diff options
Diffstat (limited to 'drivers/net/ethernet/sun')
-rw-r--r-- | drivers/net/ethernet/sun/cassini.c | 2 | ||||
-rw-r--r-- | drivers/net/ethernet/sun/niu.c | 4 | ||||
-rw-r--r-- | drivers/net/ethernet/sun/sungem.c | 34 | ||||
-rw-r--r-- | drivers/net/ethernet/sun/sunvnet.c | 437 | ||||
-rw-r--r-- | drivers/net/ethernet/sun/sunvnet.h | 20 |
5 files changed, 406 insertions, 91 deletions
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 37f87ff28f03..02d370e58110 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -4962,7 +4962,7 @@ static int cas_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) pci_cmd |= PCI_COMMAND_PARITY; pci_write_config_word(pdev, PCI_COMMAND, pci_cmd); if (pci_try_set_mwi(pdev)) - pr_warning("Could not enable MWI for %s\n", pci_name(pdev)); + pr_warn("Could not enable MWI for %s\n", pci_name(pdev)); cas_program_bridge(pdev); diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 8216be46540f..904fd1ab5f6e 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -8717,8 +8717,8 @@ static void niu_divide_channels(struct niu_parent *parent, parent->txchan_per_port[i] = 1; } if (tot_rx < NIU_NUM_RXCHAN || tot_tx < NIU_NUM_TXCHAN) { - pr_warning("niu%d: Driver bug, wasted channels, RX[%d] TX[%d]\n", - parent->index, tot_rx, tot_tx); + pr_warn("niu%d: Driver bug, wasted channels, RX[%d] TX[%d]\n", + parent->index, tot_rx, tot_tx); } } diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index f7415b6bf141..fef5dec2cffe 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -115,7 +115,7 @@ static const struct pci_device_id gem_pci_tbl[] = { MODULE_DEVICE_TABLE(pci, gem_pci_tbl); -static u16 __phy_read(struct gem *gp, int phy_addr, int reg) +static u16 __sungem_phy_read(struct gem *gp, int phy_addr, int reg) { u32 cmd; int limit = 10000; @@ -141,18 +141,18 @@ static u16 __phy_read(struct gem *gp, int phy_addr, int reg) return cmd & MIF_FRAME_DATA; } -static inline int _phy_read(struct net_device *dev, int mii_id, int reg) +static inline int _sungem_phy_read(struct net_device *dev, int mii_id, int reg) { struct gem *gp = netdev_priv(dev); - return __phy_read(gp, mii_id, reg); + return __sungem_phy_read(gp, mii_id, reg); } -static inline u16 phy_read(struct gem *gp, int reg) +static inline u16 sungem_phy_read(struct gem *gp, int reg) { - return __phy_read(gp, gp->mii_phy_addr, reg); + return __sungem_phy_read(gp, gp->mii_phy_addr, reg); } -static void __phy_write(struct gem *gp, int phy_addr, int reg, u16 val) +static void __sungem_phy_write(struct gem *gp, int phy_addr, int reg, u16 val) { u32 cmd; int limit = 10000; @@ -174,15 +174,15 @@ static void __phy_write(struct gem *gp, int phy_addr, int reg, u16 val) } } -static inline void _phy_write(struct net_device *dev, int mii_id, int reg, int val) +static inline void _sungem_phy_write(struct net_device *dev, int mii_id, int reg, int val) { struct gem *gp = netdev_priv(dev); - __phy_write(gp, mii_id, reg, val & 0xffff); + __sungem_phy_write(gp, mii_id, reg, val & 0xffff); } -static inline void phy_write(struct gem *gp, int reg, u16 val) +static inline void sungem_phy_write(struct