[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH V8 5/5] Adding VMXNET3 device implementation
|
From: |
Alexander Graf |
|
Subject: |
Re: [Qemu-devel] [PATCH V8 5/5] Adding VMXNET3 device implementation |
|
Date: |
Wed, 27 Mar 2013 15:43:15 +0100 |
On 07.12.2012, at 12:15, Dmitry Fleytman wrote:
> Signed-off-by: Dmitry Fleytman <address@hidden>
> Signed-off-by: Yan Vugenfirer <address@hidden>
> ---
> default-configs/pci.mak | 1 +
> hw/Makefile.objs | 1 +
> hw/pci.h | 1 +
> hw/vmxnet3.c | 2437 +++++++++++++++++++++++++++++++++++++++++++++++
> hw/vmxnet3.h | 762 +++++++++++++++
> 5 files changed, 3202 insertions(+)
> create mode 100644 hw/vmxnet3.c
> create mode 100644 hw/vmxnet3.h
>
> diff --git a/default-configs/pci.mak b/default-configs/pci.mak
> index ae9d1eb..cdc0cdc 100644
> --- a/default-configs/pci.mak
> +++ b/default-configs/pci.mak
> @@ -13,6 +13,7 @@ CONFIG_LSI_SCSI_PCI=y
> CONFIG_MEGASAS_SCSI_PCI=y
> CONFIG_RTL8139_PCI=y
> CONFIG_E1000_PCI=y
> +CONFIG_VMXNET3_PCI=y
> CONFIG_IDE_CORE=y
> CONFIG_IDE_QDEV=y
> CONFIG_IDE_PCI=y
> diff --git a/hw/Makefile.objs b/hw/Makefile.objs
> index d581d8d..1a38481 100644
> --- a/hw/Makefile.objs
> +++ b/hw/Makefile.objs
> @@ -111,6 +111,7 @@ common-obj-$(CONFIG_PCNET_PCI) += pcnet-pci.o
> common-obj-$(CONFIG_PCNET_COMMON) += pcnet.o
> common-obj-$(CONFIG_E1000_PCI) += e1000.o
> common-obj-$(CONFIG_RTL8139_PCI) += rtl8139.o
> +common-obj-$(CONFIG_VMXNET3_PCI) += vmxnet3.o vmxnet_utils.o vmxnet_pkt.o
>
> common-obj-$(CONFIG_SMC91C111) += smc91c111.o
> common-obj-$(CONFIG_LAN9118) += lan9118.o
> diff --git a/hw/pci.h b/hw/pci.h
> index 4da0c2a..ad52b8f 100644
> --- a/hw/pci.h
> +++ b/hw/pci.h
> @@ -60,6 +60,7 @@
> #define PCI_DEVICE_ID_VMWARE_NET 0x0720
> #define PCI_DEVICE_ID_VMWARE_SCSI 0x0730
> #define PCI_DEVICE_ID_VMWARE_IDE 0x1729
> +#define PCI_DEVICE_ID_VMWARE_VMXNET3 0x07B0
>
> /* Intel (0x8086) */
> #define PCI_DEVICE_ID_INTEL_82551IT 0x1209
> diff --git a/hw/vmxnet3.c b/hw/vmxnet3.c
> new file mode 100644
> index 0000000..c81b434
> --- /dev/null
> +++ b/hw/vmxnet3.c
> @@ -0,0 +1,2437 @@
> +/*
> + * QEMU VMWARE VMXNET3 paravirtual NIC
> + *
> + * Copyright (c) 2012 Ravello Systems LTD (http://ravellosystems.com)
> + *
> + * Developed by Daynix Computing LTD (http://www.daynix.com)
> + *
> + * Authors:
> + * Dmitry Fleytman <address@hidden>
> + * Tamir Shomer <address@hidden>
> + * Yan Vugenfirer <address@hidden>
> + *
> + * This work is licensed under the terms of the GNU GPL, version 2 or later.
> + * See the COPYING file in the top-level directory.
> + *
> + */
> +
> +#include "hw.h"
> +#include "pci.h"
> +#include "net.h"
> +#include "virtio-net.h"
> +#include "net/tap.h"
> +#include "net/checksum.h"
> +#include "sysemu.h"
> +#include "iov.h"
> +#include "bswap.h"
> +#include "msix.h"
> +#include "msi.h"
> +
> +#include "vmxnet3.h"
> +#include "vmxnet_debug.h"
> +#include "vmware_utils.h"
> +#include "vmxnet_utils.h"
> +#include "vmxnet_pkt.h"
> +
> +#define PCI_DEVICE_ID_VMWARE_VMXNET3_REVISION 0x1
> +#define VMXNET3_MSIX_BAR_SIZE 0x2000
> +
> +#define VMXNET3_BAR0_IDX (0)
> +#define VMXNET3_BAR1_IDX (1)
> +#define VMXNET3_MSIX_BAR_IDX (2)
> +
> +#define VMXNET3_OFF_MSIX_TABLE (0x000)
> +#define VMXNET3_OFF_MSIX_PBA (0x800)
> +
> +/* Link speed in Mbps should be shifted by 16 */
> +#define VMXNET3_LINK_SPEED (1000 << 16)
> +
> +/* Link status: 1 - up, 0 - down. */
> +#define VMXNET3_LINK_STATUS_UP 0x1
> +
> +/* Least significant bit should be set for revision and version */
> +#define VMXNET3_DEVICE_VERSION 0x1
> +#define VMXNET3_DEVICE_REVISION 0x1
> +
> +/* Macros for rings descriptors access */
> +#define VMXNET3_READ_TX_QUEUE_DESCR8(dpa, field) \
> + (vmw_shmem_ld8(dpa + offsetof(struct Vmxnet3_TxQueueDesc, field)))
> +
> +#define VMXNET3_WRITE_TX_QUEUE_DESCR8(dpa, field, value) \
> + (vmw_shmem_st8(dpa + offsetof(struct Vmxnet3_TxQueueDesc, field, value)))
> +
> +#define VMXNET3_READ_TX_QUEUE_DESCR32(dpa, field) \
> + (vmw_shmem_ld32(dpa + offsetof(struct Vmxnet3_TxQueueDesc, field)))
> +
> +#define VMXNET3_WRITE_TX_QUEUE_DESCR32(dpa, field, value) \
> + (vmw_shmem_st32(dpa + offsetof(struct Vmxnet3_TxQueueDesc, field),
> value))
> +
> +#define VMXNET3_READ_TX_QUEUE_DESCR64(dpa, field) \
> + (vmw_shmem_ld64(dpa + offsetof(struct Vmxnet3_TxQueueDesc, field)))
> +
> +#define VMXNET3_WRITE_TX_QUEUE_DESCR64(dpa, field, value) \
> + (vmw_shmem_st64(dpa + offsetof(struct Vmxnet3_TxQueueDesc, field),
> value))
> +
> +#define VMXNET3_READ_RX_QUEUE_DESCR64(dpa, field) \
> + (vmw_shmem_ld64(dpa + offsetof(struct Vmxnet3_RxQueueDesc, field)))
> +
> +#define VMXNET3_READ_RX_QUEUE_DESCR32(dpa, field) \
> + (vmw_shmem_ld32(dpa + offsetof(struct Vmxnet3_RxQueueDesc, field)))
> +
> +#define VMXNET3_WRITE_RX_QUEUE_DESCR64(dpa, field, value) \
> + (vmw_shmem_st64(dpa + offsetof(struct Vmxnet3_RxQueueDesc, field),
> value))
> +
> +#define VMXNET3_WRITE_RX_QUEUE_DESCR8(dpa, field, value) \
> + (vmw_shmem_st8(dpa + offsetof(struct Vmxnet3_RxQueueDesc, field), value))
> +
> +/* Macros for guest driver shared area access */
> +#define VMXNET3_READ_DRV_SHARED64(shpa, field) \
> + (vmw_shmem_ld64(shpa + offsetof(struct Vmxnet3_DriverShared, field)))
> +
> +#define VMXNET3_READ_DRV_SHARED32(shpa, field) \
> + (vmw_shmem_ld32(shpa + offsetof(struct Vmxnet3_DriverShared, field)))
> +
> +#define VMXNET3_WRITE_DRV_SHARED32(shpa, field, val) \
> + (vmw_shmem_st32(shpa + offsetof(struct Vmxnet3_DriverShared, field),
> val))
> +
> +#define VMXNET3_READ_DRV_SHARED16(shpa, field) \
> + (vmw_shmem_ld16(shpa + offsetof(struct Vmxnet3_DriverShared, field)))
> +
> +#define VMXNET3_READ_DRV_SHARED8(shpa, field) \
> + (vmw_shmem_ld8(shpa + offsetof(struct Vmxnet3_DriverShared, field)))
> +
> +#define VMXNET3_READ_DRV_SHARED(shpa, field, b, l) \
> + (vmw_shmem_read(shpa + offsetof(struct Vmxnet3_DriverShared, field), b,
> l))
> +
> +/* Cyclic ring abstraction */
> +typedef struct {
> + hwaddr pa;
> + size_t size;
> + size_t cell_size;
> + size_t next;
> + uint8_t gen;
> +} Vmxnet3Ring;
> +
> +static inline void vmxnet3_ring_init(Vmxnet3Ring *ring,
> + hwaddr pa,
> + size_t size,
> + size_t cell_size,
> + bool zero_region)
> +{
> + ring->pa = pa;
> + ring->size = size;
> + ring->cell_size = cell_size;
> + ring->gen = VMXNET3_INIT_GEN;
> + ring->next = 0;
> +
> + if (zero_region) {
> + vmw_shmem_set(pa, 0, size * cell_size);
> + }
> +}
> +
> +#define VMXNET3_RING_DUMP(macro, ring_name, ridx, r)
> \
> + macro("%s#%d: base %" PRIx64 " size %lu cell_size %lu gen %d next %lu",
> \
> + (ring_name), (ridx),
> \
> + (r)->pa, (r)->size, (r)->cell_size, (r)->gen, (r)->next)
> +
> +static inline void vmxnet3_ring_inc(Vmxnet3Ring *ring)
> +{
> + if (++ring->next >= ring->size) {
> + ring->next = 0;
> + ring->gen ^= 1;
> + }
> +}
> +
> +static inline void vmxnet3_ring_dec(Vmxnet3Ring *ring)
> +{
> + if (ring->next-- == 0) {
> + ring->next = ring->size - 1;
> + ring->gen ^= 1;
> + }
> +}
> +
> +static inline hwaddr vmxnet3_ring_curr_cell_pa(Vmxnet3Ring *ring)
> +{
> + return ring->pa + ring->next * ring->cell_size;
> +}
> +
> +static inline void vmxnet3_ring_read_curr_cell(Vmxnet3Ring *ring, void *buff)
> +{
> + vmw_shmem_read(vmxnet3_ring_curr_cell_pa(ring), buff, ring->cell_size);
> +}
> +
> +static inline void vmxnet3_ring_write_curr_cell(Vmxnet3Ring *ring, void
> *buff)
> +{
> + vmw_shmem_write(vmxnet3_ring_curr_cell_pa(ring), buff, ring->cell_size);
> +}
> +
> +static inline size_t vmxnet3_ring_curr_cell_idx(Vmxnet3Ring *ring)
> +{
> + return ring->next;
> +}
> +
> +static inline uint8_t vmxnet3_ring_curr_gen(Vmxnet3Ring *ring)
> +{
> + return ring->gen;
> +}
> +
> +/* Debug trace-related functions */
> +static inline void
> +vmxnet3_dump_tx_descr(struct Vmxnet3_TxDesc *descr)
> +{
> + VMW_PKPRN("TX DESCR: "
> + "addr %" PRIx64 ", len: %d, gen: %d, rsvd: %d, "
> + "dtype: %d, ext1: %d, msscof: %d, hlen: %d, om: %d, "
> + "eop: %d, cq: %d, ext2: %d, ti: %d, tci: %d",
> + le64_to_cpu(descr->addr), descr->len, descr->gen, descr->rsvd,
> + descr->dtype, descr->ext1, descr->msscof, descr->hlen,
> descr->om,
> + descr->eop, descr->cq, descr->ext2, descr->ti, descr->tci);
> +}
> +
> +static inline void
> +vmxnet3_dump_virt_hdr(struct virtio_net_hdr *vhdr)
> +{
> + VMW_PKPRN("VHDR: flags 0x%x, gso_type: 0x%x, hdr_len: %d, gso_size: %d, "
> + "csum_start: %d, csum_offset: %d",
> + vhdr->flags, vhdr->gso_type, vhdr->hdr_len, vhdr->gso_size,
> + vhdr->csum_start, vhdr->csum_offset);
> +}
> +
> +static inline void
> +vmxnet3_dump_rx_descr(struct Vmxnet3_RxDesc *descr)
> +{
> + VMW_PKPRN("RX DESCR: addr %" PRIx64 ", len: %d, gen: %d, rsvd: %d, "
> + "dtype: %d, ext1: %d, btype: %d",
> + le64_to_cpu(descr->addr), descr->len, descr->gen,
> + descr->rsvd, descr->dtype, descr->ext1, descr->btype);
> +}
> +
> +/* Device state and helper functions */
> +#define VMXNET3_RX_RINGS_PER_QUEUE (2)
> +
> +typedef struct {
> + Vmxnet3Ring tx_ring;
> + Vmxnet3Ring comp_ring;
> +
> + uint8_t intr_idx;
> + hwaddr tx_stats_pa;
> + struct UPT1_TxStats txq_stats;
> +} Vmxnet3TxqDescr;
> +
> +typedef struct {
> + Vmxnet3Ring rx_ring[VMXNET3_RX_RINGS_PER_QUEUE];
> + Vmxnet3Ring comp_ring;
> + uint8_t intr_idx;
> + hwaddr rx_stats_pa;
> + struct UPT1_RxStats rxq_stats;
> +} Vmxnet3RxqDescr;
> +
> +typedef struct {
> + bool is_masked;
> + bool is_pending;
> + bool is_asserted;
> +} Vmxnet3IntState;
> +
> +typedef struct {
> + PCIDevice dev;
> + NICState *nic;
> + NICConf conf;
> + MemoryRegion bar0;
