diff --git a/Makefile b/Makefile index 3bd5d9d148d3..bc9a897e0431 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 13 -SUBLEVEL = 15 +SUBLEVEL = 16 EXTRAVERSION = NAME = Fearless Coyote diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index c55fb2cb2acc..24f749324c0f 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -811,7 +811,24 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, struct cacheinfo *this_leaf; int i, sibling; - if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { + /* + * For L3, always use the pre-calculated cpu_llc_shared_mask + * to derive shared_cpu_map. + */ + if (index == 3) { + for_each_cpu(i, cpu_llc_shared_mask(cpu)) { + this_cpu_ci = get_cpu_cacheinfo(i); + if (!this_cpu_ci->info_list) + continue; + this_leaf = this_cpu_ci->info_list + index; + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) { + if (!cpu_online(sibling)) + continue; + cpumask_set_cpu(sibling, + &this_leaf->shared_cpu_map); + } + } + } else if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { unsigned int apicid, nshared, first, last; this_leaf = this_cpu_ci->info_list + index; @@ -839,19 +856,6 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, &this_leaf->shared_cpu_map); } } - } else if (index == 3) { - for_each_cpu(i, cpu_llc_shared_mask(cpu)) { - this_cpu_ci = get_cpu_cacheinfo(i); - if (!this_cpu_ci->info_list) - continue; - this_leaf = this_cpu_ci->info_list + index; - for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) { - if (!cpu_online(sibling)) - continue; - cpumask_set_cpu(sibling, - &this_leaf->shared_cpu_map); - } - } } else return 0; diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 810b138f5897..c82d9fd2f05a 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -4030,7 +4030,8 @@ smi_from_recv_msg(ipmi_smi_t intf, struct ipmi_recv_msg *recv_msg, } static void check_msg_timeout(ipmi_smi_t intf, struct seq_table *ent, - struct list_head *timeouts, long timeout_period, + struct list_head *timeouts, + unsigned long timeout_period, int slot, unsigned long *flags, unsigned int *waiting_msgs) { @@ -4043,8 +4044,8 @@ static void check_msg_timeout(ipmi_smi_t intf, struct seq_table *ent, if (!ent->inuse) return; - ent->timeout -= timeout_period; - if (ent->timeout > 0) { + if (timeout_period < ent->timeout) { + ent->timeout -= timeout_period; (*waiting_msgs)++; return; } @@ -4110,7 +4111,8 @@ static void check_msg_timeout(ipmi_smi_t intf, struct seq_table *ent, } } -static unsigned int ipmi_timeout_handler(ipmi_smi_t intf, long timeout_period) +static unsigned int ipmi_timeout_handler(ipmi_smi_t intf, + unsigned long timeout_period) { struct list_head timeouts; struct ipmi_recv_msg *msg, *msg2; diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c index 610638a80383..461bf0b8a094 100644 --- a/drivers/char/tpm/tpm-dev-common.c +++ b/drivers/char/tpm/tpm-dev-common.c @@ -110,6 +110,12 @@ ssize_t tpm_common_write(struct file *file, const char __user *buf, return -EFAULT; } + if (in_size < 6 || + in_size < be32_to_cpu(*((__be32 *) (priv->data_buffer + 2)))) { + mutex_unlock(&priv->buffer_mutex); + return -EINVAL; + } + /* atomic tpm command send and result receive. We only hold the ops * lock during this period so that the tpm can be unregistered even if * the char dev is held open. diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c99dc59d729b..76e8054bfc4e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3253,7 +3253,7 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) hash ^= (hash >> 16); hash ^= (hash >> 8); - return hash; + return hash >> 1; } /*-------------------------- Device entry points ----------------------------*/ diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index c28fa5a8734c..ba15eeadfe21 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1743,15 +1743,17 @@ static inline void bcm_sysport_mask_all_intrs(struct bcm_sysport_priv *priv) static inline void gib_set_pad_extension(struct bcm_sysport_priv *priv) { - u32 __maybe_unused reg; + u32 reg; - /* Include Broadcom tag in pad extension */ + reg = gib_readl(priv, GIB_CONTROL); + /* Include Broadcom tag in pad extension and fix up IPG_LENGTH */ if (netdev_uses_dsa(priv->netdev)) { - reg = gib_readl(priv, GIB_CONTROL); reg &= ~(GIB_PAD_EXTENSION_MASK << GIB_PAD_EXTENSION_SHIFT); reg |= ENET_BRCM_TAG_LEN << GIB_PAD_EXTENSION_SHIFT; - gib_writel(priv, reg, GIB_CONTROL); } + reg &= ~(GIB_IPG_LEN_MASK << GIB_IPG_LEN_SHIFT); + reg |= 12 << GIB_IPG_LEN_SHIFT; + gib_writel(priv, reg, GIB_CONTROL); } static int bcm_sysport_open(struct net_device *dev) diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c index e92859dab7ae..e191c4ebeaf4 100644 --- a/drivers/net/ethernet/fealnx.c +++ b/drivers/net/ethernet/fealnx.c @@ -257,8 +257,8 @@ enum rx_desc_status_bits { RXFSD = 0x00000800, /* first descriptor */ RXLSD = 0x00000400, /* last descriptor */ ErrorSummary = 0x80, /* error summary */ - RUNT = 0x40, /* runt packet received */ - LONG = 0x20, /* long packet received */ + RUNTPKT = 0x40, /* runt packet received */ + LONGPKT = 0x20, /* long packet received */ FAE = 0x10, /* frame align error */ CRC = 0x08, /* crc error */ RXER = 0x04, /* receive error */ @@ -1632,7 +1632,7 @@ static int netdev_rx(struct net_device *dev) dev->name, rx_status); dev->stats.rx_errors++; /* end of a packet. */ - if (rx_status & (LONG | RUNT)) + if (rx_status & (LONGPKT | RUNTPKT)) dev->stats.rx_length_errors++; if (rx_status & RXER) dev->stats.rx_frame_errors++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 7344433259fc..1c513dc0105e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -213,22 +213,20 @@ static inline bool mlx5e_rx_cache_get(struct mlx5e_rq *rq, static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info) { - struct page *page; - if (mlx5e_rx_cache_get(rq, dma_info)) return 0; - page = dev_alloc_pages(rq->buff.page_order); - if (unlikely(!page)) + dma_info->page = dev_alloc_pages(rq->buff.page_order); + if (unlikely(!dma_info->page)) return -ENOMEM; - dma_info->addr = dma_map_page(rq->pdev, page, 0, + dma_info->addr = dma_map_page(rq->pdev, dma_info->page, 0, RQ_PAGE_SIZE(rq), rq->buff.map_dir); if (unlikely(dma_mapping_error(rq->pdev, dma_info->addr))) { - put_page(page); + put_page(dma_info->page); + dma_info->page = NULL; return -ENOMEM; } - dma_info->page = page; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 16885827367b..553bc230d70d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1545,9 +1545,16 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) return -EAGAIN; } + /* Panic tear down fw command will stop the PCI bus communication + * with the HCA, so the health polll is no longer needed. + */ + mlx5_drain_health_wq(dev); + mlx5_stop_health_poll(dev); + ret = mlx5_cmd_force_teardown_hca(dev); if (ret) { mlx5_core_dbg(dev, "Firmware couldn't do fast unload error: %d\n", ret); + mlx5_start_health_poll(dev); return ret; } diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index b2ff88e69a81..3d4f7959dabb 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -626,7 +626,7 @@ static int asix_suspend(struct usb_interface *intf, pm_message_t message) struct usbnet *dev = usb_get_intfdata(intf); struct asix_common_private *priv = dev->driver_priv; - if (priv->suspend) + if (priv && priv->suspend) priv->suspend(dev); return usbnet_suspend(intf, message); @@ -678,7 +678,7 @@ static int asix_resume(struct usb_interface *intf) struct usbnet *dev = usb_get_intfdata(intf); struct asix_common_private *priv = dev->driver_priv; - if (priv->resume) + if (priv && priv->resume) priv->resume(dev); return usbnet_resume(intf); diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 8ab281b478f2..4f88f64cccb4 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -221,7 +221,7 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf) goto bad_desc; } - if (header.usb_cdc_ether_desc) { + if (header.usb_cdc_ether_desc && info->ether->wMaxSegmentSize) { dev->hard_mtu = le16_to_cpu(info->ether->wMaxSegmentSize); /* because of Zaurus, we may be ignoring the host * side link address we were given. diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 