Commit 48bddb14 authored by Linus Torvalds's avatar Linus Torvalds

Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Fix hotplug deadlock in hv_netvsc, from Stephen Hemminger.

 2) Fix double-free in rmnet driver, from Dan Carpenter.

 3) INET connection socket layer can double put request sockets, fix
    from Eric Dumazet.

 4) Don't match collect metadata-mode tunnels if the device is down,
    from Haishuang Yan.

 5) Do not perform TSO6/GSO on ipv6 packets with extensions headers in
    be2net driver, from Suresh Reddy.

 6) Fix scaling error in gen_estimator, from Eric Dumazet.

 7) Fix 64-bit statistics deadlock in systemport driver, from Florian
    Fainelli.

 8) Fix use-after-free in sctp_sock_dump, from Xin Long.

 9) Reject invalid BPF_END instructions in verifier, from Edward Cree.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (43 commits)
  mlxsw: spectrum_router: Only handle IPv4 and IPv6 events
  Documentation: link in networking docs
  tcp: fix data delivery rate
  bpf/verifier: reject BPF_ALU64|BPF_END
  sctp: do not mark sk dumped when inet_sctp_diag_fill returns err
  sctp: fix an use-after-free issue in sctp_sock_dump
  netvsc: increase default receive buffer size
  tcp: update skb->skb_mstamp more carefully
  net: ipv4: fix l3slave check for index returned in IP_PKTINFO
  net: smsc911x: Quieten netif during suspend
  net: systemport: Fix 64-bit stats deadlock
  net: vrf: avoid gcc-4.6 warning
  qed: remove unnecessary call to memset
  tg3: clean up redundant initialization of tnapi
  tls: make tls_sw_free_resources static
  sctp: potential read out of bounds in sctp_ulpevent_type_enabled()
  MAINTAINERS: review Renesas DT bindings as well
  net_sched: gen_estimator: fix scaling error in bytes/packets samples
  nfp: wait for the NSP resource to appear on boot
  nfp: wait for board state before talking to the NSP
  ...
parents c8503720 8e29f979
......@@ -45,7 +45,7 @@ in many more places. There's xt_bpf for netfilter, cls_bpf in the kernel
qdisc layer, SECCOMP-BPF (SECure COMPuting [1]), and lots of other places
such as team driver, PTP code, etc where BPF is being used.
[1] Documentation/prctl/seccomp_filter.txt
[1] Documentation/userspace-api/seccomp_filter.rst
Original BPF paper:
......
......@@ -11435,6 +11435,8 @@ RENESAS ETHERNET DRIVERS
R: Sergei Shtylyov <[email protected]>
L: [email protected]
L: [email protected]
F: Documentation/devicetree/bindings/net/renesas,*.txt
F: Documentation/devicetree/bindings/net/sh_eth.txt
F: drivers/net/ethernet/renesas/
F: include/linux/sh_eth.h
......
......@@ -4289,7 +4289,7 @@ static int bond_check_params(struct bond_params *params)
int bond_mode = BOND_MODE_ROUNDROBIN;
int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
int lacp_fast = 0;
int tlb_dynamic_lb = 0;
int tlb_dynamic_lb;
/* Convert string parameters. */
if (mode) {
......@@ -4601,16 +4601,13 @@ static int bond_check_params(struct bond_params *params)
}
ad_user_port_key = valptr->value;
if ((bond_mode == BOND_MODE_TLB) || (bond_mode == BOND_MODE_ALB)) {
bond_opt_initstr(&newval, "default");
valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB),
&newval);
if (!valptr) {
pr_err("Error: No tlb_dynamic_lb default value");
return -EINVAL;
}
tlb_dynamic_lb = valptr->value;
bond_opt_initstr(&newval, "default");
valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB), &newval);
if (!valptr) {
pr_err("Error: No tlb_dynamic_lb default value");
return -EINVAL;
}
tlb_dynamic_lb = valptr->value;
if (lp_interval == 0) {
pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n",
......
