qemu/hw/e1000.c

1236 lines
39 KiB
C
Raw Normal View History

/*
* QEMU e1000 emulation
*
* Software developer's manual:
* http://download.intel.com/design/network/manuals/8254x_GBe_SDM.pdf
*
* Nir Peleg, Tutis Systems Ltd. for Qumranet Inc.
* Copyright (c) 2008 Qumranet
* Based on work done by:
* Copyright (c) 2007 Dan Aloni
* Copyright (c) 2004 Antony T Curtis
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, see <http://www.gnu.org/licenses/>.
*/
#include "hw.h"
#include "pci.h"
#include "net.h"
#include "net/checksum.h"
#include "loader.h"
#include "sysemu.h"
#include "dma.h"
#include "e1000_hw.h"
#define E1000_DEBUG
#ifdef E1000_DEBUG
enum {
DEBUG_GENERAL, DEBUG_IO, DEBUG_MMIO, DEBUG_INTERRUPT,
DEBUG_RX, DEBUG_TX, DEBUG_MDIC, DEBUG_EEPROM,
DEBUG_UNKNOWN, DEBUG_TXSUM, DEBUG_TXERR, DEBUG_RXERR,
DEBUG_RXFILTER, DEBUG_NOTYET,
};
#define DBGBIT(x) (1<<DEBUG_##x)
static int debugflags = DBGBIT(TXERR) | DBGBIT(GENERAL);
#define DBGOUT(what, fmt, ...) do { \
if (debugflags & DBGBIT(what)) \
fprintf(stderr, "e1000: " fmt, ## __VA_ARGS__); \
} while (0)
#else
#define DBGOUT(what, fmt, ...) do {} while (0)
#endif
#define IOPORT_SIZE 0x40
#define PNPMMIO_SIZE 0x20000
#define MIN_BUF_SIZE 60 /* Min. octets in an ethernet frame sans FCS */
/*
* HW models:
* E1000_DEV_ID_82540EM works with Windows and Linux
* E1000_DEV_ID_82573L OK with windoze and Linux 2.6.22,
* appears to perform better than 82540EM, but breaks with Linux 2.6.18
* E1000_DEV_ID_82544GC_COPPER appears to work; not well tested
* Others never tested
*/
enum { E1000_DEVID = E1000_DEV_ID_82540EM };
/*
* May need to specify additional MAC-to-PHY entries --
* Intel's Windows driver refuses to initialize unless they match
*/
enum {
PHY_ID2_INIT = E1000_DEVID == E1000_DEV_ID_82573L ? 0xcc2 :
E1000_DEVID == E1000_DEV_ID_82544GC_COPPER ? 0xc30 :
/* default to E1000_DEV_ID_82540EM */ 0xc20
};
typedef struct E1000State_st {
PCIDevice dev;
NICState *nic;
NICConf conf;
MemoryRegion mmio;
MemoryRegion io;
uint32_t mac_reg[0x8000];
uint16_t phy_reg[0x20];
uint16_t eeprom_data[64];
uint32_t rxbuf_size;
uint32_t rxbuf_min_shift;
int check_rxov;
struct e1000_tx {
unsigned char header[256];
unsigned char vlan_header[4];
/* Fields vlan and data must not be reordered or separated. */
unsigned char vlan[4];
unsigned char data[0x10000];
uint16_t size;
unsigned char sum_needed;
unsigned char vlan_needed;
uint8_t ipcss;
uint8_t ipcso;
uint16_t ipcse;
uint8_t tucss;
uint8_t tucso;
uint16_t tucse;
uint8_t hdr_len;
uint16_t mss;
uint32_t paylen;
uint16_t tso_frames;
char tse;
int8_t ip;
int8_t tcp;
char cptse; // current packet tse bit
} tx;
struct {
uint32_t val_in; // shifted in from guest driver
uint16_t bitnum_in;
uint16_t bitnum_out;
uint16_t reading;
uint32_t old_eecd;
} eecd_state;
} E1000State;
#define defreg(x) x = (E1000_##x>>2)
enum {
defreg(CTRL), defreg(EECD), defreg(EERD), defreg(GPRC),
defreg(GPTC), defreg(ICR), defreg(ICS), defreg(IMC),
defreg(IMS), defreg(LEDCTL), defreg(MANC), defreg(MDIC),
defreg(MPC), defreg(PBA), defreg(RCTL), defreg(RDBAH),
defreg(RDBAL), defreg(RDH), defreg(RDLEN), defreg(RDT),
defreg(STATUS), defreg(SWSM), defreg(TCTL), defreg(TDBAH),
defreg(TDBAL), defreg(TDH), defreg(TDLEN), defreg(TDT),
defreg(TORH), defreg(TORL), defreg(TOTH), defreg(TOTL),
defreg(TPR), defreg(TPT), defreg(TXDCTL), defreg(WUFC),
defreg(RA), defreg(MTA), defreg(CRCERRS),defreg(VFTA),
defreg(VET),
};
enum { PHY_R = 1, PHY_W = 2, PHY_RW = PHY_R | PHY_W };
static const char phy_regcap[0x20] = {
[PHY_STATUS] = PHY_R, [M88E1000_EXT_PHY_SPEC_CTRL] = PHY_RW,
[PHY_ID1] = PHY_R, [M88E1000_PHY_SPEC_CTRL] = PHY_RW,
[PHY_CTRL] = PHY_RW, [PHY_1000T_CTRL] = PHY_RW,
[PHY_LP_ABILITY] = PHY_R, [PHY_1000T_STATUS] = PHY_R,
[PHY_AUTONEG_ADV] = PHY_RW, [M88E1000_RX_ERR_CNTR] = PHY_R,
[PHY_ID2] = PHY_R, [M88E1000_PHY_SPEC_STATUS] = PHY_R
};
static void
set_interrupt_cause(E1000State *s, int index, uint32_t val)
{
if (val)
val |= E1000_ICR_INT_ASSERTED;
s->mac_reg[ICR] = val;
s->mac_reg[ICS] = val;
qemu_set_irq(s->dev.irq[0], (s->mac_reg[IMS] & s->mac_reg[ICR]) != 0);
}
static void
set_ics(E1000State *s, int index, uint32_t val)
{
DBGOUT(INTERRUPT, "set_ics %x, ICR %x, IMR %x\n", val, s->mac_reg[ICR],
s->mac_reg[IMS]);
set_interrupt_cause(s, 0, val | s->mac_reg[ICR]);
}
static int
rxbufsize(uint32_t v)
{
v &= E1000_RCTL_BSEX | E1000_RCTL_SZ_16384 | E1000_RCTL_SZ_8192 |
E1000_RCTL_SZ_4096 | E1000_RCTL_SZ_2048 | E1000_RCTL_SZ_1024 |
E1000_RCTL_SZ_512 | E1000_RCTL_SZ_256;
switch (v) {
case E1000_RCTL_BSEX | E1000_RCTL_SZ_16384:
return 16384;
case E1000_RCTL_BSEX | E1000_RCTL_SZ_8192:
return 8192;
case E1000_RCTL_BSEX | E1000_RCTL_SZ_4096:
return 4096;
case E1000_RCTL_SZ_1024:
return 1024;
case E1000_RCTL_SZ_512:
return 512;
case E1000_RCTL_SZ_256:
return 256;
}
return 2048;
}
static void
set_ctrl(E1000State *s, int index, uint32_t val)
{
/* RST is self clearing */
s->mac_reg[CTRL] = val & ~E1000_CTRL_RST;
}
static void
set_rx_control(E1000State *s, int index, uint32_t val)
{
s->mac_reg[RCTL] = val;
s->rxbuf_size = rxbufsize(val);
s->rxbuf_min_shift = ((val / E1000_RCTL_RDMTS_QUAT) & 3) + 1;
DBGOUT(RX, "RCTL: %d, mac_reg[RCTL] = 0x%x\n", s->mac_reg[RDT],
s->mac_reg[RCTL]);
}
static void
set_mdic(E1000State *s, int index, uint32_t val)
{
uint32_t data = val & E1000_MDIC_DATA_MASK;
uint32_t addr = ((val & E1000_MDIC_REG_MASK) >> E1000_MDIC_REG_SHIFT);
if ((val & E1000_MDIC_PHY_MASK) >> E1000_MDIC_PHY_SHIFT != 1) // phy #
val = s->mac_reg[MDIC] | E1000_MDIC_ERROR;
else if (val & E1000_MDIC_OP_READ) {