> + MemoryRegion bar1;
> + MemoryRegion msix_bar;
> +
> + Vmxnet3RxqDescr rxq_descr[VMXNET3_DEVICE_MAX_RX_QUEUES];
> + Vmxnet3TxqDescr txq_descr[VMXNET3_DEVICE_MAX_TX_QUEUES];
> +
> + /* Whether MSI-X support was installed successfully */
> + bool msix_used;
> + /* Whether MSI support was installed successfully */
> + bool msi_used;
> + hwaddr drv_shmem;
> + hwaddr temp_shared_guest_driver_memory;
> +
> + uint8_t txq_num;
> +
> + /* This boolean tells whether RX packet being indicated has to */
> + /* be split into head and body chunks from different RX rings */
> + bool rx_packets_compound;
> +
> + bool rx_vlan_stripping;
> + bool lro_supported;
> +
> + uint8_t rxq_num;
> +
> + /* Network MTU */
> + uint32_t mtu;
> +
> + /* Maximum number of fragments for indicated TX packets */
> + uint32_t max_tx_frags;
> +
> + /* Maximum number of fragments for indicated RX packets */
> + uint16_t max_rx_frags;
> +
> + /* Index for events interrupt */
> + uint8_t event_int_idx;
> +
> + /* Whether automatic interrupts masking enabled */
> + bool auto_int_masking;
> +
> + bool peer_has_vhdr;
> +
> + /* TX packets to QEMU interface */
> + struct VmxnetTxPkt *tx_pkt;
> + uint32_t offload_mode;
> + uint32_t cso_or_gso_size;
> + uint16_t tci;
> + bool needs_vlan;
> +
> + struct VmxnetRxPkt *rx_pkt;
> +
> + bool tx_sop;
> + bool skip_current_tx_pkt;
> +
> + uint32_t device_active;
> + uint32_t last_command;
> +
> + uint32_t link_status_and_speed;
> +
> + Vmxnet3IntState interrupt_states[VMXNET3_MAX_INTRS];
> +
> + uint32_t temp_mac; /* To store the low part first */
> +
> + MACAddr perm_mac;
> + uint32_t vlan_table[VMXNET3_VFT_SIZE];
> + uint32_t rx_mode;
> + MACAddr *mcast_list;
> + uint32_t mcast_list_len;
> + uint32_t mcast_list_buff_size; /* needed for live migration. */
> +} VMXNET3State;
> +
> +/* Interrupt management */
> +
> +/*
> + *This function returns sign whether interrupt line is in asserted state
> + * This depends on the type of interrupt used. For INTX interrupt line will
> + * be asserted until explicit deassertion, for MSI(X) interrupt line will
> + * be deasserted automatically due to notification semantics of the MSI(X)
> + * interrupts
> + */
> +static bool _vmxnet3_assert_interrupt_line(VMXNET3State *s, uint32_t int_idx)
> +{
> + if (s->msix_used && msix_enabled(&s->dev)) {
> + VMW_IRPRN("Sending MSI-X notification for vector %u", int_idx);
> + msix_notify(&s->dev, int_idx);
> + return false;
> + }
> + if (s->msi_used && msi_enabled(&s->dev)) {
> + VMW_IRPRN("Sending MSI notification for vector %u", int_idx);
> + msi_notify(&s->dev, int_idx);
> + return false;
> + }
> +
> + VMW_IRPRN("Asserting line for interrupt %u", int_idx);
> + qemu_set_irq(s->dev.irq[int_idx], 1);
> + return true;
> +}
> +
> +static void _vmxnet3_deassert_interrupt_line(VMXNET3State *s, int lidx)
> +{
> + /*
> + * This function should never be called for MSI(X) interrupts
> + * because deassertion never required for message interrupts
> + */
> + assert(!s->msix_used || !msix_enabled(&s->dev));
> + /*
> + * This function should never be called for MSI(X) interrupts
> + * because deassertion never required for message interrupts
> + */
> + assert(!s->msi_used || !msi_enabled(&s->dev));
> +
> + VMW_IRPRN("Deasserting line for interrupt %u", lidx);
> + qemu_set_irq(s->dev.irq[lidx], 0);
> +}
> +
> +static void vmxnet3_update_interrupt_line_state(VMXNET3State *s, int lidx)
> +{
> + if (!s->interrupt_states[lidx].is_pending &&
> + s->interrupt_states[lidx].is_asserted) {
> + VMW_IRPRN("New interrupt line state for index %d is DOWN", lidx);
> + _vmxnet3_deassert_interrupt_line(s, lidx);
> + s->interrupt_states[lidx].is_asserted = false;
> + return;
> + }
> +
> + if (s->interrupt_states[lidx].is_pending &&
> + !s->interrupt_states[lidx].is_masked &&
> + !s->interrupt_states[lidx].is_asserted) {
> + VMW_IRPRN("New interrupt line state for index %d is UP", lidx);
> + s->interrupt_states[lidx].is_asserted =
> + _vmxnet3_assert_interrupt_line(s, lidx);
> + s->interrupt_states[lidx].is_pending = false;
> + return;
> + }
> +}
> +
> +static void vmxnet3_trigger_interrupt(VMXNET3State *s, int lidx)
> +{
> + s->interrupt_states[lidx].is_pending = true;
> + vmxnet3_update_interrupt_line_state(s, lidx);
> +
> + if (s->msix_used && msix_enabled(&s->dev) && s->auto_int_masking) {
> + goto do_automask;
> + }
> +
> + if (s->msi_used && msi_enabled(&s->dev) && s->auto_int_masking) {
> + goto do_automask;
> + }
> +
> + return;
> +
> +do_automask:
> + s->interrupt_states[lidx].is_masked = true;
> + vmxnet3_update_interrupt_line_state(s, lidx);
> +}
> +
> +static bool vmxnet3_interrupt_asserted(VMXNET3State *s, int lidx)
> +{
> + return s->interrupt_states[lidx].is_asserted;
> +}
> +
> +static void vmxnet3_clear_interrupt(VMXNET3State *s, int int_idx)
> +{
> + s->interrupt_states[int_idx].is_pending = false;
> + if (s->auto_int_masking) {
> + s->interrupt_states[int_idx].is_masked = true;
> + }
> + vmxnet3_update_interrupt_line_state(s, int_idx);
> +}
> +
> +static void
> +vmxnet3_on_interrupt_mask_changed(VMXNET3State *s, int lidx, bool is_masked)
> +{
> + s->interrupt_states[lidx].is_masked = is_masked;
> + vmxnet3_update_interrupt_line_state(s, lidx);
> +}
> +
> +static bool vmxnet3_verify_driver_magic(hwaddr dshmem)
> +{
> + return (VMXNET3_READ_DRV_SHARED32(dshmem, magic) == VMXNET3_REV1_MAGIC);
> +}
> +
> +#define VMXNET3_GET_BYTE(x, byte_num) (((x) >> (byte_num)*8) & 0xFF)
> +#define VMXNET3_MAKE_BYTE(byte_num, val) \
> + (((uint32_t)((val) & 0xFF)) << (byte_num)*8)
> +
> +static void vmxnet3_set_variable_mac(VMXNET3State *s, uint32_t h, uint32_t l)
> +{
> + s->conf.macaddr.a[0] = VMXNET3_GET_BYTE(l, 0);
> + s->conf.macaddr.a[1] = VMXNET3_GET_BYTE(l, 1);
> + s->conf.macaddr.a[2] = VMXNET3_GET_BYTE(l, 2);
> + s->conf.macaddr.a[3] = VMXNET3_GET_BYTE(l, 3);
> + s->conf.macaddr.a[4] = VMXNET3_GET_BYTE(h, 0);
> + s->conf.macaddr.a[5] = VMXNET3_GET_BYTE(h, 1);
> +
> + VMW_CFPRN("Variable MAC: " VMXNET_MF, VMXNET_MA(s->conf.macaddr.a));
> +
> + qemu_format_nic_info_str(&s->nic->nc, s->conf.macaddr.a);
> +}
> +
> +static uint64_t vmxnet3_get_mac_low(MACAddr *addr)
> +{
> + return VMXNET3_MAKE_BYTE(0, addr->a[0]) |
> + VMXNET3_MAKE_BYTE(1, addr->a[1]) |
> + VMXNET3_MAKE_BYTE(2, addr->a[2]) |
> + VMXNET3_MAKE_BYTE(3, addr->a[3]);
> +}
> +
> +static uint64_t vmxnet3_get_mac_high(MACAddr *addr)
> +{
> + return VMXNET3_MAKE_BYTE(0, addr->a[4]) |
> + VMXNET3_MAKE_BYTE(1, addr->a[5]);
> +}
> +
> +static void
> +vmxnet3_inc_tx_consumption_counter(VMXNET3State *s, int qidx)
> +{
> + vmxnet3_ring_inc(&s->txq_descr[qidx].tx_ring);
> +}
> +
> +static inline void
> +vmxnet3_inc_rx_consumption_counter(VMXNET3State *s, int qidx, int ridx)
> +{
> + vmxnet3_ring_inc(&s->rxq_descr[qidx].rx_ring[ridx]);
> +}
> +
> +static inline void
> +vmxnet3_inc_tx_completion_counter(VMXNET3State *s, int qidx)
> +{
> + vmxnet3_ring_inc(&s->txq_descr[qidx].comp_ring);
> +}
> +
> +static void
> +vmxnet3_inc_rx_completion_counter(VMXNET3State *s, int qidx)
> +{
> + vmxnet3_ring_inc(&s->rxq_descr[qidx].comp_ring);
> +}
> +
> +static void
> +vmxnet3_dec_rx_completion_counter(VMXNET3State *s, int qidx)
> +{
> + vmxnet3_ring_dec(&s->rxq_descr[qidx].comp_ring);
> +}
> +
> +static void vmxnet3_complete_packet(VMXNET3State *s, int qidx, uint32
> tx_ridx)
> +{
> + struct Vmxnet3_TxCompDesc txcq_descr;
> +
> + VMXNET3_RING_DUMP(VMW_RIPRN, "TXC", qidx, &s->txq_descr[qidx].comp_ring);
> +
> + txcq_descr.txdIdx = tx_ridx;
> + txcq_descr.gen = vmxnet3_ring_curr_gen(&s->txq_descr[qidx].comp_ring);
> +
> + vmxnet3_ring_write_curr_cell(&s->txq_descr[qidx].comp_ring, &txcq_descr);
> +
> + /* Flush changes in TX descriptor before changing the counter value */
> + smp_wmb();
> +
> + vmxnet3_inc_tx_completion_counter(s, qidx);
> + vmxnet3_trigger_interrupt(s, s->txq_descr[qidx].intr_idx);
> +}
> +
> +static bool
> +vmxnet3_setup_tx_offloads(VMXNET3State *s)
> +{
> + switch (s->offload_mode) {
> + case VMXNET3_OM_NONE:
> + vmxnet_tx_pkt_build_vheader(s->tx_pkt, false, false, 0);
> + break;
> +
> + case VMXNET3_OM_CSUM:
> + vmxnet_tx_pkt_build_vheader(s->tx_pkt, false, true, 0);
> + VMW_PKPRN("L4 CSO requested\n");
> + break;
> +
> + case VMXNET3_OM_TSO:
> + vmxnet_tx_pkt_build_vheader(s->tx_pkt, true, true,
> + s->cso_or_gso_size);
> + vmxnet_tx_pkt_update_ip_checksums(s->tx_pkt);
> + VMW_PKPRN("GSO offload requested.");
> + break;
> +
> + default:
> + assert(false);
> + return false;
> + }
> +
> + return true;
> +}
> +
> +static void
> +vmxnet3_tx_retrieve_metadata(VMXNET3State *s,
> + const struct Vmxnet3_TxDesc *txd)
> +{
> + s->offload_mode = txd->om;
> + s->cso_or_gso_size = txd->msscof;
> + s->tci = txd->tci;
> + s->needs_vlan = txd->ti;
> +}
> +
> +typedef enum {
> + VMXNET3_PKT_STATUS_OK,
> + VMXNET3_PKT_STATUS_ERROR,
> + VMXNET3_PKT_STATUS_DISCARD,/* only for tx */
> + VMXNET3_PKT_STATUS_OUT_OF_BUF /* only for rx */
> +} Vmxnet3PktStatus;
> +
> +static void
> +vmxnet3_on_tx_done_update_stats(VMXNET3State *s, int qidx,
> + Vmxnet3PktStatus status)
> +{
> + size_t tot_len = vmxnet_tx_pkt_get_total_len(s->tx_pkt);
> + struct UPT1_TxStats *stats = &s->txq_descr[qidx].txq_stats;
> +
> + switch (status) {
> + case VMXNET3_PKT_STATUS_OK:
> + switch (vmxnet_tx_pkt_get_packet_type(s->tx_pkt)) {
> + case ETH_PKT_BCAST:
> + stats->bcastPktsTxOK++;
> + stats->bcastBytesTxOK += tot_len;
> + break;
> + case ETH_PKT_MCAST:
> + stats->mcastPktsTxOK++;
> + stats->mcastBytesTxOK += tot_len;
> + break;
