diff options
47 files changed, 494 insertions, 241 deletions
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index a90d7364334f..f7fbdc9d1325 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -262,9 +262,9 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata, if (likely(skb)) { (*pkts_compl)++; (*bytes_compl) += skb->len; + dev_kfree_skb_any(skb); } - dev_kfree_skb_any(skb); tx_buf->first_bd = 0; tx_buf->skb = NULL; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 76b9052a961c..5907c821d131 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -1718,6 +1718,22 @@ static int bnx2x_nvram_write(struct bnx2x *bp, u32 offset, u8 *data_buf, offset += sizeof(u32); data_buf += sizeof(u32); written_so_far += sizeof(u32); + + /* At end of each 4Kb page, release nvram lock to allow MFW + * chance to take it for its own use. + */ + if ((cmd_flags & MCPR_NVM_COMMAND_LAST) && + (written_so_far < buf_size)) { + DP(BNX2X_MSG_ETHTOOL | BNX2X_MSG_NVM, + "Releasing NVM lock after offset 0x%x\n", + (u32)(offset - sizeof(u32))); + bnx2x_release_nvram_lock(bp); + usleep_range(1000, 2000); + rc = bnx2x_acquire_nvram_lock(bp); + if (rc) + return rc; + } + cmd_flags = 0; } diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index 0612b19f6313..506047c38607 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -676,6 +676,7 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget) if (!next_cmpl->valid) break; } + packets++; /* TODO: BNA_CQ_EF_LOCAL ? */ if (unlikely(flags & (BNA_CQ_EF_MAC_ERROR | @@ -692,7 +693,6 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget) else bnad_cq_setup_skb_frags(rcb, skb, sop_ci, nvecs, len); - packets++; rcb->rxq->rx_packets++; rcb->rxq->rx_bytes += totlen; ccb->bytes_per_intr += totlen; diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index c4d6bbe9458d..02e23e6f1424 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -16,7 +16,6 @@ if NET_VENDOR_CAVIUM config THUNDER_NIC_PF tristate "Thunder Physical function driver" depends on 64BIT - default ARCH_THUNDER select THUNDER_NIC_BGX ---help--- This driver supports Thunder's NIC physical function. @@ -29,14 +28,12 @@ config THUNDER_NIC_PF config THUNDER_NIC_VF tristate "Thunder Virtual function driver" depends on 64BIT - default ARCH_THUNDER ---help--- This driver supports Thunder's NIC virtual function config THUNDER_NIC_BGX tristate "Thunder MAC interface driver (BGX)" depends on 64BIT - default ARCH_THUNDER ---help--- This driver supports programming and controlling of MAC interface from NIC physical function driver. diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index a11485fbb33f..c3c7db41819d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -2332,10 +2332,11 @@ int t4_setup_debugfs(struct adapter *adap) EXT_MEM1_SIZE_G(size)); } } else { - if (i & EXT_MEM_ENABLE_F) + if (i & EXT_MEM_ENABLE_F) { size = t4_read_reg(adap, MA_EXT_MEMORY_BAR_A); add_debugfs_mem(adap, "mc", MEM_MC, EXT_MEM_SIZE_G(size)); + } } de = debugfs_create_file_size("flash", S_IRUSR, adap->debugfs_root, adap, diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 2716e6f30d9a..00e3a6b6b822 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -620,6 +620,11 @@ enum be_if_flags { BE_IF_FLAGS_VLAN_PROMISCUOUS |\ BE_IF_FLAGS_MCAST_PROMISCUOUS) +#define BE_IF_EN_FLAGS (BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_PASS_L3L4_ERRORS |\ + BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_UNTAGGED) + +#define BE_IF_ALL_FILT_FLAGS (BE_IF_EN_FLAGS | BE_IF_FLAGS_ALL_PROMISCUOUS) + /* An RX interface is an object with one or more MAC addresses and * filtering capabilities. */ struct be_cmd_req_if_create { diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 6f642426308c..c28e3bfdccd7 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -273,6 +273,10 @@ static int be_mac_addr_set(struct net_device *netdev, void *p) if (ether_addr_equal(addr->sa_data, netdev->dev_addr)) return 0; + /* if device is not running, copy MAC to netdev->dev_addr */ + if (!netif_running(netdev)) + goto done; + /* The PMAC_ADD cmd may fail if the VF doesn't have FILTMGMT * privilege or if PF did not provision the new MAC address. * On BE3, this cmd will always fail if the VF doesn't have the @@ -307,9 +311,9 @@ static int be_mac_addr_set(struct net_device *netdev, void *p) status = -EPERM; goto err; } - - memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); - dev_info(dev, "MAC address changed to %pM\n", mac); +done: + ether_addr_copy(netdev->dev_addr, addr->sa_data); + dev_info(dev, "MAC address changed to %pM\n", addr->sa_data); return 0; err: dev_warn(dev, "MAC address change to %pM failed\n", addr->sa_data); @@ -2447,10 +2451,24 @@ static void be_eq_clean(struct be_eq_obj *eqo) be_eq_notify(eqo->adapter, eqo->q.id, false, true, num, 0); } -static void be_rx_cq_clean(struct be_rx_obj *rxo) +/* Free posted rx buffers that were not used */ +static void be_rxq_clean(struct be_rx_obj *rxo) { - struct be_rx_page_info *page_info; struct be_queue_info *rxq = &rxo->q; + struct be_rx_page_info *page_info; + + while (atomic_read(&rxq->used) > 0) { + page_info = get_rx_page_info(rxo); + put_page(page_info->page); + memset(page_info, 0, sizeof(*page_info)); + } + BUG_ON(atomic_read(&rxq->used)); + rxq->tail = 0; + rxq->head = 0; +} + +static void be_rx_cq_clean(struct be_rx_obj *rxo) +{ struct be_queue_info *rx_cq = &rxo->cq; struct be_rx_compl_info *rxcp; struct be_adapter *adapter = rxo->adapter; @@ -2487,16 +2505,6 @@ static void be_rx_cq_clean(struct be_rx_obj *rxo) /* After cleanup, leave the CQ in unarmed state */ be_cq_notify(adapter, rx_cq->id, false, 0); - - /* Then free posted rx buffers that were not used */ - while (atomic_read(&rxq->used) > 0) { - page_info = get_rx_page_info(rxo); - put_page(page_info->page); - memset(page_info, 0, sizeof(*page_info)); - } - BUG_ON(atomic_read(&rxq->used)); - rxq->tail = 0; - rxq->head = 0; } static void be_tx_compl_clean(struct be_adapter *adapter) @@ -2576,8 +2584,8 @@ static void be_evt_queues_destroy(struct be_adapter *adapter) be_cmd_q_destroy(adapter, &eqo->q, QTYPE_EQ); napi_hash_del(&eqo->napi); netif_napi_del(&eqo->napi); + free_cpumask_var(eqo->affinity_mask); } - free_cpumask_var(eqo->affinity_mask); be_queue_free(adapter, &eqo->q); } } @@ -2594,13 +2602,7 @@ static int be_evt_queues_create(struct be_adapter *adapter) for_all_evt_queues(adapter, eqo, i) { int numa_node = dev_to_node(&adapter->pdev->dev); - if (!zalloc_cpumask_var(&eqo->affinity_mask, GFP_KERNEL)) - return -ENOMEM; - cpumask_set_cpu(cpumask_local_spread(i, numa_node), - eqo->affinity_mask); - netif_napi_add(adapter->netdev, &eqo->napi, be_poll, - BE_NAPI_WEIGHT); - napi_hash_add(&eqo->napi); + aic = &adapter->aic_obj[i]; eqo->adapter = adapter; eqo->idx = i; @@ -2616,6 +2618,14 @@ static int be_evt_queues_create(struct be_adapter *adapter) rc = be_cmd_eq_create(adapter, eqo); if (rc) return rc; + + if (!zalloc_cpumask_var(&eqo->affinity_mask, GFP_KERNEL)) + return -ENOMEM; + cpumask_set_cpu(cpumask_local_spread(i, numa_node), + eqo->affinity_mask); + netif_napi_add(adapter->netdev, &eqo->napi, be_poll, + BE_NAPI_WEIGHT); + napi_hash_add(&eqo->napi); } return 0; } @@ -3354,13 +3364,54 @@ static void be_rx_qs_destroy(struct be_adapter *adapter) for_all_rx_queues(adapter, rxo, i) { q = &rxo->q; if (q->created) { + /* If RXQs are destroyed while in an "out of buffer" + * state, there is a possibility of an HW stall on + * Lancer. So, post 64 buffers to each queue to relieve + * the "out of buffer" condition. + * Make sure there's space in the RXQ before posting. + */ + if (lancer_chip(adapter)) { + be_rx_cq_clean(rxo); + if (atomic_read(&q->used) == 0) + be_post_rx_frags(rxo, GFP_KERNEL, + MAX_RX_POST); + } + be_cmd_rxq_destroy(adapter, q); be_rx_cq_clean(rxo); + be_rxq_clean(rxo); } be_queue_free(adapter, q); } } +static void be_disable_if_filters(struct be_adapter *adapter) +{ + be_cmd_pmac_del(adapter, adapter->if_handle, + adapter->pmac_id[0], 0); + + be_clear_uc_list(adapter); + + /* The IFACE flags are enabled in the open path and cleared + * in the close path. When a VF gets detached from the host and + * assigned to a VM the following happens: + * - VF's IFACE flags get cleared in the detach path + * - IFACE create is issued by the VF in the attach path + * Due to a bug in the BE3/Skyhawk-R FW + * (Lancer FW doesn't have the bug), the IFACE capability flags + * specified along with the IFACE create cmd issued by a VF are not + * honoured by FW. As a consequence, if a *new* driver + * (that enables/disables IFACE flags in open/close) + * is loaded in the host and an *old* driver is * used by a VM/VF, + * the IFACE gets created *without* the needed flags. + * To avoid this, disable RX-filter flags only for Lancer. + */ + if (lancer_chip(adapter)) { + be_cmd_rx_filter(adapter, BE_IF_ALL_FILT_FLAGS, OFF); + adapter->if_flags &= ~BE_IF_ALL_FILT_FLAGS; + } +} + static int be_close(struct net_device *netdev) { struct be_adapter *adapter = netdev_priv(netdev); @@ -3373,6 +3424,8 @@ static int be_close(struct net_device *netdev) if (!(adapter->flags & BE_FLAGS_SETUP_DONE)) return 0; + be_disable_if_filters(adapter); + be_roce_dev_close(adapter); if (adapter->flags & BE_FLAGS_NAPI_ENABLED) { @@ -3392,7 +3445,6 @@ static int be_close(struct net_device *netdev) be_tx_compl_clean(adapter); be_rx_qs_destroy(adapter); - be_clear_uc_list(adapter); for_all_evt_queues(adapter, eqo, i) { if (msix_enabled(adapter)) @@ -3477,6 +3529,31 @@ static int be_rx_qs_create(struct be_adapter *adapter) return 0; } +static int be_enable_if_filters(struct be_adapter *adapter) +{ + int status; + + status = be_cmd_rx_filter(adapter, BE_IF_EN_FLAGS, ON); + if (status) + return status; + + /* For BE3 VFs, the PF programs the initial MAC address */ + if (!(BEx_chip(adapter) && be_virtfn(adapter))) { + status = be_cmd_pmac_add(adapter, adapter->netdev->dev_addr, + adapter->if_handle, + &adapter->pmac_id[0], 0); + if (status) + return status; + } + + if (adapter->vlans_added) + be_vid_config(adapter); + + be_set_rx_mode(adapter->netdev); + + return 0; +} + static int be_open(struct net_device *netdev) { struct be_adapter *adapter = netdev_priv(netdev); @@ -3490,6 +3567,10 @@ static int be_open(struct net_device *netdev) if (status) goto err; + status = be_enable_if_filters(adapter); + if (status) + goto err; + status = be_irq_register(adapter); if (status) goto err; @@ -3686,16 +3767,6 @@ static void be_cancel_err_detection(struct be_adapter *adapter) } } -static void be_mac_clear(struct be_adapter *adapter) -{ - if (adapter->pmac_id) { - be_cmd_pmac_del(adapter, adapter->if_handle, - adapter->pmac_id[0], 0); - kfree(adapter->pmac_id); - adapter->pmac_id = NULL; - } -} - #ifdef CONFIG_BE2NET_VXLAN static void be_disable_vxlan_offloads(struct be_adapter *adapter) { @@ -3770,8 +3841,8 @@ static int be_clear(struct be_adapter *adapter) #ifdef CONFIG_BE2NET_VXLAN be_disable_vxlan_offloads(adapter); #endif - /* delete the primary mac along with the uc-mac list */ - be_mac_clear(adapter); + kfree(adapter->pmac_id); + adapter->pmac_id = NULL; be_cmd_if_destroy(adapter, adapter->if_handle, 0); @@ -3782,25 +3853,11 @@ static int be_clear(struct be_adapter *adapter) return 0; } -static int be_if_create(struct be_adapter *adapter, u32 *if_handle, - u32 cap_flags, u32 vf) -{ - u32 en_flags; - - en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST | - BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS | - BE_IF_FLAGS_RSS | BE_IF_FLAGS_DEFQ_RSS; - - en_flags &= cap_flags; - - return be_cmd_if_create(adapter, cap_flags, en_flags, if_handle, vf); -} - static int be_vfs_if_create(struct be_adapter *adapter) { struct be_resources res = {0}; + u32 cap_flags, en_flags, vf; struct be_vf_cfg *vf_cfg; - u32 cap_flags, vf; int status; /* If a FW profile exists, then cap_flags are updated */ @@ -3821,8 +3878,12 @@ static int be_vfs_if_create(struct be_adapter *adapter) } } - status = be_if_create(adapter, &vf_cfg->if_handle, - cap_flags, vf + 1); + en_flags = cap_flags & (BE_IF_FLAGS_UNTAGGED | + BE_IF_FLAGS_BROADCAST | + BE_IF_FLAGS_MULTICAST | + BE_IF_FLAGS_PASS_L3L4_ERRORS); + status = be_cmd_if_create(adapter, cap_flags, en_flags, + &vf_cfg->if_handle, vf + 1); if (status) return status; } @@ -4194,15 +4255,8 @@ static int be_mac_setup(struct be_adapter *adapter) memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN); memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN); - } else { - /* Maybe the HW was reset; dev_addr must be re-programmed */ - memcpy(mac, adapter->netdev->dev_addr, ETH_ALEN); } - /* For BE3-R VFs, the PF programs the initial MAC address */ - if (!(BEx_chip(adapter) && be_virtfn(adapter))) - be_cmd_pmac_add(adapter, mac, adapter->if_handle, - &adapter->pmac_id[0], 0); return 0; } @@ -4342,6 +4396,7 @@ static int be_func_init(struct be_adapter *adapter) static int be_setup(struct be_adapter *adapter) { struct device *dev = &adapter->pdev->dev; + u32 en_flags; int status; status = be_func_init(adapter); @@ -4364,8 +4419,11 @@ static int be_setup(struct be_adapter *adapter) if (status) goto err; - status = be_if_create(adapter, &adapter->if_handle, - be_if_cap_flags(adapter), 0); + /* will enable all the needed filter flags in be_open() */ + en_flags = BE_IF_FLAGS_RSS | BE_IF_FLAGS_DEFQ_RSS; + en_flags = en_flags & be_if_cap_flags(adapter); + status = be_cmd_if_create(adapter, be_if_cap_flags(adapter), en_flags, + &adapter->if_handle, 0); if (status) goto err; @@ -4391,11 +4449,6 @@ static int be_setup(struct be_adapter *adapter) dev_err(dev, "Please upgrade firmware to version >= 4.0\n"); } - if (adapter->vlans_added) - be_vid_config(adapter); - - be_set_rx_mode(adapter->netdev); - status = be_cmd_set_flow_control(adapter, adapter->tx_fc, adapter->rx_fc); if (status) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 32e3807c650e..271bb5862346 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3433,6 +3433,7 @@ fec_probe(struct platform_device *pdev) pm_runtime_set_autosuspend_delay(&pdev->dev, FEC_MDIO_PM_TIMEOUT); pm_runtime_use_autosuspend(&pdev->dev); + pm_runtime_get_noresume(&pdev->dev); pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index 56316db6c5a6..cf8e54652df9 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -586,7 +586,8 @@ static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) frag = skb_shinfo(skb)->frags; while (nr_frags) { CBDC_SC(bdp, - BD_ENET_TX_STATS | BD_ENET_TX_LAST | BD_ENET_TX_TC); + BD_ENET_TX_STATS | BD_ENET_TX_INTR | BD_ENET_TX_LAST | + BD_ENET_TX_TC); CBDS_SC(bdp, BD_ENET_TX_READY); if ((CBDR_SC(bdp) & BD_ENET_TX_WRAP) == 0) diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c index b34214e2df5f..016743e355de 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c @@ -110,7 +110,7 @@ static int do_pd_setup(struct fs_enet_private *fep) } #define FEC_NAPI_RX_EVENT_MSK (FEC_ENET_RXF | FEC_ENET_RXB) -#define FEC_NAPI_TX_EVENT_MSK (FEC_ENET_TXF | FEC_ENET_TXB) +#define FEC_NAPI_TX_EVENT_MSK (FEC_ENET_TXF) #define FEC_RX_EVENT (FEC_ENET_RXF) #define FEC_TX_EVENT (FEC_ENET_TXF) #define FEC_ERR_EVENT_MSK (FEC_ENET_HBERR | FEC_ENET_BABR | \ diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 3e8b1bfb1f2e..d9884fd15b45 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -27,6 +27,8 @@ #include <linux/of_address.h> #include <linux/phy.h> #include <linux/clk.h> +#include <linux/hrtimer.h> +#include <linux/ktime.h> #include <uapi/linux/ppp_defs.h> #include <net/ip.h> #include <net/ipv6.h> @@ -299,6 +301,7 @@ /* Coalescing */ #define MVPP2_TXDONE_COAL_PKTS_THRESH 15 +#define MVPP2_TXDONE_HRTIMER_PERIOD_NS 1000000UL #define MVPP2_RX_COAL_PKTS 32 #define MVPP2_RX_COAL_USEC 100 @@ -660,6 +663,14 @@ struct mvpp2_pcpu_stats { u64 tx_bytes; }; +/* Per-CPU port control */ +struct mvpp2_port_pcpu { + struct hrtimer tx_done_timer; + bool timer_scheduled; + /* Tasklet for egress finalization */ + struct tasklet_struct tx_done_tasklet; +}; + struct mvpp2_port { u8 id; @@ -679,6 +690,9 @@ struct mvpp2_port { u32 pending_cause_rx; struct napi_struct napi; + /* Per-CPU port control */ + struct mvpp2_port_pcpu __percpu *pcpu; + /* Flags */ unsigned long flags; @@ -776,6 +790,9 @@ struct mvpp2_txq_pcpu { /* Array of transmitted skb */ struct sk_buff **tx_skb; + /* Array of transmitted buffers' physical addresses */ + dma_addr_t *tx_buffs; + /* Index of last TX DMA descriptor that was inserted */ int txq_put_index; @@ -913,8 +930,6 @@ struct mvpp2_bm_pool { /* Occupied buffers indicator */ atomic_t in_use; int in_use_thresh; - - spinlock_t lock; }; struct mvpp2_buff_hdr { @@ -963,9 +978,13 @@ static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu) } static void mvpp2_txq_inc_put(struct mvpp2_txq_pcpu *txq_pcpu, - struct sk_buff *skb) + struct sk_buff *skb, + struct mvpp2_tx_desc *tx_desc) { txq_pcpu->tx_skb[txq_pcpu->txq_put_index] = skb; + if (skb) + txq_pcpu->tx_buffs[txq_pcpu->txq_put_index] = + tx_desc->buf_phys_addr; txq_pcpu->txq_put_index++; if (txq_pcpu->txq_put_index == txq_pcpu->size) txq_pcpu->txq_put_index = 0; @@ -3376,7 +3395,6 @@ static int mvpp2_bm_pool_create(struct platform_device *pdev, bm_pool->pkt_size = 0; bm_pool->buf_num = 0; atomic_set(&bm_pool->in_use, 0); - spin_lock_init(&bm_pool->lock); return 0; } @@ -3647,7 +3665,6 @@ static struct mvpp2_bm_pool * mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type, int pkt_size) { - unsigned long flags = 0; struct mvpp2_bm_pool *new_pool = &port->priv->bm_pools[pool]; int num; @@ -3656,8 +3673,6 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type, return NULL; } - spin_lock_irqsave(&new_pool->lock, flags); - if (new_pool->type == MVPP2_BM_FREE) new_pool->type = type; @@ -3686,8 +3701,6 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type, if (num != pkts_num) { WARN(1, "pool %d: %d of %d allocated\n", new_pool->id, num, pkts_num); - /* We need to undo the bufs_add() allocations */ - spin_unlock_irqrestore(&new_pool->lock, flags); return NULL; } } @@ -3695,15 +3708,12 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type, mvpp2_bm_pool_bufsize_set(port->priv, new_pool, MVPP2_RX_BUF_SIZE(new_pool->pkt_size)); - spin_unlock_irqrestore(&new_pool->lock, flags); - return new_pool; } /* Initialize pools for swf */ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) { - unsigned long flags = 0; int rxq; if (!port->pool_long) { @@ -3714,9 +3724,7 @@ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) if (!port->pool_long) return -ENOMEM; - spin_lock_irqsave(&port->pool_long->lock, flags); port->pool_long->port_map |= (1 << port->id); - spin_unlock_irqrestore(&port->pool_long->lock, flags); for (rxq = 0; rxq < rxq_number; rxq++) mvpp2_rxq_long_pool_set(port, rxq, port->pool_long->id); @@ -3730,9 +3738,7 @@ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) if (!port->pool_short) return -ENOMEM; - spin_lock_irqsave(&port->pool_short->lock, flags); port->pool_short->port_map |= (1 << port->id); - spin_unlock_irqrestore(&port->pool_short->lock, flags); for (rxq = 0; rxq < rxq_number; rxq++) mvpp2_rxq_short_pool_set(port, rxq, @@ -3806,7 +3812,6 @@ static void mvpp2_interrupts_unmask(void *arg) mvpp2_write(port->priv, MVPP2_ISR_RX_TX_MASK_REG(port->id), (MVPP2_CAUSE_MISC_SUM_MASK | - MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK | MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK)); } @@ -4382,23 +4387,6 @@ static void mvpp2_rx_time_coal_set(struct mvpp2_port *port, rxq->time_coal = usec; } -/* Set threshold for TX_DONE pkts coalescing */ -static void mvpp2_tx_done_pkts_coal_set(void *arg) -{ - struct mvpp2_port *port = arg; - int queue; - u32 val; - - for (queue = 0; queue < txq_number; queue++) { - struct mvpp2_tx_queue *txq = port->txqs[queue]; - - val = (txq->done_pkts_coal << MVPP2_TRANSMITTED_THRESH_OFFSET) & - MVPP2_TRANSMITTED_THRESH_MASK; - mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id); - mvpp2_write(port->priv, MVPP2_TXQ_THRESH_REG, val); - } -} - /* Free Tx queue skbuffs */ static void mvpp2_txq_bufs_free(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, @@ -4407,8 +4395,8 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port, int i; for (i = 0; i < num; i++) { - struct mvpp2_tx_desc *tx_desc = txq->descs + - txq_pcpu->txq_get_index; + dma_addr_t buf_phys_addr = + txq_pcpu->tx_buffs[txq_pcpu->txq_get_index]; struct sk_buff *skb = txq_pcpu->tx_skb[txq_pcpu->txq_get_index]; mvpp2_txq_inc_get(txq_pcpu); @@ -4416,8 +4404,8 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port, if (!skb) continue; - dma_unmap_single(port->dev->dev.parent, tx_desc->buf_phys_addr, - tx_desc->data_size, DMA_TO_DEVICE); + dma_unmap_single(port->dev->dev.parent, buf_phys_addr, + skb_headlen(skb), DMA_TO_DEVICE); dev_kfree_skb_any(skb); } } @@ -4433,7 +4421,7 @@ static inline struct mvpp2_rx_queue *mvpp2_get_rx_queue(struct mvpp2_port *port, static inline struct mvpp2_tx_queue *mvpp2_get_tx_queue(struct mvpp2_port *port, u32 cause) { - int queue = fls(cause >> 16) - 1; + int queue = fls(cause) - 1; return port->txqs[queue]; } @@ -4460,6 +4448,29 @@ static void mvpp2_txq_done(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, netif_tx_wake_queue(nq); } +static unsigned int mvpp2_tx_done(struct mvpp2_port *port, u32 cause) +{ + struct mvpp2_tx_queue *txq; + struct mvpp2_txq_pcpu *txq_pcpu; + unsigned int tx_todo = 0; + + while (cause) { + txq = mvpp2_get_tx_queue(port, cause); + if (!txq) + break; + + txq_pcpu = this_cpu_ptr(txq->pcpu); + + if (txq_pcpu->count) { + mvpp2_txq_done(port, txq, txq_pcpu); + tx_todo += txq_pcpu->count; + } + + cause &= ~(1 << txq->log_id); + } + return tx_todo; +} + /* Rx/Tx queue initialization/cleanup methods */ /* Allocate and initialize descriptors for aggr TXQ */ @@ -4649,12 +4660,13 @@ static int mvpp2_txq_init(struct mvpp2_port *port, txq_pcpu->tx_skb = kmalloc(txq_pcpu->size * sizeof(*txq_pcpu->tx_skb), GFP_KERNEL); - if (!txq_pcpu->tx_skb) { - dma_free_coherent(port->dev->dev.parent, - txq->size * MVPP2_DESC_ALIGNED_SIZE, - txq->descs, txq->descs_phys); - return -ENOMEM; - } + if (!txq_pcpu->tx_skb) + goto error; + + txq_pcpu->tx_buffs = kmalloc(txq_pcpu->size * + sizeof(dma_addr_t), GFP_KERNEL); + if (!txq_pcpu->tx_buffs) + goto error; txq_pcpu->count = 0; txq_pcpu->reserved_num = 0; @@ -4663,6 +4675,19 @@ static int mvpp2_txq_init(struct mvpp2_port *port, } return 0; + +error: + for_each_present_cpu(cpu) { + txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); + kfree(txq_pcpu->tx_skb); + kfree(txq_pcpu->tx_buffs); + } + + dma_free_coherent(port->dev->dev.parent, + txq->size * MVPP2_DESC_ALIGNED_SIZE, + txq->descs, txq->descs_phys); + + return -ENOMEM; } /* Free allocated TXQ resources */ @@ -4675,6 +4700,7 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port, for_each_present_cpu(cpu) { txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); kfree(txq_pcpu->tx_skb); + kfree(txq_pcpu->tx_buffs); } if (txq->descs) @@ -4805,7 +4831,6 @@ static int mvpp2_setup_txqs(struct mvpp2_port *port) goto err_cleanup; } - on_each_cpu(mvpp2_tx_done_pkts_coal_set, port, 1); on_each_cpu(mvpp2_txq_sent_counter_clear, port, 1); return 0; @@ -4887,6 +4912,49 @@ static void mvpp2_link_event(struct net_device *dev) } } +static void mvpp2_timer_set(struct mvpp2_port_pcpu *port_pcpu) +{ + ktime_t interval; + + if (!port_pcpu->timer_scheduled) { + port_pcpu->timer_scheduled = true; + interval = ktime_set(0, MVPP2_TXDONE_HRTIMER_PERIOD_NS); + hrtimer_start(&port_pcpu->tx_done_timer, interval, + HRTIMER_MODE_REL_PINNED); + } +} + +static void mvpp2_tx_proc_cb(unsigned long data) +{ + struct net_device *dev = (struct net_device *)data; + struct mvpp2_port *port = netdev_priv(dev); + struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu); + unsigned int tx_todo, cause; + + if (!netif_running(dev)) + return; + port_pcpu->timer_scheduled = false; + + /* Process all the Tx queues */ + cause = (1 << txq_number) - 1; + tx_todo = mvpp2_tx_done(port, cause); + + /* Set the timer in case not all the packets were processed */ + if (tx_todo) + mvpp2_timer_set(port_pcpu); +} + +static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer) +{ + struct mvpp2_port_pcpu *port_pcpu = container_of(timer, + struct mvpp2_port_pcpu, + tx_done_timer); + + tasklet_schedule(&port_pcpu->tx_done_tasklet); + + return HRTIMER_NORESTART; +} + /* Main RX/TX processing routines */ /* Display more error info */ @@ -5144,11 +5212,11 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb, if (i == (skb_shinfo(skb)->nr_frags - 1)) { /* Last descriptor */ tx_desc->command = MVPP2_TXD_L_DESC; - mvpp2_txq_inc_put(txq_pcpu, skb); + mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc); } else { /* Descriptor in the middle: Not First, Not Last */ tx_desc->command = 0; - mvpp2_txq_inc_put(txq_pcpu, NULL); + mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc); } } @@ -5214,12 +5282,12 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev) /* First and Last descriptor */ tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_L_DESC; tx_desc->command = tx_cmd; - mvpp2_txq_inc_put(txq_pcpu, skb); + mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc); } else { /* First but not Last */ tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_PADDING_DISABLE; tx_desc->command = tx_cmd; - mvpp2_txq_inc_put(txq_pcpu, NULL); + mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc); /* Continue with other skb fragments */ if (mvpp2_tx_frag_process(port, skb, aggr_txq, txq)) { @@ -5255,6 +5323,17 @@ out: dev_kfree_skb_any(skb); } + /* Finalize TX processing */ + if (txq_pcpu->count >= txq->done_pkts_coal) + mvpp2_txq_done(port, txq, txq_pcpu); + + /* Set the timer in case not all frags were processed */ + if (txq_pcpu->count <= frags && txq_pcpu->count > 0) { + struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu); + + mvpp2_timer_set(port_pcpu); + } + return NETDEV_TX_OK; } @@ -5268,10 +5347,11 @@ static inline void mvpp2_cause_error(struct net_device *dev, int cause) netdev_err(dev, "tx fifo underrun error\n"); } -static void mvpp2_txq_done_percpu(void *arg) +static int mvpp2_poll(struct napi_struct *napi, int budget) { - struct mvpp2_port *port = arg; - u32 cause_rx_tx, cause_tx, cause_misc; + u32 cause_rx_tx, cause_rx, cause_misc; + int rx_done = 0; + struct mvpp2_port *port = netdev_priv(napi->dev); /* Rx/Tx cause register * @@ -5285,7 +5365,7 @@ static void mvpp2_txq_done_percpu(void *arg) */ cause_rx_tx = mvpp2_read(port->priv, MVPP2_ISR_RX_TX_CAUSE_REG(port->id)); - cause_tx = cause_rx_tx & MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK; + cause_rx_tx &= ~MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK; cause_misc = cause_rx_tx & MVPP2_CAUSE_MISC_SUM_MASK; if (cause_misc) { @@ -5297,26 +5377,6 @@ static void mvpp2_txq_done_percpu(void *arg) cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK); } - /* Release TX descriptors */ - if (cause_tx) { - struct mvpp2_tx_queue *txq = mvpp2_get_tx_queue(port, cause_tx); - struct mvpp2_txq_pcpu *txq_pcpu = this_cpu_ptr(txq->pcpu); - - if (txq_pcpu->count) - mvpp2_txq_done(port, txq, txq_pcpu); - } -} - -static int mvpp2_poll(struct napi_struct *napi, int budget) -{ - u32 cause_rx_tx, cause_rx; - int rx_done = 0; - struct mvpp2_port *port = netdev_priv(napi->dev); - - on_each_cpu(mvpp2_txq_done_percpu, port, 1); - - cause_rx_tx = mvpp2_read(port->priv, - MVPP2_ISR_RX_TX_CAUSE_REG(port->id)); cause_rx = cause_rx_tx & MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK; /* Process RX packets */ @@ -5561,6 +5621,8 @@ err_cleanup_rxqs: static int mvpp2_stop(struct net_device *dev) { struct mvpp2_port *port = netdev_priv(dev); + struct mvpp2_port_pcpu *port_pcpu; + int cpu; mvpp2_stop_dev(port); mvpp2_phy_disconnect(port); @@ -5569,6 +5631,13 @@ static int mvpp2_stop(struct net_device *dev) on_each_cpu(mvpp2_interrupts_mask, port, 1); free_irq(port->irq, port); + for_each_present_cpu(cpu) { + port_pcpu = per_cpu_ptr(port->pcpu, cpu); + + hrtimer_cancel(&port_pcpu->tx_done_timer); + port_pcpu->timer_scheduled = false; + tasklet_kill(&port_pcpu->tx_done_tasklet); + } mvpp2_cleanup_rxqs(port); mvpp2_cleanup_txqs(port); @@ -5784,7 +5853,6 @@ static int mvpp2_ethtool_set_coalesce(struct net_device *dev, txq->done_pkts_coal = c->tx_max_coalesced_frames; } - on_each_cpu(mvpp2_tx_done_pkts_coal_set, port, 1); return 0; } @@ -6035,6 +6103,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, { struct device_node *phy_node; struct mvpp2_port *port; + struct mvpp2_port_pcpu *port_pcpu; struct net_device *dev; struct resource *res; const char *dt_mac_addr; @@ -6044,7 +6113,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, int features; int phy_mode; int priv_common_regs_num = 2; - int err, i; + int err, i, cpu; dev = alloc_etherdev_mqs(sizeof(struct mvpp2_port), txq_number, rxq_number); @@ -6135,6 +6204,24 @@ static int mvpp2_port_probe(struct platform_device *pdev, } mvpp2_port_power_up(port); + port->pcpu = alloc_percpu(struct mvpp2_port_pcpu); + if (!port->pcpu) { + err = -ENOMEM; + goto err_free_txq_pcpu; + } + + for_each_present_cpu(cpu) { + port_pcpu = per_cpu_ptr(port->pcpu, cpu); + + hrtimer_init(&port_pcpu->tx_done_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_PINNED); + port_pcpu->tx_done_timer.function = mvpp2_hr_timer_cb; + port_pcpu->timer_scheduled = false; + + tasklet_init(&port_pcpu->tx_done_tasklet, mvpp2_tx_proc_cb, + (unsigned long)dev); + } + netif_napi_add(dev, &port->napi, mvpp2_poll, NAPI_POLL_WEIGHT); features = NETIF_F_SG | NETIF_F_IP_CSUM; dev->features = features | NETIF_F_RXCSUM; @@ -6144,7 +6231,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, err = register_netdev(dev); if (err < 0) { dev_err(&pdev->dev, "failed to register netdev\n"); - goto err_free_txq_pcpu; + goto err_free_port_pcpu; } netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr); @@ -6153,6 +6240,8 @@ static int mvpp2_port_probe(struct platform_device *pdev, priv->port_list[id] = port; return 