diff options
Diffstat (limited to 'hw')
66 files changed, 2665 insertions, 500 deletions
diff --git a/hw/Makefile.objs b/hw/Makefile.objs index 4cbe5e4e57..14b7ea4eb6 100644 --- a/hw/Makefile.objs +++ b/hw/Makefile.objs @@ -43,4 +43,6 @@ devices-dirs-y += smbios/ endif common-obj-y += $(devices-dirs-y) +common-obj-m += display/ +common-obj-m += usb/ obj-y += $(devices-dirs-y) diff --git a/hw/arm/fsl-imx6ul.c b/hw/arm/fsl-imx6ul.c index 6446034711..51b2f256ec 100644 --- a/hw/arm/fsl-imx6ul.c +++ b/hw/arm/fsl-imx6ul.c @@ -428,6 +428,9 @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) }; object_property_set_uint(OBJECT(&s->eth[i]), + s->phy_num[i], + "phy-num", &error_abort); + object_property_set_uint(OBJECT(&s->eth[i]), FSL_IMX6UL_ETH_NUM_TX_RINGS, "tx-ring-num", &error_abort); qdev_set_nic_properties(DEVICE(&s->eth[i]), &nd_table[i]); @@ -607,10 +610,17 @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) FSL_IMX6UL_OCRAM_ALIAS_ADDR, &s->ocram_alias); } +static Property fsl_imx6ul_properties[] = { + DEFINE_PROP_UINT32("fec1-phy-num", FslIMX6ULState, phy_num[0], 0), + DEFINE_PROP_UINT32("fec2-phy-num", FslIMX6ULState, phy_num[1], 1), + DEFINE_PROP_END_OF_LIST(), +}; + static void fsl_imx6ul_class_init(ObjectClass *oc, void *data) { DeviceClass *dc = DEVICE_CLASS(oc); + device_class_set_props(dc, fsl_imx6ul_properties); dc->realize = fsl_imx6ul_realize; dc->desc = "i.MX6UL SOC"; /* Reason: Uses serial_hds and nd_table in realize() directly */ diff --git a/hw/arm/mcimx6ul-evk.c b/hw/arm/mcimx6ul-evk.c index 2f845cedfc..9033d3f8f3 100644 --- a/hw/arm/mcimx6ul-evk.c +++ b/hw/arm/mcimx6ul-evk.c @@ -40,6 +40,8 @@ static void mcimx6ul_evk_init(MachineState *machine) s = FSL_IMX6UL(object_new(TYPE_FSL_IMX6UL)); object_property_add_child(OBJECT(machine), "soc", OBJECT(s)); + object_property_set_uint(OBJECT(s), 2, "fec1-phy-num", &error_fatal); + object_property_set_uint(OBJECT(s), 1, "fec2-phy-num", &error_fatal); qdev_realize(DEVICE(s), NULL, &error_fatal); memory_region_add_subregion(get_system_memory(), FSL_IMX6UL_MMDC_ADDR, diff --git a/hw/arm/pxa2xx_pic.c b/hw/arm/pxa2xx_pic.c index 105c5e63f2..ceee6aa48d 100644 --- a/hw/arm/pxa2xx_pic.c +++ b/hw/arm/pxa2xx_pic.c @@ -11,6 +11,7 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qemu/module.h" +#include "qemu/log.h" #include "cpu.h" #include "hw/arm/pxa.h" #include "hw/sysbus.h" @@ -166,7 +167,9 @@ static uint64_t pxa2xx_pic_mem_read(void *opaque, hwaddr offset, case ICHP: /* Highest Priority register */ return pxa2xx_pic_highest(s); default: - printf("%s: Bad register offset " REG_FMT "\n", __func__, offset); + qemu_log_mask(LOG_GUEST_ERROR, + "pxa2xx_pic_mem_read: bad register offset 0x%" HWADDR_PRIx + "\n", offset); return 0; } } @@ -199,7 +202,9 @@ static void pxa2xx_pic_mem_write(void *opaque, hwaddr offset, s->priority[32 + ((offset - IPR32) >> 2)] = value & 0x8000003f; break; default: - printf("%s: Bad register offset " REG_FMT "\n", __func__, offset); + qemu_log_mask(LOG_GUEST_ERROR, + "pxa2xx_pic_mem_write: bad register offset 0x%" + HWADDR_PRIx "\n", offset); return; } pxa2xx_pic_update(opaque); diff --git a/hw/arm/spitz.c b/hw/arm/spitz.c index fc18212e68..f020aff974 100644 --- a/hw/arm/spitz.c +++ b/hw/arm/spitz.c @@ -23,36 +23,66 @@ #include "hw/ssi/ssi.h" #include "hw/block/flash.h" #include "qemu/timer.h" +#include "qemu/log.h" #include "hw/arm/sharpsl.h" #include "ui/console.h" #include "hw/audio/wm8750.h" #include "audio/audio.h" #include "hw/boards.h" #include "hw/sysbus.h" +#include "hw/misc/max111x.h" #include "migration/vmstate.h" #include "exec/address-spaces.h" #include "cpu.h" -#undef REG_FMT -#define REG_FMT "0x%02lx" +enum spitz_model_e { spitz, akita, borzoi, terrier }; + +typedef struct { + MachineClass parent; + enum spitz_model_e model; + int arm_id; +} SpitzMachineClass; + +typedef struct { + MachineState parent; + PXA2xxState *mpu; + DeviceState *mux; + DeviceState *lcdtg; + DeviceState *ads7846; + DeviceState *max1111; + DeviceState *scp0; + DeviceState *scp1; + DeviceState *misc_gpio; +} SpitzMachineState; + +#define TYPE_SPITZ_MACHINE "spitz-common" +#define SPITZ_MACHINE(obj) \ + OBJECT_CHECK(SpitzMachineState, obj, TYPE_SPITZ_MACHINE) +#define SPITZ_MACHINE_GET_CLASS(obj) \ + OBJECT_GET_CLASS(SpitzMachineClass, obj, TYPE_SPITZ_MACHINE) +#define SPITZ_MACHINE_CLASS(klass) \ + OBJECT_CLASS_CHECK(SpitzMachineClass, klass, TYPE_SPITZ_MACHINE) + +#define zaurus_printf(format, ...) \ + fprintf(stderr, "%s: " format, __func__, ##__VA_ARGS__) /* Spitz Flash */ -#define FLASH_BASE 0x0c000000 -#define FLASH_ECCLPLB 0x00 /* Line parity 7 - 0 bit */ -#define FLASH_ECCLPUB 0x04 /* Line parity 15 - 8 bit */ -#define FLASH_ECCCP 0x08 /* Column parity 5 - 0 bit */ -#define FLASH_ECCCNTR 0x0c /* ECC byte counter */ -#define FLASH_ECCCLRR 0x10 /* Clear ECC */ -#define FLASH_FLASHIO 0x14 /* Flash I/O */ -#define FLASH_FLASHCTL 0x18 /* Flash Control */ - -#define FLASHCTL_CE0 (1 << 0) -#define FLASHCTL_CLE (1 << 1) -#define FLASHCTL_ALE (1 << 2) -#define FLASHCTL_WP (1 << 3) -#define FLASHCTL_CE1 (1 << 4) -#define FLASHCTL_RYBY (1 << 5) -#define FLASHCTL_NCE (FLASHCTL_CE0 | FLASHCTL_CE1) +#define FLASH_BASE 0x0c000000 +#define FLASH_ECCLPLB 0x00 /* Line parity 7 - 0 bit */ +#define FLASH_ECCLPUB 0x04 /* Line parity 15 - 8 bit */ +#define FLASH_ECCCP 0x08 /* Column parity 5 - 0 bit */ +#define FLASH_ECCCNTR 0x0c /* ECC byte counter */ +#define FLASH_ECCCLRR 0x10 /* Clear ECC */ +#define FLASH_FLASHIO 0x14 /* Flash I/O */ +#define FLASH_FLASHCTL 0x18 /* Flash Control */ + +#define FLASHCTL_CE0 (1 << 0) +#define FLASHCTL_CLE (1 << 1) +#define FLASHCTL_ALE (1 << 2) +#define FLASHCTL_WP (1 << 3) +#define FLASHCTL_CE1 (1 << 4) +#define FLASHCTL_RYBY (1 << 5) +#define FLASHCTL_NCE (FLASHCTL_CE0 | FLASHCTL_CE1) #define TYPE_SL_NAND "sl-nand" #define SL_NAND(obj) OBJECT_CHECK(SLNANDState, (obj), TYPE_SL_NAND) @@ -74,12 +104,12 @@ static uint64_t sl_read(void *opaque, hwaddr addr, unsigned size) int ryby; switch (addr) { -#define BSHR(byte, from, to) ((s->ecc.lp[byte] >> (from - to)) & (1 << to)) +#define BSHR(byte, from, to) ((s->ecc.lp[byte] >> (from - to)) & (1 << to)) case FLASH_ECCLPLB: return BSHR(0, 4, 0) | BSHR(0, 5, 2) | BSHR(0, 6, 4) | BSHR(0, 7, 6) | BSHR(1, 4, 1) | BSHR(1, 5, 3) | BSHR(1, 6, 5) | BSHR(1, 7, 7); -#define BSHL(byte, from, to) ((s->ecc.lp[byte] << (to - from)) & (1 << to)) +#define BSHL(byte, from, to) ((s->ecc.lp[byte] << (to - from)) & (1 << to)) case FLASH_ECCLPUB: return BSHL(0, 0, 0) | BSHL(0, 1, 2) | BSHL(0, 2, 4) | BSHL(0, 3, 6) | BSHL(1, 0, 1) | BSHL(1, 1, 3) | BSHL(1, 2, 5) | BSHL(1, 3, 7); @@ -105,7 +135,9 @@ static uint64_t sl_read(void *opaque, hwaddr addr, unsigned size) return ecc_digest(&s->ecc, nand_getio(s->nand)); default: - zaurus_printf("Bad register offset " REG_FMT "\n", (unsigned long)addr); + qemu_log_mask(LOG_GUEST_ERROR, + "sl_read: bad register offset 0x%02" HWADDR_PRIx "\n", + addr); } return 0; } @@ -136,7 +168,9 @@ static void sl_write(void *opaque, hwaddr addr, break; default: - zaurus_printf("Bad register offset " REG_FMT "\n", (unsigned long)addr); + qemu_log_mask(LOG_GUEST_ERROR, + "sl_write: bad register offset 0x%02" HWADDR_PRIx "\n", + addr); } } @@ -191,8 +225,8 @@ static void sl_nand_realize(DeviceState *dev, Error **errp) /* Spitz Keyboard */ -#define SPITZ_KEY_STROBE_NUM 11 -#define SPITZ_KEY_SENSE_NUM 7 +#define SPITZ_KEY_STROBE_NUM 11 +#define SPITZ_KEY_SENSE_NUM 7 static const int spitz_gpio_key_sense[SPITZ_KEY_SENSE_NUM] = { 12, 17, 91, 34, 36, 38, 39 @@ -214,11 +248,11 @@ static int spitz_keymap[SPITZ_KEY_SENSE_NUM + 1][SPITZ_KEY_STROBE_NUM] = { { 0x52, 0x43, 0x01, 0x47, 0x49, -1 , -1 , -1 , -1 , -1 , -1 }, }; -#define SPITZ_GPIO_AK_INT 13 /* Remote control */ -#define SPITZ_GPIO_SYNC 16 /* Sync button */ -#define SPITZ_GPIO_ON_KEY 95 /* Power button */ -#define SPITZ_GPIO_SWA 97 /* Lid */ -#define SPITZ_GPIO_SWB 96 /* Tablet mode */ +#define SPITZ_GPIO_AK_INT 13 /* Remote control */ +#define SPITZ_GPIO_SYNC 16 /* Sync button */ +#define SPITZ_GPIO_ON_KEY 95 /* Power button */ +#define SPITZ_GPIO_SWA 97 /* Lid */ +#define SPITZ_GPIO_SWB 96 /* Tablet mode */ /* The special buttons are mapped to unused keys */ static const int spitz_gpiomap[5] = { @@ -300,7 +334,7 @@ static void spitz_keyboard_keydown(SpitzKeyboardState *s, int keycode) #define SPITZ_MOD_CTRL (1 << 8) #define SPITZ_MOD_FN (1 << 9) -#define QUEUE_KEY(c) s->fifo[(s->fifopos + s->fifolen ++) & 0xf] = c +#define QUEUE_KEY(c) s->fifo[(s->fifopos + s->fifolen ++) & 0xf] = c static void spitz_keyboard_handler(void *opaque, int keycode) { @@ -308,25 +342,25 @@ static void spitz_keyboard_handler(void *opaque, int keycode) uint16_t code; int mapcode; switch (keycode) { - case 0x2a: /* Left Shift */ + case 0x2a: /* Left Shift */ s->modifiers |= 1; break; case 0xaa: s->modifiers &= ~1; break; - case 0x36: /* Right Shift */ + case 0x36: /* Right Shift */ s->modifiers |= 2; break; case 0xb6: s->modifiers &= ~2; break; - case 0x1d: /* Control */ + case 0x1d: /* Control */ s->modifiers |= 4; break; case 0x9d: s->modifiers &= ~4; break; - case 0x38: /* Alt */ + case 0x38: /* Alt */ s->modifiers |= 8; break; case 0xb8: @@ -536,14 +570,17 @@ static void spitz_keyboard_realize(DeviceState *dev, Error **errp) /* LCD backlight controller */ -#define LCDTG_RESCTL 0x00 -#define LCDTG_PHACTRL 0x01 -#define LCDTG_DUTYCTRL 0x02 -#define LCDTG_POWERREG0 0x03 -#define LCDTG_POWERREG1 0x04 -#define LCDTG_GPOR3 0x05 -#define LCDTG_PICTRL 0x06 -#define LCDTG_POLCTRL 0x07 +#define LCDTG_RESCTL 0x00 +#define LCDTG_PHACTRL 0x01 +#define LCDTG_DUTYCTRL 0x02 +#define LCDTG_POWERREG0 0x03 +#define LCDTG_POWERREG1 0x04 +#define LCDTG_GPOR3 0x05 +#define LCDTG_PICTRL 0x06 +#define LCDTG_POLCTRL 0x07 + +#define TYPE_SPITZ_LCDTG "spitz-lcdtg" +#define SPITZ_LCDTG(obj) OBJECT_CHECK(SpitzLCDTG, (obj), TYPE_SPITZ_LCDTG) typedef struct { SSISlave ssidev; @@ -559,12 +596,9 @@ static void spitz_bl_update(SpitzLCDTG *s) zaurus_printf("LCD Backlight now off\n"); } -/* FIXME: Implement GPIO properly and remove this hack. */ -static SpitzLCDTG *spitz_lcdtg; - static inline void spitz_bl_bit5(void *opaque, int line, int level) { - SpitzLCDTG *s = spitz_lcdtg; + SpitzLCDTG *s = opaque; int prev = s->bl_intensity; if (level) @@ -578,14 +612,14 @@ static inline void spitz_bl_bit5(void *opaque, int line, int level) static inline void spitz_bl_power(void *opaque, int line, int level) { - SpitzLCDTG *s = spitz_lcdtg; + SpitzLCDTG *s = opaque; s->bl_power = !!level; spitz_bl_update(s); } static uint32_t spitz_lcdtg_transfer(SSISlave *dev, uint32_t value) { - SpitzLCDTG *s = FROM_SSI_SLAVE(SpitzLCDTG, dev); + SpitzLCDTG *s = SPITZ_LCDTG(dev); int addr; addr = value >> 5; value &= 0x1f; @@ -612,25 +646,29 @@ static uint32_t spitz_lcdtg_transfer(SSISlave *dev, uint32_t value) return 0; } -static void spitz_lcdtg_realize(SSISlave *dev, Error **errp) +static void spitz_lcdtg_realize(SSISlave *ssi, Error **errp) { - SpitzLCDTG *s = FROM_SSI_SLAVE(SpitzLCDTG, dev); + SpitzLCDTG *s = SPITZ_LCDTG(ssi); + DeviceState *dev = DEVICE(s); - spitz_lcdtg = s; s->bl_power = 0; s->bl_intensity = 0x20; + + qdev_init_gpio_in_named(dev, spitz_bl_bit5, "bl_bit5", 1); + qdev_init_gpio_in_named(dev, spitz_bl_power, "bl_power", 1); } /* SSP devices */ -#define CORGI_SSP_PORT 2 +#define CORGI_SSP_PORT 2 -#define SPITZ_GPIO_LCDCON_CS 53 -#define SPITZ_GPIO_ADS7846_CS 14 -#define SPITZ_GPIO_MAX1111_CS 20 -#define SPITZ_GPIO_TP_INT 11 +#define SPITZ_GPIO_LCDCON_CS 53 +#define SPITZ_GPIO_ADS7846_CS 14 +#define SPITZ_GPIO_MAX1111_CS 20 +#define SPITZ_GPIO_TP_INT 11 -static DeviceState *max1111; +#define TYPE_CORGI_SSP "corgi-ssp" +#define CORGI_SSP(obj) OBJECT_CHECK(CorgiSSPState, (obj), TYPE_CORGI_SSP) /* "Demux" the signal based on current chipselect */ typedef struct { @@ -641,7 +679,7 @@ typedef struct { static uint32_t corgi_ssp_transfer(SSISlave *dev, uint32_t value) { - CorgiSSPState *s = FROM_SSI_SLAVE(CorgiSSPState, dev); + CorgiSSPState *s = CORGI_SSP(dev); int i; for (i = 0; i < 3; i++) { @@ -659,29 +697,18 @@ static void corgi_ssp_gpio_cs(void *opaque, int line, int level) s->enable[line] = !level; } -#define MAX1111_BATT_VOLT 1 -#define MAX1111_BATT_TEMP 2 -#define MAX1111_ACIN_VOLT 3 - -#define SPITZ_BATTERY_TEMP 0xe0 /* About 2.9V */ -#define SPITZ_BATTERY_VOLT 0xd0 /* About 4.0V */ -#define SPITZ_CHARGEON_ACIN 0x80 /* About 5.0V */ +#define MAX1111_BATT_VOLT 1 +#define MAX1111_BATT_TEMP 2 +#define MAX1111_ACIN_VOLT 3 -static void spitz_adc_temp_on(void *opaque, int line, int level) -{ - if (!max1111) - return; - - if (level) - max111x_set_input(max1111, MAX1111_BATT_TEMP, SPITZ_BATTERY_TEMP); - else - max111x_set_input(max1111, MAX1111_BATT_TEMP, 0); -} +#define SPITZ_BATTERY_TEMP 0xe0 /* About 2.9V */ +#define SPITZ_BATTERY_VOLT 0xd0 /* About 4.0V */ +#define SPITZ_CHARGEON_ACIN 0x80 /* About 5.0V */ static void corgi_ssp_realize(SSISlave *d, Error **errp) { DeviceState *dev = DEVICE(d); - CorgiSSPState *s = FROM_SSI_SLAVE(CorgiSSPState, d); + CorgiSSPState *s = CORGI_SSP(d); qdev_init_gpio_in(dev, corgi_ssp_gpio_cs, 3); s->bus[0] = ssi_create_bus(dev, "ssi0"); @@ -689,34 +716,36 @@ static void corgi_ssp_realize(SSISlave *d, Error **errp) s->bus[2] = ssi_create_bus(dev, "ssi2"); } -static void spitz_ssp_attach(PXA2xxState *cpu) +static void spitz_ssp_attach(SpitzMachineState *sms) { - DeviceState *mux; - DeviceState *dev; void *bus; - mux = ssi_create_slave(cpu->ssp[CORGI_SSP_PORT - 1], "corgi-ssp"); - - bus = qdev_get_child_bus(mux, "ssi0"); - ssi_create_slave(bus, "spitz-lcdtg"); - - bus = qdev_get_child_bus(mux, "ssi1"); - dev = ssi_create_slave(bus, "ads7846"); - qdev_connect_gpio_out(dev, 0, - qdev_get_gpio_in(cpu->gpio, SPITZ_GPIO_TP_INT)); - - bus = qdev_get_child_bus(mux, "ssi2"); - max1111 = ssi_create_slave(bus, "max1111"); - max111x_set_input(max1111, MAX1111_BATT_VOLT, SPITZ_BATTERY_VOLT); - max111x_set_input(max1111, MAX1111_BATT_TEMP, 0); - max111x_set_input(max1111, MAX1111_ACIN_VOLT, SPITZ_CHARGEON_ACIN); - - qdev_connect_gpio_out(cpu->gpio, SPITZ_GPIO_LCDCON_CS, - qdev_get_gpio_in(mux, 0)); - qdev_connect_gpio_out(cpu->gpio, SPITZ_GPIO_ADS7846_CS, - qdev_get_gpio_in(mux, 1)); - qdev_connect_gpio_out(cpu->gpio, SPITZ_GPIO_MAX1111_CS, - qdev_get_gpio_in(mux, 2)); + sms->mux = ssi_create_slave(sms->mpu->ssp[CORGI_SSP_PORT - 1], + TYPE_CORGI_SSP); + + bus = qdev_get_child_bus(sms->mux, "ssi0"); + sms->lcdtg = ssi_create_slave(bus, TYPE_SPITZ_LCDTG); + + bus = qdev_get_child_bus(sms->mux, "ssi1"); + sms->ads7846 = ssi_create_slave(bus, "ads7846"); + qdev_connect_gpio_out(sms->ads7846, 0, + qdev_get_gpio_in(sms->mpu->gpio, SPITZ_GPIO_TP_INT)); + + bus = qdev_get_child_bus(sms->mux, "ssi2"); + sms->max1111 = qdev_new(TYPE_MAX_1111); + qdev_prop_set_uint8(sms->max1111, "input1" /* BATT_VOLT */, + SPITZ_BATTERY_VOLT); + qdev_prop_set_uint8(sms->max1111, "input2" /* BATT_TEMP */, 0); + qdev_prop_set_uint8(sms->max1111, "input3" /* ACIN_VOLT */, + SPITZ_CHARGEON_ACIN); + ssi_realize_and_unref(sms->max1111, bus, &error_fatal); + + qdev_connect_gpio_out(sms->mpu->gpio, SPITZ_GPIO_LCDCON_CS, + qdev_get_gpio_in(sms->mux, 0)); + qdev_connect_gpio_out(sms->mpu->gpio, SPITZ_GPIO_ADS7846_CS, + qdev_get_gpio_in(sms->mux, 1)); + qdev_connect_gpio_out(sms->mpu->gpio, SPITZ_GPIO_MAX1111_CS, + qdev_get_gpio_in(sms->mux, 2)); } /* CF Microdrive */ @@ -735,11 +764,11 @@ static void spitz_microdrive_attach(PXA2xxState *cpu, int slot) /* Wm8750 and Max7310 on I2C */ -#define AKITA_MAX_ADDR 0x18 -#define SPITZ_WM_ADDRL 0x1b -#define SPITZ_WM_ADDRH 0x1a +#define AKITA_MAX_ADDR 0x18 +#define SPITZ_WM_ADDRL 0x1b +#define SPITZ_WM_ADDRH 0x1a -#define SPITZ_GPIO_WM 5 +#define SPITZ_GPIO_WM 5 static void spitz_wm8750_addr(void *opaque, int line, int level) { @@ -779,75 +808,119 @@ static void spitz_akita_i2c_setup(PXA2xxState *cpu) /* Other peripherals */ -static void spitz_out_switch(void *opaque, int line, int level) +/* + * Encapsulation of some miscellaneous GPIO line behaviour for the Spitz boards. + * + * QEMU interface: + * + named GPIO inputs "green-led", "orange-led", "charging", "discharging": + * these currently just print messages that the line has been signalled + * + named GPIO input "adc-temp-on": set to cause the battery-temperature + * value to be passed to the max111x ADC + * + named GPIO output "adc-temp": the ADC value, to be wired up to the max111x + */ +#define TYPE_SPITZ_MISC_GPIO "spitz-misc-gpio" +#define SPITZ_MISC_GPIO(obj) \ + OBJECT_CHECK(SpitzMiscGPIOState, (obj), TYPE_SPITZ_MISC_GPIO) + +typedef struct SpitzMiscGPIOState { + SysBusDevice parent_obj; + + qemu_irq adc_value; +} SpitzMiscGPIOState; + +static void spitz_misc_charging(void *opaque, int n, int level) { - switch (line) { - case 0: - zaurus_printf("Charging %s.\n", level ? "off" : "on"); - break; - case 1: - zaurus_printf("Discharging %s.\n", level ? "on" : "off"); - break; - case 2: - zaurus_printf("Green LED %s.\n", level ? "on" : "off"); - break; - case 3: - zaurus_printf("Orange LED %s.\n", level ? "on" : "off"); - break; - case 4: - spitz_bl_bit5(opaque, line, level); - break; - case 5: - spitz_bl_power(opaque, line, level); - break; - case 6: - spitz_adc_temp_on(opaque, line, level); - break; - } + zaurus_printf("Charging %s.\n", level ? "off" : "on"); } -#define SPITZ_SCP_LED_GREEN 1 -#define SPITZ_SCP_JK_B 2 -#define SPITZ_SCP_CHRG_ON 3 -#define SPITZ_SCP_MUTE_L 4 -#define SPITZ_SCP_MUTE_R 5 -#define SPITZ_SCP_CF_POWER 6 -#define SPITZ_SCP_LED_ORANGE 7 -#define SPITZ_SCP_JK_A 8 -#define SPITZ_SCP_ADC_TEMP_ON 9 -#define SPITZ_SCP2_IR_ON 1 -#define SPITZ_SCP2_AKIN_PULLUP 2 -#define SPITZ_SCP2_BACKLIGHT_CONT 7 -#define SPITZ_SCP2_BACKLIGHT_ON 8 -#define SPITZ_SCP2_MIC_BIAS 9 - -static void spitz_scoop_gpio_setup(PXA2xxState *cpu, - DeviceState *scp0, DeviceState *scp1) +static void spitz_misc_discharging(void *opaque, int n, int level) { - qemu_irq *outsignals = qemu_allocate_irqs(spitz_out_switch, cpu, 8); + zaurus_printf("Discharging %s.\n", level ? "off" : "on"); +} - qdev_connect_gpio_out(scp0, SPITZ_SCP_CHRG_ON, outsignals[0]); - qdev_connect_gpio_out(scp0, SPITZ_SCP_JK_B, outsignals[1]); - qdev_connect_gpio_out(scp0, SPITZ_SCP_LED_GREEN, outsignals[2]); - qdev_connect_gpio_out(scp0, SPITZ_SCP_LED_ORANGE, outsignals[3]); +static void spitz_misc_green_led(void *opaque, int n, int level) +{ + zaurus_printf("Green LED %s.\n", level ? "off" : "on"); +} - if (scp1) { - qdev_connect_gpio_out(scp1, SPITZ_SCP2_BACKLIGHT_CONT, outsignals[4]); - qdev_connect_gpio_out(scp1, SPITZ_SCP2_BACKLIGHT_ON, outsignals[5]); - } +static void spitz_misc_orange_led(void *opaque, int n, int level) +{ + zaurus_printf("Orange LED %s.