Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:
"Bug fixes galore, mostly in drivers as is often the case:
1) USB gadget and cdc_eem drivers need adjustments to their frame size
lengths in order to handle VLANs correctly. From Ian Coolidge.
2) TIPC and several network drivers erroneously call tasklet_disable
before tasklet_kill, fix from Xiaotian Feng.
3) r8169 driver needs to apply the WOL suspend quirk to more chipsets,
fix from Cyril Brulebois.
4) Fix multicast filters on RTL_GIGA_MAC_VER_35 r8169 chips, from
Nathan Walp.
5) FDB netlink dumps should use RTM_NEWNEIGH as the message type, not
zero. From John Fastabend.
6) Fix smsc95xx tx checksum offload on big-endian, from Steve
Glendinning.
7) __inet_diag_dump() needs to repsect and report the error value
returned from inet_diag_lock_handler() rather than ignore it.
Otherwise if an inet diag handler is not available for a particular
protocol, we essentially report success instead of giving an error
indication. Fix from Cyrill Gorcunov.
8) When the QFQ packet scheduler sees TSO/GSO packets it does not
handle things properly, and in fact ends up corrupting it's
datastructures as well as mis-schedule packets. Fix from Paolo
Valente.
9) Fix oopser in skb_loop_sk(), from Eric Leblond.
10) CXGB4 passes partially uninitialized datastructures in to FW
commands, fix from Vipul Pandya.
11) When we send unsolicited ipv6 neighbour advertisements, we should
send them to the link-local allnodes multicast address, as per
RFC4861. Fix from Hannes Frederic Sowa.
12) There is some kind of bug in the usbnet's kevent deferral
mechanism, but more immediately when it triggers an uncontrolled
stream of kernel messages spam the log. Rate limit the error log
message triggered when this problem occurs, as sending thousands
of error messages into the kernel log doesn't help matters at all,
and in fact makes further diagnosis more difficult.
From Steve Glendinning.
13) Fix gianfar restore from hibernation, from Wang Dongsheng.
14) The netlink message attribute sizes are wrong in the ipv6 GRE
driver, it was using the size of ipv4 addresses instead of ipv6
ones :-) Fix from Nicolas Dichtel."
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
gre6: fix rtnl dump messages
gianfar: ethernet vanishes after restoring from hibernation
usbnet: ratelimit kevent may have been dropped warnings
ipv6: send unsolicited neighbour advertisements to all-nodes
net: usb: cdc_eem: Fix rx skb allocation for 802.1Q VLANs
usb: gadget: g_ether: fix frame size check for 802.1Q
cxgb4: Fix initialization of SGE_CONTROL register
isdn: Make CONFIG_ISDN depend on CONFIG_NETDEVICES
cxgb4: Initialize data structures before using.
af-packet: fix oops when socket is not present
pkt_sched: enable QFQ to support TSO/GSO
net: inet_diag -- Return error code if protocol handler is missed
net: bnx2x: Fix typo in bnx2x driver
smsc95xx: fix tx checksum offload for big endian
rtnetlink: Use nlmsg type RTM_NEWNEIGH from dflt fdb dump
ptp: update adjfreq callback description
r8169: allow multicast packets on sub-8168f chipset.
r8169: Fix WoL on RTL8168d/8111d.