9c80e80c5493..8d5e97251efe 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -771,7 +771,7 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ int err; u8 iface_no; struct usb_cdc_parsed_header hdr; - u16 curr_ntb_format; + __le16 curr_ntb_format; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -889,7 +889,7 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ goto error2; } - if (curr_ntb_format == USB_CDC_NCM_NTB32_FORMAT) { + if (curr_ntb_format == cpu_to_le16(USB_CDC_NCM_NTB32_FORMAT)) { dev_info(&intf->dev, "resetting NTB format to 16-bit"); err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_FORMAT, USB_TYPE_CLASS | USB_DIR_OUT diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 8c3733608271..8d4a6f7cba61 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -499,6 +499,7 @@ static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb) return 1; } if (rawip) { + skb_reset_mac_header(skb); skb->dev = dev->net; /* normally set by eth_type_trans */ skb->protocol = proto; return 1; @@ -681,7 +682,7 @@ static int qmi_wwan_bind(struct usbnet *dev, struct usb_interface *intf) } /* errors aren't fatal - we can live with the dynamic address */ - if (cdc_ether) { + if (cdc_ether && cdc_ether->wMaxSegmentSize) { dev->hard_mtu = le16_to_cpu(cdc_ether->wMaxSegmentSize); usbnet_get_ethernet_addr(dev, cdc_ether->iMACAddress); } diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 8a1eaf3c302a..e91ef5e236cc 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1271,7 +1271,7 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it) frh->family = family; frh->action = FR_ACT_TO_TBL; - if (nla_put_u32(skb, FRA_L3MDEV, 1)) + if (nla_put_u8(skb, FRA_L3MDEV, 1)) goto nla_put_failure; if (nla_put_u32(skb, FRA_PRIORITY, FIB_RULE_PREF)) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index e17baac70f43..436154720bf8 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1632,26 +1632,19 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request, static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); - struct nd_msg *msg; - const struct ipv6hdr *iphdr; const struct in6_addr *daddr; - struct neighbour *n; + const struct ipv6hdr *iphdr; struct inet6_dev *in6_dev; + struct neighbour *n; + struct nd_msg *msg; in6_dev = __in6_dev_get(dev); if (!in6_dev) goto out; - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg))) - goto out; - iphdr = ipv6_hdr(skb); daddr = &iphdr->daddr; - msg = (struct nd_msg *)(iphdr + 1); - if (msg->icmph.icmp6_code != 0 || - msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) - goto out; if (ipv6_addr_loopback(daddr) || ipv6_addr_is_multicast(&msg->target)) @@ -2258,11 +2251,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_rdst *rdst, *fdst = NULL; const struct ip_tunnel_info *info; - struct ethhdr *eth; bool did_rsc = false; - struct vxlan_rdst *rdst, *fdst = NULL; struct vxlan_fdb *f; + struct ethhdr *eth; __be32 vni = 0; info = skb_tunnel_info(skb); @@ -2287,12 +2280,14 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) if (ntohs(eth->h_proto) == ETH_P_ARP) return arp_reduce(dev, skb, vni); #if IS_ENABLED(CONFIG_IPV6) - else if (ntohs(eth->h_proto) == ETH_P_IPV6) { - struct ipv6hdr *hdr, _hdr; - if ((hdr = skb_header_pointer(skb, - skb_network_offset(skb), - sizeof(_hdr), &_hdr)) && - hdr->nexthdr == IPPROTO_ICMPV6) + else if (ntohs(eth->h_proto) == ETH_P_IPV6 && + pskb_may_pull(skb, sizeof(struct ipv6hdr) + + sizeof(struct nd_msg)) && + ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { + struct nd_msg *m = (struct nd_msg *)(ipv6_hdr(skb) + 1); + + if (m->icmph.icmp6_code == 0 && + m->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) return neigh_reduce(dev, skb, vni); } #endif diff --git a/drivers/tty/serial/8250/8250_fintek.c b/drivers/tty/serial/8250/8250_fintek.c index e500f7dd2470..4bd376c08b59 100644 --- a/drivers/tty/serial/8250/8250_fintek.c +++ b/drivers/tty/serial/8250/8250_fintek.c @@ -118,6 +118,9 @@ static int fintek_8250_enter_key(u16 base_port, u8 key) if (!request_muxed_region(base_port, 