From b9731850d746e528d317097f907f27116798d7fe Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 12 Dec 2018 10:16:16 +0100 Subject: pci/pcie: stop plug/unplug if the slot is locked We better stop right away. For now, errors would be partially ignored (so the guest might get informed or the device might get unplugged), although actual plug/unplug will be reported as failed to the user. While at it, properly move the check to the pre_plug handler for the plug case, as we can test the slot state before the device will be realized. Reviewed-by: Igor Mammedov Reviewed-by: David Gibson Signed-off-by: David Hildenbrand Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- include/hw/pci/pcie.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/hw/pci/pcie.h b/include/hw/pci/pcie.h index cd318646a2..5b82a0d244 100644 --- a/include/hw/pci/pcie.h +++ b/include/hw/pci/pcie.h @@ -132,6 +132,8 @@ void pcie_ari_init(PCIDevice *dev, uint16_t offset, uint16_t nextfn); void pcie_dev_ser_num_init(PCIDevice *dev, uint16_t offset, uint64_t ser_num); void pcie_ats_init(PCIDevice *dev, uint16_t offset); +void pcie_cap_slot_pre_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, + Error **errp); void pcie_cap_slot_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp); void pcie_cap_slot_unplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, -- cgit v1.2.3-55-g7522 From 2974e916df8790fa4db2edac99627f5e3c79d7a7 Mon Sep 17 00:00:00 2001 From: Yuri Benditovich Date: Thu, 3 Jan 2019 15:12:29 +0200 Subject: virtio-net: support RSC v4/v6 tcp traffic for Windows HCK This commit adds implementation of RX packets coalescing, compatible with requirements of Windows Hardware compatibility kit. The device enables feature VIRTIO_NET_F_RSC_EXT in host features if it supports extended RSC functionality as defined in the specification. This feature requires at least one of VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6. Windows guest driver acks this feature only if VIRTIO_NET_F_CTRL_GUEST_OFFLOADS is also present. If the guest driver acks VIRTIO_NET_F_RSC_EXT feature, the device coalesces TCPv4 and TCPv6 packets (if respective VIRTIO_NET_F_GUEST_TSO feature is on, populates extended RSC information in virtio header and sets VIRTIO_NET_HDR_F_RSC_INFO bit in header flags. The device does not recalculate checksums in the coalesced packet, so they are not valid. In this case: All the data packets in a tcp connection are cached to a single buffer in every receive interval, and will be sent out via a timer, the 'virtio_net_rsc_timeout' controls the interval, this value may impact the performance and response time of tcp connection, 50000(50us) is an experience value to gain a performance improvement, since the whql test sends packets every 100us, so '300000(300us)' passes the test case, it is the default value as well, tune it via the command line parameter 'rsc_interval' within 'virtio-net-pci' device, for example, to launch a guest with interval set as '500000': 'virtio-net-pci,netdev=hostnet1,bus=pci.0,id=net1,mac=00, guest_rsc_ext=on,rsc_interval=500000' The timer will only be triggered if the packets pool is not empty, and it'll drain off all the cached packets. 'NetRscChain' is used to save the segments of IPv4/6 in a VirtIONet device. A new segment becomes a 'Candidate' as well as it passed sanity check, the main handler of TCP includes TCP window update, duplicated ACK check and the real data coalescing. An 'Candidate' segment means: 1. Segment is within current window and the sequence is the expected one. 2. 'ACK' of the segment is in the valid window. Sanity check includes: 1. Incorrect version in IP header 2. An IP options or IP fragment 3. Not a TCP packet 4. Sanity size check to prevent buffer overflow attack. 5. An ECN packet Even though, there might more cases should be considered such as ip identification other flags, while it breaks the test because windows set it to the same even it's not a fragment. Normally it includes 2 typical ways to handle a TCP control flag, 'bypass' and 'finalize', 'bypass' means should be sent out directly, while 'finalize' means the packets should also be bypassed, but this should be done after search for the same connection packets in the pool and drain all of them out, this is to avoid out of order fragment. All the 'SYN' packets will be bypassed since this always begin a new' connection, other flags such 'URG/FIN/RST/CWR/ECE' will trigger a finalization, because this normally happens upon a connection is going to be closed, an 'URG' packet also finalize current coalescing unit. Statistics can be used to monitor the basic coalescing status, the 'out of order' and 'out of window' means how many retransmitting packets, thus describe the performance intuitively. Difference between ip v4 and v6 processing: Fragment length in ipv4 header includes itself, while it's not included for ipv6, thus means ipv6 can carry a real 65535 payload. Note that main goal of implementing this feature in software is to create reference setup for certification tests. In such setups guest migration is not required, so the coalesced packets not yet delivered to the guest will be lost in case of migration. Signed-off-by: Wei Xu Signed-off-by: Yuri Benditovich Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/net/virtio-net.c | 667 ++++++++++++++++++++++++++++++++++++++++- include/hw/virtio/virtio-net.h | 83 +++++ include/net/eth.h | 2 + 3 files changed, 751 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index e37fc34839..9e5fb1ed62 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -41,6 +41,47 @@ #define VIRTIO_NET_RX_QUEUE_MIN_SIZE VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE #define VIRTIO_NET_TX_QUEUE_MIN_SIZE VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE +#define VIRTIO_NET_IP4_ADDR_SIZE 8 /* ipv4 saddr + daddr */ + +#define VIRTIO_NET_TCP_FLAG 0x3F +#define VIRTIO_NET_TCP_HDR_LENGTH 0xF000 + +/* IPv4 max payload, 16 bits in the header */ +#define VIRTIO_NET_MAX_IP4_PAYLOAD (65535 - sizeof(struct ip_header)) +#define VIRTIO_NET_MAX_TCP_PAYLOAD 65535 + +/* header length value in ip header without option */ +#define VIRTIO_NET_IP4_HEADER_LENGTH 5 + +#define VIRTIO_NET_IP6_ADDR_SIZE 32 /* ipv6 saddr + daddr */ +#define VIRTIO_NET_MAX_IP6_PAYLOAD VIRTIO_NET_MAX_TCP_PAYLOAD + +/* Purge coalesced packets timer interval, This value affects the performance + a lot, and should be tuned carefully, '300000'(300us) is the recommended + value to pass the WHQL test, '50000' can gain 2x netperf throughput with + tso/gso/gro 'off'. */ +#define VIRTIO_NET_RSC_DEFAULT_INTERVAL 300000 + +/* temporary until standard header include it */ +#if !defined(VIRTIO_NET_HDR_F_RSC_INFO) + +#define VIRTIO_NET_HDR_F_RSC_INFO 4 /* rsc_ext data in csum_ fields */ +#define VIRTIO_NET_F_RSC_EXT 38 + +static inline __virtio16 *virtio_net_rsc_ext_num_packets( + struct virtio_net_hdr *hdr) +{ + return &hdr->csum_start; +} + +static inline __virtio16 *virtio_net_rsc_ext_num_dupacks( + struct virtio_net_hdr *hdr) +{ + return &hdr->csum_offset; +} + +#endif + /* * Calculate the number of bytes up to and including the given 'field' of * 'container'. @@ -628,6 +669,7 @@ static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features, if (!get_vhost_net(nc->peer)) { return features; } + features = vhost_net_get_features(get_vhost_net(nc->peer), features); vdev->backend_features = features; @@ -701,6 +743,11 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features) virtio_has_feature(features, VIRTIO_F_VERSION_1)); + n->rsc4_enabled = virtio_has_feature(features, VIRTIO_NET_F_RSC_EXT) && + virtio_has_feature(features, VIRTIO_NET_F_GUEST_TSO4); + n->rsc6_enabled = virtio_has_feature(features, VIRTIO_NET_F_RSC_EXT) && + virtio_has_feature(features, VIRTIO_NET_F_GUEST_TSO6); + if (n->has_vnet_hdr) { n->curr_guest_offloads = virtio_net_guest_offloads_by_features(features); @@ -781,6 +828,12 @@ static int virtio_net_handle_offloads(VirtIONet *n, uint8_t cmd, return VIRTIO_NET_ERR; } + n->rsc4_enabled = virtio_has_feature(offloads, VIRTIO_NET_F_RSC_EXT) && + virtio_has_feature(offloads, VIRTIO_NET_F_GUEST_TSO4); + n->rsc6_enabled = virtio_has_feature(offloads, VIRTIO_NET_F_RSC_EXT) && + virtio_has_feature(offloads, VIRTIO_NET_F_GUEST_TSO6); + virtio_clear_feature(&offloads, VIRTIO_NET_F_RSC_EXT); + supported_offloads = virtio_net_supported_guest_offloads(n); if (offloads & ~supported_offloads) { return VIRTIO_NET_ERR; @@ -1292,7 +1345,7 