* [PATCH 07/10] vmxnet3: remove device counter
From: Stephen Hemminger @ 2013-01-15 17:28 UTC (permalink / raw)
To: David Miller, Shreyas Bhatewara; +Cc: pv-drivers, netdev, Stephen Hemminger
In-Reply-To: <1358270915-32758-1-git-send-email-stephen@networkplumber.org>
An atomic counter of devices present is maintained but never used.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
---
drivers/net/vmxnet3/vmxnet3_drv.c | 5 -----
drivers/net/vmxnet3/vmxnet3_int.h | 1 -
2 files changed, 6 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 0e55153..1f66a7e 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -43,8 +43,6 @@ static DEFINE_PCI_DEVICE_TABLE(vmxnet3_pciid_table) = {
MODULE_DEVICE_TABLE(pci, vmxnet3_pciid_table);
-static atomic_t devices_found;
-
static int enable_mq = 1;
static int irq_share_mode;
@@ -3005,8 +3003,6 @@ vmxnet3_probe_device(struct pci_dev *pdev,
SET_NETDEV_DEV(netdev, &pdev->dev);
vmxnet3_declare_features(adapter, dma64);
- adapter->dev_number = atomic_read(&devices_found);
-
adapter->share_intr = irq_share_mode;
if (adapter->share_intr == VMXNET3_INTR_BUDDYSHARE &&
adapter->num_tx_queues != adapter->num_rx_queues)
@@ -3057,7 +3053,6 @@ vmxnet3_probe_device(struct pci_dev *pdev,
}
vmxnet3_check_link(adapter, false);
- atomic_inc(&devices_found);
return 0;
err_register:
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 55465ed..3198384 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -352,7 +352,6 @@ struct vmxnet3_adapter {
unsigned long state; /* VMXNET3_STATE_BIT_xxx */
- int dev_number;
int share_intr;
};
--
1.7.10.4
^ permalink raw reply related
* [PATCH 06/10] vmxnet3: remove VMXNET3_MAX_DEVICES
From: Stephen Hemminger @ 2013-01-15 17:28 UTC (permalink / raw)
To: David Miller, Shreyas Bhatewara; +Cc: pv-drivers, netdev, Stephen Hemminger
In-Reply-To: <1358270915-32758-1-git-send-email-stephen@networkplumber.org>
Defined but never used.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
---
drivers/net/vmxnet3/vmxnet3_drv.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index d862937..0e55153 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -45,7 +45,6 @@ MODULE_DEVICE_TABLE(pci, vmxnet3_pciid_table);
static atomic_t devices_found;
-#define VMXNET3_MAX_DEVICES 10
static int enable_mq = 1;
static int irq_share_mode;
--
1.7.10.4
^ permalink raw reply related
* [PATCH 05/10] vmxnet3: use netdev_ printk wrappers
From: Stephen Hemminger @ 2013-01-15 17:28 UTC (permalink / raw)
To: David Miller, Shreyas Bhatewara; +Cc: pv-drivers, netdev, Stephen Hemminger
In-Reply-To: <1358270915-32758-1-git-send-email-stephen@networkplumber.org>
Use the standard netdev_xxx() and dev_xxx() wrappers to format
log messages.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
---
drivers/net/vmxnet3/vmxnet3_drv.c | 136 ++++++++++++++++-----------------
drivers/net/vmxnet3/vmxnet3_ethtool.c | 13 ++--
2 files changed, 73 insertions(+), 76 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index c566b73..d862937 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -152,8 +152,8 @@ vmxnet3_check_link(struct vmxnet3_adapter *adapter, bool affectTxQueue)
adapter->link_speed = ret >> 16;
if (ret & 1) { /* Link is up. */
- printk(KERN_INFO "%s: NIC Link is Up %d Mbps\n",
- adapter->netdev->name, adapter->link_speed);
+ netdev_info(adapter->netdev, "NIC Link is Up %d Mbps\n",
+ adapter->link_speed);
if (!netif_carrier_ok(adapter->netdev))
netif_carrier_on(adapter->netdev);
@@ -163,8 +163,7 @@ vmxnet3_check_link(struct vmxnet3_adapter *adapter, bool affectTxQueue)
adapter);
}
} else {
- printk(KERN_INFO "%s: NIC Link is Down\n",
- adapter->netdev->name);
+ netdev_info(adapter->netdev, "NIC Link is Down\n");
if (netif_carrier_ok(adapter->netdev))
netif_carrier_off(adapter->netdev);
@@ -510,8 +509,7 @@ vmxnet3_tq_create(struct vmxnet3_tx_queue *tq,
* sizeof(struct Vmxnet3_TxDesc),
&tq->tx_ring.basePA);
if (!tq->tx_ring.base) {
- printk(KERN_ERR "%s: failed to allocate tx ring\n",
- adapter->netdev->name);
+ netdev_err(adapter->netdev, "failed to allocate tx ring\n");
goto err;
}
@@ -520,8 +518,7 @@ vmxnet3_tq_create(struct vmxnet3_tx_queue *tq,
sizeof(struct Vmxnet3_TxDataDesc),
&tq->data_ring.basePA);
if (!tq->data_ring.base) {
- printk(KERN_ERR "%s: failed to allocate data ring\n",
- adapter->netdev->name);
+ netdev_err(adapter->netdev, "failed to allocate data ring\n");
goto err;
}
@@ -530,8 +527,7 @@ vmxnet3_tq_create(struct vmxnet3_tx_queue *tq,
sizeof(struct Vmxnet3_TxCompDesc),
&tq->comp_ring.basePA);
if (!tq->comp_ring.base) {
- printk(KERN_ERR "%s: failed to allocate tx comp ring\n",
- adapter->netdev->name);
+ netdev_err(adapter->netdev, "failed to allocate tx comp ring\n");
goto err;
}
@@ -1511,8 +1507,8 @@ vmxnet3_rq_create(struct vmxnet3_rx_queue *rq, struct vmxnet3_adapter *adapter)
rq->rx_ring[i].base = pci_alloc_consistent(adapter->pdev, sz,
&rq->rx_ring[i].basePA);
if (!rq->rx_ring[i].base) {
- printk(KERN_ERR "%s: failed to allocate rx ring %d\n",
- adapter->netdev->name, i);
+ netdev_err(adapter->netdev,
+ "failed to allocate rx ring %d\n", i);
goto err;
}
}
@@ -1521,8 +1517,7 @@ vmxnet3_rq_create(struct vmxnet3_rx_queue *rq, struct vmxnet3_adapter *adapter)
rq->comp_ring.base = pci_alloc_consistent(adapter->pdev, sz,
&rq->comp_ring.basePA);
if (!rq->comp_ring.base) {
- printk(KERN_ERR "%s: failed to allocate rx comp ring\n",
- adapter->netdev->name);
+ netdev_err(adapter->netdev, "failed to allocate rx comp ring\n");
goto err;
}
@@ -1814,9 +1809,10 @@ vmxnet3_request_irqs(struct vmxnet3_adapter *adapter)
adapter->rx_queue[i].name,
&(adapter->rx_queue[i]));
if (err) {
- printk(KERN_ERR "Failed to request irq for MSIX"
- ", %s, error %d\n",
- adapter->rx_queue[i].name, err);
+ netdev_err(adapter->netdev,
+ "Failed to request irq for MSIX, "
+ "%s, error %d\n",
+ adapter->rx_queue[i].name, err);
return err;
}
@@ -1845,8 +1841,9 @@ vmxnet3_request_irqs(struct vmxnet3_adapter *adapter)
#endif
intr->num_intrs = vector + 1;
if (err) {
- printk(KERN_ERR "Failed to request irq %s (intr type:%d), error"
- ":%d\n", adapter->netdev->name, intr->type, err);
+ netdev_err(adapter->netdev,
+ "Failed to request irq (intr type:%d), error %d\n",
+ intr->type, err);
} else {
/* Number of rx queues will not change after this */
for (i = 0; i < adapter->num_rx_queues; i++) {
@@ -1867,9 +1864,9 @@ vmxnet3_request_irqs(struct vmxnet3_adapter *adapter)
adapter->rx_queue[0].comp_ring.intr_idx = 0;
}
- printk(KERN_INFO "%s: intr type %u, mode %u, %u vectors "
- "allocated\n", adapter->netdev->name, intr->type,
- intr->mask_mode, intr->num_intrs);
+ netdev_info(adapter->netdev,
+ "intr type %u, mode %u, %u vectors allocated\n",
+ intr->type, intr->mask_mode, intr->num_intrs);
}
return err;
@@ -2035,8 +2032,8 @@ vmxnet3_set_mc(struct net_device *netdev)
rxConf->mfTablePA = cpu_to_le64(virt_to_phys(
new_table));
} else {
- printk(KERN_INFO "%s: failed to copy mcast list"
- ", setting ALL_MULTI\n", netdev->name);
+ netdev_info(netdev, "failed to copy mcast list"
+ ", setting ALL_MULTI\n");
new_mode |= VMXNET3_RXM_ALL_MULTI;
}
}
@@ -2221,15 +2218,15 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
vmxnet3_tq_init_all(adapter);
err = vmxnet3_rq_init_all(adapter);
if (err) {
- printk(KERN_ERR "Failed to init rx queue for %s: error %d\n",
- adapter->netdev->name, err);
+ netdev_err(adapter->netdev,
+ "Failed to init rx queue error %d\n", err);
goto rq_err;
}
err = vmxnet3_request_irqs(adapter);
if (err) {
- printk(KERN_ERR "Failed to setup irq for %s: error %d\n",
- adapter->netdev->name, err);
+ netdev_err(adapter->netdev,
+ "Failed to setup irq for error %d\n", err);
goto irq_err;
}
@@ -2246,8 +2243,8 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
spin_unlock_irqrestore(&adapter->cmd_lock, flags);
if (ret != 0) {
- printk(KERN_ERR "Failed to activate dev %s: error %u\n",
- adapter->netdev->name, ret);
+ netdev_err(adapter->netdev,
+ "Failed to activate dev: error %u\n", ret);
err = -EINVAL;
goto activate_err;
}
@@ -2362,23 +2359,22 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