DBGOUT(MDIC, "MDIC read reg 0x%x\n", addr);
if (!(phy_regcap[addr] & PHY_R)) {
DBGOUT(MDIC, "MDIC read reg %x unhandled\n", addr);
val |= E1000_MDIC_ERROR;
} else
val = (val ^ data) | s->phy_reg[addr];
} else if (val & E1000_MDIC_OP_WRITE) {
DBGOUT(MDIC, "MDIC write reg 0x%x, value 0x%x\n", addr, data);
if (!(phy_regcap[addr] & PHY_W)) {
DBGOUT(MDIC, "MDIC write reg %x unhandled\n", addr);
val |= E1000_MDIC_ERROR;
} else
s->phy_reg[addr] = data;
}
s->mac_reg[MDIC] = val | E1000_MDIC_READY;
set_ics(s, 0, E1000_ICR_MDAC);
}
static uint32_t
get_eecd(E1000State *s, int index)
{
uint32_t ret = E1000_EECD_PRES|E1000_EECD_GNT | s->eecd_state.old_eecd;
DBGOUT(EEPROM, "reading eeprom bit %d (reading %d)\n",
s->eecd_state.bitnum_out, s->eecd_state.reading);
if (!s->eecd_state.reading ||
((s->eeprom_data[(s->eecd_state.bitnum_out >> 4) & 0x3f] >>
((s->eecd_state.bitnum_out & 0xf) ^ 0xf))) & 1)
ret |= E1000_EECD_DO;
return ret;
}
static void
set_eecd(E1000State *s, int index, uint32_t val)
{
uint32_t oldval = s->eecd_state.old_eecd;
s->eecd_state.old_eecd = val & (E1000_EECD_SK | E1000_EECD_CS |
E1000_EECD_DI|E1000_EECD_FWE_MASK|E1000_EECD_REQ);
e1000: Fix wrong microwire EEPROM state initialization This change fixes initialization of e1000's microwire EEPROM internal state values so that qemu's e1000 emulation works on NetBSD, which doesn't use Intel's em driver but has its own wm driver for the Intel i8254x Gigabit Ethernet. Previously set_eecd() function in e1000.c clears EEPROM internal state values on SK rising edge during CS==L, but according to FM93C06 EEPROM (which is MicroWire compatible) data sheet, EEPROM internal status should be cleared on CS rise edge regardless of SK input: "... a rising edge on this (CS) signal is required to reset the internal state-machine to accept a new cycle .." and nothing should be changed during CS (chip select) is inactive. Intel's em driver seems to explicitly raise SK output after CS is negated in em_standby_eeprom() so many other OSes that use Intel's driver don't have this problem even on the previous e1000.c implementation, but I can't find any articles that say the MICROWIRE or EEPROM spec requires such sequence, and actually hardware works fine without it (i.e. real i82540EM has been working on NetBSD). This fix also changes initialization to clear each state value in struct eecd_state individually rather than using memset() against the whole structre. The old_eecd member stores the last SK and CS signal levels and it should be preserved even after reset of internal EEPROM state to detect next signal edges for proper EEPROM emulation. Signed-off-by: Izumi Tsutsui <tsutsui@ceres.dti.ne.jp> Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
2010-07-10 22:03:45 +08:00
if (!(E1000_EECD_CS & val)) // CS inactive; nothing to do
return;
if (E1000_EECD_CS & (val ^ oldval)) { // CS rise edge; reset state
s->eecd_state.val_in = 0;
s->eecd_state.bitnum_in = 0;
s->eecd_state.bitnum_out = 0;
s->eecd_state.reading = 0;
}
if (!(E1000_EECD_SK & (val ^ oldval))) // no clock edge
return;
if (!(E1000_EECD_SK & val)) { // falling edge
s->eecd_state.bitnum_out++;
return;
}
s->eecd_state.val_in <<= 1;
if (val & E1000_EECD_DI)
s->eecd_state.val_in |= 1;
if (++s->eecd_state.bitnum_in == 9 && !s->eecd_state.reading) {
s->eecd_state.bitnum_out = ((s->eecd_state.val_in & 0x3f)<<4)-1;
s->eecd_state.reading = (((s->eecd_state.val_in >> 6) & 7) ==
EEPROM_READ_OPCODE_MICROWIRE);
}
DBGOUT(EEPROM, "eeprom bitnum in %d out %d, reading %d\n",
s->eecd_state.bitnum_in, s->eecd_state.bitnum_out,
s->eecd_state.reading);
}
static uint32_t
flash_eerd_read(E1000State *s, int x)
{
unsigned int index, r = s->mac_reg[EERD] & ~E1000_EEPROM_RW_REG_START;
if ((s->mac_reg[EERD] & E1000_EEPROM_RW_REG_START) == 0)
return (s->mac_reg[EERD]);
if ((index = r >> E1000_EEPROM_RW_ADDR_SHIFT) > EEPROM_CHECKSUM_REG)
return (E1000_EEPROM_RW_REG_DONE | r);
return ((s->eeprom_data[index] << E1000_EEPROM_RW_REG_DATA) |
E1000_EEPROM_RW_REG_DONE | r);
}
static void
putsum(uint8_t *data, uint32_t n, uint32_t sloc, uint32_t css, uint32_t cse)
{
uint32_t sum;
if (cse && cse < n)
n = cse + 1;
if (sloc < n-1) {
sum = net_checksum_add(n-css, data+css);
cpu_to_be16wu((uint16_t *)(data + sloc),
net_checksum_finish(sum));
}
}
static inline int
vlan_enabled(E1000State *s)
{
return ((s->mac_reg[CTRL] & E1000_CTRL_VME) != 0);
}
static inline int
vlan_rx_filter_enabled(E1000State *s)
{
return ((s->mac_reg[RCTL] & E1000_RCTL_VFE) != 0);
}
static inline int
is_vlan_packet(E1000State *s, const uint8_t *buf)
{
return (be16_to_cpup((uint16_t *)(buf + 12)) ==
le16_to_cpup((uint16_t *)(s->mac_reg + VET)));
}
static inline int
is_vlan_txd(uint32_t txd_lower)
{
return ((txd_lower & E1000_TXD_CMD_VLE) != 0);
}
/* FCS aka Ethernet CRC-32. We don't get it from backends and can't
* fill it in, just pad descriptor length by 4 bytes unless guest
* told us to strip it off the packet. */
static inline int
fcs_len(E1000State *s)
{
return (s->mac_reg[RCTL] & E1000_RCTL_SECRC) ? 0 : 4;
}
static void
xmit_seg(E1000State *s)
{
uint16_t len, *sp;
unsigned int frames = s->tx.tso_frames, css, sofar, n;
struct e1000_tx *tp = &s->tx;
if (tp->tse && tp->cptse) {
css = tp->ipcss;
DBGOUT(TXSUM, "frames %d size %d ipcss %d\n",
frames, tp->size, css);
if (tp->ip) { // IPv4
cpu_to_be16wu((uint16_t *)(tp->data+css+2),
tp->size - css);
cpu_to_be16wu((uint16_t *)(tp->data+css+4),
be16_to_cpup((uint16_t *)(tp->data+css+4))+frames);
} else // IPv6
cpu_to_be16wu((uint16_t *)(tp->data+css+4),
tp->size - css);
