diff options
Diffstat (limited to 'hw')
| -rw-r--r-- | hw/acpi/pcihp.c | 6 | ||||
| -rw-r--r-- | hw/arm/aspeed.c | 17 | ||||
| -rw-r--r-- | hw/arm/aspeed_ast10x0.c | 18 | ||||
| -rw-r--r-- | hw/i2c/aspeed_i2c.c | 820 | ||||
| -rw-r--r-- | hw/i2c/trace-events | 2 | ||||
| -rw-r--r-- | hw/intc/pnv_xive2.c | 18 | ||||
| -rw-r--r-- | hw/misc/aspeed_hace.c | 4 | ||||
| -rw-r--r-- | hw/nvme/ctrl.c | 741 | ||||
| -rw-r--r-- | hw/nvme/ns.c | 2 | ||||
| -rw-r--r-- | hw/nvme/nvme.h | 55 | ||||
| -rw-r--r-- | hw/nvme/subsys.c | 75 | ||||
| -rw-r--r-- | hw/nvme/trace-events | 6 | ||||
| -rw-r--r-- | hw/pci-host/pnv_phb3.c | 8 | ||||
| -rw-r--r-- | hw/pci-host/pnv_phb4.c | 10 | ||||
| -rw-r--r-- | hw/pci-host/pnv_phb4_pec.c | 10 | ||||
| -rw-r--r-- | hw/ppc/ppc440_uc.c | 8 |
16 files changed, 1366 insertions, 434 deletions
diff --git a/hw/acpi/pcihp.c b/hw/acpi/pcihp.c index bf65bbea49..84d75e6b84 100644 --- a/hw/acpi/pcihp.c +++ b/hw/acpi/pcihp.c @@ -192,8 +192,12 @@ static bool acpi_pcihp_pc_no_hotplug(AcpiPciHpState *s, PCIDevice *dev) * ACPI doesn't allow hotplug of bridge devices. Don't allow * hot-unplug of bridge devices unless they were added by hotplug * (and so, not described by acpi). + * + * Don't allow hot-unplug of SR-IOV Virtual Functions, as they + * will be removed implicitly, when Physical Function is unplugged. */ - return (pc->is_bridge && !dev->qdev.hotplugged) || !dc->hotpluggable; + return (pc->is_bridge && !dev->qdev.hotplugged) || !dc->hotpluggable || + pci_is_vf(dev); } static void acpi_pcihp_eject_slot(AcpiPciHpState *s, unsigned bsel, unsigned slots) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index 98dc185acd..a06f7c1b62 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -519,10 +519,6 @@ static void ast2500_evb_i2c_init(AspeedMachineState *bmc) /* The AST2500 EVB expects a LM75 but a TMP105 is compatible */ i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 7), TYPE_TMP105, 0x4d); - - /* The AST2500 EVB does not have an RTC. Let's pretend that one is - * plugged on the I2C bus header */ - i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 11), "ds1338", 0x32); } static void ast2600_evb_i2c_init(AspeedMachineState *bmc) @@ -1401,6 +1397,18 @@ static void aspeed_minibmc_machine_init(MachineState *machine) AST1030_INTERNAL_FLASH_SIZE); } +static void ast1030_evb_i2c_init(AspeedMachineState *bmc) +{ + AspeedSoCState *soc = &bmc->soc; + + /* U10 24C08 connects to SDA/SCL Groupt 1 by default */ + uint8_t *eeprom_buf = g_malloc0(32 * 1024); + smbus_eeprom_init_one(aspeed_i2c_get_bus(&soc->i2c, 0), 0x50, eeprom_buf); + + /* U11 LM75 connects to SDA/SCL Group 2 by default */ + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 1), "tmp105", 0x4d); +} + static void aspeed_minibmc_machine_ast1030_evb_class_init(ObjectClass *oc, void *data) { @@ -1412,6 +1420,7 @@ static void aspeed_minibmc_machine_ast1030_evb_class_init(ObjectClass *oc, amc->hw_strap1 = 0; amc->hw_strap2 = 0; mc->init = aspeed_minibmc_machine_init; + amc->i2c_init = ast1030_evb_i2c_init; mc->default_ram_size = 0; mc->default_cpus = mc->min_cpus = mc->max_cpus = 1; amc->fmc_model = "sst25vf032b"; diff --git a/hw/arm/aspeed_ast10x0.c b/hw/arm/aspeed_ast10x0.c index d534541684..5df480a21f 100644 --- a/hw/arm/aspeed_ast10x0.c +++ b/hw/arm/aspeed_ast10x0.c @@ -114,6 +114,9 @@ static void aspeed_soc_ast1030_init(Object *obj) object_property_add_alias(obj, "hw-strap1", OBJECT(&s->scu), "hw-strap1"); object_property_add_alias(obj, "hw-strap2", OBJECT(&s->scu), "hw-strap2"); + snprintf(typename, sizeof(typename), "aspeed.i2c-%s", socname); + object_initialize_child(obj, "i2c", &s->i2c, typename); + snprintf(typename, sizeof(typename), "aspeed.timer-%s", socname); object_initialize_child(obj, "timerctrl", &s->timerctrl, typename); @@ -188,6 +191,21 @@ static void aspeed_soc_ast1030_realize(DeviceState *dev_soc, Error **errp) } sysbus_mmio_map(SYS_BUS_DEVICE(&s->scu), 0, sc->memmap[ASPEED_DEV_SCU]); + /* I2C */ + + object_property_set_link(OBJECT(&s->i2c), "dram", OBJECT(&s->sram), + &error_abort); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->i2c), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c), 0, sc->memmap[ASPEED_DEV_I2C]); + for (i = 0; i < ASPEED_I2C_GET_CLASS(&s->i2c)->num_busses; i++) { + qemu_irq irq = qdev_get_gpio_in(DEVICE(&s->armv7m), + sc->irqmap[ASPEED_DEV_I2C] + i); + /* The AST1030 I2C controller has one IRQ per bus. */ + sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c.busses[i]), 0, irq); + } + /* LPC */ if (!sysbus_realize(SYS_BUS_DEVICE(&s->lpc), errp)) { return; diff --git a/hw/i2c/aspeed_i2c.c b/hw/i2c/aspeed_i2c.c index 03a4f5a910..37ae1f2e04 100644 --- a/hw/i2c/aspeed_i2c.c +++ b/hw/i2c/aspeed_i2c.c @@ -21,6 +21,7 @@ #include "qemu/osdep.h" #include "hw/sysbus.h" #include "migration/vmstate.h" +#include "qemu/cutils.h" #include "qemu/log.h" #include "qemu/module.h" #include "qemu/error-report.h" @@ -28,196 +29,86 @@ #include "hw/i2c/aspeed_i2c.h" #include "hw/irq.h" #include "hw/qdev-properties.h" +#include "hw/registerfields.h" #include "trace.h" -/* I2C Global Register */ - -#define I2C_CTRL_STATUS 0x00 /* Device Interrupt Status */ -#define I2C_CTRL_ASSIGN 0x08 /* Device Interrupt Target - Assignment */ -#define I2C_CTRL_GLOBAL 0x0C /* Global Control Register */ -#define I2C_CTRL_SRAM_EN BIT(0) - -/* I2C Device (Bus) Register */ - -#define I2CD_FUN_CTRL_REG 0x00 /* I2CD Function Control */ -#define I2CD_POOL_PAGE_SEL(x) (((x) >> 20) & 0x7) /* AST2400 */ -#define I2CD_M_SDA_LOCK_EN (0x1 << 16) -#define I2CD_MULTI_MASTER_DIS (0x1 << 15) -#define I2CD_M_SCL_DRIVE_EN (0x1 << 14) -#define I2CD_MSB_STS (0x1 << 9) -#define I2CD_SDA_DRIVE_1T_EN (0x1 << 8) -#define I2CD_M_SDA_DRIVE_1T_EN (0x1 << 7) -#define I2CD_M_HIGH_SPEED_EN (0x1 << 6) -#define I2CD_DEF_ADDR_EN (0x1 << 5) -#define I2CD_DEF_ALERT_EN (0x1 << 4) -#define I2CD_DEF_ARP_EN (0x1 << 3) -#define I2CD_DEF_GCALL_EN (0x1 << 2) -#define I2CD_SLAVE_EN (0x1 << 1) -#define I2CD_MASTER_EN (0x1) - -#define I2CD_AC_TIMING_REG1 0x04 /* Clock and AC Timing Control #1 */ -#define I2CD_AC_TIMING_REG2 0x08 /* Clock and AC Timing Control #1 */ -#define I2CD_INTR_CTRL_REG 0x0c /* I2CD Interrupt Control */ -#define I2CD_INTR_STS_REG 0x10 /* I2CD Interrupt Status */ - -#define I2CD_INTR_SLAVE_ADDR_MATCH (0x1 << 31) /* 0: addr1 1: addr2 */ -#define I2CD_INTR_SLAVE_ADDR_RX_PENDING (0x1 << 30) -/* bits[19-16] Reserved */ - -/* All bits below are cleared by writing 1 */ -#define I2CD_INTR_SLAVE_INACTIVE_TIMEOUT (0x1 << 15) -#define I2CD_INTR_SDA_DL_TIMEOUT (0x1 << 14) -#define I2CD_INTR_BUS_RECOVER_DONE (0x1 << 13) -#define I2CD_INTR_SMBUS_ALERT (0x1 << 12) /* Bus [0-3] only */ -#define I2CD_INTR_SMBUS_ARP_ADDR (0x1 << 11) /* Removed */ -#define I2CD_INTR_SMBUS_DEV_ALERT_ADDR (0x1 << 10) /* Removed */ -#define I2CD_INTR_SMBUS_DEF_ADDR (0x1 << 9) /* Removed */ -#define I2CD_INTR_GCALL_ADDR (0x1 << 8) /* Removed */ -#define I2CD_INTR_SLAVE_ADDR_RX_MATCH (0x1 << 7) /* use RX_DONE */ -#define I2CD_INTR_SCL_TIMEOUT (0x1 << 6) -#define I2CD_INTR_ABNORMAL (0x1 << 5) -#define I2CD_INTR_NORMAL_STOP (0x1 << 4) -#define I2CD_INTR_ARBIT_LOSS (0x1 << 3) -#define I2CD_INTR_RX_DONE (0x1 << 2) -#define I2CD_INTR_TX_NAK (0x1 << 1) -#define I2CD_INTR_TX_ACK (0x1 << 0) - -#define I2CD_CMD_REG 0x14 /* I2CD Command/Status */ -#define I2CD_SDA_OE (0x1 << 28) -#define I2CD_SDA_O (0x1 << 27) -#define I2CD_SCL_OE (0x1 << 26) -#define I2CD_SCL_O (0x1 << 25) -#define I2CD_TX_TIMING (0x1 << 24) -#define I2CD_TX_STATUS (0x1 << 23) - -#define I2CD_TX_STATE_SHIFT 19 /* Tx State Machine */ -#define I2CD_TX_STATE_MASK 0xf -#define I2CD_IDLE 0x0 -#define I2CD_MACTIVE 0x8 -#define I2CD_MSTART 0x9 -#define I2CD_MSTARTR 0xa -#define I2CD_MSTOP 0xb -#define I2CD_MTXD 0xc -#define I2CD_MRXACK 0xd -#define I2CD_MRXD 0xe -#define I2CD_MTXACK 0xf -#define I2CD_SWAIT 0x1 -#define I2CD_SRXD 0x4 -#define I2CD_STXACK 0x5 -#define I2CD_STXD 0x6 -#define I2CD_SRXACK 0x7 -#define I2CD_RECOVER 0x3 - -#define I2CD_SCL_LINE_STS (0x1 << 18) -#define I2CD_SDA_LINE_STS (0x1 << 17) -#define I2CD_BUS_BUSY_STS (0x1 << 16) -#define I2CD_SDA_OE_OUT_DIR (0x1 << 15) -#define I2CD_SDA_O_OUT_DIR (0x1 << 14) -#define I2CD_SCL_OE_OUT_DIR (0x1 << 13) -#define I2CD_SCL_O_OUT_DIR (0x1 << 12) -#define I2CD_BUS_RECOVER_CMD_EN (0x1 << 11) -#define I2CD_S_ALT_EN (0x1 << 10) - -/* Command Bit */ -#define I2CD_RX_DMA_ENABLE (0x1 << 9) -#define I2CD_TX_DMA_ENABLE (0x1 << 8) -#define I2CD_RX_BUFF_ENABLE (0x1 << 7) -#define I2CD_TX_BUFF_ENABLE (0x1 << 6) -#define I2CD_M_STOP_CMD (0x1 << 5) -#define I2CD_M_S_RX_CMD_LAST (0x1 << 4) -#define I2CD_M_RX_CMD (0x1 << 3) -#define I2CD_S_TX_CMD (0x1 << 2) -#define I2CD_M_TX_CMD (0x1 << 1) -#define I2CD_M_START_CMD (0x1) - -#define I2CD_DEV_ADDR_REG 0x18 /* Slave Device Address */ -#define I2CD_POOL_CTRL_REG 0x1c /* Pool Buffer Control */ -#define I2CD_POOL_RX_COUNT(x) (((x) >> 24) & 0xff) -#define I2CD_POOL_RX_SIZE(x) ((((x) >> 16) & 0xff) + 1) -#define I2CD_POOL_TX_COUNT(x) ((((x) >> 8) & 0xff) + 1) -#define I2CD_POOL_OFFSET(x) (((x) & 0x3f) << 2) /* AST2400 */ -#define I2CD_BYTE_BUF_REG 0x20 /* Transmit/Receive Byte Buffer */ -#define I2CD_BYTE_BUF_TX_SHIFT 0 -#define I2CD_BYTE_BUF_TX_MASK 0xff -#define I2CD_BYTE_BUF_RX_SHIFT 8 -#define I2CD_BYTE_BUF_RX_MASK 0xff -#define I2CD_DMA_ADDR 0x24 /* DMA Buffer Address */ -#define I2CD_DMA_LEN 0x28 /* DMA Transfer Length < 4KB */ - -static inline bool aspeed_i2c_bus_is_master(AspeedI2CBus *bus) -{ - return bus->ctrl & I2CD_MASTER_EN; -} - -static inline bool aspeed_i2c_bus_is_enabled(AspeedI2CBus *bus) -{ - return bus->ctrl & (I2CD_MASTER_EN | I2CD_SLAVE_EN); -} +/* Enable SLAVE_ADDR_RX_MATCH always */ +#define R_I2CD_INTR_STS_ALWAYS_ENABLE R_I2CD_INTR_STS_SLAVE_ADDR_RX_MATCH_MASK static inline void aspeed_i2c_bus_raise_interrupt(AspeedI2CBus *bus) { AspeedI2CClass *aic = ASPEED_I2C_GET_CLASS(bus->controller); + uint32_t reg_intr_sts = aspeed_i2c_bus_intr_sts_offset(bus); + uint32_t intr_ctrl_reg = aspeed_i2c_bus_intr_ctrl_offset(bus); + uint32_t intr_ctrl_mask = bus->regs[intr_ctrl_reg] | + R_I2CD_INTR_STS_ALWAYS_ENABLE; + bool raise_irq; + + if (trace_event_get_state_backends(TRACE_ASPEED_I2C_BUS_RAISE_INTERRUPT)) { + g_autofree char *buf = g_strdup_printf("%s%s%s%s%s%s%s", + aspeed_i2c_bus_pkt_mode_en(bus) && + ARRAY_FIELD_EX32(bus->regs, I2CM_INTR_STS, PKT_CMD_DONE) ? + "pktdone|" : "", + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_intr_sts, TX_NAK) ? + "nak|" : "", + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_intr_sts, TX_ACK) ? + "ack|" : "", + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_intr_sts, RX_DONE) ? + "done|" : "", + ARRAY_FIELD_EX32(bus->regs, I2CD_INTR_STS, SLAVE_ADDR_RX_MATCH) ? + "slave-match|" : "", + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_intr_sts, NORMAL_STOP) ? + "normal|" : "", + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_intr_sts, ABNORMAL) ? + "abnormal" : ""); + + trace_aspeed_i2c_bus_raise_interrupt(bus->regs[reg_intr_sts], buf); + } - trace_aspeed_i2c_bus_raise_interrupt(bus->intr_status, - bus->intr_status & I2CD_INTR_TX_NAK ? "nak|" : "", - bus->intr_status & I2CD_INTR_TX_ACK ? "ack|" : "", - bus->intr_status & I2CD_INTR_RX_DONE ? "done|" : "", - bus->intr_status & I2CD_INTR_NORMAL_STOP ? "normal|" : "", - bus->intr_status & I2CD_INTR_ABNORMAL ? "abnormal" : ""); + raise_irq = bus->regs[reg_intr_sts] & intr_ctrl_mask ; - bus->intr_status &= bus->intr_ctrl; - if (bus->intr_status) { + /* In