err = pci_enable_device(pdev);
if (err) {
- printk(KERN_ERR "Failed to enable adapter %s: error %d\n",
- pci_name(pdev), err);
+ dev_err(&pdev->dev, "Failed to enable adapter: error %d\n", err);
return err;
}
if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) == 0) {
if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) {
- printk(KERN_ERR "pci_set_consistent_dma_mask failed "
- "for adapter %s\n", pci_name(pdev));
+ dev_err(&pdev->dev,
+ "pci_set_consistent_dma_mask failed\n");
err = -EIO;
goto err_set_mask;
}
*dma64 = true;
} else {
if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) {
- printk(KERN_ERR "pci_set_dma_mask failed for adapter "
- "%s\n", pci_name(pdev));
+ dev_err(&pdev->dev,
+ "pci_set_dma_mask failed\n");
err = -EIO;
goto err_set_mask;
}
@@ -2388,8 +2384,8 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
err = pci_request_selected_regions(pdev, (1 << 2) - 1,
vmxnet3_driver_name);
if (err) {
- printk(KERN_ERR "Failed to request region for adapter %s: "
- "error %d\n", pci_name(pdev), err);
+ dev_err(&pdev->dev,
+ "Failed to request region for adapter: error %d\n", err);
goto err_set_mask;
}
@@ -2399,8 +2395,7 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
mmio_len = pci_resource_len(pdev, 0);
adapter->hw_addr0 = ioremap(mmio_start, mmio_len);
if (!adapter->hw_addr0) {
- printk(KERN_ERR "Failed to map bar0 for adapter %s\n",
- pci_name(pdev));
+ dev_err(&pdev->dev, "Failed to map bar0\n");
err = -EIO;
goto err_ioremap;
}
@@ -2409,8 +2404,7 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
mmio_len = pci_resource_len(pdev, 1);
adapter->hw_addr1 = ioremap(mmio_start, mmio_len);
if (!adapter->hw_addr1) {
- printk(KERN_ERR "Failed to map bar1 for adapter %s\n",
- pci_name(pdev));
+ dev_err(&pdev->dev, "Failed to map bar1\n");
err = -EIO;
goto err_bar1;
}
@@ -2517,12 +2511,14 @@ vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size,
err = vmxnet3_rq_create(rq, adapter);
if (err) {
if (i == 0) {
- printk(KERN_ERR "Could not allocate any rx"
- "queues. Aborting.\n");
+ netdev_err(adapter->netdev,
+ "Could not allocate any rx queues. "
+ "Aborting.\n");
goto queue_err;
} else {
- printk(KERN_INFO "Number of rx queues changed "
- "to : %d.\n", i);
+ netdev_info(adapter->netdev,
+ "Number of rx queues changed "
+ "to : %d.\n", i);
adapter->num_rx_queues = i;
err = 0;
break;
@@ -2635,15 +2631,17 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu)
vmxnet3_adjust_rx_ring_size(adapter);
err = vmxnet3_rq_create_all(adapter);
if (err) {
- printk(KERN_ERR "%s: failed to re-create rx queues,"
- " error %d. Closing it.\n", netdev->name, err);
+ netdev_err(netdev,
+ "failed to re-create rx queues, "
+ " error %d. Closing it.\n", err);
goto out;
}
err = vmxnet3_activate_dev(adapter);
if (err) {
- printk(KERN_ERR "%s: failed to re-activate, error %d. "
- "Closing it\n", netdev->name, err);
+ netdev_err(netdev,
+ "failed to re-activate, error %d. "
+ "Closing it\n", err);
goto out;
}
}
@@ -2786,7 +2784,8 @@ vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter)
if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE
|| adapter->num_rx_queues != 1) {
adapter->share_intr = VMXNET3_INTR_TXSHARE;
- printk(KERN_ERR "Number of rx queues : 1\n");
+ netdev_err(adapter->netdev,
+ "Number of rx queues : 1\n");
adapter->num_rx_queues = 1;
adapter->intr.num_intrs =
VMXNET3_LINUX_MIN_MSIX_VECT;
@@ -2816,7 +2815,8 @@ vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter)
#endif /* CONFIG_PCI_MSI */
adapter->num_rx_queues = 1;
- printk(KERN_INFO "Using INTx interrupt, #Rx queues: 1.\n");
+ dev_info(&adapter->netdev->dev,
+ "Using INTx interrupt, #Rx queues: 1.\n");
adapter->intr.type = VMXNET3_IT_INTX;
/* INT-X related setting */
@@ -2842,7 +2842,7 @@ vmxnet3_tx_timeout(struct net_device *netdev)
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
adapter->tx_timeout_count++;
- printk(KERN_ERR "%s: tx hang\n", adapter->netdev->name);
+ netdev_err(adapter->netdev, "tx hang\n");
schedule_work(&adapter->work);
netif_wake_queue(adapter->netdev);
}
@@ -2862,12 +2862,12 @@ vmxnet3_reset_work(struct work_struct *data)
/* if the device is closed, we must leave it alone */
rtnl_lock();
if (netif_running(adapter->netdev)) {
- printk(KERN_INFO "%s: resetting\n", adapter->netdev->name);
+ netdev_notice(adapter->netdev, "resetting\n");
vmxnet3_quiesce_dev(adapter);
vmxnet3_reset_dev(adapter);
vmxnet3_activate_dev(adapter);
} else {
- printk(KERN_INFO "%s: already closed\n", adapter->netdev->name);
+ netdev_info(adapter->netdev, "already closed\n");
}
rtnl_unlock();
@@ -2926,8 +2926,9 @@ vmxnet3_probe_device(struct pci_dev *pdev,
num_tx_queues = rounddown_pow_of_two(num_tx_queues);
netdev = alloc_etherdev_mq(sizeof(struct vmxnet3_adapter),
max(num_tx_queues, num_rx_queues));
- printk(KERN_INFO "# of Tx queues : %d, # of Rx queues : %d\n",
- num_tx_queues, num_rx_queues);
+ dev_info(&pdev->dev,
+ "# of Tx queues : %d, # of Rx queues : %d\n",
+ num_tx_queues, num_rx_queues);
if (!netdev)
return -ENOMEM;
@@ -2942,8 +2943,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
sizeof(struct Vmxnet3_DriverShared),
&adapter->shared_pa);
if (!adapter->shared) {
- printk(KERN_ERR "Failed to allocate memory for %s\n",
- pci_name(pdev));
+ dev_err(&pdev->dev, "Failed to allocate memory\n");
err = -ENOMEM;
goto err_alloc_shared;
}
@@ -2957,8 +2957,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
&adapter->queue_desc_pa);
if (!adapter->tqd_start) {
- printk(KERN_ERR "Failed to allocate memory for %s\n",
- pci_name(pdev));
+ dev_err(&pdev->dev, "Failed to allocate memory\n");
err = -ENOMEM;
goto err_alloc_queue_desc;
}
@@ -2988,8 +2987,8 @@ vmxnet3_probe_device(struct pci_dev *pdev,
if (ver & 1) {
VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_VRRS, 1);
} else {
- printk(KERN_ERR "Incompatible h/w version (0x%x) for adapter"
- " %s\n", ver, pci_name(pdev));
+ dev_err(&pdev->dev,
+ "Incompatible h/w version (0x%x) for adapter\n", ver);
err = -EBUSY;
goto err_ver;
}
@@ -2998,8 +2997,8 @@ vmxnet3_probe_device(struct pci_dev *pdev,
if (ver & 1) {
VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_UVRS, 1);
} else {
- printk(KERN_ERR "Incompatible upt version (0x%x) for "
- "adapter %s\n", ver, pci_name(pdev));
+ dev_err(&pdev->dev,
+ "Incompatible upt version (0x%x) for adapter\n", ver);
err = -EBUSY;
goto err_ver;
}
@@ -3020,7 +3019,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
if (adapter->num_rx_queues > 1 &&
adapter->intr.type == VMXNET3_IT_MSIX) {
adapter->rss = true;
- printk(KERN_INFO "RSS is enabled.\n");
+ dev_dbg(&pdev->dev, "RSS is enabled.\n");
} else {
adapter->rss = false;
}
@@ -3054,8 +3053,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
err = register_netdev(netdev);
if (err) {
- printk(KERN_ERR "Failed to register adapter %s\n",
- pci_name(pdev));
+ dev_err(&pdev->dev, "Failed to register adapter\n");
goto err_register;
}
@@ -3302,7 +3300,7 @@ static struct pci_driver vmxnet3_driver = {
static int __init
vmxnet3_init_module(void)
{
- printk(KERN_INFO "%s - version %s\n", VMXNET3_DRIVER_DESC,
+ pr_info("%s - version %s\n", VMXNET3_DRIVER_DESC,
VMXNET3_DRIVER_VERSION_REPORT);
return pci_register_driver(&vmxnet3_driver);
}
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 8c9fa4b..9bc542b 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -522,24 +522,23 @@ vmxnet3_set_ringparam(struct net_device *netdev,
if (err) {
/* failed, most likely because of OOM, try default
* size */
- printk(KERN_ERR "%s: failed to apply new sizes, try the"
- " default ones\n", netdev->name);
+ netdev_err(netdev, "failed to apply new sizes, "
+ "try the default ones\n");
err = vmxnet3_create_queues(adapter,
VMXNET3_DEF_TX_RING_SIZE,
VMXNET3_DEF_RX_RING_SIZE,
VMXNET3_DEF_RX_RING_SIZE);
if (err) {
- printk(KERN_ERR "%s: failed to create queues "
- "with default sizes. Closing it\n",
- netdev->name);
+ netdev_err(netdev, "failed to create queues "
+ "with default sizes. Closing it\n");
goto out;
}
}
err = vmxnet3_activate_dev(adapter);
if (err)
- printk(KERN_ERR "%s: failed to re-activate, error %d."