css = tp->tucss;
len = tp->size - css;
DBGOUT(TXSUM, "tcp %d tucss %d len %d\n", tp->tcp, css, len);
if (tp->tcp) {
sofar = frames * tp->mss;
cpu_to_be32wu((uint32_t *)(tp->data+css+4), // seq
be32_to_cpupu((uint32_t *)(tp->data+css+4))+sofar);
if (tp->paylen - sofar > tp->mss)
tp->data[css + 13] &= ~9; // PSH, FIN
} else // UDP
cpu_to_be16wu((uint16_t *)(tp->data+css+4), len);
if (tp->sum_needed & E1000_TXD_POPTS_TXSM) {
unsigned int phsum;
// add pseudo-header length before checksum calculation
sp = (uint16_t *)(tp->data + tp->tucso);
phsum = be16_to_cpup(sp) + len;
phsum = (phsum >> 16) + (phsum & 0xffff);
cpu_to_be16wu(sp, phsum);
}
tp->tso_frames++;
}
if (tp->sum_needed & E1000_TXD_POPTS_TXSM)
putsum(tp->data, tp->size, tp->tucso, tp->tucss, tp->tucse);
if (tp->sum_needed & E1000_TXD_POPTS_IXSM)
putsum(tp->data, tp->size, tp->ipcso, tp->ipcss, tp->ipcse);
if (tp->vlan_needed) {
memmove(tp->vlan, tp->data, 4);
memmove(tp->data, tp->data + 4, 8);
memcpy(tp->data + 8, tp->vlan_header, 4);
qemu_send_packet(&s->nic->nc, tp->vlan, tp->size + 4);
} else
qemu_send_packet(&s->nic->nc, tp->data, tp->size);
s->mac_reg[TPT]++;
s->mac_reg[GPTC]++;
n = s->mac_reg[TOTL];
if ((s->mac_reg[TOTL] += s->tx.size) < n)
s->mac_reg[TOTH]++;
}
static void
process_tx_desc(E1000State *s, struct e1000_tx_desc *dp)
{
uint32_t txd_lower = le32_to_cpu(dp->lower.data);
uint32_t dtype = txd_lower & (E1000_TXD_CMD_DEXT | E1000_TXD_DTYP_D);
unsigned int split_size = txd_lower & 0xffff, bytes, sz, op;
unsigned int msh = 0xfffff, hdr = 0;
uint64_t addr;
struct e1000_context_desc *xp = (struct e1000_context_desc *)dp;
struct e1000_tx *tp = &s->tx;
if (dtype == E1000_TXD_CMD_DEXT) { // context descriptor
op = le32_to_cpu(xp->cmd_and_length);
tp->ipcss = xp->lower_setup.ip_fields.ipcss;
tp->ipcso = xp->lower_setup.ip_fields.ipcso;
tp->ipcse = le16_to_cpu(xp->lower_setup.ip_fields.ipcse);
tp->tucss = xp->upper_setup.tcp_fields.tucss;
tp->tucso = xp->upper_setup.tcp_fields.tucso;
tp->tucse = le16_to_cpu(xp->upper_setup.tcp_fields.tucse);
tp->paylen = op & 0xfffff;
tp->hdr_len = xp->tcp_seg_setup.fields.hdr_len;
tp->mss = le16_to_cpu(xp->tcp_seg_setup.fields.mss);
tp->ip = (op & E1000_TXD_CMD_IP) ? 1 : 0;
tp->tcp = (op & E1000_TXD_CMD_TCP) ? 1 : 0;
tp->tse = (op & E1000_TXD_CMD_TSE) ? 1 : 0;
tp->tso_frames = 0;
if (tp->tucso == 0) { // this is probably wrong
DBGOUT(TXSUM, "TCP/UDP: cso 0!\n");
tp->tucso = tp->tucss + (tp->tcp ? 16 : 6);
}
return;
} else if (dtype == (E1000_TXD_CMD_DEXT | E1000_TXD_DTYP_D)) {
// data descriptor
if (tp->size == 0) {
tp->sum_needed = le32_to_cpu(dp->upper.data) >> 8;
}
tp->cptse = ( txd_lower & E1000_TXD_CMD_TSE ) ? 1 : 0;
} else {
// legacy descriptor
tp->cptse = 0;
}
if (vlan_enabled(s) && is_vlan_txd(txd_lower) &&
(tp->cptse || txd_lower & E1000_TXD_CMD_EOP)) {
tp->vlan_needed = 1;
cpu_to_be16wu((uint16_t *)(tp->vlan_header),
le16_to_cpup((uint16_t *)(s->mac_reg + VET)));
cpu_to_be16wu((uint16_t *)(tp->vlan_header + 2),
le16_to_cpu(dp->upper.fields.special));
}
addr = le64_to_cpu(dp->buffer_addr);
if (tp->tse && tp->cptse) {
hdr = tp->hdr_len;
msh = hdr + tp->mss;
do {
bytes = split_size;
if (tp->size + bytes > msh)
bytes = msh - tp->size;
bytes = MIN(sizeof(tp->data) - tp->size, bytes);
pci_dma_read(&s->dev, addr, tp->data + tp->size, bytes);
if ((sz = tp->size + bytes) >= hdr && tp->size < hdr)
memmove(tp->header, tp->data, hdr);
tp->size = sz;
addr += bytes;
if (sz == msh) {
xmit_seg(s);
memmove(tp->data, tp->header, hdr);
tp->size = hdr;
}
} while (split_size -= bytes);
} else if (!tp->tse && tp->cptse) {
// context descriptor TSE is not set, while data descriptor TSE is set
DBGOUT(TXERR, "TCP segmentaion Error\n");
} else {
split_size = MIN(sizeof(tp->data) - tp->size, split_size);
pci_dma_read(&s->dev, addr, tp->data + tp->size, split_size);
tp->size += split_size;
}
if (!(txd_lower & E1000_TXD_CMD_EOP))
return;
if (!(tp->tse && tp->cptse && tp->size < hdr))
xmit_seg(s);
tp->tso_frames = 0;
tp->sum_needed = 0;
tp->vlan_needed = 0;
tp->size = 0;
tp->cptse = 0;
}
static uint32_t
txdesc_writeback(E1000State *s, dma_addr_t base, struct e1000_tx_desc *dp)
{
uint32_t txd_upper, txd_lower = le32_to_cpu(dp->lower.data);
if (!(txd_lower & (E1000_TXD_CMD_RS|E1000_TXD_CMD_RPS)))
return 0;
txd_upper = (le32_to_cpu(dp->upper.data) | E1000_TXD_STAT_DD) &
~(E1000_TXD_STAT_EC | E1000_TXD_STAT_LC | E1000_TXD_STAT_TU);
dp->upper.data = cpu_to_le32(txd_upper);
pci_dma_write(&s->dev, base + ((char *)&dp->upper - (char *)dp),
&dp->upper, sizeof(dp->upper));
return E1000_ICR_TXDW;
}
static uint64_t tx_desc_base(E1000State *s)
{
uint64_t bah = s->mac_reg[TDBAH];
uint64_t bal = s->mac_reg[TDBAL] & ~0xf;
return (bah << 32) + bal;
}
static void
start_xmit(E1000State *s)
{
dma_addr_t base;
struct e1000_tx_desc desc;
uint32_t tdh_start = s->mac_reg[TDH], cause = E1000_ICS_TXQE;
if (!(s->mac_reg[TCTL] & E1000_TCTL_EN)) {
DBGOUT(TX, "tx disabled\n");
return;
}
while (s->mac_reg[TDH] != s->mac_reg[TDT]) {
base = tx_desc_base(s) +
sizeof(struct e1000_tx_desc) * s->mac_reg[TDH];
pci_dma_read(&s->dev, base, &desc, sizeof(desc));
DBGOUT(TX, "index %d: %p : %x %x\n", s->mac_reg[TDH],
(void *)(intptr_t)desc.buffer_addr, desc.lower.data,
desc.upper.data);
process_tx_desc(s, &desc);
cause |= txdesc_writeback(s, base, &desc);
if (++s->mac_reg[TDH] * sizeof(desc) >= s->mac_reg[TDLEN])
s->mac_reg[TDH] = 0;
/*
* the following could happen only if guest sw assigns
* bogus values to TDT/TDLEN.
* there's nothing too intelligent we could do about this.
*/