......@@ -754,6 +754,9 @@ static int bond_option_mode_set(struct bonding *bond,
bond->params.miimon);
}
if (newval->value == BOND_MODE_ALB)
bond->params.tlb_dynamic_lb = 1;
/* don't cache arp_validate between modes */
bond->params.arp_validate = BOND_ARP_VALIDATE_NONE;
bond->params.mode = newval->value;
......
......@@ -1735,11 +1735,8 @@ static void bcm_sysport_get_stats64(struct net_device *dev,
stats->tx_packets += tx_packets;
}
/* lockless update tx_bytes and tx_packets */
u64_stats_update_begin(&priv->syncp);
stats64->tx_bytes = stats->tx_bytes;
stats64->tx_packets = stats->tx_packets;
u64_stats_update_end(&priv->syncp);
do {
start = u64_stats_fetch_begin_irq(&priv->syncp);
......
......@@ -11536,11 +11536,11 @@ static int tg3_start(struct tg3 *tp, bool reset_phy, bool test_irq,
tg3_napi_enable(tp);
for (i = 0; i < tp->irq_cnt; i++) {
struct tg3_napi *tnapi = &tp->napi[i];
err = tg3_request_irq(tp, i);
if (err) {
for (i--; i >= 0; i--) {
tnapi = &tp->napi[i];
struct tg3_napi *tnapi = &tp->napi[i];
free_irq(tnapi->irq_vec, tnapi);
}
goto out_napi_fini;
......
......@@ -930,6 +930,14 @@ static inline bool is_ipv4_pkt(struct sk_buff *skb)
return skb->protocol == htons(ETH_P_IP) && ip_hdr(skb)->version == 4;
}
static inline bool is_ipv6_ext_hdr(struct sk_buff *skb)
{
if (ip_hdr(skb)->version == 6)
return ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr);
else
return false;
}
#define be_error_recovering(adapter) \
(adapter->flags & BE_FLAGS_TRY_RECOVERY)
......
......@@ -5089,6 +5089,20 @@ static netdev_features_t be_features_check(struct sk_buff *skb,
struct be_adapter *adapter = netdev_priv(dev);
u8 l4_hdr = 0;
if (skb_is_gso(skb)) {
/* IPv6 TSO requests with extension hdrs are a problem
* to Lancer and BE3 HW. Disable TSO6 feature.
*/
if (!skyhawk_chip(adapter) && is_ipv6_ext_hdr(skb))
features &= ~NETIF_F_TSO6;
/* Lancer cannot handle the packet with MSS less than 256.
* Disable the GSO support in such cases
*/
if (lancer_chip(adapter) && skb_shinfo(skb)->gso_size < 256)
features &= ~NETIF_F_GSO_MASK;
}
/* The code below restricts offload features for some tunneled and
* Q-in-Q packets.
* Offload features for normal (non tunnel) packets are unchanged.
......
