From: Sergey Kambalin <[email protected]>
Implement the receive DMA ring handling: qemu_can_receive()/
receive() callbacks for the NIC's netdev peer, copying incoming
frame data into descriptor buffers on the active RX ring,
classifying broadcast/multicast, and raising the RXDMA_MBDONE
interrupt as descriptors complete.
Part of Sergey Kambalin's original Raspberry Pi 4B PCIe/GENET
networking series (patchwork series 829638, posted to qemu-devel in
2024, never merged). Carried forward and completed by Marcelo Manzo.
While carrying this forward, make these changes to the original code:
- Report no hardware-computed RX checksum (rx_csum = 0). The original
stored the IPv4 header checksum in host byte order, but the guest's
CHECKSUM_COMPLETE path expects a running checksum over the L4
payload, which made the guest reject otherwise-valid inbound
packets ("hw csum failure" in bcmgenet_rx_poll()) and broke
DHCP/connectivity intermittently. With 0 the guest verifies
checksums in software instead.
- Fill in the per-packet status block with stl_le_p() rather than by
casting the packet buffer to a C struct, which is undefined
behaviour for a misaligned buffer and wrong on big-endian hosts.
- Validate the guest-programmed descriptor indexes against the size
of the descriptor array, and limit the DMA write to the size of our
packet buffer, so that a guest-controlled register can't make us
access memory outside them.
Signed-off-by: Sergey Kambalin <[email protected]>
Signed-off-by: Marcelo Manzo <[email protected]>
---
hw/net/bcm2838_genet.c | 288 ++++++++++++++++++++++++++++++++-
include/hw/net/bcm2838_genet.h | 1 +
2 files changed, 288 insertions(+), 1 deletion(-)
diff --git a/hw/net/bcm2838_genet.c b/hw/net/bcm2838_genet.c
index 7eba0edbb6..a0e8dd4751 100644
--- a/hw/net/bcm2838_genet.c
+++ b/hw/net/bcm2838_genet.c
@@ -527,6 +527,25 @@ static bool
bcm2838_genet_tdma_ring_active(BCM2838GenetState *s,
return active;
}
+static bool bcm2838_genet_rdma_ring_active(BCM2838GenetState *s,
+ unsigned int ring_index)
+{
+ uint32_t ring_mask = 1 << ring_index;
+
+ bool dma_en = FIELD_EX32(s->regs.rdma.ctrl, GENET_DMA_CTRL, EN) != 0;
+ bool ring_en = (FIELD_EX32(s->regs.rdma.ring_cfg, GENET_DMA_RING_CFG, EN)
+ & ring_mask) != 0;
+ bool ring_buf_en = (FIELD_EX32(s->regs.rdma.ctrl,
+ GENET_DMA_CTRL, RING_BUF_EN)
+ & ring_mask) != 0;
+ bool active = dma_en && ring_en && ring_buf_en;
+
+ trace_bcm2838_genet_rx_dma_ring_active(ring_index,
+ active ? "active" : "halted");
+
+ return active;
+}
+
static void bcm2838_genet_tdma(BCM2838GenetState *s, hwaddr offset,
uint64_t value)
{
@@ -742,9 +761,274 @@ static const MemoryRegionOps bcm2838_genet_ops = {
.valid = {.min_access_size = 4},
};
+static int32_t bcm2838_genet_filter(BCM2838GenetState *s, const void *buf,
+ size_t size)
+{
+ qemu_log_mask(LOG_UNIMP,
+ "Packet filtration with HFB isn't implemented yet");
+ return -1;
+}
+
+static int32_t bcm2838_genet_filter2ring(BCM2838GenetState *s,
+ uint32_t filter_idx)
+{
+ qemu_log_mask(LOG_UNIMP,
+ "Packet filtration with HFB isn't implemented yet");
+ return -1;
+}
+
+static bool is_packet_broadcast(const uint8_t *buf, size_t size)
+{