drivers/net: use tasklet_kill in device remove/close process
tipc: do not use tasklet_disable before tasklet_kill
diff --git a/drivers/isdn/Kconfig b/drivers/isdn/Kconfig
index a233ed5..86cd75a 100644
--- a/drivers/isdn/Kconfig
+++ b/drivers/isdn/Kconfig
@@ -4,7 +4,7 @@
menuconfig ISDN
bool "ISDN support"
- depends on NET
+ depends on NET && NETDEVICES
depends on !S390 && !UML
---help---
ISDN ("Integrated Services Digital Network", called RNIS in France)
diff --git a/drivers/isdn/i4l/Kconfig b/drivers/isdn/i4l/Kconfig
index 2302fbe..9c6650e 100644
--- a/drivers/isdn/i4l/Kconfig
+++ b/drivers/isdn/i4l/Kconfig
@@ -6,7 +6,7 @@
config ISDN_PPP
bool "Support synchronous PPP"
- depends on INET && NETDEVICES
+ depends on INET
select SLHC
help
Over digital connections such as ISDN, there is no need to
diff --git a/drivers/isdn/i4l/isdn_common.c b/drivers/isdn/i4l/isdn_common.c
index 8c610fa..e2a945e 100644
--- a/drivers/isdn/i4l/isdn_common.c
+++ b/drivers/isdn/i4l/isdn_common.c
@@ -1312,7 +1312,6 @@
} else
return -EINVAL;
break;
-#ifdef CONFIG_NETDEVICES
case IIOCNETGPN:
/* Get peer phone number of a connected
* isdn network interface */
@@ -1322,7 +1321,6 @@
return isdn_net_getpeer(&phone, argp);
} else
return -EINVAL;
-#endif
default:
return -EINVAL;
}
@@ -1352,7 +1350,6 @@
case IIOCNETLCR:
printk(KERN_INFO "INFO: ISDN_ABC_LCR_SUPPORT not enabled\n");
return -ENODEV;
-#ifdef CONFIG_NETDEVICES
case IIOCNETAIF:
/* Add a network-interface */
if (arg) {
@@ -1491,7 +1488,6 @@
return -EFAULT;
return isdn_net_force_hangup(name);
break;
-#endif /* CONFIG_NETDEVICES */
case IIOCSETVER:
dev->net_verbose = arg;
printk(KERN_INFO "isdn: Verbose-Level is %d\n", dev->net_verbose);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index c65295d..6e5bdd1 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -1702,7 +1702,7 @@
SHMEM_EEE_ADV_STATUS_SHIFT);
if ((advertised != (eee_cfg & SHMEM_EEE_ADV_STATUS_MASK))) {
DP(BNX2X_MSG_ETHTOOL,
- "Direct manipulation of EEE advertisment is not supported\n");
+ "Direct manipulation of EEE advertisement is not supported\n");
return -EINVAL;
}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 6dd0dd0..f6cfdc6 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -9941,7 +9941,7 @@
else
rc = bnx2x_8483x_disable_eee(phy, params, vars);
if (rc) {
- DP(NETIF_MSG_LINK, "Failed to set EEE advertisment\n");
+ DP(NETIF_MSG_LINK, "Failed to set EEE advertisement\n");
return rc;
}
} else {
@@ -12987,7 +12987,7 @@
DP(NETIF_MSG_LINK, "Analyze TX Fault\n");
break;
default:
- DP(NETIF_MSG_LINK, "Analyze UNKOWN\n");
+ DP(NETIF_MSG_LINK, "Analyze UNKNOWN\n");
}
DP(NETIF_MSG_LINK, "Link changed:[%x %x]->%x\n", vars->link_up,
old_status, status);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 32eec15..730ae2c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -2519,6 +2519,7 @@
{
struct fw_bye_cmd c;
+ memset(&c, 0, sizeof(c));
INIT_CMD(c, BYE, WRITE);
return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
}
@@ -2535,6 +2536,7 @@
{
struct fw_initialize_cmd c;
+ memset(&c, 0, sizeof(c));
INIT_CMD(c, INITIALIZE, WRITE);
return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
}
@@ -2551,6 +2553,7 @@
{
struct fw_reset_cmd c;
+ memset(&c, 0, sizeof(c));
INIT_CMD(c, RESET, WRITE);
c.val = htonl(reset);
return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
@@ -2828,7 +2831,7 @@
HOSTPAGESIZEPF7(sge_hps));
t4_set_reg_field(adap, SGE_CONTROL,
- INGPADBOUNDARY(INGPADBOUNDARY_MASK) |
+ INGPADBOUNDARY_MASK |
EGRSTATUSPAGESIZE_MASK,
INGPADBOUNDARY(fl_align_log - 5) |
EGRSTATUSPAGESIZE(stat_len != 64));
@@ -3278,6 +3281,7 @@
{
struct fw_vi_enable_cmd c;
+ memset(&c, 0, sizeof(c));
c.op_to_viid = htonl(FW_CMD_OP(FW_VI_ENABLE_CMD) | FW_CMD_REQUEST |
FW_CMD_EXEC | FW_VI_ENABLE_CMD_VIID(viid));
c.ien_to_len16 = htonl(FW_VI_ENABLE_CMD_LED | FW_LEN16(c));
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 1d03dcd..19ac096 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1353,8 +1353,11 @@
struct gfar_private *priv = dev_get_drvdata(dev);
struct net_device *ndev = priv->ndev;
- if (!netif_running(ndev))