gem *gp, int reg, u16 val) { - __phy_write(gp, gp->mii_phy_addr, reg, val); + __sungem_phy_write(gp, gp->mii_phy_addr, reg, val); } static inline void gem_enable_ints(struct gem *gp) @@ -1687,9 +1687,9 @@ static void gem_init_phy(struct gem *gp) /* Some PHYs used by apple have problem getting back to us, * we do an additional reset here */ - phy_write(gp, MII_BMCR, BMCR_RESET); + sungem_phy_write(gp, MII_BMCR, BMCR_RESET); msleep(20); - if (phy_read(gp, MII_BMCR) != 0xffff) + if (sungem_phy_read(gp, MII_BMCR) != 0xffff) break; if (i == 2) netdev_warn(gp->dev, "GMAC PHY not responding !\n"); @@ -2012,7 +2012,7 @@ static int gem_check_invariants(struct gem *gp) for (i = 0; i < 32; i++) { gp->mii_phy_addr = i; - if (phy_read(gp, MII_BMCR) != 0xffff) + if (sungem_phy_read(gp, MII_BMCR) != 0xffff) break; } if (i == 32) { @@ -2696,13 +2696,13 @@ static int gem_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /* Fallthrough... */ case SIOCGMIIREG: /* Read MII PHY register. */ - data->val_out = __phy_read(gp, data->phy_id & 0x1f, + data->val_out = __sungem_phy_read(gp, data->phy_id & 0x1f, data->reg_num & 0x1f); rc = 0; break; case SIOCSMIIREG: /* Write MII PHY register. */ - __phy_write(gp, data->phy_id & 0x1f, data->reg_num & 0x1f, + __sungem_phy_write(gp, data->phy_id & 0x1f, data->reg_num & 0x1f, data->val_in); rc = 0; break; @@ -2933,8 +2933,8 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* Fill up the mii_phy structure (even if we won't use it) */ gp->phy_mii.dev = dev; - gp->phy_mii.mdio_read = _phy_read; - gp->phy_mii.mdio_write = _phy_write; + gp->phy_mii.mdio_read = _sungem_phy_read; + gp->phy_mii.mdio_write = _sungem_phy_write; #ifdef CONFIG_PPC_PMAC gp->phy_mii.platform_data = gp->of_node; #endif diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index f67539650c38..3652afd3ec78 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -15,6 +15,14 @@ #include <linux/ethtool.h> #include <linux/etherdevice.h> #include <linux/mutex.h> +#include <linux/if_vlan.h> + +#if IS_ENABLED(CONFIG_IPV6) +#include <linux/icmpv6.h> +#endif + +#include <net/icmp.h> +#include <net/route.h> #include <asm/vio.h> #include <asm/ldc.h> @@ -37,8 +45,11 @@ MODULE_VERSION(DRV_MODULE_VERSION); */ #define VNET_MAX_RETRIES 10 +static int __vnet_tx_trigger(struct vnet_port *port, u32 start); + /* Ordered from largest major to lowest */ static struct vio_version vnet_versions[] = { + { .major = 1, .minor = 6 }, { .major = 1, .minor = 0 }, }; @@ -65,6 +76,7 @@ static int vnet_send_attr(struct vio_driver_state *vio) struct vnet_port *port = to_vnet_port(vio); struct net_device *dev = port->vp->dev; struct vio_net_attr_info pkt; + int framelen = ETH_FRAME_LEN; int i; memset(&pkt, 0, sizeof(pkt)); @@ -72,19 +84,41 @@ static int vnet_send_attr(struct vio_driver_state *vio) pkt.tag.stype = VIO_SUBTYPE_INFO; pkt.tag.stype_env = VIO_ATTR_INFO; pkt.tag.sid = vio_send_sid(vio); - pkt.xfer_mode = VIO_DRING_MODE; + if (vio_version_before(vio, 1, 2)) + pkt.xfer_mode = VIO_DRING_MODE; + else + pkt.xfer_mode = VIO_NEW_DRING_MODE; pkt.addr_type = VNET_ADDR_ETHERMAC; pkt.ack_freq = 0; for (i = 0; i < 6; i++) pkt.addr |= (u64)dev->dev_addr[i] << ((5 - i) * 8); - pkt.mtu = ETH_FRAME_LEN; + if (vio_version_after(vio, 1, 3)) { + if (port->rmtu) { + port->rmtu = min(VNET_MAXPACKET, port->rmtu); + pkt.mtu = port->rmtu; + } else { + port->rmtu = VNET_MAXPACKET; + pkt.mtu = port->rmtu; + } + if (vio_version_after_eq(vio, 1, 6)) + pkt.options = VIO_TX_DRING; + } else if (vio_version_before(vio, 1, 3)) { + pkt.mtu = framelen; + } else { /* v1.3 */ + pkt.mtu = framelen + VLAN_HLEN; + } + + pkt.plnk_updt = PHYSLINK_UPDATE_NONE; + pkt.cflags = 0; viodbg(HS, "SEND NET ATTR xmode[0x%x] atype[0x%x] addr[%llx] " - "ackfreq[%u] mtu[%llu]\n", + "ackfreq[%u] plnk_updt[0x%02x] opts[0x%02x] mtu[%llu] " + "cflags[0x%04x] lso_max[%u]\n", pkt.xfer_mode, pkt.addr_type, - (unsigned long long) pkt.addr, - pkt.ack_freq, - (unsigned long long) pkt.mtu); + (unsigned long long)pkt.addr, + pkt.ack_freq, pkt.plnk_updt, pkt.options, + (unsigned long long)pkt.mtu, pkt.cflags, pkt.ipv4_lso_maxlen); + return vio_ldc_send(vio, &pkt, sizeof(pkt)); } @@ -92,18 +126,52 @@ static int vnet_send_attr(struct vio_driver_state *vio) static int handle_attr_info(struct vio_driver_state *vio, struct vio_net_attr_info *pkt) { - viodbg(HS, "GOT NET ATTR INFO xmode[0x%x] atype[0x%x] addr[%llx] " - "ackfreq[%u] mtu[%llu]\n", + struct vnet_port *port = to_vnet_port(vio); + u64 localmtu; + u8 xfer_mode; + + viodbg(HS, "GOT NET ATTR xmode[0x%x] atype[0x%x] addr[%llx] " + "ackfreq[%u] plnk_updt[0x%02x] opts[0x%02x] mtu[%llu] " + " (rmtu[%llu]) cflags[0x%04x] lso_max[%u]\n", pkt->xfer_mode, pkt->addr_type, - (unsigned long long) pkt->addr, - pkt->ack_freq, - (unsigned long long) pkt->mtu); + (unsigned long long)pkt->addr, + pkt->ack_freq, pkt->plnk_updt, pkt->options, + (unsigned long long)pkt->mtu, port->rmtu, pkt->cflags, + pkt->ipv4_lso_maxlen); pkt->tag.sid = vio_send_sid(vio); - if (pkt->xfer_mode != VIO_DRING_MODE || + xfer_mode = pkt->xfer_mode; + /* for version < 1.2, VIO_DRING_MODE = 0x3 and no bitmask */ + if (vio_version_before(vio, 1, 2) && xfer_mode == VIO_DRING_MODE) + xfer_mode = VIO_NEW_DRING_MODE; + + /* MTU negotiation: + * < v1.3 - ETH_FRAME_LEN exactly + * > v1.3 - MIN(pkt.mtu, VNET_MAXPACKET, port->rmtu) and change + * pkt->mtu for ACK + * = v1.3 - ETH_FRAME_LEN + VLAN_HLEN exactly + */ + if (vio_version_before(vio, 1, 3)) { + localmtu = ETH_FRAME_LEN; + } else if (vio_version_after(vio, 1, 3)) { + localmtu = port->rmtu ? port->rmtu : VNET_MAXPACKET; + localmtu = min(pkt->mtu, localmtu); + pkt->mtu = localmtu; + } else { /* v1.3 */ + localmtu = ETH_FRAME_LEN + VLAN_HLEN; + } + port->rmtu = localmtu; + + /* for version >= 1.6, ACK packet mode we support */ + if (vio_version_after_eq(vio, 1, 6)) { + pkt->xfer_mode = VIO_NEW_DRING_MODE; + pkt->options = VIO_TX_DRING; + } + + if (!