Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
diff --git a/MAINTAINERS b/MAINTAINERS
index 47cc449..34f09e4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1482,9 +1482,10 @@
S: Supported
F: scripts/checkpatch.pl
-CISCO 10G ETHERNET DRIVER
+CISCO VIC ETHERNET NIC DRIVER
M: Scott Feldman <scofeldm@cisco.com>
-M: Joe Eykholt <jeykholt@cisco.com>
+M: Vasanthy Kolluri <vkolluri@cisco.com>
+M: Roopa Prabhu <roprabhu@cisco.com>
S: Supported
F: drivers/net/enic/
diff --git a/drivers/media/dvb/dvb-core/dvb_net.c b/drivers/media/dvb/dvb-core/dvb_net.c
index 441c064..dba1c84 100644
--- a/drivers/media/dvb/dvb-core/dvb_net.c
+++ b/drivers/media/dvb/dvb-core/dvb_net.c
@@ -1140,7 +1140,6 @@
dprintk("%s: allmulti mode\n", dev->name);
priv->rx_mode = RX_MODE_ALL_MULTI;
} else if (!netdev_mc_empty(dev)) {
- int mci;
struct dev_mc_list *mc;
dprintk("%s: set_mc_list, %d entries\n",
@@ -1149,11 +1148,8 @@
priv->rx_mode = RX_MODE_MULTI;
priv->multi_num = 0;
- for (mci = 0, mc=dev->mc_list;
- mci < netdev_mc_count(dev);
- mc = mc->next, mci++) {
+ netdev_for_each_mc_addr(mc, dev)
dvb_set_mc_filter(dev, mc);
- }
}
netif_addr_unlock_bh(dev);
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 0ba5b8e..bf223fb 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -2593,11 +2593,11 @@
will be called ehea.
config ENIC
- tristate "Cisco 10G Ethernet NIC support"
+ tristate "Cisco VIC Ethernet NIC Support"
depends on PCI && INET
select INET_LRO
help
- This enables the support for the Cisco 10G Ethernet card.
+ This enables the support for the Cisco VIC Ethernet card.
config IXGBE
tristate "Intel(R) 10GbE PCI Express adapters support"
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 430c022..cbe9e35 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1480,14 +1480,23 @@
bond_dev->name,
bond_dev->type, slave_dev->type);
- netdev_bonding_change(bond_dev, NETDEV_BONDING_OLDTYPE);
+ res = netdev_bonding_change(bond_dev,
+ NETDEV_PRE_TYPE_CHANGE);
+ res = notifier_to_errno(res);
+ if (res) {
+ pr_err("%s: refused to change device type\n",
+ bond_dev->name);
+ res = -EBUSY;
+ goto err_undo_flags;
+ }
if (slave_dev->type != ARPHRD_ETHER)
bond_setup_by_slave(bond_dev, slave_dev);
else
ether_setup(bond_dev);
- netdev_bonding_change(bond_dev, NETDEV_BONDING_NEWTYPE);
+ netdev_bonding_change(bond_dev,
+ NETDEV_POST_TYPE_CHANGE);
}
} else if (bond_dev->type != slave_dev->type) {
pr_err("%s ether type (%d) is different from other slaves (%d), can not enslave it.\n",
diff --git a/drivers/net/e100.c b/drivers/net/e100.c
index b997e57..c0cd576 100644
--- a/drivers/net/e100.c
+++ b/drivers/net/e100.c
@@ -147,6 +147,8 @@
* - add clean lowlevel I/O emulation for cards with MII-lacking PHYs
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/kernel.h>
@@ -174,7 +176,6 @@
#define DRV_VERSION "3.5.24-k2"DRV_EXT
#define DRV_DESCRIPTION "Intel(R) PRO/100 Network Driver"
#define DRV_COPYRIGHT "Copyright(c) 1999-2006 Intel Corporation"
-#define PFX DRV_NAME ": "
#define E100_WATCHDOG_PERIOD (2 * HZ)
#define E100_NAPI_WEIGHT 16
@@ -200,10 +201,6 @@
MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
MODULE_PARM_DESC(eeprom_bad_csum_allow, "Allow bad eeprom checksums");
MODULE_PARM_DESC(use_io, "Force use of i/o access mode");
-#define DPRINTK(nlevel, klevel, fmt, args...) \
- (void)((NETIF_MSG_##nlevel & nic->msg_enable) && \
- printk(KERN_##klevel PFX "%s: %s: " fmt, nic->netdev->name, \
- __func__ , ## args))
#define INTEL_8255X_ETHERNET_DEVICE(device_id, ich) {\
PCI_VENDOR_ID_INTEL, device_id, PCI_ANY_ID, PCI_ANY_ID, \
@@ -689,12 +686,13 @@
/* Check results of self-test */
if (nic->mem->selftest.result != 0) {
- DPRINTK(HW, ERR, "Self-test failed: result=0x%08X\n",
- nic->mem->selftest.result);
+ netif_err(nic, hw, nic->netdev,
+ "Self-test failed: result=0x%08X\n",
+ nic->mem->selftest.result);
return -ETIMEDOUT;
}
if (nic->mem->selftest.signature == 0) {
- DPRINTK(HW, ERR, "Self-test failed: timed out\n");
+ netif_err(nic, hw, nic->netdev, "Self-test failed: timed out\n");
return -ETIMEDOUT;
}
@@ -797,7 +795,7 @@
/* The checksum, stored in the last word, is calculated such that
* the sum of words should be 0xBABA */
if (cpu_to_le16(0xBABA - checksum) != nic->eeprom[nic->eeprom_wc - 1]) {
- DPRINTK(PROBE, ERR, "EEPROM corrupted\n");
+ netif_err(nic, probe, nic->netdev, "EEPROM corrupted\n");
if (!eeprom_bad_csum_allow)
return -EAGAIN;
}
@@ -953,8 +951,7 @@
udelay(20);
}
if (unlikely(!i)) {
- printk("e100.mdio_ctrl(%s) won't go Ready\n",
- nic->netdev->name );
+ netdev_err(nic->netdev, "e100.mdio_ctrl won't go Ready\n");
spin_unlock_irqrestore(&nic->mdio_lock, flags);
return 0; /* No way to indicate timeout error */
}
@@ -966,9 +963,10 @@
break;
}
spin_unlock_irqrestore(&nic->mdio_lock, flags);
- DPRINTK(HW, DEBUG,
- "%s:addr=%d, reg=%d, data_in=0x%04X, data_out=0x%04X\n",
- dir == mdi_read ? "READ" : "WRITE", addr, reg, data, data_out);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "%s:addr=%d, reg=%d, data_in=0x%04X, data_out=0x%04X\n",
+ dir == mdi_read ? "READ" : "WRITE",
+ addr, reg, data, data_out);
return (u16)data_out;
}
@@ -1028,17 +1026,19 @@
return ADVERTISE_10HALF |
ADVERTISE_10FULL;
default:
- DPRINTK(HW, DEBUG,
- "%s:addr=%d, reg=%d, data=0x%04X: unimplemented emulation!\n",
- dir == mdi_read ? "READ" : "WRITE", addr, reg, data);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "%s:addr=%d, reg=%d, data=0x%04X: unimplemented emulation!\n",
+ dir == mdi_read ? "READ" : "WRITE",
+ addr, reg, data);
return 0xFFFF;
}
} else {
switch (reg) {
default:
- DPRINTK(HW, DEBUG,
- "%s:addr=%d, reg=%d, data=0x%04X: unimplemented emulation!\n",
- dir == mdi_read ? "READ" : "WRITE", addr, reg, data);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "%s:addr=%d, reg=%d, data=0x%04X: unimplemented emulation!\n",
+ dir == mdi_read ? "READ" : "WRITE",
+ addr, reg, data);
return 0xFFFF;
}
}
@@ -1155,12 +1155,15 @@
}
}
- DPRINTK(HW, DEBUG, "[00-07]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n",
- c[0], c[1], c[2], c[3], c[4], c[5], c[6], c[7]);
- DPRINTK(HW, DEBUG, "[08-15]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n",
- c[8], c[9], c[10], c[11], c[12], c[13], c[14], c[15]);
- DPRINTK(HW, DEBUG, "[16-23]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n",
- c[16], c[17], c[18], c[19], c[20], c[21], c[22], c[23]);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "[00-07]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n",
+ c[0], c[1], c[2], c[3], c[4], c[5], c[6], c[7]);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "[08-15]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n",
+ c[8], c[9], c[10], c[11], c[12], c[13], c[14], c[15]);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "[16-23]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n",
+ c[16], c[17], c[18], c[19], c[20], c[21], c[22], c[23]);
}
/*************************************************************************
@@ -1253,16 +1256,18 @@
err = request_firmware(&fw, fw_name, &nic->pdev->dev);
if (err) {
- DPRINTK(PROBE, ERR, "Failed to load firmware \"%s\": %d\n",
- fw_name, err);
+ netif_err(nic, probe, nic->netdev,
+ "Failed to load firmware \"%s\": %d\n",
+ fw_name, err);
return ERR_PTR(err);
}
/* Firmware should be precisely UCODE_SIZE (words) plus three bytes
indicating the offsets for BUNDLESMALL, BUNDLEMAX, INTDELAY */
if (fw->size != UCODE_SIZE * 4 + 3) {
- DPRINTK(PROBE, ERR, "Firmware \"%s\" has wrong size %zu\n",
- fw_name, fw->size);
+ netif_err(nic, probe, nic->netdev,
+ "Firmware \"%s\" has wrong size %zu\n",
+ fw_name, fw->size);
release_firmware(fw);
return ERR_PTR(-EINVAL);
}
@@ -1274,9 +1279,9 @@
if (timer >= UCODE_SIZE || bundle >= UCODE_SIZE ||
min_size >= UCODE_SIZE) {
- DPRINTK(PROBE, ERR,
- "\"%s\" has bogus offset values (0x%x,0x%x,0x%x)\n",
- fw_name, timer, bundle, min_size);
+ netif_err(nic, probe, nic->netdev,
+ "\"%s\" has bogus offset values (0x%x,0x%x,0x%x)\n",
+ fw_name, timer, bundle, min_size);
release_firmware(fw);
return ERR_PTR(-EINVAL);
}
@@ -1328,7 +1333,8 @@
return PTR_ERR(fw);
if ((err = e100_exec_cb(nic, (void *)fw, e100_setup_ucode)))
- DPRINTK(PROBE,ERR, "ucode cmd failed with error %d\n", err);
+ netif_err(nic, probe, nic->netdev,
+ "ucode cmd failed with error %d\n", err);
/* must restart cuc */
nic->cuc_cmd = cuc_start;
@@ -1348,7 +1354,7 @@
/* if the command failed, or is not OK, notify and return */
if (!counter || !(cb->status & cpu_to_le16(cb_ok))) {
- DPRINTK(PROBE,ERR, "ucode load failed\n");
+ netif_err(nic, probe, nic->netdev, "ucode load failed\n");
err = -EPERM;
}
@@ -1386,8 +1392,8 @@
* media is sensed automatically based on how the link partner
* is configured. This is, in essence, manual configuration.
*/
- DPRINTK(PROBE, INFO,
- "found MII-less i82503 or 80c24 or other PHY\n");
+ netif_info(nic, probe, nic->netdev,
+ "found MII-less i82503 or 80c24 or other PHY\n");
nic->mdio_ctrl = mdio_ctrl_phy_mii_emulated;
nic->mii.phy_id = 0; /* is this ok for an MII-less PHY? */
@@ -1434,18 +1440,20 @@
return 0; /* simply return and hope for the best */
else {
/* for unknown cases log a fatal error */
- DPRINTK(HW, ERR,
- "Failed to locate any known PHY, aborting.\n");
+ netif_err(nic, hw, nic->netdev,
+ "Failed to locate any known PHY, aborting\n");
return -EAGAIN;
}
} else
- DPRINTK(HW, DEBUG, "phy_addr = %d\n", nic->mii.phy_id);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "phy_addr = %d\n", nic->mii.phy_id);
/* Get phy ID */
id_lo = mdio_read(netdev, nic->mii.phy_id, MII_PHYSID1);
id_hi = mdio_read(netdev, nic->mii.phy_id, MII_PHYSID2);
nic->phy = (u32)id_hi << 16 | (u32)id_lo;
- DPRINTK(HW, DEBUG, "phy ID = 0x%08X\n", nic->phy);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "phy ID = 0x%08X\n", nic->phy);
/* Select the phy and isolate the rest */
for (addr = 0; addr < 32; addr++) {
@@ -1507,7 +1515,7 @@
e100_hw_reset(nic);
- DPRINTK(HW, ERR, "e100_hw_init\n");
+ netif_err(nic, hw, nic->netdev, "e100_hw_init\n");
if (!in_interrupt() && (err = e100_self_test(nic)))
return err;
@@ -1555,8 +1563,9 @@
{
struct nic *nic = netdev_priv(netdev);
- DPRINTK(HW, DEBUG, "mc_count=%d, flags=0x%04X\n",
- netdev_mc_count(netdev), netdev->flags);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "mc_count=%d, flags=0x%04X\n",
+ netdev_mc_count(netdev), netdev->flags);
if (netdev->flags & IFF_PROMISC)
nic->flags |= promiscuous;
@@ -1629,7 +1638,8 @@
if (e100_exec_cmd(nic, cuc_dump_reset, 0))
- DPRINTK(TX_ERR, DEBUG, "exec cuc_dump_reset failed\n");
+ netif_printk(nic, tx_err, KERN_DEBUG, nic->netdev,
+ "exec cuc_dump_reset failed\n");
}
static void e100_adjust_adaptive_ifs(struct nic *nic, int speed, int duplex)
@@ -1659,20 +1669,19 @@
struct nic *nic = (struct nic *)data;
struct ethtool_cmd cmd;
- DPRINTK(TIMER, DEBUG, "right now = %ld\n", jiffies);
+ netif_printk(nic, timer, KERN_DEBUG, nic->netdev,
+ "right now = %ld\n", jiffies);
/* mii library handles link maintenance tasks */
mii_ethtool_gset(&nic->mii, &cmd);
if (mii_link_ok(&nic->mii) && !netif_carrier_ok(nic->netdev)) {
- printk(KERN_INFO "e100: %s NIC Link is Up %s Mbps %s Duplex\n",
- nic->netdev->name,
- cmd.speed == SPEED_100 ? "100" : "10",
- cmd.duplex == DUPLEX_FULL ? "Full" : "Half");
+ netdev_info(nic->netdev, "NIC Link is Up %u Mbps %s Duplex\n",
+ cmd.speed == SPEED_100 ? 100 : 10,
+ cmd.duplex == DUPLEX_FULL ? "Full" : "Half");
} else if (!mii_link_ok(&nic->mii) && netif_carrier_ok(nic->netdev)) {
- printk(KERN_INFO "e100: %s NIC Link is Down\n",
- nic->netdev->name);
+ netdev_info(nic->netdev, "NIC Link is Down\n");
}
mii_check_link(&nic->mii);
@@ -1732,7 +1741,8 @@
Issue a NOP command followed by a 1us delay before
issuing the Tx command. */
if (e100_exec_cmd(nic, cuc_nop, 0))
- DPRINTK(TX_ERR, DEBUG, "exec cuc_nop failed\n");
+ netif_printk(nic, tx_err, KERN_DEBUG, nic->netdev,
+ "exec cuc_nop failed\n");
udelay(1);
}
@@ -1741,12 +1751,14 @@
switch (err) {
case -ENOSPC:
/* We queued the skb, but now we're out of space. */
- DPRINTK(TX_ERR, DEBUG, "No space for CB\n");
+ netif_printk(nic, tx_err, KERN_DEBUG, nic->netdev,
+ "No space for CB\n");
netif_stop_queue(netdev);
break;
case -ENOMEM:
/* This is a hard error - log it. */
- DPRINTK(TX_ERR, DEBUG, "Out of Tx resources, returning skb\n");
+ netif_printk(nic, tx_err, KERN_DEBUG, nic->netdev,
+ "Out of Tx resources, returning skb\n");
netif_stop_queue(netdev);
return NETDEV_TX_BUSY;
}
@@ -1767,9 +1779,10 @@
for (cb = nic->cb_to_clean;
cb->status & cpu_to_le16(cb_complete);
cb = nic->cb_to_clean = cb->next) {
- DPRINTK(TX_DONE, DEBUG, "cb[%d]->status = 0x%04X\n",
- (int)(((void*)cb - (void*)nic->cbs)/sizeof(struct cb)),
- cb->status);
+ netif_printk(nic, tx_done, KERN_DEBUG, nic->netdev,
+ "cb[%d]->status = 0x%04X\n",
+ (int)(((void*)cb - (void*)nic->cbs)/sizeof(struct cb)),
+ cb->status);
if (likely(cb->skb != NULL)) {
dev->stats.tx_packets++;
@@ -1912,7 +1925,8 @@
sizeof(struct rfd), PCI_DMA_BIDIRECTIONAL);
rfd_status = le16_to_cpu(rfd->status);
- DPRINTK(RX_STATUS, DEBUG, "status=0x%04X\n", rfd_status);
+ netif_printk(nic, rx_status, KERN_DEBUG, nic->netdev,
+ "status=0x%04X\n", rfd_status);
/* If data isn't ready, nothing to indicate */
if (unlikely(!(rfd_status & cb_complete))) {
@@ -2123,7 +2137,8 @@
struct nic *nic = netdev_priv(netdev);
u8 stat_ack = ioread8(&nic->csr->scb.stat_ack);
- DPRINTK(INTR, DEBUG, "stat_ack = 0x%02X\n", stat_ack);
+ netif_printk(nic, intr, KERN_DEBUG, nic->netdev,
+ "stat_ack = 0x%02X\n", stat_ack);
if (stat_ack == stat_ack_not_ours || /* Not our interrupt */
stat_ack == stat_ack_not_present) /* Hardware is ejected */
@@ -2263,8 +2278,8 @@
struct nic *nic = container_of(work, struct nic, tx_timeout_task);
struct net_device *netdev = nic->netdev;
- DPRINTK(TX_ERR, DEBUG, "scb.status=0x%02X\n",
- ioread8(&nic->csr->scb.status));
+ netif_printk(nic, tx_err, KERN_DEBUG, nic->netdev,
+ "scb.status=0x%02X\n", ioread8(&nic->csr->scb.status));
e100_down(netdev_priv(netdev));
e100_up(netdev_priv(netdev));
}
@@ -2526,8 +2541,8 @@
rfds->count = min(rfds->count, rfds->max);