+ if (!netif_running(ndev)) {
+ netif_device_attach(ndev);
+
return 0;
+ }
gfar_init_bds(ndev);
init_registers(ndev);
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index f8064df..92317e9 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -1948,10 +1948,10 @@
JME_NAPI_DISABLE(jme);
- tasklet_disable(&jme->linkch_task);
- tasklet_disable(&jme->txclean_task);
- tasklet_disable(&jme->rxclean_task);
- tasklet_disable(&jme->rxempty_task);
+ tasklet_kill(&jme->linkch_task);
+ tasklet_kill(&jme->txclean_task);
+ tasklet_kill(&jme->rxclean_task);
+ tasklet_kill(&jme->rxempty_task);
jme_disable_rx_engine(jme);
jme_disable_tx_engine(jme);
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 9b9c2ac..d19a143 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -4026,7 +4026,7 @@
dev0 = hw->dev[0];
unregister_netdev(dev0);
- tasklet_disable(&hw->phy_task);
+ tasklet_kill(&hw->phy_task);
spin_lock_irq(&hw->hw_lock);
hw->intr_mask = 0;
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index 318fee9..e558edd 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -5407,8 +5407,8 @@
/* Delay for receive task to stop scheduling itself. */
msleep(2000 / HZ);
- tasklet_disable(&hw_priv->rx_tasklet);
- tasklet_disable(&hw_priv->tx_tasklet);
+ tasklet_kill(&hw_priv->rx_tasklet);
+ tasklet_kill(&hw_priv->tx_tasklet);
free_irq(dev->irq, hw_priv->dev);
transmit_cleanup(hw_priv, 0);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index e7ff886..927aa33 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -3827,6 +3827,8 @@
void __iomem *ioaddr = tp->mmio_addr;
switch (tp->mac_version) {
+ case RTL_GIGA_MAC_VER_25:
+ case RTL_GIGA_MAC_VER_26:
case RTL_GIGA_MAC_VER_29:
case RTL_GIGA_MAC_VER_30:
case RTL_GIGA_MAC_VER_32:
@@ -4519,6 +4521,9 @@
mc_filter[1] = swab32(data);
}
+ if (tp->mac_version == RTL_GIGA_MAC_VER_35)
+ mc_filter[1] = mc_filter[0] = 0xffffffff;
+
RTL_W32(MAR0 + 4, mc_filter[1]);
RTL_W32(MAR0 + 0, mc_filter[0]);
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 0793299..1d04754 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -990,7 +990,7 @@
axienet_setoptions(ndev, lp->options &
~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
- tasklet_disable(&lp->dma_err_tasklet);
+ tasklet_kill(&lp->dma_err_tasklet);
free_irq(lp->tx_irq, ndev);
free_irq(lp->rx_irq, ndev);
diff --git a/drivers/net/usb/cdc_eem.c b/drivers/net/usb/cdc_eem.c
index c81e278..08d55b6 100644
--- a/drivers/net/usb/cdc_eem.c
+++ b/drivers/net/usb/cdc_eem.c
@@ -31,6 +31,7 @@
#include <linux/usb/cdc.h>
#include <linux/usb/usbnet.h>
#include <linux/gfp.h>
+#include <linux/if_vlan.h>
/*
@@ -92,7 +93,7 @@
/* no jumbogram (16K) support for now */
- dev->net->hard_header_len += EEM_HEAD + ETH_FCS_LEN;
+ dev->net->hard_header_len += EEM_HEAD + ETH_FCS_LEN + VLAN_HLEN;
dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
return 0;
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 7479a57..3286166 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1344,6 +1344,7 @@
} else {
u32 csum_preamble = smsc95xx_calc_csum_preamble(skb);
skb_push(skb, 4);
+ cpu_to_le32s(&csum_preamble);
memcpy(skb->data, &csum_preamble, 4);
}
}
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index cb04f90..edb81ed 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -359,10 +359,12 @@
void usbnet_defer_kevent (struct usbnet *dev, int work)
{
set_bit (work, &dev->flags);
- if (!schedule_work (&dev->kevent))
- netdev_err(dev->net, "kevent %d may have been dropped\n", work);
- else
+ if (!schedule_work (&dev->kevent)) {
+ if (net_ratelimit())
+ netdev_err(dev->net, "kevent %d may have been dropped\n", work);
+ } else {
netdev_dbg(dev->net, "kevent %d scheduled\n", work);
+ }
}
EXPORT_SYMBOL_GPL(usbnet_defer_kevent);
diff --git a/drivers/net/wireless/b43legacy/pio.c b/drivers/net/wireless/b43legacy/pio.c
index 192251a..282eede 100644
--- a/drivers/net/wireless/b43legacy/pio.c
+++ b/drivers/net/wireless/b43legacy/pio.c
@@ -382,7 +382,7 @@
{
struct b43legacy_pio_txpacket *packet, *tmp_packet;
- tasklet_disable(&queue->txtask);
+ tasklet_kill(&queue->txtask);