- " Closing it\n", netdev->name, err);
+ netdev_err(netdev, "failed to re-activate, error %d."
+ " Closing it\n", err);
}
out:
--
1.7.10.4
^ permalink raw reply related
* [PATCH 04/10] vmxnet3: use netdev_dbg
From: Stephen Hemminger @ 2013-01-15 17:28 UTC (permalink / raw)
To: David Miller, Shreyas Bhatewara; +Cc: pv-drivers, netdev, Stephen Hemminger
In-Reply-To: <1358270915-32758-1-git-send-email-stephen@networkplumber.org>
Use netdev_dbg() rather than dev_dbg() because the former prints
the device name which is more useful than the pci name.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
---
drivers/net/vmxnet3/vmxnet3_drv.c | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 7b10d9c..c566b73 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -629,7 +629,7 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx,
vmxnet3_cmd_ring_adv_next2fill(ring);
}
- dev_dbg(&adapter->netdev->dev,
+ netdev_dbg(adapter->netdev,
"alloc_rx_buf: %d allocated, next2fill %u, next2comp %u\n",
num_allocated, ring->next2fill, ring->next2comp);
@@ -688,7 +688,7 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
tbi = tq->buf_info + tq->tx_ring.next2fill;
tbi->map_type = VMXNET3_MAP_NONE;
- dev_dbg(&adapter->netdev->dev,
+ netdev_dbg(adapter->netdev,
"txd[%u]: 0x%Lx 0x%x 0x%x\n",
tq->tx_ring.next2fill,
le64_to_cpu(ctx->sop_txd->txd.addr),
@@ -728,7 +728,7 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
gdesc->dword[2] = cpu_to_le32(dw2);
gdesc->dword[3] = 0;
- dev_dbg(&adapter->netdev->dev,
+ netdev_dbg(adapter->netdev,
"txd[%u]: 0x%Lx 0x%x 0x%x\n",
tq->tx_ring.next2fill, le64_to_cpu(gdesc->txd.addr),
le32_to_cpu(gdesc->dword[2]), gdesc->dword[3]);
@@ -768,7 +768,7 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
gdesc->dword[2] = cpu_to_le32(dw2);
gdesc->dword[3] = 0;
- dev_dbg(&adapter->netdev->dev,
+ netdev_dbg(adapter->netdev,
"txd[%u]: 0x%llu %u %u\n",
tq->tx_ring.next2fill, le64_to_cpu(gdesc->txd.addr),
le32_to_cpu(gdesc->dword[2]), gdesc->dword[3]);
@@ -868,7 +868,7 @@ vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
tdd = tq->data_ring.base + tq->tx_ring.next2fill;
memcpy(tdd->data, skb->data, ctx->copy_size);
- dev_dbg(&adapter->netdev->dev,
+ netdev_dbg(adapter->netdev,
"copy %u bytes to dataRing[%u]\n",
ctx->copy_size, tq->tx_ring.next2fill);
return 1;
@@ -974,7 +974,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) {
tq->stats.tx_ring_full++;
- dev_dbg(&adapter->netdev->dev,
+ netdev_dbg(adapter->netdev,
"tx queue stopped on %s, next2comp %u"
" next2fill %u\n", adapter->netdev->name,
tq->tx_ring.next2comp, tq->tx_ring.next2fill);
@@ -1057,7 +1057,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
(struct Vmxnet3_TxDesc *)ctx.sop_txd);
gdesc = ctx.sop_txd;
#endif
- dev_dbg(&adapter->netdev->dev,
+ netdev_dbg(adapter->netdev,
"txd[%u]: SOP 0x%Lx 0x%x 0x%x\n",
(u32)(ctx.sop_txd -
tq->tx_ring.base), le64_to_cpu(gdesc->txd.addr),
@@ -1210,7 +1210,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
if (unlikely(rcd->len == 0)) {
/* Pretend the rx buffer is skipped. */
BUG_ON(!(rcd->sop && rcd->eop));
- dev_dbg(&adapter->netdev->dev,
+ netdev_dbg(adapter->netdev,
"rxRing[%u][%u] 0 length\n",
ring_idx, idx);
goto rcd_done;
@@ -2211,7 +2211,7 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
u32 ret;
unsigned long flags;
- dev_dbg(&adapter->netdev->dev, "%s: skb_buf_size %d, rx_buf_per_pkt %d,"
+ netdev_dbg(adapter->netdev, "%s: skb_buf_size %d, rx_buf_per_pkt %d,"
" ring sizes %u %u %u\n", adapter->netdev->name,
adapter->skb_buf_size, adapter->rx_buf_per_pkt,
adapter->tx_queue[0].tx_ring.size,
--
1.7.10.4
^ permalink raw reply related
* [PATCH 03/10] vmxnet3: fix messages printed before registration
From: Stephen Hemminger @ 2013-01-15 17:28 UTC (permalink / raw)
To: David Miller, Shreyas Bhatewara; +Cc: pv-drivers, netdev, Stephen Hemminger
In-Reply-To: <1358270915-32758-1-git-send-email-stephen@networkplumber.org>
This messages that occur during boot time from this device
when netdev_err is called before calling register_netdevice().
Switch to using dev_XXX macros which correlate message with PCI info which
is available.
Rather than fixing the features message, just remove it since
the information is redundant and available through ethtool.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
---
drivers/net/vmxnet3/vmxnet3_drv.c | 21 +++++++++------------
1 file changed, 9 insertions(+), 12 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 99ef9ed..7b10d9c 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -2671,10 +2671,6 @@ vmxnet3_declare_features(struct vmxnet3_adapter *adapter, bool dma64)
netdev->vlan_features = netdev->hw_features &
~(NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX);
netdev->features = netdev->hw_features | NETIF_F_HW_VLAN_FILTER;
-
- netdev_info(adapter->netdev,
- "features: sg csum vlan jf tso tsoIPv6 lro%s\n",
- dma64 ? " highDMA" : "");
}
@@ -2717,7 +2713,7 @@ vmxnet3_acquire_msix_vectors(struct vmxnet3_adapter *adapter,
adapter->intr.num_intrs = vectors;
return 0;
} else if (err < 0) {
- netdev_err(adapter->netdev,
+ dev_err(&adapter->netdev->dev,
"Failed to enable MSI-X, error: %d\n", err);
vectors = 0;
} else if (err < vector_threshold) {
@@ -2726,15 +2722,16 @@ vmxnet3_acquire_msix_vectors(struct vmxnet3_adapter *adapter,
/* If fails to enable required number of MSI-x vectors
* try enabling minimum number of vectors required.