cbs->count = max(ring->tx_pending, cbs->min);
cbs->count = min(cbs->count, cbs->max);
- DPRINTK(DRV, INFO, "Ring Param settings: rx: %d, tx %d\n",
- rfds->count, cbs->count);
+ netif_info(nic, drv, nic->netdev, "Ring Param settings: rx: %d, tx %d\n",
+ rfds->count, cbs->count);
if (netif_running(netdev))
e100_up(nic);
@@ -2704,7 +2719,7 @@
netif_carrier_off(netdev);
if ((err = e100_up(nic)))
- DPRINTK(IFUP, ERR, "Cannot open interface, aborting.\n");
+ netif_err(nic, ifup, nic->netdev, "Cannot open interface, aborting\n");
return err;
}
@@ -2738,7 +2753,7 @@
if (!(netdev = alloc_etherdev(sizeof(struct nic)))) {
if (((1 << debug) - 1) & NETIF_MSG_PROBE)
- printk(KERN_ERR PFX "Etherdev alloc failed, abort.\n");
+ pr_err("Etherdev alloc failed, aborting\n");
return -ENOMEM;
}
@@ -2756,35 +2771,34 @@
pci_set_drvdata(pdev, netdev);
if ((err = pci_enable_device(pdev))) {
- DPRINTK(PROBE, ERR, "Cannot enable PCI device, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "Cannot enable PCI device, aborting\n");
goto err_out_free_dev;
}
if (!(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) {
- DPRINTK(PROBE, ERR, "Cannot find proper PCI device "
- "base address, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "Cannot find proper PCI device base address, aborting\n");
err = -ENODEV;
goto err_out_disable_pdev;
}
if ((err = pci_request_regions(pdev, DRV_NAME))) {
- DPRINTK(PROBE, ERR, "Cannot obtain PCI resources, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "Cannot obtain PCI resources, aborting\n");
goto err_out_disable_pdev;
}
if ((err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))) {
- DPRINTK(PROBE, ERR, "No usable DMA configuration, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "No usable DMA configuration, aborting\n");
goto err_out_free_res;
}
SET_NETDEV_DEV(netdev, &pdev->dev);
if (use_io)
- DPRINTK(PROBE, INFO, "using i/o access mode\n");
+ netif_info(nic, probe, nic->netdev, "using i/o access mode\n");
nic->csr = pci_iomap(pdev, (use_io ? 1 : 0), sizeof(struct csr));
if (!nic->csr) {
- DPRINTK(PROBE, ERR, "Cannot map device registers, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "Cannot map device registers, aborting\n");
err = -ENOMEM;
goto err_out_free_res;
}
@@ -2818,7 +2832,7 @@
INIT_WORK(&nic->tx_timeout_task, e100_tx_timeout_task);
if ((err = e100_alloc(nic))) {
- DPRINTK(PROBE, ERR, "Cannot alloc driver memory, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "Cannot alloc driver memory, aborting\n");
goto err_out_iounmap;
}
@@ -2831,13 +2845,11 @@
memcpy(netdev->perm_addr, nic->eeprom, ETH_ALEN);
if (!is_valid_ether_addr(netdev->perm_addr)) {
if (!eeprom_bad_csum_allow) {
- DPRINTK(PROBE, ERR, "Invalid MAC address from "
- "EEPROM, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "Invalid MAC address from EEPROM, aborting\n");
err = -EAGAIN;
goto err_out_free;
} else {
- DPRINTK(PROBE, ERR, "Invalid MAC address from EEPROM, "
- "you MUST configure one.\n");
+ netif_err(nic, probe, nic->netdev, "Invalid MAC address from EEPROM, you MUST configure one.\n");
}
}
@@ -2853,7 +2865,7 @@
strcpy(netdev->name, "eth%d");
if ((err = register_netdev(netdev))) {
- DPRINTK(PROBE, ERR, "Cannot register net device, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "Cannot register net device, aborting\n");
goto err_out_free;
}
nic->cbs_pool = pci_pool_create(netdev->name,
@@ -2861,9 +2873,10 @@
nic->params.cbs.max * sizeof(struct cb),
sizeof(u32),
0);
- DPRINTK(PROBE, INFO, "addr 0x%llx, irq %d, MAC addr %pM\n",
- (unsigned long long)pci_resource_start(pdev, use_io ? 1 : 0),
- pdev->irq, netdev->dev_addr);
+ netif_info(nic, probe, nic->netdev,
+ "addr 0x%llx, irq %d, MAC addr %pM\n",
+ (unsigned long long)pci_resource_start(pdev, use_io ? 1 : 0),
+ pdev->irq, netdev->dev_addr);
return 0;
@@ -3021,7 +3034,7 @@
struct nic *nic = netdev_priv(netdev);
if (pci_enable_device(pdev)) {
- printk(KERN_ERR "e100: Cannot re-enable PCI device after reset.\n");
+ pr_err("Cannot re-enable PCI device after reset\n");
return PCI_ERS_RESULT_DISCONNECT;
}
pci_set_master(pdev);
@@ -3080,8 +3093,8 @@
static int __init e100_init_module(void)
{
if (((1 << debug) - 1) & NETIF_MSG_DRV) {
- printk(KERN_INFO PFX "%s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
- printk(KERN_INFO PFX "%s\n", DRV_COPYRIGHT);
+ pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
+ pr_info("%s\n", DRV_COPYRIGHT);
}
return pci_register_driver(&e100_driver);
}
diff --git a/drivers/net/e1000e/e1000.h b/drivers/net/e1000e/e1000.h
index c2ec095..8da190b 100644
--- a/drivers/net/e1000e/e1000.h
+++ b/drivers/net/e1000e/e1000.h
@@ -158,6 +158,9 @@
#define HV_M_STATUS_SPEED_1000 0x0200
#define HV_M_STATUS_LINK_UP 0x0040
+/* Time to wait before putting the device into D3 if there's no link (in ms). */
+#define LINK_TIMEOUT 100
+
enum e1000_boards {
board_82571,
board_82572,
@@ -370,6 +373,8 @@
struct work_struct update_phy_task;
struct work_struct led_blink_task;
struct work_struct print_hang_task;
+
+ bool idle_check;
};
struct e1000_info {
diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c
index 88d54d3..06ba46a 100644
--- a/drivers/net/e1000e/netdev.c
+++ b/drivers/net/e1000e/netdev.c
@@ -44,6 +44,7 @@
#include <linux/cpu.h>
#include <linux/smp.h>
#include <linux/pm_qos_params.h>
+#include <linux/pm_runtime.h>
#include <linux/aer.h>
#include "e1000.h"
@@ -3083,12 +3084,15 @@
{
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
+ struct pci_dev *pdev = adapter->pdev;
int err;
/* disallow open during test */
if (test_bit(__E1000_TESTING, &adapter->state))
return -EBUSY;
+ pm_runtime_get_sync(&pdev->dev);
+
netif_carrier_off(netdev);
/* allocate transmit descriptors */
@@ -3149,6 +3153,9 @@
netif_start_queue(netdev);
+ adapter->idle_check = true;
+ pm_runtime_put(&pdev->dev);
+
/* fire a link status change interrupt to start the watchdog */
ew32(ICS, E1000_ICS_LSC);
@@ -3162,6 +3169,7 @@
e1000e_free_tx_resources(adapter);
err_setup_tx:
e1000e_reset(adapter);
+ pm_runtime_put_sync(&pdev->dev);
return err;
}
@@ -3180,11 +3188,17 @@
static int e1000_close(struct net_device *netdev)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
+ struct pci_dev *pdev = adapter->pdev;
WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
- e1000e_down(adapter);
+
+ pm_runtime_get_sync(&pdev->dev);
+
+ if (!test_bit(__E1000_DOWN, &adapter->state)) {
+ e1000e_down(adapter);
+ e1000_free_irq(adapter);
+ }
e1000_power_down_phy(adapter);
- e1000_free_irq(adapter);
e1000e_free_tx_resources(adapter);
e1000e_free_rx_resources(adapter);
@@ -3206,6 +3220,8 @@
if (adapter->flags & FLAG_HAS_AMT)
e1000_release_hw_control(adapter);
+ pm_runtime_put_sync(&pdev->dev);
+
return 0;
}
/**
@@ -3550,6 +3566,9 @@
link = e1000e_has_link(adapter);
if ((netif_carrier_ok(netdev)) && link) {
+ /* Cancel scheduled suspend requests. */
+ pm_runtime_resume(netdev->dev.parent);
+
e1000e_enable_receives(adapter);
goto link_up;
}
@@ -3561,6 +3580,10 @@
if (link) {
if (!netif_carrier_ok(netdev)) {
bool txb2b = 1;
+
+ /* Cancel scheduled suspend requests. */
+ pm_runtime_resume(netdev->dev.parent);
+
/* update snapshot of PHY registers on LSC */
e1000_phy_read_status(adapter);
mac->ops.get_link_up_info(&adapter->hw,
@@ -3676,6 +3699,9 @@
if (adapter->flags & FLAG_RX_NEEDS_RESTART)
schedule_work(&adapter->reset_task);
+ else
+ pm_schedule_suspend(netdev->dev.parent,
+ LINK_TIMEOUT);
}
}
@@ -4473,13 +4499,15 @@
return retval;
}
-static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake)
+static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake,
+ bool runtime)
{
struct net_device *netdev = pci_get_drvdata(pdev);
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
u32 ctrl, ctrl_ext, rctl, status;
- u32 wufc = adapter->wol;
+ /* Runtime suspend should only enable wakeup for link changes */
+ u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol;
int retval = 0;
netif_device_detach(netdev);
@@ -4636,43 +4664,21 @@
}
}
-#ifdef CONFIG_PM
-static int e1000_suspend(struct pci_dev *pdev, pm_message_t state)
+#ifdef CONFIG_PM_OPS
+static bool e1000e_pm_ready(struct e1000_adapter *adapter)
{
- int retval;
- bool wake;
-
- retval = __e1000_shutdown(pdev, &wake);
- if (!retval)
- e1000_complete_shutdown(pdev, true, wake);
-
- return retval;
+ return !!adapter->tx_ring->buffer_info;
}
-static int e1000_resume(struct pci_dev *pdev)
+static int __e1000_resume(struct pci_dev *pdev)
{
struct net_device *netdev = pci_get_drvdata(pdev);
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
u32 err;
- pci_set_power_state(pdev, PCI_D0);
- pci_restore_state(pdev);
- pci_save_state(pdev);
e1000e_disable_l1aspm(pdev);
- err = pci_enable_device_mem(pdev);
- if (err) {
- dev_err(&pdev->dev,
- "Cannot enable PCI device from suspend\n");
- return err;
- }
-
- pci_set_master(pdev);
-
- pci_enable_wake(pdev, PCI_D3hot, 0);
- pci_enable_wake(pdev, PCI_D3cold, 0);
-
e1000e_set_interrupt_capability(adapter);
if (netif_running(netdev)) {
err = e1000_request_irq(adapter);
@@ -4730,13 +4736,88 @@
return 0;
}
-#endif
+
+#ifdef CONFIG_PM_SLEEP
+static int e1000_suspend(struct device *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ int retval;
+ bool wake;
+
+ retval = __e1000_shutdown(pdev, &wake, false);
+ if (!retval)
+ e1000_complete_shutdown(pdev, true, wake);
+
+ return retval;
+}
+
+static int e1000_resume(struct device *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct e1000_adapter *adapter = netdev_priv(netdev);
+
+ if (e1000e_pm_ready(adapter))
+ adapter->idle_check = true;
+
+ return __e1000_resume(pdev);
+}
+#endif /* CONFIG_PM_SLEEP */
+
+#ifdef CONFIG_PM_RUNTIME
+static int e1000_runtime_suspend(struct device *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct e1000_adapter *adapter = netdev_priv(netdev);
+
+ if (e1000e_pm_ready(adapter)) {
+ bool wake;
+
+ __e1000_shutdown(pdev, &wake, true);
+ }
+
+ return 0;
+}
+
+static int e1000_idle(struct device *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct e1000_adapter *adapter = netdev_priv(netdev);
+
+ if (!e1000e_pm_ready(adapter))
+ return 0;
+
+ if (adapter->idle_check) {
+ adapter->idle_check = false;
+ if (!e1000e_has_link(adapter))
+ pm_schedule_suspend(dev, MSEC_PER_SEC);
+ }
+
+ return -EBUSY;
+}
+
+static int e1000_runtime_resume(struct device *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct e1000_adapter *adapter = netdev_priv(netdev);
+
+ if (!e1000e_pm_ready(adapter))
+ return 0;
+
+ adapter->idle_check = !dev->power.runtime_auto;
+ return __e1000_resume(pdev);
+}
+#endif /* CONFIG_PM_RUNTIME */
+#endif /* CONFIG_PM_OPS */
static void e1000_shutdown(struct pci_dev *pdev)
{
bool wake = false;
- __e1000_shutdown(pdev, &wake);
+ __e1000_shutdown(pdev, &wake, false);
if (system_state == SYSTEM_POWER_OFF)
e1000_complete_shutdown(pdev, false, wake);
@@ -4809,8 +4890,8 @@
result = PCI_ERS_RESULT_DISCONNECT;
} else {
pci_set_master(pdev);
+ pdev->state_saved = true;
pci_restore_state(pdev);
- pci_save_state(pdev);
pci_enable_wake(pdev, PCI_D3hot, 0);
pci_enable_wake(pdev, PCI_D3cold, 0);
@@ -5217,6 +5298,12 @@
e1000_print_device_info(adapter);
+ if (pci_dev_run_wake(pdev)) {
+ pm_runtime_set_active(&pdev->dev);
+ pm_runtime_enable(&pdev->dev);
+ }
+ pm_schedule_suspend(&pdev->dev, MSEC_PER_SEC);
+
return 0;
err_register:
@@ -5259,12 +5346,16 @@
{
struct net_device *netdev = pci_get_drvdata(pdev);
struct e1000_adapter *adapter = netdev_priv(netdev);
+ bool down = test_bit(__E1000_DOWN, &adapter->state);
+
+ pm_runtime_get_sync(&pdev->dev);
/*
* flush_scheduled work may reschedule our watchdog task, so
* explicitly disable watchdog tasks from being rescheduled
*/
- set_bit(__E1000_DOWN, &adapter->state);
+ if (!down)
+ set_bit(__E1000_DOWN, &adapter->state);
del_timer_sync(&adapter->watchdog_timer);
del_timer_sync(&adapter->phy_info_timer);
@@ -5278,8 +5369,17 @@
if (!(netdev->flags & IFF_UP))
e1000_power_down_phy(adapter);
+ /* Don't lie to e1000_close() down the road. */
+ if (!down)
+ clear_bit(__E1000_DOWN, &adapter->state);
unregister_netdev(netdev);
+ if (pci_dev_run_wake(pdev)) {
+ pm_runtime_disable(&pdev->dev);
+ pm_runtime_set_suspended(&pdev->dev);
+ }
+ pm_runtime_put_noidle(&pdev->dev);
+
/*
* Release control of h/w to f/w. If f/w is AMT enabled, this
* would have already happened in close and is redundant.
@@ -5379,16 +5479,22 @@
};
MODULE_DEVICE_TABLE(pci, e1000_pci_tbl);
+#ifdef CONFIG_PM_OPS
+static const struct dev_pm_ops e1000_pm_ops = {
+ SET_SYSTEM_SLEEP_PM_OPS(e1000_suspend, e1000_resume)
+ SET_RUNTIME_PM_OPS(e1000_runtime_suspend,
+ e1000_runtime_resume, e1000_idle)
+};
+#endif
+
/* PCI Device API Driver */
static struct pci_driver e1000_driver = {
.name = e1000e_driver_name,
.id_table = e1000_pci_tbl,
.probe = e1000_probe,
.remove = __devexit_p(e1000_remove),
-#ifdef CONFIG_PM
- /* Power Management Hooks */
- .suspend = e1000_suspend,
- .resume = e1000_resume,
+#ifdef CONFIG_PM_OPS
+ .driver.pm = &e1000_pm_ops,
#endif
.shutdown = e1000_shutdown,
.err_handler = &e1000_err_handler
diff --git a/drivers/net/enic/cq_enet_desc.h b/drivers/net/enic/cq_enet_desc.h
index 03dce9e..337d194 100644
--- a/drivers/net/enic/cq_enet_desc.h
+++ b/drivers/net/enic/cq_enet_desc.h
@@ -101,14 +101,18 @@
u8 *tcp_udp_csum_ok, u8 *udp, u8 *tcp, u8 *ipv4_csum_ok,
u8 *ipv6, u8 *ipv4, u8 *ipv4_fragment, u8 *fcs_ok)
{
- u16 completed_index_flags = le16_to_cpu(desc->completed_index_flags);
- u16 q_number_rss_type_flags =
- le16_to_cpu(desc->q_number_rss_type_flags);
- u16 bytes_written_flags = le16_to_cpu(desc->bytes_written_flags);
+ u16 completed_index_flags;
+ u16 q_number_rss_type_flags;
+ u16 bytes_written_flags;
cq_desc_dec((struct cq_desc *)desc, type,
color, q_number, completed_index);
+ completed_index_flags = le16_to_cpu(desc->completed_index_flags);
+ q_number_rss_type_flags =
+ le16_to_cpu(desc->q_number_rss_type_flags);
+ bytes_written_flags = le16_to_cpu(desc->bytes_written_flags);
+
*ingress_port = (completed_index_flags &
CQ_ENET_RQ_DESC_FLAGS_INGRESS_PORT) ? 1 : 0;
*fcoe = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_FCOE) ?