> + case ETH_PKT_UCAST:
> + stats->ucastPktsTxOK++;
> + stats->ucastBytesTxOK += tot_len;
> + break;
> + default:
> + assert(false);
> + }
> +
> + if (s->offload_mode == VMXNET3_OM_TSO) {
> + /*
> + * According to VMWARE headers this statistic is a number
> + * of packets after segmentation but since we don't have
> + * this information in QEMU model, the best we can do is to
> + * provide number of non-segmented packets
> + */
> + stats->TSOPktsTxOK++;
> + stats->TSOBytesTxOK += tot_len;
> + }
> + break;
> +
> + case VMXNET3_PKT_STATUS_DISCARD:
> + stats->pktsTxDiscard++;
> + break;
> +
> + case VMXNET3_PKT_STATUS_ERROR:
> + stats->pktsTxError++;
> + break;
> +
> + default:
> + assert(false);
> + }
> +}
> +
> +static void
> +vmxnet3_on_rx_done_update_stats(VMXNET3State *s,
> + int qidx,
> + Vmxnet3PktStatus status)
> +{
> + struct UPT1_RxStats *stats = &s->rxq_descr[qidx].rxq_stats;
> + size_t tot_len = vmxnet_rx_pkt_get_total_len(s->rx_pkt);
> +
> + switch (status) {
> + case VMXNET3_PKT_STATUS_OUT_OF_BUF:
> + stats->pktsRxOutOfBuf++;
> + break;
> +
> + case VMXNET3_PKT_STATUS_ERROR:
> + stats->pktsRxError++;
> + break;
> + case VMXNET3_PKT_STATUS_OK:
> + switch (vmxnet_rx_pkt_get_packet_type(s->rx_pkt)) {
> + case ETH_PKT_BCAST:
> + stats->bcastPktsRxOK++;
> + stats->bcastBytesRxOK += tot_len;
> + break;
> + case ETH_PKT_MCAST:
> + stats->mcastPktsRxOK++;
> + stats->mcastBytesRxOK += tot_len;
> + break;
> + case ETH_PKT_UCAST:
> + stats->ucastPktsRxOK++;
> + stats->ucastBytesRxOK += tot_len;
> + break;
> + default:
> + assert(false);
> + }
> +
> + if (tot_len > s->mtu) {
> + stats->LROPktsRxOK++;
> + stats->LROBytesRxOK += tot_len;
> + }
> + break;
> + default:
> + assert(false);
> + }
> +}
> +
> +static inline bool
> +vmxnet3_pop_next_tx_descr(VMXNET3State *s,
> + int qidx,
> + struct Vmxnet3_TxDesc *txd,
> + uint32_t *descr_idx)
> +{
> + Vmxnet3Ring *ring = &s->txq_descr[qidx].tx_ring;
> +
> + vmxnet3_ring_read_curr_cell(ring, txd);
> + if (txd->gen == vmxnet3_ring_curr_gen(ring)) {
> + VMXNET3_RING_DUMP(VMW_RIPRN, "TX", qidx, ring);
> + *descr_idx = vmxnet3_ring_curr_cell_idx(ring);
> + vmxnet3_inc_tx_consumption_counter(s, qidx);
> + return true;
> + }
> +
> + return false;
> +}
> +
> +static bool
> +vmxnet3_send_packet(VMXNET3State *s, uint32_t qidx)
> +{
> + size_t bytes_sent;
> + bool res;
> + Vmxnet3PktStatus status = VMXNET3_PKT_STATUS_OK;
> +
> + res = vmxnet3_setup_tx_offloads(s);
> + if (!res) {
> + status = VMXNET3_PKT_STATUS_ERROR;
> + goto func_exit;
> + }
> +
> + /* debug prints */
> + vmxnet3_dump_virt_hdr(vmxnet_tx_pkt_get_vhdr(s->tx_pkt));
> + vmxnet_tx_pkt_dump(s->tx_pkt);
> +
> + bytes_sent = vmxnet_tx_pkt_send(s->tx_pkt, &s->nic->nc);
> + if (!bytes_sent) {
> + res = false;
> + status = VMXNET3_PKT_STATUS_DISCARD;
> + goto func_exit;
> + }
> +
> +func_exit:
> + vmxnet3_on_tx_done_update_stats(s, qidx, status);
> + return res;
> +}
> +
> +static void vmxnet3_process_tx_queue(VMXNET3State *s, int qidx)
> +{
> + struct Vmxnet3_TxDesc txd;
> + uint32_t txd_idx;
> + uint32_t data_len;
> + hwaddr data_pa;
> +
> + for (;;) {
> + if (!vmxnet3_pop_next_tx_descr(s, qidx, &txd, &txd_idx)) {
> + break;
> + }
> +
> + vmxnet3_dump_tx_descr(&txd);
> +
> + if (!s->skip_current_tx_pkt) {
> + data_len = (txd.len > 0) ? txd.len : VMXNET3_MAX_TX_BUF_SIZE;
> + data_pa = le64_to_cpu(txd.addr);
> +
> + if (!vmxnet_tx_pkt_add_raw_fragment(s->tx_pkt,
> + data_pa,
> + data_len)) {
> + s->skip_current_tx_pkt = true;
> + }
> + }
> +
> + if (s->tx_sop) {
> + vmxnet3_tx_retrieve_metadata(s, &txd);
> + s->tx_sop = false;
> + }
> +
> + if (txd.eop) {
> + if (!s->skip_current_tx_pkt) {
> + vmxnet_tx_pkt_parse(s->tx_pkt);
> +
> + if (s->needs_vlan) {
> + vmxnet_tx_pkt_setup_vlan_header(s->tx_pkt, s->tci);
> + }
> +
> + vmxnet3_send_packet(s, qidx);
> + } else {
> + vmxnet3_on_tx_done_update_stats(s, qidx,
> + VMXNET3_PKT_STATUS_ERROR);
> + }
> +
> + vmxnet3_complete_packet(s, qidx, txd_idx);
> + s->tx_sop = true;
> + s->skip_current_tx_pkt = false;
> + vmxnet_tx_pkt_reset(s->tx_pkt);
> + }
> + }
> +}
> +
> +static inline void
> +vmxnet3_read_next_rx_descr(VMXNET3State *s, int qidx, int ridx,
> + struct Vmxnet3_RxDesc *dbuf, uint32_t *didx)
> +{
> + Vmxnet3Ring *ring = &s->rxq_descr[qidx].rx_ring[ridx];
> + *didx = vmxnet3_ring_curr_cell_idx(ring);
> + vmxnet3_ring_read_curr_cell(ring, dbuf);
> +}
> +
> +static inline uint8_t
> +vmxnet3_get_rx_ring_gen(VMXNET3State *s, int qidx, int ridx)
> +{
> + return s->rxq_descr[qidx].rx_ring[ridx].gen;
> +}
> +
> +static inline hwaddr
> +vmxnet3_pop_rxc_descr(VMXNET3State *s, int qidx, uint32_t *descr_gen)
> +{
> + uint8_t ring_gen;
> + struct Vmxnet3_RxCompDesc rxcd;
> +
> + hwaddr daddr =
> + vmxnet3_ring_curr_cell_pa(&s->rxq_descr[qidx].comp_ring);
> +
> + cpu_physical_memory_read(daddr, &rxcd, sizeof(struct
> Vmxnet3_RxCompDesc));
> + ring_gen = vmxnet3_ring_curr_gen(&s->rxq_descr[qidx].comp_ring);
> +
> + if (rxcd.gen != ring_gen) {
> + *descr_gen = ring_gen;
> + vmxnet3_inc_rx_completion_counter(s, qidx);
> + return daddr;
> + }
> +
> + return 0;
> +}
> +
> +static inline void
> +vmxnet3_revert_rxc_descr(VMXNET3State *s, int qidx)
> +{
> + vmxnet3_dec_rx_completion_counter(s, qidx);
> +}
> +
> +#define RXQ_IDX (0)
> +#define RX_HEAD_BODY_RING (0)
> +#define RX_BODY_ONLY_RING (1)
> +
> +static bool
> +vmxnet3_get_next_head_rx_descr(VMXNET3State *s,
> + struct Vmxnet3_RxDesc *descr_buf,
> + uint32_t *descr_idx,
> + uint32_t *ridx)
> +{
> + for (;;) {
> + uint32_t ring_gen;
> + vmxnet3_read_next_rx_descr(s, RXQ_IDX, RX_HEAD_BODY_RING,
> + descr_buf, descr_idx);
> +
> + /* If no more free descriptors - return */
> + ring_gen = vmxnet3_get_rx_ring_gen(s, RXQ_IDX, RX_HEAD_BODY_RING);
> + if (descr_buf->gen != ring_gen) {
> + return false;
> + }
> +
> + /* Mark current descriptor as used/skipped */
> + vmxnet3_inc_rx_consumption_counter(s, RXQ_IDX, RX_HEAD_BODY_RING);
> +
> + /* If this is what we are looking for - return */
> + if (descr_buf->btype == VMXNET3_RXD_BTYPE_HEAD) {
> + *ridx = RX_HEAD_BODY_RING;
> + return true;
> + }
> + }
> +}
> +
> +static bool
> +vmxnet3_get_next_body_rx_descr(VMXNET3State *s,
> + struct Vmxnet3_RxDesc *d,
> + uint32_t *didx,
> + uint32_t *ridx)
> +{
> + vmxnet3_read_next_rx_descr(s, RXQ_IDX, RX_HEAD_BODY_RING, d, didx);
> +
> + /* Try to find corresponding descriptor in head/body ring */
> + if ((d->gen == vmxnet3_get_rx_ring_gen(s, RXQ_IDX, RX_HEAD_BODY_RING)) &&
> + (d->btype == VMXNET3_RXD_BTYPE_BODY)) {
> + vmxnet3_inc_rx_consumption_counter(s, RXQ_IDX, RX_HEAD_BODY_RING);
> + *ridx = RX_HEAD_BODY_RING;
> + return true;
> + }
> +
> + /*
> + * If there is no free descriptors on head/body ring or next free
> + * descriptor is a head descriptor switch to body only ring
> + */
> + vmxnet3_read_next_rx_descr(s, RXQ_IDX, RX_BODY_ONLY_RING, d, didx);
> +
> + /* If no more free descriptors - return */
> + if (d->gen == vmxnet3_get_rx_ring_gen(s, RXQ_IDX, RX_BODY_ONLY_RING)) {
> + assert(d->btype == VMXNET3_RXD_BTYPE_BODY);
> + *ridx = RX_BODY_ONLY_RING;
> + vmxnet3_inc_rx_consumption_counter(s, RXQ_IDX, RX_BODY_ONLY_RING);
> + return true;
> + }
> +
> + return false;
> +}
> +
> +static inline bool
> +vmxnet3_get_next_rx_descr(VMXNET3State *s, bool is_head,
> + struct Vmxnet3_RxDesc *descr_buf,
> + uint32_t *descr_idx,
> + uint32_t *ridx)
> +{
> + if (is_head || !s->rx_packets_compound) {
> + return vmxnet3_get_next_head_rx_descr(s, descr_buf, descr_idx, ridx);
> + } else {
> + return vmxnet3_get_next_body_rx_descr(s, descr_buf, descr_idx, ridx);
> + }
> +}
> +
> +static void vmxnet3_rx_update_descr(struct VmxnetRxPkt *pkt,
> + struct Vmxnet3_RxCompDesc *rxcd)
> +{
> + int csum_ok, is_gso;
> + bool isip4, isip6, istcp, isudp;
> + struct virtio_net_hdr *vhdr;
> + uint8_t offload_type;
> +
> + if (vmxnet_rx_pkt_is_vlan_stripped(pkt)) {
> + rxcd->ts = 1;
> + rxcd->tci = vmxnet_rx_pkt_get_vlan_tag(pkt);
> + }
> +
> + if (!vmxnet_rx_pkt_has_virt_hdr(pkt)) {
> + goto nocsum;
> + }
> +
> + vhdr = vmxnet_rx_pkt_get_vhdr(pkt);
> + /*
> + * Checksum is valid when lower level tell so or when lower level
> + * requires checksum offload telling that packet produced/bridged
> + * locally and did travel over network after last checksum calculation
> + * or production
> + */
> + csum_ok = VMXNET_FLAG_IS_SET(vhdr->flags, VIRTIO_NET_HDR_F_DATA_VALID) ||
> + VMXNET_FLAG_IS_SET(vhdr->flags, VIRTIO_NET_HDR_F_NEEDS_CSUM);
> +
> + offload_type = vhdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN;
> + is_gso = (offload_type != VIRTIO_NET_HDR_GSO_NONE) ? 1 : 0;
> +
> + if (!csum_ok && !is_gso) {
> + goto nocsum;
> + }
> +
> + vmxnet_rx_pkt_get_protocols(pkt, &isip4, &isip6, &isudp, &istcp);
> + if ((!istcp && !isudp) || (!isip4 && !isip6)) {
> + goto nocsum;
> + }
> +
> + rxcd->cnc = 0;
> + rxcd->v4 = isip4 ? 1 : 0;
> + rxcd->v6 = isip6 ? 1 : 0;
> + rxcd->tcp = istcp ? 1 : 0;
> + rxcd->udp = isudp ? 1 : 0;
> + rxcd->fcs = rxcd->tuc = rxcd->ipc = 1;
> + return;
> +
> +nocsum:
> + rxcd->cnc = 1;
> + return;
> +}
> +
> +static void
> +vmxnet3_physical_memory_writev(const struct iovec *iov,
> + size_t start_iov_off,
> + hwaddr target_addr,
> + size_t bytes_to_copy)
> +{
> + size_t curr_off = 0;
> + size_t copied = 0;
> +
> + while (bytes_to_copy) {
> + if (start_iov_off < (curr_off + iov->iov_len)) {
> + size_t chunk_len =
> + MIN((curr_off + iov->iov_len) - start_iov_off,
> bytes_to_copy);
> +
> + cpu_physical_memory_write(target_addr + copied,
