EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */
offsetof(struct bpf_array, map.max_entries));
EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */
-#define OFFSET1 44 /* number of bytes to jump */
+#define OFFSET1 47 /* number of bytes to jump */
EMIT2(X86_JBE, OFFSET1); /* jbe out */
label1 = cnt;
*/
EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */
EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 33
+#define OFFSET2 36
EMIT2(X86_JA, OFFSET2); /* ja out */
label2 = cnt;
EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */
EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */
/* prog = array->prog[index]; */
- EMIT4(0x48, 0x8D, 0x44, 0xD6); /* lea rax, [rsi + rdx * 8 + 0x50] */
- EMIT1(offsetof(struct bpf_array, prog));
+ EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */
+ offsetof(struct bpf_array, prog));
EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */
/* if (prog == NULL)
return bp->rx_buffers + bp->rx_buffer_size * macb_rx_ring_wrap(index);
}
+/* I/O accessors */
+static u32 hw_readl_native(struct macb *bp, int offset)
+{
+ return __raw_readl(bp->regs + offset);
+}
+
+static void hw_writel_native(struct macb *bp, int offset, u32 value)
+{
+ __raw_writel(value, bp->regs + offset);
+}
+
+static u32 hw_readl(struct macb *bp, int offset)
+{
+ return readl_relaxed(bp->regs + offset);
+}
+
+static void hw_writel(struct macb *bp, int offset, u32 value)
+{
+ writel_relaxed(value, bp->regs + offset);
+}
+
+/*
+ * Find the CPU endianness by using the loopback bit of NCR register. When the
+ * CPU is in big endian we need to program swaped mode for management
+ * descriptor access.
+ */
+static bool hw_is_native_io(void __iomem *addr)
+{
+ u32 value = MACB_BIT(LLB);
+
+ __raw_writel(value, addr + MACB_NCR);
+ value = __raw_readl(addr + MACB_NCR);
+
+ /* Write 0 back to disable everything */
+ __raw_writel(0, addr + MACB_NCR);
+
+ return value == MACB_BIT(LLB);
+}
+
+static bool hw_is_gem(void __iomem *addr, bool native_io)
+{
+ u32 id;
+
+ if (native_io)
+ id = __raw_readl(addr + MACB_MID);
+ else
+ id = readl_relaxed(addr + MACB_MID);
+
+ return MACB_BFEXT(IDNUM, id) >= 0x2;
+}
+
static void macb_set_hwaddr(struct macb *bp)
{
u32 bottom;
}
}
- netdev_info(bp->dev, "invalid hw address, using random\n");
+ dev_info(&bp->pdev->dev, "invalid hw address, using random\n");
eth_hw_addr_random(bp->dev);
}
struct macb *bp = netdev_priv(dev);
struct phy_device *phydev = bp->phy_dev;
unsigned long flags;
-
int status_change = 0;
spin_lock_irqsave(&bp->lock, flags);
static void macb_update_stats(struct macb *bp)
{
- u32 __iomem *reg = bp->regs + MACB_PFR;
u32 *p = &bp->hw_stats.macb.rx_pause_frames;
u32 *end = &bp->hw_stats.macb.tx_pause_frames + 1;
+ int offset = MACB_PFR;
WARN_ON((unsigned long)(end - p - 1) != (MACB_TPF - MACB_PFR) / 4);
- for(; p < end; p++, reg++)
- *p += readl_relaxed(reg);
+ for(; p < end; p++, offset += 4)
+ *p += bp->macb_reg_readl(bp, offset);
}
static int macb_halt_tx(struct macb *bp)
}
#endif
-static inline unsigned int macb_count_tx_descriptors(struct macb *bp,
- unsigned int len)
-{
- return (len + bp->max_tx_length - 1) / bp->max_tx_length;
-}
-
static unsigned int macb_tx_map(struct macb *bp,
struct macb_queue *queue,
struct sk_buff *skb)
* socket buffer: skb fragments of jumbo frames may need to be
* splitted into many buffer descriptors.
*/
- count = macb_count_tx_descriptors(bp, skb_headlen(skb));
+ count = DIV_ROUND_UP(skb_headlen(skb), bp->max_tx_length);
nr_frags = skb_shinfo(skb)->nr_frags;
for (f = 0; f < nr_frags; f++) {
frag_size = skb_frag_size(&skb_shinfo(skb)->frags[f]);
- count += macb_count_tx_descriptors(bp, frag_size);
+ count += DIV_ROUND_UP(frag_size, bp->max_tx_length);
}
spin_lock_irqsave(&bp->lock, flags);
static void macb_configure_dma(struct macb *bp)
{
u32 dmacfg;
- u32 tmp, ncr;
if (macb_is_gem(bp)) {
dmacfg = gem_readl(bp, DMACFG) & ~GEM_BF(RXBS, -1L);
dmacfg |= GEM_BIT(TXPBMS) | GEM_BF(RXBMS, -1L);
dmacfg &= ~GEM_BIT(ENDIA_PKT);
- /* Find the CPU endianness by using the loopback bit of net_ctrl
- * register. save it first. When the CPU is in big endian we
- * need to program swaped mode for management descriptor access.
- */
- ncr = macb_readl(bp, NCR);
- __raw_writel(MACB_BIT(LLB), bp->regs + MACB_NCR);
- tmp = __raw_readl(bp->regs + MACB_NCR);
-
- if (tmp == MACB_BIT(LLB))
+ if (bp->native_io)
dmacfg &= ~GEM_BIT(ENDIA_DESC);
else
dmacfg |= GEM_BIT(ENDIA_DESC); /* CPU in big endian */
- /* Restore net_ctrl */
- macb_writel(bp, NCR, ncr);
-
if (bp->dev->features & NETIF_F_HW_CSUM)
dmacfg |= GEM_BIT(TXCOEN);
else
static void gem_update_stats(struct macb *bp)
{
- int i;
+ unsigned int i;
u32 *p = &bp->hw_stats.gem.tx_octets_31_0;
for (i = 0; i < GEM_STATS_LEN; ++i, ++p) {
u32 offset = gem_statistics[i].offset;
- u64 val = readl_relaxed(bp->regs + offset);
+ u64 val = bp->macb_reg_readl(bp, offset);
bp->ethtool_stats[i] += val;
*p += val;
if (offset == GEM_OCTTXL || offset == GEM_OCTRXL) {
/* Add GEM_OCTTXH, GEM_OCTRXH */
- val = readl_relaxed(bp->regs + offset + 4);
+ val = bp->macb_reg_readl(bp, offset + 4);
bp->ethtool_stats[i] += ((u64)val) << 32;
*(++p) += val;
}
static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p)
{
- int i;
+ unsigned int i;
switch (sset) {
case ETH_SS_STATS:
if (dt_conf)
bp->caps = dt_conf->caps;
- if (macb_is_gem_hw(bp->regs)) {
+ if (hw_is_gem(bp->regs, bp->native_io)) {
bp->caps |= MACB_CAPS_MACB_IS_GEM;
dcfg = gem_readl(bp, DCFG1);
bp->caps |= MACB_CAPS_FIFO_MODE;
}
- netdev_dbg(bp->dev, "Cadence caps 0x%08x\n", bp->caps);
+ dev_dbg(&bp->pdev->dev, "Cadence caps 0x%08x\n", bp->caps);
}
static void macb_probe_queues(void __iomem *mem,
+ bool native_io,
unsigned int *queue_mask,
unsigned int *num_queues)
{
* we are early in the probe process and don't have the
* MACB_CAPS_MACB_IS_GEM flag positioned
*/
- if (!macb_is_gem_hw(mem))
+ if (!hw_is_gem(mem, native_io))
return;
/* bit 0 is never set but queue 0 always exists */
struct clk *pclk, *hclk, *tx_clk;
unsigned int queue_mask, num_queues;
struct macb_platform_data *pdata;
+ bool native_io;
struct phy_device *phydev;
struct net_device *dev;
struct resource *regs;
struct macb *bp;
int err;
+ regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ mem = devm_ioremap_resource(&pdev->dev, regs);
+ if (IS_ERR(mem))
+ return PTR_ERR(mem);
+
if (np) {
const struct of_device_id *match;
if (err)
return err;
- regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- mem = devm_ioremap_resource(&pdev->dev, regs);
- if (IS_ERR(mem)) {
- err = PTR_ERR(mem);
- goto err_disable_clocks;
- }
+ native_io = hw_is_native_io(mem);
- macb_probe_queues(mem, &queue_mask, &num_queues);
+ macb_probe_queues(mem, native_io, &queue_mask, &num_queues);
dev = alloc_etherdev_mq(sizeof(*bp), num_queues);
if (!dev) {
err = -ENOMEM;
bp->pdev = pdev;
bp->dev = dev;
bp->regs = mem;
+ bp->native_io = native_io;
+ if (native_io) {
+ bp->macb_reg_readl = hw_readl_native;
+ bp->macb_reg_writel = hw_writel_native;
+ } else {
+ bp->macb_reg_readl = hw_readl;
+ bp->macb_reg_writel = hw_writel;
+ }
bp->num_queues = num_queues;
bp->queue_mask = queue_mask;
if (macb_config)
bp->pclk = pclk;
bp->hclk = hclk;
bp->tx_clk = tx_clk;
- if (macb_config->jumbo_max_len) {
+ if (macb_config)
bp->jumbo_max_len = macb_config->jumbo_max_len;
- }
spin_lock_init(&bp->lock);
| GEM_BF(name, value))
/* Register access macros */
-#define macb_readl(port,reg) \
- readl_relaxed((port)->regs + MACB_##reg)
-#define macb_writel(port,reg,value) \
- writel_relaxed((value), (port)->regs + MACB_##reg)
-#define gem_readl(port, reg) \
- readl_relaxed((port)->regs + GEM_##reg)
-#define gem_writel(port, reg, value) \
- writel_relaxed((value), (port)->regs + GEM_##reg)
-#define queue_readl(queue, reg) \
- readl_relaxed((queue)->bp->regs + (queue)->reg)
-#define queue_writel(queue, reg, value) \
- writel_relaxed((value), (queue)->bp->regs + (queue)->reg)
+#define macb_readl(port, reg) (port)->macb_reg_readl((port), MACB_##reg)
+#define macb_writel(port, reg, value) (port)->macb_reg_writel((port), MACB_##reg, (value))
+#define gem_readl(port, reg) (port)->macb_reg_readl((port), GEM_##reg)
+#define gem_writel(port, reg, value) (port)->macb_reg_writel((port), GEM_##reg, (value))
+#define queue_readl(queue, reg) (queue)->bp->macb_reg_readl((queue)->bp, (queue)->reg)
+#define queue_writel(queue, reg, value) (queue)->bp->macb_reg_writel((queue)->bp, (queue)->reg, (value))
/* Conditional GEM/MACB macros. These perform the operation to the correct
* register dependent on whether the device is a GEM or a MACB. For registers
struct macb {
void __iomem *regs;
+ bool native_io;
+
+ /* hardware IO accessors */
+ u32 (*macb_reg_readl)(struct macb *bp, int offset);
+ void (*macb_reg_writel)(struct macb *bp, int offset, u32 value);
unsigned int rx_tail;
unsigned int rx_prepared_head;
struct mii_bus *mii_bus;
struct phy_device *phy_dev;
- unsigned int link;
- unsigned int speed;
- unsigned int duplex;
+ int link;
+ int speed;
+ int duplex;
u32 caps;
unsigned int dma_burst_length;
return !!(bp->caps & MACB_CAPS_MACB_IS_GEM);
}
-static inline bool macb_is_gem_hw(void __iomem *addr)
-{
- return !!(MACB_BFEXT(IDNUM, readl_relaxed(addr + MACB_MID)) >= 0x2);
-}
-
#endif /* _MACB_H */
*/
#define NICPF_CLK_PER_INT_TICK 2
+/* Time to wait before we decide that a SQ is stuck.
+ *
+ * Since both pkt rx and tx notifications are done with same CQ,
+ * when packets are being received at very high rate (eg: L2 forwarding)
+ * then freeing transmitted skbs will be delayed and watchdog
+ * will kick in, resetting interface. Hence keeping this value high.