0; +err_free_port_pcpu: + free_percpu(port->pcpu); err_free_txq_pcpu: for (i = 0; i < txq_number; i++) free_percpu(port->txqs[i]->pcpu); @@ -6171,6 +6260,7 @@ static void mvpp2_port_remove(struct mvpp2_port *port) int i; unregister_netdev(port->dev); + free_percpu(port->pcpu); free_percpu(port->stats); for (i = 0; i < txq_number; i++) free_percpu(port->txqs[i]->pcpu); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index afad529838de..06e3e1e54c35 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -391,6 +391,8 @@ static int handle_hca_cap(struct mlx5_core_dev *dev) /* disable cmdif checksum */ MLX5_SET(cmd_hca_cap, set_hca_cap, cmdif_checksum, 0); + MLX5_SET(cmd_hca_cap, set_hca_cap, log_uar_page_sz, PAGE_SHIFT - 12); + err = set_caps(dev, set_ctx, set_sz); query_ex: diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 3df51faf18ae..f790f61ea78a 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4875,10 +4875,12 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_46: case RTL_GIGA_MAC_VER_47: case RTL_GIGA_MAC_VER_48: + RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF); + break; case RTL_GIGA_MAC_VER_49: case RTL_GIGA_MAC_VER_50: case RTL_GIGA_MAC_VER_51: - RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF); + RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); break; default: RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index 7e3129e7f143..f0e4bb4e3ec5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -42,7 +42,7 @@ #define NSS_COMMON_CLK_DIV_MASK 0x7f #define NSS_COMMON_CLK_SRC_CTRL 0x14 -#define NSS_COMMON_CLK_SRC_CTRL_OFFSET(x) (1 << x) +#define NSS_COMMON_CLK_SRC_CTRL_OFFSET(x) (x) /* Mode is coded on 1 bit but is different depending on the MAC ID: * MAC0: QSGMII=0 RGMII=1 * MAC1: QSGMII=0 SGMII=0 RGMII=1 @@ -291,7 +291,7 @@ static void *ipq806x_gmac_setup(struct platform_device *pdev) /* Configure the clock src according to the mode */ regmap_read(gmac->nss_common, NSS_COMMON_CLK_SRC_CTRL, &val); - val &= ~NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id); + val &= ~(1 << NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id)); switch (gmac->phy_mode) { case PHY_INTERFACE_MODE_RGMII: val |= NSS_COMMON_CLK_SRC_CTRL_RGMII(gmac->id) << diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h index a8a730641bbb..bb1bb72121c0 100644 --- a/drivers/net/ethernet/ti/netcp.h +++ b/drivers/net/ethernet/ti/netcp.h @@ -85,7 +85,6 @@ struct netcp_intf { struct list_head rxhook_list_head; unsigned int rx_queue_id; void *rx_fdq[KNAV_DMA_FDQ_PER_CHAN]; - u32 rx_buffer_sizes[KNAV_DMA_FDQ_PER_CHAN]; struct napi_struct rx_napi; struct napi_struct tx_napi; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 9749dfd78c43..4755838c6137 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -34,6 +34,7 @@ #define NETCP_SOP_OFFSET (NET_IP_ALIGN + NET_SKB_PAD) #define NETCP_NAPI_WEIGHT 64 #define NETCP_TX_TIMEOUT (5 * HZ) +#define NETCP_PACKET_SIZE (ETH_FRAME_LEN + ETH_FCS_LEN) #define NETCP_MIN_PACKET_SIZE ETH_ZLEN #define NETCP_MAX_MCAST_ADDR 16 @@ -804,30 +805,28 @@ static void netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) if (likely(fdq == 0)) { unsigned int primary_buf_len; /* Allocate a primary receive queue entry */ - buf_len = netcp->rx_buffer_sizes[0] + NETCP_SOP_OFFSET; + buf_len = NETCP_PACKET_SIZE + NETCP_SOP_OFFSET; primary_buf_len = SKB_DATA_ALIGN(buf_len) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - if (primary_buf_len <= PAGE_SIZE) { - bufptr = netdev_alloc_frag(primary_buf_len); - pad[1] = primary_buf_len; - } else { - bufptr = kmalloc(primary_buf_len, GFP_ATOMIC | - GFP_DMA32 | __GFP_COLD); - pad[1] = 0; - } + bufptr = netdev_alloc_frag(primary_buf_len); + pad[1] = primary_buf_len; if (unlikely(!bufptr)) { - dev_warn_ratelimited(netcp->ndev_dev, "Primary RX buffer alloc failed\n"); + dev_warn_ratelimited(netcp->ndev_dev, + "Primary RX buffer alloc failed\n"); goto fail; } dma = dma_map_single(netcp->dev, bufptr, buf_len, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(netcp->dev, dma))) + goto fail; + pad[0] = (u32)bufptr; } else { /* Allocate a secondary receive queue entry */ - page = alloc_page(GFP_ATOMIC | GFP_DMA32 | __GFP_COLD); + page = alloc_page(GFP_ATOMIC | GFP_DMA | __GFP_COLD); if (unlikely(!page)) { dev_warn_ratelimited(netcp->ndev_dev, "Secondary page alloc failed\n"); goto fail; @@ -1010,7 +1009,7 @@ netcp_tx_map_skb(struct sk_buff *skb, struct netcp_intf *netcp) /* Map the linear buffer */ dma_addr = dma_map_single(dev, skb->data, pkt_len, DMA_TO_DEVICE); - if (unlikely(!dma_addr)) { + if (unlikely(dma_mapping_error(dev, dma_addr))) { dev_err(netcp->ndev_dev, "Failed to map skb buffer\n"); return NULL; } @@ -1546,8 +1545,8 @@ static int netcp_setup_navigator_resources(struct net_device *ndev) knav_queue_disable_notify(netcp->rx_queue); /* open Rx FDQs */ - for (i = 0; i < KNAV_DMA_FDQ_PER_CHAN && - netcp->rx_queue_depths[i] && netcp->rx_buffer_sizes[i]; ++i) { + for (i = 0; i < KNAV_DMA_FDQ_PER_CHAN && netcp->rx_queue_depths[i]; + ++i) { snprintf(name, sizeof(name), "rx-fdq-%s-%d", ndev->name, i); netcp->rx_fdq[i] = knav_queue_open(name, KNAV_QUEUE_GP, 0); if (IS_ERR_OR_NULL(netcp->rx_fdq[i])) { @@ -1941,14 +1940,6 @@ static int netcp_create_interface(struct netcp_device *netcp_device, netcp->rx_queue_depths[0] = 128; } - ret = of_property_read_u32_array(node_interface, "rx-buffer-size", - netcp->rx_buffer_sizes, - KNAV_DMA_FDQ_PER_CHAN); - if (ret) { - dev_err(dev, "missing \"rx-buffer-size\" parameter\n"); - netcp->rx_buffer_sizes[0] = 1536; - } - ret = of_property_read_u32_array(node_interface, "rx-pool", temp, 2); if (ret < 0) { dev_err(dev, "missing \"rx-pool\" parameter\n"); diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 2ffbf13471d0..216bfd350169 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -728,11 +728,12 @@ static int mkiss_open(struct tty_struct *tty) dev->type = ARPHRD_AX25; /* Perform the low-level AX25 initialization. */ - if ((err = ax_open(ax->dev))) { + err = ax_open(ax->dev); + if (err) goto out_free_netdev; - } - if (register_netdev(dev)) + err = register_netdev(dev); + if (err) goto out_free_buffers; /* after register_netdev() - because else printk smashes the kernel */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 7fbca37a1adf..237f8e5e493d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1756,9 +1756,9 @@ static int virtnet_probe(struct virtio_device *vdev) /* Do we support "hardware" checksums? */ if (virtio_has_feature(vdev, VIRTIO_NET_F_CSUM)) { /* This opens up the world of extra features. */ - dev->hw_features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST; + dev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_SG; if (csum) - dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST; + dev->features |= NETIF_F_HW_CSUM | NETIF_F_SG; if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) { dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO diff --git a/drivers/net/wireless/b43/tables_nphy.c b/drivers/net/wireless/b43/tables_nphy.c index 25d1cbd34306..b2f0d245bcf3 100644 --- a/drivers/net/wireless/b43/tables_nphy.c +++ b/drivers/net/wireless/b43/tables_nphy.c @@ -3728,7 +3728,7 @@ const u32 *b43_nphy_get_tx_gain_table(struct b43_wldev *dev) switch (phy->rev) { case 6: case 5: - if (sprom->fem.ghz5.extpa_gain == 3) + if (sprom->fem.ghz2.extpa_gain == 3) return b43_ntab_tx_gain_epa_rev3_hi_pwr_2g; /* fall through */ case 4: diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c