diff --git a/Documentation/networking/e100.txt b/Documentation/networking/e100.txt index f862cf3aff34..42ddbd4b52a9 100644 --- a/Documentation/networking/e100.txt +++ b/Documentation/networking/e100.txt @@ -181,17 +181,3 @@ For general information, go to the Intel support website at: If an issue is identified with the released source code on the supported kernel with a supported adapter, email the specific information related to the issue to e1000-devel@lists.sourceforge.net. - - -License -======= - -This software program is released under the terms of a license agreement -between you ('Licensee') and Intel. Do not use or load this software or any -associated materials (collectively, the 'Software') until you have carefully -read the full terms and conditions of the file COPYING located in this software -package. By loading or using the Software, you agree to the terms of this -Agreement. If you do not agree with the terms of this Agreement, do not install -or use the Software. - -* Other names and brands may be claimed as the property of others. diff --git a/MAINTAINERS b/MAINTAINERS index 9bff63cf326e..6889a6dbb42d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5578,7 +5578,7 @@ R: Jesse Brandeburg R: Shannon Nelson R: Carolyn Wyborny R: Don Skidmore -R: Matthew Vick +R: Bruce Allan R: John Ronciak R: Mitch Williams L: intel-wired-lan@lists.osuosl.org @@ -8946,6 +8946,13 @@ F: drivers/rpmsg/ F: Documentation/rpmsg.txt F: include/linux/rpmsg.h +RENESAS ETHERNET DRIVERS +R: Sergei Shtylyov +L: netdev@vger.kernel.org +L: linux-sh@vger.kernel.org +F: drivers/net/ethernet/renesas/ +F: include/linux/sh_eth.h + RESET CONTROLLER FRAMEWORK M: Philipp Zabel S: Maintained diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c index 375be509e95f..2a506fe0c8a4 100644 --- a/drivers/isdn/gigaset/ser-gigaset.c +++ b/drivers/isdn/gigaset/ser-gigaset.c @@ -67,8 +67,7 @@ static int write_modem(struct cardstate *cs) struct sk_buff *skb = bcs->tx_skb; int sent = -EOPNOTSUPP; - if (!tty || !tty->driver || !skb) - return -EINVAL; + WARN_ON(!tty || !tty->ops || !skb); if (!skb->len) { dev_kfree_skb_any(skb); @@ -109,8 +108,7 @@ static int send_cb(struct cardstate *cs) unsigned long flags; int sent = 0; - if (!tty || !tty->driver) - return -EFAULT; + WARN_ON(!tty || !tty->ops); cb = cs->cmdbuf; if (!cb) @@ -370,19 +368,18 @@ static void gigaset_freecshw(struct cardstate *cs) tasklet_kill(&cs->write_tasklet); if (!cs->hw.ser) return; - dev_set_drvdata(&cs->hw.ser->dev.dev, NULL); platform_device_unregister(&cs->hw.ser->dev); - kfree(cs->hw.ser); - cs->hw.ser = NULL; } static void gigaset_device_release(struct device *dev) { - struct platform_device *pdev = to_platform_device(dev); + struct cardstate *cs = dev_get_drvdata(dev); - /* adapted from platform_device_release() in drivers/base/platform.c */ - kfree(dev->platform_data); - kfree(pdev->resource); + if (!cs) + return; + dev_set_drvdata(dev, NULL); + kfree(cs->hw.ser); + cs->hw.ser = NULL; } /* @@ -432,7 +429,9 @@ static int gigaset_set_modem_ctrl(struct cardstate *cs, unsigned old_state, struct tty_struct *tty = cs->hw.ser->tty; unsigned int set, clear; - if (!tty || !tty->driver || !tty->ops->tiocmset) + WARN_ON(!tty || !tty->ops); + /* tiocmset is an optional tty driver method */ + if (!tty->ops->tiocmset) return -EINVAL; set = new_state & ~old_state; clear = old_state & ~new_state; diff --git a/drivers/isdn/hardware/mISDN/mISDNipac.c b/drivers/isdn/hardware/mISDN/mISDNipac.c index a77eea594b69..cb428b9ee441 100644 --- a/drivers/isdn/hardware/mISDN/mISDNipac.c +++ b/drivers/isdn/hardware/mISDN/mISDNipac.c @@ -1170,7 +1170,7 @@ mISDNipac_irq(struct ipac_hw *ipac, int maxloop) if (ipac->type & IPAC_TYPE_IPACX) { ista = ReadIPAC(ipac, ISACX_ISTA); - while (ista && cnt--) { + while (ista && --cnt) { pr_debug("%s: ISTA %02x\n", ipac->name, ista); if (ista & IPACX__ICA) ipac_irq(&ipac->hscx[0], ista); @@ -1182,7 +1182,7 @@ mISDNipac_irq(struct ipac_hw *ipac, int maxloop) } } else if (ipac->type & IPAC_TYPE_IPAC) { ista = ReadIPAC(ipac, IPAC_ISTA); - while (ista && cnt--) { + while (ista && --cnt) { pr_debug("%s: ISTA %02x\n", ipac->name, ista); if (ista & (IPAC__ICD | IPAC__EXD)) { istad = ReadISAC(isac, ISAC_ISTA); @@ -1200,7 +1200,7 @@ mISDNipac_irq(struct ipac_hw *ipac, int maxloop) ista = ReadIPAC(ipac, IPAC_ISTA); } } else if (ipac->type & IPAC_TYPE_HSCX) { - while (cnt) { + while (--cnt) { ista = ReadIPAC(ipac, IPAC_ISTAB + ipac->hscx[1].off); pr_debug("%s: B2 ISTA %02x\n", ipac->name, ista); if (ista) @@ -1211,7 +1211,6 @@ mISDNipac_irq(struct ipac_hw *ipac, int maxloop) mISDNisac_irq(isac, istad); if (0 == (ista | istad)) break; - cnt--; } } if (cnt > maxloop) /* only for ISAC/HSCX without PCI IRQ test */ diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 970781a9e677..f6a7161e3b85 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1849,7 +1849,7 @@ static int xgbe_exit(struct xgbe_prv_data *pdata) usleep_range(10, 15); /* Poll Until Poll Condition */ - while (count-- && XGMAC_IOREAD_BITS(pdata, DMA_MR, SWR)) + while (--count && XGMAC_IOREAD_BITS(pdata, DMA_MR, SWR)) usleep_range(500, 600); if (!count) @@ -1873,7 +1873,7 @@ static int xgbe_flush_tx_queues(struct xgbe_prv_data *pdata) /* Poll Until Poll Condition */ for (i = 0; i < pdata->tx_q_count; i++) { count = 2000; - while (count-- && XGMAC_MTL_IOREAD_BITS(pdata, i, + while (--count && XGMAC_MTL_IOREAD_BITS(pdata, i, MTL_Q_TQOMR, FTQ)) usleep_range(500, 600); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 9147a0107c44..d0ae1a6cc212 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -289,6 +289,7 @@ static int xgene_enet_setup_tx_desc(struct xgene_enet_desc_ring *tx_ring, struct sk_buff *skb) { struct device *dev = ndev_to_dev(tx_ring->ndev); + struct xgene_enet_pdata *pdata = netdev_priv(tx_ring->ndev); struct xgene_enet_raw_desc *raw_desc; __le64 *exp_desc = NULL, *exp_bufs = NULL; dma_addr_t dma_addr, pbuf_addr, *frag_dma_addr; @@ -419,6 +420,7 @@ out: raw_desc->m0 = cpu_to_le64(SET_VAL(LL, ll) | SET_VAL(NV, nv) | SET_VAL(USERINFO, tx_ring->tail)); tx_ring->cp_ring->cp_skb[tx_ring->tail] = skb; + pdata->tx_level += count; tx_ring->tail = tail; return count; @@ -429,14 +431,13 @@ static netdev_tx_t xgene_enet_start_xmit(struct sk_buff *skb, { struct xgene_enet_pdata *pdata = netdev_priv(ndev); struct xgene_enet_desc_ring *tx_ring = pdata->tx_ring; - struct xgene_enet_desc_ring *cp_ring = tx_ring->cp_ring; - u32 tx_level, cq_level; + u32 tx_level = pdata->tx_level; int count; - tx_level = pdata->ring_ops->len(tx_ring); - cq_level = pdata->ring_ops->len(cp_ring); - if (unlikely(tx_level > pdata->tx_qcnt_hi || - cq_level > pdata->cp_qcnt_hi)) { + if (tx_level < pdata->txc_level) + tx_level += ((typeof(pdata->tx_level))~0U); + + if ((tx_level - pdata->txc_level) > pdata->tx_qcnt_hi) { netif_stop_queue(ndev); return NETDEV_TX_BUSY; } @@ -539,10 +540,13 @@ static int xgene_enet_process_ring(struct xgene_enet_desc_ring *ring, struct xgene_enet_raw_desc *raw_desc, *exp_desc; u16 head = ring->head; u16 slots = ring->slots - 1; - int ret, count = 0, processed = 0; + int ret, desc_count, count = 0, processed = 0; + bool is_completion; do { raw_desc = &ring->raw_desc[head]; + desc_count = 0; + is_completion = false; exp_desc = NULL; if (unlikely(xgene_enet_is_desc_slot_empty(raw_desc))) break; @@ -559,18 +563,24 @@ static int xgene_enet_process_ring(struct xgene_enet_desc_ring *ring, } dma_rmb(); count++; + desc_count++; } - if (is_rx_desc(raw_desc)) + if (is_rx_desc(raw_desc)) { ret = xgene_enet_rx_frame(ring, raw_desc); - else + } else { ret = xgene_enet_tx_completion(ring, raw_desc); + is_completion = true; + } xgene_enet_mark_desc_slot_empty(raw_desc); if (exp_desc) xgene_enet_mark_desc_slot_empty(exp_desc); head = (head + 1) & slots; count++; + desc_count++; processed++; + if (is_completion) + pdata->txc_level += desc_count; if (ret) break; @@ -580,10 +590,8 @@ static int xgene_enet_process_ring(struct xgene_enet_desc_ring *ring, pdata->ring_ops->wr_cmd(ring, -count); ring->head = head; - if (netif_queue_stopped(ring->ndev)) { - if (pdata->ring_ops->len(ring) < pdata->cp_qcnt_low) - netif_wake_queue(ring->ndev); - } + if (netif_queue_stopped(ring->ndev)) + netif_start_queue(ring->ndev); } return processed; @@ -1033,9 +1041,7 @@ static int xgene_enet_create_desc_rings(struct net_device *ndev) pdata->tx_ring->cp_ring = cp_ring; pdata->tx_ring->dst_ring_num = xgene_enet_dst_ring_num(cp_ring); - pdata->tx_qcnt_hi = pdata->tx_ring->slots / 2; - pdata->cp_qcnt_hi = pdata->rx_ring->slots / 2; - pdata->cp_qcnt_low = pdata->cp_qcnt_hi / 2; + pdata->tx_qcnt_hi = pdata->tx_ring->slots - 128; return 0; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h index a6e56b88c0a0..1aa72c787f8d 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h @@ -155,11 +155,11 @@ struct xgene_enet_pdata { enum xgene_enet_id enet_id; struct xgene_enet_desc_ring *tx_ring; struct xgene_enet_desc_ring *rx_ring; + u16 tx_level; + u16 txc_level; char *dev_name; u32 rx_buff_cnt; u32 tx_qcnt_hi; - u32 cp_qcnt_hi; - u32 cp_qcnt_low; u32 rx_irq; u32 txc_irq; u8 cq_cnt; diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 2795d6db10e1..8b5988e210d5 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -1016,13 +1016,12 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter) sizeof(struct atl1c_recv_ret_status) * rx_desc_count + 8 * 4; - ring_header->desc = pci_alloc_consistent(pdev, ring_header->size, - &ring_header->dma); + ring_header->desc = dma_zalloc_coherent(&pdev->dev, ring_header->size, + &ring_header->dma, GFP_KERNEL); if (unlikely(!ring_header->desc)) { - dev_err(&pdev->dev, "pci_alloc_consistend failed\n"); + dev_err(&pdev->dev, "could not get memory for DMA buffer\n"); goto err_nomem; } - memset(ring_header->desc, 0, ring_header->size); /* init TPD ring */ tpd_ring[0].dma = roundup(ring_header->dma, 8); diff --git a/drivers/net/ethernet/aurora/Kconfig b/drivers/net/ethernet/aurora/Kconfig index a3c7106fdf85..8ba7f8ff3434 100644 --- a/drivers/net/ethernet/aurora/Kconfig +++ b/drivers/net/ethernet/aurora/Kconfig @@ -13,6 +13,7 @@ if NET_VENDOR_AURORA config AURORA_NB8800 tristate "Aurora AU-NB8800 support" + depends on HAS_DMA select PHYLIB help Support for the AU-NB8800 gigabit Ethernet controller. diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index bdf094fb6ef9..07f5f239cb65 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2693,17 +2693,16 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp) req.ver_upd = DRV_VER_UPD; if (BNXT_PF(bp)) { - unsigned long vf_req_snif_bmap[4]; + DECLARE_BITMAP(vf_req_snif_bmap, 256); u32 *data = (u32 *)vf_req_snif_bmap; - memset(vf_req_snif_bmap, 0, 32); + memset(vf_req_snif_bmap, 0, sizeof(vf_req_snif_bmap)); for (i = 0; i < ARRAY_SIZE(bnxt_vf_req_snif); i++) __set_bit(bnxt_vf_req_snif[i], vf_req_snif_bmap); - for (i = 0; i < 8; i++) { - req.vf_req_fwd[i] = cpu_to_le32(*data); - data++; - } + for (i = 0; i < 8; i++) + req.vf_req_fwd[i] = cpu_to_le32(data[i]); + req.enables |= cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_VF_REQ_FWD); } @@ -4603,7 +4602,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) bp->nge_port_cnt = 1; } - bp->state = BNXT_STATE_OPEN; + set_bit(BNXT_STATE_OPEN, &bp->state); bnxt_enable_int(bp); /* Enable TX queues */ bnxt_tx_enable(bp); @@ -4679,8 +4678,10 @@ int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) /* Change device state to avoid TX queue wake up's */ bnxt_tx_disable(bp); - bp->state = BNXT_STATE_CLOSED; - cancel_work_sync(&bp->sp_task); + clear_bit(BNXT_STATE_OPEN, &bp->state); + smp_mb__after_atomic(); + while (test_bit(BNXT_STATE_IN_SP_TASK, &bp->state)) + msleep(20); /* Flush rings before disabling interrupts */ bnxt_shutdown_nic(bp, irq_re_init); @@ -5030,8 +5031,10 @@ static void bnxt_dbg_dump_states(struct bnxt *bp) static void bnxt_reset_task(struct bnxt *bp) { bnxt_dbg_dump_states(bp); - if (netif_running(bp->dev)) - bnxt_tx_disable(bp); /* prevent tx timout again */ + if (netif_running(bp->dev)) { + bnxt_close_nic(bp, false, false); + bnxt_open_nic(bp, false, false); + } } static void bnxt_tx_timeout(struct net_device *dev) @@ -5081,8 +5084,12 @@ static void bnxt_sp_task(struct work_struct *work) struct bnxt *bp = container_of(work, struct bnxt, sp_task); int rc; - if (bp->state != BNXT_STATE_OPEN) + set_bit(BNXT_STATE_IN_SP_TASK, &bp->state); + smp_mb__after_atomic(); + if (!test_bit(BNXT_STATE_OPEN, &bp->state)) { + clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); return; + } if (test_and_clear_bit(BNXT_RX_MASK_SP_EVENT, &bp->sp_event)) bnxt_cfg_rx_mode(bp); @@ -5106,8 +5113,19 @@ static void bnxt_sp_task(struct work_struct *work) bnxt_hwrm_tunnel_dst_port_free( bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN); } - if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event)) + if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event)) { + /* bnxt_reset_task() calls bnxt_close_nic() which waits + * for BNXT_STATE_IN_SP_TASK to clear. + */ + clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); + rtnl_lock(); bnxt_reset_task(bp); + set_bit(BNXT_STATE_IN_SP_TASK, &bp->state); + rtnl_unlock(); + } + + smp_mb__before_atomic(); + clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); } static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev) @@ -5186,7 +5204,7 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev) bp->timer.function = bnxt_timer; bp->current_interval = BNXT_TIMER_INTERVAL; - bp->state = BNXT_STATE_CLOSED; + clear_bit(BNXT_STATE_OPEN, &bp->state); return 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 674bc5159b91..f199f4cc8ffe 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -925,9 +925,9 @@ struct bnxt { struct timer_list timer; - int state; -#define BNXT_STATE_CLOSED 0 -#define BNXT_STATE_OPEN 1 + unsigned long state; +#define BNXT_STATE_OPEN 0 +#define BNXT_STATE_IN_SP_TASK 1 struct bnxt_irq *irq_tbl; u8 mac_addr[ETH_ALEN]; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 7a9af2887d8e..ea044bbcd384 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -21,7 +21,7 @@ #ifdef CONFIG_BNXT_SRIOV static int bnxt_vf_ndo_prep(struct bnxt *bp, int vf_id) { - if (bp->state != BNXT_STATE_OPEN) { + if (!test_bit(BNXT_STATE_OPEN, &bp->state)) { netdev_err(bp->dev, "vf ndo called though PF is down\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 4b7fd63ae57c..5f24d11cb16a 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -37,7 +37,6 @@ 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[MAX_LMAC]; - u8 lmac_cnt; struct delayed_work dwork; struct workqueue_struct *check_link; u8 link[MAX_LMAC]; @@ -280,7 +279,6 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic) u64 lmac_credit; nic->num_vf_en = 0; - nic->lmac_cnt = 0; for (bgx = 0; bgx < NIC_MAX_BGX; bgx++) { if (!