cpu] = kvmalloc_node(size, GFP_KERNEL, + cpu_to_node(cpu)); if (i->jumpstack[cpu] == NULL) /* * Freeing will be done later on by the callers. The diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 3cbe1bcf6a74..bb7ad82dcd56 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -168,8 +168,10 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, goto err_put_timeout; } timeout_ext = nf_ct_timeout_ext_add(ct, timeout, GFP_ATOMIC); - if (timeout_ext == NULL) + if (!timeout_ext) { ret = -ENOMEM; + goto err_put_timeout; + } rcu_read_unlock(); return ret; @@ -201,6 +203,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, struct xt_ct_target_info_v1 *info) { struct nf_conntrack_zone zone; + struct nf_conn_help *help; struct nf_conn *ct; int ret = -EOPNOTSUPP; @@ -249,7 +252,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, if (info->timeout[0]) { ret = xt_ct_set_timeout(ct, par, info->timeout); if (ret < 0) - goto err3; + goto err4; } __set_bit(IPS_CONFIRMED_BIT, &ct->status); nf_conntrack_get(&ct->ct_general); @@ -257,6 +260,10 @@ out: info->ct = ct; return 0; +err4: + help = nfct_help(ct); + if (help) + module_put(help->helper->me); err3: nf_ct_tmpl_free(ct); err2: diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 37d581a31cff..3f6c4fa78bdb 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -388,10 +388,7 @@ static int recent_mt_check(const struct xt_mtchk_param *par, } sz = sizeof(*t) + sizeof(t->iphash[0]) * ip_list_hash_size; - if (sz <= PAGE_SIZE) - t = kzalloc(sz, GFP_KERNEL); - else - t = vzalloc(sz); + t = kvzalloc(sz, GFP_KERNEL); if (t == NULL) { ret = -ENOMEM; goto out; diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 770bbec878f1..e75ef39669c5 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -152,7 +152,7 @@ static int socket_mt_enable_defrag(struct net *net, int family) switch (family) { case NFPROTO_IPV4: return nf_defrag_ipv4_enable(net); -#ifdef XT_SOCKET_HAVE_IPV6 +#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) case NFPROTO_IPV6: return nf_defrag_ipv6_enable(net); #endif diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 42a95919df09..bf602e33c40a 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -516,10 +516,38 @@ ovs_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone, u16 proto, const struct sk_buff *skb) { struct nf_conntrack_tuple tuple; + struct nf_conntrack_expect *exp; if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, net, &tuple)) return NULL; - return __nf_ct_expect_find(net, zone, &tuple); + + exp = __nf_ct_expect_find(net, zone, &tuple); + if (exp) { + struct nf_conntrack_tuple_hash *h; + + /* Delete existing conntrack entry, if it clashes with the + * expectation. This can happen since conntrack ALGs do not + * check for clashes between (new) expectations and existing + * conntrack entries. nf_conntrack_in() will check the + * expectations only if a conntrack entry can not be found, + * which can lead to OVS finding the expectation (here) in the + * init direction, but which will not be removed by the + * nf_conntrack_in() call, if a matching conntrack entry is + * found instead. In this case all init direction packets + * would be reported as new related packets, while reply + * direction packets would be reported as un-related + * established packets. + */ + h = nf_conntrack_find_get(net, zone, &tuple); + if (h) { + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); + + nf_ct_delete(ct, 0, 0); + nf_conntrack_put(&ct->ct_general); + } + } + + return exp; } /* This replicates logic from nf_conntrack_core.c that is not exported. */ diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 2efb36c08f2a..dee469fed967 