if (s->mac_reg[TDH] == tdh_start) {
DBGOUT(TXERR, "TDH wraparound @%x, TDT %x, TDLEN %x\n",
tdh_start, s->mac_reg[TDT], s->mac_reg[TDLEN]);
break;
}
}
set_ics(s, 0, cause);
}
static int
receive_filter(E1000State *s, const uint8_t *buf, int size)
{
static const uint8_t bcast[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
static const int mta_shift[] = {4, 3, 2, 0};
uint32_t f, rctl = s->mac_reg[RCTL], ra[2], *rp;
if (is_vlan_packet(s, buf) && vlan_rx_filter_enabled(s)) {
uint16_t vid = be16_to_cpup((uint16_t *)(buf + 14));
uint32_t vfta = le32_to_cpup((uint32_t *)(s->mac_reg + VFTA) +
((vid >> 5) & 0x7f));
if ((vfta & (1 << (vid & 0x1f))) == 0)
return 0;
}
if (rctl & E1000_RCTL_UPE) // promiscuous
return 1;
if ((buf[0] & 1) && (rctl & E1000_RCTL_MPE)) // promiscuous mcast
return 1;
if ((rctl & E1000_RCTL_BAM) && !memcmp(buf, bcast, sizeof bcast))
return 1;
for (rp = s->mac_reg + RA; rp < s->mac_reg + RA + 32; rp += 2) {
if (!(rp[1] & E1000_RAH_AV))
continue;
ra[0] = cpu_to_le32(rp[0]);
ra[1] = cpu_to_le32(rp[1]);
if (!memcmp(buf, (uint8_t *)ra, 6)) {
DBGOUT(RXFILTER,
"unicast match[%d]: %02x:%02x:%02x:%02x:%02x:%02x\n",
(int)(rp - s->mac_reg - RA)/2,
buf[0], buf[1], buf[2], buf[3], buf[4], buf[5]);
return 1;
}
}
DBGOUT(RXFILTER, "unicast mismatch: %02x:%02x:%02x:%02x:%02x:%02x\n",
buf[0], buf[1], buf[2], buf[3], buf[4], buf[5]);
f = mta_shift[(rctl >> E1000_RCTL_MO_SHIFT) & 3];
f = (((buf[5] << 8) | buf[4]) >> f) & 0xfff;
if (s->mac_reg[MTA + (f >> 5)] & (1 << (f & 0x1f)))
return 1;
DBGOUT(RXFILTER,
"dropping, inexact filter mismatch: %02x:%02x:%02x:%02x:%02x:%02x MO %d MTA[%d] %x\n",
buf[0], buf[1], buf[2], buf[3], buf[4], buf[5],
(rctl >> E1000_RCTL_MO_SHIFT) & 3, f >> 5,
s->mac_reg[MTA + (f >> 5)]);
return 0;
}
static void
e1000_set_link_status(VLANClientState *nc)
{
E1000State *s = DO_UPCAST(NICState, nc, nc)->opaque;
uint32_t old_status = s->mac_reg[STATUS];
e1000: use MII status register for link up/down Some guests will use the standard MII status register to verify link state. They will not notice link changes unless this register is updated. Verified with Linux 3.0 and Windows XP guests. Without this patch, ethtool will report speed and duplex as unknown when the link is down, but still report the link as up. This is because the Linux e1000 driver checks the mac_reg[STATUS] register link state before it checks speed and duplex, but uses the phy_reg[PHY_STATUS] register for the actual link state check. Fix by updating both registers on link state changes. Linux guest before: (qemu) set_link e1000.0 off kvm-sid:~# ethtool eth0 Settings for eth0: Supported ports: [ TP ] Supported link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Full Supports auto-negotiation: Yes Advertised link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Full Advertised pause frame use: No Advertised auto-negotiation: Yes Speed: Unknown! Duplex: Unknown! (255) Port: Twisted Pair PHYAD: 0 Transceiver: internal Auto-negotiation: on MDI-X: Unknown Supports Wake-on: umbg Wake-on: d Current message level: 0x00000007 (7) drv probe link Link detected: yes (qemu) set_link e1000.0 on Linux guest after: (qemu) set_link e1000.0 off [ 63.384221] e1000: eth0 NIC Link is Down kvm-sid:~# ethtool eth0 Settings for eth0: Supported ports: [ TP ] Supported link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Full Supports auto-negotiation: Yes Advertised link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Full Advertised pause frame use: No Advertised auto-negotiation: Yes Speed: Unknown! Duplex: Unknown! (255) Port: Twisted Pair PHYAD: 0 Transceiver: internal Auto-negotiation: on MDI-X: Unknown Supports Wake-on: umbg Wake-on: d Current message level: 0x00000007 (7) drv probe link Link detected: no (qemu) set_link e1000.0 on [ 84.304582] e1000: eth0 NIC Link is Up 1000 Mbps Full Duplex, Flow Control: RX Signed-off-by: Bjørn Mork <bjorn@mork.no> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2011-08-17 17:03:14 +08:00
if (nc->link_down) {
s->mac_reg[STATUS] &= ~E1000_STATUS_LU;
e1000: use MII status register for link up/down Some guests will use the standard MII status register to verify link state. They will not notice link changes unless this register is updated. Verified with Linux 3.0 and Windows XP guests. Without this patch, ethtool will report speed and duplex as unknown when the link is down, but still report the link as up. This is because the Linux e1000 driver checks the mac_reg[STATUS] register link state before it checks speed and duplex, but uses the phy_reg[PHY_STATUS] register for the actual link state check. Fix by updating both registers on link state changes. Linux guest before: (qemu) set_link e1000.0 off kvm-sid:~# ethtool eth0 Settings for eth0: Supported ports: [ TP ] Supported link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Full Supports auto-negotiation: Yes Advertised link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Full Advertised pause frame use: No Advertised auto-negotiation: Yes Speed: Unknown! Duplex: Unknown! (255) Port: Twisted Pair PHYAD: 0 Transceiver: internal Auto-negotiation: on MDI-X: Unknown Supports Wake-on: umbg Wake-on: d Current message level: 0x00000007 (7) drv probe link Link detected: yes (qemu) set_link e1000.0 on Linux guest after: (qemu) set_link e1000.0 off [ 63.384221] e1000: eth0 NIC Link is Down kvm-sid:~# ethtool eth0 Settings for eth0: Supported ports: [ TP ] Supported link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Full Supports auto-negotiation: Yes Advertised link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Full Advertised pause frame use: No Advertised auto-negotiation: Yes Speed: Unknown! Duplex: Unknown! (255) Port: Twisted Pair PHYAD: 0 Transceiver: internal Auto-negotiation: on MDI-X: Unknown Supports Wake-on: umbg Wake-on: d Current message level: 0x00000007 (7) drv probe link Link detected: no (qemu) set_link e1000.0 on [ 84.304582] e1000: eth0 NIC Link is Up 1000 Mbps Full Duplex, Flow Control: RX Signed-off-by: Bjørn Mork <bjorn@mork.no> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2011-08-17 17:03:14 +08:00