+ static const uint8_t bcst_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
+
+ if (size < sizeof(bcst_addr)) {
+ return false;
+ }
+
+ return !memcmp(buf, bcst_addr, sizeof(bcst_addr));
+}
+
+static bool is_packet_multicast(const uint8_t *buf, size_t size)
+{
+ return !!(buf[0] & 0x01);
+}
+
+static ssize_t bcm2838_genet_rdma(BCM2838GenetState *s, uint32_t ring_idx,
+ const void *buf, size_t size)
+{
+ const size_t DESC_WORD_SIZE =
+ sizeof(BCM2838GenetRdmaDesc) / sizeof(uint32_t);
+
+ ssize_t len = 0;
+ BCM2838GenetRegsRdma *rdma = &s->regs.rdma;
+ BCM2838GenetRdmaRing *ring = &rdma->rings[ring_idx];
+ hwaddr write_index =
+ (ring->write_ptr + ((hwaddr)ring->write_ptr_hi << 32)) /
DESC_WORD_SIZE;
+ BCM2838GenetRdmaDesc *desc;
+
+ const hwaddr START_INDEX =
+ (ring->start_addr + ((hwaddr)ring->start_addr_hi << 32))
+ / DESC_WORD_SIZE;
+ const hwaddr END_INDEX =
+ (ring->end_addr + ((hwaddr)ring->end_addr_hi << 32)) / DESC_WORD_SIZE;
+
+ if (!bcm2838_genet_rdma_ring_active(s, ring_idx)) {
+ return -1;
+ }
+
+ if (write_index >= BCM2838_GENET_DMA_DESC_CNT) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "%s: invalid RX descriptor index %" PRIu64
+ " (exceeds %u)\n", __func__, (uint64_t)write_index,
+ BCM2838_GENET_DMA_DESC_CNT - 1);
+ return -1;
+ }
+ desc = &rdma->descs[write_index];
+
+ desc->length_status = FIELD_DP32(desc->length_status,
+ GENET_RDMA_LENGTH_STATUS, SOP, 1);
+
+ while (len < size) {
+ size_t l = size - len;
+ size_t buf_size = MIN(ring->ring_buf_size & 0xffff,
+ sizeof(s->rx_packet));
+ uint8_t *dma_buf = s->rx_packet;
+ hwaddr dma_buf_addr =
+ desc->address_lo + ((hwaddr)desc->address_hi << 32);
+ MemTxResult mem_tx_result = MEMTX_OK;
+ uint8_t *frame_buf = dma_buf + sizeof(BCM2838GenetXmitStatus) + 2;
+
+ bool crc_fwd = FIELD_EX32(s->regs.umac.cmd, GENET_UMAC_CMD, CRC_FWD);
+ size_t buflength;
+ uint32_t prod_index;
+
+ if (l > ring->ring_buf_size) {
+ l = ring->ring_buf_size;
+ }
+
+ memcpy(frame_buf, buf + len, l);
+
+ len += l;
+
+ desc->length_status = FIELD_DP32(desc->length_status,
+ GENET_RDMA_LENGTH_STATUS,
+ EOP, !!(len >= size));
+
+ buflength = l + sizeof(BCM2838GenetXmitStatus) + 2;
+ if (crc_fwd) {
+ buflength += 4;
+ }
+
+ desc->length_status = FIELD_DP32(desc->length_status,
+ GENET_RDMA_LENGTH_STATUS,
+ BUFLENGTH, buflength);
+
+ desc->length_status = FIELD_DP32(desc->length_status,
+ GENET_RDMA_LENGTH_STATUS,
+ BROADCAST,
+ !!is_packet_broadcast(frame_buf, l));
+ desc->length_status = FIELD_DP32(desc->length_status,
+ GENET_RDMA_LENGTH_STATUS,
+ MULTICAST,
+ !!is_packet_multicast(frame_buf, l));
+
+ /*
+ * Report no hardware-computed checksum. The IP header's own
+ * checksum was previously (incorrectly) stored here, but the
+ * guest's CHECKSUM_COMPLETE path expects a running checksum over
+ * the L4 payload, not the L3 header checksum -- and it was stored
+ * in host byte order besides. That mismatch was causing the guest
+ * to reject otherwise-valid inbound packets ("hw csum failure" in
+ * dmesg, tied to bcmgenet_rx_poll), breaking DHCP/connectivity
+ * intermittently. Leaving this at 0 makes the guest fall back to
+ * verifying checksums itself in software, which succeeds since the
+ * packet data itself is intact.