list_for_each_entry_safe(packet, tmp_packet, &queue->txrunning, list)
free_txpacket(packet, 0);
diff --git a/drivers/usb/gadget/u_ether.c b/drivers/usb/gadget/u_ether.c
index 6458764..4ec3c0d 100644
--- a/drivers/usb/gadget/u_ether.c
+++ b/drivers/usb/gadget/u_ether.c
@@ -20,6 +20,7 @@
#include <linux/ctype.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
+#include <linux/if_vlan.h>
#include "u_ether.h"
@@ -295,7 +296,7 @@
while (skb2) {
if (status < 0
|| ETH_HLEN > skb2->len
- || skb2->len > ETH_FRAME_LEN) {
+ || skb2->len > VLAN_ETH_FRAME_LEN) {
dev->net->stats.rx_errors++;
dev->net->stats.rx_length_errors++;
DBG(dev, "rx length %d\n", skb2->len);
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index f2dc6d8..38a9935 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -54,7 +54,8 @@
* clock operations
*
* @adjfreq: Adjusts the frequency of the hardware clock.
- * parameter delta: Desired period change in parts per billion.
+ * parameter delta: Desired frequency offset from nominal frequency
+ * in parts per billion
*
* @adjtime: Shifts the time of the hardware clock.
* parameter delta: Desired change in nanoseconds.
diff --git a/net/core/dev.c b/net/core/dev.c
index 09cb3f6..bda6d00 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1666,7 +1666,7 @@
static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb)
{
- if (ptype->af_packet_priv == NULL)
+ if (!ptype->af_packet_priv || !skb->sk)
return false;
if (ptype->id_match)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 76d4c2c..fad649a 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2192,7 +2192,8 @@
goto skip;
err = nlmsg_populate_fdb_fill(skb, dev, ha->addr,
- portid, seq, 0, NTF_SELF);
+ portid, seq,
+ RTM_NEWNEIGH, NTF_SELF);
if (err < 0)
return err;
skip:
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 535584c..0c34bfa 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -892,13 +892,16 @@
struct inet_diag_req_v2 *r, struct nlattr *bc)
{
const struct inet_diag_handler *handler;
+ int err = 0;
handler = inet_diag_lock_handler(r->sdiag_protocol);
if (!IS_ERR(handler))
handler->dump(skb, cb, r, bc);
+ else
+ err = PTR_ERR(handler);
inet_diag_unlock_handler(handler);
- return skb->len;
+ return err ? : skb->len;
}
static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 0185679..d5cb3c4 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1633,9 +1633,9 @@
/* IFLA_GRE_OKEY */
nla_total_size(4) +
/* IFLA_GRE_LOCAL */
- nla_total_size(4) +
+ nla_total_size(sizeof(struct in6_addr)) +
/* IFLA_GRE_REMOTE */
- nla_total_size(4) +
+ nla_total_size(sizeof(struct in6_addr)) +
/* IFLA_GRE_TTL */
nla_total_size(1) +
/* IFLA_GRE_TOS */
@@ -1659,8 +1659,8 @@
nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) ||
nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
- nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->raddr) ||
- nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->laddr) ||
+ nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->laddr) ||
+ nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->raddr) ||
nla_put_u8(skb, IFLA_GRE_TTL, p->hop_limit) ||
/*nla_put_u8(skb, IFLA_GRE_TOS, t->priority) ||*/
nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) ||
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index ff36194..2edce30 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -535,7 +535,7 @@
{
struct inet6_dev *idev;
struct inet6_ifaddr *ifa;
- struct in6_addr mcaddr;
+ struct in6_addr mcaddr = IN6ADDR_LINKLOCAL_ALLNODES_INIT;
idev = in6_dev_get(dev);
if (!idev)
@@ -543,7 +543,6 @@
read_lock_bh(&idev->lock);
list_for_each_entry(ifa, &idev->addr_list, if_list) {
- addrconf_addr_solict_mult(&ifa->addr, &mcaddr);
ndisc_send_na(dev, NULL, &mcaddr, &ifa->addr,
/*router=*/ !!idev->cnf.forwarding,
/*solicited=*/ false, /*override=*/ true,
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index f0dd83c..9687fa1 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -84,18 +84,19 @@
* grp->index is the index of the group; and grp->slot_shift
* is the shift for the corresponding (scaled) sigma_i.
