Merge tag 'mem-2023-05-23' of https://github.com/davidhildenbrand/qemu into staging
Hi,
"Host Memory Backends" and "Memory devices" queue ("mem"):
- New "offset" option for memory-backend-file
# -----BEGIN PGP SIGNATURE-----
#
# iQJFBAABCAAvFiEEG9nKrXNcTDpGDfzKTd4Q9wD/g1oFAmRs0h4RHGRhdmlkQHJl
# ZGhhdC5jb20ACgkQTd4Q9wD/g1r+9BAAsOtioPE3y1xBNyLhO+sbBK4w0Xf5ABRF
# QXfrSPfz0IaThzg33o7eCUMrbC5UmRyeq1aeGWFNo1RevgKxeFFlcVdvUFDeJL5R
# vS94ZzowpJ6lJvpgP8iOMmWY2nztWpIfE92nLKIeze5nlbnMwKn8ZlVWkqFialkT
# Ro1AI/ZmyvUDJj8UXQEW+p1NWE4m59TH5atQqBG3kkU7RJTU4DKVQtKbOysEwIhr
# A4y0nvgMeHLlEPUSqcERe9wOqVENdlsON6vms5AILN4/TmjSe3BHINjH9NOFveiO
# wgquSt0ystPAY0MXRPXgg6XwL1AAFR9cJt/rOZiBYpqeZHAmKOsi5qUXyv2dmXhw
# RaPV041g2RJZiFgH1N4v4aN0j8AYbtHSYYsP1snfULa8VfePPquY/UxyPaK28WHn
# on5VV5nBScYNVtKI90Gci4jxGStnM0zG503GQ26pt85+35866zertBqsTTPIO2Mm
# 7+YSkedSzmIt11GH0rqdghQte6qj1ED8lGO626s5m+qbGL9WuBXYCG9yzl5yTLsz
# I27si7Fh/Y0QQHs3GEAH2tsi89tphElnZksdj4P1/uPDIDnTF7d5I+tlUiQXHNaw
# rXAV76q4j0GgbBm4Cp1iMTUNxALes4aOG7oRMeFxvVWy0fqmfAvKhDVILGkUlYTr
# C82GUJ5x3mc=
# =izHP
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 23 May 2023 07:47:58 AM PDT
# gpg: using RSA key 1BD9CAAD735C4C3A460DFCCA4DDE10F700FF835A
# gpg: issuer "david@redhat.com"
# gpg: Good signature from "David Hildenbrand <david@redhat.com>" [unknown]
# gpg: aka "David Hildenbrand <davidhildenbrand@gmail.com>" [undefined]
# gpg: aka "David Hildenbrand <hildenbr@in.tum.de>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg: There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 1BD9 CAAD 735C 4C3A 460D FCCA 4DDE 10F7 00FF 835A
* tag 'mem-2023-05-23' of https://github.com/davidhildenbrand/qemu:
hostmem-file: add offset option
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
diff --git a/MAINTAINERS b/MAINTAINERS
index 1b64664..6addabd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2237,6 +2237,7 @@
Network packet abstractions
M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
+R: Akihiko Odaki <akihiko.odaki@daynix.com>
S: Maintained
F: include/net/eth.h
F: net/eth.c
@@ -2279,7 +2280,7 @@
S: Maintained
F: docs/system/devices/igb.rst
F: hw/net/igb*
-F: tests/avocado/igb.py
+F: tests/avocado/netdev-ethtool.py
F: tests/qtest/igb-test.c
F: tests/qtest/libqos/igb.c
diff --git a/docs/system/devices/igb.rst b/docs/system/devices/igb.rst
index 0bcdd85..04e79df 100644
--- a/docs/system/devices/igb.rst
+++ b/docs/system/devices/igb.rst
@@ -14,7 +14,8 @@
===========
This igb implementation was tested with Linux Test Project [2]_ and Windows HLK
-[3]_ during the initial development. The command used when testing with LTP is:
+[3]_ during the initial development. Later it was also tested with DPDK Test
+Suite [4]_. The command used when testing with LTP is:
.. code-block:: shell
@@ -22,8 +23,8 @@
Be aware that this implementation lacks many functionalities available with the
actual hardware, and you may experience various failures if you try to use it
-with a different operating system other than Linux and Windows or if you try
-functionalities not covered by the tests.
+with a different operating system other than DPDK, Linux, and Windows or if you
+try functionalities not covered by the tests.
Using igb
=========
@@ -32,7 +33,7 @@
:ref:`Network_emulation` in general.
However, you may also need to perform additional steps to activate SR-IOV
-feature on your guest. For Linux, refer to [4]_.
+feature on your guest. For Linux, refer to [5]_.
Developing igb
==============
@@ -60,7 +61,7 @@
.. code:: shell
- make check-avocado AVOCADO_TESTS=tests/avocado/igb.py
+ make check-avocado AVOCADO_TESTS=tests/avocado/netdev-ethtool.py
References
==========
@@ -68,4 +69,5 @@
.. [1] https://www.intel.com/content/dam/www/public/us/en/documents/datasheets/82576eb-gigabit-ethernet-controller-datasheet.pdf
.. [2] https://github.com/linux-test-project/ltp
.. [3] https://learn.microsoft.com/en-us/windows-hardware/test/hlk/
-.. [4] https://docs.kernel.org/PCI/pci-iov-howto.html
+.. [4] https://doc.dpdk.org/dts/gsg/
+.. [5] https://docs.kernel.org/PCI/pci-iov-howto.html
diff --git a/hw/net/Kconfig b/hw/net/Kconfig
index 18c7851..98e00be 100644
--- a/hw/net/Kconfig
+++ b/hw/net/Kconfig
@@ -56,7 +56,7 @@
config VMXNET3_PCI
bool
- default y if PCI_DEVICES && PC_PCI
+ default y if PCI_DEVICES
depends on PCI
config SMC91C111
diff --git a/hw/net/e1000.c b/hw/net/e1000.c
index 23d6606..aae5f0b 100644
--- a/hw/net/e1000.c
+++ b/hw/net/e1000.c
@@ -637,9 +637,8 @@
e1000x_inc_reg_if_not_full(s->mac_reg, TPT);
e1000x_grow_8reg_if_not_full(s->mac_reg, TOTL, s->tx.size + 4);
- s->mac_reg[GPTC] = s->mac_reg[TPT];
- s->mac_reg[GOTCL] = s->mac_reg[TOTL];
- s->mac_reg[GOTCH] = s->mac_reg[TOTH];
+ e1000x_inc_reg_if_not_full(s->mac_reg, GPTC);
+ e1000x_grow_8reg_if_not_full(s->mac_reg, GOTCL, s->tx.size + 4);
}
static void
@@ -805,38 +804,11 @@
}
static int
-receive_filter(E1000State *s, const uint8_t *buf, int size)
+receive_filter(E1000State *s, const void *buf)
{
- uint32_t rctl = s->mac_reg[RCTL];
- int isbcast = is_broadcast_ether_addr(buf);
- int ismcast = is_multicast_ether_addr(buf);
-
- if (e1000x_is_vlan_packet(buf, le16_to_cpu(s->mac_reg[VET])) &&
- e1000x_vlan_rx_filter_enabled(s->mac_reg)) {
- uint16_t vid = lduw_be_p(&PKT_GET_VLAN_HDR(buf)->h_tci);
- uint32_t vfta =
- ldl_le_p((uint32_t *)(s->mac_reg + VFTA) +
- ((vid >> E1000_VFTA_ENTRY_SHIFT) & E1000_VFTA_ENTRY_MASK));
- if ((vfta & (1 << (vid & E1000_VFTA_ENTRY_BIT_SHIFT_MASK))) == 0) {
- return 0;
- }
- }
-
- if (!isbcast && !ismcast && (rctl & E1000_RCTL_UPE)) { /* promiscuous ucast */
- return 1;
- }
-
- if (ismcast && (rctl & E1000_RCTL_MPE)) { /* promiscuous mcast */
- e1000x_inc_reg_if_not_full(s->mac_reg, MPRC);
- return 1;
- }
-
- if (isbcast && (rctl & E1000_RCTL_BAM)) { /* broadcast enabled */
- e1000x_inc_reg_if_not_full(s->mac_reg, BPRC);
- return 1;
- }
-
- return e1000x_rx_group_filter(s->mac_reg, buf);
+ return (!e1000x_is_vlan_packet(buf, s->mac_reg[VET]) ||
+ e1000x_rx_vlan_filter(s->mac_reg, PKT_GET_VLAN_HDR(buf))) &&
+ e1000x_rx_group_filter(s->mac_reg, buf);
}
static void
@@ -923,6 +895,7 @@
size_t desc_offset;
size_t desc_size;
size_t total_size;
+ eth_pkt_types_e pkt_type;
if (!e1000x_hw_rx_enabled(s->mac_reg)) {
return -1;
@@ -951,7 +924,7 @@
return size;
}
- if (!receive_filter(s, filter_buf, size)) {
+ if (!receive_filter(s, filter_buf)) {
return size;
}
@@ -972,6 +945,7 @@
size -= 4;
}
+ pkt_type = get_eth_packet_type(PKT_GET_ETH_HDR(filter_buf));
rdh_start = s->mac_reg[RDH];
desc_offset = 0;
total_size = size + e1000x_fcs_len(s->mac_reg);
@@ -1037,7 +1011,7 @@
}
} while (desc_offset < total_size);
- e1000x_update_rx_total_stats(s->mac_reg, size, total_size);
+ e1000x_update_rx_total_stats(s->mac_reg, pkt_type, size, total_size);
n = E1000_ICS_RXT0;
if ((rdt = s->mac_reg[RDT]) < s->mac_reg[RDH])
diff --git a/hw/net/e1000e_core.c b/hw/net/e1000e_core.c
index c0c09b6..9f185d0 100644
--- a/hw/net/e1000e_core.c
+++ b/hw/net/e1000e_core.c
@@ -165,14 +165,14 @@
timer->running = false;
- if (msi_enabled(timer->core->owner)) {
- trace_e1000e_irq_msi_notify_postponed();
- /* Clear msi_causes_pending to fire MSI eventually */
- timer->core->msi_causes_pending = 0;
- e1000e_set_interrupt_cause(timer->core, 0);
- } else {
- trace_e1000e_irq_legacy_notify_postponed();
- e1000e_set_interrupt_cause(timer->core, 0);
+ if (timer->core->mac[IMS] & timer->core->mac[ICR]) {
+ if (msi_enabled(timer->core->owner)) {
+ trace_e1000e_irq_msi_notify_postponed();
+ msi_notify(timer->core->owner, 0);
+ } else {
+ trace_e1000e_irq_legacy_notify_postponed();
+ e1000e_raise_legacy_irq(timer->core);
+ }
}
}
@@ -366,10 +366,6 @@
e1000e_intrmgr_fire_all_timers(E1000ECore *core)
{
int i;
- uint32_t val = e1000e_intmgr_collect_delayed_causes(core);
-
- trace_e1000e_irq_adding_delayed_causes(val, core->mac[ICR]);
- core->mac[ICR] |= val;
if (core->itr.running) {
timer_del(core->itr.timer);
@@ -537,7 +533,7 @@
ip6info->rss_ex_dst_valid,
ip6info->rss_ex_src_valid,
core->mac[MRQC],
- E1000_MRQC_EN_TCPIPV6(core->mac[MRQC]),
+ E1000_MRQC_EN_TCPIPV6EX(core->mac[MRQC]),
E1000_MRQC_EN_IPV6EX(core->mac[MRQC]),
E1000_MRQC_EN_IPV6(core->mac[MRQC]));
@@ -546,8 +542,8 @@
ip6info->rss_ex_src_valid))) {
if (l4hdr_proto == ETH_L4_HDR_PROTO_TCP &&
- E1000_MRQC_EN_TCPIPV6(core->mac[MRQC])) {
- return E1000_MRQ_RSS_TYPE_IPV6TCP;
+ E1000_MRQC_EN_TCPIPV6EX(core->mac[MRQC])) {
+ return E1000_MRQ_RSS_TYPE_IPV6TCPEX;
}
if (E1000_MRQC_EN_IPV6EX(core->mac[MRQC])) {
@@ -581,7 +577,7 @@
case E1000_MRQ_RSS_TYPE_IPV4TCP:
type = NetPktRssIpV4Tcp;
break;
- case E1000_MRQ_RSS_TYPE_IPV6TCP:
+ case E1000_MRQ_RSS_TYPE_IPV6TCPEX:
type = NetPktRssIpV6TcpEx;
break;
case E1000_MRQ_RSS_TYPE_IPV6:
@@ -711,9 +707,8 @@
g_assert_not_reached();
}
- core->mac[GPTC] = core->mac[TPT];
- core->mac[GOTCL] = core->mac[TOTL];
- core->mac[GOTCH] = core->mac[TOTH];
+ e1000x_inc_reg_if_not_full(core->mac, GPTC);
+ e1000x_grow_8reg_if_not_full(core->mac, GOTCL, tot_len);
}
static void
@@ -747,7 +742,8 @@
addr = le64_to_cpu(dp->buffer_addr);
if (!tx->skip_cp) {
- if (!net_tx_pkt_add_raw_fragment(tx->tx_pkt, addr, split_size)) {
+ if (!net_tx_pkt_add_raw_fragment_pci(tx->tx_pkt, core->owner,
+ addr, split_size)) {
tx->skip_cp = true;
}
}
@@ -765,7 +761,7 @@
}
tx->skip_cp = false;
- net_tx_pkt_reset(tx->tx_pkt, core->owner);
+ net_tx_pkt_reset(tx->tx_pkt, net_tx_pkt_unmap_frag_pci, core->owner);
tx->sum_needed = 0;
tx->cptse = 0;
@@ -959,6 +955,8 @@
if (!ide || !e1000e_intrmgr_delay_tx_causes(core, &cause)) {
e1000e_set_interrupt_cause(core, cause);
}
+
+ net_tx_pkt_reset(txr->tx->tx_pkt, net_tx_pkt_unmap_frag_pci, core->owner);
}
static bool
@@ -1034,48 +1032,11 @@
}
static bool
-e1000e_receive_filter(E1000ECore *core, const uint8_t *buf, int size)
+e1000e_receive_filter(E1000ECore *core, const void *buf)
{
- uint32_t rctl = core->mac[RCTL];
-
- if (e1000x_is_vlan_packet(buf, core->mac[VET]) &&
- e1000x_vlan_rx_filter_enabled(core->mac)) {
- uint16_t vid = lduw_be_p(&PKT_GET_VLAN_HDR(buf)->h_tci);
- uint32_t vfta =
- ldl_le_p((uint32_t *)(core->mac + VFTA) +
- ((vid >> E1000_VFTA_ENTRY_SHIFT) & E1000_VFTA_ENTRY_MASK));
- if ((vfta & (1 << (vid & E1000_VFTA_ENTRY_BIT_SHIFT_MASK))) == 0) {
- trace_e1000e_rx_flt_vlan_mismatch(vid);
- return false;
- } else {
- trace_e1000e_rx_flt_vlan_match(vid);
- }
- }
-
- switch (net_rx_pkt_get_packet_type(core->rx_pkt)) {
- case ETH_PKT_UCAST:
- if (rctl & E1000_RCTL_UPE) {
- return true; /* promiscuous ucast */
- }
- break;
-
- case ETH_PKT_BCAST:
- if (rctl & E1000_RCTL_BAM) {
- return true; /* broadcast enabled */
- }
- break;
-
- case ETH_PKT_MCAST:
- if (rctl & E1000_RCTL_MPE) {
- return true; /* promiscuous mcast */
- }
- break;
-
- default:
- g_assert_not_reached();
- }
-
- return e1000x_rx_group_filter(core->mac, buf);
+ return (!e1000x_is_vlan_packet(buf, core->mac[VET]) ||
+ e1000x_rx_vlan_filter(core->mac, PKT_GET_VLAN_HDR(buf))) &&
+ e1000x_rx_group_filter(core->mac, buf);
}
static inline void
@@ -1149,6 +1110,11 @@
return;
}
+ if (l4hdr_proto != ETH_L4_HDR_PROTO_TCP &&
+ l4hdr_proto != ETH_L4_HDR_PROTO_UDP) {
+ return;
+ }
+
if (!net_rx_pkt_validate_l4_csum(pkt, &csum_valid)) {
trace_e1000e_rx_metadata_l4_csum_validation_failed();
return;
@@ -1281,9 +1247,8 @@
trace_e1000e_rx_metadata_l4_cso_disabled();
}
- trace_e1000e_rx_metadata_status_flags(*status_flags);
-
func_exit:
+ trace_e1000e_rx_metadata_status_flags(*status_flags);
*status_flags = cpu_to_le32(*status_flags);
}
@@ -1488,24 +1453,10 @@
}
static void
-e1000e_update_rx_stats(E1000ECore *core,
- size_t data_size,
- size_t data_fcs_size)
+e1000e_update_rx_stats(E1000ECore *core, size_t pkt_size, size_t pkt_fcs_size)
{
- e1000x_update_rx_total_stats(core->mac, data_size, data_fcs_size);
-
- switch (net_rx_pkt_get_packet_type(core->rx_pkt)) {
- case ETH_PKT_BCAST:
- e1000x_inc_reg_if_not_full(core->mac, BPRC);
- break;
-
- case ETH_PKT_MCAST:
- e1000x_inc_reg_if_not_full(core->mac, MPRC);
- break;
-
- default:
- break;
- }
+ eth_pkt_types_e pkt_type = net_rx_pkt_get_packet_type(core->rx_pkt);
+ e1000x_update_rx_total_stats(core->mac, pkt_type, pkt_size, pkt_fcs_size);
}
static inline bool
@@ -1700,12 +1651,9 @@
e1000e_receive_internal(E1000ECore *core, const struct iovec *iov, int iovcnt,
bool has_vnet)
{
- static const int maximum_ethernet_hdr_len = (ETH_HLEN + 4);
-
- uint32_t n = 0;
- uint8_t min_buf[ETH_ZLEN];
+ uint32_t causes = 0;
+ uint8_t buf[ETH_ZLEN];
struct iovec min_iov;
- uint8_t *filter_buf;
size_t size, orig_size;
size_t iov_ofs = 0;
E1000E_RxRing rxr;
@@ -1728,24 +1676,21 @@
net_rx_pkt_unset_vhdr(core->rx_pkt);
}
- filter_buf = iov->iov_base + iov_ofs;
orig_size = iov_size(iov, iovcnt);
size = orig_size - iov_ofs;
/* Pad to minimum Ethernet frame length */
- if (size < sizeof(min_buf)) {
- iov_to_buf(iov, iovcnt, iov_ofs, min_buf, size);
- memset(&min_buf[size], 0, sizeof(min_buf) - size);
+ if (size < sizeof(buf)) {
+ iov_to_buf(iov, iovcnt, iov_ofs, buf, size);
+ memset(&buf[size], 0, sizeof(buf) - size);
e1000x_inc_reg_if_not_full(core->mac, RUC);