*/
- netdev_err(adapter->netdev,
- "Failed to enable %d MSI-X, trying %d instead\n",
+ dev_err(&adapter->netdev->dev,
+ "Failed to enable %d MSI-X, trying %d instead\n",
vectors, vector_threshold);
vectors = vector_threshold;
}
}
- netdev_info(adapter->netdev,
- "Number of MSI-X interrupts which can be allocated are lower than min threshold required.\n");
+ dev_info(&adapter->pdev->dev,
+ "Number of MSI-X interrupts which can be allocated "
+ "is lower than min threshold required.\n");
return err;
}
@@ -2800,9 +2797,9 @@ vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter)
return;
/* If we cannot allocate MSIx vectors use only one rx queue */
- netdev_info(adapter->netdev,
- "Failed to enable MSI-X, error %d . Limiting #rx queues to 1, try MSI.\n",
- err);
+ dev_info(&adapter->pdev->dev,
+ "Failed to enable MSI-X, error %d. "
+ "Limiting #rx queues to 1, try MSI.\n", err);
adapter->intr.type = VMXNET3_IT_MSI;
}
--
1.7.10.4
^ permalink raw reply related
* [PATCH 02/10] vmxnet3: remove unnecessary bookkeeping
From: Stephen Hemminger @ 2013-01-15 17:28 UTC (permalink / raw)
To: David Miller, Shreyas Bhatewara; +Cc: pv-drivers, netdev, Stephen Hemminger
In-Reply-To: <1358270915-32758-1-git-send-email-stephen@networkplumber.org>
The uncommitted[] array was set but never used except in a debug
message. Remove it.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
---
drivers/net/vmxnet3/vmxnet3_drv.c | 9 ++-------
drivers/net/vmxnet3/vmxnet3_int.h | 2 --
2 files changed, 2 insertions(+), 9 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 3402a0c..99ef9ed 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -628,12 +628,10 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx,
num_allocated++;
vmxnet3_cmd_ring_adv_next2fill(ring);
}
- rq->uncommitted[ring_idx] += num_allocated;
dev_dbg(&adapter->netdev->dev,
- "alloc_rx_buf: %d allocated, next2fill %u, next2comp "
- "%u, uncommitted %u\n", num_allocated, ring->next2fill,
- ring->next2comp, rq->uncommitted[ring_idx]);
+ "alloc_rx_buf: %d allocated, next2fill %u, next2comp %u\n",
+ num_allocated, ring->next2fill, ring->next2comp);
/* so that the device can distinguish a full ring and an empty ring */
BUG_ON(num_allocated != 0 && ring->next2fill == ring->next2comp);
@@ -1331,7 +1329,6 @@ rcd_done:
VMXNET3_WRITE_BAR0_REG(adapter,
rxprod_reg[ring_idx] + rq->qid * 8,
ring->next2fill);
- rq->uncommitted[ring_idx] = 0;
}
vmxnet3_comp_ring_adv_next2proc(&rq->comp_ring);
@@ -1376,7 +1373,6 @@ vmxnet3_rq_cleanup(struct vmxnet3_rx_queue *rq,
rq->rx_ring[ring_idx].gen = VMXNET3_INIT_GEN;
rq->rx_ring[ring_idx].next2fill =
rq->rx_ring[ring_idx].next2comp = 0;
- rq->uncommitted[ring_idx] = 0;
}
rq->comp_ring.gen = VMXNET3_INIT_GEN;
@@ -1457,7 +1453,6 @@ vmxnet3_rq_init(struct vmxnet3_rx_queue *rq,
/* reset internal state and allocate buffers for both rings */
for (i = 0; i < 2; i++) {
rq->rx_ring[i].next2fill = rq->rx_ring[i].next2comp = 0;
- rq->uncommitted[i] = 0;
memset(rq->rx_ring[i].base, 0, rq->rx_ring[i].size *
sizeof(struct Vmxnet3_RxDesc));
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index fc46a81..55465ed 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -276,8 +276,6 @@ struct vmxnet3_rx_queue {
struct vmxnet3_rx_ctx rx_ctx;
u32 qid; /* rqID in RCD for buffer from 1st ring */
u32 qid2; /* rqID in RCD for buffer from 2nd ring */
- u32 uncommitted[2]; /* # of buffers allocated since last RXPROD
- * update */
struct vmxnet3_rx_buf_info *buf_info[2];
struct Vmxnet3_RxQueueCtrl *shared;
struct vmxnet3_rq_driver_stats stats;
--
1.7.10.4
^ permalink raw reply related
* [PATCH 01/10] vmxnet3: use netdev_alloc_skb_ip_align
From: Stephen Hemminger @ 2013-01-15 17:28 UTC (permalink / raw)
To: David Miller, Shreyas Bhatewara; +Cc: pv-drivers, netdev, Stephen Hemminger
In-Reply-To: <1358270915-32758-1-git-send-email-stephen@networkplumber.org>
Use netdev_alloc_skb_align, rather than open code using dev_alloc_skb.
Change allocation at startup to use GFP_KERNEL.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
---
drivers/net/vmxnet3/vmxnet3_drv.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index dc8913c..3402a0c 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -580,15 +580,14 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx,
if (rbi->buf_type == VMXNET3_RX_BUF_SKB) {
if (rbi->skb == NULL) {
- rbi->skb = dev_alloc_skb(rbi->len +
- NET_IP_ALIGN);
+ rbi->skb = __netdev_alloc_skb_ip_align(adapter->netdev,
+ rbi->len,
+ GFP_KERNEL);
if (unlikely(rbi->skb == NULL)) {
rq->stats.rx_buf_alloc_failure++;
break;
}
- rbi->skb->dev = adapter->netdev;
- skb_reserve(rbi->skb, NET_IP_ALIGN);
rbi->dma_addr = pci_map_single(adapter->pdev,
rbi->skb->data, rbi->len,
PCI_DMA_FROMDEVICE);
@@ -1221,7 +1220,8 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
skip_page_frags = false;
ctx->skb = rbi->skb;
- new_skb = dev_alloc_skb(rbi->len + NET_IP_ALIGN);
+ new_skb = netdev_alloc_skb_ip_align(adapter->netdev,
+ rbi->len);
if (new_skb == NULL) {
/* Skb allocation failed, do not handover this
* skb to stack. Reuse it. Drop the existing pkt
@@ -1239,8 +1239,6 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
skb_put(ctx->skb, rcd->len);
/* Immediate refill */
- new_skb->dev = adapter->netdev;
- skb_reserve(new_skb, NET_IP_ALIGN);
rbi->skb = new_skb;
rbi->dma_addr = pci_map_single(adapter->pdev,
rbi->skb->data, rbi->len,
--
1.7.10.4
^ permalink raw reply related
* [PATCH 00/10] vmxnet3: patches
From: Stephen Hemminger @ 2013-01-15 17:28 UTC (permalink / raw)
To: David Miller, Shreyas Bhatewara; +Cc: pv-drivers, netdev, Stephen Hemminger
Minor VMXNET3 cleanup found while reviewing driver.
Stephen Hemminger (10):
vmxnet3: use netdev_alloc_skb_ip_align
vmxnet3: remove unnecessary bookkeeping
vmxnet3: fix messages printed before registration
vmxnet3: use netdev_dbg
vmxnet3: use netdev_ printk wrappers
vmxnet3: remove VMXNET3_MAX_DEVICES
vmxnet3: remove device counter
vmxnet3: remove unused irq_share_mode
vmxnet3: use static RSS key
vmxnet3: better RSS support
drivers/net/vmxnet3/vmxnet3_drv.c | 227 ++++++++++++++++-----------------
drivers/net/vmxnet3/vmxnet3_ethtool.c | 13 +-
drivers/net/vmxnet3/vmxnet3_int.h | 3 -
3 files changed, 118 insertions(+), 125 deletions(-)
--
1.7.10.4
^ permalink raw reply
* [net-next PATCH] net: increase fragment memory usage limits
From: Jesper Dangaard Brouer @ 2013-01-15 17:16 UTC (permalink / raw)
To: netdev; +Cc: Jesper Dangaard Brouer, Eric Dumazet, David S. Miller
Increase the amount of memory usage limits for incomplete
IP fragments.
Arguing for new thresh high/low values:
High threshold = 4 MBytes
Low threshold = 3 MBytes
The fragmentation memory accounting code, tries to account for the
real memory usage, by measuring both the size of frag queue struct
(inet_frag_queue (ipv4:ipq/ipv6:frag_queue)) and the SKB's truesize.
We want to be able to handle/hold-on-to enough fragments, to ensure
good performance, without causing incomplete fragments to hurt
scalability, by causing the number of inet_frag_queue to grow too much
(resulting longer searches for frag queues).
For IPv4, how much memory does the largest frag consume.
Maximum size fragment is 64K, which is approx 44 fragments with
MTU(1500) sized packets. Sizeof(struct ipq) is 200. A 1500 byte
packet results in a truesize of 2944 (not 2048 as I first assumed)
(44*2944)+200 = 129736 bytes
The current default high thresh of 262144 bytes, is obviously
problematic, as only two 64K fragments can fit in the queue at the
same time.
How many 64K fragment can we fit into 4 MBytes:
4*2^20/((44*2944)+200) = 32.34 fragment in queues
An attacker could send a separate/distinct fake fragment packets per
queue, causing us to allocate one inet_frag_queue per packet, and thus
attacking the hash table and its lists.
How many frag queue do we need to store, and given a current hash size
of 64, what is the average list length.
Using one MTU sized fragment per inet_frag_queue, each consuming
(2944+200) 3144 bytes.
4*2^20/(2944+200) = 1334 frag queues -> 21 avg list length
An attack could send small fragments, the smallest packet I could send
resulted in a truesize of 896 bytes (I'm a little surprised by this).
4*2^20/(896+200) = 3827 frag queues -> 59 avg list length
When increasing these number, we also need to followup with
improvements, that is going to help scalability. Simply increasing
the hash size, is not enough as the current implementation does not
have a per hash bucket locking.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
include/net/ipv6.h | 4 ++--
net/ipv4/ip_fragment.c | 22 +++++++++++++++-------
2 files changed, 17 insertions(+), 9 deletions(-)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index ed67208..e6e65fb 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -292,8 +292,8 @@ static inline int ip6_frag_mem(struct net *net)
}
#endif
-#define IPV6_FRAG_HIGH_THRESH (256 * 1024) /* 262144 */
-#define IPV6_FRAG_LOW_THRESH (192 * 1024) /* 196608 */
+#define IPV6_FRAG_HIGH_THRESH (4 * 1024*1024) /* 4194304 */
+#define IPV6_FRAG_LOW_THRESH (3 * 1024*1024) /* 3145728 */
#define IPV6_FRAG_TIMEOUT (60 * HZ) /* 60 seconds */
extern int __ipv6_addr_type(const struct in6_addr *addr);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index eb9d63a..f55a4e6 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -851,14 +851,22 @@ static inline void ip4_frags_ctl_register(void)
static int __net_init ipv4_frags_init_net(struct net *net)
{
- /*
- * Fragment cache limits. We will commit 256K at one time. Should we
- * cross that limit we will prune down to 192K. This should cope with
- * even the most extreme cases without allowing an attacker to
- * measurably harm machine performance.