+ */
+ stl_le_p(dma_buf + offsetof(BCM2838GenetXmitStatus, rx_csum), 0);
+ stl_le_p(dma_buf + offsetof(BCM2838GenetXmitStatus, length_status),
+ desc->length_status);
+
+ mem_tx_result = address_space_write(&s->dma_as, dma_buf_addr,
+ MEMTXATTRS_UNSPECIFIED,
+ dma_buf, buf_size);
+ if (mem_tx_result != MEMTX_OK) {
+ desc->length_status = FIELD_DP32(desc->length_status,
+ GENET_RDMA_LENGTH_STATUS,
+ RXERR, 1);
+ }
+
+ if (FIELD_EX32(desc->length_status,
+ GENET_RDMA_LENGTH_STATUS, RXERR) != 0) {
+ break;
+ }
+
+ prod_index = FIELD_EX32(ring->prod_index, GENET_DMA_PROD_INDEX, INDEX);
+ ring->prod_index = FIELD_DP32(ring->prod_index,
+ GENET_DMA_PROD_INDEX,
+ INDEX, ++prod_index);
+ if (++write_index > END_INDEX) {
+ write_index = START_INDEX;
+ }
+ if (write_index >= BCM2838_GENET_DMA_DESC_CNT) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "%s: invalid RX descriptor index %" PRIu64
+ " (exceeds %u)\n", __func__, (uint64_t)write_index,
+ BCM2838_GENET_DMA_DESC_CNT - 1);
+ break;
+ }
+ desc = &rdma->descs[write_index];
+ ring->write_ptr = write_index * DESC_WORD_SIZE;
+ ring->write_ptr_hi = ((hwaddr)write_index * DESC_WORD_SIZE) >> 32;
+ }
+
+ if (ring_idx == BCM2838_GENET_DMA_RING_DEFAULT) {
+ s->regs.intrl0.stat = FIELD_DP32(s->regs.intrl0.stat,
+ GENET_INTRL_0, RXDMA_MBDONE, 1);
+ } else {
+ uint32_t rx_intrs =
+ FIELD_EX32(s->regs.intrl1.stat, GENET_INTRL_1, RX_INTRS);
+ rx_intrs |= 1 << ring_idx;
+
+ s->regs.intrl1.stat = FIELD_DP32(s->regs.intrl1.stat,
+ GENET_INTRL_1, RX_INTRS, rx_intrs);
+ }
+
+ return len;
+}
+
+static ssize_t bcm2838_genet_receive(NetClientState *nc, const uint8_t *buf,
+ size_t size)
+{
+ BCM2838GenetState *s = (BCM2838GenetState *)qemu_get_nic_opaque(nc);
+ ssize_t bytes_received = -1;
+ int32_t filter_index = -1;
+ int32_t ring_index = -1;
+
+ if (FIELD_EX32(s->regs.rdma.ctrl, GENET_DMA_CTRL, EN) != 0) {
+ filter_index = bcm2838_genet_filter(s, buf, size);
+
+ if (filter_index >= 0) {
+ ring_index = bcm2838_genet_filter2ring(s, filter_index);
+ } else {
+ ring_index = BCM2838_GENET_DMA_RING_CNT - 1;
+ if (!bcm2838_genet_rdma_ring_active(s, ring_index)) {
+ for (ring_index = 0;
+ ring_index < BCM2838_GENET_DMA_RING_CNT - 1;
+ ring_index++) {
+ if (bcm2838_genet_rdma_ring_active(s, ring_index)) {
+ break;
+ }
+ }
+ }
+ }
+
+ if (size <= MAX_PACKET_SIZE) {
+ bytes_received = bcm2838_genet_rdma(s, ring_index, buf, size);
+ }
+ }
+
+ bcm2838_genet_set_irq_default(s);
+ bcm2838_genet_set_irq_prio(s);
+
+ return bytes_received;
+}
+