- min_iov.iov_base = filter_buf = min_buf;
- min_iov.iov_len = size = sizeof(min_buf);
+ min_iov.iov_base = buf;
+ min_iov.iov_len = size = sizeof(buf);
iovcnt = 1;
iov = &min_iov;
iov_ofs = 0;
- } else if (iov->iov_len < maximum_ethernet_hdr_len) {
- /* This is very unlikely, but may happen. */
- iov_to_buf(iov, iovcnt, iov_ofs, min_buf, maximum_ethernet_hdr_len);
- filter_buf = min_buf;
+ } else {
+ iov_to_buf(iov, iovcnt, iov_ofs, buf, ETH_HLEN + 4);
}
/* Discard oversized packets if !LPE and !SBP. */
@@ -1754,15 +1699,16 @@
}
net_rx_pkt_set_packet_type(core->rx_pkt,
- get_eth_packet_type(PKT_GET_ETH_HDR(filter_buf)));
+ get_eth_packet_type(PKT_GET_ETH_HDR(buf)));
- if (!e1000e_receive_filter(core, filter_buf, size)) {
+ if (!e1000e_receive_filter(core, buf)) {
trace_e1000e_rx_flt_dropped();
return orig_size;
}
net_rx_pkt_attach_iovec_ex(core->rx_pkt, iov, iovcnt, iov_ofs,
- e1000x_vlan_enabled(core->mac), core->mac[VET]);
+ e1000x_vlan_enabled(core->mac) ? 0 : -1,
+ core->mac[VET], 0);
e1000e_rss_parse_packet(core, core->rx_pkt, &rss_info);
e1000e_rx_ring_init(core, &rxr, rss_info.queue);
@@ -1779,32 +1725,32 @@
/* Perform small receive detection (RSRPD) */
if (total_size < core->mac[RSRPD]) {
- n |= E1000_ICS_SRPD;
+ causes |= E1000_ICS_SRPD;
}
/* Perform ACK receive detection */
if (!(core->mac[RFCTL] & E1000_RFCTL_ACK_DIS) &&
(e1000e_is_tcp_ack(core, core->rx_pkt))) {
- n |= E1000_ICS_ACK;
+ causes |= E1000_ICS_ACK;
}
/* Check if receive descriptor minimum threshold hit */
rdmts_hit = e1000e_rx_descr_threshold_hit(core, rxr.i);
- n |= e1000e_rx_wb_interrupt_cause(core, rxr.i->idx, rdmts_hit);
+ causes |= e1000e_rx_wb_interrupt_cause(core, rxr.i->idx, rdmts_hit);
trace_e1000e_rx_written_to_guest(rxr.i->idx);
} else {
- n |= E1000_ICS_RXO;
+ causes |= E1000_ICS_RXO;
retval = 0;
trace_e1000e_rx_not_written_to_guest(rxr.i->idx);
}
- if (!e1000e_intrmgr_delay_rx_causes(core, &n)) {
- trace_e1000e_rx_interrupt_set(n);
- e1000e_set_interrupt_cause(core, n);
+ if (!e1000e_intrmgr_delay_rx_causes(core, &causes)) {
+ trace_e1000e_rx_interrupt_set(causes);
+ e1000e_set_interrupt_cause(core, causes);
} else {
- trace_e1000e_rx_interrupt_delayed(n);
+ trace_e1000e_rx_interrupt_delayed(causes);
}
return retval;
@@ -2024,13 +1970,6 @@
}
};
-static inline void
-e1000e_clear_ims_bits(E1000ECore *core, uint32_t bits)
-{
- trace_e1000e_irq_clear_ims(bits, core->mac[IMS], core->mac[IMS] & ~bits);
- core->mac[IMS] &= ~bits;
-}
-
static inline bool
e1000e_postpone_interrupt(E1000IntrDelayTimer *timer)
{
@@ -2088,7 +2027,6 @@
effective_eiac = core->mac[EIAC] & cause;
core->mac[ICR] &= ~effective_eiac;
- core->msi_causes_pending &= ~effective_eiac;
if (!(core->mac[CTRL_EXT] & E1000_CTRL_EXT_IAME)) {
core->mac[IMS] &= ~effective_eiac;
@@ -2180,33 +2118,17 @@
trace_e1000e_irq_fix_icr_asserted(core->mac[ICR]);
}
-static void
-e1000e_send_msi(E1000ECore *core, bool msix)
+static void e1000e_raise_interrupts(E1000ECore *core,
+ size_t index, uint32_t causes)
{
- uint32_t causes = core->mac[ICR] & core->mac[IMS] & ~E1000_ICR_ASSERTED;
-
- core->msi_causes_pending &= causes;
- causes ^= core->msi_causes_pending;
- if (causes == 0) {
- return;
- }
- core->msi_causes_pending |= causes;
-
- if (msix) {
- e1000e_msix_notify(core, causes);
- } else {
- if (!e1000e_itr_should_postpone(core)) {
- trace_e1000e_irq_msi_notify(causes);
- msi_notify(core->owner, 0);
- }
- }
-}
-
-static void
-e1000e_update_interrupt_state(E1000ECore *core)
-{
- bool interrupts_pending;
bool is_msix = msix_enabled(core->owner);
+ uint32_t old_causes = core->mac[IMS] & core->mac[ICR];
+ uint32_t raised_causes;
+
+ trace_e1000e_irq_set(index << 2,
+ core->mac[index], core->mac[index] | causes);
+
+ core->mac[index] |= causes;
/* Set ICR[OTHER] for MSI-X */
if (is_msix) {
@@ -2228,40 +2150,58 @@
*/
core->mac[ICS] = core->mac[ICR];
- interrupts_pending = (core->mac[IMS] & core->mac[ICR]) ? true : false;
- if (!interrupts_pending) {
- core->msi_causes_pending = 0;
+ trace_e1000e_irq_pending_interrupts(core->mac[ICR] & core->mac[IMS],
+ core->mac[ICR], core->mac[IMS]);
+
+ raised_causes = core->mac[IMS] & core->mac[ICR] & ~old_causes;
+ if (!raised_causes) {
+ return;
}
+ if (is_msix) {
+ e1000e_msix_notify(core, raised_causes & ~E1000_ICR_ASSERTED);
+ } else if (!e1000e_itr_should_postpone(core)) {
+ if (msi_enabled(core->owner)) {
+ trace_e1000e_irq_msi_notify(raised_causes);
+ msi_notify(core->owner, 0);
+ } else {
+ e1000e_raise_legacy_irq(core);
+ }
+ }
+}
+
+static void e1000e_lower_interrupts(E1000ECore *core,
+ size_t index, uint32_t causes)
+{
+ trace_e1000e_irq_clear(index << 2,
+ core->mac[index], core->mac[index] & ~causes);
+
+ core->mac[index] &= ~causes;
+
+ /*
+ * Make sure ICR and ICS registers have the same value.
+ * The spec says that the ICS register is write-only. However in practice,
+ * on real hardware ICS is readable, and for reads it has the same value as
+ * ICR (except that ICS does not have the clear on read behaviour of ICR).
+ *
+ * The VxWorks PRO/1000 driver uses this behaviour.
+ */
+ core->mac[ICS] = core->mac[ICR];
+
trace_e1000e_irq_pending_interrupts(core->mac[ICR] & core->mac[IMS],
core->mac[ICR], core->mac[IMS]);
- if (is_msix || msi_enabled(core->owner)) {
- if (interrupts_pending) {
- e1000e_send_msi(core, is_msix);
- }
- } else {
- if (interrupts_pending) {
- if (!e1000e_itr_should_postpone(core)) {
- e1000e_raise_legacy_irq(core);
- }
- } else {
- e1000e_lower_legacy_irq(core);
- }
+ if (!(core->mac[IMS] & core->mac[ICR]) &&
+ !msix_enabled(core->owner) && !msi_enabled(core->owner)) {
+ e1000e_lower_legacy_irq(core);
}
}
static void
e1000e_set_interrupt_cause(E1000ECore *core, uint32_t val)
{
- trace_e1000e_irq_set_cause_entry(val, core->mac[ICR]);
-
val |= e1000e_intmgr_collect_delayed_causes(core);
- core->mac[ICR] |= val;
-
- trace_e1000e_irq_set_cause_exit(val, core->mac[ICR]);
-
- e1000e_update_interrupt_state(core);
+ e1000e_raise_interrupts(core, ICR, val);
}
static inline void
@@ -2527,30 +2467,27 @@
static void
e1000e_set_icr(E1000ECore *core, int index, uint32_t val)
{
- uint32_t icr = 0;
if ((core->mac[ICR] & E1000_ICR_ASSERTED) &&
(core->mac[CTRL_EXT] & E1000_CTRL_EXT_IAME)) {
trace_e1000e_irq_icr_process_iame();
- e1000e_clear_ims_bits(core, core->mac[IAM]);
+ e1000e_lower_interrupts(core, IMS, core->mac[IAM]);
}
- icr = core->mac[ICR] & ~val;
/*
* Windows driver expects that the "receive overrun" bit and other
* ones to be cleared when the "Other" bit (#24) is cleared.
*/
- icr = (val & E1000_ICR_OTHER) ? (icr & ~E1000_ICR_OTHER_CAUSES) : icr;
- trace_e1000e_irq_icr_write(val, core->mac[ICR], icr);
- core->mac[ICR] = icr;
- e1000e_update_interrupt_state(core);
+ if (val & E1000_ICR_OTHER) {
+ val |= E1000_ICR_OTHER_CAUSES;
+ }
+ e1000e_lower_interrupts(core, ICR, val);
}
static void
e1000e_set_imc(E1000ECore *core, int index, uint32_t val)
{
trace_e1000e_irq_ims_clear_set_imc(val);
- e1000e_clear_ims_bits(core, val);
- e1000e_update_interrupt_state(core);
+ e1000e_lower_interrupts(core, IMS, val);
}
static void
@@ -2571,9 +2508,6 @@
uint32_t valid_val = val & ims_valid_mask;
- trace_e1000e_irq_set_ims(val, core->mac[IMS], core->mac[IMS] | valid_val);
- core->mac[IMS] |= valid_val;
-
if ((valid_val & ims_ext_mask) &&
(core->mac[CTRL_EXT] & E1000_CTRL_EXT_PBA_CLR) &&
msix_enabled(core->owner)) {
@@ -2586,7 +2520,7 @@
e1000e_intrmgr_fire_all_timers(core);
}
- e1000e_update_interrupt_state(core);
+ e1000e_raise_interrupts(core, IMS, valid_val);
}
static void
@@ -2659,28 +2593,25 @@
e1000e_mac_icr_read(E1000ECore *core, int index)
{
uint32_t ret = core->mac[ICR];
- trace_e1000e_irq_icr_read_entry(ret);
if (core->mac[IMS] == 0) {
trace_e1000e_irq_icr_clear_zero_ims();
- core->mac[ICR] = 0;
+ e1000e_lower_interrupts(core, ICR, 0xffffffff);
}
if (!msix_enabled(core->owner)) {
trace_e1000e_irq_icr_clear_nonmsix_icr_read();
- core->mac[ICR] = 0;
+ e1000e_lower_interrupts(core, ICR, 0xffffffff);
}
if ((core->mac[ICR] & E1000_ICR_ASSERTED) &&
(core->mac[CTRL_EXT] & E1000_CTRL_EXT_IAME)) {
trace_e1000e_irq_icr_clear_iame();
- core->mac[ICR] = 0;
+ e1000e_lower_interrupts(core, ICR, 0xffffffff);
trace_e1000e_irq_icr_process_iame();
- e1000e_clear_ims_bits(core, core->mac[IAM]);
+ e1000e_lower_interrupts(core, IMS, core->mac[IAM]);
}
- trace_e1000e_irq_icr_read_exit(core->mac[ICR]);
- e1000e_update_interrupt_state(core);
return ret;
}
@@ -3422,7 +3353,7 @@
qemu_add_vm_change_state_handler(e1000e_vm_state_change, core);
for (i = 0; i < E1000E_NUM_QUEUES; i++) {
- net_tx_pkt_init(&core->tx[i].tx_pkt, core->owner, E1000E_MAX_TX_FRAGS);
+ net_tx_pkt_init(&core->tx[i].tx_pkt, E1000E_MAX_TX_FRAGS);
}
net_rx_pkt_init(&core->rx_pkt);
@@ -3447,7 +3378,6 @@
qemu_del_vm_change_state_handler(core->vmstate);
for (i = 0; i < E1000E_NUM_QUEUES; i++) {
- net_tx_pkt_reset(core->tx[i].tx_pkt, core->owner);
net_tx_pkt_uninit(core->tx[i].tx_pkt);
}
@@ -3572,7 +3502,6 @@
e1000x_reset_mac_addr(core->owner_nic, core->mac, core->permanent_mac);
for (i = 0; i < ARRAY_SIZE(core->tx); i++) {
- net_tx_pkt_reset(core->tx[i].tx_pkt, core->owner);
memset(&core->tx[i].props, 0, sizeof(core->tx[i].props));
core->tx[i].skip_cp = false;
}
diff --git a/hw/net/e1000e_core.h b/hw/net/e1000e_core.h
index 213a705..66b025c 100644
--- a/hw/net/e1000e_core.h
+++ b/hw/net/e1000e_core.h
@@ -111,8 +111,6 @@
PCIDevice *owner;
void (*owner_start_recv)(PCIDevice *d);
- uint32_t msi_causes_pending;
-
int64_t timadj;
};
diff --git a/hw/net/e1000x_common.c b/hw/net/e1000x_common.c
index b844af5..212873f 100644
--- a/hw/net/e1000x_common.c
+++ b/hw/net/e1000x_common.c
@@ -58,33 +58,64 @@
return res;
}
-bool e1000x_rx_group_filter(uint32_t *mac, const uint8_t *buf)
+bool e1000x_rx_vlan_filter(uint32_t *mac, const struct vlan_header *vhdr)
+{
+ if (e1000x_vlan_rx_filter_enabled(mac)) {
+ uint16_t vid = lduw_be_p(&vhdr->h_tci);
+ uint32_t vfta =
+ ldl_le_p((uint32_t *)(mac + VFTA) +
+ ((vid >> E1000_VFTA_ENTRY_SHIFT) & E1000_VFTA_ENTRY_MASK));
+ if ((vfta & (1 << (vid & E1000_VFTA_ENTRY_BIT_SHIFT_MASK))) == 0) {
+ trace_e1000x_rx_flt_vlan_mismatch(vid);
+ return false;
+ }
+
+ trace_e1000x_rx_flt_vlan_match(vid);
+ }
+
+ return true;
+}
+
+bool e1000x_rx_group_filter(uint32_t *mac, const struct eth_header *ehdr)
{
static const int mta_shift[] = { 4, 3, 2, 0 };
uint32_t f, ra[2], *rp, rctl = mac[RCTL];
+ if (is_broadcast_ether_addr(ehdr->h_dest)) {
+ if (rctl & E1000_RCTL_BAM) {
+ return true;
+ }
+ } else if (is_multicast_ether_addr(ehdr->h_dest)) {
+ if (rctl & E1000_RCTL_MPE) {
+ return true;
+ }
+ } else {
+ if (rctl & E1000_RCTL_UPE) {
+ return true;
+ }
+ }
+
for (rp = mac + RA; rp < mac + 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, ETH_ALEN)) {
+ if (!memcmp(ehdr->h_dest, (uint8_t *)ra, ETH_ALEN)) {
trace_e1000x_rx_flt_ucast_match((int)(rp - mac - RA) / 2,
- MAC_ARG(buf));
+ MAC_ARG(ehdr->h_dest));
return true;
}
}
- trace_e1000x_rx_flt_ucast_mismatch(MAC_ARG(buf));
+ trace_e1000x_rx_flt_ucast_mismatch(MAC_ARG(ehdr->h_dest));
f = mta_shift[(rctl >> E1000_RCTL_MO_SHIFT) & 3];
- f = (((buf[5] << 8) | buf[4]) >> f) & 0xfff;
+ f = (((ehdr->h_dest[5] << 8) | ehdr->h_dest[4]) >> f) & 0xfff;
if (mac[MTA + (f >> 5)] & (1 << (f & 0x1f))) {
- e1000x_inc_reg_if_not_full(mac, MPRC);
return true;
}
- trace_e1000x_rx_flt_inexact_mismatch(MAC_ARG(buf),
+ trace_e1000x_rx_flt_inexact_mismatch(MAC_ARG(ehdr->h_dest),
(rctl >> E1000_RCTL_MO_SHIFT) & 3,
f >> 5,
mac[MTA + (f >> 5)]);
@@ -109,16 +140,16 @@
bool e1000x_is_oversized(uint32_t *mac, size_t size)
{
+ size_t header_size = sizeof(struct eth_header) + sizeof(struct vlan_header);
/* this is the size past which hardware will
drop packets when setting LPE=0 */
- static const int maximum_ethernet_vlan_size = 1522;
+ size_t maximum_short_size = header_size + ETH_MTU;
/* this is the size past which hardware will
drop packets when setting LPE=1 */
- static const int maximum_ethernet_lpe_size = 16 * KiB;
+ size_t maximum_large_size = 16 * KiB - ETH_FCS_LEN;
- if ((size > maximum_ethernet_lpe_size ||
- (size > maximum_ethernet_vlan_size
- && !(mac[RCTL] & E1000_RCTL_LPE)))
+ if ((size > maximum_large_size ||
+ (size > maximum_short_size && !(mac[RCTL] & E1000_RCTL_LPE)))
&& !(mac[RCTL] & E1000_RCTL_SBP)) {
e1000x_inc_reg_if_not_full(mac, ROC);
trace_e1000x_rx_oversized(size);
@@ -212,23 +243,36 @@
void
e1000x_update_rx_total_stats(uint32_t *mac,
- size_t data_size,
- size_t data_fcs_size)
+ eth_pkt_types_e pkt_type,
+ size_t pkt_size,
+ size_t pkt_fcs_size)
{
static const int PRCregs[6] = { PRC64, PRC127, PRC255, PRC511,
PRC1023, PRC1522 };
- e1000x_increase_size_stats(mac, PRCregs, data_fcs_size);
+ e1000x_increase_size_stats(mac, PRCregs, pkt_fcs_size);
e1000x_inc_reg_if_not_full(mac, TPR);
- mac[GPRC] = mac[TPR];
+ e1000x_inc_reg_if_not_full(mac, GPRC);
/* TOR - Total Octets Received:
* This register includes bytes received in a packet from the <Destination
* Address> field through the <CRC> field, inclusively.
* Always include FCS length (4) in size.