2, "8250_fintek")) return -EBUSY; + /* Force to deactive all SuperIO in this base_port */ + outb(EXIT_KEY, base_port + ADDR_PORT); + outb(key, base_port + ADDR_PORT); outb(key, base_port + ADDR_PORT); return 0; diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index 1ea05ac57aa7..670f7e334f93 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -693,7 +693,7 @@ static void serial_omap_set_mctrl(struct uart_port *port, unsigned int mctrl) if ((mctrl & TIOCM_RTS) && (port->status & UPSTAT_AUTORTS)) up->efr |= UART_EFR_RTS; else - up->efr &= UART_EFR_RTS; + up->efr &= ~UART_EFR_RTS; serial_out(up, UART_EFR, up->efr); serial_out(up, UART_LCR, lcr); diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c index e82357c89979..8cf16d8c5261 100644 --- a/fs/coda/upcall.c +++ b/fs/coda/upcall.c @@ -446,8 +446,7 @@ int venus_fsync(struct super_block *sb, struct CodaFid *fid) UPARG(CODA_FSYNC); inp->coda_fsync.VFid = *fid; - error = coda_upcall(coda_vcp(sb), sizeof(union inputArgs), - &outsize, inp); + error = coda_upcall(coda_vcp(sb), insize, &outsize, inp); CODA_FREE(inp, insize); return error; diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 74407c6dd592..ec8f75813beb 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -2419,6 +2419,7 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) dlm_lockres_put(res); continue; } + dlm_move_lockres_to_recovery_list(dlm, res); } else if (res->owner == dlm->node_num) { dlm_free_dead_locks(dlm, res, dead_node); __dlm_lockres_calc_usage(dlm, res); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index bfeb647459d9..2fc8e65c07c5 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1168,6 +1168,13 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) } size_change = S_ISREG(inode->i_mode) && attr->ia_valid & ATTR_SIZE; if (size_change) { + /* + * Here we should wait dio to finish before inode lock + * to avoid a deadlock between ocfs2_setattr() and + * ocfs2_dio_end_io_write() + */ + inode_dio_wait(inode); + status = ocfs2_rw_lock(inode, 1); if (status < 0) { mlog_errno(status); @@ -1207,8 +1214,6 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) if (status) goto bail_unlock; - inode_dio_wait(inode); - if (i_size_read(inode) >= attr->ia_size) { if (ocfs2_should_order_data(inode)) { status = ocfs2_begin_ordered_truncate(inode, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fc14b8b3f6ce..1d86e09f17c1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -691,7 +691,8 @@ typedef struct pglist_data { * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; - unsigned long static_init_size; + /* Number of non-deferred pages */ + unsigned long static_init_pgcnt; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 63df75ae70ee..baf2dd102686 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3655,6 +3655,13 @@ static inline void nf_reset_trace(struct sk_buff *skb) #endif } +static inline void ipvs_reset(struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_IP_VS) + skb->ipvs_property = 0; +#endif +} + /* Note: This doesn't put any conntrack and bridge info in dst. */ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, bool copy) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 908b309d60d7..b8f51dffeae9 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1493,7 +1493,7 @@ static void rcu_prepare_for_idle(void) rdtp->last_accelerate = jiffies; for_each_rcu_flavor(rsp) { rdp = this_cpu_ptr(rsp->rda); - if (rcu_segcblist_pend_cbs(&rdp->cblist)) + if (!rcu_segcblist_pend_cbs(&rdp->cblist)) continue; rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1423da8dd16f..3bd0999c266f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -289,28 +289,37 @@ EXPORT_SYMBOL(nr_online_nodes); int page_group_by_mobility_disabled __read_mostly; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT + +/* + * Determine how many pages need to be initialized durig early boot + * (non-deferred initialization). + * The value of first_deferred_pfn will be set later, once non-deferred pages + * are initialized, but for now set it