[PATCH v3 12/16] hw/net/bcm2838_genet: implement GENET TX path

[Marcelo Manzo <marcelomanzo@gmail.com>]

From: Sergey Kambalin <serg.oker@gmail.com>

Implement the transmit DMA ring handling: walk TX descriptors
between the consumer and producer index for a ring, pull frame data
out of guest memory, and hand completed frames to the netdev peer
via qemu_send_packet(), advancing the consumer index and raising the
TXDMA_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, fix bcm2838_genet_tdma_ring_active():
it extracted the per-ring enable bit using the DMA_CTRL register's
1-bit EN field definition instead of DMA_RING_CFG's 17-bit EN field
(one bit per ring), so only ring 0 ever appeared active and TX
traffic hashed onto any other queue was silently dropped, eventually
tripping the guest's qdisc watchdog ("NETDEV WATCHDOG: transmit
queue N timed out") and breaking DHCP.

Signed-off-by: Sergey Kambalin <sergey.kambalin@auriga.com>
Signed-off-by: Marcelo Manzo <marcelomanzo@gmail.com>
---
 hw/net/bcm2838_genet.c         | 219 ++++++++++++++++++++++++++++++++-
 include/hw/net/bcm2838_genet.h |  17 +++
 2 files changed, 235 insertions(+), 1 deletion(-)

diff --git a/hw/net/bcm2838_genet.c b/hw/net/bcm2838_genet.c
index fe2a3cf890..7eba0edbb6 100644
--- a/hw/net/bcm2838_genet.c
+++ b/hw/net/bcm2838_genet.c
@@ -239,6 +239,13 @@ REG16(GENET_PHY_EXP_SEL,           0)
 FIELD(GENET_PHY_EXP_SEL, REG_ID,   0, 8)
 FIELD(GENET_PHY_EXP_SEL, BLOCK_ID, 8, 8)
 
+REG32(GENET_TX_CSUM_INFO,            0)
+FIELD(GENET_TX_CSUM_INFO, OFFSET,    0, 15)
+FIELD(GENET_TX_CSUM_INFO, PROTO_UDP, 15, 1)
+FIELD(GENET_TX_CSUM_INFO, START,     16, 15)
+FIELD(GENET_TX_CSUM_INFO, LV,        30, 1)
+
+
 static void bcm2838_genet_set_qemu_mac(BCM2838GenetState *s)
 {
     const MACAddr *addr = &s->nic_conf.macaddr;
@@ -403,6 +410,216 @@ static uint64_t bcm2838_genet_mdio_cmd(BCM2838GenetState *s, uint64_t cmd)
     return cmd;
 }
 