*/
- e1000x_grow_8reg_if_not_full(mac, TORL, data_size + 4);
- mac[GORCL] = mac[TORL];
- mac[GORCH] = mac[TORH];
+ e1000x_grow_8reg_if_not_full(mac, TORL, pkt_size + 4);
+ e1000x_grow_8reg_if_not_full(mac, GORCL, pkt_size + 4);
+
+ switch (pkt_type) {
+ case ETH_PKT_BCAST:
+ e1000x_inc_reg_if_not_full(mac, BPRC);
+ break;
+
+ case ETH_PKT_MCAST:
+ e1000x_inc_reg_if_not_full(mac, MPRC);
+ break;
+
+ default:
+ break;
+ }
}
void
diff --git a/hw/net/e1000x_common.h b/hw/net/e1000x_common.h
index 911abd8..be29168 100644
--- a/hw/net/e1000x_common.h
+++ b/hw/net/e1000x_common.h
@@ -91,8 +91,9 @@
}
void e1000x_update_rx_total_stats(uint32_t *mac,
- size_t data_size,
- size_t data_fcs_size);
+ eth_pkt_types_e pkt_type,
+ size_t pkt_size,
+ size_t pkt_fcs_size);
void e1000x_core_prepare_eeprom(uint16_t *eeprom,
const uint16_t *templ,
@@ -106,7 +107,9 @@
bool e1000x_is_vlan_packet(const void *buf, uint16_t vet);
-bool e1000x_rx_group_filter(uint32_t *mac, const uint8_t *buf);
+bool e1000x_rx_vlan_filter(uint32_t *mac, const struct vlan_header *vhdr);
+
+bool e1000x_rx_group_filter(uint32_t *mac, const struct eth_header *ehdr);
bool e1000x_hw_rx_enabled(uint32_t *mac);
diff --git a/hw/net/e1000x_regs.h b/hw/net/e1000x_regs.h
index 6d3c4c6..13760c6 100644
--- a/hw/net/e1000x_regs.h
+++ b/hw/net/e1000x_regs.h
@@ -290,18 +290,18 @@
#define E1000_RETA_IDX(hash) ((hash) & (BIT(7) - 1))
#define E1000_RETA_VAL(reta, hash) (((uint8_t *)(reta))[E1000_RETA_IDX(hash)])
-#define E1000_MRQC_EN_TCPIPV4(mrqc) ((mrqc) & BIT(16))
-#define E1000_MRQC_EN_IPV4(mrqc) ((mrqc) & BIT(17))
-#define E1000_MRQC_EN_TCPIPV6(mrqc) ((mrqc) & BIT(18))
-#define E1000_MRQC_EN_IPV6EX(mrqc) ((mrqc) & BIT(19))
-#define E1000_MRQC_EN_IPV6(mrqc) ((mrqc) & BIT(20))
+#define E1000_MRQC_EN_TCPIPV4(mrqc) ((mrqc) & BIT(16))
+#define E1000_MRQC_EN_IPV4(mrqc) ((mrqc) & BIT(17))
+#define E1000_MRQC_EN_TCPIPV6EX(mrqc) ((mrqc) & BIT(18))
+#define E1000_MRQC_EN_IPV6EX(mrqc) ((mrqc) & BIT(19))
+#define E1000_MRQC_EN_IPV6(mrqc) ((mrqc) & BIT(20))
-#define E1000_MRQ_RSS_TYPE_NONE (0)
-#define E1000_MRQ_RSS_TYPE_IPV4TCP (1)
-#define E1000_MRQ_RSS_TYPE_IPV4 (2)
-#define E1000_MRQ_RSS_TYPE_IPV6TCP (3)
-#define E1000_MRQ_RSS_TYPE_IPV6EX (4)
-#define E1000_MRQ_RSS_TYPE_IPV6 (5)
+#define E1000_MRQ_RSS_TYPE_NONE (0)
+#define E1000_MRQ_RSS_TYPE_IPV4TCP (1)
+#define E1000_MRQ_RSS_TYPE_IPV4 (2)
+#define E1000_MRQ_RSS_TYPE_IPV6TCPEX (3)
+#define E1000_MRQ_RSS_TYPE_IPV6EX (4)
+#define E1000_MRQ_RSS_TYPE_IPV6 (5)
#define E1000_ICR_ASSERTED BIT(31)
#define E1000_EIAC_MASK 0x01F00000
diff --git a/hw/net/igb.c b/hw/net/igb.c
index 51a7e91..1c989d7 100644
--- a/hw/net/igb.c
+++ b/hw/net/igb.c
@@ -433,16 +433,16 @@
pcie_ari_init(pci_dev, 0x150, 1);
- pcie_sriov_pf_init(pci_dev, IGB_CAP_SRIOV_OFFSET, "igbvf",
+ pcie_sriov_pf_init(pci_dev, IGB_CAP_SRIOV_OFFSET, TYPE_IGBVF,
IGB_82576_VF_DEV_ID, IGB_MAX_VF_FUNCTIONS, IGB_MAX_VF_FUNCTIONS,
IGB_VF_OFFSET, IGB_VF_STRIDE);
- pcie_sriov_pf_init_vf_bar(pci_dev, 0,
+ pcie_sriov_pf_init_vf_bar(pci_dev, IGBVF_MMIO_BAR_IDX,
PCI_BASE_ADDRESS_MEM_TYPE_64 | PCI_BASE_ADDRESS_MEM_PREFETCH,
- 16 * KiB);
- pcie_sriov_pf_init_vf_bar(pci_dev, 3,
+ IGBVF_MMIO_SIZE);
+ pcie_sriov_pf_init_vf_bar(pci_dev, IGBVF_MSIX_BAR_IDX,
PCI_BASE_ADDRESS_MEM_TYPE_64 | PCI_BASE_ADDRESS_MEM_PREFETCH,
- 16 * KiB);
+ IGBVF_MSIX_SIZE);
igb_init_net_peer(s, pci_dev, macaddr);
diff --git a/hw/net/igb_common.h b/hw/net/igb_common.h
index 69ac490..5c261ba 100644
--- a/hw/net/igb_common.h
+++ b/hw/net/igb_common.h
@@ -28,6 +28,14 @@
#include "igb_regs.h"
+#define TYPE_IGBVF "igbvf"
+
+#define IGBVF_MMIO_BAR_IDX (0)
+#define IGBVF_MSIX_BAR_IDX (3)
+
+#define IGBVF_MMIO_SIZE (16 * 1024)
+#define IGBVF_MSIX_SIZE (16 * 1024)
+
#define defreg(x) x = (E1000_##x >> 2)
#define defreg_indexed(x, i) x##i = (E1000_##x(i) >> 2)
#define defreg_indexeda(x, i) x##i##_A = (E1000_##x##_A(i) >> 2)
@@ -43,7 +51,7 @@
defreg_indexeda(x, 0), defreg_indexeda(x, 1), \
defreg_indexeda(x, 2), defreg_indexeda(x, 3)
-#define defregv(x) defreg_indexed(x, 0), defreg_indexed(x, 1), \
+#define defreg8(x) defreg_indexed(x, 0), defreg_indexed(x, 1), \
defreg_indexed(x, 2), defreg_indexed(x, 3), \
defreg_indexed(x, 4), defreg_indexed(x, 5), \
defreg_indexed(x, 6), defreg_indexed(x, 7)
@@ -114,6 +122,8 @@
defreg(EICS), defreg(EIMS), defreg(EIMC), defreg(EIAM),
defreg(EICR), defreg(IVAR_MISC), defreg(GPIE),
+ defreg(TSYNCRXCFG), defreg8(ETQF),
+
defreg(RXPBS), defregd(RDBAL), defregd(RDBAH), defregd(RDLEN),
defregd(SRRCTL), defregd(RDH), defregd(RDT),
defregd(RXDCTL), defregd(RXCTL), defregd(RQDPC), defreg(RA2),
@@ -125,15 +135,15 @@
defreg(VT_CTL),
- defregv(P2VMAILBOX), defregv(V2PMAILBOX), defreg(MBVFICR), defreg(MBVFIMR),
+ defreg8(P2VMAILBOX), defreg8(V2PMAILBOX), defreg(MBVFICR), defreg(MBVFIMR),
defreg(VFLRE), defreg(VFRE), defreg(VFTE), defreg(WVBR),
defreg(QDE), defreg(DTXSWC), defreg_indexed(VLVF, 0),
- defregv(VMOLR), defreg(RPLOLR), defregv(VMBMEM), defregv(VMVIR),
+ defreg8(VMOLR), defreg(RPLOLR), defreg8(VMBMEM), defreg8(VMVIR),
- defregv(PVTCTRL), defregv(PVTEICS), defregv(PVTEIMS), defregv(PVTEIMC),
- defregv(PVTEIAC), defregv(PVTEIAM), defregv(PVTEICR), defregv(PVFGPRC),
- defregv(PVFGPTC), defregv(PVFGORC), defregv(PVFGOTC), defregv(PVFMPRC),
- defregv(PVFGPRLBC), defregv(PVFGPTLBC), defregv(PVFGORLBC), defregv(PVFGOTLBC),
+ defreg8(PVTCTRL), defreg8(PVTEICS), defreg8(PVTEIMS), defreg8(PVTEIMC),
+ defreg8(PVTEIAC), defreg8(PVTEIAM), defreg8(PVTEICR), defreg8(PVFGPRC),
+ defreg8(PVFGPTC), defreg8(PVFGORC), defreg8(PVFGOTC), defreg8(PVFMPRC),
+ defreg8(PVFGPRLBC), defreg8(PVFGPTLBC), defreg8(PVFGORLBC), defreg8(PVFGOTLBC),
defreg(MTA_A),
diff --git a/hw/net/igb_core.c b/hw/net/igb_core.c
index d733fed..d00b1ca 100644
--- a/hw/net/igb_core.c
+++ b/hw/net/igb_core.c
@@ -67,14 +67,34 @@
NetClientState *nc;
} IGBTxPktVmdqCallbackContext;
+typedef struct L2Header {
+ struct eth_header eth;
+ struct vlan_header vlan[2];
+} L2Header;
+
+typedef struct PTP2 {
+ uint8_t message_id_transport_specific;
+ uint8_t version_ptp;
+ uint16_t message_length;
+ uint8_t subdomain_number;
+ uint8_t reserved0;
+ uint16_t flags;
+ uint64_t correction;
+ uint8_t reserved1[5];
+ uint8_t source_communication_technology;
+ uint32_t source_uuid_lo;
+ uint16_t source_uuid_hi;
+ uint16_t source_port_id;
+ uint16_t sequence_id;
+ uint8_t control;
+ uint8_t log_message_period;
+} PTP2;
+
static ssize_t
igb_receive_internal(IGBCore *core, const struct iovec *iov, int iovcnt,
bool has_vnet, bool *external_tx);
-static inline void
-igb_set_interrupt_cause(IGBCore *core, uint32_t val);
-
-static void igb_update_interrupt_state(IGBCore *core);
+static void igb_raise_interrupts(IGBCore *core, size_t index, uint32_t causes);
static void igb_reset(IGBCore *core, bool sw);
static inline void
@@ -92,23 +112,31 @@
pci_set_irq(core->owner, 0);
}
-static void igb_msix_notify(IGBCore *core, unsigned int vector)
+static void igb_msix_notify(IGBCore *core, unsigned int cause)
{
PCIDevice *dev = core->owner;
uint16_t vfn;
+ uint32_t effective_eiac;
+ unsigned int vector;
- vfn = 8 - (vector + 2) / IGBVF_MSIX_VEC_NUM;
+ vfn = 8 - (cause + 2) / IGBVF_MSIX_VEC_NUM;
if (vfn < pcie_sriov_num_vfs(core->owner)) {
dev = pcie_sriov_get_vf_at_index(core->owner, vfn);
assert(dev);
- vector = (vector + 2) % IGBVF_MSIX_VEC_NUM;
- } else if (vector >= IGB_MSIX_VEC_NUM) {
+ vector = (cause + 2) % IGBVF_MSIX_VEC_NUM;
+ } else if (cause >= IGB_MSIX_VEC_NUM) {
qemu_log_mask(LOG_GUEST_ERROR,
"igb: Tried to use vector unavailable for PF");
return;
+ } else {
+ vector = cause;
}
msix_notify(dev, vector);
+
+ trace_e1000e_irq_icr_clear_eiac(core->mac[EICR], core->mac[EIAC]);
+ effective_eiac = core->mac[EIAC] & BIT(cause);
+ core->mac[EICR] &= ~effective_eiac;
}
static inline void
@@ -274,6 +302,11 @@
return E1000_MRQ_RSS_TYPE_IPV4TCP;
}
+ if (l4hdr_proto == ETH_L4_HDR_PROTO_UDP &&
+ (core->mac[MRQC] & E1000_MRQC_RSS_FIELD_IPV4_UDP)) {
+ return E1000_MRQ_RSS_TYPE_IPV4UDP;
+ }
+
if (E1000_MRQC_EN_IPV4(core->mac[MRQC])) {
return E1000_MRQ_RSS_TYPE_IPV4;
}
@@ -296,7 +329,7 @@
ip6info->rss_ex_dst_valid,
ip6info->rss_ex_src_valid,
core->mac[MRQC],
- E1000_MRQC_EN_TCPIPV6(core->mac[MRQC]),
+ E1000_MRQC_EN_TCPIPV6EX(core->mac[MRQC]),
E1000_MRQC_EN_IPV6EX(core->mac[MRQC]),
E1000_MRQC_EN_IPV6(core->mac[MRQC]));
@@ -305,8 +338,13 @@
ip6info->rss_ex_src_valid))) {
if (l4hdr_proto == ETH_L4_HDR_PROTO_TCP &&
- E1000_MRQC_EN_TCPIPV6(core->mac[MRQC])) {
- return E1000_MRQ_RSS_TYPE_IPV6TCP;
+ E1000_MRQC_EN_TCPIPV6EX(core->mac[MRQC])) {
+ return E1000_MRQ_RSS_TYPE_IPV6TCPEX;
+ }
+
+ if (l4hdr_proto == ETH_L4_HDR_PROTO_UDP &&
+ (core->mac[MRQC] & E1000_MRQC_RSS_FIELD_IPV6_UDP)) {
+ return E1000_MRQ_RSS_TYPE_IPV6UDP;
}
if (E1000_MRQC_EN_IPV6EX(core->mac[MRQC])) {
@@ -338,7 +376,7 @@
case E1000_MRQ_RSS_TYPE_IPV4TCP:
type = NetPktRssIpV4Tcp;
break;
- case E1000_MRQ_RSS_TYPE_IPV6TCP:
+ case E1000_MRQ_RSS_TYPE_IPV6TCPEX:
type = NetPktRssIpV6TcpEx;
break;
case E1000_MRQ_RSS_TYPE_IPV6:
@@ -347,6 +385,12 @@
case E1000_MRQ_RSS_TYPE_IPV6EX:
type = NetPktRssIpV6Ex;
break;
+ case E1000_MRQ_RSS_TYPE_IPV4UDP:
+ type = NetPktRssIpV4Udp;
+ break;
+ case E1000_MRQ_RSS_TYPE_IPV6UDP:
+ type = NetPktRssIpV6Udp;
+ break;
default:
assert(false);
return 0;
@@ -402,7 +446,7 @@
}
}
- if (insert_vlan && e1000x_vlan_enabled(core->mac)) {
+ if (insert_vlan) {
net_tx_pkt_setup_vlan_header_ex(tx->tx_pkt, vlan,
core->mac[VET] & 0xffff);
}
@@ -411,9 +455,10 @@
static bool
igb_setup_tx_offloads(IGBCore *core, struct igb_tx *tx)
{
+ uint32_t idx = (tx->first_olinfo_status >> 4) & 1;
+
if (tx->first_cmd_type_len & E1000_ADVTXD_DCMD_TSE) {
- uint32_t idx = (tx->first_olinfo_status >> 4) & 1;
- uint32_t mss = tx->ctx[idx].mss_l4len_idx >> 16;
+ uint32_t mss = tx->ctx[idx].mss_l4len_idx >> E1000_ADVTXD_MSS_SHIFT;
if (!net_tx_pkt_build_vheader(tx->tx_pkt, true, true, mss)) {
return false;
}
@@ -423,10 +468,11 @@
return true;
}
- if (tx->first_olinfo_status & E1000_ADVTXD_POTS_TXSM) {
- if (!net_tx_pkt_build_vheader(tx->tx_pkt, false, true, 0)) {
- return false;
- }
+ if ((tx->first_olinfo_status & E1000_ADVTXD_POTS_TXSM) &&
+ !((tx->ctx[idx].type_tucmd_mlhl & E1000_ADVTXD_TUCMD_L4T_SCTP) ?