diff --git a/drivers/net/enic/enic.h b/drivers/net/enic/enic.h
index ee01f5a..5fa56f1 100644
--- a/drivers/net/enic/enic.h
+++ b/drivers/net/enic/enic.h
@@ -33,8 +33,8 @@
#include "vnic_rss.h"
#define DRV_NAME "enic"
-#define DRV_DESCRIPTION "Cisco 10G Ethernet Driver"
-#define DRV_VERSION "1.1.0.241a"
+#define DRV_DESCRIPTION "Cisco VIC Ethernet NIC Driver"
+#define DRV_VERSION "1.3.1.1"
#define DRV_COPYRIGHT "Copyright 2008-2009 Cisco Systems, Inc"
#define PFX DRV_NAME ": "
diff --git a/drivers/net/enic/enic_main.c b/drivers/net/enic/enic_main.c
index cf098bb..6d70c34 100644
--- a/drivers/net/enic/enic_main.c
+++ b/drivers/net/enic/enic_main.c
@@ -829,7 +829,7 @@
int promisc = (netdev->flags & IFF_PROMISC) ? 1 : 0;
unsigned int mc_count = netdev_mc_count(netdev);
int allmulti = (netdev->flags & IFF_ALLMULTI) ||
- mc_count > ENIC_MULTICAST_PERFECT_FILTERS;
+ mc_count > ENIC_MULTICAST_PERFECT_FILTERS;
unsigned int flags = netdev->flags | (allmulti ? IFF_ALLMULTI : 0);
u8 mc_addr[ENIC_MULTICAST_PERFECT_FILTERS][ETH_ALEN];
unsigned int i, j;
@@ -2058,8 +2058,7 @@
netdev->watchdog_timeo = 2 * HZ;
netdev->ethtool_ops = &enic_ethtool_ops;
- netdev->features |= NETIF_F_HW_VLAN_TX |
- NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_FILTER;
+ netdev->features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX;
if (ENIC_SETTING(enic, TXCSUM))
netdev->features |= NETIF_F_SG | NETIF_F_HW_CSUM;
if (ENIC_SETTING(enic, TSO))
diff --git a/drivers/net/enic/vnic_dev.c b/drivers/net/enic/vnic_dev.c
index 69b9b70..cbc0ba9 100644
--- a/drivers/net/enic/vnic_dev.c
+++ b/drivers/net/enic/vnic_dev.c
@@ -573,22 +573,18 @@
return err;
}
-int vnic_dev_notify_set(struct vnic_dev *vdev, u16 intr)
+int vnic_dev_notify_setcmd(struct vnic_dev *vdev,
+ void *notify_addr, dma_addr_t notify_pa, u16 intr)
{
u64 a0, a1;
int wait = 1000;
int r;
- if (!vdev->notify) {
- vdev->notify = pci_alloc_consistent(vdev->pdev,
- sizeof(struct vnic_devcmd_notify),
- &vdev->notify_pa);
- if (!vdev->notify)
- return -ENOMEM;
- memset(vdev->notify, 0, sizeof(struct vnic_devcmd_notify));
- }
+ memset(notify_addr, 0, sizeof(struct vnic_devcmd_notify));
+ vdev->notify = notify_addr;
+ vdev->notify_pa = notify_pa;
- a0 = vdev->notify_pa;
+ a0 = (u64)notify_pa;
a1 = ((u64)intr << 32) & 0x0000ffff00000000ULL;
a1 += sizeof(struct vnic_devcmd_notify);
@@ -597,7 +593,27 @@
return r;
}
-void vnic_dev_notify_unset(struct vnic_dev *vdev)
+int vnic_dev_notify_set(struct vnic_dev *vdev, u16 intr)
+{
+ void *notify_addr;
+ dma_addr_t notify_pa;
+
+ if (vdev->notify || vdev->notify_pa) {
+ printk(KERN_ERR "notify block %p still allocated",
+ vdev->notify);
+ return -EINVAL;
+ }
+
+ notify_addr = pci_alloc_consistent(vdev->pdev,
+ sizeof(struct vnic_devcmd_notify),
+ ¬ify_pa);
+ if (!notify_addr)
+ return -ENOMEM;
+
+ return vnic_dev_notify_setcmd(vdev, notify_addr, notify_pa, intr);
+}
+
+void vnic_dev_notify_unsetcmd(struct vnic_dev *vdev)
{
u64 a0, a1;
int wait = 1000;
@@ -607,9 +623,23 @@
a1 += sizeof(struct vnic_devcmd_notify);
vnic_dev_cmd(vdev, CMD_NOTIFY, &a0, &a1, wait);
+ vdev->notify = NULL;
+ vdev->notify_pa = 0;
vdev->notify_sz = 0;
}
+void vnic_dev_notify_unset(struct vnic_dev *vdev)
+{
+ if (vdev->notify) {
+ pci_free_consistent(vdev->pdev,
+ sizeof(struct vnic_devcmd_notify),
+ vdev->notify,
+ vdev->notify_pa);
+ }
+
+ vnic_dev_notify_unsetcmd(vdev);
+}
+
static int vnic_dev_notify_ready(struct vnic_dev *vdev)
{
u32 *words;
diff --git a/drivers/net/enic/vnic_dev.h b/drivers/net/enic/vnic_dev.h
index fc5e3eb..f5be640 100644
--- a/drivers/net/enic/vnic_dev.h
+++ b/drivers/net/enic/vnic_dev.h
@@ -107,7 +107,10 @@
void vnic_dev_del_addr(struct vnic_dev *vdev, u8 *addr);
int vnic_dev_mac_addr(struct vnic_dev *vdev, u8 *mac_addr);
int vnic_dev_raise_intr(struct vnic_dev *vdev, u16 intr);
+int vnic_dev_notify_setcmd(struct vnic_dev *vdev,
+ void *notify_addr, dma_addr_t notify_pa, u16 intr);
int vnic_dev_notify_set(struct vnic_dev *vdev, u16 intr);
+void vnic_dev_notify_unsetcmd(struct vnic_dev *vdev);
void vnic_dev_notify_unset(struct vnic_dev *vdev);
int vnic_dev_link_status(struct vnic_dev *vdev);
u32 vnic_dev_port_speed(struct vnic_dev *vdev);
diff --git a/drivers/net/enic/vnic_rq.c b/drivers/net/enic/vnic_rq.c
index 7558397..7bcd903 100644
--- a/drivers/net/enic/vnic_rq.c
+++ b/drivers/net/enic/vnic_rq.c
@@ -167,10 +167,10 @@
iowrite32(0, &rq->ctrl->enable);
/* Wait for HW to ACK disable request */
- for (wait = 0; wait < 100; wait++) {
+ for (wait = 0; wait < 1000; wait++) {
if (!(ioread32(&rq->ctrl->running)))
return 0;
- udelay(1);
+ udelay(10);
}
printk(KERN_ERR "Failed to disable RQ[%d]\n", rq->index);
diff --git a/drivers/net/enic/vnic_wq.c b/drivers/net/enic/vnic_wq.c
index d2e00e5..44fc323 100644
--- a/drivers/net/enic/vnic_wq.c
+++ b/drivers/net/enic/vnic_wq.c
@@ -160,10 +160,10 @@
iowrite32(0, &wq->ctrl->enable);
/* Wait for HW to ACK disable request */
- for (wait = 0; wait < 100; wait++) {
+ for (wait = 0; wait < 1000; wait++) {
if (!(ioread32(&wq->ctrl->running)))
return 0;
- udelay(1);
+ udelay(10);
}
printk(KERN_ERR "Failed to disable WQ[%d]\n", wq->index);
diff --git a/drivers/net/ks8842.c b/drivers/net/ks8842.c
index 5c45cb5..b91492f 100644
--- a/drivers/net/ks8842.c
+++ b/drivers/net/ks8842.c
@@ -20,6 +20,8 @@
* The Micrel KS8842 behind the timberdale FPGA
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/platform_device.h>
@@ -525,8 +527,7 @@
err = request_irq(adapter->irq, ks8842_irq, IRQF_SHARED, DRV_NAME,
adapter);
if (err) {
- printk(KERN_ERR "Failed to request IRQ: %d: %d\n",
- adapter->irq, err);
+ pr_err("Failed to request IRQ: %d: %d\n", adapter->irq, err);
return err;
}
@@ -668,8 +669,7 @@
platform_set_drvdata(pdev, netdev);
- printk(KERN_INFO DRV_NAME
- " Found chip, family: 0x%x, id: 0x%x, rev: 0x%x\n",
+ pr_info("Found chip, family: 0x%x, id: 0x%x, rev: 0x%x\n",
(id >> 8) & 0xff, (id >> 4) & 0xf, (id >> 1) & 0x7);
return 0;
diff --git a/drivers/net/ks8851.c b/drivers/net/ks8851.c
index 13cc1ca..66be4e4 100644
--- a/drivers/net/ks8851.c
+++ b/drivers/net/ks8851.c
@@ -9,6 +9,8 @@
* published by the Free Software Foundation.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#define DEBUG
#include <linux/module.h>
@@ -125,11 +127,6 @@
static int msg_enable;
-#define ks_info(_ks, _msg...) dev_info(&(_ks)->spidev->dev, _msg)
-#define ks_warn(_ks, _msg...) dev_warn(&(_ks)->spidev->dev, _msg)
-#define ks_dbg(_ks, _msg...) dev_dbg(&(_ks)->spidev->dev, _msg)
-#define ks_err(_ks, _msg...) dev_err(&(_ks)->spidev->dev, _msg)
-
/* shift for byte-enable data */
#define BYTE_EN(_x) ((_x) << 2)
@@ -167,7 +164,7 @@
ret = spi_sync(ks->spidev, msg);
if (ret < 0)
- ks_err(ks, "spi_sync() failed\n");
+ netdev_err(ks->netdev, "spi_sync() failed\n");
}
/**
@@ -197,7 +194,7 @@
ret = spi_sync(ks->spidev, msg);
if (ret < 0)
- ks_err(ks, "spi_sync() failed\n");
+ netdev_err(ks->netdev, "spi_sync() failed\n");
}
/**
@@ -263,7 +260,7 @@
ret = spi_sync(ks->spidev, msg);
if (ret < 0)
- ks_err(ks, "read: spi_sync() failed\n");
+ netdev_err(ks->netdev, "read: spi_sync() failed\n");
else if (ks8851_rx_1msg(ks))
memcpy(rxb, trx + 2, rxl);
else
@@ -417,8 +414,8 @@
u8 txb[1];
int ret;
- if (netif_msg_rx_status(ks))
- ks_dbg(ks, "%s: %d@%p\n", __func__, len, buff);
+ netif_dbg(ks, rx_status, ks->netdev,
+ "%s: %d@%p\n", __func__, len, buff);
/* set the operation we're issuing */
txb[0] = KS_SPIOP_RXFIFO;
@@ -434,7 +431,7 @@
ret = spi_sync(ks->spidev, msg);
if (ret < 0)
- ks_err(ks, "%s: spi_sync() failed\n", __func__);
+ netdev_err(ks->netdev, "%s: spi_sync() failed\n", __func__);
}
/**
@@ -446,10 +443,11 @@
*/
static void ks8851_dbg_dumpkkt(struct ks8851_net *ks, u8 *rxpkt)
{
- ks_dbg(ks, "pkt %02x%02x%02x%02x %02x%02x%02x%02x %02x%02x%02x%02x\n",
- rxpkt[4], rxpkt[5], rxpkt[6], rxpkt[7],
- rxpkt[8], rxpkt[9], rxpkt[10], rxpkt[11],
- rxpkt[12], rxpkt[13], rxpkt[14], rxpkt[15]);
+ netdev_dbg(ks->netdev,
+ "pkt %02x%02x%02x%02x %02x%02x%02x%02x %02x%02x%02x%02x\n",
+ rxpkt[4], rxpkt[5], rxpkt[6], rxpkt[7],
+ rxpkt[8], rxpkt[9], rxpkt[10], rxpkt[11],
+ rxpkt[12], rxpkt[13], rxpkt[14], rxpkt[15]);
}
/**
@@ -471,8 +469,8 @@
rxfc = ks8851_rdreg8(ks, KS_RXFC);
- if (netif_msg_rx_status(ks))
- ks_dbg(ks, "%s: %d packets\n", __func__, rxfc);
+ netif_dbg(ks, rx_status, ks->netdev,
+ "%s: %d packets\n", __func__, rxfc);
/* Currently we're issuing a read per packet, but we could possibly
* improve the code by issuing a single read, getting the receive
@@ -489,9 +487,8 @@
rxstat = rxh & 0xffff;
rxlen = rxh >> 16;
- if (netif_msg_rx_status(ks))
- ks_dbg(ks, "rx: stat 0x%04x, len 0x%04x\n",
- rxstat, rxlen);
+ netif_dbg(ks, rx_status, ks->netdev,
+ "rx: stat 0x%04x, len 0x%04x\n", rxstat, rxlen);
/* the length of the packet includes the 32bit CRC */
@@ -553,9 +550,8 @@
status = ks8851_rdreg16(ks, KS_ISR);
- if (netif_msg_intr(ks))
- dev_dbg(&ks->spidev->dev, "%s: status 0x%04x\n",
- __func__, status);
+ netif_dbg(ks, intr, ks->netdev,
+ "%s: status 0x%04x\n", __func__, status);
if (status & IRQ_LCI) {
/* should do something about checking link status */
@@ -582,8 +578,8 @@
* system */
ks->tx_space = ks8851_rdreg16(ks, KS_TXMIR);
- if (netif_msg_intr(ks))
- ks_dbg(ks, "%s: txspace %d\n", __func__, ks->tx_space);
+ netif_dbg(ks, intr, ks->netdev,
+ "%s: txspace %d\n", __func__, ks->tx_space);
}
if (status & IRQ_RXI)
@@ -659,9 +655,8 @@
unsigned fid = 0;
int ret;
- if (netif_msg_tx_queued(ks))
- dev_dbg(&ks->spidev->dev, "%s: skb %p, %d@%p, irq %d\n",
- __func__, txp, txp->len, txp->data, irq);
+ netif_dbg(ks, tx_queued, ks->netdev, "%s: skb %p, %d@%p, irq %d\n",
+ __func__, txp, txp->len, txp->data, irq);
fid = ks->fid++;
fid &= TXFR_TXFID_MASK;
@@ -685,7 +680,7 @@
ret = spi_sync(ks->spidev, msg);
if (ret < 0)
- ks_err(ks, "%s: spi_sync() failed\n", __func__);
+ netdev_err(ks->netdev, "%s: spi_sync() failed\n", __func__);
}
/**
@@ -744,8 +739,7 @@
{
unsigned pmecr;
- if (netif_msg_hw(ks))
- ks_dbg(ks, "setting power mode %d\n", pwrmode);
+ netif_dbg(ks, hw, ks->netdev, "setting power mode %d\n", pwrmode);
pmecr = ks8851_rdreg16(ks, KS_PMECR);
pmecr &= ~PMECR_PM_MASK;
@@ -769,8 +763,7 @@
* else at the moment */
mutex_lock(&ks->lock);
- if (netif_msg_ifup(ks))
- ks_dbg(ks, "opening %s\n", dev->name);
+ netif_dbg(ks, ifup, ks->netdev, "opening\n");
/* bring chip out of any power saving mode it was in */
ks8851_set_powermode(ks, PMECR_PM_NORMAL);
@@ -826,8 +819,7 @@
netif_start_queue(ks->netdev);
- if (netif_msg_ifup(ks))
- ks_dbg(ks, "network device %s up\n", dev->name);
+ netif_dbg(ks, ifup, ks->netdev, "network device up\n");
mutex_unlock(&ks->lock);
return 0;
@@ -845,8 +837,7 @@
{
struct ks8851_net *ks = netdev_priv(dev);
- if (netif_msg_ifdown(ks))
- ks_info(ks, "%s: shutting down\n", dev->name);
+ netif_info(ks, ifdown, dev, "shutting down\n");
netif_stop_queue(dev);
@@ -874,8 +865,8 @@
while (!skb_queue_empty(&ks->txq)) {
struct sk_buff *txb = skb_dequeue(&ks->txq);
- if (netif_msg_ifdown(ks))
- ks_dbg(ks, "%s: freeing txb %p\n", __func__, txb);
+ netif_dbg(ks, ifdown, ks->netdev,
+ "%s: freeing txb %p\n", __func__, txb);
dev_kfree_skb(txb);
}
@@ -904,9 +895,8 @@
unsigned needed = calc_txlen(skb->len);
netdev_tx_t ret = NETDEV_TX_OK;
- if (netif_msg_tx_queued(ks))
- ks_dbg(ks, "%s: skb %p, %d@%p\n", __func__,
- skb, skb->len, skb->data);
+ netif_dbg(ks, tx_queued, ks->netdev,
+ "%s: skb %p, %d@%p\n", __func__, skb, skb->len, skb->data);
spin_lock(&ks->statelock);
@@ -1185,17 +1175,17 @@
rd = ks8851_rdreg16(ks, KS_MBIR);
if ((rd & both_done) != both_done) {
- ks_warn(ks, "Memory selftest not finished\n");
+ netdev_warn(ks->netdev, "Memory selftest not finished\n");
return 0;
}
if (rd & MBIR_TXMBFA) {
- ks_err(ks, "TX memory selftest fail\n");
+ netdev_err(ks->netdev, "TX memory selftest fail\n");
ret |= 1;
}
if (rd & MBIR_RXMBFA) {
- ks_err(ks, "RX memory selftest fail\n");
+ netdev_err(ks->netdev, "RX memory selftest fail\n");
ret |= 2;
}
@@ -1293,9 +1283,9 @@
goto err_netdev;
}
- dev_info(&spi->dev, "revision %d, MAC %pM, IRQ %d\n",
- CIDER_REV_GET(ks8851_rdreg16(ks, KS_CIDER)),
- ndev->dev_addr, ndev->irq);
+ netdev_info(ndev, "revision %d, MAC %pM, IRQ %d\n",
+ CIDER_REV_GET(ks8851_rdreg16(ks, KS_CIDER)),
+ ndev->dev_addr, ndev->irq);
return 0;
@@ -1314,7 +1304,7 @@
struct ks8851_net *priv = dev_get_drvdata(&spi->dev);
if (netif_msg_drv(priv))
- dev_info(&spi->dev, "remove");
+ dev_info(&spi->dev, "remove\n");
unregister_netdev(priv->netdev);
free_irq(spi->irq, priv);
diff --git a/drivers/net/ks8851_mll.c b/drivers/net/ks8851_mll.c
index 84b0e15..d3c6a77 100644
--- a/drivers/net/ks8851_mll.c
+++ b/drivers/net/ks8851_mll.c
@@ -21,6 +21,8 @@
* KS8851 16bit MLL chip from Micrel Inc.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
@@ -458,11 +460,6 @@
static int msg_enable;
-#define ks_info(_ks, _msg...) dev_info(&(_ks)->pdev->dev, _msg)
-#define ks_warn(_ks, _msg...) dev_warn(&(_ks)->pdev->dev, _msg)
-#define ks_dbg(_ks, _msg...) dev_dbg(&(_ks)->pdev->dev, _msg)
-#define ks_err(_ks, _msg...) dev_err(&(_ks)->pdev->dev, _msg)
-
#define BE3 0x8000 /* Byte Enable 3 */
#define BE2 0x4000 /* Byte Enable 2 */
#define BE1 0x2000 /* Byte Enable 1 */
@@ -624,8 +621,7 @@
{
unsigned pmecr;
- if (netif_msg_hw(ks))
- ks_dbg(ks, "setting power mode %d\n", pwrmode);
+ netif_dbg(ks, hw, ks->netdev, "setting power mode %d\n", pwrmode);
ks_rdreg16(ks, KS_GRR);
pmecr = ks_rdreg16(ks, KS_PMECR);
@@ -809,7 +805,7 @@
skb->protocol = eth_type_trans(skb, netdev);
netif_rx(skb);
} else {
- printk(KERN_ERR "%s: err:skb alloc\n", __func__);
+ pr_err("%s: err:skb alloc\n", __func__);
ks_wrreg16(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_RRXEF));
if (skb)
dev_kfree_skb_irq(skb);
@@ -836,9 +832,8 @@
netif_carrier_off(netdev);
link_up_status = false;
}
- if (netif_msg_link(ks))
- ks_dbg(ks, "%s: %s\n",
- __func__, link_up_status ? "UP" : "DOWN");
+ netif_dbg(ks, link, ks->netdev,
+ "%s: %s\n", __func__, link_up_status ? "UP" : "DOWN");
}
/**
@@ -908,15 +903,13 @@
* else at the moment.
