diff options
64 files changed, 568 insertions, 420 deletions
diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt index 25170ad7d25b..101f2b2c69ad 100644 --- a/Documentation/networking/dsa/dsa.txt +++ b/Documentation/networking/dsa/dsa.txt @@ -533,16 +533,12 @@ Bridge VLAN filtering function that the driver has to call for each VLAN the given port is a member of. A switchdev object is used to carry the VID and bridge flags. -- port_fdb_prepare: bridge layer function invoked when the bridge prepares the - installation of a Forwarding Database entry. If the operation is not - supported, this function should return -EOPNOTSUPP to inform the bridge code - to fallback to a software implementation. No hardware setup must be done in - this function. See port_fdb_add for this and details. - - port_fdb_add: bridge layer function invoked when the bridge wants to install a Forwarding Database entry, the switch hardware should be programmed with the specified address in the specified VLAN Id in the forwarding database - associated with this VLAN ID + associated with this VLAN ID. If the operation is not supported, this + function should return -EOPNOTSUPP to inform the bridge code to fallback to + a software implementation. Note: VLAN ID 0 corresponds to the port private database, which, in the context of DSA, would be the its port-based VLAN, used by the associated bridge device. diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 82236a17b5e6..97b7ca8b9b86 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -92,11 +92,11 @@ device. Switch ID ^^^^^^^^^ -The switchdev driver must implement the switchdev op switchdev_port_attr_get -for SWITCHDEV_ATTR_ID_PORT_PARENT_ID for each port netdev, returning the same -physical ID for each port of a switch. The ID must be unique between switches -on the same system. The ID does not need to be unique between switches on -different systems. +The switchdev driver must implement the net_device operation +ndo_get_port_parent_id for each port netdev, returning the same physical ID for +each port of a switch. The ID must be unique between switches on the same +system. The ID does not need to be unique between switches on different +systems. The switch ID is used to locate ports on a switch and to know if aggregated ports belong to the same switch. diff --git a/MAINTAINERS b/MAINTAINERS index e6e17d8c5aae..dce5c099f43c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2851,7 +2851,7 @@ R: Martin KaFai Lau <kafai@fb.com> R: Song Liu <songliubraving@fb.com> R: Yonghong Song <yhs@fb.com> L: netdev@vger.kernel.org -L: linux-kernel@vger.kernel.org +L: bpf@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git Q: https://patchwork.ozlabs.org/project/netdev/list/?delegate=77147 @@ -2881,6 +2881,7 @@ N: bpf BPF JIT for ARM M: Shubham Bansal <illusionist.neo@gmail.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: arch/arm/net/ @@ -2889,18 +2890,21 @@ M: Daniel Borkmann <daniel@iogearbox.net> M: Alexei Starovoitov <ast@kernel.org> M: Zi Shen Lim <zlim.lnx@gmail.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Supported F: arch/arm64/net/ BPF JIT for MIPS (32-BIT AND 64-BIT) M: Paul Burton <paul.burton@mips.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: arch/mips/net/ BPF JIT for NFP NICs M: Jakub Kicinski <jakub.kicinski@netronome.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Supported F: drivers/net/ethernet/netronome/nfp/bpf/ @@ -2908,6 +2912,7 @@ BPF JIT for POWERPC (32-BIT AND 64-BIT) M: Naveen N. Rao <naveen.n.rao@linux.ibm.com> M: Sandipan Das <sandipan@linux.ibm.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: arch/powerpc/net/ @@ -2915,6 +2920,7 @@ BPF JIT for S390 M: Martin Schwidefsky <schwidefsky@de.ibm.com> M: Heiko Carstens <heiko.carstens@de.ibm.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: arch/s390/net/ X: arch/s390/net/pnet.c @@ -2922,12 +2928,14 @@ X: arch/s390/net/pnet.c BPF JIT for SPARC (32-BIT AND 64-BIT) M: David S. Miller <davem@davemloft.net> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: arch/sparc/net/ BPF JIT for X86 32-BIT M: Wang YanQing <udknight@gmail.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: arch/x86/net/bpf_jit_comp32.c @@ -2935,6 +2943,7 @@ BPF JIT for X86 64-BIT M: Alexei Starovoitov <ast@kernel.org> M: Daniel Borkmann <daniel@iogearbox.net> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Supported F: arch/x86/net/ X: arch/x86/net/bpf_jit_comp32.c @@ -3389,9 +3398,8 @@ F: Documentation/media/v4l-drivers/cafe_ccic* F: drivers/media/platform/marvell-ccic/ CAIF NETWORK LAYER -M: Dmitry Tarnyagin <dmitry.tarnyagin@lockless.no> L: netdev@vger.kernel.org -S: Supported +S: Orphan F: Documentation/networking/caif/ F: drivers/net/caif/ F: include/uapi/linux/caif/ @@ -8486,6 +8494,7 @@ L7 BPF FRAMEWORK M: John Fastabend <john.fastabend@gmail.com> M: Daniel Borkmann <daniel@iogearbox.net> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: include/linux/skmsg.h F: net/core/skmsg.c @@ -16713,6 +16722,7 @@ M: Jesper Dangaard Brouer <hawk@kernel.org> M: John Fastabend <john.fastabend@gmail.com> L: netdev@vger.kernel.org L: xdp-newbies@vger.kernel.org +L: bpf@vger.kernel.org S: Supported F: net/core/xdp.c F: include/net/xdp.h @@ -16726,6 +16736,7 @@ XDP SOCKETS (AF_XDP) M: Björn Töpel <bjorn.topel@intel.com> M: Magnus Karlsson <magnus.karlsson@intel.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: kernel/bpf/xskmap.c F: net/xdp/ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 485462d3087f..537c90c8eb0a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1183,29 +1183,22 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) } } - /* Link-local multicast packets should be passed to the - * stack on the link they arrive as well as pass them to the - * bond-master device. These packets are mostly usable when - * stack receives it with the link on which they arrive - * (e.g. LLDP) they also must be available on master. Some of - * the use cases include (but are not limited to): LLDP agents - * that must be able to operate both on enslaved interfaces as - * well as on bonds themselves; linux bridges that must be able - * to process/pass BPDUs from attached bonds when any kind of - * STP version is enabled on the network. + /* + * For packets determined by bond_should_deliver_exact_match() call to + * be suppressed we want to make an exception for link-local packets. + * This is necessary for e.g. LLDP daemons to be able to monitor + * inactive slave links without being forced to bind to them + * explicitly. + * + * At the same time, packets that are passed to the bonding master + * (including link-local ones) can have their originating interface + * determined via PACKET_ORIGDEV socket option. */ - if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) { - struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); - - if (nskb) { - nskb->dev = bond->dev; - nskb->queue_mapping = 0; - netif_rx(nskb); - } - return RX_HANDLER_PASS; - } - if (bond_should_deliver_exact_match(skb, slave, bond)) + if (bond_should_deliver_exact_match(skb, slave, bond)) { + if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) + return RX_HANDLER_PASS; return RX_HANDLER_EXACT; + } skb->dev = bond->dev; diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c index bb41becb6609..31ff1e0d1baa 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.c +++ b/drivers/net/ethernet/atheros/atlx/atl2.c @@ -1335,13 +1335,11 @@ static int atl2_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct net_device *netdev; struct atl2_adapter *adapter; - static int cards_found; + static int cards_found = 0; unsigned long mmio_start; int mmio_len; int err; - cards_found = 0; - err = pci_enable_device(pdev); if (err) return err; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 8bc7e495b027..d95730c6e0f2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3903,7 +3903,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, if (len) break; /* on first few passes, just barely sleep */ - if (i < DFLT_HWRM_CMD_TIMEOUT) + if (i < HWRM_SHORT_TIMEOUT_COUNTER) usleep_range(HWRM_SHORT_MIN_TIMEOUT, HWRM_SHORT_MAX_TIMEOUT); else @@ -3926,7 +3926,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, dma_rmb(); if (*valid) break; - udelay(1); + usleep_range(1, 5); } if (j >= HWRM_VALID_BIT_DELAY_USEC) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index a451796deefe..2fb653e0048d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -582,7 +582,7 @@ struct nqe_cn { (HWRM_SHORT_TIMEOUT_COUNTER * HWRM_SHORT_MIN_TIMEOUT + \ ((n) - HWRM_SHORT_TIMEOUT_COUNTER) * HWRM_MIN_TIMEOUT)) -#define HWRM_VALID_BIT_DELAY_USEC 20 +#define HWRM_VALID_BIT_DELAY_USEC 150 #define BNXT_HWRM_CHNL_CHIMP 0 #define BNXT_HWRM_CHNL_KONG 1 diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index f4d81765221e..62636c1ed141 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -271,7 +271,7 @@ struct xcast_addr_list { }; struct nicvf_work { - struct delayed_work work; + struct work_struct work; u8 mode; struct xcast_addr_list *mc; }; @@ -327,7 +327,11 @@ struct nicvf { struct nicvf_work rx_mode_work; /* spinlock to protect workqueue arguments from concurrent access */ spinlock_t rx_mode_wq_lock; - + /* workqueue for handling kernel ndo_set_rx_mode() calls */ + struct workqueue_struct *nicvf_rx_mode_wq; + /* mutex to protect VF's mailbox contents from concurrent access */ + struct mutex rx_mode_mtx; + struct delayed_work link_change_work; /* PTP timestamp */ struct cavium_ptp *ptp_clock; /* Inbound timestamping is on */ @@ -575,10 +579,8 @@ struct set_ptp { struct xcast { u8 