> + iov->iov_base + start_iov_off -
> curr_off,
> + chunk_len);
> +
> + copied += chunk_len;
> + start_iov_off += chunk_len;
> + curr_off = start_iov_off;
> + bytes_to_copy -= chunk_len;
> + } else {
> + curr_off += iov->iov_len;
> + }
> + iov++;
> + }
> +}
> +
> +static bool
> +vmxnet3_indicate_packet(VMXNET3State *s)
> +{
> + struct Vmxnet3_RxDesc rxd;
> + bool is_head = true;
> + uint32_t rxd_idx;
> + uint32_t rx_ridx;
> +
> + struct Vmxnet3_RxCompDesc rxcd;
> + uint32_t new_rxcd_gen = VMXNET3_INIT_GEN;
> + hwaddr new_rxcd_pa = 0;
> + hwaddr ready_rxcd_pa = 0;
> + struct iovec *data = vmxnet_rx_pkt_get_iovec(s->rx_pkt);
> + size_t bytes_copied = 0;
> + size_t bytes_left = vmxnet_rx_pkt_get_total_len(s->rx_pkt);
> + uint16_t num_frags = 0;
> + size_t chunk_size;
> +
> + vmxnet_rx_pkt_dump(s->rx_pkt);
> +
> + while (bytes_left > 0) {
> +
> + /* cannot add more frags to packet */
> + if (num_frags == s->max_rx_frags) {
> + break;
> + }
> +
> + new_rxcd_pa = vmxnet3_pop_rxc_descr(s, RXQ_IDX, &new_rxcd_gen);
> + if (!new_rxcd_pa) {
> + break;
> + }
> +
> + if (!vmxnet3_get_next_rx_descr(s, is_head, &rxd, &rxd_idx,
> &rx_ridx)) {
> + break;
> + }
> +
> + chunk_size = MIN(bytes_left, rxd.len);
> + vmxnet3_physical_memory_writev(data, bytes_copied,
> + le64_to_cpu(rxd.addr), chunk_size);
> + bytes_copied += chunk_size;
> + bytes_left -= chunk_size;
> +
> + vmxnet3_dump_rx_descr(&rxd);
> +
> + if (0 != ready_rxcd_pa) {
> + cpu_physical_memory_write(ready_rxcd_pa, &rxcd, sizeof(rxcd));
> + }
> +
> + memset(&rxcd, 0, sizeof(struct Vmxnet3_RxCompDesc));
> + rxcd.rxdIdx = rxd_idx;
> + rxcd.len = chunk_size;
> + rxcd.sop = is_head;
> + rxcd.gen = new_rxcd_gen;
> + rxcd.rqID = RXQ_IDX + rx_ridx * s->rxq_num;
> +
> + if (0 == bytes_left) {
> + vmxnet3_rx_update_descr(s->rx_pkt, &rxcd);
> + }
> +
> + VMW_RIPRN("RX Completion descriptor: rxRing: %lu rxIdx %lu len %lu "
> + "sop %d csum_correct %lu",
> + (unsigned long) rx_ridx,
> + (unsigned long) rxcd.rxdIdx,
> + (unsigned long) rxcd.len,
> + (int) rxcd.sop,
> + (unsigned long) rxcd.tuc);
> +
> + is_head = false;
> + ready_rxcd_pa = new_rxcd_pa;
> + new_rxcd_pa = 0;
> + }
> +
> + if (0 != ready_rxcd_pa) {
> + rxcd.eop = 1;
> + rxcd.err = (0 != bytes_left);
> + cpu_physical_memory_write(ready_rxcd_pa, &rxcd, sizeof(rxcd));
> +
> + /* Flush RX descriptor changes */
> + smp_wmb();
> + }
> +
> + if (0 != new_rxcd_pa) {
> + vmxnet3_revert_rxc_descr(s, RXQ_IDX);
> + }
> +
> + vmxnet3_trigger_interrupt(s, s->rxq_descr[RXQ_IDX].intr_idx);
> +
> + if (bytes_left == 0) {
> + vmxnet3_on_rx_done_update_stats(s, RXQ_IDX, VMXNET3_PKT_STATUS_OK);
> + return true;
> + } else if (num_frags == s->max_rx_frags) {
> + vmxnet3_on_rx_done_update_stats(s, RXQ_IDX,
> VMXNET3_PKT_STATUS_ERROR);
> + return false;
> + } else {
> + vmxnet3_on_rx_done_update_stats(s, RXQ_IDX,
> + VMXNET3_PKT_STATUS_OUT_OF_BUF);
> + return false;
> + }
> +}
> +
> +static void
> +vmxnet3_io_bar0_write(void *opaque, hwaddr addr,
> + uint64_t val, unsigned size)
> +{
> + VMXNET3State *s = opaque;
> +
> + if (VMW_IS_MULTIREG_ADDR(addr, VMXNET3_REG_TXPROD,
> + VMXNET3_DEVICE_MAX_TX_QUEUES, VMXNET3_REG_ALIGN)) {
> + int tx_queue_idx =
> + VMW_MULTIREG_IDX_BY_ADDR(addr, VMXNET3_REG_TXPROD,
> + VMXNET3_REG_ALIGN);
> + assert(tx_queue_idx <= s->txq_num);
> + vmxnet3_process_tx_queue(s, tx_queue_idx);
> + return;
> + }
> +
> + if (VMW_IS_MULTIREG_ADDR(addr, VMXNET3_REG_IMR,
> + VMXNET3_MAX_INTRS, VMXNET3_REG_ALIGN)) {
> + int l = VMW_MULTIREG_IDX_BY_ADDR(addr, VMXNET3_REG_IMR,
> + VMXNET3_REG_ALIGN);
> +
> + VMW_CBPRN("Interrupt mask for line %d written: 0x%" PRIx64, l, val);
> +
> + vmxnet3_on_interrupt_mask_changed(s, l, val);
> + return;
> + }
> +
> + if (VMW_IS_MULTIREG_ADDR(addr, VMXNET3_REG_RXPROD,
> + VMXNET3_DEVICE_MAX_RX_QUEUES, VMXNET3_REG_ALIGN) ||
> + VMW_IS_MULTIREG_ADDR(addr, VMXNET3_REG_RXPROD2,
> + VMXNET3_DEVICE_MAX_RX_QUEUES, VMXNET3_REG_ALIGN)) {
> + return;
> + }
> +
> + VMW_WRPRN("BAR0 unknown write [%" PRIx64 "] = %" PRIx64 ", size %d",
> + (uint64_t) addr, val, size);
> +}
> +
> +static uint64_t
> +vmxnet3_io_bar0_read(void *opaque, hwaddr addr, unsigned size)
> +{
> + if (VMW_IS_MULTIREG_ADDR(addr, VMXNET3_REG_IMR,
> + VMXNET3_MAX_INTRS, VMXNET3_REG_ALIGN)) {
> + assert(false);
> + }
> +
> + VMW_CBPRN("BAR0 unknown read [%" PRIx64 "], size %d", addr, size);
> + return 0;
> +}
> +
> +static void vmxnet3_reset(VMXNET3State *s)
> +{
> + VMW_CBPRN("Resetting vmxnet3...");
> +
> + vmxnet_tx_pkt_reset(s->tx_pkt);
> + s->tx_sop = true;
> + s->skip_current_tx_pkt = false;
> +}
> +
> +static void vmxnet3_deactivate_device(VMXNET3State *s)
> +{
> + VMW_CBPRN("Deactivating vmxnet3...");
> + s->device_active = false;
> +}
> +
> +static void vmxnet3_update_rx_mode(VMXNET3State *s)
> +{
> + s->rx_mode = VMXNET3_READ_DRV_SHARED32(s->drv_shmem,
> + devRead.rxFilterConf.rxMode);
> + VMW_CFPRN("RX mode: 0x%08X", s->rx_mode);
> +}
> +
> +static void vmxnet3_update_vlan_filters(VMXNET3State *s)
> +{
> + int i;
> +
> + /* Copy configuration from shared memory */
> + VMXNET3_READ_DRV_SHARED(s->drv_shmem,
> + devRead.rxFilterConf.vfTable,
> + s->vlan_table,
> + sizeof(s->vlan_table));
> +
> + /* Invert byte order when needed */
> + for (i = 0; i < ARRAY_SIZE(s->vlan_table); i++) {
> + s->vlan_table[i] = le32_to_cpu(s->vlan_table[i]);
> + }
> +
> + /* Dump configuration for debugging purposes */
> + VMW_CFPRN("Configured VLANs:");
> + for (i = 0; i < sizeof(s->vlan_table) * 8; i++) {
> + if (VMXNET3_VFTABLE_ENTRY_IS_SET(s->vlan_table, i)) {
> + VMW_CFPRN("\tVLAN %d is present", i);
> + }
> + }
> +}
> +
> +static void vmxnet3_update_mcast_filters(VMXNET3State *s)
> +{
> + uint16_t list_bytes =
> + VMXNET3_READ_DRV_SHARED16(s->drv_shmem,
> + devRead.rxFilterConf.mfTableLen);
> +
> + s->mcast_list_len = list_bytes / sizeof(s->mcast_list[0]);
> +
> + s->mcast_list = g_realloc(s->mcast_list, list_bytes);
> + if (NULL == s->mcast_list) {
> + if (0 == s->mcast_list_len) {
> + VMW_CFPRN("Current multicast list is empty");
> + } else {
> + VMW_ERPRN("Failed to allocate multicast list of %d elements",
> + s->mcast_list_len);
> + }
> + s->mcast_list_len = 0;
> + } else {
> + int i;
> + hwaddr mcast_list_pa =
> + VMXNET3_READ_DRV_SHARED64(s->drv_shmem,
> + devRead.rxFilterConf.mfTablePA);
> +
> + cpu_physical_memory_read(mcast_list_pa, s->mcast_list, list_bytes);
> + VMW_CFPRN("Current multicast list len is %d:", s->mcast_list_len);
> + for (i = 0; i < s->mcast_list_len; i++) {
> + VMW_CFPRN("\t" VMXNET_MF, VMXNET_MA(s->mcast_list[i].a));
> + }
> + }
> +}
> +
> +static void vmxnet3_setup_rx_filtering(VMXNET3State *s)
> +{
> + vmxnet3_update_rx_mode(s);
> + vmxnet3_update_vlan_filters(s);
> + vmxnet3_update_mcast_filters(s);
> +}
> +
> +static uint32_t vmxnet3_get_interrupt_config(VMXNET3State *s)
> +{
> + uint32_t interrupt_mode = VMXNET3_IT_AUTO | (VMXNET3_IMM_AUTO << 2);
> + VMW_CFPRN("Interrupt config is 0x%X", interrupt_mode);
> + return interrupt_mode;
> +}
> +
> +static void vmxnet3_fill_stats(VMXNET3State *s)
> +{
> + int i;
> + for (i = 0; i < s->txq_num; i++) {
> + cpu_physical_memory_write(s->txq_descr[i].tx_stats_pa,
> + &s->txq_descr[i].txq_stats,
> + sizeof(s->txq_descr[i].txq_stats));
> + }
> +
> + for (i = 0; i < s->rxq_num; i++) {
> + cpu_physical_memory_write(s->rxq_descr[i].rx_stats_pa,
> + &s->rxq_descr[i].rxq_stats,
> + sizeof(s->rxq_descr[i].rxq_stats));
> + }
> +}
> +
> +static void vmxnet3_adjust_by_guest_type(VMXNET3State *s)
> +{
> + struct Vmxnet3_GOSInfo gos;
> +
> + VMXNET3_READ_DRV_SHARED(s->drv_shmem, devRead.misc.driverInfo.gos,
> + &gos, sizeof(gos));
> + s->rx_packets_compound =
> + (gos.gosType == VMXNET3_GOS_TYPE_WIN) ? false : true;
> +
> + VMW_CFPRN("Guest type specifics: RXCOMPOUND: %d",
> s->rx_packets_compound);
> +}
> +
> +static void
> +vmxnet3_dump_conf_descr(const char *name,
> + struct Vmxnet3_VariableLenConfDesc *pm_descr)
> +{
> + VMW_CFPRN("%s descriptor dump: Version %u, Length %u",
> + name, pm_descr->confVer, pm_descr->confLen);
> +
> +};
> +
> +static void vmxnet3_update_pm_state(VMXNET3State *s)
> +{
> + struct Vmxnet3_VariableLenConfDesc pm_descr;
> +
> + pm_descr.confLen =
> + VMXNET3_READ_DRV_SHARED32(s->drv_shmem, devRead.pmConfDesc.confLen);
> + pm_descr.confVer =
> + VMXNET3_READ_DRV_SHARED32(s->drv_shmem, devRead.pmConfDesc.confVer);
> + pm_descr.confPA =
> + VMXNET3_READ_DRV_SHARED64(s->drv_shmem, devRead.pmConfDesc.confPA);
> +
> + vmxnet3_dump_conf_descr("PM State", &pm_descr);
> +}
> +
> +static void vmxnet3_update_features(VMXNET3State *s)
> +{
> + uint32_t guest_features;
> + int rxcso_supported;
> +
> + guest_features = VMXNET3_READ_DRV_SHARED32(s->drv_shmem,
> + devRead.misc.uptFeatures);
> +
> + rxcso_supported = VMXNET_FLAG_IS_SET(guest_features, UPT1_F_RXCSUM);
> + s->rx_vlan_stripping = VMXNET_FLAG_IS_SET(guest_features, UPT1_F_RXVLAN);
> + s->lro_supported = VMXNET_FLAG_IS_SET(guest_features, UPT1_F_LRO);
> +
> + VMW_CFPRN("Features configuration: LRO: %d, RXCSUM: %d, VLANSTRIP: %d",
> + s->lro_supported, rxcso_supported,
> + s->rx_vlan_stripping);
> + if (s->peer_has_vhdr) {
> + tap_set_offload(s->nic->nc.peer,
> + rxcso_supported,
> + s->lro_supported,
> + s->lro_supported,
> + 0,
> + 0);
> + }
> +}
> +
> +static void vmxnet3_activate_device(VMXNET3State *s)
> +{
> + int i;
> + static const uint32_t VMXNET3_DEF_TX_THRESHOLD = 1;
> + hwaddr qdescr_table_pa;
> + uint64_t pa;
> + uint32_t size;
> +
> + /* Verify configuration consistency */