*/
-#define QFQ_MAX_INDEX 19
-#define QFQ_MAX_WSHIFT 16
+#define QFQ_MAX_INDEX 24
+#define QFQ_MAX_WSHIFT 12
#define QFQ_MAX_WEIGHT (1<<QFQ_MAX_WSHIFT)
-#define QFQ_MAX_WSUM (2*QFQ_MAX_WEIGHT)
+#define QFQ_MAX_WSUM (16*QFQ_MAX_WEIGHT)
#define FRAC_BITS 30 /* fixed point arithmetic */
#define ONE_FP (1UL << FRAC_BITS)
#define IWSUM (ONE_FP/QFQ_MAX_WSUM)
-#define QFQ_MTU_SHIFT 11
+#define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */
#define QFQ_MIN_SLOT_SHIFT (FRAC_BITS + QFQ_MTU_SHIFT - QFQ_MAX_INDEX)
+#define QFQ_MIN_LMAX 256 /* min possible lmax for a class */
/*
* Possible group states. These values are used as indexes for the bitmaps
@@ -231,6 +232,32 @@
q->wsum += delta_w;
}
+static void qfq_update_reactivate_class(struct qfq_sched *q,
+ struct qfq_class *cl,
+ u32 inv_w, u32 lmax, int delta_w)
+{
+ bool need_reactivation = false;
+ int i = qfq_calc_index(inv_w, lmax);
+
+ if (&q->groups[i] != cl->grp && cl->qdisc->q.qlen > 0) {
+ /*
+ * shift cl->F back, to not charge the
+ * class for the not-yet-served head
+ * packet
+ */
+ cl->F = cl->S;
+ /* remove class from its slot in the old group */
+ qfq_deactivate_class(q, cl);
+ need_reactivation = true;
+ }
+
+ qfq_update_class_params(q, cl, lmax, inv_w, delta_w);
+
+ if (need_reactivation) /* activate in new group */
+ qfq_activate_class(q, cl, qdisc_peek_len(cl->qdisc));
+}
+
+
static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
struct nlattr **tca, unsigned long *arg)
{
@@ -238,7 +265,7 @@
struct qfq_class *cl = (struct qfq_class *)*arg;
struct nlattr *tb[TCA_QFQ_MAX + 1];
u32 weight, lmax, inv_w;
- int i, err;
+ int err;
int delta_w;
if (tca[TCA_OPTIONS] == NULL) {
@@ -270,16 +297,14 @@
if (tb[TCA_QFQ_LMAX]) {
lmax = nla_get_u32(tb[TCA_QFQ_LMAX]);
- if (!lmax || lmax > (1UL << QFQ_MTU_SHIFT)) {
+ if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) {
pr_notice("qfq: invalid max length %u\n", lmax);
return -EINVAL;
}
} else
- lmax = 1UL << QFQ_MTU_SHIFT;
+ lmax = psched_mtu(qdisc_dev(sch));
if (cl != NULL) {
- bool need_reactivation = false;
-
if (tca[TCA_RATE]) {
err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
qdisc_root_sleeping_lock(sch),
@@ -291,24 +316,8 @@
if (lmax == cl->lmax && inv_w == cl->inv_w)
return 0; /* nothing to update */
- i = qfq_calc_index(inv_w, lmax);
sch_tree_lock(sch);
- if (&q->groups[i] != cl->grp && cl->qdisc->q.qlen > 0) {
- /*
- * shift cl->F back, to not charge the
- * class for the not-yet-served head
- * packet
- */
- cl->F = cl->S;
- /* remove class from its slot in the old group */
- qfq_deactivate_class(q, cl);
- need_reactivation = true;
- }
-
- qfq_update_class_params(q, cl, lmax, inv_w, delta_w);
-
- if (need_reactivation) /* activate in new group */
- qfq_activate_class(q, cl, qdisc_peek_len(cl->qdisc));
+ qfq_update_reactivate_class(q, cl, inv_w, lmax, delta_w);
sch_tree_unlock(sch);
return 0;
@@ -663,15 +672,48 @@
/*
- * XXX we should make sure that slot becomes less than 32.