(xfer_mode | VIO_NEW_DRING_MODE) || pkt->addr_type != VNET_ADDR_ETHERMAC || - pkt->mtu != ETH_FRAME_LEN) { + pkt->mtu != localmtu) { viodbg(HS, "SEND NET ATTR NACK\n"); pkt->tag.stype = VIO_SUBTYPE_NACK; @@ -112,7 +180,14 @@ static int handle_attr_info(struct vio_driver_state *vio, return -ECONNRESET; } else { - viodbg(HS, "SEND NET ATTR ACK\n"); + viodbg(HS, "SEND NET ATTR ACK xmode[0x%x] atype[0x%x] " + "addr[%llx] ackfreq[%u] plnk_updt[0x%02x] opts[0x%02x] " + "mtu[%llu] (rmtu[%llu]) cflags[0x%04x] lso_max[%u]\n", + pkt->xfer_mode, pkt->addr_type, + (unsigned long long)pkt->addr, + pkt->ack_freq, pkt->plnk_updt, pkt->options, + (unsigned long long)pkt->mtu, port->rmtu, pkt->cflags, + pkt->ipv4_lso_maxlen); pkt->tag.stype = VIO_SUBTYPE_ACK; @@ -208,7 +283,7 @@ static int vnet_rx_one(struct vnet_port *port, unsigned int len, int err; err = -EMSGSIZE; - if (unlikely(len < ETH_ZLEN || len > ETH_FRAME_LEN)) { + if (unlikely(len < ETH_ZLEN || len > port->rmtu)) { dev->stats.rx_length_errors++; goto out_dropped; } @@ -283,10 +358,18 @@ static int vnet_send_ack(struct vnet_port *port, struct vio_dring_state *dr, port->raddr[0], port->raddr[1], port->raddr[2], port->raddr[3], port->raddr[4], port->raddr[5]); - err = -ECONNRESET; + break; } } while (err == -EAGAIN); + if (err <= 0 && vio_dring_state == VIO_DRING_STOPPED) { + port->stop_rx_idx = end; + port->stop_rx = true; + } else { + port->stop_rx_idx = 0; + port->stop_rx = false; + } + return err; } @@ -451,7 +534,7 @@ static int vnet_ack(struct vnet_port *port, void *msgbuf) struct net_device *dev; struct vnet *vp; u32 end; - + struct vio_net_desc *desc; if (unlikely(pkt->tag.stype_env != VIO_DRING_DATA)) return 0; @@ -459,7 +542,24 @@ static int vnet_ack(struct vnet_port *port, void *msgbuf) if (unlikely(!idx_is_pending(dr, end))) return 0; + /* sync for race conditions with vnet_start_xmit() and tell xmit it + * is time to send a trigger. + */ dr->cons = next_idx(end, dr); + desc = vio_dring_entry(dr, dr->cons); + if (desc->hdr.state == VIO_DESC_READY && port->start_cons) { + /* vnet_start_xmit() just populated this dring but missed + * sending the "start" LDC message to the consumer. + * Send a "start" trigger on its behalf. + */ + if (__vnet_tx_trigger(port, dr->cons) > 0) + port->start_cons = false; + else + port->start_cons = true; + } else { + port->start_cons = true; + } + vp = port->vp; dev = vp->dev; @@ -531,13 +631,15 @@ static void vnet_event(void *arg, int event) vio_link_state_change(vio, event); spin_unlock_irqrestore(&vio->lock, flags); - if (event == LDC_EVENT_RESET) + if (event == LDC_EVENT_RESET) { + port->rmtu = 0; vio_port_up(vio); + } return; } if (unlikely(event != LDC_EVENT_DATA_READY)) { - pr_warning("Unexpected LDC event %d\n", event); + pr_warn("Unexpected LDC event %d\n", event); spin_unlock_irqrestore(&vio->lock, flags); return; } @@ -600,7 +702,7 @@ static void vnet_event(void *arg, int event) local_irq_restore(flags); } -static int __vnet_tx_trigger(struct vnet_port *port) +static int __vnet_tx_trigger(struct vnet_port *port, u32 start) { struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING]; struct vio_dring_data hdr = { @@ -611,12 +713,21 @@ static int __vnet_tx_trigger(struct vnet_port *port) .sid = vio_send_sid(&port->vio), }, .dring_ident = dr->ident, - .start_idx = dr->prod, + .start_idx = start, .end_idx = (u32) -1, }; int