> + if (!vmxnet3_verify_driver_magic(s->drv_shmem)) {
> + VMW_ERPRN("Device configuration received from driver is invalid");
> + return;
> + }
> +
> + vmxnet3_adjust_by_guest_type(s);
> + vmxnet3_update_features(s);
> + vmxnet3_update_pm_state(s);
> + vmxnet3_setup_rx_filtering(s);
> + /* Cache fields from shared memory */
> + s->mtu = VMXNET3_READ_DRV_SHARED32(s->drv_shmem, devRead.misc.mtu);
> + VMW_CFPRN("MTU is %u", s->mtu);
> +
> + s->max_rx_frags =
> + VMXNET3_READ_DRV_SHARED16(s->drv_shmem, devRead.misc.maxNumRxSG);
> +
> + VMW_CFPRN("Max RX fragments is %u", s->max_rx_frags);
> +
> + s->event_int_idx =
> + VMXNET3_READ_DRV_SHARED8(s->drv_shmem,
> devRead.intrConf.eventIntrIdx);
> + VMW_CFPRN("Events interrupt line is %u", s->event_int_idx);
> +
> + s->auto_int_masking =
> + VMXNET3_READ_DRV_SHARED8(s->drv_shmem, devRead.intrConf.autoMask);
> + VMW_CFPRN("Automatic interrupt masking is %d", (int)s->auto_int_masking);
> +
> + s->txq_num =
> + VMXNET3_READ_DRV_SHARED8(s->drv_shmem, devRead.misc.numTxQueues);
> + s->rxq_num =
> + VMXNET3_READ_DRV_SHARED8(s->drv_shmem, devRead.misc.numRxQueues);
> +
> + VMW_CFPRN("Number of TX/RX queues %u/%u", s->txq_num, s->rxq_num);
> + assert(s->txq_num <= VMXNET3_DEVICE_MAX_TX_QUEUES);
> +
> + qdescr_table_pa =
> + VMXNET3_READ_DRV_SHARED64(s->drv_shmem, devRead.misc.queueDescPA);
> + VMW_CFPRN("TX queues descriptors table is at 0x%" PRIx64,
> qdescr_table_pa);
> +
> + /*
> + * Worst-case scenario is a packet that holds all TX rings space so
> + * we calculate total size of all TX rings for max TX fragments number
> + */
> + s->max_tx_frags = 0;
> +
> + /* TX queues */
> + for (i = 0; i < s->txq_num; i++) {
> + hwaddr qdescr_pa =
> + qdescr_table_pa + i * sizeof(struct Vmxnet3_TxQueueDesc);
> +
> + /* Read interrupt number for this TX queue */
> + s->txq_descr[i].intr_idx =
> + VMXNET3_READ_TX_QUEUE_DESCR8(qdescr_pa, conf.intrIdx);
> +
> + VMW_CFPRN("TX Queue %d interrupt: %d", i, s->txq_descr[i].intr_idx);
> +
> + /* Read rings memory locations for TX queues */
> + pa = VMXNET3_READ_TX_QUEUE_DESCR64(qdescr_pa, conf.txRingBasePA);
> + size = VMXNET3_READ_TX_QUEUE_DESCR32(qdescr_pa, conf.txRingSize);
> +
> + vmxnet3_ring_init(&s->txq_descr[i].tx_ring, pa, size,
> + sizeof(struct Vmxnet3_TxDesc), false);
> + VMXNET3_RING_DUMP(VMW_CFPRN, "TX", i, &s->txq_descr[i].tx_ring);
> +
> + s->max_tx_frags += size;
> +
> + /* TXC ring */
> + pa = VMXNET3_READ_TX_QUEUE_DESCR64(qdescr_pa, conf.compRingBasePA);
> + size = VMXNET3_READ_TX_QUEUE_DESCR32(qdescr_pa, conf.compRingSize);
> + vmxnet3_ring_init(&s->txq_descr[i].comp_ring, pa, size,
> + sizeof(struct Vmxnet3_TxCompDesc), true);
> + VMXNET3_RING_DUMP(VMW_CFPRN, "TXC", i, &s->txq_descr[i].comp_ring);
> +
> + s->txq_descr[i].tx_stats_pa =
> + qdescr_pa + offsetof(struct Vmxnet3_TxQueueDesc, stats);
> +
> + memset(&s->txq_descr[i].txq_stats, 0,
> + sizeof(s->txq_descr[i].txq_stats));
> +
> + /* Fill device-managed parameters for queues */
> + VMXNET3_WRITE_TX_QUEUE_DESCR32(qdescr_pa,
> + ctrl.txThreshold,
> + VMXNET3_DEF_TX_THRESHOLD);
> + }
> +
> + /* Preallocate TX packet wrapper */
> + VMW_CFPRN("Max TX fragments is %u", s->max_tx_frags);
> + vmxnet_tx_pkt_init(&s->tx_pkt, s->max_tx_frags, s->peer_has_vhdr);
> + vmxnet_rx_pkt_init(&s->rx_pkt, s->peer_has_vhdr);
> +
> + /* Read rings memory locations for RX queues */
> + for (i = 0; i < s->rxq_num; i++) {
> + int j;
> + hwaddr qd_pa =
> + qdescr_table_pa + s->txq_num * sizeof(struct
> Vmxnet3_TxQueueDesc) +
> + i * sizeof(struct Vmxnet3_RxQueueDesc);
> +
> + /* Read interrupt number for this RX queue */
> + s->rxq_descr[i].intr_idx =
> + VMXNET3_READ_TX_QUEUE_DESCR8(qd_pa, conf.intrIdx);
> +
> + VMW_CFPRN("RX Queue %d interrupt: %d", i, s->rxq_descr[i].intr_idx);
> +
> + /* Read rings memory locations */
> + for (j = 0; j < VMXNET3_RX_RINGS_PER_QUEUE; j++) {
> + /* RX rings */
> + pa = VMXNET3_READ_RX_QUEUE_DESCR64(qd_pa, conf.rxRingBasePA[j]);
> + size = VMXNET3_READ_RX_QUEUE_DESCR32(qd_pa, conf.rxRingSize[j]);
> + vmxnet3_ring_init(&s->rxq_descr[i].rx_ring[j], pa, size,
> + sizeof(struct Vmxnet3_RxDesc), false);
> + VMW_CFPRN("RX queue %d:%d: Base: %" PRIx64 ", Size: %d",
> + i, j, pa, size);
> + }
> +
> + /* RXC ring */
> + pa = VMXNET3_READ_RX_QUEUE_DESCR64(qd_pa, conf.compRingBasePA);
> + size = VMXNET3_READ_RX_QUEUE_DESCR32(qd_pa, conf.compRingSize);
> + vmxnet3_ring_init(&s->rxq_descr[i].comp_ring, pa, size,
> + sizeof(struct Vmxnet3_RxCompDesc), true);
> + VMW_CFPRN("RXC queue %d: Base: %" PRIx64 ", Size: %d", i, pa, size);
> +
> + s->rxq_descr[i].rx_stats_pa =
> + qd_pa + offsetof(struct Vmxnet3_RxQueueDesc, stats);
> + memset(&s->rxq_descr[i].rxq_stats, 0,
> + sizeof(s->rxq_descr[i].rxq_stats));
> + }
> +
> + /* Make sure everything is in place before device activation */
> + smp_wmb();
> +
> + /* Revert MAC address to the permanent one on device reactivation */
> + memcpy(&s->conf.macaddr.a, &s->perm_mac.a, sizeof(s->perm_mac.a));
> + VMW_CFPRN("MAC address set to: " VMXNET_MF,
> VMXNET_MA(s->conf.macaddr.a));
> +
> + s->device_active = true;
> +}
> +
> +static void vmxnet3_handle_command(VMXNET3State *s, uint64_t cmd)
> +{
> + s->last_command = cmd;
> +
> + switch (cmd) {
> + case VMXNET3_CMD_GET_PERM_MAC_HI:
> + VMW_CBPRN("Set: Get upper part of permanent MAC");
> + break;
> +
> + case VMXNET3_CMD_GET_PERM_MAC_LO:
> + VMW_CBPRN("Set: Get lower part of permanent MAC");
> + break;
> +
> + case VMXNET3_CMD_GET_STATS:
> + VMW_CBPRN("Set: Get device statistics");
> + vmxnet3_fill_stats(s);
> + break;
> +
> + case VMXNET3_CMD_ACTIVATE_DEV:
> + VMW_CBPRN("Set: Activating vmxnet3 device");
> + vmxnet3_activate_device(s);
> + break;
> +
> + case VMXNET3_CMD_UPDATE_RX_MODE:
> + VMW_CBPRN("Set: Update rx mode");
> + vmxnet3_update_rx_mode(s);
> + break;
> +
> + case VMXNET3_CMD_UPDATE_VLAN_FILTERS:
> + VMW_CBPRN("Set: Update VLAN filters");
> + vmxnet3_update_vlan_filters(s);
> + break;
> +
> + case VMXNET3_CMD_UPDATE_MAC_FILTERS:
> + VMW_CBPRN("Set: Update MAC filters");
> + vmxnet3_update_mcast_filters(s);
> + break;
> +
> + case VMXNET3_CMD_UPDATE_FEATURE:
> + VMW_CBPRN("Set: Update features");
> + vmxnet3_update_features(s);
> + break;
> +
> + case VMXNET3_CMD_UPDATE_PMCFG:
> + VMW_CBPRN("Set: Update power management config");
> + vmxnet3_update_pm_state(s);
> + break;
> +
> + case VMXNET3_CMD_GET_LINK:
> + VMW_CBPRN("Set: Get link");
> + break;
> +
> + case VMXNET3_CMD_RESET_DEV:
> + VMW_CBPRN("Set: Reset device");
> + vmxnet3_reset(s);
> + break;
> +
> + case VMXNET3_CMD_QUIESCE_DEV:
> + VMW_CBPRN("Set: VMXNET3_CMD_QUIESCE_DEV - pause the device");
> + vmxnet3_deactivate_device(s);
> + break;
> +
> + case VMXNET3_CMD_GET_CONF_INTR:
> + VMW_CBPRN("Set: VMXNET3_CMD_GET_CONF_INTR - interrupt
> configuration");
> + break;
> +
> + default:
> + VMW_CBPRN("Received unknown command: %" PRIx64, cmd);
> + break;
> + }
> +}
> +
> +static uint64_t vmxnet3_get_command_status(VMXNET3State *s)
> +{
> + uint64_t ret;
> +
> + switch (s->last_command) {
> + case VMXNET3_CMD_ACTIVATE_DEV:
> + ret = (s->device_active) ? 0 : -1;
> + VMW_CFPRN("Device active: %" PRIx64, ret);
> + break;
> +
> + case VMXNET3_CMD_GET_LINK:
> + ret = s->link_status_and_speed;
> + VMW_CFPRN("Link and speed: %" PRIx64, ret);
> + break;
> +
> + case VMXNET3_CMD_GET_PERM_MAC_LO:
> + ret = vmxnet3_get_mac_low(&s->perm_mac);
> + break;
> +
> + case VMXNET3_CMD_GET_PERM_MAC_HI:
> + ret = vmxnet3_get_mac_high(&s->perm_mac);
> + break;
> +
> + case VMXNET3_CMD_GET_CONF_INTR:
> + ret = vmxnet3_get_interrupt_config(s);
> + break;
> +
> + default:
> + VMW_WRPRN("Received request for unknown command: %x",
> s->last_command);
> + ret = -1;
> + break;
> + }
> +
> + return ret;
> +}
> +
> +static void vmxnet3_set_events(VMXNET3State *s, uint32_t val)
> +{
> + uint32_t events;
> +
> + VMW_CBPRN("Setting events: 0x%x", val);
> + events = VMXNET3_READ_DRV_SHARED32(s->drv_shmem, ecr) | val;
> + VMXNET3_WRITE_DRV_SHARED32(s->drv_shmem, ecr, events);
> +}
> +
> +static void vmxnet3_ack_events(VMXNET3State *s, uint32_t val)
> +{
> + uint32_t events;
> +
> + VMW_CBPRN("Clearing events: 0x%x", val);
> + events = VMXNET3_READ_DRV_SHARED32(s->drv_shmem, ecr) & ~val;
> + VMXNET3_WRITE_DRV_SHARED32(s->drv_shmem, ecr, events);
> +}
> +
> +static void
> +vmxnet3_io_bar1_write(void *opaque,
> + hwaddr addr,
> + uint64_t val,
> + unsigned size)
> +{
> + VMXNET3State *s = opaque;
> +
> + switch (addr) {
> + /* Vmxnet3 Revision Report Selection */
> + case VMXNET3_REG_VRRS:
> + VMW_CBPRN("Write BAR1 [VMXNET3_REG_VRRS] = %" PRIx64 ", size %d",
> + val, size);
> + break;
> +
> + /* UPT Version Report Selection */
> + case VMXNET3_REG_UVRS:
> + VMW_CBPRN("Write BAR1 [VMXNET3_REG_UVRS] = %" PRIx64 ", size %d",
> + val, size);
> + break;
> +
> + /* Driver Shared Address Low */
> + case VMXNET3_REG_DSAL:
> + VMW_CBPRN("Write BAR1 [VMXNET3_REG_DSAL] = %" PRIx64 ", size %d",
> + val, size);
> + /*
> + * Guest driver will first write the low part of the shared
> + * memory address. We save it to temp variable and set the
> + * shared address only after we get the high part
> + */
> + if (0 == val) {
> + s->device_active = false;
> + }
> + s->temp_shared_guest_driver_memory = val;
> + s->drv_shmem = 0;
> + break;
> +
> + /* Driver Shared Address High */
> + case VMXNET3_REG_DSAH:
> + VMW_CBPRN("Write BAR1 [VMXNET3_REG_DSAH] = %" PRIx64 ", size %d",
> + val, size);
> + /*
> + * Set the shared memory between guest driver and device.