s->phy_reg[PHY_STATUS] &= ~MII_SR_LINK_STATUS;
} else {
s->mac_reg[STATUS] |= E1000_STATUS_LU;
e1000: use MII status register for link up/down Some guests will use the standard MII status register to verify link state. They will not notice link changes unless this register is updated. Verified with Linux 3.0 and Windows XP guests. Without this patch, ethtool will report speed and duplex as unknown when the link is down, but still report the link as up. This is because the Linux e1000 driver checks the mac_reg[STATUS] register link state before it checks speed and duplex, but uses the phy_reg[PHY_STATUS] register for the actual link state check. Fix by updating both registers on link state changes. Linux guest before: (qemu) set_link e1000.0 off kvm-sid:~# ethtool eth0 Settings for eth0: Supported ports: [ TP ] Supported link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Full Supports auto-negotiation: Yes Advertised link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Full Advertised pause frame use: No Advertised auto-negotiation: Yes Speed: Unknown! Duplex: Unknown! (255) Port: Twisted Pair PHYAD: 0 Transceiver: internal Auto-negotiation: on MDI-X: Unknown Supports Wake-on: umbg Wake-on: d Current message level: 0x00000007 (7) drv probe link Link detected: yes (qemu) set_link e1000.0 on Linux guest after: (qemu) set_link e1000.0 off [ 63.384221] e1000: eth0 NIC Link is Down kvm-sid:~# ethtool eth0 Settings for eth0: Supported ports: [ TP ] Supported link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Full Supports auto-negotiation: Yes Advertised link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Full Advertised pause frame use: No Advertised auto-negotiation: Yes Speed: Unknown! Duplex: Unknown! (255) Port: Twisted Pair PHYAD: 0 Transceiver: internal Auto-negotiation: on MDI-X: Unknown Supports Wake-on: umbg Wake-on: d Current message level: 0x00000007 (7) drv probe link Link detected: no (qemu) set_link e1000.0 on [ 84.304582] e1000: eth0 NIC Link is Up 1000 Mbps Full Duplex, Flow Control: RX Signed-off-by: Bjørn Mork <bjorn@mork.no> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2011-08-17 17:03:14 +08:00
s->phy_reg[PHY_STATUS] |= MII_SR_LINK_STATUS;
}
if (s->mac_reg[STATUS] != old_status)
set_ics(s, 0, E1000_ICR_LSC);
}
static bool e1000_has_rxbufs(E1000State *s, size_t total_size)
{
int bufs;
/* Fast-path short packets */
if (total_size <= s->rxbuf_size) {
return s->mac_reg[RDH] != s->mac_reg[RDT] || !s->check_rxov;
}
if (s->mac_reg[RDH] < s->mac_reg[RDT]) {
bufs = s->mac_reg[RDT] - s->mac_reg[RDH];
} else if (s->mac_reg[RDH] > s->mac_reg[RDT] || !s->check_rxov) {
bufs = s->mac_reg[RDLEN] / sizeof(struct e1000_rx_desc) +
s->mac_reg[RDT] - s->mac_reg[RDH];
} else {
return false;
}
return total_size <= bufs * s->rxbuf_size;
}
static int
e1000_can_receive(VLANClientState *nc)
{
E1000State *s = DO_UPCAST(NICState, nc, nc)->opaque;
return (s->mac_reg[RCTL] & E1000_RCTL_EN) && e1000_has_rxbufs(s, 1);
}
static uint64_t rx_desc_base(E1000State *s)
{
uint64_t bah = s->mac_reg[RDBAH];
uint64_t bal = s->mac_reg[RDBAL] & ~0xf;
return (bah << 32) + bal;
}
static ssize_t
e1000_receive(VLANClientState *nc, const uint8_t *buf, size_t size)
{
E1000State *s = DO_UPCAST(NICState, nc, nc)->opaque;
struct e1000_rx_desc desc;
dma_addr_t base;
unsigned int n, rdt;
uint32_t rdh_start;
uint16_t vlan_special = 0;
uint8_t vlan_status = 0, vlan_offset = 0;
uint8_t min_buf[MIN_BUF_SIZE];
size_t desc_offset;
size_t desc_size;
size_t total_size;
if (!(s->mac_reg[RCTL] & E1000_RCTL_EN))
return -1;
/* Pad to minimum Ethernet frame length */
if (size < sizeof(min_buf)) {
memcpy(min_buf, buf, size);
memset(&min_buf[size], 0, sizeof(min_buf) - size);
buf = min_buf;
size = sizeof(min_buf);
}
if (!receive_filter(s, buf, size))
return size;
if (vlan_enabled(s) && is_vlan_packet(s, buf)) {
vlan_special = cpu_to_le16(be16_to_cpup((uint16_t *)(buf + 14)));
memmove((uint8_t *)buf + 4, buf, 12);
vlan_status = E1000_RXD_STAT_VP;
vlan_offset = 4;
size -= 4;
}
rdh_start = s->mac_reg[RDH];
desc_offset = 0;
total_size = size + fcs_len(s);
if (!e1000_has_rxbufs(s, total_size)) {
set_ics(s, 0, E1000_ICS_RXO);
return -1;
}
do {
desc_size = total_size - desc_offset;
if (desc_size > s->rxbuf_size) {
desc_size = s->rxbuf_size;
}
base = rx_desc_base(s) + sizeof(desc) * s->mac_reg[RDH];
pci_dma_read(&s->dev, base, &desc, sizeof(desc));
desc.special = vlan_special;
desc.status |= (vlan_status | E1000_RXD_STAT_DD);
if (desc.buffer_addr) {
if (desc_offset < size) {
size_t copy_size = size - desc_offset;
if (copy_size > s->rxbuf_size) {
copy_size = s->rxbuf_size;
}
pci_dma_write(&s->dev, le64_to_cpu(desc.buffer_addr),
buf + desc_offset + vlan_offset, copy_size);
}
desc_offset += desc_size;
desc.length = cpu_to_le16(desc_size);
if (desc_offset >= total_size) {
desc.status |= E1000_RXD_STAT_EOP | E1000_RXD_STAT_IXSM;
} else {
/* Guest zeroing out status is not a hardware requirement.