msg; - union { - u8 mode; - u64 mac; - } data; + u8 mode; + u64 mac:48; }; /* 128 bit shared memory between PF and each VF */ diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 6c8dcb65ff03..c90252829ed3 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -57,14 +57,8 @@ struct nicpf { #define NIC_GET_BGX_FROM_VF_LMAC_MAP(map) ((map >> 4) & 0xF) #define NIC_GET_LMAC_FROM_VF_LMAC_MAP(map) (map & 0xF) u8 *vf_lmac_map; - struct delayed_work dwork; - struct workqueue_struct *check_link; - u8 *link; - u8 *duplex; - u32 *speed; u16 cpi_base[MAX_NUM_VFS_SUPPORTED]; u16 rssi_base[MAX_NUM_VFS_SUPPORTED]; - bool mbx_lock[MAX_NUM_VFS_SUPPORTED]; /* MSI-X */ u8 num_vec; @@ -929,6 +923,35 @@ static void nic_config_timestamp(struct nicpf *nic, int vf, struct set_ptp *ptp) nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG | (pkind_idx << 3), pkind_val); } +/* Get BGX LMAC link status and update corresponding VF + * if there is a change, valid only if internal L2 switch + * is not present otherwise VF link is always treated as up + */ +static void nic_link_status_get(struct nicpf *nic, u8 vf) +{ + union nic_mbx mbx = {}; + struct bgx_link_status link; + u8 bgx, lmac; + + mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE; + + /* Get BGX, LMAC indices for the VF */ + bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + + /* Get interface link status */ + bgx_get_lmac_link_state(nic->node, bgx, lmac, &link); + + /* Send a mbox message to VF with current link status */ + mbx.link_status.link_up = link.link_up; + mbx.link_status.duplex = link.duplex; + mbx.link_status.speed = link.speed; + mbx.link_status.mac_type = link.mac_type; + + /* reply with link status */ + nic_send_msg_to_vf(nic, vf, &mbx); +} + /* Interrupt handler to handle mailbox messages from VFs */ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) { @@ -941,8 +964,6 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) int i; int ret = 0; - nic->mbx_lock[vf] = true; - mbx_addr = nic_get_mbx_addr(vf); mbx_data = (u64 *)&mbx; @@ -957,12 +978,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) switch (mbx.msg.msg) { case NIC_MBOX_MSG_READY: nic_mbx_send_ready(nic, vf); - if (vf < nic->num_vf_en) { - nic->link[vf] = 0; - nic->duplex[vf] = 0; - nic->speed[vf] = 0; - } - goto unlock; + return; case NIC_MBOX_MSG_QS_CFG: reg_addr = NIC_PF_QSET_0_127_CFG | (mbx.qs.num << NIC_QS_ID_SHIFT); @@ -1031,7 +1047,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) break; case NIC_MBOX_MSG_RSS_SIZE: nic_send_rss_size(nic, vf); - goto unlock; + return; case NIC_MBOX_MSG_RSS_CFG: case NIC_MBOX_MSG_RSS_CFG_CONT: nic_config_rss(nic, &mbx.rss_cfg); @@ -1039,7 +1055,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) case NIC_MBOX_MSG_CFG_DONE: /* Last message of VF config msg sequence */ nic_enable_vf(nic, vf, true); - goto unlock; + break; case NIC_MBOX_MSG_SHUTDOWN: /* First msg in VF teardown sequence */ if (vf >= nic->num_vf_en) @@ -1049,19 +1065,19 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) break; case NIC_MBOX_MSG_ALLOC_SQS: nic_alloc_sqs(nic, &mbx.sqs_alloc); - goto unlock; + return; case NIC_MBOX_MSG_NICVF_PTR: nic->nicvf[vf] = mbx.nicvf.nicvf; break; case NIC_MBOX_MSG_PNICVF_PTR: nic_send_pnicvf(nic, vf); - goto unlock; + return; case NIC_MBOX_MSG_SNICVF_PTR: nic_send_snicvf(nic, &mbx.nicvf); - goto unlock; + return; case NIC_MBOX_MSG_BGX_STATS: nic_get_bgx_stats(nic, &mbx.bgx_stats); - goto unlock; + return; case NIC_MBOX_MSG_LOOPBACK: ret = nic_config_loopback(nic, &mbx.lbk); break; @@ -1070,7 +1086,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) break; case NIC_MBOX_MSG_PFC: nic_pause_frame(nic, vf, &mbx.pfc); - goto unlock; + return; case NIC_MBOX_MSG_PTP_CFG: nic_config_timestamp(nic, vf, &mbx.ptp); break; @@ -1094,7 +1110,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); bgx_set_dmac_cam_filter(nic->node, bgx, lmac, - mbx.xcast.data.mac, + mbx.xcast.mac, vf < NIC_VF_PER_MBX_REG ? vf : vf - NIC_VF_PER_MBX_REG); break; @@ -1106,8 +1122,15 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) } bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); - bgx_set_xcast_mode(nic->node, bgx, lmac, mbx.xcast.data.mode); + bgx_set_xcast_mode(nic->node, bgx, lmac, mbx.xcast.mode); break; + case NIC_MBOX_MSG_BGX_LINK_CHANGE: + if (vf >= nic->num_vf_en) { + ret = -1; /* NACK */ + break; + } + nic_link_status_get(nic, vf); + return; default: dev_err(&nic->pdev->dev, "Invalid msg from VF%d, msg 0x%x\n", vf, mbx.msg.msg); @@ -1121,8 +1144,6 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) mbx.msg.msg, vf); nic_mbx_send_nack(nic, vf); } -unlock: - nic->mbx_lock[vf] = false; } static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq) @@ -1270,52 +1291,6 @@ static int nic_sriov_init(struct pci_dev *pdev, struct nicpf *nic) return 0; } -/* Poll for BGX LMAC link status and update corresponding VF - * if there is a change, valid only if internal L2 switch - * is not present otherwise VF link is always treated as up - */ -static void nic_poll_for_link(struct work_struct *work) -{ - union nic_mbx mbx = {}; - struct nicpf *nic; - struct bgx_link_status link; - u8 vf, bgx, lmac; - - nic = container_of(work, struct nicpf, dwork.work); - - mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE; - - for (vf = 0; vf < nic->num_vf_en; vf++) { - /* Poll only if VF is UP */ - if (!nic->vf_enabled[vf]) - continue; - - /* Get BGX, LMAC indices for the VF */ - bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); - lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); - /* Get interface link status */ - bgx_get_lmac_link_state(nic->node, bgx, lmac, &link); - - /* Inform VF only if link status changed */ - if (nic->link[vf] == link.link_up) - continue; - - if (!nic->mbx_lock[vf]) { - nic->link[vf] = link.link_up; - nic->duplex[vf] = link.duplex; - nic->speed[vf] = link.speed; - - /* Send a mbox message to VF with current link status */ - mbx.link_status.link_up = link.link_up; - mbx.link_status.duplex = link.duplex; - mbx.link_status.speed = link.speed; - mbx.link_status.mac_type = link.mac_type; - nic_send_msg_to_vf(nic, vf, &mbx); - } - } - queue_delayed_work(nic->check_link, &nic->dwork, HZ * 2); -} - static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct device *dev = &pdev->dev; @@ -1384,18 +1359,6 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!nic->vf_lmac_map) goto err_release_regions; - nic->link = devm_kmalloc_array(dev, max_lmac, sizeof(u8), GFP_KERNEL); - if (!nic->link) - goto err_release_regions; - - nic->duplex = devm_kmalloc_array(dev, max_lmac, sizeof(u8), GFP_KERNEL); - if (!nic->duplex) - goto err_release_regions; - - nic->speed = devm_kmalloc_array(dev, max_lmac, sizeof(u32), GFP_KERNEL); - if (!nic->speed) - goto err_release_regions; - /* Initialize hardware */ nic_init_hw(nic); @@ -1411,22 +1374,8 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_unregister_interrupts; - /* Register a physical link status poll fn() */ - nic->check_link = alloc_workqueue("check_link_status", - WQ_UNBOUND | WQ_MEM_RECLAIM, 1); - if (!nic->check_link) { - err = -ENOMEM; - goto err_disable_sriov; - } - - INIT_DELAYED_WORK(&nic->dwork, nic_poll_for_link); - queue_delayed_work(nic->check_link, &nic->dwork, 0); - return 0; -err_disable_sriov: - if (nic->flags & NIC_SRIOV_ENABLED) - pci_disable_sriov(pdev); err_unregister_interrupts: nic_unregister_interrupts(nic); err_release_regions: @@ -1447,12 +1396,6 @@ static void nic_remove(struct pci_dev *pdev) if (nic->flags & NIC_SRIOV_ENABLED) pci_disable_sriov(pdev); - if (nic->check_link) { - /* Destroy work Queue */ - cancel_delayed_work_sync(&nic->dwork); - destroy_workqueue(nic->check_link); - } - nic_unregister_interrupts(nic); pci_release_regions(pdev); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 88f8a8fa93cd..503cfadff4ac 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -68,9 +68,6 @@ module_param(cpi_alg, int, 0444); MODULE_PARM_DESC(cpi_alg, "PFC algorithm (0=none, 1=VLAN, 2=VLAN16, 3=IP Diffserv)"); -/* workqueue for handling kernel ndo_set_rx_mode() calls */ -static struct workqueue_struct *nicvf_rx_mode_wq; - static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx) { if (nic->sqs_mode) @@ -127,6 +124,9 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx) { int timeout = NIC_MBOX_MSG_TIMEOUT; int sleep = 10; + int ret = 0; + + mutex_lock(&nic->rx_mode_mtx); nic->pf_acked = false; nic->pf_nacked = false; @@ -139,7 +139,8 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx) netdev_err(nic->netdev, "PF NACK to mbox msg 0x%02x from VF%d\n", (mbx->msg.msg & 0xFF), nic->vf_id); - return -EINVAL; + ret = -EINVAL; + break; } msleep(sleep); if (nic->pf_acked) @@ -149,10 +150,12 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx) netdev_err(nic->netdev, "PF didn't ACK to mbox msg 0x%02x from VF%d\n", (mbx->msg.msg & 0xFF), nic->vf_id); - return -EBUSY; + ret = -EBUSY; + break; } } - return 0; + mutex_unlock(&nic->rx_mode_mtx); + return ret; } /* Checks if VF is able to comminicate with PF @@ -172,6 +175,17 @@ static int nicvf_check_pf_ready(struct nicvf *nic) return 1; } +static void nicvf_send_cfg_done(struct nicvf *nic) +{ + union nic_mbx mbx = {}; + + mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE; + if (nicvf_send_msg_to_pf(nic, &mbx)) { + netdev_err(nic->netdev, + "PF didn't respond to CFG DONE msg\n"); + } +} + static void nicvf_read_bgx_stats(struct nicvf *nic, struct bgx_stats_msg *bgx) { if (bgx->rx) @@ -228,21 +242,24 @@ static void nicvf_handle_mbx_intr(struct nicvf *nic) break; case NIC_MBOX_MSG_BGX_LINK_CHANGE: nic->pf_acked = true; - nic->link_up = mbx.link_status.link_up; - nic->duplex = mbx.link_status.duplex; - nic->speed = mbx.link_status.speed; - nic->mac_type = mbx.link_status.mac_type; - if (nic->link_up) { - netdev_info(nic->netdev, "Link is Up %d Mbps %s duplex\n", - nic->speed, - nic->duplex == DUPLEX_FULL ? - "Full" : "Half"); - netif_carrier_on(nic->netdev); - netif_tx_start_all_queues(nic->netdev); - } else { - netdev_info(nic->netdev, "Link is Down\n"); - netif_carrier_off(nic->netdev); - netif_tx_stop_all_queues(nic->netdev); + if (nic->link_up != mbx.link_status.link_up) { + nic->link_up = mbx.link_status.link_up; + nic->duplex = mbx.link_status.duplex; + nic->speed = mbx.link_status.speed; + nic->mac_type = mbx.link_status.mac_type; + if (nic->link_up) { + netdev_info(nic->netdev, + "Link is Up %d Mbps %s duplex\n", + nic->speed, + nic->duplex == DUPLEX_FULL ? + "Full" : "Half"); + netif_carrier_on(nic->netdev); + netif_tx_start_all_queues(nic->netdev); + } else { + netdev_info(nic->netdev, "Link is Down\n"); + netif_carrier_off(nic->netdev); + netif_tx_stop_all_queues(nic->netdev); + } } break; case NIC_MBOX_MSG_ALLOC_SQS: @@ -1311,6 +1328,11 @@ int nicvf_stop(struct net_device *netdev) struct nicvf_cq_poll *cq_poll = NULL; union nic_mbx mbx = {}; + cancel_delayed_work_sync(&nic->link_change_work); + + /* wait till all queued set_rx_mode tasks completes */ + drain_workqueue(nic->nicvf_rx_mode_wq); + mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN; nicvf_send_msg_to_pf(nic, &mbx); @@ -1410,13 +1432,27 @@ static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu) return nicvf_send_msg_to_pf(nic, &mbx); } +static void nicvf_link_status_check_task(struct work_struct *work_arg) +{ + struct nicvf *nic = container_of(work_arg, + struct nicvf, + link_change_work.work); + union nic_mbx mbx = {}; + mbx.msg.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE; + nicvf_send_msg_to_pf(nic, &mbx); + queue_delayed_work(nic->nicvf_rx_mode_wq, + &nic->link_change_work, 2 * HZ); +} + int nicvf_open(struct net_device *netdev) { int cpu, err, qidx; struct nicvf *nic = netdev_priv(netdev); struct queue_set *qs = nic->qs; struct nicvf_cq_poll *cq_poll = NULL; - union nic_mbx mbx = {}; + + /* wait till all queued set_rx_mode tasks completes if any */ + drain_workqueue(nic->nicvf_rx_mode_wq); netif_carrier_off(netdev); @@ -1512,8 +1548,12 @@ int nicvf_open(struct net_device *netdev) nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx); /* Send VF config done msg to PF */ - mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE; - nicvf_write_to_mbx(nic, &mbx); + nicvf_send_cfg_done(nic); + + INIT_DELAYED_WORK(&nic->link_change_work, + nicvf_link_status_check_task); + queue_delayed_work(nic->nicvf_rx_mode_wq, + &nic->link_change_work, 0); return 0; cleanup: @@ -1941,15 +1981,17 @@ static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs, /* flush DMAC filters and reset RX mode */ mbx.xcast.msg = NIC_MBOX_MSG_RESET_XCAST; - nicvf_send_msg_to_pf(nic, &mbx); + if (nicvf_send_msg_to_pf(nic, &mbx) < 0) + goto free_mc; if (mode & BGX_XCAST_MCAST_FILTER) { /* once enabling filtering, we need to signal to PF to add * its' own LMAC to the filter to accept packets for it. */ mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST; - mbx.xcast.data.mac = 0; - nicvf_send_msg_to_pf(nic, &mbx); + mbx.xcast.mac = 0; + if (nicvf_send_msg_to_pf(nic, &mbx) < 0) + goto free_mc; } /* check if we have any specific MACs to be added to PF DMAC filter */ @@ -1957,23 +1999,25 @@ static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs, /* now go through kernel list of MACs and add them one by one */ for (idx = 0; idx < mc_addrs->count; idx++) { mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST; - mbx.xcast.data.mac = mc_addrs->mc[idx]; - nicvf_send_msg_to_pf(nic, &mbx); + mbx.xcast.mac = mc_addrs->mc[idx]; + if (nicvf_send_msg_to_pf(nic, &mbx) < 0) + goto free_mc; } - kfree(mc_addrs); } /* and finally set rx mode for PF accordingly */ mbx.xcast.msg = NIC_MBOX_MSG_SET_XCAST; - mbx.xcast.data.mode = mode; + mbx.xcast.mode = mode; nicvf_send_msg_to_pf(nic, &mbx); +free_mc: + kfree(mc_addrs); } static void nicvf_set_rx_mode_task(struct work_struct *work_arg) { struct nicvf_work *vf_work = container_of(work_arg, struct nicvf_work, - work.work); + work); struct nicvf *nic = container_of(vf_work, struct nicvf, rx_mode_work); u8 mode; struct xcast_addr_list *mc; @@ -2030,7 +2074,7 @@ static void nicvf_set_rx_mode(struct net_device *netdev) kfree(nic->rx_mode_work.mc); nic->rx_mode_work.mc = mc_list; nic->rx_mode_work.mode = mode; - queue_delayed_work(nicvf_rx_mode_wq, &nic->rx_mode_work.work, 0); + queue_work(nic->nicvf_rx_mode_wq, &nic->rx_mode_work.work); spin_unlock(&nic->rx_mode_wq_lock); } @@ -2187,8 +2231,12 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&nic->reset_task, nicvf_reset_task); - INIT_DELAYED_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task); + nic->nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_rx_mode_wq_VF%d", + WQ_MEM_RECLAIM, + nic->vf_id); + INIT_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task); spin_lock_init(&nic->rx_mode_wq_lock); + mutex_init(&nic->rx_mode_mtx); err = register_netdev(netdev); if (err) { @@ -2228,13 +2276,15 @@ static void nicvf_remove(struct pci_dev *pdev) nic = netdev_priv(netdev); pnetdev = nic->pnicvf->netdev; - cancel_delayed_work_sync(&nic->rx_mode_work.work); - /* Check if this Qset is assigned to different VF. * If yes, clean primary and all secondary Qsets. */ if (pnetdev && (pnetdev->reg_state == NETREG_REGISTERED)) unregister_netdev(pnetdev); + if (nic->nicvf_rx_mode_wq) { + destroy_workqueue(nic->nicvf_rx_mode_wq); + nic->nicvf_rx_mode_wq = NULL; + } nicvf_unregister_interrupts(nic); pci_set_drvdata(pdev, NULL); if (nic->drv_stats) @@ -2261,17 +2311,11 @@ static struct pci_driver nicvf_driver = { static int __init nicvf_init_module(void) { pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION); - nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_generic", - WQ_MEM_RECLAIM); return pci_register_driver(&nicvf_driver); } static void __exit nicvf_cleanup_module(void) { - if (nicvf_rx_mode_wq) { - destroy_workqueue(nicvf_rx_mode_wq); - nicvf_rx_mode_wq = NULL; - } pci_unregister_driver(&nicvf_driver); } diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index e337da6ba2a4..673c57b8023f 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1217,7 +1217,7 @@ static void bgx_init_hw(struct bgx *bgx) /* Disable MAC steering (NCSI traffic) */ for (i = 0; i < RX_TRAFFIC_STEER_RULE_COUNT; i++) - bgx_reg_write(bgx, 0, BGX_CMR_RX_STREERING + (i * 8), 0x00); + bgx_reg_write(bgx, 0, BGX_CMR_RX_STEERING + (i * 8), 0x00); } static u8 bgx_get_lane2sds_cfg(struct bgx *bgx, struct lmac *lmac) diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index cbdd20b9ee6f..5cbc54e9eb19 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -60,7 +60,7 @@ #define RX_DMACX_CAM_EN BIT_ULL(48) #define RX_DMACX_CAM_LMACID(x) (((u64)x) << 49) #define RX_DMAC_COUNT 32 -#define BGX_CMR_RX_STREERING 0x300 +#define BGX_CMR_RX_STEERING 0x300 #define RX_TRAFFIC_STEER_RULE_COUNT 8 #define BGX_CMR_CHAN_MSK_AND 0x450 #define BGX_CMR_BIST_STATUS 0x460 diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index f52e2c46e6a7..e4ff531db14a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3289,8 +3289,11 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) : !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); if (!ok) { + /* Log this in case the user has forgotten to give the kernel + * any buffers, even later in the application. + */ dev_info(&vsi->back->pdev->dev, - "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n", + "Failed to allocate some buffers on %sRx ring %d (pf_q %d)\n", ring->xsk_umem ? "UMEM enabled " : "", ring->queue_index, pf_q); } @@ -6725,8 +6728,13 @@ void i40e_down(struct i40e_vsi *vsi) for (i = 0; i < vsi->num_queue_pairs; i++) { i40e_clean_tx_ring(vsi->tx_rings[i]); - if (i40e_enabled_xdp_vsi(vsi)) + if (i40e_enabled_xdp_vsi(vsi)) { + /* Make sure that in-progress ndo_xdp_xmit + * calls are completed. + */ + synchronize_rcu(); i40e_clean_tx_ring(vsi->xdp_rings[i]); + } i40e_clean_rx_ring(vsi->rx_rings[i]); } @@ -11895,6 +11903,14 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, if (old_prog) bpf_prog_put(old_prog); + /* Kick start the NAPI context if there is an AF_XDP socket open + * on that queue id. This so that receiving will start. + */ + if (need_reset && prog) + for (i = 0; i < vsi->num_queue_pairs; i++) + if (vsi->xdp_rings[i]->xsk_umem) + (void)i40e_xsk_async_xmit(vsi->netdev, i); + return 0; } @@ -11955,8 +11971,13 @@ static void i40e_queue_pair_reset_stats(struct i40e_vsi *vsi, int queue_pair) static void i40e_queue_pair_clean_rings(struct i40e_vsi *vsi, int queue_pair) { i40e_clean_tx_ring(vsi->tx_rings[queue_pair]); - if (i40e_enabled_xdp_vsi(vsi)) + if (i40e_enabled_xdp_vsi(vsi)) { + /* Make sure that in-progress ndo_xdp_xmit calls are + * completed. + */ + synchronize_rcu(); i40e_clean_tx_ring(vsi->xdp_rings[queue_pair]); + } i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index a7e14e98889f..6c97667d20ef 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -3709,6 +3709,7 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, struct i40e_netdev_priv *np = netdev_priv(dev); unsigned int queue_index = smp_processor_id(); struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; struct i40e_ring *xdp_ring; int drops = 0; int i; @@ -3716,7 +3717,8 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, if (test_bit(__I40E_VSI_DOWN, vsi->state)) return -ENETDOWN; - if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs) + if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs || + test_bit(__I40E_CONFIG_BUSY, pf->state)) return -ENXIO; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 870cf654e436..3827f16e6923 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -183,6 +183,11 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, err = i40e_queue_pair_enable(vsi, qid); if (err) return err; + + /* Kick start the NAPI context so that receiving will start */ + err = i40e_xsk_async_xmit(vsi->netdev, qid); + if (err) + return err; } return 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index daff8183534b..cb35d8202572 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -3953,8 +3953,11 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) else mrqc = IXGBE_MRQC_VMDQRSS64EN; - /* Enable L3/L4 for Tx Switched packets */ - mrqc |= IXGBE_MRQC_L3L4TXSWEN; + /* Enable L3/L4 for Tx Switched packets only for X550, + * older devices do not support this feature + */ + if (hw->mac.type >= ixgbe_mac_X550) + mrqc |= IXGBE_MRQC_L3L4TXSWEN; } else { if (tcs > 4) mrqc = IXGBE_MRQC_RTRSS8TCEN; @@ -10225,6 +10228,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; struct ixgbe_adapter *adapter = netdev_priv(dev); struct bpf_prog *old_prog; + bool need_reset; if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) return -EINVAL; @@ -10247,9 +10251,10 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) return -ENOMEM; old_prog = xchg(&adapter->xdp_prog, prog); + need_reset = (!!prog != !!old_prog); /* If transitioning XDP modes reconfigure rings */ - if (!!prog != !!old_prog) { + if (need_reset) { int err = ixgbe_setup_tc(dev, adapter->hw_tcs); if (err) { @@ -10265,6 +10270,14 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) if (old_prog) bpf_prog_put(old_prog); + /* Kick start the NAPI context if there is an AF_XDP socket open + * on that queue id. This so that receiving will start. + */ + if (need_reset && prog) + for (i = 0; i < adapter->num_rx_queues; i++) + if (adapter->xdp_ring[i]->xsk_umem) + (void)ixgbe_xsk_async_xmit(adapter->netdev, i); + return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 65c3e2c979d4..36a8879536a4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -144,11 +144,19 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, ixgbe_txrx_ring_disable(adapter, qid); err = ixgbe_add_xsk_umem(adapter, umem, qid); + if (err) + return err; - if (if_running) + if (if_running) { ixgbe_txrx_ring_enable(adapter, qid); - return err; + /* Kick start the NAPI context so that receiving will start */ + err = ixgbe_xsk_async_xmit(adapter->netdev, qid); + if (err) + return err; + } + + return 0; } static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid) @@ -634,7 +642,8 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) dma_addr_t dma; while (budget-- > 0) { - if (unlikely(!ixgbe_desc_unused(xdp_ring))) { + if (unlikely(!ixgbe_desc_unused(xdp_ring)) || + !netif_carrier_ok(xdp_ring->netdev)) { work_done = false; break; } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 9d4568eb2297..8433fb9c3eee 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2146,7 +2146,7 @@ err_drop_frame: if (unlikely(!skb)) goto err_drop_frame_ret_pool; - dma_sync_single_range_for_cpu(dev->dev.parent, + dma_sync_single_range_for_cpu(&pp->bm_priv->pdev->dev, rx_desc->buf_phys_addr, MVNETA_MH_SIZE + NET_SKB_PAD, rx_bytes, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index e23ca90289f7..0a868c829b90 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -1291,15 +1291,10 @@ wrp_alu64_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, static int wrp_alu32_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, - enum alu_op alu_op, bool skip) + enum alu_op alu_op) { const struct bpf_insn *insn = &meta->insn; - if (skip) { - meta->skip = true; - return 0; - } - wrp_alu_imm(nfp_prog, insn->dst_reg * 2, alu_op, insn->imm); wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2 + 1), 0); @@ -2309,7 +2304,7 @@ static int xor_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int xor_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_alu32_imm(nfp_prog, meta, ALU_OP_XOR, !~meta->insn.imm); + return wrp_alu32_imm(nfp_prog, meta, ALU_OP_XOR); } static int and_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) @@ -2319,7 +2314,7 @@ static int and_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int and_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_alu32_imm(nfp_prog, meta, ALU_OP_AND, !~meta->insn.imm); + return wrp_alu32_imm(nfp_prog, meta, ALU_OP_AND); } static int or_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) @@ -2329,7 +2324,7 @@ static int or_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int or_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_alu32_imm(nfp_prog, meta, ALU_OP_OR, !meta->insn.imm); + return wrp_alu32_imm(nfp_prog, meta, ALU_OP_OR); } static int add_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) @@ -2339,7 +2334,7 @@ static int add_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int add_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_alu32_imm(nfp_prog, meta, ALU_OP_ADD, !meta->insn.imm); + return wrp_alu32_imm(nfp_prog, meta, ALU_OP_ADD); } static int sub_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) @@ -2349,7 +2344,7 @@ static int sub_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int sub_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB, !meta->insn.imm); + return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB); } static int mul_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 7cdac77d0c68..07e41c42bcf5 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -499,6 +499,8 @@ static int ipvlan_nl_changelink(struct net_device *dev, if (!data) return 0; + if (!ns_capable(dev_net(ipvlan->phy_dev)->user_ns, CAP_NET_ADMIN)) + return -EPERM; if (data[IFLA_IPVLAN_MODE]) { u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]); @@ -601,6 +603,8 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, struct ipvl_dev *tmp = netdev_priv(phy_dev); phy_dev = tmp->phy_dev; + if (!ns_capable(dev_net(phy_dev)->user_ns, CAP_NET_ADMIN)) + return -EPERM; } else if (!netif_is_ipvlan_port(phy_dev)) { /* Exit early if the underlying link is invalid or busy */ if (phy_dev->type != ARPHRD_ETHER || diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index 82ab6ed3b74e..6bac602094bd 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -26,6 +26,8 @@ #include <linux/marvell_phy.h> #include <linux/phy.h> +#define MDIO_AN_10GBT_CTRL_ADV_NBT_MASK 0x01e0 + enum { MV_PCS_BASE_T = 0x0000, MV_PCS_BASE_R = 0x1000, @@ -386,8 +388,10 @@ static int mv3310_config_aneg(struct phy_device *phydev) else reg = 0; + /* Make sure we clear unsupported 2.5G/5G advertising */ ret = mv3310_modify(phydev, MDIO_MMD_AN, MDIO_AN_10GBT_CTRL, - MDIO_AN_10GBT_CTRL_ADV10G, reg); + MDIO_AN_10GBT_CTRL_ADV10G | + MDIO_AN_10GBT_CTRL_ADV_NBT_MASK, reg); if (ret < 0) return ret; if (ret > 0) diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 66b9cfe692fc..7368616286ae 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -379,7 +379,6 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) err = device_register(&bus->dev); if (err) { pr_err("mii_bus %s failed to register\n", bus->id); - put_device(&bus->dev); return -EINVAL; } diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index c6010fb1aa0f..cb4a23041a94 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -282,6 +282,13 @@ static struct phy_driver realtek_drvs[] = { .name = "RTL8366RB Gigabit Ethernet", .features = PHY_GBIT_FEATURES, .config_init = &rtl8366rb_config_init, + /* These interrupts are handled by the irq controller + * embedded inside the RTL8366RB, they get unmasked when the + * irq is requested and ACKed by reading the status register, + * which is done by the irqchip code. + */ + .ack_interrupt = genphy_no_ack_interrupt, + .config_intr = genphy_no_config_intr, .suspend = genphy_suspend, .resume = genphy_resume, }, diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 958f1cf67282..6ce3f666d142 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1256,7 +1256,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev, list_add_tail_rcu(&port->list, &team->port_list); team_port_enable(team, port); __team_compute_features(team); - __team_port_change_port_added(port, !!netif_carrier_ok(port_dev)); + __team_port_change_port_added(port, !!netif_oper_up(port_dev)); __team_options_change_check(team); netdev_info(dev, "Port device %s added\n", portname); @@ -2915,7 +2915,7 @@ static int team_device_event(struct notifier_block *unused, switch (event) { case NETDEV_UP: - if (netif_carrier_ok(dev)) + if (netif_oper_up(dev)) team_port_change_check(port, true); break; case NETDEV_DOWN: diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index ada6baf8847a..86c8c64fbb0f 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1179,7 +1179,7 @@ static int vendor_mac_passthru_addr_read(struct r8152 *tp, struct sockaddr *sa) } else { /* test for RTL8153-BND and RTL8153-BD */ ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_MISC_1); - if ((ocp_data & BND_MASK) == 0 && (ocp_data & BD_MASK)) { + if ((ocp_data & BND_MASK) == 0 && (ocp_data & BD_MASK) == 0) { netif_dbg(tp, probe, tp->netdev, "Invalid variant for MAC pass through\n"); return -ENODEV; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 95909e262ba4..7c1430ed0244 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1273,6 +1273,9 @@ static void