diff options
Diffstat (limited to '')
53 files changed, 1504 insertions, 868 deletions
diff --git a/Documentation/devicetree/bindings/net/meson-dwmac.txt b/Documentation/devicetree/bindings/net/meson-dwmac.txt index 354dd9896bb5..61cada22ae6c 100644 --- a/Documentation/devicetree/bindings/net/meson-dwmac.txt +++ b/Documentation/devicetree/bindings/net/meson-dwmac.txt @@ -9,6 +9,7 @@ Required properties on all platforms: - compatible: Depending on the platform this should be one of: - "amlogic,meson6-dwmac" - "amlogic,meson8b-dwmac" + - "amlogic,meson8m2-dwmac" - "amlogic,meson-gxbb-dwmac" Additionally "snps,dwmac" and any applicable more detailed version number described in net/stmmac.txt @@ -19,13 +20,13 @@ Required properties on all platforms: configuration (for example the PRG_ETHERNET register range on Meson8b and newer) -Required properties on Meson8b and newer: +Required properties on Meson8b, Meson8m2, GXBB and newer: - clock-names: Should contain the following: - "stmmaceth" - see stmmac.txt - "clkin0" - first parent clock of the internal mux - "clkin1" - second parent clock of the internal mux -Optional properties on Meson8b and newer: +Optional properties on Meson8b, Meson8m2, GXBB and newer: - amlogic,tx-delay-ns: The internal RGMII TX clock delay (provided by this driver) in nanoseconds. Allowed values are: 0ns, 2ns, 4ns, 6ns. diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index 30b1c8512049..0d15a12a4560 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -219,6 +219,7 @@ static int __init dummy_init_module(void) { int i, err = 0; + down_write(&pernet_ops_rwsem); rtnl_lock(); err = __rtnl_link_register(&dummy_link_ops); if (err < 0) @@ -233,6 +234,7 @@ static int __init dummy_init_module(void) out: rtnl_unlock(); + up_write(&pernet_ops_rwsem); return err; } diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index 4cacce5d2b16..5fc46c5a4f36 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -265,6 +265,22 @@ struct nicvf_drv_stats { struct cavium_ptp; +struct xcast_addr { + struct list_head list; + u64 addr; +}; + +struct xcast_addr_list { + struct list_head list; + int count; +}; + +struct nicvf_work { + struct delayed_work work; + u8 mode; + struct xcast_addr_list *mc; +}; + struct nicvf { struct nicvf *pnicvf; struct net_device *netdev; @@ -313,6 +329,7 @@ struct nicvf { struct nicvf_pfc pfc; struct tasklet_struct qs_err_task; struct work_struct reset_task; + struct nicvf_work rx_mode_work; /* PTP timestamp */ struct cavium_ptp *ptp_clock; @@ -403,6 +420,9 @@ struct nicvf { #define NIC_MBOX_MSG_PTP_CFG 0x19 /* HW packet timestamp */ #define NIC_MBOX_MSG_CFG_DONE 0xF0 /* VF configuration done */ #define NIC_MBOX_MSG_SHUTDOWN 0xF1 /* VF is being shutdown */ +#define NIC_MBOX_MSG_RESET_XCAST 0xF2 /* Reset DCAM filtering mode */ +#define NIC_MBOX_MSG_ADD_MCAST 0xF3 /* Add MAC to DCAM filters */ +#define NIC_MBOX_MSG_SET_XCAST 0xF4 /* Set MCAST/BCAST RX mode */ struct nic_cfg_msg { u8 msg; @@ -556,6 +576,14 @@ struct set_ptp { bool enable; }; +struct xcast { + u8 msg; + union { + u8 mode; + u64 mac; + } data; +}; + /* 128 bit shared memory between PF and each VF */ union nic_mbx { struct { u8 msg; } msg; @@ -576,6 +604,7 @@ union nic_mbx { struct reset_stat_cfg reset_stat; struct pfc pfc; struct set_ptp ptp; + struct xcast xcast; }; #define NIC_NODE_ID_MASK 0x03 diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 7ff66a8194e2..55af04fa03a7 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -21,6 +21,8 @@ #define DRV_NAME "nicpf" #define DRV_VERSION "1.0" +#define NIC_VF_PER_MBX_REG 64 + struct hw_info { u8 bgx_cnt; u8 chans_per_lmac; @@ -1072,6 +1074,40 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) case NIC_MBOX_MSG_PTP_CFG: nic_config_timestamp(nic, vf, &mbx.ptp); break; + case NIC_MBOX_MSG_RESET_XCAST: + if (vf >= nic->num_vf_en) { + ret = -1; /* NACK */ + 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_reset_xcast_mode(nic->node, bgx, lmac, + vf < NIC_VF_PER_MBX_REG ? vf : + vf - NIC_VF_PER_MBX_REG); + break; + + case NIC_MBOX_MSG_ADD_MCAST: + if (vf >= nic->num_vf_en) { + ret = -1; /* NACK */ + 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_set_dmac_cam_filter(nic->node, bgx, lmac, + mbx.xcast.data.mac, + vf < NIC_VF_PER_MBX_REG ? vf : + vf - NIC_VF_PER_MBX_REG); + break; + + case NIC_MBOX_MSG_SET_XCAST: + if (vf >= nic->num_vf_en) { + ret = -1; /* NACK */ + 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_set_xcast_mode(nic->node, bgx, lmac, mbx.xcast.data.mode); + break; default: dev_err(&nic->pdev->dev, "Invalid msg from VF%d, msg 0x%x\n", vf, mbx.msg.msg); @@ -1094,7 +1130,7 @@ static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq) struct nicpf *nic = (struct nicpf *)nic_irq; int mbx; u64 intr; - u8 vf, vf_per_mbx_reg = 64; + u8 vf; if (irq == pci_irq_vector(nic->pdev, NIC_PF_INTR_ID_MBOX0)) mbx = 0; @@ -1103,12 +1139,13 @@ static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq) intr = nic_reg_read(nic, NIC_PF_MAILBOX_INT + (mbx << 3)); dev_dbg(&nic->pdev->dev, "PF interrupt Mbox%d 0x%llx\n", mbx, intr); - for (vf = 0; vf < vf_per_mbx_reg; vf++) { + for (vf = 0; vf < NIC_VF_PER_MBX_REG; vf++) { if (intr & (1ULL << vf)) { dev_dbg(&nic->pdev->dev, "Intr from VF %d\n", - vf + (mbx * vf_per_mbx_reg)); + vf + (mbx * NIC_VF_PER_MBX_REG)); - nic_handle_mbx_intr(nic, vf + (mbx * vf_per_mbx_reg)); + nic_handle_mbx_intr(nic, vf + + (mbx * NIC_VF_PER_MBX_REG)); nic_clear_mbx_intr(nic, vf, mbx); } } diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 73fe3881414b..1e9a31fef729 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -21,6 +21,7 @@ #include <linux/bpf_trace.h> #include <linux/filter.h> #include <linux/net_tstamp.h> +#include <linux/workqueue.h> #include "nic_reg.h" #include "nic.h" @@ -67,6 +68,9 @@ module_param(cpi_alg, int, 0444); MODULE_PARM_DESC(cpi_alg, "PFC algorithm (0=none, 1=VLAN, 2=VLAN16, 3=IP Diffserv)"); +/* workqueue for handling kernel ndo_set_rx_mode() calls */ +static struct workqueue_struct *nicvf_rx_mode_wq; + static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx) { if (nic->sqs_mode) @@ -1919,6 +1923,100 @@ static int nicvf_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) } } +static void nicvf_set_rx_mode_task(struct work_struct *work_arg) +{ + struct nicvf_work *vf_work = container_of(work_arg, struct nicvf_work, + work.work); + struct nicvf *nic = container_of(vf_work, struct nicvf, rx_mode_work); + union nic_mbx mbx = {}; + struct xcast_addr *xaddr, *next; + + if (!vf_work) + return; + + /* From the inside of VM code flow we have only 128 bits memory + * available to send message to host's PF, so send all mc addrs + * one by one, starting from flush command in case if kernel + * requests to configure specific MAC filtering + */ + + /* flush DMAC filters and reset RX mode */ + mbx.xcast.msg = NIC_MBOX_MSG_RESET_XCAST; + nicvf_send_msg_to_pf(nic, &mbx); + + if (vf_work->mode & BGX_XCAST_MCAST_FILTER) { + /* once enabling filtering, we need to signal to PF to add + * its' own LMAC to the filter to accept packets for it. + */ + mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST; + mbx.xcast.data.mac = 0; + nicvf_send_msg_to_pf(nic, &mbx); + } + + /* check if we have any specific MACs to be added to PF DMAC filter */ + if (vf_work->mc) { + /* now go through kernel list of MACs and add them one by one */ + list_for_each_entry_safe(xaddr, next, + &vf_work->mc->list, list) { + mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST; + mbx.xcast.data.mac = xaddr->addr; + nicvf_send_msg_to_pf(nic, &mbx); + + /* after receiving ACK from PF release memory */ + list_del(&xaddr->list); + kfree(xaddr); + vf_work->mc->count--; + } + kfree(vf_work->mc); + } + + /* and finally set rx mode for PF accordingly */ + mbx.xcast.msg = NIC_MBOX_MSG_SET_XCAST; + mbx.xcast.data.mode = vf_work->mode; + + nicvf_send_msg_to_pf(nic, &mbx); +} + +static void nicvf_set_rx_mode(struct net_device *netdev) +{ + struct nicvf *nic = netdev_priv(netdev); + struct netdev_hw_addr *ha; + struct xcast_addr_list *mc_list = NULL; + u8 mode = 0; + + if (netdev->flags & IFF_PROMISC) { + mode = BGX_XCAST_BCAST_ACCEPT | BGX_XCAST_MCAST_ACCEPT; + } else { + if (netdev->flags & IFF_BROADCAST) + mode |= BGX_XCAST_BCAST_ACCEPT; + + if (netdev->flags & IFF_ALLMULTI) { + mode |= BGX_XCAST_MCAST_ACCEPT; + } else if (netdev->flags & IFF_MULTICAST) { + mode |= BGX_XCAST_MCAST_FILTER; + /* here we need to copy mc addrs */ + if (netdev_mc_count(netdev)) { + struct xcast_addr *xaddr; + + mc_list = kmalloc(sizeof(*mc_list), GFP_ATOMIC); + INIT_LIST_HEAD(&mc_list->list); + netdev_hw_addr_list_for_each(ha, &netdev->mc) { + xaddr = kmalloc(sizeof(*xaddr), + GFP_ATOMIC); + xaddr->addr = + ether_addr_to_u64(ha->addr); + list_add_tail(&xaddr->list, + &mc_list->list); + mc_list->count++; + } + } + } + } + nic->rx_mode_work.mc = mc_list; + nic->rx_mode_work.mode = mode; + queue_delayed_work(nicvf_rx_mode_wq, &nic->rx_mode_work.work, 2 * HZ); +} + static const struct net_device_ops nicvf_netdev_ops = { .ndo_open = nicvf_open, .ndo_stop = nicvf_stop, @@ -1931,6 +2029,7 @@ static const struct net_device_ops nicvf_netdev_ops = { .ndo_set_features = nicvf_set_features, .ndo_bpf = nicvf_xdp, .ndo_do_ioctl = nicvf_ioctl, + .ndo_set_rx_mode = nicvf_set_rx_mode, }; static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) @@ -2071,6 +2170,8 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&nic->reset_task, nicvf_reset_task); + INIT_DELAYED_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task); + err = register_netdev(netdev); if (err) { dev_err(dev, "Failed to register netdevice\n"); @@ -2109,6 +2210,8 @@ static void nicvf_remove(struct pci_dev *pdev) nic = netdev_priv(netdev); pnetdev = nic->pnicvf->netdev; + cancel_delayed_work_sync(&nic->rx_mode_work.work); + /* Check if this Qset is assigned to different VF. * If yes, clean primary and all secondary Qsets. */ @@ -2140,12 +2243,17 @@ static struct pci_driver nicvf_driver = { static int __init nicvf_init_module(void) { pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION); - + nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_generic", + WQ_MEM_RECLAIM); return pci_register_driver(&nicvf_driver); } static void __exit nicvf_cleanup_module(void) { + if (nicvf_rx_mode_wq) { + destroy_workqueue(nicvf_rx_mode_wq); + nicvf_rx_mode_wq = NULL; + } pci_unregister_driver(&nicvf_driver); } diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 91d34ea40e2c..5d08d2aeb172 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -24,9 +24,31 @@ #define DRV_NAME "thunder_bgx" #define DRV_VERSION "1.0" +/* RX_DMAC_CTL configuration */ +enum MCAST_MODE { + MCAST_MODE_REJECT = 0x0, + MCAST_MODE_ACCEPT = 0x1, + MCAST_MODE_CAM_FILTER = 0x2, + RSVD = 0x3 +}; + +#define BCAST_ACCEPT BIT(0) +#define CAM_ACCEPT BIT(3) +#define MCAST_MODE_MASK 0x3 +#define BGX_MCAST_MODE(x) (x << 1) + +struct dmac_map { + u64 vf_map; + u64 dmac; +}; + struct lmac { struct bgx *bgx; - int dmac; + /* actual number of DMACs configured */ + u8 dmacs_cfg; + /* overal number of possible DMACs could be configured per LMAC */ + u8 dmacs_count; + struct dmac_map *dmacs; /* DMAC:VFs tracking filter array */ u8 mac[ETH_ALEN]; u8 lmac_type; u8 lane_to_sds; @@ -223,6 +245,163 @@ void bgx_set_lmac_mac(int node, int bgx_idx, int lmacid, const u8 *mac) } EXPORT_SYMBOL(bgx_set_lmac_mac); +static void bgx_flush_dmac_cam_filter(struct bgx *bgx, int lmacid) +{ + struct lmac *lmac = NULL; + u8 idx = 0; + + lmac = &bgx->lmac[lmacid]; + /* reset CAM filters */ + for (idx = 0; idx < lmac->dmacs_count; idx++) + bgx_reg_write(bgx, 0, BGX_CMR_RX_DMACX_CAM + + ((lmacid * lmac->dmacs_count) + idx) * + sizeof(u64), 0); +} + +static void bgx_lmac_remove_filters(struct lmac *lmac, u8 vf_id) +{ + int i = 0; + + if (!lmac) + return; + + /* We've got reset filters request from some of attached VF, while the + * others might want to keep their configuration. So in this case lets + * iterate over all of configured filters and decrease number of + * referencies. if some addresses get zero refs remove them from list + */ + for (i = lmac->dmacs_cfg - 1; i >= 0; i--) { + lmac->dmacs[i].vf_map &= ~BIT_ULL(vf_id); + if (!lmac->dmacs[i].vf_map) { + lmac->dmacs_cfg--; + lmac->dmacs[i].dmac = 0; + lmac->dmacs[i].vf_map = 0; + } + } +} + +static int bgx_lmac_save_filter(struct lmac *lmac, u64 dmac, u8 vf_id) +{ + u8 i = 0; + + if (!lmac) + return -1; + + /* At the same time we could have several VFs 'attached' to some + * particular LMAC, and each VF is represented as network interface + * for kernel. So from user perspective it should be possible to + * manipulate with its' (VF) receive modes. However from PF + * driver perspective we need to keep track of filter configurations + * for different VFs to prevent filter values dupes + */ + for (i = 0; i < lmac->dmacs_cfg; i++) { + if (lmac->dmacs[i].dmac == dmac) { + lmac->dmacs[i].vf_map |= BIT_ULL(vf_id); + return -1; + } + } + + if (!(lmac->dmacs_cfg < lmac->dmacs_count)) + return -1; + + /* keep it for further tracking */ + lmac->dmacs[lmac->dmacs_cfg].dmac = dmac; + lmac->dmacs[lmac->dmacs_cfg].vf_map = BIT_ULL(vf_id); + lmac->dmacs_cfg++; + return 0; +} + +static int bgx_set_dmac_cam_filter_mac(struct bgx *bgx, int lmacid, + u64 cam_dmac, u8 idx) +{ + struct lmac *lmac = NULL; + u64 cfg = 0; + + /* skip zero addresses as meaningless */ + if (!cam_dmac || !bgx) + return -1; + + lmac = &bgx->lmac[lmacid]; + + /* configure DCAM filtering for designated LMAC */ + cfg = RX_DMACX_CAM_LMACID(lmacid & LMAC_ID_MASK) | + RX_DMACX_CAM_EN | cam_dmac; + bgx_reg_write(bgx, 0, BGX_CMR_RX_DMACX_CAM + + ((lmacid * lmac->dmacs_count) + idx) * sizeof(u64), cfg); + return 0; +} + +void bgx_set_dmac_cam_filter(int node, int bgx_idx, int lmacid, + u64 cam_dmac, u8 vf_id) +{ + struct bgx *bgx = get_bgx(node, bgx_idx); + struct lmac *lmac = NULL; + + if (!bgx) + return; + + lmac = &bgx->lmac[lmacid]; + + if (!cam_dmac) + cam_dmac = ether_addr_to_u64(lmac->mac); + + /* since we might have several VFs attached to particular LMAC + * and kernel could call mcast config for each of them with the + * same MAC, check if requested MAC is already in filtering list and + * updare/prepare list of MACs to be applied later to HW filters + */ + bgx_lmac_save_filter(lmac, cam_dmac, vf_id); +} +EXPORT_SYMBOL(bgx_set_dmac_cam_filter); + +void bgx_set_xcast_mode(int node, int bgx_idx, int lmacid, u8 mode) +{ + struct bgx *bgx = get_bgx(node, bgx_idx); + struct lmac *lmac = NULL; + u64 cfg = 0; + u8 i = 0; + + if (!bgx) + return; + + lmac = &bgx->lmac[lmacid]; + + cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_RX_DMAC_CTL); + if (mode & BGX_XCAST_BCAST_ACCEPT) + cfg |= BCAST_ACCEPT; + else + cfg &= ~BCAST_ACCEPT; + + /* disable all MCASTs and DMAC filtering */ + cfg &= ~(CAM_ACCEPT | BGX_MCAST_MODE(MCAST_MODE_MASK)); + + /* check requested bits and set filtergin mode appropriately */ + if (mode & (BGX_XCAST_MCAST_ACCEPT)) { + cfg |= (BGX_MCAST_MODE(MCAST_MODE_ACCEPT)); + } else if (mode & BGX_XCAST_MCAST_FILTER) { + cfg |= (BGX_MCAST_MODE(MCAST_MODE_CAM_FILTER) | CAM_ACCEPT); + for (i = 0; i < lmac->dmacs_cfg; i++) + bgx_set_dmac_cam_filter_mac(bgx, lmacid, + lmac->dmacs[i].dmac, i); + } + bgx_reg_write(bgx, lmacid, BGX_CMRX_RX_DMAC_CTL, cfg); +} +EXPORT_SYMBOL(bgx_set_xcast_mode); + +void