packet mode we don't mask off INTR_STS */ + if (!aspeed_i2c_bus_pkt_mode_en(bus)) { + bus->regs[reg_intr_sts] &= intr_ctrl_mask; + } + + if (raise_irq) { bus->controller->intr_status |= 1 << bus->id; qemu_irq_raise(aic->bus_get_irq(bus)); } } -static uint64_t aspeed_i2c_bus_read(void *opaque, hwaddr offset, - unsigned size) +static uint64_t aspeed_i2c_bus_old_read(AspeedI2CBus *bus, hwaddr offset, + unsigned size) { - AspeedI2CBus *bus = opaque; AspeedI2CClass *aic = ASPEED_I2C_GET_CLASS(bus->controller); - uint64_t value = -1; + uint64_t value = bus->regs[offset / sizeof(*bus->regs)]; switch (offset) { - case I2CD_FUN_CTRL_REG: - value = bus->ctrl; + case A_I2CD_FUN_CTRL: + case A_I2CD_AC_TIMING1: + case A_I2CD_AC_TIMING2: + case A_I2CD_INTR_CTRL: + case A_I2CD_INTR_STS: + case A_I2CD_DEV_ADDR: + case A_I2CD_POOL_CTRL: + case A_I2CD_BYTE_BUF: + /* Value is already set, don't do anything. */ break; - case I2CD_AC_TIMING_REG1: - value = bus->timing[0]; + case A_I2CD_CMD: + value = SHARED_FIELD_DP32(value, BUS_BUSY_STS, i2c_bus_busy(bus->bus)); break; - case I2CD_AC_TIMING_REG2: - value = bus->timing[1]; - break; - case I2CD_INTR_CTRL_REG: - value = bus->intr_ctrl; - break; - case I2CD_INTR_STS_REG: - value = bus->intr_status; - break; - case I2CD_POOL_CTRL_REG: - value = bus->pool_ctrl; - break; - case I2CD_BYTE_BUF_REG: - value = bus->buf; - break; - case I2CD_CMD_REG: - value = bus->cmd | (i2c_bus_busy(bus->bus) << 16); - break; - case I2CD_DMA_ADDR: + case A_I2CD_DMA_ADDR: if (!aic->has_dma) { qemu_log_mask(LOG_GUEST_ERROR, "%s: No DMA support\n", __func__); - break; + value = -1; } - value = bus->dma_addr; break; - case I2CD_DMA_LEN: + case A_I2CD_DMA_LEN: if (!aic->has_dma) { qemu_log_mask(LOG_GUEST_ERROR, "%s: No DMA support\n", __func__); - break; + value = -1; } - value = bus->dma_len; break; default: @@ -231,32 +122,86 @@ static uint64_t aspeed_i2c_bus_read(void *opaque, hwaddr offset, return value; } +static uint64_t aspeed_i2c_bus_new_read(AspeedI2CBus *bus, hwaddr offset, + unsigned size) +{ + uint64_t value = bus->regs[offset / sizeof(*bus->regs)]; + + switch (offset) { + case A_I2CC_FUN_CTRL: + case A_I2CC_AC_TIMING: + case A_I2CC_POOL_CTRL: + case A_I2CM_INTR_CTRL: + case A_I2CM_INTR_STS: + case A_I2CC_MS_TXRX_BYTE_BUF: + case A_I2CM_DMA_LEN: + case A_I2CM_DMA_TX_ADDR: + case A_I2CM_DMA_RX_ADDR: + case A_I2CM_DMA_LEN_STS: + case A_I2CC_DMA_ADDR: + case A_I2CC_DMA_LEN: + /* Value is already set, don't do anything. */ + break; + case A_I2CM_CMD: + value = SHARED_FIELD_DP32(value, BUS_BUSY_STS, i2c_bus_busy(bus->bus)); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, offset); + value = -1; + break; + } + + trace_aspeed_i2c_bus_read(bus->id, offset, size, value); + return value; +} + +static uint64_t aspeed_i2c_bus_read(void *opaque, hwaddr offset, + unsigned size) +{ + AspeedI2CBus *bus = opaque; + if (aspeed_i2c_is_new_mode(bus->controller)) { + return aspeed_i2c_bus_new_read(bus, offset, size); + } + return aspeed_i2c_bus_old_read(bus, offset, size); +} + static void aspeed_i2c_set_state(AspeedI2CBus *bus, uint8_t state) { - bus->cmd &= ~(I2CD_TX_STATE_MASK << I2CD_TX_STATE_SHIFT); - bus->cmd |= (state & I2CD_TX_STATE_MASK) << I2CD_TX_STATE_SHIFT; + if (aspeed_i2c_is_new_mode(bus->controller)) { + SHARED_ARRAY_FIELD_DP32(bus->regs, R_I2CC_MS_TXRX_BYTE_BUF, TX_STATE, + state); + } else { + SHARED_ARRAY_FIELD_DP32(bus->regs, R_I2CD_CMD, TX_STATE, state); + } } static uint8_t aspeed_i2c_get_state(AspeedI2CBus *bus) { - return (bus->cmd >> I2CD_TX_STATE_SHIFT) & I2CD_TX_STATE_MASK; + if (aspeed_i2c_is_new_mode(bus->controller)) { + return SHARED_ARRAY_FIELD_EX32(bus->regs, R_I2CC_MS_TXRX_BYTE_BUF, + TX_STATE); + } + return SHARED_ARRAY_FIELD_EX32(bus->regs, R_I2CD_CMD, TX_STATE); } static int aspeed_i2c_dma_read(AspeedI2CBus *bus, uint8_t *data) { MemTxResult result; AspeedI2CState *s = bus->controller; + uint32_t reg_dma_addr = aspeed_i2c_bus_dma_addr_offset(bus); + uint32_t reg_dma_len = aspeed_i2c_bus_dma_len_offset(bus); - result = address_space_read(&s->dram_as, bus->dma_addr, + result = address_space_read(&s->dram_as, bus->regs[reg_dma_addr], MEMTXATTRS_UNSPECIFIED, data, 1); if (result != MEMTX_OK) { qemu_log_mask(LOG_GUEST_ERROR, "%s: DRAM read failed @%08x\n", - __func__, bus->dma_addr); + __func__, bus->regs[reg_dma_addr]); return -1; } - bus->dma_addr++; - bus->dma_len--; + bus->regs[reg_dma_addr]++; + bus->regs[reg_dma_len]--; return 0; } @@ -265,34 +210,51 @@ static int aspeed_i2c_bus_send(AspeedI2CBus *bus, uint8_t pool_start) AspeedI2CClass *aic = ASPEED_I2C_GET_CLASS(bus->controller); int ret = -1; int i; - - if (bus->cmd & I2CD_TX_BUFF_ENABLE) { - for (i = pool_start; i < I2CD_POOL_TX_COUNT(bus->pool_ctrl); i++) { + uint32_t reg_cmd = aspeed_i2c_bus_cmd_offset(bus); + uint32_t reg_pool_ctrl = aspeed_i2c_bus_pool_ctrl_offset(bus); + uint32_t reg_byte_buf = aspeed_i2c_bus_byte_buf_offset(bus); + uint32_t reg_dma_len = aspeed_i2c_bus_dma_len_offset(bus); + int pool_tx_count = SHARED_ARRAY_FIELD_EX32(bus->regs, reg_pool_ctrl, + TX_COUNT); + + if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_BUFF_EN)) { + for (i = pool_start; i < pool_tx_count; i++) { uint8_t *pool_base = aic->bus_pool_base(bus); - trace_aspeed_i2c_bus_send("BUF", i + 1, - I2CD_POOL_TX_COUNT(bus->pool_ctrl), + trace_aspeed_i2c_bus_send("BUF", i + 1, pool_tx_count, pool_base[i]); ret = i2c_send(bus->bus, pool_base[i]); if (ret) { break; } } - bus->cmd &= ~I2CD_TX_BUFF_ENABLE; - } else if (bus->cmd & I2CD_TX_DMA_ENABLE) { - while (bus->dma_len) { + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, TX_BUFF_EN, 0); + } else if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_DMA_EN)) { + /* In new mode, clear how many bytes we TXed */ + if (aspeed_i2c_is_new_mode(bus->controller)) { + ARRAY_FIELD_DP32(bus->regs, I2CM_DMA_LEN_STS, TX_LEN, 0); + } + while (bus->regs[reg_dma_len]) { uint8_t data; aspeed_i2c_dma_read(bus, &data); - trace_aspeed_i2c_bus_send("DMA", bus->dma_len, bus->dma_len, data); + trace_aspeed_i2c_bus_send("DMA", bus->regs[reg_dma_len], + bus->regs[reg_dma_len], data); ret = i2c_send(bus->bus, data); if (ret) { break; } + /* In new mode, keep track of how many bytes we TXed */ + if (aspeed_i2c_is_new_mode(bus->controller)) { + ARRAY_FIELD_DP32(bus->regs, I2CM_DMA_LEN_STS, TX_LEN, + ARRAY_FIELD_EX32(bus->regs, I2CM_DMA_LEN_STS, + TX_LEN) + 1); + } } - bus->cmd &= ~I2CD_TX_DMA_ENABLE; + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, TX_DMA_EN, 0); } else { - trace_aspeed_i2c_bus_send("BYTE", pool_start, 1, bus->buf); - ret = i2c_send(bus->bus, bus->buf); + trace_aspeed_i2c_bus_send("BYTE", pool_start, 1, + bus->regs[reg_byte_buf]); + ret = i2c_send(bus->bus, bus->regs[reg_byte_buf]); } return ret; @@ -304,74 +266,100 @@ static void aspeed_i2c_bus_recv(AspeedI2CBus *bus) AspeedI2CClass *aic = ASPEED_I2C_GET_CLASS(s); uint8_t data; int i; - - if (bus->cmd & I2CD_RX_BUFF_ENABLE) { + uint32_t reg_cmd = aspeed_i2c_bus_cmd_offset(bus); + uint32_t reg_pool_ctrl = aspeed_i2c_bus_pool_ctrl_offset(bus); + uint32_t reg_byte_buf = aspeed_i2c_bus_byte_buf_offset(bus); + uint32_t reg_dma_len = aspeed_i2c_bus_dma_len_offset(bus); + uint32_t reg_dma_addr = aspeed_i2c_bus_dma_addr_offset(bus); + int pool_rx_count = SHARED_ARRAY_FIELD_EX32(bus->regs, reg_pool_ctrl, + RX_COUNT); + + if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, RX_BUFF_EN)) { uint8_t *pool_base = aic->bus_pool_base(bus); - for (i = 0; i < I2CD_POOL_RX_SIZE(bus->pool_ctrl); i++) { + for (i = 0; i < pool_rx_count; i++) { pool_base[i] = i2c_recv(bus->bus); - trace_aspeed_i2c_bus_recv("BUF", i + 1, - I2CD_POOL_RX_SIZE(bus->pool_ctrl), + trace_aspeed_i2c_bus_recv("BUF", i + 1, pool_rx_count, pool_base[i]); } /* Update RX count */ - bus->pool_ctrl &= ~(0xff << 24); - bus->pool_ctrl |= (i & 0xff) << 24; - bus->cmd &= ~I2CD_RX_BUFF_ENABLE; - } else if (bus->cmd & I2CD_RX_DMA_ENABLE) { + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_pool_ctrl, RX_COUNT, i & 0xff); + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, RX_BUFF_EN, 0); + } else if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, RX_DMA_EN)) { uint8_t data; + /* In new mode, clear how many bytes we RXed */ + if (aspeed_i2c_is_new_mode(bus->controller)) { + ARRAY_FIELD_DP32(bus->regs, I2CM_DMA_LEN_STS, RX_LEN, 0); + } - while (bus->dma_len) { + while (bus->regs[reg_dma_len]) { MemTxResult result; data = i2c_recv(bus->bus); - trace_aspeed_i2c_bus_recv("DMA", bus->dma_len, bus->dma_len, data); - result = address_space_write(&s->dram_as, bus->dma_addr, + trace_aspeed_i2c_bus_recv("DMA", bus->regs[reg_dma_len], + bus->regs[reg_dma_len], data); + result = address_space_write(&s->dram_as, bus->regs[reg_dma_addr], MEMTXATTRS_UNSPECIFIED, &data, 1); if (result != MEMTX_OK) { qemu_log_mask(LOG_GUEST_ERROR, "%s: DRAM write failed @%08x\n", - __func__, bus->dma_addr); + __func__, bus->regs[reg_dma_addr]); return; } - bus->dma_addr++; - bus->dma_len--; + bus->regs[reg_dma_addr]++; + bus->regs[reg_dma_len]--; + /* In new mode, keep track of how many bytes we RXed */ + if (aspeed_i2c_is_new_mode(bus->controller)) { + ARRAY_FIELD_DP32(bus->regs, I2CM_DMA_LEN_STS, RX_LEN, + ARRAY_FIELD_EX32(bus->regs, I2CM_DMA_LEN_STS, + RX_LEN) + 1); + } } - bus->cmd &= ~I2CD_RX_DMA_ENABLE; + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, RX_DMA_EN, 0); } else { data = i2c_recv(bus->bus); - trace_aspeed_i2c_bus_recv("BYTE", 1, 1, bus->buf); - bus->buf = (data & I2CD_BYTE_BUF_RX_MASK) << I2CD_BYTE_BUF_RX_SHIFT; + trace_aspeed_i2c_bus_recv("BYTE", 1, 1, bus->regs[reg_byte_buf]); + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_byte_buf, RX_BUF, data); } } static void aspeed_i2c_handle_rx_cmd(AspeedI2CBus *bus) { + uint32_t reg_cmd = aspeed_i2c_bus_cmd_offset(bus); + uint32_t reg_intr_sts = aspeed_i2c_bus_intr_sts_offset(bus); + aspeed_i2c_set_state(bus, I2CD_MRXD); aspeed_i2c_bus_recv(bus); - bus->intr_status |= I2CD_INTR_RX_DONE; - if (bus->cmd & I2CD_M_S_RX_CMD_LAST) { + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_intr_sts, RX_DONE, 1); + if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, M_S_RX_CMD_LAST)) { i2c_nack(bus->bus); } - bus->cmd &= ~(I2CD_M_RX_CMD | I2CD_M_S_RX_CMD_LAST); + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, M_RX_CMD, 0); + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, M_S_RX_CMD_LAST, 0); aspeed_i2c_set_state(bus, I2CD_MACTIVE); } static uint8_t aspeed_i2c_get_addr(AspeedI2CBus *bus) { AspeedI2CClass *aic = ASPEED_I2C_GET_CLASS(bus->controller); + uint32_t reg_byte_buf = aspeed_i2c_bus_byte_buf_offset(bus); + uint32_t reg_cmd = aspeed_i2c_bus_cmd_offset(bus); - if (bus->cmd & I2CD_TX_BUFF_ENABLE) { + if (aspeed_i2c_bus_pkt_mode_en(bus)) { + return (ARRAY_FIELD_EX32(bus->regs, I2CM_CMD, PKT_DEV_ADDR) << 1) | + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, M_RX_CMD); + } + if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_BUFF_EN)) { uint8_t *pool_base = aic->bus_pool_base(bus); return pool_base[0]; - } else if (bus->cmd & I2CD_TX_DMA_ENABLE) { + } else if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_DMA_EN)) { uint8_t data; aspeed_i2c_dma_read(bus, &data); return data; } else { - return bus->buf; + return bus->regs[reg_byte_buf]; } } @@ -379,7 +367,11 @@ static bool aspeed_i2c_check_sram(AspeedI2CBus *bus) { AspeedI2CState *s = bus->controller; AspeedI2CClass *aic = ASPEED_I2C_GET_CLASS(s); - + uint32_t reg_cmd = aspeed_i2c_bus_cmd_offset(bus); + bool dma_en = SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, RX_DMA_EN) || + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_DMA_EN) || + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, RX_BUFF_EN) || + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_BUFF_EN); if (!aic->check_sram) { return true; } @@ -388,9 +380,7 @@ static bool aspeed_i2c_check_sram(AspeedI2CBus *bus) * AST2500: SRAM must be enabled before using the Buffer Pool or * DMA mode. */ - if (!