vrf_setup(struct net_device *dev) /* default to no qdisc; user can add if desired */ dev->priv_flags |= IFF_NO_QUEUE; + + dev->min_mtu = 0; + dev->max_mtu = 0; } static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 320edcac4699..6359053bd0c7 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3554,7 +3554,7 @@ static int hwsim_get_radio_nl(struct sk_buff *msg, struct genl_info *info) goto out_err; } - genlmsg_reply(skb, info); + res = genlmsg_reply(skb, info); break; } diff --git a/include/linux/phy.h b/include/linux/phy.h index 127fcc9c3778..333b56d8f746 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -992,6 +992,14 @@ static inline int genphy_no_soft_reset(struct phy_device *phydev) { return 0; } +static inline int genphy_no_ack_interrupt(struct phy_device *phydev) +{ + return 0; +} +static inline int genphy_no_config_intr(struct phy_device *phydev) +{ + return 0; +} int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, u16 regnum); int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 71f2394abbf7..e0348cb0a1dd 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -61,10 +61,20 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, /* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. */ - if (gso_type) { + if (gso_type && skb->network_header) { + if (!skb->protocol) + virtio_net_hdr_set_proto(skb, hdr); +retry: skb_probe_transport_header(skb, -1); - if (!skb_transport_header_was_set(skb)) + if (!skb_transport_header_was_set(skb)) { + /* UFO does not specify ipv4 or 6: try both */ + if (gso_type & SKB_GSO_UDP && + skb->protocol == htons(ETH_P_IP)) { + skb->protocol = htons(ETH_P_IPV6); + goto retry; + } return -EINVAL; + } } } diff --git a/include/net/phonet/pep.h b/include/net/phonet/pep.h index b669fe6dbc3b..98f31c7ea23d 100644 --- a/include/net/phonet/pep.h +++ b/include/net/phonet/pep.h @@ -63,10 +63,11 @@ struct pnpipehdr { u8 state_after_reset; /* reset request */ u8 error_code; /* any response */ u8 pep_type; /* status indication */ - u8 data[1]; + u8 data0; /* anything else */ }; + u8 data[]; }; -#define other_pep_type data[1] +#define other_pep_type data[0] static inline struct pnpipehdr *pnp_hdr(struct sk_buff *skb) { diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 7298a53b9702..85386becbaea 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -853,7 +853,7 @@ static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) xfrm_pol_put(pols[i]); } -void __xfrm_state_destroy(struct xfrm_state *); +void __xfrm_state_destroy(struct xfrm_state *, bool); static inline void __xfrm_state_put(struct xfrm_state *x) { @@ -863,7 +863,13 @@ static inline void __xfrm_state_put(struct xfrm_state *x) static inline void xfrm_state_put(struct xfrm_state *x) { if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x); + __xfrm_state_destroy(x, false); +} + +static inline void xfrm_state_put_sync(struct xfrm_state *x) +{ + if (refcount_dec_and_test(&x->refcnt)) + __xfrm_state_destroy(x, true); } static inline void xfrm_state_hold(struct xfrm_state *x) @@ -1590,7 +1596,7 @@ struct xfrmk_spdinfo { struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq); int xfrm_state_delete(struct xfrm_state *x); -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid); +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index abf1002080df..93a5cbbde421 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -471,6 +471,7 @@ static int trie_delete_elem(struct bpf_map *map, void *_key) } if (!node || node->prefixlen != key->prefixlen || + node->prefixlen != matchlen || (node->flags & LPM_TREE_NODE_FLAG_IM)) { ret = -ENOENT; goto out; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index fa2644d276ef..e31e1b20f7f4 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -13,27 +13,13 @@ #include <net/sock.h> #include <net/tcp.h> -static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx, - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) -{ - u32 ret; - - preempt_disable(); - rcu_read_lock(); - bpf_cgroup_storage_set(storage); - ret = BPF_PROG_RUN(prog, ctx); - rcu_read_unlock(); - preempt_enable(); - - return ret; -} - -static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *ret, - u32 *time) +static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, + u32 *retval, u32 *time) { struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { 0 }; enum bpf_cgroup_storage_type stype; u64 time_start, time_spent = 0; + int ret = 0; u32 i; for_each_cgroup_storage_type(stype) { @@ -48,25 +34,42 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *ret, if (!repeat) repeat = 1; + + rcu_read_lock(); + preempt_disable(); time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { - *ret = bpf_test_run_one(prog, ctx, storage); + bpf_cgroup_storage_set(storage); + *retval = BPF_PROG_RUN(prog, ctx); + + if (signal_pending(current)) { + ret = -EINTR; + break; + } + if (need_resched()) { - if (signal_pending(current)) - break; time_spent += ktime_get_ns() - time_start; + preempt_enable(); + rcu_read_unlock(); + cond_resched(); + + rcu_read_lock(); + preempt_disable(); time_start = ktime_get_ns(); } } time_spent += ktime_get_ns() - time_start; + preempt_enable(); + rcu_read_unlock(); + do_div(time_spent, repeat); *time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent; for_each_cgroup_storage_type(stype) bpf_cgroup_storage_free(storage[stype]); - return 0; + return ret; } static int bpf_test_finish(const union bpf_attr *kattr, diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3aeff0895669..ac92b2eb32b1 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1204,14 +1204,7 @@ static void br_multicast_query_received(struct net_bridge *br, return; br_multicast_update_query_timer(br, query, max_delay); - - /* Based on RFC4541, section 2.1.1 IGMP Forwarding Rules, - * the arrival port for IGMP Queries where the source address - * is 0.0.0.0 should not be added to router port list. - */ - if ((saddr->proto == htons(ETH_P_IP) && saddr->u.ip4) || - saddr->proto == htons(ETH_P_IPV6)) - br_multicast_mark_router(br, port); + br_multicast_mark_router(br, port); } static void br_ip4_multicast_query(struct net_bridge *br, diff --git a/net/compat.c b/net/compat.c index 959d1c51826d..3d348198004f 100644 --- a/net/compat.c +++ b/net/compat.c @@ -388,8 +388,12 @@ static int __compat_sys_setsockopt(int fd, int level, int optname, char __user *optval, unsigned int optlen) { int err; - struct socket *sock = sockfd_lookup(fd, &err); + struct socket *sock; + + if (optlen > INT_MAX) + return -EINVAL; + sock = sockfd_lookup(fd, &err); if (sock) { err = security_socket_setsockopt(sock, level, optname); if (err) { diff --git a/net/dsa/port.c b/net/dsa/port.c index 2d7e01b23572..2a2a878b5ce3 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -69,7 +69,6 @@ static void dsa_port_set_state_now(struct dsa_port *dp, u8 state) int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) { - u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING; struct dsa_switch *ds = dp->ds; int port = dp->index; int err; @@ -80,7 +79,8 @@ int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) return err; } - dsa_port_set_state_now(dp, stp_state); + if (!dp->bridge_dev) + dsa_port_set_state_now(dp, BR_STATE_FORWARDING); return 0; } @@ -90,7 +90,8 @@ void dsa_port_disable(struct dsa_port *dp, struct phy_device *phy) struct dsa_switch *ds = dp->ds; int port = dp->index; - dsa_port_set_state_now(dp, BR_STATE_DISABLED); + if (!dp->bridge_dev) + dsa_port_set_state_now(dp, BR_STATE_DISABLED); if (ds->ops->port_disable) ds->ops->port_disable(ds, port, phy); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 5459f41fc26f..10e809b296ec 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -328,7 +328,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * skb->len += tailen; skb->data_len += tailen; skb->truesize += tailen; - if (sk) + if (sk && sk_fullsock(sk)) refcount_add(tailen, &sk->sk_wmem_alloc); goto out; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 3978f807fa8b..6ae89f2b541b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1457,9 +1457,23 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) struct ip_tunnel_parm *p = &t->parms; __be16 o_flags = p->o_flags; - if ((t->erspan_ver == 1 || t->erspan_ver == 2) && - !t->collect_md) - o_flags |= TUNNEL_KEY; + if (t->erspan_ver == 1 || t->erspan_ver == 2) { + if (!t->collect_md) + o_flags |= TUNNEL_KEY; + + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) + goto nla_put_failure; + + if (t->erspan_ver == 1) { + if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) + goto nla_put_failure; + } else { + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) + goto nla_put_failure; + } + } if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, @@ -1495,19 +1509,6 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) - goto nla_put_failure; - - if (t->erspan_ver == 1) { - if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) - goto nla_put_failure; - } else if (t->erspan_ver == 2) { - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) - goto nla_put_failure; - if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) - goto nla_put_failure; - } - return 0; nla_put_failure: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 730bc44dbad9..ccc78f3a4b60 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2347,6 +2347,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, /* "skb_mstamp_ns" is used as a start point for the retransmit timer */ skb->skb_mstamp_ns = tp->tcp_wstamp_ns = tp->tcp_clock_cache; list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); + tcp_init_tso_segs(skb, mss_now); goto