ULONG_MAX. + */ static inline void reset_deferred_meminit(pg_data_t *pgdat) { - unsigned long max_initialise; - unsigned long reserved_lowmem; + phys_addr_t start_addr, end_addr; + unsigned long max_pgcnt; + unsigned long reserved; /* * Initialise at least 2G of a node but also take into account that * two large system hashes that can take up 1GB for 0.25TB/node. */ - max_initialise = max(2UL << (30 - PAGE_SHIFT), - (pgdat->node_spanned_pages >> 8)); + max_pgcnt = max(2UL << (30 - PAGE_SHIFT), + (pgdat->node_spanned_pages >> 8)); /* * Compensate the all the memblock reservations (e.g. crash kernel) * from the initial estimation to make sure we will initialize enough * memory to boot. */ - reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn, - pgdat->node_start_pfn + max_initialise); - max_initialise += reserved_lowmem; + start_addr = PFN_PHYS(pgdat->node_start_pfn); + end_addr = PFN_PHYS(pgdat->node_start_pfn + max_pgcnt); + reserved = memblock_reserved_memory_within(start_addr, end_addr); + max_pgcnt += PHYS_PFN(reserved); - pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages); + pgdat->static_init_pgcnt = min(max_pgcnt, pgdat->node_spanned_pages); pgdat->first_deferred_pfn = ULONG_MAX; } @@ -337,7 +346,7 @@ static inline bool update_defer_init(pg_data_t *pgdat, if (zone_end < pgdat_end_pfn(pgdat)) return true; (*nr_initialised)++; - if ((*nr_initialised > pgdat->static_init_size) && + if ((*nr_initialised > pgdat->static_init_pgcnt) && (pfn & (PAGES_PER_SECTION - 1)) == 0) { pgdat->first_deferred_pfn = pfn; return false; diff --git a/mm/page_ext.c b/mm/page_ext.c index 88ccc044b09a..9dbabbfc4557 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -124,7 +124,6 @@ struct page_ext *lookup_page_ext(struct page *page) struct page_ext *base; base = NODE_DATA(page_to_nid(page))->node_page_ext; -#if defined(CONFIG_DEBUG_VM) /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are @@ -133,7 +132,6 @@ struct page_ext *lookup_page_ext(struct page *page) */ if (unlikely(!base)) return NULL; -#endif index = pfn - round_down(node_start_pfn(page_to_nid(page)), MAX_ORDER_NR_PAGES); return get_entry(base, index); @@ -198,7 +196,6 @@ struct page_ext *lookup_page_ext(struct page *page) { unsigned long pfn = page_to_pfn(page); struct mem_section *section = __pfn_to_section(pfn); -#if defined(CONFIG_DEBUG_VM) /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are @@ -207,7 +204,6 @@ struct page_ext *lookup_page_ext(struct page *page) */ if (!section->page_ext) return NULL; -#endif return get_entry(section->page_ext, pfn); } diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 1a4197965415..7d973f63088c 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -187,8 +187,12 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end, do { next = hugetlb_entry_end(h, addr, end); pte = huge_pte_offset(walk->mm, addr & hmask, sz); - if (pte && walk->hugetlb_entry) + + if (pte) err = walk->hugetlb_entry(pte, hmask, addr, next, walk); + else if (walk->pte_hole) + err = walk->pte_hole(addr, next, walk); + if (err) break; } while (addr = next, addr != end); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 9649579b5b9f..4a72ee4e2ae9 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -376,6 +376,9 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, dev->name); vlan_vid_add(dev, htons(ETH_P_8021Q), 0); } + if (event == NETDEV_DOWN && + (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) + vlan_vid_del(dev, htons(ETH_P_8021Q), 0); vlan_info = rtnl_dereference(dev->vlan_info); if (!vlan_info) @@ -423,9 +426,6 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, struct net_device *tmp; LIST_HEAD(close_list); - if (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER) - vlan_vid_del(dev, htons(ETH_P_8021Q), 0); - /* Put all VLANs for this dev in the down state too. */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = vlandev->flags; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 72eb23d2426f..a0155578e951 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4476,6 +4476,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) if (!xnet) return; + ipvs_reset(skb); skb_orphan(skb); skb->mark = 0; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e92e5dbcb3d6..ffe96de8a079 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2613,7 +2613,6 @@ void tcp_simple_retransmit(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; unsigned int mss = tcp_current_mss(sk); - u32 prior_lost = tp->lost_out; tcp_for_write_queue(skb, sk) { if (skb == tcp_send_head(sk)) @@ -2630,7 +2629,7 @@ void tcp_simple_retransmit(struct sock *sk) tcp_clear_retrans_hints_partial(tp); - if (prior_lost == tp->lost_out) + if (!tp->lost_out) return; if (tcp_is_reno(tp)) diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c index 6d650ed3cb59..5c871666c561 100644 --- a/net/ipv4/tcp_nv.c +++ b/net/ipv4/tcp_nv.c @@ -263,7 +263,7 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample) /* rate in 100's bits per second */ rate64 = ((u64)sample->in_flight) * 8000000; - rate = (u32)div64_u64(rate64, (u64)(avg_rtt * 100)); + rate = (u32)div64_u64(rate64, (u64)(avg_rtt ?: 1) * 100); /* Remember the maximum rate seen during this RTT * Note: It may be more than one RTT. This function should be diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 11f69bbf9307..b6a2aa1dcf56 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -149,11 +149,19 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, * is freed by GSO engine */ if (copy_destructor) { + int delta; + swap(gso_skb->sk, skb->sk); swap(gso_skb->destructor, skb->destructor); sum_truesize += skb->truesize; - refcount_add(sum_truesize - gso_skb->truesize, - &skb->sk->sk_wmem_alloc); + delta = sum_truesize - gso_skb->truesize; + /* In some pathological cases, delta can be negative. + * We need to either use refcount_add() or refcount_sub_and_test() + */ + if (likely(delta >= 0)) + refcount_add(delta, &skb->sk->sk_wmem_alloc); + else + WARN_ON_ONCE(refcount_sub_and_test(-delta, &skb->sk->sk_wmem_alloc)); } delta = htonl(oldlen + (skb_tail_pointer(skb) - diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 58587b0e2b5d..e359840f46c0 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3207,13 +3207,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, th->source = htons(ireq->ir_num); th->dest = ireq->ir_rmt_port; skb->mark = ireq->ir_mark; - /* Setting of flags are superfluous here for callers (and ECE is - * not even correctly set) - */ - tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn, - TCPHDR_SYN | TCPHDR_ACK); - - th->seq = htonl(TCP_SKB_CB(skb)->seq); + skb->ip_summed = CHECKSUM_PARTIAL; + th->seq = htonl(tcp_rsk(req)->snt_isn); /* XXX data is queued and acked as is. No buffer/window check */ th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 4d322c1b7233..e4280b6568b4 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -123,6 +123,7 @@ static int l2tp_ip_recv(struct sk_buff *skb) unsigned char *ptr, *optr; struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; + struct iphdr *iph; int length; if (!pskb_may_pull(skb, 4)) @@ -178,24 +179,17 @@ static int l2tp_ip_recv(struct sk_buff *skb) goto discard; tunnel_id = ntohl(*(__be32 *) &skb->data[4]); - tunnel = l2tp_tunnel_find(net, tunnel_id); - if (tunnel) { - sk = tunnel->sock; - sock_hold(sk); - } else { - struct iphdr *iph = (struct iphdr *) skb_network_header(skb); - - read_lock_bh(&l2tp_ip_lock); - sk = __l2tp_ip_bind_lookup(net, iph->daddr, iph->saddr, - inet_iif(skb), tunnel_id); - if (!sk) { - read_unlock_bh(&l2tp_ip_lock); - goto discard; - } + iph = (struct iphdr *)skb_network_header(skb); - sock_hold(sk); + read_lock_bh(&l2tp_ip_lock); + sk = __l2tp_ip_bind_lookup(net, iph->daddr, iph->saddr, inet_iif(skb), + tunnel_id); + if (!sk) { read_unlock_bh(&l2tp_ip_lock); + goto discard; } + sock_hold(sk); + read_unlock_bh(&l2tp_ip_lock); if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 88b397c30d86..8bcaa975b432 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -136,6 +136,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb) unsigned char *ptr, *optr; struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; + struct ipv6hdr *iph; int length; if (!pskb_may_pull(skb, 4)) @@ -192,24 +193,17 @@ static int l2tp_ip6_recv(struct sk_buff *skb) goto discard; tunnel_id = ntohl(*(__be32 *) &skb->data[4]); - tunnel = l2tp_tunnel_find(net, tunnel_id); - if (tunnel) { - sk = tunnel->sock; - sock_hold(sk); - } else { - struct ipv6hdr *iph = ipv6_hdr(skb); - - read_lock_bh(&l2tp_ip6_lock); - sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, &iph->saddr, - inet6_iif(skb), tunnel_id); - if (!sk) { - read_unlock_bh(&l2tp_ip6_lock); - goto discard; - } + iph = ipv6_hdr(skb); - sock_hold(sk); + read_lock_bh(&l2tp_ip6_lock); + sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, &iph->saddr, + inet6_iif(skb), tunnel_id); + if (!sk) { read_unlock_bh(&l2tp_ip6_lock); + goto discard; } + sock_hold(sk); + read_unlock_bh(&l2tp_ip6_lock); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 09c8dbbd2d70..2939a6b87c27 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2128,7 +2128,7 @@ static int netlink_dump(struct sock *sk) struct sk_buff *skb = NULL; struct nlmsghdr *nlh; struct module *module; - int len, err = -ENOBUFS; + int err = -ENOBUFS; int alloc_min_size; int alloc_size; @@ -2175,9 +2175,11 @@ static int netlink_dump(struct sock *sk) skb_reserve(skb, skb_tailroom(skb) - alloc_size); netlink_skb_set_owner_r(skb, sk); - len = cb->dump(skb, cb); + if (nlk->dump_done_errno > 0) + nlk->dump_done_errno = cb->dump(skb, cb); - if (len > 0) { + if (nlk->dump_done_errno > 0 || + skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) { mutex_unlock(nlk->cb_mutex); if (sk_filter(sk, skb)) @@ -2187,13 +2189,15 @@ static int netlink_dump(struct sock *sk) return 0; } - nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI); - if (!nlh) + nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, + sizeof(nlk->dump_done_errno), NLM_F_MULTI); + if (WARN_ON(!nlh)) goto errout_skb; nl_dump_check_consistent(cb, nlh); - memcpy(nlmsg_data(nlh), &len, sizeof(len)); + memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, + sizeof(nlk->dump_done_errno)); if (sk_filter(sk, skb)) kfree_skb(skb); @@ -2265,6 +2269,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, } nlk->cb_running = true; + nlk->dump_done_errno = INT_MAX; mutex_unlock(nlk->cb_mutex); diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 3490f2430532..8908fc2d3de0 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -33,6 +33,7 @@ struct netlink_sock { wait_queue_head_t wait; bool bound; bool cb_running; + int dump_done_errno; struct netlink_callback cb; struct mutex *cb_mutex; struct mutex cb_def_mutex; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 1344e3a411ae..edb462b0b73b 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -807,9 +807,10 @@ static void sctp_inet6_skb_msgname(struct sk_buff *skb, char *msgname, addr->v6.sin6_flowinfo = 0; addr->v6.sin6_port = sh->source; addr->v6.sin6_addr = ipv6_hdr(skb)->saddr; - if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) { + if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) addr->v6.sin6_scope_id = sctp_v6_skb_iif(skb); - } + else + addr->v6.sin6_scope_id = 0; } *addr_len = sctp_v6_addr_to_user(sctp_sk(skb->sk), addr); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 3d79085eb4e0..083da13e1af4 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4924,6 +4924,10 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) struct socket *sock; int err = 0; + /* Do not peel off from one netns to another one. */ + if (!net_eq(current->nsproxy->net_ns, sock_net(sk))) + return -EINVAL; + if (!asoc) return -EINVAL; diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 809ba70fbbbf..7d769b948de8 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -320,6 +320,9 @@ void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file) if (iint->flags & IMA_DIGSIG) return; + if (iint->ima_file_status != INTEGRITY_PASS) + return; + rc = ima_collect_measurement(iint, file, NULL, 0, ima_hash_algo); if (rc < 0) return;