renegade-project/linux-next
2
0
Fork 0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-27 06:34:11 +08:00
Code
98508c9300
linux-next/drivers/net/ixgbe/ixgbe_sriov.c
Lior Levy ff4ab20611 ixgbe: add support for VF Transmit rate limit using iproute2 
Implemented ixgbe_ndo_set_vf_bw function which is being used by iproute2
tool. In addition, updated ixgbe_ndo_get_vf_config function to show the
actual rate limit to the user.

The rate limitation can be configured only when the link is up and the
link speed is 10Gb.
The rate limit value can be 0 or ranged between 11 and actual link
speed measured in Mbps. A value of '0' disables the rate limit for
this specific VF.

iproute2 usage will be 'ip link set ethX vf Y rate Z'.
After the command is made, the rate will be changed instantly.
To view the current rate limit, use 'ip link show ethX'.

The rates will be zeroed only upon driver reload or a link speed change.

This feature is being supported by 82599 and X540 devices.

Signed-off-by: Lior Levy <lior.levy@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2011-03-12 04:15:08 -08:00

580 lines
16 KiB
C
Raw Blame History

/*******************************************************************************
Intel 10 Gigabit PCI Express Linux driver
Copyright(c) 1999 - 2011 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
version 2, as published by the Free Software Foundation.
This program is distributed in the hope it will be useful, but WITHOUT
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
more details.
You should have received a copy of the GNU General Public License along with
this program; if not, write to the Free Software Foundation, Inc.,
51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
Contact Information:
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
*******************************************************************************/
#include <linux/types.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/netdevice.h>
#include <linux/vmalloc.h>
#include <linux/string.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/ipv6.h>
#ifdef NETIF_F_HW_VLAN_TX
#include <linux/if_vlan.h>
#endif
#include "ixgbe.h"
#include "ixgbe_sriov.h"
static int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter,
int entries, u16 *hash_list, u32 vf)
{
struct vf_data_storage *vfinfo = &adapter->vfinfo[vf];
struct ixgbe_hw *hw = &adapter->hw;
int i;
u32 vector_bit;
u32 vector_reg;
u32 mta_reg;
/* only so many hash values supported */
entries = min(entries, IXGBE_MAX_VF_MC_ENTRIES);
/*
* salt away the number of multi cast addresses assigned
* to this VF for later use to restore when the PF multi cast
* list changes
*/
vfinfo->num_vf_mc_hashes = entries;
/*
* VFs are limited to using the MTA hash table for their multicast
* addresses
*/
for (i = 0; i < entries; i++) {
vfinfo->vf_mc_hashes[i] = hash_list[i];
}
for (i = 0; i < vfinfo->num_vf_mc_hashes; i++) {
vector_reg = (vfinfo->vf_mc_hashes[i] >> 5) & 0x7F;
vector_bit = vfinfo->vf_mc_hashes[i] & 0x1F;
mta_reg = IXGBE_READ_REG(hw, IXGBE_MTA(vector_reg));
mta_reg |= (1 << vector_bit);
IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg);
}
return 0;
}
void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter)
{
struct ixgbe_hw *hw = &adapter->hw;
struct vf_data_storage *vfinfo;
int i, j;
u32 vector_bit;
u32 vector_reg;
u32 mta_reg;