Clear EOP in case guest didn't do it. */
desc.status &= ~E1000_RXD_STAT_EOP;
}
} else { // as per intel docs; skip descriptors with null buf addr
DBGOUT(RX, "Null RX descriptor!!\n");
}
pci_dma_write(&s->dev, base, &desc, sizeof(desc));
if (++s->mac_reg[RDH] * sizeof(desc) >= s->mac_reg[RDLEN])
s->mac_reg[RDH] = 0;
s->check_rxov = 1;
/* see comment in start_xmit; same here */
if (s->mac_reg[RDH] == rdh_start) {
DBGOUT(RXERR, "RDH wraparound @%x, RDT %x, RDLEN %x\n",
rdh_start, s->mac_reg[RDT], s->mac_reg[RDLEN]);
set_ics(s, 0, E1000_ICS_RXO);
return -1;
}
} while (desc_offset < total_size);
s->mac_reg[GPRC]++;
s->mac_reg[TPR]++;
/* TOR - Total Octets Received:
* This register includes bytes received in a packet from the <Destination
* Address> field through the <CRC> field, inclusively.
*/
n = s->mac_reg[TORL] + size + /* Always include FCS length. */ 4;
if (n < s->mac_reg[TORL])
s->mac_reg[TORH]++;
s->mac_reg[TORL] = n;
n = E1000_ICS_RXT0;
if ((rdt = s->mac_reg[RDT]) < s->mac_reg[RDH])
rdt += s->mac_reg[RDLEN] / sizeof(desc);
if (((rdt - s->mac_reg[RDH]) * sizeof(desc)) <= s->mac_reg[RDLEN] >>
s->rxbuf_min_shift)
n |= E1000_ICS_RXDMT0;
set_ics(s, 0, n);
return size;
}
static uint32_t
mac_readreg(E1000State *s, int index)
{
return s->mac_reg[index];
}
static uint32_t
mac_icr_read(E1000State *s, int index)
{
uint32_t ret = s->mac_reg[ICR];
DBGOUT(INTERRUPT, "ICR read: %x\n", ret);
set_interrupt_cause(s, 0, 0);
return ret;
}
static uint32_t
mac_read_clr4(E1000State *s, int index)
{
uint32_t ret = s->mac_reg[index];
s->mac_reg[index] = 0;
return ret;
}
static uint32_t
mac_read_clr8(E1000State *s, int index)
{
uint32_t ret = s->mac_reg[index];
s->mac_reg[index] = 0;
s->mac_reg[index-1] = 0;
return ret;
}
static void
mac_writereg(E1000State *s, int index, uint32_t val)
{
s->mac_reg[index] = val;
}
static void
set_rdt(E1000State *s, int index, uint32_t val)
{
s->check_rxov = 0;
s->mac_reg[index] = val & 0xffff;
}
static void
set_16bit(E1000State *s, int index, uint32_t val)
{
s->mac_reg[index] = val & 0xffff;
}
static void
set_dlen(E1000State *s, int index, uint32_t val)
{
s->mac_reg[index] = val & 0xfff80;
}
static void
set_tctl(E1000State *s, int index, uint32_t val)
{
s->mac_reg[index] = val;
s->mac_reg[TDT] &= 0xffff;
start_xmit(s);
}
static void
set_icr(E1000State *s, int index, uint32_t val)
{
DBGOUT(INTERRUPT, "set_icr %x\n", val);
set_interrupt_cause(s, 0, s->mac_reg[ICR] & ~val);
}
static void
set_imc(E1000State *s, int index, uint32_t val)
{
s->mac_reg[IMS] &= ~val;
set_ics(s, 0, 0);
}
static void
set_ims(E1000State *s, int index, uint32_t val)
{
s->mac_reg[IMS] |= val;
set_ics(s, 0, 0);
}
#define getreg(x) [x] = mac_readreg
static uint32_t (*macreg_readops[])(E1000State *, int) = {
getreg(PBA), getreg(RCTL), getreg(TDH), getreg(TXDCTL),
getreg(WUFC), getreg(TDT), getreg(CTRL), getreg(LEDCTL),
getreg(MANC), getreg(MDIC), getreg(SWSM), getreg(STATUS),
getreg(TORL), getreg(TOTL), getreg(IMS), getreg(TCTL),
getreg(RDH), getreg(RDT), getreg(VET), getreg(ICS),
getreg(TDBAL), getreg(TDBAH), getreg(RDBAH), getreg(RDBAL),
getreg(TDLEN), getreg(RDLEN),
[TOTH] = mac_read_clr8, [TORH] = mac_read_clr8, [GPRC] = mac_read_clr4,
[GPTC] = mac_read_clr4, [TPR] = mac_read_clr4, [TPT] = mac_read_clr4,
[ICR] = mac_icr_read, [EECD] = get_eecd, [EERD] = flash_eerd_read,
[CRCERRS ... MPC] = &mac_readreg,
[RA ... RA+31] = &mac_readreg,
[MTA ... MTA+127] = &mac_readreg,
[VFTA ... VFTA+127] = &mac_readreg,
};
enum { NREADOPS = ARRAY_SIZE(macreg_readops) };
#define putreg(x) [x] = mac_writereg
static void (*macreg_writeops[])(E1000State *, int, uint32_t) = {
putreg(PBA), putreg(EERD), putreg(SWSM), putreg(WUFC),
putreg(TDBAL), putreg(TDBAH), putreg(TXDCTL), putreg(RDBAH),
putreg(RDBAL), putreg(LEDCTL), putreg(VET),
[TDLEN] = set_dlen, [RDLEN] = set_dlen, [TCTL] = set_tctl,
[TDT] = set_tctl, [MDIC] = set_mdic, [ICS] = set_ics,
[TDH] = set_16bit, [RDH] = set_16bit, [RDT] = set_rdt,
[IMC] = set_imc, [IMS] = set_ims, [ICR] = set_icr,
[EECD] = set_eecd, [RCTL] = set_rx_control, [CTRL] = set_ctrl,
[RA ... RA+31] = &mac_writereg,
[MTA ... MTA+127] = &mac_writereg,
[VFTA ... VFTA+127] = &mac_writereg,
};
enum { NWRITEOPS = ARRAY_SIZE(macreg_writeops) };
static void
e1000_mmio_write(void *opaque, target_phys_addr_t addr, uint64_t val,
unsigned size)
{
E1000State *s = opaque;
unsigned int index = (addr & 0x1ffff) >> 2;
if (index < NWRITEOPS && macreg_writeops[index]) {
macreg_writeops[index](s, index, val);
} else if (index < NREADOPS && macreg_readops[index]) {
DBGOUT(MMIO, "e1000_mmio_writel RO %x: 0x%04"PRIx64"\n", index<<2, val);
} else {