(bgx_map & (1 << bgx))) @@ -290,7 +288,6 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic) nic->vf_lmac_map[next_bgx_lmac++] = NIC_SET_VF_LMAC_MAP(bgx, lmac); nic->num_vf_en += lmac_cnt; - nic->lmac_cnt += lmac_cnt; /* Program LMAC credits */ lmac_credit = (1ull << 1); /* channel credit enable */ @@ -618,6 +615,21 @@ static int nic_config_loopback(struct nicpf *nic, struct set_loopback *lbk) return 0; } +static void nic_enable_vf(struct nicpf *nic, int vf, bool enable) +{ + int bgx, lmac; + + nic->vf_enabled[vf] = enable; + + if (vf >= nic->num_vf_en) + return; + + 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_lmac_rx_tx_enable(nic->node, bgx, lmac, enable); +} + /* Interrupt handler to handle mailbox messages from VFs */ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) { @@ -717,29 +729,14 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) break; case NIC_MBOX_MSG_CFG_DONE: /* Last message of VF config msg sequence */ - nic->vf_enabled[vf] = true; - if (vf >= nic->lmac_cnt) - goto unlock; - - 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_lmac_rx_tx_enable(nic->node, bgx, lmac, true); + nic_enable_vf(nic, vf, true); goto unlock; case NIC_MBOX_MSG_SHUTDOWN: /* First msg in VF teardown sequence */ - nic->vf_enabled[vf] = false; if (vf >= nic->num_vf_en) nic->sqs_used[vf - nic->num_vf_en] = false; nic->pqs_vf[vf] = 0; - - if (vf >= nic->lmac_cnt) - break; - - 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_lmac_rx_tx_enable(nic->node, bgx, lmac, false); + nic_enable_vf(nic, vf, false); break; case NIC_MBOX_MSG_ALLOC_SQS: nic_alloc_sqs(nic, &mbx.sqs_alloc); @@ -958,7 +955,7 @@ static void nic_poll_for_link(struct work_struct *work) mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE; - for (vf = 0; vf < nic->lmac_cnt; vf++) { + for (vf = 0; vf < nic->num_vf_en; vf++) { /* Poll only if VF is UP */ if (!nic->vf_enabled[vf]) continue; diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c index 63c2bcf8031a..b1026689b78f 100644 --- a/drivers/net/ethernet/ezchip/nps_enet.c +++ b/drivers/net/ethernet/ezchip/nps_enet.c @@ -48,21 +48,15 @@ static void nps_enet_read_rx_fifo(struct net_device *ndev, *reg = nps_enet_reg_get(priv, NPS_ENET_REG_RX_BUF); else { /* !dst_is_aligned */ for (i = 0; i < len; i++, reg++) { - u32 buf = - nps_enet_reg_get(priv, NPS_ENET_REG_RX_BUF); - - /* to accommodate word-unaligned address of "reg" - * we have to do memcpy_toio() instead of simple "=". - */ - memcpy_toio((void __iomem *)reg, &buf, sizeof(buf)); + u32 buf = nps_enet_reg_get(priv, NPS_ENET_REG_RX_BUF); + put_unaligned(buf, reg); } } /* copy last bytes (if any) */ if (last) { u32 buf = nps_enet_reg_get(priv, NPS_ENET_REG_RX_BUF); - - memcpy_toio((void __iomem *)reg, &buf, last); + memcpy((u8*)reg, &buf, last); } } @@ -367,7 +361,7 @@ static void nps_enet_send_frame(struct net_device *ndev, struct nps_enet_tx_ctl tx_ctrl; short length = skb->len; u32 i, len = DIV_ROUND_UP(length, sizeof(u32)); - u32 *src = (u32 *)virt_to_phys(skb->data); + u32 *src = (void *)skb->data; bool src_is_aligned = IS_ALIGNED((unsigned long)src, sizeof(u32)); tx_ctrl.value = 0; @@ -375,17 +369,11 @@ static void nps_enet_send_frame(struct net_device *ndev, if (src_is_aligned) for (i = 0; i < len; i++, src++) nps_enet_reg_set(priv, NPS_ENET_REG_TX_BUF, *src); - else { /* !src_is_aligned */ - for (i = 0; i < len; i++, src++) { - u32 buf; + else /* !src_is_aligned */ + for (i = 0; i < len; i++, src++) + nps_enet_reg_set(priv, NPS_ENET_REG_TX_BUF, + get_unaligned(src)); - /* to accommodate word-unaligned address of "src" - * we have to do memcpy_fromio() instead of simple "=" - */ - memcpy_fromio(&buf, (void __iomem *)src, sizeof(buf)); - nps_enet_reg_set(priv, NPS_ENET_REG_TX_BUF, buf); - } - } /* Write the length of the Frame */ tx_ctrl.nt = length; diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c index 08f5b911d96b..52e0091b4fb2 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c @@ -552,7 +552,7 @@ static void tx_restart(struct net_device *dev) cbd_t __iomem *prev_bd; cbd_t __iomem *last_tx_bd; - last_tx_bd = fep->tx_bd_base + (fpi->tx_ring * sizeof(cbd_t)); + last_tx_bd = fep->tx_bd_base + ((fpi->tx_ring - 1) * sizeof(cbd_t)); /* get the current bd held in TBPTR and scan back from this point */ recheck_bd = curr_tbptr = (cbd_t __iomem *) diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index 55c36230e176..40071dad1c57 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -464,7 +464,7 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev) * address). Print error message but continue anyway. */ if ((void *)tbipa > priv->map + resource_size(&res) - 4) - dev_err(&pdev->dev, "invalid register map (should be at least 0x%04x to contain TBI address)\n", + dev_err(&pdev->dev, "invalid register map (should be at least 0x%04zx to contain TBI address)\n", ((void *)tbipa - priv->map) + 4); iowrite32be(be32_to_cpup(prop), tbipa); diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 7cf898455e60..3e233d924cce 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -894,7 +894,8 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) FSL_GIANFAR_DEV_HAS_VLAN | FSL_GIANFAR_DEV_HAS_MAGIC_PACKET | FSL_GIANFAR_DEV_HAS_EXTENDED_HASH | - FSL_GIANFAR_DEV_HAS_TIMER; + FSL_GIANFAR_DEV_HAS_TIMER | + FSL_GIANFAR_DEV_HAS_RX_FILER; err = of_property_read_string(np, "phy-connection-type", &ctype); @@ -1396,8 +1397,9 @@ static int gfar_probe(struct platform_device *ofdev) priv->rx_queue[i]->rxic = DEFAULT_RXIC; } - /* always enable rx filer */ - priv->rx_filer_enable = 1; + /* Always enable rx filer if available */ + priv->rx_filer_enable = + (priv->device_flags & FSL_GIANFAR_DEV_HAS_RX_FILER) ? 1 : 0; /* Enable most messages by default */ priv->msg_enable = (NETIF_MSG_IFUP << 1 ) - 1; /* use pritority h/w tx queue scheduling for single queue devices */ diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h index f266b20f9ef5..cb77667971a7 100644 --- a/drivers/net/ethernet/freescale/gianfar.h +++ b/drivers/net/ethernet/freescale/gianfar.h @@ -923,6 +923,7 @@ struct gfar { #define FSL_GIANFAR_DEV_HAS_BUF_STASHING 0x00000400 #define FSL_GIANFAR_DEV_HAS_TIMER 0x00000800 #define FSL_GIANFAR_DEV_HAS_WAKE_ON_FILER 0x00001000 +#define FSL_GIANFAR_DEV_HAS_RX_FILER 0x00002000 #if (MAXGROUPS == 2) #define DEFAULT_MAPPING 0xAA diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 2a98eba660c0..b674414a4d72 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -1259,12 +1259,8 @@ int hns_dsaf_set_mac_uc_entry( if (MAC_IS_ALL_ZEROS(mac_entry->addr) || MAC_IS_BROADCAST(mac_entry->addr) || MAC_IS_MULTICAST(mac_entry->addr)) { - dev_err(dsaf_dev->dev, - "set_uc %s Mac %02x:%02x:%02x:%02x:%02x:%02x err!\n", - dsaf_dev->ae_dev.name, mac_entry->addr[0], - mac_entry->addr[1], mac_entry->addr[2], - mac_entry->addr[3], mac_entry->addr[4], - mac_entry->addr[5]); + dev_err(dsaf_dev->dev, "set_uc %s Mac %pM err!\n", + dsaf_dev->ae_dev.name, mac_entry->addr); return -EINVAL; } @@ -1331,12 +1327,8 @@ int hns_dsaf_set_mac_mc_entry( /* mac addr check */ if (MAC_IS_ALL_ZEROS(mac_entry->addr)) { - dev_err(dsaf_dev->dev, - "set uc %s Mac %02x:%02x:%02x:%02x:%02x:%02x err!\n", - dsaf_dev->ae_dev.name, mac_entry->addr[0], - mac_entry->addr[1], mac_entry->addr[2], - mac_entry->addr[3], - mac_entry->addr[4], mac_entry->addr[5]); + dev_err(dsaf_dev->dev, "set uc %s Mac %pM err!\n", + dsaf_dev->ae_dev.name, mac_entry->addr); return -EINVAL; } @@ -1410,11 +1402,8 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev, /*chechk mac addr */ if (MAC_IS_ALL_ZEROS(mac_entry->addr)) { - dev_err(dsaf_dev->dev, - "set_entry failed,addr %02x:%02x:%02x:%02x:%02x:%02x!\n", - mac_entry->addr[0], mac_entry->addr[1], - mac_entry->addr[2], mac_entry->addr[3], - mac_entry->addr[4], mac_entry->addr[5]); + dev_err(dsaf_dev->dev, "set_entry failed,addr %pM!\n", + mac_entry->addr); return -EINVAL; } @@ -1497,9 +1486,8 @@ int hns_dsaf_del_mac_entry(struct dsaf_device *dsaf_dev, u16 vlan_id, /*check mac addr */ if (MAC_IS_ALL_ZEROS(addr) || MAC_IS_BROADCAST(addr)) { - dev_err(dsaf_dev->dev, - "del_entry failed,addr %02x:%02x:%02x:%02x:%02x:%02x!\n", - addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]); + dev_err(dsaf_dev->dev, "del_entry failed,addr %pM!\n", + addr); return -EINVAL; } @@ -1563,11 +1551,8 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev, /*check mac addr */ if (MAC_IS_ALL_ZEROS(mac_entry->addr)) { - dev_err(dsaf_dev->dev, - "del_port failed, addr %02x:%02x:%02x:%02x:%02x:%02x!\n", - mac_entry->addr[0], mac_entry->addr[1], - mac_entry->addr[2], mac_entry->addr[3], - mac_entry->addr[4], mac_entry->addr[5]); + dev_err(dsaf_dev->dev, "del_port failed, addr %pM!\n", + mac_entry->addr); return -EINVAL; } @@ -1644,11 +1629,8 @@ int hns_dsaf_get_mac_uc_entry(struct dsaf_device *dsaf_dev, /* check macaddr */ if (MAC_IS_ALL_ZEROS(mac_entry->addr) || MAC_IS_BROADCAST(mac_entry->addr)) { - dev_err(dsaf_dev->dev, - "get_entry failed,addr %02x:%02x:%02x:%02x:%02x:%02x\n", - mac_entry->addr[0], mac_entry->addr[1], - mac_entry->addr[2], mac_entry->addr[3], - mac_entry->addr[4], mac_entry->addr[5]); + dev_err(dsaf_dev->dev, "get_entry failed,addr %pM\n", + mac_entry->addr); return -EINVAL; } @@ -1695,11 +1677,8 @@ int hns_dsaf_get_mac_mc_entry(struct dsaf_device *dsaf_dev, /*check mac addr */ if (MAC_IS_ALL_ZEROS(mac_entry->addr) || MAC_IS_BROADCAST(mac_entry->addr)) { - dev_err(dsaf_dev->dev, - "get_entry failed,addr %02x:%02x:%02x:%02x:%02x:%02x\n", - mac_entry->addr[0], mac_entry->addr[1], - mac_entry->addr[2], mac_entry->addr[3], - mac_entry->addr[4], mac_entry->addr[5]); + dev_err(dsaf_dev->dev, "get_entry failed,addr %pM\n", + mac_entry->addr); return -EINVAL; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index b475e1bf2e6f..bdbd80423b17 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -898,7 +898,7 @@ #define XGMAC_PAUSE_CTL_RSP_MODE_B 2 #define XGMAC_PAUSE_CTL_TX_XOFF_B 3 -static inline void dsaf_write_reg(void *base, u32 reg, u32 value) +static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value) { u8 __iomem *reg_addr = ACCESS_ONCE(base); @@ -908,7 +908,7 @@ static inline void dsaf_write_reg(void *base, u32 reg, u32 value) #define dsaf_write_dev(a, reg, value) \ dsaf_write_reg((a)->io_base, (reg), (value)) -static inline u32 dsaf_read_reg(u8 *base, u32 reg) +static inline u32 dsaf_read_reg(u8 __iomem *base, u32 reg) { u8 __iomem *reg_addr = ACCESS_ONCE(base); @@ -927,8 +927,8 @@ static inline u32 dsaf_read_reg(u8 *base, u32 reg) #define dsaf_set_bit(origin, shift, val) \ dsaf_set_field((origin), (1ull << (shift)), (shift), (val)) -static inline void dsaf_set_reg_field(void *base, u32 reg, u32 mask, u32 shift, - u32 val) +static inline void dsaf_set_reg_field(void __iomem *base, u32 reg, u32 mask, + u32 shift, u32 val) { u32 origin = dsaf_read_reg(base, reg); @@ -947,7 +947,8 @@ static inline void dsaf_set_reg_field(void *base, u32 reg, u32 mask, u32 shift, #define dsaf_get_bit(origin, shift) \ dsaf_get_field((origin), (1ull << (shift)), (shift)) -static inline u32 dsaf_get_reg_field(void *base, u32 reg, u32 mask, u32 shift) +static inline u32 dsaf_get_reg_field(void __iomem *base, u32 reg, u32 mask, + u32 shift) { u32 origin; diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 0ff8f01e57ee..1fd5ea82a9bc 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -567,10 +567,6 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw) goto init_adminq_exit; } - /* initialize locks */ - mutex_init(&hw->aq.asq_mutex); - mutex_init(&hw->aq.arq_mutex); - /* Set up register offsets */ i40e_adminq_init_regs(hw); @@ -664,8 +660,6 @@ i40e_status i40e_shutdown_adminq(struct i40e_hw *hw) i40e_shutdown_asq(hw); i40e_shutdown_arq(hw); - /* destroy the locks */ - if (hw->nvm_buff.va) i40e_free_virt_mem(hw, &hw->nvm_buff); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b825f978d441..4a9873ec28c7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -10295,6 +10295,12 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* set up a default setting for link flow control */ pf->hw.fc.requested_mode = I40E_FC_NONE; + /* set up the locks for the AQ, do this only once in probe + * and destroy them only once in remove + */ + mutex_init(&hw->aq.asq_mutex); + mutex_init(&hw->aq.arq_mutex); + err = i40e_init_adminq(hw); /* provide nvm, fw, api versions */ @@ -10697,7 +10703,6 @@ static void i40e_remove(struct pci_dev *pdev) set_bit(__I40E_DOWN, &pf->state); del_timer_sync(&pf->service_timer); cancel_work_sync(&pf->service_task); - i40e_fdir_teardown(pf); if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { i40e_free_vfs(pf); @@ -10740,6 +10745,10 @@ static void i40e_remove(struct pci_dev *pdev) "Failed to destroy the Admin Queue resources: %d\n", ret_code); + /* destroy the locks only once, here */ + mutex_destroy(&hw->aq.arq_mutex); + mutex_destroy(&hw->aq.asq_mutex); + /* Clear all dynamic memory lists of rings, q_vectors, and VSIs */ i40e_clear_interrupt_scheme(pf); for (i = 0; i < pf->num_alloc_vsi; i++) { diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c index fd123ca60761..3f65e39b3fe4 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c @@ -551,10 +551,6 @@ i40e_status i40evf_init_adminq(struct i40e_hw *hw) goto init_adminq_exit; } - /* initialize locks */ - mutex_init(&hw->aq.asq_mutex); - mutex_init(&hw->aq.arq_mutex); - /* Set up register offsets */ i40e_adminq_init_regs(hw); @@ -596,8 +592,6 @@ i40e_status i40evf_shutdown_adminq(struct i40e_hw *hw) i40e_shutdown_asq(hw); i40e_shutdown_arq(hw); - /* destroy the locks */ - if (hw->nvm_buff.va) i40e_free_virt_mem(hw, &hw->nvm_buff); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index d962164dfb0f..99d2cffae0cd 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -2476,6 +2476,12 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->bus.device = PCI_SLOT(pdev->devfn); hw->bus.func = PCI_FUNC(pdev->devfn); + /* set up the locks for the AQ, do this only once in probe + * and destroy them only once in remove + */ + mutex_init(&hw->aq.asq_mutex); + mutex_init(&hw->aq.arq_mutex); + INIT_LIST_HEAD(&adapter->mac_filter_list); INIT_LIST_HEAD(&adapter->vlan_filter_list); @@ -2629,6 +2635,10 @@ static void i40evf_remove(struct pci_dev *pdev) if (hw->aq.asq.count) i40evf_shutdown_adminq(hw); + /* destroy the locks only once, here */ + mutex_destroy(&hw->aq.arq_mutex); + mutex_destroy(&hw->aq.asq_mutex); + iounmap(hw->hw_addr); pci_release_regions(pdev); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 47395ff5d908..aed8d029b23d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7920,6 +7920,9 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) */ if (netif_running(dev)) ixgbe_close(dev); + else + ixgbe_reset(adapter); + ixgbe_clear_interrupt_scheme(adapter); #ifdef CONFIG_IXGBE_DCB diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index d9884fd15b45..a4beccf1fd46 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -3413,16 +3413,23 @@ static void mvpp2_bm_pool_bufsize_set(struct mvpp2 *priv, } /* Free all buffers from the pool */ -static void mvpp2_bm_bufs_free(struct mvpp2 *priv, struct mvpp2_bm_pool *bm_pool) +static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv, + struct mvpp2_bm_pool *bm_pool) { int i; for (i = 0; i < bm_pool->buf_num; i++) { + dma_addr_t buf_phys_addr; u32 vaddr; /* Get buffer virtual address (indirect access) */ - mvpp2_read(priv, MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); + buf_phys_addr = mvpp2_read(priv, + MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); vaddr = mvpp2_read(priv, MVPP2_BM_VIRT_ALLOC_REG); + + dma_unmap_single(dev, buf_phys_addr, + bm_pool->buf_size, DMA_FROM_DEVICE); + if (!vaddr) break; dev_kfree_skb_any((struct sk_buff *)vaddr); @@ -3439,7 +3446,7 @@ static int mvpp2_bm_pool_destroy(struct platform_device *pdev, { u32 val; - mvpp2_bm_bufs_free(priv, bm_pool); + mvpp2_bm_bufs_free(&pdev->dev, priv, bm_pool); if (bm_pool->buf_num) { WARN(1, "cannot free all buffers in pool %d\n", bm_pool->id); return 0; @@ -3692,7 +3699,8 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type, MVPP2_BM_LONG_BUF_NUM : MVPP2_BM_SHORT_BUF_NUM; else - mvpp2_bm_bufs_free(port->priv, new_pool); + mvpp2_bm_bufs_free(port->dev->dev.parent, + port->priv, new_pool); new_pool->pkt_size = pkt_size; @@ -3756,7 +3764,7 @@ static int mvpp2_bm_update_mtu(struct net_device *dev, int mtu) int pkt_size = MVPP2_RX_PKT_SIZE(mtu); /* Update BM pool with new buffer size */ - mvpp2_bm_bufs_free(port->priv, port_pool); + mvpp2_bm_bufs_free(dev->dev.parent, port->priv, port_pool); if (port_pool->buf_num) { WARN(1, "cannot free all buffers in pool %d\n", port_pool->id); return -EIO; @@ -4401,11 +4409,10 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port, mvpp2_txq_inc_get(txq_pcpu); - if (!skb) - continue; - dma_unmap_single(port->dev->dev.parent, buf_phys_addr, skb_headlen(skb), DMA_TO_DEVICE); + if (!skb) + continue; dev_kfree_skb_any(skb); } } @@ -5092,7 +5099,8 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, struct mvpp2_rx_queue *rxq) { struct net_device *dev = port->dev; - int rx_received, rx_filled, i; + int rx_received; + int rx_done = 0; u32 rcvd_pkts = 0; u32 rcvd_bytes = 0; @@ -5101,17 +5109,18 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, if (rx_todo > rx_received) rx_todo = rx_received; - rx_filled = 0; - for (i = 0; i < rx_todo; i++) { + while (rx_done < rx_todo) { struct mvpp2_rx_desc *rx_desc = mvpp2_rxq_next_desc_get(rxq); struct mvpp2_bm_pool *bm_pool; struct sk_buff *skb; + dma_addr_t phys_addr; u32 bm, rx_status; int pool, rx_bytes, err; - rx_filled++; + rx_done++; rx_status = rx_desc->status; rx_bytes = rx_desc->data_size - MVPP2_MH_SIZE; + phys_addr = rx_desc->buf_phys_addr; bm = mvpp2_bm_cookie_build(rx_desc); pool = mvpp2_bm_cookie_pool_get(bm); @@ -5128,8 +5137,10 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, * comprised by the RX descriptor. */ if (rx_status & MVPP2_RXD_ERR_SUMMARY) { + err_drop_frame: dev->stats.rx_errors++; mvpp2_rx_error(port, rx_desc); + /* Return the buffer to the pool */ mvpp2_pool_refill(port, bm, rx_desc->buf_phys_addr, rx_desc->buf_cookie); continue; @@ -5137,6 +5148,15 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, skb = (struct sk_buff *)rx_desc->buf_cookie; + err = mvpp2_rx_refill(port, bm_pool, bm, 0); + if (err) { + netdev_err(port->dev, "failed to refill BM pools\n"); + goto err_drop_frame; + } + + dma_unmap_single(dev->dev.parent, phys_addr, + bm_pool->buf_size, DMA_FROM_DEVICE); + rcvd_pkts++; rcvd_bytes += rx_bytes; atomic_inc(&bm_pool->in_use); @@ -5147,12 +5167,6 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, mvpp2_rx_csum(port, rx_status, skb); napi_gro_receive(&port->napi, skb); - - err = mvpp2_rx_refill(port, bm_pool, bm, 0); - if (err) { - netdev_err(port->dev, "failed to refill BM pools\n"); - rx_filled--; - } } if (rcvd_pkts) { @@ -5166,7 +5180,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, /* Update Rx queue management counters */ wmb(); - mvpp2_rxq_status_update(port, rxq->id, rx_todo, rx_filled); + mvpp2_rxq_status_update(port, rxq->id, rx_done, rx_done); return rx_todo; } diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 6fec3e993d02..cad6c44df91c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -4306,9 +4306,10 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, return -EOPNOTSUPP; ctrl = (struct mlx4_net_trans_rule_hw_ctrl *)inbox->buf; - ctrl->port = mlx4_slave_convert_port(dev, slave, ctrl->port); - if (ctrl->port <= 0) + err = mlx4_slave_convert_port(dev, slave, ctrl->port); + if (err <= 0) return -EINVAL; + ctrl->port = err; qpn = be32_to_cpu(ctrl->qpn) & 0xffffff; err = get_res(dev, slave, qpn, RES_QP, &rqp); if (err) { diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index ac17d8669b1a..1292c360390c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -299,6 +299,7 @@ struct qed_hwfn { /* Flag indicating whether interrupts are enabled or not*/ bool b_int_enabled; + bool b_int_requested; struct qed_mcp_info *mcp_info; @@ -491,6 +492,8 @@ u32 qed_unzip_data(struct qed_hwfn *p_hwfn, u32 input_len, u8 *input_buf, u32 max_size, u8 *unzip_buf); +int qed_slowpath_irq_req(struct qed_hwfn *hwfn); + #define QED_ETH_INTERFACE_VERSION 300 #endif /* _QED_H */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 803b190ccada..817bbd5476ff 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -1385,52 +1385,63 @@ err0: return rc; } -static u32 qed_hw_bar_size(struct qed_dev *cdev, - u8 bar_id) +static u32 qed_hw_bar_size(struct qed_hwfn *p_hwfn, + u8 bar_id) { - u32 size = pci_resource_len(cdev->pdev, (bar_id > 0) ? 