+ */
+#define NICVF_TX_TIMEOUT (50 * HZ)
+
struct nicvf_cq_poll {
u8 cq_idx; /* Completion queue index */
struct napi_struct napi;
/* Tx */
u64 tx_frames_ok;
u64 tx_drops;
- u64 tx_busy;
u64 tx_tso;
+ u64 txq_stop;
+ u64 txq_wake;
};
struct nicvf {
NICVF_DRV_STAT(rx_frames_jumbo),
NICVF_DRV_STAT(rx_drops),
NICVF_DRV_STAT(tx_frames_ok),
- NICVF_DRV_STAT(tx_busy),
NICVF_DRV_STAT(tx_tso),
NICVF_DRV_STAT(tx_drops),
+ NICVF_DRV_STAT(txq_stop),
+ NICVF_DRV_STAT(txq_wake),
};
static const struct nicvf_stat nicvf_queue_stats[] = {
static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
{
+ struct nicvf *nic = netdev_priv(netdev);
int stats, qidx;
if (sset != ETH_SS_STATS)
data += ETH_GSTRING_LEN;
}
- for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) {
+ for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) {
for (stats = 0; stats < nicvf_n_queue_stats; stats++) {
sprintf(data, "rxq%d: %s", qidx,
nicvf_queue_stats[stats].name);
}
}
- for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) {
+ for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) {
for (stats = 0; stats < nicvf_n_queue_stats; stats++) {
sprintf(data, "txq%d: %s", qidx,
nicvf_queue_stats[stats].name);
static int nicvf_get_sset_count(struct net_device *netdev, int sset)
{
+ struct nicvf *nic = netdev_priv(netdev);
+
if (sset != ETH_SS_STATS)
return -EINVAL;
return nicvf_n_hw_stats + nicvf_n_drv_stats +
(nicvf_n_queue_stats *
- (MAX_RCV_QUEUES_PER_QS + MAX_SND_QUEUES_PER_QS)) +
+ (nic->qs->rq_cnt + nic->qs->sq_cnt)) +
BGX_RX_STATS_COUNT + BGX_TX_STATS_COUNT;
}
*(data++) = ((u64 *)&nic->drv_stats)
[nicvf_drv_stats[stat].index];
- for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) {
+ for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) {
for (stat = 0; stat < nicvf_n_queue_stats; stat++)
*(data++) = ((u64 *)&nic->qs->rq[qidx].stats)
[nicvf_queue_stats[stat].index];
}
- for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) {
+ for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) {
for (stat = 0; stat < nicvf_n_queue_stats; stat++)
*(data++) = ((u64 *)&nic->qs->sq[qidx].stats)
[nicvf_queue_stats[stat].index];
{
struct nicvf *nic = netdev_priv(dev);
int err = 0;
+ bool if_up = netif_running(dev);
if (!channel->rx_count || !channel->tx_count)
return -EINVAL;
if (channel->tx_count > MAX_SND_QUEUES_PER_QS)
return -EINVAL;
+ if (if_up)
+ nicvf_stop(dev);
+
nic->qs->rq_cnt = channel->rx_count;
nic->qs->sq_cnt = channel->tx_count;
nic->qs->cq_cnt = max(nic->qs->rq_cnt, nic->qs->sq_cnt);
if (err)
return err;
- if (!netif_running(dev))
- return err;
+ if (if_up)
+ nicvf_open(dev);
- nicvf_stop(dev);
- nicvf_open(dev);
netdev_info(dev, "Setting num Tx rings to %d, Rx rings to %d success\n",
nic->qs->sq_cnt, nic->qs->rq_cnt);
nic->duplex == DUPLEX_FULL ?
"Full duplex" : "Half duplex");
netif_carrier_on(nic->netdev);
- netif_tx_wake_all_queues(nic->netdev);
+ netif_tx_start_all_queues(nic->netdev);
} else {
netdev_info(nic->netdev, "%s: Link is Down\n",
nic->netdev->name);
if (skb) {
prefetch(skb);
dev_consume_skb_any(skb);
+ sq->skbuff[cqe_tx->sqe_ptr] = (u64)NULL;
}
}
static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
struct napi_struct *napi, int budget)
{
- int processed_cqe, work_done = 0;
+ int processed_cqe, work_done = 0, tx_done = 0;
int cqe_count, cqe_head;
struct nicvf *nic = netdev_priv(netdev);
struct queue_set *qs = nic->qs;
struct cmp_queue *cq = &qs->cq[cq_idx];
struct cqe_rx_t *cq_desc;
+ struct netdev_queue *txq;
spin_lock_bh(&cq->lock);
loop:
cqe_head = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, cq_idx) >> 9;
cqe_head &= 0xFFFF;
- netdev_dbg(nic->netdev, "%s cqe_count %d cqe_head %d\n",
- __func__, cqe_count, cqe_head);
+ netdev_dbg(nic->netdev, "%s CQ%d cqe_count %d cqe_head %d\n",
+ __func__, cq_idx, cqe_count, cqe_head);
while (processed_cqe < cqe_count) {
/* Get the CQ descriptor */
cq_desc = (struct cqe_rx_t *)GET_CQ_DESC(cq, cqe_head);
break;
}
- netdev_dbg(nic->netdev, "cq_desc->cqe_type %d\n",
- cq_desc->cqe_type);
+ netdev_dbg(nic->netdev, "CQ%d cq_desc->cqe_type %d\n",
+ cq_idx, cq_desc->cqe_type);
switch (cq_desc->cqe_type) {
case CQE_TYPE_RX:
nicvf_rcv_pkt_handler(netdev, napi, cq,
case CQE_TYPE_SEND:
nicvf_snd_pkt_handler(netdev, cq,
(void *)cq_desc, CQE_TYPE_SEND);
+ tx_done++;
break;
case CQE_TYPE_INVALID:
case CQE_TYPE_RX_SPLIT:
}
processed_cqe++;
}
- netdev_dbg(nic->netdev, "%s processed_cqe %d work_done %d budget %d\n",
- __func__, processed_cqe, work_done, budget);
+ netdev_dbg(nic->netdev,
+ "%s CQ%d processed_cqe %d work_done %d budget %d\n",
+ __func__, cq_idx, processed_cqe, work_done, budget);
/* Ring doorbell to inform H/W to reuse processed CQEs */
nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_DOOR,
goto loop;
done:
+ /* Wakeup TXQ if its stopped earlier due to SQ full */
+ if (tx_done) {
+ txq = netdev_get_tx_queue(netdev, cq_idx);
+ if (netif_tx_queue_stopped(txq)) {
+ netif_tx_start_queue(txq);
+ nic->drv_stats.txq_wake++;
+ if (netif_msg_tx_err(nic))
+ netdev_warn(netdev,
+ "%s: Transmit queue wakeup SQ%d\n",
+ netdev->name, cq_idx);
+ }
+ }
+
spin_unlock_bh(&cq->lock);
return work_done;
}
struct net_device *netdev = napi->dev;
struct nicvf *nic = netdev_priv(netdev);
struct nicvf_cq_poll *cq;
- struct netdev_queue *txq;
cq = container_of(napi, struct nicvf_cq_poll, napi);
work_done = nicvf_cq_intr_handler(netdev, cq->cq_idx, napi, budget);
- txq = netdev_get_tx_queue(netdev, cq->cq_idx);
- if (netif_tx_queue_stopped(txq))
- netif_tx_wake_queue(txq);
-
if (work_done < budget) {
/* Slow packet rate, exit polling */
napi_complete(napi);
return NETDEV_TX_OK;
}
- if (!nicvf_sq_append_skb(nic, skb) && !netif_tx_queue_stopped(txq)) {
+ if (!netif_tx_queue_stopped(txq) && !nicvf_sq_append_skb(nic, skb)) {
netif_tx_stop_queue(txq);
- nic->drv_stats.tx_busy++;
+ nic->drv_stats.txq_stop++;
if (netif_msg_tx_err(nic))
netdev_warn(netdev,
"%s: Transmit ring full, stopping SQ%d\n",
nicvf_send_msg_to_pf(nic, &mbx);
netif_carrier_off(netdev);
- netif_tx_disable(netdev);
/* Disable RBDR & QS error interrupts */
for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) {
kfree(cq_poll);
}
+ netif_tx_disable(netdev);
+
/* Free resources */
nicvf_config_data_transfer(nic, false);
for (qidx = 0; qidx < qs->rbdr_cnt; qidx++)
nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx);
+ nic->drv_stats.txq_stop = 0;
+ nic->drv_stats.txq_wake = 0;
+
netif_carrier_on(netdev);
netif_tx_start_all_queues(netdev);
netdev->hw_features = netdev->features;
netdev->netdev_ops = &nicvf_netdev_ops;
+ netdev->watchdog_timeo = NICVF_TX_TIMEOUT;
INIT_WORK(&nic->reset_task, nicvf_reset_task);
pci_disable_device(pdev);
}
+static void nicvf_shutdown(struct pci_dev *pdev)
+{
+ nicvf_remove(pdev);
+}
+
static struct pci_driver nicvf_driver = {
.name = DRV_NAME,
.id_table = nicvf_id_table,
.probe = nicvf_probe,
.remove = nicvf_remove,
+ .shutdown = nicvf_shutdown,
};
static int __init nicvf_init_module(void)
/* Allocate a new page */
if (!nic->rb_page) {
- nic->rb_page = alloc_pages(gfp | __GFP_COMP, order);
+ nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
+ order);
if (!nic->rb_page) {
- netdev_err(nic->netdev, "Failed to allocate new rcv buffer\n");
+ netdev_err(nic->netdev,
+ "Failed to allocate new rcv buffer\n");
return -ENOMEM;
}
nic->rb_page_offset = 0;
return;
if (sq->tso_hdrs)
- dma_free_coherent(&nic->pdev->dev, sq->dmem.q_len,
+ dma_free_coherent(&nic->pdev->dev,
+ sq->dmem.q_len * TSO_HEADER_SIZE,
sq->tso_hdrs, sq->tso_hdrs_phys);
kfree(sq->skbuff);
continue;
}
skb = (struct sk_buff *)sq->skbuff[sq->head];
+ if (skb)
+ dev_kfree_skb_any(skb);
atomic64_add(1, (atomic64_t *)&netdev->stats.tx_packets);
atomic64_add(hdr->tot_len,
(atomic64_t *)&netdev->stats.tx_bytes);
- dev_kfree_skb_any(skb);
nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
}
}
memset(gather, 0, SND_QUEUE_DESC_SIZE);
gather->subdesc_type = SQ_DESC_TYPE_GATHER;
- gather->ld_type = NIC_SEND_LD_TYPE_E_LDWB;
+ gather->ld_type = NIC_SEND_LD_TYPE_E_LDD;
gather->size = size;
gather->addr = data;
}
}
nicvf_sq_add_hdr_subdesc(sq, hdr_qentry,
seg_subdescs - 1, skb, seg_len);
- sq->skbuff[hdr_qentry] = 0;
+ sq->skbuff[hdr_qentry] = (u64)NULL;
qentry = nicvf_get_nxt_sqentry(sq, qentry);
desc_cnt += seg_subdescs;
/* Inform HW to xmit all TSO segments */
nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR,
skb_get_queue_mapping(skb), desc_cnt);
+ nic->drv_stats.tx_tso++;
return 1;
}
#define SND_QUEUE_CNT 8
#define CMP_QUEUE_CNT 8 /* Max of RCV and SND qcount */
-#define SND_QSIZE SND_QUEUE_SIZE4
+#define SND_QSIZE SND_QUEUE_SIZE2
#define SND_QUEUE_LEN (1ULL << (SND_QSIZE + 10))
#define MAX_SND_QUEUE_LEN (1ULL << (SND_QUEUE_SIZE6 + 10))
#define SND_QUEUE_THRESH 2ULL
/* Since timestamp not enabled, otherwise 2 */
#define MAX_CQE_PER_PKT_XMIT 1
-#define CMP_QSIZE CMP_QUEUE_SIZE4
+/* Keep CQ and SQ sizes same, if timestamping
+ * is enabled this equation will change.
+ */
+#define CMP_QSIZE CMP_QUEUE_SIZE2
#define CMP_QUEUE_LEN (1ULL << (CMP_QSIZE + 10))
#define CMP_QUEUE_CQE_THRESH 0
#define CMP_QUEUE_TIMER_THRESH 220 /* 10usec */
#define MAX_CQES_FOR_TX ((SND_QUEUE_LEN / MIN_SQ_DESC_PER_PKT_XMIT) * \
MAX_CQE_PER_PKT_XMIT)
-#define RQ_CQ_DROP ((CMP_QUEUE_LEN - MAX_CQES_FOR_TX) / 256)
+/* Calculate number of CQEs to reserve for all SQEs.
+ * Its 1/256th level of CQ size.