DBGOUT(UNKNOWN, "MMIO unknown write addr=0x%08x,val=0x%08"PRIx64"\n",
index<<2, val);
}
}
static uint64_t
e1000_mmio_read(void *opaque, target_phys_addr_t addr, unsigned size)
{
E1000State *s = opaque;
unsigned int index = (addr & 0x1ffff) >> 2;
if (index < NREADOPS && macreg_readops[index])
{
return macreg_readops[index](s, index);
}
DBGOUT(UNKNOWN, "MMIO unknown read addr=0x%08x\n", index<<2);
return 0;
}
static const MemoryRegionOps e1000_mmio_ops = {
.read = e1000_mmio_read,
.write = e1000_mmio_write,
.endianness = DEVICE_LITTLE_ENDIAN,
.impl = {
.min_access_size = 4,
.max_access_size = 4,
},
};
static uint64_t e1000_io_read(void *opaque, target_phys_addr_t addr,
unsigned size)
{
E1000State *s = opaque;
(void)s;
return 0;
}
static void e1000_io_write(void *opaque, target_phys_addr_t addr,
uint64_t val, unsigned size)
{
E1000State *s = opaque;
(void)s;
}
static const MemoryRegionOps e1000_io_ops = {
.read = e1000_io_read,
.write = e1000_io_write,
.endianness = DEVICE_LITTLE_ENDIAN,
};
static bool is_version_1(void *opaque, int version_id)
{
return version_id == 1;
}
static const VMStateDescription vmstate_e1000 = {
.name = "e1000",
.version_id = 2,
.minimum_version_id = 1,
.minimum_version_id_old = 1,
.fields = (VMStateField []) {
VMSTATE_PCI_DEVICE(dev, E1000State),
VMSTATE_UNUSED_TEST(is_version_1, 4), /* was instance id */
VMSTATE_UNUSED(4), /* Was mmio_base. */
VMSTATE_UINT32(rxbuf_size, E1000State),
VMSTATE_UINT32(rxbuf_min_shift, E1000State),
VMSTATE_UINT32(eecd_state.val_in, E1000State),
VMSTATE_UINT16(eecd_state.bitnum_in, E1000State),
VMSTATE_UINT16(eecd_state.bitnum_out, E1000State),
VMSTATE_UINT16(eecd_state.reading, E1000State),
VMSTATE_UINT32(eecd_state.old_eecd, E1000State),
VMSTATE_UINT8(tx.ipcss, E1000State),
VMSTATE_UINT8(tx.ipcso, E1000State),
VMSTATE_UINT16(tx.ipcse, E1000State),
VMSTATE_UINT8(tx.tucss, E1000State),
VMSTATE_UINT8(tx.tucso, E1000State),
VMSTATE_UINT16(tx.tucse, E1000State),
VMSTATE_UINT32(tx.paylen, E1000State),
VMSTATE_UINT8(tx.hdr_len, E1000State),
VMSTATE_UINT16(tx.mss, E1000State),
VMSTATE_UINT16(tx.size, E1000State),
VMSTATE_UINT16(tx.tso_frames, E1000State),
VMSTATE_UINT8(tx.sum_needed, E1000State),
VMSTATE_INT8(tx.ip, E1000State),
VMSTATE_INT8(tx.tcp, E1000State),
VMSTATE_BUFFER(tx.header, E1000State),
VMSTATE_BUFFER(tx.data, E1000State),
VMSTATE_UINT16_ARRAY(eeprom_data, E1000State, 64),
VMSTATE_UINT16_ARRAY(phy_reg, E1000State, 0x20),
VMSTATE_UINT32(mac_reg[CTRL], E1000State),
VMSTATE_UINT32(mac_reg[EECD], E1000State),
VMSTATE_UINT32(mac_reg[EERD], E1000State),
VMSTATE_UINT32(mac_reg[GPRC], E1000State),
VMSTATE_UINT32(mac_reg[GPTC], E1000State),
VMSTATE_UINT32(mac_reg[ICR], E1000State),
VMSTATE_UINT32(mac_reg[ICS], E1000State),
VMSTATE_UINT32(mac_reg[IMC], E1000State),
VMSTATE_UINT32(mac_reg[IMS], E1000State),
VMSTATE_UINT32(mac_reg[LEDCTL], E1000State),
VMSTATE_UINT32(mac_reg[MANC], E1000State),
VMSTATE_UINT32(mac_reg[MDIC], E1000State),
VMSTATE_UINT32(mac_reg[MPC], E1000State),
VMSTATE_UINT32(mac_reg[PBA], E1000State),
VMSTATE_UINT32(mac_reg[RCTL], E1000State),
VMSTATE_UINT32(mac_reg[RDBAH], E1000State),
VMSTATE_UINT32(mac_reg[RDBAL], E1000State),
VMSTATE_UINT32(mac_reg[RDH], E1000State),
VMSTATE_UINT32(mac_reg[RDLEN], E1000State),
VMSTATE_UINT32(mac_reg[RDT], E1000State),
VMSTATE_UINT32(mac_reg[STATUS], E1000State),
VMSTATE_UINT32(mac_reg[SWSM], E1000State),
VMSTATE_UINT32(mac_reg[TCTL], E1000State),
VMSTATE_UINT32(mac_reg[TDBAH], E1000State),
VMSTATE_UINT32(mac_reg[TDBAL], E1000State),
VMSTATE_UINT32(mac_reg[TDH], E1000State),
VMSTATE_UINT32(mac_reg[TDLEN], E1000State),
VMSTATE_UINT32(mac_reg[TDT], E1000State),
VMSTATE_UINT32(mac_reg[TORH], E1000State),
VMSTATE_UINT32(mac_reg[TORL], E1000State),
VMSTATE_UINT32(mac_reg[TOTH], E1000State),
VMSTATE_UINT32(mac_reg[TOTL], E1000State),
VMSTATE_UINT32(mac_reg[TPR], E1000State),
VMSTATE_UINT32(mac_reg[TPT], E1000State),
VMSTATE_UINT32(mac_reg[TXDCTL], E1000State),
VMSTATE_UINT32(mac_reg[WUFC], E1000State),
VMSTATE_UINT32(mac_reg[VET], E1000State),
VMSTATE_UINT32_SUB_ARRAY(mac_reg, E1000State, RA, 32),
VMSTATE_UINT32_SUB_ARRAY(mac_reg, E1000State, MTA, 128),
VMSTATE_UINT32_SUB_ARRAY(mac_reg, E1000State, VFTA, 128),
VMSTATE_END_OF_LIST()
}
};
static const uint16_t e1000_eeprom_template[64] = {
0x0000, 0x0000, 0x0000, 0x0000, 0xffff, 0x0000, 0x0000, 0x0000,
0x3000, 0x1000, 0x6403, E1000_DEVID, 0x8086, E1000_DEVID, 0x8086, 0x3040,
0x0008, 0x2000, 0x7e14, 0x0048, 0x1000, 0x00d8, 0x0000, 0x2700,
0x6cc9, 0x3150, 0x0722, 0x040b, 0x0984, 0x0000, 0xc000, 0x0706,
0x1008, 0x0000, 0x0f04, 0x7fff, 0x4d01, 0xffff, 0xffff, 0xffff,
0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff,