*/
- if (netif_msg_ifup(ks))
- ks_dbg(ks, "%s - entry\n", __func__);
+ netif_dbg(ks, ifup, ks->netdev, "%s - entry\n", __func__);
/* reset the HW */
err = request_irq(ks->irq, ks_irq, KS_INT_FLAGS, DRV_NAME, netdev);
if (err) {
- printk(KERN_ERR "Failed to request IRQ: %d: %d\n",
- ks->irq, err);
+ pr_err("Failed to request IRQ: %d: %d\n", ks->irq, err);
return err;
}
@@ -929,8 +922,7 @@
ks_enable_qmu(ks);
netif_start_queue(ks->netdev);
- if (netif_msg_ifup(ks))
- ks_dbg(ks, "network device %s up\n", netdev->name);
+ netif_dbg(ks, ifup, ks->netdev, "network device up\n");
return 0;
}
@@ -947,8 +939,7 @@
{
struct ks_net *ks = netdev_priv(netdev);
- if (netif_msg_ifdown(ks))
- ks_info(ks, "%s: shutting down\n", netdev->name);
+ netif_info(ks, ifdown, netdev, "shutting down\n");
netif_stop_queue(netdev);
@@ -1429,21 +1420,21 @@
rd = ks_rdreg16(ks, KS_MBIR);
if ((rd & both_done) != both_done) {
- ks_warn(ks, "Memory selftest not finished\n");
+ netdev_warn(ks->netdev, "Memory selftest not finished\n");
return 0;
}
if (rd & MBIR_TXMBFA) {
- ks_err(ks, "TX memory selftest fails\n");
+ netdev_err(ks->netdev, "TX memory selftest fails\n");
ret |= 1;
}
if (rd & MBIR_RXMBFA) {
- ks_err(ks, "RX memory selftest fails\n");
+ netdev_err(ks->netdev, "RX memory selftest fails\n");
ret |= 2;
}
- ks_info(ks, "the selftest passes\n");
+ netdev_info(ks->netdev, "the selftest passes\n");
return ret;
}
@@ -1514,7 +1505,7 @@
ks->frame_head_info = (struct type_frame_head *) \
kmalloc(MHEADER_SIZE, GFP_KERNEL);
if (!ks->frame_head_info) {
- printk(KERN_ERR "Error: Fail to allocate frame memory\n");
+ pr_err("Error: Fail to allocate frame memory\n");
return false;
}
@@ -1580,7 +1571,7 @@
ks->mii.mdio_read = ks_phy_read;
ks->mii.mdio_write = ks_phy_write;
- ks_info(ks, "message enable is %d\n", msg_enable);
+ netdev_info(netdev, "message enable is %d\n", msg_enable);
/* set the default message enable */
ks->msg_enable = netif_msg_init(msg_enable, (NETIF_MSG_DRV |
NETIF_MSG_PROBE |
@@ -1589,13 +1580,13 @@
/* simple check for a valid chip being connected to the bus */
if ((ks_rdreg16(ks, KS_CIDER) & ~CIDER_REV_MASK) != CIDER_ID) {
- ks_err(ks, "failed to read device ID\n");
+ netdev_err(netdev, "failed to read device ID\n");
err = -ENODEV;
goto err_register;
}
if (ks_read_selftest(ks)) {
- ks_err(ks, "failed to read device ID\n");
+ netdev_err(netdev, "failed to read device ID\n");
err = -ENODEV;
goto err_register;
}
@@ -1626,9 +1617,8 @@
id = ks_rdreg16(ks, KS_CIDER);
- printk(KERN_INFO DRV_NAME
- " Found chip, family: 0x%x, id: 0x%x, rev: 0x%x\n",
- (id >> 8) & 0xff, (id >> 4) & 0xf, (id >> 1) & 0x7);
+ netdev_info(netdev, "Found chip, family: 0x%x, id: 0x%x, rev: 0x%x\n",
+ (id >> 8) & 0xff, (id >> 4) & 0xf, (id >> 1) & 0x7);
return 0;
err_register:
diff --git a/drivers/net/ksz884x.c b/drivers/net/ksz884x.c
index 0f59099..b47a2b3 100644
--- a/drivers/net/ksz884x.c
+++ b/drivers/net/ksz884x.c
@@ -14,10 +14,11 @@
* GNU General Public License for more details.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
-#include <linux/version.h>
#include <linux/ioport.h>
#include <linux/pci.h>
#include <linux/proc_fs.h>
@@ -1483,11 +1484,6 @@
int promiscuous;
};
-#define ks_info(_ks, _msg...) dev_info(&(_ks)->pdev->dev, _msg)
-#define ks_warn(_ks, _msg...) dev_warn(&(_ks)->pdev->dev, _msg)
-#define ks_dbg(_ks, _msg...) dev_dbg(&(_ks)->pdev->dev, _msg)
-#define ks_err(_ks, _msg...) dev_err(&(_ks)->pdev->dev, _msg)
-
#define DRV_NAME "KSZ884X PCI"
#define DEVICE_NAME "KSZ884x PCI"
#define DRV_VERSION "1.0.0"
@@ -3834,7 +3830,7 @@
alloc >>= 1;
}
if (alloc != 1 || shift < MIN_DESC_SHIFT) {
- printk(KERN_ALERT "Hardware descriptor numbers not right!\n");
+ pr_alert("Hardware descriptor numbers not right!\n");
while (alloc) {
shift++;
alloc >>= 1;
@@ -4545,8 +4541,7 @@
(((sizeof(struct ksz_hw_desc) + DESC_ALIGNMENT - 1) /
DESC_ALIGNMENT) * DESC_ALIGNMENT);
if (hw->rx_desc_info.size != sizeof(struct ksz_hw_desc))
- printk(KERN_ALERT
- "Hardware descriptor size not right!\n");
+ pr_alert("Hardware descriptor size not right!\n");
ksz_check_desc_num(&hw->rx_desc_info);
ksz_check_desc_num(&hw->tx_desc_info);
@@ -5319,10 +5314,10 @@
u32 data;
hw->intr_mask &= ~KS884X_INT_TX_STOPPED;
- printk(KERN_INFO "Tx stopped\n");
+ pr_info("Tx stopped\n");
data = readl(hw->io + KS_DMA_TX_CTRL);
if (!(data & DMA_TX_ENABLE))
- printk(KERN_INFO "Tx disabled\n");
+ pr_info("Tx disabled\n");
break;
}
} while (0);
@@ -5495,6 +5490,18 @@
return 0;
}
+static void set_media_state(struct net_device *dev, int media_state)
+{
+ struct dev_priv *priv = netdev_priv(dev);
+
+ if (media_state == priv->media_state)
+ netif_carrier_on(dev);
+ else
+ netif_carrier_off(dev);
+ netif_info(priv, link, dev, "link %s\n",
+ media_state == priv->media_state ? "on" : "off");
+}
+
/**
* netdev_open - open network device
* @dev: Network device.
@@ -5584,15 +5591,7 @@
priv->media_state = port->linked->state;
- if (media_connected == priv->media_state)
- netif_carrier_on(dev);
- else
- netif_carrier_off(dev);
- if (netif_msg_link(priv))
- printk(KERN_INFO "%s link %s\n", dev->name,
- (media_connected == priv->media_state ?
- "on" : "off"));
-
+ set_media_state(dev, media_connected);
netif_start_queue(dev);
return 0;
@@ -6682,16 +6681,8 @@
{
if (priv->media_state != port->linked->state) {
priv->media_state = port->linked->state;
- if (netif_running(dev)) {
- if (media_connected == priv->media_state)
- netif_carrier_on(dev);
- else
- netif_carrier_off(dev);
- if (netif_msg_link(priv))
- printk(KERN_INFO "%s link %s\n", dev->name,
- (media_connected == priv->media_state ?
- "on" : "off"));
- }
+ if (netif_running(dev))
+ set_media_state(dev, media_connected);
}
}
@@ -6985,7 +6976,7 @@
int pi;
int port_count;
int result;
- char banner[80];
+ char banner[sizeof(version)];
struct ksz_switch *sw = NULL;
result = pci_enable_device(pdev);
@@ -7009,10 +7000,9 @@
result = -ENOMEM;
- info = kmalloc(sizeof(struct platform_info), GFP_KERNEL);
+ info = kzalloc(sizeof(struct platform_info), GFP_KERNEL);
if (!info)
goto pcidev_init_dev_err;
- memset(info, 0, sizeof(struct platform_info));
hw_priv = &info->dev_info;
hw_priv->pdev = pdev;
@@ -7026,15 +7016,15 @@
cnt = hw_init(hw);
if (!cnt) {
if (msg_enable & NETIF_MSG_PROBE)
- printk(KERN_ALERT "chip not detected\n");
+ pr_alert("chip not detected\n");
result = -ENODEV;
goto pcidev_init_alloc_err;
}
- sprintf(banner, "%s\n", version);
- banner[13] = cnt + '0';
- ks_info(hw_priv, "%s", banner);
- ks_dbg(hw_priv, "Mem = %p; IRQ = %d\n", hw->io, pdev->irq);
+ snprintf(banner, sizeof(banner), "%s", version);
+ banner[13] = cnt + '0'; /* Replace x in "Micrel KSZ884x" */
+ dev_info(&hw_priv->pdev->dev, "%s\n", banner);
+ dev_dbg(&hw_priv->pdev->dev, "Mem = %p; IRQ = %d\n", hw->io, pdev->irq);
/* Assume device is KSZ8841. */
hw->dev_count = 1;
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 40faa36..445e73c 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -748,6 +748,9 @@
list_for_each_entry_safe(vlan, next, &port->vlans, list)
vlan->dev->rtnl_link_ops->dellink(vlan->dev, NULL);
break;
+ case NETDEV_PRE_TYPE_CHANGE:
+ /* Forbid underlaying device to change its type. */
+ return NOTIFY_BAD;
}
return NOTIFY_DONE;
}
diff --git a/drivers/net/mlx4/en_netdev.c b/drivers/net/mlx4/en_netdev.c
index c48b0f4b..7cd0933 100644
--- a/drivers/net/mlx4/en_netdev.c
+++ b/drivers/net/mlx4/en_netdev.c
@@ -160,39 +160,29 @@
static void mlx4_en_clear_list(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
- struct dev_mc_list *plist = priv->mc_list;
- struct dev_mc_list *next;
- while (plist) {
- next = plist->next;
- kfree(plist);
- plist = next;
- }
- priv->mc_list = NULL;
+ kfree(priv->mc_addrs);
+ priv->mc_addrs_cnt = 0;
}
static void mlx4_en_cache_mclist(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct dev_mc_list *mclist;
- struct dev_mc_list *tmp;
- struct dev_mc_list *plist = NULL;
+ char *mc_addrs;
+ int mc_addrs_cnt = netdev_mc_count(dev);
+ int i;
- for (mclist = dev->mc_list; mclist; mclist = mclist->next) {
- tmp = kmalloc(sizeof(struct dev_mc_list), GFP_ATOMIC);
- if (!tmp) {
- en_err(priv, "failed to allocate multicast list\n");
- mlx4_en_clear_list(dev);
- return;
- }
- memcpy(tmp, mclist, sizeof(struct dev_mc_list));
- tmp->next = NULL;
- if (plist)
- plist->next = tmp;
- else
- priv->mc_list = tmp;
- plist = tmp;
+ mc_addrs = kmalloc(mc_addrs_cnt * ETH_ALEN, GFP_ATOMIC);
+ if (!mc_addrs) {
+ en_err(priv, "failed to allocate multicast list\n");
+ return;
}
+ i = 0;
+ netdev_for_each_mc_addr(mclist, dev)
+ memcpy(mc_addrs + i++ * ETH_ALEN, mclist->dmi_addr, ETH_ALEN);
+ priv->mc_addrs = mc_addrs;
+ priv->mc_addrs_cnt = mc_addrs_cnt;
}
@@ -212,7 +202,6 @@
mcast_task);
struct mlx4_en_dev *mdev = priv->mdev;
struct net_device *dev = priv->dev;
- struct dev_mc_list *mclist;
u64 mcast_addr = 0;
int err;
@@ -288,6 +277,8 @@
if (err)
en_err(priv, "Failed disabling multicast filter\n");
} else {
+ int i;
+
err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
0, MLX4_MCAST_DISABLE);
if (err)
@@ -302,8 +293,9 @@
netif_tx_lock_bh(dev);
mlx4_en_cache_mclist(dev);
netif_tx_unlock_bh(dev);
- for (mclist = priv->mc_list; mclist; mclist = mclist->next) {
- mcast_addr = mlx4_en_mac_to_u64(mclist->dmi_addr);
+ for (i = 0; i < priv->mc_addrs_cnt; i++) {
+ mcast_addr =
+ mlx4_en_mac_to_u64(priv->mc_addrs + i * ETH_ALEN);
mlx4_SET_MCAST_FLTR(mdev->dev, priv->port,
mcast_addr, 0, MLX4_MCAST_CONFIG);
}
@@ -984,7 +976,6 @@
priv->flags = prof->flags;
priv->tx_ring_num = prof->tx_ring_num;
priv->rx_ring_num = prof->rx_ring_num;
- priv->mc_list = NULL;
priv->mac_index = -1;
priv->msg_enable = MLX4_EN_MSG_LEVEL;
spin_lock_init(&priv->stats_lock);
diff --git a/drivers/net/mlx4/mlx4_en.h b/drivers/net/mlx4/mlx4_en.h
index 82c3ebc..b55e46c 100644
--- a/drivers/net/mlx4/mlx4_en.h
+++ b/drivers/net/mlx4/mlx4_en.h
@@ -492,7 +492,8 @@
struct mlx4_en_perf_stats pstats;
struct mlx4_en_pkt_stats pkstats;
struct mlx4_en_port_stats port_stats;
- struct dev_mc_list *mc_list;
+ char *mc_addrs;
+ int mc_addrs_cnt;
struct mlx4_en_stat_out_mbox hw_stats;
};
diff --git a/drivers/net/phy/mdio-bitbang.c b/drivers/net/phy/mdio-bitbang.c
index 2576055..0ff0661 100644
--- a/drivers/net/phy/mdio-bitbang.c
+++ b/drivers/net/phy/mdio-bitbang.c
@@ -23,8 +23,13 @@
#include <linux/types.h>
#include <linux/delay.h>
-#define MDIO_READ 1
-#define MDIO_WRITE 0
+#define MDIO_READ 2
+#define MDIO_WRITE 1
+
+#define MDIO_C45 (1<<15)
+#define MDIO_C45_ADDR (MDIO_C45 | 0)
+#define MDIO_C45_READ (MDIO_C45 | 3)
+#define MDIO_C45_WRITE (MDIO_C45 | 1)
#define MDIO_SETUP_TIME 10
#define MDIO_HOLD_TIME 10
@@ -90,7 +95,7 @@
/* Utility to send the preamble, address, and
* register (common to read and write).
*/
-static void mdiobb_cmd(struct mdiobb_ctrl *ctrl, int read, u8 phy, u8 reg)
+static void mdiobb_cmd(struct mdiobb_ctrl *ctrl, int op, u8 phy, u8 reg)
{
const struct mdiobb_ops *ops = ctrl->ops;
int i;
@@ -109,23 +114,56 @@
for (i = 0; i < 32; i++)
mdiobb_send_bit(ctrl, 1);
- /* send the start bit (01) and the read opcode (10) or write (10) */
+ /* send the start bit (01) and the read opcode (10) or write (10).