+ * '+ 1' to account for pipelining
+ */
+#define RQ_CQ_DROP ((256 / (CMP_QUEUE_LEN / \
+ (CMP_QUEUE_LEN - MAX_CQES_FOR_TX))) + 1)
/* Descriptor size in bytes */
#define SND_QUEUE_DESC_SIZE 16
bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg);
bgx_flush_dmac_addrs(bgx, lmacid);
- if (lmac->phydev)
+ if ((bgx->lmac_type != BGX_MODE_XFI) &&
+ (bgx->lmac_type != BGX_MODE_XLAUI) &&
+ (bgx->lmac_type != BGX_MODE_40G_KR) &&
+ (bgx->lmac_type != BGX_MODE_10G_KR) && lmac->phydev)
phy_disconnect(lmac->phydev);
lmac->phydev = NULL;
};
void fec_ptp_init(struct platform_device *pdev);
+void fec_ptp_stop(struct platform_device *pdev);
void fec_ptp_start_cyclecounter(struct net_device *ndev);
int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr);
int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr);
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/string.h>
+#include <linux/pm_runtime.h>
#include <linux/ptrace.h>
#include <linux/errno.h>
#include <linux/ioport.h>
#define FEC_ENET_RAEM_V 0x8
#define FEC_ENET_RAFL_V 0x8
#define FEC_ENET_OPD_V 0xFFF0
+#define FEC_MDIO_PM_TIMEOUT 100 /* ms */
static struct platform_device_id fec_devtype[] = {
{
static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
{
struct fec_enet_private *fep = bus->priv;
+ struct device *dev = &fep->pdev->dev;
unsigned long time_left;
+ int ret = 0;
+
+ ret = pm_runtime_get_sync(dev);
+ if (IS_ERR_VALUE(ret))
+ return ret;
fep->mii_timeout = 0;
init_completion(&fep->mdio_done);
if (time_left == 0) {
fep->mii_timeout = 1;
netdev_err(fep->netdev, "MDIO read timeout\n");
- return -ETIMEDOUT;
+ ret = -ETIMEDOUT;
+ goto out;
}
- /* return value */
- return FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA));
+ ret = FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA));
+
+out:
+ pm_runtime_mark_last_busy(dev);
+ pm_runtime_put_autosuspend(dev);
+
+ return ret;
}
static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
u16 value)
{
struct fec_enet_private *fep = bus->priv;
+ struct device *dev = &fep->pdev->dev;
unsigned long time_left;
+ int ret = 0;
+
+ ret = pm_runtime_get_sync(dev);
+ if (IS_ERR_VALUE(ret))
+ return ret;
fep->mii_timeout = 0;
init_completion(&fep->mdio_done);
if (time_left == 0) {
fep->mii_timeout = 1;
netdev_err(fep->netdev, "MDIO write timeout\n");
- return -ETIMEDOUT;
+ ret = -ETIMEDOUT;
}
- return 0;
+ pm_runtime_mark_last_busy(dev);
+ pm_runtime_put_autosuspend(dev);
+
+ return ret;
}
static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
ret = clk_prepare_enable(fep->clk_ahb);
if (ret)
return ret;
- ret = clk_prepare_enable(fep->clk_ipg);
- if (ret)
- goto failed_clk_ipg;
if (fep->clk_enet_out) {
ret = clk_prepare_enable(fep->clk_enet_out);
if (ret)
}
} else {
clk_disable_unprepare(fep->clk_ahb);
- clk_disable_unprepare(fep->clk_ipg);
if (fep->clk_enet_out)
clk_disable_unprepare(fep->clk_enet_out);
if (fep->clk_ptp) {
if (fep->clk_enet_out)
clk_disable_unprepare(fep->clk_enet_out);
failed_clk_enet_out:
- clk_disable_unprepare(fep->clk_ipg);
-failed_clk_ipg:
clk_disable_unprepare(fep->clk_ahb);
return ret;
struct fec_enet_private *fep = netdev_priv(ndev);
int ret;
+ ret = pm_runtime_get_sync(&fep->pdev->dev);
+ if (IS_ERR_VALUE(ret))
+ return ret;
+
pinctrl_pm_select_default_state(&fep->pdev->dev);
ret = fec_enet_clk_enable(ndev, true);
if (ret)
- return ret;
+ goto clk_enable;
/* I should reset the ring buffers here, but I don't yet know
* a simple way to do that.
fec_enet_free_buffers(ndev);
err_enet_alloc:
fec_enet_clk_enable(ndev, false);
+clk_enable:
+ pm_runtime_mark_last_busy(&fep->pdev->dev);
+ pm_runtime_put_autosuspend(&fep->pdev->dev);
pinctrl_pm_select_sleep_state(&fep->pdev->dev);
return ret;
}
fec_enet_clk_enable(ndev, false);
pinctrl_pm_select_sleep_state(&fep->pdev->dev);
+ pm_runtime_mark_last_busy(&fep->pdev->dev);
+ pm_runtime_put_autosuspend(&fep->pdev->dev);
+
fec_enet_free_buffers(ndev);
return 0;
fep->bufdesc_size;
/* Allocate memory for buffer descriptors. */
- cbd_base = dma_alloc_coherent(NULL, bd_size, &bd_dma,
- GFP_KERNEL);
+ cbd_base = dmam_alloc_coherent(&fep->pdev->dev, bd_size, &bd_dma,
+ GFP_KERNEL);
if (!cbd_base) {
return -ENOMEM;
}
if (ret)
goto failed_clk;
+ ret = clk_prepare_enable(fep->clk_ipg);
+ if (ret)
+ goto failed_clk_ipg;
+
fep->reg_phy = devm_regulator_get(&pdev->dev, "phy");
if (!IS_ERR(fep->reg_phy)) {
ret = regulator_enable(fep->reg_phy);
fep->reg_phy = NULL;
}
+ pm_runtime_set_autosuspend_delay(&pdev->dev, FEC_MDIO_PM_TIMEOUT);
+ pm_runtime_use_autosuspend(&pdev->dev);
+ pm_runtime_set_active(&pdev->dev);
+ pm_runtime_enable(&pdev->dev);
+
fec_reset_phy(pdev);
if (fep->bufdesc_ex)
fep->rx_copybreak = COPYBREAK_DEFAULT;
INIT_WORK(&fep->tx_timeout_work, fec_enet_timeout_work);
+
+ pm_runtime_mark_last_busy(&pdev->dev);
+ pm_runtime_put_autosuspend(&pdev->dev);
+
return 0;
failed_register:
failed_mii_init:
failed_irq:
failed_init:
+ fec_ptp_stop(pdev);
if (fep->reg_phy)
regulator_disable(fep->reg_phy);
failed_regulator:
+ clk_disable_unprepare(fep->clk_ipg);
+failed_clk_ipg:
fec_enet_clk_enable(ndev, false);
failed_clk:
failed_phy:
struct net_device *ndev = platform_get_drvdata(pdev);
struct fec_enet_private *fep = netdev_priv(ndev);
- cancel_delayed_work_sync(&fep->time_keep);
cancel_work_sync(&fep->tx_timeout_work);
+ fec_ptp_stop(pdev);
unregister_netdev(ndev);
fec_enet_mii_remove(fep);
if (fep->reg_phy)
regulator_disable(fep->reg_phy);
- if (fep->ptp_clock)
- ptp_clock_unregister(fep->ptp_clock);
of_node_put(fep->phy_node);
free_netdev(ndev);
return ret;
}
-static SIMPLE_DEV_PM_OPS(fec_pm_ops, fec_suspend, fec_resume);
+static int __maybe_unused fec_runtime_suspend(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+ struct fec_enet_private *fep = netdev_priv(ndev);
+
+ clk_disable_unprepare(fep->clk_ipg);
+
+ return 0;
+}
+
+static int __maybe_unused fec_runtime_resume(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+ struct fec_enet_private *fep = netdev_priv(ndev);
+
+ return clk_prepare_enable(fep->clk_ipg);
+}
+
+static const struct dev_pm_ops fec_pm_ops = {
+ SET_SYSTEM_SLEEP_PM_OPS(fec_suspend, fec_resume)
+ SET_RUNTIME_PM_OPS(fec_runtime_suspend, fec_runtime_resume, NULL)
+};
static struct platform_driver fec_driver = {
.driver = {
schedule_delayed_work(&fep->time_keep, HZ);
}
+void fec_ptp_stop(struct platform_device *pdev)
+{
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct fec_enet_private *fep = netdev_priv(ndev);
+
+ cancel_delayed_work_sync(&fep->time_keep);
+ if (fep->ptp_clock)
+ ptp_clock_unregister(fep->ptp_clock);
+}
+
/**
* fec_ptp_check_pps_event
* @fep: the fec_enet_private structure handle
}
}
-static void lock_tx_qs(struct gfar_private *priv)
-{
- int i;
-
- for (i = 0; i < priv->num_tx_queues; i++)
- spin_lock(&priv->tx_queue[i]->txlock);
-}
-
-static void unlock_tx_qs(struct gfar_private *priv)
-{
- int i;
-
- for (i = 0; i < priv->num_tx_queues; i++)
- spin_unlock(&priv->tx_queue[i]->txlock);
-}
-
static int gfar_alloc_tx_queues(struct gfar_private *priv)
{
int i;
priv->dev = &ofdev->dev;
SET_NETDEV_DEV(dev, &ofdev->dev);
- spin_lock_init(&priv->bflock);
INIT_WORK(&priv->reset_task, gfar_reset_task);
platform_set_drvdata(ofdev, priv);
goto register_fail;
}
- device_init_wakeup(&dev->dev,
- priv->device_flags &
- FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
+ device_set_wakeup_capable(&dev->dev, priv->device_flags &
+ FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
/* fill out IRQ number and name fields */
for (i = 0; i < priv->num_grps; i++) {
struct gfar_private *priv = dev_get_drvdata(dev);
struct net_device *ndev = priv->ndev;
struct gfar __iomem *regs = priv->gfargrp[0].regs;
- unsigned long flags;
u32 tempval;
-
int magic_packet = priv->wol_en &&
(priv->device_flags &
FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
+ if (!netif_running(ndev))
+ return 0;
+
+ disable_napi(priv);
+ netif_tx_lock(ndev);
netif_device_detach(ndev);
+ netif_tx_unlock(ndev);
- if (netif_running(ndev)) {
+ gfar_halt(priv);
- local_irq_save(flags);
- lock_tx_qs(priv);
+ if (magic_packet) {
+ /* Enable interrupt on Magic Packet */
+ gfar_write(®s->imask, IMASK_MAG);
- gfar_halt_nodisable(priv);
+ /* Enable Magic Packet mode */
+ tempval = gfar_read(®s->maccfg2);
+ tempval |= MACCFG2_MPEN;
+ gfar_write(®s->maccfg2, tempval);
- /* Disable Tx, and Rx if wake-on-LAN is disabled. */
+ /* re-enable the Rx block */
tempval = gfar_read(®s->maccfg1);
-
- tempval &= ~MACCFG1_TX_EN;
-
- if (!magic_packet)
- tempval &= ~MACCFG1_RX_EN;
-
+ tempval |= MACCFG1_RX_EN;
gfar_write(®s->maccfg1, tempval);
- unlock_tx_qs(priv);
- local_irq_restore(flags);
-
- disable_napi(priv);
-
- if (magic_packet) {
- /* Enable interrupt on Magic Packet */
- gfar_write(®s->imask, IMASK_MAG);
-
- /* Enable Magic Packet mode */
- tempval = gfar_read(®s->maccfg2);
- tempval |= MACCFG2_MPEN;
- gfar_write(®s->maccfg2, tempval);
- } else {
- phy_stop(priv->phydev);
- }
+ } else {
+ phy_stop(priv->phydev);
}
return 0;
struct gfar_private *priv = dev_get_drvdata(dev);
struct net_device *ndev = priv->ndev;
struct gfar __iomem *regs = priv->gfargrp[0].regs;
- unsigned long flags;
u32 tempval;
int magic_packet = priv->wol_en &&
(priv->device_flags &
FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
- if (!netif_running(ndev)) {
- netif_device_attach(ndev);
+ if (!netif_running(ndev))
return 0;
- }
- if (!magic_packet && priv->phydev)
+ if (magic_packet) {
+ /* Disable Magic Packet mode */
+ tempval = gfar_read(®s->maccfg2);
+ tempval &= ~MACCFG2_MPEN;
+ gfar_write(®s->maccfg2, tempval);
+ } else {
phy_start(priv->phydev);
-
- /* Disable Magic Packet mode, in case something
- * else woke us up.