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -203,8 +203,7 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, *arg = (unsigned long) head; rcu_assign_pointer(tp->root, new); - if (head) - call_rcu(&head->rcu, mall_destroy_rcu); + call_rcu(&head->rcu, mall_destroy_rcu); return 0; err_replace_hw_filter: diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index d00f4c7c2f3a..b30a2c70bd48 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -376,10 +376,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt) if (mask != q->tab_mask) { struct sk_buff **ntab; - ntab = kcalloc(mask + 1, sizeof(struct sk_buff *), - GFP_KERNEL | __GFP_NOWARN); - if (!ntab) - ntab = vzalloc((mask + 1) * sizeof(struct sk_buff *)); + ntab = kvmalloc_array((mask + 1), sizeof(struct sk_buff *), GFP_KERNEL | __GFP_ZERO); if (!ntab) return -ENOMEM; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index da4f67bda0ee..b488721a0059 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -624,16 +624,6 @@ static void fq_rehash(struct fq_sched_data *q, q->stat_gc_flows += fcnt; } -static void *fq_alloc_node(size_t sz, int node) -{ - void *ptr; - - ptr = kmalloc_node(sz, GFP_KERNEL | __GFP_REPEAT | __GFP_NOWARN, node); - if (!ptr) - ptr = vmalloc_node(sz, node); - return ptr; -} - static void fq_free(void *addr) { kvfree(addr); @@ -650,7 +640,7 @@ static int fq_resize(struct Qdisc *sch, u32 log) return 0; /* If XPS was setup, we can allocate memory on right NUMA node */ - array = fq_alloc_node(sizeof(struct rb_root) << log, + array = kvmalloc_node(sizeof(struct rb_root) << log, GFP_KERNEL | __GFP_REPEAT, netdev_queue_numa_node_read(sch->dev_queue)); if (!array) return -ENOMEM; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 18bbb5476c83..9201abce928c 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -446,27 +446,13 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt) return 0; } -static void *fq_codel_zalloc(size_t sz) -{ - void *ptr = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN); - - if (!ptr) - ptr = vzalloc(sz); - return ptr; -} - -static void fq_codel_free(void *addr) -{ - kvfree(addr); -} - static void fq_codel_destroy(struct Qdisc *sch) { struct fq_codel_sched_data *q = qdisc_priv(sch); tcf_destroy_chain(&q->filter_list); - fq_codel_free(q->backlogs); - fq_codel_free(q->flows); + kvfree(q->backlogs); + kvfree(q->flows); } static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) @@ -493,13 +479,13 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) } if (!q->flows) { - q->flows = fq_codel_zalloc(q->flows_cnt * - sizeof(struct fq_codel_flow)); + q->flows = kvzalloc(q->flows_cnt * + sizeof(struct fq_codel_flow), GFP_KERNEL); if (!q->flows) return -ENOMEM; - q->backlogs = fq_codel_zalloc(q->flows_cnt * sizeof(u32)); + q->backlogs = kvzalloc(q->flows_cnt * sizeof(u32), GFP_KERNEL); if (!q->backlogs) { - fq_codel_free(q->flows); + kvfree(q->flows); return -ENOMEM; } for (i = 0; i < q->flows_cnt; i++) { diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index c19d346e6c5a..51d3ba682af9 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -467,29 +467,14 @@ static void hhf_reset(struct Qdisc *sch) rtnl_kfree_skbs(skb, skb); } -static void *hhf_zalloc(size_t sz) -{ - void *ptr = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN); - - if (!ptr) - ptr = vzalloc(sz); - - return ptr; -} - -static void hhf_free(void *addr) -{ - kvfree(addr); -} - static void hhf_destroy(struct Qdisc *sch) { int i; struct hhf_sched_data *q = qdisc_priv(sch); for (i = 0; i < HHF_ARRAYS_CNT; i++) { - hhf_free(q->hhf_arrays[i]); - hhf_free(q->hhf_valid_bits[i]); + kvfree(q->hhf_arrays[i]); + kvfree(q->hhf_valid_bits[i]); } for (i = 0; i < HH_FLOWS_CNT; i++) { @@ -503,7 +488,7 @@ static void hhf_destroy(struct Qdisc *sch) kfree(flow); } } - hhf_free(q->hh_flows); + kvfree(q->hh_flows); } static const struct nla_policy hhf_policy[TCA_HHF_MAX + 1] = { @@ -609,8 +594,8 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt) if (!q->hh_flows) { /* Initialize heavy-hitter flow table. */ - q->hh_flows = hhf_zalloc(HH_FLOWS_CNT * - sizeof(struct list_head)); + q->hh_flows = kvzalloc(HH_FLOWS_CNT * + sizeof(struct list_head), GFP_KERNEL); if (!q->hh_flows) return -ENOMEM; for (i = 0; i < HH_FLOWS_CNT; i++) @@ -624,8 +609,8 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt) /* Initialize heavy-hitter filter arrays. */ for (i = 0; i < HHF_ARRAYS_CNT; i++) { - q->hhf_arrays[i] = hhf_zalloc(HHF_ARRAYS_LEN * - sizeof(u32)); + q->hhf_arrays[i] = kvzalloc(HHF_ARRAYS_LEN * + sizeof(u32), GFP_KERNEL); if (!q->hhf_arrays[i]) { /* Note: hhf_destroy() will be called * by our caller. @@ -637,8 +622,8 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt) /* Initialize valid bits of heavy-hitter filter arrays. */ for (i = 0; i < HHF_ARRAYS_CNT; i++) { - q->hhf_valid_bits[i] = hhf_zalloc(HHF_ARRAYS_LEN / - BITS_PER_BYTE); + q->hhf_valid_bits[i] = kvzalloc(HHF_ARRAYS_LEN / + BITS_PER_BYTE, GFP_KERNEL); if (!q->hhf_valid_bits[i]) { /* Note: hhf_destroy() will be called * by our caller. diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index f0ce4780f395..1b3dd6190e93 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -702,15 +702,11 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) spinlock_t *root_lock; struct disttable *d; int i; - size_t s; if (n > NETEM_DIST_MAX) return -EINVAL; - s = sizeof(struct disttable) + n * sizeof(s16); - d = kmalloc(s, GFP_KERNEL | __GFP_NOWARN); - if (!d) - d = vmalloc(s); + d = kvmalloc(sizeof(struct disttable) + n * sizeof(s16), GFP_KERNEL); if (!d) return -ENOMEM; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index b00e02c139de..332d94be6e1c 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -685,11 +685,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) static void *sfq_alloc(size_t sz) { - void *ptr = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN); - - if (!ptr) - ptr = vmalloc(sz); - return ptr; + return kvmalloc(sz, GFP_KERNEL); } static void sfq_free(void *addr) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5b6ee21368a6..6793d7348cc8 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -101,7 +101,7 @@ struct proto smc_proto = { .unhash = smc_unhash_sk, .obj_size = sizeof(struct smc_sock), .h.smc_hash = &smc_v4_hashinfo, - .slab_flags = SLAB_DESTROY_BY_RCU, + .slab_flags = SLAB_TYPESAFE_BY_RCU, }; EXPORT_SYMBOL_GPL(smc_proto); diff --git a/net/sysctl_net.c b/net/sysctl_net.c index 919981324171..9aed6fe1bf1a 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -106,7 +106,6 @@ __init int net_sysctl_init(void) ret = register_pernet_subsys(&sysctl_pernet_ops); if (ret) goto out1; - register_sysctl_root(&net_sysctl_root); out: return ret; out1: diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 570fc95dc507..c3bc9da30cff 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2764,8 +2764,8 @@ static int nl80211_parse_mon_options(struct cfg80211_registered_device *rdev, nla_data(info->attrs[NL80211_ATTR_MU_MIMO_GROUP_DATA]); /* bits 0 and 63 are reserved and must be zero */ - if ((mumimo_groups[0] & BIT(7)) || - (mumimo_groups[VHT_MUMIMO_GROUPS_DATA_LEN - 1] & BIT(0))) + if ((mumimo_groups[0] & BIT(0)) || + (mumimo_groups[VHT_MUMIMO_GROUPS_DATA_LEN - 1] & BIT(7))) return -EINVAL; params->vht_mumimo_groups = mumimo_groups; |