for (i = 0; i < adapter->num_vfs; i++) {
vfinfo = &adapter->vfinfo[i];
for (j = 0; j < vfinfo->num_vf_mc_hashes; j++) {
hw->addr_ctrl.mta_in_use++;
vector_reg = (vfinfo->vf_mc_hashes[j] >> 5) & 0x7F;
vector_bit = vfinfo->vf_mc_hashes[j] & 0x1F;
mta_reg = IXGBE_READ_REG(hw, IXGBE_MTA(vector_reg));
mta_reg |= (1 << vector_bit);
IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg);
}
}
}
static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid,
u32 vf)
{
return adapter->hw.mac.ops.set_vfta(&adapter->hw, vid, vf, (bool)add);
}
void ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf)
{
struct ixgbe_hw *hw = &adapter->hw;
int new_mtu = msgbuf[1];
u32 max_frs;
int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
/* Only X540 supports jumbo frames in IOV mode */
if (adapter->hw.mac.type != ixgbe_mac_X540)
return;
/* MTU < 68 is an error and causes problems on some kernels */
if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE)) {
e_err(drv, "VF mtu %d out of range\n", new_mtu);
return;
}
max_frs = (IXGBE_READ_REG(hw, IXGBE_MAXFRS) &
IXGBE_MHADD_MFS_MASK) >> IXGBE_MHADD_MFS_SHIFT;
if (max_frs < new_mtu) {
max_frs = new_mtu << IXGBE_MHADD_MFS_SHIFT;
IXGBE_WRITE_REG(hw, IXGBE_MAXFRS, max_frs);
}
e_info(hw, "VF requests change max MTU to %d\n", new_mtu);
}
static void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf, bool aupe)
{
u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf));
vmolr |= (IXGBE_VMOLR_ROMPE |
IXGBE_VMOLR_BAM);
if (aupe)
vmolr |= IXGBE_VMOLR_AUPE;
else
vmolr &= ~IXGBE_VMOLR_AUPE;
IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr);
}
static void ixgbe_set_vmvir(struct ixgbe_adapter *adapter, u32 vid, u32 vf)
{
struct ixgbe_hw *hw = &adapter->hw;
if (vid)
IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf),
(vid | IXGBE_VMVIR_VLANA_DEFAULT));
else
IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), 0);
}
static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf)
{
struct ixgbe_hw *hw = &adapter->hw;
int rar_entry = hw->mac.num_rar_entries - (vf + 1);
/* reset offloads to defaults */
if (adapter->vfinfo[vf].pf_vlan) {
ixgbe_set_vf_vlan(adapter, true,
adapter->vfinfo[vf].pf_vlan, vf);
ixgbe_set_vmvir(adapter,
(adapter->vfinfo[vf].pf_vlan |
(adapter->vfinfo[vf].pf_qos <<
VLAN_PRIO_SHIFT)), vf);
ixgbe_set_vmolr(hw, vf, false);
} else {
ixgbe_set_vmvir(adapter, 0, vf);
ixgbe_set_vmolr(hw, vf, true);
}
/* reset multicast table array for vf */
adapter->vfinfo[vf].num_vf_mc_hashes = 0;
/* Flush and reset the mta with the new values */
ixgbe_set_rx_mode(adapter->netdev);
hw->mac.ops.clear_rar(hw, rar_entry);
}
static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter,
int vf, unsigned char *mac_addr)
{
struct ixgbe_hw *hw = &adapter->hw;
int rar_entry = hw->mac.num_rar_entries - (vf + 1);
memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, 6);
hw->mac.ops.set_rar(hw, rar_entry, mac_addr, vf, IXGBE_RAH_AV);
return 0;
}
int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask)
{
unsigned char vf_mac_addr[6];
struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
unsigned int vfn = (event_mask & 0x3f);
bool enable = ((event_mask & 0x10000000U) != 0);
if (enable) {
random_ether_addr(vf_mac_addr);
e_info(probe, "IOV: VF %d is enabled MAC %pM\n",
vfn, vf_mac_addr);
/*
* Store away the VF "permananet" MAC address, it will ask
* for it later.