+ net_tx_pkt_update_sctp_checksum(tx->tx_pkt) :
+ net_tx_pkt_build_vheader(tx->tx_pkt, false, true, 0))) {
+ return false;
}
if (tx->first_olinfo_status & E1000_ADVTXD_POTS_IXSM) {
@@ -538,9 +584,8 @@
g_assert_not_reached();
}
- core->mac[GPTC] = core->mac[TPT];
- core->mac[GOTCL] = core->mac[TOTL];
- core->mac[GOTCH] = core->mac[TOTH];
+ e1000x_inc_reg_if_not_full(core->mac, GPTC);
+ e1000x_grow_8reg_if_not_full(core->mac, GOTCL, tot_len);
if (core->mac[MRQC] & 1) {
uint16_t pool = qn % IGB_NUM_VM_POOLS;
@@ -598,7 +643,8 @@
length = cmd_type_len & 0xFFFF;
if (!tx->skip_cp) {
- if (!net_tx_pkt_add_raw_fragment(tx->tx_pkt, buffer_addr, length)) {
+ if (!net_tx_pkt_add_raw_fragment_pci(tx->tx_pkt, dev,
+ buffer_addr, length)) {
tx->skip_cp = true;
}
}
@@ -607,8 +653,15 @@
if (!tx->skip_cp && net_tx_pkt_parse(tx->tx_pkt)) {
idx = (tx->first_olinfo_status >> 4) & 1;
igb_tx_insert_vlan(core, queue_index, tx,
- tx->ctx[idx].vlan_macip_lens >> 16,
- !!(cmd_type_len & E1000_TXD_CMD_VLE));
+ tx->ctx[idx].vlan_macip_lens >> IGB_TX_FLAGS_VLAN_SHIFT,
+ !!(tx->first_cmd_type_len & E1000_TXD_CMD_VLE));
+
+ if ((tx->first_cmd_type_len & E1000_ADVTXD_MAC_TSTAMP) &&
+ (core->mac[TSYNCTXCTL] & E1000_TSYNCTXCTL_ENABLED) &&
+ !(core->mac[TSYNCTXCTL] & E1000_TSYNCTXCTL_VALID)) {
+ core->mac[TSYNCTXCTL] |= E1000_TSYNCTXCTL_VALID;
+ e1000x_timestamp(core->mac, core->timadj, TXSTMPL, TXSTMPH);
+ }
if (igb_tx_pkt_send(core, tx, queue_index)) {
igb_on_tx_done_update_stats(core, tx->tx_pkt, queue_index);
@@ -617,7 +670,7 @@
tx->first = true;
tx->skip_cp = false;
- net_tx_pkt_reset(tx->tx_pkt, dev);
+ net_tx_pkt_reset(tx->tx_pkt, net_tx_pkt_unmap_frag_pci, dev);
}
}
@@ -843,8 +896,6 @@
d = core->owner;
}
- net_tx_pkt_reset(txr->tx->tx_pkt, d);
-
while (!igb_ring_empty(core, txi)) {
base = igb_ring_head_descr(core, txi);
@@ -859,9 +910,11 @@
}
if (eic) {
- core->mac[EICR] |= eic;
- igb_set_interrupt_cause(core, E1000_ICR_TXDW);
+ igb_raise_interrupts(core, EICR, eic);
+ igb_raise_interrupts(core, ICR, E1000_ICR_TXDW);
}
+
+ net_tx_pkt_reset(txr->tx->tx_pkt, net_tx_pkt_unmap_frag_pci, d);
}
static uint32_t
@@ -949,47 +1002,81 @@
return !!(core->mac[RXCSUM] & E1000_RXCSUM_TUOFLD);
}
-static bool
-igb_rx_is_oversized(IGBCore *core, uint16_t qn, size_t size)
+static bool igb_rx_is_oversized(IGBCore *core, const struct eth_header *ehdr,
+ size_t size, size_t vlan_num,
+ bool lpe, uint16_t rlpml)
{
- uint16_t pool = qn % IGB_NUM_VM_POOLS;
- bool lpe = !!(core->mac[VMOLR0 + pool] & E1000_VMOLR_LPE);
- int max_ethernet_lpe_size =
- core->mac[VMOLR0 + pool] & E1000_VMOLR_RLPML_MASK;
- int max_ethernet_vlan_size = 1522;
-
- return size > (lpe ? max_ethernet_lpe_size : max_ethernet_vlan_size);
+ size_t vlan_header_size = sizeof(struct vlan_header) * vlan_num;
+ size_t header_size = sizeof(struct eth_header) + vlan_header_size;
+ return lpe ? size + ETH_FCS_LEN > rlpml : size > header_size + ETH_MTU;
}
-static uint16_t igb_receive_assign(IGBCore *core, const struct eth_header *ehdr,
- size_t size, E1000E_RSSInfo *rss_info,
- bool *external_tx)
+static uint16_t igb_receive_assign(IGBCore *core, const struct iovec *iov,
+ size_t iovcnt, size_t iov_ofs,
+ const L2Header *l2_header, size_t size,
+ E1000E_RSSInfo *rss_info,
+ uint16_t *etqf, bool *ts, bool *external_tx)
{
static const int ta_shift[] = { 4, 3, 2, 0 };
+ const struct eth_header *ehdr = &l2_header->eth;
uint32_t f, ra[2], *macp, rctl = core->mac[RCTL];
uint16_t queues = 0;
uint16_t oversized = 0;
- uint16_t vid = lduw_be_p(&PKT_GET_VLAN_HDR(ehdr)->h_tci) & VLAN_VID_MASK;
- bool accepted = false;
+ size_t vlan_num = 0;
+ PTP2 ptp2;
+ bool lpe;
+ uint16_t rlpml;
int i;
memset(rss_info, 0, sizeof(E1000E_RSSInfo));
+ *ts = false;
if (external_tx) {
*external_tx = true;
}
- if (e1000x_is_vlan_packet(ehdr, core->mac[VET] & 0xffff) &&
- e1000x_vlan_rx_filter_enabled(core->mac)) {
- uint32_t vfta =
- ldl_le_p((uint32_t *)(core->mac + VFTA) +
- ((vid >> E1000_VFTA_ENTRY_SHIFT) & E1000_VFTA_ENTRY_MASK));
- if ((vfta & (1 << (vid & E1000_VFTA_ENTRY_BIT_SHIFT_MASK))) == 0) {
- trace_e1000e_rx_flt_vlan_mismatch(vid);
- return queues;
- } else {
- trace_e1000e_rx_flt_vlan_match(vid);
+ if (core->mac[CTRL_EXT] & BIT(26)) {
+ if (be16_to_cpu(ehdr->h_proto) == core->mac[VET] >> 16 &&
+ be16_to_cpu(l2_header->vlan[0].h_proto) == (core->mac[VET] & 0xffff)) {
+ vlan_num = 2;
}
+ } else {
+ if (be16_to_cpu(ehdr->h_proto) == (core->mac[VET] & 0xffff)) {
+ vlan_num = 1;
+ }
+ }
+
+ lpe = !!(core->mac[RCTL] & E1000_RCTL_LPE);
+ rlpml = core->mac[RLPML];
+ if (!(core->mac[RCTL] & E1000_RCTL_SBP) &&
+ igb_rx_is_oversized(core, ehdr, size, vlan_num, lpe, rlpml)) {
+ trace_e1000x_rx_oversized(size);
+ return queues;
+ }
+
+ for (*etqf = 0; *etqf < 8; (*etqf)++) {
+ if ((core->mac[ETQF0 + *etqf] & E1000_ETQF_FILTER_ENABLE) &&
+ be16_to_cpu(ehdr->h_proto) == (core->mac[ETQF0 + *etqf] & E1000_ETQF_ETYPE_MASK)) {
+ if ((core->mac[ETQF0 + *etqf] & E1000_ETQF_1588) &&
+ (core->mac[TSYNCRXCTL] & E1000_TSYNCRXCTL_ENABLED) &&
+ !(core->mac[TSYNCRXCTL] & E1000_TSYNCRXCTL_VALID) &&
+ iov_to_buf(iov, iovcnt, iov_ofs + ETH_HLEN, &ptp2, sizeof(ptp2)) >= sizeof(ptp2) &&
+ (ptp2.version_ptp & 15) == 2 &&
+ ptp2.message_id_transport_specific == ((core->mac[TSYNCRXCFG] >> 8) & 255)) {
+ e1000x_timestamp(core->mac, core->timadj, RXSTMPL, RXSTMPH);
+ *ts = true;
+ core->mac[TSYNCRXCTL] |= E1000_TSYNCRXCTL_VALID;
+ core->mac[RXSATRL] = le32_to_cpu(ptp2.source_uuid_lo);
+ core->mac[RXSATRH] = le16_to_cpu(ptp2.source_uuid_hi) |
+ (le16_to_cpu(ptp2.sequence_id) << 16);
+ }
+ break;
+ }
+ }
+
+ if (vlan_num &&
+ !e1000x_rx_vlan_filter(core->mac, l2_header->vlan + vlan_num - 1)) {
+ return queues;
}
if (core->mac[MRQC] & 1) {
@@ -1042,7 +1129,9 @@
if (e1000x_vlan_rx_filter_enabled(core->mac)) {
uint16_t mask = 0;
- if (e1000x_is_vlan_packet(ehdr, core->mac[VET] & 0xffff)) {
+ if (vlan_num) {
+ uint16_t vid = be16_to_cpu(l2_header->vlan[vlan_num - 1].h_tci) & VLAN_VID_MASK;
+
for (i = 0; i < E1000_VLVF_ARRAY_SIZE; i++) {
if ((core->mac[VLVF0 + i] & E1000_VLVF_VLANID_MASK) == vid &&
(core->mac[VLVF0 + i] & E1000_VLVF_VLANID_ENABLE)) {
@@ -1070,7 +1159,11 @@
queues &= core->mac[VFRE];
if (queues) {
for (i = 0; i < IGB_NUM_VM_POOLS; i++) {
- if ((queues & BIT(i)) && igb_rx_is_oversized(core, i, size)) {
+ lpe = !!(core->mac[VMOLR0 + i] & E1000_VMOLR_LPE);
+ rlpml = core->mac[VMOLR0 + i] & E1000_VMOLR_RLPML_MASK;
+ if ((queues & BIT(i)) &&
+ igb_rx_is_oversized(core, ehdr, size, vlan_num,
+ lpe, rlpml)) {
oversized |= BIT(i);
}
}
@@ -1097,33 +1190,7 @@
}
}
} else {
- switch (net_rx_pkt_get_packet_type(core->rx_pkt)) {
- case ETH_PKT_UCAST:
- if (rctl & E1000_RCTL_UPE) {
- accepted = true; /* promiscuous ucast */
- }
- break;
-
- case ETH_PKT_BCAST:
- if (rctl & E1000_RCTL_BAM) {
- accepted = true; /* broadcast enabled */
- }
- break;
-
- case ETH_PKT_MCAST:
- if (rctl & E1000_RCTL_MPE) {
- accepted = true; /* promiscuous mcast */
- }
- break;
-
- default:
- g_assert_not_reached();
- }
-
- if (!accepted) {
- accepted = e1000x_rx_group_filter(core->mac, ehdr->h_dest);
- }
-
+ bool accepted = e1000x_rx_group_filter(core->mac, ehdr);
if (!accepted) {
for (macp = core->mac + RA2; macp < core->mac + RA2 + 16; macp += 2) {
if (!(macp[1] & E1000_RAH_AV)) {
@@ -1217,7 +1284,7 @@
igb_build_rx_metadata(IGBCore *core,
struct NetRxPkt *pkt,
bool is_eop,
- const E1000E_RSSInfo *rss_info,
+ const E1000E_RSSInfo *rss_info, uint16_t etqf, bool ts,
uint16_t *pkt_info, uint16_t *hdr_info,
uint32_t *rss,
uint32_t *status_flags,
@@ -1225,9 +1292,8 @@
uint16_t *vlan_tag)
{
struct virtio_net_hdr *vhdr;
- bool hasip4, hasip6;
+ bool hasip4, hasip6, csum_valid;
EthL4HdrProto l4hdr_proto;
- uint32_t pkt_type;
*status_flags = E1000_RXD_STAT_DD;
@@ -1266,34 +1332,47 @@
trace_e1000e_rx_metadata_ack();
}
- if (hasip6 && (core->mac[RFCTL] & E1000_RFCTL_IPV6_DIS)) {
- trace_e1000e_rx_metadata_ipv6_filtering_disabled();
- pkt_type = E1000_RXD_PKT_MAC;
- } else if (l4hdr_proto == ETH_L4_HDR_PROTO_TCP ||
- l4hdr_proto == ETH_L4_HDR_PROTO_UDP) {
- pkt_type = hasip4 ? E1000_RXD_PKT_IP4_XDP : E1000_RXD_PKT_IP6_XDP;
- } else if (hasip4 || hasip6) {
- pkt_type = hasip4 ? E1000_RXD_PKT_IP4 : E1000_RXD_PKT_IP6;
- } else {
- pkt_type = E1000_RXD_PKT_MAC;
- }
-
- trace_e1000e_rx_metadata_pkt_type(pkt_type);
-
if (pkt_info) {
- if (rss_info->enabled) {
- *pkt_info = rss_info->type;
- }
+ *pkt_info = rss_info->enabled ? rss_info->type : 0;
- *pkt_info |= (pkt_type << 4);
- } else {
- *status_flags |= E1000_RXD_PKT_TYPE(pkt_type);
+ if (etqf < 8) {
+ *pkt_info |= (BIT(11) | etqf) << 4;
+ } else {
+ if (hasip4) {
+ *pkt_info |= E1000_ADVRXD_PKT_IP4;
+ }
+
+ if (hasip6) {
+ *pkt_info |= E1000_ADVRXD_PKT_IP6;
+ }
+
+ switch (l4hdr_proto) {
+ case ETH_L4_HDR_PROTO_TCP:
+ *pkt_info |= E1000_ADVRXD_PKT_TCP;
+ break;
+
+ case ETH_L4_HDR_PROTO_UDP:
+ *pkt_info |= E1000_ADVRXD_PKT_UDP;
+ break;
+
+ case ETH_L4_HDR_PROTO_SCTP:
+ *pkt_info |= E1000_ADVRXD_PKT_SCTP;
+ break;
+
+ default:
+ break;
+ }
+ }
}
if (hdr_info) {
*hdr_info = 0;
}
+ if (ts) {
+ *status_flags |= BIT(16);
+ }
+
/* RX CSO information */
if (hasip6 && (core->mac[RFCTL] & E1000_RFCTL_IPV6_XSUM_DIS)) {
trace_e1000e_rx_metadata_ipv6_sum_disabled();
@@ -1317,6 +1396,15 @@
if (igb_rx_l4_cso_enabled(core)) {
switch (l4hdr_proto) {
+ case ETH_L4_HDR_PROTO_SCTP:
+ if (!net_rx_pkt_validate_l4_csum(pkt, &csum_valid)) {
+ trace_e1000e_rx_metadata_l4_csum_validation_failed();
+ goto func_exit;
+ }
+ if (!csum_valid) {
+ *status_flags |= E1000_RXDEXT_STATERR_TCPE;
+ }
+ /* fall through */
case ETH_L4_HDR_PROTO_TCP:
*status_flags |= E1000_RXD_STAT_TCPCS;
break;
@@ -1326,22 +1414,21 @@
break;
default:
- goto func_exit;
+ break;
}
} else {
trace_e1000e_rx_metadata_l4_cso_disabled();
}
- trace_e1000e_rx_metadata_status_flags(*status_flags);
-
func_exit:
+ trace_e1000e_rx_metadata_status_flags(*status_flags);
*status_flags = cpu_to_le32(*status_flags);
}
static inline void
igb_write_lgcy_rx_descr(IGBCore *core, struct e1000_rx_desc *desc,
struct NetRxPkt *pkt,
- const E1000E_RSSInfo *rss_info,
+ const E1000E_RSSInfo *rss_info, uint16_t etqf, bool ts,
uint16_t length)
{
uint32_t status_flags, rss;
@@ -1352,7 +1439,7 @@
desc->csum = 0;
igb_build_rx_metadata(core, pkt, pkt != NULL,
- rss_info,
+ rss_info, etqf, ts,
NULL, NULL, &rss,
&status_flags, &ip_id,
&desc->special);
@@ -1363,7 +1450,7 @@
static inline void
igb_write_adv_rx_descr(IGBCore *core, union e1000_adv_rx_desc *desc,
struct NetRxPkt *pkt,
- const E1000E_RSSInfo *rss_info,
+ const E1000E_RSSInfo *rss_info, uint16_t etqf, bool ts,
uint16_t length)
{
memset(&desc->wb, 0, sizeof(desc->wb));
@@ -1371,7 +1458,7 @@
desc->wb.upper.length = cpu_to_le16(length);
igb_build_rx_metadata(core, pkt, pkt != NULL,
- rss_info,
+ rss_info, etqf, ts,
&desc->wb.lower.lo_dword.pkt_info,
&desc->wb.lower.lo_dword.hdr_info,
&desc->wb.lower.hi_dword.rss,
@@ -1382,12 +1469,15 @@
static inline void
igb_write_rx_descr(IGBCore *core, union e1000_rx_desc_union *desc,
-struct NetRxPkt *pkt, const E1000E_RSSInfo *rss_info, uint16_t length)
+ struct NetRxPkt *pkt, const E1000E_RSSInfo *rss_info,
+ uint16_t etqf, bool ts, uint16_t length)
{
if (igb_rx_use_legacy_descriptor(core)) {
- igb_write_lgcy_rx_descr(core, &desc->legacy, pkt, rss_info, length);
+ igb_write_lgcy_rx_descr(core, &desc->legacy, pkt, rss_info,
+ etqf, ts, length);
} else {
- igb_write_adv_rx_descr(core, &desc->adv, pkt, rss_info, length);
+ igb_write_adv_rx_descr(core, &desc->adv, pkt, rss_info,
+ etqf, ts, length);
}
}
@@ -1438,29 +1528,17 @@
static void
igb_update_rx_stats(IGBCore *core, const E1000E_RingInfo *rxi,
- size_t data_size, size_t data_fcs_size)
+ size_t pkt_size, size_t pkt_fcs_size)
{
- e1000x_update_rx_total_stats(core->mac, data_size, data_fcs_size);
-
- switch (net_rx_pkt_get_packet_type(core->rx_pkt)) {
- case ETH_PKT_BCAST:
- e1000x_inc_reg_if_not_full(core->mac, BPRC);
- break;
-
- case ETH_PKT_MCAST:
- e1000x_inc_reg_if_not_full(core->mac, MPRC);
- break;
-
- default:
- break;
- }
+ eth_pkt_types_e pkt_type = net_rx_pkt_get_packet_type(core->rx_pkt);
+ e1000x_update_rx_total_stats(core->mac, pkt_type, pkt_size, pkt_fcs_size);
if (core->mac[MRQC] & 1) {
uint16_t pool = rxi->idx % IGB_NUM_VM_POOLS;
- core->mac[PVFGORC0 + (pool * 64)] += data_size + 4;
+ core->mac[PVFGORC0 + (pool * 64)] += pkt_size + 4;
core->mac[PVFGPRC0 + (pool * 64)]++;
- if (net_rx_pkt_get_packet_type(core->rx_pkt) == ETH_PKT_MCAST) {
+ if (pkt_type == ETH_PKT_MCAST) {
core->mac[PVFMPRC0 + (pool * 64)]++;
}
}
@@ -1476,7 +1554,8 @@
static void
igb_write_packet_to_guest(IGBCore *core, struct NetRxPkt *pkt,
const E1000E_RxRing *rxr,
- const E1000E_RSSInfo *rss_info)
+ const E1000E_RSSInfo *rss_info,
+ uint16_t etqf, bool ts)
{
PCIDevice *d;
dma_addr_t base;
@@ -1558,7 +1637,7 @@
}
igb_write_rx_descr(core, &desc, is_last ? core->rx_pkt : NULL,
- rss_info, written);
+ rss_info, etqf, ts, written);
igb_pci_dma_write_rx_desc(core, d, base, &desc, core->rx_desc_len);
igb_ring_advance(core, rxi, core->rx_desc_len / E1000_MIN_RX_DESC_LEN);
@@ -1602,19 +1681,22 @@
igb_receive_internal(IGBCore *core, const struct iovec *iov, int iovcnt,
bool has_vnet, bool *external_tx)
{
- static const int maximum_ethernet_hdr_len = (ETH_HLEN + 4);
-
uint16_t queues = 0;
- uint32_t n = 0;
- uint8_t min_buf[ETH_ZLEN];
+ uint32_t causes = 0;
+ uint32_t ecauses = 0;
+ union {
+ L2Header l2_header;
+ uint8_t octets[ETH_ZLEN];
+ } buf;
struct iovec min_iov;
- struct eth_header *ehdr;
- uint8_t *filter_buf;
size_t size, orig_size;
size_t iov_ofs = 0;
E1000E_RxRing rxr;
E1000E_RSSInfo rss_info;
+ uint16_t etqf;
+ bool ts;
size_t total_size;
+ int strip_vlan_index;
int i;
trace_e1000e_rx_receive_iov(iovcnt);
@@ -1635,36 +1717,30 @@
net_rx_pkt_unset_vhdr(core->rx_pkt);
}
- filter_buf = iov->iov_base + iov_ofs;
orig_size = iov_size(iov, iovcnt);
size = orig_size - iov_ofs;
/* Pad to minimum Ethernet frame length */
- if (size < sizeof(min_buf)) {
- iov_to_buf(iov, iovcnt, iov_ofs, min_buf, size);
- memset(&min_buf[size], 0, sizeof(min_buf) - size);