+static void bcm2838_genet_xmit_packet(NetClientState *s, void *packet,
+                                      size_t size)
+{
+    uint8_t *buf = packet + sizeof(BCM2838GenetXmitStatus);
+    size_t len = size;
+    uint16_t len_type = 0;
+
+    len -= sizeof(BCM2838GenetXmitStatus);
+    net_checksum_calculate(buf, len, CSUM_ALL);
+
+    memcpy(&len_type, &buf[12], sizeof(len_type));
+    len_type = ntohs(len_type);
+    if (len_type < MAX_PAYLOAD_SIZE) {
+        len_type = len;
+        len_type = htons(len_type);
+        memcpy(&buf[12], &len_type, sizeof(len_type));
+    }
+
+    qemu_send_packet(s, buf, len);
+}
+
+static uint64_t bcm2838_genet_tx(BCM2838GenetState *s, unsigned int ring_index,
+                                 uint32_t prod_index,
+                                 uint32_t cons_index)
+{
+    const unsigned int DESC_SIZE_WORDS
+        = sizeof(BCM2838GenetTdmaDesc) / sizeof(uint32_t);
+    const uint64_t RING_START_ADDR
+        = ((uint64_t)s->regs.tdma.rings[ring_index].start_addr_hi << 32)
+            + s->regs.tdma.rings[ring_index].start_addr;
+    const uint64_t RING_END_ADDR
+        = ((uint64_t)s->regs.tdma.rings[ring_index].end_addr_hi << 32)
+            + s->regs.tdma.rings[ring_index].end_addr;
+
+    hwaddr data_addr;
+    uint64_t desc_index;
+    uint32_t desc_status = 0;
+    uint32_t buflength = 0;
+    uint64_t num_descs = 0;
+    uint64_t read_ptr
+        = ((uint64_t)s->regs.tdma.rings[ring_index].read_ptr_hi << 32)
+            + s->regs.tdma.rings[ring_index].read_ptr;
+    off_t packet_off = 0;
+
+    uint32_t prod_index_fld = FIELD_EX32(prod_index,
+                                         GENET_DMA_PROD_INDEX, INDEX);
+    uint32_t cons_index_fld = FIELD_EX32(cons_index,
+                                        GENET_DMA_CONS_INDEX, INDEX);
+
+    while (cons_index_fld != prod_index_fld) {
+        desc_index = read_ptr / DESC_SIZE_WORDS;
+        if (desc_index >= BCM2838_GENET_DMA_DESC_CNT) {
+            qemu_log_mask(
+                LOG_GUEST_ERROR,
+                "%s: invalid TX descriptor index %" PRIu64 " (exceeds %u)\n",
+                __func__, desc_index, BCM2838_GENET_DMA_DESC_CNT - 1);
+            break;
+        }
+        desc_status = s->regs.tdma.descs[desc_index].length_status;
+        data_addr = ((uint64_t)s->regs.tdma.descs[desc_index].address_hi << 32)
+            + s->regs.tdma.descs[desc_index].address_lo;
+        trace_bcm2838_genet_tx(ring_index, desc_index, desc_status,
+                               data_addr);
+
+        if (FIELD_EX32(desc_status, GENET_RDMA_LENGTH_STATUS, SOP) != 0) {
+            packet_off = 0;
+        }
+
+        buflength = FIELD_EX32(desc_status,
+                               GENET_RDMA_LENGTH_STATUS, BUFLENGTH);
+
+        /* TODO: Add address_space_read() return value check */
+        address_space_read(&s->dma_as, data_addr,
+                                        MEMTXATTRS_UNSPECIFIED,
+                                        s->tx_packet + packet_off,
+                                        buflength);
+        packet_off += buflength;
+
+        if (FIELD_EX32(desc_status, GENET_RDMA_LENGTH_STATUS, EOP) != 0) {
+            bcm2838_genet_xmit_packet(qemu_get_queue(s->nic), s->tx_packet,
+                                                     packet_off);
+            packet_off = 0;
+        }
+
+        num_descs++;
+        cons_index_fld++;
+        s->regs.tdma.descs[desc_index].length_status =
+            FIELD_DP32(s->regs.tdma.descs[desc_index].length_status,
+                       GENET_RDMA_LENGTH_STATUS, OWN, 1);
+        read_ptr = read_ptr == RING_END_ADDR + 1 - DESC_SIZE_WORDS
+            ? RING_START_ADDR : read_ptr + DESC_SIZE_WORDS;
+    }
+
+    s->regs.tdma.rings[ring_index].read_ptr = read_ptr;
+    s->regs.tdma.rings[ring_index].read_ptr_hi = read_ptr >> 32;
+
+    return num_descs;
+}
+
+static bool bcm2838_genet_tdma_ring_active(BCM2838GenetState *s,
+                                           unsigned int ring_index)
+{
+    uint32_t ctrl_reg = s->regs.tdma.ctrl;
+    uint32_t ring_cfg_reg = s->regs.tdma.ring_cfg;
+    uint32_t ring_mask = 1 << ring_index;
+    bool dma_en = FIELD_EX32(ctrl_reg, GENET_DMA_CTRL, EN) != 0;
+    bool ring_en =
+        (FIELD_EX32(ring_cfg_reg, GENET_DMA_RING_CFG, EN) & ring_mask) != 0;
+    bool ring_buf_en =
+        (FIELD_EX32(ctrl_reg, GENET_DMA_CTRL, RING_BUF_EN) & ring_mask) != 0;
+    bool active = dma_en && ring_en && ring_buf_en;
+
+    trace_bcm2838_genet_tx_dma_ring_active(ring_index,
+                                           active ? "active" : "halted");
+    return active;
+}
+
+static void bcm2838_genet_tdma(BCM2838GenetState *s, hwaddr offset,
+                               uint64_t value)
+{
+    hwaddr ring_offset;
+    uint64_t num_descs_tx;
+    unsigned int ring_index;
+     uint32_t tx_intrs;
+    uint32_t cons_index;
+    uint32_t prod_index = value;
+    uint32_t ring_cfg = value;
+    uint32_t dma_ctrl = value;
+
+    uint32_t cons_index_fld;
+    uint32_t prod_index_fld =
+        FIELD_EX32(prod_index, GENET_DMA_PROD_INDEX, INDEX);
+
+    uint32_t exst_tdma_en =