......@@ -575,15 +575,14 @@ static void mlxsw_sp_span_entry_destroy(struct mlxsw_sp *mlxsw_sp,
}
static struct mlxsw_sp_span_entry *
mlxsw_sp_span_entry_find(struct mlxsw_sp_port *port)
mlxsw_sp_span_entry_find(struct mlxsw_sp *mlxsw_sp, u8 local_port)
{
struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp;
int i;
for (i = 0; i < mlxsw_sp->span.entries_count; i++) {
struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i];
if (curr->used && curr->local_port == port->local_port)
if (curr->used && curr->local_port == local_port)
return curr;
}
return NULL;
......@@ -594,7 +593,8 @@ static struct mlxsw_sp_span_entry
{
struct mlxsw_sp_span_entry *span_entry;
span_entry = mlxsw_sp_span_entry_find(port);
span_entry = mlxsw_sp_span_entry_find(port->mlxsw_sp,
port->local_port);
if (span_entry) {
/* Already exists, just take a reference */
span_entry->ref_count++;
......@@ -783,12 +783,13 @@ static int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from,
}
static void mlxsw_sp_span_mirror_remove(struct mlxsw_sp_port *from,
struct mlxsw_sp_port *to,
u8 destination_port,
enum mlxsw_sp_span_type type)
{
struct mlxsw_sp_span_entry *span_entry;
span_entry = mlxsw_sp_span_entry_find(to);
span_entry = mlxsw_sp_span_entry_find(from->mlxsw_sp,
destination_port);
if (!span_entry) {
netdev_err(from->dev, "no span entry found\n");
return;
......@@ -1563,14 +1564,12 @@ static void
mlxsw_sp_port_del_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port,
struct mlxsw_sp_port_mall_mirror_tc_entry *mirror)
{
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
enum mlxsw_sp_span_type span_type;
struct mlxsw_sp_port *to_port;
to_port = mlxsw_sp->ports[mirror->to_local_port];
span_type = mirror->ingress ?
MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS;
mlxsw_sp_span_mirror_remove(mlxsw_sp_port, to_port, span_type);
mlxsw_sp_span_mirror_remove(mlxsw_sp_port, mirror->to_local_port,
span_type);
}
static int
......@@ -2545,7 +2544,9 @@ static int mlxsw_sp_flash_device(struct net_device *dev,
return err;
}
#define MLXSW_SP_QSFP_I2C_ADDR 0x50
#define MLXSW_SP_I2C_ADDR_LOW 0x50
#define MLXSW_SP_I2C_ADDR_HIGH 0x51
#define MLXSW_SP_EEPROM_PAGE_LENGTH 256
static int mlxsw_sp_query_module_eeprom(struct mlxsw_sp_port *mlxsw_sp_port,
u16 offset, u16 size, void *data,
......@@ -2554,12 +2555,25 @@ static int mlxsw_sp_query_module_eeprom(struct mlxsw_sp_port *mlxsw_sp_port,
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
char eeprom_tmp[MLXSW_SP_REG_MCIA_EEPROM_SIZE];
char mcia_pl[MLXSW_REG_MCIA_LEN];
u16 i2c_addr;
int status;
int err;
size = min_t(u16, size, MLXSW_SP_REG_MCIA_EEPROM_SIZE);
if (offset < MLXSW_SP_EEPROM_PAGE_LENGTH &&
offset + size > MLXSW_SP_EEPROM_PAGE_LENGTH)
/* Cross pages read, read until offset 256 in low page */
size = MLXSW_SP_EEPROM_PAGE_LENGTH - offset;
i2c_addr = MLXSW_SP_I2C_ADDR_LOW;
if (offset >= MLXSW_SP_EEPROM_PAGE_LENGTH) {
i2c_addr = MLXSW_SP_I2C_ADDR_HIGH;
offset -= MLXSW_SP_EEPROM_PAGE_LENGTH;
}
mlxsw_reg_mcia_pack(mcia_pl, mlxsw_sp_port->mapping.module,
0, 0, offset, size, MLXSW_SP_QSFP_I2C_ADDR);
0, 0, offset, size, i2c_addr);
err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(mcia), mcia_pl);
if (err)
......
......@@ -4868,7 +4868,8 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
struct fib_notifier_info *info = ptr;
struct mlxsw_sp_router *router;
if (!net_eq(info->net, &init_net))
if (!net_eq(info->net, &init_net) ||
(info->family != AF_INET && info->family != AF_INET6))
return NOTIFY_DONE;
fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
......