+ /* Fragment cache limits.
+ *
+ * The fragment memory accounting code, (tries to) account for
+ * the real memory usage, by measuring both the size of frag
+ * queue struct (inet_frag_queue (ipv4:ipq/ipv6:frag_queue))
+ * and the SKB's truesize.
+ *
+ * A 64K fragment consumes 129736 bytes (44*2944)+200
+ * (1500 truesize == 2944, sizeof(struct ipq) == 200)
+ *
+ * We will commit 4MB at one time. Should we cross that limit
+ * we will prune down to 3MB, making room for approx 8 big 64K
+ * fragments 8x128k.
*/
- net->ipv4.frags.high_thresh = 256 * 1024;
- net->ipv4.frags.low_thresh = 192 * 1024;
+ net->ipv4.frags.high_thresh = 4 * 1024 * 1024;
+ net->ipv4.frags.low_thresh = 3 * 1024 * 1024;
/*
* Important NOTE! Fragment queue must be destroyed before MSL expires.
* RFC791 is wrong proposing to prolongate timer each fragment arrival
^ permalink raw reply related
* RE: per route MTU settings
From: Lukas Tribus @ 2013-01-15 17:07 UTC (permalink / raw)
To: pupilla, steffen.klassert; +Cc: netdev
Hi pupilla,
looks like the behavior changed with 3.2-rc5 and "[PATCH 5/5] ipv4:
Don't use the cached pmtu informations for input routes" ([1], [2]).
Actually, a "mtu lock XYZ" applied to a route is a bit of a corner case.
Steffen, you already made this statement once and I can only agree with you:
> The router that can't send the packet to the next hop network has to
> send the ICMP Destination Unreachable message. We never propagated
> learned PMTU informations and I would not like to change this
But here is our issue:
- the linux "ip_forwarder" has an MTU of 1500 Byte on relevant interfaces
- there is a route with a "static" mtu lock at 1200 Byte
- the box is supposed to forward a packet heading the 1200B MTU route
What happens is:
- the packet is dropped (because it exceeds the 1200 Byte)
- an ICMP Type 3 Code 4 message is generated with 576 Byte next-hop MTU
Notice that the 576 Byte indicated as next-hop MTU in the ICMP packet
doesn't match neither outgoing interface MTU, nor the static route's MTU.
Prior to your patch (for example in 3.2-rc4), 1200 Byte was indicated as
MTU in the ICMP packet.
root@ubuntuvm:~# cat /proc/version
Linux version 3.2.0-030200rc5-generic (root@gomeisa) (gcc version 4.4.3 (Ubuntu 4.4.3-4ubuntu5) ) #201112091935 SMP Sat Dec 10 00:36:07 UTC 2011
root@ubuntuvm:~# echo 1> /proc/sys/net/ipv4/ip_forward
root@ubuntuvm:~# echo 0> /proc/sys/net/ipv4/conf/eth0/send_redirects
root@ubuntuvm:~# ip route add 8.8.8.8/32 via 10.0.0.254 mtu lock 1200
root@ubuntuvm:~# ip r
default via 10.0.0.254 dev eth0 metric 100
8.8.8.8 via 10.0.0.254 dev eth0 mtu lock 1200
10.0.0.0/24 dev eth0 proto kernel scope link src 10.0.0.55
root@ubuntuvm:~# tcpdump -nvvv icmp -i eth0
tcpdump: listening on eth0, link-type EN10MB (Ethernet), capture size 65535 bytes
01:49:20.193798 IP (tos 0x0, ttl 128, id 12090, offset 0, flags [DF], proto ICMP (1), length 1428)
10.0.0.3> 8.8.8.8: ICMP echo request, id 1, seq 4150, length 1408
01:49:20.193847 IP (tos 0xc0, ttl 64, id 15646, offset 0, flags [none], proto ICMP (1), length 576)
10.0.0.55> 10.0.0.3: ICMP 8.8.8.8 unreachable - need to frag (mtu 576), length 556
IP (tos 0x0, ttl 128, id 12090, offset 0, flags [DF], proto ICMP (1), length 1428)
10.0.0.3> 8.8.8.8: ICMP echo request, id 1, seq 4150, length 1408
^C
2 packets captured
2 packets received by filter
0 packets dropped by kernel
Now, what is the kernel supposed to do in this case?
In my opinion either act like <3.2-rc4 and return 1200 Byte in the ICMP
error message or forward the packet anyway (we have the necessary interface
MTU to do it), ignoring the route with "mtu lock".
Steffen, could you share your opinion about this?
Its probably a good idea to avoid "mtu lock" on routes completely though.
Regards,
Lukas
[1] http://git.kernel.org/?p=linux/kernel/git/davem/net-next.git;a=commit;h=261663b0ee2ee8e3947f4c11c1a08be18cd2cea1
[2] http://patchwork.ozlabs.org/patch/127288/
^ permalink raw reply
* Re: [PATCH V4 3/3] tuntap: allow polling/writing/reading when detached
From: Michael S. Tsirkin @ 2013-01-15 16:48 UTC (permalink / raw)
To: Jason Wang; +Cc: davem, netdev, linux-kernel
In-Reply-To: <1358245726-16250-4-git-send-email-jasowang@redhat.com>
On Tue, Jan 15, 2013 at 06:28:46PM +0800, Jason Wang wrote:
> We forbid polling, writing and reading when the file were detached, this may
> complex the user in several cases:
>
> - when guest pass some buffers to vhost/qemu and then disable some queues,
> vhost/qemu needs to to its own cleanup which is complex. We can do this simply
> by allowing a user can still write to an disabled queue to handle this. And
> user can still do read but just nothing returned.
> - align the polling behavior with macvtap which never fails when the queue is
> created. this can simplify the polling errors handling of its user (e.g vhost)
>
> Signed-off-by: Jason Wang <jasowang@redhat.com>
> ---
> drivers/net/tun.c | 18 +++++++++++-------
> 1 files changed, 11 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/net/tun.c b/drivers/net/tun.c
> index af372d0..eb68937 100644
> --- a/drivers/net/tun.c
> +++ b/drivers/net/tun.c
> @@ -307,7 +307,7 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash,
>
> rcu_read_lock();
>
> - if (tun->numqueues == 1)
> + if (tun->numqueues == 1 || queue_index >= tun->numqueues)
> goto unlock;
>
> e = tun_flow_find(head, rxhash);
Hmm I don't understand - does something ensure that queue_index is >
numqueues if the queue is disabled?
Can we check tun->disabled and skip tun_flow_update completely?
We might need to switch to rcu_assign for tun->disabled for this
but otherwise it looks easy.
> @@ -406,21 +406,21 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
>
> tun = rtnl_dereference(tfile->tun);
>
> - if (tun) {
> + if (tun && !tfile->detached) {
> u16 index = tfile->queue_index;
> BUG_ON(index >= tun->numqueues);
> dev = tun->dev;
>
> rcu_assign_pointer(tun->tfiles[index],
> tun->tfiles[tun->numqueues - 1]);
> - rcu_assign_pointer(tfile->tun, NULL);
> ntfile = rtnl_dereference(tun->tfiles[index]);
> ntfile->queue_index = index;
>
> --tun->numqueues;
> - if (clean)
> + if (clean) {
> + rcu_assign_pointer(tfile->tun, NULL);
> sock_put(&tfile->sk);
> - else
> + } else
> tun_disable_queue(tun, tfile);
>
> synchronize_net();
> @@ -465,6 +465,10 @@ static void tun_detach_all(struct net_device *dev)
> rcu_assign_pointer(tfile->tun, NULL);
> --tun->numqueues;
> }
> + list_for_each_entry(tfile, &tun->disabled, next) {
> + wake_up_all(&tfile->wq.wait);
> + rcu_assign_pointer(tfile->tun, NULL);
> + }
> BUG_ON(tun->numqueues != 0);
>
> synchronize_net();
> @@ -491,7 +495,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file)
> int err;
>
> err = -EINVAL;
> - if (rtnl_dereference(tfile->tun))
> + if (rtnl_dereference(tfile->tun) && !tfile->detached)
> goto out;
>
> err = -EBUSY;
> @@ -1795,7 +1799,7 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr)
> ret = tun_attach(tun, file);
> } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
> tun = rtnl_dereference(tfile->tun);
> - if (!tun || !(tun->flags & TUN_TAP_MQ))
> + if (!tun || !(tun->flags & TUN_TAP_MQ) || tfile->detached)
> ret = -EINVAL;
> else
> __tun_detach(tfile, false);
> --
> 1.7.1
^ permalink raw reply
* [RFC(v2) net-next 13/13] ipv6: Complete neighbour entry removal from dst_entry.
From: YOSHIFUJI Hideaki @ 2013-01-15 16:46 UTC (permalink / raw)
To: netdev; +Cc: yoshfuji, xiyou.wangcong
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
---
include/net/ip6_fib.h | 2 --
net/ipv6/route.c | 68 +++--------------------------------------------
net/ipv6/xfrm6_policy.c | 1 -
3 files changed, 3 insertions(+), 68 deletions(-)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index fdc48a9..6919a50 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -89,8 +89,6 @@ struct fib6_table;
struct rt6_info {
struct dst_entry dst;
- struct neighbour *n;
-
/*
* Tail elements of dst_entry (__refcnt etc.)