2 : 0); + u32 bar_reg = (bar_id == 0 ? PGLUE_B_REG_PF_BAR0_SIZE + : PGLUE_B_REG_PF_BAR1_SIZE); + u32 val = qed_rd(p_hwfn, p_hwfn->p_main_ptt, bar_reg); - return size / cdev->num_hwfns; + /* Get the BAR size(in KB) from hardware given val */ + return 1 << (val + 15); } int qed_hw_prepare(struct qed_dev *cdev, int personality) { - int rc, i; + struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); + int rc; /* Store the precompiled init data ptrs */ qed_init_iro_array(cdev); /* Initialize the first hwfn - will learn number of hwfns */ - rc = qed_hw_prepare_single(&cdev->hwfns[0], cdev->regview, + rc = qed_hw_prepare_single(p_hwfn, + cdev->regview, cdev->doorbells, personality); if (rc) return rc; - personality = cdev->hwfns[0].hw_info.personality; + personality = p_hwfn->hw_info.personality; /* Initialize the rest of the hwfns */ - for (i = 1; i < cdev->num_hwfns; i++) { + if (cdev->num_hwfns > 1) { void __iomem *p_regview, *p_doorbell; + u8 __iomem *addr; - p_regview = cdev->regview + - i * qed_hw_bar_size(cdev, 0); - p_doorbell = cdev->doorbells + - i * qed_hw_bar_size(cdev, 1); - rc = qed_hw_prepare_single(&cdev->hwfns[i], p_regview, + /* adjust bar offset for second engine */ + addr = cdev->regview + qed_hw_bar_size(p_hwfn, 0) / 2; + p_regview = addr; + + /* adjust doorbell bar offset for second engine */ + addr = cdev->doorbells + qed_hw_bar_size(p_hwfn, 1) / 2; + p_doorbell = addr; + + /* prepare second hw function */ + rc = qed_hw_prepare_single(&cdev->hwfns[1], p_regview, p_doorbell, personality); + + /* in case of error, need to free the previously + * initiliazed hwfn 0. + */ if (rc) { - /* Cleanup previously initialized hwfns */ - while (--i >= 0) { - qed_init_free(&cdev->hwfns[i]); - qed_mcp_free(&cdev->hwfns[i]); - qed_hw_hwfn_free(&cdev->hwfns[i]); - } - return rc; + qed_init_free(p_hwfn); + qed_mcp_free(p_hwfn); + qed_hw_hwfn_free(p_hwfn); } } - return 0; + return rc; } void qed_hw_remove(struct qed_dev *cdev) diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index de50e84902af..9cc9d62c1fec 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -783,22 +783,16 @@ void qed_int_igu_enable_int(struct qed_hwfn *p_hwfn, qed_wr(p_hwfn, p_ptt, IGU_REG_PF_CONFIGURATION, igu_pf_conf); } -void qed_int_igu_enable(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - enum qed_int_mode int_mode) +int qed_int_igu_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + enum qed_int_mode int_mode) { - int i; - - p_hwfn->b_int_enabled = 1; + int rc, i; /* Mask non-link attentions */ for (i = 0; i < 9; i++) qed_wr(p_hwfn, p_ptt, MISC_REG_AEU_ENABLE1_IGU_OUT_0 + (i << 2), 0); - /* Enable interrupt Generation */ - qed_int_igu_enable_int(p_hwfn, p_ptt, int_mode); - /* Configure AEU signal change to produce attentions for link */ qed_wr(p_hwfn, p_ptt, IGU_REG_LEADING_EDGE_LATCH, 0xfff); qed_wr(p_hwfn, p_ptt, IGU_REG_TRAILING_EDGE_LATCH, 0xfff); @@ -808,6 +802,19 @@ void qed_int_igu_enable(struct qed_hwfn *p_hwfn, /* Unmask AEU signals toward IGU */ qed_wr(p_hwfn, p_ptt, MISC_REG_AEU_MASK_ATTN_IGU, 0xff); + if ((int_mode != QED_INT_MODE_INTA) || IS_LEAD_HWFN(p_hwfn)) { + rc = qed_slowpath_irq_req(p_hwfn); + if (rc != 0) { + DP_NOTICE(p_hwfn, "Slowpath IRQ request failed\n"); + return -EINVAL; + } + p_hwfn->b_int_requested = true; + } + /* Enable interrupt Generation */ + qed_int_igu_enable_int(p_hwfn, p_ptt, int_mode); + p_hwfn->b_int_enabled = 1; + + return rc; } void qed_int_igu_disable_int(struct qed_hwfn *p_hwfn, @@ -1127,3 +1134,11 @@ int qed_int_get_num_sbs(struct qed_hwfn *p_hwfn, return info->igu_sb_cnt; } + +void qed_int_disable_post_isr_release(struct qed_dev *cdev) +{ + int i; + + for_each_hwfn(cdev, i) + cdev->hwfns[i].b_int_requested = false; +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h index 16b57518e706..51e0b09a7f47 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.h +++ b/drivers/net/ethernet/qlogic/qed/qed_int.h @@ -169,10 +169,14 @@ int qed_int_get_num_sbs(struct qed_hwfn *p_hwfn, int *p_iov_blks); /** - * @file + * @brief qed_int_disable_post_isr_release - performs the cleanup post ISR + * release. The API need to be called after releasing all slowpath IRQs + * of the device. + * + * @param cdev * - * @brief Interrupt handler */ +void qed_int_disable_post_isr_release(struct qed_dev *cdev); #define QED_CAU_DEF_RX_TIMER_RES 0 #define QED_CAU_DEF_TX_TIMER_RES 0 @@ -366,10 +370,11 @@ void qed_int_setup(struct qed_hwfn *p_hwfn, * @param p_hwfn * @param p_ptt * @param int_mode + * + * @return int */ -void qed_int_igu_enable(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - enum qed_int_mode int_mode); +int qed_int_igu_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + enum qed_int_mode int_mode); /** * @brief - Initialize CAU status block entry diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 947c7af72b25..174f7341c5c3 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -476,41 +476,22 @@ static irqreturn_t qed_single_int(int irq, void *dev_instance) return rc; } -static int qed_slowpath_irq_req(struct qed_dev *cdev) +int qed_slowpath_irq_req(struct qed_hwfn *hwfn) { - int i = 0, rc = 0; + struct qed_dev *cdev = hwfn->cdev; + int rc = 0; + u8 id; if (cdev->int_params.out.int_mode == QED_INT_MODE_MSIX) { - /* Request all the slowpath MSI-X vectors */ - for (i = 0; i < cdev->num_hwfns; i++) { - snprintf(cdev->hwfns[i].name, NAME_SIZE, - "sp-%d-%02x:%02x.%02x", - i, cdev->pdev->bus->number, - PCI_SLOT(cdev->pdev->devfn), - cdev->hwfns[i].abs_pf_id); - - rc = request_irq(cdev->int_params.msix_table[i].vector, - qed_msix_sp_int, 0, - cdev->hwfns[i].name, - cdev->hwfns[i].sp_dpc); - if (rc) - break; - - DP_VERBOSE(&cdev->hwfns[i], - (NETIF_MSG_INTR | QED_MSG_SP), + id = hwfn->my_id; + snprintf(hwfn->name, NAME_SIZE, "sp-%d-%02x:%02x.%02x", + id, cdev->pdev->bus->number, + PCI_SLOT(cdev->pdev->devfn), hwfn->abs_pf_id); + rc = request_irq(cdev->int_params.msix_table[id].vector, + qed_msix_sp_int, 0, hwfn->name, hwfn->sp_dpc); + if (!rc) + DP_VERBOSE(hwfn, (NETIF_MSG_INTR | QED_MSG_SP), "Requested slowpath MSI-X\n"); - } - - if (i != cdev->num_hwfns) { - /* Free already request MSI-X vectors */ - for (i--; i >= 0; i--) { - unsigned int vec = - cdev->int_params.msix_table[i].vector; - synchronize_irq(vec); - free_irq(cdev->int_params.msix_table[i].vector, - cdev->hwfns[i].sp_dpc); - } - } } else { unsigned long flags = 0; @@ -534,13 +515,17 @@ static void qed_slowpath_irq_free(struct qed_dev *cdev) if (cdev->int_params.out.int_mode == QED_INT_MODE_MSIX) { for_each_hwfn(cdev, i) { + if (!cdev->hwfns[i].b_int_requested) + break; synchronize_irq(cdev->int_params.msix_table[i].vector); free_irq(cdev->int_params.msix_table[i].vector, cdev->hwfns[i].sp_dpc); } } else { - free_irq(cdev->pdev->irq, cdev); + if (QED_LEADING_HWFN(cdev)->b_int_requested) + free_irq(cdev->pdev->irq, cdev); } + qed_int_disable_post_isr_release(cdev); } static int qed_nic_stop(struct qed_dev *cdev) @@ -765,16 +750,11 @@ static int qed_slowpath_start(struct qed_dev *cdev, if (rc) goto err1; - /* Request the slowpath IRQ */ - rc = qed_slowpath_irq_req(cdev); - if (rc) - goto err2; - /* Allocate stream for unzipping */ rc = qed_alloc_stream_mem(cdev); if (rc) { DP_NOTICE(cdev, "Failed to allocate stream memory\n"); - goto err3; + goto err2; } /* Start the slowpath */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h index 7a5ce5914ace..e8df12335a97 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h +++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h @@ -363,4 +363,8 @@ 0x7 << 0) #define MCP_REG_NVM_CFG4_FLASH_SIZE_SHIFT \ 0 +#define PGLUE_B_REG_PF_BAR0_SIZE \ + 0x2aae60UL +#define PGLUE_B_REG_PF_BAR1_SIZE \ + 0x2aae64UL #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index 31a1f1eb4f56..287fadfab52d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -124,8 +124,12 @@ struct qed_spq { dma_addr_t p_phys; struct qed_spq_entry *p_virt; - /* Used as index for completions (returns on EQ by FW) */ - u16 echo_idx; +#define SPQ_RING_SIZE \ + (CORE_SPQE_PAGE_SIZE_BYTES / sizeof(struct slow_path_element)) + + /* Bitmap for handling out-of-order completions */ + DECLARE_BITMAP(p_comp_bitmap, SPQ_RING_SIZE); + u8 comp_bitmap_idx; /* Statistics */ u32 unlimited_pending_count; diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index 7c0b8459666e..3dd548ab8df1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -112,8 +112,6 @@ static int qed_spq_fill_entry(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent) { - p_ent->elem.hdr.echo = 0; - p_hwfn->p_spq->echo_idx++; p_ent->flags = 0; switch (p_ent->comp_mode) { @@ -195,10 +193,12 @@ static int qed_spq_hw_post(struct qed_hwfn *p_hwfn, struct qed_spq *p_spq, struct qed_spq_entry *p_ent) { - struct qed_chain *p_chain = &p_hwfn->p_spq->chain; + struct qed_chain *p_chain = &p_hwfn->p_spq->chain; + u16 echo = qed_chain_get_prod_idx(p_chain); struct slow_path_element *elem; struct core_db_data db; + p_ent->elem.hdr.echo = cpu_to_le16(echo); elem = qed_chain_produce(p_chain); if (!elem) { DP_NOTICE(p_hwfn, "Failed to produce from SPQ chain\n"); @@ -437,7 +437,9 @@ void qed_spq_setup(struct qed_hwfn *p_hwfn) p_spq->comp_count = 0; p_spq->comp_sent_count = 0; p_spq->unlimited_pending_count = 0; - p_spq->echo_idx = 0; + + bitmap_zero(p_spq->p_comp_bitmap, SPQ_RING_SIZE); + p_spq->comp_bitmap_idx = 0; /* SPQ cid, cannot fail */ qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_CORE, &p_spq->cid); @@ -582,26 +584,32 @@ qed_spq_add_entry(struct qed_hwfn *p_hwfn, struct qed_spq *p_spq = p_hwfn->p_spq; if (p_ent->queue == &p_spq->unlimited_pending) { - struct qed_spq_entry *p_en2; if (list_empty(&p_spq->free_pool)) { list_add_tail(&p_ent->list, &p_spq->unlimited_pending); p_spq->unlimited_pending_count++; return 0; + } else { + struct qed_spq_entry *p_en2; + + p_en2 = list_first_entry(&p_spq->free_pool, + struct qed_spq_entry, + list); + list_del(&p_en2->list); + + /* Copy the ring element physical pointer to the new + * entry, since we are about to override the entire ring + * entry and don't want to lose the pointer. + */ + p_ent->elem.data_ptr = p_en2->elem.data_ptr; + + *p_en2 = *p_ent; + + kfree(p_ent); + + p_ent = p_en2; } - - p_en2 = list_first_entry(&p_spq->free_pool, - struct qed_spq_entry, - list); - list_del(&p_en2->list); - - /* Strcut assignment */ - *p_en2 = *p_ent; - - kfree(p_ent); - - p_ent = p_en2; } /* entry is to be placed in 'pending' queue */ @@ -777,13 +785,38 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, list_for_each_entry_safe(p_ent, tmp, &p_spq->completion_pending, list) { if (p_ent->elem.hdr.echo == echo) { + u16 pos = le16_to_cpu(echo) % SPQ_RING_SIZE; + list_del(&p_ent->list); - qed_chain_return_produced(&p_spq->chain); + /* Avoid overriding of SPQ entries when getting + * out-of-order completions, by marking the completions + * in a bitmap and increasing the chain consumer only + * for the first successive completed entries. + */ + bitmap_set(p_spq->p_comp_bitmap, pos, SPQ_RING_SIZE); + + while (test_bit(p_spq->comp_bitmap_idx, + p_spq->p_comp_bitmap)) { + bitmap_clear(p_spq->p_comp_bitmap, + p_spq->comp_bitmap_idx, + SPQ_RING_SIZE); + p_spq->comp_bitmap_idx++; + qed_chain_return_produced(&p_spq->chain); + } + p_spq->comp_count++; found = p_ent; break; } + + /* This is relatively uncommon - depends on scenarios + * which have mutliple per-PF sent ramrods. + */ + DP_VERBOSE(p_hwfn, QED_MSG_SPQ, + "Got completion for echo %04x - doesn't match echo %04x in completion pending list\n", + le16_to_cpu(echo), + le16_to_cpu(p_ent->elem.hdr.echo)); } /* Release lock before callback, as callback may post diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c index be7d7a62cc0d..b1a452f291ee 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c @@ -246,7 +246,8 @@ int qlcnic_83xx_check_vnic_state(struct qlcnic_adapter *adapter) u32 state; state = QLCRDX(ahw, QLC_83XX_VNIC_STATE); - while (state != QLCNIC_DEV_NPAR_OPER && idc->vnic_wait_limit--) { + while (state != QLCNIC_DEV_NPAR_OPER && idc->vnic_wait_limit) { + idc->vnic_wait_limit--; msleep(1000); state = QLCRDX(ahw, QLC_83XX_VNIC_STATE); } diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index 02b7115b6aaa..997976426799 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -4211,8 +4211,9 @@ static int ql_change_rx_buffers(struct ql_adapter *qdev) /* Wait for an outstanding reset to complete. */ if (!test_bit(QL_ADAPTER_UP, &qdev->flags)) { - int i = 3; - while (i-- && !test_bit(QL_ADAPTER_UP, &qdev->flags)) { + int i = 4; + + while (--i && !test_bit(QL_ADAPTER_UP, &qdev->flags)) { netif_err(qdev, ifup, qdev->ndev, "Waiting for adapter UP...\n"); ssleep(1); diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index ddb2c6c6ec94..689a4a5c8dcf 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -736,9 +736,8 @@ qcaspi_netdev_tx_timeout(struct net_device *dev) netdev_info(qca->net_dev, "Transmit timeout at %ld, latency %ld\n", jiffies, jiffies - dev->trans_start); qca->net_dev->stats.tx_errors++; - /* wake the queue if there is room */ - if (qcaspi_tx_ring_has_space(&qca->txr)) - netif_wake_queue(dev); + /* Trigger tx queue flush and QCA7000 reset */ + qca->sync = QCASPI_SYNC_UNKNOWN; } static int diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index ed5da4d47668..467d41698fd5 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -905,6 +905,9 @@ static int ravb_phy_init(struct net_device *ndev) netdev_info(ndev, "limited PHY to 100Mbit/s\n"); } + /* 10BASE is not supported */ + phydev->supported &= ~PHY_10BT_FEATURES; + netdev_info(ndev, "attached PHY %d (IRQ %d) to driver %s\n", phydev->addr, phydev->irq, phydev->drv->name); @@ -1037,7 +1040,7 @@ static const char ravb_gstrings_stats[][ETH_GSTRING_LEN] = { "rx_queue_1_mcast_packets", "rx_queue_1_errors", "rx_queue_1_crc_errors", - "rx_queue_1_frame_errors_", + "rx_queue_1_frame_errors", "rx_queue_1_length_errors", "rx_queue_1_missed_errors", "rx_queue_1_over_errors", diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index e7bab7909ed9..a0eaf50499a2 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -52,6 +52,8 @@ NETIF_MSG_RX_ERR| \ NETIF_MSG_TX_ERR) +#define SH_ETH_OFFSET_INVALID ((u16)~0) + #define SH_ETH_OFFSET_DEFAULTS \ [0 ... SH_ETH_MAX_REGISTER_OFFSET - 1] = SH_ETH_OFFSET_INVALID @@ -404,6 +406,28 @@ static const u16 sh_eth_offset_fast_sh3_sh2[SH_ETH_MAX_REGISTER_OFFSET] = { static void sh_eth_rcv_snd_disable(struct net_device *ndev); static struct net_device_stats *sh_eth_get_stats(struct net_device *ndev); +static void sh_eth_write(struct net_device *ndev, u32 data, int enum_index) +{ + struct sh_eth_private *mdp = netdev_priv(ndev); + u16 offset = mdp->reg_offset[enum_index]; + + if (WARN_ON(offset == SH_ETH_OFFSET_INVALID)) + return; + + iowrite32(data, mdp->addr + offset); +} + +static u32 sh_eth_read(struct net_device *ndev, int enum_index) +{ + struct sh_eth_private *mdp = netdev_priv(ndev); + u16 offset = mdp->reg_offset[enum_index]; + + if (WARN_ON(offset == SH_ETH_OFFSET_INVALID)) + return ~0U; + + return ioread32(mdp->addr + offset); +} + static bool sh_eth_is_gether(struct sh_eth_private *mdp) { return mdp->reg_offset == sh_eth_offset_gigabit; @@ -1172,7 +1196,7 @@ static void sh_eth_ring_format(struct net_device *ndev) break; } mdp->rx_skbuff[i] = skb; - rxdesc->addr = dma_addr; + rxdesc->addr = cpu_to_edmac(mdp, dma_addr); rxdesc->status = cpu_to_edmac(mdp, RD_RACT | RD_RFP); /* Rx descriptor address set */ @@ -1403,7 +1427,8 @@ static int sh_eth_txfree(struct net_device *ndev) entry, edmac_to_cpu(mdp, txdesc->status)); /* Free the original skb. */ if (mdp->tx_skbuff[entry]) { - dma_unmap_single(&ndev->dev, txdesc->addr, + dma_unmap_single(&ndev->dev, + edmac_to_cpu(mdp, txdesc->addr), txdesc->buffer_length, DMA_TO_DEVICE); dev_kfree_skb_irq(mdp->tx_skbuff[entry]); mdp->tx_skbuff[entry] = NULL; @@ -1462,6 +1487,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) if (mdp->cd->shift_rd0) desc_status >>= 16; + skb = mdp->rx_skbuff[entry]; if (desc_status & (RD_RFS1 | RD_RFS2 | RD_RFS3 | RD_RFS4 | RD_RFS5 | RD_RFS6 | RD_RFS10)) { ndev->stats.rx_errors++; @@ -1477,16 +1503,16 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) ndev->stats.rx_missed_errors++; if (desc_status & RD_RFS10) ndev->stats.rx_over_errors++; - } else { + } else if (skb) { + dma_addr = edmac_to_cpu(mdp, rxdesc->addr); if (!mdp->cd->hw_swap) sh_eth_soft_swap( - phys_to_virt(ALIGN(rxdesc->addr, 4)), + phys_to_virt(ALIGN(dma_addr, 4)), pkt_len + 2); - skb = mdp->rx_skbuff[entry]; mdp->rx_skbuff[entry] = NULL; if (mdp->cd->rpadir) skb_reserve(skb, NET_IP_ALIGN); - dma_unmap_single(&ndev->dev, rxdesc->addr, + dma_unmap_single(&ndev->dev, dma_addr, ALIGN(mdp->rx_buf_sz, 32), DMA_FROM_DEVICE); skb_put(skb, pkt_len); @@ -1523,7 +1549,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) mdp->rx_skbuff[entry] = skb; skb_checksum_none_assert(skb); - rxdesc->addr = dma_addr; + rxdesc->addr = cpu_to_edmac(mdp, dma_addr); } dma_wmb(); /* RACT bit must be set after all the above writes */ if (entry >= mdp->num_rx_ring - 1) @@ -2331,8 +2357,8 @@ static void sh_eth_tx_timeout(struct net_device *ndev) /* Free all the skbuffs in the Rx queue. */ for (i = 0; i < mdp->num_rx_ring; i++) { rxdesc = &mdp->rx_ring[i]; - rxdesc->status = 0; - rxdesc->addr = 0xBADF00D0; + rxdesc->status = cpu_to_edmac(mdp, 0); + rxdesc->addr = cpu_to_edmac(mdp, 0xBADF00D0); dev_kfree_skb(mdp->rx_skbuff[i]); mdp->rx_skbuff[i] = NULL; } @@ -2350,6 +2376,7 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct sh_eth_private *mdp = netdev_priv(ndev); struct sh_eth_txdesc *txdesc; + dma_addr_t dma_addr; u32 entry; unsigned long flags; @@ -2372,14 +2399,14 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev) txdesc = &mdp->tx_ring[entry]; /* soft swap. */ if (!mdp->cd->hw_swap) - sh_eth_soft_swap(phys_to_virt(ALIGN(txdesc->addr, 4)), - skb->len + 2); - txdesc->addr = dma_map_single(&ndev->dev, skb->data, skb->len, - DMA_TO_DEVICE); - if (dma_mapping_error(&ndev->dev, txdesc->addr)) { + sh_eth_soft_swap(PTR_ALIGN(skb->data, 4), skb->len + 2); + dma_addr = dma_map_single(&ndev->dev, skb->data, skb->len, + DMA_TO_DEVICE); + if (dma_mapping_error(&ndev->dev, dma_addr)) { kfree_skb(skb); return NETDEV_TX_OK; } + txdesc->addr = cpu_to_edmac(mdp, dma_addr); txdesc->buffer_length = skb->len; dma_wmb(); /* TACT bit must be set after all the above writes */ diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index 50382b1c9ddc..26ad1cf0bcf1 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -546,31 +546,6 @@ static inline void sh_eth_soft_swap(char *src, int len) #endif } -#define SH_ETH_OFFSET_INVALID ((u16) ~0) - -static inline void sh_eth_write(struct net_device *ndev, u32 data, - int enum_index) -{ - struct sh_eth_private *mdp = netdev_priv(ndev); - u16 offset = mdp->reg_offset[enum_index]; - - if (WARN_ON(offset == SH_ETH_OFFSET_INVALID)) - return; - - iowrite32(data, mdp->addr + offset); -} - -static inline u32 sh_eth_read(struct net_device *ndev, int enum_index) -{ - struct sh_eth_private *mdp = netdev_priv(ndev); - u16 offset = mdp->reg_offset[enum_index]; - - if (WARN_ON(offset == SH_ETH_OFFSET_INVALID)) - return ~0U; - - return ioread32(mdp->addr + offset); -} - static inline void *sh_eth_tsu_get_offset(struct sh_eth_private *mdp, int enum_index) { diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index bc6d21b471be..e6a084a6be12 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -3299,7 +3299,8 @@ static int efx_ef10_filter_remove_internal(struct efx_nic *efx, new_spec.priority = EFX_FILTER_PRI_AUTO; new_spec.flags = (EFX_FILTER_FLAG_RX | - EFX_FILTER_FLAG_RX_RSS); + (efx_rss_enabled(efx) ? + EFX_FILTER_FLAG_RX_RSS : 0)); new_spec.dmaq_id = 0; new_spec.rss_context = EFX_FILTER_RSS_CONTEXT_DEFAULT; rc = efx_ef10_filter_push(efx, &new_spec, @@ -3921,6 +3922,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx, { struct efx_ef10_filter_table *table = efx->filter_state; struct efx_ef10_dev_addr *addr_list; + enum efx_filter_flags filter_flags; struct efx_filter_spec spec; u8 baddr[ETH_ALEN]; unsigned int i, j; @@ -3935,11 +3937,11 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx, addr_count = table->dev_uc_count; } + filter_flags = efx_rss_enabled(efx) ? EFX_FILTER_FLAG_RX_RSS : 0; + /* Insert/renew filters */ for (i = 0; i < addr_count; i++) { - efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, - EFX_FILTER_FLAG_RX_RSS, - 0); + efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0); efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC, addr_list[i].addr); rc = efx_ef10_filter_insert(efx, &spec, true); @@ -3968,9 +3970,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx, if (multicast && rollback) { /* Also need an Ethernet broadcast filter */ - efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, - EFX_FILTER_FLAG_RX_RSS, - 0); + efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0); eth_broadcast_addr(baddr); efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC, baddr); rc = efx_ef10_filter_insert(efx, &spec, true); @@ -4000,13 +4000,14 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx, bool multicast, { struct efx_ef10_filter_table *table = efx->filter_state; struct efx_ef10_nic_data *nic_data = efx->nic_data; + enum efx_filter_flags filter_flags; struct efx_filter_spec spec; u8 baddr[ETH_ALEN]; int rc; - efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, - EFX_FILTER_FLAG_RX_RSS, - 0); + filter_flags = efx_rss_enabled(efx) ? EFX_FILTER_FLAG_RX_RSS : 0; + + efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0); if (multicast) efx_filter_set_mc_def(&spec); @@ -4023,8 +4024,7 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx, bool multicast, if (!nic_data->workaround_26807) { /* Also need an Ethernet broadcast filter */ efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, - EFX_FILTER_FLAG_RX_RSS, - 0); + filter_flags, 0); eth_broadcast_addr(baddr); efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC, baddr); diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index 1aaf76c1ace8..10827476bc0b 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -76,6 +76,11 @@ void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue); #define EFX_TXQ_MAX_ENT(efx) (EFX_WORKAROUND_35388(efx) ? \ EFX_MAX_DMAQ_SIZE / 2 : EFX_MAX_DMAQ_SIZE) +static inline bool efx_rss_enabled(struct efx_nic *efx) +{ + return efx->rss_spread > 1; +} + /* Filters */ void efx_mac_reconfigure(struct efx_nic *efx); diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index 5a1c5a8f278a..133e9e35be9e 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -2242,7 +2242,7 @@ efx_farch_filter_init_rx_auto(struct efx_nic *efx, */ spec->priority = EFX_FILTER_PRI_AUTO; spec->flags = (EFX_FILTER_FLAG_RX | - (efx->n_rx_channels > 1 ? EFX_FILTER_FLAG_RX_RSS : 0) | + (efx_rss_enabled(efx) ? EFX_FILTER_FLAG_RX_RSS : 0) | (efx->rx_scatter ? EFX_FILTER_FLAG_RX_SCATTER : 0)); spec->dmaq_id = 0; } diff --git a/drivers/net/ethernet/sfc/txc43128_phy.c b/drivers/net/ethernet/sfc/txc43128_phy.c index 3d5ee3259885..194f67d9f3bf 100644 --- a/drivers/net/ethernet/sfc/txc43128_phy.c +++ b/drivers/net/ethernet/sfc/txc43128_phy.c @@ -418,7 +418,7 @@ static void txc_reset_logic_mmd(struct efx_nic *efx, int mmd) val |= (1 << TXC_GLCMD_LMTSWRST_LBN); efx_mdio_write(efx, mmd, TXC_GLRGS_GLCMD, val); - while (tries--) { + while (--tries) { val = efx_mdio_read(efx, mmd, TXC_GLRGS_GLCMD); if (!(val & (1 << TXC_GLCMD_LMTSWRST_LBN))) break; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c index 52b8ed9bd87c..adff46375a32 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c @@ -153,7 +153,11 @@ static int sun7i_gmac_probe(struct platform_device *pdev) if (ret) return ret; - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + sun7i_gmac_exit(pdev, plat_dat->bsp_priv); + + return ret; } static const struct of_device_id sun7i_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3c6549aee11d..a5b869eb4678 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3046,8 +3046,6 @@ int stmmac_suspend(struct net_device *ndev) priv->hw->dma->stop_tx(priv->ioaddr); priv->hw->dma->stop_rx(priv->ioaddr); - stmmac_clear_descriptors(priv); - /* Enable Power down mode by programming the PMT regs */ if (device_may_wakeup(priv->device)) { priv->hw->mac->pmt(priv->hw, priv->wolopts); @@ -3105,7 +3103,12 @@ int stmmac_resume(struct net_device *ndev) netif_device_attach(ndev); - init_dma_desc_rings(ndev, GFP_ATOMIC); + priv->cur_rx = 0; + priv->dirty_rx = 0; + priv->dirty_tx = 0; + priv->cur_tx = 0; + stmmac_clear_descriptors(priv); + stmmac_hw_setup(ndev, false); stmmac_init_tx_coalesce(priv); stmmac_set_rx_mode(ndev); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index de5c30c9f059..c2b79f5d1c89 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -967,8 +967,6 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, err = udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev, &fl6.saddr, &fl6.daddr, prio, ttl, sport, geneve->dst_port, !udp_csum); - - iptunnel_xmit_stats(err, &dev->stats, dev->tstats); return NETDEV_TX_OK; tx_error: diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c index 908e8d486342..7f8e7662e28c 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/phy/mdio-mux.c @@ -149,9 +149,14 @@ int mdio_mux_init(struct device *dev, } cb->bus_number = v; cb->parent = pb; - cb->mii_bus = mdiobus_alloc(); - cb->mii_bus->priv = cb; + cb->mii_bus = mdiobus_alloc(); + if (!cb->mii_bus) { + ret_val = -ENOMEM; + of_node_put(child_bus_node); + break; + } + cb->mii_bus->priv = cb; cb->mii_bus->irq = cb->phy_irq; cb->mii_bus->name = "mdio_mux"; snprintf(cb->mii_bus->id, MII_BUS_ID_SIZE, "%x.%x", diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index cf6312fafea5..e13ad6cdcc22 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -339,9 +339,18 @@ static int ksz9021_config_init(struct phy_device *phydev) { const struct device *dev = &phydev->dev; const struct device_node *of_node = dev->of_node; + const struct device *dev_walker; - if (!of_node && dev->parent->of_node) - of_node = dev->parent->of_node; + /* The Micrel driver has a deprecated option to place phy OF + * properties in the MAC node. Walk up the tree of devices to + * find a device with an OF node. + */ + dev_walker = &phydev->dev; + do { + of_node = dev_walker->of_node; + dev_walker = dev_walker->parent; + + } while (!of_node && dev_walker); if (of_node) { ksz9021_load_values_from_of(phydev, of_node, diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 5e0b43283bce..0a37f840fcc5 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -568,6 +568,9 @@ static int pppoe_create(struct net *net, struct socket *sock, int kern) sk->sk_family = PF_PPPOX; sk->sk_protocol = PX_PROTO_OE; + INIT_WORK(&pppox_sk(sk)->proto.pppoe.padt_work, + pppoe_unbind_sock_work); + return 0; } @@ -632,8 +635,6 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr, lock_sock(sk); - INIT_WORK(&po->proto.pppoe.padt_work, pppoe_unbind_sock_work); - error = -EINVAL; if (sp->sa_protocol != PX_PROTO_OE) goto end; @@ -663,8 +664,13 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr, po->pppoe_dev = NULL; } - memset(sk_pppox(po) + 1, 0, - sizeof(struct pppox_sock) - sizeof(struct sock)); + po->pppoe_ifindex = 0; + memset(&po->pppoe_pa, 0, sizeof(po->pppoe_pa)); + memset(&po->pppoe_relay, 0, sizeof(po->pppoe_relay)); + memset(&po->chan, 0, sizeof(po->chan)); + po->next = NULL; + po->num = 0; + sk->sk_state = PPPOX_NONE; } diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index fc69e41d0950..597c53e0a2ec 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -419,6 +419,9 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, struct pptp_opt *opt = &po->proto.pptp; int error = 0; + if (sockaddr_len < sizeof(struct sockaddr_pppox)) + return -EINVAL; + lock_sock(sk); opt->src_addr = sp->sa_addr.pptp; @@ -440,6 +443,9 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr, struct flowi4 fl4; int error = 0; + if (sockaddr_len < sizeof(struct sockaddr_pppox)) + return -EINVAL; + if (sp->sa_protocol != PX_PROTO_PPTP) return -EINVAL; diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index bbde9884ab8a..8973abdec9f6 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -158,7 +158,7 @@ static int cdc_mbim_bind(struct usbnet *dev, struct usb_interface *intf) if (!cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting)) goto err; - ret = cdc_ncm_bind_common(dev, intf, data_altsetting, 0); + ret = cdc_ncm_bind_common(dev, intf, data_altsetting, dev->driver_info->data); if (ret) goto err; @@ -582,6 +582,26 @@ static const struct driver_info cdc_mbim_info_zlp = { .tx_fixup = cdc_mbim_tx_fixup, }; +/* The spefication explicitly allows NDPs to be placed anywhere in the + * frame, but some devices fail unless the NDP is placed after the IP + * packets. Using the CDC_NCM_FLAG_NDP_TO_END flags to force this + * behaviour. + * + * Note: The current implementation of this feature restricts each NTB + * to a single NDP, implying that multiplexed sessions cannot share an + * NTB. This might affect performace for multiplexed sessions. + */ +static const struct driver_info cdc_mbim_info_ndp_to_end = { + .description = "CDC MBIM", + .flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN, + .bind = cdc_mbim_bind, + .unbind = cdc_mbim_unbind, + .manage_power = cdc_mbim_manage_power, + .rx_fixup = cdc_mbim_rx_fixup, + .tx_fixup = cdc_mbim_tx_fixup, + .data = CDC_NCM_FLAG_NDP_TO_END, +}; + static const struct usb_device_id mbim_devs[] = { /* This duplicate NCM entry is intentional. MBIM devices can * be disguised as NCM by default, and this is necessary to @@ -597,6 +617,10 @@ static const struct usb_device_id mbim_devs[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x0bdb, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&cdc_mbim_info, }, + /* Huawei E3372 fails unless NDP comes after the IP packets */ + { USB_DEVICE_AND_INTERFACE_INFO(0x12d1, 0x157d, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&cdc_mbim_info_ndp_to_end, + }, /* default entry */ { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&cdc_mbim_info_zlp, diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 3b1ba8237768..1e9843a41168 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -955,10 +955,18 @@ static struct usb_cdc_ncm_ndp16 *cdc_ncm_ndp(struct cdc_ncm_ctx *ctx, struct sk_ * NTH16 header as we would normally do. NDP isn't written to the SKB yet, and * the wNdpIndex field in the header is actually not consistent with reality. It will be later. */ - if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) + if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) { if (ctx->delayed_ndp16->dwSignature == sign) return ctx->delayed_ndp16; + /* We can only push a single NDP to the end. Return + * NULL to send what we've already got and queue this + * skb for later. + */ + else if (ctx->delayed_ndp16->dwSignature) + return NULL; + } + /* follow the chain of NDPs, looking for a match */ while (ndpoffset) { ndp16 = (struct usb_cdc_ncm_ndp16 *)(skb->data + ndpoffset); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index d9427ca3dba7..2e32c41536ae 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3067,17 +3067,6 @@ static int rtl8152_open(struct net_device *netdev) mutex_lock(&tp->control); - /* The WORK_ENABLE may be set when autoresume occurs */ - if (test_bit(WORK_ENABLE, &tp->flags)) { - clear_bit(WORK_ENABLE, &tp->flags); - usb_kill_urb(tp->intr_urb); - cancel_delayed_work_sync(&tp->schedule); - - /* disable the tx/rx, if the workqueue has enabled them. */ - if (netif_carrier_ok(netdev)) - tp->rtl_ops.disable(tp); - } - tp->rtl_ops.up(tp); rtl8152_set_speed(tp, AUTONEG_ENABLE, @@ -3124,12 +3113,6 @@ static int rtl8152_close(struct net_device *netdev) } else { mutex_lock(&tp->control); - /* The autosuspend may have been enabled and wouldn't - * be disable when autoresume occurs, because the - * netif_running() would be false. - */ - rtl_runtime_suspend_enable(tp, false); - tp->rtl_ops.down(tp); mutex_unlock(&tp->control); @@ -3512,7 +3495,7 @@ static int rtl8152_resume(struct usb_interface *intf) netif_device_attach(tp->netdev); } - if (netif_running(tp->netdev)) { + if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) { if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { rtl_runtime_suspend_enable(tp, false); clear_bit(SELECTIVE_SUSPEND, &tp->flags); @@ -3532,6 +3515,8 @@ static int rtl8152_resume(struct usb_interface *intf) } usb_submit_urb(tp->intr_urb, GFP_KERNEL); } else if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { + if (tp->netdev->flags & IFF_UP) + rtl_runtime_suspend_enable(tp, false); clear_bit(SELECTIVE_SUSPEND, &tp->flags); } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 6369a5734d4c..ba363cedef80 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1158,7 +1158,6 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, struct pcpu_sw_netstats *stats; union vxlan_addr saddr; int err = 0; - union vxlan_addr *remote_ip; /* For flow based devices, map all packets to VNI 0 */ if (vs->flags & VXLAN_F_COLLECT_METADATA) @@ -1169,7 +1168,6 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, if (!vxlan) goto drop; - remote_ip = &vxlan->default_dst.remote_ip; skb_reset_mac_header(skb); skb_scrub_packet(skb, !net_eq(vxlan->net, dev_net(vxlan->dev))); skb->protocol = eth_type_trans(skb, vxlan->dev); @@ -1179,8 +1177,8 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr)) goto drop; - /* Re-examine inner Ethernet packet */ - if (remote_ip->sa.sa_family == AF_INET) { + /* Get data from the outer IP header */ + if (vxlan_get_sk_family(vs) == AF_INET) { oip = ip_hdr(skb); saddr.sin.sin_addr.s_addr = oip->saddr; saddr.sa.sa_family = AF_INET; @@ -1848,6 +1846,34 @@ static int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *sk !