(s->ctrl_global & I2C_CTRL_SRAM_EN) && - (bus->cmd & (I2CD_RX_DMA_ENABLE | I2CD_TX_DMA_ENABLE | - I2CD_RX_BUFF_ENABLE | I2CD_TX_BUFF_ENABLE))) { + if (!FIELD_EX32(s->ctrl_global, I2C_CTRL_GLOBAL, SRAM_EN) && dma_en) { qemu_log_mask(LOG_GUEST_ERROR, "%s: SRAM is not enabled\n", __func__); return false; } @@ -402,27 +392,31 @@ static void aspeed_i2c_bus_cmd_dump(AspeedI2CBus *bus) { g_autofree char *cmd_flags = NULL; uint32_t count; - - if (bus->cmd & (I2CD_RX_BUFF_ENABLE | I2CD_RX_BUFF_ENABLE)) { - count = I2CD_POOL_TX_COUNT(bus->pool_ctrl); - } else if (bus->cmd & (I2CD_RX_DMA_ENABLE | I2CD_RX_DMA_ENABLE)) { - count = bus->dma_len; + uint32_t reg_cmd = aspeed_i2c_bus_cmd_offset(bus); + uint32_t reg_pool_ctrl = aspeed_i2c_bus_pool_ctrl_offset(bus); + uint32_t reg_intr_sts = aspeed_i2c_bus_intr_sts_offset(bus); + uint32_t reg_dma_len = aspeed_i2c_bus_dma_len_offset(bus); + if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, RX_BUFF_EN)) { + count = SHARED_ARRAY_FIELD_EX32(bus->regs, reg_pool_ctrl, TX_COUNT); + } else if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, RX_DMA_EN)) { + count = bus->regs[reg_dma_len]; } else { /* BYTE mode */ count = 1; } cmd_flags = g_strdup_printf("%s%s%s%s%s%s%s%s%s", - bus->cmd & I2CD_M_START_CMD ? "start|" : "", - bus->cmd & I2CD_RX_DMA_ENABLE ? "rxdma|" : "", - bus->cmd & I2CD_TX_DMA_ENABLE ? "txdma|" : "", - bus->cmd & I2CD_RX_BUFF_ENABLE ? "rxbuf|" : "", - bus->cmd & I2CD_TX_BUFF_ENABLE ? "txbuf|" : "", - bus->cmd & I2CD_M_TX_CMD ? "tx|" : "", - bus->cmd & I2CD_M_RX_CMD ? "rx|" : "", - bus->cmd & I2CD_M_S_RX_CMD_LAST ? "last|" : "", - bus->cmd & I2CD_M_STOP_CMD ? "stop" : ""); - - trace_aspeed_i2c_bus_cmd(bus->cmd, cmd_flags, count, bus->intr_status); + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, M_START_CMD) ? "start|" : "", + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, RX_DMA_EN) ? "rxdma|" : "", + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_DMA_EN) ? "txdma|" : "", + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, RX_BUFF_EN) ? "rxbuf|" : "", + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_BUFF_EN) ? "txbuf|" : "", + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, M_TX_CMD) ? "tx|" : "", + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, M_RX_CMD) ? "rx|" : "", + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, M_S_RX_CMD_LAST) ? "last|" : "", + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, M_STOP_CMD) ? "stop|" : ""); + + trace_aspeed_i2c_bus_cmd(bus->regs[reg_cmd], cmd_flags, count, + bus->regs[reg_intr_sts]); } /* @@ -432,9 +426,10 @@ static void aspeed_i2c_bus_cmd_dump(AspeedI2CBus *bus) static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) { uint8_t pool_start = 0; - - bus->cmd &= ~0xFFFF; - bus->cmd |= value & 0xFFFF; + uint32_t reg_intr_sts = aspeed_i2c_bus_intr_sts_offset(bus); + uint32_t reg_cmd = aspeed_i2c_bus_cmd_offset(bus); + uint32_t reg_pool_ctrl = aspeed_i2c_bus_pool_ctrl_offset(bus); + uint32_t reg_dma_len = aspeed_i2c_bus_dma_len_offset(bus); if (!aspeed_i2c_check_sram(bus)) { return; @@ -444,7 +439,7 @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) aspeed_i2c_bus_cmd_dump(bus); } - if (bus->cmd & I2CD_M_START_CMD) { + if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, M_START_CMD)) { uint8_t state = aspeed_i2c_get_state(bus) & I2CD_MACTIVE ? I2CD_MSTARTR : I2CD_MSTART; uint8_t addr; @@ -452,24 +447,30 @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) aspeed_i2c_set_state(bus, state); addr = aspeed_i2c_get_addr(bus); - if (i2c_start_transfer(bus->bus, extract32(addr, 1, 7), extract32(addr, 0, 1))) { - bus->intr_status |= I2CD_INTR_TX_NAK; + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_intr_sts, TX_NAK, 1); + if (aspeed_i2c_bus_pkt_mode_en(bus)) { + ARRAY_FIELD_DP32(bus->regs, I2CM_INTR_STS, PKT_CMD_FAIL, 1); + } } else { - bus->intr_status |= I2CD_INTR_TX_ACK; + /* START doesn't set TX_ACK in packet mode */ + if (!aspeed_i2c_bus_pkt_mode_en(bus)) { + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_intr_sts, TX_ACK, 1); + } } - bus->cmd &= ~I2CD_M_START_CMD; + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, M_START_CMD, 0); /* * The START command is also a TX command, as the slave * address is sent on the bus. Drop the TX flag if nothing * else needs to be sent in this sequence. */ - if (bus->cmd & I2CD_TX_BUFF_ENABLE) { - if (I2CD_POOL_TX_COUNT(bus->pool_ctrl) == 1) { - bus->cmd &= ~I2CD_M_TX_CMD; + if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_BUFF_EN)) { + if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_pool_ctrl, TX_COUNT) + == 1) { + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, M_TX_CMD, 0); } else { /* * Increase the start index in the TX pool buffer to @@ -477,105 +478,267 @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) */ pool_start++; } - } else if (bus->cmd & I2CD_TX_DMA_ENABLE) { - if (bus->dma_len == 0) { - bus->cmd &= ~I2CD_M_TX_CMD; + } else if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_DMA_EN)) { + if (bus->regs[reg_dma_len] == 0) { + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, M_TX_CMD, 0); } } else { - bus->cmd &= ~I2CD_M_TX_CMD; + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, M_TX_CMD, 0); } /* No slave found */ if (!i2c_bus_busy(bus->bus)) { + if (aspeed_i2c_bus_pkt_mode_en(bus)) { + ARRAY_FIELD_DP32(bus->regs, I2CM_INTR_STS, PKT_CMD_FAIL, 1); + ARRAY_FIELD_DP32(bus->regs, I2CM_INTR_STS, PKT_CMD_DONE, 1); + } return; } aspeed_i2c_set_state(bus, I2CD_MACTIVE); } - if (bus->cmd & I2CD_M_TX_CMD) { + if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, M_TX_CMD)) { aspeed_i2c_set_state(bus, I2CD_MTXD); if (aspeed_i2c_bus_send(bus, pool_start)) { - bus->intr_status |= (I2CD_INTR_TX_NAK); + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_intr_sts, TX_NAK, 1); i2c_end_transfer(bus->bus); } else { - bus->intr_status |= I2CD_INTR_TX_ACK; + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_intr_sts, TX_ACK, 1); } - bus->cmd &= ~I2CD_M_TX_CMD; + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, M_TX_CMD, 0); aspeed_i2c_set_state(bus, I2CD_MACTIVE); } - if ((bus->cmd & (I2CD_M_RX_CMD | I2CD_M_S_RX_CMD_LAST)) && - !(bus->intr_status & I2CD_INTR_RX_DONE)) { + if ((SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, M_RX_CMD) || + SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, M_S_RX_CMD_LAST)) && + !SHARED_ARRAY_FIELD_EX32(bus->regs, reg_intr_sts, RX_DONE)) { aspeed_i2c_handle_rx_cmd(bus); } - if (bus->cmd & I2CD_M_STOP_CMD) { + if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, M_STOP_CMD)) { if (!(aspeed_i2c_get_state(bus) & I2CD_MACTIVE)) { qemu_log_mask(LOG_GUEST_ERROR, "%s: abnormal stop\n", __func__); - bus->intr_status |= I2CD_INTR_ABNORMAL; + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_intr_sts, ABNORMAL, 1); + if (aspeed_i2c_bus_pkt_mode_en(bus)) { + ARRAY_FIELD_DP32(bus->regs, I2CM_INTR_STS, PKT_CMD_FAIL, 1); + } } else { aspeed_i2c_set_state(bus, I2CD_MSTOP); i2c_end_transfer(bus->bus); - bus->intr_status |= I2CD_INTR_NORMAL_STOP; + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_intr_sts, NORMAL_STOP, 1); } - bus->cmd &= ~I2CD_M_STOP_CMD; + SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, M_STOP_CMD, 0); aspeed_i2c_set_state(bus, I2CD_IDLE); } + + if (aspeed_i2c_bus_pkt_mode_en(bus)) { + ARRAY_FIELD_DP32(bus->regs, I2CM_INTR_STS, PKT_CMD_DONE, 1); + } } -static void aspeed_i2c_bus_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) +static void aspeed_i2c_bus_new_write(AspeedI2CBus *bus, hwaddr offset, + uint64_t value, unsigned size) { - AspeedI2CBus *bus = opaque; AspeedI2CClass *aic = ASPEED_I2C_GET_CLASS(bus->controller); bool handle_rx; + bool w1t; trace_aspeed_i2c_bus_write(bus->id, offset, size, value); switch (offset) { - case I2CD_FUN_CTRL_REG: - if (value & I2CD_SLAVE_EN) { + case A_I2CC_FUN_CTRL: + if (SHARED_FIELD_EX32(value, SLAVE_EN)) { qemu_log_mask(LOG_UNIMP, "%s: slave mode not implemented\n", __func__); break; } - bus->ctrl = value & 0x0071C3FF; + bus->regs[R_I2CD_FUN_CTRL] = value & 0x007dc3ff; + break; + case A_I2CC_AC_TIMING: + bus->regs[R_I2CC_AC_TIMING] = value & 0x1ffff0ff; break; - case I2CD_AC_TIMING_REG1: - bus->timing[0] = value & 0xFFFFF0F; + case A_I2CC_MS_TXRX_BYTE_BUF: + SHARED_ARRAY_FIELD_DP32(bus->regs, R_I2CC_MS_TXRX_BYTE_BUF, TX_BUF, + value); break; - case I2CD_AC_TIMING_REG2: - bus->timing[1] = value & 0x7; + case A_I2CC_POOL_CTRL: + bus->regs[R_I2CC_POOL_CTRL] &= ~0xffffff; + bus->regs[R_I2CC_POOL_CTRL] |= (value & 0xffffff); break; - case I2CD_INTR_CTRL_REG: - bus->intr_ctrl = value & 0x7FFF; + case A_I2CM_INTR_CTRL: + bus->regs[R_I2CM_INTR_CTRL] = value & 0x0007f07f; break; - case I2CD_INTR_STS_REG: - handle_rx = (bus->intr_status & I2CD_INTR_RX_DONE) && - (value & I2CD_INTR_RX_DONE); - bus->intr_status &= ~(value & 0x7FFF); - if (!bus->intr_status) { + case A_I2CM_INTR_STS: + handle_rx = SHARED_ARRAY_FIELD_EX32(bus->regs, R_I2CM_INTR_STS, RX_DONE) + && SHARED_FIELD_EX32(value, RX_DONE); + + /* In packet mode, clearing PKT_CMD_DONE clears other interrupts. */ + if (aspeed_i2c_bus_pkt_mode_en(bus) && + FIELD_EX32(value, I2CM_INTR_STS, PKT_CMD_DONE)) { + bus->regs[R_I2CM_INTR_STS] &= 0xf0001000; + if (!bus->regs[R_I2CM_INTR_STS]) { + bus->controller->intr_status &= ~(1 << bus->id); + qemu_irq_lower(aic->bus_get_irq(bus)); + } + break; + } + bus->regs[R_I2CM_INTR_STS] &= ~(value & 0xf007f07f); + if (!bus->regs[R_I2CM_INTR_STS]) { bus->controller->intr_status &= ~(1 << bus->id); qemu_irq_lower(aic->bus_get_irq(bus)); } - if (handle_rx && (bus->cmd & (I2CD_M_RX_CMD | I2CD_M_S_RX_CMD_LAST))) { + if (handle_rx && (SHARED_ARRAY_FIELD_EX32(bus->regs, R_I2CM_CMD, + M_RX_CMD) || + SHARED_ARRAY_FIELD_EX32(bus->regs, R_I2CM_CMD, + M_S_RX_CMD_LAST))) { aspeed_i2c_handle_rx_cmd(bus); aspeed_i2c_bus_raise_interrupt(bus); } break; - case I2CD_DEV_ADDR_REG: - qemu_log_mask(LOG_UNIMP, "%s: slave mode not implemented\n", + case A_I2CM_CMD: + if (!aspeed_i2c_bus_is_enabled(bus)) { + break; + } + + if (!aspeed_i2c_bus_is_master(bus)) { + qemu_log_mask(LOG_UNIMP, "%s: slave mode not implemented\n", + __func__); + break; + } + + if (!aic->has_dma && + (SHARED_FIELD_EX32(value, RX_DMA_EN) || + SHARED_FIELD_EX32(value, TX_DMA_EN))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: No DMA support\n", __func__); + break; + } + + if (bus->regs[R_I2CM_INTR_STS] & 0xffff0000) { + qemu_log_mask(LOG_UNIMP, "%s: Packet mode is not implemented\n", + __func__); + break; + } + + value &= 0xff0ffbfb; + if (ARRAY_FIELD_EX32(bus->regs, I2CM_CMD, W1_CTRL)) { + bus->regs[R_I2CM_CMD] |= value; + } else { + bus->regs[R_I2CM_CMD] = value; + } + + aspeed_i2c_bus_handle_cmd(bus, value); + aspeed_i2c_bus_raise_interrupt(bus); + break; + case A_I2CM_DMA_TX_ADDR: + bus->regs[R_I2CM_DMA_TX_ADDR] = FIELD_EX32(value, I2CM_DMA_TX_ADDR, + ADDR); + bus->regs[R_I2CC_DMA_ADDR] = FIELD_EX32(value, I2CM_DMA_TX_ADDR, ADDR); + bus->regs[R_I2CC_DMA_LEN] = ARRAY_FIELD_EX32(bus->regs, I2CM_DMA_LEN, + TX_BUF_LEN) + 