+ if (size < sizeof(buf)) {
+ iov_to_buf(iov, iovcnt, iov_ofs, &buf, size);
+ memset(&buf.octets[size], 0, sizeof(buf) - size);
e1000x_inc_reg_if_not_full(core->mac, RUC);
- min_iov.iov_base = filter_buf = min_buf;
- min_iov.iov_len = size = sizeof(min_buf);
+ min_iov.iov_base = &buf;
+ min_iov.iov_len = size = sizeof(buf);
iovcnt = 1;
iov = &min_iov;
iov_ofs = 0;
- } else if (iov->iov_len < maximum_ethernet_hdr_len) {
- /* This is very unlikely, but may happen. */
- iov_to_buf(iov, iovcnt, iov_ofs, min_buf, maximum_ethernet_hdr_len);
- filter_buf = min_buf;
+ } else {
+ iov_to_buf(iov, iovcnt, iov_ofs, &buf, sizeof(buf.l2_header));
}
- /* Discard oversized packets if !LPE and !SBP. */
- if (e1000x_is_oversized(core->mac, size)) {
- return orig_size;
- }
+ net_rx_pkt_set_packet_type(core->rx_pkt,
+ get_eth_packet_type(&buf.l2_header.eth));
+ net_rx_pkt_set_protocols(core->rx_pkt, iov, iovcnt, iov_ofs);
- ehdr = PKT_GET_ETH_HDR(filter_buf);
- net_rx_pkt_set_packet_type(core->rx_pkt, get_eth_packet_type(ehdr));
- net_rx_pkt_set_protocols(core->rx_pkt, filter_buf, size);
-
- queues = igb_receive_assign(core, ehdr, size, &rss_info, external_tx);
+ queues = igb_receive_assign(core, iov, iovcnt, iov_ofs,
+ &buf.l2_header, size,
+ &rss_info, &etqf, &ts, external_tx);
if (!queues) {
trace_e1000e_rx_flt_dropped();
return orig_size;
@@ -1678,36 +1754,46 @@
igb_rx_ring_init(core, &rxr, i);
+ if (!igb_rx_strip_vlan(core, rxr.i)) {
+ strip_vlan_index = -1;
+ } else if (core->mac[CTRL_EXT] & BIT(26)) {
+ strip_vlan_index = 1;
+ } else {
+ strip_vlan_index = 0;
+ }
+
net_rx_pkt_attach_iovec_ex(core->rx_pkt, iov, iovcnt, iov_ofs,
- igb_rx_strip_vlan(core, rxr.i),
- core->mac[VET] & 0xffff);
+ strip_vlan_index,
+ core->mac[VET] & 0xffff,
+ core->mac[VET] >> 16);
total_size = net_rx_pkt_get_total_len(core->rx_pkt) +
e1000x_fcs_len(core->mac);
if (!igb_has_rxbufs(core, rxr.i, total_size)) {
- n |= E1000_ICS_RXO;
+ causes |= E1000_ICS_RXO;
trace_e1000e_rx_not_written_to_guest(rxr.i->idx);
continue;
}
- n |= E1000_ICR_RXDW;
+ causes |= E1000_ICR_RXDW;
igb_rx_fix_l4_csum(core, core->rx_pkt);
- igb_write_packet_to_guest(core, core->rx_pkt, &rxr, &rss_info);
+ igb_write_packet_to_guest(core, core->rx_pkt, &rxr, &rss_info, etqf, ts);
/* Check if receive descriptor minimum threshold hit */
if (igb_rx_descr_threshold_hit(core, rxr.i)) {
- n |= E1000_ICS_RXDMT0;
+ causes |= E1000_ICS_RXDMT0;
}
- core->mac[EICR] |= igb_rx_wb_eic(core, rxr.i->idx);
+ ecauses |= igb_rx_wb_eic(core, rxr.i->idx);
trace_e1000e_rx_written_to_guest(rxr.i->idx);
}
- trace_e1000e_rx_interrupt_set(n);
- igb_set_interrupt_cause(core, n);
+ trace_e1000e_rx_interrupt_set(causes);
+ igb_raise_interrupts(core, EICR, ecauses);
+ igb_raise_interrupts(core, ICR, causes);
return orig_size;
}
@@ -1767,7 +1853,7 @@
}
if (core->mac[STATUS] != old_status) {
- igb_set_interrupt_cause(core, E1000_ICR_LSC);
+ igb_raise_interrupts(core, ICR, E1000_ICR_LSC);
}
}
@@ -1847,13 +1933,6 @@
}
}
-static inline void
-igb_clear_ims_bits(IGBCore *core, uint32_t bits)
-{
- trace_e1000e_irq_clear_ims(bits, core->mac[IMS], core->mac[IMS] & ~bits);
- core->mac[IMS] &= ~bits;
-}
-
static inline bool
igb_postpone_interrupt(IGBIntrDelayTimer *timer)
{
@@ -1876,10 +1955,8 @@
return igb_postpone_interrupt(&core->eitr[idx]);
}
-static void igb_send_msix(IGBCore *core)
+static void igb_send_msix(IGBCore *core, uint32_t causes)
{
- uint32_t causes = core->mac[EICR] & core->mac[EIMS];
- uint32_t effective_eiac;
int vector;
for (vector = 0; vector < IGB_INTR_NUM; ++vector) {
@@ -1887,10 +1964,6 @@
trace_e1000e_irq_msix_notify_vec(vector);
igb_msix_notify(core, vector);
-
- trace_e1000e_irq_icr_clear_eiac(core->mac[EICR], core->mac[EIAC]);
- effective_eiac = core->mac[EIAC] & BIT(vector);
- core->mac[EICR] &= ~effective_eiac;
}
}
}
@@ -1906,119 +1979,116 @@
trace_e1000e_irq_fix_icr_asserted(core->mac[ICR]);
}
-static void
-igb_update_interrupt_state(IGBCore *core)
+static void igb_raise_interrupts(IGBCore *core, size_t index, uint32_t causes)
{
- uint32_t icr;
- uint32_t causes;
+ uint32_t old_causes = core->mac[ICR] & core->mac[IMS];
+ uint32_t old_ecauses = core->mac[EICR] & core->mac[EIMS];
+ uint32_t raised_causes;
+ uint32_t raised_ecauses;
uint32_t int_alloc;
- icr = core->mac[ICR] & core->mac[IMS];
+ trace_e1000e_irq_set(index << 2,
+ core->mac[index], core->mac[index] | causes);
- if (msix_enabled(core->owner)) {
- if (icr) {
- causes = 0;
- if (icr & E1000_ICR_DRSTA) {
- int_alloc = core->mac[IVAR_MISC] & 0xff;
- if (int_alloc & E1000_IVAR_VALID) {
- causes |= BIT(int_alloc & 0x1f);
- }
+ core->mac[index] |= causes;
+
+ if (core->mac[GPIE] & E1000_GPIE_MSIX_MODE) {
+ raised_causes = core->mac[ICR] & core->mac[IMS] & ~old_causes;
+
+ if (raised_causes & E1000_ICR_DRSTA) {
+ int_alloc = core->mac[IVAR_MISC] & 0xff;
+ if (int_alloc & E1000_IVAR_VALID) {
+ core->mac[EICR] |= BIT(int_alloc & 0x1f);
}
- /* Check if other bits (excluding the TCP Timer) are enabled. */
- if (icr & ~E1000_ICR_DRSTA) {
- int_alloc = (core->mac[IVAR_MISC] >> 8) & 0xff;
- if (int_alloc & E1000_IVAR_VALID) {
- causes |= BIT(int_alloc & 0x1f);
- }
- trace_e1000e_irq_add_msi_other(core->mac[EICR]);
+ }
+ /* Check if other bits (excluding the TCP Timer) are enabled. */
+ if (raised_causes & ~E1000_ICR_DRSTA) {
+ int_alloc = (core->mac[IVAR_MISC] >> 8) & 0xff;
+ if (int_alloc & E1000_IVAR_VALID) {
+ core->mac[EICR] |= BIT(int_alloc & 0x1f);
}
- core->mac[EICR] |= causes;
}
- if ((core->mac[EICR] & core->mac[EIMS])) {
- igb_send_msix(core);
+ raised_ecauses = core->mac[EICR] & core->mac[EIMS] & ~old_ecauses;
+ if (!raised_ecauses) {
+ return;
}
+
+ igb_send_msix(core, raised_ecauses);
} else {
igb_fix_icr_asserted(core);
- if (icr) {
- core->mac[EICR] |= (icr & E1000_ICR_DRSTA) | E1000_EICR_OTHER;
- } else {
- core->mac[EICR] &= ~E1000_EICR_OTHER;
+ raised_causes = core->mac[ICR] & core->mac[IMS] & ~old_causes;
+ if (!raised_causes) {
+ return;
}
- trace_e1000e_irq_pending_interrupts(core->mac[ICR] & core->mac[IMS],
- core->mac[ICR], core->mac[IMS]);
+ core->mac[EICR] |= (raised_causes & E1000_ICR_DRSTA) | E1000_EICR_OTHER;
- if (msi_enabled(core->owner)) {
- if (icr) {
- msi_notify(core->owner, 0);
- }
+ if (msix_enabled(core->owner)) {
+ trace_e1000e_irq_msix_notify_vec(0);
+ msix_notify(core->owner, 0);
+ } else if (msi_enabled(core->owner)) {
+ trace_e1000e_irq_msi_notify(raised_causes);
+ msi_notify(core->owner, 0);
} else {
- if (icr) {
- igb_raise_legacy_irq(core);
- } else {
- igb_lower_legacy_irq(core);
- }
+ igb_raise_legacy_irq(core);
}
}
}
-static void
-igb_set_interrupt_cause(IGBCore *core, uint32_t val)
+static void igb_lower_interrupts(IGBCore *core, size_t index, uint32_t causes)
{
- trace_e1000e_irq_set_cause_entry(val, core->mac[ICR]);
+ trace_e1000e_irq_clear(index << 2,
+ core->mac[index], core->mac[index] & ~causes);
- core->mac[ICR] |= val;
+ core->mac[index] &= ~causes;
- trace_e1000e_irq_set_cause_exit(val, core->mac[ICR]);
+ trace_e1000e_irq_pending_interrupts(core->mac[ICR] & core->mac[IMS],
+ core->mac[ICR], core->mac[IMS]);
- igb_update_interrupt_state(core);
+ if (!(core->mac[ICR] & core->mac[IMS]) &&
+ !(core->mac[GPIE] & E1000_GPIE_MSIX_MODE)) {
+ core->mac[EICR] &= ~E1000_EICR_OTHER;
+
+ if (!msix_enabled(core->owner) && !msi_enabled(core->owner)) {
+ igb_lower_legacy_irq(core);
+ }
+ }
}
static void igb_set_eics(IGBCore *core, int index, uint32_t val)
{
bool msix = !!(core->mac[GPIE] & E1000_GPIE_MSIX_MODE);
+ uint32_t mask = msix ? E1000_EICR_MSIX_MASK : E1000_EICR_LEGACY_MASK;
trace_igb_irq_write_eics(val, msix);
-
- core->mac[EICS] |=
- val & (msix ? E1000_EICR_MSIX_MASK : E1000_EICR_LEGACY_MASK);
-
- /*
- * TODO: Move to igb_update_interrupt_state if EICS is modified in other
- * places.
- */
- core->mac[EICR] = core->mac[EICS];
-
- igb_update_interrupt_state(core);
+ igb_raise_interrupts(core, EICR, val & mask);
}
static void igb_set_eims(IGBCore *core, int index, uint32_t val)
{
bool msix = !!(core->mac[GPIE] & E1000_GPIE_MSIX_MODE);
+ uint32_t mask = msix ? E1000_EICR_MSIX_MASK : E1000_EICR_LEGACY_MASK;
trace_igb_irq_write_eims(val, msix);
-
- core->mac[EIMS] |=
- val & (msix ? E1000_EICR_MSIX_MASK : E1000_EICR_LEGACY_MASK);
-
- igb_update_interrupt_state(core);
+ igb_raise_interrupts(core, EIMS, val & mask);
}
static void mailbox_interrupt_to_vf(IGBCore *core, uint16_t vfn)
{
uint32_t ent = core->mac[VTIVAR_MISC + vfn];
+ uint32_t causes;
if ((ent & E1000_IVAR_VALID)) {
- core->mac[EICR] |= (ent & 0x3) << (22 - vfn * IGBVF_MSIX_VEC_NUM);
- igb_update_interrupt_state(core);
+ causes = (ent & 0x3) << (22 - vfn * IGBVF_MSIX_VEC_NUM);
+ igb_raise_interrupts(core, EICR, causes);
}
}
static void mailbox_interrupt_to_pf(IGBCore *core)
{
- igb_set_interrupt_cause(core, E1000_ICR_VMMB);
+ igb_raise_interrupts(core, ICR, E1000_ICR_VMMB);
}
static void igb_set_pfmailbox(IGBCore *core, int index, uint32_t val)
@@ -2109,13 +2179,12 @@
static void igb_set_eimc(IGBCore *core, int index, uint32_t val)
{
bool msix = !!(core->mac[GPIE] & E1000_GPIE_MSIX_MODE);
+ uint32_t mask = msix ? E1000_EICR_MSIX_MASK : E1000_EICR_LEGACY_MASK;
+
+ trace_igb_irq_write_eimc(val, msix);
/* Interrupts are disabled via a write to EIMC and reflected in EIMS. */
- core->mac[EIMS] &=
- ~(val & (msix ? E1000_EICR_MSIX_MASK : E1000_EICR_LEGACY_MASK));
-
- trace_igb_irq_write_eimc(val, core->mac[EIMS], msix);
- igb_update_interrupt_state(core);
+ igb_lower_interrupts(core, EIMS, val & mask);
}
static void igb_set_eiac(IGBCore *core, int index, uint32_t val)
@@ -2155,11 +2224,10 @@
* TODO: In IOV mode, only bit zero of this vector is available for the PF
* function.
*/
- core->mac[EICR] &=
- ~(val & (msix ? E1000_EICR_MSIX_MASK : E1000_EICR_LEGACY_MASK));
+ uint32_t mask = msix ? E1000_EICR_MSIX_MASK : E1000_EICR_LEGACY_MASK;
trace_igb_irq_write_eicr(val, msix);
- igb_update_interrupt_state(core);
+ igb_lower_interrupts(core, EICR, val & mask);
}
static void igb_set_vtctrl(IGBCore *core, int index, uint32_t val)
@@ -2259,7 +2327,7 @@
igb_update_flowctl_status(core);
/* signal link status change to the guest */
- igb_set_interrupt_cause(core, E1000_ICR_LSC);
+ igb_raise_interrupts(core, ICR, E1000_ICR_LSC);
}
}
@@ -2332,7 +2400,7 @@
core->mac[MDIC] = val | E1000_MDIC_READY;
if (val & E1000_MDIC_INT_EN) {
- igb_set_interrupt_cause(core, E1000_ICR_MDAC);
+ igb_raise_interrupts(core, ICR, E1000_ICR_MDAC);
}
}
@@ -2440,49 +2508,39 @@
igb_set_ics(IGBCore *core, int index, uint32_t val)
{
trace_e1000e_irq_write_ics(val);
- igb_set_interrupt_cause(core, val);
+ igb_raise_interrupts(core, ICR, val);
}
static void
igb_set_imc(IGBCore *core, int index, uint32_t val)
{
trace_e1000e_irq_ims_clear_set_imc(val);
- igb_clear_ims_bits(core, val);
- igb_update_interrupt_state(core);
+ igb_lower_interrupts(core, IMS, val);
}
static void
igb_set_ims(IGBCore *core, int index, uint32_t val)
{
- uint32_t valid_val = val & 0x77D4FBFD;
-
- trace_e1000e_irq_set_ims(val, core->mac[IMS], core->mac[IMS] | valid_val);
- core->mac[IMS] |= valid_val;
- igb_update_interrupt_state(core);
+ igb_raise_interrupts(core, IMS, val & 0x77D4FBFD);
}
-static void igb_commit_icr(IGBCore *core)
+static void igb_nsicr(IGBCore *core)
{
/*
- * If GPIE.NSICR = 0, then the copy of IAM to IMS will occur only if at
+ * If GPIE.NSICR = 0, then the clear of IMS will occur only if at
* least one bit is set in the IMS and there is a true interrupt as
* reflected in ICR.INTA.
*/
if ((core->mac[GPIE] & E1000_GPIE_NSICR) ||
(core->mac[IMS] && (core->mac[ICR] & E1000_ICR_INT_ASSERTED))) {
- igb_set_ims(core, IMS, core->mac[IAM]);
- } else {
- igb_update_interrupt_state(core);
+ igb_lower_interrupts(core, IMS, core->mac[IAM]);
}
}
static void igb_set_icr(IGBCore *core, int index, uint32_t val)
{
- uint32_t icr = core->mac[ICR] & ~val;
-
- trace_igb_irq_icr_write(val, core->mac[ICR], icr);
- core->mac[ICR] = icr;
- igb_commit_icr(core);
+ igb_nsicr(core);
+ igb_lower_interrupts(core, ICR, val);
}
static uint32_t
@@ -2533,21 +2591,21 @@
igb_mac_icr_read(IGBCore *core, int index)
{
uint32_t ret = core->mac[ICR];
- trace_e1000e_irq_icr_read_entry(ret);
if (core->mac[GPIE] & E1000_GPIE_NSICR) {
trace_igb_irq_icr_clear_gpie_nsicr();
- core->mac[ICR] = 0;
+ igb_lower_interrupts(core, ICR, 0xffffffff);
} else if (core->mac[IMS] == 0) {
trace_e1000e_irq_icr_clear_zero_ims();
- core->mac[ICR] = 0;
+ igb_lower_interrupts(core, ICR, 0xffffffff);
+ } else if (core->mac[ICR] & E1000_ICR_INT_ASSERTED) {
+ igb_lower_interrupts(core, ICR, 0xffffffff);
} else if (!msix_enabled(core->owner)) {
trace_e1000e_irq_icr_clear_nonmsix_icr_read();
- core->mac[ICR] = 0;
+ igb_lower_interrupts(core, ICR, 0xffffffff);
}
- trace_e1000e_irq_icr_read_exit(core->mac[ICR]);
- igb_commit_icr(core);
+ igb_nsicr(core);
return ret;
}
@@ -3282,6 +3340,8 @@
[EIAM] = igb_mac_readreg,
[IVAR0 ... IVAR0 + 7] = igb_mac_readreg,
igb_getreg(IVAR_MISC),
+ igb_getreg(TSYNCRXCFG),
+ [ETQF0 ... ETQF0 + 7] = igb_mac_readreg,
igb_getreg(VT_CTL),
[P2VMAILBOX0 ... P2VMAILBOX7] = igb_mac_readreg,
[V2PMAILBOX0 ... V2PMAILBOX7] = igb_mac_vfmailbox_read,
@@ -3689,6 +3749,8 @@
[EIMS] = igb_set_eims,
[IVAR0 ... IVAR0 + 7] = igb_mac_writereg,
igb_putreg(IVAR_MISC),
+ igb_putreg(TSYNCRXCFG),
+ [ETQF0 ... ETQF0 + 7] = igb_mac_writereg,
igb_putreg(VT_CTL),
[P2VMAILBOX0 ... P2VMAILBOX7] = igb_set_pfmailbox,
[V2PMAILBOX0 ... V2PMAILBOX7] = igb_set_vfmailbox,
@@ -3955,7 +4017,7 @@
core->vmstate = qemu_add_vm_change_state_handler(igb_vm_state_change, core);
for (i = 0; i < IGB_NUM_QUEUES; i++) {
- net_tx_pkt_init(&core->tx[i].tx_pkt, NULL, E1000E_MAX_TX_FRAGS);
+ net_tx_pkt_init(&core->tx[i].tx_pkt, E1000E_MAX_TX_FRAGS);
}
net_rx_pkt_init(&core->rx_pkt);
@@ -3980,7 +4042,6 @@
qemu_del_vm_change_state_handler(core->vmstate);
for (i = 0; i < IGB_NUM_QUEUES; i++) {
- net_tx_pkt_reset(core->tx[i].tx_pkt, NULL);
net_tx_pkt_uninit(core->tx[i].tx_pkt);
}
@@ -4073,54 +4134,54 @@
[VMOLR0 ... VMOLR0 + 7] = 0x2600 | E1000_VMOLR_STRCRC,
[RPLOLR] = E1000_RPLOLR_STRCRC,
[RLPML] = 0x2600,