bgx_reset_xcast_mode(int node, int bgx_idx, int lmacid, u8 vf_id) +{ + struct bgx *bgx = get_bgx(node, bgx_idx); + + if (!bgx) + return; + + bgx_lmac_remove_filters(&bgx->lmac[lmacid], vf_id); + bgx_flush_dmac_cam_filter(bgx, lmacid); + bgx_set_xcast_mode(node, bgx_idx, lmacid, + (BGX_XCAST_BCAST_ACCEPT | BGX_XCAST_MCAST_ACCEPT)); +} +EXPORT_SYMBOL(bgx_reset_xcast_mode); + void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable) { struct bgx *bgx = get_bgx(node, bgx_idx); @@ -468,18 +647,6 @@ u64 bgx_get_tx_stats(int node, int bgx_idx, int lmac, int idx) } EXPORT_SYMBOL(bgx_get_tx_stats); -static void bgx_flush_dmac_addrs(struct bgx *bgx, int lmac) -{ - u64 offset; - - while (bgx->lmac[lmac].dmac > 0) { - offset = ((bgx->lmac[lmac].dmac - 1) * sizeof(u64)) + - (lmac * MAX_DMAC_PER_LMAC * sizeof(u64)); - bgx_reg_write(bgx, 0, BGX_CMR_RX_DMACX_CAM + offset, 0); - bgx->lmac[lmac].dmac--; - } -} - /* Configure BGX LMAC in internal loopback mode */ void bgx_lmac_internal_loopback(int node, int bgx_idx, int lmac_idx, bool enable) @@ -912,6 +1079,11 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid) bgx_reg_write(bgx, lmacid, BGX_SMUX_TX_MIN_PKT, 60 + 4); } + /* actual number of filters available to exact LMAC */ + lmac->dmacs_count = (RX_DMAC_COUNT / bgx->lmac_count); + lmac->dmacs = kcalloc(lmac->dmacs_count, sizeof(*lmac->dmacs), + GFP_KERNEL); + /* Enable lmac */ bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG, CMR_EN); @@ -998,7 +1170,8 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid) cfg &= ~CMR_EN; bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg); - bgx_flush_dmac_addrs(bgx, lmacid); + bgx_flush_dmac_cam_filter(bgx, lmacid); + kfree(lmac->dmacs); if ((lmac->lmac_type != BGX_MODE_XFI) && (lmac->lmac_type != BGX_MODE_XLAUI) && diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index 5a7567d31138..cbdd20b9ee6f 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -30,6 +30,7 @@ #define DEFAULT_PAUSE_TIME 0xFFFF #define BGX_ID_MASK 0x3 +#define LMAC_ID_MASK 0x3 #define MAX_DMAC_PER_LMAC_TNS_BYPASS_MODE 2 @@ -57,7 +58,7 @@ #define BGX_CMRX_RX_FIFO_LEN 0x108 #define BGX_CMR_RX_DMACX_CAM 0x200 #define RX_DMACX_CAM_EN BIT_ULL(48) -#define RX_DMACX_CAM_LMACID(x) (x << 49) +#define RX_DMACX_CAM_LMACID(x) (((u64)x) << 49) #define RX_DMAC_COUNT 32 #define BGX_CMR_RX_STREERING 0x300 #define RX_TRAFFIC_STEER_RULE_COUNT 8 @@ -205,17 +206,13 @@ #define LMAC_INTR_LINK_UP BIT(0) #define LMAC_INTR_LINK_DOWN BIT(1) -/* RX_DMAC_CTL configuration*/ -enum MCAST_MODE { - MCAST_MODE_REJECT, - MCAST_MODE_ACCEPT, - MCAST_MODE_CAM_FILTER, - RSVD -}; - -#define BCAST_ACCEPT 1 -#define CAM_ACCEPT 1 +#define BGX_XCAST_BCAST_ACCEPT BIT(0) +#define BGX_XCAST_MCAST_ACCEPT BIT(1) +#define BGX_XCAST_MCAST_FILTER BIT(2) +void bgx_set_dmac_cam_filter(int node, int bgx_idx, int lmacid, u64 mac, u8 vf); +void bgx_reset_xcast_mode(int node, int bgx_idx, int lmacid, u8 vf); +void bgx_set_xcast_mode(int node, int bgx_idx, int lmacid, u8 mode); void octeon_mdiobus_force_mod_depencency(void); void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable); void bgx_add_dmac_addr(u64 dmac, int node, int bgx_idx, int lmac); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index cac86e9ae0dd..9dcc5765f11f 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -369,7 +369,6 @@ static int hns_mac_port_config_bc_en(struct hns_mac_cb *mac_cb, { int ret; struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev; - u8 addr[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; struct dsaf_drv_mac_single_dest_entry mac_entry; /* directy return ok in debug network mode */ @@ -377,7 +376,7 @@ static int hns_mac_port_config_bc_en(struct hns_mac_cb *mac_cb, return 0; if (!HNS_DSAF_IS_DEBUG(dsaf_dev)) { - memcpy(mac_entry.addr, addr, sizeof(mac_entry.addr)); + eth_broadcast_addr(mac_entry.addr); mac_entry.in_vlan_id = vlan_id; mac_entry.in_port_num = mac_cb->mac_id; mac_entry.port_num = port_num; @@ -404,7 +403,6 @@ int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vmid, bool enable) int ret; struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev; u8 port_num; - u8 addr[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; struct mac_entry_idx *uc_mac_entry; struct dsaf_drv_mac_single_dest_entry mac_entry; @@ -414,7 +412,7 @@ int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vmid, bool enable) uc_mac_entry = &mac_cb->addr_entry_idx[vmid]; if (!HNS_DSAF_IS_DEBUG(dsaf_dev)) { - memcpy(mac_entry.addr, addr, sizeof(mac_entry.addr)); + eth_broadcast_addr(mac_entry.addr); mac_entry.in_vlan_id = uc_mac_entry->vlan_id; mac_entry.in_port_num = mac_cb->mac_id; ret = hns_mac_get_inner_port_num(mac_cb, vmid, &port_num); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index a31b4adf6e6a..8c55965a66ac 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1614,10 +1614,6 @@ static void hns3_remove(struct pci_dev *pdev) struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev); hnae3_unregister_ae_dev(ae_dev); - - devm_kfree(&pdev->dev, ae_dev); - - pci_set_drvdata(pdev, NULL); } static struct pci_driver hns3_driver = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 2d5d4aea3bcb..7cb794094a70 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -1,5 +1,5 @@ /* - * Amlogic Meson8b and GXBB DWMAC glue layer + * Amlogic Meson8b, Meson8m2 and GXBB DWMAC glue layer * * Copyright (C) 2016 Martin Blumenstingl <martin.blumenstingl@googlemail.com> * @@ -318,6 +318,7 @@ err_remove_config_dt: static const struct of_device_id meson8b_dwmac_match[] = { { .compatible = "amlogic,meson8b-dwmac" }, + { .compatible = "amlogic,meson8m2-dwmac" }, { .compatible = "amlogic,meson-gxbb-dwmac" }, { } }; @@ -335,5 +336,5 @@ static struct platform_driver meson8b_dwmac_driver = { module_platform_driver(meson8b_dwmac_driver); MODULE_AUTHOR("Martin Blumenstingl <martin.blumenstingl@googlemail.com>"); -MODULE_DESCRIPTION("Amlogic Meson8b and GXBB DWMAC glue layer"); +MODULE_DESCRIPTION("Amlogic Meson8b, Meson8m2 and GXBB DWMAC glue layer"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 4a4952363e8a..e2b68d9328a7 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -365,14 +365,15 @@ static inline void *rndis_get_ppi(struct rndis_packet *rpkt, u32 type) static int rndis_filter_receive_data(struct net_device *ndev, struct netvsc_device *nvdev, - struct rndis_message *msg, struct vmbus_channel *channel, - void *data, u32 data_buflen) + struct rndis_message *msg, + u32 data_buflen) { struct rndis_packet *rndis_pkt = &msg->msg.pkt; const struct ndis_tcp_ip_checksum_info *csum_info; const struct ndis_pkt_8021q_info *vlan; u32 data_offset; + void *data; /* Remove the rndis header and pass it back up the stack */ data_offset = RNDIS_HEADER_SIZE + rndis_pkt->data_offset; @@ -393,14 +394,15 @@ static int rndis_filter_receive_data(struct net_device *ndev, vlan = rndis_get_ppi(rndis_pkt, IEEE_8021Q_INFO); + csum_info = rndis_get_ppi(rndis_pkt, TCPIP_CHKSUM_PKTINFO); + + data = (void *)msg + data_offset; + /* * Remove the rndis trailer padding from rndis packet message * rndis_pkt->data_len tell us the real data length, we only copy * the data packet to the stack, without the rndis trailer padding */ - data = (void *)((unsigned long)data + data_offset); - csum_info = rndis_get_ppi(rndis_pkt, TCPIP_CHKSUM_PKTINFO); - return netvsc_recv_callback(ndev, nvdev, channel, data, rndis_pkt->data_len, csum_info, vlan); @@ -419,8 +421,8 @@ int rndis_filter_receive(struct net_device *ndev, switch (rndis_msg->ndis_msg_type) { case RNDIS_MSG_PACKET: - return rndis_filter_receive_data(ndev, net_dev, rndis_msg, - channel, data, buflen); + return rndis_filter_receive_data(ndev, net_dev, channel, + rndis_msg, buflen); case RNDIS_MSG_INIT_C: case RNDIS_MSG_QUERY_C: case RNDIS_MSG_SET_C: diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index 0008da7e9d4c..5f2897ec0edc 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -330,6 +330,7 @@ static int __init ifb_init_module(void) { int i, err; + down_write(&pernet_ops_rwsem); rtnl_lock(); err = __rtnl_link_register(&ifb_link_ops); if (err < 0) @@ -344,6 +345,7 @@ static int __init ifb_init_module(void) out: rtnl_unlock(); + up_write(&pernet_ops_rwsem); return err; } diff --git a/drivers/net/netdevsim/devlink.c b/drivers/net/netdevsim/devlink.c index bbdcf064ba10..27ae05c5fdaf 100644 --- a/drivers/net/netdevsim/devlink.c +++ b/drivers/net/netdevsim/devlink.c @@ -218,22 +218,22 @@ void nsim_devlink_teardown(struct netdevsim *ns) } } -void nsim_devlink_setup(struct netdevsim *ns) +int nsim_devlink_setup(struct netdevsim *ns) { struct net *net = nsim_to_net(ns); bool *reg_devlink = net_generic(net, nsim_devlink_id); struct devlink *devlink; - int err = -ENOMEM; + int err; /* only one device per namespace controls devlink */ if (!*reg_devlink) { ns->devlink = NULL; - return; + return 0; } devlink = devlink_alloc(&nsim_devlink_ops, 0); if (!devlink) - return; + return -ENOMEM; err = devlink_register(devlink, &ns->dev); if (err) @@ -247,12 +247,14 @@ void nsim_devlink_setup(struct netdevsim *ns) *reg_devlink = false; - return; + return 0; err_dl_unregister: devlink_unregister(devlink); err_devlink_free: devlink_free(devlink); + + return err; } /* Initialize per network namespace state */ diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 8b30ab3ea2c2..ec68f38213d9 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -167,10 +167,14 @@ static int nsim_init(struct net_device *dev) SET_NETDEV_DEV(dev, &ns->dev); - nsim_devlink_setup(ns); + err = nsim_devlink_setup(ns); + if (err) + goto err_unreg_dev; return 0; +err_unreg_dev: + device_unregister(&ns->dev); err_bpf_uninit: nsim_bpf_uninit(ns); err_debugfs_destroy: diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index afb8cf90c0fd..3a8581af3b85 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -117,7 +117,7 @@ enum nsim_resource_id { NSIM_RESOURCE_IPV6_FIB_RULES, }; -void nsim_devlink_setup(struct netdevsim *ns); +int nsim_devlink_setup(struct netdevsim *ns); void nsim_devlink_teardown(struct netdevsim *ns); int nsim_devlink_init(void); @@ -128,8 +128,9 @@ void nsim_fib_exit(void); u64 nsim_fib_get_val(struct net *net, enum nsim_resource_id res_id, bool max); int nsim_fib_set_max(struct net *net, enum nsim_resource_id res_id, u64 val); #else -static inline void nsim_devlink_setup(struct netdevsim *ns) +static inline int nsim_devlink_setup(struct netdevsim *ns) { + return 0; } static inline void nsim_devlink_teardown(struct netdevsim *ns) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 2ea788f6f95d..9e96c2fe2793 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -42,6 +42,22 @@ enum rxrpc_skb_trace { rxrpc_skb_tx_seen, }; +enum rxrpc_local_trace { + rxrpc_local_got, + rxrpc_local_new, + rxrpc_local_processing, + rxrpc_local_put, + rxrpc_local_queued, +}; + +enum rxrpc_peer_trace { + rxrpc_peer_got, + rxrpc_peer_new, + rxrpc_peer_processing, + rxrpc_peer_put, + rxrpc_peer_queued_error, +}; + enum rxrpc_conn_trace { rxrpc_conn_got, rxrpc_conn_new_client, @@ -215,6 +231,20 @@ enum rxrpc_congest_change { EM(rxrpc_skb_tx_rotated, "Tx ROT") \ E_(rxrpc_skb_tx_seen, "Tx SEE") +#define rxrpc_local_traces \ + EM(rxrpc_local_got, "GOT") \ + EM(rxrpc_local_new, "NEW") \ + EM(rxrpc_local_processing, "PRO") \ + EM(rxrpc_local_put, "PUT") \ + E_(rxrpc_local_queued, "QUE") + +#define rxrpc_peer_traces \ + EM(rxrpc_peer_got, "GOT") \ + EM(rxrpc_peer_new, "NEW") \ + EM(rxrpc_peer_processing, "PRO") \ + EM(rxrpc_peer_put, "PUT") \ + E_(rxrpc_peer_queued_error, "QER") + #define rxrpc_conn_traces \ EM(rxrpc_conn_got, "GOT") \ EM(rxrpc_conn_new_client, "NWc") \ @@ -416,6 +446,7 @@ enum rxrpc_congest_change { #define E_(a, b) TRACE_DEFINE_ENUM(a); rxrpc_skb_traces; +rxrpc_local_traces; rxrpc_conn_traces; rxrpc_client_traces; rxrpc_call_traces; @@ -439,6 +470,60 @@ rxrpc_congest_changes; #define EM(a, b) { a, b }, #define E_(a, b) { a, b } +TRACE_EVENT(rxrpc_local, + TP_PROTO(struct rxrpc_local *local, enum rxrpc_local_trace op, + int usage, const void *where), + + TP_ARGS(local, op, usage, where), + + TP_STRUCT__entry( + __field(unsigned int, local ) + __field(int, op ) + __field(int, usage ) + __field(const void *, where ) + ), + + TP_fast_assign( + __entry->local = local->debug_id; + __entry->op = op; + __entry->usage = usage; + __entry->where = where; + ), + + TP_printk("L=%08x %s u=%d sp=%pSR", + __entry->local, + __print_symbolic(__entry->op, rxrpc_local_traces), + __entry->usage, + __entry->where) + ); + +TRACE_EVENT(rxrpc_peer, + TP_PROTO(struct rxrpc_peer *peer, enum rxrpc_peer_trace op, + int usage, const void *where), + + TP_ARGS(peer, op, usage, where), + + TP_STRUCT__entry( + __field(unsigned int, peer ) + __field(int, op ) + __field(int, usage ) + __field(const void *, where ) + ), + + TP_fast_assign( + __entry->peer = peer->debug_id; + __entry->op = op; + __entry->usage = usage; + __entry->where = where; + ), + + TP_printk("P=%08x %s u=%d sp=%pSR", + __entry->peer, + __print_symbolic(__entry->op, rxrpc_peer_traces), + __entry->usage, + __entry->where) + ); + TRACE_EVENT(rxrpc_conn, TP_PROTO(struct rxrpc_connection *conn, enum rxrpc_conn_trace op, int usage, const void *where), diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h index 4ac9f1f02b06..bf6d28677cfe 100644 --- a/include/uapi/linux/tipc.h +++ b/include/uapi/linux/tipc.h @@ -45,33 +45,33 @@ * TIPC addressing primitives */ -struct tipc_portid { +struct tipc_socket_addr { __u32 ref; __u32 node; }; -struct tipc_name { +struct tipc_service_addr { __u32 type; __u32 instance; }; -struct tipc_name_seq { +struct tipc_service_range { __u32 type; __u32 lower; __u32 upper; }; /* - * Application-accessible port name types + * Application-accessible service types */ -#define TIPC_CFG_SRV 0 /* configuration service name type */ -#define TIPC_TOP_SRV 1 /* topology service name type */ -#define TIPC_LINK_STATE 2 /* link state name type */ -#define TIPC_RESERVED_TYPES 64 /* lowest user-publishable name type */ +#define TIPC_NODE_STATE 0 /* node state service type */ +#define TIPC_TOP_SRV 1 /* topology server service type */ +#define TIPC_LINK_STATE 2 /* link state service type */ +#define TIPC_RESERVED_TYPES 64 /* lowest user-allowed service type */ /* - * Publication scopes when binding port names and port name sequences + * Publication scopes when binding service / service range */ enum tipc_scope { TIPC_CLUSTER_SCOPE = 2, /* 0 can also be used */ @@ -108,28 +108,28 @@ enum tipc_scope { * TIPC topology subscription service definitions */ -#define TIPC_SUB_PORTS 0x01 /* filter for port availability */ -#define TIPC_SUB_SERVICE 0x02 /* filter for service availability */ -#define TIPC_SUB_CANCEL 0x04 /* cancel a subscription */ +#define TIPC_SUB_PORTS 0x01 /* filter: evt at each match */ +#define TIPC_SUB_SERVICE 0x02 /* filter: evt at first up/last down */ +#define TIPC_SUB_CANCEL 0x04 /* filter: cancel a subscription */ #define TIPC_WAIT_FOREVER (~0) /* timeout for permanent subscription */ struct tipc_subscr { - struct tipc_name_seq seq; /* name sequence of interest */ + struct tipc_service_range seq; /* range of interest */ __u32 timeout; /* subscription duration (in ms) */ __u32 filter; /* bitmask of filter options */ char usr_handle[8]; /* available for subscriber use */ }; #define TIPC_PUBLISHED 1 /* publication event */ -#define TIPC_WITHDRAWN 2 /* withdraw event */ +#define TIPC_WITHDRAWN 2 /* withdrawal event */ #define TIPC_SUBSCR_TIMEOUT 3 /* subscription timeout event */ struct tipc_event { __u32 event; /* event type */ - __u32 found_lower; /* matching name seq instances */ - __u32 found_upper; /* " " " " */ - struct tipc_portid port; /* associated port */ + __u32 found_lower; /* matching range */ + __u32 found_upper; /* " " */ + struct tipc_socket_addr port; /* associated socket */ struct tipc_subscr s; /* associated subscription */ }; @@ -149,20 +149,20 @@ struct tipc_event { #define SOL_TIPC 271 #endif -#define TIPC_ADDR_NAMESEQ 1 -#define TIPC_ADDR_MCAST 1 -#define TIPC_ADDR_NAME 2 -#define TIPC_ADDR_ID 3 +#define TIPC_ADDR_MCAST 1 +#define TIPC_SERVICE_RANGE 1 +#define TIPC_SERVICE_ADDR 2 +#define TIPC_SOCKET_ADDR 3 struct sockaddr_tipc { unsigned short family; unsigned char addrtype; signed char scope; union { - struct tipc_portid id; - struct tipc_name_seq nameseq; + struct tipc_socket_addr id; + struct tipc_service_range nameseq; struct { - struct tipc_name name; + struct tipc_service_addr name; __u32 domain; } name; } addr; @@ -216,7 +216,7 @@ struct tipc_group_req { #define TIPC_MAX_MEDIA_NAME 16 #define TIPC_MAX_IF_NAME 16 #define TIPC_MAX_BEARER_NAME 32 -#define TIPC_MAX_LINK_NAME 60 +#define TIPC_MAX_LINK_NAME 68 #define SIOCGETLINKNAME SIOCPROTOPRIVATE @@ -230,8 +230,13 @@ struct tipc_sioc_ln_req { /* The macros and functions below are deprecated: */ +#define TIPC_CFG_SRV 0 #define TIPC_ZONE_SCOPE 1 +#define TIPC_ADDR_NAMESEQ 1 +#define TIPC_ADDR_NAME 2 +#define TIPC_ADDR_ID 3 + #define TIPC_NODE_BITS 12 #define TIPC_CLUSTER_BITS 12 #define TIPC_ZONE_BITS 8 @@ -250,6 +255,10 @@ struct tipc_sioc_ln_req { #define TIPC_ZONE_CLUSTER_MASK (TIPC_ZONE_MASK | TIPC_CLUSTER_MASK) +#define tipc_portid tipc_socket_addr +#define tipc_name tipc_service_addr +#define tipc_name_seq tipc_service_range + static inline __u32 tipc_addr(unsigned int zone, unsigned int cluster, unsigned int node) diff --git a/net/bridge/br.c b/net/bridge/br.c index 26e1616b2c90..671d13c10f6f 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -52,7 +52,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v switch (event) { case NETDEV_CHANGEMTU: - dev_set_mtu(br->dev, br_mtu(br)); + br_mtu_auto_adjust(br); break; case NETDEV_CHANGEADDR: diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 278fc999d355..e682a668ce57 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -224,11 +224,11 @@ static void br_get_stats64(struct net_device *dev, static int br_change_mtu(struct net_device *dev, int new_mtu) { struct net_bridge *br = netdev_priv(dev); - if (new_mtu > br_mtu(br)) - return -EINVAL; dev->mtu = new_mtu; + /* this flag will be cleared if the MTU was automatically adjusted */ + br->mtu_set_by_user = true; #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* remember the MTU in the rtable for PMTU */ dst_metric_set(&br->fake_rtable.dst, RTAX_MTU, new_mtu); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 87b2afd455c7..82c1a6f430b3 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -424,41 +424,32 @@ int br_del_bridge(struct net *net, const char *name) return ret; } -static bool min_mtu(int a, int b) -{ - return a < b ? 1 : 0; -} - -static bool max_mtu(int a, int b) -{ - return a > b ? 1 : 0; -} - /* MTU of the bridge pseudo-device: ETH_DATA_LEN or the minimum of the ports */ -static int __br_mtu(const struct net_bridge *br, bool (compare_fn)(int, int)) +static int br_mtu_min(const struct net_bridge *br) { const struct net_bridge_port *p; - int mtu = 0; + int ret_mtu = 0; - ASSERT_RTNL(); + list_for_each_entry(p, &br->port_list, list) + if (!ret_mtu || ret_mtu > p->dev->mtu) + ret_mtu = p->dev->mtu; - if (list_empty(&br->port_list)) - mtu = ETH_DATA_LEN; - else { - list_for_each_entry(p, &br->port_list, list) { - if (!mtu || compare_fn(p->dev->mtu, mtu)) - mtu = p->dev->mtu; - } - } - return mtu; + return ret_mtu ? ret_mtu : ETH_DATA_LEN; } -int br_mtu(const struct net_bridge *br) +void br_mtu_auto_adjust(struct net_bridge *br) { - if (br_vlan_enabled(br->dev)) - return __br_mtu(br, max_mtu); - else - return __br_mtu(br, min_mtu); + ASSERT_RTNL(); + + /* if the bridge MTU was manually configured don't mess with it */ + if (br->mtu_set_by_user) + return; + + /* change to the minimum MTU and clear the flag which was set by + * the bridge ndo_change_mtu callback + */ + dev_set_mtu(br->dev, br_mtu_min(br)); + br->mtu_set_by_user = false; } static void br_set_gso_limits(struct net_bridge *br) @@ -612,7 +603,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, if (changed_addr) call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); - dev_set_mtu(br->dev, br_mtu(br)); + br_mtu_auto_adjust(br); br_set_gso_limits(br); kobject_uevent(&p->kobj, KOBJ_ADD); @@ -659,7 +650,7 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) */ del_nbp(p); - dev_set_mtu(br->dev, br_mtu(br)); + br_mtu_auto_adjust(br); br_set_gso_limits(br); spin_lock_bh(&br->lock); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 048d5b51813b..a7cb3ece5031 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -410,6 +410,7 @@ struct net_bridge { int offload_fwd_mark; #endif bool neigh_suppress_enabled; + bool mtu_set_by_user; struct hlist_head fdb_list; }; @@ -578,7 +579,7 @@ int br_del_bridge(struct net *net, const char *name); int br_add_if(struct net_bridge *br, struct net_device *dev, struct netlink_ext_ack *extack); int br_del_if(struct net_bridge *br, struct net_device *dev); -int br_mtu(const struct net_bridge *br); +void br_mtu_auto_adjust(struct net_bridge *br); netdev_features_t br_features_recompute(struct net_bridge *br, netdev_features_t features); void br_port_flags_change(struct net_bridge_port *port, unsigned long mask); diff --git a/net/core/dev.c b/net/core/dev.c index 07da7add4845..8edb58829124 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1633,7 +1633,6 @@ int register_netdevice_notifier(struct notifier_block *nb) goto unlock; if (dev_boot_phase) goto unlock; - down_read(&net_rwsem); for_each_net(net) { for_each_netdev(net, dev) { err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); @@ -1647,7 +1646,6 @@ int register_netdevice_notifier(struct notifier_block *nb) call_netdevice_notifier(nb, NETDEV_UP, dev); } } - up_read(&net_rwsem); unlock: rtnl_unlock(); @@ -1671,7 +1669,6 @@ rollback: } outroll: - up_read(&net_rwsem); raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } @@ -1704,7 +1701,6 @@ int unregister_netdevice_notifier(struct notifier_block *nb) if (err) goto unlock; - down_read(&net_rwsem); for_each_net(net) { for_each_netdev(net, dev) { if (dev->flags & IFF_UP) { @@ -1715,7 +1711,6 @@ int unregister_netdevice_notifier(struct notifier_block *nb) call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); } } - up_read(&net_rwsem); unlock: rtnl_unlock(); up_write(&pernet_ops_rwsem); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 7fdf321d4997..a11e03f920d3 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -51,6 +51,7 @@ static bool init_net_initialized; * outside. */ DECLARE_RWSEM(pernet_ops_rwsem); +EXPORT_SYMBOL_GPL(pernet_ops_rwsem); #define MIN_PERNET_OPS_ID \ ((sizeof(struct net_generic) + sizeof(void *) - 1) / sizeof(void *)) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e86b28482ca7..45936922d7e2 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -412,17 +412,17 @@ static void __rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops) * __rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink. * @ops: struct rtnl_link_ops * to unregister * - * The caller must hold the rtnl_mutex. + * The caller must hold the rtnl_mutex and guarantee net_namespace_list + * integrity (hold pernet_ops_rwsem for writing to close the race + * with setup_net() and cleanup_net()). */ void __rtnl_link_unregister(struct rtnl_link_ops *ops) { struct net *net; - down_read(&net_rwsem); for_each_net(net) { __rtnl_kill_links(net, ops); } - up_read(&net_rwsem); list_del(&ops->list); } EXPORT_SYMBOL_GPL(__rtnl_link_unregister); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index ec5ec68be1aa..9a2c8e7c000e 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -324,6 +324,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, mutex_unlock(&call->user_mutex); } + rxrpc_put_peer(cp.peer); _leave(" = %p", call); return call; } @@ -447,6 +448,7 @@ int rxrpc_kernel_retry_call(struct socket *sock, struct rxrpc_call *call, ret = rxrpc_retry_client_call(rx, call, &cp, srx, GFP_KERNEL); mutex_unlock(&call->user_mutex); + rxrpc_put_peer(cp.peer); _leave(" = %d", ret); return ret; } @@ -762,6 +764,7 @@ static __poll_t rxrpc_poll(struct file *file, struct socket *sock, static int rxrpc_create(struct net *net, struct socket *sock, int protocol, int kern) { + struct rxrpc_net *rxnet; struct rxrpc_sock *rx; struct sock *sk; @@ -801,6 +804,9 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol, rwlock_init(&rx->call_lock); memset(&rx->srx, 0, sizeof(rx->srx)); + rxnet = rxrpc_net(sock_net(&rx->sk)); + timer_reduce(&rxnet->peer_keepalive_timer, jiffies + 1); + _leave(" = 0 [%p]", rx); return 0; } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 21cf164b6d85..90d7079e0aa9 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -75,7 +75,9 @@ struct rxrpc_net { u32 epoch; /* Local epoch for detecting local-end reset */ struct list_head calls; /* List of calls active in this namespace */ rwlock_t call_lock; /* Lock for ->calls */ + atomic_t nr_calls; /* Count of allocated calls */ + atomic_t nr_conns; struct list_head conn_proc_list; /* List of conns in this namespace for proc */ struct list_head service_conns; /* Service conns in this namespace */ rwlock_t conn_lock; /* Lock for ->conn_proc_list, ->service_conns */ @@ -97,8 +99,16 @@ struct rxrpc_net { struct list_head local_endpoints; struct mutex local_mutex; /* Lock for ->local_endpoints */ - spinlock_t peer_hash_lock; /* Lock for ->peer_hash */ DECLARE_HASHTABLE (peer_hash, 10); + spinlock_t peer_hash_lock; /* Lock for ->peer_hash */ + +#define RXRPC_KEEPALIVE_TIME 20 /* NAT keepalive time in seconds */ + u8 peer_keepalive_cursor; + ktime_t peer_keepalive_base; + struct hlist_head peer_keepalive[RXRPC_KEEPALIVE_TIME + 1]; + struct hlist_head peer_keepalive_new; + struct timer_list peer_keepalive_timer; + struct work_struct peer_keepalive_work; }; /* @@ -285,6 +295,8 @@ struct rxrpc_peer { struct hlist_head error_targets; /* targets for net error distribution */ struct work_struct error_distributor; struct rb_root service_conns; /* Service connections */ + struct hlist_node keepalive_link; /* Link in net->peer_keepalive[] */ + time64_t last_tx_at; /* Last time packet sent here */ seqlock_t service_conn_lock; spinlock_t lock; /* access lock */ unsigned int if_mtu; /* interface MTU for this peer */ @@ -518,6 +530,7 @@ struct rxrpc_call { struct rxrpc_connection *conn; /* connection carrying call */ struct rxrpc_peer *peer; /* Peer record for remote address */ struct rxrpc_sock __rcu *socket; /* socket responsible */ + struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ struct mutex user_mutex; /* User access mutex */ unsigned long ack_at; /* When deferred ACK needs to happen */ unsigned long ack_lost_at; /* When ACK is figured as lost */ @@ -969,31 +982,12 @@ extern void rxrpc_process_local_events(struct rxrpc_local *); * local_object.c */ struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc *); -void __rxrpc_put_local(struct rxrpc_local *); +struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *); +struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *); +void rxrpc_put_local(struct rxrpc_local *); +void rxrpc_queue_local(struct rxrpc_local *); void rxrpc_destroy_all_locals(struct rxrpc_net *); -static inline void rxrpc_get_local(struct rxrpc_local *local) -{ - atomic_inc(&local->usage); -} - -static inline -struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) -{ - return atomic_inc_not_zero(&local->usage) ? local : NULL; -} - -static inline void rxrpc_put_local(struct rxrpc_local *local) -{ - if (local && atomic_dec_and_test(&local->usage)) - __rxrpc_put_local(local); -} - -static inline void rxrpc_queue_local(struct rxrpc_local *local) -{ - rxrpc_queue_work(&local->processor); -} - /* * misc.c */ @@ -1026,6 +1020,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *, bool, rxrpc_serial_t *); int rxrpc_send_abort_packet(struct rxrpc_call *); int rxrpc_send_data_packet(struct rxrpc_call *, struct sk_buff *, bool); void rxrpc_reject_packets(struct rxrpc_local *); +void rxrpc_send_keepalive(struct rxrpc_peer *); /* * peer_event.c @@ -1034,6 +1029,7 @@ void rxrpc_error_report(struct sock *); void rxrpc_peer_error_distributor(struct work_struct *); void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); +void rxrpc_peer_keepalive_worker(struct work_struct *); /* * peer_object.c @@ -1045,25 +1041,11 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *, struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t); struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *, struct rxrpc_peer *); - -static inline struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer) -{ - atomic_inc(&peer->usage); - return peer; -} - -static inline -struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) -{ - return atomic_inc_not_zero(&peer->usage) ? peer : NULL; -} - -extern void __rxrpc_put_peer(struct rxrpc_peer *peer); -static inline void rxrpc_put_peer(struct rxrpc_peer *peer) -{ - if (peer && atomic_dec_and_test(&peer->usage)) - __rxrpc_put_peer(peer); -} +void rxrpc_destroy_all_peers(struct rxrpc_net *); +struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *); +struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *); +void rxrpc_put_peer(struct rxrpc_peer *); +void __rxrpc_queue_peer_error(struct rxrpc_peer *); /* * proc.c diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 92ebd1d7e0bb..f67017dcb25e 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -138,6 +138,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, write_unlock(&rx->call_lock); + rxnet = call->rxnet; write_lock(&rxnet->call_lock); list_add_tail(&call->link, &rxnet->calls); write_unlock(&rxnet->call_lock); @@ -218,6 +219,8 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) list_del(&conn->proc_link); write_unlock(&rxnet->conn_lock); kfree(conn); + if (atomic_dec_and_test(&rxnet->nr_conns)) + wake_up_atomic_t(&rxnet->nr_conns); tail = (tail + 1) & (size - 1); } @@ -225,7 +228,7 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) tail = b->call_backlog_tail; while (CIRC_CNT(head, tail, size) > 0) { struct rxrpc_call *call = b->call_backlog[tail]; - call->socket = rx; + rcu_assign_pointer(call->socket, rx); if (rx->discard_new_call) { _debug("discard %lx", call->user_call_ID); rx->discard_new_call(call, call->user_call_ID); @@ -295,8 +298,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, b->conn_backlog[conn_tail] = NULL; smp_store_release(&b->conn_backlog_tail, (conn_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); - rxrpc_get_local(local); - conn->params.local = local; + conn->params.local = rxrpc_get_local(local); conn->params.peer = peer; rxrpc_see_connection(conn); rxrpc_new_incoming_connection(rx, conn, skb); @@ -456,6 +458,7 @@ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, unsigned long user_call_ID, rxrpc_notify_rx_t notify_rx) __releases(&rx->sk.sk_lock.slock) + __acquires(call->user_mutex) { struct rxrpc_call *call; struct rb_node *parent, **pp; diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 6a62e42e1d8d..6e0d788b4dc4 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -226,7 +226,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) ktime_to_ns(ktime_sub(skb->tstamp, max_age))); } - resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(oldest, now))); + resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); resend_at += jiffies + rxrpc_resend_timeout; WRITE_ONCE(call->resend_at, resend_at); @@ -238,7 +238,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) * retransmitting data. */ if (!retrans) { - rxrpc_reduce_call_timer(call, resend_at, now, + rxrpc_reduce_call_timer(call, resend_at, now_j, rxrpc_timer_set_for_resend); spin_unlock_bh(&call->lock); ack_ts = ktime_sub(now, call->acks_latest_ts); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 147657dfe757..f721c2b7e234 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -103,6 +103,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, unsigned int debug_id) { struct rxrpc_call *call; + struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); call = kmem_cache_zalloc(rxrpc_call_jar, gfp); if (!call) @@ -153,6 +154,9 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, call->cong_cwnd = 2; call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1; + + call->rxnet = rxnet; + atomic_inc(&rxnet->nr_calls); return call; nomem_2: @@ -219,9 +223,10 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, gfp_t gfp, unsigned int debug_id) __releases(&rx->sk.sk_lock.slock) + __acquires(&call->user_mutex) { struct rxrpc_call *call, *xcall; - struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); + struct rxrpc_net *rxnet; struct rb_node *parent, **pp; const void *here = __builtin_return_address(0); int ret; @@ -271,6 +276,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, write_unlock(&rx->call_lock); + rxnet = call->rxnet; write_lock(&rxnet->call_lock); list_add_tail(&call->link, &rxnet->calls); write_unlock(&rxnet->call_lock); @@ -616,7 +622,7 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) */ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) { - struct rxrpc_net *rxnet; + struct rxrpc_net *rxnet = call->rxnet; const void *here = __builtin_return_address(0); int n; @@ -630,7 +636,6 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); if (!list_empty(&call->link)) { - rxnet = rxrpc_net(sock_net(&call->socket->sk)); write_lock(&rxnet->call_lock); list_del_init(&call->link); write_unlock(&rxnet->call_lock); @@ -646,11 +651,14 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) { struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu); + struct rxrpc_net *rxnet = call->rxnet; rxrpc_put_peer(call->peer); kfree(call->rxtx_buffer); kfree(call->rxtx_annotations); kmem_cache_free(rxrpc_call_jar, call); + if (atomic_dec_and_test(&rxnet->nr_calls)) + wake_up_atomic_t(&rxnet->nr_calls); } /* @@ -715,4 +723,7 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet) } write_unlock(&rxnet->call_lock); + + atomic_dec(&rxnet->nr_calls); + wait_on_atomic_t(&rxnet->nr_calls, atomic_t_wait, TASK_UNINTERRUPTIBLE); } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 064175068059..5736f643c516 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -207,6 +207,7 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) if (ret < 0) goto error_2; + atomic_inc(&rxnet->nr_conns); write_lock(&rxnet->conn_lock); list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); write_unlock(&rxnet->conn_lock); @@ -776,7 +777,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) unsigned int channel = call->cid & RXRPC_CHANNELMASK; struct rxrpc_connection *conn = call->conn; struct rxrpc_channel *chan = &conn->channels[channel]; - struct rxrpc_net *rxnet = rxrpc_net(sock_net(&call->socket->sk)); + struct rxrpc_net *rxnet = conn->params.local->rxnet; trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect); call->conn = NULL; diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index d2ec3fd593e8..c717152070df 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -136,6 +136,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, } kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len); + conn->params.peer->last_tx_at = ktime_get_real(); _leave(""); return; } @@ -239,6 +240,8 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, return -EAGAIN; } + conn->params.peer->last_tx_at = ktime_get_real(); + _leave(" = 0"); return 0; } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index ccbac190add1..0950ee3d26f5 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -365,6 +365,9 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu) key_put(conn->params.key); key_put(conn->server_key); rxrpc_put_peer(conn->params.peer); + + if (atomic_dec_and_test(&conn->params.local->rxnet->nr_conns)) + wake_up_atomic_t(&conn->params.local->rxnet->nr_conns); rxrpc_put_local(conn->params.local); kfree(conn); @@ -418,7 +421,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) */ if (atomic_cmpxchg(&conn->usage, 1, 0) != 1) continue; - trace_rxrpc_conn(conn, rxrpc_conn_reap_service, 0, 0); + trace_rxrpc_conn(conn, rxrpc_conn_reap_service, 0, NULL); if (rxrpc_conn_is_client(conn)) BUG(); @@ -458,6 +461,7 @@ void rxrpc_destroy_all_connections(struct rxrpc_net *rxnet) _enter(""); + atomic_dec(&rxnet->nr_conns); rxrpc_destroy_all_client_connections(rxnet); del_timer_sync(&rxnet->service_conn_reap_timer); @@ -475,5 +479,9 @@ void rxrpc_destroy_all_connections(struct rxrpc_net *rxnet) ASSERT(list_empty(&rxnet->conn_proc_list)); + /* We need to wait for the connections to be destroyed by RCU as they + * pin things that we still need to get rid of. + */ + wait_on_atomic_t(&rxnet->nr_conns, atomic_t_wait, TASK_UNINTERRUPTIBLE); _leave(""); } diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index f6fcdb3130a1..80773a50c755 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -132,6 +132,7 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn conn->state = RXRPC_CONN_SERVICE_PREALLOC; atomic_set(&conn->usage, 2); + atomic_inc(&rxnet->nr_conns); write_lock(&rxnet->conn_lock); list_add_tail(&conn->link, &rxnet->service_conns); list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 2a868fdab0ae..21800e6f5019 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1183,6 +1183,8 @@ void rxrpc_data_ready(struct sock *udp_sk) switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_VERSION: + if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED)) + goto discard; rxrpc_post_packet_to_local(local, skb); goto out; @@ -1240,16 +1242,19 @@ void rxrpc_data_ready(struct sock *udp_sk) goto discard_unlock; if (sp->hdr.callNumber == chan->last_call) { - /* For the previous service call, if completed successfully, we - * discard all further packets. + if (chan->call || + sp->hdr.type == RXRPC_PACKET_TYPE_ABORT) + goto discard_unlock; + + /* For the previous service call, if completed + * successfully, we discard all further packets. */ if (rxrpc_conn_is_service(conn) && - (chan->last_type == RXRPC_PACKET_TYPE_ACK || - sp->hdr.type == RXRPC_PACKET_TYPE_ABORT)) + chan->last_type == RXRPC_PACKET_TYPE_ACK) goto discard_unlock; - /* But otherwise we need to retransmit the final packet from - * data cached in the connection record. + /* But otherwise we need to retransmit the final packet + * from data cached in the connection record. */ rxrpc_post_packet_to_conn(conn, skb); goto out_unlock; diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 38b99db30e54..8b54e9531d52 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -95,6 +95,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local->debug_id = atomic_inc_return(&rxrpc_debug_id); memcpy(&local->srx, srx, sizeof(*srx)); local->srx.srx_service = 0; + trace_rxrpc_local(local, rxrpc_local_new, 1, NULL); } _leave(" = %p", local); @@ -257,15 +258,74 @@ addr_in_use: } /* + * Get a ref on a local endpoint. + */ +struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local) +{ + const void *here = __builtin_return_address(0); + int n; + + n = atomic_inc_return(&local->usage); + trace_rxrpc_local(local, rxrpc_local_got, n, here); + return local; +} + +/* + * Get a ref on a local endpoint unless its usage has already reached 0. + */ +struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) +{ + const void *here = __builtin_return_address(0); + + if (local) { + int n = __atomic_add_unless(&local->usage, 1, 0); + if (n > 0) + trace_rxrpc_local(local, rxrpc_local_got, n + 1, here); + else + local = NULL; + } + return local; +} + +/* + * Queue a local endpoint. + */ +void rxrpc_queue_local(struct rxrpc_local *local) +{ + const void *here = __builtin_return_address(0); + + if (rxrpc_queue_work(&local->processor)) + trace_rxrpc_local(local, rxrpc_local_queued, + atomic_read(&local->usage), here); +} + +/* * A local endpoint reached its end of life. */ -void __rxrpc_put_local(struct rxrpc_local *local) +static void __rxrpc_put_local(struct rxrpc_local *local) { _enter("%d", local->debug_id); rxrpc_queue_work(&local->processor); } /* + * Drop a ref on a local endpoint. + */ +void rxrpc_put_local(struct rxrpc_local *local) +{ + const void *here = __builtin_return_address(0); + int n; + + if (local) { + n = atomic_dec_return(&local->usage); + trace_rxrpc_local(local, rxrpc_local_put, n, here); + + if (n == 0) + __rxrpc_put_local(local); + } +} + +/* * Destroy a local endpoint's socket and then hand the record to RCU to dispose * of. * @@ -322,7 +382,8 @@ static void rxrpc_local_processor(struct work_struct *work) container_of(work, struct rxrpc_local, processor); bool again; - _enter("%d", local->debug_id); + trace_rxrpc_local(local, rxrpc_local_processing, + atomic_read(&local->usage), NULL); do { again = false; diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index f18c9248e0d4..c7a023fb22d0 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -32,13 +32,22 @@ static void rxrpc_service_conn_reap_timeout(struct timer_list *timer) rxrpc_queue_work(&rxnet->service_conn_reaper); } +static void rxrpc_peer_keepalive_timeout(struct timer_list *timer) +{ + struct rxrpc_net *rxnet = + container_of(timer, struct rxrpc_net, peer_keepalive_timer); + + if (rxnet->live) + rxrpc_queue_work(&rxnet->peer_keepalive_work); +} + /* * Initialise a per-network namespace record. */ static __net_init int rxrpc_init_net(struct net *net) { struct rxrpc_net *rxnet = rxrpc_net(net); - int ret; + int ret, i; rxnet->live = true; get_random_bytes(&rxnet->epoch, sizeof(rxnet->epoch)); @@ -46,7 +55,9 @@ static __net_init int rxrpc_init_net(struct net *net) INIT_LIST_HEAD(&rxnet->calls); rwlock_init(&rxnet->call_lock); + atomic_set(&rxnet->nr_calls, 1); + atomic_set(&rxnet->nr_conns, 1); INIT_LIST_HEAD(&rxnet->conn_proc_list); INIT_LIST_HEAD(&rxnet->service_conns); rwlock_init(&rxnet->conn_lock); @@ -70,8 +81,16 @@ static __net_init int rxrpc_init_net(struct net *net) INIT_LIST_HEAD(&rxnet->local_endpoints); mutex_init(&rxnet->local_mutex); + hash_init(rxnet->peer_hash); spin_lock_init(&rxnet->peer_hash_lock); + for (i = 0; i < ARRAY_SIZE(rxnet->peer_keepalive); i++) + INIT_HLIST_HEAD(&rxnet->peer_keepalive[i]); + INIT_HLIST_HEAD(&rxnet->peer_keepalive_new); + timer_setup(&rxnet->peer_keepalive_timer, + rxrpc_peer_keepalive_timeout, 0); + INIT_WORK(&rxnet->peer_keepalive_work, rxrpc_peer_keepalive_worker); + rxnet->peer_keepalive_base = ktime_add(ktime_get_real(), NSEC_PER_SEC); ret = -ENOMEM; rxnet->proc_net = proc_net_mkdir(net, "rxrpc", net->proc_net); @@ -95,8 +114,11 @@ static __net_exit void rxrpc_exit_net(struct net *net) struct rxrpc_net *rxnet = rxrpc_net(net); rxnet->live = false; + del_timer_sync(&rxnet->peer_keepalive_timer); + cancel_work_sync(&rxnet->peer_keepalive_work); rxrpc_destroy_all_calls(rxnet); rxrpc_destroy_all_connections(rxnet); + rxrpc_destroy_all_peers(rxnet); rxrpc_destroy_all_locals(rxnet); proc_remove(rxnet->proc_net); } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index cf73dc006c3b..7f1fc04775b3 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -32,6 +32,8 @@ struct rxrpc_abort_buffer { __be32 abort_code; }; +static const char rxrpc_keepalive_string[] = ""; + /* * Arrange for a keepalive ping a certain time after we last transmitted. This * lets the far side know we're still interested in this call and helps keep @@ -122,6 +124,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, struct kvec iov[2]; rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; + ktime_t now; size_t len, n; int ret; u8 reason; @@ -203,8 +206,10 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, } ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); + now = ktime_get_real(); if (ping) - call->ping_time = ktime_get_real(); + call->ping_time = now; + conn->params.peer->last_tx_at = ktime_get_real(); if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { @@ -288,6 +293,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 1, sizeof(pkt)); + conn->params.peer->last_tx_at = ktime_get_real(); rxrpc_put_connection(conn); return ret; @@ -378,6 +384,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, * message and update the peer record */ ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); + conn->params.peer->last_tx_at = ktime_get_real(); up_read(&conn->params.local->defrag_sem); if (ret == -EMSGSIZE) @@ -429,6 +436,7 @@ send_fragmentable: if (ret == 0) { ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); + conn->params.peer->last_tx_at = ktime_get_real(); opt = IP_PMTUDISC_DO; kernel_setsockopt(conn->params.local->socket, SOL_IP, @@ -446,6 +454,7 @@ send_fragmentable: if (ret == 0) { ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); + conn->params.peer->last_tx_at = ktime_get_real(); opt = IPV6_PMTUDISC_DO; kernel_setsockopt(conn->params.local->socket, @@ -515,3 +524,51 @@ void rxrpc_reject_packets(struct rxrpc_local *local) _leave(""); } + +/* + * Send a VERSION reply to a peer as a keepalive. + */ +void rxrpc_send_keepalive(struct rxrpc_peer *peer) +{ + struct rxrpc_wire_header whdr; + struct msghdr msg; + struct kvec iov[2]; + size_t len; + int ret; + + _enter(""); + + msg.msg_name = &peer->srx.transport; + msg.msg_namelen = peer->srx.transport_len; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + whdr.epoch = htonl(peer->local->rxnet->epoch); + whdr.cid = 0; + whdr.callNumber = 0; + whdr.seq = 0; + whdr.serial = 0; + whdr.type = RXRPC_PACKET_TYPE_VERSION; /* Not client-initiated */ + whdr.flags = RXRPC_LAST_PACKET; + whdr.userStatus = 0; + whdr.securityIndex = 0; + whdr._rsvd = 0; + whdr.serviceId = 0; + + iov[0].iov_base = &whdr; + iov[0].iov_len = sizeof(whdr); + iov[1].iov_base = (char *)rxrpc_keepalive_string; + iov[1].iov_len = sizeof(rxrpc_keepalive_string); + + len = iov[0].iov_len + iov[1].iov_len; + + _proto("Tx VERSION (keepalive)"); + + ret = kernel_sendmsg(peer->local->socket, &msg, iov, 2, len); + if (ret < 0) + _debug("sendmsg failed: %d", ret); + + peer->last_tx_at = ktime_get_real(); + _leave(""); +} diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 7f749505e699..78c2f95d1f22 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -192,7 +192,7 @@ void rxrpc_error_report(struct sock *sk) rxrpc_free_skb(skb, rxrpc_skb_rx_freed); /* The ref we obtained is passed off to the work item */ - rxrpc_queue_work(&peer->error_distributor); + __rxrpc_queue_peer_error(peer); _leave(""); } @@ -348,3 +348,99 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt, usage, avg); } + +/* + * Perform keep-alive pings with VERSION packets to keep any NAT alive. + */ +void rxrpc_peer_keepalive_worker(struct work_struct *work) +{ + struct rxrpc_net *rxnet = + container_of(work, struct rxrpc_net, peer_keepalive_work); + struct rxrpc_peer *peer; + unsigned long delay; + ktime_t base, now = ktime_get_real(); + s64 diff; + u8 cursor, slot; + + base = rxnet->peer_keepalive_base; + cursor = rxnet->peer_keepalive_cursor; + + _enter("%u,%lld", cursor, ktime_sub(now, base)); + +next_bucket: + diff = ktime_to_ns(ktime_sub(now, base)); + if (diff < 0) + goto resched; + + _debug("at %u", cursor); + spin_lock_bh(&rxnet->peer_hash_lock); +next_peer: + if (!rxnet->live) { + spin_unlock_bh(&rxnet->peer_hash_lock); + goto out; + } + + /* Everything in the bucket at the cursor is processed this second; the + * bucket at cursor + 1 goes now + 1s and so on... + */ + if (hlist_empty(&rxnet->peer_keepalive[cursor])) { + if (hlist_empty(&rxnet->peer_keepalive_new)) { + spin_unlock_bh(&rxnet->peer_hash_lock); + goto emptied_bucket; + } + + hlist_move_list(&rxnet->peer_keepalive_new, + &rxnet->peer_keepalive[cursor]); + } + + peer = hlist_entry(rxnet->peer_keepalive[cursor].first, + struct rxrpc_peer, keepalive_link); + hlist_del_init(&peer->keepalive_link); + if (!rxrpc_get_peer_maybe(peer)) + goto next_peer; + + spin_unlock_bh(&rxnet->peer_hash_lock); + + _debug("peer %u {%pISp}", peer->debug_id, &peer->srx.transport); + +recalc: + diff = ktime_divns(ktime_sub(peer->last_tx_at, base), NSEC_PER_SEC); + if (diff < -30 || diff > 30) + goto send; /* LSW of 64-bit time probably wrapped on 32-bit */ + diff += RXRPC_KEEPALIVE_TIME - 1; + if (diff < 0) + goto send; + + slot = (diff > RXRPC_KEEPALIVE_TIME - 1) ? RXRPC_KEEPALIVE_TIME - 1 : diff; + if (slot == 0) + goto send; + + /* A transmission to this peer occurred since last we examined it so + * put it into the appropriate future bucket. + */ + slot = (slot + cursor) % ARRAY_SIZE(rxnet->peer_keepalive); + spin_lock_bh(&rxnet->peer_hash_lock); + hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive[slot]); + rxrpc_put_peer(peer); + goto next_peer; + +send: + rxrpc_send_keepalive(peer); + now = ktime_get_real(); + goto recalc; + +emptied_bucket: + cursor++; + if (cursor >= ARRAY_SIZE(rxnet->peer_keepalive)) + cursor = 0; + base = ktime_add_ns(base, NSEC_PER_SEC); + goto next_bucket; + +resched: + rxnet->peer_keepalive_base = base; + rxnet->peer_keepalive_cursor = cursor; + delay = nsecs_to_jiffies(-diff) + 1; + timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay); +out: + _leave(""); +} diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index d02a99f37f5f..1b7e8107b3ae 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -322,6 +322,7 @@ struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local, if (!peer) { peer = prealloc; hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); + hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive_new); } spin_unlock(&rxnet->peer_hash_lock); @@ -363,9 +364,12 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); if (peer && !rxrpc_get_peer_maybe(peer)) peer = NULL; - if (!peer) + if (!peer) { hash_add_rcu(rxnet->peer_hash, &candidate->hash_link, hash_key); + hlist_add_head(&candidate->keepalive_link, + &rxnet->peer_keepalive_new); + } spin_unlock_bh(&rxnet->peer_hash_lock); @@ -382,9 +386,54 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, } /* - * Discard a ref on a remote peer record. + * Get a ref on a peer record. + */ +struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer) +{ + const void *here = __builtin_return_address(0); + int n; + + n = atomic_inc_return(&peer->usage); + trace_rxrpc_peer(peer, rxrpc_peer_got, n, here); + return peer; +} + +/* + * Get a ref on a peer record unless its usage has already reached 0. + */ +struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) +{ + const void *here = __builtin_return_address(0); + + if (peer) { + int n = __atomic_add_unless(&peer->usage, 1, 0); + if (n > 0) + trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here); + else + peer = NULL; + } + return peer; +} + +/* + * Queue a peer record. This passes the caller's ref to the workqueue. + */ +void __rxrpc_queue_peer_error(struct rxrpc_peer *peer) +{ + const void *here = __builtin_return_address(0); + int n; + + n = atomic_read(&peer->usage); + if (rxrpc_queue_work(&peer->error_distributor)) + trace_rxrpc_peer(peer, rxrpc_peer_queued_error, n, here); + else + rxrpc_put_peer(peer); +} + +/* + * Discard a peer record. */ -void __rxrpc_put_peer(struct rxrpc_peer *peer) +static void __rxrpc_put_peer(struct rxrpc_peer *peer) { struct rxrpc_net *rxnet = peer->local->rxnet; @@ -392,11 +441,49 @@ void __rxrpc_put_peer(struct rxrpc_peer *peer) spin_lock_bh(&rxnet->peer_hash_lock); hash_del_rcu(&peer->hash_link); + hlist_del_init(&peer->keepalive_link); spin_unlock_bh(&rxnet->peer_hash_lock); kfree_rcu(peer, rcu); } +/* + * Drop a ref on a peer record. + */ +void rxrpc_put_peer(struct rxrpc_peer *peer) +{ + const void *here = __builtin_return_address(0); + int n; + + if (peer) { + n = atomic_dec_return(&peer->usage); + trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + if (n == 0) + __rxrpc_put_peer(peer); + } +} + +/* + * Make sure all peer records have been discarded. + */ +void rxrpc_destroy_all_peers(struct rxrpc_net *rxnet) +{ + struct rxrpc_peer *peer; + int i; + + for (i = 0; i < HASH_SIZE(rxnet->peer_hash); i++) { + if (hlist_empty(&rxnet->peer_hash[i])) + continue; + + hlist_for_each_entry(peer, &rxnet->peer_hash[i], hash_link) { + pr_err("Leaked peer %u {%u} %pISp\n", + peer->debug_id, + atomic_read(&peer->usage), + &peer->srx.transport); + } + } +} + /** * rxrpc_kernel_get_peer - Get the peer address of a call * @sock: The socket on which the call is in progress. diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index f79f260c6ddc..7e45db058823 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -29,6 +29,8 @@ static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = { * generate a list of extant and dead calls in /proc/net/rxrpc_calls */ static void *rxrpc_call_seq_start(struct seq_file *seq, loff_t *_pos) + __acquires(rcu) + __acquires(rxnet->call_lock) { struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); @@ -45,6 +47,8 @@ static void *rxrpc_call_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void rxrpc_call_seq_stop(struct seq_file *seq, void *v) + __releases(rxnet->call_lock) + __releases(rcu) { struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); @@ -135,6 +139,7 @@ const struct file_operations rxrpc_call_seq_fops = { * generate a list of extant virtual connections in /proc/net/rxrpc_conns */ static void *rxrpc_connection_seq_start(struct seq_file *seq, loff_t *_pos) + __acquires(rxnet->conn_lock) { struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); @@ -151,6 +156,7 @@ static void *rxrpc_connection_seq_next(struct seq_file *seq, void *v, } static void rxrpc_connection_seq_stop(struct seq_file *seq, void *v) + __releases(rxnet->conn_lock) { struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 77cb23c7bd0a..588fea0dd362 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -668,6 +668,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) return -EAGAIN; } + conn->params.peer->last_tx_at = ktime_get_real(); _leave(" = 0"); return 0; } @@ -722,6 +723,7 @@ static int rxkad_send_response(struct rxrpc_connection *conn, return -EAGAIN; } + conn->params.peer->last_tx_at = ktime_get_real(); _leave(" = 0"); return 0; } diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index e9f428351293..c4479afe8ae7 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -19,9 +19,6 @@ #include <keys/rxrpc-type.h> #include "ar-internal.h" -static LIST_HEAD(rxrpc_security_methods); -static DECLARE_RWSEM(rxrpc_security_sem); - static const struct rxrpc_security *rxrpc_security_types[] = { [RXRPC_SECURITY_NONE] = &rxrpc_no_security, #ifdef CONFIG_RXKAD diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 8503f279b467..206e802ccbdc 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -130,7 +130,9 @@ static inline void rxrpc_instant_resend(struct rxrpc_call *call, int ix) spin_lock_bh(&call->lock); if (call->state < RXRPC_CALL_COMPLETE) { - call->rxtx_annotations[ix] = RXRPC_TX_ANNO_RETRANS; + call->rxtx_annotations[ix] = + (call->rxtx_annotations[ix] & RXRPC_TX_ANNO_LAST) | + RXRPC_TX_ANNO_RETRANS; if (!test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) rxrpc_queue_call(call); } @@ -554,6 +556,7 @@ static struct rxrpc_call * rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, struct rxrpc_send_params *p) __releases(&rx->sk.sk_lock.slock) + __acquires(&call->user_mutex) { struct rxrpc_conn_parameters cp; struct rxrpc_call *call; @@ -583,6 +586,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, atomic_inc_return(&rxrpc_debug_id)); /* The socket is now unlocked */ + rxrpc_put_peer(cp.peer); _leave(" = %p\n", call); return call; } @@ -594,6 +598,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, */ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) __releases(&rx->sk.sk_lock.slock) + __releases(&call->user_mutex) { enum rxrpc_call_state state; struct rxrpc_call *call; diff --git a/net/tipc/core.h b/net/tipc/core.h index d0f64ca62d02..8020a6c360ff 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -58,6 +58,7 @@ #include <linux/etherdevice.h> #include <net/netns/generic.h> #include <linux/rhashtable.h> +#include <net/genetlink.h> struct tipc_node; struct tipc_bearer; diff --git a/net/tipc/link.c b/net/tipc/link.c index 1289b4ba404f..695acb783969 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -462,7 +462,8 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, sprintf(peer_str, "%x", peer); } /* Peer i/f name will be completed by reset/activate message */ - sprintf(l->name, "%s:%s-%s:unknown", self_str, if_name, peer_str); + snprintf(l->name, sizeof(l->name), "%s:%s-%s:unknown", + self_str, if_name, peer_str); strcpy(l->if_name, if_name); l->addr = peer; @@ -1810,7 +1811,7 @@ int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb, void tipc_link_set_queue_limits(struct tipc_link *l, u32 win) { - int max_bulk = TIPC_MAX_PUBLICATIONS / (l->mtu / ITEM_SIZE); + int max_bulk = TIPC_MAX_PUBL / (l->mtu / ITEM_SIZE); l->window = win; l->backlog[TIPC_LOW_IMPORTANCE].limit = max_t(u16, 50, win); diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 8240a85b0d0c..51b4b96f89db 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -204,12 +204,12 @@ void tipc_named_node_up(struct net *net, u32 dnode) */ static void tipc_publ_purge(struct net *net, struct publication *publ, u32 addr) { - struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_net *tn = tipc_net(net); struct publication *p; spin_lock_bh(&tn->nametbl_lock); - p = tipc_nametbl_remove_publ(net, publ->type, publ->lower, - publ->node, publ->port, publ->key); + p = tipc_nametbl_remove_publ(net, publ->type, publ->lower, publ->upper, + publ->node, publ->key); if (p) tipc_node_unsubscribe(net, &p->binding_node, addr); spin_unlock_bh(&tn->nametbl_lock); @@ -261,28 +261,31 @@ void tipc_publ_notify(struct net *net, struct list_head *nsub_list, u32 addr) static bool tipc_update_nametbl(struct net *net, struct distr_item *i, u32 node, u32 dtype) { - struct publication *publ = NULL; + struct publication *p = NULL; + u32 lower = ntohl(i->lower); + u32 upper = ntohl(i->upper); + u32 type = ntohl(i->type); + u32 port = ntohl(i->port); + u32 key = ntohl(i->key); if (dtype == PUBLICATION) { - publ = tipc_nametbl_insert_publ(net, ntohl(i->type), - ntohl(i->lower), - ntohl(i->upper), - TIPC_CLUSTER_SCOPE, node, - ntohl(i->port), ntohl(i->key)); - if (publ) { - tipc_node_subscribe(net, &publ->binding_node, node); + p = tipc_nametbl_insert_publ(net, type, lower, upper, + TIPC_CLUSTER_SCOPE, node, + port, key); + if (p) { + tipc_node_subscribe(net, &p->binding_node, node); return true; } } else if (dtype == WITHDRAWAL) { - publ = tipc_nametbl_remove_publ(net, ntohl(i->type), - ntohl(i->lower), - node, ntohl(i->port), - ntohl(i->key)); - if (publ) { - tipc_node_unsubscribe(net, &publ->binding_node, node); - kfree_rcu(publ, rcu); + p = tipc_nametbl_remove_publ(net, type, lower, + upper, node, key); + if (p) { + tipc_node_unsubscribe(net, &p->binding_node, node); + kfree_rcu(p, rcu); return true; } + pr_warn_ratelimited("Failed to remove binding %u,%u from %x\n", + type, lower, node); } else { pr_warn("Unrecognized name table message received\n"); } @@ -290,53 +293,6 @@ static bool tipc_update_nametbl(struct net *net, struct distr_item *i, } /** - * tipc_named_add_backlog - add a failed name table update to the backlog - * - */ -static void tipc_named_add_backlog(struct net *net, struct distr_item *i, - u32 type, u32 node) -{ - struct distr_queue_item *e; - struct tipc_net *tn = net_generic(net, tipc_net_id); - unsigned long now = get_jiffies_64(); - - e = kzalloc(sizeof(*e), GFP_ATOMIC); - if (!e) - return; - e->dtype = type; - e->node = node; - e->expires = now + msecs_to_jiffies(sysctl_tipc_named_timeout); - memcpy(e, i, sizeof(*i)); - list_add_tail(&e->next, &tn->dist_queue); -} - -/** - * tipc_named_process_backlog - try to process any pending name table updates - * from the network. - */ -void tipc_named_process_backlog(struct net *net) -{ - struct distr_queue_item *e, *tmp; - struct tipc_net *tn = net_generic(net, tipc_net_id); - unsigned long now = get_jiffies_64(); - - list_for_each_entry_safe(e, tmp, &tn->dist_queue, next) { - if (time_after(e->expires, now)) { - if (!tipc_update_nametbl(net, &e->i, e->node, e->dtype)) - continue; - } else { - pr_warn_ratelimited("Dropping name table update (%d) of {%u, %u, %u} from %x key=%u\n", - e->dtype, ntohl(e->i.type), - ntohl(e->i.lower), - ntohl(e->i.upper), - e->node, ntohl(e->i.key)); - } - list_del(&e->next); - kfree(e); - } -} - -/** * tipc_named_rcv - process name table update messages sent by another node */ void tipc_named_rcv(struct net *net, struct sk_buff_head *inputq) @@ -358,12 +314,10 @@ void tipc_named_rcv(struct net *net, struct sk_buff_head *inputq) count = msg_data_sz(msg) / ITEM_SIZE; node = msg_orignode(msg); while (count--) { - if (!tipc_update_nametbl(net, item, node, mtype)) - tipc_named_add_backlog(net, item, mtype, node); + tipc_update_nametbl(net, item, node, mtype); item++; } kfree_skb(skb); - tipc_named_process_backlog(net); } spin_unlock_bh(&tn->nametbl_lock); } diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h index 4753e628d7c4..63fc73e0fa6c 100644 --- a/net/tipc/name_distr.h +++ b/net/tipc/name_distr.h @@ -72,7 +72,6 @@ struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ); void tipc_named_node_up(struct net *net, u32 dnode); void tipc_named_rcv(struct net *net, struct sk_buff_head *msg_queue); void tipc_named_reinit(struct net *net); -void tipc_named_process_backlog(struct net *net); void tipc_publ_notify(struct net *net, struct list_head *nsub_list, u32 addr); #endif diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 4359605b1bec..b1fe20972aa9 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -44,52 +44,40 @@ #include "addr.h" #include "node.h" #include "group.h" -#include <net/genetlink.h> - -#define TIPC_NAMETBL_SIZE 1024 /* must be a power of 2 */ /** - * struct name_info - name sequence publication info - * @node_list: list of publications on own node of this <type,lower,upper> - * @all_publ: list of all publications of this <type,lower,upper> + * struct service_range - container for all bindings of a service range + * @lower: service range lower bound + * @upper: service range upper bound + * @tree_node: member of service range RB tree + * @local_publ: list of identical publications made from this node + * Used by closest_first lookup and multicast lookup algorithm + * @all_publ: all publications identical to this one, whatever node and scope + * Used by round-robin lookup algorithm */ -struct name_info { - struct list_head local_publ; - struct list_head all_publ; -}; - -/** - * struct sub_seq - container for all published instances of a name sequence - * @lower: name sequence lower bound - * @upper: name sequence upper bound - * @info: pointer to name sequence publication info - */ -struct sub_seq { +struct service_range { u32 lower; u32 upper; - struct name_info *info; + struct rb_node tree_node; + struct list_head local_publ; + struct list_head all_publ; }; /** - * struct name_seq - container for all published instances of a name type - * @type: 32 bit 'type' value for name sequence - * @sseq: pointer to dynamically-sized array of sub-sequences of this 'type'; - * sub-sequences are sorted in ascending order - * @alloc: number of sub-sequences currently in array - * @first_free: array index of first unused sub-sequence entry - * @ns_list: links to adjacent name sequences in hash chain - * @subscriptions: list of subscriptions for this 'type' - * @lock: spinlock controlling access to publication lists of all sub-sequences + * struct tipc_service - container for all published instances of a service type + * @type: 32 bit 'type' value for service + * @ranges: rb tree containing all service ranges for this service + * @service_list: links to adjacent name ranges in hash chain + * @subscriptions: list of subscriptions for this service type + * @lock: spinlock controlling access to pertaining service ranges/publications * @rcu: RCU callback head used for deferred freeing */ -struct name_seq { +struct tipc_service { u32 type; - struct sub_seq *sseqs; - u32 alloc; - u32 first_free; - struct hlist_node ns_list; + struct rb_root ranges; + struct hlist_node service_list; struct list_head subscriptions; - spinlock_t lock; + spinlock_t lock; /* Covers service range list */ struct rcu_head rcu; }; @@ -99,17 +87,16 @@ static int hash(int x) } /** - * publ_create - create a publication structure + * tipc_publ_create - create a publication structure */ -static struct publication *publ_create(u32 type, u32 lower, u32 upper, - u32 scope, u32 node, u32 port, - u32 key) +static struct publication *tipc_publ_create(u32 type, u32 lower, u32 upper, + u32 scope, u32 node, u32 port, + u32 key) { struct publication *publ = kzalloc(sizeof(*publ), GFP_ATOMIC); - if (publ == NULL) { - pr_warn("Publication creation failure, no memory\n"); + + if (!publ) return NULL; - } publ->type = type; publ->lower = lower; @@ -119,446 +106,360 @@ static struct publication *publ_create(u32 type, u32 lower, u32 upper, publ->port = port; publ->key = key; INIT_LIST_HEAD(&publ->binding_sock); + INIT_LIST_HEAD(&publ->binding_node); + INIT_LIST_HEAD(&publ->local_publ); + INIT_LIST_HEAD(&publ->all_publ); return publ; } /** - * tipc_subseq_alloc - allocate a specified number of sub-sequence structures - */ -static struct sub_seq *tipc_subseq_alloc(u32 cnt) -{ - return kcalloc(cnt, sizeof(struct sub_seq), GFP_ATOMIC); -} - -/** - * tipc_nameseq_create - create a name sequence structure for the specified 'type' + * tipc_service_create - create a service structure for the specified 'type' * - * Allocates a single sub-sequence structure and sets it to all 0's. + * Allocates a single range structure and sets it to all 0's. */ -static struct name_seq *tipc_nameseq_create(u32 type, struct hlist_head *seq_head) +static struct tipc_service *tipc_service_create(u32 type, struct hlist_head *hd) { - struct name_seq *nseq = kzalloc(sizeof(*nseq), GFP_ATOMIC); - struct sub_seq *sseq = tipc_subseq_alloc(1); + struct tipc_service *service = kzalloc(sizeof(*service), GFP_ATOMIC); - if (!nseq || !sseq) { - pr_warn("Name sequence creation failed, no memory\n"); - kfree(nseq); - kfree(sseq); + if (!service) { + pr_warn("Service creation failed, no memory\n"); return NULL; } - spin_lock_init(&nseq->lock); - nseq->type = type; - nseq->sseqs = sseq; - nseq->alloc = 1; - INIT_HLIST_NODE(&nseq->ns_list); - INIT_LIST_HEAD(&nseq->subscriptions); - hlist_add_head_rcu(&nseq->ns_list, seq_head); - return nseq; + spin_lock_init(&service->lock); + service->type = type; + service->ranges = RB_ROOT; + INIT_HLIST_NODE(&service->service_list); + INIT_LIST_HEAD(&service->subscriptions); + hlist_add_head_rcu(&service->service_list, hd); + return service; } /** - * nameseq_find_subseq - find sub-sequence (if any) matching a name instance + * tipc_service_find_range - find service range matching a service instance * - * Very time-critical, so binary searches through sub-sequence array. + * Very time-critical, so binary search through range rb tree */ -static struct sub_seq *nameseq_find_subseq(struct name_seq *nseq, - u32 instance) +static struct service_range *tipc_service_find_range(struct tipc_service *sc, + u32 instance) { - struct sub_seq *sseqs = nseq->sseqs; - int low = 0; - int high = nseq->first_free - 1; - int mid; - - while (low <= high) { - mid = (low + high) / 2; - if (instance < sseqs[mid].lower) - high = mid - 1; - else if (instance > sseqs[mid].upper) - low = mid + 1; + struct rb_node *n = sc->ranges.rb_node; + struct service_range *sr; + + while (n) { + sr = container_of(n, struct service_range, tree_node); + if (sr->lower > instance) + n = n->rb_left; + else if (sr->upper < instance) + n = n->rb_right; else - return &sseqs[mid]; + return sr; } return NULL; } -/** - * nameseq_locate_subseq - determine position of name instance in sub-sequence - * - * Returns index in sub-sequence array of the entry that contains the specified - * instance value; if no entry contains that value, returns the position - * where a new entry for it would be inserted in the array. - * - * Note: Similar to binary search code for locating a sub-sequence. - */ -static u32 nameseq_locate_subseq(struct name_seq *nseq, u32 instance) +static struct service_range *tipc_service_create_range(struct tipc_service *sc, + u32 lower, u32 upper) { - struct sub_seq *sseqs = nseq->sseqs; - int low = 0; - int high = nseq->first_free - 1; - int mid; - - while (low <= high) { - mid = (low + high) / 2; - if (instance < sseqs[mid].lower) - high = mid - 1; - else if (instance > sseqs[mid].upper) - low = mid + 1; + struct rb_node **n, *parent = NULL; + struct service_range *sr, *tmp; + + n = &sc->ranges.rb_node; + while (*n) { + tmp = container_of(*n, struct service_range, tree_node); + parent = *n; + tmp = container_of(parent, struct service_range, tree_node); + if (lower < tmp->lower) + n = &(*n)->rb_left; + else if (lower > tmp->lower) + n = &(*n)->rb_right; + else if (upper < tmp->upper) + n = &(*n)->rb_left; + else if (upper > tmp->upper) + n = &(*n)->rb_right; else - return mid; + return tmp; } - return low; + sr = kzalloc(sizeof(*sr), GFP_ATOMIC); + if (!sr) + return NULL; + sr->lower = lower; + sr->upper = upper; + INIT_LIST_HEAD(&sr->local_publ); + INIT_LIST_HEAD(&sr->all_publ); + rb_link_node(&sr->tree_node, parent, n); + rb_insert_color(&sr->tree_node, &sc->ranges); + return sr; } -/** - * tipc_nameseq_insert_publ - */ -static struct publication *tipc_nameseq_insert_publ(struct net *net, - struct name_seq *nseq, +static struct publication *tipc_service_insert_publ(struct net *net, + struct tipc_service *sc, u32 type, u32 lower, u32 upper, u32 scope, - u32 node, u32 port, u32 key) + u32 node, u32 port, + u32 key) { - struct tipc_subscription *s; - struct tipc_subscription *st; - struct publication *publ; - struct sub_seq *sseq; - struct name_info *info; - int created_subseq = 0; - - sseq = nameseq_find_subseq(nseq, lower); - if (sseq) { - - /* Lower end overlaps existing entry => need an exact match */ - if ((sseq->lower != lower) || (sseq->upper != upper)) { - return NULL; - } - - info = sseq->info; + struct tipc_subscription *sub, *tmp; + struct service_range *sr; + struct publication *p; + bool first = false; - /* Check if an identical publication already exists */ - list_for_each_entry(publ, &info->all_publ, all_publ) { - if (publ->port == port && publ->key == key && - (!publ->node || publ->node == node)) - return NULL; - } - } else { - u32 inspos; - struct sub_seq *freesseq; + sr = tipc_service_create_range(sc, lower, upper); + if (!sr) + goto err; - /* Find where lower end should be inserted */ - inspos = nameseq_locate_subseq(nseq, lower); + first = list_empty(&sr->all_publ); - /* Fail if upper end overlaps into an existing entry */ - if ((inspos < nseq->first_free) && - (upper >= nseq->sseqs[inspos].lower)) { + /* Return if the publication already exists */ + list_for_each_entry(p, &sr->all_publ, all_publ) { + if (p->key == key && (!p->node || p->node == node)) return NULL; - } - - /* Ensure there is space for new sub-sequence */ - if (nseq->first_free == nseq->alloc) { - struct sub_seq *sseqs = tipc_subseq_alloc(nseq->alloc * 2); - - if (!sseqs) { - pr_warn("Cannot publish {%u,%u,%u}, no memory\n", - type, lower, upper); - return NULL; - } - memcpy(sseqs, nseq->sseqs, - nseq->alloc * sizeof(struct sub_seq)); - kfree(nseq->sseqs); - nseq->sseqs = sseqs; - nseq->alloc *= 2; - } - - info = kzalloc(sizeof(*info), GFP_ATOMIC); - if (!info) { - pr_warn("Cannot publish {%u,%u,%u}, no memory\n", - type, lower, upper); - return NULL; - } - - INIT_LIST_HEAD(&info->local_publ); - INIT_LIST_HEAD(&info->all_publ); - - /* Insert new sub-sequence */ - sseq = &nseq->sseqs[inspos]; - freesseq = &nseq->sseqs[nseq->first_free]; - memmove(sseq + 1, sseq, (freesseq - sseq) * sizeof(*sseq)); - memset(sseq, 0, sizeof(*sseq)); - nseq->first_free++; - sseq->lower = lower; - sseq->upper = upper; - sseq->info = info; - created_subseq = 1; } - /* Insert a publication */ - publ = publ_create(type, lower, upper, scope, node, port, key); - if (!publ) - return NULL; - - list_add(&publ->all_publ, &info->all_publ); - + /* Create and insert publication */ + p = tipc_publ_create(type, lower, upper, scope, node, port, key); + if (!p) + goto err; if (in_own_node(net, node)) - list_add(&publ->local_publ, &info->local_publ); + list_add(&p->local_publ, &sr->local_publ); + list_add(&p->all_publ, &sr->all_publ); /* Any subscriptions waiting for notification? */ - list_for_each_entry_safe(s, st, &nseq->subscriptions, nameseq_list) { - tipc_sub_report_overlap(s, publ->lower, publ->upper, - TIPC_PUBLISHED, publ->port, - publ->node, publ->scope, - created_subseq); + list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) { + tipc_sub_report_overlap(sub, p->lower, p->upper, TIPC_PUBLISHED, + p->port, p->node, p->scope, first); } - return publ; + return p; +err: + pr_warn("Failed to bind to %u,%u,%u, no memory\n", type, lower, upper); + return NULL; } /** - * tipc_nameseq_remove_publ - * - * NOTE: There may be cases where TIPC is asked to remove a publication - * that is not in the name table. For example, if another node issues a - * publication for a name sequence that overlaps an existing name sequence - * the publication will not be recorded, which means the publication won't - * be found when the name sequence is later withdrawn by that node. - * A failed withdraw request simply returns a failure indication and lets the - * caller issue any error or warning messages associated with such a problem. + * tipc_service_remove_publ - remove a publication from a service */ -static struct publication *tipc_nameseq_remove_publ(struct net *net, - struct name_seq *nseq, - u32 inst, u32 node, - u32 port, u32 key) +static struct publication *tipc_service_remove_publ(struct net *net, + struct tipc_service *sc, + u32 lower, u32 upper, + u32 node, u32 key) { - struct publication *publ; - struct sub_seq *sseq = nameseq_find_subseq(nseq, inst); - struct name_info *info; - struct sub_seq *free; - struct tipc_subscription *s, *st; - int removed_subseq = 0; - - if (!sseq) + struct tipc_subscription *sub, *tmp; + struct service_range *sr; + struct publication *p; + bool found = false; + bool last = false; + struct rb_node *n; + + sr = tipc_service_find_range(sc, lower); + if (!sr) return NULL; - info = sseq->info; + /* Find exact matching service range */ + for (n = &sr->tree_node; n; n = rb_next(n)) { + sr = container_of(n, struct service_range, tree_node); + if (sr->upper == upper) + break; + } + if (!n || sr->lower != lower || sr->upper != upper) + return NULL; - /* Locate publication, if it exists */ - list_for_each_entry(publ, &info->all_publ, all_publ) { - if (publ->key == key && publ->port == port && - (!publ->node || publ->node == node)) - goto found; + /* Find publication, if it exists */ + list_for_each_entry(p, &sr->all_publ, all_publ) { + if (p->key != key || (node && node != p->node)) + continue; + found = true; + break; } - return NULL; + if (!found) + return NULL; -found: - list_del(&publ->all_publ); - if (in_own_node(net, node)) - list_del(&publ->local_publ); - - /* Contract subseq list if no more publications for that subseq */ - if (list_empty(&info->all_publ)) { - kfree(info); - free = &nseq->sseqs[nseq->first_free--]; - memmove(sseq, sseq + 1, (free - (sseq + 1)) * sizeof(*sseq)); - removed_subseq = 1; + list_del(&p->all_publ); + list_del(&p->local_publ); + + /* Remove service range item if this was its last publication */ + if (list_empty(&sr->all_publ)) { + last = true; + rb_erase(&sr->tree_node, &sc->ranges); + kfree(sr); } /* Notify any waiting subscriptions */ - list_for_each_entry_safe(s, st, &nseq->subscriptions, nameseq_list) { - tipc_sub_report_overlap(s, publ->lower, publ->upper, - TIPC_WITHDRAWN, publ->port, - publ->node, publ->scope, - removed_subseq); + list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) { + tipc_sub_report_overlap(sub, p->lower, p->upper, TIPC_WITHDRAWN, + p->port, p->node, p->scope, last); } - - return publ; + return p; } /** - * tipc_nameseq_subscribe - attach a subscription, and optionally - * issue the prescribed number of events if there is any sub- - * sequence overlapping with the requested sequence + * tipc_service_subscribe - attach a subscription, and optionally + * issue the prescribed number of events if there is any service + * range overlapping with the requested range */ -static void tipc_nameseq_subscribe(struct name_seq *nseq, +static void tipc_service_subscribe(struct tipc_service *service, struct tipc_subscription *sub) { - struct sub_seq *sseq = nseq->sseqs; + struct tipc_subscr *sb = &sub->evt.s; + struct service_range *sr; struct tipc_name_seq ns; - struct tipc_subscr *s = &sub->evt.s; - bool no_status; + struct publication *p; + struct rb_node *n; + bool