+ Clause 45 operation uses 00 for the start and 11, 10 for
+ read/write */
mdiobb_send_bit(ctrl, 0);
- mdiobb_send_bit(ctrl, 1);
- mdiobb_send_bit(ctrl, read);
- mdiobb_send_bit(ctrl, !read);
+ if (op & MDIO_C45)
+ mdiobb_send_bit(ctrl, 0);
+ else
+ mdiobb_send_bit(ctrl, 1);
+ mdiobb_send_bit(ctrl, (op >> 1) & 1);
+ mdiobb_send_bit(ctrl, (op >> 0) & 1);
mdiobb_send_num(ctrl, phy, 5);
mdiobb_send_num(ctrl, reg, 5);
}
+/* In clause 45 mode all commands are prefixed by MDIO_ADDR to specify the
+ lower 16 bits of the 21 bit address. This transfer is done identically to a
+ MDIO_WRITE except for a different code. To enable clause 45 mode or
+ MII_ADDR_C45 into the address. Theoretically clause 45 and normal devices
+ can exist on the same bus. Normal devices should ignore the MDIO_ADDR
+ phase. */
+static int mdiobb_cmd_addr(struct mdiobb_ctrl *ctrl, int phy, u32 addr)
+{
+ unsigned int dev_addr = (addr >> 16) & 0x1F;
+ unsigned int reg = addr & 0xFFFF;
+ mdiobb_cmd(ctrl, MDIO_C45_ADDR, phy, dev_addr);
+
+ /* send the turnaround (10) */
+ mdiobb_send_bit(ctrl, 1);
+ mdiobb_send_bit(ctrl, 0);
+
+ mdiobb_send_num(ctrl, reg, 16);
+
+ ctrl->ops->set_mdio_dir(ctrl, 0);
+ mdiobb_get_bit(ctrl);
+
+ return dev_addr;
+}
static int mdiobb_read(struct mii_bus *bus, int phy, int reg)
{
struct mdiobb_ctrl *ctrl = bus->priv;
int ret, i;
- mdiobb_cmd(ctrl, MDIO_READ, phy, reg);
+ if (reg & MII_ADDR_C45) {
+ reg = mdiobb_cmd_addr(ctrl, phy, reg);
+ mdiobb_cmd(ctrl, MDIO_C45_READ, phy, reg);
+ } else
+ mdiobb_cmd(ctrl, MDIO_READ, phy, reg);
+
ctrl->ops->set_mdio_dir(ctrl, 0);
/* check the turnaround bit: the PHY should be driving it to zero */
@@ -148,7 +186,11 @@
{
struct mdiobb_ctrl *ctrl = bus->priv;
- mdiobb_cmd(ctrl, MDIO_WRITE, phy, reg);
+ if (reg & MII_ADDR_C45) {
+ reg = mdiobb_cmd_addr(ctrl, phy, reg);
+ mdiobb_cmd(ctrl, MDIO_C45_WRITE, phy, reg);
+ } else
+ mdiobb_cmd(ctrl, MDIO_WRITE, phy, reg);
/* send the turnaround (10) */
mdiobb_send_bit(ctrl, 1);
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index e17b702..6a6b819 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -208,7 +208,7 @@
* because the bus read/write functions may wait for an interrupt
* to conclude the operation.
*/
-int mdiobus_read(struct mii_bus *bus, int addr, u16 regnum)
+int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum)
{
int retval;
@@ -233,7 +233,7 @@
* because the bus read/write functions may wait for an interrupt
* to conclude the operation.
*/
-int mdiobus_write(struct mii_bus *bus, int addr, u16 regnum, u16 val)
+int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val)
{
int err;
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index 9d3ebf3..964305c 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -23,6 +23,7 @@
#include <linux/tcp.h>
#include <linux/init.h>
#include <linux/dma-mapping.h>
+#include <linux/pm_runtime.h>
#include <asm/system.h>
#include <asm/io.h>
@@ -504,6 +505,7 @@
struct mii_if_info mii;
struct rtl8169_counters counters;
+ u32 saved_wolopts;
};
MODULE_AUTHOR("Realtek and the Linux r8169 crew <netdev@vger.kernel.org>");
@@ -744,53 +746,61 @@
spin_lock_irqsave(&tp->lock, flags);
if (tp->link_ok(ioaddr)) {
+ /* This is to cancel a scheduled suspend if there's one. */
+ pm_request_resume(&tp->pci_dev->dev);
netif_carrier_on(dev);
netif_info(tp, ifup, dev, "link up\n");
} else {
netif_carrier_off(dev);
netif_info(tp, ifdown, dev, "link down\n");
+ pm_schedule_suspend(&tp->pci_dev->dev, 100);
}
spin_unlock_irqrestore(&tp->lock, flags);
}
+#define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST | WAKE_MCAST)
+
+static u32 __rtl8169_get_wol(struct rtl8169_private *tp)
+{
+ void __iomem *ioaddr = tp->mmio_addr;
+ u8 options;
+ u32 wolopts = 0;
+
+ options = RTL_R8(Config1);
+ if (!(options & PMEnable))
+ return 0;
+
+ options = RTL_R8(Config3);
+ if (options & LinkUp)
+ wolopts |= WAKE_PHY;
+ if (options & MagicPacket)
+ wolopts |= WAKE_MAGIC;
+
+ options = RTL_R8(Config5);
+ if (options & UWF)
+ wolopts |= WAKE_UCAST;
+ if (options & BWF)
+ wolopts |= WAKE_BCAST;
+ if (options & MWF)
+ wolopts |= WAKE_MCAST;
+
+ return wolopts;
+}
+
static void rtl8169_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
{
struct rtl8169_private *tp = netdev_priv(dev);
- void __iomem *ioaddr = tp->mmio_addr;
- u8 options;
-
- wol->wolopts = 0;
-
-#define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST | WAKE_MCAST)
- wol->supported = WAKE_ANY;
spin_lock_irq(&tp->lock);
- options = RTL_R8(Config1);
- if (!(options & PMEnable))
- goto out_unlock;
+ wol->supported = WAKE_ANY;
+ wol->wolopts = __rtl8169_get_wol(tp);
- options = RTL_R8(Config3);
- if (options & LinkUp)
- wol->wolopts |= WAKE_PHY;
- if (options & MagicPacket)
- wol->wolopts |= WAKE_MAGIC;
-
- options = RTL_R8(Config5);
- if (options & UWF)
- wol->wolopts |= WAKE_UCAST;
- if (options & BWF)
- wol->wolopts |= WAKE_BCAST;
- if (options & MWF)
- wol->wolopts |= WAKE_MCAST;
-
-out_unlock:
spin_unlock_irq(&tp->lock);
}
-static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
{
- struct rtl8169_private *tp = netdev_priv(dev);
void __iomem *ioaddr = tp->mmio_addr;
unsigned int i;
static const struct {
@@ -807,23 +817,29 @@
{ WAKE_ANY, Config5, LanWake }
};
- spin_lock_irq(&tp->lock);
-
RTL_W8(Cfg9346, Cfg9346_Unlock);
for (i = 0; i < ARRAY_SIZE(cfg); i++) {
u8 options = RTL_R8(cfg[i].reg) & ~cfg[i].mask;
- if (wol->wolopts & cfg[i].opt)
+ if (wolopts & cfg[i].opt)
options |= cfg[i].mask;
RTL_W8(cfg[i].reg, options);
}
RTL_W8(Cfg9346, Cfg9346_Lock);
+}
+
+static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+ struct rtl8169_private *tp = netdev_priv(dev);
+
+ spin_lock_irq(&tp->lock);
if (wol->wolopts)
tp->features |= RTL_FEATURE_WOL;
else
tp->features &= ~RTL_FEATURE_WOL;
+ __rtl8169_set_wol(tp, wol->wolopts);
device_set_wakeup_enable(&tp->pci_dev->dev, wol->wolopts);
spin_unlock_irq(&tp->lock);
@@ -3189,6 +3205,12 @@
device_set_wakeup_enable(&pdev->dev, tp->features & RTL_FEATURE_WOL);
+ if (pci_dev_run_wake(pdev)) {
+ pm_runtime_set_active(&pdev->dev);
+ pm_runtime_enable(&pdev->dev);
+ }
+ pm_runtime_idle(&pdev->dev);
+
out:
return rc;
@@ -3211,10 +3233,18 @@
struct net_device *dev = pci_get_drvdata(pdev);
struct rtl8169_private *tp = netdev_priv(dev);
+ pm_runtime_get_sync(&pdev->dev);
+
flush_scheduled_work();
unregister_netdev(dev);
+ if (pci_dev_run_wake(pdev)) {
+ pm_runtime_disable(&pdev->dev);
+ pm_runtime_set_suspended(&pdev->dev);
+ }
+ pm_runtime_put_noidle(&pdev->dev);
+
/* restore original MAC address */
rtl_rar_set(tp, dev->perm_addr);
@@ -3237,6 +3267,7 @@
struct pci_dev *pdev = tp->pci_dev;
int retval = -ENOMEM;
+ pm_runtime_get_sync(&pdev->dev);
rtl8169_set_rxbufsize(tp, dev);
@@ -3247,7 +3278,7 @@
tp->TxDescArray = pci_alloc_consistent(pdev, R8169_TX_RING_BYTES,
&tp->TxPhyAddr);
if (!tp->TxDescArray)
- goto out;
+ goto err_pm_runtime_put;
tp->RxDescArray = pci_alloc_consistent(pdev, R8169_RX_RING_BYTES,
&tp->RxPhyAddr);
@@ -3274,6 +3305,9 @@
rtl8169_request_timer(dev);
+ tp->saved_wolopts = 0;
+ pm_runtime_put_noidle(&pdev->dev);
+
rtl8169_check_link_status(dev, tp, tp->mmio_addr);
out:
return retval;
@@ -3283,9 +3317,13 @@
err_free_rx_1:
pci_free_consistent(pdev, R8169_RX_RING_BYTES, tp->RxDescArray,
tp->RxPhyAddr);
+ tp->RxDescArray = NULL;
err_free_tx_0:
pci_free_consistent(pdev, R8169_TX_RING_BYTES, tp->TxDescArray,
tp->TxPhyAddr);
+ tp->TxDescArray = NULL;
+err_pm_runtime_put:
+ pm_runtime_put_noidle(&pdev->dev);
goto out;
}
@@ -4692,6 +4730,8 @@
struct rtl8169_private *tp = netdev_priv(dev);
struct pci_dev *pdev = tp->pci_dev;
+ pm_runtime_get_sync(&pdev->dev);
+
/* update counters before going down */
rtl8169_update_counters(dev);
@@ -4706,6 +4746,8 @@
tp->TxDescArray = NULL;
tp->RxDescArray = NULL;
+ pm_runtime_put_sync(&pdev->dev);
+
return 0;
}
@@ -4804,21 +4846,74 @@
return 0;
}
+static void __rtl8169_resume(struct net_device *dev)
+{
+ netif_device_attach(dev);
+ rtl8169_schedule_work(dev, rtl8169_reset_task);
+}
+
static int rtl8169_resume(struct device *device)
{
struct pci_dev *pdev = to_pci_dev(device);
struct net_device *dev = pci_get_drvdata(pdev);
- if (!netif_running(dev))
- goto out;
+ if (netif_running(dev))
+ __rtl8169_resume(dev);
- netif_device_attach(dev);
-
- rtl8169_schedule_work(dev, rtl8169_reset_task);
-out:
return 0;
}
+static int rtl8169_runtime_suspend(struct device *device)
+{
+ struct pci_dev *pdev = to_pci_dev(device);
+ struct net_device *dev = pci_get_drvdata(pdev);
+ struct rtl8169_private *tp = netdev_priv(dev);
+
+ if (!tp->TxDescArray)
+ return 0;
+
+ spin_lock_irq(&tp->lock);
+ tp->saved_wolopts = __rtl8169_get_wol(tp);
+ __rtl8169_set_wol(tp, WAKE_ANY);
+ spin_unlock_irq(&tp->lock);
+
+ rtl8169_net_suspend(dev);
+
+ return 0;
+}
+
+static int rtl8169_runtime_resume(struct device *device)
+{
+ struct pci_dev *pdev = to_pci_dev(device);
+ struct net_device *dev = pci_get_drvdata(pdev);
+ struct rtl8169_private *tp = netdev_priv(dev);
+
+ if (!tp->TxDescArray)
+ return 0;
+
+ spin_lock_irq(&tp->lock);
+ __rtl8169_set_wol(tp, tp->saved_wolopts);
+ tp->saved_wolopts = 0;
+ spin_unlock_irq(&tp->lock);
+
+ __rtl8169_resume(dev);
+
+ return 0;
+}
+
+static int rtl8169_runtime_idle(struct device *device)
+{
+ struct pci_dev *pdev = to_pci_dev(device);
+ struct net_device *dev = pci_get_drvdata(pdev);
+ struct rtl8169_private *tp = netdev_priv(dev);
+
+ if (!tp->TxDescArray)
+ return 0;
+
+ rtl8169_check_link_status(dev, tp, tp->mmio_addr);
+ return -EBUSY;
+}
+
static const struct dev_pm_ops rtl8169_pm_ops = {
.suspend = rtl8169_suspend,
.resume = rtl8169_resume,
@@ -4826,6 +4921,9 @@
.thaw = rtl8169_resume,
.poweroff = rtl8169_suspend,
.restore = rtl8169_resume,
+ .runtime_suspend = rtl8169_runtime_suspend,
+ .runtime_resume = rtl8169_runtime_resume,
+ .runtime_idle = rtl8169_runtime_idle,
};
#define RTL8169_PM_OPS (&rtl8169_pm_ops)
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 6f1e303..7576ad5 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -619,7 +619,7 @@
return;
qeth_l2_del_all_mc(card);
spin_lock_bh(&card->mclock);
- for (dm = dev->mc_list; dm; dm = dm->next)
+ netdev_for_each_mc_addr(dm, dev)
qeth_l2_add_mc(card, dm->da_addr, 0);
netdev_for_each_uc_addr(ha, dev)
diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index c9bf92c..cfd420b 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -37,6 +37,38 @@
__u32 tx_compressed;
};
+struct rtnl_link_stats64 {
+ __u64 rx_packets; /* total packets received */
+ __u64 tx_packets; /* total packets transmitted */
+ __u64 rx_bytes; /* total bytes received */
+ __u64 tx_bytes; /* total bytes transmitted */
+ __u64 rx_errors; /* bad packets received */
+ __u64 tx_errors; /* packet transmit problems */
+ __u64 rx_dropped; /* no space in linux buffers */
+ __u64 tx_dropped; /* no space available in linux */
+ __u64 multicast; /* multicast packets received */
+ __u64 collisions;
+
+ /* detailed rx_errors: */
+ __u64 rx_length_errors;
+ __u64 rx_over_errors; /* receiver ring buff overflow */
+ __u64 rx_crc_errors; /* recved pkt with crc error */
+ __u64 rx_frame_errors; /* recv'd frame alignment error */
+ __u64 rx_fifo_errors; /* recv'r fifo overrun */
+ __u64 rx_missed_errors; /* receiver missed packet */
+
+ /* detailed tx_errors */
+ __u64 tx_aborted_errors;
+ __u64 tx_carrier_errors;
+ __u64 tx_fifo_errors;
+ __u64 tx_heartbeat_errors;
+ __u64 tx_window_errors;
+
+ /* for cslip etc */
+ __u64 rx_compressed;
+ __u64 tx_compressed;
+};
+
/* The struct should be in sync with struct ifmap */
struct rtnl_link_ifmap {
__u64 mem_start;
@@ -83,6 +115,7 @@
IFLA_VF_VLAN,
IFLA_VF_TX_RATE, /* TX Bandwidth Allocation */
IFLA_VFINFO,
+ IFLA_STATS64,
__IFLA_MAX
};
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fa8b476..9fc6ee8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -223,6 +223,7 @@
unsigned dropped;
unsigned time_squeeze;
unsigned cpu_collision;
+ unsigned received_rps;
};
DECLARE_PER_CPU(struct netif_rx_stats, netdev_rx_stat);
@@ -530,6 +531,24 @@
unsigned long tx_dropped;
} ____cacheline_aligned_in_smp;
+/*
+ * This structure holds an RPS map which can be of variable length. The
+ * map is an array of CPUs.
+ */
+struct rps_map {
+ unsigned int len;
+ struct rcu_head rcu;
+ u16 cpus[0];
+};
+#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16)))
+
+/* This structure contains an instance of an RX queue. */
+struct netdev_rx_queue {
+ struct rps_map *rps_map;
+ struct kobject kobj;
+ struct netdev_rx_queue *first;
+ atomic_t count;
+} ____cacheline_aligned_in_smp;
/*
* This structure defines the management hooks for network devices.
@@ -878,6 +897,13 @@
unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */
+ struct kset *queues_kset;
+
+ struct netdev_rx_queue *_rx;
+
+ /* Number of RX queues allocated at alloc_netdev_mq() time */
+ unsigned int num_rx_queues;
+
struct netdev_queue rx_queue;
struct netdev_queue *_tx ____cacheline_aligned_in_smp;
@@ -1311,14 +1337,18 @@
*/
struct softnet_data {
struct Qdisc *output_queue;
- struct sk_buff_head input_pkt_queue;
struct list_head poll_list;
struct sk_buff *completion_queue;
+ /* Elements below can be accessed between CPUs for RPS */
+#ifdef CONFIG_SMP
+ struct call_single_data csd ____cacheline_aligned_in_smp;
+#endif
+ struct sk_buff_head input_pkt_queue;
struct napi_struct backlog;
};
-DECLARE_PER_CPU(struct softnet_data,softnet_data);
+DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
#define HAVE_NETIF_QUEUE
@@ -1975,7 +2005,7 @@
extern int dev_set_promiscuity(struct net_device *dev, int inc);
extern int dev_set_allmulti(struct net_device *dev, int inc);
extern void netdev_state_change(struct net_device *dev);
-extern void netdev_bonding_change(struct net_device *dev,
+extern int netdev_bonding_change(struct net_device *dev,
unsigned long event);
extern void netdev_features_change(struct net_device *dev);
/* Load a device via the kmod */
diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index fee6c2f..f3635fc 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -199,8 +199,8 @@
#define NETDEV_FEAT_CHANGE 0x000B
#define NETDEV_BONDING_FAILOVER 0x000C
#define NETDEV_PRE_UP 0x000D
-#define NETDEV_BONDING_OLDTYPE 0x000E
-#define NETDEV_BONDING_NEWTYPE 0x000F
+#define NETDEV_PRE_TYPE_CHANGE 0x000E
+#define NETDEV_POST_TYPE_CHANGE 0x000F
#define NETDEV_POST_INIT 0x0010
#define NETDEV_UNREGISTER_BATCH 0x0011
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 14d7fdf..d9bce4b 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -81,6 +81,10 @@
*/
#define MII_BUS_ID_SIZE (20 - 3)
+/* Or MII_ADDR_C45 into regnum for read/write on mii_bus to enable the 21 bit
+ IEEE 802.3ae clause 45 addressing mode used by 10GIGE phy chips. */
+#define MII_ADDR_C45 (1<<30)
+
/*
* The Bus class for PHYs. Devices which provide access to
* PHYs should register using this structure
@@ -127,8 +131,8 @@
void mdiobus_unregister(struct mii_bus *bus);
void mdiobus_free(struct mii_bus *bus);
struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
-int mdiobus_read(struct mii_bus *bus, int addr, u16 regnum);
-int mdiobus_write(struct mii_bus *bus, int addr, u16 regnum, u16 val);
+int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum);
+int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val);
#define PHY_INTERRUPT_DISABLED 0x0
@@ -422,7 +426,7 @@
* because the bus read/write functions may wait for an interrupt
* to conclude the operation.