*/
memcpy(adapter->vfinfo[vfn].vf_mac_addresses, vf_mac_addr, 6);
}
return 0;
}
static inline void ixgbe_vf_reset_msg(struct ixgbe_adapter *adapter, u32 vf)
{
struct ixgbe_hw *hw = &adapter->hw;
u32 reg;
u32 reg_offset, vf_shift;
vf_shift = vf % 32;
reg_offset = vf / 32;
/* enable transmit and receive for vf */
reg = IXGBE_READ_REG(hw, IXGBE_VFTE(reg_offset));
reg |= (reg | (1 << vf_shift));
IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), reg);
reg = IXGBE_READ_REG(hw, IXGBE_VFRE(reg_offset));
reg |= (reg | (1 << vf_shift));
IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), reg);
/* Enable counting of spoofed packets in the SSVPC register */
reg = IXGBE_READ_REG(hw, IXGBE_VMECM(reg_offset));
reg |= (1 << vf_shift);
IXGBE_WRITE_REG(hw, IXGBE_VMECM(reg_offset), reg);
ixgbe_vf_reset_event(adapter, vf);
}
static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
{
u32 mbx_size = IXGBE_VFMAILBOX_SIZE;
u32 msgbuf[mbx_size];
struct ixgbe_hw *hw = &adapter->hw;
s32 retval;
int entries;
u16 *hash_list;
int add, vid;
u8 *new_mac;
retval = ixgbe_read_mbx(hw, msgbuf, mbx_size, vf);
if (retval)
pr_err("Error receiving message from VF\n");
/* this is a message we already processed, do nothing */
if (msgbuf[0] & (IXGBE_VT_MSGTYPE_ACK | IXGBE_VT_MSGTYPE_NACK))
return retval;
/*
* until the vf completes a virtual function reset it should not be
* allowed to start any configuration.
*/
if (msgbuf[0] == IXGBE_VF_RESET) {
unsigned char *vf_mac = adapter->vfinfo[vf].vf_mac_addresses;
new_mac = (u8 *)(&msgbuf[1]);
e_info(probe, "VF Reset msg received from vf %d\n", vf);
adapter->vfinfo[vf].clear_to_send = false;
ixgbe_vf_reset_msg(adapter, vf);
adapter->vfinfo[vf].clear_to_send = true;
if (is_valid_ether_addr(new_mac) &&
!adapter->vfinfo[vf].pf_set_mac)
ixgbe_set_vf_mac(adapter, vf, vf_mac);
else
ixgbe_set_vf_mac(adapter,
vf, adapter->vfinfo[vf].vf_mac_addresses);
/* reply to reset with ack and vf mac address */
msgbuf[0] = IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK;
memcpy(new_mac, vf_mac, IXGBE_ETH_LENGTH_OF_ADDRESS);
/*
* Piggyback the multicast filter type so VF can compute the
* correct vectors
*/
msgbuf[3] = hw->mac.mc_filter_type;
ixgbe_write_mbx(hw, msgbuf, IXGBE_VF_PERMADDR_MSG_LEN, vf);
return retval;
}
if (!adapter->vfinfo[vf].clear_to_send) {
msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK;
ixgbe_write_mbx(hw, msgbuf, 1, vf);
return retval;
}
switch ((msgbuf[0] & 0xFFFF)) {
case IXGBE_VF_SET_MAC_ADDR:
new_mac = ((u8 *)(&msgbuf[1]));
if (is_valid_ether_addr(new_mac) &&
!adapter->vfinfo[vf].pf_set_mac) {
ixgbe_set_vf_mac(adapter, vf, new_mac);
} else if (memcmp(adapter->vfinfo[vf].vf_mac_addresses,
new_mac, ETH_ALEN)) {
e_warn(drv, "VF %d attempted to override "
"administratively set MAC address\nReload "
"the VF driver to resume operations\n", vf);
retval = -1;
}
break;
case IXGBE_VF_SET_MULTICAST:
entries = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK)
>> IXGBE_VT_MSGINFO_SHIFT;
hash_list = (u16 *)&msgbuf[1];
retval = ixgbe_set_vf_multicasts(adapter, entries,
hash_list, vf);
break;
case IXGBE_VF_SET_LPE:
ixgbe_set_vf_lpe(adapter, msgbuf);
break;
case IXGBE_VF_SET_VLAN:
add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK)
>> IXGBE_VT_MSGINFO_SHIFT;
vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK);
if (adapter->vfinfo[vf].pf_vlan) {
e_warn(drv, "VF %d attempted to override "
"administratively set VLAN configuration\n"
"Reload the VF driver to resume operations\n",
vf);
retval = -1;
} else {
retval = ixgbe_set_vf_vlan(adapter, add, vid, vf);
}
break;
default:
e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]);
retval = IXGBE_ERR_MBX;
break;
}
/* notify the VF of the results of what it sent us */
if (retval)
msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK;
else
msgbuf[0] |= IXGBE_VT_MSGTYPE_ACK;
msgbuf[0] |= IXGBE_VT_MSGTYPE_CTS;
ixgbe_write_mbx(hw, msgbuf, 1, vf);
return retval;
}
static void ixgbe_rcv_ack_from_vf(struct ixgbe_adapter *adapter, u32 vf)
{
struct ixgbe_hw *hw = &adapter->hw;
u32 msg = IXGBE_VT_MSGTYPE_NACK;
/* if device isn't clear to send it shouldn't be reading either */
if (!adapter->vfinfo[vf].clear_to_send)
ixgbe_write_mbx(hw, &msg, 1, vf);
}
void ixgbe_msg_task(struct ixgbe_adapter *adapter)
{
struct ixgbe_hw *hw = &adapter->hw;
u32 vf;
for (vf = 0; vf < adapter->num_vfs; vf++) {
/* process any reset requests */
if (!ixgbe_check_for_rst(hw, vf))
ixgbe_vf_reset_event(adapter, vf);
/* process any messages pending */
if (!ixgbe_check_for_msg(hw, vf))
ixgbe_rcv_msg_from_vf(adapter, vf);
/* process any acks */
if (!ixgbe_check_for_ack(hw, vf))
ixgbe_rcv_ack_from_vf(adapter, vf);
}
}
void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter)
{
struct ixgbe_hw *hw = &adapter->hw;
/* disable transmit and receive for all vfs */
IXGBE_WRITE_REG(hw, IXGBE_VFTE(0), 0);
IXGBE_WRITE_REG(hw, IXGBE_VFTE(1), 0);
IXGBE_WRITE_REG(hw, IXGBE_VFRE(0), 0);
IXGBE_WRITE_REG(hw, IXGBE_VFRE(1), 0);
}
void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter)
{
struct ixgbe_hw *hw = &adapter->hw;
u32 ping;
int i;
for (i = 0 ; i < adapter->num_vfs; i++) {
ping = IXGBE_PF_CONTROL_MSG;
if (adapter->vfinfo[i].clear_to_send)
ping |= IXGBE_VT_MSGTYPE_CTS;
ixgbe_write_mbx(hw, &ping, 1, i);
}
}
int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
if (!is_valid_ether_addr(mac) || (vf >= adapter->num_vfs))
return -EINVAL;
adapter->vfinfo[vf].pf_set_mac = true;
dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", mac, vf);
dev_info(&adapter->pdev->dev, "Reload the VF driver to make this"
" change effective.");
if (test_bit(__IXGBE_DOWN, &adapter->state)) {
dev_warn(&adapter->pdev->dev, "The VF MAC address has been set,"
" but the PF device is not up.\n");
dev_warn(&adapter->pdev->dev, "Bring the PF device up before"
" attempting to use the VF device.\n");
}
return ixgbe_set_vf_mac(adapter, vf, mac);
}
int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos)
{
int err = 0;
struct ixgbe_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
if ((vf >= adapter->num_vfs) || (vlan > 4095) || (qos > 7))
return -EINVAL;
if (vlan || qos) {
err = ixgbe_set_vf_vlan(adapter, true, vlan, vf);
if (err)
goto out;
ixgbe_set_vmvir(adapter, vlan | (qos << VLAN_PRIO_SHIFT), vf);
ixgbe_set_vmolr(hw, vf, false);
hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf);
adapter->vfinfo[vf].pf_vlan = vlan;