- * This is guaranteed by the input values.
- * roundedS is always cl->S rounded on grp->slot_shift bits.
+ * If the weight and lmax (max_pkt_size) of the classes do not change,
+ * then QFQ guarantees that the slot index is never higher than
+ * 2 + ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) * (QFQ_MAX_WEIGHT/QFQ_MAX_WSUM).
+ *
+ * With the current values of the above constants, the index is
+ * then guaranteed to never be higher than 2 + 256 * (1 / 16) = 18.
+ *
+ * When the weight of a class is increased or the lmax of the class is
+ * decreased, a new class with smaller slot size may happen to be
+ * activated. The activation of this class should be properly delayed
+ * to when the service of the class has finished in the ideal system
+ * tracked by QFQ. If the activation of the class is not delayed to
+ * this reference time instant, then this class may be unjustly served
+ * before other classes waiting for service. This may cause
+ * (unfrequently) the above bound to the slot index to be violated for
+ * some of these unlucky classes.
+ *
+ * Instead of delaying the activation of the new class, which is quite
+ * complex, the following inaccurate but simple solution is used: if
+ * the slot index is higher than QFQ_MAX_SLOTS-2, then the timestamps
+ * of the class are shifted backward so as to let the slot index
+ * become equal to QFQ_MAX_SLOTS-2. This threshold is used because, if
+ * the slot index is above it, then the data structure implementing
+ * the bucket list either gets immediately corrupted or may get
+ * corrupted on a possible next packet arrival that causes the start
+ * time of the group to be shifted backward.
*/
static void qfq_slot_insert(struct qfq_group *grp, struct qfq_class *cl,
u64 roundedS)
{
u64 slot = (roundedS - grp->S) >> grp->slot_shift;
- unsigned int i = (grp->front + slot) % QFQ_MAX_SLOTS;
+ unsigned int i; /* slot index in the bucket list */
+
+ if (unlikely(slot > QFQ_MAX_SLOTS - 2)) {
+ u64 deltaS = roundedS - grp->S -
+ ((u64)(QFQ_MAX_SLOTS - 2)<<grp->slot_shift);
+ cl->S -= deltaS;
+ cl->F -= deltaS;
+ slot = QFQ_MAX_SLOTS - 2;
+ }
+
+ i = (grp->front + slot) % QFQ_MAX_SLOTS;
hlist_add_head(&cl->next, &grp->slots[i]);
__set_bit(slot, &grp->full_slots);
@@ -892,6 +934,13 @@
}
pr_debug("qfq_enqueue: cl = %x\n", cl->common.classid);
+ if (unlikely(cl->lmax < qdisc_pkt_len(skb))) {
+ pr_debug("qfq: increasing maxpkt from %u to %u for class %u",
+ cl->lmax, qdisc_pkt_len(skb), cl->common.classid);
+ qfq_update_reactivate_class(q, cl, cl->inv_w,
+ qdisc_pkt_len(skb), 0);
+ }
+
err = qdisc_enqueue(skb, cl->qdisc);
if (unlikely(err != NET_XMIT_SUCCESS)) {
pr_debug("qfq_enqueue: enqueue failed %d\n", err);
diff --git a/net/tipc/handler.c b/net/tipc/handler.c
index 111ff83..b36f0fc 100644
--- a/net/tipc/handler.c
+++ b/net/tipc/handler.c
@@ -116,7 +116,6 @@
return;
handler_enabled = 0;
- tasklet_disable(&tipc_tasklet);
tasklet_kill(&tipc_tasklet);
spin_lock_bh(&qitem_lock);