index 5000bfcded61..5514ad6d4e54 100644 --- a/drivers/net/wireless/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/iwlwifi/mvm/scan.c @@ -1023,7 +1023,7 @@ static void iwl_mvm_scan_umac_dwell(struct iwl_mvm *mvm, cmd->scan_priority = iwl_mvm_scan_priority(mvm, IWL_SCAN_PRIORITY_EXT_6); - if (iwl_mvm_scan_total_iterations(params) == 0) + if (iwl_mvm_scan_total_iterations(params) == 1) cmd->ooc_priority = iwl_mvm_scan_priority(mvm, IWL_SCAN_PRIORITY_EXT_6); else diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c index 6203c4ad9bba..9e144e71da0b 100644 --- a/drivers/net/wireless/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/iwlwifi/pcie/trans.c @@ -478,10 +478,16 @@ static void iwl_pcie_apm_stop(struct iwl_trans *trans, bool op_mode_leave) if (trans->cfg->device_family == IWL_DEVICE_FAMILY_7000) iwl_set_bits_prph(trans, APMG_PCIDEV_STT_REG, APMG_PCIDEV_STT_VAL_WAKE_ME); - else if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) + else if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) { + iwl_set_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG, + CSR_RESET_LINK_PWR_MGMT_DISABLED); iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, CSR_HW_IF_CONFIG_REG_PREPARE | CSR_HW_IF_CONFIG_REG_ENABLE_PME); + mdelay(1); + iwl_clear_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG, + CSR_RESET_LINK_PWR_MGMT_DISABLED); + } mdelay(5); } @@ -575,6 +581,10 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans) if (ret >= 0) return 0; + iwl_set_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG, + CSR_RESET_LINK_PWR_MGMT_DISABLED); + msleep(1); + for (iter = 0; iter < 10; iter++) { /* If HW is not ready, prepare the conditions to check again */ iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, @@ -582,8 +592,10 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans) do { ret = iwl_pcie_set_hw_ready(trans); - if (ret >= 0) - return 0; + if (ret >= 0) { + ret = 0; + goto out; + } usleep_range(200, 1000); t += 200; @@ -593,6 +605,10 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans) IWL_ERR(trans, "Couldn't prepare the card\n"); +out: + iwl_clear_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG, + CSR_RESET_LINK_PWR_MGMT_DISABLED); + return ret; } diff --git a/drivers/net/wireless/iwlwifi/pcie/tx.c b/drivers/net/wireless/iwlwifi/pcie/tx.c index 2b86c2135de3..607acb53c847 100644 --- a/drivers/net/wireless/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/iwlwifi/pcie/tx.c @@ -1875,8 +1875,19 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb, /* start timer if queue currently empty */ if (q->read_ptr == q->write_ptr) { - if (txq->wd_timeout) - mod_timer(&txq->stuck_timer, jiffies + txq->wd_timeout); + if (txq->wd_timeout) { + /* + * If the TXQ is active, then set the timer, if not, + * set the timer in remainder so that the timer will + * be armed with the right value when the station will + * wake up. + */ + if (!txq->frozen) + mod_timer(&txq->stuck_timer, + jiffies + txq->wd_timeout); + else + txq->frozen_expiry_remainder = txq->wd_timeout; + } IWL_DEBUG_RPM(trans, "Q: %d first tx - take ref\n", q->id); iwl_trans_pcie_ref(trans); } diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c index b6cc9ff47fc2..1c6788aecc62 100644 --- a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c +++ b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c @@ -172,6 +172,7 @@ static int rsi_load_ta_instructions(struct rsi_common *common) (struct rsi_91x_sdiodev *)adapter->rsi_dev; u32 len; u32 num_blocks; + const u8 *fw; const struct firmware *fw_entry = NULL; u32 block_size = dev->tx_blk_size; int status = 0; @@ -200,6 +201,10 @@ static int rsi_load_ta_instructions(struct rsi_common *common) return status; } + /* Copy firmware into DMA-accessible memory */ + fw = kmemdup(fw_entry->data, fw_entry->size, GFP_KERNEL); + if (!fw) + return -ENOMEM; len = fw_entry->size; if (len % 4) @@ -210,7 +215,8 @@ static int rsi_load_ta_instructions(struct rsi_common *common) rsi_dbg(INIT_ZONE, "%s: Instruction size:%d\n", __func__, len); rsi_dbg(INIT_ZONE, "%s: num blocks: %d\n", __func__, num_blocks); - status = rsi_copy_to_card(common, fw_entry->data, len, num_blocks); + status = rsi_copy_to_card(common, fw, len, num_blocks); + kfree(fw); release_firmware(fw_entry); return status; } diff --git a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c index 1106ce76707e..30c2cf7fa93b 100644 --- a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c +++ b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c @@ -146,7 +146,10 @@ static int rsi_load_ta_instructions(struct rsi_common *common) return status; } + /* Copy firmware into DMA-accessible memory */ fw = kmemdup(fw_entry->data, fw_entry->size, GFP_KERNEL); + if (!fw) + return -ENOMEM; len = fw_entry->size; if (len % 4) @@ -158,6 +161,7 @@ static int rsi_load_ta_instructions(struct rsi_common *common) rsi_dbg(INIT_ZONE, "%s: num blocks: %d\n", __func__, num_blocks); status = rsi_copy_to_card(common, fw, len, num_blocks); + kfree(fw); release_firmware(fw_entry); return status; } diff --git a/drivers/net/wireless/rtlwifi/core.c b/drivers/net/wireless/rtlwifi/core.c index 3b3a88b53b11..585d0883c7e5 100644 --- a/drivers/net/wireless/rtlwifi/core.c +++ b/drivers/net/wireless/rtlwifi/core.c @@ -1015,9 +1015,12 @@ static void send_beacon_frame(struct ieee80211_hw *hw, { struct rtl_priv *rtlpriv = rtl_priv(hw); struct sk_buff *skb = ieee80211_beacon_get(hw, vif); + struct rtl_tcb_desc tcb_desc; - if (skb) - rtlpriv->intf_ops->adapter_tx(hw, NULL, skb, NULL); + if (skb) { + memset(&tcb_desc, 0, sizeof(struct rtl_tcb_desc)); + rtlpriv->intf_ops->adapter_tx(hw, NULL, skb, &tcb_desc); + } } static void rtl_op_bss_info_changed(struct ieee80211_hw *hw, diff --git a/drivers/net/wireless/rtlwifi/rtl8723be/sw.c b/drivers/net/wireless/rtlwifi/rtl8723be/sw.c index 1017f02d7bf7..7bf88d9dcdc3 100644 --- a/drivers/net/wireless/rtlwifi/rtl8723be/sw.c +++ b/drivers/net/wireless/rtlwifi/rtl8723be/sw.c @@ -385,6 +385,7 @@ module_param_named(debug, rtl8723be_mod_params.debug, int, 0444); module_param_named(ips, rtl8723be_mod_params.inactiveps, bool, 0444); module_param_named(swlps, rtl8723be_mod_params.swctrl_lps, bool, 0444); module_param_named(fwlps, rtl8723be_mod_params.fwctrl_lps, bool, 0444); +module_param_named(msi, rtl8723be_mod_params.msi_support, bool, 0444); module_param_named(disable_watchdog, rtl8723be_mod_params.disable_watchdog, bool, 0444); MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n"); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 1a83e190fc15..28577a31549d 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -61,6 +61,12 @@ void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue, void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue) { atomic_dec(&queue->inflight_packets); + + /* Wake the dealloc thread _after_ decrementing inflight_packets so + * that if kthread_stop() has already been called, the dealloc thread + * does not wait forever with nothing to wake it. + */ + wake_up(&queue->dealloc_wq); } int xenvif_schedulable(struct xenvif *vif) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 1b406e706a01..3f44b522b831 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1541,7 +1541,6 @@ void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success) smp_wmb(); queue->dealloc_prod++; } while (ubuf); - wake_up(&queue->dealloc_wq); spin_unlock_irqrestore(&queue->callback_lock, flags); if (likely(zerocopy_success)) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d6cdd6e87d53..22b6d9ca1654 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2884,11 +2884,11 @@ static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) * * PHY drivers may accept clones of transmitted packets for * timestamping via their phy_driver.txtstamp method. These drivers - * must call this function to return the skb back to the stack, with - * or without a timestamp. + * must call this function to return the skb back to the stack with a + * timestamp. * * @skb: clone of the the original outgoing packet - * @hwtstamps: hardware time stamps, may be NULL if not available + * @hwtstamps: hardware time stamps * */ void skb_complete_tx_timestamp(struct sk_buff *skb, diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index fb54e6aed096..6d0b471eede8 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1138,6 +1138,9 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, * @bat_priv: the bat priv with all the soft interface information * @skb: packet to check * @hdr_size: size of the encapsulation header + * + * Returns true if the packet was snooped and consumed by DAT. False if the + * packet has to be delivered to the interface */ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size) @@ -1145,7 +1148,7 @@ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, uint16_t type; __be32 ip_src, ip_dst; uint8_t *hw_src, *hw_dst; - bool ret = false; + bool dropped = false; unsigned short vid; if (!atomic_read(&bat_priv->distributed_arp_table)) @@ -1174,12 +1177,17 @@ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, /* if this REPLY is directed to a client of mine, let's deliver the * packet to the interface */ - ret = !batadv_is_my_client(bat_priv, hw_dst, vid); + dropped = !batadv_is_my_client(bat_priv, hw_dst, vid); + + /* if this REPLY is sent on behalf of a client of mine, let's drop the + * packet because the client will reply by itself + */ + dropped |= batadv_is_my_client(bat_priv, hw_src, vid); out: - if (ret) + if (dropped) kfree_skb(skb); - /* if ret == false -> packet has to be delivered to the interface */ - return ret; + /* if dropped == false -> deliver to the interface */ + return dropped; } /** diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index bb0158620628..cffa92dd9877 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -439,6 +439,8 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv, INIT_HLIST_NODE(&gw_node->list); gw_node->orig_node = orig_node; + gw_node->bandwidth_down = ntohl(gateway->bandwidth_down); + gw_node->bandwidth_up = ntohl(gateway->bandwidth_up); atomic_set(&gw_node->refcount, 1); spin_lock_bh(&bat_priv->gw.list_lock); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index c002961da75d..a2fc843c2243 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -479,6 +479,9 @@ out: */ void batadv_softif_vlan_free_ref(struct batadv_softif_vlan *vlan) { + if (!vlan) + return; + if (atomic_dec_and_test(&vlan->refcount)) { spin_lock_bh(&vlan->bat_priv->softif_vlan_list_lock); hlist_del_rcu(&vlan->list); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index b4824951010b..5e953297d3b2 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -594,6 +594,9 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, /* increase the refcounter of the related vlan */ vlan = batadv_softif_vlan_get(bat_priv, vid); + if (WARN(!vlan, "adding TT local entry %pM to non-existent VLAN %d", + addr, BATADV_PRINT_VID(vid))) + goto out; batadv_dbg(BATADV_DBG_TT, bat_priv, "Creating new local tt entry: %pM (vid: %d, ttvn: %d)\n", @@ -1034,6 +1037,7 @@ uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv, struct batadv_tt_local_entry *tt_local_entry; uint16_t flags, curr_flags = BATADV_NO_FLAGS; struct batadv_softif_vlan *vlan; + void *tt_entry_exists; tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid); if (!tt_local_entry) @@ -1061,11 +1065,22 @@ uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv, * immediately purge it */ batadv_tt_local_event(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL); - hlist_del_rcu(&tt_local_entry->common.hash_entry); + + tt_entry_exists = batadv_hash_remove(bat_priv->tt.local_hash, + batadv_compare_tt, + batadv_choose_tt, + &tt_local_entry->common); + if (!tt_entry_exists) + goto out; + + /* extra call to free the local tt entry */ batadv_tt_local_entry_free_ref(tt_local_entry); /* decrease the reference held for this vlan */ vlan = batadv_softif_vlan_get(bat_priv, vid); + if (!vlan) + goto out; + batadv_softif_vlan_free_ref(vlan); batadv_softif_vlan_free_ref(vlan); @@ -1166,8 +1181,10 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) /* decrease the reference held for this vlan */ vlan = batadv_softif_vlan_get(bat_priv, tt_common_entry->vid); - batadv_softif_vlan_free_ref(vlan); - batadv_softif_vlan_free_ref(vlan); + if (vlan) { + batadv_softif_vlan_free_ref(vlan); + batadv_softif_vlan_free_ref(vlan); + } batadv_tt_local_entry_free_ref(tt_local); } @@ -3207,8 +3224,10 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) /* decrease the reference held for this vlan */ vlan = batadv_softif_vlan_get(bat_priv, tt_common->vid); - batadv_softif_vlan_free_ref(vlan); - batadv_softif_vlan_free_ref(vlan); + if (vlan) { + batadv_softif_vlan_free_ref(vlan); + batadv_softif_vlan_free_ref(vlan); + } batadv_tt_local_entry_free_ref(tt_local); } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 3da5525eb8a2..4d74a0639c4c 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -112,6 +112,8 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */ + nla_total_size(1) /* IFLA_BRPORT_LEARNING */ + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */ + + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + 0; } @@ -506,6 +508,8 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 }, [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 }, [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, + [IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 }, + [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 }, }; /* Change the state of the port and notify spanning tree */ diff --git a/net/core/datagram.c b/net/core/datagram.c index 4967262b2707..617088aee21d 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -131,12 +131,12 @@ out_noerr: goto out; } -static int skb_set_peeked(struct sk_buff *skb) +static struct sk_buff *skb_set_peeked(struct sk_buff *skb) { struct sk_buff *nskb; if (skb->peeked) - return 0; + return skb; /* We have to unshare an skb before modifying it. */ if (!skb_shared(skb)) @@ -144,7 +144,7 @@ static int skb_set_peeked(struct sk_buff *skb) nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) - return -ENOMEM; + return ERR_PTR(-ENOMEM); skb->prev->next = nskb; skb->next->prev = nskb; @@ -157,7 +157,7 @@ static int skb_set_peeked(struct sk_buff *skb) done: skb->peeked = 1; - return 0; + return skb; } /** @@ -229,8 +229,9 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, continue; } - error = skb_set_peeked(skb); - if (error) + skb = skb_set_peeked(skb); + error = PTR_ERR(skb); + if (IS_ERR(skb)) goto unlock_err; atomic_inc(&skb->users); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 1ebdf1c0d118..1cbd209192ea 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3514,8 +3514,6 @@ static int pktgen_thread_worker(void *arg) set_freezable(); - __set_current_state(TASK_RUNNING); - while (!kthread_should_stop()) { pkt_dev = next_to_run(t); @@ -3560,7 +3558,6 @@ static int pktgen_thread_worker(void *arg) try_to_freeze(); } - set_current_state(TASK_INTERRUPTIBLE); pr_debug("%s stopping all device\n", t->tsk->comm); pktgen_stop(t); diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 87b22c0bc08c..b42f0e26f89e 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -103,10 +103,16 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) spin_lock_bh(&queue->syn_wait_lock); while ((req = lopt->syn_table[i]) != NULL) { lopt->syn_table[i] = req->dl_next; + /* Because of following del_timer_sync(), + * we must release the spinlock here + * or risk a dead lock. + */ + spin_unlock_bh(&queue->syn_wait_lock); atomic_inc(&lopt->qlen_dec); - if (del_timer(&req->rsk_timer)) + if (del_timer_sync(&req->rsk_timer)) reqsk_put(req); reqsk_put(req); + spin_lock_bh(&queue->syn_wait_lock); } spin_unlock_bh(&queue->syn_wait_lock); } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 60021d0d9326..05e3145f7dc3 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -593,7 +593,7 @@ static bool reqsk_queue_unlink(struct request_sock_queue *queue, } spin_unlock(&queue->syn_wait_lock); - if (del_timer(&req->rsk_timer)) + if (del_timer_sync(&req->rsk_timer)) reqsk_put(req); return found; } diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index fe8cc183411e..95ea633e8356 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -226,7 +226,8 @@ synproxy_send_client_ack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); + synproxy_send_tcp(skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + niph, nth, tcp_hdr_size); } static bool diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d7d4c2b79cf2..0ea2e1c5d395 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1348,7 +1348,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr); if (req) { nsk = tcp_check_req(sk, skb, req, false); - if (!nsk) + if (!nsk || nsk == sk) reqsk_put(req); return nsk; } diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index 6edb7b106de7..ebbb754c2111 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -37,12 +37,13 @@ synproxy_build_ip(struct sk_buff *skb, const struct in6_addr *saddr, } static void -synproxy_send_tcp(const struct sk_buff *skb, struct sk_buff *nskb, +synproxy_send_tcp(const struct synproxy_net *snet, + const struct sk_buff *skb, struct sk_buff *nskb, struct nf_conntrack *nfct, enum ip_conntrack_info ctinfo, struct ipv6hdr *niph, struct tcphdr *nth, unsigned int tcp_hdr_size) { - struct net *net = nf_ct_net((struct nf_conn *)nfct); + struct net *net = nf_ct_net(snet->tmpl); struct dst_entry *dst; struct flowi6 fl6; @@ -83,7 +84,8 @@ free_nskb: } static void -synproxy_send_client_synack(const struct sk_buff *skb, const struct tcphdr *th, +synproxy_send_client_synack(const struct synproxy_net *snet, + const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) { struct sk_buff *nskb; @@ -119,7 +121,7 @@ synproxy_send_client_synack(const struct sk_buff *skb, const struct tcphdr *th, synproxy_build_options(nth, opts); - synproxy_send_tcp(skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size); } @@ -163,7 +165,7 @@ synproxy_send_server_syn(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, + synproxy_send_tcp(snet, skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, niph, nth, tcp_hdr_size); } @@ -203,7 +205,7 @@ synproxy_send_server_ack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); + synproxy_send_tcp(snet, skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); } static void @@ -241,7 +243,8 @@ synproxy_send_client_ack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); + synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + niph, nth, tcp_hdr_size); } static bool @@ -301,7 +304,7 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) XT_SYNPROXY_OPT_SACK_PERM | XT_SYNPROXY_OPT_ECN); - synproxy_send_client_synack(skb, th, &opts); + synproxy_send_client_synack(snet, skb, th, &opts); return NF_DROP; } else if (th->ack && !(th->fin || th->rst || th->syn)) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6090969937f8..9de4d2bcd916 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1831,6 +1831,7 @@ int ip6_route_add(struct fib6_config *cfg) int gwa_type; gw_addr = &cfg->fc_gateway; + gwa_type = ipv6_addr_type(gw_addr); /* if gw_addr is local we will fail to detect this in case * address is still TENTATIVE (DAD in progress). rt6_lookup() @@ -1838,11 +1839,12 @@ int ip6_route_add(struct fib6_config *cfg) * prefix route was assigned to, which might be non-loopback. */ err = -EINVAL; - if (ipv6_chk_addr_and_flags(net, gw_addr, NULL, 0, 0)) + if (ipv6_chk_addr_and_flags(net, gw_addr, + gwa_type & IPV6_ADDR_LINKLOCAL ? + dev : NULL, 0, 0)) goto out; rt->rt6i_gateway = *gw_addr; - gwa_type = ipv6_addr_type(gw_addr); if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) { struct rt6_info *grt; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6748c4277aff..7a6cea5e4274 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -943,7 +943,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb) &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb)); if (req) { nsk = tcp_check_req(sk, skb, req, false); - if (!nsk) + if (!nsk || nsk == sk) reqsk_put(req); return nsk; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 651039ad1681..3c20d02aee73 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -292,7 +292,7 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags) { struct nf_conn *tmpl; - tmpl = kzalloc(sizeof(struct nf_conn), GFP_KERNEL); + tmpl = kzalloc(sizeof(*tmpl), flags); if (tmpl == NULL) return NULL; @@ -303,7 +303,7 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags) if (zone) { struct nf_conntrack_zone *nf_ct_zone; - nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, GFP_ATOMIC); + nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, flags); if (!nf_ct_zone) goto out_free; nf_ct_zone->id = zone; @@ -1544,10 +1544,8 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) sz = nr_slots * sizeof(struct hlist_nulls_head); hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, get_order(sz)); - if (!hash) { - printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n"); + if (!hash) hash = vzalloc(sz); - } if (hash && nulls) for (i = 0; i < nr_slots; i++) diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 71f1e9fdfa18..d7f168527903 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -353,10 +353,8 @@ static int __net_init synproxy_net_init(struct net *net) int err = -ENOMEM; ct = nf_ct_tmpl_alloc(net, 0, GFP_KERNEL); - if (IS_ERR(ct)) { - err = PTR_ERR(ct); + if (!ct) goto err1; - } if (!nfct_seqadj_ext_add(ct)) goto err2; diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index c6630030c912..43ddeee404e9 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -202,9 +202,10 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, goto err1; ct = nf_ct_tmpl_alloc(par->net, info->zone, GFP_KERNEL); - ret = PTR_ERR(ct); - if (IS_ERR(ct)) + if (!ct) { + ret = -ENOMEM; goto err2; + } ret = 0; if ((info->ct_events || info->exp_events) && diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index d8e2e3918ce2..67d210477863 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1096,6 +1096,11 @@ static int netlink_insert(struct sock *sk, u32 portid) err = __netlink_insert(table, sk); if (err) { + /* In case the hashtable backend returns with -EBUSY + * from here, it must not escape to the caller. + */ + if (unlikely(err == -EBUSY)) + err = -EOVERFLOW; if (err == -EEXIST) err = -EADDRINUSE; nlk_sk(sk)->portid = 0; |