+static void bcm2838_genet_phy_update_link(BCM2838GenetState *s)
+{
+ bool qemu_link_down = qemu_get_queue(s->nic)->link_down != 0;
+
+ bool lstatus = FIELD_EX32(s->phy_regs.bmsr, GENET_PHY_BMSR, LSTATUS) != 0;
+
+ if (qemu_link_down && lstatus) {
+ trace_bcm2838_genet_phy_update_link("down");
+
+ s->phy_regs.bmsr = FIELD_DP32(s->phy_regs.bmsr,
+ GENET_PHY_BMSR, ANEGCOMPLETE, 0);
+ s->phy_regs.bmsr = FIELD_DP32(s->phy_regs.bmsr,
+ GENET_PHY_BMSR, LSTATUS, 0);
+ s->regs.intrl0.stat = FIELD_DP32(s->regs.intrl0.stat,
+ GENET_INTRL_0, LINK_DOWN, 1);
+ } else if (!qemu_link_down && !lstatus) {
+ trace_bcm2838_genet_phy_update_link("up");
+
+ /*
+ * Complete auto-negotiation (fixed link partner's abilities for now:
+ * 1Gbps with flow control)
+ */
+ s->phy_regs.stat1000 = FIELD_DP32(s->phy_regs.stat1000,
+ GENET_PHY_STAT_1000, HALF, 1);
+ s->phy_regs.stat1000 = FIELD_DP32(s->phy_regs.stat1000,
+ GENET_PHY_STAT_1000, FULL, 1);
+
+ s->phy_regs.lpa = FIELD_DP32(s->phy_regs.lpa,
+ GENET_PHY_LPA, PAUSE_CAP, 1);
+ s->phy_regs.lpa = FIELD_DP32(s->phy_regs.lpa,
+ GENET_PHY_LPA, PAUSE_ASYM, 1);
+ s->phy_regs.lpa = FIELD_DP32(s->phy_regs.lpa, GENET_PHY_LPA, LPACK, 1);
+
+ s->phy_regs.bmsr = FIELD_DP32(s->phy_regs.bmsr,
+ GENET_PHY_BMSR, ANEGCOMPLETE, 1);
+ s->phy_regs.bmsr = FIELD_DP32(s->phy_regs.bmsr,
+ GENET_PHY_BMSR, LSTATUS, 1);
+
+ s->regs.intrl0.stat = FIELD_DP32(s->regs.intrl0.stat,
+ GENET_INTRL_0, LINK_UP, 1);
+ }
+
+ bcm2838_genet_set_irq_default(s);
+}
+static void bcm2838_genet_set_link(NetClientState *nc)
+{
+ BCM2838GenetState *s = qemu_get_nic_opaque(nc);
+
+ bcm2838_genet_phy_update_link(s);
+}
+
static NetClientInfo bcm2838_genet_client_info = {
.type = NET_CLIENT_DRIVER_NIC,
- .size = sizeof(NICState)
+ .size = sizeof(NICState),
+ .receive = bcm2838_genet_receive,
+ .link_status_changed = bcm2838_genet_set_link,
};
static void bcm2838_genet_realize(DeviceState *dev, Error **errp)
@@ -798,6 +1082,8 @@ static void bcm2838_genet_phy_reset(BCM2838GenetState *s)
s->phy_aux_ctl_shd_regs.misc = 0x1E;
trace_bcm2838_genet_phy_reset("done");
+
+ bcm2838_genet_phy_update_link(s);
}
static void bcm2838_genet_reset(Object *obj, ResetType type)
diff --git a/include/hw/net/bcm2838_genet.h b/include/hw/net/bcm2838_genet.h
index bad582fe0d..960042f6f4 100644
--- a/include/hw/net/bcm2838_genet.h
+++ b/include/hw/net/bcm2838_genet.h
@@ -422,6 +422,7 @@ struct BCM2838GenetState {
qemu_irq irq_prio;
uint8_t tx_packet[MAX_FRAME_SIZE];
+ uint8_t rx_packet[MAX_FRAME_SIZE];
};
#endif /* BCM2838_GENET_H */
--
2.55.0