- */
- local_irq_save(flags);
- lock_tx_qs(priv);
-
- tempval = gfar_read(®s->maccfg2);
- tempval &= ~MACCFG2_MPEN;
- gfar_write(®s->maccfg2, tempval);
+ }
gfar_start(priv);
- unlock_tx_qs(priv);
- local_irq_restore(flags);
-
netif_device_attach(ndev);
-
enable_napi(priv);
return 0;
/* Install our interrupt handlers for Error,
* Transmit, and Receive
*/
- err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, 0,
+ err = request_irq(gfar_irq(grp, ER)->irq, gfar_error,
+ IRQF_NO_SUSPEND,
gfar_irq(grp, ER)->name, grp);
if (err < 0) {
netif_err(priv, intr, dev, "Can't get IRQ %d\n",
goto rx_irq_fail;
}
} else {
- err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, 0,
+ err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt,
+ IRQF_NO_SUSPEND,
gfar_irq(grp, TX)->name, grp);
if (err < 0) {
netif_err(priv, intr, dev, "Can't get IRQ %d\n",
if (err)
return err;
- device_set_wakeup_enable(&dev->dev, priv->wol_en);
-
return err;
}
int oldduplex;
int oldlink;
- /* Bitfield update lock */
- spinlock_t bflock;
-
uint32_t msg_enable;
struct work_struct reset_task;
static int gfar_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
{
struct gfar_private *priv = netdev_priv(dev);
- unsigned long flags;
if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) &&
wol->wolopts != 0)
device_set_wakeup_enable(&dev->dev, wol->wolopts & WAKE_MAGIC);
- spin_lock_irqsave(&priv->bflock, flags);
- priv->wol_en = !!device_may_wakeup(&dev->dev);
- spin_unlock_irqrestore(&priv->bflock, flags);
+ priv->wol_en = !!device_may_wakeup(&dev->dev);
return 0;
}
{
struct mlx4_cmd *cmd = &mlx4_priv(dev)->cmd;
struct mlx4_cmd_context *context;
+ long ret_wait;
int err = 0;
down(&cmd->event_sem);
if (err)
goto out_reset;
- if (!wait_for_completion_timeout(&context->done,
- msecs_to_jiffies(timeout))) {
+ if (op == MLX4_CMD_SENSE_PORT) {
+ ret_wait =
+ wait_for_completion_interruptible_timeout(&context->done,
+ msecs_to_jiffies(timeout));
+ if (ret_wait < 0) {
+ context->fw_status = 0;
+ context->out_param = 0;
+ context->result = 0;
+ }
+ } else {
+ ret_wait = (long)wait_for_completion_timeout(&context->done,
+ msecs_to_jiffies(timeout));
+ }
+ if (!ret_wait) {
mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n",
op);
if (op == MLX4_CMD_NOP) {
static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring)
{
- BUG_ON((u32)(ring->prod - ring->cons) > ring->actual_size);
return ring->prod == ring->cons;
}
continue;
mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN to slave: %d, port:%d\n",
__func__, i, port);
- s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+ s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
eqe->event.port_change.port =
cpu_to_be32(
continue;
if (i == mlx4_master_func_num(dev))
continue;
- s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+ s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
eqe->event.port_change.port =
cpu_to_be32(
} else if (err == -ENOENT) {
err = 0;
continue;
+ } else if (mlx4_is_slave(dev) && err == -EINVAL) {
+ priv->def_counter[port] = MLX4_SINK_COUNTER_INDEX(dev);
+ mlx4_warn(dev, "can't allocate counter from old PF driver, using index %d\n",
+ MLX4_SINK_COUNTER_INDEX(dev));
+ err = 0;
} else {
mlx4_err(dev, "%s: failed to allocate default counter port %d err %d\n",
__func__, port + 1, err);
if (fw->size & 0xF) {
addr = dest + size;
for (i = 0; i < (fw->size & 0xF); i++)
- data[i] = temp[size + i];
+ data[i] = ((u8 *)temp)[size + i];
for (; i < 16; i++)
data[i] = 0;
ret = qlcnic_ms_mem_write128(adapter, addr,
SIMPLE_DEV_PM_OPS(stmmac_pltfr_pm_ops, stmmac_pltfr_suspend,
stmmac_pltfr_resume);
EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops);
+
+MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet platform support");
+MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
+MODULE_LICENSE("GPL");
struct sk_buff *skb_new;
skb_new = skb_realloc_headroom(skb, len);
- if (!skb_new) {
- rp->tx_errors++;
+ if (!skb_new)
goto out_drop;
- }
kfree_skb(skb);
skb = skb_new;
} else
/* SGMII functions */
int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port);
+bool netcp_sgmii_rtreset(void __iomem *sgmii_ofs, int port, bool set);
int netcp_sgmii_get_port_link(void __iomem *sgmii_ofs, int port);
int netcp_sgmii_config(void __iomem *sgmii_ofs, int port, u32 interface);
static int netcp_remove(struct platform_device *pdev)
{
struct netcp_device *netcp_device = platform_get_drvdata(pdev);
+ struct netcp_intf *netcp_intf, *netcp_tmp;
struct netcp_inst_modpriv *inst_modpriv, *tmp;
struct netcp_module *module;
list_del(&inst_modpriv->inst_list);
kfree(inst_modpriv);
}
- WARN(!list_empty(&netcp_device->interface_head), "%s interface list not empty!\n",
- pdev->name);
- devm_kfree(&pdev->dev, netcp_device);
+ /* now that all modules are removed, clean up the interfaces */
+ list_for_each_entry_safe(netcp_intf, netcp_tmp,
+ &netcp_device->interface_head,
+ interface_list) {
+ netcp_delete_interface(netcp_device, netcp_intf->ndev);
+ }
+
+ WARN(!list_empty(&netcp_device->interface_head),
+ "%s interface list not empty!\n", pdev->name);
+
pm_runtime_put_sync(&pdev->dev);
pm_runtime_disable(&pdev->dev);
platform_set_drvdata(pdev, NULL);
writel(slave->mac_control, GBE_REG_ADDR(slave, emac_regs, mac_control));
}
+static void gbe_sgmii_rtreset(struct gbe_priv *priv,
+ struct gbe_slave *slave, bool set)
+{
+ void __iomem *sgmii_port_regs;
+
+ if (SLAVE_LINK_IS_XGMII(slave))
+ return;
+
+ if ((priv->ss_version == GBE_SS_VERSION_14) && (slave->slave_num >= 2))
+ sgmii_port_regs = priv->sgmii_port34_regs;
+ else
+ sgmii_port_regs = priv->sgmii_port_regs;
+
+ netcp_sgmii_rtreset(sgmii_port_regs, slave->slave_num, set);
+}
+
static void gbe_slave_stop(struct gbe_intf *intf)
{
struct gbe_priv *gbe_dev = intf->gbe_dev;
struct gbe_slave *slave = intf->slave;
+ gbe_sgmii_rtreset(gbe_dev, slave, true);
gbe_port_reset(slave);
/* Disable forwarding */
cpsw_ale_control_set(gbe_dev->ale, slave->port_num,
gbe_sgmii_config(priv, slave);
gbe_port_reset(slave);
+ gbe_sgmii_rtreset(priv, slave, false);
gbe_port_config(priv, slave, priv->rx_packet_max);
gbe_set_slave_mac(slave, gbe_intf);
/* enable forwarding */
{
struct gbe_slave *slave;
- for (;;) {
+ while (!list_empty(&gbe_dev->secondary_slaves)) {
slave = first_sec_slave(gbe_dev);
- if (!slave)
- break;
+
if (slave->phy)
phy_disconnect(slave->phy);
list_del(&slave->slave_list);
&gbe_dev->dma_chan_name);
if (ret < 0) {
dev_err(dev, "missing \"tx-channel\" parameter\n");
- ret = -ENODEV;
- goto quit;
+ return -EINVAL;
}
if (!strcmp(node->name, "gbe")) {
ret = get_gbe_resource_version(gbe_dev, node);
if (ret)
- goto quit;
+ return ret;
dev_dbg(dev, "ss_version: 0x%08x\n", gbe_dev->ss_version);
else
ret = -ENODEV;
- if (ret)
- goto quit;
} else if (!strcmp(node->name, "xgbe")) {
ret = set_xgbe_ethss10_priv(gbe_dev, node);
if (ret)
- goto quit;
+ return ret;
ret = netcp_xgbe_serdes_init(gbe_dev->xgbe_serdes_regs,
gbe_dev->ss_regs);
- if (ret)
- goto quit;
} else {
dev_err(dev, "unknown GBE node(%s)\n", node->name);
ret = -ENODEV;
- goto quit;
}
+ if (ret)
+ return ret;
+
interfaces = of_get_child_by_name(node, "interfaces");
if (!interfaces)
dev_err(dev, "could not find interfaces\n");
ret = netcp_txpipe_init(&gbe_dev->tx_pipe, netcp_device,
gbe_dev->dma_chan_name, gbe_dev->tx_queue_id);
if (ret)
- goto quit;
+ return ret;
ret = netcp_txpipe_open(&gbe_dev->tx_pipe);
if (ret)
- goto quit;
+ return ret;
/* Create network interfaces */
INIT_LIST_HEAD(&gbe_dev->gbe_intf_head);
if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves)
break;
}
+ of_node_put(interfaces);
if (!gbe_dev->num_slaves)
dev_warn(dev, "No network interface configured\n");
of_node_put(secondary_ports);
if (!gbe_dev->num_slaves) {
- dev_err(dev, "No network interface or secondary ports configured\n");
+ dev_err(dev,
+ "No network interface or secondary ports configured\n");
ret = -ENODEV;
- goto quit;
+ goto free_sec_ports;
}
memset(&ale_params, 0, sizeof(ale_params));
if (!gbe_dev->ale) {
dev_err(gbe_dev->dev, "error initializing ale engine\n");
ret = -ENODEV;
- goto quit;
+ goto free_sec_ports;
} else {
dev_dbg(gbe_dev->dev, "Created a gbe ale engine\n");
}
*inst_priv = gbe_dev;
return 0;
-quit:
- if (gbe_dev->hw_stats)
- devm_kfree(dev, gbe_dev->hw_stats);
- cpsw_ale_destroy(gbe_dev->ale);
- if (gbe_dev->ss_regs)
- devm_iounmap(dev, gbe_dev->ss_regs);
- of_node_put(interfaces);
- devm_kfree(dev, gbe_dev);
+free_sec_ports:
+ free_secondary_ports(gbe_dev);
return ret;
}
free_secondary_ports(gbe_dev);
if (!list_empty(&gbe_dev->gbe_intf_head))
- dev_alert(gbe_dev->dev, "unreleased ethss interfaces present\n");
+ dev_alert(gbe_dev->dev,
+ "unreleased ethss interfaces present\n");
- devm_kfree(gbe_dev->dev, gbe_dev->hw_stats);
- devm_iounmap(gbe_dev->dev, gbe_dev->ss_regs);
- memset(gbe_dev, 0x00, sizeof(*gbe_dev));
- devm_kfree(gbe_dev->dev, gbe_dev);
return 0;
}
#include "netcp.h"
+#define SGMII_SRESET_RESET BIT(0)
+#define SGMII_SRESET_RTRESET BIT(1)
+
#define SGMII_REG_STATUS_LOCK BIT(4)
#define SGMII_REG_STATUS_LINK BIT(0)
#define SGMII_REG_STATUS_AUTONEG BIT(2)
int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port)
{
/* Soft reset */
- sgmii_write_reg_bit(sgmii_ofs, SGMII_SRESET_REG(port), 0x1);
- while (sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)) != 0x0)
+ sgmii_write_reg_bit(sgmii_ofs, SGMII_SRESET_REG(port),
+ SGMII_SRESET_RESET);
+
+ while ((sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)) &
+ SGMII_SRESET_RESET) != 0x0)
;
+
return 0;
}
+/* port is 0 based */
+bool netcp_sgmii_rtreset(void __iomem *sgmii_ofs, int port, bool set)
+{
+ u32 reg;
+ bool oldval;
+
+ /* Initiate a soft reset */
+ reg = sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port));
+ oldval = (reg & SGMII_SRESET_RTRESET) != 0x0;
+ if (set)
+ reg |= SGMII_SRESET_RTRESET;
+ else
+ reg &= ~SGMII_SRESET_RTRESET;
+ sgmii_write_reg(sgmii_ofs, SGMII_SRESET_REG(port), reg);
+ wmb();
+
+ return oldval;
+}
+
int netcp_sgmii_get_port_link(void __iomem *sgmii_ofs, int port)
{
u32 status = 0, link = 0;
struct virtio_net_hdr vnet_hdr = { 0 };
int vnet_hdr_len = 0;
int copylen = 0;
+ int depth;
bool zerocopy = false;
size_t linear;
ssize_t n;
skb_probe_transport_header(skb, ETH_HLEN);
+ /* Move network header to the right position for VLAN tagged packets */
+ if ((skb->protocol == htons(ETH_P_8021Q) ||
+ skb->protocol == htons(ETH_P_8021AD)) &&
+ __vlan_get_protocol(skb, skb->protocol, &depth) != 0)
+ skb_set_network_header(skb, depth);
+
rcu_read_lock();
vlan = rcu_dereference(q->vlan);
/* copy skb_ubuf_info for callback when skb has no error */
#include <linux/usb/cdc.h>
/* Version Information */
-#define DRIVER_VERSION "v1.08.0 (2015/01/13)"
+#define DRIVER_VERSION "v1.08.1 (2015/07/28)"
#define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
#define DRIVER_DESC "Realtek RTL8152/RTL8153 Based USB Ethernet Adapters"
#define MODULENAME "r8152"
static void rtl8152_tx_timeout(struct net_device *netdev)
{
struct r8152 *tp = netdev_priv(netdev);
- int i;
netif_warn(tp, tx_err, netdev, "Tx timeout\n");
- for (i = 0; i < RTL8152_MAX_TX; i++)
- usb_unlink_urb(tp->tx_info[i].urb);
+
+ usb_queue_reset_device(tp->intf);
}
static void rtl8152_set_rx_mode(struct net_device *netdev)
{
int i, ret = 0;
- napi_disable(&tp->napi);
INIT_LIST_HEAD(&tp->rx_done);
for (i = 0; i < RTL8152_MAX_RX; i++) {
INIT_LIST_HEAD(&tp->rx_info[i].list);
if (ret)
break;
}
- napi_enable(&tp->napi);
if (ret && ++i < RTL8152_MAX_RX) {
struct list_head rx_queue;
if (test_bit(RTL8152_UNPLUG, &tp->flags))
return -ENODEV;
+ usb_disable_lpm(tp->udev);
set_tx_qlen(tp);
rtl_set_eee_plus(tp);
r8153_set_rx_early_timeout(tp);
device_set_wakeup_enable(&tp->udev->dev, false);
}
+static void r8153_u1u2en(struct r8152 *tp, bool enable)
+{
+ u8 u1u2[8];
+
+ if (enable)
+ memset(u1u2, 0xff, sizeof(u1u2));
+ else
+ memset(u1u2, 0x00, sizeof(u1u2));
+
+ usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2);
+}
+
+static void r8153_u2p3en(struct r8152 *tp, bool enable)
+{
+ u32 ocp_data;
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL);
+ if (enable && tp->version != RTL_VER_03 && tp->version != RTL_VER_04)