\n", level ? "off" : "on"); +} + +static void spitz_misc_adc_temp(void *opaque, int n, int level) +{ + SpitzMiscGPIOState *s = SPITZ_MISC_GPIO(opaque); + int batt_temp = level ? SPITZ_BATTERY_TEMP : 0; - qdev_connect_gpio_out(scp0, SPITZ_SCP_ADC_TEMP_ON, outsignals[6]); + qemu_set_irq(s->adc_value, batt_temp); } -#define SPITZ_GPIO_HSYNC 22 -#define SPITZ_GPIO_SD_DETECT 9 -#define SPITZ_GPIO_SD_WP 81 -#define SPITZ_GPIO_ON_RESET 89 -#define SPITZ_GPIO_BAT_COVER 90 -#define SPITZ_GPIO_CF1_IRQ 105 -#define SPITZ_GPIO_CF1_CD 94 -#define SPITZ_GPIO_CF2_IRQ 106 -#define SPITZ_GPIO_CF2_CD 93 +static void spitz_misc_gpio_init(Object *obj) +{ + SpitzMiscGPIOState *s = SPITZ_MISC_GPIO(obj); + DeviceState *dev = DEVICE(obj); + + qdev_init_gpio_in_named(dev, spitz_misc_charging, "charging", 1); + qdev_init_gpio_in_named(dev, spitz_misc_discharging, "discharging", 1); + qdev_init_gpio_in_named(dev, spitz_misc_green_led, "green-led", 1); + qdev_init_gpio_in_named(dev, spitz_misc_orange_led, "orange-led", 1); + qdev_init_gpio_in_named(dev, spitz_misc_adc_temp, "adc-temp-on", 1); + + qdev_init_gpio_out_named(dev, &s->adc_value, "adc-temp", 1); +} + +#define SPITZ_SCP_LED_GREEN 1 +#define SPITZ_SCP_JK_B 2 +#define SPITZ_SCP_CHRG_ON 3 +#define SPITZ_SCP_MUTE_L 4 +#define SPITZ_SCP_MUTE_R 5 +#define SPITZ_SCP_CF_POWER 6 +#define SPITZ_SCP_LED_ORANGE 7 +#define SPITZ_SCP_JK_A 8 +#define SPITZ_SCP_ADC_TEMP_ON 9 +#define SPITZ_SCP2_IR_ON 1 +#define SPITZ_SCP2_AKIN_PULLUP 2 +#define SPITZ_SCP2_BACKLIGHT_CONT 7 +#define SPITZ_SCP2_BACKLIGHT_ON 8 +#define SPITZ_SCP2_MIC_BIAS 9 + +static void spitz_scoop_gpio_setup(SpitzMachineState *sms) +{ + DeviceState *miscdev = sysbus_create_simple(TYPE_SPITZ_MISC_GPIO, -1, NULL); + + sms->misc_gpio = miscdev; + + qdev_connect_gpio_out(sms->scp0, SPITZ_SCP_CHRG_ON, + qdev_get_gpio_in_named(miscdev, "charging", 0)); + qdev_connect_gpio_out(sms->scp0, SPITZ_SCP_JK_B, + qdev_get_gpio_in_named(miscdev, "discharging", 0)); + qdev_connect_gpio_out(sms->scp0, SPITZ_SCP_LED_GREEN, + qdev_get_gpio_in_named(miscdev, "green-led", 0)); + qdev_connect_gpio_out(sms->scp0, SPITZ_SCP_LED_ORANGE, + qdev_get_gpio_in_named(miscdev, "orange-led", 0)); + qdev_connect_gpio_out(sms->scp0, SPITZ_SCP_ADC_TEMP_ON, + qdev_get_gpio_in_named(miscdev, "adc-temp-on", 0)); + qdev_connect_gpio_out_named(miscdev, "adc-temp", 0, + qdev_get_gpio_in(sms->max1111, MAX1111_BATT_TEMP)); + + if (sms->scp1) { + qdev_connect_gpio_out(sms->scp1, SPITZ_SCP2_BACKLIGHT_CONT, + qdev_get_gpio_in_named(sms->lcdtg, "bl_bit5", 0)); + qdev_connect_gpio_out(sms->scp1, SPITZ_SCP2_BACKLIGHT_ON, + qdev_get_gpio_in_named(sms->lcdtg, "bl_power", 0)); + } +} + +#define SPITZ_GPIO_HSYNC 22 +#define SPITZ_GPIO_SD_DETECT 9 +#define SPITZ_GPIO_SD_WP 81 +#define SPITZ_GPIO_ON_RESET 89 +#define SPITZ_GPIO_BAT_COVER 90 +#define SPITZ_GPIO_CF1_IRQ 105 +#define SPITZ_GPIO_CF1_CD 94 +#define SPITZ_GPIO_CF2_IRQ 106 +#define SPITZ_GPIO_CF2_CD 93 static int spitz_hsync; @@ -905,27 +978,27 @@ static void spitz_gpio_setup(PXA2xxState *cpu, int slots) } /* Board init. */ -enum spitz_model_e { spitz, akita, borzoi, terrier }; - -#define SPITZ_RAM 0x04000000 -#define SPITZ_ROM 0x00800000 +#define SPITZ_RAM 0x04000000 +#define SPITZ_ROM 0x00800000 static struct arm_boot_info spitz_binfo = { .loader_start = PXA2XX_SDRAM_BASE, .ram_size = 0x04000000, }; -static void spitz_common_init(MachineState *machine, - enum spitz_model_e model, int arm_id) +static void spitz_common_init(MachineState *machine) { + SpitzMachineClass *smc = SPITZ_MACHINE_GET_CLASS(machine); + SpitzMachineState *sms = SPITZ_MACHINE(machine); + enum spitz_model_e model = smc->model; PXA2xxState *mpu; - DeviceState *scp0, *scp1 = NULL; MemoryRegion *address_space_mem = get_system_memory(); MemoryRegion *rom = g_new(MemoryRegion, 1); /* Setup CPU & memory */ mpu = pxa270_init(address_space_mem, spitz_binfo.ram_size, machine->cpu_type); + sms->mpu = mpu; sl_flash_register(mpu, (model == spitz) ? FLASH_128M : FLASH_1024M); @@ -935,14 +1008,16 @@ static void spitz_common_init(MachineState *machine, /* Setup peripherals */ spitz_keyboard_register(mpu); - spitz_ssp_attach(mpu); + spitz_ssp_attach(sms); - scp0 = sysbus_create_simple("scoop", 0x10800000, NULL); + sms->scp0 = sysbus_create_simple("scoop", 0x10800000, NULL); if (model != akita) { - scp1 = sysbus_create_simple("scoop", 0x08800040, NULL); + sms->scp1 = sysbus_create_simple("scoop", 0x08800040, NULL); + } else { + sms->scp1 = NULL; } - spitz_scoop_gpio_setup(mpu, scp0, scp1); + spitz_scoop_gpio_setup(sms); spitz_gpio_setup(mpu, (model == akita) ? 1 : 2); @@ -958,100 +1033,100 @@ static void spitz_common_init(MachineState *machine, /* A 4.0 GB microdrive is permanently sitting in CF slot 0. */ spitz_microdrive_attach(mpu, 0); - spitz_binfo.board_id = arm_id; + spitz_binfo.board_id = smc->arm_id; arm_load_kernel(mpu->cpu, machine, &spitz_binfo); sl_bootparam_write(SL_PXA_PARAM_BASE); } -static void spitz_init(MachineState *machine) -{ - spitz_common_init(machine, spitz, 0x2c9); -} - -static void borzoi_init(MachineState *machine) +static void spitz_common_class_init(ObjectClass *oc, void *data) { - spitz_common_init(machine, borzoi, 0x33f); -} + MachineClass *mc = MACHINE_CLASS(oc); -static void akita_init(MachineState *machine) -{ - spitz_common_init(machine, akita, 0x2e8); + mc->block_default_type = IF_IDE; + mc->ignore_memory_transaction_failures = true; + mc->init = spitz_common_init; } -static void terrier_init(MachineState *machine) -{ - spitz_common_init(machine, terrier, 0x33f); -} +static const TypeInfo spitz_common_info = { + .name = TYPE_SPITZ_MACHINE, + .parent = TYPE_MACHINE, + .abstract = true, + .instance_size = sizeof(SpitzMachineState), + .class_size = sizeof(SpitzMachineClass), + .class_init = spitz_common_class_init, +}; static void akitapda_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); + SpitzMachineClass *smc = SPITZ_MACHINE_CLASS(oc); mc->desc = "Sharp SL-C1000 (Akita) PDA (PXA270)"; - mc->init = akita_init; - mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("pxa270-c0"); + smc->model = akita; + smc->arm_id = 0x2e8; } static const TypeInfo akitapda_type = { .name = MACHINE_TYPE_NAME("akita"), - .parent = TYPE_MACHINE, + .parent = TYPE_SPITZ_MACHINE, .class_init = akitapda_class_init, }; static void spitzpda_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); + SpitzMachineClass *smc = SPITZ_MACHINE_CLASS(oc); mc->desc = "Sharp SL-C3000 (Spitz) PDA (PXA270)"; - mc->init = spitz_init; - mc->block_default_type = IF_IDE; - mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("pxa270-c0"); + smc->model = spitz; + smc->arm_id = 0x2c9; } static const TypeInfo spitzpda_type = { .name = MACHINE_TYPE_NAME("spitz"), - .parent = TYPE_MACHINE, + .parent = TYPE_SPITZ_MACHINE, .class_init = spitzpda_class_init, }; static void borzoipda_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); + SpitzMachineClass *smc = SPITZ_MACHINE_CLASS(oc); mc->desc = "Sharp SL-C3100 (Borzoi) PDA (PXA270)"; - mc->init = borzoi_init; - mc->block_default_type = IF_IDE; - mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("pxa270-c0"); + smc->model = borzoi; + smc->arm_id = 0x33f; } static const TypeInfo borzoipda_type = { .name = MACHINE_TYPE_NAME("borzoi"), - .parent = TYPE_MACHINE, + .parent = TYPE_SPITZ_MACHINE, .class_init = borzoipda_class_init, }; static void terrierpda_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); + SpitzMachineClass *smc = SPITZ_MACHINE_CLASS(oc); mc->desc = "Sharp SL-C3200 (Terrier) PDA (PXA270)"; - mc->init = terrier_init; - mc->block_default_type = IF_IDE; - mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("pxa270-c5"); + smc->model = terrier; + smc->arm_id = 0x33f; } static const TypeInfo terrierpda_type = { .name = MACHINE_TYPE_NAME("terrier"), - .parent = TYPE_MACHINE, + .parent = TYPE_SPITZ_MACHINE, .class_init = terrierpda_class_init, }; static void spitz_machine_init(void) { + type_register_static(&spitz_common_info); type_register_static(&akitapda_type); type_register_static(&spitzpda_type); type_register_static(&borzoipda_type); @@ -1152,7 +1227,7 @@ static void corgi_ssp_class_init(ObjectClass *klass, void *data) } static const TypeInfo corgi_ssp_info = { - .name = "corgi-ssp", + .name = TYPE_CORGI_SSP, .parent = TYPE_SSI_SLAVE, .instance_size = sizeof(CorgiSSPState), .class_init = corgi_ssp_class_init, @@ -1181,18 +1256,30 @@ static void spitz_lcdtg_class_init(ObjectClass *klass, void *data) } static const TypeInfo spitz_lcdtg_info = { - .name = "spitz-lcdtg", + .name = TYPE_SPITZ_LCDTG, .parent = TYPE_SSI_SLAVE, .instance_size = sizeof(SpitzLCDTG), .class_init = spitz_lcdtg_class_init, }; +static const TypeInfo spitz_misc_gpio_info = { + .name = TYPE_SPITZ_MISC_GPIO, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(SpitzMiscGPIOState), + .instance_init = spitz_misc_gpio_init, + /* + * No class_init required: device has no internal state so does not + * need to set up reset or vmstate, and does not have a realize method. + */ +}; + static void spitz_register_types(void) { type_register_static(&corgi_ssp_info); type_register_static(&spitz_lcdtg_info); type_register_static(&spitz_keyboard_info); type_register_static(&sl_nand_info); + type_register_static(&spitz_misc_gpio_info); } type_init(spitz_register_types) diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index 1384a2cf2a..91f0df7b13 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -749,6 +749,7 @@ static void build_fadt_rev5(GArray *table_data, BIOSLinker *linker, static void build_dsdt(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) { + VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms); Aml *scope, *dsdt; MachineState *ms = MACHINE(vms); const MemMapEntry *memmap = vms->memmap; @@ -767,7 +768,9 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) acpi_dsdt_add_cpus(scope, vms->smp_cpus); acpi_dsdt_add_uart(scope, &memmap[VIRT_UART], (irqmap[VIRT_UART] + ARM_SPI_BASE)); - acpi_dsdt_add_flash(scope, &memmap[VIRT_FLASH]); + if (vmc->acpi_expose_flash) { + acpi_dsdt_add_flash(scope, &memmap[VIRT_FLASH]); + } acpi_dsdt_add_fw_cfg(scope, &memmap[VIRT_FW_CFG]); acpi_dsdt_add_virtio(scope, &memmap[VIRT_MMIO], (irqmap[VIRT_MMIO] + ARM_SPI_BASE), NUM_VIRTIO_TRANSPORTS); diff --git a/hw/arm/virt.c b/hw/arm/virt.c index af3050bc4b..7d9f7157da 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -600,6 +600,7 @@ static void create_its(VirtMachineState *vms) sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, vms->memmap[VIRT_GIC_ITS].base); fdt_add_its_gic_node(vms); + vms->msi_controller = VIRT_MSI_CTRL_ITS; } static void create_v2m(VirtMachineState *vms) @@ -620,6 +621,7 @@ static void create_v2m(VirtMachineState *vms) } fdt_add_v2m_gic_node(vms); + vms->msi_controller = VIRT_MSI_CTRL_GICV2M; } static void create_gic(VirtMachineState *vms) @@ -2198,8 +2200,36 @@ out: static void virt_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { + VirtMachineState *vms = VIRT_MACHINE(hotplug_dev); + if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) { virt_memory_pre_plug(hotplug_dev, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) { + hwaddr db_start = 0, db_end = 0; + char *resv_prop_str; + + switch (vms->msi_controller) { + case VIRT_MSI_CTRL_NONE: + return; + case VIRT_MSI_CTRL_ITS: + /* GITS_TRANSLATER page */ + db_start = base_memmap[VIRT_GIC_ITS].base + 0x10000; + db_end = base_memmap[VIRT_GIC_ITS].base + + base_memmap[VIRT_GIC_ITS].size - 1; + break; + case VIRT_MSI_CTRL_GICV2M: + /* MSI_SETSPI_NS page */ + db_start = base_memmap[VIRT_GIC_V2M].base; + db_end = db_start + base_memmap[VIRT_GIC_V2M].size - 1; + break; + } + resv_prop_str = g_strdup_printf("0x%"PRIx64":0x%"PRIx64":%u", + db_start, db_end, + VIRTIO_IOMMU_RESV_MEM_T_MSI); + + qdev_prop_set_uint32(dev, "len-reserved-regions", 1); + qdev_prop_set_string(dev, "reserved-regions[0]", resv_prop_str); + g_free(resv_prop_str); } } @@ -2371,6 +2401,7 @@ static void virt_machine_class_init(ObjectClass *oc, void *data) hc->unplug = virt_machine_device_unplug_cb; mc->nvdimm_supported = true; mc->auto_enable_numa_with_memhp = true; + mc->auto_enable_numa_with_memdev = true; mc->default_ram_id = "mach-virt.ram"; object_class_property_add(oc, "acpi", "OnOffAuto", @@ -2480,9 +2511,13 @@ DEFINE_VIRT_MACHINE_AS_LATEST(5, 1) static void virt_machine_5_0_options(MachineClass *mc) { + VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc)); + virt_machine_5_1_options(mc); compat_props_add(mc->compat_props, hw_compat_5_0, hw_compat_5_0_len); mc->numa_mem_supported = true; + vmc->acpi_expose_flash = true; + mc->auto_enable_numa_with_memdev = false; } DEFINE_VIRT_MACHINE(5, 0) diff --git a/hw/arm/z2.c b/hw/arm/z2.c index a0f4095990..e1f22f5868 100644 --- a/hw/arm/z2.c +++ b/hw/arm/z2.c @@ -111,9 +111,12 @@ typedef struct { int pos; } ZipitLCD; +#define TYPE_ZIPIT_LCD "zipit-lcd" +#define ZIPIT_LCD(obj) OBJECT_CHECK(ZipitLCD, (obj), TYPE_ZIPIT_LCD) + static uint32_t zipit_lcd_transfer(SSISlave *dev, uint32_t value) { - ZipitLCD *z = FROM_SSI_SLAVE(ZipitLCD, dev); + ZipitLCD *z = ZIPIT_LCD(dev); uint16_t val; if (z->selected) { z->buf[z->pos] = value & 0xff; @@ -153,7 +156,7 @@ static void z2_lcd_cs(void *opaque, int line, int level) static void zipit_lcd_realize(SSISlave *dev, Error **errp) { - ZipitLCD *z = FROM_SSI_SLAVE(ZipitLCD, dev); + ZipitLCD *z = ZIPIT_LCD(dev); z->selected = 0; z->enabled = 0; z->pos = 0; @@ -185,7 +188,7 @@ static void zipit_lcd_class_init(ObjectClass *klass, void *data) } static const TypeInfo zipit_lcd_info = { - .name = "zipit-lcd", + .name = TYPE_ZIPIT_LCD, .parent = TYPE_SSI_SLAVE, .instance_size = sizeof(ZipitLCD), .class_init = zipit_lcd_class_init, @@ -325,7 +328,7 @@ static void z2_init(MachineState *machine) type_register_static(&zipit_lcd_info); type_register_static(&aer915_info); - z2_lcd = ssi_create_slave(mpu->ssp[1], "zipit-lcd"); + z2_lcd = ssi_create_slave(mpu->ssp[1], TYPE_ZIPIT_LCD); bus = pxa2xx_i2c_bus(mpu->i2c[0]); i2c_create_slave(bus, TYPE_AER915, 0x55); wm = i2c_create_slave(bus, TYPE_WM8750, 0x1b); diff --git a/hw/audio/ac97.c b/hw/audio/ac97.c index 8a9b9924c4..38522cf0ba 100644 --- a/hw/audio/ac97.c +++ b/hw/audio/ac97.c @@ -1393,12 +1393,6 @@ static void ac97_exit(PCIDevice *dev) AUD_remove_card(&s->card); } -static int ac97_init (PCIBus *bus) -{ - pci_create_simple(bus, -1, TYPE_AC97); - return 0; -} - static Property ac97_properties[] = { DEFINE_AUDIO_PROPERTIES(AC97LinkState, card), DEFINE_PROP_END_OF_LIST (), @@ -1436,7 +1430,8 @@ static const TypeInfo ac97_info = { static void ac97_register_types (void) { type_register_static (&ac97_info); - pci_register_soundhw("ac97", "Intel 82801AA AC97 Audio", ac97_init); + deprecated_register_soundhw("ac97", "Intel 82801AA AC97 Audio", + 0, TYPE_AC97); } type_init (ac97_register_types) diff --git a/hw/audio/adlib.c b/hw/audio/adlib.c index 7c3b67dcfb..65dff5b6fc 100644 --- a/hw/audio/adlib.c +++ b/hw/audio/adlib.c @@ -319,16 +319,10 @@ static const TypeInfo adlib_info = { .class_init = adlib_class_initfn, }; -static int Adlib_init (ISABus *bus) -{ - isa_create_simple (bus, TYPE_ADLIB); - return 0; -} - static void adlib_register_types (void) { type_register_static (&adlib_info); - isa_register_soundhw("adlib", ADLIB_DESC, Adlib_init); + deprecated_register_soundhw("adlib", ADLIB_DESC, 1, TYPE_ADLIB); } type_init (adlib_register_types) diff --git a/hw/audio/cs4231a.c b/hw/audio/cs4231a.c index ffdbb58d6a..59705a8d47 100644 --- a/hw/audio/cs4231a.c +++ b/hw/audio/cs4231a.c @@ -683,12 +683,6 @@ static void cs4231a_realizefn (DeviceState *dev, Error **errp) AUD_register_card ("cs4231a", &s->card); } -static int cs4231a_init (ISABus *bus) -{ - isa_create_simple (bus, TYPE_CS4231A); - return 0; -} - static Property cs4231a_properties[] = { DEFINE_AUDIO_PROPERTIES(CSState, card), DEFINE_PROP_UINT32 ("iobase", CSState, port, 0x534), @@ -720,7 +714,7 @@ static const TypeInfo cs4231a_info = { static void cs4231a_register_types (void) { type_register_static (&cs4231a_info); - isa_register_soundhw("cs4231a", "CS4231A", cs4231a_init); + deprecated_register_soundhw("cs4231a", "CS4231A", 1, TYPE_CS4231A); } type_init (cs4231a_register_types) diff --git a/hw/audio/es1370.c b/hw/audio/es1370.c index 5f8a83ff56..4255463a49 100644 --- a/hw/audio/es1370.c +++ b/hw/audio/es1370.c @@ -884,12 +884,6 @@ static void es1370_exit(PCIDevice *dev) AUD_remove_card(&s->card); } -static int es1370_init (PCIBus *bus) -{ - pci_create_simple (bus, -1, TYPE_ES1370); - return 0; -} - static Property es1370_properties[] = { DEFINE_AUDIO_PROPERTIES(ES1370State, card), DEFINE_PROP_END_OF_LIST(), @@ -928,7 +922,8 @@ static const TypeInfo es1370_info = { static void es1370_register_types (void) { type_register_static (&es1370_info); - pci_register_soundhw("es1370", "ENSONIQ AudioPCI ES1370", es1370_init); + deprecated_register_soundhw("es1370", "ENSONIQ AudioPCI ES1370", + 0, TYPE_ES1370); } type_init (es1370_register_types) diff --git a/hw/audio/gus.c b/hw/audio/gus.c index c8df2bde6b..7e4a8cadad 100644 --- a/hw/audio/gus.c +++ b/hw/audio/gus.c @@ -286,12 +286,6 @@ static void gus_realizefn (DeviceState *dev, Error **errp) AUD_set_active_out (s->voice, 1); } -static int GUS_init (ISABus *bus) -{ - isa_create_simple (bus, TYPE_GUS); - return 0; -} - static Property gus_properties[] = { DEFINE_AUDIO_PROPERTIES(GUSState, card), DEFINE_PROP_UINT32 ("freq", GUSState, freq, 44100), @@ -322,7 +316,7 @@ static const TypeInfo gus_info = { static void gus_register_types (void) { type_register_static (&gus_info); - isa_register_soundhw("gus", "Gravis Ultrasound GF1", GUS_init); + deprecated_register_soundhw("gus", "Gravis Ultrasound GF1", 1, TYPE_GUS); } type_init (gus_register_types) diff --git a/hw/audio/intel-hda.c b/hw/audio/intel-hda.c index f673b8317a..f6cea49686 100644 --- a/hw/audio/intel-hda.c +++ b/hw/audio/intel-hda.c @@ -25,6 +25,7 @@ #include "qemu/bitops.h" #include "qemu/log.h" #include "qemu/module.h" +#include "qemu/error-report.h" #include "hw/audio/soundhw.h" #include "intel-hda.h" #include "migration/vmstate.h" @@ -1307,6 +1308,8 @@ static int intel_hda_and_codec_init(PCIBus *bus) BusState *hdabus; DeviceState *codec; + warn_report("'-soundhw hda' is deprecated, " + "please use '-device intel-hda -device hda-duplex' instead"); controller = DEVICE(pci_create_simple(bus, -1, "intel-hda")); hdabus = QLIST_FIRST(&controller->child_bus); codec = qdev_new("hda-duplex"); diff --git a/hw/audio/pcspk.c b/hw/audio/pcspk.c index c37a387861..ea539e7605 100644 --- a/hw/audio/pcspk.c +++ b/hw/audio/pcspk.c @@ -28,6 +28,7 @@ #include "audio/audio.h" #include "qemu/module.h" #include "qemu/timer.h" +#include "qemu/error-report.h" #include "hw/timer/i8254.h" #include "migration/vmstate.h" #include "hw/audio/pcspk.h" @@ -112,11 +113,15 @@ static void pcspk_callback(void *opaque, int free) } } -static int pcspk_audio_init(ISABus *bus) +static int pcspk_audio_init(PCSpkState *s) { - PCSpkState *s = pcspk_state; struct audsettings as = {PCSPK_SAMPLE_RATE, 1, AUDIO_FORMAT_U8, 0}; + if (s->voice) { + /* already initialized */ + return 0; + } + AUD_register_card(s_spk, &s->card); s->voice = AUD_open_out(&s->card, s->voice, s_spk, s, pcspk_callback, &as); @@ -185,6 +190,10 @@ static void pcspk_realizefn(DeviceState *dev, Error **errp) isa_register_ioport(isadev, &s->ioport, s->iobase); + if (s->card.state) { + pcspk_audio_init(s); + } + pcspk_state = s; } @@ -210,7 +219,7 @@ static const VMStateDescription vmstate_spk = { static Property pcspk_properties[] = { DEFINE_AUDIO_PROPERTIES(PCSpkState, card), - DEFINE_PROP_UINT32("iobase", PCSpkState, iobase, -1), + DEFINE_PROP_UINT32("iobase", PCSpkState, iobase, 0x61), DEFINE_PROP_BOOL("migrate", PCSpkState, migrate, true), DEFINE_PROP_END_OF_LIST(), }; @@ -236,9 +245,18 @@ static const TypeInfo pcspk_info = { .class_init = pcspk_class_initfn, }; +static int pcspk_audio_init_soundhw(ISABus *bus) +{ + PCSpkState *s = pcspk_state; + + warn_report("'-soundhw pcspk' is deprecated, " + "please set a backend using '-machine pcspk-audiodev=<name>' instead"); + return pcspk_audio_init(s); +} + static void pcspk_register(void) { type_register_static(&pcspk_info); - isa_register_soundhw("pcspk", "PC speaker", pcspk_audio_init); + isa_register_soundhw("pcspk", "PC speaker", pcspk_audio_init_soundhw); } type_init(pcspk_register) diff --git a/hw/audio/sb16.c b/hw/audio/sb16.c index df6f755a37..2d9e50f99b 100644 --- a/hw/audio/sb16.c +++ b/hw/audio/sb16.c @@ -1415,12 +1415,6 @@ static void sb16_realizefn (DeviceState *dev, Error **errp) AUD_register_card ("sb16", &s->card); } -static int SB16_init (ISABus *bus) -{ - isa_create_simple (bus, TYPE_SB16); - return 0; -} - static Property sb16_properties[] = { DEFINE_AUDIO_PROPERTIES(SB16State, card), DEFINE_PROP_UINT32 ("version", SB16State, ver, 0x0405), /* 4.5 */ @@ -1453,7 +1447,8 @@ static const TypeInfo sb16_info = { static void sb16_register_types (void) { type_register_static (&sb16_info); - isa_register_soundhw("sb16", "Creative Sound Blaster 16", SB16_init); + deprecated_register_soundhw("sb16", "Creative Sound Blaster 16", + 1, TYPE_SB16); } type_init (sb16_register_types) diff --git a/hw/audio/soundhw.c b/hw/audio/soundhw.c index c750473c8f..173b674ff5 100644 --- a/hw/audio/soundhw.c +++ b/hw/audio/soundhw.c @@ -22,6 +22,7 @@ * THE SOFTWARE. */ #include "qemu/osdep.h" +#include "qemu/option.h" #include "qemu/help_option.h" #include "qemu/error-report.h" #include "qom/object.h" @@ -32,6 +33,7 @@ struct soundhw { const char *name; const char *descr; + const char *typename; int enabled; int isa; union { @@ -65,6 +67,17 @@ void pci_register_soundhw(const char *name, const char *descr, soundhw_count++; } +void deprecated_register_soundhw(const char *name, const char *descr, + int isa, const char *typename) +{ + assert(soundhw_count < ARRAY_SIZE(soundhw) - 1); + soundhw[soundhw_count].name = name; + soundhw[soundhw_count].descr = descr; + soundhw[soundhw_count].isa = isa; + soundhw[soundhw_count].typename = typename; + soundhw_count++; +} + void select_soundhw(const char *optarg) { struct soundhw *c; @@ -136,7 +149,16 @@ void soundhw_init(void) for (c = soundhw; c->name; ++c) { if (c->enabled) { - if (c->isa) { + if (c->typename) { + warn_report("'-soundhw %s' is deprecated, " + "please use '-device %s' instead", + c->name, c->typename); + if (c->isa) { + isa_create_simple(isa_bus, c->typename); + } else { + pci_create_simple(pci_bus, -1, c->typename); + } + } else if (c->isa) { if (!isa_bus) { error_report("ISA bus not available for %s", c->name); exit(1); diff --git a/hw/core/numa.c b/hw/core/numa.c index 2725886d06..6a20ce7cf1 100644 --- a/hw/core/numa.c +++ b/hw/core/numa.c @@ -688,8 +688,9 @@ void numa_complete_configuration(MachineState *ms) NodeInfo *numa_info = ms->numa_state->nodes; /* - * If memory hotplug is enabled (slots > 0) but without '-numa' - * options explicitly on CLI, guestes will break. + * If memory hotplug is enabled (slot > 0) or memory devices are enabled + * (ms->maxram_size > ram_size) but without '-numa' options explicitly on + * CLI, guests will break. * * Windows: won't enable memory hotplug without SRAT table at all * @@ -704,9 +705,9 @@ void numa_complete_configuration(MachineState *ms) * assume there is just one node with whole RAM. */ if (ms->numa_state->num_nodes == 0 && - ((ms->ram_slots > 0 && - mc->auto_enable_numa_with_memhp) || - mc->auto_enable_numa)) { + ((ms->ram_slots && mc->auto_enable_numa_with_memhp) || + (ms->maxram_size > ms->ram_size && mc->auto_enable_numa_with_memdev) || + mc->auto_enable_numa)) { NumaNodeOptions node = { }; parse_numa_node(ms, &node, &error_abort); numa_info[0].node_mem = ram_size; @@ -824,6 +825,7 @@ static void numa_stat_memory_devices(NumaNodeMem node_mem[]) MemoryDeviceInfoList *info; PCDIMMDeviceInfo *pcdimm_info; VirtioPMEMDeviceInfo *vpi; + VirtioMEMDeviceInfo *vmi; for (info = info_list; info; info = info->next) { MemoryDeviceInfo *value = info->value; @@ -844,6 +846,11 @@ static void numa_stat_memory_devices(NumaNodeMem node_mem[]) node_mem[0].node_mem += vpi->size; node_mem[0].node_plugged_mem += vpi->size; break; + case MEMORY_DEVICE_INFO_KIND_VIRTIO_MEM: + vmi = value->u.virtio_mem.data; + node_mem[vmi->node].node_mem += vmi->size; + node_mem[vmi->node].node_plugged_mem += vmi->size; + break; default: g_assert_not_reached(); } diff --git a/hw/core/qdev-properties.c b/hw/core/qdev-properties.c index 71f8aca7c6..ca7771f307 100644 --- a/hw/core/qdev-properties.c +++ b/hw/core/qdev-properties.c @@ -15,6 +15,7 @@ #include "chardev/char.h" #include "qemu/uuid.h" #include "qemu/units.h" +#include "qemu/cutils.h" void qdev_prop_set_after_realize(DeviceState *dev, const char *name, Error **errp) @@ -578,6 +579,94 @@ const PropertyInfo qdev_prop_macaddr = { .set = set_mac, }; +/* --- Reserved Region --- */ + +/* + * Accepted syntax: + * <low address>:<high address>:<type> + * where low/high addresses are uint64_t in hexadecimal + * and type is a non-negative decimal integer + */ +static void get_reserved_region(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + DeviceState *dev = DEVICE(obj); + Property *prop = opaque; + ReservedRegion *rr = qdev_get_prop_ptr(dev, prop); + char buffer[64]; + char *p = buffer; + int rc; + + rc = snprintf(buffer, sizeof(buffer), "0x%"PRIx64":0x%"PRIx64":%u", + rr->low, rr->high, rr->type); + assert(rc < sizeof(buffer)); + + visit_type_str(v, name, &p, errp); +} + +static void set_reserved_region(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + DeviceState *dev = DEVICE(obj); + Property *prop = opaque; + ReservedRegion *rr = qdev_get_prop_ptr(dev, prop); + Error *local_err = NULL; + const char *endptr; + char *str; + int ret; + + if (dev->realized) { + qdev_prop_set_after_realize(dev, name, errp); + return; + } + + visit_type_str(v, name, &str, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + + ret = qemu_strtou64(str, &endptr, 16, &rr->low); + if (ret) { + error_setg(errp, "start address of '%s'" + " must be a hexadecimal integer", name); + goto out; + } + if (*endptr != ':') { + goto separator_error; + } + + ret = qemu_strtou64(endptr + 1, &endptr, 16, &rr->high); + if (ret) { + error_setg(errp, "end address of '%s'" + " must be a hexadecimal integer", name); + goto out; + } + if (*endptr != ':') { + goto separator_error; + } + + ret = qemu_strtoui(endptr + 1, &endptr, 10, &rr->type); + if (ret) { + error_setg(errp, "type of '%s'" + " must be a non-negative decimal integer", name); + } + goto out; + +separator_error: + error_setg(errp, "reserved region fields must be separated with ':'"); +out: + g_free(str); + return; +} + +const PropertyInfo qdev_prop_reserved_region = { + .name = "reserved_region", + .description = "Reserved Region, example: 0xFEE00000:0xFEEFFFFF:0", + .get = get_reserved_region, + .set = set_reserved_region, +}; + /* --- on/off/auto --- */ const PropertyInfo qdev_prop_on_off_auto = { diff --git a/hw/core/qdev.c b/hw/core/qdev.c index 2131c7f951..9de16eae05 100644 --- a/hw/core/qdev.c +++ b/hw/core/qdev.c @@ -137,6 +137,9 @@ void qdev_set_parent_bus(DeviceState *dev, BusState *bus) */ DeviceState *qdev_new(const char *name) { + if (!object_class_by_name(name)) { + module_load_qom_one(name); + } return DEVICE(object_new(name)); } @@ -147,10 +150,9 @@ DeviceState *qdev_new(const char *name) */ DeviceState *qdev_try_new(const char *name) { - if (!object_class_by_name(name)) { + if (!module_object_class_by_name(name)) { return NULL; } - return DEVICE(object_new(name)); } diff --git a/hw/display/Makefile.objs b/hw/display/Makefile.objs index 77a7d622bd..e907f3182b 100644 --- a/hw/display/Makefile.objs +++ b/hw/display/Makefile.objs @@ -44,18 +44,24 @@ common-obj-$(CONFIG_ARTIST) += artist.o obj-$(CONFIG_VGA) += vga.o -common-obj-$(CONFIG_QXL) += qxl.o qxl-logger.o qxl-render.o - -obj-$(CONFIG_VIRTIO_GPU) += virtio-gpu-base.o virtio-gpu.o virtio-gpu-3d.o -obj-$(CONFIG_VHOST_USER_GPU) += vhost-user-gpu.o -obj-$(call land,$(CONFIG_VIRTIO_GPU),$(CONFIG_VIRTIO_PCI)) += virtio-gpu-pci.o -obj-$(call land,$(CONFIG_VHOST_USER_GPU),$(CONFIG_VIRTIO_PCI)) += vhost-user-gpu-pci.o -obj-$(CONFIG_VIRTIO_VGA) += virtio-vga.o -obj-$(CONFIG_VHOST_USER_VGA) += vhost-user-vga.o -virtio-gpu.o-cflags := $(VIRGL_CFLAGS) -virtio-gpu.o-libs += $(VIRGL_LIBS) -virtio-gpu-3d.o-cflags := $(VIRGL_CFLAGS) -virtio-gpu-3d.o-libs += $(VIRGL_LIBS) +ifeq ($(CONFIG_QXL),y) +common-obj-m += qxl.mo +qxl.mo-objs = qxl.o qxl-logger.o qxl-render.o +endif + +ifeq ($(CONFIG_VIRTIO_GPU),y) +common-obj-m += virtio-gpu.mo +virtio-gpu-obj-$(CONFIG_VIRTIO_GPU) += virtio-gpu-base.o virtio-gpu.o virtio-gpu-3d.o +virtio-gpu-obj-$(CONFIG_VHOST_USER_GPU) += vhost-user-gpu.o +virtio-gpu-obj-$(call land,$(CONFIG_VIRTIO_GPU),$(CONFIG_VIRTIO_PCI)) += virtio-gpu-pci.o +virtio-gpu-obj-$(call land,$(CONFIG_VHOST_USER_GPU),$(CONFIG_VIRTIO_PCI)) += vhost-user-gpu-pci.o +virtio-gpu-obj-$(CONFIG_VIRTIO_VGA) += virtio-vga.o +virtio-gpu-obj-$(CONFIG_VHOST_USER_VGA) += vhost-user-vga.o +virtio-gpu.mo-objs := $(virtio-gpu-obj-y) +virtio-gpu.mo-cflags := $(VIRGL_CFLAGS) +virtio-gpu.mo-libs := $(VIRGL_LIBS) +endif + common-obj-$(CONFIG_DPCD) += dpcd.o common-obj-$(CONFIG_XLNX_ZYNQMP_ARM) += xlnx_dp.o diff --git a/hw/display/ads7846.c b/hw/display/ads7846.c index 9228b40b1a..56bf82fe07 100644 --- a/hw/display/ads7846.c +++ b/hw/display/ads7846.c @@ -29,6 +29,9 @@ typedef struct { int output; } ADS7846State; +#define TYPE_ADS7846 "ads7846" +#define ADS7846(obj) OBJECT_CHECK(ADS7846State, (obj), TYPE_ADS7846) + /* Control-byte bitfields */ #define CB_PD0 (1 << 0) #define CB_PD1 (1 << 1) @@ -61,7 +64,7 @@ static void ads7846_int_update(ADS7846State *s) static uint32_t ads7846_transfer(SSISlave *dev, uint32_t value) { - ADS7846State *s = FROM_SSI_SLAVE(ADS7846State, dev); + ADS7846State *s = ADS7846(dev); switch (s->cycle ++) { case 0: @@ -139,7 +142,7 @@ static const VMStateDescription vmstate_ads7846 = { static void ads7846_realize(SSISlave *d, Error **errp) { DeviceState *dev = DEVICE(d); - ADS7846State *s = FROM_SSI_SLAVE(ADS7846State, d); + ADS7846State *s = ADS7846(d); qdev_init_gpio_out(dev, &s->interrupt, 1); @@ -166,7 +169,7 @@ static void ads7846_class_init(ObjectClass *klass, void *data) } static const TypeInfo ads7846_info = { - .name = "ads7846", + .name = TYPE_ADS7846, .parent = TYPE_SSI_SLAVE, .instance_size = sizeof(ADS7846State), .class_init = ads7846_class_init, diff --git a/hw/display/bcm2835_fb.c b/hw/display/bcm2835_fb.c index c6263808a2..7c0e5eef2d 100644 --- a/hw/display/bcm2835_fb.c +++ b/hw/display/bcm2835_fb.c @@ -282,6 +282,10 @@ static void bcm2835_fb_mbox_push(BCM2835FBState *s, uint32_t value) newconf.base = s->vcram_base | (value & 0xc0000000); newconf.base += BCM2835_FB_OFFSET; + /* Copy fields which we don't want to change from the existing config */ + newconf.pixo = s->config.pixo; + newconf.alpha = s->config.alpha; + bcm2835_fb_validate_config(&newconf); pitch = bcm2835_fb_get_pitch(&newconf); diff --git a/hw/display/ssd0323.c b/hw/display/ssd0323.c index c3bdb18742..32d27f008a 100644 --- a/hw/display/ssd0323.c +++ b/hw/display/ssd0323.c @@ -66,9 +66,13 @@ typedef struct { uint8_t framebuffer[128 * 80 / 2]; } ssd0323_state; +#define TYPE_SSD0323 "ssd0323" +#define SSD0323(obj) OBJECT_CHECK(ssd0323_state, (obj), TYPE_SSD0323) + + static uint32_t ssd0323_transfer(SSISlave *dev, uint32_t data) { - ssd0323_state *s = FROM_SSI_SLAVE(ssd0323_state, dev); + ssd0323_state *s = SSD0323(dev); switch (s->mode) { case SSD0323_DATA: @@ -346,7 +350,7 @@ static const GraphicHwOps ssd0323_ops = { static void ssd0323_realize(SSISlave *d, Error **errp) { DeviceState *dev = DEVICE(d); - ssd0323_state *s = FROM_SSI_SLAVE(ssd0323_state, d); + ssd0323_state *s = SSD0323(d); s->col_end = 63; s->row_end = 79; @@ -368,7 +372,7 @@ static void ssd0323_class_init(ObjectClass *klass, void *data) } static const TypeInfo ssd0323_info = { - .name = "ssd0323", + .name = TYPE_SSD0323, .parent = TYPE_SSI_SLAVE, .instance_size = sizeof(ssd0323_state), .class_init = ssd0323_class_init, diff --git a/hw/gpio/zaurus.c b/hw/gpio/zaurus.c index 9a12c68342..258e926493 100644 --- a/hw/gpio/zaurus.c +++ b/hw/gpio/zaurus.c @@ -22,9 +22,7 @@ #include "hw/sysbus.h" #include "migration/vmstate.h" #include "qemu/module.h" - -#undef REG_FMT -#define REG_FMT "0x%02lx" +#include "qemu/log.h" /* SCOOP devices */ @@ -104,7 +102,9 @@ static uint64_t scoop_read(void *opaque, hwaddr addr, case SCOOP_GPRR: return s->gpio_level; default: - zaurus_printf("Bad register offset " REG_FMT "\n", (unsigned long)addr); + qemu_log_mask(LOG_GUEST_ERROR, + "scoop_read: bad register offset 0x%02" HWADDR_PRIx "\n", + addr); } return 0; @@ -150,7 +150,9 @@ static void scoop_write(void *opaque, hwaddr addr, scoop_gpio_handler_update(s); break; default: - zaurus_printf("Bad register offset " REG_FMT "\n", (unsigned long)addr); + qemu_log_mask(LOG_GUEST_ERROR, + "scoop_write: bad register offset 0x%02" HWADDR_PRIx "\n", + addr); } } diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig index c93f32f657..03e347b207 100644 --- a/hw/i386/Kconfig +++ b/hw/i386/Kconfig @@ -35,6 +35,7 @@ config PC select ACPI_PCI select ACPI_VMGENID select VIRTIO_PMEM_SUPPORTED + select VIRTIO_MEM_SUPPORTED config PC_PCI bool diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index df7ad254ac..c56398e991 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -3758,7 +3758,7 @@ static bool vtd_decide_config(IntelIOMMUState *s, Error **errp) /* Currently only address widths supported are 39 and 48 bits */ if ((s->aw_bits != VTD_HOST_AW_39BIT) && (s->aw_bits != VTD_HOST_AW_48BIT)) { - error_setg(errp, "Supported values for x-aw-bits are: %d, %d", + error_setg(errp, "Supported values for aw-bits are: %d, %d", VTD_HOST_AW_39BIT, VTD_HOST_AW_48BIT); return false; } diff --git a/hw/i386/microvm.c b/hw/i386/microvm.c index 5e931975a0..81d0888930 100644 --- a/hw/i386/microvm.c +++ b/hw/i386/microvm.c @@ -464,6 +464,7 @@ static void microvm_class_init(ObjectClass *oc, void *data) mc->max_cpus = 288; mc->has_hotpluggable_cpus = false; mc->auto_enable_numa_with_memhp = false; + mc->auto_enable_numa_with_memdev = false; mc->default_cpu_type = TARGET_DEFAULT_CPU_TYPE; mc->nvdimm_supported = false; mc->default_ram_id = "microvm.ram"; diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 4af9679d03..d7f27bc16b 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -88,6 +88,7 @@ #include "hw/net/ne2000-isa.h" #include "standard-headers/asm-x86/bootparam.h" #include "hw/virtio/virtio-pmem-pci.h" +#include "hw/virtio/virtio-mem-pci.h" #include "hw/mem/memory-device.h" #include "sysemu/replay.h" #include "qapi/qmp/qerror.h" @@ -1155,11 +1156,10 @@ static void pc_superio_init(ISABus *isa_bus, bool create_fdctrl, bool no_vmport) g_free(a20_line); } -void pc_basic_device_init(ISABus *isa_bus, qemu_irq *gsi, +void pc_basic_device_init(struct PCMachineState *pcms, + ISABus *isa_bus, qemu_irq *gsi, ISADevice **rtc_state, bool create_fdctrl, - bool no_vmport, - bool has_pit, uint32_t hpet_irqs) { int i; @@ -1210,7 +1210,7 @@ void pc_basic_device_init(ISABus *isa_bus, qemu_irq *gsi, qemu_register_boot_set(pc_boot_set, *rtc_state); - if (!xen_enabled() && has_pit) { + if (!xen_enabled() && pcms->pit_enabled) { if (kvm_pit_in_kernel()) { pit = kvm_pit_init(isa_bus, 0x40); } else { @@ -1220,13 +1220,13 @@ void pc_basic_device_init(ISABus *isa_bus, qemu_irq *gsi, /* connect PIT to output control line of the HPET */ qdev_connect_gpio_out(hpet, 0, qdev_get_gpio_in(DEVICE(pit), 0)); } - pcspk_init(isa_bus, pit); + pcspk_init(pcms->pcspk, isa_bus, pit); } i8257_dma_init(isa_bus, 0); /* Super I/O */ - pc_superio_init(isa_bus, create_fdctrl, no_vmport); + pc_superio_init(isa_bus, create_fdctrl, pcms->vmport != ON_OFF_AUTO_ON); } void pc_nic_init(PCMachineClass *pcmc, ISABus *isa_bus, PCIBus *pci_bus) @@ -1637,19 +1637,20 @@ static void pc_cpu_pre_plug(HotplugHandler *hotplug_dev, numa_cpu_pre_plug(cpu_slot, dev, errp); } -static void pc_virtio_pmem_pci_pre_plug(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) +static void pc_virtio_md_pci_pre_plug(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) { HotplugHandler *hotplug_dev2 = qdev_get_bus_hotplug_handler(dev); Error *local_err = NULL; - if (!hotplug_dev2) { + if (!hotplug_dev2 && dev->hotplugged) { /* * Without a bus hotplug handler, we cannot control the plug/unplug - * order. This should never be the case on x86, however better add - * a safety net. + * order. We should never reach this point when hotplugging on x86, + * however, better add a safety net. */ - error_setg(errp, "virtio-pmem-pci not supported on this bus."); + error_setg(errp, "hotplug of virtio based memory devices not supported" + " on this bus."); return; } /* @@ -1658,14 +1659,14 @@ static void pc_virtio_pmem_pci_pre_plug(HotplugHandler *hotplug_dev, */ memory_device_pre_plug(MEMORY_DEVICE(dev), MACHINE(hotplug_dev), NULL, &local_err); - if (!local_err) { + if (!local_err && hotplug_dev2) { hotplug_handler_pre_plug(hotplug_dev2, dev, &local_err); } error_propagate(errp, local_err); } -static void pc_virtio_pmem_pci_plug(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) +static void pc_virtio_md_pci_plug(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) { HotplugHandler *hotplug_dev2 = qdev_get_bus_hotplug_handler(dev); Error *local_err = NULL; @@ -1676,24 +1677,26 @@ static void pc_virtio_pmem_pci_plug(HotplugHandler *hotplug_dev, * device bits. */ memory_device_plug(MEMORY_DEVICE(dev), MACHINE(hotplug_dev)); - hotplug_handler_plug(hotplug_dev2, dev, &local_err); - if (local_err) { - memory_device_unplug(MEMORY_DEVICE(dev), MACHINE(hotplug_dev)); + if (hotplug_dev2) { + hotplug_handler_plug(hotplug_dev2, dev, &local_err); + if (local_err) { + memory_device_unplug(MEMORY_DEVICE(dev), MACHINE(hotplug_dev)); + } } error_propagate(errp, local_err); } -static void pc_virtio_pmem_pci_unplug_request(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) +static void pc_virtio_md_pci_unplug_request(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) { - /* We don't support virtio pmem hot unplug */ - error_setg(errp, "virtio pmem device unplug not supported."); + /* We don't support hot unplug of virtio based memory devices */ + error_setg(errp, "virtio based memory devices cannot be unplugged."); } -static void pc_virtio_pmem_pci_unplug(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) +static void pc_virtio_md_pci_unplug(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) { - /* We don't support virtio pmem hot unplug */ + /* We don't support hot unplug of virtio based memory devices */ } static void pc_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev, @@ -1703,8 +1706,9 @@ static void pc_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev, pc_memory_pre_plug(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { pc_cpu_pre_plug(hotplug_dev, dev, errp); - } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) { - pc_virtio_pmem_pci_pre_plug(hotplug_dev, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { + pc_virtio_md_pci_pre_plug(hotplug_dev, dev, errp); } } @@ -1715,8 +1719,9 @@ static void pc_machine_device_plug_cb(HotplugHandler *hotplug_dev, pc_memory_plug(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { pc_cpu_plug(hotplug_dev, dev, errp); - } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) { - pc_virtio_pmem_pci_plug(hotplug_dev, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { + pc_virtio_md_pci_plug(hotplug_dev, dev, errp); } } @@ -1727,8 +1732,9 @@ static void pc_machine_device_unplug_request_cb(HotplugHandler *hotplug_dev, pc_memory_unplug_request(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { pc_cpu_unplug_request_cb(hotplug_dev, dev, errp); - } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) { - pc_virtio_pmem_pci_unplug_request(hotplug_dev, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { + pc_virtio_md_pci_unplug_request(hotplug_dev, dev, errp); } else { error_setg(errp, "acpi: device unplug request for not supported device" " type: %s", object_get_typename(OBJECT(dev))); @@ -1742,8 +1748,9 @@ static void pc_machine_device_unplug_cb(HotplugHandler *hotplug_dev, pc_memory_unplug(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { pc_cpu_unplug_cb(hotplug_dev, dev, errp); - } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) { - pc_virtio_pmem_pci_unplug(hotplug_dev, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { + pc_virtio_md_pci_unplug(hotplug_dev, dev, errp); } else { error_setg(errp, "acpi: device unplug for not supported device" " type: %s", object_get_typename(OBJECT(dev))); @@ -1755,7 +1762,8 @@ static HotplugHandler *pc_get_hotplug_handler(MachineState *machine, { if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) || object_dynamic_cast(OBJECT(dev), TYPE_CPU) || - object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) { + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { return HOTPLUG_HANDLER(machine); } @@ -1892,6 +1900,9 @@ static void pc_machine_initfn(Object *obj) pcms->pit_enabled = true; pc_system_flash_create(pcms); + pcms->pcspk = isa_new(TYPE_PC_SPEAKER); + object_property_add_alias(OBJECT(pcms), "pcspk-audiodev", + OBJECT(pcms->pcspk), "audiodev"); } static void pc_machine_reset(MachineState *machine) @@ -1966,6 +1977,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data) mc->get_default_cpu_node_id = x86_get_default_cpu_node_id; mc->possible_cpu_arch_ids = x86_possible_cpu_arch_ids; mc->auto_enable_numa_with_memhp = true; + mc->auto_enable_numa_with_memdev = true; mc->has_hotpluggable_cpus = true; mc->default_boot_order = "cad"; mc->hot_add_cpu = pc_hot_add_cpu; diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 1d832b2878..2bb42a8141 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -235,8 +235,7 @@ static void pc_init1(MachineState *machine, } /* init basic PC hardware */ - pc_basic_device_init(isa_bus, x86ms->gsi, &rtc_state, true, - (pcms->vmport != ON_OFF_AUTO_ON), pcms->pit_enabled, + pc_basic_device_init(pcms, isa_bus, x86ms->gsi, &rtc_state, true, 0x4); pc_nic_init(pcmc, isa_bus, pci_bus); @@ -444,6 +443,7 @@ static void pc_i440fx_5_0_machine_options(MachineClass *m) m->numa_mem_supported = true; compat_props_add(m->compat_props, hw_compat_5_0, hw_compat_5_0_len); compat_props_add(m->compat_props, pc_compat_5_0, pc_compat_5_0_len); + m->auto_enable_numa_with_memdev = false; } DEFINE_I440FX_MACHINE(v5_0, "pc-i440fx-5.0", NULL, diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index 047ea8db28..33163ed18d 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -275,8 +275,7 @@ static void pc_q35_init(MachineState *machine) } /* init basic PC hardware */ - pc_basic_device_init(isa_bus, x86ms->gsi, &rtc_state, !mc->no_floppy, - (pcms->vmport != ON_OFF_AUTO_ON), pcms->pit_enabled, + pc_basic_device_init(pcms, isa_bus, x86ms->gsi, &rtc_state, !mc->no_floppy, 0xff0104); /* connect pm stuff to lpc */ @@ -372,6 +371,7 @@ static void pc_q35_5_0_machine_options(MachineClass *m) m->numa_mem_supported = true; compat_props_add(m->compat_props, hw_compat_5_0, hw_compat_5_0_len); compat_props_add(m->compat_props, pc_compat_5_0, pc_compat_5_0_len); + m->auto_enable_numa_with_memhp = false; } DEFINE_Q35_MACHINE(v5_0, "pc-q35-5.0", NULL, diff --git a/hw/isa/i82378.c b/hw/isa/i82378.c index d9e6c7fa00..75a2da2881 100644 --- a/hw/isa/i82378.c +++ b/hw/isa/i82378.c @@ -102,7 +102,7 @@ static void i82378_realize(PCIDevice *pci, Error **errp) pit = i8254_pit_init(isabus, 0x40, 0, NULL); /* speaker */ - pcspk_init(isabus, pit); + pcspk_init(isa_new(TYPE_PC_SPEAKER), isabus, pit); /* 2 82C37 (dma) */ isa_create_simple(isabus, "i82374"); diff --git a/hw/m68k/mcf5206.c b/hw/m68k/mcf5206.c index a2fef04f8e..94a37a1a46 100644 --- a/hw/m68k/mcf5206.c +++ b/hw/m68k/mcf5206.c @@ -10,7 +10,6 @@ #include "qemu/error-report.h" #include "qemu/log.h" #include "cpu.h" -#include "hw/hw.h" #include "hw/irq.h" #include "hw/m68k/mcf.h" #include "qemu/timer.h" @@ -69,10 +68,16 @@ static void m5206_timer_recalibrate(m5206_timer_state *s) if (mode == 2) prescale *= 16; - if (mode == 3 || mode == 0) - hw_error("m5206_timer: mode %d not implemented\n", mode); - if ((s->tmr & TMR_FRR) == 0) - hw_error("m5206_timer: free running mode not implemented\n"); + if (mode == 3 || mode == 0) { + qemu_log_mask(LOG_UNIMP, "m5206_timer: mode %d not implemented\n", + mode); + goto exit; + } + if ((s->tmr & TMR_FRR) == 0) { + qemu_log_mask(LOG_UNIMP, + "m5206_timer: free running mode not implemented\n"); + goto exit; + } /* Assume 66MHz system clock. */ ptimer_set_freq(s->timer, 66000000 / prescale); @@ -391,7 +396,9 @@ static uint32_t m5206_mbar_readb(void *opaque, hwaddr offset) m5206_mbar_state *s = (m5206_mbar_state *)opaque; offset &= 0x3ff; if (offset >= 0x200) { - hw_error("Bad MBAR read offset 0x%x", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, "Bad MBAR read offset 0x%" HWADDR_PRIX, + offset); + return 0; } if (m5206_mbar_width[offset >> 2] > 1) { uint16_t val; @@ -410,7 +417,9 @@ static uint32_t m5206_mbar_readw(void *opaque, hwaddr offset) int width; offset &= 0x3ff; if (offset >= 0x200) { - hw_error("Bad MBAR read offset 0x%x", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, "Bad MBAR read offset 0x%" HWADDR_PRIX, + offset); + return 0; } width = m5206_mbar_width[offset >> 2]; if (width > 2) { @@ -434,7 +443,9 @@ static uint32_t m5206_mbar_readl(void *opaque, hwaddr offset) int width; offset &= 0x3ff; if (offset >= 0x200) { - hw_error("Bad MBAR read offset 0x%x", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, "Bad MBAR read offset 0x%" HWADDR_PRIX, + offset); + return 0; } width = m5206_mbar_width[offset >> 2]; if (width < 4) { @@ -458,7 +469,9 @@ static void m5206_mbar_writeb(void *opaque, hwaddr offset, int width; offset &= 0x3ff; if (offset >= 0x200) { - hw_error("Bad MBAR write offset 0x%x", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, "Bad MBAR write offset 0x%" HWADDR_PRIX, + offset); + return; } width = m5206_mbar_width[offset >> 2]; if (width > 1) { @@ -482,7 +495,9 @@ static void m5206_mbar_writew(void *opaque, hwaddr offset, int width; offset &= 0x3ff; if (offset >= 0x200) { - hw_error("Bad MBAR write offset 0x%x", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, "Bad MBAR write offset 0x%" HWADDR_PRIX, + offset); + return; } width = m5206_mbar_width[offset >> 2]; if (width > 2) { @@ -510,7 +525,9 @@ static void m5206_mbar_writel(void *opaque, hwaddr offset, int width; offset &= 0x3ff; if (offset >= 0x200) { - hw_error("Bad MBAR write offset 0x%x", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, "Bad MBAR write offset 0x%" HWADDR_PRIX, + offset); + return; } width = m5206_mbar_width[offset >> 2]; if (width < 4) { diff --git a/hw/mips/jazz.c b/hw/mips/jazz.c index c3b0da60cc..0002bff695 100644 --- a/hw/mips/jazz.c +++ b/hw/mips/jazz.c @@ -250,7 +250,7 @@ static void mips_jazz_init(MachineState *machine, isa_bus_irqs(isa_bus, i8259); i8257_dma_init(isa_bus, 0); pit = i8254_pit_init(isa_bus, 0x40, 0, NULL); - pcspk_init(isa_bus, pit); + pcspk_init(isa_new(TYPE_PC_SPEAKER), isa_bus, pit); /* Video card */ switch (jazz_model) { diff --git a/hw/misc/max111x.c b/hw/misc/max111x.c index 2b87bdee5b..7e6723f343 100644 --- a/hw/misc/max111x.c +++ b/hw/misc/max111x.c @@ -11,29 +11,11 @@ */ #include "qemu/osdep.h" +#include "hw/misc/max111x.h" #include "hw/irq.h" -#include "hw/ssi/ssi.h" #include "migration/vmstate.h" #include "qemu/module.h" - -typedef struct { - SSISlave parent_obj; - - qemu_irq interrupt; - uint8_t tb1, rb2, rb3; - int cycle; - - uint8_t input[8]; - int inputs, com; -} MAX111xState; - -#define TYPE_MAX_111X "max111x" - -#define MAX_111X(obj) \ - OBJECT_CHECK(MAX111xState, (obj), TYPE_MAX_111X) - -#define TYPE_MAX_1110 "max1110" -#define TYPE_MAX_1111 "max1111" +#include "hw/qdev-properties.h" /* Control-byte bitfields */ #define CB_PD0 (1 << 0) @@ -127,27 +109,24 @@ static const VMStateDescription vmstate_max111x = { } }; +static void max111x_input_set(void *opaque, int line, int value) +{ + MAX111xState *s = MAX_111X(opaque); + + assert(line >= 0 && line < s->inputs); + s->input[line] = value; +} + static int max111x_init(SSISlave *d, int inputs) { DeviceState *dev = DEVICE(d); MAX111xState *s = MAX_111X(dev); qdev_init_gpio_out(dev, &s->interrupt, 1); + qdev_init_gpio_in(dev, max111x_input_set, inputs); s->inputs = inputs; - /* TODO: add a user interface for setting these */ - s->input[0] = 0xf0; - s->input[1] = 0xe0; - s->input[2] = 0xd0; - s->input[3] = 0xc0; - s->input[4] = 0xb0; - s->input[5] = 0xa0; - s->input[6] = 0x90; - s->input[7] = 0x80; - s->com = 0; - vmstate_register(VMSTATE_IF(dev), VMSTATE_INSTANCE_ID_ANY, - &vmstate_max111x, s); return 0; } @@ -161,18 +140,51 @@ static void max1111_realize(SSISlave *dev, Error **errp) max111x_init(dev, 4); } -void max111x_set_input(DeviceState *dev, int line, uint8_t value) +static void max111x_reset(DeviceState *dev) { MAX111xState *s = MAX_111X(dev); - assert(line >= 0 && line < s->inputs); - s->input[line] = value; + int i; + + for (i = 0; i < s->inputs; i++) { + s->input[i] = s->reset_input[i]; + } + s->com = 0; + s->tb1 = 0; + s->rb2 = 0; + s->rb3 = 0; + s->cycle = 0; } +static Property max1110_properties[] = { + /* Reset values for ADC inputs */ + DEFINE_PROP_UINT8("input0", MAX111xState, reset_input[0], 0xf0), + DEFINE_PROP_UINT8("input1", MAX111xState, reset_input[1], 0xe0), + DEFINE_PROP_UINT8("input2", MAX111xState, reset_input[2], 0xd0), + DEFINE_PROP_UINT8("input3", MAX111xState, reset_input[3], 0xc0), + DEFINE_PROP_END_OF_LIST(), +}; + +static Property max1111_properties[] = { + /* Reset values for ADC inputs */ + DEFINE_PROP_UINT8("input0", MAX111xState, reset_input[0], 0xf0), + DEFINE_PROP_UINT8("input1", MAX111xState, reset_input[1], 0xe0), + DEFINE_PROP_UINT8("input2", MAX111xState, reset_input[2], 0xd0), + DEFINE_PROP_UINT8("input3", MAX111xState, reset_input[3], 0xc0), + DEFINE_PROP_UINT8("input4", MAX111xState, reset_input[4], 0xb0), + DEFINE_PROP_UINT8("input5", MAX111xState, reset_input[5], 0xa0), + DEFINE_PROP_UINT8("input6", MAX111xState, reset_input[6], 0x90), + DEFINE_PROP_UINT8("input7", MAX111xState, reset_input[7], 0x80), + DEFINE_PROP_END_OF_LIST(), +}; + static void max111x_class_init(ObjectClass *klass, void *data) { SSISlaveClass *k = SSI_SLAVE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); k->transfer = max111x_transfer; + dc->reset = max111x_reset; + dc->vmsd = &vmstate_max111x; } static const TypeInfo max111x_info = { @@ -186,8 +198,10 @@ static const TypeInfo max111x_info = { static void max1110_class_init(ObjectClass *klass, void *data) { SSISlaveClass *k = SSI_SLAVE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); k->realize = max1110_realize; + device_class_set_props(dc, max1110_properties); } static const TypeInfo max1110_info = { @@ -199,8 +213,10 @@ static const TypeInfo max1110_info = { static void max1111_class_init(ObjectClass *klass, void *data) { SSISlaveClass *k = SSI_SLAVE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); k->realize = max1111_realize; + device_class_set_props(dc, max1111_properties); } static const TypeInfo max1111_info = { diff --git a/hw/net/imx_fec.c b/hw/net/imx_fec.c index eefedc252d..2c14804041 100644 --- a/hw/net/imx_fec.c +++ b/hw/net/imx_fec.c @@ -280,12 +280,16 @@ static void imx_phy_reset(IMXFECState *s) static uint32_t imx_phy_read(IMXFECState *s, int reg) { uint32_t val; + uint32_t phy = reg / 32; - if (reg > 31) { - /* we only advertise one phy */ + if (phy != s->phy_num) { + qemu_log_mask(LOG_GUEST_ERROR, "[%s.phy]%s: Bad phy num %u\n", + TYPE_IMX_FEC, __func__, phy); return 0; } + reg %= 32; + switch (reg) { case 0: /* Basic Control */ val = s->phy_control; @@ -331,20 +335,25 @@ static uint32_t imx_phy_read(IMXFECState *s, int reg) break; } - trace_imx_phy_read(val, reg); + trace_imx_phy_read(val, phy, reg); return val; } static void imx_phy_write(IMXFECState *s, int reg, uint32_t val) { - trace_imx_phy_write(val, reg); + uint32_t phy = reg / 32; - if (reg > 31) { - /* we only advertise one phy */ + if (phy != s->phy_num) { + qemu_log_mask(LOG_GUEST_ERROR, "[%s.phy]%s: Bad phy num %u\n", + TYPE_IMX_FEC, __func__, phy); return; } + reg %= 32; + + trace_imx_phy_write(val, phy, reg); + switch (reg) { case 0: /* Basic Control */ if (val & 0x8000) { @@ -926,7 +935,7 @@ static void imx_eth_write(void *opaque, hwaddr offset, uint64_t value, extract32(value, 18, 10))); } else { - /* This a write operation */ + /* This is a write operation */ imx_phy_write(s, extract32(value, 18, 10), extract32(value, 0, 16)); } /* raise the interrupt as the PHY operation is done */ @@ -1315,6 +1324,7 @@ static void imx_eth_realize(DeviceState *dev, Error **errp) static Property imx_eth_properties[] = { DEFINE_NIC_PROPERTIES(IMXFECState, conf), DEFINE_PROP_UINT32("tx-ring-num", IMXFECState, tx_ring_num, 1), + DEFINE_PROP_UINT32("phy-num", IMXFECState, phy_num, 0), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/net/trace-events b/hw/net/trace-events index e6875c4c0f..5db45456d9 100644 --- a/hw/net/trace-events +++ b/hw/net/trace-events @@ -413,8 +413,8 @@ i82596_set_multicast(uint16_t count) "Added %d multicast entries" i82596_channel_attention(void *s) "%p: Received CHANNEL ATTENTION" # imx_fec.c -imx_phy_read(uint32_t val, int reg) "0x%04"PRIx32" <= reg[%d]" -imx_phy_write(uint32_t val, int reg) "0x%04"PRIx32" => reg[%d]" +imx_phy_read(uint32_t val, int phy, int reg) "0x%04"PRIx32" <= phy[%d].reg[%d]" +imx_phy_write(uint32_t val, int phy, int reg) "0x%04"PRIx32" => phy[%d].reg[%d]" imx_phy_update_link(const char *s) "%s" imx_phy_reset(void) "" imx_fec_read_bd(uint64_t addr, int flags, int len, int data) "tx_bd 0x%"PRIx64" flags 0x%04x len %d data 0x%08x" diff --git a/hw/net/vhost_net-stub.c b/hw/net/vhost_net-stub.c index aac0e98228..a7f4252630 100644 --- a/hw/net/vhost_net-stub.c +++ b/hw/net/vhost_net-stub.c @@ -52,6 +52,17 @@ uint64_t vhost_net_get_features(struct vhost_net *net, uint64_t features) return features; } +int vhost_net_get_config(struct vhost_net *net, uint8_t *config, + uint32_t config_len) +{ + return 0; +} +int vhost_net_set_config(struct vhost_net *net, const uint8_t *data, + uint32_t offset, uint32_t size, uint32_t flags) +{ + return 0; +} + void vhost_net_ack_features(struct vhost_net *net, uint64_t features) { } diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index 6b82803fa7..24d555e764 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -17,6 +17,7 @@ #include "net/net.h" #include "net/tap.h" #include "net/vhost-user.h" +#include "net/vhost-vdpa.h" #include "standard-headers/linux/vhost_types.h" #include "hw/virtio/virtio-net.h" @@ -33,12 +34,6 @@ #include "hw/virtio/vhost.h" #include "hw/virtio/virtio-bus.h" -struct vhost_net { - struct vhost_dev dev; - struct vhost_virtqueue vqs[2]; - int backend; - NetClientState *nc; -}; /* Features supported by host kernel. */ static const int kernel_feature_bits[] = { @@ -96,6 +91,11 @@ static const int *vhost_net_get_feature_bits(struct vhost_net *net) case NET_CLIENT_DRIVER_VHOST_USER: feature_bits = user_feature_bits; break; +#ifdef CONFIG_VHOST_NET_VDPA + case NET_CLIENT_DRIVER_VHOST_VDPA: + feature_bits = vdpa_feature_bits; + break; +#endif default: error_report("Feature bits not defined for this type: %d", net->nc->info->type); @@ -110,6 +110,16 @@ uint64_t vhost_net_get_features(struct vhost_net *net, uint64_t features) return vhost_get_features(&net->dev, vhost_net_get_feature_bits(net), features); } +int vhost_net_get_config(struct vhost_net *net, uint8_t *config, + uint32_t config_len) +{ + return vhost_dev_get_config(&net->dev, config, config_len); +} +int vhost_net_set_config(struct vhost_net *net, const uint8_t *data, + uint32_t offset, uint32_t size, uint32_t flags) +{ + return vhost_dev_set_config(&net->dev, data, offset, size, flags); +} void vhost_net_ack_features(struct vhost_net *net, uint64_t features) { @@ -306,7 +316,9 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(dev))); VirtioBusState *vbus = VIRTIO_BUS(qbus); VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus); + struct vhost_net *net; int r, e, i; + NetClientState *peer; if (!k->set_guest_notifiers) { error_report("binding does not support guest notifiers"); @@ -314,9 +326,9 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, } for (i = 0; i < total_queues; i++) { - struct vhost_net *net; - net = get_vhost_net(ncs[i].peer); + peer = qemu_get_peer(ncs, i); + net = get_vhost_net(peer); vhost_net_set_vq_index(net, i * 2); /* Suppress the masking guest notifiers on vhost user @@ -335,15 +347,16 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, } for (i = 0; i < total_queues; i++) { - r = vhost_net_start_one(get_vhost_net(ncs[i].peer), dev); + peer = qemu_get_peer(ncs, i); + r = vhost_net_start_one(get_vhost_net(peer), dev); if (r < 0) { goto err_start; } - if (ncs[i].peer->vring_enable) { + if (peer->vring_enable) { /* restore vring enable state */ - r = vhost_set_vring_enable(ncs[i].peer, ncs[i].peer->vring_enable); + r = vhost_set_vring_enable(peer, peer->vring_enable); if (r < 0) { goto err_start; @@ -355,7 +368,8 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, err_start: while (--i >= 0) { - vhost_net_stop_one(get_vhost_net(ncs[i].peer), dev); + peer = qemu_get_peer(ncs , i); + vhost_net_stop_one(get_vhost_net(peer), dev); } e = k->set_guest_notifiers(qbus->parent, total_queues * 2, false); if (e < 0) { @@ -430,6 +444,12 @@ VHostNetState *get_vhost_net(NetClientState *nc) assert(vhost_net); break; #endif +#ifdef CONFIG_VHOST_NET_VDPA + case NET_CLIENT_DRIVER_VHOST_VDPA: + vhost_net = vhost_vdpa_get_vhost_net(nc); + assert(vhost_net); + break; +#endif default: break; } diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 9bb5578e5d..1596cb1397 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -43,6 +43,7 @@ #include "monitor/qdev.h" #include "hw/pci/pci.h" #include "net_rx_pkt.h" +#include "hw/virtio/vhost.h" #define VIRTIO_NET_VM_VERSION 11 @@ -125,6 +126,8 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) VirtIONet *n = VIRTIO_NET(vdev); struct virtio_net_config netcfg; + int ret = 0; + memset(&netcfg, 0 , sizeof(struct virtio_net_config)); virtio_stw_p(vdev, &netcfg.status, n->status); virtio_stw_p(vdev, &netcfg.max_virtqueue_pairs, n->max_queues); virtio_stw_p(vdev, &netcfg.mtu, n->net_conf.mtu); @@ -138,6 +141,15 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) virtio_stl_p(vdev, &netcfg.supported_hash_types, VIRTIO_NET_RSS_SUPPORTED_HASHES); memcpy(config, &netcfg, n->config_size); + + NetClientState *nc = qemu_get_queue(n->nic); + if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) { + ret = vhost_net_get_config(get_vhost_net(nc->peer), (uint8_t *)&netcfg, + n->config_size); + if (ret != -1) { + memcpy(config, &netcfg, n->config_size); + } + } } static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config) @@ -153,6 +165,13 @@ static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config) memcpy(n->mac, netcfg.mac, ETH_ALEN); qemu_format_nic_info_str(qemu_get_queue(n->nic), n->mac); } + + NetClientState *nc = qemu_get_queue(n->nic); + if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) { + vhost_net_set_config(get_vhost_net(nc->peer), (uint8_t *)&netcfg, + 0, n->config_size, + VHOST_SET_CONFIG_TYPE_MASTER); + } } static bool virtio_net_started(VirtIONet *n, uint8_t status) diff --git a/hw/riscv/sifive_clint.c b/hw/riscv/sifive_clint.c index b11ffa0edc..669c21adc2 100644 --- a/hw/riscv/sifive_clint.c +++ b/hw/riscv/sifive_clint.c @@ -181,7 +181,7 @@ static const MemoryRegionOps sifive_clint_ops = { .endianness = DEVICE_LITTLE_ENDIAN, .valid = { .min_access_size = 4, - .max_access_size = 4 + .max_access_size = 8 } }; diff --git a/hw/riscv/sifive_plic.c b/hw/riscv/sifive_plic.c index 4f216c5585..c20c192034 100644 --- a/hw/riscv/sifive_plic.c +++ b/hw/riscv/sifive_plic.c @@ -166,6 +166,9 @@ static void sifive_plic_update(SiFivePLICState *plic) static uint32_t sifive_plic_claim(SiFivePLICState *plic, uint32_t addrid) { int i, j; + uint32_t max_irq = 0; + uint32_t max_prio = plic->target_priority[addrid]; + for (i = 0; i < plic->bitfield_words; i++) { uint32_t pending_enabled_not_claimed = (plic->pending[i] & ~plic->claimed[i]) & @@ -177,14 +180,18 @@ static uint32_t sifive_plic_claim(SiFivePLICState *plic, uint32_t addrid) int irq = (i << 5) + j; uint32_t prio = plic->source_priority[irq]; int enabled = pending_enabled_not_claimed & (1 << j); - if (enabled && prio > plic->target_priority[addrid]) { - sifive_plic_set_pending(plic, irq, false); - sifive_plic_set_claimed(plic, irq, true); - return irq; + if (enabled && prio > max_prio) { + max_irq = irq; + max_prio = prio; } } } - return 0; + + if (max_irq) { + sifive_plic_set_pending(plic, max_irq, false); + sifive_plic_set_claimed(plic, max_irq, true); + } + return max_irq; } static uint64_t sifive_plic_read(void *opaque, hwaddr addr, unsigned size) @@ -248,8 +255,8 @@ static uint64_t sifive_plic_read(void *opaque, hwaddr addr, unsigned size) plic->addr_config[addrid].hartid, mode_to_char(plic->addr_config[addrid].mode), value); - sifive_plic_print_state(plic); } + sifive_plic_update(plic); return value; } } @@ -280,6 +287,7 @@ static void sifive_plic_write(void *opaque, hwaddr addr, uint64_t value, qemu_log("plic: write priority: irq=%d priority=%d\n", irq, plic->source_priority[irq]); } + sifive_plic_update(plic); return; } else if (addr >= plic->pending_base && /* 1 bit per source */ addr < plic->pending_base + (plic->num_sources >> 3)) diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c index 142e52a8ff..736965c928 100644 --- a/hw/s390x/s390-pci-bus.c +++ b/hw/s390x/s390-pci-bus.c @@ -637,22 +637,24 @@ static AddressSpace *s390_pci_dma_iommu(PCIBus *bus, void *opaque, int devfn) static uint8_t set_ind_atomic(uint64_t ind_loc, uint8_t to_be_set) { - uint8_t ind_old, ind_new; + uint8_t expected, actual; hwaddr len = 1; - uint8_t *ind_addr; + /* avoid multiple fetches */ + uint8_t volatile *ind_addr; ind_addr = cpu_physical_memory_map(ind_loc, &len, true); if (!ind_addr) { s390_pci_generate_error_event(ERR_EVENT_AIRERR, 0, 0, 0, 0); return -1; } + actual = *ind_addr; do { - ind_old = *ind_addr; - ind_new = ind_old | to_be_set; - } while (atomic_cmpxchg(ind_addr, ind_old, ind_new) != ind_old); - cpu_physical_memory_unmap(ind_addr, len, 1, len); + expected = actual; + actual = atomic_cmpxchg(ind_addr, expected, expected | to_be_set); + } while (actual != expected); + cpu_physical_memory_unmap((void *)ind_addr, len, 1, len); - return ind_old; + return actual; } static void s390_msi_ctrl_write(void *opaque, hwaddr addr, uint64_t data, diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index b111406d56..023fd25f2b 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -43,7 +43,6 @@ #include "hw/qdev-properties.h" #include "hw/s390x/tod.h" #include "sysemu/sysemu.h" -#include "sysemu/balloon.h" #include "hw/s390x/pv.h" #include "migration/blocker.h" @@ -329,7 +328,7 @@ static void s390_machine_unprotect(S390CcwMachineState *ms) ms->pv = false; migrate_del_blocker(pv_mig_blocker); error_free_or_abort(&pv_mig_blocker); - qemu_balloon_inhibit(false); + ram_block_discard_disable(false); } static int s390_machine_protect(S390CcwMachineState *ms) @@ -338,17 +337,22 @@ static int s390_machine_protect(S390CcwMachineState *ms) int rc; /* - * Ballooning on protected VMs needs support in the guest for - * sharing and unsharing balloon pages. Block ballooning for - * now, until we have a solution to make at least Linux guests - * either support it or fail gracefully. + * Discarding of memory in RAM blocks does not work as expected with + * protected VMs. Sharing and unsharing pages would be required. Disable + * it for now, until until we have a solution to make at least Linux + * guests either support it (e.g., virtio-balloon) or fail gracefully. */ - qemu_balloon_inhibit(true); + rc = ram_block_discard_disable(true); + if (rc) { + error_report("protected VMs: cannot disable RAM discard"); + return rc; + } + error_setg(&pv_mig_blocker, "protected VMs are currently not migrateable."); rc = migrate_add_blocker(pv_mig_blocker, &local_err); if (rc) { - qemu_balloon_inhibit(false); + ram_block_discard_disable(false); error_report_err(local_err); error_free_or_abort(&pv_mig_blocker); return rc; @@ -357,7 +361,7 @@ static int s390_machine_protect(S390CcwMachineState *ms) /* Create SE VM */ rc = s390_pv_vm_enable(); if (rc) { - qemu_balloon_inhibit(false); + ram_block_discard_disable(false); migrate_del_blocker(pv_mig_blocker); error_free_or_abort(&pv_mig_blocker); return rc; diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c index c1f4bb1d33..3c988a000b 100644 --- a/hw/s390x/virtio-ccw.c +++ b/hw/s390x/virtio-ccw.c @@ -786,9 +786,10 @@ static inline VirtioCcwDevice *to_virtio_ccw_dev_fast(DeviceState *d) static uint8_t virtio_set_ind_atomic(SubchDev *sch, uint64_t ind_loc, uint8_t to_be_set) { - uint8_t ind_old, ind_new; + uint8_t expected, actual; hwaddr len = 1; - uint8_t *ind_addr; + /* avoid multiple fetches */ + uint8_t volatile *ind_addr; ind_addr = cpu_physical_memory_map(ind_loc, &len, true); if (!ind_addr) { @@ -796,14 +797,15 @@ static uint8_t virtio_set_ind_atomic(SubchDev *sch, uint64_t ind_loc, __func__, sch->cssid, sch->ssid, sch->schid); return -1; } + actual = *ind_addr; do { - ind_old = *ind_addr; - ind_new = ind_old | to_be_set; - } while (atomic_cmpxchg(ind_addr, ind_old, ind_new) != ind_old); - trace_virtio_ccw_set_ind(ind_loc, ind_old, ind_new); - cpu_physical_memory_unmap(ind_addr, len, 1, len); + expected = actual; + actual = atomic_cmpxchg(ind_addr, expected, expected | to_be_set); + } while (actual != expected); + trace_virtio_ccw_set_ind(ind_loc, actual, actual | to_be_set); + cpu_physical_memory_unmap((void *)ind_addr, len, 1, len); - return ind_old; + return actual; } static void virtio_ccw_notify(DeviceState *d, uint16_t vector) diff --git a/hw/sd/ssi-sd.c b/hw/sd/ssi-sd.c index 25cec2ddea..25cdf4c966 100644 --- a/hw/sd/ssi-sd.c +++ b/hw/sd/ssi-sd.c @@ -74,7 +74,7 @@ typedef struct { static uint32_t ssi_sd_transfer(SSISlave *dev, uint32_t val) { - ssi_sd_state *s = FROM_SSI_SLAVE(ssi_sd_state, dev); + ssi_sd_state *s = SSI_SD(dev); /* Special case: allow CMD12 (STOP TRANSMISSION) while reading data. */ if (s->mode == SSI_SD_DATA_READ && val == 0x4d) { @@ -241,7 +241,7 @@ static const VMStateDescription vmstate_ssi_sd = { static void ssi_sd_realize(SSISlave *d, Error **errp) { - ssi_sd_state *s = FROM_SSI_SLAVE(ssi_sd_state, d); + ssi_sd_state *s = SSI_SD(d); DeviceState *carddev; DriveInfo *dinfo; Error *err = NULL; diff --git a/hw/ssi/ssi.c b/hw/ssi/ssi.c index 67b48c31cd..a35d7ebb26 100644 --- a/hw/ssi/ssi.c +++ b/hw/ssi/ssi.c @@ -90,11 +90,16 @@ static const TypeInfo ssi_slave_info = { .abstract = true, }; +bool ssi_realize_and_unref(DeviceState *dev, SSIBus *bus, Error **errp) +{ + return qdev_realize_and_unref(dev, &bus->parent_obj, errp); +} + DeviceState *ssi_create_slave(SSIBus *bus, const char *name) { DeviceState *dev = qdev_new(name); - qdev_realize_and_unref(dev, &bus->parent_obj, &error_fatal); + ssi_realize_and_unref(dev, bus, &error_fatal); return dev; } diff --git a/hw/usb/Makefile.objs b/hw/usb/Makefile.objs index fa5c3fa1b8..e342ff59fa 100644 --- a/hw/usb/Makefile.objs +++ b/hw/usb/Makefile.objs @@ -29,11 +29,13 @@ common-obj-$(CONFIG_USB_NETWORK) += dev-network.o ifeq ($(CONFIG_USB_SMARTCARD),y) common-obj-y += dev-smartcard-reader.o -common-obj-$(CONFIG_SMARTCARD) += smartcard.mo +ifeq ($(CONFIG_SMARTCARD),y) +common-obj-m += smartcard.mo smartcard.mo-objs := ccid-card-passthru.o ccid-card-emulated.o smartcard.mo-cflags := $(SMARTCARD_CFLAGS) smartcard.mo-libs := $(SMARTCARD_LIBS) endif +endif ifeq ($(CONFIG_POSIX),y) common-obj-$(CONFIG_USB_STORAGE_MTP) += dev-mtp.o @@ -41,9 +43,12 @@ endif # usb redirection ifeq ($(CONFIG_USB),y) -common-obj-$(CONFIG_USB_REDIR) += redirect.o quirks.o -redirect.o-cflags = $(USB_REDIR_CFLAGS) -redirect.o-libs = $(USB_REDIR_LIBS) +ifeq ($(CONFIG_USB_REDIR),y) +common-obj-m += redirect.mo +redirect.mo-objs = redirect.o quirks.o +redirect.mo-cflags = $(USB_REDIR_CFLAGS) +redirect.mo-libs = $(USB_REDIR_LIBS) +endif endif # usb pass-through diff --git a/hw/vfio/ap.c b/hw/vfio/ap.c index 95564c17ed..b9330a8e6f 100644 --- a/hw/vfio/ap.c +++ b/hw/vfio/ap.c @@ -105,12 +105,12 @@ static void vfio_ap_realize(DeviceState *dev, Error **errp) vapdev->vdev.dev = dev; /* - * vfio-ap devices operate in a way compatible with - * memory ballooning, as no pages are pinned in the host. + * vfio-ap devices operate in a way compatible with discarding of + * memory in RAM blocks, as no pages are pinned in the host. * This needs to be set before vfio_get_device() for vfio common to - * handle the balloon inhibitor. + * handle ram_block_discard_disable(). */ - vapdev->vdev.balloon_allowed = true; + vapdev->vdev.ram_block_discard_allowed = true; ret = vfio_get_device(vfio_group, mdevid, &vapdev->vdev, errp); if (ret) { diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c index 06e69d7066..ff7f369779 100644 --- a/hw/vfio/ccw.c +++ b/hw/vfio/ccw.c @@ -574,12 +574,13 @@ static void vfio_ccw_get_device(VFIOGroup *group, VFIOCCWDevice *vcdev, /* * All vfio-ccw devices are believed to operate in a way compatible with - * memory ballooning, ie. pages pinned in the host are in the current - * working set of the guest driver and therefore never overlap with pages - * available to the guest balloon driver. This needs to be set before - * vfio_get_device() for vfio common to handle the balloon inhibitor. + * discarding of memory in RAM blocks, ie. pages pinned in the host are + * in the current working set of the guest driver and therefore never + * overlap e.g., with pages available to the guest balloon driver. This + * needs to be set before vfio_get_device() for vfio common to handle + * ram_block_discard_disable(). */ - vcdev->vdev.balloon_allowed = true; + vcdev->vdev.ram_block_discard_allowed = true; if (vfio_get_device(group, vcdev->cdev.mdevid, &vcdev->vdev, errp)) { goto out_err; diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 0b3593b3c0..33357140b8 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -33,7 +33,6 @@ #include "qemu/error-report.h" #include "qemu/main-loop.h" #include "qemu/range.h" -#include "sysemu/balloon.h" #include "sysemu/kvm.h" #include "sysemu/reset.h" #include "trace.h" @@ -1215,31 +1214,36 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, space = vfio_get_address_space(as); /* - * VFIO is currently incompatible with memory ballooning insofar as the + * VFIO is currently incompatible with discarding of RAM insofar as the * madvise to purge (zap) the page from QEMU's address space does not * interact with the memory API and therefore leaves stale virtual to * physical mappings in the IOMMU if the page was previously pinned. We - * therefore add a balloon inhibit for each group added to a container, + * therefore set discarding broken for each group added to a container, * whether the container is used individually or shared. This provides * us with options to allow devices within a group to opt-in and allow - * ballooning, so long as it is done consistently for a group (for instance + * discarding, so long as it is done consistently for a group (for instance * if the device is an mdev device where it is known that the host vendor * driver will never pin pages outside of the working set of the guest - * driver, which would thus not be ballooning candidates). + * driver, which would thus not be discarding candidates). * * The first opportunity to induce pinning occurs here where we attempt to * attach the group to existing containers within the AddressSpace. If any - * pages are already zapped from the virtual address space, such as from a - * previous ballooning opt-in, new pinning will cause valid mappings to be + * pages are already zapped from the virtual address space, such as from + * previous discards, new pinning will cause valid mappings to be * re-established. Likewise, when the overall MemoryListener for a new * container is registered, a replay of mappings within the AddressSpace * will occur, re-establishing any previously zapped pages as well. * - * NB. Balloon inhibiting does not currently block operation of the - * balloon driver or revoke previously pinned pages, it only prevents - * calling madvise to modify the virtual mapping of ballooned pages. + * Especially virtio-balloon is currently only prevented from discarding + * new memory, it will not yet set ram_block_discard_set_required() and + * therefore, neither stops us here or deals with the sudden memory + * consumption of inflated memory. */ - qemu_balloon_inhibit(true); + ret = ram_block_discard_disable(true); + if (ret) { + error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken"); + return ret; + } QLIST_FOREACH(container, &space->containers, next) { if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) { @@ -1405,7 +1409,7 @@ close_fd_exit: close(fd); put_space_exit: - qemu_balloon_inhibit(false); + ram_block_discard_disable(false); vfio_put_address_space(space); return ret; @@ -1526,8 +1530,8 @@ void vfio_put_group(VFIOGroup *group) return; } - if (!group->balloon_allowed) { - qemu_balloon_inhibit(false); + if (!group->ram_block_discard_allowed) { + ram_block_discard_disable(false); } vfio_kvm_device_del_group(group); vfio_disconnect_container(group); @@ -1565,22 +1569,23 @@ int vfio_get_device(VFIOGroup *group, const char *name, } /* - * Clear the balloon inhibitor for this group if the driver knows the - * device operates compatibly with ballooning. Setting must be consistent - * per group, but since compatibility is really only possible with mdev - * currently, we expect singleton groups. + * Set discarding of RAM as not broken for this group if the driver knows + * the device operates compatibly with discarding. Setting must be + * consistent per group, but since compatibility is really only possible + * with mdev currently, we expect singleton groups. */ - if (vbasedev->balloon_allowed != group->balloon_allowed) { + if (vbasedev->ram_block_discard_allowed != + group->ram_block_discard_allowed) { if (!QLIST_EMPTY(&group->device_list)) { - error_setg(errp, - "Inconsistent device balloon setting within group"); + error_setg(errp, "Inconsistent setting of support for discarding " + "RAM (e.g., balloon) within group"); close(fd); return -1; } - if (!group->balloon_allowed) { - group->balloon_allowed = true; - qemu_balloon_inhibit(false); + if (!group->ram_block_discard_allowed) { + group->ram_block_discard_allowed = true; + ram_block_discard_disable(false); } } diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 6838bcc4b3..d020ea9f82 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -2789,7 +2789,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) } /* - * Mediated devices *might* operate compatibly with memory ballooning, but + * Mediated devices *might* operate compatibly with discarding of RAM, but * we cannot know for certain, it depends on whether the mdev vendor driver * stays in sync with the active working set of the guest driver. Prevent * the x-balloon-allowed option unless this is minimally an mdev device. @@ -2802,7 +2802,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) trace_vfio_mdev(vdev->vbasedev.name, is_mdev); - if (vdev->vbasedev.balloon_allowed && !is_mdev) { + if (vdev->vbasedev.ram_block_discard_allowed && !is_mdev) { error_setg(errp, "x-balloon-allowed only potentially compatible " "with mdev devices"); vfio_put_group(group); @@ -3156,7 +3156,7 @@ static Property vfio_pci_dev_properties[] = { VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT, false), DEFINE_PROP_BOOL("x-no-mmap", VFIOPCIDevice, vbasedev.no_mmap, false), DEFINE_PROP_BOOL("x-balloon-allowed", VFIOPCIDevice, - vbasedev.balloon_allowed, false), + vbasedev.ram_block_discard_allowed, false), DEFINE_PROP_BOOL("x-no-kvm-intx", VFIOPCIDevice, no_kvm_intx, false), DEFINE_PROP_BOOL("x-no-kvm-msi", VFIOPCIDevice, no_kvm_msi, false), DEFINE_PROP_BOOL("x-no-kvm-msix", VFIOPCIDevice, no_kvm_msix, false), diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig index 83122424fa..0eda25c4e1 100644 --- a/hw/virtio/Kconfig +++ b/hw/virtio/Kconfig @@ -47,3 +47,14 @@ config VIRTIO_PMEM depends on VIRTIO depends on VIRTIO_PMEM_SUPPORTED select MEM_DEVICE + +config VIRTIO_MEM_SUPPORTED + bool + +config VIRTIO_MEM + bool + default y + depends on VIRTIO + depends on LINUX + depends on VIRTIO_MEM_SUPPORTED + select MEM_DEVICE diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs index 13e75f171f..fc91719b4a 100644 --- a/hw/virtio/Makefile.objs +++ b/hw/virtio/Makefile.objs @@ -5,6 +5,7 @@ obj-y += virtio.o obj-$(CONFIG_VHOST) += vhost.o vhost-backend.o common-obj-$(call lnot,$(CONFIG_VHOST)) += vhost-stub.o obj-$(CONFIG_VHOST_USER) += vhost-user.o +obj-$(CONFIG_VHOST_VDPA) += vhost-vdpa.o common-obj-$(CONFIG_VIRTIO_RNG) += virtio-rng.o common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o @@ -19,6 +20,8 @@ obj-$(call land,$(CONFIG_VHOST_USER_FS),$(CONFIG_VIRTIO_PCI)) += vhost-user-fs-p obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock-common.o vhost-vsock.o obj-$(CONFIG_VHOST_USER_VSOCK) += vhost-vsock-common.o vhost-user-vsock.o +obj-$(CONFIG_VIRTIO_MEM) += virtio-mem.o +common-obj-$(call land,$(CONFIG_VIRTIO_MEM),$(CONFIG_VIRTIO_PCI)) += virtio-mem-pci.o ifeq ($(CONFIG_VIRTIO_PCI),y) obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock-pci.o diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index 6427a0047d..045e89cae6 100644 --- a/hw/virtio/trace-events +++ b/hw/virtio/trace-events @@ -74,3 +74,14 @@ virtio_iommu_get_domain(uint32_t domain_id) "Alloc domain=%d" virtio_iommu_put_domain(uint32_t domain_id) "Free domain=%d" virtio_iommu_translate_out(uint64_t virt_addr, uint64_t phys_addr, uint32_t sid) "0x%"PRIx64" -> 0x%"PRIx64 " for sid=%d" virtio_iommu_report_fault(uint8_t reason, uint32_t flags, uint32_t endpoint, uint64_t addr) "FAULT reason=%d flags=%d endpoint=%d address =0x%"PRIx64 +virtio_iommu_fill_resv_property(uint32_t devid, uint8_t subtype, uint64_t start, uint64_t end) "dev= %d, type=%d start=0x%"PRIx64" end=0x%"PRIx64 + +# virtio-mem.c +virtio_mem_send_response(uint16_t type) "type=%" PRIu16 +virtio_mem_plug_request(uint64_t addr, uint16_t nb_blocks) "addr=0x%" PRIx64 " nb_blocks=%" PRIu16 +virtio_mem_unplug_request(uint64_t addr, uint16_t nb_blocks) "addr=0x%" PRIx64 " nb_blocks=%" PRIu16 +virtio_mem_unplugged_all(void) "" +virtio_mem_unplug_all_request(void) "" +virtio_mem_resized_usable_region(uint64_t old_size, uint64_t new_size) "old_size=0x%" PRIx64 "new_size=0x%" PRIx64 +virtio_mem_state_request(uint64_t addr, uint16_t nb_blocks) "addr=0x%" PRIx64 " nb_blocks=%" PRIu16 +virtio_mem_state_response(uint16_t state) "state=%" PRIu16 diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c index 48905383f8..782b1d67d9 100644 --- a/hw/virtio/vhost-backend.c +++ b/hw/virtio/vhost-backend.c @@ -15,6 +15,7 @@ #include "qemu/main-loop.h" #include "standard-headers/linux/vhost_types.h" +#include "hw/virtio/vhost-vdpa.h" #ifdef CONFIG_VHOST_KERNEL #include <linux/vhost.h> #include <sys/ioctl.h> @@ -286,6 +287,11 @@ int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type) dev->vhost_ops = &user_ops; break; #endif +#ifdef CONFIG_VHOST_VDPA + case VHOST_BACKEND_TYPE_VDPA: + dev->vhost_ops = &vdpa_ops; + break; +#endif default: error_report("Unknown vhost backend type"); r = -1; diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c new file mode 100644 index 0000000000..a3d17fe0f9 --- /dev/null +++ b/hw/virtio/vhost-vdpa.c @@ -0,0 +1,475 @@ +/* + * vhost-vdpa + * + * Copyright(c) 2017-2018 Intel Corporation. + * Copyright(c) 2020 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include <linux/vhost.h> +#include <linux/vfio.h> +#include <sys/eventfd.h> +#include <sys/ioctl.h> +#include "hw/virtio/vhost.h" +#include "hw/virtio/vhost-backend.h" +#include "hw/virtio/virtio-net.h" +#include "hw/virtio/vhost-vdpa.h" +#include "qemu/main-loop.h" +#include <linux/kvm.h> +#include "sysemu/kvm.h" + +static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section) +{ + return (!memory_region_is_ram(section->mr) && + !memory_region_is_iommu(section->mr)) || + /* + * Sizing an enabled 64-bit BAR can cause spurious mappings to + * addresses in the upper part of the 64-bit address space. These + * are never accessed by the CPU and beyond the address width of + * some IOMMU hardware. TODO: VDPA should tell us the IOMMU width. + */ + section->offset_within_address_space & (1ULL << 63); +} + +static int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size, + void *vaddr, bool readonly) +{ + struct vhost_msg_v2 msg; + int fd = v->device_fd; + int ret = 0; + + msg.type = v->msg_type; + msg.iotlb.iova = iova; + msg.iotlb.size = size; + msg.iotlb.uaddr = (uint64_t)(uintptr_t)vaddr; + msg.iotlb.perm = readonly ? VHOST_ACCESS_RO : VHOST_ACCESS_RW; + msg.iotlb.type = VHOST_IOTLB_UPDATE; + + if (write(fd, &msg, sizeof(msg)) != sizeof(msg)) { + error_report("failed to write, fd=%d, errno=%d (%s)", + fd, errno, strerror(errno)); + return -EIO ; + } + + return ret; +} + +static int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, hwaddr iova, + hwaddr size) +{ + struct vhost_msg_v2 msg; + int fd = v->device_fd; + int ret = 0; + + msg.type = v->msg_type; + msg.iotlb.iova = iova; + msg.iotlb.size = size; + msg.iotlb.type = VHOST_IOTLB_INVALIDATE; + + if (write(fd, &msg, sizeof(msg)) != sizeof(msg)) { + error_report("failed to write, fd=%d, errno=%d (%s)", + fd, errno, strerror(errno)); + return -EIO ; + } + + return ret; +} + +static void vhost_vdpa_listener_region_add(MemoryListener *listener, + MemoryRegionSection *section) +{ + struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener); + hwaddr iova; + Int128 llend, llsize; + void *vaddr; + int ret; + + if (vhost_vdpa_listener_skipped_section(section)) { + return; + } + + if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) != + (section->offset_within_region & ~TARGET_PAGE_MASK))) { + error_report("%s received unaligned region", __func__); + return; + } + + iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); + llend = int128_make64(section->offset_within_address_space); + llend = int128_add(llend, section->size); + llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK)); + + if (int128_ge(int128_make64(iova), llend)) { + return; + } + + memory_region_ref(section->mr); + + /* Here we assume that memory_region_is_ram(section->mr)==true */ + + vaddr = memory_region_get_ram_ptr(section->mr) + + section->offset_within_region + + (iova - section->offset_within_address_space); + + llsize = int128_sub(llend, int128_make64(iova)); + + ret = vhost_vdpa_dma_map(v, iova, int128_get64(llsize), + vaddr, section->readonly); + if (ret) { + error_report("vhost vdpa map fail!"); + if (memory_region_is_ram_device(section->mr)) { + /* Allow unexpected mappings not to be fatal for RAM devices */ + error_report("map ram fail!"); + return ; + } + goto fail; + } + + return; + +fail: + if (memory_region_is_ram_device(section->mr)) { + error_report("failed to vdpa_dma_map. pci p2p may not work"); + return; + + } + /* + * On the initfn path, store the first error in the container so we + * can gracefully fail. Runtime, there's not much we can do other + * than throw a hardware error. + */ + error_report("vhost-vdpa: DMA mapping failed, unable to continue"); + return; + +} + +static void vhost_vdpa_listener_region_del(MemoryListener *listener, + MemoryRegionSection *section) +{ + struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener); + hwaddr iova; + Int128 llend, llsize; + int ret; + bool try_unmap = true; + + if (vhost_vdpa_listener_skipped_section(section)) { + return; + } + + if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) != + (section->offset_within_region & ~TARGET_PAGE_MASK))) { + error_report("%s received unaligned region", __func__); + return; + } + + iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); + llend = int128_make64(section->offset_within_address_space); + llend = int128_add(llend, section->size); + llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK)); + + if (int128_ge(int128_make64(iova), llend)) { + return; + } + + llsize = int128_sub(llend, int128_make64(iova)); + + if (try_unmap) { + ret = vhost_vdpa_dma_unmap(v, iova, int128_get64(llsize)); + if (ret) { + error_report("vhost_vdpa dma unmap error!"); + } + } + + memory_region_unref(section->mr); +} +/* + * IOTLB API is used by vhost-vpda which requires incremental updating + * of the mapping. So we can not use generic vhost memory listener which + * depends on the addnop(). + */ +static const MemoryListener vhost_vdpa_memory_listener = { + .region_add = vhost_vdpa_listener_region_add, + .region_del = vhost_vdpa_listener_region_del, +}; + +static int vhost_vdpa_call(struct vhost_dev *dev, unsigned long int request, + void *arg) +{ + struct vhost_vdpa *v = dev->opaque; + int fd = v->device_fd; + + assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA); + + return ioctl(fd, request, arg); +} + +static void vhost_vdpa_add_status(struct vhost_dev *dev, uint8_t status) +{ + uint8_t s; + + if (vhost_vdpa_call(dev, VHOST_VDPA_GET_STATUS, &s)) { + return; + } + + s |= status; + + vhost_vdpa_call(dev, VHOST_VDPA_SET_STATUS, &s); +} + +static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque) +{ + struct vhost_vdpa *v; + uint64_t features; + assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA); + + v = opaque; + dev->opaque = opaque ; + vhost_vdpa_call(dev, VHOST_GET_FEATURES, &features); + dev->backend_features = features; + v->listener = vhost_vdpa_memory_listener; + v->msg_type = VHOST_IOTLB_MSG_V2; + + vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE | + VIRTIO_CONFIG_S_DRIVER); + + return 0; +} + +static int vhost_vdpa_cleanup(struct vhost_dev *dev) +{ + struct vhost_vdpa *v; + assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA); + v = dev->opaque; + memory_listener_unregister(&v->listener); + + dev->opaque = NULL; + return 0; +} + +static int vhost_vdpa_memslots_limit(struct vhost_dev *dev) +{ + return INT_MAX; +} + +static int vhost_vdpa_set_mem_table(struct vhost_dev *dev, + struct vhost_memory *mem) +{ + + if (mem->padding) { + return -1; + } + + return 0; +} + +static int vhost_vdpa_set_features(struct vhost_dev *dev, + uint64_t features) +{ + int ret; + ret = vhost_vdpa_call(dev, VHOST_SET_FEATURES, &features); + uint8_t status = 0; + if (ret) { + return ret; + } + vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_FEATURES_OK); + vhost_vdpa_call(dev, VHOST_VDPA_GET_STATUS, &status); + + return !(status & VIRTIO_CONFIG_S_FEATURES_OK); +} + +int vhost_vdpa_get_device_id(struct vhost_dev *dev, + uint32_t *device_id) +{ + return vhost_vdpa_call(dev, VHOST_VDPA_GET_DEVICE_ID, device_id); +} + +static int vhost_vdpa_reset_device(struct vhost_dev *dev) +{ + uint8_t status = 0; + + return vhost_vdpa_call(dev, VHOST_VDPA_SET_STATUS, &status); +} + +static int vhost_vdpa_get_vq_index(struct vhost_dev *dev, int idx) +{ + assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs); + + return idx - dev->vq_index; +} + +static int vhost_vdpa_set_vring_ready(struct vhost_dev *dev) +{ + int i; + for (i = 0; i < dev->nvqs; ++i) { + struct vhost_vring_state state = { + .index = dev->vq_index + i, + .num = 1, + }; + vhost_vdpa_call(dev, VHOST_VDPA_SET_VRING_ENABLE, &state); + } + return 0; +} + +static int vhost_vdpa_set_config(struct vhost_dev *dev, const uint8_t *data, + uint32_t offset, uint32_t size, + uint32_t flags) +{ + struct vhost_vdpa_config *config; + int ret; + unsigned long config_size = offsetof(struct vhost_vdpa_config, buf); + config = g_malloc(size + config_size); + if (config == NULL) { + return -1; + } + config->off = offset; + config->len = size; + memcpy(config->buf, data, size); + ret = vhost_vdpa_call(dev, VHOST_VDPA_SET_CONFIG, config); + g_free(config); + return ret; +} + +static int vhost_vdpa_get_config(struct vhost_dev *dev, uint8_t *config, + uint32_t config_len) +{ + struct vhost_vdpa_config *v_config; + unsigned long config_size = offsetof(struct vhost_vdpa_config, buf); + int ret; + + v_config = g_malloc(config_len + config_size); + if (v_config == NULL) { + return -1; + } + v_config->len = config_len; + v_config->off = 0; + ret = vhost_vdpa_call(dev, VHOST_VDPA_GET_CONFIG, v_config); + memcpy(config, v_config->buf, config_len); + g_free(v_config); + return ret; + } + +static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) +{ + struct vhost_vdpa *v = dev->opaque; + if (started) { + uint8_t status = 0; + memory_listener_register(&v->listener, &address_space_memory); + vhost_vdpa_set_vring_ready(dev); + vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK); + vhost_vdpa_call(dev, VHOST_VDPA_GET_STATUS, &status); + + return !(status & VIRTIO_CONFIG_S_DRIVER_OK); + } else { + vhost_vdpa_reset_device(dev); + vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE | + VIRTIO_CONFIG_S_DRIVER); + memory_listener_unregister(&v->listener); + + return 0; + } +} + +static int vhost_vdpa_set_log_base(struct vhost_dev *dev, uint64_t base, + struct vhost_log *log) +{ + return vhost_vdpa_call(dev, VHOST_SET_LOG_BASE, &base); +} + +static int vhost_vdpa_set_vring_addr(struct vhost_dev *dev, + struct vhost_vring_addr *addr) +{ + return vhost_vdpa_call(dev, VHOST_SET_VRING_ADDR, addr); +} + +static int vhost_vdpa_set_vring_num(struct vhost_dev *dev, + struct vhost_vring_state *ring) +{ + return vhost_vdpa_call(dev, VHOST_SET_VRING_NUM, ring); +} + +static int vhost_vdpa_set_vring_base(struct vhost_dev *dev, + struct vhost_vring_state *ring) +{ + return vhost_vdpa_call(dev, VHOST_SET_VRING_BASE, ring); +} + +static int vhost_vdpa_get_vring_base(struct vhost_dev *dev, + struct vhost_vring_state *ring) +{ + return vhost_vdpa_call(dev, VHOST_GET_VRING_BASE, ring); +} + +static int vhost_vdpa_set_vring_kick(struct vhost_dev *dev, + struct vhost_vring_file *file) +{ + return vhost_vdpa_call(dev, VHOST_SET_VRING_KICK, file); +} + +static int vhost_vdpa_set_vring_call(struct vhost_dev *dev, + struct vhost_vring_file *file) +{ + return vhost_vdpa_call(dev, VHOST_SET_VRING_CALL, file); +} + +static int vhost_vdpa_get_features(struct vhost_dev *dev, + uint64_t *features) +{ + return vhost_vdpa_call(dev, VHOST_GET_FEATURES, features); +} + +static int vhost_vdpa_set_owner(struct vhost_dev *dev) +{ + return vhost_vdpa_call(dev, VHOST_SET_OWNER, NULL); +} + +static int vhost_vdpa_vq_get_addr(struct vhost_dev *dev, + struct vhost_vring_addr *addr, struct vhost_virtqueue *vq) +{ + assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA); + addr->desc_user_addr = (uint64_t)(unsigned long)vq->desc_phys; + addr->avail_user_addr = (uint64_t)(unsigned long)vq->avail_phys; + addr->used_user_addr = (uint64_t)(unsigned long)vq->used_phys; + return 0; +} + +static bool vhost_vdpa_force_iommu(struct vhost_dev *dev) +{ + return true; +} + +const VhostOps vdpa_ops = { + .backend_type = VHOST_BACKEND_TYPE_VDPA, + .vhost_backend_init = vhost_vdpa_init, + .vhost_backend_cleanup = vhost_vdpa_cleanup, + .vhost_set_log_base = vhost_vdpa_set_log_base, + .vhost_set_vring_addr = vhost_vdpa_set_vring_addr, + .vhost_set_vring_num = vhost_vdpa_set_vring_num, + .vhost_set_vring_base = vhost_vdpa_set_vring_base, + .vhost_get_vring_base = vhost_vdpa_get_vring_base, + .vhost_set_vring_kick = vhost_vdpa_set_vring_kick, + .vhost_set_vring_call = vhost_vdpa_set_vring_call, + .vhost_get_features = vhost_vdpa_get_features, + .vhost_set_owner = vhost_vdpa_set_owner, + .vhost_set_vring_endian = NULL, + .vhost_backend_memslots_limit = vhost_vdpa_memslots_limit, + .vhost_set_mem_table = vhost_vdpa_set_mem_table, + .vhost_set_features = vhost_vdpa_set_features, + .vhost_reset_device = vhost_vdpa_reset_device, + .vhost_get_vq_index = vhost_vdpa_get_vq_index, + .vhost_get_config = vhost_vdpa_get_config, + .vhost_set_config = vhost_vdpa_set_config, + .vhost_requires_shm_log = NULL, + .vhost_migration_done = NULL, + .vhost_backend_can_merge = NULL, + .vhost_net_set_mtu = NULL, + .vhost_set_iotlb_callback = NULL, + .vhost_send_device_iotlb_msg = NULL, + .vhost_dev_start = vhost_vdpa_dev_start, + .vhost_get_device_id = vhost_vdpa_get_device_id, + .vhost_vq_get_addr = vhost_vdpa_vq_get_addr, + .vhost_force_iommu = vhost_vdpa_force_iommu, +}; diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index 5fd25fe520..1a1384e7a6 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -773,15 +773,25 @@ static int vhost_virtqueue_set_addr(struct vhost_dev *dev, struct vhost_virtqueue *vq, unsigned idx, bool enable_log) { - struct vhost_vring_addr addr = { - .index = idx, - .desc_user_addr = (uint64_t)(unsigned long)vq->desc, - .avail_user_addr = (uint64_t)(unsigned long)vq->avail, - .used_user_addr = (uint64_t)(unsigned long)vq->used, - .log_guest_addr = vq->used_phys, - .flags = enable_log ? (1 << VHOST_VRING_F_LOG) : 0, - }; - int r = dev->vhost_ops->vhost_set_vring_addr(dev, &addr); + struct vhost_vring_addr addr; + int r; + memset(&addr, 0, sizeof(struct vhost_vring_addr)); + + if (dev->vhost_ops->vhost_vq_get_addr) { + r = dev->vhost_ops->vhost_vq_get_addr(dev, &addr, vq); + if (r < 0) { + VHOST_OPS_DEBUG("vhost_vq_get_addr failed"); + return -errno; + } + } else { + addr.desc_user_addr = (uint64_t)(unsigned long)vq->desc; + addr.avail_user_addr = (uint64_t)(unsigned long)vq->avail; + addr.used_user_addr = (uint64_t)(unsigned long)vq->used; + } + addr.index = idx; + addr.log_guest_addr = vq->used_phys; + addr.flags = enable_log ? (1 << VHOST_VRING_F_LOG) : 0; + r = dev->vhost_ops->vhost_set_vring_addr(dev, &addr); if (r < 0) { VHOST_OPS_DEBUG("vhost_set_vring_addr failed"); return -errno; @@ -800,6 +810,11 @@ static int vhost_dev_set_features(struct vhost_dev *dev, if (!vhost_dev_has_iommu(dev)) { features &= ~(0x1ULL << VIRTIO_F_IOMMU_PLATFORM); } + if (dev->vhost_ops->vhost_force_iommu) { + if (dev->vhost_ops->vhost_force_iommu(dev) == true) { + features |= 0x1ULL << VIRTIO_F_IOMMU_PLATFORM; + } + } r = dev->vhost_ops->vhost_set_features(dev, features); if (r < 0) { VHOST_OPS_DEBUG("vhost_set_features failed"); @@ -1685,9 +1700,15 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) goto fail_log; } } - - if (vhost_dev_has_iommu(hdev)) { - hdev->vhost_ops->vhost_set_iotlb_callback(hdev, true); + if (hdev->vhost_ops->vhost_dev_start) { + r = hdev->vhost_ops->vhost_dev_start(hdev, true); + if (r) { + goto fail_log; + } + } + if (vhost_dev_has_iommu(hdev) && + hdev->vhost_ops->vhost_set_iotlb_callback) { + hdev->vhost_ops->vhost_set_iotlb_callback(hdev, true); /* Update used ring information for IOTLB to work correctly, * vhost-kernel code requires for this.*/ @@ -1722,6 +1743,9 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev) /* should only be called after backend is connected */ assert(hdev->vhost_ops); + if (hdev->vhost_ops->vhost_dev_start) { + hdev->vhost_ops->vhost_dev_start(hdev, false); + } for (i = 0; i < hdev->nvqs; ++i) { vhost_virtqueue_stop(hdev, vdev, @@ -1730,7 +1754,9 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev) } if (vhost_dev_has_iommu(hdev)) { - hdev->vhost_ops->vhost_set_iotlb_callback(hdev, false); + if (hdev->vhost_ops->vhost_set_iotlb_callback) { + hdev->vhost_ops->vhost_set_iotlb_callback(hdev, false); + } memory_listener_unregister(&hdev->iommu_listener); } vhost_log_put(hdev, true); diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c index 10507b2a43..ae31f0817a 100644 --- a/hw/virtio/virtio-balloon.c +++ b/hw/virtio/virtio-balloon.c @@ -63,6 +63,12 @@ static bool virtio_balloon_pbp_matches(PartiallyBalloonedPage *pbp, return pbp->base_gpa == base_gpa; } +static bool virtio_balloon_inhibited(void) +{ + /* Postcopy cannot deal with concurrent discards, so it's special. */ + return ram_block_discard_is_disabled() || migration_in_incoming_postcopy(); +} + static void balloon_inflate_page(VirtIOBalloon *balloon, MemoryRegion *mr, hwaddr mr_offset, PartiallyBalloonedPage *pbp) @@ -336,7 +342,7 @@ static void virtio_balloon_handle_report(VirtIODevice *vdev, VirtQueue *vq) * accessible by another device or process, or if the guest is * expecting it to retain a non-zero value. */ - if (qemu_balloon_is_inhibited() || dev->poison_val) { + if (virtio_balloon_inhibited() || dev->poison_val) { goto skip_element; } @@ -421,7 +427,7 @@ static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq) trace_virtio_balloon_handle_output(memory_region_name(section.mr), pa); - if (!qemu_balloon_is_inhibited()) { + if (!virtio_balloon_inhibited()) { if (vq == s->ivq) { balloon_inflate_page(s, section.mr, section.offset_within_region, &pbp); @@ -628,8 +634,13 @@ static void virtio_balloon_free_page_done(VirtIOBalloon *s) { VirtIODevice *vdev = VIRTIO_DEVICE(s); - s->free_page_report_status = FREE_PAGE_REPORT_S_DONE; - virtio_notify_config(vdev); + if (s->free_page_report_status != FREE_PAGE_REPORT_S_DONE) { + /* See virtio_balloon_free_page_stop() */ + qemu_mutex_lock(&s->free_page_lock); + s->free_page_report_status = FREE_PAGE_REPORT_S_DONE; + qemu_mutex_unlock(&s->free_page_lock); + virtio_notify_config(vdev); + } } static int @@ -653,17 +664,26 @@ virtio_balloon_free_page_report_notify(NotifierWithReturn *n, void *data) case PRECOPY_NOTIFY_SETUP: precopy_enable_free_page_optimization(); break; - case PRECOPY_NOTIFY_COMPLETE: - case PRECOPY_NOTIFY_CLEANUP: case PRECOPY_NOTIFY_BEFORE_BITMAP_SYNC: virtio_balloon_free_page_stop(dev); break; case PRECOPY_NOTIFY_AFTER_BITMAP_SYNC: if (vdev->vm_running) { virtio_balloon_free_page_start(dev); - } else { - virtio_balloon_free_page_done(dev); + break; } + /* + * Set S_DONE before migrating the vmstate, so the guest will reuse + * all hinted pages once running on the destination. Fall through. + */ + case PRECOPY_NOTIFY_CLEANUP: + /* + * Especially, if something goes wrong during precopy or if migration + * is canceled, we have to properly communicate S_DONE to the VM. + */ + virtio_balloon_free_page_done(dev); + break; + case PRECOPY_NOTIFY_COMPLETE: break; default: virtio_error(vdev, "%s: %d reason unknown", __func__, pnd->reason); diff --git a/hw/virtio/virtio-iommu-pci.c b/hw/virtio/virtio-iommu-pci.c index 4588361d6b..592abc9279 100644 --- a/hw/virtio/virtio-iommu-pci.c +++ b/hw/virtio/virtio-iommu-pci.c @@ -33,6 +33,9 @@ struct VirtIOIOMMUPCI { static Property virtio_iommu_pci_properties[] = { DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0), + DEFINE_PROP_ARRAY("reserved-regions", VirtIOIOMMUPCI, + vdev.nb_reserved_regions, vdev.reserved_regions, + qdev_prop_reserved_region, ReservedRegion), DEFINE_PROP_END_OF_LIST(), }; @@ -40,6 +43,7 @@ static void virtio_iommu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) { VirtIOIOMMUPCI *dev = VIRTIO_IOMMU_PCI(vpci_dev); DeviceState *vdev = DEVICE(&dev->vdev); + VirtIOIOMMU *s = VIRTIO_IOMMU(vdev); if (!qdev_get_machine_hotplug_handler(DEVICE(vpci_dev))) { MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine()); @@ -54,6 +58,13 @@ static void virtio_iommu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) "-no-acpi\n"); return; } + for (int i = 0; i < s->nb_reserved_regions; i++) { + if (s->reserved_regions[i].type != VIRTIO_IOMMU_RESV_MEM_T_RESERVED && + s->reserved_regions[i].type != VIRTIO_IOMMU_RESV_MEM_T_MSI) { + error_setg(errp, "reserved region %d has an invalid type", i); + error_append_hint(errp, "Valid values are 0 and 1\n"); + } + } object_property_set_link(OBJECT(dev), OBJECT(pci_get_bus(&vpci_dev->pci_dev)), "primary-bus", &error_abort); diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c index 483883ec1d..b39e836181 100644 --- a/hw/virtio/virtio-iommu.c +++ b/hw/virtio/virtio-iommu.c @@ -38,6 +38,7 @@ /* Max size */ #define VIOMMU_DEFAULT_QUEUE_SIZE 256 +#define VIOMMU_PROBE_SIZE 512 typedef struct VirtIOIOMMUDomain { uint32_t id; @@ -378,6 +379,65 @@ static int virtio_iommu_unmap(VirtIOIOMMU *s, return ret; } +static ssize_t virtio_iommu_fill_resv_mem_prop(VirtIOIOMMU *s, uint32_t ep, + uint8_t *buf, size_t free) +{ + struct virtio_iommu_probe_resv_mem prop = {}; + size_t size = sizeof(prop), length = size - sizeof(prop.head), total; + int i; + + total = size * s->nb_reserved_regions; + + if (total > free) { + return -ENOSPC; + } + + for (i = 0; i < s->nb_reserved_regions; i++) { + unsigned subtype = s->reserved_regions[i].type; + + assert(subtype == VIRTIO_IOMMU_RESV_MEM_T_RESERVED || + subtype == VIRTIO_IOMMU_RESV_MEM_T_MSI); + prop.head.type = cpu_to_le16(VIRTIO_IOMMU_PROBE_T_RESV_MEM); + prop.head.length = cpu_to_le16(length); + prop.subtype = subtype; + prop.start = cpu_to_le64(s->reserved_regions[i].low); + prop.end = cpu_to_le64(s->reserved_regions[i].high); + + memcpy(buf, &prop, size); + + trace_virtio_iommu_fill_resv_property(ep, prop.subtype, + prop.start, prop.end); + buf += size; + } + return total; +} + +/** + * virtio_iommu_probe - Fill the probe request buffer with + * the properties the device is able to return + */ +static int virtio_iommu_probe(VirtIOIOMMU *s, + struct virtio_iommu_req_probe *req, + uint8_t *buf) +{ + uint32_t ep_id = le32_to_cpu(req->endpoint); + size_t free = VIOMMU_PROBE_SIZE; + ssize_t count; + + if (!virtio_iommu_mr(s, ep_id)) { + return VIRTIO_IOMMU_S_NOENT; + } + + count = virtio_iommu_fill_resv_mem_prop(s, ep_id, buf, free); + if (count < 0) { + return VIRTIO_IOMMU_S_INVAL; + } + buf += count; + free -= count; + + return VIRTIO_IOMMU_S_OK; +} + static int virtio_iommu_iov_to_req(struct iovec *iov, unsigned int iov_cnt, void *req, size_t req_sz) @@ -407,15 +467,27 @@ virtio_iommu_handle_req(detach) virtio_iommu_handle_req(map) virtio_iommu_handle_req(unmap) +static int virtio_iommu_handle_probe(VirtIOIOMMU *s, + struct iovec *iov, + unsigned int iov_cnt, + uint8_t *buf) +{ + struct virtio_iommu_req_probe req; + int ret = virtio_iommu_iov_to_req(iov, iov_cnt, &req, sizeof(req)); + + return ret ? ret : virtio_iommu_probe(s, &req, buf); +} + static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq) { VirtIOIOMMU *s = VIRTIO_IOMMU(vdev); struct virtio_iommu_req_head head; struct virtio_iommu_req_tail tail = {}; + size_t output_size = sizeof(tail), sz; VirtQueueElement *elem; unsigned int iov_cnt; struct iovec *iov; - size_t sz; + void *buf = NULL; for (;;) { elem = virtqueue_pop(vq, sizeof(VirtQueueElement)); @@ -452,6 +524,17 @@ static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq) case VIRTIO_IOMMU_T_UNMAP: tail.status = virtio_iommu_handle_unmap(s, iov, iov_cnt); break; + case VIRTIO_IOMMU_T_PROBE: + { + struct virtio_iommu_req_tail *ptail; + + output_size = s->config.probe_size + sizeof(tail); + buf = g_malloc0(output_size); + + ptail = (struct virtio_iommu_req_tail *) + (buf + s->config.probe_size); + ptail->status = virtio_iommu_handle_probe(s, iov, iov_cnt, buf); + } default: tail.status = VIRTIO_IOMMU_S_UNSUPP; } @@ -459,12 +542,13 @@ static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq) out: sz = iov_from_buf(elem->in_sg, elem->in_num, 0, - &tail, sizeof(tail)); - assert(sz == sizeof(tail)); + buf ? buf : &tail, output_size); + assert(sz == output_size); - virtqueue_push(vq, elem, sizeof(tail)); + virtqueue_push(vq, elem, sz); virtio_notify(vdev, vq); g_free(elem); + g_free(buf); } } @@ -523,6 +607,7 @@ static IOMMUTLBEntry virtio_iommu_translate(IOMMUMemoryRegion *mr, hwaddr addr, uint32_t sid, flags; bool bypass_allowed; bool found; + int i; interval.low = addr; interval.high = addr + 1; @@ -556,6 +641,25 @@ static IOMMUTLBEntry virtio_iommu_translate(IOMMUMemoryRegion *mr, hwaddr addr, goto unlock; } + for (i = 0; i < s->nb_reserved_regions; i++) { + ReservedRegion *reg = &s->reserved_regions[i]; + + if (addr >= reg->low && addr <= reg->high) { + switch (reg->type) { + case VIRTIO_IOMMU_RESV_MEM_T_MSI: + entry.perm = flag; + break; + case VIRTIO_IOMMU_RESV_MEM_T_RESERVED: + default: + virtio_iommu_report_fault(s, VIRTIO_IOMMU_FAULT_R_MAPPING, + VIRTIO_IOMMU_FAULT_F_ADDRESS, + sid, addr); + break; + } + goto unlock; + } + } + if (!ep->domain) { if (!bypass_allowed) { error_report_once("%s %02x:%02x.%01x not attached to any domain", @@ -667,6 +771,7 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) s->config.page_size_mask = TARGET_PAGE_MASK; s->config.input_range.end = -1UL; s->config.domain_range.end = 32; + s->config.probe_size = VIOMMU_PROBE_SIZE; virtio_add_feature(&s->features, VIRTIO_RING_F_EVENT_IDX); virtio_add_feature(&s->features, VIRTIO_RING_F_INDIRECT_DESC); @@ -676,6 +781,7 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) virtio_add_feature(&s->features, VIRTIO_IOMMU_F_MAP_UNMAP); virtio_add_feature(&s->features, VIRTIO_IOMMU_F_BYPASS); virtio_add_feature(&s->features, VIRTIO_IOMMU_F_MMIO); + virtio_add_feature(&s->features, VIRTIO_IOMMU_F_PROBE); qemu_mutex_init(&s->mutex); diff --git a/hw/virtio/virtio-mem-pci.c b/hw/virtio/virtio-mem-pci.c new file mode 100644 index 0000000000..1a8e854123 --- /dev/null +++ b/hw/virtio/virtio-mem-pci.c @@ -0,0 +1,157 @@ +/* + * Virtio MEM PCI device + * + * Copyright (C) 2020 Red Hat, Inc. + * + * Authors: + * David Hildenbrand <david@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "virtio-mem-pci.h" +#include "hw/mem/memory-device.h" +#include "qapi/error.h" +#include "qapi/qapi-events-misc.h" + +static void virtio_mem_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VirtIOMEMPCI *mem_pci = VIRTIO_MEM_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&mem_pci->vdev); + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static void virtio_mem_pci_set_addr(MemoryDeviceState *md, uint64_t addr, + Error **errp) +{ + object_property_set_uint(OBJECT(md), addr, VIRTIO_MEM_ADDR_PROP, errp); +} + +static uint64_t virtio_mem_pci_get_addr(const MemoryDeviceState *md) +{ + return object_property_get_uint(OBJECT(md), VIRTIO_MEM_ADDR_PROP, + &error_abort); +} + +static MemoryRegion *virtio_mem_pci_get_memory_region(MemoryDeviceState *md, + Error **errp) +{ + VirtIOMEMPCI *pci_mem = VIRTIO_MEM_PCI(md); + VirtIOMEM *vmem = VIRTIO_MEM(&pci_mem->vdev); + VirtIOMEMClass *vmc = VIRTIO_MEM_GET_CLASS(vmem); + + return vmc->get_memory_region(vmem, errp); +} + +static uint64_t virtio_mem_pci_get_plugged_size(const MemoryDeviceState *md, + Error **errp) +{ + return object_property_get_uint(OBJECT(md), VIRTIO_MEM_SIZE_PROP, + errp); +} + +static void virtio_mem_pci_fill_device_info(const MemoryDeviceState *md, + MemoryDeviceInfo *info) +{ + VirtioMEMDeviceInfo *vi = g_new0(VirtioMEMDeviceInfo, 1); + VirtIOMEMPCI *pci_mem = VIRTIO_MEM_PCI(md); + VirtIOMEM *vmem = VIRTIO_MEM(&pci_mem->vdev); + VirtIOMEMClass *vpc = VIRTIO_MEM_GET_CLASS(vmem); + DeviceState *dev = DEVICE(md); + + if (dev->id) { + vi->has_id = true; + vi->id = g_strdup(dev->id); + } + + /* let the real device handle everything else */ + vpc->fill_device_info(vmem, vi); + + info->u.virtio_mem.data = vi; + info->type = MEMORY_DEVICE_INFO_KIND_VIRTIO_MEM; +} + +static void virtio_mem_pci_size_change_notify(Notifier *notifier, void *data) +{ + VirtIOMEMPCI *pci_mem = container_of(notifier, VirtIOMEMPCI, + size_change_notifier); + DeviceState *dev = DEVICE(pci_mem); + const uint64_t * const size_p = data; + const char *id = NULL; + + if (dev->id) { + id = g_strdup(dev->id); + } + + qapi_event_send_memory_device_size_change(!!id, id, *size_p); +} + +static void virtio_mem_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + MemoryDeviceClass *mdc = MEMORY_DEVICE_CLASS(klass); + + k->realize = virtio_mem_pci_realize; + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_MEM; + pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; + pcidev_k->class_id = PCI_CLASS_OTHERS; + + mdc->get_addr = virtio_mem_pci_get_addr; + mdc->set_addr = virtio_mem_pci_set_addr; + mdc->get_plugged_size = virtio_mem_pci_get_plugged_size; + mdc->get_memory_region = virtio_mem_pci_get_memory_region; + mdc->fill_device_info = virtio_mem_pci_fill_device_info; +} + +static void virtio_mem_pci_instance_init(Object *obj) +{ + VirtIOMEMPCI *dev = VIRTIO_MEM_PCI(obj); + VirtIOMEMClass *vmc; + VirtIOMEM *vmem; + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_MEM); + + dev->size_change_notifier.notify = virtio_mem_pci_size_change_notify; + vmem = VIRTIO_MEM(&dev->vdev); + vmc = VIRTIO_MEM_GET_CLASS(vmem); + /* + * We never remove the notifier again, as we expect both devices to + * disappear at the same time. + */ + vmc->add_size_change_notifier(vmem, &dev->size_change_notifier); + + object_property_add_alias(obj, VIRTIO_MEM_BLOCK_SIZE_PROP, + OBJECT(&dev->vdev), VIRTIO_MEM_BLOCK_SIZE_PROP); + object_property_add_alias(obj, VIRTIO_MEM_SIZE_PROP, OBJECT(&dev->vdev), + VIRTIO_MEM_SIZE_PROP); + object_property_add_alias(obj, VIRTIO_MEM_REQUESTED_SIZE_PROP, + OBJECT(&dev->vdev), + VIRTIO_MEM_REQUESTED_SIZE_PROP); +} + +static const VirtioPCIDeviceTypeInfo virtio_mem_pci_info = { + .base_name = TYPE_VIRTIO_MEM_PCI, + .generic_name = "virtio-mem-pci", + .instance_size = sizeof(VirtIOMEMPCI), + .instance_init = virtio_mem_pci_instance_init, + .class_init = virtio_mem_pci_class_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_MEMORY_DEVICE }, + { } + }, +}; + +static void virtio_mem_pci_register_types(void) +{ + virtio_pci_types_register(&virtio_mem_pci_info); +} +type_init(virtio_mem_pci_register_types) diff --git a/hw/virtio/virtio-mem-pci.h b/hw/virtio/virtio-mem-pci.h new file mode 100644 index 0000000000..b51a28b275 --- /dev/null +++ b/hw/virtio/virtio-mem-pci.h @@ -0,0 +1,34 @@ +/* + * Virtio MEM PCI device + * + * Copyright (C) 2020 Red Hat, Inc. + * + * Authors: + * David Hildenbrand <david@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. + * See the COPYING file in the top-level directory. + */ + +#ifndef QEMU_VIRTIO_MEM_PCI_H +#define QEMU_VIRTIO_MEM_PCI_H + +#include "hw/virtio/virtio-pci.h" +#include "hw/virtio/virtio-mem.h" + +typedef struct VirtIOMEMPCI VirtIOMEMPCI; + +/* + * virtio-mem-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VIRTIO_MEM_PCI "virtio-mem-pci-base" +#define VIRTIO_MEM_PCI(obj) \ + OBJECT_CHECK(VirtIOMEMPCI, (obj), TYPE_VIRTIO_MEM_PCI) + +struct VirtIOMEMPCI { + VirtIOPCIProxy parent_obj; + VirtIOMEM vdev; + Notifier size_change_notifier; +}; + +#endif /* QEMU_VIRTIO_MEM_PCI_H */ diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c new file mode 100644 index 0000000000..65850530e7 --- /dev/null +++ b/hw/virtio/virtio-mem.c @@ -0,0 +1,873 @@ +/* + * Virtio MEM device + * + * Copyright (C) 2020 Red Hat, Inc. + * + * Authors: + * David Hildenbrand <david@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/iov.h" +#include "qemu/cutils.h" +#include "qemu/error-report.h" +#include "qemu/units.h" +#include "sysemu/numa.h" +#include "sysemu/sysemu.h" +#include "sysemu/reset.h" +#include "hw/virtio/virtio.h" +#include "hw/virtio/virtio-bus.h" +#include "hw/virtio/virtio-access.h" +#include "hw/virtio/virtio-mem.h" +#include "qapi/error.h" +#include "qapi/visitor.h" +#include "exec/ram_addr.h" +#include "migration/misc.h" +#include "hw/boards.h" +#include "hw/qdev-properties.h" +#include "config-devices.h" +#include "trace.h" + +/* + * Use QEMU_VMALLOC_ALIGN, so no THP will have to be split when unplugging + * memory (e.g., 2MB on x86_64). + */ +#define VIRTIO_MEM_MIN_BLOCK_SIZE QEMU_VMALLOC_ALIGN +/* + * Size the usable region bigger than the requested size if possible. Esp. + * Linux guests will only add (aligned) memory blocks in case they fully + * fit into the usable region, but plug+online only a subset of the pages. + * The memory block size corresponds mostly to the section size. + * + * This allows e.g., to add 20MB with a section size of 128MB on x86_64, and + * a section size of 1GB on arm64 (as long as the start address is properly + * aligned, similar to ordinary DIMMs). + * + * We can change this at any time and maybe even make it configurable if + * necessary (as the section size can change). But it's more likely that the + * section size will rather get smaller and not bigger over time. + */ +#if defined(TARGET_X86_64) || defined(TARGET_I386) +#define VIRTIO_MEM_USABLE_EXTENT (2 * (128 * MiB)) +#else +#error VIRTIO_MEM_USABLE_EXTENT not defined +#endif + +static bool virtio_mem_is_busy(void) +{ + /* + * Postcopy cannot handle concurrent discards and we don't want to migrate + * pages on-demand with stale content when plugging new blocks. + * + * For precopy, we don't want unplugged blocks in our migration stream, and + * when plugging new blocks, the page content might differ between source + * and destination (observable by the guest when not initializing pages + * after plugging them) until we're running on the destination (as we didn't + * migrate these blocks when they were unplugged). + */ + return migration_in_incoming_postcopy() || !migration_is_idle(); +} + +static bool virtio_mem_test_bitmap(VirtIOMEM *vmem, uint64_t start_gpa, + uint64_t size, bool plugged) +{ + const unsigned long first_bit = (start_gpa - vmem->addr) / vmem->block_size; + const unsigned long last_bit = first_bit + (size / vmem->block_size) - 1; + unsigned long found_bit; + + /* We fake a shorter bitmap to avoid searching too far. */ + if (plugged) { + found_bit = find_next_zero_bit(vmem->bitmap, last_bit + 1, first_bit); + } else { + found_bit = find_next_bit(vmem->bitmap, last_bit + 1, first_bit); + } + return found_bit > last_bit; +} + +static void virtio_mem_set_bitmap(VirtIOMEM *vmem, uint64_t start_gpa, + uint64_t size, bool plugged) +{ + const unsigned long bit = (start_gpa - vmem->addr) / vmem->block_size; + const unsigned long nbits = size / vmem->block_size; + + if (plugged) { + bitmap_set(vmem->bitmap, bit, nbits); + } else { + bitmap_clear(vmem->bitmap, bit, nbits); + } +} + +static void virtio_mem_send_response(VirtIOMEM *vmem, VirtQueueElement *elem, + struct virtio_mem_resp *resp) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(vmem); + VirtQueue *vq = vmem->vq; + + trace_virtio_mem_send_response(le16_to_cpu(resp->type)); + iov_from_buf(elem->in_sg, elem->in_num, 0, resp, sizeof(*resp)); + + virtqueue_push(vq, elem, sizeof(*resp)); + virtio_notify(vdev, vq); +} + +static void virtio_mem_send_response_simple(VirtIOMEM *vmem, + VirtQueueElement *elem, + uint16_t type) +{ + struct virtio_mem_resp resp = { + .type = cpu_to_le16(type), + }; + + virtio_mem_send_response(vmem, elem, &resp); +} + +static bool virtio_mem_valid_range(VirtIOMEM *vmem, uint64_t gpa, uint64_t size) +{ + if (!QEMU_IS_ALIGNED(gpa, vmem->block_size)) { + return false; + } + if (gpa + size < gpa || !size) { + return false; + } + if (gpa < vmem->addr || gpa >= vmem->addr + vmem->usable_region_size) { + return false; + } + if (gpa + size > vmem->addr + vmem->usable_region_size) { + return false; + } + return true; +} + +static int virtio_mem_set_block_state(VirtIOMEM *vmem, uint64_t start_gpa, + uint64_t size, bool plug) +{ + const uint64_t offset = start_gpa - vmem->addr; + int ret; + + if (virtio_mem_is_busy()) { + return -EBUSY; + } + + if (!plug) { + ret = ram_block_discard_range(vmem->memdev->mr.ram_block, offset, size); + if (ret) { + error_report("Unexpected error discarding RAM: %s", + strerror(-ret)); + return -EBUSY; + } + } + virtio_mem_set_bitmap(vmem, start_gpa, size, plug); + return 0; +} + +static int virtio_mem_state_change_request(VirtIOMEM *vmem, uint64_t gpa, + uint16_t nb_blocks, bool plug) +{ + const uint64_t size = nb_blocks * vmem->block_size; + int ret; + + if (!virtio_mem_valid_range(vmem, gpa, size)) { + return VIRTIO_MEM_RESP_ERROR; + } + + if (plug && (vmem->size + size > vmem->requested_size)) { + return VIRTIO_MEM_RESP_NACK; + } + + /* test if really all blocks are in the opposite state */ + if (!virtio_mem_test_bitmap(vmem, gpa, size, !plug)) { + return VIRTIO_MEM_RESP_ERROR; + } + + ret = virtio_mem_set_block_state(vmem, gpa, size, plug); + if (ret) { + return VIRTIO_MEM_RESP_BUSY; + } + if (plug) { + vmem->size += size; + } else { + vmem->size -= size; + } + notifier_list_notify(&vmem->size_change_notifiers, &vmem->size); + return VIRTIO_MEM_RESP_ACK; +} + +static void virtio_mem_plug_request(VirtIOMEM *vmem, VirtQueueElement *elem, + struct virtio_mem_req *req) +{ + const uint64_t gpa = le64_to_cpu(req->u.plug.addr); + const uint16_t nb_blocks = le16_to_cpu(req->u.plug.nb_blocks); + uint16_t type; + + trace_virtio_mem_plug_request(gpa, nb_blocks); + type = virtio_mem_state_change_request(vmem, gpa, nb_blocks, true); + virtio_mem_send_response_simple(vmem, elem, type); +} + +static void virtio_mem_unplug_request(VirtIOMEM *vmem, VirtQueueElement *elem, + struct virtio_mem_req *req) +{ + const uint64_t gpa = le64_to_cpu(req->u.unplug.addr); + const uint16_t nb_blocks = le16_to_cpu(req->u.unplug.nb_blocks); + uint16_t type; + + trace_virtio_mem_unplug_request(gpa, nb_blocks); + type = virtio_mem_state_change_request(vmem, gpa, nb_blocks, false); + virtio_mem_send_response_simple(vmem, elem, type); +} + +static void virtio_mem_resize_usable_region(VirtIOMEM *vmem, + uint64_t requested_size, + bool can_shrink) +{ + uint64_t newsize = MIN(memory_region_size(&vmem->memdev->mr), + requested_size + VIRTIO_MEM_USABLE_EXTENT); + + if (!requested_size) { + newsize = 0; + } + + if (newsize < vmem->usable_region_size && !can_shrink) { + return; + } + + trace_virtio_mem_resized_usable_region(vmem->usable_region_size, newsize); + vmem->usable_region_size = newsize; +} + +static int virtio_mem_unplug_all(VirtIOMEM *vmem) +{ + RAMBlock *rb = vmem->memdev->mr.ram_block; + int ret; + + if (virtio_mem_is_busy()) { + return -EBUSY; + } + + ret = ram_block_discard_range(rb, 0, qemu_ram_get_used_length(rb)); + if (ret) { + error_report("Unexpected error discarding RAM: %s", strerror(-ret)); + return -EBUSY; + } + bitmap_clear(vmem->bitmap, 0, vmem->bitmap_size); + if (vmem->size) { + vmem->size = 0; + notifier_list_notify(&vmem->size_change_notifiers, &vmem->size); + } + trace_virtio_mem_unplugged_all(); + virtio_mem_resize_usable_region(vmem, vmem->requested_size, true); + return 0; +} + +static void virtio_mem_unplug_all_request(VirtIOMEM *vmem, + VirtQueueElement *elem) +{ + trace_virtio_mem_unplug_all_request(); + if (virtio_mem_unplug_all(vmem)) { + virtio_mem_send_response_simple(vmem, elem, VIRTIO_MEM_RESP_BUSY); + } else { + virtio_mem_send_response_simple(vmem, elem, VIRTIO_MEM_RESP_ACK); + } +} + +static void virtio_mem_state_request(VirtIOMEM *vmem, VirtQueueElement *elem, + struct virtio_mem_req *req) +{ + const uint16_t nb_blocks = le16_to_cpu(req->u.state.nb_blocks); + const uint64_t gpa = le64_to_cpu(req->u.state.addr); + const uint64_t size = nb_blocks * vmem->block_size; + struct virtio_mem_resp resp = { + .type = cpu_to_le16(VIRTIO_MEM_RESP_ACK), + }; + + trace_virtio_mem_state_request(gpa, nb_blocks); + if (!virtio_mem_valid_range(vmem, gpa, size)) { + virtio_mem_send_response_simple(vmem, elem, VIRTIO_MEM_RESP_ERROR); + return; + } + + if (virtio_mem_test_bitmap(vmem, gpa, size, true)) { + resp.u.state.state = cpu_to_le16(VIRTIO_MEM_STATE_PLUGGED); + } else if (virtio_mem_test_bitmap(vmem, gpa, size, false)) { + resp.u.state.state = cpu_to_le16(VIRTIO_MEM_STATE_UNPLUGGED); + } else { + resp.u.state.state = cpu_to_le16(VIRTIO_MEM_STATE_MIXED); + } + trace_virtio_mem_state_response(le16_to_cpu(resp.u.state.state)); + virtio_mem_send_response(vmem, elem, &resp); +} + +static void virtio_mem_handle_request(VirtIODevice *vdev, VirtQueue *vq) +{ + const int len = sizeof(struct virtio_mem_req); + VirtIOMEM *vmem = VIRTIO_MEM(vdev); + VirtQueueElement *elem; + struct virtio_mem_req req; + uint16_t type; + + while (true) { + elem = virtqueue_pop(vq, sizeof(VirtQueueElement)); + if (!elem) { + return; + } + + if (iov_to_buf(elem->out_sg, elem->out_num, 0, &req, len) < len) { + virtio_error(vdev, "virtio-mem protocol violation: invalid request" + " size: %d", len); + g_free(elem); + return; + } + + if (iov_size(elem->in_sg, elem->in_num) < + sizeof(struct virtio_mem_resp)) { + virtio_error(vdev, "virtio-mem protocol violation: not enough space" + " for response: %zu", + iov_size(elem->in_sg, elem->in_num)); + g_free(elem); + return; + } + + type = le16_to_cpu(req.type); + switch (type) { + case VIRTIO_MEM_REQ_PLUG: + virtio_mem_plug_request(vmem, elem, &req); + break; + case VIRTIO_MEM_REQ_UNPLUG: + virtio_mem_unplug_request(vmem, elem, &req); + break; + case VIRTIO_MEM_REQ_UNPLUG_ALL: + virtio_mem_unplug_all_request(vmem, elem); + break; + case VIRTIO_MEM_REQ_STATE: + virtio_mem_state_request(vmem, elem, &req); + break; + default: + virtio_error(vdev, "virtio-mem protocol violation: unknown request" + " type: %d", type); + g_free(elem); + return; + } + + g_free(elem); + } +} + +static void virtio_mem_get_config(VirtIODevice *vdev, uint8_t *config_data) +{ + VirtIOMEM *vmem = VIRTIO_MEM(vdev); + struct virtio_mem_config *config = (void *) config_data; + + config->block_size = cpu_to_le64(vmem->block_size); + config->node_id = cpu_to_le16(vmem->node); + config->requested_size = cpu_to_le64(vmem->requested_size); + config->plugged_size = cpu_to_le64(vmem->size); + config->addr = cpu_to_le64(vmem->addr); + config->region_size = cpu_to_le64(memory_region_size(&vmem->memdev->mr)); + config->usable_region_size = cpu_to_le64(vmem->usable_region_size); +} + +static uint64_t virtio_mem_get_features(VirtIODevice *vdev, uint64_t features, + Error **errp) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + + if (ms->numa_state) { +#if defined(CONFIG_ACPI) + virtio_add_feature(&features, VIRTIO_MEM_F_ACPI_PXM); +#endif + } + return features; +} + +static void virtio_mem_system_reset(void *opaque) +{ + VirtIOMEM *vmem = VIRTIO_MEM(opaque); + + /* + * During usual resets, we will unplug all memory and shrink the usable + * region size. This is, however, not possible in all scenarios. Then, + * the guest has to deal with this manually (VIRTIO_MEM_REQ_UNPLUG_ALL). + */ + virtio_mem_unplug_all(vmem); +} + +static void virtio_mem_device_realize(DeviceState *dev, Error **errp) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + int nb_numa_nodes = ms->numa_state ? ms->numa_state->num_nodes : 0; + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VirtIOMEM *vmem = VIRTIO_MEM(dev); + uint64_t page_size; + RAMBlock *rb; + int ret; + + if (!vmem->memdev) { + error_setg(errp, "'%s' property is not set", VIRTIO_MEM_MEMDEV_PROP); + return; + } else if (host_memory_backend_is_mapped(vmem->memdev)) { + char *path = object_get_canonical_path_component(OBJECT(vmem->memdev)); + + error_setg(errp, "'%s' property specifies a busy memdev: %s", + VIRTIO_MEM_MEMDEV_PROP, path); + g_free(path); + return; + } else if (!memory_region_is_ram(&vmem->memdev->mr) || + memory_region_is_rom(&vmem->memdev->mr) || + !vmem->memdev->mr.ram_block) { + error_setg(errp, "'%s' property specifies an unsupported memdev", + VIRTIO_MEM_MEMDEV_PROP); + return; + } + + if ((nb_numa_nodes && vmem->node >= nb_numa_nodes) || + (!nb_numa_nodes && vmem->node)) { + error_setg(errp, "'%s' property has value '%" PRIu32 "', which exceeds" + "the number of numa nodes: %d", VIRTIO_MEM_NODE_PROP, + vmem->node, nb_numa_nodes ? nb_numa_nodes : 1); + return; + } + + if (enable_mlock) { + error_setg(errp, "Incompatible with mlock"); + return; + } + + rb = vmem->memdev->mr.ram_block; + page_size = qemu_ram_pagesize(rb); + + if (vmem->block_size < page_size) { + error_setg(errp, "'%s' property has to be at least the page size (0x%" + PRIx64 ")", VIRTIO_MEM_BLOCK_SIZE_PROP, page_size); + return; + } else if (!QEMU_IS_ALIGNED(vmem->requested_size, vmem->block_size)) { + error_setg(errp, "'%s' property has to be multiples of '%s' (0x%" PRIx64 + ")", VIRTIO_MEM_REQUESTED_SIZE_PROP, + VIRTIO_MEM_BLOCK_SIZE_PROP, vmem->block_size); + return; + } else if (!QEMU_IS_ALIGNED(memory_region_size(&vmem->memdev->mr), + vmem->block_size)) { + error_setg(errp, "'%s' property memdev size has to be multiples of" + "'%s' (0x%" PRIx64 ")", VIRTIO_MEM_MEMDEV_PROP, + VIRTIO_MEM_BLOCK_SIZE_PROP, vmem->block_size); + return; + } + + if (ram_block_discard_require(true)) { + error_setg(errp, "Discarding RAM is disabled"); + return; + } + + ret = ram_block_discard_range(rb, 0, qemu_ram_get_used_length(rb)); + if (ret) { + error_setg_errno(errp, -ret, "Unexpected error discarding RAM"); + ram_block_discard_require(false); + return; + } + + virtio_mem_resize_usable_region(vmem, vmem->requested_size, true); + + vmem->bitmap_size = memory_region_size(&vmem->memdev->mr) / + vmem->block_size; + vmem->bitmap = bitmap_new(vmem->bitmap_size); + + virtio_init(vdev, TYPE_VIRTIO_MEM, VIRTIO_ID_MEM, + sizeof(struct virtio_mem_config)); + vmem->vq = virtio_add_queue(vdev, 128, virtio_mem_handle_request); + + host_memory_backend_set_mapped(vmem->memdev, true); + vmstate_register_ram(&vmem->memdev->mr, DEVICE(vmem)); + qemu_register_reset(virtio_mem_system_reset, vmem); + precopy_add_notifier(&vmem->precopy_notifier); +} + +static void virtio_mem_device_unrealize(DeviceState *dev) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VirtIOMEM *vmem = VIRTIO_MEM(dev); + + precopy_remove_notifier(&vmem->precopy_notifier); + qemu_unregister_reset(virtio_mem_system_reset, vmem); + vmstate_unregister_ram(&vmem->memdev->mr, DEVICE(vmem)); + host_memory_backend_set_mapped(vmem->memdev, false); + virtio_del_queue(vdev, 0); + virtio_cleanup(vdev); + g_free(vmem->bitmap); + ram_block_discard_require(false); +} + +static int virtio_mem_restore_unplugged(VirtIOMEM *vmem) +{ + RAMBlock *rb = vmem->memdev->mr.ram_block; + unsigned long first_zero_bit, last_zero_bit; + uint64_t offset, length; + int ret; + + /* Find consecutive unplugged blocks and discard the consecutive range. */ + first_zero_bit = find_first_zero_bit(vmem->bitmap, vmem->bitmap_size); + while (first_zero_bit < vmem->bitmap_size) { + offset = first_zero_bit * vmem->block_size; + last_zero_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size, + first_zero_bit + 1) - 1; + length = (last_zero_bit - first_zero_bit + 1) * vmem->block_size; + + ret = ram_block_discard_range(rb, offset, length); + if (ret) { + error_report("Unexpected error discarding RAM: %s", + strerror(-ret)); + return -EINVAL; + } + first_zero_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size, + last_zero_bit + 2); + } + return 0; +} + +static int virtio_mem_post_load(void *opaque, int version_id) +{ + if (migration_in_incoming_postcopy()) { + return 0; + } + + return virtio_mem_restore_unplugged(VIRTIO_MEM(opaque)); +} + +typedef struct VirtIOMEMMigSanityChecks { + VirtIOMEM *parent; + uint64_t addr; + uint64_t region_size; + uint64_t block_size; + uint32_t node; +} VirtIOMEMMigSanityChecks; + +static int virtio_mem_mig_sanity_checks_pre_save(void *opaque) +{ + VirtIOMEMMigSanityChecks *tmp = opaque; + VirtIOMEM *vmem = tmp->parent; + + tmp->addr = vmem->addr; + tmp->region_size = memory_region_size(&vmem->memdev->mr); + tmp->block_size = vmem->block_size; + tmp->node = vmem->node; + return 0; +} + +static int virtio_mem_mig_sanity_checks_post_load(void *opaque, int version_id) +{ + VirtIOMEMMigSanityChecks *tmp = opaque; + VirtIOMEM *vmem = tmp->parent; + const uint64_t new_region_size = memory_region_size(&vmem->memdev->mr); + + if (tmp->addr != vmem->addr) { + error_report("Property '%s' changed from 0x%" PRIx64 " to 0x%" PRIx64, + VIRTIO_MEM_ADDR_PROP, tmp->addr, vmem->addr); + return -EINVAL; + } + /* + * Note: Preparation for resizeable memory regions. The maximum size + * of the memory region must not change during migration. + */ + if (tmp->region_size != new_region_size) { + error_report("Property '%s' size changed from 0x%" PRIx64 " to 0x%" + PRIx64, VIRTIO_MEM_MEMDEV_PROP, tmp->region_size, + new_region_size); + return -EINVAL; + } + if (tmp->block_size != vmem->block_size) { + error_report("Property '%s' changed from 0x%" PRIx64 " to 0x%" PRIx64, + VIRTIO_MEM_BLOCK_SIZE_PROP, tmp->block_size, + vmem->block_size); + return -EINVAL; + } + if (tmp->node != vmem->node) { + error_report("Property '%s' changed from %" PRIu32 " to %" PRIu32, + VIRTIO_MEM_NODE_PROP, tmp->node, vmem->node); + return -EINVAL; + } + return 0; +} + +static const VMStateDescription vmstate_virtio_mem_sanity_checks = { + .name = "virtio-mem-device/sanity-checks", + .pre_save = virtio_mem_mig_sanity_checks_pre_save, + .post_load = virtio_mem_mig_sanity_checks_post_load, + .fields = (VMStateField[]) { + VMSTATE_UINT64(addr, VirtIOMEMMigSanityChecks), + VMSTATE_UINT64(region_size, VirtIOMEMMigSanityChecks), + VMSTATE_UINT64(block_size, VirtIOMEMMigSanityChecks), + VMSTATE_UINT32(node, VirtIOMEMMigSanityChecks), + VMSTATE_END_OF_LIST(), + }, +}; + +static const VMStateDescription vmstate_virtio_mem_device = { + .name = "virtio-mem-device", + .minimum_version_id = 1, + .version_id = 1, + .post_load = virtio_mem_post_load, + .fields = (VMStateField[]) { + VMSTATE_WITH_TMP(VirtIOMEM, VirtIOMEMMigSanityChecks, + vmstate_virtio_mem_sanity_checks), + VMSTATE_UINT64(usable_region_size, VirtIOMEM), + VMSTATE_UINT64(size, VirtIOMEM), + VMSTATE_UINT64(requested_size, VirtIOMEM), + VMSTATE_BITMAP(bitmap, VirtIOMEM, 0, bitmap_size), + VMSTATE_END_OF_LIST() + }, +}; + +static const VMStateDescription vmstate_virtio_mem = { + .name = "virtio-mem", + .minimum_version_id = 1, + .version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_VIRTIO_DEVICE, + VMSTATE_END_OF_LIST() + }, +}; + +static void virtio_mem_fill_device_info(const VirtIOMEM *vmem, + VirtioMEMDeviceInfo *vi) +{ + vi->memaddr = vmem->addr; + vi->node = vmem->node; + vi->requested_size = vmem->requested_size; + vi->size = vmem->size; + vi->max_size = memory_region_size(&vmem->memdev->mr); + vi->block_size = vmem->block_size; + vi->memdev = object_get_canonical_path(OBJECT(vmem->memdev)); +} + +static MemoryRegion *virtio_mem_get_memory_region(VirtIOMEM *vmem, Error **errp) +{ + if (!vmem->memdev) { + error_setg(errp, "'%s' property must be set", VIRTIO_MEM_MEMDEV_PROP); + return NULL; + } + + return &vmem->memdev->mr; +} + +static void virtio_mem_add_size_change_notifier(VirtIOMEM *vmem, + Notifier *notifier) +{ + notifier_list_add(&vmem->size_change_notifiers, notifier); +} + +static void virtio_mem_remove_size_change_notifier(VirtIOMEM *vmem, + Notifier *notifier) +{ + notifier_remove(notifier); +} + +static void virtio_mem_get_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + const VirtIOMEM *vmem = VIRTIO_MEM(obj); + uint64_t value = vmem->size; + + visit_type_size(v, name, &value, errp); +} + +static void virtio_mem_get_requested_size(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + const VirtIOMEM *vmem = VIRTIO_MEM(obj); + uint64_t value = vmem->requested_size; + + visit_type_size(v, name, &value, errp); +} + +static void virtio_mem_set_requested_size(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + VirtIOMEM *vmem = VIRTIO_MEM(obj); + Error *err = NULL; + uint64_t value; + + visit_type_size(v, name, &value, &err); + if (err) { + error_propagate(errp, err); + return; + } + + /* + * The block size and memory backend are not fixed until the device was + * realized. realize() will verify these properties then. + */ + if (DEVICE(obj)->realized) { + if (!QEMU_IS_ALIGNED(value, vmem->block_size)) { + error_setg(errp, "'%s' has to be multiples of '%s' (0x%" PRIx64 + ")", name, VIRTIO_MEM_BLOCK_SIZE_PROP, + vmem->block_size); + return; + } else if (value > memory_region_size(&vmem->memdev->mr)) { + error_setg(errp, "'%s' cannot exceed the memory backend size" + "(0x%" PRIx64 ")", name, + memory_region_size(&vmem->memdev->mr)); + return; + } + + if (value != vmem->requested_size) { + virtio_mem_resize_usable_region(vmem, value, false); + vmem->requested_size = value; + } + /* + * Trigger a config update so the guest gets notified. We trigger + * even if the size didn't change (especially helpful for debugging). + */ + virtio_notify_config(VIRTIO_DEVICE(vmem)); + } else { + vmem->requested_size = value; + } +} + +static void virtio_mem_get_block_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + const VirtIOMEM *vmem = VIRTIO_MEM(obj); + uint64_t value = vmem->block_size; + + visit_type_size(v, name, &value, errp); +} + +static void virtio_mem_set_block_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + VirtIOMEM *vmem = VIRTIO_MEM(obj); + Error *err = NULL; + uint64_t value; + + if (DEVICE(obj)->realized) { + error_setg(errp, "'%s' cannot be changed", name); + return; + } + + visit_type_size(v, name, &value, &err); + if (err) { + error_propagate(errp, err); + return; + } + + if (value < VIRTIO_MEM_MIN_BLOCK_SIZE) { + error_setg(errp, "'%s' property has to be at least 0x%" PRIx32, name, + VIRTIO_MEM_MIN_BLOCK_SIZE); + return; + } else if (!is_power_of_2(value)) { + error_setg(errp, "'%s' property has to be a power of two", name); + return; + } + vmem->block_size = value; +} + +static void virtio_mem_precopy_exclude_unplugged(VirtIOMEM *vmem) +{ + void * const host = qemu_ram_get_host_addr(vmem->memdev->mr.ram_block); + unsigned long first_zero_bit, last_zero_bit; + uint64_t offset, length; + + /* + * Find consecutive unplugged blocks and exclude them from migration. + * + * Note: Blocks cannot get (un)plugged during precopy, no locking needed. + */ + first_zero_bit = find_first_zero_bit(vmem->bitmap, vmem->bitmap_size); + while (first_zero_bit < vmem->bitmap_size) { + offset = first_zero_bit * vmem->block_size; + last_zero_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size, + first_zero_bit + 1) - 1; + length = (last_zero_bit - first_zero_bit + 1) * vmem->block_size; + + qemu_guest_free_page_hint(host + offset, length); + first_zero_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size, + last_zero_bit + 2); + } +} + +static int virtio_mem_precopy_notify(NotifierWithReturn *n, void *data) +{ + VirtIOMEM *vmem = container_of(n, VirtIOMEM, precopy_notifier); + PrecopyNotifyData *pnd = data; + + switch (pnd->reason) { + case PRECOPY_NOTIFY_SETUP: + precopy_enable_free_page_optimization(); + break; + case PRECOPY_NOTIFY_AFTER_BITMAP_SYNC: + virtio_mem_precopy_exclude_unplugged(vmem); + break; + default: + break; + } + + return 0; +} + +static void virtio_mem_instance_init(Object *obj) +{ + VirtIOMEM *vmem = VIRTIO_MEM(obj); + + vmem->block_size = VIRTIO_MEM_MIN_BLOCK_SIZE; + notifier_list_init(&vmem->size_change_notifiers); + vmem->precopy_notifier.notify = virtio_mem_precopy_notify; + + object_property_add(obj, VIRTIO_MEM_SIZE_PROP, "size", virtio_mem_get_size, + NULL, NULL, NULL); + object_property_add(obj, VIRTIO_MEM_REQUESTED_SIZE_PROP, "size", + virtio_mem_get_requested_size, + virtio_mem_set_requested_size, NULL, NULL); + object_property_add(obj, VIRTIO_MEM_BLOCK_SIZE_PROP, "size", + virtio_mem_get_block_size, virtio_mem_set_block_size, + NULL, NULL); +} + +static Property virtio_mem_properties[] = { + DEFINE_PROP_UINT64(VIRTIO_MEM_ADDR_PROP, VirtIOMEM, addr, 0), + DEFINE_PROP_UINT32(VIRTIO_MEM_NODE_PROP, VirtIOMEM, node, 0), + DEFINE_PROP_LINK(VIRTIO_MEM_MEMDEV_PROP, VirtIOMEM, memdev, + TYPE_MEMORY_BACKEND, HostMemoryBackend *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void virtio_mem_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); + VirtIOMEMClass *vmc = VIRTIO_MEM_CLASS(klass); + + device_class_set_props(dc, virtio_mem_properties); + dc->vmsd = &vmstate_virtio_mem; + + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + vdc->realize = virtio_mem_device_realize; + vdc->unrealize = virtio_mem_device_unrealize; + vdc->get_config = virtio_mem_get_config; + vdc->get_features = virtio_mem_get_features; + vdc->vmsd = &vmstate_virtio_mem_device; + + vmc->fill_device_info = virtio_mem_fill_device_info; + vmc->get_memory_region = virtio_mem_get_memory_region; + vmc->add_size_change_notifier = virtio_mem_add_size_change_notifier; + vmc->remove_size_change_notifier = virtio_mem_remove_size_change_notifier; +} + +static const TypeInfo virtio_mem_info = { + .name = TYPE_VIRTIO_MEM, + .parent = TYPE_VIRTIO_DEVICE, + .instance_size = sizeof(VirtIOMEM), + .instance_init = virtio_mem_instance_init, + .class_init = virtio_mem_class_init, + .class_size = sizeof(VirtIOMEMClass), +}; + +static void virtio_register_types(void) +{ + type_register_static(&virtio_mem_info); +} + +type_init(virtio_register_types) diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index 7bc8c1c056..8554cf2a03 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -1107,6 +1107,18 @@ static AddressSpace *virtio_pci_get_dma_as(DeviceState *d) return pci_get_address_space(dev); } +static bool virtio_pci_queue_enabled(DeviceState *d, int n) +{ + VirtIOPCIProxy *proxy = VIRTIO_PCI(d); + VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus); + + if (virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1)) { + return proxy->vqs[vdev->queue_sel].enabled; + } + + return virtio_queue_enabled(vdev, n); +} + static int virtio_pci_add_mem_cap(VirtIOPCIProxy *proxy, struct virtio_pci_cap *cap) { @@ -2064,6 +2076,7 @@ static void virtio_pci_bus_class_init(ObjectClass *klass, void *data) k->ioeventfd_enabled = virtio_pci_ioeventfd_enabled; k->ioeventfd_assign = virtio_pci_ioeventfd_assign; k->get_dma_as = virtio_pci_get_dma_as; + k->queue_enabled = virtio_pci_queue_enabled; } static const TypeInfo virtio_pci_bus_info = { diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index cc9c9dc162..5bd2a2f621 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -3286,6 +3286,12 @@ hwaddr virtio_queue_get_desc_addr(VirtIODevice *vdev, int n) bool virtio_queue_enabled(VirtIODevice *vdev, int n) { + BusState *qbus = qdev_get_parent_bus(DEVICE(vdev)); + VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + + if (k->queue_enabled) { + return k->queue_enabled(qbus->parent, n); + } return virtio_queue_get_desc_addr(vdev, n) != 0; } |