(vxflags & VXLAN_F_UDP_CSUM)); } +#if IS_ENABLED(CONFIG_IPV6) +static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, + struct sk_buff *skb, int oif, + const struct in6_addr *daddr, + struct in6_addr *saddr) +{ + struct dst_entry *ndst; + struct flowi6 fl6; + int err; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = oif; + fl6.daddr = *daddr; + fl6.saddr = vxlan->cfg.saddr.sin6.sin6_addr; + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = IPPROTO_UDP; + + err = ipv6_stub->ipv6_dst_lookup(vxlan->net, + vxlan->vn6_sock->sock->sk, + &ndst, &fl6); + if (err < 0) + return ERR_PTR(err); + + *saddr = fl6.saddr; + return ndst; +} +#endif + /* Bypass encapsulation if the destination is local */ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct vxlan_dev *dst_vxlan) @@ -2035,21 +2061,17 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, #if IS_ENABLED(CONFIG_IPV6) } else { struct dst_entry *ndst; - struct flowi6 fl6; + struct in6_addr saddr; u32 rt6i_flags; if (!vxlan->vn6_sock) goto drop; sk = vxlan->vn6_sock->sock->sk; - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_oif = rdst ? rdst->remote_ifindex : 0; - fl6.daddr = dst->sin6.sin6_addr; - fl6.saddr = vxlan->cfg.saddr.sin6.sin6_addr; - fl6.flowi6_mark = skb->mark; - fl6.flowi6_proto = IPPROTO_UDP; - - if (ipv6_stub->ipv6_dst_lookup(vxlan->net, sk, &ndst, &fl6)) { + ndst = vxlan6_get_route(vxlan, skb, + rdst ? rdst->remote_ifindex : 0, + &dst->sin6.sin6_addr, &saddr); + if (IS_ERR(ndst)) { netdev_dbg(dev, "no route to %pI6\n", &dst->sin6.sin6_addr); dev->stats.tx_carrier_errors++; @@ -2081,7 +2103,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } ttl = ttl ? : ip6_dst_hoplimit(ndst); - err = vxlan6_xmit_skb(ndst, sk, skb, dev, &fl6.saddr, &fl6.daddr, + err = vxlan6_xmit_skb(ndst, sk, skb, dev, &saddr, &dst->sin6.sin6_addr, 0, ttl, src_port, dst_port, htonl(vni << 8), md, !net_eq(vxlan->net, dev_net(vxlan->dev)), flags); @@ -2395,9 +2417,30 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) vxlan->cfg.port_max, true); dport = info->key.tp_dst ? : vxlan->cfg.dst_port; - if (ip_tunnel_info_af(info) == AF_INET) + if (ip_tunnel_info_af(info) == AF_INET) { + if (!vxlan->vn4_sock) + return -EINVAL; return egress_ipv4_tun_info(dev, skb, info, sport, dport); - return -EINVAL; + } else { +#if IS_ENABLED(CONFIG_IPV6) + struct dst_entry *ndst; + + if (!vxlan->vn6_sock) + return -EINVAL; + ndst = vxlan6_get_route(vxlan, skb, 0, + &info->key.u.ipv6.dst, + &info->key.u.ipv6.src); + if (IS_ERR(ndst)) + return PTR_ERR(ndst); + dst_release(ndst); + + info->key.tp_src = sport; + info->key.tp_dst = dport; +#else /* !CONFIG_IPV6 */ + return -EPFNOSUPPORT; +#endif + } + return 0; } static const struct net_device_ops vxlan_netdev_ops = { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3b5d134e945a..3143c847bddb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2084,7 +2084,7 @@ struct pcpu_sw_netstats { }) #define netdev_alloc_pcpu_stats(type) \ - __netdev_alloc_pcpu_stats(type, GFP_KERNEL); + __netdev_alloc_pcpu_stats(type, GFP_KERNEL) #include diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 249d1bb01e03..5646b24bfc64 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -14,7 +14,7 @@ struct nfnl_callback { int (*call_rcu)(struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]); - int (*call_batch)(struct sock *nl, struct sk_buff *skb, + int (*call_batch)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]); const struct nla_policy *policy; /* netlink attribute policy */ diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 6a4347639c03..1d1ba2c5ee7a 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -9,6 +9,8 @@ #ifndef __COMMON_HSI__ #define __COMMON_HSI__ +#define CORE_SPQE_PAGE_SIZE_BYTES 4096 + #define FW_MAJOR_VERSION 8 #define FW_MINOR_VERSION 4 #define FW_REVISION_VERSION 2 diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index b920c3605c46..41b9049b57e2 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -111,7 +111,8 @@ static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain) used = ((u32)0x10000u + (u32)(p_chain->prod_idx)) - (u32)p_chain->cons_idx; if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) - used -= (used / p_chain->elem_per_page); + used -= p_chain->prod_idx / p_chain->elem_per_page - + p_chain->cons_idx / p_chain->elem_per_page; return p_chain->capacity - used; } diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 843ceca9a21e..e50b31d18462 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -19,6 +19,7 @@ #include #include +#include #include #include #include @@ -339,10 +340,11 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, int rhashtable_init(struct rhashtable *ht, const struct rhashtable_params *params); -int rhashtable_insert_slow(struct rhashtable *ht, const void *key, - struct rhash_head *obj, - struct bucket_table *old_tbl); -int rhashtable_insert_rehash(struct rhashtable *ht); +struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht, + const void *key, + struct rhash_head *obj, + struct bucket_table *old_tbl); +int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl); int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter); void rhashtable_walk_exit(struct rhashtable_iter *iter); @@ -598,9 +600,11 @@ restart: new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (unlikely(new_tbl)) { - err = rhashtable_insert_slow(ht, key, obj, new_tbl); - if (err == -EAGAIN) + tbl = rhashtable_insert_slow(ht, key, obj, new_tbl); + if (!IS_ERR_OR_NULL(tbl)) goto slow_path; + + err = PTR_ERR(tbl); goto out; } @@ -611,7 +615,7 @@ restart: if (unlikely(rht_grow_above_100(ht, tbl))) { slow_path: spin_unlock_bh(lock); - err = rhashtable_insert_rehash(ht); + err = rhashtable_insert_rehash(ht, tbl); rcu_read_unlock(); if (err) return err; diff --git a/include/net/dst.h b/include/net/dst.h index 1279f9b09791..c7329dcd90cc 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -322,6 +322,39 @@ static inline void skb_dst_force(struct sk_buff *skb) } } +/** + * dst_hold_safe - Take a reference on a dst if possible + * @dst: pointer to dst entry + * + * This helper returns false if it could not safely + * take a reference on a dst. + */ +static inline bool dst_hold_safe(struct dst_entry *dst) +{ + if (dst->flags & DST_NOCACHE) + return atomic_inc_not_zero(&dst->__refcnt); + dst_hold(dst); + return true; +} + +/** + * skb_dst_force_safe - makes sure skb dst is refcounted + * @skb: buffer + * + * If dst is not yet refcounted and not destroyed, grab a ref on it. + */ +static inline void skb_dst_force_safe(struct sk_buff *skb) +{ + if (skb_dst_is_noref(skb)) { + struct dst_entry *dst = skb_dst(skb); + + if (!dst_hold_safe(dst)) + dst = NULL; + + skb->_skb_refdst = (unsigned long)dst; + } +} + /** * __skb_tunnel_rx - prepare skb for rx reinsert diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 2134e6d815bc..625bdf95d673 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -210,18 +210,37 @@ struct inet_sock { #define IP_CMSG_ORIGDSTADDR BIT(6) #define IP_CMSG_CHECKSUM BIT(7) -/* SYNACK messages might be attached to request sockets. +/** + * sk_to_full_sk - Access to a full socket + * @sk: pointer to a socket + * + * SYNACK messages might be attached to request sockets. * Some places want to reach the listener in this case. */ -static inline struct sock *skb_to_full_sk(const struct sk_buff *skb) +static inline struct sock *sk_to_full_sk(struct sock *sk) { - struct sock *sk = skb->sk; - +#ifdef CONFIG_INET if (sk && sk->sk_state == TCP_NEW_SYN_RECV) sk = inet_reqsk(sk)->rsk_listener; +#endif return sk; } +/* sk_to_full_sk() variant with a const argument */ +static inline const struct sock *sk_const_to_full_sk(const struct sock *sk) +{ +#ifdef CONFIG_INET + if (sk && sk->sk_state == TCP_NEW_SYN_RECV) + sk = ((const struct request_sock *)sk)->rsk_listener; +#endif + return sk; +} + +static inline struct sock *skb_to_full_sk(const struct sk_buff *skb) +{ + return sk_to_full_sk(skb->sk); +} + static inline struct inet_sock *inet_sk(const struct sock *sk) { return (struct inet_sock *)sk; diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 4a6009d4486b..235c7811a86a 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -78,6 +78,7 @@ void inet_initpeers(void) __init; static inline void inetpeer_set_addr_v4(struct inetpeer_addr *iaddr, __be32 ip) { iaddr->a4.addr = ip; + iaddr->a4.vif = 0; iaddr->family = AF_INET; } diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 7bbb71081aeb..eea9bdeecba2 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1493,7 +1493,8 @@ struct sctp_association { * : SACK's are not delayed (see Section 6). */ __u8 sack_needed:1, /* Do we need to sack the peer? */ - sack_generation:1; + sack_generation:1, + zero_window_announced:1; __u32 sack_cnt; __u32 adaptation_ind; /* Adaptation Code point. */ diff --git a/include/net/sock.h b/include/net/sock.h index 52d27ee924f4..14d3c0734007 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -388,7 +388,7 @@ struct sock { struct socket_wq *sk_wq_raw; }; #ifdef CONFIG_XFRM - struct xfrm_policy *sk_policy[2]; + struct xfrm_policy __rcu *sk_policy[2]; #endif struct dst_entry *sk_rx_dst; struct dst_entry __rcu *sk_dst_cache; @@ -404,6 +404,7 @@ struct sock { sk_userlocks : 4, sk_protocol : 8, sk_type : 16; +#define SK_PROTOCOL_MAX U8_MAX kmemcheck_bitfield_end(flags); int sk_wmem_queued; gfp_t sk_allocation; @@ -740,6 +741,8 @@ enum sock_flags { SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ }; +#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) + static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) { nsk->sk_flags = osk->sk_flags; @@ -814,7 +817,7 @@ void sk_stream_write_space(struct sock *sk); static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { /* dont let skb dst not refcounted, we are going to leave rcu lock */ - skb_dst_force(skb); + skb_dst_force_safe(skb); if (!sk->sk_backlog.tail) sk->sk_backlog.head = skb; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index c1c899c3a51b..e289ada6adf6 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -79,7 +79,7 @@ struct vxlanhdr { }; /* VXLAN header flags. */ -#define VXLAN_HF_RCO BIT(24) +#define VXLAN_HF_RCO BIT(21) #define VXLAN_HF_VNI BIT(27) #define VXLAN_HF_GBP BIT(31) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 4a9c21f9b4ea..d6f6e5006ee9 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -548,6 +548,7 @@ struct xfrm_policy { u16 family; struct xfrm_sec_ctx *security; struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; + struct rcu_head rcu; }; static inline struct net *xp_net(const struct xfrm_policy *xp) @@ -1141,12 +1142,14 @@ static inline int xfrm6_route_forward(struct sk_buff *skb) return xfrm_route_forward(skb, AF_INET6); } -int __xfrm_sk_clone_policy(struct sock *sk); +int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk); -static inline int xfrm_sk_clone_policy(struct sock *sk) +static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { - if (unlikely(sk->sk_policy[0] || sk->sk_policy[1])) - return __xfrm_sk_clone_policy(sk); + sk->sk_policy[0] = NULL; + sk->sk_policy[1] = NULL; + if (unlikely(osk->sk_policy[0] || osk->sk_policy[1])) + return __xfrm_sk_clone_policy(sk, osk); return 0; } @@ -1154,12 +1157,16 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir); static inline void xfrm_sk_free_policy(struct sock *sk) { - if (unlikely(sk->sk_policy[0] != NULL)) { - xfrm_policy_delete(sk->sk_policy[0], XFRM_POLICY_MAX); + struct xfrm_policy *pol; + + pol = rcu_dereference_protected(sk->sk_policy[0], 1); + if (unlikely(pol != NULL)) { + xfrm_policy_delete(pol, XFRM_POLICY_MAX); sk->sk_policy[0] = NULL; } - if (unlikely(sk->sk_policy[1] != NULL)) { - xfrm_policy_delete(sk->sk_policy[1], XFRM_POLICY_MAX+1); + pol = rcu_dereference_protected(sk->sk_policy[1], 1); + if (unlikely(pol != NULL)) { + xfrm_policy_delete(pol, XFRM_POLICY_MAX+1); sk->sk_policy[1] = NULL; } } @@ -1169,7 +1176,7 @@ void xfrm_garbage_collect(struct net *net); #else static inline void xfrm_sk_free_policy(struct sock *sk) {} -static inline int xfrm_sk_clone_policy(struct sock *sk) { return 0; } +static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { return 0; } static inline int xfrm6_route_forward(struct sk_buff *skb) { return 1; } static inline int xfrm4_route_forward(struct sk_buff *skb) { return 1; } static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb) diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 628e6e64c2fb..c2e5d6cb34e3 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -186,6 +186,7 @@ header-y += if_tunnel.h header-y += if_vlan.h header-y += if_x25.h header-y += igmp.h +header-y += ila.h header-y += in6.h header-y += inet_diag.h header-y += in.h diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 28ccedd000f5..a27222d5b413 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -628,7 +628,7 @@ struct ovs_action_hash { * @OVS_CT_ATTR_MARK: u32 value followed by u32 mask. For each bit set in the * mask, the corresponding bit in the value is copied to the connection * tracking mark field in the connection. - * @OVS_CT_ATTR_LABEL: %OVS_CT_LABELS_LEN value followed by %OVS_CT_LABELS_LEN + * @OVS_CT_ATTR_LABELS: %OVS_CT_LABELS_LEN value followed by %OVS_CT_LABELS_LEN * mask. For each bit set in the mask, the corresponding bit in the value is * copied to the connection tracking label field in the connection. * @OVS_CT_ATTR_HELPER: variable length string defining conntrack ALG. diff --git a/lib/rhashtable.c b/lib/rhashtable.c index a54ff8949f91..eb9240c458fa 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -389,33 +389,31 @@ static bool rhashtable_check_elasticity(struct rhashtable *ht, return false; } -int rhashtable_insert_rehash(struct rhashtable *ht) +int rhashtable_insert_rehash(struct rhashtable *ht, + struct bucket_table *tbl) { struct bucket_table *old_tbl; struct bucket_table *new_tbl; - struct bucket_table *tbl; unsigned int size; int err; old_tbl = rht_dereference_rcu(ht->tbl, ht); - tbl = rhashtable_last_table(ht, old_tbl); size = tbl->size; + err = -EBUSY; + if (rht_grow_above_75(ht, tbl)) size *= 2; /* Do not schedule more than one rehash */ else if (old_tbl != tbl) - return -EBUSY; + goto fail; + + err = -ENOMEM; new_tbl = bucket_table_alloc(ht, size, GFP_ATOMIC); - if (new_tbl == NULL) { - /* Schedule async resize/rehash to try allocation - * non-atomic context. - */ - schedule_work(&ht->run_work); - return -ENOMEM; - } + if (new_tbl == NULL) + goto fail; err = rhashtable_rehash_attach(ht, tbl, new_tbl); if (err) { @@ -426,12 +424,24 @@ int rhashtable_insert_rehash(struct rhashtable *ht) schedule_work(&ht->run_work); return err; + +fail: + /* Do not fail the insert if someone else did a rehash. */ + if (likely(rcu_dereference_raw(tbl->future_tbl))) + return 0; + + /* Schedule async rehash to retry allocation in process context. */ + if (err == -ENOMEM) + schedule_work(&ht->run_work); + + return err; } EXPORT_SYMBOL_GPL(rhashtable_insert_rehash); -int rhashtable_insert_slow(struct rhashtable *ht, const void *key, - struct rhash_head *obj, - struct bucket_table *tbl) +struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht, + const void *key, + struct rhash_head *obj, + struct bucket_table *tbl) { struct rhash_head *head; unsigned int hash; @@ -467,7 +477,12 @@ int rhashtable_insert_slow(struct rhashtable *ht, const void *key, exit: spin_unlock(rht_bucket_lock(tbl, hash)); - return err; + if (err == 0) + return NULL; + else if (err == -EAGAIN) + return tbl; + else + return ERR_PTR(err); } EXPORT_SYMBOL_GPL(rhashtable_insert_slow); @@ -503,10 +518,10 @@ int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter) if (!iter->walker) return -ENOMEM; - mutex_lock(&ht->mutex); + spin_lock(&ht->lock); iter->walker->tbl = rht_dereference(ht->tbl, ht); list_add(&iter->walker->list, &iter->walker->tbl->walkers); - mutex_unlock(&ht->mutex); + spin_unlock(&ht->lock); return 0; } @@ -520,10 +535,10 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_init); */ void rhashtable_walk_exit(struct rhashtable_iter *iter) { - mutex_lock(&iter->ht->mutex); + spin_lock(&iter->ht->lock); if (iter->walker->tbl) list_del(&iter->walker->list); - mutex_unlock(&iter->ht->mutex); + spin_unlock(&iter->ht->lock); kfree(iter->walker); } EXPORT_SYMBOL_GPL(rhashtable_walk_exit); @@ -547,14 +562,12 @@ int rhashtable_walk_start(struct rhashtable_iter *iter) { struct rhashtable *ht = iter->ht; - mutex_lock(&ht->mutex); - - if (iter->walker->tbl) - list_del(&iter->walker->list); - rcu_read_lock(); - mutex_unlock(&ht->mutex); + spin_lock(&ht->lock); + if (iter->walker->tbl) + list_del(&iter->walker->list); + spin_unlock(&ht->lock); if (!iter->walker->tbl) { iter->walker->tbl = rht_dereference_rcu(ht->tbl, ht); @@ -723,9 +736,6 @@ int rhashtable_init(struct rhashtable *ht, if (params->nulls_base && params->nulls_base < (1U << RHT_BASE_SHIFT)) return -EINVAL; - if (params->nelem_hint) - size = rounded_hashtable_size(params); - memset(ht, 0, sizeof(*ht)); mutex_init(&ht->mutex); spin_lock_init(&ht->lock); @@ -745,6 +755,9 @@ int rhashtable_init(struct rhashtable *ht, ht->p.min_size = max(ht->p.min_size, HASH_MIN_SIZE); + if (params->nelem_hint) + size = rounded_hashtable_size(&ht->p); + /* The maximum (not average) chain length grows with the * size of the hash table, at a rate of (log N)/(log log N). * The value of 16 is selected so that even if the hash diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index ae3a47f9d1d5..fbd0acf80b13 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -805,6 +805,9 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; ax25_cb *ax25; + if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + return -EINVAL; + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 83bc1aaf5800..a49c705fb86b 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -566,6 +566,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) int select; batadv_dat_addr_t last_max = BATADV_DAT_ADDR_MAX, ip_key; struct batadv_dat_candidate *res; + struct batadv_dat_entry dat; if (!bat_priv->orig_hash) return NULL; @@ -575,7 +576,9 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) if (!res) return NULL; - ip_key = (batadv_dat_addr_t)batadv_hash_dat(&ip_dst, + dat.ip = ip_dst; + dat.vid = 0; + ip_key = (batadv_dat_addr_t)batadv_hash_dat(&dat, BATADV_DAT_ADDR_MAX); batadv_dbg(BATADV_DBG_DAT, bat_priv, diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 8d990b070a2e..3207667e69de 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -836,6 +836,7 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, u8 *orig_addr; struct batadv_orig_node *orig_node = NULL; int check, hdr_size = sizeof(*unicast_packet); + enum batadv_subtype subtype; bool is4addr; unicast_packet = (struct batadv_unicast_packet *)skb->data; @@ -863,10 +864,20 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, /* packet for me */ if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) { if (is4addr) { - batadv_dat_inc_counter(bat_priv, - unicast_4addr_packet->subtype); - orig_addr = unicast_4addr_packet->src; - orig_node = batadv_orig_hash_find(bat_priv, orig_addr); + subtype = unicast_4addr_packet->subtype; + batadv_dat_inc_counter(bat_priv, subtype); + + /* Only payload data should be considered for speedy + * join. For example, DAT also uses unicast 4addr + * types, but those packets should not be considered + * for speedy join, since the clients do not actually + * reside at the sending originator. + */ + if (subtype == BATADV_P_DATA) { + orig_addr = unicast_4addr_packet->src; + orig_node = batadv_orig_hash_find(bat_priv, + orig_addr); + } } if (batadv_dat_snoop_incoming_arp_request(bat_priv, skb, diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 4228b10c47ea..76f19ba62462 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -68,13 +68,15 @@ static void batadv_tt_global_del(struct batadv_priv *bat_priv, unsigned short vid, const char *message, bool roaming); -/* returns 1 if they are the same mac addr */ +/* returns 1 if they are the same mac addr and vid */ static int batadv_compare_tt(const struct hlist_node *node, const void *data2) { const void *data1 = container_of(node, struct batadv_tt_common_entry, hash_entry); + const struct batadv_tt_common_entry *tt1 = data1; + const struct batadv_tt_common_entry *tt2 = data2; - return batadv_compare_eth(data1, data2); + return (tt1->vid == tt2->vid) && batadv_compare_eth(data1, data2); } /** @@ -1427,9 +1429,15 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, } /* if the client was temporary added before receiving the first - * OGM announcing it, we have to clear the TEMP flag + * OGM announcing it, we have to clear the TEMP flag. Also, + * remove the previous temporary orig node and re-add it + * if required. If the orig entry changed, the new one which + * is a non-temporary entry is preferred. */ - common->flags &= ~BATADV_TT_CLIENT_TEMP; + if (common->flags & BATADV_TT_CLIENT_TEMP) { + batadv_tt_global_del_orig_list(tt_global_entry); + common->flags &= ~BATADV_TT_CLIENT_TEMP; + } /* the change can carry possible "attribute" flags like the * TT_CLIENT_WIFI, therefore they have to be copied in the diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index fe129663bd3f..f52bcbf2e58c 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -526,6 +526,9 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, if (!addr || addr->sa_family != AF_BLUETOOTH) return -EINVAL; + if (addr_len < sizeof(struct sockaddr_sco)) + return -EINVAL; + lock_sock(sk); if (sk->sk_state != BT_OPEN) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 152b9c70e252..b2df375ec9c2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3643,7 +3643,8 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb, serr->ee.ee_info = tstype; if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; - if (sk->sk_protocol == IPPROTO_TCP) + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) serr->ee.ee_data -= sk->sk_tskey; } @@ -4268,7 +4269,7 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) return NULL; } - memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len, + memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len - VLAN_HLEN, 2 * ETH_ALEN); skb->mac_header += VLAN_HLEN; return skb; diff --git a/net/core/sock.c b/net/core/sock.c index e31dfcee1729..0d91f7dca751 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -433,8 +433,6 @@ static bool sock_needs_netstamp(const struct sock *sk) } } -#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) - static void sock_disable_timestamp(struct sock *sk, unsigned long flags) { if (sk->sk_flags & flags) { @@ -874,7 +872,8 @@ set_rcvbuf: if (val & SOF_TIMESTAMPING_OPT_ID && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { - if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) { if (sk->sk_state != TCP_ESTABLISHED) { ret = -EINVAL; break; @@ -1552,7 +1551,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) */ is_charged = sk_filter_charge(newsk, filter); - if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk))) { + if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ newsk->sk_destruct = NULL; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index eebf5ac8ce18..13d6b1a6e0fc 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -678,6 +678,9 @@ static int dn_create(struct net *net, struct socket *sock, int protocol, { struct sock *sk; + if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + return -EINVAL; + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 11c4ca13ec3b..5c5db6636704 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -257,6 +257,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol, int try_loading_module = 0; int err; + if (protocol < 0 || protocol >= IPPROTO_MAX) + return -EINVAL; + sock->state = SS_UNCONNECTED; /* Look for the requested type/protocol pair. */ diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index cc8f3e506cde..473447593060 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1155,6 +1155,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info; struct in_device *in_dev; struct net *net = dev_net(dev); unsigned int flags; @@ -1193,6 +1194,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo case NETDEV_CHANGEMTU: rt_cache_flush(net); break; + case NETDEV_CHANGEUPPER: + info = ptr; + /* flush all routes if dev is linked to or unlinked from + * an L3 master device (e.g., VRF) + */ + if (info->upper_dev && netif_is_l3_master(info->upper_dev)) + fib_disable_ip(dev, NETDEV_DOWN, true); + break; } return NOTIFY_DONE; } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index e0fcbbbcfe54..bd903fe0f750 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -24,6 +24,7 @@ struct fou { u16 type; struct udp_offload udp_offloads; struct list_head list; + struct rcu_head rcu; }; #define FOU_F_REMCSUM_NOPARTIAL BIT(0) @@ -417,7 +418,7 @@ static void fou_release(struct fou *fou) list_del(&fou->list); udp_tunnel_sock_release(sock); - kfree(fou); + kfree_rcu(fou, rcu); } static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg) diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index a35584176535..c187c60e3e0c 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -60,6 +60,7 @@ config NFT_REJECT_IPV4 config NFT_DUP_IPV4 tristate "IPv4 nf_tables packet duplication support" + depends on !NF_CONNTRACK || NF_CONNTRACK select NF_DUP_IPV4 help This module enables IPv4 packet duplication support for nf_tables. diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index db003438aaf5..d8841a2f1569 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1493,7 +1493,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb) if (likely(sk->sk_rx_dst)) skb_dst_drop(skb); else - skb_dst_force(skb); + skb_dst_force_safe(skb); __skb_queue_tail(&tp->ucopy.prequeue, skb); tp->ucopy.memory += skb->truesize; @@ -1721,8 +1721,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - if (dst) { - dst_hold(dst); + if (dst && dst_hold_safe(dst)) { sk->sk_rx_dst = dst; inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index cb7ca569052c..9bfc39ff2285 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3150,7 +3150,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; - int syn_loss = 0, space, err = 0, copied; + int syn_loss = 0, space, err = 0; unsigned long last_syn_loss = 0; struct sk_buff *syn_data; @@ -3188,17 +3188,18 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) goto fallback; syn_data->ip_summed = CHECKSUM_PARTIAL; memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); - copied = copy_from_iter(skb_put(syn_data, space), space, - &fo->data->msg_iter); - if (unlikely(!copied)) { - kfree_skb(syn_data); - goto fallback; + if (space) { + int copied = copy_from_iter(skb_put(syn_data, space), space, + &fo->data->msg_iter); + if (unlikely(!copied)) { + kfree_skb(syn_data); + goto fallback; + } + if (copied != space) { + skb_trim(syn_data, copied); + space = copied; + } } - if (copied != space) { - skb_trim(syn_data, copied); - space = copied; - } - /* No more data pending in inet_wait_for_connect() */ if (space == fo->size) fo->data = NULL; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 61f26851655c..17f8e7ea133b 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -350,6 +350,12 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) setup_timer(&ndev->rs_timer, addrconf_rs_timer, (unsigned long)ndev); memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf)); + + if (ndev->cnf.stable_secret.initialized) + ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + else + ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64; + ndev->cnf.mtu6 = dev->mtu; ndev->cnf.sysctl = NULL; ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); @@ -2455,7 +2461,7 @@ ok: #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (in6_dev->cnf.optimistic_dad && !net->ipv6.devconf_all->forwarding && sllao) - addr_flags = IFA_F_OPTIMISTIC; + addr_flags |= IFA_F_OPTIMISTIC; #endif /* Do not allow to create too much of autoconfigured diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 8ec0df75f1c4..9f5137cd604e 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -109,6 +109,9 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol, int try_loading_module = 0; int err; + if (protocol < 0 || protocol >= IPPROTO_MAX) + return -EINVAL; + /* Look for the requested type/protocol pair. */ lookup_protocol: err = -ESOCKTNOSUPPORT; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 3c7b9310b33f..e5ea177d34c6 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1571,13 +1571,11 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], return -EEXIST; } else { t = nt; - - ip6gre_tunnel_unlink(ign, t); - ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]); - ip6gre_tunnel_link(ign, t); - netdev_state_change(dev); } + ip6gre_tunnel_unlink(ign, t); + ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]); + ip6gre_tunnel_link(ign, t); return 0; } diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index f6a024e141e5..e10a04c9cdc7 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -49,6 +49,7 @@ config NFT_REJECT_IPV6 config NFT_DUP_IPV6 tristate "IPv6 nf_tables packet duplication support" + depends on !NF_CONNTRACK || NF_CONNTRACK select NF_DUP_IPV6 help This module enables IPv6 packet duplication support for nf_tables. diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e7aab561b7b4..6b8a8a9091fa 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -93,10 +93,9 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - if (dst) { + if (dst && dst_hold_safe(dst)) { const struct rt6_info *rt = (const struct rt6_info *)dst; - dst_hold(dst); sk->sk_rx_dst = dst; inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index e6aa48b5395c..923abd6b3064 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1086,6 +1086,9 @@ static int irda_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; struct irda_sock *self; + if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + return -EINVAL; + if (net != &init_net) return -EAFNOSUPPORT; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index da471eef07bb..c12f348138ac 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1169,8 +1169,7 @@ static int sta_apply_parameters(struct ieee80211_local *local, * rc isn't initialized here yet, so ignore it */ __ieee80211_vht_handle_opmode(sdata, sta, - params->opmode_notif, - band, false); + params->opmode_notif, band); } if (ieee80211_vif_is_mesh(&sdata->vif)) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index d832bd59236b..5322b4c71630 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1709,10 +1709,10 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta); void ieee80211_sta_set_rx_nss(struct sta_info *sta); u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, u8 opmode, - enum ieee80211_band band, bool nss_only); + enum ieee80211_band band); void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, u8 opmode, - enum ieee80211_band band, bool nss_only); + enum ieee80211_band band); void ieee80211_apply_vhtcap_overrides(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta_vht_cap *vht_cap); void ieee80211_get_vht_mask_from_cap(__le16 vht_cap, diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index b140cc6651f4..3aa04344942b 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1379,21 +1379,26 @@ static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, */ if (has_80211h_pwr && (!has_cisco_pwr || pwr_level_80211h <= pwr_level_cisco)) { + new_ap_level = pwr_level_80211h; + + if (sdata->ap_power_level == new_ap_level) + return 0; + sdata_dbg(sdata, "Limiting TX power to %d (%d - %d) dBm as advertised by %pM\n", pwr_level_80211h, chan_pwr, pwr_reduction_80211h, sdata->u.mgd.bssid); - new_ap_level = pwr_level_80211h; } else { /* has_cisco_pwr is always true here. */ + new_ap_level = pwr_level_cisco; + + if (sdata->ap_power_level == new_ap_level) + return 0; + sdata_dbg(sdata, "Limiting TX power to %d dBm as advertised by %pM\n", pwr_level_cisco, sdata->u.mgd.bssid); - new_ap_level = pwr_level_cisco; } - if (sdata->ap_power_level == new_ap_level) - return 0; - sdata->ap_power_level = new_ap_level; if (__ieee80211_recalc_txpower(sdata)) return BSS_CHANGED_TXPOWER; @@ -3575,7 +3580,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (sta && elems.opmode_notif) ieee80211_vht_handle_opmode(sdata, sta, *elems.opmode_notif, - rx_status->band, true); + rx_status->band); mutex_unlock(&local->sta_mtx); changed |= ieee80211_handle_pwr_constr(sdata, chan, mgmt, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 8bae5de0dc44..82af407fea7a 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2736,8 +2736,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) opmode = mgmt->u.action.u.vht_opmode_notif.operating_mode; ieee80211_vht_handle_opmode(rx->sdata, rx->sta, - opmode, status->band, - false); + opmode, status->band); goto handled; } default: diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 74058020b7d6..33344f5a66a8 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1641,6 +1641,29 @@ void ieee80211_stop_device(struct ieee80211_local *local) drv_stop(local); } +static void ieee80211_flush_completed_scan(struct ieee80211_local *local, + bool aborted) +{ + /* It's possible that we don't handle the scan completion in + * time during suspend, so if it's still marked as completed + * here, queue the work and flush it to clean