+ ocp_data |= U2P3_ENABLE;
+ else
+ ocp_data &= ~U2P3_ENABLE;
+ ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data);
+}
+
+static void r8153_power_cut_en(struct r8152 *tp, bool enable)
+{
+ u32 ocp_data;
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_POWER_CUT);
+ if (enable)
+ ocp_data |= PWR_EN | PHASE2_EN;
+ else
+ ocp_data &= ~(PWR_EN | PHASE2_EN);
+ ocp_write_word(tp, MCU_TYPE_USB, USB_POWER_CUT, ocp_data);
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0);
+ ocp_data &= ~PCUT_STATUS;
+ ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data);
+}
+
+static bool rtl_can_wakeup(struct r8152 *tp)
+{
+ struct usb_device *udev = tp->udev;
+
+ return (udev->actconfig->desc.bmAttributes & USB_CONFIG_ATT_WAKEUP);
+}
+
static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable)
{
if (enable) {
u32 ocp_data;
+ r8153_u1u2en(tp, false);
+ r8153_u2p3en(tp, false);
+
__rtl_set_wol(tp, WAKE_ANY);
ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG);
ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
} else {
__rtl_set_wol(tp, tp->saved_wolopts);
+ r8153_u2p3en(tp, true);
+ r8153_u1u2en(tp, true);
}
}
set_bit(PHY_RESET, &tp->flags);
}
-static void r8153_u1u2en(struct r8152 *tp, bool enable)
-{
- u8 u1u2[8];
-
- if (enable)
- memset(u1u2, 0xff, sizeof(u1u2));
- else
- memset(u1u2, 0x00, sizeof(u1u2));
-
- usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2);
-}
-
-static void r8153_u2p3en(struct r8152 *tp, bool enable)
-{
- u32 ocp_data;
-
- ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL);
- if (enable)
- ocp_data |= U2P3_ENABLE;
- else
- ocp_data &= ~U2P3_ENABLE;
- ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data);
-}
-
-static void r8153_power_cut_en(struct r8152 *tp, bool enable)
-{
- u32 ocp_data;
-
- ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_POWER_CUT);
- if (enable)
- ocp_data |= PWR_EN | PHASE2_EN;
- else
- ocp_data &= ~(PWR_EN | PHASE2_EN);
- ocp_write_word(tp, MCU_TYPE_USB, USB_POWER_CUT, ocp_data);
-
- ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0);
- ocp_data &= ~PCUT_STATUS;
- ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data);
-}
-
static void r8153_first_init(struct r8152 *tp)
{
u32 ocp_data;
r8153_disable_aldps(tp);
rtl_disable(tp);
r8153_enable_aldps(tp);
+ usb_enable_lpm(tp->udev);
}
static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u16 speed, u8 duplex)
if (test_bit(RTL8152_UNPLUG, &tp->flags))
return;
+ r8153_u1u2en(tp, false);
r8153_disable_aldps(tp);
r8153_first_init(tp);
r8153_enable_aldps(tp);
+ r8153_u2p3en(tp, true);
+ r8153_u1u2en(tp, true);
+ usb_enable_lpm(tp->udev);
}
static void rtl8153_down(struct r8152 *tp)
}
r8153_u1u2en(tp, false);
+ r8153_u2p3en(tp, false);
r8153_power_cut_en(tp, false);
r8153_disable_aldps(tp);
r8153_enter_oob(tp);
if (!netif_carrier_ok(netdev)) {
tp->rtl_ops.enable(tp);
set_bit(RTL8152_SET_RX_MODE, &tp->flags);
+ napi_disable(&tp->napi);
netif_carrier_on(netdev);
rtl_start_rx(tp);
+ napi_enable(&tp->napi);
}
} else {
if (netif_carrier_ok(netdev)) {
msleep(20);
}
+ usb_disable_lpm(tp->udev);
r8153_u2p3en(tp, false);
if (tp->version == RTL_VER_04) {
r8153_enable_aldps(tp);
r8152b_enable_fc(tp);
rtl_tally_reset(tp);
+ r8153_u2p3en(tp, true);
+}
+
+static int rtl8152_pre_reset(struct usb_interface *intf)
+{
+ struct r8152 *tp = usb_get_intfdata(intf);
+ struct net_device *netdev;
+
+ if (!tp)
+ return 0;
+
+ netdev = tp->netdev;
+ if (!netif_running(netdev))
+ return 0;
+
+ napi_disable(&tp->napi);
+ clear_bit(WORK_ENABLE, &tp->flags);
+ usb_kill_urb(tp->intr_urb);
+ cancel_delayed_work_sync(&tp->schedule);
+ if (netif_carrier_ok(netdev)) {
+ netif_stop_queue(netdev);
+ mutex_lock(&tp->control);
+ tp->rtl_ops.disable(tp);
+ mutex_unlock(&tp->control);
+ }
+
+ return 0;
+}
+
+static int rtl8152_post_reset(struct usb_interface *intf)
+{
+ struct r8152 *tp = usb_get_intfdata(intf);
+ struct net_device *netdev;
+
+ if (!tp)
+ return 0;
+
+ netdev = tp->netdev;
+ if (!netif_running(netdev))
+ return 0;
+
+ set_bit(WORK_ENABLE, &tp->flags);
+ if (netif_carrier_ok(netdev)) {
+ mutex_lock(&tp->control);
+ tp->rtl_ops.enable(tp);
+ rtl8152_set_rx_mode(netdev);
+ mutex_unlock(&tp->control);
+ netif_wake_queue(netdev);
+ }
+
+ napi_enable(&tp->napi);
+
+ return 0;
}
static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
rtl_runtime_suspend_enable(tp, false);
clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+ napi_disable(&tp->napi);
set_bit(WORK_ENABLE, &tp->flags);
if (netif_carrier_ok(tp->netdev))
rtl_start_rx(tp);
+ napi_enable(&tp->napi);
} else {
tp->rtl_ops.up(tp);
rtl8152_set_speed(tp, AUTONEG_ENABLE,
if (usb_autopm_get_interface(tp->intf) < 0)
return;
- mutex_lock(&tp->control);
-
- wol->supported = WAKE_ANY;
- wol->wolopts = __rtl_get_wol(tp);
-
- mutex_unlock(&tp->control);
+ if (!rtl_can_wakeup(tp)) {
+ wol->supported = 0;
+ wol->wolopts = 0;
+ } else {
+ mutex_lock(&tp->control);
+ wol->supported = WAKE_ANY;
+ wol->wolopts = __rtl_get_wol(tp);
+ mutex_unlock(&tp->control);
+ }
usb_autopm_put_interface(tp->intf);
}
struct r8152 *tp = netdev_priv(dev);
int ret;
+ if (!rtl_can_wakeup(tp))
+ return -EOPNOTSUPP;
+
ret = usb_autopm_get_interface(tp->intf);
if (ret < 0)
goto out_set_wol;
goto out1;
}
+ if (!rtl_can_wakeup(tp))
+ __rtl_set_wol(tp, 0);
+
tp->saved_wolopts = __rtl_get_wol(tp);
if (tp->saved_wolopts)
device_set_wakeup_enable(&udev->dev, true);
.suspend = rtl8152_suspend,
.resume = rtl8152_resume,
.reset_resume = rtl8152_resume,
+ .pre_reset = rtl8152_pre_reset,
+ .post_reset = rtl8152_post_reset,
.supports_autosuspend = 1,
.disable_hub_initiated_lpm = 1,
};
#ifndef __MACB_PDATA_H__
#define __MACB_PDATA_H__
+/**
+ * struct macb_platform_data - platform data for MACB Ethernet
+ * @phy_mask: phy mask passed when register the MDIO bus
+ * within the driver
+ * @phy_irq_pin: PHY IRQ
+ * @is_rmii: using RMII interface?
+ * @rev_eth_addr: reverse Ethernet address byte order
+ */
struct macb_platform_data {
u32 phy_mask;
- int phy_irq_pin; /* PHY IRQ */
- u8 is_rmii; /* using RMII interface? */
- u8 rev_eth_addr; /* reverse Ethernet address byte order */
+ int phy_irq_pin;
+ u8 is_rmii;
+ u8 rev_eth_addr;
};
#endif /* __MACB_PDATA_H__ */
int tcf_hash_search(struct tc_action *a, u32 index);
void tcf_hash_destroy(struct tc_action *a);
-int tcf_hash_release(struct tc_action *a, int bind);
u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo);
int tcf_hash_check(u32 index, struct tc_action *a, int bind);
int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est);
void tcf_hash_insert(struct tc_action *a);
+int __tcf_hash_release(struct tc_action *a, bool bind, bool strict);
+
+static inline int tcf_hash_release(struct tc_action *a, bool bind)
+{
+ return __tcf_hash_release(a, bind, false);
+}
+
int tcf_register_action(struct tc_action_ops *a, unsigned int mask);
int tcf_unregister_action(struct tc_action_ops *a);
int tcf_action_destroy(struct list_head *actions, int bind);
* @INET_FRAG_FIRST_IN: first fragment has arrived
* @INET_FRAG_LAST_IN: final fragment has arrived
* @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction
- * @INET_FRAG_EVICTED: frag queue is being evicted
*/
enum {
INET_FRAG_FIRST_IN = BIT(0),
INET_FRAG_LAST_IN = BIT(1),
INET_FRAG_COMPLETE = BIT(2),
- INET_FRAG_EVICTED = BIT(3)
};
/**
* @flags: fragment queue flags
* @max_size: maximum received fragment size
* @net: namespace that this frag belongs to
+ * @list_evictor: list of queues to forcefully evict (e.g. due to low memory)
*/
struct inet_frag_queue {
spinlock_t lock;
__u8 flags;
u16 max_size;
struct netns_frags *net;
+ struct hlist_node list_evictor;
};
#define INETFRAGS_HASHSZ 1024
inet_frag_destroy(q, f);
}
+static inline bool inet_frag_evicting(struct inet_frag_queue *q)
+{
+ return !hlist_unhashed(&q->list_evictor);
+}
+
/* Memory Tracking Functions. */
/* The default percpu_counter batch size is not big enough to scale to
return percpu_counter_read(&nf->mem);
}
-static inline void sub_frag_mem_limit(struct inet_frag_queue *q, int i)
+static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
{
- __percpu_counter_add(&q->net->mem, -i, frag_percpu_counter_batch);
+ __percpu_counter_add(&nf->mem, -i, frag_percpu_counter_batch);
}
-static inline void add_frag_mem_limit(struct inet_frag_queue *q, int i)
+static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
{
- __percpu_counter_add(&q->net->mem, i, frag_percpu_counter_batch);
+ __percpu_counter_add(&nf->mem, i, frag_percpu_counter_batch);
}
static inline void init_frag_mem_limit(struct netns_frags *nf)
struct fib_table {
struct hlist_node tb_hlist;
u32 tb_id;
- int tb_default;
int tb_num_default;
struct rcu_head rcu;
unsigned long *tb_data;
int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
u8 tos, int oif, struct net_device *dev,
struct in_device *idev, u32 *itag);
-void fib_select_default(struct fib_result *res);
+void fib_select_default(const struct flowi4 *flp, struct fib_result *res);
#ifdef CONFIG_IP_ROUTE_CLASSID
static inline int fib_num_tclassid_users(struct net *net)
{
extern unsigned int nf_conntrack_hash_rnd;
void init_nf_conntrack_hash_rnd(void);
-void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl);
+struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags);
#define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count)
#define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)
spinlock_t lock;
struct hlist_nulls_head unconfirmed;
struct hlist_nulls_head dying;
- struct hlist_nulls_head tmpl;
};
struct netns_ct {
void sk_set_memalloc(struct sock *sk);
void sk_clear_memalloc(struct sock *sk);
-int sk_wait_data(struct sock *sk, long *timeo);
+int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb);
struct request_sock_ops;
struct timewait_sock_ops;
return 1;
chan = conn->smp;
+ if (!chan) {
+ BT_ERR("SMP security requested but not available");
+ return 1;
+ }
if (!hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED))
return 1;
int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb)
{
- if (!is_skb_forwardable(skb->dev, skb)) {
- kfree_skb(skb);
- } else {
- skb_push(skb, ETH_HLEN);
- br_drop_fake_rtable(skb);
- skb_sender_cpu_clear(skb);
- dev_queue_xmit(skb);
+ if (!is_skb_forwardable(skb->dev, skb))
+ goto drop;
+
+ skb_push(skb, ETH_HLEN);
+ br_drop_fake_rtable(skb);
+ skb_sender_cpu_clear(skb);
+
+ if (skb->ip_summed == CHECKSUM_PARTIAL &&
+ (skb->protocol == htons(ETH_P_8021Q) ||
+ skb->protocol == htons(ETH_P_8021AD))) {
+ int depth;
+
+ if (!__vlan_get_protocol(skb, skb->protocol, &depth))
+ goto drop;
+
+ skb_set_network_header(skb, depth);
}
+ dev_queue_xmit(skb);
+
+ return 0;
+
+drop:
+ kfree_skb(skb);
return 0;
}
EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit);
if (p->port->state == BR_STATE_DISABLED)
goto unlock;
+ entry->state = p->state;
rcu_assign_pointer(*pp, p->next);
hlist_del_init(&p->mglist);
del_timer(&p->timer);
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) ||
- (port && port->state == BR_STATE_DISABLED) ||
- timer_pending(&other_query->timer))
+ (port && port->state == BR_STATE_DISABLED))
goto out;
mdb = mlock_dereference(br->mdb, br);
if (!mp)
goto out;
+ if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) {
+ struct net_bridge_port_group __rcu **pp;
+
+ for (pp = &mp->ports;
+ (p = mlock_dereference(*pp, br)) != NULL;
+ pp = &p->next) {
+ if (p->port != port)
+ continue;
+
+ rcu_assign_pointer(*pp, p->next);
+ hlist_del_init(&p->mglist);
+ del_timer(&p->timer);
+ call_rcu_bh(&p->rcu, br_multicast_free_pg);
+ br_mdb_notify(br->dev, port, group, RTM_DELMDB);
+
+ if (!mp->ports && !mp->mglist &&
+ netif_running(br->dev))
+ mod_timer(&mp->timer, jiffies);
+ }
+ goto out;
+ }
+
+ if (timer_pending(&other_query->timer))
+ goto out;
+
if (br->multicast_querier) {
__br_multicast_send_query(br, port, &mp->addr);
}
}
- if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) {
- struct net_bridge_port_group __rcu **pp;
-
- for (pp = &mp->ports;
- (p = mlock_dereference(*pp, br)) != NULL;
- pp = &p->next) {
- if (p->port != port)
- continue;
-
- rcu_assign_pointer(*pp, p->next);
- hlist_del_init(&p->mglist);
- del_timer(&p->timer);