*/
-static inline int phy_read(struct phy_device *phydev, u16 regnum)
+static inline int phy_read(struct phy_device *phydev, u32 regnum)
{
return mdiobus_read(phydev->bus, phydev->addr, regnum);
}
@@ -437,7 +441,7 @@
* because the bus read/write functions may wait for an interrupt
* to conclude the operation.
*/
-static inline int phy_write(struct phy_device *phydev, u16 regnum, u16 val)
+static inline int phy_write(struct phy_device *phydev, u32 regnum, u16 val)
{
return mdiobus_write(phydev->bus, phydev->addr, regnum, val);
}
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 03f816a..def10b0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -300,6 +300,7 @@
* @nfct_reasm: netfilter conntrack re-assembly pointer
* @nf_bridge: Saved data about a bridged frame - see br_netfilter.c
* @skb_iif: ifindex of device we arrived on
+ * @rxhash: the packet hash computed on receive
* @queue_mapping: Queue mapping for multiqueue devices
* @tc_index: Traffic control index
* @tc_verd: traffic control verdict
@@ -375,6 +376,8 @@
#endif
#endif
+ __u32 rxhash;
+
kmemcheck_bitfield_begin(flags2);
__u16 queue_mapping:16;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 4535122..c39a5f4 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -530,6 +530,10 @@
}
unregister_netdevice_many(&list);
break;
+
+ case NETDEV_PRE_TYPE_CHANGE:
+ /* Forbid underlaying device to change its type. */
+ return NOTIFY_BAD;
}
out:
diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c
index b6234b7..326ab45 100644
--- a/net/bluetooth/bnep/netdev.c
+++ b/net/bluetooth/bnep/netdev.c
@@ -87,7 +87,7 @@
memcpy(__skb_put(skb, ETH_ALEN), dev->broadcast, ETH_ALEN);
r->len = htons(ETH_ALEN * 2);
} else {
- struct dev_mc_list *dmi = dev->mc_list;
+ struct dev_mc_list *dmi;
int i, len = skb->len;
if (dev->flags & IFF_BROADCAST) {
@@ -97,12 +97,12 @@
/* FIXME: We should group addresses here. */
- for (i = 0;
- i < netdev_mc_count(dev) && i < BNEP_MAX_MULTICAST_FILTERS;
- i++) {
+ i = 0;
+ netdev_for_each_mc_addr(dmi, dev) {
+ if (i == BNEP_MAX_MULTICAST_FILTERS)
+ break;
memcpy(__skb_put(skb, ETH_ALEN), dmi->dmi_addr, ETH_ALEN);
memcpy(__skb_put(skb, ETH_ALEN), dmi->dmi_addr, ETH_ALEN);
- dmi = dmi->next;
}
r->len = htons(skb->len - len);
}
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 90a9024..5b8a6e7 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -26,12 +26,13 @@
const unsigned char *dest = skb->data;
struct net_bridge_fdb_entry *dst;
struct net_bridge_mdb_entry *mdst;
+ struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats);
+
+ brstats->tx_packets++;
+ brstats->tx_bytes += skb->len;
BR_INPUT_SKB_CB(skb)->brdev = dev;
- dev->stats.tx_packets++;
- dev->stats.tx_bytes += skb->len;
-
skb_reset_mac_header(skb);
skb_pull(skb, ETH_HLEN);
@@ -81,6 +82,31 @@
return 0;
}
+static struct net_device_stats *br_get_stats(struct net_device *dev)
+{
+ struct net_bridge *br = netdev_priv(dev);
+ struct net_device_stats *stats = &dev->stats;
+ struct br_cpu_netstats sum = { 0 };
+ unsigned int cpu;
+
+ for_each_possible_cpu(cpu) {
+ const struct br_cpu_netstats *bstats
+ = per_cpu_ptr(br->stats, cpu);
+
+ sum.tx_bytes += bstats->tx_bytes;
+ sum.tx_packets += bstats->tx_packets;
+ sum.rx_bytes += bstats->rx_bytes;
+ sum.rx_packets += bstats->rx_packets;
+ }
+
+ stats->tx_bytes = sum.tx_bytes;
+ stats->tx_packets = sum.tx_packets;
+ stats->rx_bytes = sum.rx_bytes;
+ stats->rx_packets = sum.rx_packets;
+
+ return stats;
+}
+
static int br_change_mtu(struct net_device *dev, int new_mtu)
{
struct net_bridge *br = netdev_priv(dev);
@@ -180,19 +206,28 @@
.ndo_open = br_dev_open,
.ndo_stop = br_dev_stop,
.ndo_start_xmit = br_dev_xmit,
+ .ndo_get_stats = br_get_stats,
.ndo_set_mac_address = br_set_mac_address,
.ndo_set_multicast_list = br_dev_set_multicast_list,
.ndo_change_mtu = br_change_mtu,
.ndo_do_ioctl = br_dev_ioctl,
};
+static void br_dev_free(struct net_device *dev)
+{
+ struct net_bridge *br = netdev_priv(dev);
+
+ free_percpu(br->stats);
+ free_netdev(dev);
+}
+
void br_dev_setup(struct net_device *dev)
{
random_ether_addr(dev->dev_addr);
ether_setup(dev);
dev->netdev_ops = &br_netdev_ops;
- dev->destructor = free_netdev;
+ dev->destructor = br_dev_free;
SET_ETHTOOL_OPS(dev, &br_ethtool_ops);
dev->tx_queue_len = 0;
dev->priv_flags = IFF_EBRIDGE;
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index b6a3872..b7cdd2e 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -185,6 +185,12 @@
br = netdev_priv(dev);
br->dev = dev;
+ br->stats = alloc_percpu(struct br_cpu_netstats);
+ if (!br->stats) {
+ free_netdev(dev);
+ return NULL;
+ }
+
spin_lock_init(&br->lock);
INIT_LIST_HEAD(&br->port_list);
spin_lock_init(&br->hash_lock);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index d74d570..333dfb7 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -23,9 +23,11 @@
static int br_pass_frame_up(struct sk_buff *skb)
{
struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
+ struct net_bridge *br = netdev_priv(brdev);
+ struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats);
- brdev->stats.rx_packets++;
- brdev->stats.rx_bytes += skb->len;
+ brstats->rx_packets++;
+ brstats->rx_bytes += skb->len;
indev = skb->dev;
skb->dev = brdev;
diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c
index 763a3ec..1413b72 100644
--- a/net/bridge/br_notify.c
+++ b/net/bridge/br_notify.c
@@ -82,6 +82,10 @@
case NETDEV_UNREGISTER:
br_del_if(br, dev);
break;
+
+ case NETDEV_PRE_TYPE_CHANGE:
+ /* Forbid underlaying device to change its type. */
+ return NOTIFY_BAD;
}
/* Events that may cause spanning tree to refresh */
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 846d7d1..791d4ab 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -135,6 +135,14 @@
spinlock_t lock;
struct list_head port_list;
struct net_device *dev;
+
+ struct br_cpu_netstats __percpu {
+ unsigned long rx_packets;
+ unsigned long rx_bytes;
+ unsigned long tx_packets;
+ unsigned long tx_bytes;
+ } *stats;
+
spinlock_t hash_lock;
struct hlist_head hash[BR_HASH_SIZE];
unsigned long feature_mask;
diff --git a/net/core/dev.c b/net/core/dev.c
index 59d4394..c0e2608 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1084,9 +1084,9 @@
}
EXPORT_SYMBOL(netdev_state_change);
-void netdev_bonding_change(struct net_device *dev, unsigned long event)
+int netdev_bonding_change(struct net_device *dev, unsigned long event)
{
- call_netdevice_notifiers(event, dev);
+ return call_netdevice_notifiers(event, dev);
}
EXPORT_SYMBOL(netdev_bonding_change);
@@ -1931,7 +1931,7 @@
return rc;
}
-static u32 skb_tx_hashrnd;
+static u32 hashrnd __read_mostly;
u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
{
@@ -1949,7 +1949,7 @@
else
hash = skb->protocol;
- hash = jhash_1word(hash, skb_tx_hashrnd);
+ hash = jhash_1word(hash, hashrnd);
return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32);
}
@@ -1959,10 +1959,9 @@
{
if (unlikely(queue_index >= dev->real_num_tx_queues)) {
if (net_ratelimit()) {
- WARN(1, "%s selects TX queue %d, but "
+ netdev_warn(dev, "selects TX queue %d, but "
"real number of TX queues is %d\n",
- dev->name, queue_index,
- dev->real_num_tx_queues);
+ queue_index, dev->real_num_tx_queues);
}
return 0;
}
@@ -2175,6 +2174,178 @@
DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
+#ifdef CONFIG_SMP
+/*
+ * get_rps_cpu is called from netif_receive_skb and returns the target
+ * CPU from the RPS map of the receiving queue for a given skb.
+ */
+static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb)
+{
+ struct ipv6hdr *ip6;
+ struct iphdr *ip;
+ struct netdev_rx_queue *rxqueue;
+ struct rps_map *map;
+ int cpu = -1;
+ u8 ip_proto;
+ u32 addr1, addr2, ports, ihl;
+
+ rcu_read_lock();
+
+ if (skb_rx_queue_recorded(skb)) {
+ u16 index = skb_get_rx_queue(skb);
+ if (unlikely(index >= dev->num_rx_queues)) {
+ if (net_ratelimit()) {
+ netdev_warn(dev, "received packet on queue "
+ "%u, but number of RX queues is %u\n",
+ index, dev->num_rx_queues);
+ }
+ goto done;
+ }
+ rxqueue = dev->_rx + index;
+ } else
+ rxqueue = dev->_rx;
+
+ if (!rxqueue->rps_map)
+ goto done;
+
+ if (skb->rxhash)
+ goto got_hash; /* Skip hash computation on packet header */
+
+ switch (skb->protocol) {
+ case __constant_htons(ETH_P_IP):
+ if (!pskb_may_pull(skb, sizeof(*ip)))
+ goto done;
+
+ ip = (struct iphdr *) skb->data;
+ ip_proto = ip->protocol;
+ addr1 = ip->saddr;
+ addr2 = ip->daddr;
+ ihl = ip->ihl;
+ break;
+ case __constant_htons(ETH_P_IPV6):
+ if (!pskb_may_pull(skb, sizeof(*ip6)))
+ goto done;
+
+ ip6 = (struct ipv6hdr *) skb->data;
+ ip_proto = ip6->nexthdr;
+ addr1 = ip6->saddr.s6_addr32[3];
+ addr2 = ip6->daddr.s6_addr32[3];
+ ihl = (40 >> 2);
+ break;
+ default:
+ goto done;
+ }
+ ports = 0;
+ switch (ip_proto) {
+ case IPPROTO_TCP:
+ case IPPROTO_UDP:
+ case IPPROTO_DCCP:
+ case IPPROTO_ESP:
+ case IPPROTO_AH:
+ case IPPROTO_SCTP:
+ case IPPROTO_UDPLITE:
+ if (pskb_may_pull(skb, (ihl * 4) + 4))
+ ports = *((u32 *) (skb->data + (ihl * 4)));
+ break;
+
+ default:
+ break;
+ }
+
+ skb->rxhash = jhash_3words(addr1, addr2, ports, hashrnd);
+ if (!skb->rxhash)
+ skb->rxhash = 1;
+
+got_hash:
+ map = rcu_dereference(rxqueue->rps_map);
+ if (map) {
+ u16 tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
+
+ if (cpu_online(tcpu)) {
+ cpu = tcpu;
+ goto done;
+ }
+ }
+
+done:
+ rcu_read_unlock();
+ return cpu;
+}
+
+/*
+ * This structure holds the per-CPU mask of CPUs for which IPIs are scheduled
+ * to be sent to kick remote softirq processing. There are two masks since
+ * the sending of IPIs must be done with interrupts enabled. The select field
+ * indicates the current mask that enqueue_backlog uses to schedule IPIs.
+ * select is flipped before net_rps_action is called while still under lock,
+ * net_rps_action then uses the non-selected mask to send the IPIs and clears
+ * it without conflicting with enqueue_backlog operation.
+ */
+struct rps_remote_softirq_cpus {
+ cpumask_t mask[2];
+ int select;
+};
+static DEFINE_PER_CPU(struct rps_remote_softirq_cpus, rps_remote_softirq_cpus);
+
+/* Called from hardirq (IPI) context */
+static void trigger_softirq(void *data)
+{
+ struct softnet_data *queue = data;
+ __napi_schedule(&queue->backlog);
+ __get_cpu_var(netdev_rx_stat).received_rps++;
+}
+#endif /* CONFIG_SMP */
+
+/*
+ * enqueue_to_backlog is called to queue an skb to a per CPU backlog
+ * queue (may be a remote CPU queue).
+ */
+static int enqueue_to_backlog(struct sk_buff *skb, int cpu)
+{
+ struct softnet_data *queue;
+ unsigned long flags;
+
+ queue = &per_cpu(softnet_data, cpu);
+
+ local_irq_save(flags);
+ __get_cpu_var(netdev_rx_stat).total++;
+
+ spin_lock(&queue->input_pkt_queue.lock);
+ if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
+ if (queue->input_pkt_queue.qlen) {
+enqueue:
+ __skb_queue_tail(&queue->input_pkt_queue, skb);
+ spin_unlock_irqrestore(&queue->input_pkt_queue.lock,
+ flags);
+ return NET_RX_SUCCESS;
+ }
+
+ /* Schedule NAPI for backlog device */
+ if (napi_schedule_prep(&queue->backlog)) {
+#ifdef CONFIG_SMP
+ if (cpu != smp_processor_id()) {
+ struct rps_remote_softirq_cpus *rcpus =
+ &__get_cpu_var(rps_remote_softirq_cpus);
+
+ cpu_set(cpu, rcpus->mask[rcpus->select]);
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ } else
+ __napi_schedule(&queue->backlog);
+#else
+ __napi_schedule(&queue->backlog);
+#endif
+ }
+ goto enqueue;
+ }
+
+ spin_unlock(&queue->input_pkt_queue.lock);
+
+ __get_cpu_var(netdev_rx_stat).dropped++;
+ local_irq_restore(flags);
+
+ kfree_skb(skb);
+ return NET_RX_DROP;
+}
/**
* netif_rx - post buffer to the network code
@@ -2193,8 +2364,7 @@
int netif_rx(struct sk_buff *skb)
{
- struct softnet_data *queue;
- unsigned long flags;
+ int cpu;
/* if netpoll wants it, pretend we never saw it */
if (netpoll_rx(skb))
@@ -2203,31 +2373,15 @@
if (!skb->tstamp.tv64)
net_timestamp(skb);
- /*
- * The code is rearranged so that the path is the most
- * short when CPU is congested, but is still operating.
- */
- local_irq_save(flags);
- queue = &__get_cpu_var(softnet_data);
+#ifdef CONFIG_SMP
+ cpu = get_rps_cpu(skb->dev, skb);
+ if (cpu < 0)
+ cpu = smp_processor_id();
+#else
+ cpu = smp_processor_id();
+#endif
- __get_cpu_var(netdev_rx_stat).total++;
- if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
- if (queue->input_pkt_queue.qlen) {
-enqueue:
- __skb_queue_tail(&queue->input_pkt_queue, skb);
- local_irq_restore(flags);
- return NET_RX_SUCCESS;
- }
-
- napi_schedule(&queue->backlog);
- goto enqueue;
- }
-
- __get_cpu_var(netdev_rx_stat).dropped++;
- local_irq_restore(flags);
-
- kfree_skb(skb);
- return NET_RX_DROP;
+ return enqueue_to_backlog(skb, cpu);
}
EXPORT_SYMBOL(netif_rx);
@@ -2464,22 +2618,7 @@
rcu_read_unlock();
}
-/**
- * netif_receive_skb - process receive buffer from network
- * @skb: buffer to process
- *
- * netif_receive_skb() is the main receive data processing function.
- * It always succeeds. The buffer may be dropped during processing
- * for congestion control or by the protocol layers.
- *
- * This function may only be called from softirq context and interrupts
- * should be enabled.
- *
- * Return values (usually ignored):
- * NET_RX_SUCCESS: no congestion
- * NET_RX_DROP: packet was dropped
- */
-int netif_receive_skb(struct sk_buff *skb)
+int __netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
struct net_device *orig_dev;
@@ -2590,6 +2729,37 @@
rcu_read_unlock();
return ret;
}
+
+/**
+ * netif_receive_skb - process receive buffer from network
+ * @skb: buffer to process
+ *
+ * netif_receive_skb() is the main receive data processing function.
+ * It always succeeds. The buffer may be dropped during processing
+ * for congestion control or by the protocol layers.
+ *
+ * This function may only be called from softirq context and interrupts
+ * should be enabled.
+ *
+ * Return values (usually ignored):
+ * NET_RX_SUCCESS: no congestion
+ * NET_RX_DROP: packet was dropped
+ */
+int netif_receive_skb(struct sk_buff *skb)
+{
+#ifdef CONFIG_SMP
+ int cpu;
+
+ cpu = get_rps_cpu(skb->dev, skb);
+
+ if (cpu < 0)
+ return __netif_receive_skb(skb);
+ else
+ return enqueue_to_backlog(skb, cpu);
+#else
+ return __netif_receive_skb(skb);
+#endif
+}
EXPORT_SYMBOL(netif_receive_skb);
/* Network device is going away, flush any packets still pending */
@@ -2916,16 +3086,16 @@
do {
struct sk_buff *skb;
- local_irq_disable();
+ spin_lock_irq(&queue->input_pkt_queue.lock);
skb = __skb_dequeue(&queue->input_pkt_queue);
if (!skb) {
__napi_complete(napi);
- local_irq_enable();
+ spin_unlock_irq(&queue->input_pkt_queue.lock);
break;
}
- local_irq_enable();
+ spin_unlock_irq(&queue->input_pkt_queue.lock);
- netif_receive_skb(skb);
+ __netif_receive_skb(skb);
} while (++work < quota && jiffies == start_time);
return work;
@@ -3014,6 +3184,24 @@
}
EXPORT_SYMBOL(netif_napi_del);
+#ifdef CONFIG_SMP
+/*
+ * net_rps_action sends any pending IPI's for rps. This is only called from
+ * softirq and interrupts must be enabled.