......@@ -44,6 +44,16 @@
#include "../nfp_net.h"
#include "../nfp_port.h"
#define NFP_FLOWER_WHITELIST_DISSECTOR \
(BIT(FLOW_DISSECTOR_KEY_CONTROL) | \
BIT(FLOW_DISSECTOR_KEY_BASIC) | \
BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | \
BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | \
BIT(FLOW_DISSECTOR_KEY_PORTS) | \
BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | \
BIT(FLOW_DISSECTOR_KEY_VLAN) | \
BIT(FLOW_DISSECTOR_KEY_IP))
static int
nfp_flower_xmit_flow(struct net_device *netdev,
struct nfp_fl_payload *nfp_flow, u8 mtype)
......@@ -112,6 +122,9 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls,
u8 key_layer;
int key_size;
if (flow->dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR)
return -EOPNOTSUPP;
if (dissector_uses_key(flow->dissector,
FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
struct flow_dissector_key_control *mask_enc_ctl =
......
......@@ -74,6 +74,45 @@ static const struct pci_device_id nfp_pci_device_ids[] = {
};
MODULE_DEVICE_TABLE(pci, nfp_pci_device_ids);
static bool nfp_board_ready(struct nfp_pf *pf)
{
const char *cp;
long state;
int err;
cp = nfp_hwinfo_lookup(pf->hwinfo, "board.state");
if (!cp)
return false;
err = kstrtol(cp, 0, &state);
if (err < 0)
return false;
return state == 15;
}
static int nfp_pf_board_state_wait(struct nfp_pf *pf)
{
const unsigned long wait_until = jiffies + 10 * HZ;
while (!nfp_board_ready(pf)) {
if (time_is_before_eq_jiffies(wait_until)) {
nfp_err(pf->cpp, "NFP board initialization timeout\n");
return -EINVAL;
}
nfp_info(pf->cpp, "waiting for board initialization\n");
if (msleep_interruptible(500))
return -ERESTARTSYS;
/* Refresh cached information */
kfree(pf->hwinfo);
pf->hwinfo = nfp_hwinfo_read(pf->cpp);
}
return 0;
}
static int nfp_pcie_sriov_read_nfd_limit(struct nfp_pf *pf)
{
int err;
......@@ -312,6 +351,10 @@ static int nfp_nsp_init(struct pci_dev *pdev, struct nfp_pf *pf)
struct nfp_nsp *nsp;
int err;
err = nfp_resource_wait(pf->cpp, NFP_RESOURCE_NSP, 30);
if (err)
return err;
nsp = nfp_nsp_open(pf->cpp);
if (IS_ERR(nsp)) {
err = PTR_ERR(nsp);
......@@ -425,6 +468,10 @@ static int nfp_pci_probe(struct pci_dev *pdev,
nfp_hwinfo_lookup(pf->hwinfo, "assembly.revision"),
nfp_hwinfo_lookup(pf->hwinfo, "cpld.version"));
err = nfp_pf_board_state_wait(pf);
if (err)
goto err_hwinfo_free;
err = devlink_register(devlink, &pdev->dev);
if (err)
goto err_hwinfo_free;
......
......@@ -64,23 +64,6 @@
#define NFP_PF_CSR_SLICE_SIZE (32 * 1024)
static int nfp_is_ready(struct nfp_pf *pf)
{
const char *cp;
long state;
int err;
cp = nfp_hwinfo_lookup(pf->hwinfo, "board.state");
if (!cp)
return 0;
err = kstrtol(cp, 0, &state);
if (err < 0)
return 0;
return state == 15;
}
/**
* nfp_net_get_mac_addr() - Get the MAC address.
* @pf: NFP PF handle
......@@ -725,12 +708,6 @@ int nfp_net_pci_probe(struct nfp_pf *pf)
INIT_WORK(&pf->port_refresh_work, nfp_net_refresh_vnics);
/* Verify that the board has completed initialization */
if (!nfp_is_ready(pf)) {
nfp_err(pf->cpp, "NFP is not ready for NIC operation.\n");
return -EINVAL;
}
if (!pf->rtbl) {
nfp_err(pf->cpp, "No %s, giving up.\n",
pf->fw_loaded ? "symbol table" : "firmware found");
......