> + * We already should have low address part.
> + */
> + s->drv_shmem = s->temp_shared_guest_driver_memory | (val << 32);
> + break;
> +
> + /* Command */
> + case VMXNET3_REG_CMD:
> + VMW_CBPRN("Write BAR1 [VMXNET3_REG_CMD] = %" PRIx64 ", size %d",
> + val, size);
> + vmxnet3_handle_command(s, val);
> + break;
> +
> + /* MAC Address Low */
> + case VMXNET3_REG_MACL:
> + VMW_CBPRN("Write BAR1 [VMXNET3_REG_MACL] = %" PRIx64 ", size %d",
> + val, size);
> + s->temp_mac = val;
> + break;
> +
> + /* MAC Address High */
> + case VMXNET3_REG_MACH:
> + VMW_CBPRN("Write BAR1 [VMXNET3_REG_MACH] = %" PRIx64 ", size %d",
> + val, size);
> + vmxnet3_set_variable_mac(s, val, s->temp_mac);
> + break;
> +
> + /* Interrupt Cause Register */
> + case VMXNET3_REG_ICR:
> + VMW_CBPRN("Write BAR1 [VMXNET3_REG_ICR] = %" PRIx64 ", size %d",
> + val, size);
> + assert(false);
> + break;
> +
> + /* Event Cause Register */
> + case VMXNET3_REG_ECR:
> + VMW_CBPRN("Write BAR1 [VMXNET3_REG_ECR] = %" PRIx64 ", size %d",
> + val, size);
> + vmxnet3_ack_events(s, val);
> + break;
> +
> + default:
> + VMW_CBPRN("Unknown Write to BAR1 [%" PRIx64 "] = %" PRIx64 ", size
> %d",
> + addr, val, size);
> + break;
> + }
> +}
> +
> +static uint64_t
> +vmxnet3_io_bar1_read(void *opaque, hwaddr addr, unsigned size)
> +{
> + VMXNET3State *s = opaque;
> + uint64_t ret = 0;
> +
> + switch (addr) {
> + /* Vmxnet3 Revision Report Selection */
> + case VMXNET3_REG_VRRS:
> + VMW_CBPRN("Read BAR1 [VMXNET3_REG_VRRS], size %d", size);
> + ret = VMXNET3_DEVICE_REVISION;
> + break;
> +
> + /* UPT Version Report Selection */
> + case VMXNET3_REG_UVRS:
> + VMW_CBPRN("Read BAR1 [VMXNET3_REG_UVRS], size %d", size);
> + ret = VMXNET3_DEVICE_VERSION;
> + break;
> +
> + /* Command */
> + case VMXNET3_REG_CMD:
> + VMW_CBPRN("Read BAR1 [VMXNET3_REG_CMD], size %d", size);
> + ret = vmxnet3_get_command_status(s);
> + break;
> +
> + /* MAC Address Low */
> + case VMXNET3_REG_MACL:
> + VMW_CBPRN("Read BAR1 [VMXNET3_REG_MACL], size %d", size);
> + ret = vmxnet3_get_mac_low(&s->conf.macaddr);
> + break;
> +
> + /* MAC Address High */
> + case VMXNET3_REG_MACH:
> + VMW_CBPRN("Read BAR1 [VMXNET3_REG_MACH], size %d", size);
> + ret = vmxnet3_get_mac_high(&s->conf.macaddr);
> + break;
> +
> + /*
> + * Interrupt Cause Register
> + * Used for legacy interrupts only so interrupt index always 0
> + */
> + case VMXNET3_REG_ICR:
> + VMW_CBPRN("Read BAR1 [VMXNET3_REG_ICR], size %d", size);
> + if (vmxnet3_interrupt_asserted(s, 0)) {
> + vmxnet3_clear_interrupt(s, 0);
> + ret = true;
> + } else {
> + ret = false;
> + }
> + break;
> +
> + default:
> + VMW_CBPRN("Unknow read BAR1[%" PRIx64 "], %d bytes", addr, size);
> + break;
> + }
> +
> + return ret;
> +}
> +
> +static int
> +vmxnet3_can_receive(NetClientState *nc)
> +{
> + VMXNET3State *s = DO_UPCAST(NICState, nc, nc)->opaque;
> + return s->device_active &&
> + VMXNET_FLAG_IS_SET(s->link_status_and_speed,
> VMXNET3_LINK_STATUS_UP);
> +}
> +
> +static inline bool
> +vmxnet3_is_registered_vlan(VMXNET3State *s, const void *data)
> +{
> + uint16_t vlan_tag = eth_get_pkt_tci(data) & VLAN_VID_MASK;
> + if (IS_SPECIAL_VLAN_ID(vlan_tag)) {
> + return true;
> + }
> +
> + return VMXNET3_VFTABLE_ENTRY_IS_SET(s->vlan_table, vlan_tag);
> +}
> +
> +static bool
> +vmxnet3_is_allowed_mcast_group(VMXNET3State *s, const uint8_t *group_mac)
> +{
> + int i;
> + for (i = 0; i < s->mcast_list_len; i++) {
> + if (!memcmp(group_mac, s->mcast_list[i].a,
> sizeof(s->mcast_list[i]))) {
> + return true;
> + }
> + }
> + return false;
> +}
> +
> +static bool
> +vmxnet3_rx_filter_may_indicate(VMXNET3State *s, const void *data,
> + size_t size)
> +{
> + struct eth_header *ehdr = PKT_GET_ETH_HDR(data);
> +
> + if (VMXNET_FLAG_IS_SET(s->rx_mode, VMXNET3_RXM_PROMISC)) {
> + return true;
> + }
> +
> + if (!vmxnet3_is_registered_vlan(s, data)) {
> + return false;
> + }
> +
> + switch (vmxnet_rx_pkt_get_packet_type(s->rx_pkt)) {
> + case ETH_PKT_UCAST:
> + if (!VMXNET_FLAG_IS_SET(s->rx_mode, VMXNET3_RXM_UCAST)) {
> + return false;
> + }
> + if (memcmp(s->conf.macaddr.a, ehdr->h_dest, ETH_ALEN)) {
> + return false;
> + }
> + break;
> +
> + case ETH_PKT_BCAST:
> + if (!VMXNET_FLAG_IS_SET(s->rx_mode, VMXNET3_RXM_BCAST)) {
> + return false;
> + }
> + break;
> +
> + case ETH_PKT_MCAST:
> + if (VMXNET_FLAG_IS_SET(s->rx_mode, VMXNET3_RXM_ALL_MULTI)) {
> + return true;
> + }
> + if (!VMXNET_FLAG_IS_SET(s->rx_mode, VMXNET3_RXM_MCAST)) {
> + return false;
> + }
> + if (!vmxnet3_is_allowed_mcast_group(s, ehdr->h_dest)) {
> + return false;
> + }
> + break;
> +
> + default:
> + assert(false);
> + }
> +
> + return true;
> +}
> +
> +static ssize_t
> +vmxnet3_receive(NetClientState *nc, const uint8_t *buf, size_t size)
> +{
> + VMXNET3State *s = DO_UPCAST(NICState, nc, nc)->opaque;
> + size_t bytes_indicated;
> +
> + if (!vmxnet3_can_receive(&s->nic->nc)) {
> + VMW_PKPRN("Cannot receive now");
> + return -1;
> + }
> +
> + if (s->peer_has_vhdr) {
> + vmxnet_rx_pkt_set_vhdr(s->rx_pkt, (struct virtio_net_hdr *)buf);
> + buf += sizeof(struct virtio_net_hdr);
> + size -= sizeof(struct virtio_net_hdr);
> + }
> +
> + vmxnet_rx_pkt_set_packet_type(s->rx_pkt,
> + get_eth_packet_type(PKT_GET_ETH_HDR(buf)));
> +
> + if (vmxnet3_rx_filter_may_indicate(s, buf, size)) {
> + vmxnet_rx_pkt_attach_data(s->rx_pkt, buf, size,
> s->rx_vlan_stripping);
> + bytes_indicated = vmxnet3_indicate_packet(s) ? size : -1;
> + if (bytes_indicated < size) {
> + VMW_PKPRN("RX: %lu of %lu bytes indicated", bytes_indicated,
> size);
> + }
> + } else {
> + VMW_PKPRN("Packet dropped by RX filter");
> + bytes_indicated = size;
> + }
> +
> + assert(size > 0);
> + assert(bytes_indicated != 0);
> + return bytes_indicated;
> +}
> +
> +static void vmxnet3_cleanup(NetClientState *nc)
> +{
> + VMXNET3State *s = DO_UPCAST(NICState, nc, nc)->opaque;
> + s->nic = NULL;
> +}
> +
> +static void vmxnet3_set_link_status(NetClientState *nc)
> +{
> + VMXNET3State *s = DO_UPCAST(NICState, nc, nc)->opaque;
> +
> + if (nc->link_down) {
> + s->link_status_and_speed &= ~VMXNET3_LINK_STATUS_UP;
> + } else {
> + s->link_status_and_speed |= VMXNET3_LINK_STATUS_UP;
> + }
> +
> + vmxnet3_set_events(s, VMXNET3_ECR_LINK);
> + vmxnet3_trigger_interrupt(s, s->event_int_idx);
> +}
> +
> +static NetClientInfo net_vmxnet3_info = {
> + .type = NET_CLIENT_OPTIONS_KIND_NIC,
> + .size = sizeof(NICState),
> + .can_receive = vmxnet3_can_receive,
> + .receive = vmxnet3_receive,
> + .cleanup = vmxnet3_cleanup,
> + .link_status_changed = vmxnet3_set_link_status,
> +};
> +
> +static bool vmxnet3_peer_has_vnet_hdr(VMXNET3State *s)
> +{
> + NetClientState *peer = s->nic->nc.peer;
> +
> + if ((NULL != peer) &&
> + (peer->info->type == NET_CLIENT_OPTIONS_KIND_TAP) &&
> + tap_has_vnet_hdr(peer)) {
> + return true;
> + }
> +
> + VMW_WRPRN("Peer has no virtio extension. Task offloads will be
> emulated.");
> + return false;
> +}
> +
> +static void vmxnet3_net_uninit(VMXNET3State *s)
> +{
> + if (NULL != s->mcast_list) {
> + g_free(s->mcast_list);
> + }
> +
> + vmxnet_tx_pkt_reset(s->tx_pkt);
> + vmxnet_tx_pkt_uninit(s->tx_pkt);
> + vmxnet_rx_pkt_uninit(s->rx_pkt);
> +}
> +
> +static void vmxnet3_net_init(VMXNET3State *s)
> +{
> + VMW_CBPRN("vmxnet3_net_init called...");
> +
> + qemu_macaddr_default_if_unset(&s->conf.macaddr);
> +
> + /* Windows guest will query the address that was set on init */
> + memcpy(&s->perm_mac.a, &s->conf.macaddr.a, sizeof(s->perm_mac.a));
> +
> + s->mcast_list = NULL;
> + s->mcast_list_len = 0;
> +
> + s->link_status_and_speed = VMXNET3_LINK_SPEED | VMXNET3_LINK_STATUS_UP;
> +
> + VMW_CFPRN("Permanent MAC: " MAC_FMT, MAC_ARG(s->perm_mac.a));
> +
> + s->nic = qemu_new_nic(&net_vmxnet3_info, &s->conf,
> + object_get_typename(OBJECT(s)),
> + s->dev.qdev.id, s);
> +
> + s->peer_has_vhdr = vmxnet3_peer_has_vnet_hdr(s);
> + s->tx_sop = true;
> + s->skip_current_tx_pkt = false;
> + s->tx_pkt = NULL;
> + s->rx_pkt = NULL;
> + s->rx_vlan_stripping = false;
> + s->lro_supported = false;
> +
> + if (s->peer_has_vhdr) {
> + tap_set_vnet_hdr_len(s->nic->nc.peer, sizeof(struct virtio_net_hdr));
> + tap_using_vnet_hdr(s->nic->nc.peer, 1);
> + }
> +
> + qemu_format_nic_info_str(&s->nic->nc, s->conf.macaddr.a);
> +}
> +
> +static void
> +vmxnet3_unuse_msix_vectors(VMXNET3State *s, int num_vectors)
> +{
> + int i;
> + for (i = 0; i < num_vectors; i++) {
> + msix_vector_unuse(&s->dev, i);
> + }
> +}
> +
> +static bool
> +vmxnet3_use_msix_vectors(VMXNET3State *s, int num_vectors)
> +{
> + int i;
> + for (i = 0; i < num_vectors; i++) {