- [TXCTL0] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL1] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL2] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL3] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL4] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL5] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL6] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL7] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL8] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL9] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL10] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL11] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL12] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL13] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL14] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
- [TXCTL15] = E1000_DCA_TXCTRL_DATA_RRO_EN |
- E1000_DCA_TXCTRL_TX_WB_RO_EN |
- E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL0] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL1] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL2] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL3] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL4] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL5] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL6] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL7] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL8] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL9] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL10] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL11] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL12] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL13] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL14] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
+ [TXCTL15] = E1000_DCA_TXCTRL_DATA_RRO_EN |
+ E1000_DCA_TXCTRL_TX_WB_RO_EN |
+ E1000_DCA_TXCTRL_DESC_RRO_EN,
};
static void igb_reset(IGBCore *core, bool sw)
@@ -4159,7 +4220,6 @@
for (i = 0; i < ARRAY_SIZE(core->tx); i++) {
tx = &core->tx[i];
- net_tx_pkt_reset(tx->tx_pkt, NULL);
memset(tx->ctx, 0, sizeof(tx->ctx));
tx->first = true;
tx->skip_cp = false;
diff --git a/hw/net/igb_regs.h b/hw/net/igb_regs.h
index c5c5b3c..82ff195 100644
--- a/hw/net/igb_regs.h
+++ b/hw/net/igb_regs.h
@@ -42,11 +42,6 @@
} wb;
};
-#define E1000_ADVTXD_DTYP_CTXT 0x00200000 /* Advanced Context Descriptor */
-#define E1000_ADVTXD_DTYP_DATA 0x00300000 /* Advanced Data Descriptor */
-#define E1000_ADVTXD_DCMD_DEXT 0x20000000 /* Descriptor Extension (1=Adv) */
-#define E1000_ADVTXD_DCMD_TSE 0x80000000 /* TCP/UDP Segmentation Enable */
-
#define E1000_ADVTXD_POTS_IXSM 0x00000100 /* Insert TCP/UDP Checksum */
#define E1000_ADVTXD_POTS_TXSM 0x00000200 /* Insert TCP/UDP Checksum */
@@ -151,6 +146,10 @@
#define IGB_82576_VF_DEV_ID 0x10CA
#define IGB_I350_VF_DEV_ID 0x1520
+/* VLAN info */
+#define IGB_TX_FLAGS_VLAN_MASK 0xffff0000
+#define IGB_TX_FLAGS_VLAN_SHIFT 16
+
/* from igb/e1000_82575.h */
#define E1000_MRQC_ENABLE_RSS_MQ 0x00000002
@@ -160,6 +159,29 @@
#define E1000_MRQC_RSS_FIELD_IPV6_UDP 0x00800000
#define E1000_MRQC_RSS_FIELD_IPV6_UDP_EX 0x01000000
+/* Adv Transmit Descriptor Config Masks */
+#define E1000_ADVTXD_MAC_TSTAMP 0x00080000 /* IEEE1588 Timestamp packet */
+#define E1000_ADVTXD_DTYP_CTXT 0x00200000 /* Advanced Context Descriptor */
+#define E1000_ADVTXD_DTYP_DATA 0x00300000 /* Advanced Data Descriptor */
+#define E1000_ADVTXD_DCMD_EOP 0x01000000 /* End of Packet */
+#define E1000_ADVTXD_DCMD_IFCS 0x02000000 /* Insert FCS (Ethernet CRC) */
+#define E1000_ADVTXD_DCMD_RS 0x08000000 /* Report Status */
+#define E1000_ADVTXD_DCMD_DEXT 0x20000000 /* Descriptor extension (1=Adv) */
+#define E1000_ADVTXD_DCMD_VLE 0x40000000 /* VLAN pkt enable */
+#define E1000_ADVTXD_DCMD_TSE 0x80000000 /* TCP Seg enable */
+#define E1000_ADVTXD_PAYLEN_SHIFT 14 /* Adv desc PAYLEN shift */
+
+#define E1000_ADVTXD_MACLEN_SHIFT 9 /* Adv ctxt desc mac len shift */
+#define E1000_ADVTXD_TUCMD_L4T_UDP 0x00000000 /* L4 Packet TYPE of UDP */
+#define E1000_ADVTXD_TUCMD_IPV4 0x00000400 /* IP Packet Type: 1=IPv4 */
+#define E1000_ADVTXD_TUCMD_L4T_TCP 0x00000800 /* L4 Packet TYPE of TCP */
+#define E1000_ADVTXD_TUCMD_L4T_SCTP 0x00001000 /* L4 packet TYPE of SCTP */
+/* IPSec Encrypt Enable for ESP */
+#define E1000_ADVTXD_L4LEN_SHIFT 8 /* Adv ctxt L4LEN shift */
+#define E1000_ADVTXD_MSS_SHIFT 16 /* Adv ctxt MSS shift */
+/* Adv ctxt IPSec SA IDX mask */
+/* Adv ctxt IPSec ESP len mask */
+
/* Additional Transmit Descriptor Control definitions */
#define E1000_TXDCTL_QUEUE_ENABLE 0x02000000 /* Enable specific Tx Queue */
@@ -188,6 +210,15 @@
#define E1000_DCA_TXCTRL_CPUID_SHIFT 24 /* Tx CPUID now in the last byte */
#define E1000_DCA_RXCTRL_CPUID_SHIFT 24 /* Rx CPUID now in the last byte */
+/* ETQF register bit definitions */
+#define E1000_ETQF_FILTER_ENABLE BIT(26)
+#define E1000_ETQF_1588 BIT(30)
+#define E1000_ETQF_IMM_INT BIT(29)
+#define E1000_ETQF_QUEUE_ENABLE BIT(31)
+#define E1000_ETQF_QUEUE_SHIFT 16
+#define E1000_ETQF_QUEUE_MASK 0x00070000
+#define E1000_ETQF_ETYPE_MASK 0x0000FFFF
+
#define E1000_DTXSWC_MAC_SPOOF_MASK 0x000000FF /* Per VF MAC spoof control */
#define E1000_DTXSWC_VLAN_SPOOF_MASK 0x0000FF00 /* Per VF VLAN spoof control */
#define E1000_DTXSWC_LLE_MASK 0x00FF0000 /* Per VF Local LB enables */
@@ -291,6 +322,9 @@
/* E1000_EITR_CNT_IGNR is only for 82576 and newer */
#define E1000_EITR_CNT_IGNR 0x80000000 /* Don't reset counters on write */
+#define E1000_TSYNCTXCTL_VALID 0x00000001 /* tx timestamp valid */
+#define E1000_TSYNCTXCTL_ENABLED 0x00000010 /* enable tx timestampping */
+
/* PCI Express Control */
#define E1000_GCR_CMPL_TMOUT_MASK 0x0000F000
#define E1000_GCR_CMPL_TMOUT_10ms 0x00001000
@@ -362,6 +396,20 @@
#define E1000_FRTIMER 0x01048 /* Free Running Timer - RW */
#define E1000_FCRTV 0x02460 /* Flow Control Refresh Timer Value - RW */
+#define E1000_TSYNCRXCFG 0x05F50 /* Time Sync Rx Configuration - RW */
+
+/* Filtering Registers */
+#define E1000_SAQF(_n) (0x5980 + 4 * (_n))
+#define E1000_DAQF(_n) (0x59A0 + 4 * (_n))
+#define E1000_SPQF(_n) (0x59C0 + 4 * (_n))
+#define E1000_FTQF(_n) (0x59E0 + 4 * (_n))
+#define E1000_SAQF0 E1000_SAQF(0)
+#define E1000_DAQF0 E1000_DAQF(0)
+#define E1000_SPQF0 E1000_SPQF(0)
+#define E1000_FTQF0 E1000_FTQF(0)
+#define E1000_SYNQF(_n) (0x055FC + (4 * (_n))) /* SYN Packet Queue Fltr */
+#define E1000_ETQF(_n) (0x05CB0 + (4 * (_n))) /* EType Queue Fltr */
+
#define E1000_RQDPC(_n) (0x0C030 + ((_n) * 0x40))
#define E1000_RXPBS 0x02404 /* Rx Packet Buffer Size - RW */
@@ -637,10 +685,19 @@
#define E1000_RSS_QUEUE(reta, hash) (E1000_RETA_VAL(reta, hash) & 0x0F)
+#define E1000_MRQ_RSS_TYPE_IPV4UDP 7
+#define E1000_MRQ_RSS_TYPE_IPV6UDP 8
+
#define E1000_STATUS_IOV_MODE 0x00040000
#define E1000_STATUS_NUM_VFS_SHIFT 14
+#define E1000_ADVRXD_PKT_IP4 BIT(4)
+#define E1000_ADVRXD_PKT_IP6 BIT(6)
+#define E1000_ADVRXD_PKT_TCP BIT(8)
+#define E1000_ADVRXD_PKT_UDP BIT(9)
+#define E1000_ADVRXD_PKT_SCTP BIT(10)
+
static inline uint8_t igb_ivar_entry_rx(uint8_t i)
{
return i < 8 ? i * 4 : (i - 8) * 4 + 2;
diff --git a/hw/net/igbvf.c b/hw/net/igbvf.c
index 70beb7a..284ea61 100644
--- a/hw/net/igbvf.c
+++ b/hw/net/igbvf.c
@@ -50,15 +50,8 @@
#include "trace.h"
#include "qapi/error.h"
-#define TYPE_IGBVF "igbvf"
OBJECT_DECLARE_SIMPLE_TYPE(IgbVfState, IGBVF)
-#define IGBVF_MMIO_BAR_IDX (0)
-#define IGBVF_MSIX_BAR_IDX (3)
-
-#define IGBVF_MMIO_SIZE (16 * 1024)
-#define IGBVF_MSIX_SIZE (16 * 1024)
-
struct IgbVfState {
PCIDevice parent_obj;
diff --git a/hw/net/net_rx_pkt.c b/hw/net/net_rx_pkt.c
index 39cdea0..32e5f3f 100644
--- a/hw/net/net_rx_pkt.c
+++ b/hw/net/net_rx_pkt.c
@@ -16,6 +16,7 @@
*/
#include "qemu/osdep.h"
+#include "qemu/crc32c.h"
#include "trace.h"
#include "net_rx_pkt.h"
#include "net/checksum.h"
@@ -23,7 +24,10 @@
struct NetRxPkt {
struct virtio_net_hdr virt_hdr;
- uint8_t ehdr_buf[sizeof(struct eth_header) + sizeof(struct vlan_header)];
+ struct {
+ struct eth_header eth;
+ struct vlan_header vlan;
+ } ehdr_buf;
struct iovec *vec;
uint16_t vec_len_total;
uint16_t vec_len;
@@ -89,7 +93,7 @@
if (pkt->ehdr_buf_len) {
net_rx_pkt_iovec_realloc(pkt, iovcnt + 1);
- pkt->vec[0].iov_base = pkt->ehdr_buf;
+ pkt->vec[0].iov_base = &pkt->ehdr_buf;
pkt->vec[0].iov_len = pkt->ehdr_buf_len;
pkt->tot_len = pllen + pkt->ehdr_buf_len;
@@ -103,7 +107,7 @@
iov, iovcnt, ploff, pkt->tot_len);
}
- eth_get_protocols(pkt->vec, pkt->vec_len, &pkt->hasip4, &pkt->hasip6,
+ eth_get_protocols(pkt->vec, pkt->vec_len, 0, &pkt->hasip4, &pkt->hasip6,
&pkt->l3hdr_off, &pkt->l4hdr_off, &pkt->l5hdr_off,
&pkt->ip6hdr_info, &pkt->ip4hdr_info, &pkt->l4hdr_info);
@@ -120,7 +124,7 @@
assert(pkt);
if (strip_vlan) {
- pkt->ehdr_buf_len = eth_strip_vlan(iov, iovcnt, iovoff, pkt->ehdr_buf,
+ pkt->ehdr_buf_len = eth_strip_vlan(iov, iovcnt, iovoff, &pkt->ehdr_buf,
&ploff, &tci);
} else {
pkt->ehdr_buf_len = 0;
@@ -133,20 +137,17 @@
void net_rx_pkt_attach_iovec_ex(struct NetRxPkt *pkt,
const struct iovec *iov, int iovcnt,
- size_t iovoff, bool strip_vlan,
- uint16_t vet)
+ size_t iovoff, int strip_vlan_index,
+ uint16_t vet, uint16_t vet_ext)
{
uint16_t tci = 0;
uint16_t ploff = iovoff;
assert(pkt);
- if (strip_vlan) {
- pkt->ehdr_buf_len = eth_strip_vlan_ex(iov, iovcnt, iovoff, vet,
- pkt->ehdr_buf,
- &ploff, &tci);
- } else {
- pkt->ehdr_buf_len = 0;
- }
+ pkt->ehdr_buf_len = eth_strip_vlan_ex(iov, iovcnt, iovoff,
+ strip_vlan_index, vet, vet_ext,
+ &pkt->ehdr_buf,
+ &ploff, &tci);
pkt->tci = tci;
@@ -186,17 +187,13 @@
return pkt->tot_len;
}
-void net_rx_pkt_set_protocols(struct NetRxPkt *pkt, const void *data,
- size_t len)
+void net_rx_pkt_set_protocols(struct NetRxPkt *pkt,
+ const struct iovec *iov, size_t iovcnt,
+ size_t iovoff)
{
- const struct iovec iov = {
- .iov_base = (void *)data,
- .iov_len = len
- };
-
assert(pkt);
- eth_get_protocols(&iov, 1, &pkt->hasip4, &pkt->hasip6,
+ eth_get_protocols(iov, iovcnt, iovoff, &pkt->hasip4, &pkt->hasip6,
&pkt->l3hdr_off, &pkt->l4hdr_off, &pkt->l5hdr_off,
&pkt->ip6hdr_info, &pkt->ip4hdr_info, &pkt->l4hdr_info);
}
@@ -240,11 +237,6 @@
return &pkt->ip4hdr_info;
}
-eth_l4_hdr_info *net_rx_pkt_get_l4_info(struct NetRxPkt *pkt)
-{
- return &pkt->l4hdr_info;
-}
-
static inline void
_net_rx_rss_add_chunk(uint8_t *rss_input, size_t *bytes_written,
void *ptr, size_t size)
@@ -560,32 +552,73 @@
return csum;
}
+static bool
+_net_rx_pkt_validate_sctp_sum(struct NetRxPkt *pkt)
+{
+ size_t csum_off;
+ size_t off = pkt->l4hdr_off;
+ size_t vec_len = pkt->vec_len;
+ struct iovec *vec;
+ uint32_t calculated = 0;
+ uint32_t original;
+ bool valid;
+
+ for (vec = pkt->vec; vec->iov_len < off; vec++) {
+ off -= vec->iov_len;
+ vec_len--;
+ }
+
+ csum_off = off + 8;
+
+ if (!iov_to_buf(vec, vec_len, csum_off, &original, sizeof(original))) {
+ return false;
+ }
+
+ if (!iov_from_buf(vec, vec_len, csum_off,
+ &calculated, sizeof(calculated))) {
+ return false;
+ }
+
+ calculated = crc32c(0xffffffff,
+ (uint8_t *)vec->iov_base + off, vec->iov_len - off);
+ calculated = iov_crc32c(calculated ^ 0xffffffff, vec + 1, vec_len - 1);
+ valid = calculated == le32_to_cpu(original);
+ iov_from_buf(vec, vec_len, csum_off, &original, sizeof(original));
+
+ return valid;
+}
+
bool net_rx_pkt_validate_l4_csum(struct NetRxPkt *pkt, bool *csum_valid)
{
- uint16_t csum;
+ uint32_t csum;
trace_net_rx_pkt_l4_csum_validate_entry();
- if (pkt->l4hdr_info.proto != ETH_L4_HDR_PROTO_TCP &&
- pkt->l4hdr_info.proto != ETH_L4_HDR_PROTO_UDP) {
- trace_net_rx_pkt_l4_csum_validate_not_xxp();
- return false;
- }
-
- if (pkt->l4hdr_info.proto == ETH_L4_HDR_PROTO_UDP &&
- pkt->l4hdr_info.hdr.udp.uh_sum == 0) {
- trace_net_rx_pkt_l4_csum_validate_udp_with_no_checksum();
- return false;
- }
-
if (pkt->hasip4 && pkt->ip4hdr_info.fragment) {
trace_net_rx_pkt_l4_csum_validate_ip4_fragment();
return false;
}
- csum = _net_rx_pkt_calc_l4_csum(pkt);
+ switch (pkt->l4hdr_info.proto) {
+ case ETH_L4_HDR_PROTO_UDP:
+ if (pkt->l4hdr_info.hdr.udp.uh_sum == 0) {
+ trace_net_rx_pkt_l4_csum_validate_udp_with_no_checksum();
+ return false;
+ }
+ /* fall through */
+ case ETH_L4_HDR_PROTO_TCP:
+ csum = _net_rx_pkt_calc_l4_csum(pkt);
+ *csum_valid = ((csum == 0) || (csum == 0xFFFF));
+ break;
- *csum_valid = ((csum == 0) || (csum == 0xFFFF));
+ case ETH_L4_HDR_PROTO_SCTP:
+ *csum_valid = _net_rx_pkt_validate_sctp_sum(pkt);
+ break;
+
+ default:
+ trace_net_rx_pkt_l4_csum_validate_not_xxp();
+ return false;
+ }
trace_net_rx_pkt_l4_csum_validate_csum(*csum_valid);
diff --git a/hw/net/net_rx_pkt.h b/hw/net/net_rx_pkt.h
index d00b484..55ec67a 100644
--- a/hw/net/net_rx_pkt.h
+++ b/hw/net/net_rx_pkt.h
@@ -55,12 +55,14 @@
* parse and set packet analysis results
*
* @pkt: packet
- * @data: pointer to the data buffer to be parsed
- * @len: data length
+ * @iov: received data scatter-gather list
+ * @iovcnt: number of elements in iov
+ * @iovoff: data start offset in the iov
*
*/
-void net_rx_pkt_set_protocols(struct NetRxPkt *pkt, const void *data,
- size_t len);
+void net_rx_pkt_set_protocols(struct NetRxPkt *pkt,
+ const struct iovec *iov, size_t iovcnt,
+ size_t iovoff);
/**
* fetches packet analysis results
@@ -117,15 +119,6 @@
*/
eth_ip4_hdr_info *net_rx_pkt_get_ip4_info(struct NetRxPkt *pkt);
-/**
- * fetches L4 header analysis results
- *
- * Return: pointer to analysis results structure which is stored in internal
- * packet area.
- *
- */
-eth_l4_hdr_info *net_rx_pkt_get_l4_info(struct NetRxPkt *pkt);
-
typedef enum {
NetPktRssIpV4,
NetPktRssIpV4Tcp,
@@ -230,18 +223,19 @@
/**
* attach scatter-gather data to rx packet
*
-* @pkt: packet
-* @iov: received data scatter-gather list
-* @iovcnt number of elements in iov
-* @iovoff data start offset in the iov
-* @strip_vlan: should the module strip vlan from data
-* @vet: VLAN tag Ethernet type
+* @pkt: packet
+* @iov: received data scatter-gather list
+* @iovcnt: number of elements in iov
+* @iovoff: data start offset in the iov
+* @strip_vlan_index: index of Q tag if it is to be stripped. negative otherwise.