......@@ -97,6 +97,8 @@ nfp_resource_acquire(struct nfp_cpp *cpp, const char *name);
void nfp_resource_release(struct nfp_resource *res);
int nfp_resource_wait(struct nfp_cpp *cpp, const char *name, unsigned int secs);
u32 nfp_resource_cpp_id(struct nfp_resource *res);
const char *nfp_resource_name(struct nfp_resource *res);
......
......@@ -249,6 +249,51 @@ void nfp_resource_release(struct nfp_resource *res)
kfree(res);
}
/**
* nfp_resource_wait() - Wait for resource to appear
* @cpp: NFP CPP handle
* @name: Name of the resource
* @secs: Number of seconds to wait
*
* Wait for resource to appear in the resource table, grab and release
* its lock. The wait is jiffies-based, don't expect fine granularity.
*
* Return: 0 on success, errno otherwise.
*/
int nfp_resource_wait(struct nfp_cpp *cpp, const char *name, unsigned int secs)
{
unsigned long warn_at = jiffies + NFP_MUTEX_WAIT_FIRST_WARN * HZ;
unsigned long err_at = jiffies + secs * HZ;
struct nfp_resource *res;
while (true) {
res = nfp_resource_acquire(cpp, name);
if (!IS_ERR(res)) {
nfp_resource_release(res);
return 0;
}
if (PTR_ERR(res) != -ENOENT) {
nfp_err(cpp, "error waiting for resource %s: %ld\n",
name, PTR_ERR(res));
return PTR_ERR(res);
}
if (time_is_before_eq_jiffies(err_at)) {
nfp_err(cpp, "timeout waiting for resource %s\n", name);
return -ETIMEDOUT;
}
if (time_is_before_eq_jiffies(warn_at)) {
warn_at = jiffies + NFP_MUTEX_WAIT_NEXT_WARN * HZ;
nfp_info(cpp, "waiting for NFP resource %s\n", name);
}
if (msleep_interruptible(10)) {
nfp_err(cpp, "wait for resource %s interrupted\n",
name);
return -ERESTARTSYS;
}
}
}
/**
* nfp_resource_cpp_id() - Return the cpp_id of a resource handle
* @res: NFP Resource handle
......
......@@ -11,6 +11,7 @@
#include <linux/module.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/mii.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
......
......@@ -1244,7 +1244,6 @@ int qed_dcbx_get_config_params(struct qed_hwfn *p_hwfn,
if (!dcbx_info)
return -ENOMEM;
memset(dcbx_info, 0, sizeof(*dcbx_info));
rc = qed_dcbx_query_params(p_hwfn, dcbx_info, QED_DCBX_OPERATIONAL_MIB);
if (rc) {
kfree(dcbx_info);
......
......@@ -84,6 +84,10 @@ struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb)
if (((int)skb->len - (int)packet_len) < 0)
return NULL;
/* Some hardware can send us empty frames. Catch them */
if (ntohs(maph->pkt_len) == 0)
return NULL;
skbn = alloc_skb(packet_len + RMNET_MAP_DEAGGR_SPACING, GFP_ATOMIC);
if (!skbn)
return NULL;
......@@ -94,11 +98,5 @@ struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb)
memcpy(skbn->data, skb->data, packet_len);
skb_pull(skb, packet_len);
/* Some hardware can send us empty frames. Catch them */
if (ntohs(maph->pkt_len) == 0) {
kfree_skb(skb);
return NULL;
}
return skbn;
}
......@@ -2595,6 +2595,11 @@ static int smsc911x_suspend(struct device *dev)
struct net_device *ndev = dev_get_drvdata(dev);
struct smsc911x_data *pdata = netdev_priv(ndev);
if (netif_running(ndev)) {
netif_stop_queue(ndev);
netif_device_detach(ndev);
}
/* enable wake on LAN, energy detection and the external PME
* signal. */
smsc911x_reg_write(pdata, PMT_CTRL,
......@@ -2628,7 +2633,15 @@ static int smsc911x_resume(struct device *dev)
while (!(smsc911x_reg_read(pdata, PMT_CTRL) & PMT_CTRL_READY_) && --to)
udelay(1000);
return (to == 0) ? -EIO : 0;
if (to == 0)
return -EIO;
if (netif_running(ndev)) {
netif_device_attach(ndev);
netif_start_queue(ndev);
}
return 0;
}
static const struct dev_pm_ops smsc911x_pm_ops = {
......