- call_rcu_bh(&p->rcu, br_multicast_free_pg);
- br_mdb_notify(br->dev, port, group, RTM_DELMDB);
-
- if (!mp->ports && !mp->mglist &&
- netif_running(br->dev))
- mod_timer(&mp->timer, jiffies);
- }
- goto out;
- }
-
now = jiffies;
time = now + br->multicast_last_member_count *
br->multicast_last_member_interval;
struct nlattr *tb[],
struct nlattr *data[])
{
+ struct net_bridge *br = netdev_priv(brdev);
+ int ret;
+
if (!data)
return 0;
- return br_setport(br_port_get_rtnl(dev), data);
+
+ spin_lock_bh(&br->lock);
+ ret = br_setport(br_port_get_rtnl(dev), data);
+ spin_unlock_bh(&br->lock);
+
+ return ret;
}
static int br_port_fill_slave_info(struct sk_buff *skb,
br_send_config_bpdu(p, &bpdu);
p->topology_change_ack = 0;
p->config_pending = 0;
- mod_timer(&p->hold_timer,
- round_jiffies(jiffies + BR_HOLD_TIME));
+ if (p->br->stp_enabled == BR_KERNEL_STP)
+ mod_timer(&p->hold_timer,
+ round_jiffies(jiffies + BR_HOLD_TIME));
}
}
struct net_bridge_port *p;
spin_lock_bh(&br->lock);
- mod_timer(&br->hello_timer, jiffies + br->hello_time);
+ if (br->stp_enabled == BR_KERNEL_STP)
+ mod_timer(&br->hello_timer, jiffies + br->hello_time);
mod_timer(&br->gc_timer, jiffies + HZ/10);
br_config_bpdu_generation(br);
int r;
char *argv[] = { BR_STP_PROG, br->dev->name, "start", NULL };
char *envp[] = { NULL };
+ struct net_bridge_port *p;
r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
if (r == 0) {
br->stp_enabled = BR_USER_STP;
br_debug(br, "userspace STP started\n");
+ /* Stop hello and hold timers */
+ del_timer(&br->hello_timer);
+ list_for_each_entry(p, &br->port_list, list)
+ del_timer(&p->hold_timer);
} else {
br->stp_enabled = BR_KERNEL_STP;
br_debug(br, "using kernel STP\n");
int r;
char *argv[] = { BR_STP_PROG, br->dev->name, "stop", NULL };
char *envp[] = { NULL };
+ struct net_bridge_port *p;
if (br->stp_enabled == BR_USER_STP) {
r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
br_info(br, "userspace STP stopped, return code %d\n", r);
/* To start timers on any ports left in blocking */
+ mod_timer(&br->hello_timer, jiffies + br->hello_time);
+ list_for_each_entry(p, &br->port_list, list)
+ mod_timer(&p->hold_timer,
+ round_jiffies(jiffies + BR_HOLD_TIME));
spin_lock_bh(&br->lock);
br_port_state_selection(br);
spin_unlock_bh(&br->lock);
if (br->dev->flags & IFF_UP) {
br_config_bpdu_generation(br);
- mod_timer(&br->hello_timer, round_jiffies(jiffies + br->hello_time));
+ if (br->stp_enabled != BR_USER_STP)
+ mod_timer(&br->hello_timer,
+ round_jiffies(jiffies + br->hello_time));
}
spin_unlock(&br->lock);
}
struct cgroup_cls_state *task_cls_state(struct task_struct *p)
{
- return css_cls_state(task_css(p, net_cls_cgrp_id));
+ return css_cls_state(task_css_check(p, net_cls_cgrp_id,
+ rcu_read_lock_bh_held()));
}
EXPORT_SYMBOL_GPL(task_cls_state);
sock_copy(newsk, sk);
/* SANITY */
- get_net(sock_net(newsk));
+ if (likely(newsk->sk_net_refcnt))
+ get_net(sock_net(newsk));
sk_node_init(&newsk->sk_node);
sock_lock_init(newsk);
bh_lock_sock(newsk);
* sk_wait_data - wait for data to arrive at sk_receive_queue
* @sk: sock to wait on
* @timeo: for how long
+ * @skb: last skb seen on sk_receive_queue
*
* Now socket state including sk->sk_err is changed only under lock,
* hence we may omit checks after joining wait queue.
* We check receive queue before schedule() only as optimization;
* it is very likely that release_sock() added new data.
*/
-int sk_wait_data(struct sock *sk, long *timeo)
+int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
{
int rc;
DEFINE_WAIT(wait);
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
- rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue));
+ rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb);
clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
finish_wait(sk_sleep(sk), &wait);
return rc;
break;
}
- sk_wait_data(sk, &timeo);
+ sk_wait_data(sk, &timeo, NULL);
continue;
found_ok_skb:
if (len > skb->len)
} else {
fq->q.meat += skb->len;
}
- add_frag_mem_limit(&fq->q, skb->truesize);
+ add_frag_mem_limit(fq->q.net, skb->truesize);
if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
fq->q.meat == fq->q.len) {
clone->data_len = clone->len;
head->data_len -= clone->len;
head->len -= clone->len;
- add_frag_mem_limit(&fq->q, clone->truesize);
+ add_frag_mem_limit(fq->q.net, clone->truesize);
}
WARN_ON(head == NULL);
}
fp = next;
}
- sub_frag_mem_limit(&fq->q, sum_truesize);
+ sub_frag_mem_limit(fq->q.net, sum_truesize);
head->next = NULL;
head->dev = dev;
neigh = neigh_lookup(&arp_tbl, &ip, dev);
if (neigh) {
- read_lock_bh(&neigh->lock);
- memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
- r->arp_flags = arp_state_to_flags(neigh);
- read_unlock_bh(&neigh->lock);
- r->arp_ha.sa_family = dev->type;
- strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev));
+ if (!(neigh->nud_state & NUD_NOARP)) {
+ read_lock_bh(&neigh->lock);
+ memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
+ r->arp_flags = arp_state_to_flags(neigh);
+ read_unlock_bh(&neigh->lock);
+ r->arp_ha.sa_family = dev->type;
+ strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev));
+ err = 0;
+ }
neigh_release(neigh);
- err = 0;
}
return err;
}
queue_delayed_work(system_power_efficient_wq,
&check_lifetime_work, 0);
rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid);
- blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
}
return 0;
}
u8 fa_state;
u8 fa_slen;
u32 tb_id;
+ s16 fa_default;
struct rcu_head rcu;
};
}
/* Must be invoked inside of an RCU protected region. */
-void fib_select_default(struct fib_result *res)
+void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
{
struct fib_info *fi = NULL, *last_resort = NULL;
struct hlist_head *fa_head = res->fa_head;
struct fib_table *tb = res->table;
+ u8 slen = 32 - res->prefixlen;
int order = -1, last_idx = -1;
- struct fib_alias *fa;
+ struct fib_alias *fa, *fa1 = NULL;
+ u32 last_prio = res->fi->fib_priority;
+ u8 last_tos = 0;
hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
struct fib_info *next_fi = fa->fa_info;
+ if (fa->fa_slen != slen)
+ continue;
+ if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
+ continue;
+ if (fa->tb_id != tb->tb_id)
+ continue;
+ if (next_fi->fib_priority > last_prio &&
+ fa->fa_tos == last_tos) {
+ if (last_tos)
+ continue;
+ break;
+ }
+ if (next_fi->fib_flags & RTNH_F_DEAD)
+ continue;
+ last_tos = fa->fa_tos;
+ last_prio = next_fi->fib_priority;
+
if (next_fi->fib_scope != res->scope ||
fa->fa_type != RTN_UNICAST)
continue;
-
- if (next_fi->fib_priority > res->fi->fib_priority)
- break;
if (!next_fi->fib_nh[0].nh_gw ||
next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
continue;
if (!fi) {
if (next_fi != res->fi)
break;
+ fa1 = fa;
} else if (!fib_detect_death(fi, order, &last_resort,
- &last_idx, tb->tb_default)) {
+ &last_idx, fa1->fa_default)) {
fib_result_assign(res, fi);
- tb->tb_default = order;
+ fa1->fa_default = order;
goto out;
}
fi = next_fi;
}
if (order <= 0 || !fi) {
- tb->tb_default = -1;
+ if (fa1)
+ fa1->fa_default = -1;
goto out;
}
if (!fib_detect_death(fi, order, &last_resort, &last_idx,
- tb->tb_default)) {
+ fa1->fa_default)) {
fib_result_assign(res, fi);
- tb->tb_default = order;
+ fa1->fa_default = order;
goto out;
}
if (last_idx >= 0)
fib_result_assign(res, last_resort);
- tb->tb_default = last_idx;
+ fa1->fa_default = last_idx;
out:
return;
}
new_fa->fa_state = state & ~FA_S_ACCESSED;
new_fa->fa_slen = fa->fa_slen;
new_fa->tb_id = tb->tb_id;
+ new_fa->fa_default = -1;
err = switchdev_fib_ipv4_add(key, plen, fi,
new_fa->fa_tos,
new_fa->fa_state = 0;
new_fa->fa_slen = slen;
new_fa->tb_id = tb->tb_id;
+ new_fa->fa_default = -1;
/* (Optionally) offload fib entry to switch hardware. */
err = switchdev_fib_ipv4_add(key, plen, fi, tos, cfg->fc_type,
if (hlist_empty(&n->leaf)) {
put_child_root(pn, n->key, NULL);
node_free(n);
- } else {
- leaf_pull_suffix(pn, n);
}
}
}
if (hlist_empty(&n->leaf)) {
put_child_root(pn, n->key, NULL);
node_free(n);
- } else {
- leaf_pull_suffix(pn, n);
}
}
return NULL;
tb->tb_id = id;
- tb->tb_default = -1;
tb->tb_num_default = 0;
tb->tb_data = (alias ? alias->__data : tb->__data);
unsigned int evicted = 0;
HLIST_HEAD(expired);
-evict_again:
spin_lock(&hb->chain_lock);
hlist_for_each_entry_safe(fq, n, &hb->chain, list) {
if (!inet_fragq_should_evict(fq))
continue;
- if (!del_timer(&fq->timer)) {
- /* q expiring right now thus increment its refcount so
- * it won't be freed under us and wait until the timer
- * has finished executing then destroy it
- */
- atomic_inc(&fq->refcnt);
- spin_unlock(&hb->chain_lock);
- del_timer_sync(&fq->timer);
- inet_frag_put(fq, f);
- goto evict_again;
- }
+ if (!del_timer(&fq->timer))
+ continue;
- fq->flags |= INET_FRAG_EVICTED;
- hlist_del(&fq->list);
- hlist_add_head(&fq->list, &expired);
+ hlist_add_head(&fq->list_evictor, &expired);
++evicted;
}
spin_unlock(&hb->chain_lock);
- hlist_for_each_entry_safe(fq, n, &expired, list)
+ hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
f->frag_expire((unsigned long) fq);
return evicted;
int i;
nf->low_thresh = 0;
- local_bh_disable();
evict_again:
+ local_bh_disable();
seq = read_seqbegin(&f->rnd_seqlock);
for (i = 0; i < INETFRAGS_HASHSZ ; i++)
inet_evict_bucket(f, &f->hash[i]);
- if (read_seqretry(&f->rnd_seqlock, seq))
- goto evict_again;
-
local_bh_enable();
+ cond_resched();
+
+ if (read_seqretry(&f->rnd_seqlock, seq) ||
+ percpu_counter_sum(&nf->mem))
+ goto evict_again;
percpu_counter_destroy(&nf->mem);
}
struct inet_frag_bucket *hb;
hb = get_frag_bucket_locked(fq, f);
- if (!(fq->flags & INET_FRAG_EVICTED))
- hlist_del(&fq->list);
+ hlist_del(&fq->list);
+ fq->flags |= INET_FRAG_COMPLETE;
spin_unlock(&hb->chain_lock);
}
if (!(fq->flags & INET_FRAG_COMPLETE)) {
fq_unlink(fq, f);
atomic_dec(&fq->refcnt);
- fq->flags |= INET_FRAG_COMPLETE;
}
}
EXPORT_SYMBOL(inet_frag_kill);
fp = xp;
}
sum = sum_truesize + f->qsize;
- sub_frag_mem_limit(q, sum);
if (f->destructor)
f->destructor(q);
kmem_cache_free(f->frags_cachep, q);
+
+ sub_frag_mem_limit(nf, sum);
}
EXPORT_SYMBOL(inet_frag_destroy);
q->net = nf;
f->constructor(q, arg);
- add_frag_mem_limit(q, f->qsize);
+ add_frag_mem_limit(nf, f->qsize);
setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
spin_lock_init(&q->lock);
ipq_kill(qp);
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
- if (!(qp->q.flags & INET_FRAG_EVICTED)) {
+ if (!inet_frag_evicting(&qp->q)) {
struct sk_buff *head = qp->q.fragments;
const struct iphdr *iph;
int err;
kfree_skb(fp);
fp = xp;
} while (fp);
- sub_frag_mem_limit(&qp->q, sum_truesize);
+ sub_frag_mem_limit(qp->q.net, sum_truesize);
qp->q.flags = 0;
qp->q.len = 0;
qp->q.fragments = next;
qp->q.meat -= free_it->len;
- sub_frag_mem_limit(&qp->q, free_it->truesize);
+ sub_frag_mem_limit(qp->q.net, free_it->truesize);
kfree_skb(free_it);
}
}
qp->q.stamp = skb->tstamp;
qp->q.meat += skb->len;
qp->ecn |= ecn;
- add_frag_mem_limit(&qp->q, skb->truesize);
+ add_frag_mem_limit(qp->q.net, skb->truesize);
if (offset == 0)
qp->q.flags |= INET_FRAG_FIRST_IN;
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
- add_frag_mem_limit(&qp->q, clone->truesize);
+ add_frag_mem_limit(qp->q.net, clone->truesize);
}
skb_push(head, head->data - skb_network_header(head));
}
fp = next;
}
- sub_frag_mem_limit(&qp->q, sum_truesize);
+ sub_frag_mem_limit(qp->q.net, sum_truesize);
head->next = NULL;
head->dev = dev;
if (!res.prefixlen &&
res.table->tb_num_default > 1 &&
res.type == RTN_UNICAST && !fl4->flowi4_oif)
- fib_select_default(&res);
+ fib_select_default(fl4, &res);
if (!fl4->saddr)
fl4->saddr = FIB_RES_PREFSRC(net, res);
ret = -EAGAIN;
break;
}
- sk_wait_data(sk, &timeo);
+ sk_wait_data(sk, &timeo, NULL);
if (signal_pending(current)) {
ret = sock_intr_errno(timeo);
break;
int target; /* Read at least this many bytes */
long timeo;
struct task_struct *user_recv = NULL;
- struct sk_buff *skb;
+ struct sk_buff *skb, *last;
u32 urg_hole = 0;
if (unlikely(flags & MSG_ERRQUEUE))
/* Next get a buffer. */
+ last = skb_peek_tail(&sk->sk_receive_queue);
skb_queue_walk(&sk->sk_receive_queue, skb) {
+ last = skb;
/* Now that we have two receive queues this
* shouldn't happen.