err, delay; int retries = 0; + if (port->stop_rx) { + err = vnet_send_ack(port, + &port->vio.drings[VIO_DRIVER_RX_RING], + port->stop_rx_idx, -1, + VIO_DRING_STOPPED); + if (err <= 0) + return err; + } + hdr.seq = dr->snd_nxt; delay = 1; do { @@ -676,6 +787,117 @@ struct vnet_port *tx_port_find(struct vnet *vp, struct sk_buff *skb) return ret; } +static struct sk_buff *vnet_clean_tx_ring(struct vnet_port *port, + unsigned *pending) +{ + struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING]; + struct sk_buff *skb = NULL; + int i, txi; + + *pending = 0; + + txi = dr->prod-1; + if (txi < 0) + txi = VNET_TX_RING_SIZE-1; + + for (i = 0; i < VNET_TX_RING_SIZE; ++i) { + struct vio_net_desc *d; + + d = vio_dring_entry(dr, txi); + + if (d->hdr.state == VIO_DESC_DONE) { + if (port->tx_bufs[txi].skb) { + BUG_ON(port->tx_bufs[txi].skb->next); + + port->tx_bufs[txi].skb->next = skb; + skb = port->tx_bufs[txi].skb; + port->tx_bufs[txi].skb = NULL; + + ldc_unmap(port->vio.lp, + port->tx_bufs[txi].cookies, + port->tx_bufs[txi].ncookies); + } + d->hdr.state = VIO_DESC_FREE; + } else if (d->hdr.state == VIO_DESC_READY) { + (*pending)++; + } else if (d->hdr.state == VIO_DESC_FREE) { + break; + } + --txi; + if (txi < 0) + txi = VNET_TX_RING_SIZE-1; + } + return skb; +} + +static inline void vnet_free_skbs(struct sk_buff *skb) +{ + struct sk_buff *next; + + while (skb) { + next = skb->next; + skb->next = NULL; + dev_kfree_skb(skb); + skb = next; + } +} + +static void vnet_clean_timer_expire(unsigned long port0) +{ + struct vnet_port *port = (struct vnet_port *)port0; + struct sk_buff *freeskbs; + unsigned pending; + unsigned long flags; + + spin_lock_irqsave(&port->vio.lock, flags); + freeskbs = vnet_clean_tx_ring(port, &pending); + spin_unlock_irqrestore(&port->vio.lock, flags); + + vnet_free_skbs(freeskbs); + + if (pending) + (void)mod_timer(&port->clean_timer, + jiffies + VNET_CLEAN_TIMEOUT); + else + del_timer(&port->clean_timer); +} + +static inline struct sk_buff *vnet_skb_shape(struct sk_buff *skb, void **pstart, + int *plen) +{ + struct sk_buff *nskb; + int len, pad; + + len = skb->len; + pad = 0; + if (len < ETH_ZLEN) { + pad += ETH_ZLEN - skb->len; + len += pad; + } + len += VNET_PACKET_SKIP; + pad += 8 - (len & 7); + len += 8 - (len & 7); + + if (((unsigned long)skb->data & 7) != VNET_PACKET_SKIP || + skb_tailroom(skb) < pad || + skb_headroom(skb) < VNET_PACKET_SKIP) { + nskb = alloc_and_align_skb(skb->dev, skb->len); + skb_reserve(nskb, VNET_PACKET_SKIP); + if (skb_copy_bits(skb, 0, nskb->data, skb->len)) { + dev_kfree_skb(nskb); + dev_kfree_skb(skb); + return NULL; + } + (void)skb_put(nskb, skb->len); + dev_kfree_skb(skb); + skb = nskb; + } + + *pstart = skb->data - VNET_PACKET_SKIP; + *plen = len; + return skb; +} + static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct vnet *vp = netdev_priv(dev); @@ -684,16 +906,55 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) struct vio_net_desc *d; unsigned long flags; unsigned int len; - void *tx_buf; - int i, err; + struct sk_buff *freeskbs = NULL; + int i, err, txi; + void *start = NULL; + int nlen = 0; + unsigned pending = 0; if (unlikely(!port)) goto out_dropped; + skb = vnet_skb_shape(skb, &start, &nlen); + + if (unlikely(!skb)) + goto out_dropped; + + if (skb->len > port->rmtu) { + unsigned long localmtu = port->rmtu - ETH_HLEN; + + if (vio_version_after_eq(&port->vio, 1, 3)) + localmtu -= VLAN_HLEN; + + if (skb->protocol == htons(ETH_P_IP)) { + struct flowi4 fl4; + struct rtable *rt = NULL; + + memset(&fl4, 0, sizeof(fl4)); + fl4.flowi4_oif = dev->ifindex; + fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); + fl4.daddr = ip_hdr(skb)->daddr; + fl4.saddr = ip_hdr(skb)->saddr; + + rt = ip_route_output_key(dev_net(dev), &fl4); + if (!IS_ERR(rt)) { + skb_dst_set(skb, &rt->dst); + icmp_send(skb, ICMP_DEST_UNREACH, + ICMP_FRAG_NEEDED, + htonl(localmtu)); + } + } +#if IS_ENABLED(CONFIG_IPV6) + else if (skb->protocol == htons(ETH_P_IPV6)) + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, localmtu); +#endif + goto out_dropped; + } + spin_lock_irqsave(&port->vio.lock, flags); dr = &port->vio.drings[VIO_DRIVER_TX_RING]; - if (unlikely(vnet_tx_dring_avail(dr) < 2)) { + if (unlikely(vnet_tx_dring_avail(dr) < 1)) { if (!netif_queue_stopped(dev)) { netif_stop_queue(dev); @@ -707,14 +968,27 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) d = vio_dring_cur(dr); - tx_buf = port->tx_bufs[dr->prod].buf; - skb_copy_from_linear_data(skb, tx_buf + VNET_PACKET_SKIP, skb->len); + txi = dr->prod; + + freeskbs = vnet_clean_tx_ring(port, &pending); + + BUG_ON(port->tx_bufs[txi].skb); len = skb->len; - if (len < ETH_ZLEN) { + if (len < ETH_ZLEN) len = ETH_ZLEN; - memset(tx_buf+VNET_PACKET_SKIP+skb->len, 0, len - skb->len); + + port->tx_bufs[txi].skb = skb; + skb = NULL; + + err = ldc_map_single(port->vio.lp, start, nlen, + port->tx_bufs[txi].cookies, VNET_MAXCOOKIES, + (LDC_MAP_SHADOW | LDC_MAP_DIRECT | LDC_MAP_RW)); + if (err < 0) { + netdev_info(dev, "tx buffer map error %d\n", err); + goto out_dropped_unlock; } + port->tx_bufs[txi].ncookies = err; /* We don't rely on the ACKs to free the skb in vnet_start_xmit(), * thus it is safe to not set VIO_ACK_ENABLE for each transmission: @@ -726,9 +1000,9 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) */ d->hdr.ack = VIO_ACK_DISABLE; d->size = len; - d->ncookies = port->tx_bufs[dr->prod].ncookies; + d->ncookies = port->tx_bufs[txi].ncookies; for (i = 0; i < d->ncookies; i++) - d->cookies[i] = port->tx_bufs[dr->prod].cookies[i]; + d->cookies[i] = port->tx_bufs[txi].cookies[i]; /* This has to be a non-SMP write barrier because we are writing * to memory which is shared with the peer LDOM. @@ -737,7 +1011,30 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) d->hdr.state = VIO_DESC_READY; - err = __vnet_tx_trigger(port); + /* Exactly one ldc "start" trigger (for dr->cons) needs to be sent + * to notify the consumer that some descriptors are READY. + * After that "start" trigger, no additional triggers are needed until + * a DRING_STOPPED is received from the consumer. The dr->cons field + * (set up by vnet_ack()) has the value of the next dring index + * that has not yet been ack-ed. We send