first; - ns.type = tipc_sub_read(s, seq.type); - ns.lower = tipc_sub_read(s, seq.lower); - ns.upper = tipc_sub_read(s, seq.upper); - no_status = tipc_sub_read(s, filter) & TIPC_SUB_NO_STATUS; + ns.type = tipc_sub_read(sb, seq.type); + ns.lower = tipc_sub_read(sb, seq.lower); + ns.upper = tipc_sub_read(sb, seq.upper); tipc_sub_get(sub); - list_add(&sub->nameseq_list, &nseq->subscriptions); + list_add(&sub->service_list, &service->subscriptions); - if (no_status || !sseq) + if (tipc_sub_read(sb, filter) & TIPC_SUB_NO_STATUS) return; - while (sseq != &nseq->sseqs[nseq->first_free]) { - if (tipc_sub_check_overlap(&ns, sseq->lower, sseq->upper)) { - struct publication *crs; - struct name_info *info = sseq->info; - int must_report = 1; - - list_for_each_entry(crs, &info->all_publ, all_publ) { - tipc_sub_report_overlap(sub, sseq->lower, - sseq->upper, - TIPC_PUBLISHED, - crs->port, - crs->node, - crs->scope, - must_report); - must_report = 0; - } + for (n = rb_first(&service->ranges); n; n = rb_next(n)) { + sr = container_of(n, struct service_range, tree_node); + if (sr->lower > ns.upper) + break; + if (!tipc_sub_check_overlap(&ns, sr->lower, sr->upper)) + continue; + first = true; + + list_for_each_entry(p, &sr->all_publ, all_publ) { + tipc_sub_report_overlap(sub, sr->lower, sr->upper, + TIPC_PUBLISHED, p->port, + p->node, p->scope, first); + first = false; } - sseq++; } } -static struct name_seq *nametbl_find_seq(struct net *net, u32 type) +static struct tipc_service *tipc_service_find(struct net *net, u32 type) { - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct hlist_head *seq_head; - struct name_seq *ns; - - seq_head = &tn->nametbl->seq_hlist[hash(type)]; - hlist_for_each_entry_rcu(ns, seq_head, ns_list) { - if (ns->type == type) - return ns; + struct name_table *nt = tipc_name_table(net); + struct hlist_head *service_head; + struct tipc_service *service; + + service_head = &nt->services[hash(type)]; + hlist_for_each_entry_rcu(service, service_head, service_list) { + if (service->type == type) + return service; } - return NULL; }; struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type, - u32 lower, u32 upper, u32 scope, - u32 node, u32 port, u32 key) + u32 lower, u32 upper, + u32 scope, u32 node, + u32 port, u32 key) { - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct publication *publ; - struct name_seq *seq = nametbl_find_seq(net, type); - int index = hash(type); + struct name_table *nt = tipc_name_table(net); + struct tipc_service *sc; + struct publication *p; if (scope > TIPC_NODE_SCOPE || lower > upper) { - pr_debug("Failed to publish illegal {%u,%u,%u} with scope %u\n", + pr_debug("Failed to bind illegal {%u,%u,%u} with scope %u\n", type, lower, upper, scope); return NULL; } - - if (!seq) - seq = tipc_nameseq_create(type, &tn->nametbl->seq_hlist[index]); - if (!seq) + sc = tipc_service_find(net, type); + if (!sc) + sc = tipc_service_create(type, &nt->services[hash(type)]); + if (!sc) return NULL; - spin_lock_bh(&seq->lock); - publ = tipc_nameseq_insert_publ(net, seq, type, lower, upper, - scope, node, port, key); - spin_unlock_bh(&seq->lock); - return publ; + spin_lock_bh(&sc->lock); + p = tipc_service_insert_publ(net, sc, type, lower, upper, + scope, node, port, key); + spin_unlock_bh(&sc->lock); + return p; } struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, - u32 lower, u32 node, u32 port, - u32 key) + u32 lower, u32 upper, + u32 node, u32 key) { - struct publication *publ; - struct name_seq *seq = nametbl_find_seq(net, type); + struct tipc_service *sc = tipc_service_find(net, type); + struct publication *p = NULL; - if (!seq) + if (!sc) return NULL; - spin_lock_bh(&seq->lock); - publ = tipc_nameseq_remove_publ(net, seq, lower, node, port, key); - if (!seq->first_free && list_empty(&seq->subscriptions)) { - hlist_del_init_rcu(&seq->ns_list); - kfree(seq->sseqs); - spin_unlock_bh(&seq->lock); - kfree_rcu(seq, rcu); - return publ; + spin_lock_bh(&sc->lock); + p = tipc_service_remove_publ(net, sc, lower, upper, node, key); + + /* Delete service item if this no more publications and subscriptions */ + if (RB_EMPTY_ROOT(&sc->ranges) && list_empty(&sc->subscriptions)) { + hlist_del_init_rcu(&sc->service_list); + kfree_rcu(sc, rcu); } - spin_unlock_bh(&seq->lock); - return publ; + spin_unlock_bh(&sc->lock); + return p; } /** - * tipc_nametbl_translate - perform name translation + * tipc_nametbl_translate - perform service instance to socket translation * - * On entry, 'destnode' is the search domain used during translation. + * On entry, 'dnode' is the search domain used during translation. * * On exit: - * - if name translation is deferred to another node/cluster/zone, - * leaves 'destnode' unchanged (will be non-zero) and returns 0 - * - if name translation is attempted and succeeds, sets 'destnode' - * to publishing node and returns port reference (will be non-zero) - * - if name translation is attempted and fails, sets 'destnode' to 0 - * and returns 0 + * - if translation is deferred to another node, leave 'dnode' unchanged and + * return 0 + * - if translation is attempted and succeeds, set 'dnode' to the publishing + * node and return the published (non-zero) port number + * - if translation is attempted and fails, set 'dnode' to 0 and return 0 + * + * Note that for legacy users (node configured with Z.C.N address format) the + * 'closest-first' lookup algorithm must be maintained, i.e., if dnode is 0 + * we must look in the local binding list first */ -u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, - u32 *destnode) +u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *dnode) { struct tipc_net *tn = tipc_net(net); bool legacy = tn->legacy_addr_format; u32 self = tipc_own_addr(net); - struct sub_seq *sseq; - struct name_info *info; - struct publication *publ; - struct name_seq *seq; + struct service_range *sr; + struct tipc_service *sc; + struct list_head *list; + struct publication *p; u32 port = 0; u32 node = 0; - if (!tipc_in_scope(legacy, *destnode, self)) + if (!tipc_in_scope(legacy, *dnode, self)) return 0; rcu_read_lock(); - seq = nametbl_find_seq(net, type); - if (unlikely(!seq)) + sc = tipc_service_find(net, type); + if (unlikely(!sc)) goto not_found; - spin_lock_bh(&seq->lock); - sseq = nameseq_find_subseq(seq, instance); - if (unlikely(!sseq)) + + spin_lock_bh(&sc->lock); + sr = tipc_service_find_range(sc, instance); + if (unlikely(!sr)) goto no_match; - info = sseq->info; - - /* Closest-First Algorithm */ - if (legacy && !*destnode) { - if (!list_empty(&info->local_publ)) { - publ = list_first_entry(&info->local_publ, - struct publication, - local_publ); - list_move_tail(&publ->local_publ, - &info->local_publ); - } else { - publ = list_first_entry(&info->all_publ, - struct publication, - all_publ); - list_move_tail(&publ->all_publ, - &info->all_publ); - } - } - /* Round-Robin Algorithm */ - else if (*destnode == tipc_own_addr(net)) { - if (list_empty(&info->local_publ)) + /* Select lookup algorithm: local, closest-first or round-robin */ + if (*dnode == self) { + list = &sr->local_publ; + if (list_empty(list)) goto no_match; - publ = list_first_entry(&info->local_publ, struct publication, - local_publ); - list_move_tail(&publ->local_publ, &info->local_publ); + p = list_first_entry(list, struct publication, local_publ); + list_move_tail(&p->local_publ, &sr->local_publ); + } else if (legacy && !*dnode && !list_empty(&sr->local_publ)) { + list = &sr->local_publ; + p = list_first_entry(list, struct publication, local_publ); + list_move_tail(&p->local_publ, &sr->local_publ); } else { - publ = list_first_entry(&info->all_publ, struct publication, - all_publ); - list_move_tail(&publ->all_publ, &info->all_publ); + list = &sr->all_publ; + p = list_first_entry(list, struct publication, all_publ); + list_move_tail(&p->all_publ, &sr->all_publ); } - - port = publ->port; - node = publ->node; + port = p->port; + node = p->node; no_match: - spin_unlock_bh(&seq->lock); + spin_unlock_bh(&sc->lock); not_found: rcu_read_unlock(); - *destnode = node; + *dnode = node; return port; } @@ -567,34 +468,36 @@ bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 scope, bool all) { u32 self = tipc_own_addr(net); - struct publication *publ; - struct name_info *info; - struct name_seq *seq; - struct sub_seq *sseq; + struct service_range *sr; + struct tipc_service *sc; + struct publication *p; *dstcnt = 0; rcu_read_lock(); - seq = nametbl_find_seq(net, type); - if (unlikely(!seq)) + sc = tipc_service_find(net, type); + if (unlikely(!sc)) goto exit; - spin_lock_bh(&seq->lock); - sseq = nameseq_find_subseq(seq, instance); - if (likely(sseq)) { - info = sseq->info; - list_for_each_entry(publ, &info->all_publ, all_publ) { - if (publ->scope != scope) - continue; - if (publ->port == exclude && publ->node == self) - continue; - tipc_dest_push(dsts, publ->node, publ->port); - (*dstcnt)++; - if (all) - continue; - list_move_tail(&publ->all_publ, &info->all_publ); - break; - } + + spin_lock_bh(&sc->lock); + + sr = tipc_service_find_range(sc, instance); + if (!sr) + goto no_match; + + list_for_each_entry(p, &sr->all_publ, all_publ) { + if (p->scope != scope) + continue; + if (p->port == exclude && p->node == self) + continue; + tipc_dest_push(dsts, p->node, p->port); + (*dstcnt)++; + if (all) + continue; + list_move_tail(&p->all_publ, &sr->all_publ); + break; } - spin_unlock_bh(&seq->lock); +no_match: + spin_unlock_bh(&sc->lock); exit: rcu_read_unlock(); return !list_empty(dsts); @@ -603,61 +506,64 @@ exit: void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper, u32 scope, bool exact, struct list_head *dports) { - struct sub_seq *sseq_stop; - struct name_info *info; + struct service_range *sr; + struct tipc_service *sc; struct publication *p; - struct name_seq *seq; - struct sub_seq *sseq; + struct rb_node *n; rcu_read_lock(); - seq = nametbl_find_seq(net, type); - if (!seq) + sc = tipc_service_find(net, type); + if (!sc) goto exit; - spin_lock_bh(&seq->lock); - sseq = seq->sseqs + nameseq_locate_subseq(seq, lower); - sseq_stop = seq->sseqs + seq->first_free; - for (; sseq != sseq_stop; sseq++) { - if (sseq->lower > upper) + spin_lock_bh(&sc->lock); + + for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { + sr = container_of(n, struct service_range, tree_node); + if (sr->upper < lower) + continue; + if (sr->lower > upper) break; - info = sseq->info; - list_for_each_entry(p, &info->local_publ, local_publ) { + list_for_each_entry(p, &sr->local_publ, local_publ) { if (p->scope == scope || (!exact && p->scope < scope)) tipc_dest_push(dports, 0, p->port); } } - spin_unlock_bh(&seq->lock); + spin_unlock_bh(&sc->lock); exit: rcu_read_unlock(); } /* tipc_nametbl_lookup_dst_nodes - find broadcast destination nodes * - Creates list of nodes that overlap the given multicast address - * - Determines if any node local ports overlap + * - Determines if any node local destinations overlap */ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, u32 upper, struct tipc_nlist *nodes) { - struct sub_seq *sseq, *stop; - struct publication *publ; - struct name_info *info; - struct name_seq *seq; + struct service_range *sr; + struct tipc_service *sc; + struct publication *p; + struct rb_node *n; rcu_read_lock(); - seq = nametbl_find_seq(net, type); - if (!seq) + sc = tipc_service_find(net, type); + if (!sc) goto exit; - spin_lock_bh(&seq->lock); - sseq = seq->sseqs + nameseq_locate_subseq(seq, lower); - stop = seq->sseqs + seq->first_free; - for (; sseq != stop && sseq->lower <= upper; sseq++) { - info = sseq->info; - list_for_each_entry(publ, &info->all_publ, all_publ) { - tipc_nlist_add(nodes, publ->node); + spin_lock_bh(&sc->lock); + + for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { + sr = container_of(n, struct service_range, tree_node); + if (sr->upper < lower) + continue; + if (sr->lower > upper) + break; + list_for_each_entry(p, &sr->all_publ, all_publ) { + tipc_nlist_add(nodes, p->node); } } - spin_unlock_bh(&seq->lock); + spin_unlock_bh(&sc->lock); exit: rcu_read_unlock(); } @@ -667,90 +573,85 @@ exit: void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp, u32 type, u32 scope) { - struct sub_seq *sseq, *stop; - struct name_info *info; + struct service_range *sr; + struct tipc_service *sc; struct publication *p; - struct name_seq *seq; + struct rb_node *n; rcu_read_lock(); - seq = nametbl_find_seq(net, type); - if (!seq) + sc = tipc_service_find(net, type); + if (!sc) goto exit; - spin_lock_bh(&seq->lock); - sseq = seq->sseqs; - stop = seq->sseqs + seq->first_free; - for (; sseq != stop; sseq++) { - info = sseq->info; - list_for_each_entry(p, &info->all_publ, all_publ) { + spin_lock_bh(&sc->lock); + for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { + sr = container_of(n, struct service_range, tree_node); + list_for_each_entry(p, &sr->all_publ, all_publ) { if (p->scope != scope) continue; tipc_group_add_member(grp, p->node, p->port, p->lower); } } - spin_unlock_bh(&seq->lock); + spin_unlock_bh(&sc->lock); exit: rcu_read_unlock(); } -/* - * tipc_nametbl_publish - add name publication to network name tables +/* tipc_nametbl_publish - add service binding to name table */ struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower, - u32 upper, u32 scope, u32 port_ref, + u32 upper, u32 scope, u32 port, u32 key) { - struct publication *publ; - struct sk_buff *buf = NULL; - struct tipc_net *tn = net_generic(net, tipc_net_id); + struct name_table *nt = tipc_name_table(net); + struct tipc_net *tn = tipc_net(net); + struct publication *p = NULL; + struct sk_buff *skb = NULL; spin_lock_bh(&tn->nametbl_lock); - if (tn->nametbl->local_publ_count >= TIPC_MAX_PUBLICATIONS) { - pr_warn("Publication failed, local publication limit reached (%u)\n", - TIPC_MAX_PUBLICATIONS); - spin_unlock_bh(&tn->nametbl_lock); - return NULL; + + if (nt->local_publ_count >= TIPC_MAX_PUBL) { + pr_warn("Bind failed, max limit %u reached\n", TIPC_MAX_PUBL); + goto exit; } - publ = tipc_nametbl_insert_publ(net, type, lower, upper, scope, - tipc_own_addr(net), port_ref, key); - if (likely(publ)) { - tn->nametbl->local_publ_count++; - buf = tipc_named_publish(net, publ); - /* Any pending external events? */ - tipc_named_process_backlog(net); + p = tipc_nametbl_insert_publ(net, type, lower, upper, scope, + tipc_own_addr(net), port, key); + if (p) { + nt->local_publ_count++; + skb = tipc_named_publish(net, p); } +exit: spin_unlock_bh(&tn->nametbl_lock); - if (buf) - tipc_node_broadcast(net, buf); - return publ; + if (skb) + tipc_node_broadcast(net, skb); + return p; } /** - * tipc_nametbl_withdraw - withdraw name publication from network name tables + * tipc_nametbl_withdraw - withdraw a service binding */ -int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 port, - u32 key) +int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, + u32 upper, u32 key) { - struct publication *publ; + struct name_table *nt = tipc_name_table(net); + struct tipc_net *tn = tipc_net(net); + u32 self = tipc_own_addr(net); struct sk_buff *skb = NULL; - struct tipc_net *tn = net_generic(net, tipc_net_id); + struct publication *p; spin_lock_bh(&tn->nametbl_lock); - publ = tipc_nametbl_remove_publ(net, type, lower, tipc_own_addr(net), - port, key); - if (likely(publ)) { - tn->nametbl->local_publ_count--; - skb = tipc_named_withdraw(net, publ); - /* Any