*/
/* Do not sleep, just process backlog. */
release_sock(sk);
lock_sock(sk);
- } else
- sk_wait_data(sk, &timeo);
+ } else {
+ sk_wait_data(sk, &timeo, last);
+ }
if (user_recv) {
int chunk;
static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct netdev_notifier_change_info *change_info;
struct net *net = dev_net(dev);
struct inet6_dev *idev;
ndisc_send_unsol_na(dev);
in6_dev_put(idev);
break;
+ case NETDEV_CHANGE:
+ change_info = ptr;
+ if (change_info->flags_changed & IFF_NOARP)
+ neigh_changeaddr(&nd_tbl, dev);
+ break;
case NETDEV_DOWN:
neigh_ifdown(&nd_tbl, dev);
fib6_run_gc(0, net, false);
fq->ecn |= ecn;
if (payload_len > fq->q.max_size)
fq->q.max_size = payload_len;
- add_frag_mem_limit(&fq->q, skb->truesize);
+ add_frag_mem_limit(fq->q.net, skb->truesize);
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
clone->ip_summed = head->ip_summed;
NFCT_FRAG6_CB(clone)->orig = NULL;
- add_frag_mem_limit(&fq->q, clone->truesize);
+ add_frag_mem_limit(fq->q.net, clone->truesize);
}
/* We have to remove fragment header from datagram and to relocate
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
}
- sub_frag_mem_limit(&fq->q, head->truesize);
+ sub_frag_mem_limit(fq->q.net, head->truesize);
head->ignore_df = 1;
head->next = NULL;
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
- if (fq->q.flags & INET_FRAG_EVICTED)
+ if (inet_frag_evicting(&fq->q))
goto out_rcu_unlock;
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
fq->ecn |= ecn;
- add_frag_mem_limit(&fq->q, skb->truesize);
+ add_frag_mem_limit(fq->q.net, skb->truesize);
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
- add_frag_mem_limit(&fq->q, clone->truesize);
+ add_frag_mem_limit(fq->q.net, clone->truesize);
}
/* We have to remove fragment header from datagram and to relocate
}
fp = next;
}
- sub_frag_mem_limit(&fq->q, sum_truesize);
+ sub_frag_mem_limit(fq->q.net, sum_truesize);
head->next = NULL;
head->dev = dev;
if (signal_pending(current))
break;
rc = 0;
- if (sk_wait_data(sk, &timeo))
+ if (sk_wait_data(sk, &timeo, NULL))
break;
}
return rc;
release_sock(sk);
lock_sock(sk);
} else
- sk_wait_data(sk, &timeo);
+ sk_wait_data(sk, &timeo, NULL);
if ((flags & MSG_PEEK) && peek_seq != llc->copied_seq) {
net_dbg_ratelimited("LLC(%s:%d): Application bug, race in MSG_PEEK\n",
* return *ignored=0 i.e. ICMP and NF_DROP
*/
sched = rcu_dereference(svc->scheduler);
- dest = sched->schedule(svc, skb, iph);
+ if (sched) {
+ /* read svc->sched_data after svc->scheduler */
+ smp_rmb();
+ dest = sched->schedule(svc, skb, iph);
+ } else {
+ dest = NULL;
+ }
if (!dest) {
IP_VS_DBG(1, "p-schedule: no dest found.\n");
kfree(param.pe_data);
}
sched = rcu_dereference(svc->scheduler);
- dest = sched->schedule(svc, skb, iph);
+ if (sched) {
+ /* read svc->sched_data after svc->scheduler */
+ smp_rmb();
+ dest = sched->schedule(svc, skb, iph);
+ } else {
+ dest = NULL;
+ }
if (dest == NULL) {
IP_VS_DBG(1, "Schedule: no dest found.\n");
return NULL;
__ip_vs_dst_cache_reset(dest);
spin_unlock_bh(&dest->dst_lock);
- sched = rcu_dereference_protected(svc->scheduler, 1);
if (add) {
ip_vs_start_estimator(svc->net, &dest->stats);
list_add_rcu(&dest->n_list, &svc->destinations);
svc->num_dests++;
- if (sched->add_dest)
+ sched = rcu_dereference_protected(svc->scheduler, 1);
+ if (sched && sched->add_dest)
sched->add_dest(svc, dest);
} else {
- if (sched->upd_dest)
+ sched = rcu_dereference_protected(svc->scheduler, 1);
+ if (sched && sched->upd_dest)
sched->upd_dest(svc, dest);
}
}
struct ip_vs_scheduler *sched;
sched = rcu_dereference_protected(svc->scheduler, 1);
- if (sched->del_dest)
+ if (sched && sched->del_dest)
sched->del_dest(svc, dest);
}
}
ip_vs_use_count_inc();
/* Lookup the scheduler by 'u->sched_name' */
- sched = ip_vs_scheduler_get(u->sched_name);
- if (sched == NULL) {
- pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name);
- ret = -ENOENT;
- goto out_err;
+ if (strcmp(u->sched_name, "none")) {
+ sched = ip_vs_scheduler_get(u->sched_name);
+ if (!sched) {
+ pr_info("Scheduler module ip_vs_%s not found\n",
+ u->sched_name);
+ ret = -ENOENT;
+ goto out_err;
+ }
}
if (u->pe_name && *u->pe_name) {
spin_lock_init(&svc->stats.lock);
/* Bind the scheduler */
- ret = ip_vs_bind_scheduler(svc, sched);
- if (ret)
- goto out_err;
- sched = NULL;
+ if (sched) {
+ ret = ip_vs_bind_scheduler(svc, sched);
+ if (ret)
+ goto out_err;
+ sched = NULL;
+ }
/* Bind the ct retriever */
RCU_INIT_POINTER(svc->pe, pe);
static int
ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
{
- struct ip_vs_scheduler *sched, *old_sched;
+ struct ip_vs_scheduler *sched = NULL, *old_sched;
struct ip_vs_pe *pe = NULL, *old_pe = NULL;
int ret = 0;
/*
* Lookup the scheduler, by 'u->sched_name'
*/
- sched = ip_vs_scheduler_get(u->sched_name);
- if (sched == NULL) {
- pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name);
- return -ENOENT;
+ if (strcmp(u->sched_name, "none")) {
+ sched = ip_vs_scheduler_get(u->sched_name);
+ if (!sched) {
+ pr_info("Scheduler module ip_vs_%s not found\n",
+ u->sched_name);
+ return -ENOENT;
+ }
}
old_sched = sched;
old_sched = rcu_dereference_protected(svc->scheduler, 1);
if (sched != old_sched) {
+ if (old_sched) {
+ ip_vs_unbind_scheduler(svc, old_sched);
+ RCU_INIT_POINTER(svc->scheduler, NULL);
+ /* Wait all svc->sched_data users */
+ synchronize_rcu();
+ }
/* Bind the new scheduler */
- ret = ip_vs_bind_scheduler(svc, sched);
- if (ret) {
- old_sched = sched;
- goto out;
+ if (sched) {
+ ret = ip_vs_bind_scheduler(svc, sched);
+ if (ret) {
+ ip_vs_scheduler_put(sched);
+ goto out;
+ }
}
- /* Unbind the old scheduler on success */
- ip_vs_unbind_scheduler(svc, old_sched);
}
/*
const struct ip_vs_iter *iter = seq->private;
const struct ip_vs_dest *dest;
struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler);
+ char *sched_name = sched ? sched->name : "none";
if (iter->table == ip_vs_svc_table) {
#ifdef CONFIG_IP_VS_IPV6
ip_vs_proto_name(svc->protocol),
&svc->addr.in6,
ntohs(svc->port),
- sched->name);
+ sched_name);
else
#endif
seq_printf(seq, "%s %08X:%04X %s %s ",
ip_vs_proto_name(svc->protocol),
ntohl(svc->addr.ip),
ntohs(svc->port),
- sched->name,
+ sched_name,
(svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
} else {
seq_printf(seq, "FWM %08X %s %s",
- svc->fwmark, sched->name,
+ svc->fwmark, sched_name,
(svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
}
{
struct ip_vs_scheduler *sched;
struct ip_vs_kstats kstats;
+ char *sched_name;
sched = rcu_dereference_protected(src->scheduler, 1);
+ sched_name = sched ? sched->name : "none";
dst->protocol = src->protocol;
dst->addr = src->addr.ip;
dst->port = src->port;
dst->fwmark = src->fwmark;
- strlcpy(dst->sched_name, sched->name, sizeof(dst->sched_name));
+ strlcpy(dst->sched_name, sched_name, sizeof(dst->sched_name));
dst->flags = src->flags;
dst->timeout = src->timeout / HZ;
dst->netmask = src->netmask;
struct ip_vs_flags flags = { .flags = svc->flags,
.mask = ~0 };
struct ip_vs_kstats kstats;
+ char *sched_name;
nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE);
if (!nl_service)
}
sched = rcu_dereference_protected(svc->scheduler, 1);
+ sched_name = sched ? sched->name : "none";
pe = rcu_dereference_protected(svc->pe, 1);
- if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched->name) ||
+ if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched_name) ||
(pe && nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, pe->name)) ||
nla_put(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags) ||
nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) ||
if (sched->done_service)
sched->done_service(svc);
- /* svc->scheduler can not be set to NULL */
+ /* svc->scheduler can be set to NULL only by caller */
}
void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg)
{
- struct ip_vs_scheduler *sched;
+ struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler);
+ char *sched_name = sched ? sched->name : "none";
- sched = rcu_dereference(svc->scheduler);
if (svc->fwmark) {
IP_VS_ERR_RL("%s: FWM %u 0x%08X - %s\n",
- sched->name, svc->fwmark, svc->fwmark, msg);
+ sched_name, svc->fwmark, svc->fwmark, msg);
#ifdef CONFIG_IP_VS_IPV6
} else if (svc->af == AF_INET6) {
IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n",
- sched->name, ip_vs_proto_name(svc->protocol),
+ sched_name, ip_vs_proto_name(svc->protocol),
&svc->addr.in6, ntohs(svc->port), msg);
#endif
} else {
IP_VS_ERR_RL("%s: %s %pI4:%d - %s\n",
- sched->name, ip_vs_proto_name(svc->protocol),
+ sched_name, ip_vs_proto_name(svc->protocol),
&svc->addr.ip, ntohs(svc->port), msg);
}
}
pkts = atomic_add_return(1, &cp->in_pkts);
else
pkts = sysctl_sync_threshold(ipvs);
- ip_vs_sync_conn(net, cp->control, pkts);
+ ip_vs_sync_conn(net, cp, pkts);
}
}
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = daddr;
- fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ?
FLOWI_FLAG_KNOWN_NH : 0;
return -1;
err_unreach:
+ /* The ip6_link_failure function requires the dev field to be set
+ * in order to get the net (further for the sake of fwmark
+ * reflection).
+ */
+ if (!skb->dev)
+ skb->dev = skb_dst(skb)->dev;
+
dst_link_failure(skb);
return -1;
}
if (ret == NF_ACCEPT) {
nf_reset(skb);
skb_forward_csum(skb);
+ if (!skb->sk)
+ skb_sender_cpu_clear(skb);
}
return ret;
}
+/* In the event of a remote destination, it's possible that we would have
+ * matches against an old socket (particularly a TIME-WAIT socket). This
+ * causes havoc down the line (ip_local_out et. al. expect regular sockets
+ * and invalid memory accesses will happen) so simply drop the association
+ * in this case.