......@@ -204,6 +204,8 @@ int netvsc_recv_callback(struct net_device *net,
const struct ndis_pkt_8021q_info *vlan);
void netvsc_channel_cb(void *context);
int netvsc_poll(struct napi_struct *napi, int budget);
void rndis_set_subchannel(struct work_struct *w);
bool rndis_filter_opened(const struct netvsc_device *nvdev);
int rndis_filter_open(struct netvsc_device *nvdev);
int rndis_filter_close(struct netvsc_device *nvdev);
......@@ -782,6 +784,7 @@ struct netvsc_device {
u32 num_chn;
atomic_t open_chn;
struct work_struct subchan_work;
wait_queue_head_t subchan_open;
struct rndis_device *extension;
......
......@@ -81,6 +81,7 @@ static struct netvsc_device *alloc_net_device(void)
init_completion(&net_device->channel_init_wait);
init_waitqueue_head(&net_device->subchan_open);
INIT_WORK(&net_device->subchan_work, rndis_set_subchannel);
return net_device;
}
......@@ -557,6 +558,8 @@ void netvsc_device_remove(struct hv_device *device)
= rtnl_dereference(net_device_ctx->nvdev);
int i;
cancel_work_sync(&net_device->subchan_work);
netvsc_disconnect_vsp(device);
RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);
......
......@@ -49,7 +49,7 @@
#define NETVSC_MIN_TX_SECTIONS 10
#define NETVSC_DEFAULT_TX 192 /* ~1M */
#define NETVSC_MIN_RX_SECTIONS 10 /* ~64K */
#define NETVSC_DEFAULT_RX 2048 /* ~4M */
#define NETVSC_DEFAULT_RX 10485 /* Max ~16M */
#define LINKCHANGE_INT (2 * HZ)
#define VF_TAKEOVER_INT (HZ / 10)
......@@ -853,10 +853,7 @@ static int netvsc_set_channels(struct net_device *net,
rndis_filter_device_remove(dev, nvdev);
nvdev = rndis_filter_device_add(dev, &device_info);
if (!IS_ERR(nvdev)) {
netif_set_real_num_tx_queues(net, nvdev->num_chn);
netif_set_real_num_rx_queues(net, nvdev->num_chn);
} else {
if (IS_ERR(nvdev)) {
ret = PTR_ERR(nvdev);
device_info.num_chn = orig;
nvdev = rndis_filter_device_add(dev, &device_info);
......@@ -1954,9 +1951,6 @@ static int netvsc_probe(struct hv_device *dev,
NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
net->vlan_features = net->features;
netif_set_real_num_tx_queues(net, nvdev->num_chn);
netif_set_real_num_rx_queues(net, nvdev->num_chn);
netdev_lockdep_set_classes(net);
/* MTU range: 68 - 1500 or 65521 */
......@@ -2012,9 +2006,10 @@ static int netvsc_remove(struct hv_device *dev)
if (vf_netdev)
netvsc_unregister_vf(vf_netdev);
unregister_netdevice(net);
rndis_filter_device_remove(dev,
rtnl_dereference(ndev_ctx->nvdev));
unregister_netdevice(net);
rtnl_unlock();
hv_set_drvdata(dev, NULL);
......