a "start" trigger here + * if, and only if, start_cons is true (reset it afterward). Conversely, + * vnet_ack() should check if the dring corresponding to cons + * is marked READY, but start_cons was false. + * If so, vnet_ack() should send out the missed "start" trigger. + * + * Note that the wmb() above makes sure the cookies et al. are + * not globally visible before the VIO_DESC_READY, and that the + * stores are ordered correctly by the compiler. The consumer will + * not proceed until the VIO_DESC_READY is visible assuring that + * the consumer does not observe anything related to descriptors + * out of order. The HV trap from the LDC start trigger is the + * producer to consumer announcement that work is available to the + * consumer + */ + if (!port->start_cons) + goto ldc_start_done; /* previous trigger suffices */ + + err = __vnet_tx_trigger(port, dr->cons); if (unlikely(err < 0)) { netdev_info(dev, "TX trigger error %d\n", err); d->hdr.state = VIO_DESC_FREE; @@ -745,11 +1042,14 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) goto out_dropped_unlock; } +ldc_start_done: + port->start_cons = false; + dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; + dev->stats.tx_bytes += port->tx_bufs[txi].skb->len; dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1); - if (unlikely(vnet_tx_dring_avail(dr) < 2)) { + if (unlikely(vnet_tx_dring_avail(dr) < 1)) { netif_stop_queue(dev); if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr)) netif_wake_queue(dev); @@ -757,7 +1057,9 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) spin_unlock_irqrestore(&port->vio.lock, flags); - dev_kfree_skb(skb); + vnet_free_skbs(freeskbs); + + (void)mod_timer(&port->clean_timer, jiffies + VNET_CLEAN_TIMEOUT); return NETDEV_TX_OK; @@ -765,7 +1067,14 @@ out_dropped_unlock: spin_unlock_irqrestore(&port->vio.lock, flags); out_dropped: - dev_kfree_skb(skb); + if (skb) + dev_kfree_skb(skb); + vnet_free_skbs(freeskbs); + if (pending) + (void)mod_timer(&port->clean_timer, + jiffies + VNET_CLEAN_TIMEOUT); + else if (port) + del_timer(&port->clean_timer); dev->stats.tx_dropped++; return NETDEV_TX_OK; } @@ -911,7 +1220,7 @@ static void vnet_set_rx_mode(struct net_device *dev) static int vnet_change_mtu(struct net_device *dev, int new_mtu) { - if (new_mtu != ETH_DATA_LEN) + if (new_mtu < 68 || new_mtu > 65535) return -EINVAL; dev->mtu = new_mtu; @@ -967,17 +1276,22 @@ static void vnet_port_free_tx_bufs(struct vnet_port *port) } for (i = 0; i < VNET_TX_RING_SIZE; i++) { - void *buf = port->tx_bufs[i].buf; + struct vio_net_desc *d; + void *skb = port->tx_bufs[i].skb; - if (!buf) + if (!skb) continue; + d = vio_dring_entry(dr, i); + if (d->hdr.state == VIO_DESC_READY) + pr_warn("active transmit buffers freed\n"); + ldc_unmap(port->vio.lp, port->tx_bufs[i].cookies, port->tx_bufs[i].ncookies); - - kfree(buf); - port->tx_bufs[i].buf = NULL; + dev_kfree_skb(skb); + port->tx_bufs[i].skb = NULL; + d->hdr.state = VIO_DESC_FREE; } } @@ -988,34 +1302,6 @@ static int vnet_port_alloc_tx_bufs(struct vnet_port *port) int i, err, ncookies; void *dring; - for (i = 0; i < VNET_TX_RING_SIZE; i++) { - void *buf = kzalloc(ETH_FRAME_LEN + 8, GFP_KERNEL); - int map_len = (ETH_FRAME_LEN + 7) & ~7; - - err = -ENOMEM; - if (!buf) - goto err_out; - - err = -EFAULT; - if ((unsigned long)buf & (8UL - 1)) { - pr_err("TX buffer misaligned\n"); - kfree(buf); - goto err_out; - } - - err = ldc_map_single(port->vio.lp, buf, map_len, - port->tx_bufs[i].cookies, 2, - (LDC_MAP_SHADOW | - LDC_MAP_DIRECT | - LDC_MAP_RW)); - if (err < 0) { - kfree(buf); - goto err_out; - } - port->tx_bufs[i].buf = buf; - port->tx_bufs[i].ncookies = err; - } - dr = &port->vio.drings[VIO_DRIVER_TX_RING]; len = (VNET_TX_RING_SIZE * @@ -1038,9 +1324,16 @@ static int vnet_port_alloc_tx_bufs(struct vnet_port *port) (sizeof(struct ldc_trans_cookie) * 2)); dr->num_entries = VNET_TX_RING_SIZE; dr->prod = dr->cons = 0; + port->start_cons = true; /* need an initial trigger */ dr->pending = VNET_TX_RING_SIZE; dr->ncookies = ncookies; + for (i = 0; i < VNET_TX_RING_SIZE; ++i) { + struct vio_net_desc *d; + + d = vio_dring_entry(dr, i); + d->hdr.state = VIO_DESC_FREE; + } return 0; err_out: @@ -1072,6 +1365,8 @@ static struct vnet *vnet_new(const u64 *local_mac) dev = alloc_etherdev(sizeof(*vp)); if (!dev) return ERR_PTR(-ENOMEM); + dev->needed_headroom = VNET_PACKET_SKIP + 8; + dev->needed_tailroom = 8; for (i = 0; i < ETH_ALEN; i++) dev->dev_addr[i] = (*local_mac >> (5 - i) * 8) & 0xff; @@ -1266,6 +1561,9 @@ static int vnet_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) pr_info("%s: PORT ( remote-mac %pM%s )\n", vp->dev->name, port->raddr, switch_port ? " switch-port" : ""); + setup_timer(&port->clean_timer, vnet_clean_timer_expire, + (unsigned long)port); + vio_port_up(&port->vio); mdesc_release(hp); @@ -1292,6 +1590,7 @@ static int vnet_port_remove(struct vio_dev *vdev) unsigned long flags; del_timer_sync(&port->vio.timer); + del_timer_sync(&port->clean_timer); spin_lock_irqsave(&vp->lock, flags); list_del(&port->list); diff --git a/drivers/net/ethernet/sun/sunvnet.h b/drivers/net/ethernet/sun/sunvnet.h index de5c2c64996f..c91104542619 100644 --- a/drivers/net/ethernet/sun/sunvnet.h +++ b/drivers/net/ethernet/sun/sunvnet.h @@ -11,6 +11,12 @@ */ #define VNET_TX_TIMEOUT (5 * HZ) +/* length of time (or less) we expect pending descriptors to be marked + * as VIO_DESC_DONE and skbs ready to be freed + */ +#define VNET_CLEAN_TIMEOUT ((HZ/100)+1) + +#define VNET_MAXPACKET (65535ULL + ETH_HLEN + VLAN_HLEN) #define VNET_TX_RING_SIZE 512 #define VNET_TX_WAKEUP_THRESH(dr) ((dr)->pending / 4) @@ -20,10 +26,12 @@ */ #define VNET_PACKET_SKIP 6 +#define VNET_MAXCOOKIES (VNET_MAXPACKET/PAGE_SIZE + 1) + struct vnet_tx_entry { - void *buf; + struct sk_buff *skb; unsigned int ncookies; - struct ldc_trans_cookie cookies[2]; + struct ldc_trans_cookie cookies[VNET_MAXCOOKIES]; }; struct vnet; @@ -40,6 +48,14 @@ struct vnet_port { struct vnet_tx_entry tx_bufs[VNET_TX_RING_SIZE]; struct list_head list; + + u32 stop_rx_idx; + bool stop_rx; + bool start_cons; + + struct timer_list clean_timer; + + u64 rmtu; }; static inline struct vnet_port *to_vnet_port(struct vio_driver_state *vio) |