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, return size; } -static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, +static ssize_t virtio_net_do_receive(NetClientState *nc, const uint8_t *buf, size_t size) { ssize_t r; @@ -1303,6 +1356,612 @@ static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, return r; } +static void virtio_net_rsc_extract_unit4(VirtioNetRscChain *chain, + const uint8_t *buf, + VirtioNetRscUnit *unit) +{ + uint16_t ip_hdrlen; + struct ip_header *ip; + + ip = (struct ip_header *)(buf + chain->n->guest_hdr_len + + sizeof(struct eth_header)); + unit->ip = (void *)ip; + ip_hdrlen = (ip->ip_ver_len & 0xF) << 2; + unit->ip_plen = &ip->ip_len; + unit->tcp = (struct tcp_header *)(((uint8_t *)unit->ip) + ip_hdrlen); + unit->tcp_hdrlen = (htons(unit->tcp->th_offset_flags) & 0xF000) >> 10; + unit->payload = htons(*unit->ip_plen) - ip_hdrlen - unit->tcp_hdrlen; +} + +static void virtio_net_rsc_extract_unit6(VirtioNetRscChain *chain, + const uint8_t *buf, + VirtioNetRscUnit *unit) +{ + struct ip6_header *ip6; + + ip6 = (struct ip6_header *)(buf + chain->n->guest_hdr_len + + sizeof(struct eth_header)); + unit->ip = ip6; + unit->ip_plen = &(ip6->ip6_ctlun.ip6_un1.ip6_un1_plen); + unit->tcp = (struct tcp_header *)(((uint8_t *)unit->ip)\ + + sizeof(struct ip6_header)); + unit->tcp_hdrlen = (htons(unit->tcp->th_offset_flags) & 0xF000) >> 10; + + /* There is a difference between payload lenght in ipv4 and v6, + ip header is excluded in ipv6 */ + unit->payload = htons(*unit->ip_plen) - unit->tcp_hdrlen; +} + +static size_t virtio_net_rsc_drain_seg(VirtioNetRscChain *chain, + VirtioNetRscSeg *seg) +{ + int ret; + struct virtio_net_hdr *h; + + h = (struct virtio_net_hdr *)seg->buf; + h->flags = 0; + h->gso_type = VIRTIO_NET_HDR_GSO_NONE; + + if (seg->is_coalesced) { + *virtio_net_rsc_ext_num_packets(h) = seg->packets; + *virtio_net_rsc_ext_num_dupacks(h) = seg->dup_ack; + h->flags = VIRTIO_NET_HDR_F_RSC_INFO; + if (chain->proto == ETH_P_IP) { + h->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; + } else { + h->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + } + } + + ret = virtio_net_do_receive(seg->nc, seg->buf, seg->size); + QTAILQ_REMOVE(&chain->buffers, seg, next); + g_free(seg->buf); + g_free(seg); + + return ret; +} + +static void virtio_net_rsc_purge(void *opq) +{ + VirtioNetRscSeg *seg, *rn; + VirtioNetRscChain *chain = (VirtioNetRscChain *)opq; + + QTAILQ_FOREACH_SAFE(seg, &chain->buffers, next, rn) { + if (virtio_net_rsc_drain_seg(chain, seg) == 0) { + chain->stat.purge_failed++; + continue; + } + } + + chain->stat.timer++; + if (!QTAILQ_EMPTY(&chain->buffers)) { + timer_mod(chain->drain_timer, + qemu_clock_get_ns(QEMU_CLOCK_HOST) + chain->n->rsc_timeout); + } +} + +static void virtio_net_rsc_cleanup(VirtIONet *n) +{ + VirtioNetRscChain *chain, *rn_chain; + VirtioNetRscSeg *seg, *rn_seg; + + QTAILQ_FOREACH_SAFE(chain, &n->rsc_chains, next, rn_chain) { + QTAILQ_FOREACH_SAFE(seg, &chain->buffers, next, rn_seg) { + QTAILQ_REMOVE(&chain->buffers, seg, next); + g_free(seg->buf); + g_free(seg); + } + + timer_del(chain->drain_timer); + timer_free(chain->drain_timer); + QTAILQ_REMOVE(&n->rsc_chains, chain, next); + g_free(chain); + } +} + +static void virtio_net_rsc_cache_buf(VirtioNetRscChain *chain, + NetClientState *nc, + const uint8_t *buf, size_t size) +{ + uint16_t hdr_len; + VirtioNetRscSeg *seg; + + hdr_len = chain->n->guest_hdr_len; + seg = g_malloc(sizeof(VirtioNetRscSeg)); + seg->buf = g_malloc(hdr_len + sizeof(struct eth_header) + + sizeof(struct ip6_header) + VIRTIO_NET_MAX_TCP_PAYLOAD); + memcpy(seg->buf, buf, size); + seg->size = size; + seg->packets = 1; + seg->dup_ack = 0; + seg->is_coalesced = 0; + seg->nc = nc; + + QTAILQ_INSERT_TAIL(&chain->buffers, seg, next); + chain->stat.cache++; + + switch (chain->proto) { + case ETH_P_IP: + virtio_net_rsc_extract_unit4(chain, seg->buf, &seg->unit); + break; + case ETH_P_IPV6: + virtio_net_rsc_extract_unit6(chain, seg->buf, &seg->unit); + break; + default: + g_assert_not_reached(); + } +} + +static int32_t virtio_net_rsc_handle_ack(VirtioNetRscChain *chain, + VirtioNetRscSeg *seg, + const uint8_t *buf, + struct tcp_header *n_tcp, + struct tcp_header *o_tcp) +{ + uint32_t nack, oack; + uint16_t nwin, owin; + + nack = htonl(n_tcp->th_ack); + nwin = htons(n_tcp->th_win); + oack = htonl(o_tcp->th_ack); + owin = htons(o_tcp->th_win); + + if ((nack - oack) >= VIRTIO_NET_MAX_TCP_PAYLOAD) { + chain->stat.ack_out_of_win++; + return RSC_FINAL; + } else if (nack == oack) { + /* duplicated ack or window probe */ + if (nwin == owin) { + /* duplicated ack, add dup ack count due to whql test up to 1 */ + chain->stat.dup_ack++; + return RSC_FINAL; + } else { + /* Coalesce window update */ + o_tcp->th_win = n_tcp->th_win; + chain->stat.win_update++; + return RSC_COALESCE; + } + } else { + /* pure ack, go to 'C', finalize*/ + chain->stat.pure_ack++; + return RSC_FINAL; + } +} + +static int32_t virtio_net_rsc_coalesce_data(VirtioNetRscChain *chain, + VirtioNetRscSeg *seg, + const uint8_t *buf, + VirtioNetRscUnit *n_unit) +{ + void *data; + uint16_t o_ip_len; + uint32_t nseq, oseq; + VirtioNetRscUnit *o_unit; + + o_unit = &seg->unit; + o_ip_len = htons(*o_unit->ip_plen); + nseq = htonl(n_unit->tcp->th_seq); + oseq = htonl(o_unit->tcp->th_seq); + + /* out of order or retransmitted. */ + if ((nseq - oseq) > VIRTIO_NET_MAX_TCP_PAYLOAD) { + chain->stat.data_out_of_win++; + return RSC_FINAL; + } + + data = ((uint8_t *)n_unit->tcp) + n_unit->tcp_hdrlen; + if (nseq == oseq) { + if ((o_unit->payload == 0) && n_unit->payload) { + /* From no payload to payload, normal case, not a dup ack or etc */ + chain->stat.data_after_pure_ack++; + goto coalesce; + } else { + return virtio_net_rsc_handle_ack(chain, seg, buf, + n_unit->tcp, o_unit->tcp); + } + } else if ((nseq - oseq) != o_unit->payload) { + /* Not a consistent packet, out of order */ + chain->stat.data_out_of_order++; + return RSC_FINAL; + } else { +coalesce: + if ((o_ip_len + n_unit->payload) > chain->max_payload) { + chain->stat.over_size++; + return RSC_FINAL; + } + + /* Here comes the right data, the payload length in v4/v6 is different, + so use the field value to update and record the new data len */ + o_unit->payload += n_unit->payload; /* update new data len */ + + /* update field in ip header */ + *o_unit->ip_plen = htons(o_ip_len + n_unit->payload); + + /* Bring 'PUSH' big, the whql test guide says 'PUSH' can be coalesced + for windows guest, while this may change the behavior for linux + guest (only if it uses RSC feature). */ + o_unit->tcp->th_offset_flags = n_unit->tcp->th_offset_flags; + + o_unit->tcp->th_ack = n_unit->tcp->th_ack; + o_unit->tcp->th_win = n_unit->tcp->th_win; + + memmove(seg->buf + seg->size, data, n_unit->payload); + seg->size += n_unit->payload; + seg->packets++; + chain->stat.coalesced++; + return RSC_COALESCE; + } +} + +static int32_t virtio_net_rsc_coalesce4(VirtioNetRscChain *chain, + VirtioNetRscSeg *seg, + const uint8_t *buf, size_t size, + VirtioNetRscUnit *unit) +{ + struct ip_header *ip1, *ip2; + + ip1 = (struct ip_header *)(unit->ip); + ip2 = (struct ip_header *)(seg->unit.ip); + if ((ip1->ip_src ^ ip2->ip_src) || (ip1->ip_dst ^ ip2->ip_dst) + || (unit->tcp->th_sport ^ seg->unit.tcp->th_sport) + || (unit->tcp->th_dport ^ seg->unit.tcp->th_dport)) { + chain->stat.no_match++; + return RSC_NO_MATCH; + } + + return virtio_net_rsc_coalesce_data(chain, seg, buf, unit); +} + +static int32_t virtio_net_rsc_coalesce6(VirtioNetRscChain *chain, + VirtioNetRscSeg *seg, + const uint8_t *buf, size_t size, + VirtioNetRscUnit *unit) +{ + struct ip6_header *ip1, *ip2; + + ip1 = (struct ip6_header *)(unit->ip); + ip2 = (struct ip6_header *)(seg->unit.ip); + if (memcmp(&ip1->ip6_src, &ip2->ip6_src, sizeof(struct in6_address)) + || memcmp(&ip1->ip6_dst, &ip2->ip6_dst, sizeof(struct in6_address)) + || (unit->tcp->th_sport ^ seg->unit.tcp->th_sport) + || (unit->tcp->th_dport ^ seg->unit.tcp->th_dport)) { + chain->stat.no_match++; + return RSC_NO_MATCH; + } + + return virtio_net_rsc_coalesce_data(chain, seg, buf, unit); +} + +/* Packets with 'SYN' should bypass, other flag should be sent after drain + * to prevent out of order */ +static int virtio_net_rsc_tcp_ctrl_check(VirtioNetRscChain *chain, + struct tcp_header *tcp) +{ + uint16_t tcp_hdr; + uint16_t tcp_flag; + + tcp_flag = htons(tcp->th_offset_flags); + tcp_hdr = (tcp_flag & VIRTIO_NET_TCP_HDR_LENGTH) >> 10; + tcp_flag &= VIRTIO_NET_TCP_FLAG; + tcp_flag = htons(tcp->th_offset_flags) & 0x3F; + if (tcp_flag & TH_SYN) { + chain->stat.tcp_syn++; + return RSC_BYPASS; + } + + if (tcp_flag & (TH_FIN | TH_URG | TH_RST | TH_ECE | TH_CWR)) { + chain->stat.tcp_ctrl_drain++; + return RSC_FINAL; + } + + if (tcp_hdr > sizeof(struct tcp_header)) { + chain->stat.tcp_all_opt++; + return RSC_FINAL; + } + + return RSC_CANDIDATE; +} + +static size_t virtio_net_rsc_do_coalesce(VirtioNetRscChain *chain, + NetClientState *nc, + const uint8_t *buf, size_t size, + VirtioNetRscUnit *unit) +{ + int ret; + VirtioNetRscSeg *seg, *nseg; + + if (QTAILQ_EMPTY(&chain->buffers)) { + chain->stat.empty_cache++; + virtio_net_rsc_cache_buf(chain, nc, buf, size); + timer_mod(chain->drain_timer, + qemu_clock_get_ns(QEMU_CLOCK_HOST) + chain->n->rsc_timeout); + return size; + } + + QTAILQ_FOREACH_SAFE(seg, &chain->buffers, next, nseg) { + if (chain->proto == ETH_P_IP) { + ret = virtio_net_rsc_coalesce4(chain, seg, buf, size, unit); + } else { + ret = virtio_net_rsc_coalesce6(chain, seg, buf, size, unit); + } + + if (ret == RSC_FINAL) { + if (virtio_net_rsc_drain_seg(chain, seg) == 0) { + /* Send failed */ + chain->stat.final_failed++; + return 0; + } + + /* Send current packet */ + return virtio_net_do_receive(nc, buf, size); + } else if (ret == RSC_NO_MATCH) { + continue; + } else { + /* Coalesced, mark coalesced flag to tell calc cksum for ipv4 */ + seg->is_coalesced = 1; + return size; + } + } + + chain->stat.no_match_cache++; + virtio_net_rsc_cache_buf(chain, nc, buf, size); + return size; +} + +/* Drain a connection data, this is to avoid out of order segments */ +static size_t virtio_net_rsc_drain_flow(VirtioNetRscChain *chain, + NetClientState *nc, + const uint8_t *buf, size_t size, + uint16_t ip_start, uint16_t ip_size, + uint16_t tcp_port) +{ + VirtioNetRscSeg *seg, *nseg; + uint32_t ppair1, ppair2; + + ppair1 = *(uint32_t *)(buf + tcp_port); + QTAILQ_FOREACH_SAFE(seg, &chain->buffers, next, nseg) { + ppair2 = *(uint32_t *)(seg->buf + tcp_port); + if (memcmp(buf + ip_start, seg->buf + ip_start, ip_size) + || (ppair1 != ppair2)) { + continue; + } + if (virtio_net_rsc_drain_seg(chain, seg) == 0) { + chain->stat.drain_failed++; + } + + break; + } + + return virtio_net_do_receive(nc, buf, size); +} + +static int32_t virtio_net_rsc_sanity_check4(VirtioNetRscChain *chain, + struct ip_header *ip, + const uint8_t *buf, size_t size) +{ + uint16_t ip_len; + + /* Not an ipv4 packet */ + if (((ip->ip_ver_len & 0xF0) >> 4) != IP_HEADER_VERSION_4) { + chain->stat.ip_option++; + return RSC_BYPASS; + } + + /* Don't handle packets with ip option */ + if ((ip->ip_ver_len & 0xF) != VIRTIO_NET_IP4_HEADER_LENGTH) { + chain->stat.ip_option++; + return RSC_BYPASS; + } + + if (ip->ip_p != IPPROTO_TCP) { + chain->stat.bypass_not_tcp++; + return RSC_BYPASS; + } + + /* Don't handle packets with ip fragment */ + if (!(htons(ip->ip_off) & IP_DF)) { + chain->stat.ip_frag++; + return RSC_BYPASS; + } + + /* Don't handle packets with ecn flag */ + if (IPTOS_ECN(ip->ip_tos)) { + chain->stat.ip_ecn++; + return RSC_BYPASS; + } + + ip_len = htons(ip->ip_len); + if (ip_len < (sizeof(struct ip_header) + sizeof(struct tcp_header)) + || ip_len > (size - chain->n->guest_hdr_len - + sizeof(struct eth_header))) { + chain->stat.ip_hacked++; + return RSC_BYPASS; + } + + return RSC_CANDIDATE; +} + +static size_t virtio_net_rsc_receive4(VirtioNetRscChain *chain, + NetClientState *nc, + const uint8_t *buf, size_t size) +{ + int32_t ret; + uint16_t hdr_len; + VirtioNetRscUnit unit; + + hdr_len = ((VirtIONet *)(chain->n))->guest_hdr_len; + + if (size < (hdr_len + sizeof(struct eth_header) + sizeof(struct ip_header) + + sizeof(struct tcp_header))) { + chain->stat.bypass_not_tcp++; + return virtio_net_do_receive(nc, buf, size); + } + + virtio_net_rsc_extract_unit4(chain, buf, &unit); + if (virtio_net_rsc_sanity_check4(chain, unit.ip, buf, size) + != RSC_CANDIDATE) { + return virtio_net_do_receive(nc, buf, size); + } + + ret = virtio_net_rsc_tcp_ctrl_check(chain, unit.tcp); + if (ret == RSC_BYPASS) { + return virtio_net_do_receive(nc, buf, size); + } else if (ret == RSC_FINAL) { + return virtio_net_rsc_drain_flow(chain, nc, buf, size, + ((hdr_len + sizeof(struct eth_header)) + 12), + VIRTIO_NET_IP4_ADDR_SIZE, + hdr_len + sizeof(struct eth_header) + sizeof(struct ip_header)); + } + + return virtio_net_rsc_do_coalesce(chain, nc, buf, size, &unit); +} + +static int32_t virtio_net_rsc_sanity_check6(VirtioNetRscChain *chain, + struct ip6_header *ip6, + const uint8_t *buf, size_t size) +{ + uint16_t ip_len; + + if (((ip6->ip6_ctlun.ip6_un1.ip6_un1_flow & 0xF0) >> 4) + != IP_HEADER_VERSION_6) { + return RSC_BYPASS; + } + + /* Both option and protocol is checked in this */ + if (ip6->ip6_ctlun.ip6_un1.ip6_un1_nxt != IPPROTO_TCP) { + chain->stat.bypass_not_tcp++; + return RSC_BYPASS; + } + + ip_len = htons(ip6->ip6_ctlun.ip6_un1.ip6_un1_plen); + if (ip_len < sizeof(struct tcp_header) || + ip_len > (size - chain->n->guest_hdr_len - sizeof(struct eth_header) + - sizeof(struct ip6_header))) { + chain->stat.ip_hacked++; + return RSC_BYPASS; + } + + /* Don't handle packets with ecn flag */ + if (IP6_ECN(ip6->ip6_ctlun.ip6_un3.ip6_un3_ecn)) { + chain->stat.ip_ecn++; + return RSC_BYPASS; + } + + return RSC_CANDIDATE; +} + +static size_t virtio_net_rsc_receive6(void *opq, NetClientState *nc, + const uint8_t *buf, size_t size) +{ + int32_t ret; + uint16_t hdr_len; + VirtioNetRscChain *chain; + VirtioNetRscUnit unit; + + chain = (VirtioNetRscChain *)opq; + hdr_len = ((VirtIONet *)(chain->n))->guest_hdr_len; + + if (size < (hdr_len + sizeof(struct eth_header) + sizeof(struct ip6_header) + + sizeof(tcp_header))) { + return virtio_net_do_receive(nc, buf, size); + } + + virtio_net_rsc_extract_unit6(chain, buf, &unit); + if (RSC_CANDIDATE != virtio_net_rsc_sanity_check6(chain, + unit.ip, buf, size)) { + return virtio_net_do_receive(nc, buf, size); + } + + ret = virtio_net_rsc_tcp_ctrl_check(chain, unit.tcp); + if (ret == RSC_BYPASS) { + return virtio_net_do_receive(nc, buf, size); + } else if (ret == RSC_FINAL) { + return virtio_net_rsc_drain_flow(chain, nc, buf, size, + ((hdr_len + sizeof(struct eth_header)) + 8), + VIRTIO_NET_IP6_ADDR_SIZE, + hdr_len + sizeof(struct eth_header) + + sizeof(struct ip6_header)); + } + + return virtio_net_rsc_do_coalesce(chain, nc, buf, size, &unit); +} + +static VirtioNetRscChain *virtio_net_rsc_lookup_chain(VirtIONet *n, + NetClientState *nc, + uint16_t proto) +{ + VirtioNetRscChain *chain; + + if ((proto != (uint16_t)ETH_P_IP) && (proto != (uint16_t)ETH_P_IPV6)) { + return NULL; + } + + QTAILQ_FOREACH(chain, &n->rsc_chains, next) { + if (chain->proto == proto) { + return chain; + } + } + + chain = g_malloc(sizeof(*chain)); + chain->n = n; + chain->proto = proto; + if (proto == (uint16_t)ETH_P_IP) { + chain->max_payload = VIRTIO_NET_MAX_IP4_PAYLOAD; + chain->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; + } else { + chain->max_payload = VIRTIO_NET_MAX_IP6_PAYLOAD; + chain->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + } + chain->drain_timer = timer_new_ns(QEMU_CLOCK_HOST, + virtio_net_rsc_purge, chain); + memset(&chain->stat, 0, sizeof(chain->stat)); + + QTAILQ_INIT(&chain->buffers); + QTAILQ_INSERT_TAIL(&n->rsc_chains, chain, next); + + return chain; +} + +static ssize_t virtio_net_rsc_receive(NetClientState *nc, + const uint8_t *buf, + size_t size) +{ + uint16_t proto; + VirtioNetRscChain *chain; + struct eth_header *eth; + VirtIONet *n; + + n = qemu_get_nic_opaque(nc); + if (size < (n->host_hdr_len + sizeof(struct eth_header))) { + return virtio_net_do_receive(nc, buf, size); + } + + eth = (struct eth_header *)(buf + n->guest_hdr_len); + proto = htons(eth->h_proto); + + chain = virtio_net_rsc_lookup_chain(n, nc, proto); + if (chain) { + chain->stat.received++; + if (proto == (uint16_t)ETH_P_IP && n->rsc4_enabled) { + return virtio_net_rsc_receive4(chain, nc, buf, size); + } else if (proto == (uint16_t)ETH_P_IPV6 && n->rsc6_enabled) { + return virtio_net_rsc_receive6(chain, nc, buf, size); + } + } + return virtio_net_do_receive(nc, buf, size); +} + +static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, + size_t size) +{ + VirtIONet *n = qemu_get_nic_opaque(nc); + if ((n->rsc4_enabled || n->rsc6_enabled)) { + return virtio_net_rsc_receive(nc, buf, size); + } else { + return virtio_net_do_receive(nc, buf, size); + } +} + static int32_t virtio_net_flush_tx(VirtIONetQueue *q); static void virtio_net_tx_complete(NetClientState *nc, ssize_t len) @@ -2075,6 +2734,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) nc = qemu_get_queue(n->nic); nc->rxfilter_notify_enabled = 1; + QTAILQ_INIT(&n->rsc_chains); n->qdev = dev; } @@ -2104,6 +2764,7 @@ static void virtio_net_device_unrealize(DeviceState *dev, Error **errp) timer_free(n->announce_timer); g_free(n->vqs); qemu_del_nic(n->nic); + virtio_net_rsc_cleanup(n); virtio_cleanup(vdev); } @@ -2184,6 +2845,10 @@ static Property virtio_net_properties[] = { DEFINE_PROP_BIT64("ctrl_guest_offloads", VirtIONet, host_features, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, true), DEFINE_PROP_BIT64("mq", VirtIONet, host_features, VIRTIO_NET_F_MQ, false), + DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features, + VIRTIO_NET_F_RSC_EXT, false), + DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout, + VIRTIO_NET_RSC_DEFAULT_INTERVAL), DEFINE_NIC_PROPERTIES(VirtIONet, nic_conf), DEFINE_PROP_UINT32("x-txtimer", VirtIONet, net_conf.txtimer, TX_TIMER_INTERVAL), diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h index 4d7f3c82ca..c7ec1a755f 100644 --- a/include/hw/virtio/virtio-net.h +++ b/include/hw/virtio/virtio-net.h @@ -44,6 +44,83 @@ typedef struct virtio_net_conf uint8_t duplex; } virtio_net_conf; +/* Coalesced packets type & status */ +typedef enum { + RSC_COALESCE, /* Data been coalesced */ + RSC_FINAL, /* Will terminate current connection */ + RSC_NO_MATCH, /* No matched in the buffer pool */ + RSC_BYPASS, /* Packet to be bypass, not tcp, tcp ctrl, etc */ + RSC_CANDIDATE /* Data want to be coalesced */ +} CoalesceStatus; + +typedef struct VirtioNetRscStat { + uint32_t received; + uint32_t coalesced; + uint32_t over_size; + uint32_t cache; + uint32_t empty_cache; + uint32_t no_match_cache; + uint32_t win_update; + uint32_t no_match; + uint32_t tcp_syn; + uint32_t tcp_ctrl_drain; + uint32_t dup_ack; + uint32_t dup_ack1; + uint32_t dup_ack2; + uint32_t pure_ack; + uint32_t ack_out_of_win; + uint32_t data_out_of_win; + uint32_t data_out_of_order; + uint32_t data_after_pure_ack; + uint32_t bypass_not_tcp; + uint32_t tcp_option; + uint32_t tcp_all_opt; + uint32_t ip_frag; + uint32_t ip_ecn; + uint32_t ip_hacked; + uint32_t ip_option; + uint32_t purge_failed; + uint32_t drain_failed; + uint32_t final_failed; + int64_t timer; +} VirtioNetRscStat; + +/* Rsc unit general info used to checking if can coalescing */ +typedef struct VirtioNetRscUnit { + void *ip; /* ip header */ + uint16_t *ip_plen; /* data len pointer in ip header field */ + struct tcp_header *tcp; /* tcp header */ + uint16_t tcp_hdrlen; /* tcp header len */ + uint16_t payload; /* pure payload without virtio/eth/ip/tcp */ +} VirtioNetRscUnit; + +/* Coalesced segmant */ +typedef struct VirtioNetRscSeg { + QTAILQ_ENTRY(VirtioNetRscSeg) next; + void *buf; + size_t size; + uint16_t packets; + uint16_t dup_ack; + bool is_coalesced; /* need recal ipv4 header checksum, mark here */ + VirtioNetRscUnit unit; + NetClientState *nc; +} VirtioNetRscSeg; + +struct VirtIONet; +typedef struct VirtIONet VirtIONet; + +/* Chain is divided by protocol(ipv4/v6) and NetClientInfo */ +typedef struct VirtioNetRscChain { + QTAILQ_ENTRY(VirtioNetRscChain) next; + VirtIONet *n; /* VirtIONet */ + uint16_t proto; + uint8_t gso_type; + uint16_t max_payload; + QEMUTimer *drain_timer; + QTAILQ_HEAD(, VirtioNetRscSeg) buffers; + VirtioNetRscStat stat; +} VirtioNetRscChain; + /* Maximum packet size we can receive from tap device: header + 64k */ #define VIRTIO_NET_MAX_BUFSIZE (sizeof(struct virtio_net_hdr) + (64 * KiB)) @@ -66,12 +143,18 @@ typedef struct VirtIONet { VirtIONetQueue *vqs; VirtQueue *ctrl_vq; NICState *nic; + /* RSC Chains - temporary storage of coalesced data, + all these data are lost in case of migration */ + QTAILQ_HEAD(, VirtioNetRscChain) rsc_chains; uint32_t tx_timeout; int32_t tx_burst; uint32_t has_vnet_hdr; size_t host_hdr_len; size_t guest_hdr_len; uint64_t host_features; + uint32_t rsc_timeout; + uint8_t rsc4_enabled; + uint8_t rsc6_enabled; uint8_t has_ufo; uint32_t mergeable_rx_bufs; uint8_t promisc; diff --git a/include/net/eth.h b/include/net/eth.h index e6dc8a7ba0..7f45c678e7 100644 --- a/include/net/eth.h +++ b/include/net/eth.h @@ -177,6 +177,8 @@ struct tcp_hdr { #define TH_PUSH 0x08 #define TH_ACK 0x10 #define TH_URG 0x20 +#define TH_ECE 0x40 +#define TH_CWR 0x80 u_short th_win; /* window */ u_short th_sum; /* checksum */ u_short th_urp; /* urgent pointer */ -- cgit v1.2.3-55-g7522 From d7741743f4f3d2683d1bb6938f88dc0167c21afa Mon Sep 17 00:00:00 2001 From: Eduardo Habkost Date: Thu, 10 Jan 2019 16:04:57 -0200 Subject: globals: Allow global properties to be optional Making some global properties optional will let us simplify compat code when a given property works on most (but not all) subclasses of a given type. Device types will be able to opt out from optional compat properties by simply not registering those properties. Signed-off-by: Eduardo Habkost Reviewed-by: Cornelia Huck Reviewed-by: Marc-André Lureau Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- include/hw/qdev-core.h | 3 +++ qom/object.c | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h index 9614f76ae6..0a84c42756 100644 --- a/include/hw/qdev-core.h +++ b/include/hw/qdev-core.h @@ -250,6 +250,8 @@ struct PropertyInfo { /** * GlobalProperty: * @used: Set to true if property was used when initializing a device. + * @optional: If set to true, GlobalProperty will be skipped without errors + * if the property doesn't exist. * * An error is fatal for non-hotplugged devices, when the global is applied. */ @@ -258,6 +260,7 @@ typedef struct GlobalProperty { const char *property; const char *value; bool used; + bool optional; } GlobalProperty; static inline void diff --git a/qom/object.c b/qom/object.c index 4e5226ca12..b8c732063b 100644 --- a/qom/object.c +++ b/qom/object.c @@ -385,6 +385,9 @@ void object_apply_global_props(Object *obj, const GPtrArray *props, Error **errp if (object_dynamic_cast(obj, p->driver) == NULL) { continue; } + if (p->optional && !object_property_find(obj, p->property, NULL)) { + continue; + } p->used = true; object_property_parse(obj, p->value, p->property, &err); if (err != NULL) { -- cgit v1.2.3-55-g7522 From 3b97c01e9ccdfbd517a0fd631838d6252dbfa692 Mon Sep 17 00:00:00 2001 From: Stefan Berger Date: Tue, 15 Jan 2019 02:27:50 +0400 Subject: tpm: allocate/map buffer for TPM Physical Presence interface Implement a virtual memory device for the TPM Physical Presence interface. The memory is located at 0xFED45000 and used by ACPI to send messages to the firmware (BIOS) and by the firmware to provide parameters for each one of the supported codes. This interface should be used by all TPM devices on x86 and can be added by calling tpm_ppi_init_io(). Note: bios_linker cannot be used to allocate the PPI memory region, since the reserved memory should stay stable across reboots, and might be needed before the ACPI tables are installed. Signed-off-by: Stefan Berger Signed-off-by: Marc-André Lureau Reviewed-by: Igor Mammedov Reviewed-by: Philippe Mathieu-Daudé Reviewed-by: Michael S. Tsirkin Tested-by: Stefan Berger Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/tpm/Makefile.objs | 1 + hw/tpm/tpm_crb.c | 7 +++++++ hw/tpm/tpm_ppi.c | 31 +++++++++++++++++++++++++++++++ hw/tpm/tpm_ppi.h | 36 ++++++++++++++++++++++++++++++++++++ hw/tpm/tpm_tis.c | 7 +++++++ include/hw/acpi/tpm.h | 6 ++++++ 6 files changed, 88 insertions(+) create mode 100644 hw/tpm/tpm_ppi.c create mode 100644 hw/tpm/tpm_ppi.h (limited to 'include') diff --git a/hw/tpm/Makefile.objs b/hw/tpm/Makefile.objs index 1dc9f8bf2c..700c878622 100644 --- a/hw/tpm/Makefile.objs +++ b/hw/tpm/Makefile.objs @@ -1,4 +1,5 @@ common-obj-y += tpm_util.o +obj-y += tpm_ppi.o common-obj-$(CONFIG_TPM_TIS) += tpm_tis.o common-obj-$(CONFIG_TPM_CRB) += tpm_crb.o common-obj-$(CONFIG_TPM_PASSTHROUGH) += tpm_passthrough.o diff --git a/hw/tpm/tpm_crb.c b/hw/tpm/tpm_crb.c index d5b0ac5920..012ec686d4 100644 --- a/hw/tpm/tpm_crb.c +++ b/hw/tpm/tpm_crb.c @@ -29,6 +29,7 @@ #include "sysemu/reset.h" #include "tpm_int.h" #include "tpm_util.h" +#include "tpm_ppi.h" #include "trace.h" typedef struct CRBState { @@ -43,6 +44,7 @@ typedef struct CRBState { size_t be_buffer_size; bool ppi_enabled; + TPMPPI ppi; } CRBState; #define CRB(obj) OBJECT_CHECK(CRBState, (obj), TYPE_TPM_CRB) @@ -294,6 +296,11 @@ static void tpm_crb_realize(DeviceState *dev, Error **errp) memory_region_add_subregion(get_system_memory(), TPM_CRB_ADDR_BASE + sizeof(s->regs), &s->cmdmem); + if (s->ppi_enabled) { + tpm_ppi_init(&s->ppi, get_system_memory(), + TPM_PPI_ADDR_BASE, OBJECT(s)); + } + qemu_register_reset(tpm_crb_reset, dev); } diff --git a/hw/tpm/tpm_ppi.c b/hw/tpm/tpm_ppi.c new file mode 100644 index 0000000000..cf17779c20 --- /dev/null +++ b/hw/tpm/tpm_ppi.c @@ -0,0 +1,31 @@ +/* + * tpm_ppi.c - TPM Physical Presence Interface + * + * Copyright (C) 2018 IBM Corporation + * + * Authors: + * Stefan Berger + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" + +#include "qapi/error.h" +#include "cpu.h" +#include "sysemu/memory_mapping.h" +#include "migration/vmstate.h" +#include "tpm_ppi.h" + +void tpm_ppi_init(TPMPPI *tpmppi, struct MemoryRegion *m, + hwaddr addr, Object *obj) +{ + tpmppi->buf = g_malloc0(HOST_PAGE_ALIGN(TPM_PPI_ADDR_SIZE)); + memory_region_init_ram_device_ptr(&tpmppi->ram, obj, "tpm-ppi", + TPM_PPI_ADDR_SIZE, tpmppi->buf); + vmstate_register_ram(&tpmppi->ram, DEVICE(obj)); + + memory_region_add_subregion(m, addr, &tpmppi->ram); +} diff --git a/hw/tpm/tpm_ppi.h b/hw/tpm/tpm_ppi.h new file mode 100644 index 0000000000..c5e555fe2c --- /dev/null +++ b/hw/tpm/tpm_ppi.h @@ -0,0 +1,36 @@ +/* + * TPM Physical Presence Interface + * + * Copyright (C) 2018 IBM Corporation + * + * Authors: + * Stefan Berger + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ +#ifndef TPM_TPM_PPI_H +#define TPM_TPM_PPI_H + +#include "hw/acpi/tpm.h" +#include "exec/address-spaces.h" + +typedef struct TPMPPI { + MemoryRegion ram; + uint8_t *buf; +} TPMPPI; + +/** + * tpm_ppi_init: + * @tpmppi: a TPMPPI + * @m: the address-space / MemoryRegion to use + * @addr: the address of the PPI region + * @obj: the owner object + * + * Register the TPM PPI memory region at @addr on the given address + * space for the object @obj. + **/ +void tpm_ppi_init(TPMPPI *tpmppi, struct MemoryRegion *m, + hwaddr addr, Object *obj); + +#endif /* TPM_TPM_PPI_H */ diff --git a/hw/tpm/tpm_tis.c b/hw/tpm/tpm_tis.c index 1698d83cd3..02d9d5c911 100644 --- a/hw/tpm/tpm_tis.c +++ b/hw/tpm/tpm_tis.c @@ -31,6 +31,7 @@ #include "sysemu/tpm_backend.h" #include "tpm_int.h" #include "tpm_util.h" +#include "tpm_ppi.h" #include "trace.h" #define TPM_TIS_NUM_LOCALITIES 5 /* per spec */ @@ -83,6 +84,7 @@ typedef struct TPMState { size_t be_buffer_size; bool ppi_enabled; + TPMPPI ppi; } TPMState; #define TPM(obj) OBJECT_CHECK(TPMState, (obj), TYPE_TPM_TIS) @@ -983,6 +985,11 @@ static void tpm_tis_realizefn(DeviceState *dev, Error **errp) memory_region_add_subregion(isa_address_space(ISA_DEVICE(dev)), TPM_TIS_ADDR_BASE, &s->mmio); + + if (s->ppi_enabled) { + tpm_ppi_init(&s->ppi, isa_address_space(ISA_DEVICE(dev)), + TPM_PPI_ADDR_BASE, OBJECT(s)); + } } static void tpm_tis_initfn(Object *obj) diff --git a/include/hw/acpi/tpm.h b/include/hw/acpi/tpm.h index 3580ffd50c..b8796df916 100644 --- a/include/hw/acpi/tpm.h +++ b/include/hw/acpi/tpm.h @@ -188,4 +188,10 @@ REG32(CRB_DATA_BUFFER, 0x80) #define TPM2_START_METHOD_MMIO 6 #define TPM2_START_METHOD_CRB 7 +/* + * Physical Presence Interface + */ +#define TPM_PPI_ADDR_SIZE 0x400 +#define TPM_PPI_ADDR_BASE 0xFED45000 + #endif /* HW_ACPI_TPM_H */ -- cgit v1.2.3-55-g7522 From 0fe246690315335a40a132f05cb6fdc7bfb9adca Mon Sep 17 00:00:00 2001 From: Stefan Berger Date: Tue, 15 Jan 2019 02:27:51 +0400 Subject: acpi: expose TPM/PPI configuration parameters to firmware via fw_cfg To avoid having to hard code the base address of the PPI virtual memory device we introduce a fw_cfg file etc/tpm/config that holds the base address of the PPI device, the version of the PPI interface and the version of the attached TPM. Signed-off-by: Stefan Berger [ Marc-André: renamed to etc/tpm/config, made it static, document it ] Signed-off-by: Marc-André Lureau Acked-by: Michael S. Tsirkin Reviewed-by: Philippe Mathieu-Daudé Reviewed-by: Michael S. Tsirkin Tested-by: Stefan Berger Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- docs/specs/tpm.txt | 19 +++++++++++++++++++ hw/i386/acpi-build.c | 19 +++++++++++++++++++ include/hw/acpi/tpm.h | 3 +++ 3 files changed, 41 insertions(+) (limited to 'include') diff --git a/docs/specs/tpm.txt b/docs/specs/tpm.txt index 1af82bba86..e4bb094700 100644 --- a/docs/specs/tpm.txt +++ b/docs/specs/tpm.txt @@ -34,6 +34,25 @@ The CRB interface makes a memory mapped IO region in the area 0xfed40000 - QEMU files related to TPM CRB interface: - hw/tpm/tpm_crb.c += fw_cfg interface = + +The bios/firmware may read the "etc/tpm/config" fw_cfg entry for +configuring the guest appropriately. + +The entry of 6 bytes has the following content, in little-endian: + + #define TPM_VERSION_UNSPEC 0 + #define TPM_VERSION_1_2 1 + #define TPM_VERSION_2_0 2 + + #define TPM_PPI_VERSION_NONE 0 + #define TPM_PPI_VERSION_1_30 1 + + struct FwCfgTPMConfig { + uint32_t tpmppi_address; /* PPI memory location */ + uint8_t tpm_version; /* TPM version */ + uint8_t tpmppi_version; /* PPI version */ + }; = ACPI Interface = diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index 14f757fc36..9898247705 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -119,6 +119,12 @@ typedef struct AcpiBuildPciBusHotplugState { bool pcihp_bridge_en; } AcpiBuildPciBusHotplugState; +typedef struct FwCfgTPMConfig { + uint32_t tpmppi_address; + uint8_t tpm_version; + uint8_t tpmppi_version; +} QEMU_PACKED FwCfgTPMConfig; + static void init_common_fadt_data(Object *o, AcpiFadtData *data) { uint32_t io = object_property_get_uint(o, ACPI_PM_PROP_PM_IO_BASE, NULL); @@ -2847,6 +2853,8 @@ void acpi_setup(void) AcpiBuildTables tables; AcpiBuildState *build_state; Object *vmgenid_dev; + TPMIf *tpm; + static FwCfgTPMConfig tpm_config; if (!pcms->fw_cfg) { ACPI_BUILD_DPRINTF("No fw cfg. Bailing out.\n"); @@ -2881,6 +2889,17 @@ void acpi_setup(void) fw_cfg_add_file(pcms->fw_cfg, ACPI_BUILD_TPMLOG_FILE, tables.tcpalog->data, acpi_data_len(tables.tcpalog)); + tpm = tpm_find(); + if (tpm && object_property_get_bool(OBJECT(tpm), "ppi", &error_abort)) { + tpm_config = (FwCfgTPMConfig) { + .tpmppi_address = cpu_to_le32(TPM_PPI_ADDR_BASE), + .tpm_version = tpm_get_version(tpm), + .tpmppi_version = TPM_PPI_VERSION_NONE + }; + fw_cfg_add_file(pcms->fw_cfg, "etc/tpm/config", + &tpm_config, sizeof tpm_config); + } + vmgenid_dev = find_vmgenid_dev(); if (vmgenid_dev) { vmgenid_add_fw_cfg(VMGENID(vmgenid_dev), pcms->fw_cfg, diff --git a/include/hw/acpi/tpm.h b/include/hw/acpi/tpm.h index b8796df916..a6109a97fc 100644 --- a/include/hw/acpi/tpm.h +++ b/include/hw/acpi/tpm.h @@ -194,4 +194,7 @@ REG32(CRB_DATA_BUFFER, 0x80) #define TPM_PPI_ADDR_SIZE 0x400 #define TPM_PPI_ADDR_BASE 0xFED45000 +#define TPM_PPI_VERSION_NONE 0 +#define TPM_PPI_VERSION_1_30 1 + #endif /* HW_ACPI_TPM_H */ -- cgit v1.2.3-55-g7522 From ac6dd31e3fe7e19be6fcaa7bf2396780b355137d Mon Sep 17 00:00:00 2001 From: Stefan Berger Date: Tue, 15 Jan 2019 02:27:52 +0400 Subject: acpi: build TPM Physical Presence interface The TPM Physical Presence interface consists of an ACPI part, a shared memory part, and code in the firmware. Users can send messages to the firmware by writing a code into the shared memory through invoking the ACPI code. When a reboot happens, the firmware looks for the code and acts on it by sending sequences of commands to the TPM. This patch adds the ACPI code. It is similar to the one in EDK2 but doesn't assume that SMIs are necessary to use. It uses a similar datastructure for the shared memory as EDK2 does so that EDK2 and SeaBIOS could both make use of it. I extended the shared memory data structure with an array of 256 bytes, one for each code that could be implemented. The array contains flags describing the individual codes. This decouples the ACPI implementation from the firmware implementation. The underlying TCG specification is accessible from the following page. https://trustedcomputinggroup.org/tcg-physical-presence-interface-specification/ This patch implements version 1.30. Signed-off-by: Stefan Berger [ Marc-André - ACPI code improvements and windows fixes ] Signed-off-by: Marc-André Lureau Acked-by: Michael S. Tsirkin Reviewed-by: Igor Mammedov Reviewed-by: Michael S. Tsirkin Tested-by: Stefan Berger Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- docs/specs/tpm.txt | 83 +++++++++++ hw/acpi/Makefile.objs | 1 + hw/acpi/tpm.c | 404 ++++++++++++++++++++++++++++++++++++++++++++++++++ hw/i386/acpi-build.c | 12 +- include/hw/acpi/tpm.h | 12 ++ stubs/tpm.c | 5 + 6 files changed, 514 insertions(+), 3 deletions(-) create