adapter->vfinfo[vf].pf_qos = qos;
dev_info(&adapter->pdev->dev,
"Setting VLAN %d, QOS 0x%x on VF %d\n", vlan, qos, vf);
if (test_bit(__IXGBE_DOWN, &adapter->state)) {
dev_warn(&adapter->pdev->dev,
"The VF VLAN has been set,"
" but the PF device is not up.\n");
dev_warn(&adapter->pdev->dev,
"Bring the PF device up before"
" attempting to use the VF device.\n");
}
} else {
err = ixgbe_set_vf_vlan(adapter, false,
adapter->vfinfo[vf].pf_vlan, vf);
ixgbe_set_vmvir(adapter, vlan, vf);
ixgbe_set_vmolr(hw, vf, true);
hw->mac.ops.set_vlan_anti_spoofing(hw, false, vf);
adapter->vfinfo[vf].pf_vlan = 0;
adapter->vfinfo[vf].pf_qos = 0;
}
out:
return err;
}
static int ixgbe_link_mbps(int internal_link_speed)
{
switch (internal_link_speed) {
case IXGBE_LINK_SPEED_100_FULL:
return 100;
case IXGBE_LINK_SPEED_1GB_FULL:
return 1000;
case IXGBE_LINK_SPEED_10GB_FULL:
return 10000;
default:
return 0;
}
}
static void ixgbe_set_vf_rate_limit(struct ixgbe_hw *hw, int vf, int tx_rate,
int link_speed)
{
int rf_dec, rf_int;
u32 bcnrc_val;
if (tx_rate != 0) {
/* Calculate the rate factor values to set */
rf_int = link_speed / tx_rate;
rf_dec = (link_speed - (rf_int * tx_rate));
rf_dec = (rf_dec * (1<<IXGBE_RTTBCNRC_RF_INT_SHIFT)) / tx_rate;
bcnrc_val = IXGBE_RTTBCNRC_RS_ENA;
bcnrc_val |= ((rf_int<<IXGBE_RTTBCNRC_RF_INT_SHIFT) &
IXGBE_RTTBCNRC_RF_INT_MASK);
bcnrc_val |= (rf_dec & IXGBE_RTTBCNRC_RF_DEC_MASK);
} else {
bcnrc_val = 0;
}
IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, 2*vf); /* vf Y uses queue 2*Y */
IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val);
}
void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter)
{
int actual_link_speed, i;
bool reset_rate = false;
/* VF Tx rate limit was not set */
if (adapter->vf_rate_link_speed == 0)
return;
actual_link_speed = ixgbe_link_mbps(adapter->link_speed);
if (actual_link_speed != adapter->vf_rate_link_speed) {
reset_rate = true;
adapter->vf_rate_link_speed = 0;
dev_info(&adapter->pdev->dev,
"Link speed has been changed. VF Transmit rate "
"is disabled\n");
}
for (i = 0; i < adapter->num_vfs; i++) {
if (reset_rate)
adapter->vfinfo[i].tx_rate = 0;
ixgbe_set_vf_rate_limit(&adapter->hw, i,
adapter->vfinfo[i].tx_rate,
actual_link_speed);
}
}
int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
int actual_link_speed;
actual_link_speed = ixgbe_link_mbps(adapter->link_speed);
if ((vf >= adapter->num_vfs) || (!adapter->link_up) ||
(tx_rate > actual_link_speed) || (actual_link_speed != 10000) ||
((tx_rate != 0) && (tx_rate <= 10)))
/* rate limit cannot be set to 10Mb or less in 10Gb adapters */
return -EINVAL;
adapter->vf_rate_link_speed = actual_link_speed;
adapter->vfinfo[vf].tx_rate = (u16)tx_rate;
ixgbe_set_vf_rate_limit(hw, vf, tx_rate, actual_link_speed);
return 0;
}
int ixgbe_ndo_get_vf_config(struct net_device *netdev,
int vf, struct ifla_vf_info *ivi)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
if (vf >= adapter->num_vfs)
return -EINVAL;
ivi->vf = vf;
memcpy(&ivi->mac, adapter->vfinfo[vf].vf_mac_addresses, ETH_ALEN);
ivi->tx_rate = adapter->vfinfo[vf].tx_rate;
ivi->vlan = adapter->vfinfo[vf].pf_vlan;
ivi->qos = adapter->vfinfo[vf].pf_qos;
return 0;
}
View Git Blame Copy Permalink