0x0100, 0x4000, 0x121c, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff,
0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0x0000,
};
static const uint16_t phy_reg_init[] = {
[PHY_CTRL] = 0x1140, [PHY_STATUS] = 0x796d, // link initially up
[PHY_ID1] = 0x141, [PHY_ID2] = PHY_ID2_INIT,
[PHY_1000T_CTRL] = 0x0e00, [M88E1000_PHY_SPEC_CTRL] = 0x360,
[M88E1000_EXT_PHY_SPEC_CTRL] = 0x0d60, [PHY_AUTONEG_ADV] = 0xde1,
[PHY_LP_ABILITY] = 0x1e0, [PHY_1000T_STATUS] = 0x3c00,
[M88E1000_PHY_SPEC_STATUS] = 0xac00,
};
static const uint32_t mac_reg_init[] = {
[PBA] = 0x00100030,
[LEDCTL] = 0x602,
[CTRL] = E1000_CTRL_SWDPIN2 | E1000_CTRL_SWDPIN0 |
E1000_CTRL_SPD_1000 | E1000_CTRL_SLU,
[STATUS] = 0x80000000 | E1000_STATUS_GIO_MASTER_ENABLE |
E1000_STATUS_ASDV | E1000_STATUS_MTXCKOK |
E1000_STATUS_SPEED_1000 | E1000_STATUS_FD |
E1000_STATUS_LU,
[MANC] = E1000_MANC_EN_MNG2HOST | E1000_MANC_RCV_TCO_EN |
E1000_MANC_ARP_EN | E1000_MANC_0298_EN |
E1000_MANC_RMCP_EN,
};
/* PCI interface */
static void
e1000_mmio_setup(E1000State *d)
{
int i;
const uint32_t excluded_regs[] = {
E1000_MDIC, E1000_ICR, E1000_ICS, E1000_IMS,
E1000_IMC, E1000_TCTL, E1000_TDT, PNPMMIO_SIZE
};
memory_region_init_io(&d->mmio, &e1000_mmio_ops, d, "e1000-mmio",
PNPMMIO_SIZE);
memory_region_add_coalescing(&d->mmio, 0, excluded_regs[0]);
for (i = 0; excluded_regs[i] != PNPMMIO_SIZE; i++)
memory_region_add_coalescing(&d->mmio, excluded_regs[i] + 4,
excluded_regs[i+1] - excluded_regs[i] - 4);
memory_region_init_io(&d->io, &e1000_io_ops, d, "e1000-io", IOPORT_SIZE);
}
static void
e1000_cleanup(VLANClientState *nc)
{
E1000State *s = DO_UPCAST(NICState, nc, nc)->opaque;
s->nic = NULL;
}
static int
pci_e1000_uninit(PCIDevice *dev)
{
E1000State *d = DO_UPCAST(E1000State, dev, dev);
memory_region_destroy(&d->mmio);
memory_region_destroy(&d->io);
qemu_del_vlan_client(&d->nic->nc);
return 0;
}
static void e1000_reset(void *opaque)
{
E1000State *d = opaque;
memset(d->phy_reg, 0, sizeof d->phy_reg);
memmove(d->phy_reg, phy_reg_init, sizeof phy_reg_init);
memset(d->mac_reg, 0, sizeof d->mac_reg);
memmove(d->mac_reg, mac_reg_init, sizeof mac_reg_init);
d->rxbuf_min_shift = 1;
memset(&d->tx, 0, sizeof d->tx);
if (d->nic->nc.link_down) {
d->mac_reg[STATUS] &= ~E1000_STATUS_LU;
d->phy_reg[PHY_STATUS] &= ~MII_SR_LINK_STATUS;
}
}
static NetClientInfo net_e1000_info = {
.type = NET_CLIENT_TYPE_NIC,
.size = sizeof(NICState),
.can_receive = e1000_can_receive,
.receive = e1000_receive,
.cleanup = e1000_cleanup,
.link_status_changed = e1000_set_link_status,
};
static int pci_e1000_init(PCIDevice *pci_dev)
{
E1000State *d = DO_UPCAST(E1000State, dev, pci_dev);
uint8_t *pci_conf;
uint16_t checksum = 0;
int i;
uint8_t *macaddr;
pci_conf = d->dev.config;
/* TODO: RST# value should be 0, PCI spec 6.2.4 */
pci_conf[PCI_CACHE_LINE_SIZE] = 0x10;
pci_conf[PCI_INTERRUPT_PIN] = 1; /* interrupt pin A */
e1000_mmio_setup(d);
pci_register_bar(&d->dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY, &d->mmio);
pci_register_bar(&d->dev, 1, PCI_BASE_ADDRESS_SPACE_IO, &d->io);
memmove(d->eeprom_data, e1000_eeprom_template,
sizeof e1000_eeprom_template);
qemu_macaddr_default_if_unset(&d->conf.macaddr);
macaddr = d->conf.macaddr.a;
for (i = 0; i < 3; i++)
d->eeprom_data[i] = (macaddr[2*i+1]<<8) | macaddr[2*i];
for (i = 0; i < EEPROM_CHECKSUM_REG; i++)
checksum += d->eeprom_data[i];
checksum = (uint16_t) EEPROM_SUM - checksum;
d->eeprom_data[EEPROM_CHECKSUM_REG] = checksum;
d->nic = qemu_new_nic(&net_e1000_info, &d->conf,
object_get_typename(OBJECT(d)), d->dev.qdev.id, d);
qemu_format_nic_info_str(&d->nic->nc, macaddr);
add_boot_device_path(d->conf.bootindex, &pci_dev->qdev, "/ethernet-phy@0");
return 0;
}
static void qdev_e1000_reset(DeviceState *dev)
{
E1000State *d = DO_UPCAST(E1000State, dev.qdev, dev);
e1000_reset(d);
}
static Property e1000_properties[] = {
DEFINE_NIC_PROPERTIES(E1000State, conf),
DEFINE_PROP_END_OF_LIST(),
};
static void e1000_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
k->init = pci_e1000_init;
k->exit = pci_e1000_uninit;
k->romfile = "pxe-e1000.rom";
k->vendor_id = PCI_VENDOR_ID_INTEL;
k->device_id = E1000_DEVID;
k->revision = 0x03;
k->class_id = PCI_CLASS_NETWORK_ETHERNET;
dc->desc = "Intel Gigabit Ethernet";
dc->reset = qdev_e1000_reset;
dc->vmsd = &vmstate_e1000;
dc->props = e1000_properties;
}
static TypeInfo e1000_info = {
.name = "e1000",
.parent = TYPE_PCI_DEVICE,
.instance_size = sizeof(E1000State),
.class_init = e1000_class_init,
};
static void e1000_register_devices(void)
{
type_register_static(&e1000_info);
}
device_init(e1000_register_devices)