repair; /* Skip network transmission */ } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5c3cd5d84a6f..372fdc5381a9 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -562,10 +562,12 @@ static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info) for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) { int (*handler)(struct sk_buff *skb, u32 info); + const struct ip_tunnel_encap_ops *encap; - if (!iptun_encaps[i]) + encap = rcu_dereference(iptun_encaps[i]); + if (!encap) continue; - handler = rcu_dereference(iptun_encaps[i]->err_handler); + handler = encap->err_handler; if (handler && !handler(skb, info)) return 0; } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 5afe9f83374d..239d4a65ad6e 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -296,7 +296,7 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info skb->len += tailen; skb->data_len += tailen; skb->truesize += tailen; - if (sk) + if (sk && sk_fullsock(sk)) refcount_add(tailen, &sk->sk_wmem_alloc); goto out; diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c index b858bd5280bf..867474abe269 100644 --- a/net/ipv6/fou6.c +++ b/net/ipv6/fou6.c @@ -72,7 +72,7 @@ static int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, static int gue6_err_proto_handler(int proto, struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, u32 info) + u8 type, u8 code, int offset, __be32 info) { const struct inet6_protocol *ipprot; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 43890898b0b5..26f25b6e2833 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1722,6 +1722,9 @@ static int ip6erspan_tap_validate(struct nlattr *tb[], struct nlattr *data[], static void ip6erspan_set_version(struct nlattr *data[], struct __ip6_tnl_parm *parms) { + if (!data) + return; + parms->erspan_ver = 1; if (data[IFLA_GRE_ERSPAN_VER]) parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); @@ -2104,9 +2107,23 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) struct __ip6_tnl_parm *p = &t->parms; __be16 o_flags = p->o_flags; - if ((p->erspan_ver == 1 || p->erspan_ver == 2) && - !p->collect_md) - o_flags |= TUNNEL_KEY; + if (p->erspan_ver == 1 || p->erspan_ver == 2) { + if (!p->collect_md) + o_flags |= TUNNEL_KEY; + + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver)) + goto nla_put_failure; + + if (p->erspan_ver == 1) { + if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index)) + goto nla_put_failure; + } else { + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid)) + goto nla_put_failure; + } + } if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, @@ -2121,8 +2138,7 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) || nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) || nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags) || - nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark) || - nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index)) + nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE, @@ -2140,19 +2156,6 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver)) - goto nla_put_failure; - - if (p->erspan_ver == 1) { - if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index)) - goto nla_put_failure; - } else if (p->erspan_ver == 2) { - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir)) - goto nla_put_failure; - if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid)) - goto nla_put_failure; - } - return 0; nla_put_failure: diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 964491cf3672..ce15dc4ccbfa 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1274,18 +1274,29 @@ static DEFINE_SPINLOCK(rt6_exception_lock); static void rt6_remove_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex) { + struct fib6_info *from; struct net *net; if (!bucket || !rt6_ex) return; net = dev_net(rt6_ex->rt6i->dst.dev); + net->ipv6.rt6_stats->fib_rt_cache--; + + /* purge completely the exception to allow releasing the held resources: + * some [sk] cache may keep the dst around for unlimited time + */ + from = rcu_dereference_protected(rt6_ex->rt6i->from, + lockdep_is_held(&rt6_exception_lock)); + rcu_assign_pointer(rt6_ex->rt6i->from, NULL); + fib6_info_release(from); + dst_dev_put(&rt6_ex->rt6i->dst); + hlist_del_rcu(&rt6_ex->hlist); dst_release(&rt6_ex->rt6i->dst); kfree_rcu(rt6_ex, rcu); WARN_ON_ONCE(!bucket->depth); bucket->depth--; - net->ipv6.rt6_stats->fib_rt_cache--; } /* Remove oldest rt6_ex in bucket and free the memory @@ -1599,15 +1610,15 @@ static int rt6_remove_exception_rt(struct rt6_info *rt) static void rt6_update_exception_stamp_rt(struct rt6_info *rt) { struct rt6_exception_bucket *bucket; - struct fib6_info *from = rt->from; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; - - if (!from || - !(rt->rt6i_flags & RTF_CACHE)) - return; + struct fib6_info *from; rcu_read_lock(); + from = rcu_dereference(rt->from); + if (!from || !(rt->rt6i_flags & RTF_CACHE)) + goto unlock; + bucket = rcu_dereference(from->rt6i_exception_bucket); #ifdef CONFIG_IPV6_SUBTREES @@ -1626,6 +1637,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) if (rt6_ex) rt6_ex->stamp = jiffies; +unlock: rcu_read_unlock(); } @@ -2742,20 +2754,24 @@ static int ip6_route_check_nh_onlink(struct net *net, u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; const struct in6_addr *gw_addr = &cfg->fc_gateway; u32 flags = RTF_LOCAL | RTF_ANYCAST | RTF_REJECT; + struct fib6_info *from; struct rt6_info *grt; int err; err = 0; grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0); if (grt) { + rcu_read_lock(); + from = rcu_dereference(grt->from); if (!grt->dst.error && /* ignore match if it is the default route */ - grt->from && !ipv6_addr_any(&grt->from->fib6_dst.addr) && + from && !ipv6_addr_any(&from->fib6_dst.addr) && (grt->rt6i_flags & flags || dev != grt->dst.dev)) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway or device mismatch"); err = -EINVAL; } + rcu_read_unlock(); ip6_rt_put(grt); } @@ -4649,7 +4665,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, table = rt->fib6_table->tb6_id; else table = RT6_TABLE_UNSPEC; - rtm->rtm_table = table; + rtm->rtm_table = table < 256 ? table : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table)) goto nla_put_failure; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 2596ffdeebea..b444483cdb2b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -288,8 +288,8 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int peeked, peeking, off; int err; int is_udplite = IS_UDPLITE(sk); + struct udp_mib __percpu *mib; bool checksum_valid = false; - struct udp_mib *mib; int is_udp4; if (flags & MSG_ERRQUEUE) @@ -420,17 +420,19 @@ EXPORT_SYMBOL(udpv6_encap_enable); */ static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, u32 info) + u8 type, u8 code, int offset, __be32 info) { int i; for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) { int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, u32 info); + u8 type, u8 code, int offset, __be32 info); + const struct ip6_tnl_encap_ops *encap; - if (!ip6tun_encaps[i]) + encap = rcu_dereference(ip6tun_encaps[i]); + if (!encap) continue; - handler = rcu_dereference(ip6tun_encaps[i]->err_handler); + handler = encap->err_handler; if (handler && !handler(skb, opt, type, code, offset, info)) return 0; } diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f5b4febeaa25..bc65db782bfb 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -344,8 +344,8 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); xfrm_flush_gc(); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); diff --git a/net/key/af_key.c b/net/key/af_key.c index 655c787f9d54..5651c29cb5bd 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -196,30 +196,22 @@ static int pfkey_release(struct socket *sock) return 0; } -static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2, - gfp_t allocation, struct sock *sk) +static int pfkey_broadcast_one(struct sk_buff *skb, gfp_t allocation, + struct sock *sk) { int err = -ENOBUFS; - sock_hold(sk); - if (*skb2 == NULL) { - if (refcount_read(&skb->users) != 1) { - *skb2 = skb_clone(skb, allocation); - } else { - *skb2 = skb; - refcount_inc(&skb->users); - } - } - if (*skb2 != NULL) { - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) { - skb_set_owner_r(*skb2, sk); - skb_queue_tail(&sk->sk_receive_queue, *skb2); - sk->sk_data_ready(sk); - *skb2 = NULL; - err = 0; - } + if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) + return err; + + skb = skb_clone(skb, allocation); + + if (skb) { + skb_set_owner_r(skb, sk); + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk); + err = 0; } - sock_put(sk); return err; } @@ -234,7 +226,6 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; - struct sk_buff *skb2 = NULL; int err = -ESRCH; /* XXX Do we need something like netlink_overrun? I think @@ -253,7 +244,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, * socket. */ if (pfk->promisc) - pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); + pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* the exact target will be processed later */ if (sk == one_sk) @@ -268,7 +259,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, continue; } - err2 = pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); + err2 = pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* Error is cleared after successful sending to at least one * registered KM */ @@ -278,9 +269,8 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, rcu_read_unlock(); if (one_sk != NULL) - err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk); + err = pfkey_broadcast_one(skb, allocation, one_sk); - kfree_skb(skb2); kfree_skb(skb); return err; } @@ -1783,7 +1773,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m if (proto == 0) return -EINVAL; - err = xfrm_state_flush(net, proto, true); + err = xfrm_state_flush(net, proto, true, false); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 87a729926734..977dea436ee8 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -615,13 +615,13 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, * We need a bit of data queued to build aggregates properly, so * instruct the TCP stack to allow more than a single ms of data * to be queued in the stack. The value is a bit-shift of 1 - * second, so 8 is ~4ms of queued data. Only affects local TCP + * second, so 7 is ~8ms of queued data. Only affects local TCP * sockets. * This is the default, anyhow - drivers may need to override it * for local reasons (longer buffers, longer completion time, or * similar). */ - local->hw.tx_sk_pacing_shift = 8; + local->hw.tx_sk_pacing_shift = 7; /* set up some defaults */ local->hw.queues = 1; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index bb4d71efb6fb..c2a6da5d80da 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2644,6 +2644,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) struct ieee80211_sub_if_data *sdata = rx->sdata; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; u16 ac, q, hdrlen; + int tailroom = 0; hdr = (struct ieee80211_hdr *) skb->data; hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -2732,8 +2733,12 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) if (!ifmsh->mshcfg.dot11MeshForwarding) goto out; + if (sdata->crypto_tx_tailroom_needed_cnt) + tailroom = IEEE80211_ENCRYPT_TAILROOM; + fwd_skb = skb_copy_expand(skb, local->tx_headroom + - sdata->encrypt_headroom, 0, GFP_ATOMIC); + sdata->encrypt_headroom, + tailroom, GFP_ATOMIC); if (!fwd_skb) goto out; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 9fc76b19cd3c..db3473540303 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -132,7 +132,7 @@ static int pep_indicate(struct sock *sk, u8 id, u8 code, ph->utid = 0; ph->message_id = id; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = code; + ph->error_code = code; return pn_skb_send(sk, skb, NULL); } @@ -153,7 +153,7 @@ static int pipe_handler_request(struct sock *sk, u8 id, u8 code, ph->utid = id; /* whatever */ ph->message_id = id; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = code; + ph->error_code = code; return pn_skb_send(sk, skb, NULL); } @@ -208,7 +208,7 @@ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code, struct pnpipehdr *ph; struct sockaddr_pn dst; u8 data[4] = { - oph->data[0], /* PEP type */ + oph->pep_type, /* PEP type */ code, /* error code, at an unusual offset */ PAD, PAD, }; @@ -221,7 +221,7 @@ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code, ph->utid = oph->utid; ph->message_id = PNS_PEP_CTRL_RESP; ph->pipe_handle = oph->pipe_handle; - ph->data[0] = oph->data[1]; /* CTRL id */ + ph->data0 = oph->data[0]; /* CTRL id */ pn_skb_get_src_sockaddr(oskb, &dst); return pn_skb_send(sk, skb, &dst); @@ -272,17 +272,17 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) return -EINVAL; hdr = pnp_hdr(skb); - if (hdr->data[0] != PN_PEP_TYPE_COMMON) { + if (hdr->pep_type != PN_PEP_TYPE_COMMON) { net_dbg_ratelimited("Phonet unknown PEP type: %u\n", - (unsigned int)hdr->data[0]); + (unsigned int)hdr->pep_type); return -EOPNOTSUPP; } - switch (hdr->data[1]) { + switch (hdr->data[0]) { case PN_PEP_IND_FLOW_CONTROL: switch (pn->tx_fc) { case PN_LEGACY_FLOW_CONTROL: - switch (hdr->data[4]) { + switch (hdr->data[3]) { case PEP_IND_BUSY: atomic_set(&pn->tx_credits, 0); break; @@ -292,7 +292,7 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) } break; case PN_ONE_CREDIT_FLOW_CONTROL: - if (hdr->data[4] == PEP_IND_READY) + if (hdr->data[3] == PEP_IND_READY) atomic_set(&pn->tx_credits, wake = 1); break; } @@ -301,12 +301,12 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) case PN_PEP_IND_ID_MCFC_GRANT_CREDITS: if (pn->tx_fc != PN_MULTI_CREDIT_FLOW_CONTROL) break; - atomic_add(wake = hdr->data[4], &pn->tx_credits); + atomic_add(wake = hdr->data[3], &pn->tx_credits); break; default: net_dbg_ratelimited("Phonet unknown PEP indication: %u\n", - (unsigned int)hdr->data[1]); + (unsigned int)hdr->data[0]); return -EOPNOTSUPP; } if (wake) @@ -318,7 +318,7 @@ static int pipe_rcv_created(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); struct pnpipehdr *hdr = pnp_hdr(skb); - u8 n_sb = hdr->data[0]; + u8 n_sb = hdr->data0; pn->rx_fc = pn->tx_fc = PN_LEGACY_FLOW_CONTROL; __skb_pull(skb, sizeof(*hdr)); @@ -506,7 +506,7 @@ static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb) return -ECONNREFUSED; /* Parse sub-blocks */ - n_sb = hdr->data[4]; + n_sb = hdr->data[3]; while (n_sb > 0) { u8 type, buf[6], len = sizeof(buf); const u8 *data = pep_get_sb(skb, &type, &len, buf); @@ -739,7 +739,7 @@ static int pipe_do_remove(struct sock *sk) ph->utid = 0; ph->message_id = PNS_PIPE_REMOVE_REQ; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = PAD; + ph->data0 = PAD; return pn_skb_send(sk, skb, NULL); } @@ -817,7 +817,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, peer_type = hdr->other_pep_type << 8; /* Parse sub-blocks (options) */ - n_sb = hdr->data[4]; + n_sb = hdr->data[3]; while (n_sb > 0) { u8 type, buf[1], len = sizeof(buf); const u8 *data = pep_get_sb(skb, &type, &len, buf); @@ -1109,7 +1109,7 @@ static int pipe_skb_send(struct sock *sk, struct sk_buff *skb) ph->utid = 0; if (pn->aligned) { ph->message_id = PNS_PIPE_ALIGNED_DATA; - ph->data[0] = 0; /* padding */ + ph->data0 = 0; /* padding */ } else ph->message_id = PNS_PIPE_DATA; ph->pipe_handle = pn->pipe_handle; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 033696e6f74f..ad158d311ffa 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -207,7 +207,8 @@ void sctp_transport_reset_hb_timer(struct sctp_transport *transport) /* When a data chunk is sent, reset the heartbeat interval. */ expires = jiffies + sctp_transport_timeout(transport); - if (time_before(transport->hb_timer.expires, expires) && + if ((time_before(transport->hb_timer.expires, expires) || + !timer_pending(&transport->hb_timer)) && !mod_timer(&transport->hb_timer, expires + prandom_u32_max(transport->rto))) sctp_transport_hold(transport); diff --git a/net/smc/smc.h b/net/smc/smc.h index 5721416d0605..adbdf195eb08 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -113,9 +113,9 @@ struct smc_host_cdc_msg { /* Connection Data Control message */ } __aligned(8); enum smc_urg_state { - SMC_URG_VALID, /* data present */ - SMC_URG_NOTYET, /* data pending */ - SMC_URG_READ /* data was already read */ + SMC_URG_VALID = 1, /* data present */ + SMC_URG_NOTYET = 2, /* data pending */ + SMC_URG_READ = 3, /* data was already read */ }; struct smc_connection { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 1217c90a363b..684f2125fc6b 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -388,7 +388,7 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout) rc_ = tipc_sk_sock_err((sock_), timeo_); \ if (rc_) \ break; \ - prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE); \ + add_wait_queue(sk_sleep(sk_), &wait_); \ release_sock(sk_); \ *(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \ sched_annotate_sleep(); \ @@ -1677,7 +1677,7 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk) static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) { struct sock *sk = sock->sk; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); long timeo = *timeop; int err = sock_error(sk); @@ -1685,15 +1685,17 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) return err; for (;;) { - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { if (sk->sk_shutdown & RCV_SHUTDOWN) { err = -ENOTCONN; break; } + add_wait_queue(sk_sleep(sk), &wait); release_sock(sk); - timeo = schedule_timeout(timeo); + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); + sched_annotate_sleep(); lock_sock(sk); + remove_wait_queue(sk_sleep(sk), &wait); } err = 0; if (!skb_queue_empty(&sk->sk_receive_queue)) @@ -1709,7 +1711,6 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) if (err) break; } - finish_wait(sk_sleep(sk), &wait); *timeop = timeo; return err; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 74d1eed7cbd4..a95d479caeea 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -890,7 +890,7 @@ retry: addr->hash ^= sk->sk_type; __unix_remove_socket(sk); - u->addr = addr; + smp_store_release(&u->addr, addr); __unix_insert_socket(&unix_socket_table[addr->hash], sk); spin_unlock(&unix_table_lock); err = 0; @@ -1060,7 +1060,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = 0; __unix_remove_socket(sk); - u->addr = addr; + smp_store_release(&u->addr, addr); __unix_insert_socket(list, sk); out_unlock: @@ -1331,15 +1331,29 @@ restart: RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq); otheru = unix_sk(other); - /* copy address information from listening to new sock*/ - if (otheru->addr) { - refcount_inc(&otheru->addr->refcnt); - newu->addr = otheru->addr; - } + /* copy address information from listening to new sock + * + * The contents of *(otheru->addr) and otheru->path + * are seen fully set up here, since we have found + * otheru in hash under unix_table_lock. Insertion + * into the hash chain we'd found it in had been done + * in an earlier critical area protected by unix_table_lock, + * the same one where we'd set *(otheru->addr) contents, + * as well as otheru->path and otheru->addr itself. + * + * Using smp_store_release() here to set newu->addr + * is enough