+* @vet: VLAN tag Ethernet type
+* @vet_ext: outer VLAN tag Ethernet type
*
*/
void net_rx_pkt_attach_iovec_ex(struct NetRxPkt *pkt,
- const struct iovec *iov, int iovcnt,
- size_t iovoff, bool strip_vlan,
- uint16_t vet);
+ const struct iovec *iov, int iovcnt,
+ size_t iovoff, int strip_vlan_index,
+ uint16_t vet, uint16_t vet_ext);
/**
* attach data to rx packet
diff --git a/hw/net/net_tx_pkt.c b/hw/net/net_tx_pkt.c
index 8dc8568..2e5f58b 100644
--- a/hw/net/net_tx_pkt.c
+++ b/hw/net/net_tx_pkt.c
@@ -16,12 +16,13 @@
*/
#include "qemu/osdep.h"
-#include "net_tx_pkt.h"
+#include "qemu/crc32c.h"
#include "net/eth.h"
#include "net/checksum.h"
#include "net/tap.h"
#include "net/net.h"
#include "hw/pci/pci_device.h"
+#include "net_tx_pkt.h"
enum {
NET_TX_PKT_VHDR_FRAG = 0,
@@ -32,8 +33,6 @@
/* TX packet private context */
struct NetTxPkt {
- PCIDevice *pci_dev;
-
struct virtio_net_hdr virt_hdr;
struct iovec *raw;
@@ -42,7 +41,10 @@
struct iovec *vec;
- uint8_t l2_hdr[ETH_MAX_L2_HDR_LEN];
+ struct {
+ struct eth_header eth;
+ struct vlan_header vlan[3];
+ } l2_hdr;
union {
struct ip_header ip;
struct ip6_header ip6;
@@ -59,13 +61,10 @@
uint8_t l4proto;
};
-void net_tx_pkt_init(struct NetTxPkt **pkt, PCIDevice *pci_dev,
- uint32_t max_frags)
+void net_tx_pkt_init(struct NetTxPkt **pkt, uint32_t max_frags)
{
struct NetTxPkt *p = g_malloc0(sizeof *p);
- p->pci_dev = pci_dev;
-
p->vec = g_new(struct iovec, max_frags + NET_TX_PKT_PL_START_FRAG);
p->raw = g_new(struct iovec, max_frags);
@@ -137,6 +136,23 @@
pkt->virt_hdr.csum_offset, &csum, sizeof(csum));
}
+bool net_tx_pkt_update_sctp_checksum(struct NetTxPkt *pkt)
+{
+ uint32_t csum = 0;
+ struct iovec *pl_start_frag = pkt->vec + NET_TX_PKT_PL_START_FRAG;
+
+ if (iov_from_buf(pl_start_frag, pkt->payload_frags, 8, &csum, sizeof(csum)) < sizeof(csum)) {
+ return false;
+ }
+
+ csum = cpu_to_le32(iov_crc32c(0xffffffff, pl_start_frag, pkt->payload_frags));
+ if (iov_from_buf(pl_start_frag, pkt->payload_frags, 8, &csum, sizeof(csum)) < sizeof(csum)) {
+ return false;
+ }
+
+ return true;
+}
+
static void net_tx_pkt_calculate_hdr_len(struct NetTxPkt *pkt)
{
pkt->hdr_len = pkt->vec[NET_TX_PKT_L2HDR_FRAG].iov_len +
@@ -370,24 +386,17 @@
void net_tx_pkt_setup_vlan_header_ex(struct NetTxPkt *pkt,
uint16_t vlan, uint16_t vlan_ethtype)
{
- bool is_new;
assert(pkt);
- eth_setup_vlan_headers_ex(pkt->vec[NET_TX_PKT_L2HDR_FRAG].iov_base,
- vlan, vlan_ethtype, &is_new);
+ eth_setup_vlan_headers(pkt->vec[NET_TX_PKT_L2HDR_FRAG].iov_base,
+ &pkt->vec[NET_TX_PKT_L2HDR_FRAG].iov_len,
+ vlan, vlan_ethtype);
- /* update l2hdrlen */
- if (is_new) {
- pkt->hdr_len += sizeof(struct vlan_header);
- pkt->vec[NET_TX_PKT_L2HDR_FRAG].iov_len +=
- sizeof(struct vlan_header);
- }
+ pkt->hdr_len += sizeof(struct vlan_header);
}
-bool net_tx_pkt_add_raw_fragment(struct NetTxPkt *pkt, hwaddr pa,
- size_t len)
+bool net_tx_pkt_add_raw_fragment(struct NetTxPkt *pkt, void *base, size_t len)
{
- hwaddr mapped_len = 0;
struct iovec *ventry;
assert(pkt);
@@ -395,23 +404,12 @@
return false;
}
- if (!len) {
- return true;
- }
-
ventry = &pkt->raw[pkt->raw_frags];
- mapped_len = len;
+ ventry->iov_base = base;
+ ventry->iov_len = len;
+ pkt->raw_frags++;
- ventry->iov_base = pci_dma_map(pkt->pci_dev, pa,
- &mapped_len, DMA_DIRECTION_TO_DEVICE);
-
- if ((ventry->iov_base != NULL) && (len == mapped_len)) {
- ventry->iov_len = mapped_len;
- pkt->raw_frags++;
- return true;
- } else {
- return false;
- }
+ return true;
}
bool net_tx_pkt_has_fragments(struct NetTxPkt *pkt)
@@ -445,7 +443,8 @@
#endif
}
-void net_tx_pkt_reset(struct NetTxPkt *pkt, PCIDevice *pci_dev)
+void net_tx_pkt_reset(struct NetTxPkt *pkt,
+ NetTxPktFreeFrag callback, void *context)
{
int i;
@@ -465,17 +464,37 @@
assert(pkt->raw);
for (i = 0; i < pkt->raw_frags; i++) {
assert(pkt->raw[i].iov_base);
- pci_dma_unmap(pkt->pci_dev, pkt->raw[i].iov_base,
- pkt->raw[i].iov_len, DMA_DIRECTION_TO_DEVICE, 0);
+ callback(context, pkt->raw[i].iov_base, pkt->raw[i].iov_len);
}
}
- pkt->pci_dev = pci_dev;
pkt->raw_frags = 0;
pkt->hdr_len = 0;
pkt->l4proto = 0;
}
+void net_tx_pkt_unmap_frag_pci(void *context, void *base, size_t len)
+{
+ pci_dma_unmap(context, base, len, DMA_DIRECTION_TO_DEVICE, 0);
+}
+
+bool net_tx_pkt_add_raw_fragment_pci(struct NetTxPkt *pkt, PCIDevice *pci_dev,
+ dma_addr_t pa, size_t len)
+{
+ dma_addr_t mapped_len = len;
+ void *base = pci_dma_map(pci_dev, pa, &mapped_len, DMA_DIRECTION_TO_DEVICE);
+ if (!base) {
+ return false;
+ }
+
+ if (mapped_len != len || !net_tx_pkt_add_raw_fragment(pkt, base, len)) {
+ net_tx_pkt_unmap_frag_pci(pci_dev, base, mapped_len);
+ return false;
+ }
+
+ return true;
+}
+
static void net_tx_pkt_do_sw_csum(struct NetTxPkt *pkt,
struct iovec *iov, uint32_t iov_len,
uint16_t csl)
@@ -697,7 +716,7 @@
}
static bool net_tx_pkt_do_sw_fragmentation(struct NetTxPkt *pkt,
- NetTxPktCallback callback,
+ NetTxPktSend callback,
void *context)
{
uint8_t gso_type = pkt->virt_hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN;
@@ -794,7 +813,7 @@
}
bool net_tx_pkt_send_custom(struct NetTxPkt *pkt, bool offload,
- NetTxPktCallback callback, void *context)
+ NetTxPktSend callback, void *context)
{
assert(pkt);
diff --git a/hw/net/net_tx_pkt.h b/hw/net/net_tx_pkt.h
index e5ce6f2..0a716e7 100644
--- a/hw/net/net_tx_pkt.h
+++ b/hw/net/net_tx_pkt.h
@@ -26,17 +26,16 @@
struct NetTxPkt;
-typedef void (* NetTxPktCallback)(void *, const struct iovec *, int, const struct iovec *, int);
+typedef void (*NetTxPktFreeFrag)(void *, void *, size_t);
+typedef void (*NetTxPktSend)(void *, const struct iovec *, int, const struct iovec *, int);
/**
* Init function for tx packet functionality
*
* @pkt: packet pointer
- * @pci_dev: PCI device processing this packet
* @max_frags: max tx ip fragments
*/
-void net_tx_pkt_init(struct NetTxPkt **pkt, PCIDevice *pci_dev,
- uint32_t max_frags);
+void net_tx_pkt_init(struct NetTxPkt **pkt, uint32_t max_frags);
/**
* Clean all tx packet resources.
@@ -95,12 +94,11 @@
* populate data fragment into pkt context.
*
* @pkt: packet
- * @pa: physical address of fragment
+ * @base: pointer to fragment
* @len: length of fragment
*
*/
-bool net_tx_pkt_add_raw_fragment(struct NetTxPkt *pkt, hwaddr pa,
- size_t len);
+bool net_tx_pkt_add_raw_fragment(struct NetTxPkt *pkt, void *base, size_t len);
/**
* Fix ip header fields and calculate IP header and pseudo header checksums.
@@ -119,6 +117,14 @@
void net_tx_pkt_update_ip_hdr_checksum(struct NetTxPkt *pkt);
/**
+ * Calculate the SCTP checksum.
+ *
+ * @pkt: packet
+ *
+ */
+bool net_tx_pkt_update_sctp_checksum(struct NetTxPkt *pkt);
+
+/**
* get length of all populated data.
*
* @pkt: packet
@@ -148,10 +154,30 @@
* reset tx packet private context (needed to be called between packets)
*
* @pkt: packet
- * @dev: PCI device processing the next packet
- *
+ * @callback: function to free the fragments
+ * @context: pointer to be passed to the callback
*/
-void net_tx_pkt_reset(struct NetTxPkt *pkt, PCIDevice *dev);
+void net_tx_pkt_reset(struct NetTxPkt *pkt,
+ NetTxPktFreeFrag callback, void *context);
+
+/**
+ * Unmap a fragment mapped from a PCI device.
+ *
+ * @context: PCI device owning fragment
+ * @base: pointer to fragment
+ * @len: length of fragment
+ */
+void net_tx_pkt_unmap_frag_pci(void *context, void *base, size_t len);
+
+/**
+ * map data fragment from PCI device and populate it into pkt context.
+ *
+ * @pci_dev: PCI device owning fragment
+ * @pa: physical address of fragment
+ * @len: length of fragment
+ */
+bool net_tx_pkt_add_raw_fragment_pci(struct NetTxPkt *pkt, PCIDevice *pci_dev,
+ dma_addr_t pa, size_t len);
/**
* Send packet to qemu. handles sw offloads if vhdr is not supported.
@@ -173,7 +199,7 @@
* @ret: operation result
*/
bool net_tx_pkt_send_custom(struct NetTxPkt *pkt, bool offload,
- NetTxPktCallback callback, void *context);
+ NetTxPktSend callback, void *context);
/**
* parse raw packet data and analyze offload requirements.
diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
index 5a5aaf8..5f1a4d3 100644
--- a/hw/net/rtl8139.c
+++ b/hw/net/rtl8139.c
@@ -2154,6 +2154,9 @@
int large_send_mss = (txdw0 >> CP_TC_LGSEN_MSS_SHIFT) &
CP_TC_LGSEN_MSS_MASK;
+ if (large_send_mss == 0) {
+ goto skip_offload;
+ }
DPRINTF("+++ C+ mode offloaded task TSO IP data %d "
"frame data %d specified MSS=%d\n",
diff --git a/hw/net/trace-events b/hw/net/trace-events
index d35554f..e4a98b2 100644
--- a/hw/net/trace-events
+++ b/hw/net/trace-events
@@ -106,6 +106,8 @@
# e1000x_common.c
e1000x_rx_can_recv_disabled(bool link_up, bool rx_enabled, bool pci_master) "link_up: %d, rx_enabled %d, pci_master %d"
e1000x_vlan_is_vlan_pkt(bool is_vlan_pkt, uint16_t eth_proto, uint16_t vet) "Is VLAN packet: %d, ETH proto: 0x%X, VET: 0x%X"
+e1000x_rx_flt_vlan_mismatch(uint16_t vid) "VID mismatch: 0x%X"
+e1000x_rx_flt_vlan_match(uint16_t vid) "VID match: 0x%X"
e1000x_rx_flt_ucast_match(uint32_t idx, uint8_t b0, uint8_t b1, uint8_t b2, uint8_t b3, uint8_t b4, uint8_t b5) "unicast match[%d]: %02x:%02x:%02x:%02x:%02x:%02x"
e1000x_rx_flt_ucast_mismatch(uint8_t b0, uint8_t b1, uint8_t b2, uint8_t b3, uint8_t b4, uint8_t b5) "unicast mismatch: %02x:%02x:%02x:%02x:%02x:%02x"
e1000x_rx_flt_inexact_mismatch(uint8_t b0, uint8_t b1, uint8_t b2, uint8_t b3, uint8_t b4, uint8_t b5, uint32_t mo, uint32_t mta, uint32_t mta_val) "inexact mismatch: %02x:%02x:%02x:%02x:%02x:%02x MO %d MTA[%d] 0x%x"
@@ -154,8 +156,6 @@
e1000e_rx_can_recv(void) "Can receive"
e1000e_rx_has_buffers(int ridx, uint32_t free_desc, size_t total_size, uint32_t desc_buf_size) "ring #%d: free descr: %u, packet size %zu, descr buffer size %u"
e1000e_rx_null_descriptor(void) "Null RX descriptor!!"
-e1000e_rx_flt_vlan_mismatch(uint16_t vid) "VID mismatch: 0x%X"
-e1000e_rx_flt_vlan_match(uint16_t vid) "VID match: 0x%X"
e1000e_rx_desc_ps_read(uint64_t a0, uint64_t a1, uint64_t a2, uint64_t a3) "buffers: [0x%"PRIx64", 0x%"PRIx64", 0x%"PRIx64", 0x%"PRIx64"]"
e1000e_rx_desc_ps_write(uint16_t a0, uint16_t a1, uint16_t a2, uint16_t a3) "bytes written: [%u, %u, %u, %u]"
e1000e_rx_desc_buff_sizes(uint32_t b0, uint32_t b1, uint32_t b2, uint32_t b3) "buffer sizes: [%u, %u, %u, %u]"
@@ -179,7 +179,7 @@
e1000e_rx_rss_type(uint32_t type) "RSS type is %u"
e1000e_rx_rss_ip4(int l4hdr_proto, uint32_t mrqc, bool tcpipv4_enabled, bool ipv4_enabled) "RSS IPv4: L4 header protocol %d, mrqc 0x%X, tcpipv4 enabled %d, ipv4 enabled %d"
e1000e_rx_rss_ip6_rfctl(uint32_t rfctl) "RSS IPv6: rfctl 0x%X"
-e1000e_rx_rss_ip6(bool ex_dis, bool new_ex_dis, int l4hdr_proto, bool has_ext_headers, bool ex_dst_valid, bool ex_src_valid, uint32_t mrqc, bool tcpipv6_enabled, bool ipv6ex_enabled, bool ipv6_enabled) "RSS IPv6: ex_dis: %d, new_ex_dis: %d, L4 header protocol %d, has_ext_headers %d, ex_dst_valid %d, ex_src_valid %d, mrqc 0x%X, tcpipv6 enabled %d, ipv6ex enabled %d, ipv6 enabled %d"
+e1000e_rx_rss_ip6(bool ex_dis, bool new_ex_dis, int l4hdr_proto, bool has_ext_headers, bool ex_dst_valid, bool ex_src_valid, uint32_t mrqc, bool tcpipv6ex_enabled, bool ipv6ex_enabled, bool ipv6_enabled) "RSS IPv6: ex_dis: %d, new_ex_dis: %d, L4 header protocol %d, has_ext_headers %d, ex_dst_valid %d, ex_src_valid %d, mrqc 0x%X, tcpipv6ex enabled %d, ipv6ex enabled %d, ipv6 enabled %d"
e1000e_rx_metadata_protocols(bool hasip4, bool hasip6, int l4hdr_protocol) "protocols: ip4: %d, ip6: %d, l4hdr: %d"
e1000e_rx_metadata_vlan(uint16_t vlan_tag) "VLAN tag is 0x%X"
@@ -205,21 +205,16 @@
e1000e_irq_legacy_notify(bool level) "IRQ line state: %d"
e1000e_irq_msix_notify_vec(uint32_t vector) "MSI-X notify vector 0x%x"
e1000e_irq_postponed_by_xitr(uint32_t reg) "Interrupt postponed by [E]ITR register 0x%x"
-e1000e_irq_clear_ims(uint32_t bits, uint32_t old_ims, uint32_t new_ims) "Clearing IMS bits 0x%x: 0x%x --> 0x%x"
-e1000e_irq_set_ims(uint32_t bits, uint32_t old_ims, uint32_t new_ims) "Setting IMS bits 0x%x: 0x%x --> 0x%x"
+e1000e_irq_clear(uint32_t offset, uint32_t old, uint32_t new) "Clearing interrupt register 0x%x: 0x%x --> 0x%x"
+e1000e_irq_set(uint32_t offset, uint32_t old, uint32_t new) "Setting interrupt register 0x%x: 0x%x --> 0x%x"
e1000e_irq_fix_icr_asserted(uint32_t new_val) "ICR_ASSERTED bit fixed: 0x%x"
e1000e_irq_add_msi_other(uint32_t new_val) "ICR_OTHER bit added: 0x%x"
e1000e_irq_pending_interrupts(uint32_t pending, uint32_t icr, uint32_t ims) "ICR PENDING: 0x%x (ICR: 0x%x, IMS: 0x%x)"
-e1000e_irq_set_cause_entry(uint32_t val, uint32_t icr) "Going to set IRQ cause 0x%x, ICR: 0x%x"
-e1000e_irq_set_cause_exit(uint32_t val, uint32_t icr) "Set IRQ cause 0x%x, ICR: 0x%x"
-e1000e_irq_icr_write(uint32_t bits, uint32_t old_icr, uint32_t new_icr) "Clearing ICR bits 0x%x: 0x%x --> 0x%x"
e1000e_irq_write_ics(uint32_t val) "Adding ICR bits 0x%x"
e1000e_irq_icr_process_iame(void) "Clearing IMS bits due to IAME"
e1000e_irq_read_ics(uint32_t ics) "Current ICS: 0x%x"
e1000e_irq_read_ims(uint32_t ims) "Current IMS: 0x%x"
e1000e_irq_icr_clear_nonmsix_icr_read(void) "Clearing ICR on read due to non MSI-X int"
-e1000e_irq_icr_read_entry(uint32_t icr) "Starting ICR read. Current ICR: 0x%x"
-e1000e_irq_icr_read_exit(uint32_t icr) "Ending ICR read. Current ICR: 0x%x"
e1000e_irq_icr_clear_zero_ims(void) "Clearing ICR on read due to zero IMS"
e1000e_irq_icr_clear_iame(void) "Clearing ICR on read due to IAME"
e1000e_irq_iam_clear_eiame(uint32_t iam, uint32_t cause) "Clearing IMS due to EIAME, IAM: 0x%X, cause: 0x%X"
@@ -235,7 +230,6 @@
e1000e_irq_eitr_set(uint32_t eitr_num, uint32_t val) "EITR[%u] = %u"
e1000e_irq_itr_set(uint32_t val) "ITR = %u"
e1000e_irq_fire_all_timers(uint32_t val) "Firing all delay/throttling timers on all interrupts enable (0x%X written to IMS)"
-e1000e_irq_adding_delayed_causes(uint32_t val, uint32_t icr) "Merging delayed causes 0x%X to ICR 0x%X"
e1000e_irq_msix_pending_clearing(uint32_t cause, uint32_t int_cfg, uint32_t vec) "Clearing MSI-X pending bit for cause 0x%x, IVAR config 0x%x, vector %u"
e1000e_wrn_msix_vec_wrong(uint32_t cause, uint32_t cfg) "Invalid configuration for cause 0x%x: 0x%x"
@@ -288,12 +282,11 @@
igb_rx_metadata_rss(uint32_t rss) "RSS data: 0x%X"
igb_irq_icr_clear_gpie_nsicr(void) "Clearing ICR on read due to GPIE.NSICR enabled"
-igb_irq_icr_write(uint32_t bits, uint32_t old_icr, uint32_t new_icr) "Clearing ICR bits 0x%x: 0x%x --> 0x%x"
igb_irq_set_iam(uint32_t icr) "Update IAM: 0x%x"