......@@ -1039,8 +1039,6 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
/* Set the channel before opening.*/
nvchan->channel = new_sc;
netif_napi_add(ndev, &nvchan->napi,
netvsc_poll, NAPI_POLL_WEIGHT);
ret = vmbus_open(new_sc, nvscdev->ring_size * PAGE_SIZE,
nvscdev->ring_size * PAGE_SIZE, NULL, 0,
......@@ -1048,10 +1046,86 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
if (ret == 0)
napi_enable(&nvchan->napi);
else
netif_napi_del(&nvchan->napi);
netdev_notice(ndev, "sub channel open failed: %d\n", ret);
atomic_inc(&nvscdev->open_chn);
wake_up(&nvscdev->subchan_open);
if (atomic_inc_return(&nvscdev->open_chn) == nvscdev->num_chn)
wake_up(&nvscdev->subchan_open);
}
/* Open sub-channels after completing the handling of the device probe.
* This breaks overlap of processing the host message for the
* new primary channel with the initialization of sub-channels.
*/
void rndis_set_subchannel(struct work_struct *w)
{
struct netvsc_device *nvdev
= container_of(w, struct netvsc_device, subchan_work);
struct nvsp_message *init_packet = &nvdev->channel_init_pkt;
struct net_device_context *ndev_ctx;
struct rndis_device *rdev;
struct net_device *ndev;
struct hv_device *hv_dev;
int i, ret;
if (!rtnl_trylock()) {
schedule_work(w);
return;
}
rdev = nvdev->extension;
if (!rdev)
goto unlock; /* device was removed */
ndev = rdev->ndev;
ndev_ctx = netdev_priv(ndev);
hv_dev = ndev_ctx->device_ctx;
memset(init_packet, 0, sizeof(struct nvsp_message));
init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL;
init_packet->msg.v5_msg.subchn_req.op = NVSP_SUBCHANNEL_ALLOCATE;
init_packet->msg.v5_msg.subchn_req.num_subchannels =
nvdev->num_chn - 1;
ret = vmbus_sendpacket(hv_dev->channel, init_packet,
sizeof(struct nvsp_message),
(unsigned long)init_packet,
VM_PKT_DATA_INBAND,
VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
if (ret) {
netdev_err(ndev, "sub channel allocate send failed: %d\n", ret);
goto failed;
}
wait_for_completion(&nvdev->channel_init_wait);
if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) {
netdev_err(ndev, "sub channel request failed\n");
goto failed;
}
nvdev->num_chn = 1 +
init_packet->msg.v5_msg.subchn_comp.num_subchannels;
/* wait for all sub channels to open */
wait_event(nvdev->subchan_open,
atomic_read(&nvdev->open_chn) == nvdev->num_chn);
/* ignore failues from setting rss parameters, still have channels */
rndis_filter_set_rss_param(rdev, netvsc_hash_key);
netif_set_real_num_tx_queues(ndev, nvdev->num_chn);
netif_set_real_num_rx_queues(ndev, nvdev->num_chn);
rtnl_unlock();
return;
failed:
/* fallback to only primary channel */
for (i = 1; i < nvdev->num_chn; i++)
netif_napi_del(&nvdev->chan_table[i].napi);
nvdev->max_chn = 1;
nvdev->num_chn = 1;
unlock:
rtnl_unlock();
}
struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
......@@ -1063,7 +1137,6 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
struct rndis_device *rndis_device;
struct ndis_offload hwcaps;
struct ndis_offload_params offloads;
struct nvsp_message *init_packet;
struct ndis_recv_scale_cap rsscap;
u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
unsigned int gso_max_size = GSO_MAX_SIZE;
......@@ -1215,9 +1288,7 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
net_device->num_chn);
atomic_set(&net_device->open_chn, 1);
if (net_device->num_chn == 1)
return net_device;
vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open);
for (i = 1; i < net_device->num_chn; i++) {
ret = netvsc_alloc_recv_comp_ring(net_device, i);
......@@ -1228,38 +1299,15 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
}
}
vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open);