1; + break; + case A_I2CM_DMA_RX_ADDR: + bus->regs[R_I2CM_DMA_RX_ADDR] = FIELD_EX32(value, I2CM_DMA_RX_ADDR, + ADDR); + bus->regs[R_I2CC_DMA_ADDR] = FIELD_EX32(value, I2CM_DMA_RX_ADDR, ADDR); + bus->regs[R_I2CC_DMA_LEN] = ARRAY_FIELD_EX32(bus->regs, I2CM_DMA_LEN, + RX_BUF_LEN) + 1; + break; + case A_I2CM_DMA_LEN: + w1t = ARRAY_FIELD_EX32(bus->regs, I2CM_DMA_LEN, RX_BUF_LEN_W1T) || + ARRAY_FIELD_EX32(bus->regs, I2CM_DMA_LEN, TX_BUF_LEN_W1T); + /* If none of the w1t bits are set, just write to the reg as normal. */ + if (!w1t) { + bus->regs[R_I2CM_DMA_LEN] = value; + break; + } + if (ARRAY_FIELD_EX32(bus->regs, I2CM_DMA_LEN, RX_BUF_LEN_W1T)) { + ARRAY_FIELD_DP32(bus->regs, I2CM_DMA_LEN, RX_BUF_LEN, + FIELD_EX32(value, I2CM_DMA_LEN, RX_BUF_LEN)); + } + if (ARRAY_FIELD_EX32(bus->regs, I2CM_DMA_LEN, TX_BUF_LEN_W1T)) { + ARRAY_FIELD_DP32(bus->regs, I2CM_DMA_LEN, TX_BUF_LEN, + FIELD_EX32(value, I2CM_DMA_LEN, TX_BUF_LEN)); + } + break; + case A_I2CM_DMA_LEN_STS: + /* Writes clear to 0 */ + bus->regs[R_I2CM_DMA_LEN_STS] = 0; + break; + case A_I2CC_DMA_ADDR: + case A_I2CC_DMA_LEN: + /* RO */ + break; + case A_I2CS_DMA_LEN_STS: + case A_I2CS_DMA_TX_ADDR: + case A_I2CS_DMA_RX_ADDR: + case A_I2CS_DEV_ADDR: + case A_I2CS_INTR_CTRL: + case A_I2CS_INTR_STS: + case A_I2CS_CMD: + case A_I2CS_DMA_LEN: + qemu_log_mask(LOG_UNIMP, "%s: Slave mode is not implemented\n", __func__); break; - case I2CD_POOL_CTRL_REG: - bus->pool_ctrl &= ~0xffffff; - bus->pool_ctrl |= (value & 0xffffff); + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset 0x%" HWADDR_PRIx "\n", + __func__, offset); + } +} + +static void aspeed_i2c_bus_old_write(AspeedI2CBus *bus, hwaddr offset, + uint64_t value, unsigned size) +{ + AspeedI2CClass *aic = ASPEED_I2C_GET_CLASS(bus->controller); + bool handle_rx; + + trace_aspeed_i2c_bus_write(bus->id, offset, size, value); + + switch (offset) { + case A_I2CD_FUN_CTRL: + if (SHARED_FIELD_EX32(value, SLAVE_EN)) { + qemu_log_mask(LOG_UNIMP, "%s: slave mode not implemented\n", + __func__); + break; + } + bus->regs[R_I2CD_FUN_CTRL] = value & 0x0071C3FF; + break; + case A_I2CD_AC_TIMING1: + bus->regs[R_I2CD_AC_TIMING1] = value & 0xFFFFF0F; + break; + case A_I2CD_AC_TIMING2: + bus->regs[R_I2CD_AC_TIMING2] = value & 0x7; + break; + case A_I2CD_INTR_CTRL: + bus->regs[R_I2CD_INTR_CTRL] = value & 0x7FFF; + break; + case A_I2CD_INTR_STS: + handle_rx = SHARED_ARRAY_FIELD_EX32(bus->regs, R_I2CD_INTR_STS, RX_DONE) + && SHARED_FIELD_EX32(value, RX_DONE); + bus->regs[R_I2CD_INTR_STS] &= ~(value & 0x7FFF); + if (!bus->regs[R_I2CD_INTR_STS]) { + bus->controller->intr_status &= ~(1 << bus->id); + qemu_irq_lower(aic->bus_get_irq(bus)); + } + if (handle_rx && (SHARED_ARRAY_FIELD_EX32(bus->regs, R_I2CD_CMD, + M_RX_CMD) || + SHARED_ARRAY_FIELD_EX32(bus->regs, R_I2CD_CMD, + M_S_RX_CMD_LAST))) { + aspeed_i2c_handle_rx_cmd(bus); + aspeed_i2c_bus_raise_interrupt(bus); + } + break; + case A_I2CD_DEV_ADDR: + bus->regs[R_I2CD_DEV_ADDR] = value; + break; + case A_I2CD_POOL_CTRL: + bus->regs[R_I2CD_POOL_CTRL] &= ~0xffffff; + bus->regs[R_I2CD_POOL_CTRL] |= (value & 0xffffff); break; - case I2CD_BYTE_BUF_REG: - bus->buf = (value & I2CD_BYTE_BUF_TX_MASK) << I2CD_BYTE_BUF_TX_SHIFT; + case A_I2CD_BYTE_BUF: + SHARED_ARRAY_FIELD_DP32(bus->regs, R_I2CD_BYTE_BUF, TX_BUF, value); break; - case I2CD_CMD_REG: + case A_I2CD_CMD: if (!aspeed_i2c_bus_is_enabled(bus)) { break; } @@ -587,31 +750,35 @@ static void aspeed_i2c_bus_write(void *opaque, hwaddr offset, } if (!aic->has_dma && - value & (I2CD_RX_DMA_ENABLE | I2CD_TX_DMA_ENABLE)) { + (SHARED_FIELD_EX32(value, RX_DMA_EN) || + SHARED_FIELD_EX32(value, TX_DMA_EN))) { qemu_log_mask(LOG_GUEST_ERROR, "%s: No DMA support\n", __func__); break; } + bus->regs[R_I2CD_CMD] &= ~0xFFFF; + bus->regs[R_I2CD_CMD] |= value & 0xFFFF; + aspeed_i2c_bus_handle_cmd(bus, value); aspeed_i2c_bus_raise_interrupt(bus); break; - case I2CD_DMA_ADDR: + case A_I2CD_DMA_ADDR: if (!aic->has_dma) { qemu_log_mask(LOG_GUEST_ERROR, "%s: No DMA support\n", __func__); break; } - bus->dma_addr = value & 0x3ffffffc; + bus->regs[R_I2CD_DMA_ADDR] = value & 0x3ffffffc; break; - case I2CD_DMA_LEN: + case A_I2CD_DMA_LEN: if (!aic->has_dma) { qemu_log_mask(LOG_GUEST_ERROR, "%s: No DMA support\n", __func__); break; } - bus->dma_len = value & 0xfff; - if (!bus->dma_len) { + bus->regs[R_I2CD_DMA_LEN] = value & 0xfff; + if (!bus->regs[R_I2CD_DMA_LEN]) { qemu_log_mask(LOG_UNIMP, "%s: invalid DMA length\n", __func__); } break; @@ -622,16 +789,34 @@ static void aspeed_i2c_bus_write(void *opaque, hwaddr offset, } } +static void aspeed_i2c_bus_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + AspeedI2CBus *bus = opaque; + if (aspeed_i2c_is_new_mode(bus->controller)) { + aspeed_i2c_bus_new_write(bus, offset, value, size); + } else { + aspeed_i2c_bus_old_write(bus, offset, value, size); + } +} + static uint64_t aspeed_i2c_ctrl_read(void *opaque, hwaddr offset, unsigned size) { AspeedI2CState *s = opaque; switch (offset) { - case I2C_CTRL_STATUS: + case A_I2C_CTRL_STATUS: return s->intr_status; - case I2C_CTRL_GLOBAL: + case A_I2C_CTRL_GLOBAL: return s->ctrl_global; + case A_I2C_CTRL_NEW_CLK_DIVIDER: + if (aspeed_i2c_is_new_mode(s)) { + return s->new_clk_divider; + } + qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset 0x%" HWADDR_PRIx "\n", + __func__, offset); + break; default: qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, offset); @@ -647,10 +832,18 @@ static void aspeed_i2c_ctrl_write(void *opaque, hwaddr offset, AspeedI2CState *s = opaque; switch (offset) { - case I2C_CTRL_GLOBAL: + case A_I2C_CTRL_GLOBAL: s->ctrl_global = value; break; - case I2C_CTRL_STATUS: + case A_I2C_CTRL_NEW_CLK_DIVIDER: + if (aspeed_i2c_is_new_mode(s)) { + s->new_clk_divider = value; + } else { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset 0x%" HWADDR_PRIx + "\n", __func__, offset); + } + break; + case A_I2C_CTRL_STATUS: default: qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, offset); @@ -707,19 +900,10 @@ static const MemoryRegionOps aspeed_i2c_pool_ops = { static const VMStateDescription aspeed_i2c_bus_vmstate = { .name = TYPE_ASPEED_I2C, - .version_id = 3, - .minimum_version_id = 3, + .version_id = 5, + .minimum_version_id = 5, .fields = (VMStateField[]) { - VMSTATE_UINT8(id, AspeedI2CBus), - VMSTATE_UINT32(ctrl, AspeedI2CBus), - VMSTATE_UINT32_ARRAY(timing, AspeedI2CBus, 2), - VMSTATE_UINT32(intr_ctrl, AspeedI2CBus), - VMSTATE_UINT32(intr_status, AspeedI2CBus), - VMSTATE_UINT32(cmd, AspeedI2CBus), - VMSTATE_UINT32(buf, AspeedI2CBus), - VMSTATE_UINT32(pool_ctrl, AspeedI2CBus), - VMSTATE_UINT32(dma_addr, AspeedI2CBus), - VMSTATE_UINT32(dma_len, AspeedI2CBus), + VMSTATE_UINT32_ARRAY(regs, AspeedI2CBus, ASPEED_I2C_NEW_NUM_REG), VMSTATE_END_OF_LIST() } }; @@ -856,12 +1040,7 @@ static void aspeed_i2c_bus_reset(DeviceState *dev) { AspeedI2CBus *s = ASPEED_I2C_BUS(dev); - s->intr_ctrl = 0; - s->intr_status = 0; - s->cmd = 0; - s->buf = 0; - s->dma_addr = 0; - s->dma_len = 0; + memset(s->regs, 0, sizeof(s->regs)); i2c_end_transfer(s->bus); } @@ -919,9 +1098,10 @@ static qemu_irq aspeed_2400_i2c_bus_get_irq(AspeedI2CBus *bus) static uint8_t *aspeed_2400_i2c_bus_pool_base(AspeedI2CBus *bus) { uint8_t *pool_page = - &bus->controller->pool[I2CD_POOL_PAGE_SEL(bus->ctrl) * 0x100]; + &bus->controller->pool[ARRAY_FIELD_EX32(bus->regs, I2CD_FUN_CTRL, + POOL_PAGE_SEL) * 0x100]; - return &pool_page[I2CD_POOL_OFFSET(bus->pool_ctrl)]; + return &pool_page[ARRAY_FIELD_EX32(bus->regs, I2CD_POOL_CTRL, OFFSET)]; } static void aspeed_2400_i2c_class_init(ObjectClass *klass, void *data) @@ -1013,6 +1193,29 @@ static const TypeInfo aspeed_2600_i2c_info = { .class_init = aspeed_2600_i2c_class_init, }; +static void aspeed_1030_i2c_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + AspeedI2CClass *aic = ASPEED_I2C_CLASS(klass); + + dc->desc = "ASPEED 1030 I2C Controller"; + + aic->num_busses = 14; + aic->reg_size = 0x80; + aic->gap = -1; /* no gap */ + aic->bus_get_irq = aspeed_2600_i2c_bus_get_irq; + aic->pool_size = 0x200; + aic->pool_base = 0xC00; + aic->bus_pool_base = aspeed_2600_i2c_bus_pool_base; + aic->has_dma = true; +} + +static const TypeInfo aspeed_1030_i2c_info = { + .name = TYPE_ASPEED_1030_I2C, + .parent = TYPE_ASPEED_I2C, + .class_init = aspeed_1030_i2c_class_init, +}; + static void aspeed_i2c_register_types(void) { type_register_static(&aspeed_i2c_bus_info); @@ -1020,6 +1223,7 @@ static void aspeed_i2c_register_types(void) type_register_static(&aspeed_2400_i2c_info); type_register_static(&aspeed_2500_i2c_info); type_register_static(&aspeed_2600_i2c_info); + type_register_static(&aspeed_1030_i2c_info); } type_init(aspeed_i2c_register_types) diff --git a/hw/i2c/trace-events b/hw/i2c/trace-events index 7d8907c1ee..209275ed2d 100644 --- a/hw/i2c/trace-events +++ b/hw/i2c/trace-events @@ -9,7 +9,7 @@ i2c_recv(uint8_t address, uint8_t data) "recv(addr:0x%02x) data:0x%02x" # aspeed_i2c.c aspeed_i2c_bus_cmd(uint32_t cmd, const char *cmd_flags, uint32_t count, uint32_t intr_status) "handling cmd=0x%x %s count=%d intr=0x%x" -aspeed_i2c_bus_raise_interrupt(uint32_t intr_status, const char *str1, const char *str2, const char *str3, const char *str4, const char *str5) "handled intr=0x%x %s%s%s%s%s" +aspeed_i2c_bus_raise_interrupt(uint32_t intr_status, const char *s) "handled intr=0x%x %s" aspeed_i2c_bus_read(uint32_t busid, uint64_t offset, unsigned size, uint64_t value) "bus[%d]: To 0x%" PRIx64 " of size %u: 0x%" PRIx64 aspeed_i2c_bus_write(uint32_t busid, uint64_t offset, unsigned size, uint64_t value) "bus[%d]: To 0x%" PRIx64 " of size %u: 0x%" PRIx64 aspeed_i2c_bus_send(const char *mode, int i, int count, uint8_t byte) "%s send %d/%d 0x%02x" diff --git a/hw/intc/pnv_xive2.c b/hw/intc/pnv_xive2.c index a39e070e82..f31c53c28d 100644 --- a/hw/intc/pnv_xive2.c +++ b/hw/intc/pnv_xive2.c @@ -1574,6 +1574,12 @@ static const MemoryRegionOps pnv_xive2_ic_sync_ops = { * When the TM direct pages of the IC controller are accessed, the * target HW thread is deduced from the page offset. */ +static uint32_t pnv_xive2_ic_tm_get_pir(PnvXive2 *xive, hwaddr offset) +{ + /* On P10, the node ID shift in the PIR register is 8 bits */ + return xive->chip->chip_id << 8 | offset >> xive->ic_shift; +} + static XiveTCTX *pnv_xive2_get_indirect_tctx(PnvXive2 *xive, uint32_t pir) { PnvChip *chip = xive->chip; @@ -1596,10 +1602,12 @@ static uint64_t pnv_xive2_ic_tm_indirect_read(void *opaque, hwaddr offset, unsigned size) { PnvXive2 *xive = PNV_XIVE2(opaque); - uint32_t pir = offset >> xive->ic_shift; - XiveTCTX *tctx = pnv_xive2_get_indirect_tctx(xive, pir); + uint32_t pir; + XiveTCTX *tctx; uint64_t val = -1; + pir = pnv_xive2_ic_tm_get_pir(xive, offset); + tctx = pnv_xive2_get_indirect_tctx(xive, pir); if (tctx) { val = xive_tctx_tm_read(NULL, tctx, offset, size); } @@ -1611,9 +1619,11 @@ static void pnv_xive2_ic_tm_indirect_write(void *opaque, hwaddr offset, uint64_t val, unsigned size) { PnvXive2 *xive = PNV_XIVE2(opaque); - uint32_t pir = offset >> xive->ic_shift; - XiveTCTX *tctx = pnv_xive2_get_indirect_tctx(xive, pir); + uint32_t pir; + XiveTCTX *tctx; + pir = pnv_xive2_ic_tm_get_pir(xive, offset); + tctx = pnv_xive2_get_indirect_tctx(xive, pir); if (tctx) { xive_tctx_tm_write(NULL, tctx, offset, val, size); } diff --git a/hw/misc/aspeed_hace.c b/hw/misc/aspeed_hace.c index 4b5997e18f..731234b78c 100644 --- a/hw/misc/aspeed_hace.c +++ b/hw/misc/aspeed_hace.c @@ -340,12 +340,12 @@ static void aspeed_hace_write(void *opaque, hwaddr addr, uint64_t data, if ((data & HASH_HMAC_MASK)) { qemu_log_mask(LOG_UNIMP, - "%s: HMAC engine command mode %"PRIx64" not implemented", + "%s: HMAC engine command mode %"PRIx64" not implemented\n", __func__, (data & HASH_HMAC_MASK) >> 8); } if (data & BIT(1)) { qemu_log_mask(LOG_UNIMP, - "%s: Cascaded mode not implemented", + "%s: Cascaded mode not implemented\n", __func__); } algo = hash_algo_lookup(data); diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c index 1e6e0fcad9..d349b3e426 100644 --- a/hw/nvme/ctrl.c +++ b/hw/nvme/ctrl.c @@ -35,6 +35,11 @@ * mdts=<N[optional]>,vsl=<N[optional]>, \ * zoned.zasl=<N[optional]>, \ * zoned.auto_transition=<on|off[optional]>, \ + * sriov_max_vfs=<N[optional]> \ + * sriov_vq_flexible=<N[optional]> \ + * sriov_vi_flexible=<N[optional]> \ + * sriov_max_vi_per_vf=<N[optional]> \ + * sriov_max_vq_per_vf=<N[optional]> \ * subsys=<subsys_id> * -device nvme-ns,drive=<drive_id>,bus=<bus_name>,nsid=<nsid>,\ * zoned=<true|false[optional]>, \ @@ -106,6 +111,35 @@ * transitioned to zone state closed for resource management purposes. * Defaults to 'on'. * + * - `sriov_max_vfs` + * Indicates the maximum number of PCIe virtual functions supported + * by the controller. The default value is 0. Specifying a non-zero value + * enables reporting of both SR-IOV and ARI capabilities by the NVMe device. + * Virtual function controllers will not report SR-IOV capability. + * + * NOTE: Single Root I/O Virtualization support is experimental. + * All the related parameters may be subject to change. + * + * - `sriov_vq_flexible` + * Indicates the total number of flexible queue resources assignable to all + * the secondary controllers. Implicitly sets the number of primary + * controller's private resources to `(max_ioqpairs - sriov_vq_flexible)`. + * + * - `sriov_vi_flexible` + * Indicates the total number of flexible interrupt resources assignable to + * all the secondary controllers. Implicitly sets the number of primary + * controller's private resources to `(msix_qsize - sriov_vi_flexible)`. + * + * - `sriov_max_vi_per_vf` + * Indicates the maximum number of virtual interrupt resources assignable + * to a secondary controller. The default 0 resolves to + * `(sriov_vi_flexible / sriov_max_vfs)`. + * + * - `sriov_max_vq_per_vf` + * Indicates the maximum number of virtual queue resources assignable to + * a secondary controller. The default 0 resolves to + * `(sriov_vq_flexible / sriov_max_vfs)`. + * * nvme namespace device parameters * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * - `shared` @@ -154,12 +188,14 @@ #include "qemu/error-report.h" #include "qemu/log.h" #include "qemu/units.h" +#include "qemu/range.h" #include "qapi/error.h" #include "qapi/visitor.h" #include "sysemu/sysemu.h" #include "sysemu/block-backend.h" #include "sysemu/hostmem.h" #include "hw/pci/msix.h" +#include "hw/pci/pcie_sriov.h" #include "migration/vmstate.h" #include "nvme.h" @@ -176,6 +212,10 @@ #define NVME_TEMPERATURE_CRITICAL 0x175 #define NVME_NUM_FW_SLOTS 1 #define NVME_DEFAULT_MAX_ZA_SIZE (128 * KiB) +#define NVME_MAX_VFS 127 +#define NVME_VF_RES_GRANULARITY 1 +#define NVME_VF_OFFSET 0x1 +#define NVME_VF_STRIDE 1 #define NVME_GUEST_ERR(trace, fmt, ...) \ do { \ @@ -223,6 +263,7 @@ static const uint32_t nvme_cse_acs[256] = { [NVME_ADM_CMD_GET_FEATURES] = NVME_CMD_EFF_CSUPP, [NVME_ADM_CMD_ASYNC_EV_REQ] = NVME_CMD_EFF_CSUPP, [NVME_ADM_CMD_NS_ATTACHMENT] = NVME_CMD_EFF_CSUPP | NVME_CMD_EFF_NIC, + [NVME_ADM_CMD_VIRT_MNGMT] = NVME_CMD_EFF_CSUPP, [NVME_ADM_CMD_FORMAT_NVM] = NVME_CMD_EFF_CSUPP | NVME_CMD_EFF_LBCC, }; @@ -254,6 +295,7 @@ static const uint32_t nvme_cse_iocs_zoned[256] = { }; static void nvme_process_sq(void *opaque); +static void nvme_ctrl_reset(NvmeCtrl *n, NvmeResetType rst); static uint16_t nvme_sqid(NvmeRequest *req) { @@ -437,12 +479,12 @@ static bool nvme_nsid_valid(NvmeCtrl *n, uint32_t nsid) static int nvme_check_sqid(NvmeCtrl *n, uint16_t sqid) { - return sqid < n->params.max_ioqpairs + 1 && n->sq[sqid] != NULL ? 0 : -1; + return sqid < n->conf_ioqpairs + 1 && n->sq[sqid] != NULL ? 0 : -1; } static int nvme_check_cqid(NvmeCtrl *n, uint16_t cqid) { - return cqid < n->params.max_ioqpairs + 1 && n->cq[cqid] != NULL ? 0 : -1; + return cqid < n->conf_ioqpairs + 1 && n->cq[cqid] != NULL ? 0 : -1; } static void nvme_inc_cq_tail(NvmeCQueue *cq) @@ -808,10 +850,6 @@ static uint16_t nvme_map_sgl_data(NvmeCtrl *n, NvmeSg *sg, uint8_t type = NVME_SGL_TYPE(segment[i].type); switch (type) { - case NVME_SGL_DESCR_TYPE_BIT_BUCKET: - if (cmd->opcode == NVME_CMD_WRITE) { - continue; - } case NVME_SGL_DESCR_TYPE_DATA_BLOCK: break; case NVME_SGL_DESCR_TYPE_SEGMENT: @@ -844,10 +882,6 @@ static uint16_t nvme_map_sgl_data(NvmeCtrl *n, NvmeSg *sg, trans_len = MIN(*len, dlen); - if (type == NVME_SGL_DESCR_TYPE_BIT_BUCKET) { - goto next; - } - addr = le64_to_cpu(segment[i].addr); if (UINT64_MAX - addr < dlen) { @@ -859,7 +893,6 @@ static uint16_t nvme_map_sgl_data(NvmeCtrl *n, NvmeSg *sg, return status; } -next: *len -= trans_len; } @@ -917,8 +950,7 @@ static uint16_t nvme_map_sgl(NvmeCtrl *n, NvmeSg *sg, NvmeSglDescriptor sgl, seg_len = le32_to_cpu(sgld->len); /* check the length of the (Last) Segment descriptor */ - if ((!seg_len || seg_len & 0xf) && - (NVME_SGL_TYPE(sgld->type) != NVME_SGL_DESCR_TYPE_BIT_BUCKET)) { + if (!seg_len || seg_len & 0xf) { return NVME_INVALID_SGL_SEG_DESCR | NVME_DNR; } @@ -956,26 +988,20 @@ static uint16_t nvme_map_sgl(NvmeCtrl *n, NvmeSg *sg, NvmeSglDescriptor sgl, last_sgld = &segment[nsgld - 1]; /* - * If the segment ends with a Data Block or Bit Bucket Descriptor Type, - * then we are done. + * If the segment ends with a Data Block, then we are done. */ - switch (NVME_SGL_TYPE(last_sgld->type)) { - case NVME_SGL_DESCR_TYPE_DATA_BLOCK: - case NVME_SGL_DESCR_TYPE_BIT_BUCKET: + if (NVME_SGL_TYPE(last_sgld->type) == NVME_SGL_DESCR_TYPE_DATA_BLOCK) { status = nvme_map_sgl_data(n, sg, segment, nsgld, &len, cmd); if (status) { goto unmap; } goto out; - - default: - break; } /* - * If the last descriptor was not a Data Block or Bit Bucket, then the - * current segment must not be a Last Segment. + * If the last descriptor was not a Data Block, then the current + * segment must not be a Last Segment. */ if (NVME_SGL_TYPE(sgld->type) == NVME_SGL_DESCR_TYPE_LAST_SEGMENT) { status = NVME_INVALID_SGL_SEG_DESCR | NVME_DNR; @@ -4284,8 +4310,7 @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeRequest *req) trace_pci_nvme_err_invalid_create_sq_cqid(cqid); return NVME_INVALID_CQID | NVME_DNR; } - if (unlikely(!sqid || sqid > n->params.max_ioqpairs || - n->sq[sqid] != NULL)) { + if (unlikely(!sqid || sqid > n->conf_ioqpairs || n->sq[sqid] != NULL)) { trace_pci_nvme_err_invalid_create_sq_sqid(sqid); return NVME_INVALID_QID | NVME_DNR; } @@ -4637,8 +4662,7 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeRequest *req) trace_pci_nvme_create_cq(prp1, cqid, vector, qsize, qflags, NVME_CQ_FLAGS_IEN(qflags) != 0); - if (unlikely(!cqid || cqid > n->params.max_ioqpairs || - n->cq[cqid] != NULL)) { + if (unlikely(!cqid || cqid > n->conf_ioqpairs || n->cq[cqid] != NULL)) { trace_pci_nvme_err_invalid_create_cq_cqid(cqid); return NVME_INVALID_QID | NVME_DNR; } @@ -4654,7 +4678,7 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeRequest *req) trace_pci_nvme_err_invalid_create_cq_vector(vector); return NVME_INVALID_IRQ_VECTOR | NVME_DNR; } - if (unlikely(vector >= n->params.msix_qsize)) { + if (unlikely(vector >= n->conf_msix_qsize)) { trace_pci_nvme_err_invalid_create_cq_vector(vector); return NVME_INVALID_IRQ_VECTOR | NVME_DNR; } @@ -4793,6 +4817,37 @@ static uint16_t nvme_identify_ctrl_list(NvmeCtrl *n, NvmeRequest *req, return nvme_c2h(n, (uint8_t *)list, sizeof(list), req); } +static uint16_t nvme_identify_pri_ctrl_cap(NvmeCtrl *n, NvmeRequest *req) +{ + trace_pci_nvme_identify_pri_ctrl_cap(le16_to_cpu(n->pri_ctrl_cap.cntlid)); + + return nvme_c2h(n, (uint8_t *)&n->pri_ctrl_cap, + sizeof(NvmePriCtrlCap), req); +} + +static uint16_t nvme_identify_sec_ctrl_list(NvmeCtrl *n, NvmeRequest *req) +{ + NvmeIdentify *c = (NvmeIdentify *)&req->cmd; + uint16_t pri_ctrl_id = le16_to_cpu(n->pri_ctrl_cap.cntlid); + uint16_t min_id = le16_to_cpu(c->ctrlid); + uint8_t num_sec_ctrl = n->sec_ctrl_list.numcntl; + NvmeSecCtrlList list = {0}; + uint8_t i; + + for (i = 0; i < num_sec_ctrl; i++) { + if (n->sec_ctrl_list.sec[i].scid >= min_id) { + list.numcntl = num_sec_ctrl - i; + memcpy(&list.sec, n->sec_ctrl_list.sec + i, + list.numcntl * sizeof(NvmeSecCtrlEntry)); + break; + } + } + + trace_pci_nvme_identify_sec_ctrl_list(pri_ctrl_id, list.numcntl); + + return nvme_c2h(n, (uint8_t *)&list, sizeof(list), req); +} + static uint16_t nvme_identify_ns_csi(NvmeCtrl *n, NvmeRequest *req, bool active) { @@ -5009,6 +5064,10 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeRequest *req) return nvme_identify_ctrl_list(n, req, true); case NVME_ID_CNS_CTRL_LIST: return nvme_identify_ctrl_list(n, req, false); + case NVME_ID_CNS_PRIMARY_CTRL_CAP: + return nvme_identify_pri_ctrl_cap(n, req); + case NVME_ID_CNS_SECONDARY_CTRL_LIST: + return nvme_identify_sec_ctrl_list(n, req); case NVME_ID_CNS_CS_NS: return nvme_identify_ns_csi(n, req, true); case NVME_ID_CNS_CS_NS_PRESENT: @@ -5217,13 +5276,12 @@ defaults: break; case NVME_NUMBER_OF_QUEUES: - result = (n->params.max_ioqpairs - 1) | - ((n->params.max_ioqpairs - 1) << 16); + result = (n->conf_ioqpairs - 1) | ((n->conf_ioqpairs - 1) << 16); trace_pci_nvme_getfeat_numq(result); break; case NVME_INTERRUPT_VECTOR_CONF: iv = dw11 & 0xffff; - if (iv >= n->params.max_ioqpairs + 1) { + if (iv >= n->conf_ioqpairs + 1) { return NVME_INVALID_FIELD | NVME_DNR; } @@ -5379,10 +5437,10 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeRequest *req) trace_pci_nvme_setfeat_numq((dw11 & 0xffff) + 1, ((dw11 >> 16) & 0xffff) + 1, - n->params.max_ioqpairs, - n->params.max_ioqpairs); - req->cqe.result = cpu_to_le32((n->params.max_ioqpairs - 1) | - ((n->params.max_ioqpairs - 1) << 16)); + n->conf_ioqpairs, + n->conf_ioqpairs); + req->cqe.result = cpu_to_le32((n->conf_ioqpairs - 1) | + ((n->conf_ioqpairs - 1) << 16)); break; case NVME_ASYNCHRONOUS_EVENT_CONF: n->features.async_config = dw11; @@ -5769,6 +5827,167 @@ out: return status; } +static void nvme_get_virt_res_num(NvmeCtrl *n, uint8_t rt, int *num_total, + int *num_prim, int *num_sec) +{ + *num_total = le32_to_cpu(rt ? + n->pri_ctrl_cap.vifrt : n->pri_ctrl_cap.vqfrt); + *num_prim = le16_to_cpu(rt ? + n->pri_ctrl_cap.virfap : n->pri_ctrl_cap.vqrfap); + *num_sec = le16_to_cpu(rt ? n->pri_ctrl_cap.virfa : n->pri_ctrl_cap.vqrfa); +} + +static uint16_t nvme_assign_virt_res_to_prim(NvmeCtrl *n, NvmeRequest *req, + uint16_t cntlid, uint8_t rt, + int nr) +{ + int num_total, num_prim, num_sec; + + if (cntlid != n->cntlid) { + return NVME_INVALID_CTRL_ID | NVME_DNR; + } + + nvme_get_virt_res_num(n, rt, &num_total, &num_prim, &num_sec); + + if (nr > num_total) { + return NVME_INVALID_NUM_RESOURCES | NVME_DNR; + } + + if (nr > num_total - num_sec) { + return NVME_INVALID_RESOURCE_ID | NVME_DNR; + } + + if (rt) { + n->next_pri_ctrl_cap.virfap = cpu_to_le16(nr); + } else { + n->next_pri_ctrl_cap.vqrfap = cpu_to_le16(nr); + } + + req->cqe.result = cpu_to_le32(nr); + return req->status; +} + +static void nvme_update_virt_res(NvmeCtrl *n, NvmeSecCtrlEntry *sctrl, + uint8_t rt, int nr) +{ + int prev_nr, prev_total; + + if (rt) { + prev_nr = le16_to_cpu(sctrl->nvi); + prev_total = le32_to_cpu(n->pri_ctrl_cap.virfa); + sctrl->nvi = cpu_to_le16(nr); + n->pri_ctrl_cap.virfa = cpu_to_le32(prev_total + nr - prev_nr); + } else { + prev_nr = le16_to_cpu(sctrl->nvq); + prev_total = le32_to_cpu(n->pri_ctrl_cap.vqrfa); + sctrl->nvq = cpu_to_le16(nr); + n->pri_ctrl_cap.vqrfa = cpu_to_le32(prev_total + nr - prev_nr); + } +} + +static uint16_t nvme_assign_virt_res_to_sec(NvmeCtrl *n, NvmeRequest *req, + uint16_t cntlid, uint8_t rt, int nr) +{ + int num_total, num_prim, num_sec, num_free, diff, limit; + NvmeSecCtrlEntry *sctrl; + + sctrl = nvme_sctrl_for_cntlid(n, cntlid); + if (!sctrl) { + return NVME_INVALID_CTRL_ID | NVME_DNR; + } + + if (sctrl->scs) { + return NVME_INVALID_SEC_CTRL_STATE | NVME_DNR; + } + + limit = le16_to_cpu(rt ? n->pri_ctrl_cap.vifrsm : n->pri_ctrl_cap.vqfrsm); + if (nr > limit) { + return NVME_INVALID_NUM_RESOURCES | NVME_DNR; + } + + nvme_get_virt_res_num(n, rt, &num_total, &num_prim, &num_sec); + num_free = num_total - num_prim - num_sec; + diff = nr - le16_to_cpu(rt ? sctrl->nvi : sctrl->nvq); + + if (diff > num_free) { + return NVME_INVALID_RESOURCE_ID | NVME_DNR; + } + + nvme_update_virt_res(n, sctrl, rt, nr); + req->cqe.result = cpu_to_le32(nr); + + return req->status; +} + +static uint16_t nvme_virt_set_state(NvmeCtrl *n, uint16_t cntlid, bool online) +{ + NvmeCtrl *sn = NULL; + NvmeSecCtrlEntry *sctrl; + int vf_index; + + sctrl = nvme_sctrl_for_cntlid(n, cntlid); + if (!sctrl) { + return NVME_INVALID_CTRL_ID | NVME_DNR; + } + + if (!pci_is_vf(&n->parent_obj)) { + vf_index = le16_to_cpu(sctrl->vfn) - 1; + sn = NVME(pcie_sriov_get_vf_at_index(&n->parent_obj, vf_index)); + } + + if (online) { + if (!sctrl->nvi || (le16_to_cpu(sctrl->nvq) < 2) || !sn) { + return NVME_INVALID_SEC_CTRL_STATE | NVME_DNR; + } + + if (!sctrl->scs) { + sctrl->scs = 0x1; + nvme_ctrl_reset(sn, NVME_RESET_FUNCTION); + } + } else { + nvme_update_virt_res(n, sctrl, NVME_VIRT_RES_INTERRUPT, 0); + nvme_update_virt_res(n, sctrl, NVME_VIRT_RES_QUEUE, 0); + + if (sctrl->scs) { + sctrl->scs = 0x0; + if (sn) { + nvme_ctrl_reset(sn, NVME_RESET_FUNCTION); + } + } + } + + return NVME_SUCCESS; +} + +static uint16_t nvme_virt_mngmt(NvmeCtrl *n, NvmeRequest *req) +{ + uint32_t dw10 = le32_to_cpu(req->cmd.cdw10); + uint32_t dw11 = le32_to_cpu(req->cmd.cdw11); + uint8_t act = dw10 & 0xf; + uint8_t rt = (dw10 >> 8) & 0x7; + uint16_t cntlid = (dw10 >> 16) & 0xffff; + int nr = dw11 & 0xffff; + + trace_pci_nvme_virt_mngmt(nvme_cid(req), act, cntlid, rt ? "VI" : "VQ", nr); + + if (rt != NVME_VIRT_RES_QUEUE && rt != NVME_VIRT_RES_INTERRUPT) { + return NVME_INVALID_RESOURCE_ID | NVME_DNR; + } + + switch (act) { + case NVME_VIRT_MNGMT_ACTION_SEC_ASSIGN: + return nvme_assign_virt_res_to_sec(n, req, cntlid, rt, nr); + case NVME_VIRT_MNGMT_ACTION_PRM_ALLOC: + return nvme_assign_virt_res_to_prim(n, req, cntlid, rt, nr); + case NVME_VIRT_MNGMT_ACTION_SEC_ONLINE: + return nvme_virt_set_state(n, cntlid, true); + case NVME_VIRT_MNGMT_ACTION_SEC_OFFLINE: + return nvme_virt_set_state(n, cntlid, false); + default: + return NVME_INVALID_FIELD | NVME_DNR; + } +} + static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeRequest *req) { trace_pci_nvme_admin_cmd(nvme_cid(req), nvme_sqid(req), req->cmd.opcode, @@ -5811,6 +6030,8 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeRequest *req) return nvme_aer(n, req); case NVME_ADM_CMD_NS_ATTACHMENT: return nvme_ns_attachment(n, req); + case NVME_ADM_CMD_VIRT_MNGMT: + return nvme_virt_mngmt(n, req); case NVME_ADM_CMD_FORMAT_NVM: return nvme_format(n, req); default: @@ -5857,8 +6078,48 @@ static void nvme_process_sq(void *opaque) } } -static void nvme_ctrl_reset(NvmeCtrl *n) +static void nvme_update_msixcap_ts(PCIDevice *pci_dev, uint32_t table_size) { + uint8_t *config; + + if (!msix_present(pci_dev)) { + return; + } + + assert(table_size > 0 && table_size <= pci_dev->msix_entries_nr); + + config = pci_dev->config + pci_dev->msix_cap; + pci_set_word_by_mask(config + PCI_MSIX_FLAGS, PCI_MSIX_FLAGS_QSIZE, + table_size - 1); +} + +static void nvme_activate_virt_res(NvmeCtrl *n) +{ + PCIDevice *pci_dev = &n->parent_obj; + NvmePriCtrlCap *cap = &n->pri_ctrl_cap; + NvmeSecCtrlEntry *sctrl; + + /* -1 to account for the admin queue */ + if (pci_is_vf(pci_dev)) { + sctrl = nvme_sctrl(n); + cap->vqprt = sctrl->nvq; + cap->viprt = sctrl->nvi; + n->conf_ioqpairs = sctrl->nvq ? le16_to_cpu(sctrl->nvq) - 1 : 0; + n->conf_msix_qsize = sctrl->nvi ? le16_to_cpu(sctrl->nvi) : 1; + } else { + cap->vqrfap = n->next_pri_ctrl_cap.vqrfap; + cap->virfap = n->next_pri_ctrl_cap.virfap; + n->conf_ioqpairs = le16_to_cpu(cap->vqprt) + + le16_to_cpu(cap->vqrfap) - 1; + n->conf_msix_qsize = le16_to_cpu(cap->viprt) + + le16_to_cpu(cap->virfap); + } +} + +static void nvme_ctrl_reset(NvmeCtrl *n, NvmeResetType rst) +{ + PCIDevice *pci_dev = &n->parent_obj; + NvmeSecCtrlEntry *sctrl; NvmeNamespace *ns; int i; @@ -5888,9 +6149,41 @@ static void nvme_ctrl_reset(NvmeCtrl *n) g_free(event); } + if (n->params.sriov_max_vfs) { + if (!pci_is_vf(pci_dev)) { + for (i = 0; i < n->sec_ctrl_list.numcntl; i++) { + sctrl = &n->sec_ctrl_list.sec[i]; + nvme_virt_set_state(n, le16_to_cpu(sctrl->scid), false); + } + + if (rst != NVME_RESET_CONTROLLER) { + pcie_sriov_pf_disable_vfs(pci_dev); + } + } + + if (rst != NVME_RESET_CONTROLLER) { + nvme_activate_virt_res(n); + } + } + n->aer_queued = 0; + n->aer_mask = 0; n->outstanding_aers = 0; n->qs_created = false; + + nvme_update_msixcap_ts(pci_dev, n->conf_msix_qsize); + + if (pci_is_vf(pci_dev)) { + sctrl = nvme_sctrl(n); + + stl_le_p(&n->bar.csts, sctrl->scs ? 0 : NVME_CSTS_FAILED); + } else { + stl_le_p(&n->bar.csts, 0); + } + + stl_le_p(&n->bar.intms, 0); + stl_le_p(&n->bar.intmc, 0); + stl_le_p(&n->bar.cc, 0); } static void nvme_ctrl_shutdown(NvmeCtrl *n) @@ -5936,7 +6229,15 @@ static int nvme_start_ctrl(NvmeCtrl *n) uint64_t acq = ldq_le_p(&n->bar.acq); uint32_t page_bits = NVME_CC_MPS(cc) + 12; uint32_t page_size = 1 << page_bits; + NvmeSecCtrlEntry *sctrl = nvme_sctrl(n); + if (pci_is_vf(&n->parent_obj) && !sctrl->scs) { + trace_pci_nvme_err_startfail_virt_state(le16_to_cpu(sctrl->nvi), + le16_to_cpu(sctrl->nvq), + sctrl->scs ? "ONLINE" : + "OFFLINE"); + return -1; + } if (unlikely(n->cq[0])) { trace_pci_nvme_err_startfail_cq(); return -1; @@ -6017,8 +6318,6 @@ static int nvme_start_ctrl(NvmeCtrl *n) nvme_set_timestamp(n, 0ULL); - QTAILQ_INIT(&n->aer_queue); - nvme_select_iocs(n); return 0; @@ -6096,20 +6395,21 @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, nvme_irq_check(n); break; case NVME_REG_CC: + stl_le_p(&n->bar.cc, data); + trace_pci_nvme_mmio_cfg(data & 0xffffffff); - /* Windows first sends data, then sends enable bit */ - if (!NVME_CC_EN(data) && !NVME_CC_EN(cc) && - !NVME_CC_SHN(data) && !NVME_CC_SHN(cc)) - { - cc = data; + if (NVME_CC_SHN(data) && !(NVME_CC_SHN(cc))) { + trace_pci_nvme_mmio_shutdown_set(); + nvme_ctrl_shutdown(n); + csts &= ~(CSTS_SHST_MASK << CSTS_SHST_SHIFT); + csts |= NVME_CSTS_SHST_COMPLETE; + } else if (!NVME_CC_SHN(data) && NVME_CC_SHN(cc)) { + trace_pci_nvme_mmio_shutdown_cleared(); + csts &= ~(CSTS_SHST_MASK << CSTS_SHST_SHIFT); } if (NVME_CC_EN(data) && !NVME_CC_EN(cc)) { - cc = data; - - /* flush CC since nvme_start_ctrl() needs the value */ - stl_le_p(&n->bar.cc, cc); if (unlikely(nvme_start_ctrl(n))) { trace_pci_nvme_err_startfail(); csts = NVME_CSTS_FAILED; @@ -6119,23 +6419,11 @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, } } else if (!NVME_CC_EN(data) && NVME_CC_EN(cc)) { trace_pci_nvme_mmio_stopped(); - nvme_ctrl_reset(n); - cc = 0; - csts &= ~NVME_CSTS_READY; - } + nvme_ctrl_reset(n, NVME_RESET_CONTROLLER); - if (NVME_CC_SHN(data) && !(NVME_CC_SHN(cc))) { - trace_pci_nvme_mmio_shutdown_set(); - nvme_ctrl_shutdown(n); - cc = data; - csts |= NVME_CSTS_SHST_COMPLETE; - } else if (!NVME_CC_SHN(data) && NVME_CC_SHN(cc)) { - trace_pci_nvme_mmio_shutdown_cleared(); - csts &= ~NVME_CSTS_SHST_COMPLETE; - cc = data; + break; } - stl_le_p(&n->bar.cc, cc); stl_le_p(&n->bar.csts, csts); break; @@ -6319,6 +6607,12 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) return 0; } + if (pci_is_vf(&n->parent_obj) && !nvme_sctrl(n)->scs && + addr != NVME_REG_CSTS) { + trace_pci_nvme_err_ignored_mmio_vf_offline(addr, size); + return 0; + } + /* * When PMRWBM bit 1 is set then read from * from PMRSTS should ensure prior writes @@ -6468,6 +6762,12 @@ static void nvme_mmio_write(void *opaque, hwaddr addr, uint64_t data, trace_pci_nvme_mmio_write(addr, data, size); + if (pci_is_vf(&n->parent_obj) && !nvme_sctrl(n)->scs && + addr != NVME_REG_CSTS) { + trace_pci_nvme_err_ignored_mmio_vf_offline(addr, size); + return; + } + if (addr < sizeof(n->bar)) { nvme_write_bar(n, addr, data, size); } else { @@ -6569,19 +6869,140 @@ static void nvme_check_constraints(NvmeCtrl *n, Error **errp) error_setg(errp, "vsl must be non-zero"); return; } + + if (params->sriov_max_vfs) { + if (!n->subsys) { + error_setg(errp, "subsystem is required for the use of SR-IOV"); + return; + } + + if (params->sriov_max_vfs > NVME_MAX_VFS) { + error_setg(errp, "sriov_max_vfs must be between 0 and %d", + NVME_MAX_VFS); + return; + } + + if (params->cmb_size_mb) { + error_setg(errp, "CMB is not supported with SR-IOV"); + return; + } + + if (n->pmr.dev) { + error_setg(errp, "PMR is not supported with SR-IOV"); + return; + } + + if (!params->sriov_vq_flexible || !params->sriov_vi_flexible) { + error_setg(errp, "both sriov_vq_flexible and sriov_vi_flexible" + " must be set for the use of SR-IOV"); + return; + } + + if (params->sriov_vq_flexible < params->sriov_max_vfs * 2) { + error_setg(errp, "sriov_vq_flexible must be greater than or equal" + " to %d (sriov_max_vfs * 2)", params->sriov_max_vfs * 2); + return; + } + + if (params->max_ioqpairs < params->sriov_vq_flexible + 2) { + error_setg(errp, "(max_ioqpairs - sriov_vq_flexible) must be" + " greater than or equal to 2"); + return; + } + + if (params->sriov_vi_flexible < params->sriov_max_vfs) { + error_setg(errp, "sriov_vi_flexible must be greater than or equal" + " to %d (sriov_max_vfs)", params->sriov_max_vfs); + return; + } + + if (params->msix_qsize < params->sriov_vi_flexible + 1) { + error_setg(errp, "(msix_qsize - sriov_vi_flexible) must be" + " greater than or equal to 1"); + return; + } + + if (params->sriov_max_vi_per_vf && + (params->sriov_max_vi_per_vf - 1) % NVME_VF_RES_GRANULARITY) { + error_setg(errp, "sriov_max_vi_per_vf must meet:" + " (sriov_max_vi_per_vf - 1) %% %d == 0 and" + " sriov_max_vi_per_vf >= 1", NVME_VF_RES_GRANULARITY); + return; + } + + if (params->sriov_max_vq_per_vf && + (params->sriov_max_vq_per_vf < 2 || + (params->sriov_max_vq_per_vf - 1) % NVME_VF_RES_GRANULARITY)) { + error_setg(errp, "sriov_max_vq_per_vf must meet:" + " (sriov_max_vq_per_vf - 1) %% %d == 0 and" + " sriov_max_vq_per_vf >= 2", NVME_VF_RES_GRANULARITY); + return; + } + } } static void nvme_init_state(NvmeCtrl *n) { - /* add one to max_ioqpairs to account for the admin queue pair */ - n->reg_size = pow2ceil(sizeof(NvmeBar) + - 2 * (n->params.max_ioqpairs + 1) * NVME_DB_SIZE); + NvmePriCtrlCap *cap = &n->pri_ctrl_cap; + NvmeSecCtrlList *list = &n->sec_ctrl_list; + NvmeSecCtrlEntry *sctrl; + uint8_t max_vfs; + int i; + + if (pci_is_vf(&n->parent_obj)) { + sctrl = nvme_sctrl(n); + max_vfs = 0; + n->conf_ioqpairs = sctrl->nvq ? le16_to_cpu(sctrl->nvq) - 1 : 0; + n->conf_msix_qsize = sctrl->nvi ? le16_to_cpu(sctrl->nvi) : 1; + } else { + max_vfs = n->params.sriov_max_vfs; + n->conf_ioqpairs = n->params.max_ioqpairs; + n->conf_msix_qsize = n->params.msix_qsize; + } + n->sq = g_new0(NvmeSQueue *, n->params.max_ioqpairs + 1); n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1); n->temperature = NVME_TEMPERATURE; n->features.temp_thresh_hi = NVME_TEMPERATURE_WARNING; n->starttime_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL); n->aer_reqs = g_new0(NvmeRequest *, n->params.aerl + 1); + QTAILQ_INIT(&n->aer_queue); + + list->numcntl = cpu_to_le16(max_vfs); + for (i = 0; i < max_vfs; i++) { + sctrl = &list->sec[i]; + sctrl->pcid = cpu_to_le16(n->cntlid); + sctrl->vfn = cpu_to_le16(i + 1); + } + + cap->cntlid = cpu_to_le16(n->cntlid); + cap->crt = NVME_CRT_VQ | NVME_CRT_VI; + + if (pci_is_vf(&n->parent_obj)) { + cap->vqprt = cpu_to_le16(1 + n->conf_ioqpairs); + } else { + cap->vqprt = cpu_to_le16(1 + n->params.max_ioqpairs - + n->params.sriov_vq_flexible); + cap->vqfrt = cpu_to_le32(n->params.sriov_vq_flexible); + cap->vqrfap = cap->vqfrt; + cap->vqgran = cpu_to_le16(NVME_VF_RES_GRANULARITY); + cap->vqfrsm = n->params.sriov_max_vq_per_vf ? + cpu_to_le16(n->params.sriov_max_vq_per_vf) : + cap->vqfrt / MAX(max_vfs, 1); + } + + if (pci_is_vf(&n->parent_obj)) { + cap->viprt = cpu_to_le16(n->conf_msix_qsize); + } else { + cap->viprt = cpu_to_le16(n->params.msix_qsize - + n->params.sriov_vi_flexible); + cap->vifrt = cpu_to_le32(n->params.sriov_vi_flexible); + cap->virfap = cap->vifrt; + cap->vigran = cpu_to_le16(NVME_VF_RES_GRANULARITY); + cap->vifrsm = n->params.sriov_max_vi_per_vf ? + cpu_to_le16(n->params.sriov_max_vi_per_vf) : + cap->vifrt / MAX(max_vfs, 1); + } } static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev) @@ -6626,10 +7047,77 @@ static void nvme_init_pmr(NvmeCtrl *n, PCIDevice *pci_dev) memory_region_set_enabled(&n->pmr.dev->mr, false); } +static uint64_t nvme_bar_size(unsigned total_queues, unsigned total_irqs, + unsigned *msix_table_offset, + unsigned *msix_pba_offset) +{ + uint64_t bar_size, msix_table_size, msix_pba_size; + + bar_size = sizeof(NvmeBar) + 2 * total_queues * NVME_DB_SIZE; + bar_size = QEMU_ALIGN_UP(bar_size, 4 * KiB); + + if (msix_table_offset) { + *msix_table_offset = bar_size; + } + + msix_table_size = PCI_MSIX_ENTRY_SIZE * total_irqs; + bar_size += msix_table_size; + bar_size = QEMU_ALIGN_UP(bar_size, 4 * KiB); + + if (msix_pba_offset) { + *msix_pba_offset = bar_size; + } + + msix_pba_size = QEMU_ALIGN_UP(total_irqs, 64) / 8; + bar_size += msix_pba_size; + + bar_size = pow2ceil(bar_size); + return bar_size; +} + +static void nvme_init_sriov(NvmeCtrl *n, PCIDevice *pci_dev, uint16_t offset) +{ + uint16_t vf_dev_id = n->params.use_intel_id ? + PCI_DEVICE_ID_INTEL_NVME : PCI_DEVICE_ID_REDHAT_NVME; + NvmePriCtrlCap *cap = &n->pri_ctrl_cap; + uint64_t bar_size = nvme_bar_size(le16_to_cpu(cap->vqfrsm), + le16_to_cpu(cap->vifrsm), + NULL, NULL); + + pcie_sriov_pf_init(pci_dev, offset, "nvme", vf_dev_id, + n->params.sriov_max_vfs, n->params.sriov_max_vfs, + NVME_VF_OFFSET, NVME_VF_STRIDE); + + pcie_sriov_pf_init_vf_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY | + PCI_BASE_ADDRESS_MEM_TYPE_64, bar_size); +} + +static int nvme_add_pm_capability(PCIDevice *pci_dev, uint8_t offset) +{ + Error *err = NULL; + int ret; + + ret = pci_add_capability(pci_dev, PCI_CAP_ID_PM, offset, + PCI_PM_SIZEOF, &err); + if (err) { + error_report_err(err); + return ret; + } + + pci_set_word(pci_dev->config + offset + PCI_PM_PMC, + PCI_PM_CAP_VER_1_2); + pci_set_word(pci_dev->config + offset + PCI_PM_CTRL, + PCI_PM_CTRL_NO_SOFT_RESET); + pci_set_word(pci_dev->wmask + offset + PCI_PM_CTRL, + PCI_PM_CTRL_STATE_MASK); + + return 0; +} + static int nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp) { uint8_t *pci_conf = pci_dev->config; - uint64_t bar_size, msix_table_size, msix_pba_size; + uint64_t bar_size; unsigned msix_table_offset, msix_pba_offset; int ret; @@ -6640,34 +7128,35 @@ static int nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp) if (n->params.use_intel_id) { pci_config_set_vendor_id(pci_conf, PCI_VENDOR_ID_INTEL); - pci_config_set_device_id(pci_conf, 0x5845); + pci_config_set_device_id(pci_conf, PCI_DEVICE_ID_INTEL_NVME); } else { pci_config_set_vendor_id(pci_conf, PCI_VENDOR_ID_REDHAT); pci_config_set_device_id(pci_conf, PCI_DEVICE_ID_REDHAT_NVME); } pci_config_set_class(pci_conf, PCI_CLASS_STORAGE_EXPRESS); + nvme_add_pm_capability(pci_dev, 0x60); pcie_endpoint_cap_init(pci_dev, 0x80); + pcie_cap_flr_init(pci_dev); + if (n->params.sriov_max_vfs) { + pcie_ari_init(pci_dev, 0x100, 1); + } - bar_size = QEMU_ALIGN_UP(n->reg_size, 4 * KiB); - msix_table_offset = bar_size; - msix_table_size = PCI_MSIX_ENTRY_SIZE * n->params.msix_qsize; - - bar_size += msix_table_size; - bar_size = QEMU_ALIGN_UP(bar_size, 4 * KiB); - msix_pba_offset = bar_size; - msix_pba_size = QEMU_ALIGN_UP(n->params.msix_qsize, 64) / 8; - - bar_size += msix_pba_size; - bar_size = pow2ceil(bar_size); + /* add one to max_ioqpairs to account for the admin queue pair */ + bar_size = nvme_bar_size(n->params.max_ioqpairs + 1, n->params.msix_qsize, + &msix_table_offset, &msix_pba_offset); memory_region_init(&n->bar0, OBJECT(n), "nvme-bar0", bar_size); memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n, "nvme", - n->reg_size); + msix_table_offset); memory_region_add_subregion(&n->bar0, 0, &n->iomem); - pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY | - PCI_BASE_ADDRESS_MEM_TYPE_64, &n->bar0); + if (pci_is_vf(pci_dev)) { + pcie_sriov_vf_register_bar(pci_dev, 0, &n->bar0); + } else { + pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY | + PCI_BASE_ADDRESS_MEM_TYPE_64, &n->bar0); + } ret = msix_init(pci_dev, n->params.msix_qsize, &n->bar0, 0, msix_table_offset, &n->bar0, 0, msix_pba_offset, 0, &err); @@ -6680,6 +7169,8 @@ static int nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp) } } + nvme_update_msixcap_ts(pci_dev, n->conf_msix_qsize); + if (n->params.cmb_size_mb) { nvme_init_cmb(n, pci_dev); } @@ -6688,6 +7179,10 @@ static int nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp) nvme_init_pmr(n, pci_dev); } + if (!pci_is_vf(pci_dev) && n->params.sriov_max_vfs) { + nvme_init_sriov(n, pci_dev, 0x120); + } + return 0; } @@ -6709,6 +7204,7 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) NvmeIdCtrl *id = &n->id_ctrl; uint8_t *pci_conf = pci_dev->config; uint64_t cap = ldq_le_p(&n->bar.cap); + NvmeSecCtrlEntry *sctrl = nvme_sctrl(n); id->vid = cpu_to_le16(pci_get_word(pci_conf + PCI_VENDOR_ID)); id->ssvid = cpu_to_le16(pci_get_word(pci_conf + PCI_SUBSYSTEM_VENDOR_ID)); @@ -6775,8 +7271,7 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) id->vwc = NVME_VWC_NSID_BROADCAST_SUPPORT | NVME_VWC_PRESENT; id->ocfs = cpu_to_le16(NVME_OCFS_COPY_FORMAT_0 | NVME_OCFS_COPY_FORMAT_1); - id->sgls = cpu_to_le32(NVME_CTRL_SGLS_SUPPORT_NO_ALIGN | - NVME_CTRL_SGLS_BITBUCKET); + id->sgls = cpu_to_le32(NVME_CTRL_SGLS_SUPPORT_NO_ALIGN); nvme_init_subnqn(n); @@ -6801,6 +7296,10 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) stl_le_p(&n->bar.vs, NVME_SPEC_VER); n->bar.intmc = n->bar.intms = 0; + + if (pci_is_vf(&n->parent_obj) && !sctrl->scs) { + stl_le_p(&n->bar.csts, NVME_CSTS_FAILED); + } } static int nvme_init_subsys(NvmeCtrl *n, Error **errp) @@ -6838,6 +7337,16 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp) NvmeCtrl *n = NVME(pci_dev); NvmeNamespace *ns; Error *local_err = NULL; + NvmeCtrl *pn = NVME(pcie_sriov_get_pf(pci_dev)); + + if (pci_is_vf(pci_dev)) { + /* + * VFs derive settings from the parent. PF's lifespan exceeds + * that of VF's, so it's safe to share params.serial. + */ + memcpy(&n->params, &pn->params, sizeof(NvmeParams)); + n->subsys = pn->subsys; + } nvme_check_constraints(n, &local_err); if (local_err) { @@ -6848,15 +7357,14 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp) qbus_init(&n->bus, sizeof(NvmeBus), TYPE_NVME_BUS, &pci_dev->qdev, n->parent_obj.qdev.id); - nvme_init_state(n); - if (nvme_init_pci(n, pci_dev, errp)) { - return; - } - if (nvme_init_subsys(n, errp)) { error_propagate(errp, local_err); return; } + nvme_init_state(n); + if (nvme_init_pci(n, pci_dev, errp)) { + return; + } nvme_init_ctrl(n, pci_dev); /* setup a namespace if the controller drive property was given */ @@ -6878,7 +7386,7 @@ static void nvme_exit(PCIDevice *pci_dev) NvmeNamespace *ns; int i; - nvme_ctrl_reset(n); + nvme_ctrl_reset(n, NVME_RESET_FUNCTION); if (n->subsys) { for (i = 1; i <= NVME_MAX_NAMESPACES; i++) { @@ -6902,6 +7410,11 @@ static void nvme_exit(PCIDevice *pci_dev) if (n->pmr.dev) { host_memory_backend_set_mapped(n->pmr.dev, false); } + + if (!pci_is_vf(pci_dev) && n->params.sriov_max_vfs) { + pcie_sriov_pf_exit(pci_dev); + } + msix_uninit(pci_dev, &n->bar0, &n->bar0); memory_region_del_subregion(&n->bar0, &n->iomem); } @@ -6926,6 +7439,15 @@ static Property nvme_props[] = { DEFINE_PROP_UINT8("zoned.zasl", NvmeCtrl, params.zasl, 0), DEFINE_PROP_BOOL("zoned.auto_transition", NvmeCtrl, params.auto_transition_zones, true), + DEFINE_PROP_UINT8("sriov_max_vfs", NvmeCtrl, params.sriov_max_vfs, 0), + DEFINE_PROP_UINT16("sriov_vq_flexible", NvmeCtrl, + params.sriov_vq_flexible, 0), + DEFINE_PROP_UINT16("sriov_vi_flexible", NvmeCtrl, + params.sriov_vi_flexible, 0), + DEFINE_PROP_UINT8("sriov_max_vi_per_vf", NvmeCtrl, + params.sriov_max_vi_per_vf, 0), + DEFINE_PROP_UINT8("sriov_max_vq_per_vf", NvmeCtrl, + params.sriov_max_vq_per_vf, 0), DEFINE_PROP_END_OF_LIST(), }; @@ -6971,6 +7493,47 @@ static void nvme_set_smart_warning(Object *obj, Visitor *v, const char *name, } } +static void nvme_pci_reset(DeviceState *qdev) +{ + PCIDevice *pci_dev = PCI_DEVICE(qdev); + NvmeCtrl *n = NVME(pci_dev); + + trace_pci_nvme_pci_reset(); + nvme_ctrl_reset(n, NVME_RESET_FUNCTION); +} + +static void nvme_sriov_pre_write_ctrl(PCIDevice *dev, uint32_t address, + uint32_t val, int len) +{ + NvmeCtrl *n = NVME(dev); + NvmeSecCtrlEntry *sctrl; + uint16_t sriov_cap = dev->exp.sriov_cap; + uint32_t off = address - sriov_cap; + int i, num_vfs; + + if (!sriov_cap) { + return; + } + + if (range_covers_byte(off, len, PCI_SRIOV_CTRL)) { + if (!