+*/
+static inline void ip_vs_drop_early_demux_sk(struct sk_buff *skb)
+{
+ /* If dev is set, the packet came from the LOCAL_IN callback and
+ * not from a local TCP socket.
+ */
+ if (skb->dev)
+ skb_orphan(skb);
+}
+
/* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */
static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
struct ip_vs_conn *cp, int local)
ip_vs_notrack(skb);
else
ip_vs_update_conntrack(skb, cp, 1);
+
+ /* Remove the early_demux association unless it's bound for the
+ * exact same port and address on this host after translation.
+ */
+ if (!local || cp->vport != cp->dport ||
+ !ip_vs_addr_equal(cp->af, &cp->vaddr, &cp->daddr))
+ ip_vs_drop_early_demux_sk(skb);
+
if (!local) {
skb_forward_csum(skb);
+ if (!skb->sk)
+ skb_sender_cpu_clear(skb);
NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
NULL, skb_dst(skb)->dev, dst_output_sk);
} else
ret = NF_ACCEPT;
+
return ret;
}
if (likely(!(cp->flags & IP_VS_CONN_F_NFCT)))
ip_vs_notrack(skb);
if (!local) {
+ ip_vs_drop_early_demux_sk(skb);
skb_forward_csum(skb);
+ if (!skb->sk)
+ skb_sender_cpu_clear(skb);
NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
NULL, skb_dst(skb)->dev, dst_output_sk);
} else
struct ipv6hdr *old_ipv6h = NULL;
#endif
+ ip_vs_drop_early_demux_sk(skb);
+
if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) {
new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb)
spin_unlock(&pcpu->lock);
}
+/* Released via destroy_conntrack() */
+struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags)
+{
+ struct nf_conn *tmpl;
+
+ tmpl = kzalloc(sizeof(struct nf_conn), GFP_KERNEL);
+ if (tmpl == NULL)
+ return NULL;
+
+ tmpl->status = IPS_TEMPLATE;
+ write_pnet(&tmpl->ct_net, net);
+
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+ if (zone) {
+ struct nf_conntrack_zone *nf_ct_zone;
+
+ nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, GFP_ATOMIC);
+ if (!nf_ct_zone)
+ goto out_free;
+ nf_ct_zone->id = zone;
+ }
+#endif
+ atomic_set(&tmpl->ct_general.use, 0);
+
+ return tmpl;
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+out_free:
+ kfree(tmpl);
+ return NULL;
+#endif
+}
+EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc);
+
+static void nf_ct_tmpl_free(struct nf_conn *tmpl)
+{
+ nf_ct_ext_destroy(tmpl);
+ nf_ct_ext_free(tmpl);
+ kfree(tmpl);
+}
+
static void
destroy_conntrack(struct nf_conntrack *nfct)
{
NF_CT_ASSERT(atomic_read(&nfct->use) == 0);
NF_CT_ASSERT(!timer_pending(&ct->timeout));
+ if (unlikely(nf_ct_is_template(ct))) {
+ nf_ct_tmpl_free(ct);
+ return;
+ }
rcu_read_lock();
l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
if (l4proto && l4proto->destroy)
}
EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
-/* deletion from this larval template list happens via nf_ct_put() */
-void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl)
-{
- struct ct_pcpu *pcpu;
-
- __set_bit(IPS_TEMPLATE_BIT, &tmpl->status);
- __set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
- nf_conntrack_get(&tmpl->ct_general);
-
- /* add this conntrack to the (per cpu) tmpl list */
- local_bh_disable();
- tmpl->cpu = smp_processor_id();
- pcpu = per_cpu_ptr(nf_ct_net(tmpl)->ct.pcpu_lists, tmpl->cpu);
-
- spin_lock(&pcpu->lock);
- /* Overload tuple linked list to put us in template list. */
- hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
- &pcpu->tmpl);
- spin_unlock_bh(&pcpu->lock);
-}
-EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert);
-
/* Confirm a connection given skb; places it in hash table */
int
__nf_conntrack_confirm(struct sk_buff *skb)
spin_lock_init(&pcpu->lock);
INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL);
INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL);
- INIT_HLIST_NULLS_HEAD(&pcpu->tmpl, TEMPLATE_NULLS_VAL);
}
net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
a->mask.src.u3.all[count] & b->mask.src.u3.all[count];
}
- return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask);
+ return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) &&
+ nf_ct_zone(a->master) == nf_ct_zone(b->master);
}
static inline int expect_matches(const struct nf_conntrack_expect *a,
}
err = nf_ct_expect_related_report(exp, portid, report);
- if (err < 0)
- goto err_exp;
-
- return 0;
-err_exp:
nf_ct_expect_put(exp);
err_ct:
nf_ct_put(ct);
static int __net_init synproxy_net_init(struct net *net)
{
struct synproxy_net *snet = synproxy_pernet(net);
- struct nf_conntrack_tuple t;
struct nf_conn *ct;
int err = -ENOMEM;
- memset(&t, 0, sizeof(t));
- ct = nf_conntrack_alloc(net, 0, &t, &t, GFP_KERNEL);
+ ct = nf_ct_tmpl_alloc(net, 0, GFP_KERNEL);
if (IS_ERR(ct)) {
err = PTR_ERR(ct);
goto err1;
if (!nfct_synproxy_ext_add(ct))
goto err2;
- nf_conntrack_tmpl_insert(net, ct);
+ __set_bit(IPS_CONFIRMED_BIT, &ct->status);
+ nf_conntrack_get(&ct->ct_general);
snet->tmpl = ct;
snet->stats = alloc_percpu(struct synproxy_stats);
static int xt_ct_tg_check(const struct xt_tgchk_param *par,
struct xt_ct_target_info_v1 *info)
{
- struct nf_conntrack_tuple t;
struct nf_conn *ct;
int ret = -EOPNOTSUPP;
if (ret < 0)
goto err1;
- memset(&t, 0, sizeof(t));
- ct = nf_conntrack_alloc(par->net, info->zone, &t, &t, GFP_KERNEL);
+ ct = nf_ct_tmpl_alloc(par->net, info->zone, GFP_KERNEL);
ret = PTR_ERR(ct);
if (IS_ERR(ct))
goto err2;
if (ret < 0)
goto err3;
}
-
- nf_conntrack_tmpl_insert(par->net, ct);
+ __set_bit(IPS_CONFIRMED_BIT, &ct->status);
+ nf_conntrack_get(&ct->ct_general);
out:
info->ct = ct;
return 0;
goto out;
}
+ sysfs_attr_init(&info->timer->attr.attr);
info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL);
if (!info->timer->attr.attr.name) {
ret = -ENOMEM;
}
tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
addr, hlen);
- if (tp_len > dev->mtu + dev->hard_header_len) {
+ if (likely(tp_len >= 0) &&
+ tp_len > dev->mtu + dev->hard_header_len) {
struct ethhdr *ehdr;
/* Earlier code assumed this would be a VLAN pkt,
* double-check this now that we have the actual
static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
{
struct packet_sock *po = pkt_sk(sk);
- const struct net_device *dev_curr;
+ struct net_device *dev_curr;
__be16 proto_curr;
bool need_rehook;
po->num = proto;
po->prot_hook.type = proto;
-
- if (po->prot_hook.dev)
- dev_put(po->prot_hook.dev);
-
po->prot_hook.dev = dev;
po->ifindex = dev ? dev->ifindex : 0;
packet_cached_dev_assign(po, dev);
}
+ if (dev_curr)
+ dev_put(dev_curr);
if (proto == 0 || !need_rehook)
goto out_unlock;
}
EXPORT_SYMBOL(tcf_hash_destroy);
-int tcf_hash_release(struct tc_action *a, int bind)
+int __tcf_hash_release(struct tc_action *a, bool bind, bool strict)
{
struct tcf_common *p = a->priv;
int ret = 0;
if (p) {
if (bind)
p->tcfc_bindcnt--;
- else if (p->tcfc_bindcnt > 0)
+ else if (strict && p->tcfc_bindcnt > 0)
return -EPERM;
p->tcfc_refcnt--;
ret = 1;
}
}
+
return ret;
}
-EXPORT_SYMBOL(tcf_hash_release);
+EXPORT_SYMBOL(__tcf_hash_release);
static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb,
struct tc_action *a)
head = &hinfo->htab[tcf_hash(i, hinfo->hmask)];
hlist_for_each_entry_safe(p, n, head, tcfc_head) {
a->priv = p;
- ret = tcf_hash_release(a, 0);
+ ret = __tcf_hash_release(a, false, true);
if (ret == ACT_P_DELETED) {
module_put(a->ops->owner);
n_i++;
int ret = 0;
list_for_each_entry_safe(a, tmp, actions, list) {
- ret = tcf_hash_release(a, bind);
+ ret = __tcf_hash_release(a, bind, true);
if (ret == ACT_P_DELETED)
module_put(a->ops->owner);
else if (ret < 0)
struct tcf_bpf_cfg {
struct bpf_prog *filter;
struct sock_filter *bpf_ops;
- char *bpf_name;
+ const char *bpf_name;
u32 bpf_fd;
u16 bpf_num_ops;
+ bool is_ebpf;
};
static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act,
cfg->bpf_ops = bpf_ops;
cfg->bpf_num_ops = bpf_num_ops;
cfg->filter = fp;
+ cfg->is_ebpf = false;
return 0;
}
cfg->bpf_fd = bpf_fd;
cfg->bpf_name = name;
cfg->filter = fp;
+ cfg->is_ebpf = true;
return 0;
}
+static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg)
+{
+ if (cfg->is_ebpf)
+ bpf_prog_put(cfg->filter);
+ else
+ bpf_prog_destroy(cfg->filter);
+
+ kfree(cfg->bpf_ops);
+ kfree(cfg->bpf_name);
+}
+
+static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
+ struct tcf_bpf_cfg *cfg)
+{
+ cfg->is_ebpf = tcf_bpf_is_ebpf(prog);
+ cfg->filter = prog->filter;
+
+ cfg->bpf_ops = prog->bpf_ops;
+ cfg->bpf_name = prog->bpf_name;
+}
+
static int tcf_bpf_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action *act,
int replace, int bind)
{
struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
+ struct tcf_bpf_cfg cfg, old;
struct tc_act_bpf *parm;
struct tcf_bpf *prog;
- struct tcf_bpf_cfg cfg;
bool is_bpf, is_ebpf;
int ret;
prog = to_bpf(act);
spin_lock_bh(&prog->tcf_lock);
+ if (ret != ACT_P_CREATED)
+ tcf_bpf_prog_fill_cfg(prog, &old);
+
prog->bpf_ops = cfg.bpf_ops;
prog->bpf_name = cfg.bpf_name;
if (ret == ACT_P_CREATED)
tcf_hash_insert(act);
+ else
+ tcf_bpf_cfg_cleanup(&old);
return ret;
destroy_fp:
- if (is_ebpf)
- bpf_prog_put(cfg.filter);
- else
- bpf_prog_destroy(cfg.filter);
-
- kfree(cfg.bpf_ops);
- kfree(cfg.bpf_name);
-
+ tcf_bpf_cfg_cleanup(&cfg);
return ret;
}
static void tcf_bpf_cleanup(struct tc_action *act, int bind)
{
- const struct tcf_bpf *prog = act->priv;
-
- if (tcf_bpf_is_ebpf(prog))
- bpf_prog_put(prog->filter);
- else
- bpf_prog_destroy(prog->filter);
+ struct tcf_bpf_cfg tmp;
- kfree(prog->bpf_ops);
- kfree(prog->bpf_name);
+ tcf_bpf_prog_fill_cfg(act->priv, &tmp);
+ tcf_bpf_cfg_cleanup(&tmp);
}
static struct tc_action_ops act_bpf_ops __read_mostly = {
}
ret = ACT_P_CREATED;
} else {
- p = to_pedit(a);
- tcf_hash_release(a, bind);
if (bind)
return 0;
+ tcf_hash_release(a, bind);
if (!ovr)
return -EEXIST;
-
+ p = to_pedit(a);
if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) {
keys = kmalloc(ksize, GFP_KERNEL);
if (keys == NULL)
{
struct choke_sched_data *q = qdisc_priv(sch);
+ while (q->head != q->tail) {
+ struct sk_buff *skb = q->tab[q->head];
+
+ q->head = (q->head + 1) & q->tab_mask;
+ if (!skb)
+ continue;
+ qdisc_qstats_backlog_dec(sch, skb);
+ --sch->q.qlen;
+ qdisc_drop(skb, sch);
+ }
+
+ memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
+ q->head = q->tail = 0;
red_restart(&q->vars);
}
.peek = qdisc_peek_head,
.init = plug_init,
.change = plug_change,
+ .reset = qdisc_reset_queue,
.owner = THIS_MODULE,
};
if (copy_from_user(&sctp_sk(sk)->subscribe, optval, optlen))
return -EFAULT;
- if (sctp_sk(sk)->subscribe.sctp_data_io_event)
- pr_warn_ratelimited(DEPRECATED "%s (pid %d) "
- "Requested SCTP_SNDRCVINFO event.\n"
- "Use SCTP_RCVINFO through SCTP_RECVRCVINFO option instead.\n",
- current->comm, task_pid_nr(current));
-
/* At the time when a user app subscribes to SCTP_SENDER_DRY_EVENT,
* if there is no data to be sent or retransmit, the stack will
* immediately send up this notification.