to make those stores, as well as stores + * to newu->path visible to anyone who gets newu->addr + * by smp_load_acquire(). IOW, the same warranties + * as for unix_sock instances bound in unix_bind() or + * in unix_autobind(). + */ if (otheru->path.dentry) { path_get(&otheru->path); newu->path = otheru->path; } + refcount_inc(&otheru->addr->refcnt); + smp_store_release(&newu->addr, otheru->addr); /* Set credentials */ copy_peercred(sk, other); @@ -1453,7 +1467,7 @@ out: static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; - struct unix_sock *u; + struct unix_address *addr; DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, uaddr); int err = 0; @@ -1468,19 +1482,15 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) sock_hold(sk); } - u = unix_sk(sk); - unix_state_lock(sk); - if (!u->addr) { + addr = smp_load_acquire(&unix_sk(sk)->addr); + if (!addr) { sunaddr->sun_family = AF_UNIX; sunaddr->sun_path[0] = 0; err = sizeof(short); } else { - struct unix_address *addr = u->addr; - err = addr->len; memcpy(sunaddr, addr->name, addr->len); } - unix_state_unlock(sk); sock_put(sk); out: return err; @@ -2073,11 +2083,11 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg, static void unix_copy_addr(struct msghdr *msg, struct sock *sk) { - struct unix_sock *u = unix_sk(sk); + struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr); - if (u->addr) { - msg->msg_namelen = u->addr->len; - memcpy(msg->msg_name, u->addr->name, u->addr->len); + if (addr) { + msg->msg_namelen = addr->len; + memcpy(msg->msg_name, addr->name, addr->len); } } @@ -2581,15 +2591,14 @@ static int unix_open_file(struct sock *sk) if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; - unix_state_lock(sk); + if (!smp_load_acquire(&unix_sk(sk)->addr)) + return -ENOENT; + path = unix_sk(sk)->path; - if (!path.dentry) { - unix_state_unlock(sk); + if (!path.dentry) return -ENOENT; - } path_get(&path); - unix_state_unlock(sk); fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) @@ -2830,7 +2839,7 @@ static int unix_seq_show(struct seq_file *seq, void *v) (s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING), sock_i_ino(s)); - if (u->addr) { + if (u->addr) { // under unix_table_lock here int i, len; seq_putc(seq, ' '); diff --git a/net/unix/diag.c b/net/unix/diag.c index 384c84e83462..3183d9b8ab33 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -10,7 +10,8 @@ static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb) { - struct unix_address *addr = unix_sk(sk)->addr; + /* might or might not have unix_table_lock */ + struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr); if (!addr) return 0; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index ec3a828672ef..eff31348e20b 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -679,8 +679,7 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sockaddr_x25 *addr = (struct sockaddr_x25 *)uaddr; int len, i, rc = 0; - if (!sock_flag(sk, SOCK_ZAPPED) || - addr_len != sizeof(struct sockaddr_x25) || + if (addr_len != sizeof(struct sockaddr_x25) || addr->sx25_family != AF_X25) { rc = -EINVAL; goto out; @@ -699,9 +698,13 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } lock_sock(sk); - x25_sk(sk)->source_addr = addr->sx25_addr; - x25_insert_socket(sk); - sock_reset_flag(sk, SOCK_ZAPPED); + if (sock_flag(sk, SOCK_ZAPPED)) { + x25_sk(sk)->source_addr = addr->sx25_addr; + x25_insert_socket(sk); + sock_reset_flag(sk, SOCK_ZAPPED); + } else { + rc = -EINVAL; + } release_sock(sk); SOCK_DEBUG(sk, "x25_bind: socket is bound\n"); out: diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 45f3b528dc09..85e4fe4f18cc 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -366,7 +366,6 @@ static int xsk_release(struct socket *sock) xskq_destroy(xs->rx); xskq_destroy(xs->tx); - xdp_put_umem(xs->umem); sock_orphan(sk); sock->sk = NULL; @@ -718,6 +717,18 @@ static const struct proto_ops xsk_proto_ops = { .sendpage = sock_no_sendpage, }; +static void xsk_destruct(struct sock *sk) +{ + struct xdp_sock *xs = xdp_sk(sk); + + if (!sock_flag(sk, SOCK_DEAD)) + return; + + xdp_put_umem(xs->umem); + + sk_refcnt_debug_dec(sk); +} + static int xsk_create(struct net *net, struct socket *sock, int protocol, int kern) { @@ -744,6 +755,9 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol, sk->sk_family = PF_XDP; + sk->sk_destruct = xsk_destruct; + sk_refcnt_debug_inc(sk); + sock_set_flag(sk, SOCK_RCU_FREE); xs = xdp_sk(sk); diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 6be8c7df15bb..dbb3c1945b5c 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -76,10 +76,10 @@ static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb) int ifindex; struct xfrm_if *xi; - if (!skb->dev) + if (!secpath_exists(skb) || !skb->dev) return NULL; - xfrmn = net_generic(dev_net(skb->dev), xfrmi_net_id); + xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id); ifindex = skb->dev->ifindex; for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ba0a4048c846..8d1a898d0ba5 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3314,8 +3314,10 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (ifcb) { xi = ifcb->decode_session(skb); - if (xi) + if (xi) { if_id = xi->p.if_id; + net = xi->net; + } } rcu_read_unlock(); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 23c92891758a..1bb971f46fc6 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -432,7 +432,7 @@ void xfrm_state_free(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_free); -static void xfrm_state_gc_destroy(struct xfrm_state *x) +static void ___xfrm_state_destroy(struct xfrm_state *x) { tasklet_hrtimer_cancel(&x->mtimer); del_timer_sync(&x->rtimer); @@ -474,7 +474,7 @@ static void xfrm_state_gc_task(struct work_struct *work) synchronize_rcu(); hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) - xfrm_state_gc_destroy(x); + ___xfrm_state_destroy(x); } static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) @@ -598,14 +598,19 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) } EXPORT_SYMBOL(xfrm_state_alloc); -void __xfrm_state_destroy(struct xfrm_state *x) +void __xfrm_state_destroy(struct xfrm_state *x, bool sync) { WARN_ON(x->km.state != XFRM_STATE_DEAD); - spin_lock_bh(&xfrm_state_gc_lock); - hlist_add_head(&x->gclist, &xfrm_state_gc_list); - spin_unlock_bh(&xfrm_state_gc_lock); - schedule_work(&xfrm_state_gc_work); + if (sync) { + synchronize_rcu(); + ___xfrm_state_destroy(x); + } else { + spin_lock_bh(&xfrm_state_gc_lock); + hlist_add_head(&x->gclist, &xfrm_state_gc_list); + spin_unlock_bh(&xfrm_state_gc_lock); + schedule_work(&xfrm_state_gc_work); + } } EXPORT_SYMBOL(__xfrm_state_destroy); @@ -708,7 +713,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool } #endif -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync) { int i, err = 0, cnt = 0; @@ -730,7 +735,10 @@ restart: err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); - xfrm_state_put(x); + if (sync) + xfrm_state_put_sync(x); + else + xfrm_state_put(x); if (!err) cnt++; @@ -2215,7 +2223,7 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x) if (atomic_read(&t->tunnel_users) == 2) xfrm_state_delete(t); atomic_dec(&t->tunnel_users); - xfrm_state_put(t); + xfrm_state_put_sync(t); x->tunnel = NULL; } } @@ -2375,8 +2383,8 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); flush_work(&xfrm_state_gc_work); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index c6d26afcf89d..a131f9ff979e 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1932,7 +1932,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_usersa_flush *p = nlmsg_data(nlh); int err; - err = xfrm_state_flush(net, p->proto, true); + err = xfrm_state_flush(net, p->proto, true, false); if (err) { if (err == -ESRCH) /* empty table */ return 0; diff --git a/security/lsm_audit.c b/security/lsm_audit.c index f84001019356..33028c098ef3 100644 --- a/security/lsm_audit.c +++ b/security/lsm_audit.c @@ -321,6 +321,7 @@ static void dump_common_audit_data(struct audit_buffer *ab, if (a->u.net->sk) { struct sock *sk = a->u.net->sk; struct unix_sock *u; + struct unix_address *addr; int len = 0; char *p = NULL; @@ -351,14 +352,15 @@ static void dump_common_audit_data(struct audit_buffer *ab, #endif case AF_UNIX: u = unix_sk(sk); + addr = smp_load_acquire(&u->addr); + if (!addr) + break; if (u->path.dentry) { audit_log_d_path(ab, " path=", &u->path); break; } - if (!u->addr) - break; - len = u->addr->len-sizeof(short); - p = &u->addr->name->sun_path[0]; + len = addr->len-sizeof(short); + p = &addr->name->sun_path[0]; audit_log_format(ab, " path="); if (*p) audit_log_untrustedstring(ab, p); diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c index 147e34cfceb7..02d7c871862a 100644 --- a/tools/testing/selftests/bpf/test_lpm_map.c +++ b/tools/testing/selftests/bpf/test_lpm_map.c @@ -474,6 +474,16 @@ static void test_lpm_delete(void) assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 && errno == ENOENT); + key->prefixlen = 30; // unused prefix so far + inet_pton(AF_INET, "192.255.0.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == -1 && + errno == ENOENT); + + key->prefixlen = 16; // same prefix as the root node + inet_pton(AF_INET, "192.255.0.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == -1 && + errno == ENOENT); + /* assert initial lookup */ key->prefixlen = 32; inet_pton(AF_INET, "192.168.0.1", key->data); diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 802b4af18729..1080ff55a788 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -388,6 +388,7 @@ fib_carrier_unicast_test() set -e $IP link set dev dummy0 carrier off + sleep 1 set +e echo " Carrier down" |