> + int res = msix_vector_use(&s->dev, i);
> + if (0 > res) {
> + VMW_WRPRN("Failed to use MSI-X vector %d, error %d", i, res);
> + vmxnet3_unuse_msix_vectors(s, i);
> + return false;
> + }
> + }
> + return true;
> +}
> +
> +static bool
> +vmxnet3_init_msix(VMXNET3State *s)
> +{
> + int res = msix_init(&s->dev, VMXNET3_MAX_INTRS,
> + &s->msix_bar,
> + VMXNET3_MSIX_BAR_IDX, VMXNET3_OFF_MSIX_TABLE,
> + &s->msix_bar,
> + VMXNET3_MSIX_BAR_IDX, VMXNET3_OFF_MSIX_PBA,
> + 0);
> +
> + if (0 > res) {
> + VMW_WRPRN("Failed to initialize MSI-X, error %d", res);
> + s->msix_used = false;
> + } else {
> + if (!vmxnet3_use_msix_vectors(s, VMXNET3_MAX_INTRS)) {
> + VMW_WRPRN("Failed to use MSI-X vectors, error %d", res);
> + msix_uninit(&s->dev, &s->msix_bar, &s->msix_bar);
> + s->msix_used = false;
> + } else {
> + s->msix_used = true;
> + }
> + }
> + return s->msix_used;
> +}
> +
> +static void
> +vmxnet3_cleanup_msix(VMXNET3State *s)
> +{
> + if (s->msix_used) {
> + msix_vector_unuse(&s->dev, VMXNET3_MAX_INTRS);
> + msix_uninit(&s->dev, &s->msix_bar, &s->msix_bar);
> + }
> +}
> +
> +static bool
> +vmxnet3_init_msi(VMXNET3State *s)
> +{
> +#define VMXNET3_MSI_NUM_VECTORS (1)
> +#define VMXNET3_MSI_OFFSET (0x50)
> +#define VMXNET3_USE_64BIT (true)
> +#define VMXNET3_PER_VECTOR_MASK (false)
> +
> + int res;
> + res = msi_init(&s->dev, VMXNET3_MSI_OFFSET, VMXNET3_MSI_NUM_VECTORS,
> + VMXNET3_USE_64BIT, VMXNET3_PER_VECTOR_MASK);
> + if (0 > res) {
> + VMW_WRPRN("Failed to initialize MSI, error %d", res);
> + s->msi_used = false;
> + } else {
> + s->msi_used = true;
> + }
> +
> + return s->msi_used;
> +}
> +
> +static void
> +vmxnet3_cleanup_msi(VMXNET3State *s)
> +{
> + if (s->msi_used) {
> + msi_uninit(&s->dev);
> + }
> +}
> +
> +static void
> +vmxnet3_msix_save(QEMUFile *f, void *opaque)
> +{
> + msix_save(&((VMXNET3State *)opaque)->dev, f);
> +}
> +
> +static int
> +vmxnet3_msix_load(QEMUFile *f, void *opaque, int version_id)
> +{
> + msix_load(&((VMXNET3State *)opaque)->dev, f);
> + return 0;
> +}
> +
> +static int vmxnet3_pci_init(PCIDevice *dev)
> +{
> + static const MemoryRegionOps b0_ops = {
> + .read = vmxnet3_io_bar0_read,
> + .write = vmxnet3_io_bar0_write,
> + .endianness = DEVICE_LITTLE_ENDIAN,
> + .impl = {
> + .min_access_size = 4,
> + .max_access_size = 4,
> + },
> + };
> +
> + static const MemoryRegionOps b1_ops = {
> + .read = vmxnet3_io_bar1_read,
> + .write = vmxnet3_io_bar1_write,
> + .endianness = DEVICE_LITTLE_ENDIAN,
> + .impl = {
> + .min_access_size = 4,
> + .max_access_size = 4,
> + },
> + };
> +
> + VMXNET3State *s = DO_UPCAST(VMXNET3State, dev, dev);
> + int i;
> +
> + VMW_CBPRN("Starting init...");
> +
> + memory_region_init_io(&s->bar0, &b0_ops, s,
> + "vmxnet3-b0", VMXNET3_PT_REG_SIZE);
> + pci_register_bar(&s->dev, VMXNET3_BAR0_IDX,
> + PCI_BASE_ADDRESS_SPACE_MEMORY, &s->bar0);
> +
> + memory_region_init_io(&s->bar1, &b1_ops, s,
> + "vmxnet3-b1", VMXNET3_VD_REG_SIZE);
> + pci_register_bar(&s->dev, VMXNET3_BAR1_IDX,
> + PCI_BASE_ADDRESS_SPACE_MEMORY, &s->bar1);
> +
> + memory_region_init(&s->msix_bar, "vmxnet3-msix-bar",
> + VMXNET3_MSIX_BAR_SIZE);
> + pci_register_bar(&s->dev, VMXNET3_MSIX_BAR_IDX,
> + PCI_BASE_ADDRESS_SPACE_MEMORY, &s->msix_bar);
> +
> + for (i = 0; i < ARRAY_SIZE(s->interrupt_states); i++) {
> + s->interrupt_states[i].is_asserted = false;
> + s->interrupt_states[i].is_pending = false;
> + s->interrupt_states[i].is_masked = true;
> + }
> +
> + /* Interrupt pin A */
> + s->dev.config[PCI_INTERRUPT_PIN] = 0x01;
> +
> + if (!vmxnet3_init_msix(s)) {
> + VMW_WRPRN("Failed to initialize MSI-X, configuration is
> inconsistent.");
> + }
> +
> + if (!vmxnet3_init_msi(s)) {
> + VMW_WRPRN("Failed to initialize MSI, configuration is
> inconsistent.");
> + }
> +
> + vmxnet3_net_init(s);
> +
> + register_savevm(&dev->qdev, "vmxnet3-msix", -1, 1,
> + vmxnet3_msix_save, vmxnet3_msix_load, s);
> +
> + add_boot_device_path(s->conf.bootindex, &dev->qdev, "/address@hidden");
> +
> + return 0;
> +}
> +
> +
> +static void vmxnet3_pci_uninit(PCIDevice *dev)
> +{
> + VMXNET3State *s = DO_UPCAST(VMXNET3State, dev, dev);
> +
> + VMW_CBPRN("Starting uninit...");
> +
> + unregister_savevm(&dev->qdev, "vmxnet3-msix", s);
> +
> + vmxnet3_net_uninit(s);
> +
> + vmxnet3_cleanup_msix(s);
> +
> + vmxnet3_cleanup_msi(s);
> +
> + memory_region_destroy(&s->bar0);
> + memory_region_destroy(&s->bar1);
> + memory_region_destroy(&s->msix_bar);
> +}
> +
> +static void vmxnet3_qdev_reset(DeviceState *dev)
> +{
> + VMXNET3State *s = DO_UPCAST(VMXNET3State, dev.qdev, dev);
> + VMW_CBPRN("Starting QDEV reset...");
> + vmxnet3_reset(s);
> +}
> +
> +static bool vmxnet3_mc_list_needed(void *opaque)
> +{
> + return true;
> +}
> +
> +static int vmxnet3_mcast_list_pre_load(void *opaque)
> +{
> + VMXNET3State *s = opaque;
> +
> + s->mcast_list = g_malloc(s->mcast_list_buff_size);
> +
> + return 0;
> +}
> +
> +
> +static void vmxnet3_pre_save(void *opaque)
> +{
> + VMXNET3State *s = opaque;
> +
> + s->mcast_list_buff_size = s->mcast_list_len * sizeof(MACAddr);
> +}
> +
> +static const VMStateDescription vmxtate_vmxnet3_mcast_list = {
> + .name = "vmxnet3/mcast_list",
> + .version_id = 1,
> + .minimum_version_id = 1,
> + .minimum_version_id_old = 1,
> + .pre_load = vmxnet3_mcast_list_pre_load,
> + .fields = (VMStateField[]) {
> + VMSTATE_VBUFFER_UINT32(mcast_list, VMXNET3State, 0, NULL, 0,
> + mcast_list_buff_size),
> + VMSTATE_END_OF_LIST()
> + }
> +};
> +
> +static void vmxnet3_get_ring_from_file(QEMUFile *f, Vmxnet3Ring *r)
> +{
> +#if HWADDR_BITS == 64
> + r->pa = qemu_get_be64(f);
> +#else
> + r->pa = qemu_get_be32(f);
> +#endif
> + r->size = qemu_get_be32(f);
> + r->cell_size = qemu_get_be32(f);
> + r->next = qemu_get_be32(f);
> + r->gen = qemu_get_byte(f);
> +}
> +
> +static void vmxnet3_put_ring_to_file(QEMUFile *f, Vmxnet3Ring *r)
> +{
> +#if HWADDR_BITS == 64
> + qemu_put_be64(f, r->pa);
> +#else
> + qemu_put_be32(f, r->pa);
> +#endif
> + qemu_put_be32(f, r->size);
> + qemu_put_be32(f, r->cell_size);
> + qemu_put_be32(f, r->next);
> + qemu_put_byte(f, r->gen);
> +}
> +
> +static void vmxnet3_get_tx_stats_from_file(QEMUFile *f,
> + struct UPT1_TxStats *tx_stat)
> +{
> + tx_stat->TSOPktsTxOK = qemu_get_be64(f);
> + tx_stat->TSOBytesTxOK = qemu_get_be64(f);
> + tx_stat->ucastPktsTxOK = qemu_get_be64(f);
> + tx_stat->ucastBytesTxOK = qemu_get_be64(f);
> + tx_stat->mcastPktsTxOK = qemu_get_be64(f);
> + tx_stat->mcastBytesTxOK = qemu_get_be64(f);
> + tx_stat->bcastPktsTxOK = qemu_get_be64(f);
> + tx_stat->bcastBytesTxOK = qemu_get_be64(f);
> + tx_stat->pktsTxError = qemu_get_be64(f);
> + tx_stat->pktsTxDiscard = qemu_get_be64(f);
> +}
> +
> +static void vmxnet3_put_tx_stats_to_file(QEMUFile *f,
> + struct UPT1_TxStats *tx_stat)
> +{
> + qemu_put_be64(f, tx_stat->TSOPktsTxOK);
> + qemu_put_be64(f, tx_stat->TSOBytesTxOK);
> + qemu_put_be64(f, tx_stat->ucastPktsTxOK);
> + qemu_put_be64(f, tx_stat->ucastBytesTxOK);
> + qemu_put_be64(f, tx_stat->mcastPktsTxOK);
> + qemu_put_be64(f, tx_stat->mcastBytesTxOK);
> + qemu_put_be64(f, tx_stat->bcastPktsTxOK);
> + qemu_put_be64(f, tx_stat->bcastBytesTxOK);
> + qemu_put_be64(f, tx_stat->pktsTxError);
> + qemu_put_be64(f, tx_stat->pktsTxDiscard);
> +}
> +
> +static int vmxnet3_get_txq_descr(QEMUFile *f, void *pv, size_t size)
> +{
> + Vmxnet3TxqDescr *r = pv;
> +
> + vmxnet3_get_ring_from_file(f, &r->tx_ring);
> + vmxnet3_get_ring_from_file(f, &r->comp_ring);
> + r->intr_idx = qemu_get_byte(f);
> +
> +#if HWADDR_BITS == 64
> + r->tx_stats_pa = qemu_get_be64(f);
> +#else
> + r->tx_stats_pa = qemu_get_be32(f);
> +#endif
> +
> + vmxnet3_get_tx_stats_from_file(f, &r->txq_stats);
> +
> + return 0;
> +}
> +
> +static void vmxnet3_put_txq_descr(QEMUFile *f, void *pv, size_t size)
> +{
> + Vmxnet3TxqDescr *r = pv;
> +
> + vmxnet3_put_ring_to_file(f, &r->tx_ring);
> + vmxnet3_put_ring_to_file(f, &r->comp_ring);
> + qemu_put_byte(f, r->intr_idx);
> +#if HWADDR_BITS == 64
> + qemu_put_be64(f, r->tx_stats_pa);
> +#else
> + qemu_put_be32(f, r->tx_stats_pa);
> +#endif
> + vmxnet3_put_tx_stats_to_file(f, &r->txq_stats);
> +}
> +
> +const VMStateInfo txq_descr_info = {
> + .name = "txq_descr",
> + .get = vmxnet3_get_txq_descr,
> + .put = vmxnet3_put_txq_descr
> +};
> +
> +static void vmxnet3_get_rx_stats_from_file(QEMUFile *f,
> + struct UPT1_RxStats *rx_stat)
> +{
> + rx_stat->LROPktsRxOK = qemu_get_be64(f);
> + rx_stat->LROBytesRxOK = qemu_get_be64(f);
> + rx_stat->ucastPktsRxOK = qemu_get_be64(f);
> + rx_stat->ucastBytesRxOK = qemu_get_be64(f);