mode 100644 hw/acpi/tpm.c (limited to 'include') diff --git a/docs/specs/tpm.txt b/docs/specs/tpm.txt index e4bb094700..424d1511fc 100644 --- a/docs/specs/tpm.txt +++ b/docs/specs/tpm.txt @@ -76,6 +76,89 @@ URL: https://trustedcomputinggroup.org/tcg-acpi-specification/ +== ACPI PPI Interface == + +QEMU supports the Physical Presence Interface (PPI) for TPM 1.2 and TPM 2. This +interface requires ACPI and firmware support. The specification can be found at +the following URL: + +https://trustedcomputinggroup.org/resource/tcg-physical-presence-interface-specification/ + +PPI enables a system administrator (root) to request a modification to the +TPM upon reboot. The PPI specification defines the operation requests and the +actions the firmware has to take. The system administrator passes the operation +request number to the firmware through an ACPI interface which writes this +number to a memory location that the firmware knows. Upon reboot, the firmware +finds the number and sends commands to the the TPM. The firmware writes the TPM +result code and the operation request number to a memory location that ACPI can +read from and pass the result on to the administrator. + +The PPI specification defines a set of mandatory and optional operations for +the firmware to implement. The ACPI interface also allows an administrator to +list the supported operations. In QEMU the ACPI code is generated by QEMU, yet +the firmware needs to implement support on a per-operations basis, and +different firmwares may support a different subset. Therefore, QEMU introduces +the virtual memory device for PPI where the firmware can indicate which +operations it supports and ACPI can enable the ones that are supported and +disable all others. This interface lies in main memory and has the following +layout: + + +----------+--------+--------+-------------------------------------------+ + | Field | Length | Offset | Description | + +----------+--------+--------+-------------------------------------------+ + | func | 0x100 | 0x000 | Firmware sets values for each supported | + | | | | operation. See defined values below. | + +----------+--------+--------+-------------------------------------------+ + | ppin | 0x1 | 0x100 | SMI interrupt to use. Set by firmware. | + | | | | Not supported. | + +----------+--------+--------+-------------------------------------------+ + | ppip | 0x4 | 0x101 | ACPI function index to pass to SMM code. | + | | | | Set by ACPI. Not supported. | + +----------+--------+--------+-------------------------------------------+ + | pprp | 0x4 | 0x105 | Result of last executed operation. Set by | + | | | | firmware. See function index 5 for values.| + +----------+--------+--------+-------------------------------------------+ + | pprq | 0x4 | 0x109 | Operation request number to execute. See | + | | | | 'Physical Presence Interface Operation | + | | | | Summary' tables in specs. Set by ACPI. | + +----------+--------+--------+-------------------------------------------+ + | pprm | 0x4 | 0x10d | Operation request optional parameter. | + | | | | Values depend on operation. Set by ACPI. | + +----------+--------+--------+-------------------------------------------+ + | lppr | 0x4 | 0x111 | Last executed operation request number. | + | | | | Copied from pprq field by firmware. | + +----------+--------+--------+-------------------------------------------+ + | fret | 0x4 | 0x115 | Result code from SMM function. | + | | | | Not supported. | + +----------+--------+--------+-------------------------------------------+ + | res1 | 0x40 | 0x119 | Reserved for future use | + +----------+--------+--------+-------------------------------------------+ + | next_step| 0x1 | 0x159 | Operation to execute after reboot by | + | | | | firmware. Used by firmware. | + +----------+--------+--------+-------------------------------------------+ + + The following values are supported for the 'func' field. They correspond + to the values used by ACPI function index 8. + + +----------+-------------------------------------------------------------+ + | value | Description | + +----------+-------------------------------------------------------------+ + | 0 | Operation is not implemented. | + +----------+-------------------------------------------------------------+ + | 1 | Operation is only accessible through firmware. | + +----------+-------------------------------------------------------------+ + | 2 | Operation is blocked for OS by firmware configuration. | + +----------+-------------------------------------------------------------+ + | 3 | Operation is allowed and physically present user required. | + +----------+-------------------------------------------------------------+ + | 4 | Operation is allowed and physically present user is not | + | | required. | + +----------+-------------------------------------------------------------+ + +The location of the table is given by the fw_cfg tpmppi_address field. +The PPI memory region size is 0x400 (TPM_PPI_ADDR_SIZE) to leave +enough room for future updates. + QEMU files related to TPM ACPI tables: - hw/i386/acpi-build.c diff --git a/hw/acpi/Makefile.objs b/hw/acpi/Makefile.objs index 11c35bcb44..2d46e3789a 100644 --- a/hw/acpi/Makefile.objs +++ b/hw/acpi/Makefile.objs @@ -11,6 +11,7 @@ common-obj-$(call lnot,$(CONFIG_ACPI_X86)) += acpi-stub.o common-obj-y += acpi_interface.o common-obj-y += bios-linker-loader.o common-obj-y += aml-build.o +common-obj-$(CONFIG_TPM) += tpm.o common-obj-$(CONFIG_IPMI) += ipmi.o common-obj-$(call lnot,$(CONFIG_IPMI)) += ipmi-stub.o diff --git a/hw/acpi/tpm.c b/hw/acpi/tpm.c new file mode 100644 index 0000000000..9f205378f2 --- /dev/null +++ b/hw/acpi/tpm.c @@ -0,0 +1,404 @@ +/* Support for generating ACPI TPM tables + * + * Copyright (C) 2018 IBM, Corp. + * Copyright (C) 2018 Red Hat Inc + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + + * You should have received a copy of the GNU General Public License along + * with this program; if not, see . + */ +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/acpi/tpm.h" + +void tpm_build_ppi_acpi(TPMIf *tpm, Aml *dev) +{ + Aml *method, *field, *ifctx, *ifctx2, *ifctx3, *func_mask, + *not_implemented, *pak, *tpm2, *tpm3, *pprm, *pprq, *zero, *one; + + if (!object_property_get_bool(OBJECT(tpm), "ppi", &error_abort)) { + return; + } + + zero = aml_int(0); + one = aml_int(1); + func_mask = aml_int(TPM_PPI_FUNC_MASK); + not_implemented = aml_int(TPM_PPI_FUNC_NOT_IMPLEMENTED); + + /* + * TPP2 is for the registers that ACPI code used to pass + * the PPI code and parameter (PPRQ, PPRM) to the firmware. + */ + aml_append(dev, + aml_operation_region("TPP2", AML_SYSTEM_MEMORY, + aml_int(TPM_PPI_ADDR_BASE + 0x100), + 0x5A)); + field = aml_field("TPP2", AML_ANY_ACC, AML_NOLOCK, AML_PRESERVE); + aml_append(field, aml_named_field("PPIN", 8)); + aml_append(field, aml_named_field("PPIP", 32)); + aml_append(field, aml_named_field("PPRP", 32)); + aml_append(field, aml_named_field("PPRQ", 32)); + aml_append(field, aml_named_field("PPRM", 32)); + aml_append(field, aml_named_field("LPPR", 32)); + aml_append(dev, field); + pprq = aml_name("PPRQ"); + pprm = aml_name("PPRM"); + + /* + * DerefOf in Windows is broken with SYSTEM_MEMORY. Use a dynamic + * operation region inside of a method for getting FUNC[op]. + */ + method = aml_method("TPFN", 1, AML_SERIALIZED); + { + Aml *op = aml_arg(0); + ifctx = aml_if(aml_lgreater_equal(op, aml_int(0x100))); + { + aml_append(ifctx, aml_return(zero)); + } + aml_append(method, ifctx); + + aml_append(method, + aml_operation_region("TPP1", AML_SYSTEM_MEMORY, + aml_add(aml_int(TPM_PPI_ADDR_BASE), op, NULL), 0x1)); + field = aml_field("TPP1", AML_BYTE_ACC, AML_NOLOCK, AML_PRESERVE); + aml_append(field, aml_named_field("TPPF", 8)); + aml_append(method, field); + aml_append(method, aml_return(aml_name("TPPF"))); + } + aml_append(dev, method); + + /* + * Use global TPM2 & TPM3 variables to workaround Windows ACPI bug + * when returning packages. + */ + pak = aml_package(2); + aml_append(pak, zero); + aml_append(pak, zero); + aml_append(dev, aml_name_decl("TPM2", pak)); + tpm2 = aml_name("TPM2"); + + pak = aml_package(3); + aml_append(pak, zero); + aml_append(pak, zero); + aml_append(pak, zero); + aml_append(dev, aml_name_decl("TPM3", pak)); + tpm3 = aml_name("TPM3"); + + method = aml_method("_DSM", 4, AML_SERIALIZED); + { + uint8_t zerobyte[1] = { 0 }; + Aml *function, *arguments, *rev, *op, *op_arg, *op_flags, *uuid; + + uuid = aml_arg(0); + rev = aml_arg(1); + function = aml_arg(2); + arguments = aml_arg(3); + op = aml_local(0); + op_flags = aml_local(1); + + /* Physical Presence Interface */ + ifctx = aml_if( + aml_equal(uuid, + aml_touuid("3DDDFAA6-361B-4EB4-A424-8D10089D1653"))); + { + /* standard DSM query function */ + ifctx2 = aml_if(aml_equal(function, zero)); + { + uint8_t byte_list[2] = { 0xff, 0x01 }; /* functions 1-8 */ + + aml_append(ifctx2, + aml_return(aml_buffer(sizeof(byte_list), + byte_list))); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.0: 2.1.1 Get Physical Presence Interface Version + * + * Arg 2 (Integer): Function Index = 1 + * Arg 3 (Package): Arguments = Empty Package + * Returns: Type: String + */ + ifctx2 = aml_if(aml_equal(function, one)); + { + aml_append(ifctx2, aml_return(aml_string("1.3"))); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.0: 2.1.3 Submit TPM Operation Request to Pre-OS Environment + * + * Arg 2 (Integer): Function Index = 2 + * Arg 3 (Package): Arguments = Package: Type: Integer + * Operation Value of the Request + * Returns: Type: Integer + * 0: Success + * 1: Operation Value of the Request Not Supported + * 2: General Failure + */ + ifctx2 = aml_if(aml_equal(function, aml_int(2))); + { + /* get opcode */ + aml_append(ifctx2, + aml_store(aml_derefof(aml_index(arguments, + zero)), op)); + + /* get opcode flags */ + aml_append(ifctx2, + aml_store(aml_call1("TPFN", op), op_flags)); + + /* if func[opcode] & TPM_PPI_FUNC_NOT_IMPLEMENTED */ + ifctx3 = aml_if( + aml_equal( + aml_and(op_flags, func_mask, NULL), + not_implemented)); + { + /* 1: Operation Value of the Request Not Supported */ + aml_append(ifctx3, aml_return(one)); + } + aml_append(ifctx2, ifctx3); + + aml_append(ifctx2, aml_store(op, pprq)); + aml_append(ifctx2, aml_store(zero, pprm)); + /* 0: success */ + aml_append(ifctx2, aml_return(zero)); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.0: 2.1.4 Get Pending TPM Operation Requested By the OS + * + * Arg 2 (Integer): Function Index = 3 + * Arg 3 (Package): Arguments = Empty Package + * Returns: Type: Package of Integers + * Integer 1: Function Return code + * 0: Success + * 1: General Failure + * Integer 2: Pending operation requested by the OS + * 0: None + * >0: Operation Value of the Pending Request + * Integer 3: Optional argument to pending operation + * requested by the OS + * 0: None + * >0: Argument Value of the Pending Request + */ + ifctx2 = aml_if(aml_equal(function, aml_int(3))); + { + /* + * Revision ID of 1, no integer parameter beyond + * parameter two are expected + */ + ifctx3 = aml_if(aml_equal(rev, one)); + { + /* TPM2[1] = PPRQ */ + aml_append(ifctx3, + aml_store(pprq, aml_index(tpm2, one))); + aml_append(ifctx3, aml_return(tpm2)); + } + aml_append(ifctx2, ifctx3); + + /* + * A return value of {0, 23, 1} indicates that + * operation 23 with argument 1 is pending. + */ + ifctx3 = aml_if(aml_equal(rev, aml_int(2))); + { + /* TPM3[1] = PPRQ */ + aml_append(ifctx3, + aml_store(pprq, aml_index(tpm3, one))); + /* TPM3[2] = PPRM */ + aml_append(ifctx3, + aml_store(pprm, aml_index(tpm3, aml_int(2)))); + aml_append(ifctx3, aml_return(tpm3)); + } + aml_append(ifctx2, ifctx3); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.0: 2.1.5 Get Platform-Specific Action to Transition to + * Pre-OS Environment + * + * Arg 2 (Integer): Function Index = 4 + * Arg 3 (Package): Arguments = Empty Package + * Returns: Type: Integer + * 0: None + * 1: Shutdown + * 2: Reboot + * 3: OS Vendor-specific + */ + ifctx2 = aml_if(aml_equal(function, aml_int(4))); + { + /* reboot */ + aml_append(ifctx2, aml_return(aml_int(2))); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.0: 2.1.6 Return TPM Operation Response to OS Environment + * + * Arg 2 (Integer): Function Index = 5 + * Arg 3 (Package): Arguments = Empty Package + * Returns: Type: Package of Integer + * Integer 1: Function Return code + * 0: Success + * 1: General Failure + * Integer 2: Most recent operation request + * 0: None + * >0: Operation Value of the most recent request + * Integer 3: Response to the most recent operation request + * 0: Success + * 0x00000001..0x00000FFF: Corresponding TPM + * error code + * 0xFFFFFFF0: User Abort or timeout of dialog + * 0xFFFFFFF1: firmware Failure + */ + ifctx2 = aml_if(aml_equal(function, aml_int(5))); + { + /* TPM3[1] = LPPR */ + aml_append(ifctx2, + aml_store(aml_name("LPPR"), + aml_index(tpm3, one))); + /* TPM3[2] = PPRP */ + aml_append(ifctx2, + aml_store(aml_name("PPRP"), + aml_index(tpm3, aml_int(2)))); + aml_append(ifctx2, aml_return(tpm3)); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.0: 2.1.7 Submit preferred user language + * + * Arg 2 (Integer): Function Index = 6 + * Arg 3 (Package): Arguments = String Package + * Preferred language code + * Returns: Type: Integer + * Function Return Code + * 3: Not implemented + */ + ifctx2 = aml_if(aml_equal(function, aml_int(6))); + { + /* 3 = not implemented */ + aml_append(ifctx2, aml_return(aml_int(3))); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.1: 2.1.7 Submit TPM Operation Request to + * Pre-OS Environment 2 + * + * Arg 2 (Integer): Function Index = 7 + * Arg 3 (Package): Arguments = Package: Type: Integer + * Integer 1: Operation Value of the Request + * Integer 2: Argument for Operation (optional) + * Returns: Type: Integer + * 0: Success + * 1: Not Implemented + * 2: General Failure + * 3: Operation blocked by current firmware settings + */ + ifctx2 = aml_if(aml_equal(function, aml_int(7))); + { + /* get opcode */ + aml_append(ifctx2, aml_store(aml_derefof(aml_index(arguments, + zero)), + op)); + + /* get opcode flags */ + aml_append(ifctx2, aml_store(aml_call1("TPFN", op), + op_flags)); + /* if func[opcode] & TPM_PPI_FUNC_NOT_IMPLEMENTED */ + ifctx3 = aml_if( + aml_equal( + aml_and(op_flags, func_mask, NULL), + not_implemented)); + { + /* 1: not implemented */ + aml_append(ifctx3, aml_return(one)); + } + aml_append(ifctx2, ifctx3); + + /* if func[opcode] & TPM_PPI_FUNC_BLOCKED */ + ifctx3 = aml_if( + aml_equal( + aml_and(op_flags, func_mask, NULL), + aml_int(TPM_PPI_FUNC_BLOCKED))); + { + /* 3: blocked by firmware */ + aml_append(ifctx3, aml_return(aml_int(3))); + } + aml_append(ifctx2, ifctx3); + + /* revision to integer */ + ifctx3 = aml_if(aml_equal(rev, one)); + { + /* revision 1 */ + /* PPRQ = op */ + aml_append(ifctx3, aml_store(op, pprq)); + /* no argument, PPRM = 0 */ + aml_append(ifctx3, aml_store(zero, pprm)); + } + aml_append(ifctx2, ifctx3); + + ifctx3 = aml_if(aml_equal(rev, aml_int(2))); + { + /* revision 2 */ + /* PPRQ = op */ + op_arg = aml_derefof(aml_index(arguments, one)); + aml_append(ifctx3, aml_store(op, pprq)); + /* PPRM = arg3[1] */ + aml_append(ifctx3, aml_store(op_arg, pprm)); + } + aml_append(ifctx2, ifctx3); + /* 0: success */ + aml_append(ifctx2, aml_return(zero)); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.1: 2.1.8 Get User Confirmation Status for Operation + * + * Arg 2 (Integer): Function Index = 8 + * Arg 3 (Package): Arguments = Package: Type: Integer + * Operation Value that may need user confirmation + * Returns: Type: Integer + * 0: Not implemented + * 1: Firmware only + * 2: Blocked for OS by firmware configuration + * 3: Allowed and physically present user required + * 4: Allowed and physically present user not required + */ + ifctx2 = aml_if(aml_equal(function, aml_int(8))); + { + /* get opcode */ + aml_append(ifctx2, + aml_store(aml_derefof(aml_index(arguments, + zero)), + op)); + + /* get opcode flags */ + aml_append(ifctx2, aml_store(aml_call1("TPFN", op), + op_flags)); + /* return confirmation status code */ + aml_append(ifctx2, + aml_return( + aml_and(op_flags, func_mask, NULL))); + } + aml_append(ifctx, ifctx2); + + aml_append(ifctx, aml_return(aml_buffer(1, zerobyte))); + } + aml_append(method, ifctx); + } + aml_append(dev, method); +} diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index 9898247705..2e21a31f82 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -1802,6 +1802,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, uint32_t nr_mem = machine->ram_slots; int root_bus_limit = 0xFF; PCIBus *bus = NULL; + TPMIf *tpm = tpm_find(); int i; dsdt = init_aml_allocator(); @@ -2139,7 +2140,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, /* Scan all PCI buses. Generate tables to support hotplug. */ build_append_pci_bus_devices(scope, bus, pm->pcihp_bridge_en); - if (TPM_IS_TIS(tpm_find())) { + if (TPM_IS_TIS(tpm)) { dev = aml_device("ISA.TPM"); aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0C31"))); aml_append(dev, aml_name_decl("_STA", aml_int(0xF))); @@ -2153,6 +2154,9 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, */ /* aml_append(crs, aml_irq_no_flags(TPM_TIS_IRQ)); */ aml_append(dev, aml_name_decl("_CRS", crs)); + + tpm_build_ppi_acpi(tpm, dev); + aml_append(scope, dev); } @@ -2160,7 +2164,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, } } - if (TPM_IS_CRB(tpm_find())) { + if (TPM_IS_CRB(tpm)) { dev = aml_device("TPM"); aml_append(dev, aml_name_decl("_HID", aml_string("MSFT0101"))); crs = aml_resource_template(); @@ -2172,6 +2176,8 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, aml_append(method, aml_return(aml_int(0x0f))); aml_append(dev, method); + tpm_build_ppi_acpi(tpm, dev); + aml_append(sb_scope, dev); } @@ -2894,7 +2900,7 @@ void acpi_setup(void) tpm_config = (FwCfgTPMConfig) { .tpmppi_address = cpu_to_le32(TPM_PPI_ADDR_BASE), .tpm_version = tpm_get_version(tpm), - .tpmppi_version = TPM_PPI_VERSION_NONE + .tpmppi_version = TPM_PPI_VERSION_1_30 }; fw_cfg_add_file(pcms->fw_cfg, "etc/tpm/config", &tpm_config, sizeof tpm_config); diff --git a/include/hw/acpi/tpm.h b/include/hw/acpi/tpm.h index a6109a97fc..1a2a57a21f 100644 --- a/include/hw/acpi/tpm.h +++ b/include/hw/acpi/tpm.h @@ -18,6 +18,8 @@ #include "qemu/units.h" #include "hw/registerfields.h" +#include "hw/acpi/aml-build.h" +#include "sysemu/tpm.h" #define TPM_TIS_ADDR_BASE 0xFED40000 #define TPM_TIS_ADDR_SIZE 0x5000 @@ -197,4 +199,14 @@ REG32(CRB_DATA_BUFFER, 0x80) #define TPM_PPI_VERSION_NONE 0 #define TPM_PPI_VERSION_1_30 1 +/* whether function is blocked by BIOS settings; bits 0, 1, 2 */ +#define TPM_PPI_FUNC_NOT_IMPLEMENTED (0 << 0) +#define TPM_PPI_FUNC_BIOS_ONLY (1 << 0) +#define TPM_PPI_FUNC_BLOCKED (2 << 0) +#define TPM_PPI_FUNC_ALLOWED_USR_REQ (3 << 0) +#define TPM_PPI_FUNC_ALLOWED_USR_NOT_REQ (4 << 0) +#define TPM_PPI_FUNC_MASK (7 << 0) + +void tpm_build_ppi_acpi(TPMIf *tpm, Aml *dev); + #endif /* HW_ACPI_TPM_H */ diff --git a/stubs/tpm.c b/stubs/tpm.c index 80939cd3db..66c99d667d 100644 --- a/stubs/tpm.c +++ b/stubs/tpm.c @@ -8,6 +8,7 @@ #include "qemu/osdep.h" #include "qapi/qapi-commands-tpm.h" #include "sysemu/tpm.h" +#include "hw/acpi/tpm.h" void tpm_init(void) { @@ -31,3 +32,7 @@ TpmModelList *qmp_query_tpm_models(Error **errp) { return NULL; } + +void tpm_build_ppi_acpi(TPMIf *tpm, Aml *dev) +{ +} -- cgit v1.2.3-55-g7522 From 1daff2f8193496b0e5e0ab56dc48c570c81f804e Mon Sep 17 00:00:00 2001 From: Philippe Mathieu-Daudé Date: Thu, 3 Jan 2019 09:56:34 +0100 Subject: qemu/compiler: Define QEMU_NONSTRING GCC 8 introduced the -Wstringop-truncation checker to detect truncation by the strncat and strncpy functions (closely related to -Wstringop-overflow, which detect buffer overflow by string-modifying functions declared in ). In tandem of -Wstringop-truncation, the "nonstring" attribute was added: The nonstring variable attribute specifies that an object or member declaration with type array of char, signed char, or unsigned char, or pointer to such a type is intended to store character arrays that do not necessarily contain a terminating NUL. This is useful in detecting uses of such arrays or pointers with functions that expect NUL-terminated strings, and to avoid warnings when such an array or pointer is used as an argument to a bounded string manipulation function such as strncpy. From the GCC manual: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-nonstring-variable-attribute Add the QEMU_NONSTRING macro which checks if the compiler supports this attribute. Suggested-by: Michael S. Tsirkin Reviewed-by: Eric Blake Reviewed-by: Michael S. Tsirkin Reviewed-by: Richard Henderson Reviewed-by: Thomas Huth Signed-off-by: Philippe Mathieu-Daudé --- include/qemu/compiler.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/qemu/compiler.h b/include/qemu/compiler.h index 261842beae..2d8f507c73 100644 --- a/include/qemu/compiler.h +++ b/include/qemu/compiler.h @@ -151,6 +151,21 @@ # define QEMU_ERROR(X) #endif +/* + * The nonstring variable attribute specifies that an object or member + * declaration with type array of char or pointer to char is intended + * to store character arrays that do not necessarily contain a terminating + * NUL character. This is useful in detecting uses of such arrays or pointers + * with functions that expect NUL-terminated strings, and to avoid warnings + * when such an array or pointer is used as an argument to a bounded string + * manipulation function such as strncpy. + */ +#if __has_attribute(nonstring) +# define QEMU_NONSTRING __attribute__((nonstring)) +#else +# define QEMU_NONSTRING +#endif + /* Implement C11 _Generic via GCC builtins. Example: * * QEMU_GENERIC(x, (float, sinf), (long double, sinl), sin) (x) -- cgit v1.2.3-55-g7522 From 9cbb8eca1729eab1123847e37454975bb555008a Mon Sep 17 00:00:00 2001 From: Philippe Mathieu-Daudé Date: Thu, 3 Jan 2019 09:56:36 +0100 Subject: hw/acpi: Use QEMU_NONSTRING for non NUL-terminated arrays GCC 8 added a -Wstringop-truncation warning: The -Wstringop-truncation warning added in GCC 8.0 via r254630 for bug 81117 is specifically intended to highlight likely unintended uses of the strncpy function that truncate the terminating NUL character from the source string. This new warning leads to compilation failures: CC hw/acpi/core.o In function 'acpi_table_install', inlined from 'acpi_table_add' at qemu/hw/acpi/core.c:296:5: qemu/hw/acpi/core.c:184:9: error: 'strncpy' specified bound 4 equals destination size [-Werror=stringop-truncation] strncpy(ext_hdr->sig, hdrs->sig, sizeof ext_hdr->sig); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ make: *** [qemu/rules.mak:69: hw/acpi/core.o] Error 1 Use the QEMU_NONSTRING attribute, since ACPI tables don't require the strings to be NUL-terminated. Suggested-by: Michael S. Tsirkin Reviewed-by: Michael S. Tsirkin Reviewed-by: Igor Mammedov Signed-off-by: Philippe Mathieu-Daudé --- hw/acpi/core.c | 12 ++++++++---- include/hw/acpi/acpi-defs.h | 13 ++++++++----- 2 files changed, 16 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/hw/acpi/core.c b/hw/acpi/core.c index d6f0709691..47877c0ec1 100644 --- a/hw/acpi/core.c +++ b/hw/acpi/core.c @@ -35,14 +35,18 @@ struct acpi_table_header { uint16_t _length; /* our length, not actual part of the hdr */ /* allows easier parsing for fw_cfg clients */ - char sig[4]; /* ACPI signature (4 ASCII characters) */ + char sig[4] + QEMU_NONSTRING; /* ACPI signature (4 ASCII characters) */ uint32_t length; /* Length of table, in bytes, including header */ uint8_t revision; /* ACPI Specification minor version # */ uint8_t checksum; /* To make sum of entire table == 0 */ - char oem_id[6]; /* OEM identification */ - char oem_table_id[8]; /* OEM table identification */ + char oem_id[6] + QEMU_NONSTRING; /* OEM identification */ + char oem_table_id[8] + QEMU_NONSTRING; /* OEM table identification */ uint32_t oem_revision; /* OEM revision number */ - char asl_compiler_id[4]; /* ASL compiler vendor ID */ + char asl_compiler_id[4] + QEMU_NONSTRING; /* ASL compiler vendor ID */ uint32_t asl_compiler_revision; /* ASL compiler revision number */ } QEMU_PACKED; diff --git a/include/hw/acpi/acpi-defs.h b/include/hw/acpi/acpi-defs.h index 5021cb9e79..4ed160afae 100644 --- a/include/hw/acpi/acpi-defs.h +++ b/include/hw/acpi/acpi-defs.h @@ -41,8 +41,8 @@ enum { }; typedef struct AcpiRsdpData { - uint8_t oem_id[6]; /* OEM identification */ - uint8_t revision; /* Must be 0 for 1.0, 2 for 2.0 */ + uint8_t oem_id[6] QEMU_NONSTRING; /* OEM identification */ + uint8_t revision; /* Must be 0 for 1.0, 2 for 2.0 */ unsigned *rsdt_tbl_offset; unsigned *xsdt_tbl_offset; @@ -57,10 +57,13 @@ typedef struct AcpiRsdpData { uint32_t length; /* Length of table, in bytes, including header */ \ uint8_t revision; /* ACPI Specification minor version # */ \ uint8_t checksum; /* To make sum of entire table == 0 */ \ - uint8_t oem_id [6]; /* OEM identification */ \ - uint8_t oem_table_id [8]; /* OEM table identification */ \ + uint8_t oem_id[6] \ + QEMU_NONSTRING; /* OEM identification */ \ + uint8_t oem_table_id[8] \ + QEMU_NONSTRING; /* OEM table identification */ \ uint32_t oem_revision; /* OEM revision number */ \ - uint8_t asl_compiler_id [4]; /* ASL compiler vendor ID */ \ + uint8_t asl_compiler_id[4] \ + QEMU_NONSTRING; /* ASL compiler vendor ID */ \ uint32_t asl_compiler_revision; /* ASL compiler revision number */ -- cgit v1.2.3-55-g7522