* and these elements (rarely used in hot path) are in
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9605658..e30177a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -151,19 +151,6 @@ static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst,
return neigh_create(&nd_tbl, daddr, dst->dev);
}
-static int rt6_bind_neighbour(struct rt6_info *rt, struct net_device *dev)
-{
- struct neighbour *n = __ipv6_neigh_lookup(dev, &rt->rt6i_gateway);
- if (!n) {
- n = neigh_create(&nd_tbl, &rt->rt6i_gateway, dev);
- if (IS_ERR(n))
- return PTR_ERR(n);
- }
- rt->n = n;
-
- return 0;
-}
-
static struct dst_ops ip6_dst_ops_template = {
.family = AF_INET6,
.protocol = cpu_to_be16(ETH_P_IPV6),
@@ -301,9 +288,6 @@ static void ip6_dst_destroy(struct dst_entry *dst)
struct rt6_info *rt = (struct rt6_info *)dst;
struct inet6_dev *idev = rt->rt6i_idev;
- if (rt->n)
- neigh_release(rt->n);
-
if (!(rt->dst.flags & DST_HOST))
dst_destroy_metrics_generic(dst);
@@ -354,11 +338,13 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
in6_dev_put(idev);
}
}
+#if 0
if (rt->n && rt->n->dev == dev) {
rt->n->dev = loopback_dev;
dev_hold(loopback_dev);
dev_put(dev);
}
+#endif
}
}
@@ -846,8 +832,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
rt = ip6_rt_copy(ort, daddr);
if (rt) {
- int attempts = !in_softirq();
-
if (!(rt->rt6i_flags & RTF_GATEWAY)) {
if (ort->rt6i_dst.plen != 128 &&
ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
@@ -863,32 +847,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
rt->rt6i_src.plen = 128;
}
#endif
-
- retry:
- if (rt6_bind_neighbour(rt, rt->dst.dev)) {
- struct net *net = dev_net(rt->dst.dev);
- int saved_rt_min_interval =
- net->ipv6.sysctl.ip6_rt_gc_min_interval;
- int saved_rt_elasticity =
- net->ipv6.sysctl.ip6_rt_gc_elasticity;
-
- if (attempts-- > 0) {
- net->ipv6.sysctl.ip6_rt_gc_elasticity = 1;
- net->ipv6.sysctl.ip6_rt_gc_min_interval = 0;
-
- ip6_dst_gc(&net->ipv6.ip6_dst_ops);
-
- net->ipv6.sysctl.ip6_rt_gc_elasticity =
- saved_rt_elasticity;
- net->ipv6.sysctl.ip6_rt_gc_min_interval =
- saved_rt_min_interval;
- goto retry;
- }
-
- net_warn_ratelimited("Neighbour table overflow\n");
- dst_free(&rt->dst);
- return NULL;
- }
}
return rt;
@@ -899,10 +857,8 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort,
{
struct rt6_info *rt = ip6_rt_copy(ort, daddr);
- if (rt) {
+ if (rt)
rt->rt6i_flags |= RTF_CACHE;
- rt->n = neigh_clone(ort->n);
- }
return rt;
}
@@ -937,7 +893,6 @@ restart:
read_unlock_bh(&table->tb6_lock);
if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY))) {
- BUG_ON(rt->n != NULL);
nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
} else if (!(rt->dst.flags & DST_HOST))
nrt = rt6_alloc_clone(rt, &fl6->daddr);
@@ -1499,12 +1454,6 @@ int ip6_route_add(struct fib6_config *cfg)
} else
rt->rt6i_prefsrc.plen = 0;
- if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) {
- err = rt6_bind_neighbour(rt, dev);
- if (err)
- goto out;
- }
-
rt->rt6i_flags = cfg->fc_flags;
install_route:
@@ -1691,11 +1640,6 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
if (!neigh)
return;
- /* Duplicate redirect: silently ignore. */
- old_neigh = rt->n;
- if (neigh == old_neigh)
- goto out;
-
/*
* We have finally decided to accept it.
*/
@@ -1716,7 +1660,6 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
nrt->rt6i_flags &= ~RTF_GATEWAY;
nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
- nrt->n = neigh_clone(neigh);
if (ip6_ins_rt(nrt))
goto out;
@@ -2049,11 +1992,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
rt->rt6i_flags |= RTF_ANYCAST;
else
rt->rt6i_flags |= RTF_LOCAL;
- err = rt6_bind_neighbour(rt, rt->dst.dev);
- if (err) {
- dst_free(&rt->dst);
- return ERR_PTR(err);
- }
rt->rt6i_dst.addr = *addr;
rt->rt6i_dst.plen = 128;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index c984413..1282737 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -110,7 +110,6 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
/* Sheit... I remember I did this right. Apparently,
* it was magically lost, so this code needs audit */
- xdst->u.rt6.n = neigh_clone(rt->n);
xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST |
RTF_LOCAL);
xdst->u.rt6.rt6i_metric = rt->rt6i_metric;
--
1.7.9.5
^ permalink raw reply related
* [RFC(v2) net-next 12/13] ipv6: Remove temporary dst for icmpv6.
From: YOSHIFUJI Hideaki @ 2013-01-15 16:46 UTC (permalink / raw)
To: netdev; +Cc: yoshfuji, xiyou.wangcong
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
---
net/ipv6/ip6_fib.c | 2 +-
net/ipv6/route.c | 98 ----------------------------------------------------
2 files changed, 1 insertion(+), 99 deletions(-)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 710cafd..1d7c448 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1643,7 +1643,7 @@ void fib6_run_gc(unsigned long expires, struct net *net)
gc_args.timeout = net->ipv6.sysctl.ip6_rt_gc_interval;
}
- gc_args.more = icmp6_dst_gc();
+ gc_args.more = 0;
fib6_clean_all(net, fib6_age, 0, NULL);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e30a2aa..9605658 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1252,103 +1252,6 @@ static unsigned int ip6_mtu(const struct dst_entry *dst)
return mtu;
}
-static struct dst_entry *icmp6_dst_gc_list;
-static DEFINE_SPINLOCK(icmp6_dst_lock);
-
-struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
- struct neighbour *neigh,
- struct flowi6 *fl6)
-{
- struct dst_entry *dst;
- struct rt6_info *rt;
- struct inet6_dev *idev = in6_dev_get(dev);
- struct net *net = dev_net(dev);
-
- if (unlikely(!idev))
- return ERR_PTR(-ENODEV);
-
- rt = ip6_dst_alloc(net, dev, 0, NULL);
- if (unlikely(!rt)) {
- in6_dev_put(idev);
- dst = ERR_PTR(-ENOMEM);
- goto out;
- }
-
- if (neigh)
- neigh_hold(neigh);
- else {
- neigh = ip6_neigh_lookup(&rt->dst, NULL, &fl6->daddr);
- if (IS_ERR(neigh)) {
- in6_dev_put(idev);
- dst_free(&rt->dst);
- return ERR_CAST(neigh);
- }
- }
-
- rt->dst.flags |= DST_HOST;
- rt->dst.output = ip6_output;
- rt->n = neigh;
- atomic_set(&rt->dst.__refcnt, 1);
- rt->rt6i_dst.addr = fl6->daddr;
- rt->rt6i_dst.plen = 128;
- rt->rt6i_idev = idev;
- dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 0);
-
- spin_lock_bh(&icmp6_dst_lock);
- rt->dst.next = icmp6_dst_gc_list;
- icmp6_dst_gc_list = &rt->dst;
- spin_unlock_bh(&icmp6_dst_lock);
-
- fib6_force_start_gc(net);
-
- dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0);
-
-out:
- return dst;
-}
-
-int icmp6_dst_gc(void)
-{
- struct dst_entry *dst, **pprev;
- int more = 0;
-
- spin_lock_bh(&icmp6_dst_lock);
- pprev = &icmp6_dst_gc_list;
-
- while ((dst = *pprev) != NULL) {
- if (!atomic_read(&dst->__refcnt)) {
- *pprev = dst->next;
- dst_free(dst);
- } else {
- pprev = &dst->next;
- ++more;
- }
- }
-
- spin_unlock_bh(&icmp6_dst_lock);
-
- return more;
-}
-
-static void icmp6_clean_all(int (*func)(struct rt6_info *rt, void *arg),
- void *arg)
-{
- struct dst_entry *dst, **pprev;
-
- spin_lock_bh(&icmp6_dst_lock);
- pprev = &icmp6_dst_gc_list;
- while ((dst = *pprev) != NULL) {
- struct rt6_info *rt = (struct rt6_info *) dst;
- if (func(rt, arg)) {
- *pprev = dst->next;
- dst_free(dst);
- } else {
- pprev = &dst->next;
- }
- }
- spin_unlock_bh(&icmp6_dst_lock);
-}
-
static int ip6_dst_gc(struct dst_ops *ops)
{
unsigned long now = jiffies;
@@ -2235,7 +2138,6 @@ void rt6_ifdown(struct net *net, struct net_device *dev)
};
fib6_clean_all(net, fib6_ifdown, 0, &adn);
- icmp6_clean_all(fib6_ifdown, &adn);
}
struct rt6_mtu_change_arg {
--
1.7.9.5
^ permalink raw reply related
* [RFC(v2) net-next 11/13] ipv6: Use ip6_route_output() instead of icmp6_dst_alloc().