pending external events? */ - tipc_named_process_backlog(net); - list_del_init(&publ->binding_sock); - kfree_rcu(publ, rcu); + + p = tipc_nametbl_remove_publ(net, type, lower, upper, self, key); + if (p) { + nt->local_publ_count--; + skb = tipc_named_withdraw(net, p); + list_del_init(&p->binding_sock); + kfree_rcu(p, rcu); } else { - pr_err("Unable to remove local publication\n" - "(type=%u, lower=%u, port=%u, key=%u)\n", - type, lower, port, key); + pr_err("Failed to remove local publication {%u,%u,%u}/%u\n", + type, lower, upper, key); } spin_unlock_bh(&tn->nametbl_lock); @@ -766,27 +667,24 @@ int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 port, */ void tipc_nametbl_subscribe(struct tipc_subscription *sub) { + struct name_table *nt = tipc_name_table(sub->net); struct tipc_net *tn = tipc_net(sub->net); struct tipc_subscr *s = &sub->evt.s; u32 type = tipc_sub_read(s, seq.type); - int index = hash(type); - struct name_seq *seq; - struct tipc_name_seq ns; + struct tipc_service *sc; spin_lock_bh(&tn->nametbl_lock); - seq = nametbl_find_seq(sub->net, type); - if (!seq) - seq = tipc_nameseq_create(type, &tn->nametbl->seq_hlist[index]); - if (seq) { - spin_lock_bh(&seq->lock); - tipc_nameseq_subscribe(seq, sub); - spin_unlock_bh(&seq->lock); + sc = tipc_service_find(sub->net, type); + if (!sc) + sc = tipc_service_create(type, &nt->services[hash(type)]); + if (sc) { + spin_lock_bh(&sc->lock); + tipc_service_subscribe(sc, sub); + spin_unlock_bh(&sc->lock); } else { - ns.type = tipc_sub_read(s, seq.type); - ns.lower = tipc_sub_read(s, seq.lower); - ns.upper = tipc_sub_read(s, seq.upper); - pr_warn("Failed to create subscription for {%u,%u,%u}\n", - ns.type, ns.lower, ns.upper); + pr_warn("Failed to subscribe for {%u,%u,%u}\n", type, + tipc_sub_read(s, seq.lower), + tipc_sub_read(s, seq.upper)); } spin_unlock_bh(&tn->nametbl_lock); } @@ -796,124 +694,122 @@ void tipc_nametbl_subscribe(struct tipc_subscription *sub) */ void tipc_nametbl_unsubscribe(struct tipc_subscription *sub) { - struct tipc_subscr *s = &sub->evt.s; struct tipc_net *tn = tipc_net(sub->net); - struct name_seq *seq; + struct tipc_subscr *s = &sub->evt.s; u32 type = tipc_sub_read(s, seq.type); + struct tipc_service *sc; spin_lock_bh(&tn->nametbl_lock); - seq = nametbl_find_seq(sub->net, type); - if (seq != NULL) { - spin_lock_bh(&seq->lock); - list_del_init(&sub->nameseq_list); - tipc_sub_put(sub); - if (!seq->first_free && list_empty(&seq->subscriptions)) { - hlist_del_init_rcu(&seq->ns_list); - kfree(seq->sseqs); - spin_unlock_bh(&seq->lock); - kfree_rcu(seq, rcu); - } else { - spin_unlock_bh(&seq->lock); - } + sc = tipc_service_find(sub->net, type); + if (!sc) + goto exit; + + spin_lock_bh(&sc->lock); + list_del_init(&sub->service_list); + tipc_sub_put(sub); + + /* Delete service item if no more publications and subscriptions */ + if (RB_EMPTY_ROOT(&sc->ranges) && list_empty(&sc->subscriptions)) { + hlist_del_init_rcu(&sc->service_list); + kfree_rcu(sc, rcu); } + spin_unlock_bh(&sc->lock); +exit: spin_unlock_bh(&tn->nametbl_lock); } int tipc_nametbl_init(struct net *net) { - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct name_table *tipc_nametbl; + struct tipc_net *tn = tipc_net(net); + struct name_table *nt; int i; - tipc_nametbl = kzalloc(sizeof(*tipc_nametbl), GFP_ATOMIC); - if (!tipc_nametbl) + nt = kzalloc(sizeof(*nt), GFP_ATOMIC); + if (!nt) return -ENOMEM; for (i = 0; i < TIPC_NAMETBL_SIZE; i++) - INIT_HLIST_HEAD(&tipc_nametbl->seq_hlist[i]); + INIT_HLIST_HEAD(&nt->services[i]); - INIT_LIST_HEAD(&tipc_nametbl->node_scope); - INIT_LIST_HEAD(&tipc_nametbl->cluster_scope); - tn->nametbl = tipc_nametbl; + INIT_LIST_HEAD(&nt->node_scope); + INIT_LIST_HEAD(&nt->cluster_scope); + tn->nametbl = nt; spin_lock_init(&tn->nametbl_lock); return 0; } /** - * tipc_purge_publications - remove all publications for a given type - * - * tipc_nametbl_lock must be held when calling this function + * tipc_service_delete - purge all publications for a service and delete it */ -static void tipc_purge_publications(struct net *net, struct name_seq *seq) +static void tipc_service_delete(struct net *net, struct tipc_service *sc) { - struct publication *publ, *safe; - struct sub_seq *sseq; - struct name_info *info; - - spin_lock_bh(&seq->lock); - sseq = seq->sseqs; - info = sseq->info; - list_for_each_entry_safe(publ, safe, &info->all_publ, all_publ) { - tipc_nameseq_remove_publ(net, seq, publ->lower, publ->node, - publ->port, publ->key); - kfree_rcu(publ, rcu); + struct service_range *sr, *tmpr; + struct publication *p, *tmpb; + + spin_lock_bh(&sc->lock); + rbtree_postorder_for_each_entry_safe(sr, tmpr, &sc->ranges, tree_node) { + list_for_each_entry_safe(p, tmpb, + &sr->all_publ, all_publ) { + tipc_service_remove_publ(net, sc, p->lower, p->upper, + p->node, p->key); + kfree_rcu(p, rcu); + } } - hlist_del_init_rcu(&seq->ns_list); - kfree(seq->sseqs); - spin_unlock_bh(&seq->lock); - - kfree_rcu(seq, rcu); + hlist_del_init_rcu(&sc->service_list); + spin_unlock_bh(&sc->lock); + kfree_rcu(sc, rcu); } void tipc_nametbl_stop(struct net *net) { + struct name_table *nt = tipc_name_table(net); + struct tipc_net *tn = tipc_net(net); + struct hlist_head *service_head; + struct tipc_service *service; u32 i; - struct name_seq *seq; - struct hlist_head *seq_head; - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct name_table *tipc_nametbl = tn->nametbl; /* Verify name table is empty and purge any lingering * publications, then release the name table */ spin_lock_bh(&tn->nametbl_lock); for (i = 0; i < TIPC_NAMETBL_SIZE; i++) { - if (hlist_empty(&tipc_nametbl->seq_hlist[i])) + if (hlist_empty(&nt->services[i])) continue; - seq_head = &tipc_nametbl->seq_hlist[i]; - hlist_for_each_entry_rcu(seq, seq_head, ns_list) { - tipc_purge_publications(net, seq); + service_head = &nt->services[i]; + hlist_for_each_entry_rcu(service, service_head, service_list) { + tipc_service_delete(net, service); } } spin_unlock_bh(&tn->nametbl_lock); synchronize_net(); - kfree(tipc_nametbl); - + kfree(nt); } static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg, - struct name_seq *seq, - struct sub_seq *sseq, u32 *last_publ) + struct tipc_service *service, + struct service_range *sr, + u32 *last_key) { - void *hdr; - struct nlattr *attrs; - struct nlattr *publ; struct publication *p; + struct nlattr *attrs; + struct nlattr *b; + void *hdr; - if (*last_publ) { - list_for_each_entry(p, &sseq->info->all_publ, all_publ) - if (p->key == *last_publ) + if (*last_key) { + list_for_each_entry(p, &sr->all_publ, all_publ) + if (p->key == *last_key) break; - if (p->key != *last_publ) + if (p->key != *last_key) return -EPIPE; } else { - p = list_first_entry(&sseq->info->all_publ, struct publication, + p = list_first_entry(&sr->all_publ, + struct publication, all_publ); } - list_for_each_entry_from(p, &sseq->info->all_publ, all_publ) { - *last_publ = p->key; + list_for_each_entry_from(p, &sr->all_publ, all_publ) { + *last_key = p->key; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, @@ -925,15 +821,15 @@ static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg, if (!attrs) goto msg_full; - publ = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE_PUBL); - if (!publ) + b = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE_PUBL); + if (!b) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_TYPE, seq->type)) + if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_TYPE, service->type)) goto publ_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_LOWER, sseq->lower)) + if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_LOWER, sr->lower)) goto publ_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_UPPER, sseq->upper)) + if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_UPPER, sr->upper)) goto publ_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_SCOPE, p->scope)) goto publ_msg_full; @@ -944,16 +840,16 @@ static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg, if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_KEY, p->key)) goto publ_msg_full; - nla_nest_end(msg->skb, publ); + nla_nest_end(msg->skb, b); nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); } - *last_publ = 0; + *last_key = 0; return 0; publ_msg_full: - nla_nest_cancel(msg->skb, publ); + nla_nest_cancel(msg->skb, b); attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: @@ -962,39 +858,34 @@ msg_full: return -EMSGSIZE; } -static int __tipc_nl_subseq_list(struct tipc_nl_msg *msg, struct name_seq *seq, - u32 *last_lower, u32 *last_publ) +static int __tipc_nl_service_range_list(struct tipc_nl_msg *msg, + struct tipc_service *sc, + u32 *last_lower, u32 *last_key) { - struct sub_seq *sseq; - struct sub_seq *sseq_start; + struct service_range *sr; + struct rb_node *n; int err; - if (*last_lower) { - sseq_start = nameseq_find_subseq(seq, *last_lower); - if (!sseq_start) - return -EPIPE; - } else { - sseq_start = seq->sseqs; - } - - for (sseq = sseq_start; sseq != &seq->sseqs[seq->first_free]; sseq++) { - err = __tipc_nl_add_nametable_publ(msg, seq, sseq, last_publ); + for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { + sr = container_of(n, struct service_range, tree_node); + if (sr->lower < *last_lower) + continue; + err = __tipc_nl_add_nametable_publ(msg, sc, sr, last_key); if (err) { - *last_lower = sseq->lower; + *last_lower = sr->lower; return err; } } *last_lower = 0; - return 0; } -static int tipc_nl_seq_list(struct net *net, struct tipc_nl_msg *msg, - u32 *last_type, u32 *last_lower, u32 *last_publ) +static int tipc_nl_service_list(struct net *net, struct tipc_nl_msg *msg, + u32 *last_type, u32 *last_lower, u32 *last_key) { - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct hlist_head *seq_head; - struct name_seq *seq = NULL; + struct tipc_net *tn = tipc_net(net); + struct tipc_service *service = NULL; + struct hlist_head *head; int err; int i; @@ -1004,30 +895,31 @@ static int tipc_nl_seq_list(struct net *net, struct tipc_nl_msg *msg, i = 0; for (; i < TIPC_NAMETBL_SIZE; i++) { - seq_head = &tn->nametbl->seq_hlist[i]; + head = &tn->nametbl->services[i]; if (*last_type) { - seq = nametbl_find_seq(net, *last_type); - if (!seq) + service = tipc_service_find(net, *last_type); + if (!service) return -EPIPE; } else { - hlist_for_each_entry_rcu(seq, seq_head, ns_list) + hlist_for_each_entry_rcu(service, head, service_list) break; - if (!seq) + if (!service) continue; } - hlist_for_each_entry_from_rcu(seq, ns_list) { - spin_lock_bh(&seq->lock); - err = __tipc_nl_subseq_list(msg, seq, last_lower, - last_publ); + hlist_for_each_entry_from_rcu(service, service_list) { + spin_lock_bh(&service->lock); + err = __tipc_nl_service_range_list(msg, service, + last_lower, + last_key); if (err) { - *last_type = seq->type; - spin_unlock_bh(&seq->lock); + *last_type = service->type; + spin_unlock_bh(&service->lock); return err; } - spin_unlock_bh(&seq->lock); + spin_unlock_bh(&service->lock); } *last_type = 0; } @@ -1036,13 +928,13 @@ static int tipc_nl_seq_list(struct net *net, struct tipc_nl_msg *msg, int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb) { - int err; - int done = cb->args[3]; + struct net *net = sock_net(skb->sk); u32 last_type = cb->args[0]; u32 last_lower = cb->args[1]; - u32 last_publ = cb->args[2]; - struct net *net = sock_net(skb->sk); + u32 last_key = cb->args[2]; + int done = cb->args[3]; struct tipc_nl_msg msg; + int err; if (done) return 0; @@ -1052,7 +944,8 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb) msg.seq = cb->nlh->nlmsg_seq; rcu_read_lock(); - err = tipc_nl_seq_list(net, &msg, &last_type, &last_lower, &last_publ); + err = tipc_nl_service_list(net, &msg, &last_type, + &last_lower, &last_key); if (!err) { done = 1; } else if (err != -EMSGSIZE) { @@ -1068,7 +961,7 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb) cb->args[0] = last_type; cb->args[1] = last_lower; - cb->args[2] = last_publ; + cb->args[2] = last_key; cb->args[3] = done; return skb->len; diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 34a4ccb907aa..4b14fc28d9e2 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -97,7 +97,7 @@ struct publication { * @local_publ_count: number of publications issued by this node */ struct name_table { - struct hlist_head seq_hlist[TIPC_NAMETBL_SIZE]; + struct hlist_head services[TIPC_NAMETBL_SIZE]; struct list_head node_scope; struct list_head cluster_scope; u32 local_publ_count; @@ -116,16 +116,16 @@ bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 domain, struct list_head *dsts, int *dstcnt, u32 exclude, bool all); struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower, - u32 upper, u32 scope, u32 port_ref, + u32 upper, u32 scope, u32 port, u32 key); -int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 ref, +int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 upper, u32 key); struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type, u32 lower, u32 upper, u32 scope, u32 node, u32 ref, u32 key); struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, - u32 lower, u32 node, u32 ref, - u32 key); + u32 lower, u32 upper, + u32 node, u32 key); void tipc_nametbl_subscribe(struct tipc_subscription *s); void tipc_nametbl_unsubscribe(struct tipc_subscription *s); int tipc_nametbl_init(struct net *net); diff --git a/net/tipc/net.c b/net/tipc/net.c index 29538dc00857..856f9e97ea29 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -136,7 +136,7 @@ void tipc_net_stop(struct net *net) if (!self) return; - tipc_nametbl_withdraw(net, TIPC_CFG_SRV, self, 0, self); + tipc_nametbl_withdraw(net, TIPC_CFG_SRV, self, self, self); rtnl_lock(); tipc_bearer_stop(net); tipc_node_stop(net); diff --git a/net/tipc/node.c b/net/tipc/node.c index 4fb4327311bb..c77dd2f3c589 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -324,12 +324,12 @@ static void tipc_node_write_unlock(struct tipc_node *n) if (flags & TIPC_NOTIFY_LINK_UP) { tipc_mon_peer_up(net, addr, bearer_id); tipc_nametbl_publish(net, TIPC_LINK_STATE, addr, addr, - TIPC_NODE_SCOPE, link_id, addr); + TIPC_NODE_SCOPE, link_id, link_id); } if (flags & TIPC_NOTIFY_LINK_DOWN) { tipc_mon_peer_down(net, addr, bearer_id); tipc_nametbl_withdraw(net, TIPC_LINK_STATE, addr, - link_id, addr); + addr, link_id); } } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 275b666f6231..3e5eba30865e 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2634,12 +2634,12 @@ static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope, if (publ->upper != seq->upper) break; tipc_nametbl_withdraw(net, publ->type, publ->lower, - publ->port, publ->key); + publ->upper, publ->key); rc = 0; break; } tipc_nametbl_withdraw(net, publ->type, publ->lower, - publ->port, publ->key); + publ->upper, publ->key); rc = 0; } if (list_empty(&tsk->publications)) diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index 8b2d22b18f22..d793b4343885 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -40,7 +40,7 @@ #include "topsrv.h" #define TIPC_MAX_SUBSCR 65535 -#define TIPC_MAX_PUBLICATIONS 65535 +#define TIPC_MAX_PUBL 65535 struct tipc_subscription; struct tipc_conn; @@ -58,7 +58,7 @@ struct tipc_subscription { struct kref kref; struct net *net; struct timer_list timer; - struct list_head nameseq_list; + struct list_head service_list; struct list_head sub_list; struct tipc_event evt; int conid; |