> + rx_stat->mcastPktsRxOK = qemu_get_be64(f);
> + rx_stat->mcastBytesRxOK = qemu_get_be64(f);
> + rx_stat->bcastPktsRxOK = qemu_get_be64(f);
> + rx_stat->bcastBytesRxOK = qemu_get_be64(f);
> + rx_stat->pktsRxOutOfBuf = qemu_get_be64(f);
> + rx_stat->pktsRxError = qemu_get_be64(f);
> +}
> +
> +static void vmxnet3_put_rx_stats_to_file(QEMUFile *f,
> + struct UPT1_RxStats *rx_stat)
> +{
> + qemu_put_be64(f, rx_stat->LROPktsRxOK);
> + qemu_put_be64(f, rx_stat->LROBytesRxOK);
> + qemu_put_be64(f, rx_stat->ucastPktsRxOK);
> + qemu_put_be64(f, rx_stat->ucastBytesRxOK);
> + qemu_put_be64(f, rx_stat->mcastPktsRxOK);
> + qemu_put_be64(f, rx_stat->mcastBytesRxOK);
> + qemu_put_be64(f, rx_stat->bcastPktsRxOK);
> + qemu_put_be64(f, rx_stat->bcastBytesRxOK);
> + qemu_put_be64(f, rx_stat->pktsRxOutOfBuf);
> + qemu_put_be64(f, rx_stat->pktsRxError);
> +}
> +
> +static int vmxnet3_get_rxq_descr(QEMUFile *f, void *pv, size_t size)
> +{
> + Vmxnet3RxqDescr *r = pv;
> + int i;
> +
> + for (i = 0; i < VMXNET3_RX_RINGS_PER_QUEUE; i++) {
> + vmxnet3_get_ring_from_file(f, &r->rx_ring[i]);
> + }
> +
> + vmxnet3_get_ring_from_file(f, &r->comp_ring);
> + r->intr_idx = qemu_get_byte(f);
> +#if HWADDR_BITS == 64
> + r->rx_stats_pa = qemu_get_be64(f);
> +#else
> + r->rx_stats_pa = qemu_get_be32(f);
> +#endif
> +
> + vmxnet3_get_rx_stats_from_file(f, &r->rxq_stats);
> +
> + return 0;
> +}
> +
> +static void vmxnet3_put_rxq_descr(QEMUFile *f, void *pv, size_t size)
> +{
> + Vmxnet3RxqDescr *r = pv;
> + int i;
> +
> + for (i = 0; i < VMXNET3_RX_RINGS_PER_QUEUE; i++) {
> + vmxnet3_put_ring_to_file(f, &r->rx_ring[i]);
> + }
> +
> + vmxnet3_put_ring_to_file(f, &r->comp_ring);
> + qemu_put_byte(f, r->intr_idx);
> +#if HWADDR_BITS == 64
> + qemu_put_be64(f, r->rx_stats_pa);
> +#else
> + qemu_put_be32(f, r->rx_stats_pa);
> +#endif
> + vmxnet3_put_rx_stats_to_file(f, &r->rxq_stats);
> +}
> +
> +static int vmxnet3_post_load(void *opaque, int version_id)
> +{
> + VMXNET3State *s = opaque;
> +
> + vmxnet_tx_pkt_init(&s->tx_pkt, s->max_tx_frags, s->peer_has_vhdr);
> + vmxnet_rx_pkt_init(&s->rx_pkt, s->peer_has_vhdr);
> +
> + if (s->msix_used) {
> + if (!vmxnet3_use_msix_vectors(s, VMXNET3_MAX_INTRS)) {
> + VMW_WRPRN("Failed to re-use MSI-X vectors");
> + msix_uninit(&s->dev, &s->msix_bar, &s->msix_bar);
> + s->msix_used = false;
> + return -1;
> + }
> + }
> +
> + return 0;
> +}
> +
> +const VMStateInfo rxq_descr_info = {
> + .name = "rxq_descr",
> + .get = vmxnet3_get_rxq_descr,
> + .put = vmxnet3_put_rxq_descr
> +};
> +
> +static int vmxnet3_get_int_state(QEMUFile *f, void *pv, size_t size)
> +{
> + Vmxnet3IntState *r = pv;
> +
> + r->is_masked = qemu_get_byte(f);
> + r->is_pending = qemu_get_byte(f);
> + r->is_asserted = qemu_get_byte(f);
> +
> + return 0;
> +}
> +
> +static void vmxnet3_put_int_state(QEMUFile *f, void *pv, size_t size)
> +{
> + Vmxnet3IntState *r = pv;
> +
> + qemu_put_byte(f, r->is_masked);
> + qemu_put_byte(f, r->is_pending);
> + qemu_put_byte(f, r->is_asserted);
> +}
> +
> +const VMStateInfo int_state_info = {
> + .name = "int_state",
> + .get = vmxnet3_get_int_state,
> + .put = vmxnet3_put_int_state
> +};
> +
> +static const VMStateDescription vmstate_vmxnet3 = {
> + .name = "vmxnet3",
> + .version_id = 1,
> + .minimum_version_id = 1,
> + .minimum_version_id_old = 1,
> + .pre_save = vmxnet3_pre_save,
> + .post_load = vmxnet3_post_load,
> + .fields = (VMStateField[]) {
> + VMSTATE_PCI_DEVICE(dev, VMXNET3State),
> + VMSTATE_BOOL(rx_packets_compound, VMXNET3State),
> + VMSTATE_BOOL(rx_vlan_stripping, VMXNET3State),
> + VMSTATE_BOOL(lro_supported, VMXNET3State),
> + VMSTATE_UINT32(rx_mode, VMXNET3State),
> + VMSTATE_UINT32(mcast_list_len, VMXNET3State),
> + VMSTATE_UINT32(mcast_list_buff_size, VMXNET3State),
> + VMSTATE_UINT32_ARRAY(vlan_table, VMXNET3State, VMXNET3_VFT_SIZE),
> + VMSTATE_UINT32(mtu, VMXNET3State),
> + VMSTATE_UINT16(max_rx_frags, VMXNET3State),
> + VMSTATE_UINT32(max_tx_frags, VMXNET3State),
> + VMSTATE_UINT8(event_int_idx, VMXNET3State),
> + VMSTATE_BOOL(auto_int_masking, VMXNET3State),
> + VMSTATE_UINT8(txq_num, VMXNET3State),
> + VMSTATE_UINT8(rxq_num, VMXNET3State),
> + VMSTATE_UINT32(device_active, VMXNET3State),
> + VMSTATE_UINT32(last_command, VMXNET3State),
> + VMSTATE_UINT32(link_status_and_speed, VMXNET3State),
> + VMSTATE_UINT32(temp_mac, VMXNET3State),
> +#if HWADDR_BITS == 64
> + VMSTATE_UINT64(drv_shmem, VMXNET3State),
> + VMSTATE_UINT64(temp_shared_guest_driver_memory, VMXNET3State),
> +#else
> + VMSTATE_UINT32(drv_shmem, VMXNET3State),
> + VMSTATE_UINT32(temp_shared_guest_driver_memory, VMXNET3State),
> +#endif
> +
> + VMSTATE_ARRAY(txq_descr, VMXNET3State,
> + VMXNET3_DEVICE_MAX_TX_QUEUES, 0, txq_descr_info,
> + Vmxnet3TxqDescr),
> + VMSTATE_ARRAY(rxq_descr, VMXNET3State,
> + VMXNET3_DEVICE_MAX_RX_QUEUES, 0, rxq_descr_info,
> + Vmxnet3RxqDescr),
> + VMSTATE_ARRAY(interrupt_states, VMXNET3State, VMXNET3_MAX_INTRS,
> + 0, int_state_info, Vmxnet3IntState),
> +
> + VMSTATE_END_OF_LIST()
> + },
> + .subsections = (VMStateSubsection[]) {
> + {
> + .vmsd = &vmxtate_vmxnet3_mcast_list,
> + .needed = vmxnet3_mc_list_needed
> + },
> + {
> + /* empty element. */
> + }
> + }
> +};
> +
> +static void
> +vmxnet3_write_config(PCIDevice *pci, uint32_t addr, uint32_t val, int len)
> +{
> + pci_default_write_config(pci, addr, val, len);
> + msix_write_config(pci, addr, val, len);
> + msi_write_config(pci, addr, val, len);
> +}
> +
> +static Property vmxnet3_properties[] = {
> + DEFINE_NIC_PROPERTIES(VMXNET3State, conf),
> + DEFINE_PROP_END_OF_LIST(),
> +};
> +
> +static void vmxnet3_class_init(ObjectClass *class, void *data)
> +{
> + DeviceClass *dc = DEVICE_CLASS(class);
> + PCIDeviceClass *c = PCI_DEVICE_CLASS(class);
> +
> + c->init = vmxnet3_pci_init;
> + c->exit = vmxnet3_pci_uninit;
> + c->vendor_id = PCI_VENDOR_ID_VMWARE;
> + c->device_id = PCI_DEVICE_ID_VMWARE_VMXNET3;
> + c->revision = PCI_DEVICE_ID_VMWARE_VMXNET3_REVISION;
> + c->class_id = PCI_CLASS_NETWORK_ETHERNET;
> + c->subsystem_vendor_id = PCI_VENDOR_ID_VMWARE;
> + c->subsystem_id = PCI_DEVICE_ID_VMWARE_VMXNET3;
> + c->config_write = vmxnet3_write_config,
> + dc->desc = "VMWare Paravirtualized Ethernet v3";
> + dc->reset = vmxnet3_qdev_reset;
> + dc->vmsd = &vmstate_vmxnet3;
> + dc->props = vmxnet3_properties;
> +}
> +
> +static TypeInfo vmxnet3_info = {
> + .name = "vmxnet3",
> + .parent = TYPE_PCI_DEVICE,
> + .instance_size = sizeof(VMXNET3State),
> + .class_init = vmxnet3_class_init,
> +};
> +
> +static void vmxnet3_register_types(void)
> +{
> + VMW_CBPRN("vmxnet3_register_types called...");
> + type_register_static(&vmxnet3_info);
> +}
> +
> +type_init(vmxnet3_register_types)
> diff --git a/hw/vmxnet3.h b/hw/vmxnet3.h
> new file mode 100644
> index 0000000..b6089ba
> --- /dev/null
> +++ b/hw/vmxnet3.h
> @@ -0,0 +1,762 @@
> +/*
> + * QEMU VMWARE VMXNET3 paravirtual NIC
> + *
> + * Copyright (c) 2012 Ravello Systems LTD (http://ravellosystems.com)
> + *
> + * Developed by Daynix Computing LTD (http://www.daynix.com)
> + *
> + * Authors:
> + * Dmitry Fleytman <address@hidden>
> + * Tamir Shomer <address@hidden>
> + * Yan Vugenfirer <address@hidden>
> + *
> + * This work is licensed under the terms of the GNU GPL, version 2 or later.
> + * See the COPYING file in the top-level directory.
> + *
> + */
> +
> +#ifndef _QEMU_VMXNET3_H
> +#define _QEMU_VMXNET3_H
> +
> +#define VMXNET_VERSION_3
> +
> +#define VMXNET3_DEVICE_MAX_TX_QUEUES 8
> +#define VMXNET3_DEVICE_MAX_RX_QUEUES 8 /* Keep this value as a power of 2
> */
> +
> +/*
> + * VMWARE headers we got from Linux kernel do not fully comply QEMU coding
> + * standards in sense of types and defines used.
> + * Since we didn't want to change VMWARE code, following set of typedefs
> + * and defines needed to compile these headers with QEMU introduced.
> + */
> +#define u64 uint64_t
> +#define u32 uint32_t
> +#define u16 uint16_t
> +#define u8 uint8_t
> +#define __le16 uint16_t
> +#define __le32 uint32_t
> +#define __le64 uint64_t
> +#define __packed QEMU_PACKED
> +
> +#if defined(HOST_WORDS_BIGENDIAN)
> +#define const_cpu_to_le64(x) bswap_64(x)
This breaks compilation on ppc.
Why the hell are you byte swapping enum values? The read function you use to
fetch shared register values already swaps bytes for you. And what happened to
code quality standards in QEMU? My eyes are really getting sore looking at this
code...
Alex
| [Prev in Thread] |
Current Thread |
[Next in Thread] |
- Re: [Qemu-devel] [PATCH V8 5/5] Adding VMXNET3 device implementation,
Alexander Graf <=