From: YOSHIFUJI Hideaki @ 2013-01-15 16:46 UTC (permalink / raw)
To: netdev; +Cc: yoshfuji, xiyou.wangcong
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
---
net/ipv6/mcast.c | 5 ++---
net/ipv6/ndisc.c | 3 ++-
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 8237ee1..e041c39 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1391,9 +1391,8 @@ static void mld_sendpack(struct sk_buff *skb)
icmpv6_flow_init(net->ipv6.igmp_sk, &fl6, ICMPV6_MLD2_REPORT,
&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
skb->dev->ifindex);
- dst = icmp6_dst_alloc(skb->dev, NULL, &fl6);
-
err = 0;
+ dst = ip6_route_output(net, net->ipv6.igmp_sk, &fl6);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
dst = NULL;
@@ -1759,7 +1758,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
icmpv6_flow_init(sk, &fl6, type,
&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
skb->dev->ifindex);
- dst = icmp6_dst_alloc(skb->dev, NULL, &fl6);
+ dst = ip6_route_output(net, sk, &fl6);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto err_out;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 5733cd2..f19fe55 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -448,7 +448,8 @@ static void ndisc_send_skb(struct sk_buff *skb, struct net_device *dev,
type = icmp6h->icmp6_type;
icmpv6_flow_init(sk, &fl6, type, saddr, daddr, dev->ifindex);
- dst = icmp6_dst_alloc(dev, neigh, &fl6);
+
+ dst = ip6_route_output(net, sk, &fl6);
if (IS_ERR(dst)) {
kfree_skb(skb);
return;
--
1.7.9.5
^ permalink raw reply related
* [RFC(v2) net-next 10/13] ipv6: Do not depend on rt->n in ip6_pol_route().
From: YOSHIFUJI Hideaki @ 2013-01-15 16:46 UTC (permalink / raw)
To: netdev; +Cc: yoshfuji, xiyou.wangcong
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
---
net/ipv6/route.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ffdc8a6..e30a2aa 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -936,9 +936,10 @@ restart:
dst_hold(&rt->dst);
read_unlock_bh(&table->tb6_lock);
- if (!rt->n && !(rt->rt6i_flags & RTF_NONEXTHOP))
+ if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY))) {
+ BUG_ON(rt->n != NULL);
nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
- else if (!(rt->dst.flags & DST_HOST))
+ } else if (!(rt->dst.flags & DST_HOST))
nrt = rt6_alloc_clone(rt, &fl6->daddr);
else
goto out2;
--
1.7.9.5
^ permalink raw reply related
* [RFC(v2) net-next 09/13] ipv6: Do not depend on rt->n in rt6_check_neigh().
From: YOSHIFUJI Hideaki @ 2013-01-15 16:46 UTC (permalink / raw)
To: netdev; +Cc: yoshfuji, xiyou.wangcong
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
---
net/ipv6/route.c | 15 ++++++++++-----
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e16a483..ffdc8a6 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -552,20 +552,25 @@ static inline bool rt6_check_neigh(struct rt6_info *rt)
struct neighbour *neigh;
bool ret = false;
- neigh = rt->n;
if (rt->rt6i_flags & RTF_NONEXTHOP ||
- !(rt->rt6i_flags & RTF_GATEWAY))
+ !(rt->rt6i_flags & RTF_GATEWAY)) {
ret = true;
- else if (neigh) {
- read_lock_bh(&neigh->lock);
+ goto out;
+ }
+ rcu_read_lock_bh();
+ neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
+ if (neigh) {
+ read_lock(&neigh->lock);
if (neigh->nud_state & NUD_VALID)
ret = true;
#ifdef CONFIG_IPV6_ROUTER_PREF
else if (!(neigh->nud_state & NUD_FAILED))
ret = true;
#endif
- read_unlock_bh(&neigh->lock);
+ read_unlock(&neigh->lock);
}
+ rcu_read_unlock_bh();
+out:
return ret;
}
--
1.7.9.5
^ permalink raw reply related
* [RFC(v2) net-next 08/13] ipv6: Do not deoend on rt->n in ip6_dst_lookup_tail().
From: YOSHIFUJI Hideaki @ 2013-01-15 16:46 UTC (permalink / raw)
To: netdev; +Cc: yoshfuji, xiyou.wangcong
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
---
net/ipv6/ip6_output.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 9fc5d1d..b2fe048 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -921,8 +921,12 @@ static int ip6_dst_lookup_tail(struct sock *sk,
* dst entry of the nexthop router
*/
rt = (struct rt6_info *) *dst;
- n = rt->n;
- if (n && !(n->nud_state & NUD_VALID)) {
+ rcu_read_lock_bh();
+ n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr));
+ err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
+ rcu_read_unlock_bh();
+
+ if (err) {
struct inet6_ifaddr *ifp;
struct flowi6 fl_gw6;
int redirect;
--
1.7.9.5
^ permalink raw reply related
* [RFC(v2) net-next 07/13] ipv6: Do not repend on rt->n in rt6_probe().
From: YOSHIFUJI Hideaki @ 2013-01-15 16:45 UTC (permalink / raw)
To: netdev; +Cc: yoshfuji, xiyou.wangcong
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
---
net/ipv6/route.c | 26 ++++++++++++++++----------
1 file changed, 16 insertions(+), 10 deletions(-)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d82eb1f..e16a483 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -498,28 +498,34 @@ static void rt6_probe(struct rt6_info *rt)
* Router Reachability Probe MUST be rate-limited
* to no more than one per minute.
*/
- neigh = rt ? rt->n : NULL;
- if (!neigh)
- return;
- write_lock_bh(&neigh->lock);
- if (neigh->nud_state & NUD_VALID) {
- write_unlock_bh(&neigh->lock);
+ if (!rt || !(rt->rt6i_flags & RTF_GATEWAY))
return;
+ rcu_read_lock_bh();
+ neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
+ if (neigh) {
+ write_lock(&neigh->lock);
+ if (neigh->nud_state & NUD_VALID)
+ goto out;
}
- if (!(neigh->nud_state & NUD_VALID) &&
+
+ if (!neigh ||
time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
struct in6_addr mcaddr;
struct in6_addr *target;
neigh->updated = jiffies;
- write_unlock_bh(&neigh->lock);
- target = (struct in6_addr *)&neigh->primary_key;
+ if (neigh)
+ write_unlock(&neigh->lock);
+
+ target = (struct in6_addr *)&rt->rt6i_gateway;
addrconf_addr_solict_mult(target, &mcaddr);
ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL);
} else {
- write_unlock_bh(&neigh->lock);
+out:
+ write_unlock(&neigh->lock);
}
+ rcu_read_unlock_bh();
}
#else
static inline void rt6_probe(struct rt6_info *rt)
--
1.7.9.5
^ permalink raw reply related
* [RFC(v2) net-next 06/13] ipv6: Do not depend on rt->n in ip6_finish_output2().
From: YOSHIFUJI Hideaki @ 2013-01-15 16:45 UTC (permalink / raw)
To: netdev; +Cc: yoshfuji, xiyou.wangcong
If neigh is not found, create new one.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
---
net/ipv6/ip6_output.c | 18 +++++++++++++-----
1 file changed, 13 insertions(+), 5 deletions(-)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 9250c69..9fc5d1d 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -88,7 +88,8 @@ static int ip6_finish_output2(struct sk_buff *skb)
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
struct neighbour *neigh;
- struct rt6_info *rt;
+ struct in6_addr *nexthop;
+ int ret;
skb->protocol = htons(ETH_P_IPV6);
skb->dev = dev;
@@ -123,10 +124,17 @@ static int ip6_finish_output2(struct sk_buff *skb)
skb->len);
}
- rt = (struct rt6_info *) dst;
- neigh = rt->n;
- if (neigh)
- return dst_neigh_output(dst, neigh, skb);
+ rcu_read_lock_bh();
+ nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
+ neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
+ if (unlikely(!neigh))
+ neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
+ if (neigh) {
+ ret = dst_neigh_output(dst, neigh, skb);
+ rcu_read_unlock_bh();
+ return ret;
+ }
+ rcu_read_unlock_bh();
IP6_INC_STATS_BH(dev_net(dst->dev),
ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
--
1.7.9.5
^ permalink raw reply related
* [RFC(v2) net-next 05/13] ipv6: Introduce rt6_nexthop() to select nexthop address.
From: YOSHIFUJI Hideaki @ 2013-01-15 16:45 UTC (permalink / raw)
To: netdev; +Cc: yoshfuji, xiyou.wangcong
For RTF_GATEWAY route, return rt->rt6i_gateway.
Otherwise, return 2nd argument (destination address).
This will be used for rt->n removal.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
---
include/net/ip6_route.h | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 27d8318..9af6480 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -23,6 +23,7 @@ struct route_info {
#include <net/sock.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
+#include <linux/route.h>
#define RT6_LOOKUP_F_IFACE 0x00000001
#define RT6_LOOKUP_F_REACHABLE 0x00000002
@@ -194,4 +195,12 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
}
+static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, struct in6_addr *dest)
+{
+ BUG_ON(rt == NULL);
+ if (rt->rt6i_flags & RTF_GATEWAY)
+ return &rt->rt6i_gateway;
+ return dest;
+}
+
#endif
--
1.7.9.5
^ permalink raw reply related
* [RFC(v2) net-next 04/13] ipv6 route: Dump gateway based on RTF_GATEWAY flag and rt->rt6i_gateway.