+        FIELD_EX32(s->regs.tdma.ctrl, GENET_DMA_CTRL, EN);
+    uint32_t exst_ring_en =
+        FIELD_EX32(s->regs.tdma.ring_cfg, GENET_DMA_RING_CFG, EN);
+    uint32_t incm_tdma_en =
+        FIELD_EX32(dma_ctrl, GENET_DMA_CTRL, EN);
+    uint32_t incm_ring_en =
+        FIELD_EX32(ring_cfg, GENET_DMA_RING_CFG, EN);
+    uint32_t incm_ring_buf_en =
+        FIELD_EX32(dma_ctrl, GENET_DMA_CTRL, RING_BUF_EN);
+
+    switch (offset) {
+    case BCM2838_GENET_TDMA_RINGS
+        ... BCM2838_GENET_TDMA_RINGS + sizeof(s->regs.tdma.rings) - 1:
+        ring_index = (offset - BCM2838_GENET_TDMA_RINGS)
+            / sizeof(BCM2838GenetTdmaRing);
+        if (bcm2838_genet_tdma_ring_active(s, ring_index)) {
+            ring_offset = offset - BCM2838_GENET_TDMA_RINGS
+                - ring_index * sizeof(BCM2838GenetTdmaRing);
+            switch (ring_offset) {
+            case BCM2838_GENET_TRING_PROD_INDEX:
+                cons_index = s->regs.tdma.rings[ring_index].cons_index;
+                cons_index_fld = FIELD_EX32(cons_index,
+                                            GENET_DMA_CONS_INDEX, INDEX);
+                if (cons_index_fld != prod_index_fld) {
+                    trace_bcm2838_genet_tx_request(ring_index,
+                                                   prod_index_fld,
+                                                   cons_index_fld);
+                    num_descs_tx = bcm2838_genet_tx(s, ring_index, prod_index,
+                                                    cons_index);
+                    if (num_descs_tx > 0) {
+                        s->regs.tdma.rings[ring_index].cons_index =
+                            FIELD_DP32(s->regs.tdma.rings[ring_index].cons_index,
+                                       GENET_DMA_CONS_INDEX, INDEX,
+                                       cons_index + num_descs_tx);
+
+                        if (ring_index == BCM2838_GENET_DMA_RING_DEFAULT) {
+                            s->regs.intrl0.stat =
+                                FIELD_DP32(s->regs.intrl0.stat, GENET_INTRL_0,
+                                           TXDMA_MBDONE, 1);
+                        } else {
+                            tx_intrs =  FIELD_EX32(s->regs.intrl1.stat,
+                                                   GENET_INTRL_1, TX_INTRS);
+                            s->regs.intrl1.stat =
+                                FIELD_DP32(s->regs.intrl1.stat,
+                                           GENET_INTRL_1, TX_INTRS,
+                                           tx_intrs | 1 << ring_index);
+                        }
+                    }
+                }
+                break;
+            default:
+                break;
+            }
+        }
+        break;
+    case BCM2838_GENET_TDMA_RING_CFG:
+        if (exst_ring_en != incm_ring_en) {
+            trace_bcm2838_genet_tx_dma_ring(incm_ring_en);
+        }
+        break;
+    case BCM2838_GENET_TDMA_CTRL:
+        s->regs.tdma.status = (~dma_ctrl) & GENET_DMA_ENABLE_MASK;
+        if (exst_tdma_en != incm_tdma_en) {
+            trace_bcm2838_genet_tx_dma(incm_tdma_en == 1
+                                       ? "enabled"
+                                       : "disabled");
+        }
+        if (exst_ring_en != incm_ring_buf_en) {
+            trace_bcm2838_genet_tx_dma_ring_buf(incm_ring_buf_en);
+        }
+        break;
+    default:
+        break;
+    }
+}
+
 static uint64_t bcm2838_genet_read(void *opaque, hwaddr offset, unsigned size)
 {
     uint64_t value = ~0;
@@ -496,7 +713,7 @@ static void bcm2838_genet_write(void *opaque, hwaddr offset, uint64_t value,
             break;
         case BCM2838_GENET_TDMA_REGS
             ... BCM2838_GENET_TDMA_REGS + sizeof(BCM2838GenetRegsTdma) - 1:
-            qemu_log_mask(LOG_UNIMP, "TDMA isn't implemented yet");
+            bcm2838_genet_tdma(s, offset, value);
             break;
         default:
             break;
diff --git a/include/hw/net/bcm2838_genet.h b/include/hw/net/bcm2838_genet.h
index b34c4b3ce7..bad582fe0d 100644
--- a/include/hw/net/bcm2838_genet.h
+++ b/include/hw/net/bcm2838_genet.h
@@ -110,6 +110,21 @@ OBJECT_DECLARE_SIMPLE_TYPE(BCM2838GenetState, BCM2838_GENET)
 #define BCM2838_GENET_PHY_EXP_SHD_BLOCKS_CNT 256
 #define BCM2838_GENET_PHY_EXP_SHD_REGS_CNT   256
 
+#define MAX_FRAME_SIZE                  0xFFF
+#define MAX_PACKET_SIZE                 1518
+#define MAX_PAYLOAD_SIZE                1500
+#define TX_MIN_PKT_SIZE                 60
+
+
+typedef struct BCM2838GenetXmitStatus {
+    uint32_t  length_status;  /* length and peripheral status */
+    uint32_t  ext_status;     /* Extended status */
+    uint32_t  rx_csum;        /* partial rx checksum */
+    uint32_t  unused1[9];     /* unused */
+    uint32_t  tx_csum_info;   /* Tx checksum info. */
+    uint32_t  unused2[3];     /* unused */
+} BCM2838GenetXmitStatus;
+
 typedef struct {
     uint32_t rev_ctrl;
     uint32_t port_ctrl;
@@ -405,6 +420,8 @@ struct BCM2838GenetState {
 
     qemu_irq irq_default;
     qemu_irq irq_prio;
+
+    uint8_t tx_packet[MAX_FRAME_SIZE];
 };
 
 #endif /* BCM2838_GENET_H */
-- 
2.55.0