+ */
+static void net_rps_action(cpumask_t *mask)
+{
+ int cpu;
+
+ /* Send pending IPI's to kick RPS processing on remote cpus. */
+ for_each_cpu_mask_nr(cpu, *mask) {
+ struct softnet_data *queue = &per_cpu(softnet_data, cpu);
+ if (cpu_online(cpu))
+ __smp_call_function_single(cpu, &queue->csd, 0);
+ }
+ cpus_clear(*mask);
+}
+#endif
static void net_rx_action(struct softirq_action *h)
{
@@ -3021,6 +3209,10 @@
unsigned long time_limit = jiffies + 2;
int budget = netdev_budget;
void *have;
+#ifdef CONFIG_SMP
+ int select;
+ struct rps_remote_softirq_cpus *rcpus;
+#endif
local_irq_disable();
@@ -3083,8 +3275,18 @@
netpoll_poll_unlock(have);
}
out:
+#ifdef CONFIG_SMP
+ rcpus = &__get_cpu_var(rps_remote_softirq_cpus);
+ select = rcpus->select;
+ rcpus->select ^= 1;
+
local_irq_enable();
+ net_rps_action(&rcpus->mask[select]);
+#else
+ local_irq_enable();
+#endif
+
#ifdef CONFIG_NET_DMA
/*
* There may not be any more sk_buffs coming right now, so push
@@ -3329,10 +3531,10 @@
{
struct netif_rx_stats *s = v;
- seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
+ seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
s->total, s->dropped, s->time_squeeze, 0,
0, 0, 0, 0, /* was fastroute */
- s->cpu_collision);
+ s->cpu_collision, s->received_rps);
return 0;
}
@@ -5069,6 +5271,23 @@
dev->iflink = -1;
+ if (!dev->num_rx_queues) {
+ /*
+ * Allocate a single RX queue if driver never called
+ * alloc_netdev_mq
+ */
+
+ dev->_rx = kzalloc(sizeof(struct netdev_rx_queue), GFP_KERNEL);
+ if (!dev->_rx) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ dev->_rx->first = dev->_rx;
+ atomic_set(&dev->_rx->count, 1);
+ dev->num_rx_queues = 1;
+ }
+
/* Init, if this function is available */
if (dev->netdev_ops->ndo_init) {
ret = dev->netdev_ops->ndo_init(dev);
@@ -5426,9 +5645,11 @@
void (*setup)(struct net_device *), unsigned int queue_count)
{
struct netdev_queue *tx;
+ struct netdev_rx_queue *rx;
struct net_device *dev;
size_t alloc_size;
struct net_device *p;
+ int i;
BUG_ON(strlen(name) >= sizeof(dev->name));
@@ -5454,11 +5675,27 @@
goto free_p;
}
+ rx = kcalloc(queue_count, sizeof(struct netdev_rx_queue), GFP_KERNEL);
+ if (!rx) {
+ printk(KERN_ERR "alloc_netdev: Unable to allocate "
+ "rx queues.\n");
+ goto free_tx;
+ }
+
+ atomic_set(&rx->count, queue_count);
+
+ /*
+ * Set a pointer to first element in the array which holds the
+ * reference count.
+ */
+ for (i = 0; i < queue_count; i++)
+ rx[i].first = rx;
+
dev = PTR_ALIGN(p, NETDEV_ALIGN);
dev->padded = (char *)dev - (char *)p;
if (dev_addr_init(dev))
- goto free_tx;
+ goto free_rx;
dev_unicast_init(dev);
@@ -5468,6 +5705,9 @@
dev->num_tx_queues = queue_count;
dev->real_num_tx_queues = queue_count;
+ dev->_rx = rx;
+ dev->num_rx_queues = queue_count;
+
dev->gso_max_size = GSO_MAX_SIZE;
netdev_init_queues(dev);
@@ -5482,9 +5722,10 @@
strcpy(dev->name, name);
return dev;
+free_rx:
+ kfree(rx);
free_tx:
kfree(tx);
-
free_p:
kfree(p);
return NULL;
@@ -5987,6 +6228,12 @@
queue->completion_queue = NULL;
INIT_LIST_HEAD(&queue->poll_list);
+#ifdef CONFIG_SMP
+ queue->csd.func = trigger_softirq;
+ queue->csd.info = queue;
+ queue->csd.flags = 0;
+#endif
+
queue->backlog.poll = process_backlog;
queue->backlog.weight = weight_p;
queue->backlog.gro_list = NULL;
@@ -6025,7 +6272,7 @@
static int __init initialize_hashrnd(void)
{
- get_random_bytes(&skb_tx_hashrnd, sizeof(skb_tx_hashrnd));
+ get_random_bytes(&hashrnd, sizeof(hashrnd));
return 0;
}
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 9a24377..2ff3489 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -108,7 +108,7 @@
struct fib_rules_ops *ops;
int err;
- ops = kmemdup(tmpl, sizeof (*ops), GFP_KERNEL);
+ ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL);
if (ops == NULL)
return ERR_PTR(-ENOMEM);
@@ -123,7 +123,6 @@
return ops;
}
-
EXPORT_SYMBOL_GPL(fib_rules_register);
void fib_rules_cleanup_ops(struct fib_rules_ops *ops)
@@ -157,7 +156,6 @@
call_rcu(&ops->rcu, fib_rules_put_rcu);
}
-
EXPORT_SYMBOL_GPL(fib_rules_unregister);
static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
@@ -220,7 +218,6 @@
return err;
}
-
EXPORT_SYMBOL_GPL(fib_rules_lookup);
static int validate_rulemsg(struct fib_rule_hdr *frh, struct nlattr **tb,
@@ -613,7 +610,7 @@
break;
cb->args[1] = 0;
- skip:
+skip:
idx++;
}
rcu_read_unlock();
@@ -685,7 +682,6 @@
struct fib_rules_ops *ops;
ASSERT_RTNL();
- rcu_read_lock();
switch (event) {
case NETDEV_REGISTER:
@@ -699,8 +695,6 @@
break;
}
- rcu_read_unlock();
-
return NOTIFY_DONE;
}
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 099c753..7a46343 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -466,6 +466,216 @@
};
#endif
+/*
+ * RX queue sysfs structures and functions.
+ */
+struct rx_queue_attribute {
+ struct attribute attr;
+ ssize_t (*show)(struct netdev_rx_queue *queue,
+ struct rx_queue_attribute *attr, char *buf);
+ ssize_t (*store)(struct netdev_rx_queue *queue,
+ struct rx_queue_attribute *attr, const char *buf, size_t len);
+};
+#define to_rx_queue_attr(_attr) container_of(_attr, \
+ struct rx_queue_attribute, attr)
+
+#define to_rx_queue(obj) container_of(obj, struct netdev_rx_queue, kobj)
+
+static ssize_t rx_queue_attr_show(struct kobject *kobj, struct attribute *attr,
+ char *buf)
+{
+ struct rx_queue_attribute *attribute = to_rx_queue_attr(attr);
+ struct netdev_rx_queue *queue = to_rx_queue(kobj);
+
+ if (!attribute->show)
+ return -EIO;
+
+ return attribute->show(queue, attribute, buf);
+}
+
+static ssize_t rx_queue_attr_store(struct kobject *kobj, struct attribute *attr,
+ const char *buf, size_t count)
+{
+ struct rx_queue_attribute *attribute = to_rx_queue_attr(attr);
+ struct netdev_rx_queue *queue = to_rx_queue(kobj);
+
+ if (!attribute->store)
+ return -EIO;
+
+ return attribute->store(queue, attribute, buf, count);
+}
+
+static struct sysfs_ops rx_queue_sysfs_ops = {
+ .show = rx_queue_attr_show,
+ .store = rx_queue_attr_store,
+};
+
+static ssize_t show_rps_map(struct netdev_rx_queue *queue,
+ struct rx_queue_attribute *attribute, char *buf)
+{
+ struct rps_map *map;
+ cpumask_var_t mask;
+ size_t len = 0;
+ int i;
+
+ if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
+ return -ENOMEM;
+
+ rcu_read_lock();
+ map = rcu_dereference(queue->rps_map);
+ if (map)
+ for (i = 0; i < map->len; i++)
+ cpumask_set_cpu(map->cpus[i], mask);
+
+ len += cpumask_scnprintf(buf + len, PAGE_SIZE, mask);
+ if (PAGE_SIZE - len < 3) {
+ rcu_read_unlock();
+ free_cpumask_var(mask);
+ return -EINVAL;
+ }
+ rcu_read_unlock();
+
+ free_cpumask_var(mask);
+ len += sprintf(buf + len, "\n");
+ return len;
+}
+
+static void rps_map_release(struct rcu_head *rcu)
+{
+ struct rps_map *map = container_of(rcu, struct rps_map, rcu);
+
+ kfree(map);
+}
+
+ssize_t store_rps_map(struct netdev_rx_queue *queue,
+ struct rx_queue_attribute *attribute,
+ const char *buf, size_t len)
+{
+ struct rps_map *old_map, *map;
+ cpumask_var_t mask;
+ int err, cpu, i;
+ static DEFINE_SPINLOCK(rps_map_lock);
+
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+ return -ENOMEM;
+
+ err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits);
+ if (err) {
+ free_cpumask_var(mask);
+ return err;
+ }
+
+ map = kzalloc(max_t(unsigned,
+ RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES),
+ GFP_KERNEL);
+ if (!map) {
+ free_cpumask_var(mask);
+ return -ENOMEM;
+ }
+
+ i = 0;
+ for_each_cpu_and(cpu, mask, cpu_online_mask)
+ map->cpus[i++] = cpu;
+
+ if (i)
+ map->len = i;
+ else {
+ kfree(map);
+ map = NULL;
+ }
+
+ spin_lock(&rps_map_lock);
+ old_map = queue->rps_map;
+ rcu_assign_pointer(queue->rps_map, map);
+ spin_unlock(&rps_map_lock);
+
+ if (old_map)
+ call_rcu(&old_map->rcu, rps_map_release);
+
+ free_cpumask_var(mask);
+ return len;
+}
+
+static struct rx_queue_attribute rps_cpus_attribute =
+ __ATTR(rps_cpus, S_IRUGO | S_IWUSR, show_rps_map, store_rps_map);
+
+static struct attribute *rx_queue_default_attrs[] = {
+ &rps_cpus_attribute.attr,
+ NULL
+};
+
+static void rx_queue_release(struct kobject *kobj)
+{
+ struct netdev_rx_queue *queue = to_rx_queue(kobj);
+ struct rps_map *map = queue->rps_map;
+ struct netdev_rx_queue *first = queue->first;
+
+ if (map)
+ call_rcu(&map->rcu, rps_map_release);
+
+ if (atomic_dec_and_test(&first->count))
+ kfree(first);
+}
+
+static struct kobj_type rx_queue_ktype = {
+ .sysfs_ops = &rx_queue_sysfs_ops,
+ .release = rx_queue_release,
+ .default_attrs = rx_queue_default_attrs,
+};
+
+static int rx_queue_add_kobject(struct net_device *net, int index)
+{
+ struct netdev_rx_queue *queue = net->_rx + index;
+ struct kobject *kobj = &queue->kobj;
+ int error = 0;
+
+ kobj->kset = net->queues_kset;
+ error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL,
+ "rx-%u", index);
+ if (error) {
+ kobject_put(kobj);
+ return error;
+ }
+
+ kobject_uevent(kobj, KOBJ_ADD);
+
+ return error;
+}
+
+static int rx_queue_register_kobjects(struct net_device *net)
+{
+ int i;
+ int error = 0;
+
+ net->queues_kset = kset_create_and_add("queues",
+ NULL, &net->dev.kobj);
+ if (!net->queues_kset)
+ return -ENOMEM;
+ for (i = 0; i < net->num_rx_queues; i++) {
+ error = rx_queue_add_kobject(net, i);
+ if (error)
+ break;
+ }
+
+ if (error)
+ while (--i >= 0)
+ kobject_put(&net->_rx[i].kobj);
+
+ return error;
+}
+
+static void rx_queue_remove_kobjects(struct net_device *net)
+{
+ int i;
+
+ for (i = 0; i < net->num_rx_queues; i++)
+ kobject_put(&net->_rx[i].kobj);
+ kset_unregister(net->queues_kset);
+}
+
#endif /* CONFIG_SYSFS */
#ifdef CONFIG_HOTPLUG
@@ -529,6 +739,8 @@
if (!net_eq(dev_net(net), &init_net))
return;
+ rx_queue_remove_kobjects(net);
+
device_del(dev);
}
@@ -537,6 +749,7 @@
{
struct device *dev = &(net->dev);
const struct attribute_group **groups = net->sysfs_groups;
+ int error = 0;
dev->class = &net_class;
dev->platform_data = net;
@@ -563,7 +776,17 @@
if (!net_eq(dev_net(net), &init_net))
return 0;
- return device_add(dev);
+ error = device_add(dev);
+ if (error)
+ return error;
+
+ error = rx_queue_register_kobjects(net);
+ if (error) {
+ device_del(dev);
+ return error;
+ }
+
+ return error;
}
int netdev_class_create_file(struct class_attribute *class_attr)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 4568120..e1121f0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -600,7 +600,39 @@
a->rx_compressed = b->rx_compressed;
a->tx_compressed = b->tx_compressed;
-};
+}
+
+static void copy_rtnl_link_stats64(struct rtnl_link_stats64 *a,
+ const struct net_device_stats *b)
+{
+ a->rx_packets = b->rx_packets;
+ a->tx_packets = b->tx_packets;
+ a->rx_bytes = b->rx_bytes;
+ a->tx_bytes = b->tx_bytes;
+ a->rx_errors = b->rx_errors;
+ a->tx_errors = b->tx_errors;
+ a->rx_dropped = b->rx_dropped;
+ a->tx_dropped = b->tx_dropped;
+
+ a->multicast = b->multicast;
+ a->collisions = b->collisions;
+
+ a->rx_length_errors = b->rx_length_errors;
+ a->rx_over_errors = b->rx_over_errors;
+ a->rx_crc_errors = b->rx_crc_errors;
+ a->rx_frame_errors = b->rx_frame_errors;
+ a->rx_fifo_errors = b->rx_fifo_errors;
+ a->rx_missed_errors = b->rx_missed_errors;
+
+ a->tx_aborted_errors = b->tx_aborted_errors;
+ a->tx_carrier_errors = b->tx_carrier_errors;
+ a->tx_fifo_errors = b->tx_fifo_errors;
+ a->tx_heartbeat_errors = b->tx_heartbeat_errors;
+ a->tx_window_errors = b->tx_window_errors;
+
+ a->rx_compressed = b->rx_compressed;
+ a->tx_compressed = b->tx_compressed;
+}
static inline int rtnl_vfinfo_size(const struct net_device *dev)
{
@@ -698,6 +730,14 @@
stats = dev_get_stats(dev);
copy_rtnl_link_stats(nla_data(attr), stats);
+ attr = nla_reserve(skb, IFLA_STATS64,
+ sizeof(struct rtnl_link_stats64));
+ if (attr == NULL)
+ goto nla_put_failure;
+
+ stats = dev_get_stats(dev);
+ copy_rtnl_link_stats64(nla_data(attr), stats);
+
if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) {
int i;
struct ifla_vf_info ivi;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 93c4e06..bdea0ef 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -534,6 +534,7 @@
new->network_header = old->network_header;
new->mac_header = old->mac_header;
skb_dst_set(new, dst_clone(skb_dst(old)));
+ new->rxhash = old->rxhash;
#ifdef CONFIG_XFRM
new->sp = secpath_get(old->sp);
#endif
@@ -581,6 +582,7 @@
C(len);
C(data_len);
C(mac_len);
+ C(rxhash);
n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len;
n->cloned = 1;
n->nohdr = 0;
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 0c94a1a..c9a1c68 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -587,9 +587,15 @@
config DEFAULT_HTCP
bool "Htcp" if TCP_CONG_HTCP=y
+ config DEFAULT_HYBLA
+ bool "Hybla" if TCP_CONG_HYBLA=y
+
config DEFAULT_VEGAS
bool "Vegas" if TCP_CONG_VEGAS=y
+ config DEFAULT_VENO
+ bool "Veno" if TCP_CONG_VENO=y
+
config DEFAULT_WESTWOOD
bool "Westwood" if TCP_CONG_WESTWOOD=y
@@ -610,8 +616,10 @@
default "bic" if DEFAULT_BIC
default "cubic" if DEFAULT_CUBIC
default "htcp" if DEFAULT_HTCP
+ default "hybla" if DEFAULT_HYBLA
default "vegas" if DEFAULT_VEGAS
default "westwood" if DEFAULT_WESTWOOD
+ default "veno" if DEFAULT_VENO
default "reno" if DEFAULT_RENO
default "cubic"
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 51ca946..c75320e 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1095,10 +1095,10 @@
case NETDEV_DOWN:
ip_mc_down(in_dev);
break;
- case NETDEV_BONDING_OLDTYPE:
+ case NETDEV_PRE_TYPE_CHANGE:
ip_mc_unmap(in_dev);
break;
- case NETDEV_BONDING_NEWTYPE:
+ case NETDEV_POST_TYPE_CHANGE:
ip_mc_remap(in_dev);
break;
case NETDEV_CHANGEMTU:
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3381b43..8d41abc 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -137,8 +137,8 @@
static void addrconf_join_anycast(struct inet6_ifaddr *ifp);
static void addrconf_leave_anycast(struct inet6_ifaddr *ifp);
-static void addrconf_bonding_change(struct net_device *dev,
- unsigned long event);
+static void addrconf_type_change(struct net_device *dev,
+ unsigned long event);
static int addrconf_ifdown(struct net_device *dev, int how);
static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags);
@@ -2584,9 +2584,9 @@
return notifier_from_errno(err);
}
break;
- case NETDEV_BONDING_OLDTYPE:
- case NETDEV_BONDING_NEWTYPE:
- addrconf_bonding_change(dev, event);
+ case NETDEV_PRE_TYPE_CHANGE:
+ case NETDEV_POST_TYPE_CHANGE:
+ addrconf_type_change(dev, event);
break;
}
@@ -2601,16 +2601,16 @@
.priority = 0
};