things up. + * Instead of calling the worker function directly here, we + * really queue it to avoid potential races with other flows + * scheduling the same work. + */ + if (test_bit(SCAN_COMPLETED, &local->scanning)) { + /* If coming from reconfiguration failure, abort the scan so + * we don't attempt to continue a partial HW scan - which is + * possible otherwise if (e.g.) the 2.4 GHz portion was the + * completed scan, and a 5 GHz portion is still pending. + */ + if (aborted) + set_bit(SCAN_ABORTED, &local->scanning); + ieee80211_queue_delayed_work(&local->hw, &local->scan_work, 0); + flush_delayed_work(&local->scan_work); + } +} + static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; @@ -1660,6 +1683,8 @@ static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local) local->suspended = false; local->in_reconfig = false; + ieee80211_flush_completed_scan(local, true); + /* scheduled scan clearly can't be running any more, but tell * cfg80211 and clear local state */ @@ -1698,6 +1723,27 @@ static void ieee80211_assign_chanctx(struct ieee80211_local *local, mutex_unlock(&local->chanctx_mtx); } +static void ieee80211_reconfig_stations(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + + /* add STAs back */ + mutex_lock(&local->sta_mtx); + list_for_each_entry(sta, &local->sta_list, list) { + enum ieee80211_sta_state state; + + if (!sta->uploaded || sta->sdata != sdata) + continue; + + for (state = IEEE80211_STA_NOTEXIST; + state < sta->sta_state; state++) + WARN_ON(drv_sta_state(local, sta->sdata, sta, state, + state + 1)); + } + mutex_unlock(&local->sta_mtx); +} + int ieee80211_reconfig(struct ieee80211_local *local) { struct ieee80211_hw *hw = &local->hw; @@ -1833,50 +1879,11 @@ int ieee80211_reconfig(struct ieee80211_local *local) WARN_ON(drv_add_chanctx(local, ctx)); mutex_unlock(&local->chanctx_mtx); - list_for_each_entry(sdata, &local->interfaces, list) { - if (!ieee80211_sdata_running(sdata)) - continue; - ieee80211_assign_chanctx(local, sdata); - } - sdata = rtnl_dereference(local->monitor_sdata); if (sdata && ieee80211_sdata_running(sdata)) ieee80211_assign_chanctx(local, sdata); } - /* add STAs back */ - mutex_lock(&local->sta_mtx); - list_for_each_entry(sta, &local->sta_list, list) { - enum ieee80211_sta_state state; - - if (!sta->uploaded) - continue; - - /* AP-mode stations will be added later */ - if (sta->sdata->vif.type == NL80211_IFTYPE_AP) - continue; - - for (state = IEEE80211_STA_NOTEXIST; - state < sta->sta_state; state++) - WARN_ON(drv_sta_state(local, sta->sdata, sta, state, - state + 1)); - } - mutex_unlock(&local->sta_mtx); - - /* reconfigure tx conf */ - if (hw->queues >= IEEE80211_NUM_ACS) { - list_for_each_entry(sdata, &local->interfaces, list) { - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN || - sdata->vif.type == NL80211_IFTYPE_MONITOR || - !ieee80211_sdata_running(sdata)) - continue; - - for (i = 0; i < IEEE80211_NUM_ACS; i++) - drv_conf_tx(local, sdata, i, - &sdata->tx_conf[i]); - } - } - /* reconfigure hardware */ ieee80211_hw_config(local, ~0); @@ -1889,6 +1896,22 @@ int ieee80211_reconfig(struct ieee80211_local *local) if (!ieee80211_sdata_running(sdata)) continue; + ieee80211_assign_chanctx(local, sdata); + + switch (sdata->vif.type) { + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_MONITOR: + break; + default: + ieee80211_reconfig_stations(sdata); + /* fall through */ + case NL80211_IFTYPE_AP: /* AP stations are handled later */ + for (i = 0; i < IEEE80211_NUM_ACS; i++) + drv_conf_tx(local, sdata, i, + &sdata->tx_conf[i]); + break; + } + /* common change flags for all interface types */ changed = BSS_CHANGED_ERP_CTS_PROT | BSS_CHANGED_ERP_PREAMBLE | @@ -2074,17 +2097,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) mb(); local->resuming = false; - /* It's possible that we don't handle the scan completion in - * time during suspend, so if it's still marked as completed - * here, queue the work and flush it to clean things up. - * Instead of calling the worker function directly here, we - * really queue it to avoid potential races with other flows - * scheduling the same work. - */ - if (test_bit(SCAN_COMPLETED, &local->scanning)) { - ieee80211_queue_delayed_work(&local->hw, &local->scan_work, 0); - flush_delayed_work(&local->scan_work); - } + ieee80211_flush_completed_scan(local, false); if (local->open_count && !reconfig_due_to_wowlan) drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_SUSPEND); diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index ff1c798921a6..c38b2f07a919 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -378,7 +378,7 @@ void ieee80211_sta_set_rx_nss(struct sta_info *sta) u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, u8 opmode, - enum ieee80211_band band, bool nss_only) + enum ieee80211_band band) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; @@ -401,9 +401,6 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, changed |= IEEE80211_RC_NSS_CHANGED; } - if (nss_only) - return changed; - switch (opmode & IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK) { case IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ: sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_20; @@ -430,13 +427,12 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, u8 opmode, - enum ieee80211_band band, bool nss_only) + enum ieee80211_band band) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band]; - u32 changed = __ieee80211_vht_handle_opmode(sdata, sta, opmode, - band, nss_only); + u32 changed = __ieee80211_vht_handle_opmode(sdata, sta, opmode, band); if (changed > 0) rate_control_rate_update(local, sband, sta, changed); diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index c70d750148b6..c32fc411a911 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -27,6 +27,8 @@ */ #define MAX_MP_SELECT_LABELS 4 +#define MPLS_NEIGH_TABLE_UNSPEC (NEIGH_LINK_TABLE + 1) + static int zero = 0; static int label_limit = (1 << 20) - 1; @@ -317,7 +319,13 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, } } - err = neigh_xmit(nh->nh_via_table, out_dev, mpls_nh_via(rt, nh), skb); + /* If via wasn't specified then send out using device address */ + if (nh->nh_via_table == MPLS_NEIGH_TABLE_UNSPEC) + err = neigh_xmit(NEIGH_LINK_TABLE, out_dev, + out_dev->dev_addr, skb); + else + err = neigh_xmit(nh->nh_via_table, out_dev, + mpls_nh_via(rt, nh), skb); if (err) net_dbg_ratelimited("%s: packet transmission failed: %d\n", __func__, err); @@ -534,6 +542,10 @@ static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt, if (!mpls_dev_get(dev)) goto errout; + if ((nh->nh_via_table == NEIGH_LINK_TABLE) && + (dev->addr_len != nh->nh_via_alen)) + goto errout; + RCU_INIT_POINTER(nh->nh_dev, dev); return 0; @@ -592,10 +604,14 @@ static int mpls_nh_build(struct net *net, struct mpls_route *rt, goto errout; } - err = nla_get_via(via, &nh->nh_via_alen, &nh->nh_via_table, - __mpls_nh_via(rt, nh)); - if (err) - goto errout; + if (via) { + err = nla_get_via(via, &nh->nh_via_alen, &nh->nh_via_table, + __mpls_nh_via(rt, nh)); + if (err) + goto errout; + } else { + nh->nh_via_table = MPLS_NEIGH_TABLE_UNSPEC; + } err = mpls_nh_assign_dev(net, rt, nh, oif); if (err) @@ -677,9 +693,6 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg, nla_newdst = nla_find(attrs, attrlen, RTA_NEWDST); } - if (!nla_via) - goto errout; - err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh, rtnh->rtnh_ifindex, nla_via, nla_newdst); @@ -1118,6 +1131,7 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->rc_label = LABEL_NOT_SPECIFIED; cfg->rc_protocol = rtm->rtm_protocol; + cfg->rc_via_table = MPLS_NEIGH_TABLE_UNSPEC; cfg->rc_nlflags = nlh->nlmsg_flags; cfg->rc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->rc_nlinfo.nlh = nlh; @@ -1231,7 +1245,8 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_labels(skb, RTA_NEWDST, nh->nh_labels, nh->nh_label)) goto nla_put_failure; - if (nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), + if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC && + nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; dev = rtnl_dereference(nh->nh_dev); @@ -1257,7 +1272,8 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, nh->nh_labels, nh->nh_label)) goto nla_put_failure; - if (nla_put_via(skb, nh->nh_via_table, + if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC && + nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; @@ -1319,7 +1335,8 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt) if (nh->nh_dev) payload += nla_total_size(4); /* RTA_OIF */ - payload += nla_total_size(2 + nh->nh_via_alen); /* RTA_VIA */ + if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC) /* RTA_VIA */ + payload += nla_total_size(2 + nh->nh_via_alen); if (nh->nh_labels) /* RTA_NEWDST */ payload += nla_total_size(nh->nh_labels * 4); } else { @@ -1328,7 +1345,9 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt) for_nexthops(rt) { nhsize += nla_total_size(sizeof(struct rtnexthop)); - nhsize += nla_total_size(2 + nh->nh_via_alen); + /* RTA_VIA */ + if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC) + nhsize += nla_total_size(2 + nh->nh_via_alen); if (nh->nh_labels) nhsize += nla_total_size(nh->nh_labels * 4); } endfor_nexthops(rt); diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 67591aef9cae..64afd3d0b144 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -54,10 +54,10 @@ int mpls_output(struct net *net, struct sock *sk, struct sk_buff *skb) unsigned int ttl; /* Obtain the ttl */ - if (skb->protocol == htons(ETH_P_IP)) { + if (dst->ops->family == AF_INET) { ttl = ip_hdr(skb)->ttl; rt = (struct rtable *)dst; - } else if (skb->protocol == htons(ETH_P_IPV6)) { + } else if (dst->ops->family == AF_INET6) { ttl = ipv6_hdr(skb)->hop_limit; rt6 = (struct rt6_info *)dst; } else { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 93cc4737018f..2cb429d34c03 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -89,6 +89,7 @@ nf_tables_afinfo_lookup(struct net *net, int family, bool autoload) } static void nft_ctx_init(struct nft_ctx *ctx, + struct net *net, const struct sk_buff *skb, const struct nlmsghdr *nlh, struct nft_af_info *afi, @@ -96,7 +97,7 @@ static void nft_ctx_init(struct nft_ctx *ctx, struct nft_chain *chain, const struct nlattr * const *nla) { - ctx->net = sock_net(skb->sk); + ctx->net = net; ctx->afi = afi; ctx->table = table; ctx->chain = chain; @@ -672,15 +673,14 @@ err: return ret; } -static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_newtable(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nlattr *name; struct nft_af_info *afi; struct nft_table *table; - struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; u32 flags = 0; struct nft_ctx ctx; @@ -706,7 +706,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla); return nf_tables_updtable(&ctx); } @@ -730,7 +730,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, INIT_LIST_HEAD(&table->sets); table->flags = flags; - nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla); err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); if (err < 0) goto err3; @@ -810,18 +810,17 @@ out: return err; } -static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_deltable(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_af_info *afi; struct nft_table *table; - struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nft_ctx ctx; - nft_ctx_init(&ctx, skb, nlh, NULL, NULL, NULL, nla); + nft_ctx_init(&ctx, net, skb, nlh, NULL, NULL, NULL, nla); if (family == AF_UNSPEC || nla[NFTA_TABLE_NAME] == NULL) return nft_flush(&ctx, family); @@ -1221,8 +1220,8 @@ static void nf_tables_chain_destroy(struct nft_chain *chain) } } -static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_newchain(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); @@ -1232,7 +1231,6 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, struct nft_chain *chain; struct nft_base_chain *basechain = NULL; struct nlattr *ha[NFTA_HOOK_MAX + 1]; - struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct net_device *dev = NULL; u8 policy = NF_ACCEPT; @@ -1313,7 +1311,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, return PTR_ERR(stats); } - nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla); trans = nft_trans_alloc(&ctx, NFT_MSG_NEWCHAIN, sizeof(struct nft_trans_chain)); if (trans == NULL) { @@ -1461,7 +1459,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, if (err < 0) goto err1; - nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla); err = nft_trans_chain_add(&ctx, NFT_MSG_NEWCHAIN); if (err < 0) goto err2; @@ -1476,15 +1474,14 @@ err1: return err; } -static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_delchain(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_af_info *afi; struct nft_table *table; struct nft_chain *chain; - struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nft_ctx ctx; @@ -1506,7 +1503,7 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb, if (chain->use > 0) return -EBUSY; - nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla); return nft_delchain(&ctx); } @@ -2010,13 +2007,12 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, static struct nft_expr_info *info; -static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_newrule(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_af_info *afi; - struct net *net = sock_net(skb->sk); struct nft_table *table; struct nft_chain *chain; struct nft_rule *rule, *old_rule = NULL; @@ -2075,7 +2071,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, return PTR_ERR(old_rule); } - nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla); n = 0; size = 0; @@ -2176,13 +2172,12 @@ err1: return err; } -static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_delrule(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_af_info *afi; - struct net *net = sock_net(skb->sk); struct nft_table *table; struct nft_chain *chain = NULL; struct nft_rule *rule; @@ -2205,7 +2200,7 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb, return PTR_ERR(chain); } - nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla); if (chain) { if (nla[NFTA_RULE_HANDLE]) { @@ -2344,12 +2339,11 @@ static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { [NFTA_SET_DESC_SIZE] = { .type = NLA_U32 }, }; -static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, +static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { - struct net *net = sock_net(skb->sk); const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_af_info *afi = NULL; struct nft_table *table = NULL; @@ -2371,7 +2365,7 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, return -ENOENT; } - nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla); + nft_ctx_init(ctx, net, skb, nlh, afi, table, NULL, nla); return 0; } @@ -2623,6 +2617,7 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { + struct net *net = sock_net(skb->sk); const struct nft_set *set; struct nft_ctx ctx; struct sk_buff *skb2; @@ -2630,7 +2625,7 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb, int err; /* Verify existence before starting dump */ - err = nft_ctx_init_from_setattr(&ctx, skb, nlh, nla); + err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla); if (err < 0) return err; @@ -2693,14 +2688,13 @@ static int nf_tables_set_desc_parse(const struct nft_ctx *ctx, return 0; } -static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_newset(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nft_set_ops *ops; struct nft_af_info *afi; - struct net *net = sock_net(skb->sk); struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; @@ -2798,7 +2792,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, if (IS_ERR(table)) return PTR_ERR(table); - nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla); set = nf_tables_set_lookup(table, nla[NFTA_SET_NAME]); if (IS_ERR(set)) { @@ -2882,8 +2876,8 @@ static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set nft_set_destroy(set); } -static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_delset(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); @@ -2896,7 +2890,7 @@ static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb, if (nla[NFTA_SET_TABLE] == NULL) return -EINVAL; - err = nft_ctx_init_from_setattr(&ctx, skb, nlh, nla); + err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla); if (err < 0) return err; @@ -3024,7 +3018,7 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + [NFTA_SET_ELEM_LIST_SET_ID] = { .type = NLA_U32 }, }; -static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, +static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -3033,7 +3027,6 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_af_info *afi; struct nft_table *table; - struct net *net = sock_net(skb->sk); afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false); if (IS_ERR(afi)) @@ -3045,7 +3038,7 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, if (!trans && (table->flags & NFT_TABLE_INACTIVE)) return -ENOENT; - nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla); + nft_ctx_init(ctx, net, skb, nlh, afi, table, NULL, nla); return 0; } @@ -3135,6 +3128,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); const struct nft_set *set; struct nft_set_dump_args args; struct nft_ctx ctx; @@ -3150,8 +3144,8 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) if (err < 0) return err; - err = nft_ctx_init_from_elemattr(&ctx, cb->skb, cb->nlh, (void *)nla, - false); + err = nft_ctx_init_from_elemattr(&ctx, net, cb->skb, cb->nlh, + (void *)nla, false); if (err < 0) return err; @@ -3212,11 +3206,12 @@ static int nf_tables_getsetelem(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { + struct net *net = sock_net(skb->sk); const struct nft_set *set; struct nft_ctx ctx; int err; - err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, false); if (err < 0) return err; @@ -3528,11 +3523,10 @@ err1: return err; } -static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { - struct net *net = sock_net(skb->sk); const struct nlattr *attr; struct nft_set *set; struct nft_ctx ctx; @@ -3541,7 +3535,7 @@ static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb, if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) return -EINVAL; - err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, true); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, true); if (err < 0) return err; @@ -3623,8 +3617,8 @@ err1: return err; } -static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, +static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nlattr *attr; @@ -3635,7 +3629,7 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb, if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) return -EINVAL; - err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, false); if (err < 0) return err; @@ -4030,7 +4024,8 @@ static int nf_tables_abort(struct sk_buff *skb) struct nft_trans *trans, *next; struct nft_trans_elem *te; - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list, + list) { switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 46453ab318db..77afe913d03d 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -295,8 +295,6 @@ replay: if (!skb) return netlink_ack(oskb, nlh, -ENOMEM); - skb->sk = oskb->sk; - nfnl_lock(subsys_id); ss = rcu_dereference_protected(table[subsys_id].subsys, lockdep_is_held(&table[subsys_id].mutex)); @@ -381,7 +379,7 @@ replay: goto ack; if (nc->call_batch) { - err = nc->call_batch(net->nfnl, skb, nlh, + err = nc->call_batch(net, net->nfnl, skb, nlh, (const struct nlattr **)cda); } diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 7d81d280cb4f..861c6615253b 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -365,8 +365,9 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, break; } + nfnl_ct = rcu_dereference(nfnl_ct_hook); + if (queue->flags & NFQA_CFG_F_CONNTRACK) { - nfnl_ct = rcu_dereference(nfnl_ct_hook); if (nfnl_ct != NULL) { ct = nfnl_ct->get_ct(entskb, &ctinfo); if (ct != NULL) @@ -1064,9 +1065,10 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, if (entry == NULL) return -ENOENT; + /* rcu lock already held from nfnl->call_rcu. */ + nfnl_ct = rcu_dereference(nfnl_ct_hook); + if (nfqa[NFQA_CT]) { - /* rcu lock already held from nfnl->call_rcu. */ - nfnl_ct = rcu_dereference(nfnl_ct_hook); if (nfnl_ct != NULL) ct = nfqnl_ct_parse(nfnl_ct, nlh, nfqa, entry, &ctinfo); } @@ -1417,6 +1419,7 @@ static int __init nfnetlink_queue_init(void) cleanup_netlink_notifier: netlink_unregister_notifier(&nfqnl_rtnl_notifier); + unregister_pernet_subsys(&nfnl_queue_net_ops); out: return status; } diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c2cc11168fd5..3e8892216f94 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -53,6 +53,8 @@ struct ovs_conntrack_info { struct md_labels labels; }; +static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info); + static u16 key_to_nfproto(const struct sw_flow_key *key) { switch (ntohs(key->eth.type)) { @@ -141,6 +143,7 @@ static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, * previously sent the packet to conntrack via the ct action. */ static void ovs_ct_update_key(const struct sk_buff *skb, + const struct ovs_conntrack_info *info, struct sw_flow_key *key, bool post_ct) { const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; @@ -158,13 +161,15 @@ static void ovs_ct_update_key(const struct sk_buff *skb, zone = nf_ct_zone(ct); } else if (post_ct) { state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID; + if (info) + zone = &info->zone; } __ovs_ct_update_key(key, state, zone, ct); } void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) { - ovs_ct_update_key(skb, key, false); + ovs_ct_update_key(skb, NULL, key, false); } int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb) @@ -418,7 +423,7 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, } } - ovs_ct_update_key(skb, key, true); + ovs_ct_update_key(skb, info, key, true); return 0; } @@ -708,7 +713,7 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, nf_conntrack_get(&ct_info.ct->ct_general); return 0; err_free_ct: - nf_conntrack_free(ct_info.ct); + __ovs_ct_free_action(&ct_info); return err; } @@ -750,6 +755,11 @@ void ovs_ct_free_action(const struct nlattr *a) { struct ovs_conntrack_info *ct_info = nla_data(a); + __ovs_ct_free_action(ct_info); +} + +static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info) +{ if (ct_info->helper) module_put(ct_info->helper->me); if (ct_info->ct) diff --git a/net/rfkill/core.c b/net/rfkill/core.c index b41e9ea2ffff..f53bf3b6558b 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -49,7 +49,6 @@ struct rfkill { spinlock_t lock; - const char *name; enum rfkill_type type; unsigned long state; @@ -73,6 +72,7 @@ struct rfkill { struct delayed_work poll_work; struct work_struct uevent_work; struct work_struct sync_work; + char name[]; }; #define to_rfkill(d) container_of(d, struct rfkill, dev) @@ -876,14 +876,14 @@ struct rfkill * __must_check rfkill_alloc(const char *name, if (WARN_ON(type == RFKILL_TYPE_ALL || type >= NUM_RFKILL_TYPES)) return NULL; - rfkill = kzalloc(sizeof(*rfkill), GFP_KERNEL); + rfkill = kzalloc(sizeof(*rfkill) + strlen(name) + 1, GFP_KERNEL); if (!rfkill) return NULL; spin_lock_init(&rfkill->lock); INIT_LIST_HEAD(&rfkill->node); rfkill->type = type; - rfkill->name = name; + strcpy(rfkill->name, name); rfkill->ops = ops; rfkill->data = ops_data; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 7ec667dd4ce1..b5c2cf2aa6d4 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -950,7 +950,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, } lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock); if (!netif_is_multiqueue(dev)) - sch->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + sch->flags |= TCQ_F_ONETXQUEUE; } sch->handle = handle; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index acb45b8c2a9d..ec529121f38a 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -323,14 +323,13 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, } } } - rcu_read_unlock(); - if (baddr) { fl6->saddr = baddr->v6.sin6_addr; fl6->fl6_sport = baddr->v6.sin6_port; final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); dst = ip6_dst_lookup_flow(sk, fl6, final_p); } + rcu_read_unlock(); out: if (!IS_ERR_OR_NULL(dst)) { @@ -642,6 +641,7 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, struct sock *newsk; struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct sctp6_sock *newsctp6sk; + struct ipv6_txoptions *opt; newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, 0); if (!newsk) @@ -661,6 +661,13 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); + rcu_read_lock(); + opt = rcu_dereference(np->opt); + if (opt) + opt = ipv6_dup_options(newsk, opt); + RCU_INIT_POINTER(newnp->opt, opt); + rcu_read_unlock(); + /* Initialize sk's sport, dport, rcv_saddr and daddr for getsockname() * and getpeername(). */ diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 7e8f0a117106..c0380cfb16ae 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -324,6 +324,7 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk) sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk"); + sctp_chunk_hold(chunk); sctp_outq_tail_data(q, chunk); if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS); @@ -1251,6 +1252,7 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) */ sack_a_rwnd = ntohl(sack->a_rwnd); + asoc->peer.zero_window_announced = !sack_a_rwnd; outstanding = q->outstanding_bytes; if (outstanding < sack_a_rwnd) diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 763e06a55155..5d6a03fad378 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1652,7 +1652,7 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep, /* Set an expiration time for the cookie. */ cookie->c.expiration = ktime_add(asoc->cookie_life, - ktime_get()); + ktime_get_real()); /* Copy the peer's init packet. */ memcpy(&cookie->c.peer_init[0], init_chunk->chunk_hdr, @@ -1780,7 +1780,7 @@ no_hmac: if (sock_flag(ep->base.sk, SOCK_TIMESTAMP)) kt = skb_get_ktime(skb); else - kt = ktime_get(); + kt = ktime_get_real(); if (!asoc && ktime_before(bear_cookie->expiration, kt)) { /* diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 6f46aa16cb76..cd34a4a34065 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -5412,7 +5412,8 @@ sctp_disposition_t sctp_sf_do_6_3_3_rtx(struct net *net, SCTP_INC_STATS(net, SCTP_MIB_T3_RTX_EXPIREDS); if (asoc->overall_error_count >= asoc->max_retrans) { - if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING) { + if (asoc->peer.zero_window_announced && + asoc->state == SCTP_STATE_SHUTDOWN_PENDING) { /* * We are here likely because the receiver had its rwnd * closed for a while and we have not been able to diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 03c8256063ec..9b6cc6de80d8 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1952,8 +1952,6 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) /* Now send the (possibly) fragmented message. */ list_for_each_entry(chunk, &datamsg->chunks, frag_list) { - sctp_chunk_hold(chunk); - /* Do accounting for the write space. */ sctp_set_owner_w(chunk); @@ -1966,15 +1964,13 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) * breaks. */ err = sctp_primitive_SEND(net, asoc, datamsg); + sctp_datamsg_put(datamsg); /* Did the lower layer accept the chunk? */ - if (err) { - sctp_datamsg_free(datamsg); + if (err) goto out_free; - } pr_debug("%s: we sent primitively\n", __func__); - sctp_datamsg_put(datamsg); err = msg_len; if (unlikely(wait_connect)) { @@ -7167,6 +7163,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newsk->sk_type = sk->sk_type; newsk->sk_bound_dev_if = sk->sk_bound_dev_if; newsk->sk_flags = sk->sk_flags; + newsk->sk_tsflags = sk->sk_tsflags; newsk->sk_no_check_tx = sk->sk_no_check_tx; newsk->sk_no_check_rx = sk->sk_no_check_rx; newsk->sk_reuse = sk->sk_reuse; @@ -7199,6 +7196,9 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->mc_ttl = 1; newinet->mc_index = 0; newinet->mc_list = NULL; + + if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) + net_enable_timestamp(); } static inline void sctp_copy_descendant(struct sock *sk_to, diff --git a/net/socket.c b/net/socket.c index 456fadb3d819..29822d6dd91e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1695,6 +1695,7 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, msg.msg_name = addr ? (struct sockaddr *)&address : NULL; /* We assume all kernel code knows the size of sockaddr_storage */ msg.msg_namelen = 0; + msg.msg_iocb = NULL; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, iov_iter_count(&msg.msg_iter), flags); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 45aebd966978..a4631477cedf 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2256,14 +2256,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg */ - err = mutex_lock_interruptible(&u->readlock); - if (unlikely(err)) { - /* recvmsg() in non blocking mode is supposed to return -EAGAIN - * sk_rcvtimeo is not honored by mutex_lock_interruptible() - */ - err = noblock ? -EAGAIN : -ERESTARTSYS; - goto out; - } + mutex_lock(&u->readlock); if (flags & MSG_PEEK) skip = sk_peek_offset(sk, flags); @@ -2307,12 +2300,12 @@ again: timeo = unix_stream_data_wait(sk, timeo, last, last_len); - if (signal_pending(current) || - mutex_lock_interruptible(&u->readlock)) { + if (signal_pending(current)) { err = sock_intr_errno(timeo); goto out; } + mutex_lock(&u->readlock); continue; unlock: unix_state_unlock(sk); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c71e274c810a..75b0d23ee882 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -7941,8 +7941,10 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) if (nla_get_flag(info->attrs[NL80211_ATTR_USE_RRM])) { if (!(rdev->wiphy.features & NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES) || - !(rdev->wiphy.features & NL80211_FEATURE_QUIET)) + !(rdev->wiphy.features & NL80211_FEATURE_QUIET)) { + kzfree(connkeys); return -EINVAL; + } connect.flags |= ASSOC_REQ_USE_RRM; } @@ -9503,6 +9505,7 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) if (new_triggers.tcp && new_triggers.tcp->sock) sock_release(new_triggers.tcp->sock); kfree(new_triggers.tcp); + kfree(new_triggers.nd_config); return err; } #endif diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 2e8d6f39ed56..06d050da0d94 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -3029,6 +3029,7 @@ int set_regdom(const struct ieee80211_regdomain *rd, break; default: WARN(1, "invalid initiator %d\n", lr->initiator); + kfree(rd); return -EINVAL; } @@ -3221,8 +3222,10 @@ int __init regulatory_init(void) /* We always try to get an update for the static regdomain */ err = regulatory_hint_core(cfg80211_world_regdom->alpha2); if (err) { - if (err == -ENOMEM) + if (err == -ENOMEM) { + platform_device_unregister(reg_pdev); return err; + } /* * N.B. kobject_uevent_env() can fail mainly for when we're out * memory which is handled and propagated appropriately above diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 09bfcbac63bb..948fa5560de5 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -303,6 +303,14 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) } EXPORT_SYMBOL(xfrm_policy_alloc); +static void xfrm_policy_destroy_rcu(struct rcu_head *head) +{ + struct xfrm_policy *policy = container_of(head, struct xfrm_policy, rcu); + + security_xfrm_policy_free(policy->security); + kfree(policy); +} + /* Destroy xfrm_policy: descendant resources must be released to this moment. */ void xfrm_policy_destroy(struct xfrm_policy *policy) @@ -312,8 +320,7 @@ void xfrm_policy_destroy(struct xfrm_policy *policy) if (del_timer(&policy->timer) || del_timer(&policy->polq.hold_timer)) BUG(); - security_xfrm_policy_free(policy->security); - kfree(policy); + call_rcu(&policy->rcu, xfrm_policy_destroy_rcu); } EXPORT_SYMBOL(xfrm_policy_destroy); @@ -1214,8 +1221,10 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, struct xfrm_policy *pol; struct net *net = sock_net(sk); + rcu_read_lock(); read_lock_bh(&net->xfrm.xfrm_policy_lock); - if ((pol = sk->sk_policy[dir]) != NULL) { + pol = rcu_dereference(sk->sk_policy[dir]); + if (pol != NULL) { bool match = xfrm_selector_match(&pol->selector, fl, sk->sk_family); int err = 0; @@ -1239,6 +1248,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, } out: read_unlock_bh(&net->xfrm.xfrm_policy_lock); + rcu_read_unlock(); return pol; } @@ -1307,13 +1317,14 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) #endif write_lock_bh(&net->xfrm.xfrm_policy_lock); - old_pol = sk->sk_policy[dir]; - sk->sk_policy[dir] = pol; + old_pol = rcu_dereference_protected(sk->sk_policy[dir], + lockdep_is_held(&net->xfrm.xfrm_policy_lock)); if (pol) { pol->curlft.add_time = get_seconds(); pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0); xfrm_sk_policy_link(pol, dir); } + rcu_assign_pointer(sk->sk_policy[dir], pol); if (old_pol) { if (pol) xfrm_policy_requeue(old_pol, pol); @@ -1361,17 +1372,26 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) return newp; } -int __xfrm_sk_clone_policy(struct sock *sk) +int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { - struct xfrm_policy *p0 = sk->sk_policy[0], - *p1 = sk->sk_policy[1]; + const struct xfrm_policy *p; + struct xfrm_policy *np; + int i, ret = 0; - sk->sk_policy[0] = sk->sk_policy[1] = NULL; - if (p0 && (sk->sk_policy[0] = clone_policy(p0, 0)) == NULL) - return -ENOMEM; - if (p1 && (sk->sk_policy[1] = clone_policy(p1, 1)) == NULL) - return -ENOMEM; - return 0; + rcu_read_lock(); + for (i = 0; i < 2; i++) { + p = rcu_dereference(osk->sk_policy[i]); + if (p) { + np = clone_policy(p, i); + if (unlikely(!np)) { + ret = -ENOMEM; + break; + } + rcu_assign_pointer(sk->sk_policy[i], np); + } + } + rcu_read_unlock(); + return ret; } static int @@ -2198,6 +2218,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, xdst = NULL; route = NULL; + sk = sk_const_to_full_sk(sk); if (sk && sk->sk_policy[XFRM_POLICY_OUT]) { num_pols = 1; pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl); @@ -2477,6 +2498,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } pol = NULL; + sk = sk_to_full_sk(sk); if (sk && sk->sk_policy[dir]) { pol = xfrm_sk_policy_lookup(sk, dir, &fl); if (IS_ERR(pol)) {