(val & PCI_SRIOV_CTRL_VFE)) { + num_vfs = pci_get_word(dev->config + sriov_cap + PCI_SRIOV_NUM_VF); + for (i = 0; i < num_vfs; i++) { + sctrl = &n->sec_ctrl_list.sec[i]; + nvme_virt_set_state(n, le16_to_cpu(sctrl->scid), false); + } + } + } +} + +static void nvme_pci_write_config(PCIDevice *dev, uint32_t address, + uint32_t val, int len) +{ + nvme_sriov_pre_write_ctrl(dev, address, val, len); + pci_default_write_config(dev, address, val, len); + pcie_cap_flr_write_config(dev, address, val, len); +} + static const VMStateDescription nvme_vmstate = { .name = "nvme", .unmigratable = 1, @@ -6982,6 +7545,7 @@ static void nvme_class_init(ObjectClass *oc, void *data) PCIDeviceClass *pc = PCI_DEVICE_CLASS(oc); pc->realize = nvme_realize; + pc->config_write = nvme_pci_write_config; pc->exit = nvme_exit; pc->class_id = PCI_CLASS_STORAGE_EXPRESS; pc->revision = 2; @@ -6990,6 +7554,7 @@ static void nvme_class_init(ObjectClass *oc, void *data) dc->desc = "Non-Volatile Memory Express"; device_class_set_props(dc, nvme_props); dc->vmsd = &nvme_vmstate; + dc->reset = nvme_pci_reset; } static void nvme_instance_init(Object *obj) diff --git a/hw/nvme/ns.c b/hw/nvme/ns.c index 1b9c9d1156..870c3ca1a2 100644 --- a/hw/nvme/ns.c +++ b/hw/nvme/ns.c @@ -597,7 +597,7 @@ static void nvme_ns_realize(DeviceState *dev, Error **errp) for (i = 0; i < ARRAY_SIZE(subsys->ctrls); i++) { NvmeCtrl *ctrl = subsys->ctrls[i]; - if (ctrl) { + if (ctrl && ctrl != SUBSYS_SLOT_RSVD) { nvme_attach_ns(ctrl, ns); } } diff --git a/hw/nvme/nvme.h b/hw/nvme/nvme.h index e41771604f..99437d39bb 100644 --- a/hw/nvme/nvme.h +++ b/hw/nvme/nvme.h @@ -24,7 +24,7 @@ #include "block/nvme.h" -#define NVME_MAX_CONTROLLERS 32 +#define NVME_MAX_CONTROLLERS 256 #define NVME_MAX_NAMESPACES 256 #define NVME_EUI64_DEFAULT ((uint64_t)0x5254000000000000) @@ -43,6 +43,7 @@ typedef struct NvmeBus { #define TYPE_NVME_SUBSYS "nvme-subsys" #define NVME_SUBSYS(obj) \ OBJECT_CHECK(NvmeSubsystem, (obj), TYPE_NVME_SUBSYS) +#define SUBSYS_SLOT_RSVD (void *)0xFFFF typedef struct NvmeSubsystem { DeviceState parent_obj; @@ -68,6 +69,10 @@ static inline NvmeCtrl *nvme_subsys_ctrl(NvmeSubsystem *subsys, return NULL; } + if (subsys->ctrls[cntlid] == SUBSYS_SLOT_RSVD) { + return NULL; + } + return subsys->ctrls[cntlid]; } @@ -335,6 +340,7 @@ static inline const char *nvme_adm_opc_str(uint8_t opc) case NVME_ADM_CMD_GET_FEATURES: return "NVME_ADM_CMD_GET_FEATURES"; case NVME_ADM_CMD_ASYNC_EV_REQ: return "NVME_ADM_CMD_ASYNC_EV_REQ"; case NVME_ADM_CMD_NS_ATTACHMENT: return "NVME_ADM_CMD_NS_ATTACHMENT"; + case NVME_ADM_CMD_VIRT_MNGMT: return "NVME_ADM_CMD_VIRT_MNGMT"; case NVME_ADM_CMD_FORMAT_NVM: return "NVME_ADM_CMD_FORMAT_NVM"; default: return "NVME_ADM_CMD_UNKNOWN"; } @@ -406,6 +412,11 @@ typedef struct NvmeParams { uint8_t zasl; bool auto_transition_zones; bool legacy_cmb; + uint8_t sriov_max_vfs; + uint16_t sriov_vq_flexible; + uint16_t sriov_vi_flexible; + uint8_t sriov_max_vq_per_vf; + uint8_t sriov_max_vi_per_vf; } NvmeParams; typedef struct NvmeCtrl { @@ -423,7 +434,6 @@ typedef struct NvmeCtrl { uint16_t max_prp_ents; uint16_t cqe_size; uint16_t sqe_size; - uint32_t reg_size; uint32_t max_q_ents; uint8_t outstanding_aers; uint32_t irq_status; @@ -433,6 +443,8 @@ typedef struct NvmeCtrl { uint64_t starttime_ms; uint16_t temperature; uint8_t smart_critical_warning; + uint32_t conf_msix_qsize; + uint32_t conf_ioqpairs; struct { MemoryRegion mem; @@ -477,8 +489,20 @@ typedef struct NvmeCtrl { uint32_t async_config; NvmeHostBehaviorSupport hbs; } features; + + NvmePriCtrlCap pri_ctrl_cap; + NvmeSecCtrlList sec_ctrl_list; + struct { + uint16_t vqrfap; + uint16_t virfap; + } next_pri_ctrl_cap; /* These override pri_ctrl_cap after reset */ } NvmeCtrl; +typedef enum NvmeResetType { + NVME_RESET_FUNCTION = 0, + NVME_RESET_CONTROLLER = 1, +} NvmeResetType; + static inline NvmeNamespace *nvme_ns(NvmeCtrl *n, uint32_t nsid) { if (!nsid || nsid > NVME_MAX_NAMESPACES) { @@ -511,6 +535,33 @@ static inline uint16_t nvme_cid(NvmeRequest *req) return le16_to_cpu(req->cqe.cid); } +static inline NvmeSecCtrlEntry *nvme_sctrl(NvmeCtrl *n) +{ + PCIDevice *pci_dev = &n->parent_obj; + NvmeCtrl *pf = NVME(pcie_sriov_get_pf(pci_dev)); + + if (pci_is_vf(pci_dev)) { + return &pf->sec_ctrl_list.sec[pcie_sriov_vf_number(pci_dev)]; + } + + return NULL; +} + +static inline NvmeSecCtrlEntry *nvme_sctrl_for_cntlid(NvmeCtrl *n, + uint16_t cntlid) +{ + NvmeSecCtrlList *list = &n->sec_ctrl_list; + uint8_t i; + + for (i = 0; i < list->numcntl; i++) { + if (le16_to_cpu(list->sec[i].scid) == cntlid) { + return &list->sec[i]; + } + } + + return NULL; +} + void nvme_attach_ns(NvmeCtrl *n, NvmeNamespace *ns); uint16_t nvme_bounce_data(NvmeCtrl *n, void *ptr, uint32_t len, NvmeTxDirection dir, NvmeRequest *req); diff --git a/hw/nvme/subsys.c b/hw/nvme/subsys.c index 691a90d209..9d2643678b 100644 --- a/hw/nvme/subsys.c +++ b/hw/nvme/subsys.c @@ -11,20 +11,71 @@ #include "nvme.h" -int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp) +static int nvme_subsys_reserve_cntlids(NvmeCtrl *n, int start, int num) { NvmeSubsystem *subsys = n->subsys; - int cntlid, nsid; + NvmeSecCtrlList *list = &n->sec_ctrl_list; + NvmeSecCtrlEntry *sctrl; + int i, cnt = 0; + + for (i = start; i < ARRAY_SIZE(subsys->ctrls) && cnt < num; i++) { + if (!subsys->ctrls[i]) { + sctrl = &list->sec[cnt]; + sctrl->scid = cpu_to_le16(i); + subsys->ctrls[i] = SUBSYS_SLOT_RSVD; + cnt++; + } + } + + return cnt; +} - for (cntlid = 0; cntlid < ARRAY_SIZE(subsys->ctrls); cntlid++) { - if (!subsys->ctrls[cntlid]) { - break; +static void nvme_subsys_unreserve_cntlids(NvmeCtrl *n) +{ + NvmeSubsystem *subsys = n->subsys; + NvmeSecCtrlList *list = &n->sec_ctrl_list; + NvmeSecCtrlEntry *sctrl; + int i, cntlid; + + for (i = 0; i < n->params.sriov_max_vfs; i++) { + sctrl = &list->sec[i]; + cntlid = le16_to_cpu(sctrl->scid); + + if (cntlid) { + assert(subsys->ctrls[cntlid] == SUBSYS_SLOT_RSVD); + subsys->ctrls[cntlid] = NULL; + sctrl->scid = 0; } } +} - if (cntlid == ARRAY_SIZE(subsys->ctrls)) { - error_setg(errp, "no more free controller id"); - return -1; +int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp) +{ + NvmeSubsystem *subsys = n->subsys; + NvmeSecCtrlEntry *sctrl = nvme_sctrl(n); + int cntlid, nsid, num_rsvd, num_vfs = n->params.sriov_max_vfs; + + if (pci_is_vf(&n->parent_obj)) { + cntlid = le16_to_cpu(sctrl->scid); + } else { + for (cntlid = 0; cntlid < ARRAY_SIZE(subsys->ctrls); cntlid++) { + if (!subsys->ctrls[cntlid]) { + break; + } + } + + if (cntlid == ARRAY_SIZE(subsys->ctrls)) { + error_setg(errp, "no more free controller id"); + return -1; + } + + num_rsvd = nvme_subsys_reserve_cntlids(n, cntlid + 1, num_vfs); + if (num_rsvd != num_vfs) { + nvme_subsys_unreserve_cntlids(n); + error_setg(errp, + "no more free controller ids for secondary controllers"); + return -1; + } } if (!subsys->serial) { @@ -48,7 +99,13 @@ int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp) void nvme_subsys_unregister_ctrl(NvmeSubsystem *subsys, NvmeCtrl *n) { - subsys->ctrls[n->cntlid] = NULL; + if (pci_is_vf(&n->parent_obj)) { + subsys->ctrls[n->cntlid] = SUBSYS_SLOT_RSVD; + } else { + subsys->ctrls[n->cntlid] = NULL; + nvme_subsys_unreserve_cntlids(n); + } + n->cntlid = -1; } diff --git a/hw/nvme/trace-events b/hw/nvme/trace-events index ff1b458969..065e1c891d 100644 --- a/hw/nvme/trace-events +++ b/hw/nvme/trace-events @@ -56,6 +56,8 @@ pci_nvme_identify_ctrl(void) "identify controller" pci_nvme_identify_ctrl_csi(uint8_t csi) "identify controller, csi=0x%"PRIx8"" pci_nvme_identify_ns(uint32_t ns) "nsid %"PRIu32"" pci_nvme_identify_ctrl_list(uint8_t cns, uint16_t cntid) "cns 0x%"PRIx8" cntid %"PRIu16"" +pci_nvme_identify_pri_ctrl_cap(uint16_t cntlid) "identify primary controller capabilities cntlid=%"PRIu16"" +pci_nvme_identify_sec_ctrl_list(uint16_t cntlid, uint8_t numcntl) "identify secondary controller list cntlid=%"PRIu16" numcntl=%"PRIu8"" pci_nvme_identify_ns_csi(uint32_t ns, uint8_t csi) "nsid=%"PRIu32", csi=0x%"PRIx8"" pci_nvme_identify_nslist(uint32_t ns) "nsid %"PRIu32"" pci_nvme_identify_nslist_csi(uint16_t ns, uint8_t csi) "nsid=%"PRIu16", csi=0x%"PRIx8"" @@ -108,6 +110,8 @@ pci_nvme_zd_extension_set(uint32_t zone_idx) "set descriptor extension for zone_ pci_nvme_clear_ns_close(uint32_t state, uint64_t slba) "zone state=%"PRIu32", slba=%"PRIu64" transitioned to Closed state" pci_nvme_clear_ns_reset(uint32_t state, uint64_t slba) "zone state=%"PRIu32", slba=%"PRIu64" transitioned to Empty state" pci_nvme_zoned_zrwa_implicit_flush(uint64_t zslba, uint32_t nlb) "zslba 0x%"PRIx64" nlb %"PRIu32"" +pci_nvme_pci_reset(void) "PCI Function Level Reset" +pci_nvme_virt_mngmt(uint16_t cid, uint16_t act, uint16_t cntlid, const char* rt, uint16_t nr) "cid %"PRIu16", act=0x%"PRIx16", ctrlid=%"PRIu16" %s nr=%"PRIu16"" # error conditions pci_nvme_err_mdts(size_t len) "len %zu" @@ -177,7 +181,9 @@ pci_nvme_err_startfail_asqent_sz_zero(void) "nvme_start_ctrl failed because the pci_nvme_err_startfail_acqent_sz_zero(void) "nvme_start_ctrl failed because the admin completion queue size is zero" pci_nvme_err_startfail_zasl_too_small(uint32_t zasl, uint32_t pagesz) "nvme_start_ctrl failed because zone append size limit %"PRIu32" is too small, needs to be >= %"PRIu32"" pci_nvme_err_startfail(void) "setting controller enable bit failed" +pci_nvme_err_startfail_virt_state(uint16_t vq, uint16_t vi, const char *state) "nvme_start_ctrl failed due to ctrl state: vi=%u vq=%u %s" pci_nvme_err_invalid_mgmt_action(uint8_t action) "action=0x%"PRIx8"" +pci_nvme_err_ignored_mmio_vf_offline(uint64_t addr, unsigned size) "addr 0x%"PRIx64" size %d" # undefined behavior pci_nvme_ub_mmiowr_misaligned32(uint64_t offset) "MMIO write not 32-bit aligned, offset=0x%"PRIx64"" diff --git a/hw/pci-host/pnv_phb3.c b/hw/pci-host/pnv_phb3.c index 3f03467dde..26ac9b7123 100644 --- a/hw/pci-host/pnv_phb3.c +++ b/hw/pci-host/pnv_phb3.c @@ -1088,10 +1088,10 @@ static const char *pnv_phb3_root_bus_path(PCIHostState *host_bridge, } static Property pnv_phb3_properties[] = { - DEFINE_PROP_UINT32("index", PnvPHB3, phb_id, 0), - DEFINE_PROP_UINT32("chip-id", PnvPHB3, chip_id, 0), - DEFINE_PROP_LINK("chip", PnvPHB3, chip, TYPE_PNV_CHIP, PnvChip *), - DEFINE_PROP_END_OF_LIST(), + DEFINE_PROP_UINT32("index", PnvPHB3, phb_id, 0), + DEFINE_PROP_UINT32("chip-id", PnvPHB3, chip_id, 0), + DEFINE_PROP_LINK("chip", PnvPHB3, chip, TYPE_PNV_CHIP, PnvChip *), + DEFINE_PROP_END_OF_LIST(), }; static void pnv_phb3_class_init(ObjectClass *klass, void *data) diff --git a/hw/pci-host/pnv_phb4.c b/hw/pci-host/pnv_phb4.c index 13ba9e45d8..6594016121 100644 --- a/hw/pci-host/pnv_phb4.c +++ b/hw/pci-host/pnv_phb4.c @@ -1692,11 +1692,11 @@ static void pnv_phb4_xive_notify(XiveNotifier *xf, uint32_t srcno, } static Property pnv_phb4_properties[] = { - DEFINE_PROP_UINT32("index", PnvPHB4, phb_id, 0), - DEFINE_PROP_UINT32("chip-id", PnvPHB4, chip_id, 0), - DEFINE_PROP_LINK("pec", PnvPHB4, pec, TYPE_PNV_PHB4_PEC, - PnvPhb4PecState *), - DEFINE_PROP_END_OF_LIST(), + DEFINE_PROP_UINT32("index", PnvPHB4, phb_id, 0), + DEFINE_PROP_UINT32("chip-id", PnvPHB4, chip_id, 0), + DEFINE_PROP_LINK("pec", PnvPHB4, pec, TYPE_PNV_PHB4_PEC, + PnvPhb4PecState *), + DEFINE_PROP_END_OF_LIST(), }; static void pnv_phb4_class_init(ObjectClass *klass, void *data) diff --git a/hw/pci-host/pnv_phb4_pec.c b/hw/pci-host/pnv_phb4_pec.c index 61bc0b503e..8b7e823fa5 100644 --- a/hw/pci-host/pnv_phb4_pec.c +++ b/hw/pci-host/pnv_phb4_pec.c @@ -215,11 +215,11 @@ static int pnv_pec_dt_xscom(PnvXScomInterface *dev, void *fdt, } static Property pnv_pec_properties[] = { - DEFINE_PROP_UINT32("index", PnvPhb4PecState, index, 0), - DEFINE_PROP_UINT32("chip-id", PnvPhb4PecState, chip_id, 0), - DEFINE_PROP_LINK("chip", PnvPhb4PecState, chip, TYPE_PNV_CHIP, - PnvChip *), - DEFINE_PROP_END_OF_LIST(), + DEFINE_PROP_UINT32("index", PnvPhb4PecState, index, 0), + DEFINE_PROP_UINT32("chip-id", PnvPhb4PecState, chip_id, 0), + DEFINE_PROP_LINK("chip", PnvPhb4PecState, chip, TYPE_PNV_CHIP, + PnvChip *), + DEFINE_PROP_END_OF_LIST(), }; static uint32_t pnv_pec_xscom_pci_base(PnvPhb4PecState *pec) diff --git a/hw/ppc/ppc440_uc.c b/hw/ppc/ppc440_uc.c index 993e3ba955..a1ecf6dd1c 100644 --- a/hw/ppc/ppc440_uc.c +++ b/hw/ppc/ppc440_uc.c @@ -1180,6 +1180,14 @@ static void dcr_write_pcie(void *opaque, int dcrn, uint32_t val) case PEGPL_CFGMSK: s->cfg_mask = val; size = ~(val & 0xfffffffe) + 1; + /* + * Firmware sets this register to E0000001. Why we are not sure, + * but the current guess is anything above PCIE_MMCFG_SIZE_MAX is + * ignored. + */ + if (size > PCIE_MMCFG_SIZE_MAX) { + size = PCIE_MMCFG_SIZE_MAX; + } pcie_host_mmcfg_update(PCIE_HOST_BRIDGE(s), val & 1, s->cfg_base, size); break; case PEGPL_MSGBAH: |