-static void addrconf_bonding_change(struct net_device *dev, unsigned long event)
+static void addrconf_type_change(struct net_device *dev, unsigned long event)
{
struct inet6_dev *idev;
ASSERT_RTNL();
idev = __in6_dev_get(dev);
- if (event == NETDEV_BONDING_NEWTYPE)
+ if (event == NETDEV_POST_TYPE_CHANGE)
ipv6_mc_remap(idev);
- else if (event == NETDEV_BONDING_OLDTYPE)
+ else if (event == NETDEV_PRE_TYPE_CHANGE)
ipv6_mc_unmap(idev);
}
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 853c52b..937ecda 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -159,7 +159,8 @@
poll_wait(file, sk->sk_sleep, wait);
- poll_wait(file, &rds_poll_waitq, wait);
+ if (rs->rs_seen_congestion)
+ poll_wait(file, &rds_poll_waitq, wait);
read_lock_irqsave(&rs->rs_recv_lock, flags);
if (!rs->rs_cong_monitor) {
@@ -181,6 +182,10 @@
mask |= (POLLOUT | POLLWRNORM);
read_unlock_irqrestore(&rs->rs_recv_lock, flags);
+ /* clear state any time we wake a seen-congested socket */
+ if (mask)
+ rs->rs_seen_congestion = 0;
+
return mask;
}
diff --git a/net/rds/cong.c b/net/rds/cong.c
index 6d06cac..dd2711d 100644
--- a/net/rds/cong.c
+++ b/net/rds/cong.c
@@ -218,8 +218,6 @@
spin_lock_irqsave(&rds_cong_lock, flags);
list_for_each_entry(conn, &map->m_conn_list, c_map_item) {
- if (conn->c_loopback)
- continue;
if (!test_and_set_bit(0, &conn->c_map_queued)) {
rds_stats_inc(s_cong_update_queued);
queue_delayed_work(rds_wq, &conn->c_send_w, 0);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 647cb8f..e1f124b 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -203,9 +203,10 @@
rdma_notify(ic->i_cm_id, IB_EVENT_COMM_EST);
break;
default:
- rds_ib_conn_error(conn, "RDS/IB: Fatal QP Event %u "
+ rdsdebug("Fatal QP Event %u "
"- connection %pI4->%pI4, reconnecting\n",
event->event, &conn->c_laddr, &conn->c_faddr);
+ rds_conn_drop(conn);
break;
}
}
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 4b0da86..cfb1d90 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -234,8 +234,8 @@
{
flush_workqueue(rds_wq);
rds_ib_flush_mr_pool(pool, 1);
- BUG_ON(atomic_read(&pool->item_count));
- BUG_ON(atomic_read(&pool->free_pinned));
+ WARN_ON(atomic_read(&pool->item_count));
+ WARN_ON(atomic_read(&pool->free_pinned));
kfree(pool);
}
@@ -440,6 +440,7 @@
/* FIXME we need a way to tell a r/w MR
* from a r/o MR */
+ BUG_ON(in_interrupt());
set_page_dirty(page);
put_page(page);
}
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 04dc0d3..c338881 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -468,8 +468,8 @@
set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
rds_ib_stats_inc(s_ib_ack_send_failure);
- /* Need to finesse this later. */
- BUG();
+
+ rds_ib_conn_error(ic->conn, "sending ack failed\n");
} else
rds_ib_stats_inc(s_ib_ack_sent);
}
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index a10fab6..17fa808 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -243,8 +243,12 @@
struct rds_message *rm;
rm = rds_send_get_message(conn, send->s_op);
- if (rm)
+ if (rm) {
+ if (rm->m_rdma_op)
+ rds_ib_send_unmap_rdma(ic, rm->m_rdma_op);
rds_ib_send_rdma_complete(rm, wc.status);
+ rds_message_put(rm);
+ }
}
oldest = (oldest + 1) % ic->i_send_ring.w_nr;
@@ -482,6 +486,13 @@
BUG_ON(off % RDS_FRAG_SIZE);
BUG_ON(hdr_off != 0 && hdr_off != sizeof(struct rds_header));
+ /* Do not send cong updates to IB loopback */
+ if (conn->c_loopback
+ && rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) {
+ rds_cong_map_updated(conn->c_fcong, ~(u64) 0);
+ return sizeof(struct rds_header) + RDS_CONG_MAP_BYTES;
+ }
+
/* FIXME we may overallocate here */
if (be32_to_cpu(rm->m_inc.i_hdr.h_len) == 0)
i = 1;
@@ -574,8 +585,7 @@
rds_ib_send_grab_credits(ic, 0, &posted, 1, RDS_MAX_ADV_CREDIT - adv_credits);
adv_credits += posted;
BUG_ON(adv_credits > 255);
- } else if (ic->i_rm != rm)
- BUG();
+ }
send = &ic->i_sends[pos];
first = send;
@@ -714,8 +724,8 @@
ic->i_rm = prev->s_rm;
prev->s_rm = NULL;
}
- /* Finesse this later */
- BUG();
+
+ rds_ib_conn_error(ic->conn, "ib_post_send failed\n");
goto out;
}
diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c
index 394cf6b..6bc638f 100644
--- a/net/rds/iw_cm.c
+++ b/net/rds/iw_cm.c
@@ -156,9 +156,11 @@
case IB_EVENT_QP_REQ_ERR:
case IB_EVENT_QP_FATAL:
default:
- rds_iw_conn_error(conn, "RDS/IW: Fatal QP Event %u - connection %pI4->%pI4...reconnecting\n",
+ rdsdebug("Fatal QP Event %u "
+ "- connection %pI4->%pI4, reconnecting\n",
event->event, &conn->c_laddr,
&conn->c_faddr);
+ rds_conn_drop(conn);
break;
}
}
diff --git a/net/rds/iw_recv.c b/net/rds/iw_recv.c
index 54af7d6..337e4e5 100644
--- a/net/rds/iw_recv.c
+++ b/net/rds/iw_recv.c
@@ -468,8 +468,8 @@
set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
rds_iw_stats_inc(s_iw_ack_send_failure);
- /* Need to finesse this later. */
- BUG();
+
+ rds_iw_conn_error(ic->conn, "sending ack failed\n");
} else
rds_iw_stats_inc(s_iw_ack_sent);
}
diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c
index 1379e9d..52182ff 100644
--- a/net/rds/iw_send.c
+++ b/net/rds/iw_send.c
@@ -616,8 +616,7 @@
rds_iw_send_grab_credits(ic, 0, &posted, 1, RDS_MAX_ADV_CREDIT - adv_credits);
adv_credits += posted;
BUG_ON(adv_credits > 255);
- } else if (ic->i_rm != rm)
- BUG();
+ }
send = &ic->i_sends[pos];
first = send;
diff --git a/net/rds/loop.c b/net/rds/loop.c
index 4a61997..93a45f1 100644
--- a/net/rds/loop.c
+++ b/net/rds/loop.c
@@ -80,16 +80,9 @@
struct rds_cong_map *map,
unsigned long offset)
{
- unsigned long i;
-
BUG_ON(offset);
BUG_ON(map != conn->c_lcong);
- for (i = 0; i < RDS_CONG_MAP_PAGES; i++) {
- memcpy((void *)conn->c_fcong->m_page_addrs[i],
- (void *)map->m_page_addrs[i], PAGE_SIZE);
- }
-
rds_cong_map_updated(conn->c_fcong, ~(u64) 0);
return sizeof(struct rds_header) + RDS_CONG_MAP_BYTES;
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 4c64daa..61b359d 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -438,8 +438,10 @@
/* Mark page dirty if it was possibly modified, which
* is the case for a RDMA_READ which copies from remote
* to local memory */
- if (!ro->r_write)
+ if (!ro->r_write) {
+ BUG_ON(in_interrupt());
set_page_dirty(page);
+ }
put_page(page);
}
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index 9ece910..5ea82fc 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -101,7 +101,7 @@
break;
case RDMA_CM_EVENT_DISCONNECTED:
- printk(KERN_WARNING "RDS/RDMA: DISCONNECT event - dropping connection "
+ rdsdebug("DISCONNECT event - dropping connection "
"%pI4->%pI4\n", &conn->c_laddr,
&conn->c_faddr);
rds_conn_drop(conn);
@@ -109,8 +109,7 @@
default:
/* things like device disconnect? */
- printk(KERN_ERR "unknown event %u\n", event->event);
- BUG();
+ printk(KERN_ERR "RDS: unknown event %u!\n", event->event);
break;
}
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 85d6f89..4bec6e2 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -388,6 +388,8 @@
/* flag indicating we were congested or not */
int rs_congested;
+ /* seen congestion (ENOBUFS) when sending? */
+ int rs_seen_congestion;
/* rs_lock protects all these adjacent members before the newline */
spinlock_t rs_lock;
diff --git a/net/rds/send.c b/net/rds/send.c
index b2fccfc..4629a0b 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -507,12 +507,13 @@
*/
void rds_send_remove_from_sock(struct list_head *messages, int status)
{
- unsigned long flags = 0; /* silence gcc :P */
+ unsigned long flags;
struct rds_sock *rs = NULL;
struct rds_message *rm;
- local_irq_save(flags);
while (!list_empty(messages)) {
+ int was_on_sock = 0;
+
rm = list_entry(messages->next, struct rds_message,
m_conn_item);
list_del_init(&rm->m_conn_item);
@@ -527,20 +528,19 @@
* while we're messing with it. It does not prevent the
* message from being removed from the socket, though.
*/
- spin_lock(&rm->m_rs_lock);
+ spin_lock_irqsave(&rm->m_rs_lock, flags);
if (!test_bit(RDS_MSG_ON_SOCK, &rm->m_flags))
goto unlock_and_drop;
if (rs != rm->m_rs) {
if (rs) {
- spin_unlock(&rs->rs_lock);
rds_wake_sk_sleep(rs);
sock_put(rds_rs_to_sk(rs));
}
rs = rm->m_rs;
- spin_lock(&rs->rs_lock);
sock_hold(rds_rs_to_sk(rs));
}
+ spin_lock(&rs->rs_lock);
if (test_and_clear_bit(RDS_MSG_ON_SOCK, &rm->m_flags)) {
struct rds_rdma_op *ro = rm->m_rdma_op;
@@ -557,21 +557,22 @@
notifier->n_status = status;
rm->m_rdma_op->r_notifier = NULL;
}
- rds_message_put(rm);
+ was_on_sock = 1;
rm->m_rs = NULL;
}
+ spin_unlock(&rs->rs_lock);
unlock_and_drop:
- spin_unlock(&rm->m_rs_lock);
+ spin_unlock_irqrestore(&rm->m_rs_lock, flags);
rds_message_put(rm);
+ if (was_on_sock)
+ rds_message_put(rm);
}
if (rs) {
- spin_unlock(&rs->rs_lock);
rds_wake_sk_sleep(rs);
sock_put(rds_rs_to_sk(rs));
}
- local_irq_restore(flags);
}
/*
@@ -633,9 +634,6 @@
list_move(&rm->m_sock_item, &list);
rds_send_sndbuf_remove(rs, rm);
clear_bit(RDS_MSG_ON_SOCK, &rm->m_flags);
-
- /* If this is a RDMA operation, notify the app. */
- __rds_rdma_send_complete(rs, rm, RDS_RDMA_CANCELED);
}
/* order flag updates with the rs lock */
@@ -644,9 +642,6 @@
spin_unlock_irqrestore(&rs->rs_lock, flags);
- if (wake)
- rds_wake_sk_sleep(rs);
-
conn = NULL;
/* now remove the messages from the conn list as needed */
@@ -654,6 +649,10 @@
/* We do this here rather than in the loop above, so that
* we don't have to nest m_rs_lock under rs->rs_lock */
spin_lock_irqsave(&rm->m_rs_lock, flags2);
+ /* If this is a RDMA operation, notify the app. */
+ spin_lock(&rs->rs_lock);
+ __rds_rdma_send_complete(rs, rm, RDS_RDMA_CANCELED);
+ spin_unlock(&rs->rs_lock);
rm->m_rs = NULL;
spin_unlock_irqrestore(&rm->m_rs_lock, flags2);
@@ -682,6 +681,9 @@
if (conn)
spin_unlock_irqrestore(&conn->c_lock, flags);
+ if (wake)
+ rds_wake_sk_sleep(rs);
+
while (!list_empty(&list)) {
rm = list_entry(list.next, struct rds_message, m_sock_item);
list_del_init(&rm->m_sock_item);
@@ -815,7 +817,7 @@
int ret = 0;
int queued = 0, allocated_mr = 0;
int nonblock = msg->msg_flags & MSG_DONTWAIT;
- long timeo = sock_rcvtimeo(sk, nonblock);
+ long timeo = sock_sndtimeo(sk, nonblock);
/* Mirror Linux UDP mirror of BSD error message compatibility */
/* XXX: Perhaps MSG_MORE someday */
@@ -894,8 +896,10 @@
queue_delayed_work(rds_wq, &conn->c_conn_w, 0);
ret = rds_cong_wait(conn->c_fcong, dport, nonblock, rs);
- if (ret)
+ if (ret) {
+ rs->rs_seen_congestion = 1;
goto out;
+ }
while (!rds_send_queue_rm(rs, conn, rm, rs->rs_bound_port,
dport, &queued)) {
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index c00daff..40bfcf8 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -97,6 +97,7 @@
goto out;
}
+ rds_stats_add(s_copy_to_user, to_copy);
size -= to_copy;
ret += to_copy;
skb_off += to_copy;
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index 34fdcc0..a28b895 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -240,7 +240,9 @@
tc->t_last_seen_una = rds_tcp_snd_una(tc);
rds_send_drop_acked(conn, rds_tcp_snd_una(tc), rds_tcp_is_acked);
- queue_delayed_work(rds_wq, &conn->c_send_w, 0);
+ if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf)
+ queue_delayed_work(rds_wq, &conn->c_send_w, 0);
+
out:
read_unlock(&sk->sk_callback_lock);
diff --git a/net/rds/threads.c b/net/rds/threads.c
index 00fa10e..786c20e 100644
--- a/net/rds/threads.c
+++ b/net/rds/threads.c
@@ -259,7 +259,7 @@
int __init rds_threads_init(void)
{
- rds_wq = create_singlethread_workqueue("krdsd");
+ rds_wq = create_workqueue("krdsd");
if (rds_wq == NULL)
return -ENOMEM;
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index a3bfd40..90a0519 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -558,10 +558,7 @@
struct tipc_bearer *unused1,
struct tipc_media_addr *unused2)
{
- static int send_count = 0;
-
int bp_index;
- int swap_time;
/* Prepare buffer for broadcasting (if first time trying to send it) */
@@ -575,11 +572,6 @@
msg_set_mc_netid(msg, tipc_net_id);
}
- /* Determine if bearer pairs should be swapped following this attempt */
-
- if ((swap_time = (++send_count >= 10)))
- send_count = 0;
-
/* Send buffer over bearers until all targets reached */
bcbearer->remains = tipc_cltr_bcast_nodes;
@@ -595,21 +587,22 @@
if (bcbearer->remains_new.count == bcbearer->remains.count)
continue; /* bearer pair doesn't add anything */
- if (!p->publ.blocked &&
- !p->media->send_msg(buf, &p->publ, &p->media->bcast_addr)) {
- if (swap_time && s && !s->publ.blocked)
- goto swap;
- else
- goto update;
+ if (p->publ.blocked ||
+ p->media->send_msg(buf, &p->publ, &p->media->bcast_addr)) {
+ /* unable to send on primary bearer */
+ if (!s || s->publ.blocked ||
+ s->media->send_msg(buf, &s->publ,
+ &s->media->bcast_addr)) {
+ /* unable to send on either bearer */
+ continue;
+ }
}
- if (!s || s->publ.blocked ||
- s->media->send_msg(buf, &s->publ, &s->media->bcast_addr))
- continue; /* unable to send using bearer pair */
-swap:
- bcbearer->bpairs[bp_index].primary = s;
- bcbearer->bpairs[bp_index].secondary = p;
-update:
+ if (s) {
+ bcbearer->bpairs[bp_index].primary = s;
+ bcbearer->bpairs[bp_index].secondary = p;
+ }
+
if (bcbearer->remains_new.count == 0)
return 0;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 1a7e466..49f2be8 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1553,7 +1553,7 @@
/* Continue retransmission now, if there is anything: */
- if (r_q_size && buf && !skb_cloned(buf)) {
+ if (r_q_size && buf) {
msg_set_ack(buf_msg(buf), mod(l_ptr->next_in_no - 1));
msg_set_bcast_ack(buf_msg(buf), l_ptr->owner->bclink.last_in);
if (tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) {
@@ -1722,15 +1722,16 @@
dbg("Retransmitting %u in link %x\n", retransmits, l_ptr);
if (tipc_bearer_congested(l_ptr->b_ptr, l_ptr)) {
- if (!skb_cloned(buf)) {
+ if (l_ptr->retransm_queue_size == 0) {
msg_dbg(msg, ">NO_RETR->BCONG>");
dbg_print_link(l_ptr, " ");
l_ptr->retransm_queue_head = msg_seqno(msg);
l_ptr->retransm_queue_size = retransmits;
- return;
} else {
- /* Don't retransmit if driver already has the buffer */
+ err("Unexpected retransmit on link %s (qsize=%d)\n",
+ l_ptr->name, l_ptr->retransm_queue_size);
}
+ return;
} else {
/* Detect repeated retransmit failures on uncongested bearer */
@@ -1745,7 +1746,7 @@
}
}
- while (retransmits && (buf != l_ptr->next_out) && buf && !skb_cloned(buf)) {
+ while (retransmits && (buf != l_ptr->next_out) && buf) {
msg = buf_msg(buf);
msg_set_ack(msg, mod(l_ptr->next_in_no - 1));
msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in);