igb_irq_read_iam(uint32_t icr) "Current IAM: 0x%x"
igb_irq_write_eics(uint32_t val, bool msix) "Update EICS: 0x%x MSI-X: %d"
igb_irq_write_eims(uint32_t val, bool msix) "Update EIMS: 0x%x MSI-X: %d"
-igb_irq_write_eimc(uint32_t val, uint32_t eims, bool msix) "Update EIMC: 0x%x EIMS: 0x%x MSI-X: %d"
+igb_irq_write_eimc(uint32_t val, bool msix) "Update EIMC: 0x%x MSI-X: %d"
igb_irq_write_eiac(uint32_t val) "Update EIAC: 0x%x"
igb_irq_write_eiam(uint32_t val, bool msix) "Update EIAM: 0x%x MSI-X: %d"
igb_irq_write_eicr(uint32_t val, bool msix) "Update EICR: 0x%x MSI-X: %d"
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 8ce239a..6df6b73 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -1834,9 +1834,12 @@
VIRTIO_NET_HASH_REPORT_UDPv6,
VIRTIO_NET_HASH_REPORT_UDPv6_EX
};
+ struct iovec iov = {
+ .iov_base = (void *)buf,
+ .iov_len = size
+ };
- net_rx_pkt_set_protocols(pkt, buf + n->host_hdr_len,
- size - n->host_hdr_len);
+ net_rx_pkt_set_protocols(pkt, &iov, 1, n->host_hdr_len);
net_rx_pkt_get_protocols(pkt, &hasip4, &hasip6, &l4hdr_proto);
net_hash_type = virtio_net_get_hash_type(hasip4, hasip6, l4hdr_proto,
n->rss_data.hash_types);
diff --git a/hw/net/vmxnet3.c b/hw/net/vmxnet3.c
index f7b874c..18b9edf 100644
--- a/hw/net/vmxnet3.c
+++ b/hw/net/vmxnet3.c
@@ -651,9 +651,8 @@
data_len = (txd.len > 0) ? txd.len : VMXNET3_MAX_TX_BUF_SIZE;
data_pa = txd.addr;
- if (!net_tx_pkt_add_raw_fragment(s->tx_pkt,
- data_pa,
- data_len)) {
+ if (!net_tx_pkt_add_raw_fragment_pci(s->tx_pkt, PCI_DEVICE(s),
+ data_pa, data_len)) {
s->skip_current_tx_pkt = true;
}
}
@@ -678,9 +677,12 @@
vmxnet3_complete_packet(s, qidx, txd_idx);
s->tx_sop = true;
s->skip_current_tx_pkt = false;
- net_tx_pkt_reset(s->tx_pkt, PCI_DEVICE(s));
+ net_tx_pkt_reset(s->tx_pkt,
+ net_tx_pkt_unmap_frag_pci, PCI_DEVICE(s));
}
}
+
+ net_tx_pkt_reset(s->tx_pkt, net_tx_pkt_unmap_frag_pci, PCI_DEVICE(s));
}
static inline void
@@ -1159,7 +1161,6 @@
{
if (s->device_active) {
VMW_CBPRN("Deactivating vmxnet3...");
- net_tx_pkt_reset(s->tx_pkt, PCI_DEVICE(s));
net_tx_pkt_uninit(s->tx_pkt);
net_rx_pkt_uninit(s->rx_pkt);
s->device_active = false;
@@ -1519,7 +1520,7 @@
/* Preallocate TX packet wrapper */
VMW_CFPRN("Max TX fragments is %u", s->max_tx_frags);
- net_tx_pkt_init(&s->tx_pkt, PCI_DEVICE(s), s->max_tx_frags);
+ net_tx_pkt_init(&s->tx_pkt, s->max_tx_frags);
net_rx_pkt_init(&s->rx_pkt);
/* Read rings memory locations for RX queues */
@@ -2001,7 +2002,12 @@
get_eth_packet_type(PKT_GET_ETH_HDR(buf)));
if (vmxnet3_rx_filter_may_indicate(s, buf, size)) {
- net_rx_pkt_set_protocols(s->rx_pkt, buf, size);
+ struct iovec iov = {
+ .iov_base = (void *)buf,
+ .iov_len = size
+ };
+
+ net_rx_pkt_set_protocols(s->rx_pkt, &iov, 1, 0);
vmxnet3_rx_need_csum_calculate(s->rx_pkt, buf, size);
net_rx_pkt_attach_data(s->rx_pkt, buf, size, s->rx_vlan_stripping);
bytes_indicated = vmxnet3_indicate_packet(s) ? size : -1;
@@ -2399,7 +2405,7 @@
{
VMXNET3State *s = opaque;
- net_tx_pkt_init(&s->tx_pkt, PCI_DEVICE(s), s->max_tx_frags);
+ net_tx_pkt_init(&s->tx_pkt, s->max_tx_frags);
net_rx_pkt_init(&s->rx_pkt);
if (s->msix_used) {
diff --git a/include/net/eth.h b/include/net/eth.h
index c5ae449..3b80b6e 100644
--- a/include/net/eth.h
+++ b/include/net/eth.h
@@ -32,6 +32,8 @@
#define ETH_ALEN 6
#define ETH_HLEN 14
#define ETH_ZLEN 60 /* Min. octets in frame without FCS */
+#define ETH_FCS_LEN 4
+#define ETH_MTU 1500
struct eth_header {
uint8_t h_dest[ETH_ALEN]; /* destination eth addr */
@@ -222,6 +224,7 @@
#define IP_HEADER_VERSION_6 (6)
#define IP_PROTO_TCP (6)
#define IP_PROTO_UDP (17)
+#define IP_PROTO_SCTP (132)
#define IPTOS_ECN_MASK 0x03
#define IPTOS_ECN(x) ((x) & IPTOS_ECN_MASK)
#define IPTOS_ECN_CE 0x03
@@ -312,10 +315,10 @@
}
static inline uint32_t
-eth_get_l2_hdr_length_iov(const struct iovec *iov, int iovcnt)
+eth_get_l2_hdr_length_iov(const struct iovec *iov, size_t iovcnt, size_t iovoff)
{
uint8_t p[sizeof(struct eth_header) + sizeof(struct vlan_header)];
- size_t copied = iov_to_buf(iov, iovcnt, 0, p, ARRAY_SIZE(p));
+ size_t copied = iov_to_buf(iov, iovcnt, iovoff, p, ARRAY_SIZE(p));
if (copied < ARRAY_SIZE(p)) {
return copied;
@@ -340,26 +343,19 @@
size_t
eth_strip_vlan(const struct iovec *iov, int iovcnt, size_t iovoff,
- uint8_t *new_ehdr_buf,
+ void *new_ehdr_buf,
uint16_t *payload_offset, uint16_t *tci);
size_t
-eth_strip_vlan_ex(const struct iovec *iov, int iovcnt, size_t iovoff,
- uint16_t vet, uint8_t *new_ehdr_buf,
+eth_strip_vlan_ex(const struct iovec *iov, int iovcnt, size_t iovoff, int index,
+ uint16_t vet, uint16_t vet_ext, void *new_ehdr_buf,
uint16_t *payload_offset, uint16_t *tci);
uint16_t
eth_get_l3_proto(const struct iovec *l2hdr_iov, int iovcnt, size_t l2hdr_len);
-void eth_setup_vlan_headers_ex(struct eth_header *ehdr, uint16_t vlan_tag,
- uint16_t vlan_ethtype, bool *is_new);
-
-static inline void
-eth_setup_vlan_headers(struct eth_header *ehdr, uint16_t vlan_tag,
- bool *is_new)
-{
- eth_setup_vlan_headers_ex(ehdr, vlan_tag, ETH_P_VLAN, is_new);
-}
+void eth_setup_vlan_headers(struct eth_header *ehdr, size_t *ehdr_size,
+ uint16_t vlan_tag, uint16_t vlan_ethtype);
uint8_t eth_get_gso_type(uint16_t l3_proto, uint8_t *l3_hdr, uint8_t l4proto);
@@ -384,7 +380,8 @@
typedef enum EthL4HdrProto {
ETH_L4_HDR_PROTO_INVALID,
ETH_L4_HDR_PROTO_TCP,
- ETH_L4_HDR_PROTO_UDP
+ ETH_L4_HDR_PROTO_UDP,
+ ETH_L4_HDR_PROTO_SCTP
} EthL4HdrProto;
typedef struct eth_l4_hdr_info_st {
@@ -397,7 +394,7 @@
bool has_tcp_data;
} eth_l4_hdr_info;
-void eth_get_protocols(const struct iovec *iov, int iovcnt,
+void eth_get_protocols(const struct iovec *iov, size_t iovcnt, size_t iovoff,
bool *hasip4, bool *hasip6,
size_t *l3hdr_off,
size_t *l4hdr_off,
diff --git a/include/qemu/crc32c.h b/include/qemu/crc32c.h
index 5b78884..88b4d2b 100644
--- a/include/qemu/crc32c.h
+++ b/include/qemu/crc32c.h
@@ -30,5 +30,6 @@
uint32_t crc32c(uint32_t crc, const uint8_t *data, unsigned int length);
+uint32_t iov_crc32c(uint32_t crc, const struct iovec *iov, size_t iov_cnt);
#endif
diff --git a/net/eth.c b/net/eth.c
index 70bcd8e..649e66b 100644
--- a/net/eth.c
+++ b/net/eth.c
@@ -21,26 +21,16 @@
#include "net/checksum.h"
#include "net/tap.h"
-void eth_setup_vlan_headers_ex(struct eth_header *ehdr, uint16_t vlan_tag,
- uint16_t vlan_ethtype, bool *is_new)
+void eth_setup_vlan_headers(struct eth_header *ehdr, size_t *ehdr_size,
+ uint16_t vlan_tag, uint16_t vlan_ethtype)
{
struct vlan_header *vhdr = PKT_GET_VLAN_HDR(ehdr);
- switch (be16_to_cpu(ehdr->h_proto)) {
- case ETH_P_VLAN:
- case ETH_P_DVLAN:
- /* vlan hdr exists */
- *is_new = false;
- break;
-
- default:
- /* No VLAN header, put a new one */
- vhdr->h_proto = ehdr->h_proto;
- ehdr->h_proto = cpu_to_be16(vlan_ethtype);
- *is_new = true;
- break;
- }
+ memmove(vhdr + 1, vhdr, *ehdr_size - ETH_HLEN);
vhdr->h_tci = cpu_to_be16(vlan_tag);
+ vhdr->h_proto = ehdr->h_proto;
+ ehdr->h_proto = cpu_to_be16(vlan_ethtype);
+ *ehdr_size += sizeof(*vhdr);
}
uint8_t
@@ -136,7 +126,7 @@
return l4len > TCP_HEADER_DATA_OFFSET(tcp);
}
-void eth_get_protocols(const struct iovec *iov, int iovcnt,
+void eth_get_protocols(const struct iovec *iov, size_t iovcnt, size_t iovoff,
bool *hasip4, bool *hasip6,
size_t *l3hdr_off,
size_t *l4hdr_off,
@@ -147,26 +137,24 @@
{
int proto;
bool fragment = false;
- size_t l2hdr_len = eth_get_l2_hdr_length_iov(iov, iovcnt);
size_t input_size = iov_size(iov, iovcnt);
size_t copied;
uint8_t ip_p;
*hasip4 = *hasip6 = false;
+ *l3hdr_off = iovoff + eth_get_l2_hdr_length_iov(iov, iovcnt, iovoff);
l4hdr_info->proto = ETH_L4_HDR_PROTO_INVALID;
- proto = eth_get_l3_proto(iov, iovcnt, l2hdr_len);
-
- *l3hdr_off = l2hdr_len;
+ proto = eth_get_l3_proto(iov, iovcnt, *l3hdr_off);
if (proto == ETH_P_IP) {
struct ip_header *iphdr = &ip4hdr_info->ip4_hdr;
- if (input_size < l2hdr_len) {
+ if (input_size < *l3hdr_off) {
return;
}
- copied = iov_to_buf(iov, iovcnt, l2hdr_len, iphdr, sizeof(*iphdr));
+ copied = iov_to_buf(iov, iovcnt, *l3hdr_off, iphdr, sizeof(*iphdr));
if (copied < sizeof(*iphdr) ||
IP_HEADER_VERSION(iphdr) != IP_HEADER_VERSION_4) {
return;
@@ -175,17 +163,17 @@
*hasip4 = true;
ip_p = iphdr->ip_p;
ip4hdr_info->fragment = IP4_IS_FRAGMENT(iphdr);
- *l4hdr_off = l2hdr_len + IP_HDR_GET_LEN(iphdr);
+ *l4hdr_off = *l3hdr_off + IP_HDR_GET_LEN(iphdr);
fragment = ip4hdr_info->fragment;
} else if (proto == ETH_P_IPV6) {
- if (!eth_parse_ipv6_hdr(iov, iovcnt, l2hdr_len, ip6hdr_info)) {
+ if (!eth_parse_ipv6_hdr(iov, iovcnt, *l3hdr_off, ip6hdr_info)) {
return;
}
*hasip6 = true;
ip_p = ip6hdr_info->l4proto;
- *l4hdr_off = l2hdr_len + ip6hdr_info->full_hdr_len;
+ *l4hdr_off = *l3hdr_off + ip6hdr_info->full_hdr_len;
fragment = ip6hdr_info->fragment;
} else {
return;
@@ -223,16 +211,20 @@
*l5hdr_off = *l4hdr_off + sizeof(l4hdr_info->hdr.udp);
}
break;
+
+ case IP_PROTO_SCTP:
+ l4hdr_info->proto = ETH_L4_HDR_PROTO_SCTP;
+ break;
}
}
size_t
eth_strip_vlan(const struct iovec *iov, int iovcnt, size_t iovoff,
- uint8_t *new_ehdr_buf,
+ void *new_ehdr_buf,
uint16_t *payload_offset, uint16_t *tci)
{
struct vlan_header vlan_hdr;
- struct eth_header *new_ehdr = (struct eth_header *) new_ehdr_buf;
+ struct eth_header *new_ehdr = new_ehdr_buf;
size_t copied = iov_to_buf(iov, iovcnt, iovoff,
new_ehdr, sizeof(*new_ehdr));
@@ -277,36 +269,50 @@
}
size_t
-eth_strip_vlan_ex(const struct iovec *iov, int iovcnt, size_t iovoff,
- uint16_t vet, uint8_t *new_ehdr_buf,
+eth_strip_vlan_ex(const struct iovec *iov, int iovcnt, size_t iovoff, int index,
+ uint16_t vet, uint16_t vet_ext, void *new_ehdr_buf,
uint16_t *payload_offset, uint16_t *tci)
{
struct vlan_header vlan_hdr;
- struct eth_header *new_ehdr = (struct eth_header *) new_ehdr_buf;
+ uint16_t *new_ehdr_proto;
+ size_t new_ehdr_size;
+ size_t copied;
- size_t copied = iov_to_buf(iov, iovcnt, iovoff,
- new_ehdr, sizeof(*new_ehdr));
+ switch (index) {
+ case 0:
+ new_ehdr_proto = &PKT_GET_ETH_HDR(new_ehdr_buf)->h_proto;
+ new_ehdr_size = sizeof(struct eth_header);
+ copied = iov_to_buf(iov, iovcnt, iovoff, new_ehdr_buf, new_ehdr_size);
+ break;
- if (copied < sizeof(*new_ehdr)) {
+ case 1:
+ new_ehdr_proto = &PKT_GET_VLAN_HDR(new_ehdr_buf)->h_proto;
+ new_ehdr_size = sizeof(struct eth_header) + sizeof(struct vlan_header);
+ copied = iov_to_buf(iov, iovcnt, iovoff, new_ehdr_buf, new_ehdr_size);
+ if (be16_to_cpu(PKT_GET_ETH_HDR(new_ehdr_buf)->h_proto) != vet_ext) {
+ return 0;
+ }
+ break;
+
+ default:
return 0;
}
- if (be16_to_cpu(new_ehdr->h_proto) == vet) {
- copied = iov_to_buf(iov, iovcnt, iovoff + sizeof(*new_ehdr),
- &vlan_hdr, sizeof(vlan_hdr));
-
- if (copied < sizeof(vlan_hdr)) {
- return 0;
- }
-
- new_ehdr->h_proto = vlan_hdr.h_proto;
-
- *tci = be16_to_cpu(vlan_hdr.h_tci);
- *payload_offset = iovoff + sizeof(*new_ehdr) + sizeof(vlan_hdr);
- return sizeof(struct eth_header);
+ if (copied < new_ehdr_size || be16_to_cpu(*new_ehdr_proto) != vet) {
+ return 0;
}
- return 0;
+ copied = iov_to_buf(iov, iovcnt, iovoff + new_ehdr_size,
+ &vlan_hdr, sizeof(vlan_hdr));
+ if (copied < sizeof(vlan_hdr)) {
+ return 0;
+ }
+
+ *new_ehdr_proto = vlan_hdr.h_proto;
+ *payload_offset = iovoff + new_ehdr_size + sizeof(vlan_hdr);
+ *tci = be16_to_cpu(vlan_hdr.h_tci);
+
+ return new_ehdr_size;
}
void
diff --git a/scripts/ci/org.centos/stream/8/x86_64/test-avocado b/scripts/ci/org.centos/stream/8/x86_64/test-avocado
index 7bb5b31..73e7a1a 100755
--- a/scripts/ci/org.centos/stream/8/x86_64/test-avocado
+++ b/scripts/ci/org.centos/stream/8/x86_64/test-avocado
@@ -30,7 +30,8 @@
tests/avocado/cpu_queries.py:QueryCPUModelExpansion.test \
tests/avocado/empty_cpu_model.py:EmptyCPUModel.test \
tests/avocado/hotplug_cpu.py:HotPlugCPU.test \
- tests/avocado/igb.py:IGB.test \
+ tests/avocado/netdev-ethtool.py:NetDevEthtool.test_igb \
+ tests/avocado/netdev-ethtool.py:NetDevEthtool.test_igb_nomsi \
tests/avocado/info_usernet.py:InfoUsernet.test_hostfwd \
tests/avocado/intel_iommu.py:IntelIOMMU.test_intel_iommu \
tests/avocado/intel_iommu.py:IntelIOMMU.test_intel_iommu_pt \
diff --git a/tests/avocado/netdev-ethtool.py b/tests/avocado/netdev-ethtool.py
index f7e9464..5f33288 100644
--- a/tests/avocado/netdev-ethtool.py
+++ b/tests/avocado/netdev-ethtool.py
@@ -7,7 +7,6 @@
from avocado import skip
from avocado_qemu import QemuSystemTest
-from avocado_qemu import exec_command, exec_command_and_wait_for_pattern
from avocado_qemu import wait_for_console_pattern
class NetDevEthtool(QemuSystemTest):
@@ -30,7 +29,7 @@
# URL into a unique one
return self.fetch_asset(name=name, locations=(url), asset_hash=sha1)
- def common_test_code(self, netdev, extra_args=None, kvm=False):
+ def common_test_code(self, netdev, extra_args=None):
# This custom kernel has drivers for all the supported network
# devices we can emulate in QEMU
@@ -58,9 +57,6 @@
'-drive', drive,
'-device', netdev)
- if kvm:
- self.vm.add_args('-accel', 'kvm')
-
self.vm.set_console(console_index=0)
self.vm.launch()
@@ -71,10 +67,6 @@
# no need to gracefully shutdown, just finish
self.vm.kill()
- # Skip testing for MSI for now. Allegedly it was fixed by:
- # 28e96556ba (igb: Allocate MSI-X vector when testing)
- # but I'm seeing oops in the kernel
- @skip("Kernel bug with MSI enabled")
def test_igb(self):
"""
:avocado: tags=device:igb
@@ -87,13 +79,6 @@
"""
self.common_test_code("igb", "pci=nomsi")
- def test_igb_nomsi_kvm(self):
- """
- :avocado: tags=device:igb
- """
- self.require_accelerator('kvm')
- self.common_test_code("igb", "pci=nomsi", True)
-
# It seems the other popular cards we model in QEMU currently fail
# the pattern test with:
#
diff --git a/tests/qtest/libqos/igb.c b/tests/qtest/libqos/igb.c
index 12fb531..a603468 100644
--- a/tests/qtest/libqos/igb.c
+++ b/tests/qtest/libqos/igb.c
@@ -114,6 +114,7 @@
e1000e_macreg_write(&d->e1000e, E1000_RCTL, E1000_RCTL_EN);
/* Enable all interrupts */
+ e1000e_macreg_write(&d->e1000e, E1000_GPIE, E1000_GPIE_MSIX_MODE);
e1000e_macreg_write(&d->e1000e, E1000_IMS, 0xFFFFFFFF);
e1000e_macreg_write(&d->e1000e, E1000_EIMS, 0xFFFFFFFF);
diff --git a/util/crc32c.c b/util/crc32c.c
index 762657d..ea7f345 100644
--- a/util/crc32c.c
+++ b/util/crc32c.c
@@ -113,3 +113,11 @@
return crc^0xffffffff;
}
+uint32_t iov_crc32c(uint32_t crc, const struct iovec *iov, size_t iov_cnt)
+{
+ while (iov_cnt--) {
+ crc = crc32c(crc, iov->iov_base, iov->iov_len) ^ 0xffffffff;
+ iov++;
+ }
+ return crc ^ 0xffffffff;
+}