From: YOSHIFUJI Hideaki @ 2013-01-15 16:44 UTC (permalink / raw)
To: netdev; +Cc: yoshfuji, xiyou.wangcong
Do not depend on rt->n.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
---
net/ipv6/route.c | 12 ++++--------
1 file changed, 4 insertions(+), 8 deletions(-)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 5d9ca27..d82eb1f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2484,7 +2484,6 @@ static int rt6_fill_node(struct net *net,
struct nlmsghdr *nlh;
long expires;
u32 table;
- struct neighbour *n;
if (prefix) { /* user wants prefix routes only */
if (!(rt->rt6i_flags & RTF_PREFIX_RT)) {
@@ -2597,9 +2596,8 @@ static int rt6_fill_node(struct net *net,
if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
goto nla_put_failure;
- n = rt->n;
- if (n) {
- if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0)
+ if (rt->rt6i_flags & RTF_GATEWAY) {
+ if (nla_put(skb, RTA_GATEWAY, 16, &rt->rt6i_gateway) < 0)
goto nla_put_failure;
}
@@ -2794,7 +2792,6 @@ struct rt6_proc_arg
static int rt6_info_route(struct rt6_info *rt, void *p_arg)
{
struct seq_file *m = p_arg;
- struct neighbour *n;
seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
@@ -2803,9 +2800,8 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg)
#else
seq_puts(m, "00000000000000000000000000000000 00 ");
#endif
- n = rt->n;
- if (n) {
- seq_printf(m, "%pi6", n->primary_key);
+ if (rt->rt6i_flags & RTF_GATEWAY) {
+ seq_printf(m, "%pi6", &rt->rt6i_gateway);
} else {
seq_puts(m, "00000000000000000000000000000000");
}
--
1.7.9.5
^ permalink raw reply related
* [RFC(v2) net-next 03/13] ndisc: Introduce __ipv6_neigh_lookup_noref().
From: YOSHIFUJI Hideaki @ 2013-01-15 16:44 UTC (permalink / raw)
To: netdev; +Cc: yoshfuji, xiyou.wangcong
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
---
include/net/ndisc.h | 22 +++++++++++++++-------
1 file changed, 15 insertions(+), 7 deletions(-)
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index bbc938e..ec48f42 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -148,14 +148,13 @@ static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, _
(p32[3] * hash_rnd[3]));
}
-static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, const void *pkey)
+static inline struct neighbour *__ipv6_neigh_lookup_noref(struct net_device *dev, const void *pkey)
{
struct neigh_hash_table *nht;
const u32 *p32 = pkey;
struct neighbour *n;
u32 hash_val;
- rcu_read_lock_bh();
nht = rcu_dereference_bh(nd_tbl.nht);
hash_val = ndisc_hashfn(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
@@ -164,12 +163,21 @@ static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, cons
u32 *n32 = (u32 *) n->primary_key;
if (n->dev == dev &&
((n32[0] ^ p32[0]) | (n32[1] ^ p32[1]) |
- (n32[2] ^ p32[2]) | (n32[3] ^ p32[3])) == 0) {
- if (!atomic_inc_not_zero(&n->refcnt))
- n = NULL;
- break;
- }
+ (n32[2] ^ p32[2]) | (n32[3] ^ p32[3])) == 0)
+ return n;
}
+
+ return NULL;
+}
+
+static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, const void *pkey)
+{
+ struct neighbour *n;
+
+ rcu_read_lock_bh();
+ n = __ipv6_neigh_lookup_noref(dev, pkey);
+ if (n && !atomic_inc_not_zero(&n->refcnt))
+ n = NULL;
rcu_read_unlock_bh();
return n;
--
1.7.9.5
^ permalink raw reply related
* [RFC(v2) net-next 02/13] ndisc: Remove tbl argument for __ipv6_neigh_lookup().
From: YOSHIFUJI Hideaki @ 2013-01-15 16:44 UTC (permalink / raw)
To: netdev; +Cc: yoshfuji, xiyou.wangcong
We can refer to nd_tbl directly.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
---
include/net/ndisc.h | 4 ++--
net/ipv6/route.c | 4 ++--
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 23b3a7c..bbc938e 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -148,7 +148,7 @@ static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, _
(p32[3] * hash_rnd[3]));
}
-static inline struct neighbour *__ipv6_neigh_lookup(struct neigh_table *tbl, struct net_device *dev, const void *pkey)
+static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, const void *pkey)
{
struct neigh_hash_table *nht;
const u32 *p32 = pkey;
@@ -156,7 +156,7 @@ static inline struct neighbour *__ipv6_neigh_lookup(struct neigh_table *tbl, str
u32 hash_val;
rcu_read_lock_bh();
- nht = rcu_dereference_bh(tbl->nht);
+ nht = rcu_dereference_bh(nd_tbl.nht);
hash_val = ndisc_hashfn(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
n != NULL;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1341f68..5d9ca27 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -145,7 +145,7 @@ static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst,
struct neighbour *n;
daddr = choose_neigh_daddr(rt, skb, daddr);
- n = __ipv6_neigh_lookup(&nd_tbl, dst->dev, daddr);
+ n = __ipv6_neigh_lookup(dst->dev, daddr);
if (n)
return n;
return neigh_create(&nd_tbl, daddr, dst->dev);
@@ -153,7 +153,7 @@ static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst,
static int rt6_bind_neighbour(struct rt6_info *rt, struct net_device *dev)
{
- struct neighbour *n = __ipv6_neigh_lookup(&nd_tbl, dev, &rt->rt6i_gateway);
+ struct neighbour *n = __ipv6_neigh_lookup(dev, &rt->rt6i_gateway);
if (!n) {
n = neigh_create(&nd_tbl, &rt->rt6i_gateway, dev);
if (IS_ERR(n))
--
1.7.9.5
^ permalink raw reply related
* [RFC(v2) net-next 01/13] ndisc: Refer/Update neigh->updated with write lock.
From: YOSHIFUJI Hideaki @ 2013-01-15 16:44 UTC (permalink / raw)
To: netdev; +Cc: yoshfuji, xiyou.wangcong
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
---
net/ipv6/route.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7c34c01..1341f68 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -499,22 +499,26 @@ static void rt6_probe(struct rt6_info *rt)
* to no more than one per minute.
*/
neigh = rt ? rt->n : NULL;
- if (!neigh || (neigh->nud_state & NUD_VALID))
+ if (!neigh)
+ return;
+ write_lock_bh(&neigh->lock);
+ if (neigh->nud_state & NUD_VALID) {
+ write_unlock_bh(&neigh->lock);
return;
- read_lock_bh(&neigh->lock);
+ }
if (!(neigh->nud_state & NUD_VALID) &&
time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
struct in6_addr mcaddr;
struct in6_addr *target;
neigh->updated = jiffies;
- read_unlock_bh(&neigh->lock);
+ write_unlock_bh(&neigh->lock);
target = (struct in6_addr *)&neigh->primary_key;
addrconf_addr_solict_mult(target, &mcaddr);
ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL);
} else {
- read_unlock_bh(&neigh->lock);
+ write_unlock_bh(&neigh->lock);
}
}
#else
--
1.7.9.5
^ permalink raw reply related
* [RFC(v2) net-next 00/13] IPv6 rt->n removal (V2)
From: YOSHIFUJI Hideaki @ 2013-01-15 16:44 UTC (permalink / raw)
To: netdev; +Cc: yoshfuji, xiyou.wangcong
Hello.
This is RFC (Take 2).
Some unused variable / code still remain.
Need to revisit refcounting (rt->dst.dev, rt->n->dev).
--yoshfuji
YOSHIFUJI Hideaki (13):
ndisc: Refer/Update neigh->updated with write lock.
ndisc: Remove tbl argument for __ipv6_neigh_lookup().
ndisc: Introduce __ipv6_neigh_lookup_noref().
ipv6 route: Dump gateway based on RTF_GATEWAY flag and
rt->rt6i_gateway.
ipv6: Introduce rt6_nexthop() to select nexthop address.
ipv6: Do not depend on rt->n in ip6_finish_output2().
ipv6: Do not repend on rt->n in rt6_probe().
ipv6: Do not deoend on rt->n in ip6_dst_lookup_tail().
ipv6: Do not depend on rt->n in rt6_check_neigh().
ipv6: Do not depend on rt->n in ip6_pol_route().
ipv6: Use ip6_route_output() instead of icmp6_dst_alloc().
ipv6: Remove temporary dst for icmpv6.
ipv6: Complete neighbour entry removal from dst_entry.
include/net/ip6_fib.h | 2 -
include/net/ip6_route.h | 9 ++
include/net/ndisc.h | 24 +++--
net/ipv6/ip6_fib.c | 2 +-
net/ipv6/ip6_output.c | 26 ++++--
net/ipv6/mcast.c | 5 +-
net/ipv6/ndisc.c | 3 +-
net/ipv6/route.c | 222 ++++++++---------------------------------------
net/ipv6/xfrm6_policy.c | 1 -
9 files changed, 86 insertions(+), 208 deletions(-)
--
1.7.9.5
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox