target-arm queue: aspeed patches from Cédric, and cleanup and sd card patches from Philippe. thanks -- PMM The following changes since commit bac5ba3dc5da706f52c149fa6c0bd1dc96899bec: Merge remote-tracking branch 'remotes/thibault/tags/samuel-thibault' into staging (2018-06-08 10:26:16 +0100) are available in the Git repository at: git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20180608 for you to fetch changes up to 113f31c06c6bf16451892b2459d83c9b9c5e9844: sdcard: Disable CMD19/CMD23 for Spec v2 (2018-06-08 13:15:34 +0100) ---------------------------------------------------------------- target-arm queue: * arm_gicv3_kvm: fix migration of registers corresponding to IRQs 992 to 1020 in the KVM GIC * aspeed: remove ignore_memory_transaction_failures on all boards * aspeed: add support for the witherspoon-bmc board * aspeed: add an I2C RTC device and EEPROM I2C devices * aspeed: add the pc9552 chips to the witherspoon machine * ftgmac100: fix various bugs * hw/arm: Remove the deprecated xlnx-ep108 machine * hw/i2c: Add trace events * add missing '\n' on various qemu_log() logging strings * sdcard: clean up spec version support so we report the right spec version to the guest and only implement the commands that are supposed to be present in that version ---------------------------------------------------------------- Cédric Le Goater (11): aspeed: remove ignore_memory_transaction_failures on all boards aspeed: add support for the witherspoon-bmc board aspeed: add an I2C RTC device to all machines smbus: add a smbus_eeprom_init_one() routine aspeed: Add EEPROM I2C devices misc: add pca9552 LED blinker model aspeed: add the pc9552 chips to the witherspoon machine ftgmac100: compute maximum frame size depending on the protocol ftgmac100: add IEEE 802.1Q VLAN support ftgmac100: fix multicast hash routine ftgmac100: remove check on runt messages Philippe Mathieu-Daudé (18): hw/i2c: Add trace events hw/sd/milkymist-memcard: Add trailing '\n' to qemu_log() call hw/digic: Add trailing '\n' to qemu_log() calls xilinx-dp: Add trailing '\n' to qemu_log() call ppc/pnv: Add trailing '\n' to qemu_log() calls hw/core/register: Add trailing '\n' to qemu_log() call hw/mips/boston: Add trailing '\n' to qemu_log() calls stellaris: Add trailing '\n' to qemu_log() calls target/arm: Add trailing '\n' to qemu_log() calls target/m68k: Add trailing '\n' to qemu_log() call RISC-V: Add trailing '\n' to qemu_log() calls target/xtensa: Add trailing '\n' to qemu_log() calls sdcard: Update the Configuration Register (SCR) to Spec Version 1.10 sdcard: Allow commands valid in SPI mode sdcard: Add a 'spec_version' property, default to Spec v2.00 sdcard: Disable SEND_IF_COND (CMD8) for Spec v1 sdcard: Reflect when the Spec v3 is supported in the Config Register (SCR) sdcard: Disable CMD19/CMD23 for Spec v2 Shannon Zhao (1): arm_gicv3_kvm: kvm_dist_get/put: skip the registers banked by GICR Thomas Huth (1): hw/arm: Remove the deprecated xlnx-ep108 machine Makefile.objs | 1 + hw/misc/Makefile.objs | 1 + tests/Makefile.include | 2 + include/hw/i2c/smbus.h | 1 + include/hw/intc/arm_gicv3_common.h | 1 + include/hw/misc/pca9552.h | 32 +++++ include/hw/misc/pca9552_regs.h | 32 +++++ include/hw/net/ftgmac100.h | 7 +- include/hw/sd/sd.h | 6 + tests/libqos/i2c.h | 2 + hw/arm/aspeed.c | 88 +++++++++++++- hw/arm/stellaris.c | 11 +- hw/arm/xlnx-zcu102.c | 62 +--------- hw/char/digic-uart.c | 4 +- hw/core/register.c | 2 +- hw/display/xlnx_dp.c | 4 +- hw/i2c/core.c | 25 ++-- hw/i2c/smbus_eeprom.c | 16 ++- hw/intc/arm_gicv3_common.c | 79 ++++++++++++ hw/intc/arm_gicv3_kvm.c | 38 ++++++ hw/mips/boston.c | 8 +- hw/misc/pca9552.c | 240 +++++++++++++++++++++++++++++++++++++ hw/net/ftgmac100.c | 64 ++++++---- hw/ppc/pnv_core.c | 4 +- hw/sd/milkymist-memcard.c | 2 +- hw/sd/sd.c | 50 +++++--- hw/timer/digic-timer.c | 4 +- target/arm/helper.c | 4 +- target/m68k/translate.c | 2 +- target/riscv/op_helper.c | 6 +- target/xtensa/translate.c | 6 +- tests/pca9552-test.c | 116 ++++++++++++++++++ tests/tmp105-test.c | 2 - default-configs/arm-softmmu.mak | 1 + hw/i2c/trace-events | 7 ++ qemu-doc.texi | 5 - 36 files changed, 788 insertions(+), 147 deletions(-) create mode 100644 include/hw/misc/pca9552.h create mode 100644 include/hw/misc/pca9552_regs.h create mode 100644 hw/misc/pca9552.c create mode 100644 tests/pca9552-test.c create mode 100644 hw/i2c/trace-events From: Shannon Zhao <zhaoshenglong@huawei.com> While we skip the GIC_INTERNAL irqs, we don't change the register offset accordingly. This will overlap the GICR registers value and leave the last GIC_INTERNAL irq's registers out of update. Fix this by skipping the registers banked by GICR. Also for migration compatibility if the migration source (old version qemu) doesn't send gicd_no_migration_shift_bug = 1 to destination, then we shift the data of PPI to get the right data for SPI. Fixes: 367b9f527becdd20ddf116e17a3c0c2bbc486920 Cc: qemu-stable@nongnu.org Reviewed-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Shannon Zhao <zhaoshenglong@huawei.com> Message-id: 1527816987-16108-1-git-send-email-zhaoshenglong@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/intc/arm_gicv3_common.h | 1 + hw/intc/arm_gicv3_common.c | 79 ++++++++++++++++++++++++++++++ hw/intc/arm_gicv3_kvm.c | 38 ++++++++++++++ 3 files changed, 118 insertions(+) diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3State { uint32_t revision; bool security_extn; bool irq_reset_nonsecure; + bool gicd_no_migration_shift_bug; int dev_fd; /* kvm device fd if backed by kvm vgic support */ Error *migration_blocker; diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ #include "hw/intc/arm_gicv3_common.h" #include "gicv3_internal.h" #include "hw/arm/linux-boot-if.h" +#include "sysemu/kvm.h" static int gicv3_pre_save(void *opaque) { @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_gicv3_cpu = { } }; +static int gicv3_gicd_no_migration_shift_bug_pre_load(void *opaque) +{ + GICv3State *cs = opaque; + + /* + * The gicd_no_migration_shift_bug flag is used for migration compatibility + * for old version QEMU which may have the GICD bmp shift bug under KVM mode. + * Strictly, what we want to know is whether the migration source is using + * KVM. Since we don't have any way to determine that, we look at whether the + * destination is using KVM; this is close enough because for the older QEMU + * versions with this bug KVM -> TCG migration didn't work anyway. If the + * source is a newer QEMU without this bug it will transmit the migration + * subsection which sets the flag to true; otherwise it will remain set to + * the value we select here. + */ + if (kvm_enabled()) { + cs->gicd_no_migration_shift_bug = false; + } + + return 0; +} + +static int gicv3_gicd_no_migration_shift_bug_post_load(void *opaque, + int version_id) +{ + GICv3State *cs = opaque; + + if (cs->gicd_no_migration_shift_bug) { + return 0; + } + + /* Older versions of QEMU had a bug in the handling of state save/restore + * to the KVM GICv3: they got the offset in the bitmap arrays wrong, + * so that instead of the data for external interrupts 32 and up + * starting at bit position 32 in the bitmap, it started at bit + * position 64. If we're receiving data from a QEMU with that bug, + * we must move the data down into the right place. + */ + memmove(cs->group, (uint8_t *)cs->group + GIC_INTERNAL / 8, + sizeof(cs->group) - GIC_INTERNAL / 8); + memmove(cs->grpmod, (uint8_t *)cs->grpmod + GIC_INTERNAL / 8, + sizeof(cs->grpmod) - GIC_INTERNAL / 8); + memmove(cs->enabled, (uint8_t *)cs->enabled + GIC_INTERNAL / 8, + sizeof(cs->enabled) - GIC_INTERNAL / 8); + memmove(cs->pending, (uint8_t *)cs->pending + GIC_INTERNAL / 8, + sizeof(cs->pending) - GIC_INTERNAL / 8); + memmove(cs->active, (uint8_t *)cs->active + GIC_INTERNAL / 8, + sizeof(cs->active) - GIC_INTERNAL / 8); + memmove(cs->edge_trigger, (uint8_t *)cs->edge_trigger + GIC_INTERNAL / 8, + sizeof(cs->edge_trigger) - GIC_INTERNAL / 8); + + /* + * While this new version QEMU doesn't have this kind of bug as we fix it, + * so it needs to set the flag to true to indicate that and it's necessary + * for next migration to work from this new version QEMU. + */ + cs->gicd_no_migration_shift_bug = true; + + return 0; +} + +const VMStateDescription vmstate_gicv3_gicd_no_migration_shift_bug = { + .name = "arm_gicv3/gicd_no_migration_shift_bug", + .version_id = 1, + .minimum_version_id = 1, + .pre_load = gicv3_gicd_no_migration_shift_bug_pre_load, + .post_load = gicv3_gicd_no_migration_shift_bug_post_load, + .fields = (VMStateField[]) { + VMSTATE_BOOL(gicd_no_migration_shift_bug, GICv3State), + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_gicv3 = { .name = "arm_gicv3", .version_id = 1, @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_gicv3 = { VMSTATE_STRUCT_VARRAY_POINTER_UINT32(cpu, GICv3State, num_cpu, vmstate_gicv3_cpu, GICv3CPUState), VMSTATE_END_OF_LIST() + }, + .subsections = (const VMStateDescription * []) { + &vmstate_gicv3_gicd_no_migration_shift_bug, + NULL } }; @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_common_reset(DeviceState *dev) gicv3_gicd_group_set(s, i); } } + s->gicd_no_migration_shift_bug = true; } static void arm_gic_common_linux_init(ARMLinuxBootIf *obj, diff --git a/hw/intc/arm_gicv3_kvm.c b/hw/intc/arm_gicv3_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_kvm.c +++ b/hw/intc/arm_gicv3_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_dist_get_edge_trigger(GICv3State *s, uint32_t offset, uint32_t reg; int irq; + /* For the KVM GICv3, affinity routing is always enabled, and the first 2 + * GICD_ICFGR<n> registers are always RAZ/WI. The corresponding + * functionality is replaced by GICR_ICFGR<n>. It doesn't need to sync + * them. So it should increase the offset to skip GIC_INTERNAL irqs. + * This matches the for_each_dist_irq_reg() macro which also skips the + * first GIC_INTERNAL irqs. + */ + offset += (GIC_INTERNAL * 2) / 8; for_each_dist_irq_reg(irq, s->num_irq, 2) { kvm_gicd_access(s, offset, &reg, false); reg = half_unshuffle32(reg >> 1); @@ -XXX,XX +XXX,XX @@ static void kvm_dist_put_edge_trigger(GICv3State *s, uint32_t offset, uint32_t reg; int irq; + /* For the KVM GICv3, affinity routing is always enabled, and the first 2 + * GICD_ICFGR<n> registers are always RAZ/WI. The corresponding + * functionality is replaced by GICR_ICFGR<n>. It doesn't need to sync + * them. So it should increase the offset to skip GIC_INTERNAL irqs. + * This matches the for_each_dist_irq_reg() macro which also skips the + * first GIC_INTERNAL irqs. + */ + offset += (GIC_INTERNAL * 2) / 8; for_each_dist_irq_reg(irq, s->num_irq, 2) { reg = *gic_bmp_ptr32(bmp, irq); if (irq % 32 != 0) { @@ -XXX,XX +XXX,XX @@ static void kvm_dist_getbmp(GICv3State *s, uint32_t offset, uint32_t *bmp) uint32_t reg; int irq; + /* For the KVM GICv3, affinity routing is always enabled, and the + * GICD_IGROUPR0/GICD_IGRPMODR0/GICD_ISENABLER0/GICD_ISPENDR0/ + * GICD_ISACTIVER0 registers are always RAZ/WI. The corresponding + * functionality is replaced by the GICR registers. It doesn't need to sync + * them. So it should increase the offset to skip GIC_INTERNAL irqs. + * This matches the for_each_dist_irq_reg() macro which also skips the + * first GIC_INTERNAL irqs. + */ + offset += (GIC_INTERNAL * 1) / 8; for_each_dist_irq_reg(irq, s->num_irq, 1) { kvm_gicd_access(s, offset, &reg, false); *gic_bmp_ptr32(bmp, irq) = reg; @@ -XXX,XX +XXX,XX @@ static void kvm_dist_putbmp(GICv3State *s, uint32_t offset, uint32_t reg; int irq; + /* For the KVM GICv3, affinity routing is always enabled, and the + * GICD_IGROUPR0/GICD_IGRPMODR0/GICD_ISENABLER0/GICD_ISPENDR0/ + * GICD_ISACTIVER0 registers are always RAZ/WI. The corresponding + * functionality is replaced by the GICR registers. It doesn't need to sync + * them. So it should increase the offset and clroffset to skip GIC_INTERNAL + * irqs. This matches the for_each_dist_irq_reg() macro which also skips the + * first GIC_INTERNAL irqs. + */ + offset += (GIC_INTERNAL * 1) / 8; + if (clroffset != 0) { + clroffset += (GIC_INTERNAL * 1) / 8; + } + for_each_dist_irq_reg(irq, s->num_irq, 1) { /* If this bitmap is a set/clear register pair, first write to the * clear-reg to clear all bits before using the set-reg to write -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20180530064049.27976-2-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ static void palmetto_bmc_class_init(ObjectClass *oc, void *data) mc->no_floppy = 1; mc->no_cdrom = 1; mc->no_parallel = 1; - mc->ignore_memory_transaction_failures = true; } static const TypeInfo palmetto_bmc_type = { @@ -XXX,XX +XXX,XX @@ static void ast2500_evb_class_init(ObjectClass *oc, void *data) mc->no_floppy = 1; mc->no_cdrom = 1; mc->no_parallel = 1; - mc->ignore_memory_transaction_failures = true; } static const TypeInfo ast2500_evb_type = { @@ -XXX,XX +XXX,XX @@ static void romulus_bmc_class_init(ObjectClass *oc, void *data) mc->no_floppy = 1; mc->no_cdrom = 1; mc->no_parallel = 1; - mc->ignore_memory_transaction_failures = true; } static const TypeInfo romulus_bmc_type = { -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> The Witherspoon boards are OpenPOWER system hosting POWER9 Processors. Add support for their BMC including a couple of I2C devices as found on real HW. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Message-id: 20180530064049.27976-3-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ enum { PALMETTO_BMC, AST2500_EVB, ROMULUS_BMC, + WITHERSPOON_BMC, }; /* Palmetto hardware value: 0x120CE416 */ @@ -XXX,XX +XXX,XX @@ enum { SCU_AST2500_HW_STRAP_ACPI_ENABLE | \ SCU_HW_STRAP_SPI_MODE(SCU_HW_STRAP_SPI_MASTER)) +/* Witherspoon hardware value: 0xF10AD216 (but use romulus definition) */ +#define WITHERSPOON_BMC_HW_STRAP1 ROMULUS_BMC_HW_STRAP1 + static void palmetto_bmc_i2c_init(AspeedBoardState *bmc); static void ast2500_evb_i2c_init(AspeedBoardState *bmc); +static void witherspoon_bmc_i2c_init(AspeedBoardState *bmc); static const AspeedBoardConfig aspeed_boards[] = { [PALMETTO_BMC] = { @@ -XXX,XX +XXX,XX @@ static const AspeedBoardConfig aspeed_boards[] = { .spi_model = "mx66l1g45g", .num_cs = 2, }, + [WITHERSPOON_BMC] = { + .soc_name = "ast2500-a1", + .hw_strap1 = WITHERSPOON_BMC_HW_STRAP1, + .fmc_model = "mx25l25635e", + .spi_model = "mx66l1g45g", + .num_cs = 2, + .i2c_init = witherspoon_bmc_i2c_init, + }, }; #define FIRMWARE_ADDR 0x0 @@ -XXX,XX +XXX,XX @@ static const TypeInfo romulus_bmc_type = { .class_init = romulus_bmc_class_init, }; +static void witherspoon_bmc_i2c_init(AspeedBoardState *bmc) +{ + AspeedSoCState *soc = &bmc->soc; + + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 4), "tmp423", 0x4c); + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 5), "tmp423", 0x4c); + + /* The Witherspoon expects a TMP275 but a TMP105 is compatible */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 9), "tmp105", 0x4a); +} + +static void witherspoon_bmc_init(MachineState *machine) +{ + aspeed_board_init(machine, &aspeed_boards[WITHERSPOON_BMC]); +} + +static void witherspoon_bmc_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + + mc->desc = "OpenPOWER Witherspoon BMC (ARM1176)"; + mc->init = witherspoon_bmc_init; + mc->max_cpus = 1; + mc->no_sdcard = 1; + mc->no_floppy = 1; + mc->no_cdrom = 1; + mc->no_parallel = 1; +} + +static const TypeInfo witherspoon_bmc_type = { + .name = MACHINE_TYPE_NAME("witherspoon-bmc"), + .parent = TYPE_MACHINE, + .class_init = witherspoon_bmc_class_init, +}; + static void aspeed_machine_init(void) { type_register_static(&palmetto_bmc_type); type_register_static(&ast2500_evb_type); type_register_static(&romulus_bmc_type); + type_register_static(&witherspoon_bmc_type); } type_init(aspeed_machine_init) -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> The AST2500 EVB does not have an RTC but we can pretend that one is plugged on the I2C bus header. The romulus and witherspoon boards expects an Epson RX8900 I2C RTC but a ds1338 is good enough for the basic features we need. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Message-id: 20180530064049.27976-4-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ enum { static void palmetto_bmc_i2c_init(AspeedBoardState *bmc); static void ast2500_evb_i2c_init(AspeedBoardState *bmc); +static void romulus_bmc_i2c_init(AspeedBoardState *bmc); static void witherspoon_bmc_i2c_init(AspeedBoardState *bmc); static const AspeedBoardConfig aspeed_boards[] = { @@ -XXX,XX +XXX,XX @@ static const AspeedBoardConfig aspeed_boards[] = { .fmc_model = "n25q256a", .spi_model = "mx66l1g45g", .num_cs = 2, + .i2c_init = romulus_bmc_i2c_init, }, [WITHERSPOON_BMC] = { .soc_name = "ast2500-a1", @@ -XXX,XX +XXX,XX @@ static void ast2500_evb_i2c_init(AspeedBoardState *bmc) /* The AST2500 EVB expects a LM75 but a TMP105 is compatible */ i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 7), "tmp105", 0x4d); + + /* The AST2500 EVB does not have an RTC. Let's pretend that one is + * plugged on the I2C bus header */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 11), "ds1338", 0x32); } static void ast2500_evb_init(MachineState *machine) @@ -XXX,XX +XXX,XX @@ static const TypeInfo ast2500_evb_type = { .class_init = ast2500_evb_class_init, }; +static void romulus_bmc_i2c_init(AspeedBoardState *bmc) +{ + AspeedSoCState *soc = &bmc->soc; + + /* The romulus board expects Epson RX8900 I2C RTC but a ds1338 is + * good enough */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 11), "ds1338", 0x32); +} + static void romulus_bmc_init(MachineState *machine) { aspeed_board_init(machine, &aspeed_boards[ROMULUS_BMC]); @@ -XXX,XX +XXX,XX @@ static void witherspoon_bmc_i2c_init(AspeedBoardState *bmc) /* The Witherspoon expects a TMP275 but a TMP105 is compatible */ i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 9), "tmp105", 0x4a); + + /* The witherspoon board expects Epson RX8900 I2C RTC but a ds1338 is + * good enough */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 11), "ds1338", 0x32); } static void witherspoon_bmc_init(MachineState *machine) -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> This is an helper routine to add a single EEPROM on an I2C bus. It can be directly used by smbus_eeprom_init() which adds a certain number of EEPROMs on mips and x86 machines. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180530064049.27976-5-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/i2c/smbus.h | 1 + hw/i2c/smbus_eeprom.c | 16 +++++++++++----- 2 files changed, 12 insertions(+), 5 deletions(-) diff --git a/include/hw/i2c/smbus.h b/include/hw/i2c/smbus.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/i2c/smbus.h +++ b/include/hw/i2c/smbus.h @@ -XXX,XX +XXX,XX @@ int smbus_read_block(I2CBus *bus, uint8_t addr, uint8_t command, uint8_t *data); int smbus_write_block(I2CBus *bus, uint8_t addr, uint8_t command, uint8_t *data, int len); +void smbus_eeprom_init_one(I2CBus *smbus, uint8_t address, uint8_t *eeprom_buf); void smbus_eeprom_init(I2CBus *smbus, int nb_eeprom, const uint8_t *eeprom_spd, int size); diff --git a/hw/i2c/smbus_eeprom.c b/hw/i2c/smbus_eeprom.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/smbus_eeprom.c +++ b/hw/i2c/smbus_eeprom.c @@ -XXX,XX +XXX,XX @@ static void smbus_eeprom_register_types(void) type_init(smbus_eeprom_register_types) +void smbus_eeprom_init_one(I2CBus *smbus, uint8_t address, uint8_t *eeprom_buf) +{ + DeviceState *dev; + + dev = qdev_create((BusState *) smbus, "smbus-eeprom"); + qdev_prop_set_uint8(dev, "address", address); + qdev_prop_set_ptr(dev, "data", eeprom_buf); + qdev_init_nofail(dev); +} + void smbus_eeprom_init(I2CBus *smbus, int nb_eeprom, const uint8_t *eeprom_spd, int eeprom_spd_size) { @@ -XXX,XX +XXX,XX @@ void smbus_eeprom_init(I2CBus *smbus, int nb_eeprom, } for (i = 0; i < nb_eeprom; i++) { - DeviceState *eeprom; - eeprom = qdev_create((BusState *)smbus, "smbus-eeprom"); - qdev_prop_set_uint8(eeprom, "address", 0x50 + i); - qdev_prop_set_ptr(eeprom, "data", eeprom_buf + (i * 256)); - qdev_init_nofail(eeprom); + smbus_eeprom_init_one(smbus, 0x50 + i, eeprom_buf + (i * 256)); } } -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> The Aspeed boards have at least one EEPROM to hold the Vital Product Data (VPD). Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Message-id: 20180530064049.27976-6-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/arm.h" #include "hw/arm/aspeed_soc.h" #include "hw/boards.h" +#include "hw/i2c/smbus.h" #include "qemu/log.h" #include "sysemu/block-backend.h" #include "hw/loader.h" @@ -XXX,XX +XXX,XX @@ static void palmetto_bmc_i2c_init(AspeedBoardState *bmc) { AspeedSoCState *soc = &bmc->soc; DeviceState *dev; + uint8_t *eeprom_buf = g_malloc0(32 * 1024); /* The palmetto platform expects a ds3231 RTC but a ds1338 is * enough to provide basic RTC features. Alarms will be missing */ i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 0), "ds1338", 0x68); + smbus_eeprom_init_one(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 0), 0x50, + eeprom_buf); + /* add a TMP423 temperature sensor */ dev = i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 2), "tmp423", 0x4c); @@ -XXX,XX +XXX,XX @@ static const TypeInfo palmetto_bmc_type = { static void ast2500_evb_i2c_init(AspeedBoardState *bmc) { AspeedSoCState *soc = &bmc->soc; + uint8_t *eeprom_buf = g_malloc0(8 * 1024); + + smbus_eeprom_init_one(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 3), 0x50, + eeprom_buf); /* The AST2500 EVB expects a LM75 but a TMP105 is compatible */ i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 7), "tmp105", 0x4d); @@ -XXX,XX +XXX,XX @@ static const TypeInfo romulus_bmc_type = { static void witherspoon_bmc_i2c_init(AspeedBoardState *bmc) { AspeedSoCState *soc = &bmc->soc; + uint8_t *eeprom_buf = g_malloc0(8 * 1024); i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 4), "tmp423", 0x4c); i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 5), "tmp423", 0x4c); @@ -XXX,XX +XXX,XX @@ static void witherspoon_bmc_i2c_init(AspeedBoardState *bmc) /* The witherspoon board expects Epson RX8900 I2C RTC but a ds1338 is * good enough */ i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 11), "ds1338", 0x32); + + smbus_eeprom_init_one(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 11), 0x51, + eeprom_buf); } static void witherspoon_bmc_init(MachineState *machine) -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> Specs are available here : https://www.nxp.com/docs/en/application-note/AN264.pdf This is a simple model supporting the basic registers for led and GPIO mode. The device also supports two blinking rates but not the model yet. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180530064049.27976-7-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + tests/Makefile.include | 2 + include/hw/misc/pca9552.h | 32 +++++ include/hw/misc/pca9552_regs.h | 32 +++++ tests/libqos/i2c.h | 2 + hw/misc/pca9552.c | 240 ++++++++++++++++++++++++++++++++ tests/pca9552-test.c | 116 +++++++++++++++ tests/tmp105-test.c | 2 - default-configs/arm-softmmu.mak | 1 + 9 files changed, 426 insertions(+), 2 deletions(-) create mode 100644 include/hw/misc/pca9552.h create mode 100644 include/hw/misc/pca9552_regs.h create mode 100644 hw/misc/pca9552.c create mode 100644 tests/pca9552-test.c diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_SGA) += sga.o common-obj-$(CONFIG_ISA_TESTDEV) += pc-testdev.o common-obj-$(CONFIG_PCI_TESTDEV) += pci-testdev.o common-obj-$(CONFIG_EDU) += edu.o +common-obj-$(CONFIG_PCA9552) += pca9552.o common-obj-y += unimp.o common-obj-$(CONFIG_FW_CFG_DMA) += vmcoreinfo.o diff --git a/tests/Makefile.include b/tests/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -XXX,XX +XXX,XX @@ check-qtest-sparc64-y += tests/prom-env-test$(EXESUF) check-qtest-sparc64-y += tests/boot-serial-test$(EXESUF) check-qtest-arm-y = tests/tmp105-test$(EXESUF) +check-qtest-arm-y += tests/pca9552-test$(EXESUF) check-qtest-arm-y += tests/ds1338-test$(EXESUF) check-qtest-arm-y += tests/m25p80-test$(EXESUF) gcov-files-arm-y += hw/misc/tmp105.c @@ -XXX,XX +XXX,XX @@ tests/bios-tables-test$(EXESUF): tests/bios-tables-test.o \ tests/boot-sector.o tests/acpi-utils.o $(libqos-obj-y) tests/pxe-test$(EXESUF): tests/pxe-test.o tests/boot-sector.o $(libqos-obj-y) tests/tmp105-test$(EXESUF): tests/tmp105-test.o $(libqos-omap-obj-y) +tests/pca9552-test$(EXESUF): tests/pca9552-test.o $(libqos-omap-obj-y) tests/ds1338-test$(EXESUF): tests/ds1338-test.o $(libqos-imx-obj-y) tests/m25p80-test$(EXESUF): tests/m25p80-test.o tests/i440fx-test$(EXESUF): tests/i440fx-test.o $(libqos-pc-obj-y) diff --git a/include/hw/misc/pca9552.h b/include/hw/misc/pca9552.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/pca9552.h @@ -XXX,XX +XXX,XX @@ +/* + * PCA9552 I2C LED blinker + * + * Copyright (c) 2017-2018, IBM Corporation. + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * later. See the COPYING file in the top-level directory. + */ +#ifndef PCA9552_H +#define PCA9552_H + +#include "hw/i2c/i2c.h" + +#define TYPE_PCA9552 "pca9552" +#define PCA9552(obj) OBJECT_CHECK(PCA9552State, (obj), TYPE_PCA9552) + +#define PCA9552_NR_REGS 10 + +typedef struct PCA9552State { + /*< private >*/ + I2CSlave i2c; + /*< public >*/ + + uint8_t len; + uint8_t pointer; + + uint8_t regs[PCA9552_NR_REGS]; + uint8_t max_reg; + uint8_t nr_leds; +} PCA9552State; + +#endif diff --git a/include/hw/misc/pca9552_regs.h b/include/hw/misc/pca9552_regs.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/pca9552_regs.h @@ -XXX,XX +XXX,XX @@ +/* + * PCA9552 I2C LED blinker registers + * + * Copyright (c) 2017-2018, IBM Corporation. + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * later. See the COPYING file in the top-level directory. + */ +#ifndef PCA9552_REGS_H +#define PCA9552_REGS_H + +/* + * Bits [0:3] are used to address a specific register. + */ +#define PCA9552_INPUT0 0 /* read only input register 0 */ +#define PCA9552_INPUT1 1 /* read only input register 1 */ +#define PCA9552_PSC0 2 /* read/write frequency prescaler 0 */ +#define PCA9552_PWM0 3 /* read/write PWM register 0 */ +#define PCA9552_PSC1 4 /* read/write frequency prescaler 1 */ +#define PCA9552_PWM1 5 /* read/write PWM register 1 */ +#define PCA9552_LS0 6 /* read/write LED0 to LED3 selector */ +#define PCA9552_LS1 7 /* read/write LED4 to LED7 selector */ +#define PCA9552_LS2 8 /* read/write LED8 to LED11 selector */ +#define PCA9552_LS3 9 /* read/write LED12 to LED15 selector */ + +/* + * Bit [4] is used to activate the Auto-Increment option of the + * register address + */ +#define PCA9552_AUTOINC (1 << 4) + +#endif diff --git a/tests/libqos/i2c.h b/tests/libqos/i2c.h index XXXXXXX..XXXXXXX 100644 --- a/tests/libqos/i2c.h +++ b/tests/libqos/i2c.h @@ -XXX,XX +XXX,XX @@ struct I2CAdapter { QTestState *qts; }; +#define OMAP2_I2C_1_BASE 0x48070000 + void i2c_send(I2CAdapter *i2c, uint8_t addr, const uint8_t *buf, uint16_t len); void i2c_recv(I2CAdapter *i2c, uint8_t addr, diff --git a/hw/misc/pca9552.c b/hw/misc/pca9552.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/pca9552.c @@ -XXX,XX +XXX,XX @@ +/* + * PCA9552 I2C LED blinker + * + * https://www.nxp.com/docs/en/application-note/AN264.pdf + * + * Copyright (c) 2017-2018, IBM Corporation. + * + * 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 "qemu/log.h" +#include "hw/hw.h" +#include "hw/misc/pca9552.h" +#include "hw/misc/pca9552_regs.h" + +#define PCA9552_LED_ON 0x0 +#define PCA9552_LED_OFF 0x1 +#define PCA9552_LED_PWM0 0x2 +#define PCA9552_LED_PWM1 0x3 + +static uint8_t pca9552_pin_get_config(PCA9552State *s, int pin) +{ + uint8_t reg = PCA9552_LS0 + (pin / 4); + uint8_t shift = (pin % 4) << 1; + + return extract32(s->regs[reg], shift, 2); +} + +static void pca9552_update_pin_input(PCA9552State *s) +{ + int i; + + for (i = 0; i < s->nr_leds; i++) { + uint8_t input_reg = PCA9552_INPUT0 + (i / 8); + uint8_t input_shift = (i % 8); + uint8_t config = pca9552_pin_get_config(s, i); + + switch (config) { + case PCA9552_LED_ON: + s->regs[input_reg] |= 1 << input_shift; + break; + case PCA9552_LED_OFF: + s->regs[input_reg] &= ~(1 << input_shift); + break; + case PCA9552_LED_PWM0: + case PCA9552_LED_PWM1: + /* TODO */ + default: + break; + } + } +} + +static uint8_t pca9552_read(PCA9552State *s, uint8_t reg) +{ + switch (reg) { + case PCA9552_INPUT0: + case PCA9552_INPUT1: + case PCA9552_PSC0: + case PCA9552_PWM0: + case PCA9552_PSC1: + case PCA9552_PWM1: + case PCA9552_LS0: + case PCA9552_LS1: + case PCA9552_LS2: + case PCA9552_LS3: + return s->regs[reg]; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: unexpected read to register %d\n", + __func__, reg); + return 0xFF; + } +} + +static void pca9552_write(PCA9552State *s, uint8_t reg, uint8_t data) +{ + switch (reg) { + case PCA9552_PSC0: + case PCA9552_PWM0: + case PCA9552_PSC1: + case PCA9552_PWM1: + s->regs[reg] = data; + break; + + case PCA9552_LS0: + case PCA9552_LS1: + case PCA9552_LS2: + case PCA9552_LS3: + s->regs[reg] = data; + pca9552_update_pin_input(s); + break; + + case PCA9552_INPUT0: + case PCA9552_INPUT1: + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: unexpected write to register %d\n", + __func__, reg); + } +} + +/* + * When Auto-Increment is on, the register address is incremented + * after each byte is sent to or received by the device. The index + * rollovers to 0 when the maximum register address is reached. + */ +static void pca9552_autoinc(PCA9552State *s) +{ + if (s->pointer != 0xFF && s->pointer & PCA9552_AUTOINC) { + uint8_t reg = s->pointer & 0xf; + + reg = (reg + 1) % (s->max_reg + 1); + s->pointer = reg | PCA9552_AUTOINC; + } +} + +static int pca9552_recv(I2CSlave *i2c) +{ + PCA9552State *s = PCA9552(i2c); + uint8_t ret; + + ret = pca9552_read(s, s->pointer & 0xf); + + /* + * From the Specs: + * + * Important Note: When a Read sequence is initiated and the + * AI bit is set to Logic Level 1, the Read Sequence MUST + * start by a register different from 0. + * + * I don't know what should be done in this case, so throw an + * error. + */ + if (s->pointer == PCA9552_AUTOINC) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Autoincrement read starting with register 0\n", + __func__); + } + + pca9552_autoinc(s); + + return ret; +} + +static int pca9552_send(I2CSlave *i2c, uint8_t data) +{ + PCA9552State *s = PCA9552(i2c); + + /* First byte sent by is the register address */ + if (s->len == 0) { + s->pointer = data; + s->len++; + } else { + pca9552_write(s, s->pointer & 0xf, data); + + pca9552_autoinc(s); + } + + return 0; +} + +static int pca9552_event(I2CSlave *i2c, enum i2c_event event) +{ + PCA9552State *s = PCA9552(i2c); + + s->len = 0; + return 0; +} + +static const VMStateDescription pca9552_vmstate = { + .name = "PCA9552", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT8(len, PCA9552State), + VMSTATE_UINT8(pointer, PCA9552State), + VMSTATE_UINT8_ARRAY(regs, PCA9552State, PCA9552_NR_REGS), + VMSTATE_I2C_SLAVE(i2c, PCA9552State), + VMSTATE_END_OF_LIST() + } +}; + +static void pca9552_reset(DeviceState *dev) +{ + PCA9552State *s = PCA9552(dev); + + s->regs[PCA9552_PSC0] = 0xFF; + s->regs[PCA9552_PWM0] = 0x80; + s->regs[PCA9552_PSC1] = 0xFF; + s->regs[PCA9552_PWM1] = 0x80; + s->regs[PCA9552_LS0] = 0x55; /* all OFF */ + s->regs[PCA9552_LS1] = 0x55; + s->regs[PCA9552_LS2] = 0x55; + s->regs[PCA9552_LS3] = 0x55; + + pca9552_update_pin_input(s); + + s->pointer = 0xFF; + s->len = 0; +} + +static void pca9552_initfn(Object *obj) +{ + PCA9552State *s = PCA9552(obj); + + /* If support for the other PCA955X devices are implemented, these + * constant values might be part of class structure describing the + * PCA955X device + */ + s->max_reg = PCA9552_LS3; + s->nr_leds = 16; +} + +static void pca9552_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + I2CSlaveClass *k = I2C_SLAVE_CLASS(klass); + + k->event = pca9552_event; + k->recv = pca9552_recv; + k->send = pca9552_send; + dc->reset = pca9552_reset; + dc->vmsd = &pca9552_vmstate; +} + +static const TypeInfo pca9552_info = { + .name = TYPE_PCA9552, + .parent = TYPE_I2C_SLAVE, + .instance_init = pca9552_initfn, + .instance_size = sizeof(PCA9552State), + .class_init = pca9552_class_init, +}; + +static void pca9552_register_types(void) +{ + type_register_static(&pca9552_info); +} + +type_init(pca9552_register_types) diff --git a/tests/pca9552-test.c b/tests/pca9552-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/pca9552-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTest testcase for the PCA9552 LED blinker + * + * Copyright (c) 2017-2018, IBM Corporation. + * + * 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 "libqtest.h" +#include "libqos/i2c.h" +#include "hw/misc/pca9552_regs.h" + +#define PCA9552_TEST_ID "pca9552-test" +#define PCA9552_TEST_ADDR 0x60 + +static I2CAdapter *i2c; + +static uint8_t pca9552_get8(I2CAdapter *i2c, uint8_t addr, uint8_t reg) +{ + uint8_t resp[1]; + i2c_send(i2c, addr, &reg, 1); + i2c_recv(i2c, addr, resp, 1); + return resp[0]; +} + +static void pca9552_set8(I2CAdapter *i2c, uint8_t addr, uint8_t reg, + uint8_t value) +{ + uint8_t cmd[2]; + uint8_t resp[1]; + + cmd[0] = reg; + cmd[1] = value; + i2c_send(i2c, addr, cmd, 2); + i2c_recv(i2c, addr, resp, 1); + g_assert_cmphex(resp[0], ==, cmd[1]); +} + +static void receive_autoinc(void) +{ + uint8_t resp; + uint8_t reg = PCA9552_LS0 | PCA9552_AUTOINC; + + i2c_send(i2c, PCA9552_TEST_ADDR, &reg, 1); + + /* PCA9552_LS0 */ + i2c_recv(i2c, PCA9552_TEST_ADDR, &resp, 1); + g_assert_cmphex(resp, ==, 0x54); + + /* PCA9552_LS1 */ + i2c_recv(i2c, PCA9552_TEST_ADDR, &resp, 1); + g_assert_cmphex(resp, ==, 0x55); + + /* PCA9552_LS2 */ + i2c_recv(i2c, PCA9552_TEST_ADDR, &resp, 1); + g_assert_cmphex(resp, ==, 0x55); + + /* PCA9552_LS3 */ + i2c_recv(i2c, PCA9552_TEST_ADDR, &resp, 1); + g_assert_cmphex(resp, ==, 0x54); +} + +static void send_and_receive(void) +{ + uint8_t value; + + value = pca9552_get8(i2c, PCA9552_TEST_ADDR, PCA9552_LS0); + g_assert_cmphex(value, ==, 0x55); + + value = pca9552_get8(i2c, PCA9552_TEST_ADDR, PCA9552_INPUT0); + g_assert_cmphex(value, ==, 0x0); + + /* Switch on LED 0 */ + pca9552_set8(i2c, PCA9552_TEST_ADDR, PCA9552_LS0, 0x54); + value = pca9552_get8(i2c, PCA9552_TEST_ADDR, PCA9552_LS0); + g_assert_cmphex(value, ==, 0x54); + + value = pca9552_get8(i2c, PCA9552_TEST_ADDR, PCA9552_INPUT0); + g_assert_cmphex(value, ==, 0x01); + + /* Switch on LED 12 */ + pca9552_set8(i2c, PCA9552_TEST_ADDR, PCA9552_LS3, 0x54); + value = pca9552_get8(i2c, PCA9552_TEST_ADDR, PCA9552_LS3); + g_assert_cmphex(value, ==, 0x54); + + value = pca9552_get8(i2c, PCA9552_TEST_ADDR, PCA9552_INPUT1); + g_assert_cmphex(value, ==, 0x10); +} + +int main(int argc, char **argv) +{ + QTestState *s = NULL; + int ret; + + g_test_init(&argc, &argv, NULL); + + s = qtest_start("-machine n800 " + "-device pca9552,bus=i2c-bus.0,id=" PCA9552_TEST_ID + ",address=0x60"); + i2c = omap_i2c_create(s, OMAP2_I2C_1_BASE); + + qtest_add_func("/pca9552/tx-rx", send_and_receive); + qtest_add_func("/pca9552/rx-autoinc", receive_autoinc); + + ret = g_test_run(); + + if (s) { + qtest_quit(s); + } + g_free(i2c); + + return ret; +} diff --git a/tests/tmp105-test.c b/tests/tmp105-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/tmp105-test.c +++ b/tests/tmp105-test.c @@ -XXX,XX +XXX,XX @@ #include "qapi/qmp/qdict.h" #include "hw/misc/tmp105_regs.h" -#define OMAP2_I2C_1_BASE 0x48070000 - #define TMP105_TEST_ID "tmp105-test" #define TMP105_TEST_ADDR 0x49 diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/default-configs/arm-softmmu.mak +++ b/default-configs/arm-softmmu.mak @@ -XXX,XX +XXX,XX @@ CONFIG_TSC2005=y CONFIG_LM832X=y CONFIG_TMP105=y CONFIG_TMP421=y +CONFIG_PCA9552=y CONFIG_STELLARIS=y CONFIG_STELLARIS_INPUT=y CONFIG_STELLARIS_ENET=y -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> The pca9552 LED blinkers on the Witherspoon machine are used for leds but also as GPIOs to control fans and GPUs. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180530064049.27976-8-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ static void witherspoon_bmc_i2c_init(AspeedBoardState *bmc) AspeedSoCState *soc = &bmc->soc; uint8_t *eeprom_buf = g_malloc0(8 * 1024); + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 3), "pca9552", 0x60); + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 4), "tmp423", 0x4c); i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 5), "tmp423", 0x4c); @@ -XXX,XX +XXX,XX @@ static void witherspoon_bmc_i2c_init(AspeedBoardState *bmc) smbus_eeprom_init_one(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 11), 0x51, eeprom_buf); + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 11), "pca9552", + 0x60); } static void witherspoon_bmc_init(MachineState *machine) -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> The maximum frame size includes the CRC and depends if a VLAN tag is inserted or not. Adjust the frame size limit in the transmit handler using on the FTGMAC100State buffer size and in the receive handler use the packet protocol. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180530061711.23673-2-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/net/ftgmac100.h | 7 ++++++- hw/net/ftgmac100.c | 23 ++++++++++++----------- 2 files changed, 18 insertions(+), 12 deletions(-) diff --git a/include/hw/net/ftgmac100.h b/include/hw/net/ftgmac100.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/net/ftgmac100.h +++ b/include/hw/net/ftgmac100.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "net/net.h" +/* + * Max frame size for the receiving buffer + */ +#define FTGMAC100_MAX_FRAME_SIZE 9220 + typedef struct FTGMAC100State { /*< private >*/ SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ typedef struct FTGMAC100State { qemu_irq irq; MemoryRegion iomem; - uint8_t *frame; + uint8_t frame[FTGMAC100_MAX_FRAME_SIZE]; uint32_t irq_state; uint32_t isr; diff --git a/hw/net/ftgmac100.c b/hw/net/ftgmac100.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/ftgmac100.c +++ b/hw/net/ftgmac100.c @@ -XXX,XX +XXX,XX @@ typedef struct { /* * Max frame size for the receiving buffer */ -#define FTGMAC100_MAX_FRAME_SIZE 10240 +#define FTGMAC100_MAX_FRAME_SIZE 9220 /* Limits depending on the type of the frame * * 9216 for Jumbo frames (+ 4 for VLAN) * 1518 for other frames (+ 4 for VLAN) */ -static int ftgmac100_max_frame_size(FTGMAC100State *s) +static int ftgmac100_max_frame_size(FTGMAC100State *s, uint16_t proto) { - return (s->maccr & FTGMAC100_MACCR_JUMBO_LF ? 9216 : 1518) + 4; + int max = (s->maccr & FTGMAC100_MACCR_JUMBO_LF ? 9216 : 1518); + + return max + (proto == ETH_P_VLAN ? 4 : 0); } static void ftgmac100_update_irq(FTGMAC100State *s) @@ -XXX,XX +XXX,XX @@ static void ftgmac100_do_tx(FTGMAC100State *s, uint32_t tx_ring, uint8_t *ptr = s->frame; uint32_t addr = tx_descriptor; uint32_t flags = 0; - int max_frame_size = ftgmac100_max_frame_size(s); while (1) { FTGMAC100Desc bd; @@ -XXX,XX +XXX,XX @@ static void ftgmac100_do_tx(FTGMAC100State *s, uint32_t tx_ring, flags = bd.des1; } - len = bd.des0 & 0x3FFF; - if (frame_size + len > max_frame_size) { + len = FTGMAC100_TXDES0_TXBUF_SIZE(bd.des0); + if (frame_size + len > sizeof(s->frame)) { qemu_log_mask(LOG_GUEST_ERROR, "%s: frame too big : %d bytes\n", __func__, len); - len = max_frame_size - frame_size; + s->isr |= FTGMAC100_INT_XPKT_LOST; + len = sizeof(s->frame) - frame_size; } if (dma_memory_read(&address_space_memory, bd.des3, ptr, len)) { @@ -XXX,XX +XXX,XX @@ static ssize_t ftgmac100_receive(NetClientState *nc, const uint8_t *buf, uint32_t buf_len; size_t size = len; uint32_t first = FTGMAC100_RXDES0_FRS; - int max_frame_size = ftgmac100_max_frame_size(s); + uint16_t proto = be16_to_cpu(PKT_GET_ETH_HDR(buf)->h_proto); + int max_frame_size = ftgmac100_max_frame_size(s, proto); if ((s->maccr & (FTGMAC100_MACCR_RXDMA_EN | FTGMAC100_MACCR_RXMAC_EN)) != (FTGMAC100_MACCR_RXDMA_EN | FTGMAC100_MACCR_RXMAC_EN)) { @@ -XXX,XX +XXX,XX @@ static ssize_t ftgmac100_receive(NetClientState *nc, const uint8_t *buf, /* Huge frames are truncated. */ if (size > max_frame_size) { - size = max_frame_size; qemu_log_mask(LOG_GUEST_ERROR, "%s: frame too big : %zd bytes\n", __func__, size); + size = max_frame_size; flags |= FTGMAC100_RXDES0_FTL; } @@ -XXX,XX +XXX,XX @@ static void ftgmac100_realize(DeviceState *dev, Error **errp) object_get_typename(OBJECT(dev)), DEVICE(dev)->id, s); qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a); - - s->frame = g_malloc(FTGMAC100_MAX_FRAME_SIZE); } static const VMStateDescription vmstate_ftgmac100 = { -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> The ftgmac100 NIC supports VLAN tag insertion and the MAC engine also has a control to remove VLAN tags from received packets. The VLAN control bits and VLAN tag information are contained in the second word of the transmit and receive descriptors. The Insert VLAN bit and the VLAN Tag available bit are only valid in the first segment of the packet. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180530061711.23673-3-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/ftgmac100.c | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) diff --git a/hw/net/ftgmac100.c b/hw/net/ftgmac100.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/ftgmac100.c +++ b/hw/net/ftgmac100.c @@ -XXX,XX +XXX,XX @@ static void ftgmac100_do_tx(FTGMAC100State *s, uint32_t tx_ring, break; } + /* Check for VLAN */ + if (bd.des0 & FTGMAC100_TXDES0_FTS && + bd.des1 & FTGMAC100_TXDES1_INS_VLANTAG && + be16_to_cpu(PKT_GET_ETH_HDR(ptr)->h_proto) != ETH_P_VLAN) { + if (frame_size + len + 4 > sizeof(s->frame)) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: frame too big : %d bytes\n", + __func__, len); + s->isr |= FTGMAC100_INT_XPKT_LOST; + len = sizeof(s->frame) - frame_size - 4; + } + memmove(ptr + 16, ptr + 12, len - 12); + stw_be_p(ptr + 12, ETH_P_VLAN); + stw_be_p(ptr + 14, bd.des1); + len += 4; + } + ptr += len; frame_size += len; if (bd.des0 & FTGMAC100_TXDES0_LTS) { @@ -XXX,XX +XXX,XX @@ static ssize_t ftgmac100_receive(NetClientState *nc, const uint8_t *buf, buf_len += size - 4; } buf_addr = bd.des3; - dma_memory_write(&address_space_memory, buf_addr, buf, buf_len); + if (first && proto == ETH_P_VLAN && buf_len >= 18) { + bd.des1 = lduw_be_p(buf + 14) | FTGMAC100_RXDES1_VLANTAG_AVAIL; + + if (s->maccr & FTGMAC100_MACCR_RM_VLAN) { + dma_memory_write(&address_space_memory, buf_addr, buf, 12); + dma_memory_write(&address_space_memory, buf_addr + 12, buf + 16, + buf_len - 16); + } else { + dma_memory_write(&address_space_memory, buf_addr, buf, buf_len); + } + } else { + bd.des1 = 0; + dma_memory_write(&address_space_memory, buf_addr, buf, buf_len); + } buf += buf_len; if (size < 4) { dma_memory_write(&address_space_memory, buf_addr + buf_len, -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> Based on the multicast hash calculation of the FTGMAC100 Linux driver. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180530061711.23673-4-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/ftgmac100.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/net/ftgmac100.c b/hw/net/ftgmac100.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/ftgmac100.c +++ b/hw/net/ftgmac100.c @@ -XXX,XX +XXX,XX @@ static int ftgmac100_filter(FTGMAC100State *s, const uint8_t *buf, size_t len) return 0; } - /* TODO: this does not seem to work for ftgmac100 */ - mcast_idx = net_crc32(buf, ETH_ALEN) >> 26; + mcast_idx = net_crc32_le(buf, ETH_ALEN); + mcast_idx = (~(mcast_idx >> 2)) & 0x3f; if (!(s->math[mcast_idx / 32] & (1 << (mcast_idx % 32)))) { return 0; } -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> This is a ethernet wire limitation not needed in emulation. It breaks U-Boot n/w stack also. Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 20180530061711.23673-5-clg@kaod.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/ftgmac100.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/hw/net/ftgmac100.c b/hw/net/ftgmac100.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/ftgmac100.c +++ b/hw/net/ftgmac100.c @@ -XXX,XX +XXX,XX @@ static ssize_t ftgmac100_receive(NetClientState *nc, const uint8_t *buf, return size; } - if (size < 64 && !(s->maccr & FTGMAC100_MACCR_RX_RUNT)) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: dropped runt frame of %zd bytes\n", - __func__, size); - return size; - } - if (!ftgmac100_filter(s, buf, size)) { return size; } -- 2.17.1 From: Thomas Huth <thuth@redhat.com> It has been marked as deprecated since QEMU v2.11, so it is time to remove this now. The xlnx-zcu102 machine is very much the same and can be used as a replacement instead. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-zcu102.c | 62 ++------------------------------------------ qemu-doc.texi | 5 ---- 2 files changed, 2 insertions(+), 65 deletions(-) diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zcu102.c +++ b/hw/arm/xlnx-zcu102.c @@ -XXX,XX +XXX,XX @@ typedef struct XlnxZCU102 { #define ZCU102_MACHINE(obj) \ OBJECT_CHECK(XlnxZCU102, (obj), TYPE_ZCU102_MACHINE) -#define TYPE_EP108_MACHINE MACHINE_TYPE_NAME("xlnx-ep108") -#define EP108_MACHINE(obj) \ - OBJECT_CHECK(XlnxZCU102, (obj), TYPE_EP108_MACHINE) - static struct arm_boot_info xlnx_zcu102_binfo; static bool zcu102_get_secure(Object *obj, Error **errp) @@ -XXX,XX +XXX,XX @@ static void zcu102_set_virt(Object *obj, bool value, Error **errp) s->virt = value; } -static void xlnx_zynqmp_init(XlnxZCU102 *s, MachineState *machine) +static void xlnx_zcu102_init(MachineState *machine) { + XlnxZCU102 *s = ZCU102_MACHINE(machine); int i; uint64_t ram_size = machine->ram_size; @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_init(XlnxZCU102 *s, MachineState *machine) arm_load_kernel(s->soc.boot_cpu_ptr, &xlnx_zcu102_binfo); } -static void xlnx_ep108_init(MachineState *machine) -{ - XlnxZCU102 *s = EP108_MACHINE(machine); - - if (!qtest_enabled()) { - info_report("The Xilinx EP108 machine is deprecated, please use the " - "ZCU102 machine (which has the same features) instead."); - } - - xlnx_zynqmp_init(s, machine); -} - -static void xlnx_ep108_machine_instance_init(Object *obj) -{ - XlnxZCU102 *s = EP108_MACHINE(obj); - - /* EP108, we don't support setting secure or virt */ - s->secure = false; - s->virt = false; -} - -static void xlnx_ep108_machine_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Xilinx ZynqMP EP108 board (Deprecated, please use xlnx-zcu102)"; - mc->init = xlnx_ep108_init; - mc->block_default_type = IF_IDE; - mc->units_per_default_bus = 1; - mc->ignore_memory_transaction_failures = true; - mc->max_cpus = XLNX_ZYNQMP_NUM_APU_CPUS + XLNX_ZYNQMP_NUM_RPU_CPUS; - mc->default_cpus = XLNX_ZYNQMP_NUM_APU_CPUS; -} - -static const TypeInfo xlnx_ep108_machine_init_typeinfo = { - .name = MACHINE_TYPE_NAME("xlnx-ep108"), - .parent = TYPE_MACHINE, - .class_init = xlnx_ep108_machine_class_init, - .instance_init = xlnx_ep108_machine_instance_init, - .instance_size = sizeof(XlnxZCU102), -}; - -static void xlnx_ep108_machine_init_register_types(void) -{ - type_register_static(&xlnx_ep108_machine_init_typeinfo); -} - -static void xlnx_zcu102_init(MachineState *machine) -{ - XlnxZCU102 *s = ZCU102_MACHINE(machine); - - xlnx_zynqmp_init(s, machine); -} - static void xlnx_zcu102_machine_instance_init(Object *obj) { XlnxZCU102 *s = ZCU102_MACHINE(obj); @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_machine_init_register_types(void) } type_init(xlnx_zcu102_machine_init_register_types) -type_init(xlnx_ep108_machine_init_register_types) diff --git a/qemu-doc.texi b/qemu-doc.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-doc.texi +++ b/qemu-doc.texi @@ -XXX,XX +XXX,XX @@ support page sizes < 4096 any longer. @section System emulator machines -@subsection Xilinx EP108 (since 2.11.0) - -The ``xlnx-ep108'' machine has been replaced by the ``xlnx-zcu102'' machine. -The ``xlnx-zcu102'' machine has the same features and capabilites in QEMU. - @section Block device options @subsection "backing": "" (since 2.12.0) -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180606191801.6331-1-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- Makefile.objs | 1 + hw/i2c/core.c | 25 ++++++++++++++++++------- hw/i2c/trace-events | 7 +++++++ 3 files changed, 26 insertions(+), 7 deletions(-) create mode 100644 hw/i2c/trace-events diff --git a/Makefile.objs b/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/Makefile.objs +++ b/Makefile.objs @@ -XXX,XX +XXX,XX @@ trace-events-subdirs += hw/char trace-events-subdirs += hw/display trace-events-subdirs += hw/dma trace-events-subdirs += hw/hppa +trace-events-subdirs += hw/i2c trace-events-subdirs += hw/i386 trace-events-subdirs += hw/i386/xen trace-events-subdirs += hw/ide diff --git a/hw/i2c/core.c b/hw/i2c/core.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/core.c +++ b/hw/i2c/core.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "hw/i2c/i2c.h" +#include "trace.h" #define I2C_BROADCAST 0x00 @@ -XXX,XX +XXX,XX @@ int i2c_start_transfer(I2CBus *bus, uint8_t address, int recv) } QLIST_FOREACH(node, &bus->current_devs, next) { + I2CSlave *s = node->elt; int rv; - sc = I2C_SLAVE_GET_CLASS(node->elt); + sc = I2C_SLAVE_GET_CLASS(s); /* If the bus is already busy, assume this is a repeated start condition. */ if (sc->event) { - rv = sc->event(node->elt, recv ? I2C_START_RECV : I2C_START_SEND); + trace_i2c_event("start", s->address); + rv = sc->event(s, recv ? I2C_START_RECV : I2C_START_SEND); if (rv && !bus->broadcast) { if (bus_scanned) { /* First call, terminate the transfer. */ @@ -XXX,XX +XXX,XX @@ void i2c_end_transfer(I2CBus *bus) I2CNode *node, *next; QLIST_FOREACH_SAFE(node, &bus->current_devs, next, next) { - sc = I2C_SLAVE_GET_CLASS(node->elt); + I2CSlave *s = node->elt; + sc = I2C_SLAVE_GET_CLASS(s); if (sc->event) { - sc->event(node->elt, I2C_FINISH); + trace_i2c_event("finish", s->address); + sc->event(s, I2C_FINISH); } QLIST_REMOVE(node, next); g_free(node); @@ -XXX,XX +XXX,XX @@ void i2c_end_transfer(I2CBus *bus) int i2c_send_recv(I2CBus *bus, uint8_t *data, bool send) { I2CSlaveClass *sc; + I2CSlave *s; I2CNode *node; int ret = 0; if (send) { QLIST_FOREACH(node, &bus->current_devs, next) { - sc = I2C_SLAVE_GET_CLASS(node->elt); + s = node->elt; + sc = I2C_SLAVE_GET_CLASS(s); if (sc->send) { - ret = ret || sc->send(node->elt, *data); + trace_i2c_send(s->address, *data); + ret = ret || sc->send(s, *data); } else { ret = -1; } @@ -XXX,XX +XXX,XX @@ int i2c_send_recv(I2CBus *bus, uint8_t *data, bool send) sc = I2C_SLAVE_GET_CLASS(QLIST_FIRST(&bus->current_devs)->elt); if (sc->recv) { - ret = sc->recv(QLIST_FIRST(&bus->current_devs)->elt); + s = QLIST_FIRST(&bus->current_devs)->elt; + ret = sc->recv(s); + trace_i2c_recv(s->address, ret); if (ret < 0) { return ret; } else { @@ -XXX,XX +XXX,XX @@ void i2c_nack(I2CBus *bus) QLIST_FOREACH(node, &bus->current_devs, next) { sc = I2C_SLAVE_GET_CLASS(node->elt); if (sc->event) { + trace_i2c_event("nack", node->elt->address); sc->event(node->elt, I2C_NACK); } } diff --git a/hw/i2c/trace-events b/hw/i2c/trace-events new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/i2c/trace-events @@ -XXX,XX +XXX,XX @@ +# See docs/devel/tracing.txt for syntax documentation. + +# hw/i2c/core.c + +i2c_event(const char *event, uint8_t address) "%s(addr:0x%02x)" +i2c_send(uint8_t address, uint8_t data) "send(addr:0x%02x) data:0x%02x" +i2c_recv(uint8_t address, uint8_t data) "recv(addr:0x%02x) data:0x%02x" -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180606152128.449-2-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/milkymist-memcard.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/sd/milkymist-memcard.c b/hw/sd/milkymist-memcard.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/milkymist-memcard.c +++ b/hw/sd/milkymist-memcard.c @@ -XXX,XX +XXX,XX @@ static uint64_t memcard_read(void *opaque, hwaddr addr, r = s->response[s->response_read_ptr++]; if (s->response_read_ptr > s->response_len) { qemu_log_mask(LOG_GUEST_ERROR, "milkymist_memcard: " - "read more cmd bytes than available. Clipping."); + "read more cmd bytes than available: clipping\n"); s->response_read_ptr = 0; } } -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180606152128.449-3-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/digic-uart.c | 4 ++-- hw/timer/digic-timer.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/hw/char/digic-uart.c b/hw/char/digic-uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/digic-uart.c +++ b/hw/char/digic-uart.c @@ -XXX,XX +XXX,XX @@ static uint64_t digic_uart_read(void *opaque, hwaddr addr, default: qemu_log_mask(LOG_UNIMP, "digic-uart: read access to unknown register 0x" - TARGET_FMT_plx, addr << 2); + TARGET_FMT_plx "\n", addr << 2); } return ret; @@ -XXX,XX +XXX,XX @@ static void digic_uart_write(void *opaque, hwaddr addr, uint64_t value, default: qemu_log_mask(LOG_UNIMP, "digic-uart: write access to unknown register 0x" - TARGET_FMT_plx, addr << 2); + TARGET_FMT_plx "\n", addr << 2); } } diff --git a/hw/timer/digic-timer.c b/hw/timer/digic-timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/digic-timer.c +++ b/hw/timer/digic-timer.c @@ -XXX,XX +XXX,XX @@ static uint64_t digic_timer_read(void *opaque, hwaddr offset, unsigned size) default: qemu_log_mask(LOG_UNIMP, "digic-timer: read access to unknown register 0x" - TARGET_FMT_plx, offset); + TARGET_FMT_plx "\n", offset); } return ret; @@ -XXX,XX +XXX,XX @@ static void digic_timer_write(void *opaque, hwaddr offset, default: qemu_log_mask(LOG_UNIMP, "digic-timer: read access to unknown register 0x" - TARGET_FMT_plx, offset); + TARGET_FMT_plx "\n", offset); } } -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20180606152128.449-4-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/display/xlnx_dp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/hw/display/xlnx_dp.c b/hw/display/xlnx_dp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/xlnx_dp.c +++ b/hw/display/xlnx_dp.c @@ -XXX,XX +XXX,XX @@ static void xlnx_dp_avbufm_write(void *opaque, hwaddr offset, uint64_t value, case AV_BUF_STC_SNAPSHOT1: case AV_BUF_HCOUNT_VCOUNT_INT0: case AV_BUF_HCOUNT_VCOUNT_INT1: - qemu_log_mask(LOG_UNIMP, "avbufm: unimplmented"); + qemu_log_mask(LOG_UNIMP, "avbufm: unimplemented register 0x%04" + PRIx64 "\n", + offset << 2); break; default: s->avbufm_registers[offset] = value; -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Acked-by: David Gibson <david@gibson.dropbear.id.au> Message-id: 20180606152128.449-5-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ppc/pnv_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/ppc/pnv_core.c b/hw/ppc/pnv_core.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ppc/pnv_core.c +++ b/hw/ppc/pnv_core.c @@ -XXX,XX +XXX,XX @@ static uint64_t pnv_core_xscom_read(void *opaque, hwaddr addr, val = 0x24f000000000000ull; break; default: - qemu_log_mask(LOG_UNIMP, "Warning: reading reg=0x%" HWADDR_PRIx, + qemu_log_mask(LOG_UNIMP, "Warning: reading reg=0x%" HWADDR_PRIx "\n", addr); } @@ -XXX,XX +XXX,XX @@ static uint64_t pnv_core_xscom_read(void *opaque, hwaddr addr, static void pnv_core_xscom_write(void *opaque, hwaddr addr, uint64_t val, unsigned int width) { - qemu_log_mask(LOG_UNIMP, "Warning: writing to reg=0x%" HWADDR_PRIx, + qemu_log_mask(LOG_UNIMP, "Warning: writing to reg=0x%" HWADDR_PRIx "\n", addr); } -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20180606152128.449-6-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/core/register.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/core/register.c b/hw/core/register.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/register.c +++ b/hw/core/register.c @@ -XXX,XX +XXX,XX @@ void register_write(RegisterInfo *reg, uint64_t val, uint64_t we, if (test) { qemu_log_mask(LOG_UNIMP, "%s:%s writing %#" PRIx64 " to unimplemented bits:" \ - " %#" PRIx64 "", + " %#" PRIx64 "\n", prefix, reg->access->name, val, ac->unimp); } -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180606152128.449-7-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/mips/boston.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/hw/mips/boston.c b/hw/mips/boston.c index XXXXXXX..XXXXXXX 100644 --- a/hw/mips/boston.c +++ b/hw/mips/boston.c @@ -XXX,XX +XXX,XX @@ static uint64_t boston_platreg_read(void *opaque, hwaddr addr, uint32_t gic_freq, val; if (size != 4) { - qemu_log_mask(LOG_UNIMP, "%uB platform register read", size); + qemu_log_mask(LOG_UNIMP, "%uB platform register read\n", size); return 0; } @@ -XXX,XX +XXX,XX @@ static uint64_t boston_platreg_read(void *opaque, hwaddr addr, val |= PLAT_DDR_CFG_MHZ; return val; default: - qemu_log_mask(LOG_UNIMP, "Read platform register 0x%" HWADDR_PRIx, + qemu_log_mask(LOG_UNIMP, "Read platform register 0x%" HWADDR_PRIx "\n", addr & 0xffff); return 0; } @@ -XXX,XX +XXX,XX @@ static void boston_platreg_write(void *opaque, hwaddr addr, uint64_t val, unsigned size) { if (size != 4) { - qemu_log_mask(LOG_UNIMP, "%uB platform register write", size); + qemu_log_mask(LOG_UNIMP, "%uB platform register write\n", size); return; } @@ -XXX,XX +XXX,XX @@ static void boston_platreg_write(void *opaque, hwaddr addr, break; default: qemu_log_mask(LOG_UNIMP, "Write platform register 0x%" HWADDR_PRIx - " = 0x%" PRIx64, addr & 0xffff, val); + " = 0x%" PRIx64 "\n", addr & 0xffff, val); break; } } -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180606152128.449-8-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static uint64_t gptm_read(void *opaque, hwaddr offset, return s->rtc; } qemu_log_mask(LOG_UNIMP, - "GPTM: read of TAR but timer read not supported"); + "GPTM: read of TAR but timer read not supported\n"); return 0; case 0x4c: /* TBR */ qemu_log_mask(LOG_UNIMP, - "GPTM: read of TBR but timer read not supported"); + "GPTM: read of TBR but timer read not supported\n"); return 0; default: qemu_log_mask(LOG_GUEST_ERROR, @@ -XXX,XX +XXX,XX @@ static void stellaris_i2c_write(void *opaque, hwaddr offset, break; case 0x20: /* MCR */ if (value & 1) { - qemu_log_mask(LOG_UNIMP, "stellaris_i2c: Loopback not implemented"); + qemu_log_mask(LOG_UNIMP, + "stellaris_i2c: Loopback not implemented\n"); } if (value & 0x20) { qemu_log_mask(LOG_UNIMP, - "stellaris_i2c: Slave mode not implemented"); + "stellaris_i2c: Slave mode not implemented\n"); } s->mcr = value & 0x31; break; @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_write(void *opaque, hwaddr offset, s->sspri = value; break; case 0x28: /* PSSI */ - qemu_log_mask(LOG_UNIMP, "ADC: sample initiate unimplemented"); + qemu_log_mask(LOG_UNIMP, "ADC: sample initiate unimplemented\n"); break; case 0x30: /* SAC */ s->sac = value; -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180606152128.449-9-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void hw_breakpoint_update(ARMCPU *cpu, int n) case 4: /* unlinked address mismatch (reserved if AArch64) */ case 5: /* linked address mismatch (reserved if AArch64) */ qemu_log_mask(LOG_UNIMP, - "arm: address mismatch breakpoint types not implemented"); + "arm: address mismatch breakpoint types not implemented\n"); return; case 0: /* unlinked address match */ case 1: /* linked address match */ @@ -XXX,XX +XXX,XX @@ void hw_breakpoint_update(ARMCPU *cpu, int n) case 8: /* unlinked VMID match (reserved if no EL2) */ case 10: /* unlinked context ID and VMID match (reserved if no EL2) */ qemu_log_mask(LOG_UNIMP, - "arm: unlinked context breakpoint types not implemented"); + "arm: unlinked context breakpoint types not implemented\n"); return; case 9: /* linked VMID match (reserved if no EL2) */ case 11: /* linked context ID and VMID match (reserved if no EL2) */ -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Laurent Vivier <laurent@vivier.eu> Message-id: 20180606152128.449-10-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/m68k/translate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/m68k/translate.c b/target/m68k/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/translate.c +++ b/target/m68k/translate.c @@ -XXX,XX +XXX,XX @@ DISAS_INSN(undef) /* ??? This is both instructions that are as yet unimplemented for the 680x0 series, as well as those that are implemented but actually illegal for CPU32 or pre-68020. */ - qemu_log_mask(LOG_UNIMP, "Illegal instruction: %04x @ %08x", + qemu_log_mask(LOG_UNIMP, "Illegal instruction: %04x @ %08x\n", insn, s->insn_pc); gen_exception(s, s->insn_pc, EXCP_UNSUPPORTED); } -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180606152128.449-11-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/riscv/op_helper.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/target/riscv/op_helper.c b/target/riscv/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/op_helper.c +++ b/target/riscv/op_helper.c @@ -XXX,XX +XXX,XX @@ void csr_write_helper(CPURISCVState *env, target_ulong val_to_write, if ((val_to_write & 3) == 0) { env->stvec = val_to_write >> 2 << 2; } else { - qemu_log_mask(LOG_UNIMP, "CSR_STVEC: vectored traps not supported"); + qemu_log_mask(LOG_UNIMP, + "CSR_STVEC: vectored traps not supported\n"); } break; case CSR_SCOUNTEREN: @@ -XXX,XX +XXX,XX @@ void csr_write_helper(CPURISCVState *env, target_ulong val_to_write, if ((val_to_write & 3) == 0) { env->mtvec = val_to_write >> 2 << 2; } else { - qemu_log_mask(LOG_UNIMP, "CSR_MTVEC: vectored traps not supported"); + qemu_log_mask(LOG_UNIMP, + "CSR_MTVEC: vectored traps not supported\n"); } break; case CSR_MCOUNTEREN: -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Acked-by: Max Filippov <jcmvbkbc@gmail.com> Message-id: 20180606152128.449-12-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/xtensa/translate.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/target/xtensa/translate.c b/target/xtensa/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/translate.c +++ b/target/xtensa/translate.c @@ -XXX,XX +XXX,XX @@ static void translate_rur(DisasContext *dc, const uint32_t arg[], if (uregnames[par[0]].name) { tcg_gen_mov_i32(cpu_R[arg[0]], cpu_UR[par[0]]); } else { - qemu_log_mask(LOG_UNIMP, "RUR %d not implemented, ", par[0]); + qemu_log_mask(LOG_UNIMP, "RUR %d not implemented\n", par[0]); } } } @@ -XXX,XX +XXX,XX @@ static void translate_slli(DisasContext *dc, const uint32_t arg[], { if (gen_window_check2(dc, arg[0], arg[1])) { if (arg[2] == 32) { - qemu_log_mask(LOG_GUEST_ERROR, "slli a%d, a%d, 32 is undefined", + qemu_log_mask(LOG_GUEST_ERROR, "slli a%d, a%d, 32 is undefined\n", arg[0], arg[1]); } tcg_gen_shli_i32(cpu_R[arg[0]], cpu_R[arg[1]], arg[2] & 0x1f); @@ -XXX,XX +XXX,XX @@ static void translate_wur(DisasContext *dc, const uint32_t arg[], if (uregnames[par[0]].name) { gen_wur(par[0], cpu_R[arg[0]]); } else { - qemu_log_mask(LOG_UNIMP, "WUR %d not implemented, ", par[0]); + qemu_log_mask(LOG_UNIMP, "WUR %d not implemented\n", par[0]); } } } -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> The initial implementation is based on the Specs v1.10 (see a1bb27b1e98). However the SCR is anouncing the card being v1.01. The new chapters added in version 1.10 are: 4.3.10 Switch function command Switch function command (CMD6) 1 is used to switch or expand memory card functions. [...] This is a new feature, introduced in SD physical Layer Specification Version 1.10. Therefore, cards that are compatible with earlier versions of the spec do not support it. The host shall check the "SD_SPEC" field in the SCR register to recognize what version of the spec the card complies with before using CMD6. It is mandatory for SD memory card of Ver1.10 to support CMD6. 4.3.11 High-Speed mode (25MB/sec interface speed) Though the Rev 1.01 SD memory card supports up to 12.5MB/sec interface speed, the speed of 25MB/sec is necessary to support increasing performance needs of the host and because of memory size which continues to grow. To achieve 25MB/sec interface speed, clock rate is increased to 50MHz and CLK/CMD/DAT signal timing and circuit conditions are reconsidered and changed from Physical Layer Specification Version 1.01. 4.3.12 Command system (This chapter is newly added in version 1.10) SD commands CMD34-37, CMD50, CMD57 are reserved for SD command system expansion via the switch command. [These commands] will be considered as illegal commands (as defined in revision 1.01 of the SD physical layer specification). The SWITCH_FUNCTION is implemented since the first commit, a1bb27b1e98. The 25MB/sec High-Speed mode was already updated in d7ecb867529. The current implementation does not implements CMD34-37, CMD50 and CMD57, thus these commands already return ILLEGAL. With this patch, the SCR register now matches the description of the header: * SD Memory Card emulation as defined in the "SD Memory Card Physical * layer specification, Version 1.10." Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180607180641.874-2-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/sd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/sd/sd.c b/hw/sd/sd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/sd.c +++ b/hw/sd/sd.c @@ -XXX,XX +XXX,XX @@ static void sd_ocr_powerup(void *opaque) static void sd_set_scr(SDState *sd) { - sd->scr[0] = (0 << 4) /* SCR version 1.0 */ - | 0; /* Spec Versions 1.0 and 1.01 */ + sd->scr[0] = (0 << 4) /* SCR structure version 1.0 */ + | 1; /* Spec Version 1.10 */ sd->scr[1] = (2 << 4) /* SDSC Card (Security Version 1.01) */ | 0b0101; /* 1-bit or 4-bit width bus modes */ sd->scr[2] = 0x00; /* Extended Security is not supported. */ -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> From the "Physical Layer Simplified Specification Version 1.10" Chapter 7.3 "SPI Mode Transaction Packets" Table 57: "Commands and arguments" Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Acked-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20180607180641.874-3-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/sd.c | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/hw/sd/sd.c b/hw/sd/sd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/sd.c +++ b/hw/sd/sd.c @@ -XXX,XX +XXX,XX @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) return sd_illegal; case 6: /* CMD6: SWITCH_FUNCTION */ - if (sd->spi) - goto bad_cmd; switch (sd->mode) { case sd_data_transfer_mode: sd_function_switch(sd, req.arg); @@ -XXX,XX +XXX,XX @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) /* Block write commands (Class 4) */ case 24: /* CMD24: WRITE_SINGLE_BLOCK */ - if (sd->spi) { - goto unimplemented_spi_cmd; - } switch (sd->state) { case sd_transfer_state: /* Writing in SPI mode not implemented. */ @@ -XXX,XX +XXX,XX @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) break; case 25: /* CMD25: WRITE_MULTIPLE_BLOCK */ - if (sd->spi) { - goto unimplemented_spi_cmd; - } switch (sd->state) { case sd_transfer_state: /* Writing in SPI mode not implemented. */ @@ -XXX,XX +XXX,XX @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) break; case 27: /* CMD27: PROGRAM_CSD */ - if (sd->spi) { - goto unimplemented_spi_cmd; - } switch (sd->state) { case sd_transfer_state: sd->state = sd_receivingdata_state; @@ -XXX,XX +XXX,XX @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) /* Lock card commands (Class 7) */ case 42: /* CMD42: LOCK_UNLOCK */ - if (sd->spi) { - goto unimplemented_spi_cmd; - } switch (sd->state) { case sd_transfer_state: sd->state = sd_receivingdata_state; -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> As of this commit, the Spec v1 is not working, and all controllers expect the cards to be conformant to Spec v2. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20180607180641.874-4-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/sd/sd.h | 5 +++++ hw/sd/sd.c | 23 ++++++++++++++++++++--- 2 files changed, 25 insertions(+), 3 deletions(-) diff --git a/include/hw/sd/sd.h b/include/hw/sd/sd.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/sd/sd.h +++ b/include/hw/sd/sd.h @@ -XXX,XX +XXX,XX @@ #define APP_CMD (1 << 5) #define AKE_SEQ_ERROR (1 << 3) +enum SDPhySpecificationVersion { + SD_PHY_SPECv1_10_VERS = 1, + SD_PHY_SPECv2_00_VERS = 2, +}; + typedef enum { SD_VOLTAGE_0_4V = 400, /* currently not supported */ SD_VOLTAGE_1_8V = 1800, diff --git a/hw/sd/sd.c b/hw/sd/sd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/sd.c +++ b/hw/sd/sd.c @@ -XXX,XX +XXX,XX @@ /* * SD Memory Card emulation as defined in the "SD Memory Card Physical - * layer specification, Version 1.10." + * layer specification, Version 2.00." * * Copyright (c) 2006 Andrzej Zaborowski <balrog@zabor.org> * Copyright (c) 2007 CodeSourcery + * Copyright (c) 2018 Philippe Mathieu-Daudé <f4bug@amsat.org> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -XXX,XX +XXX,XX @@ struct SDState { uint8_t sd_status[64]; /* Configurable properties */ + uint8_t spec_version; BlockBackend *blk; bool spi; @@ -XXX,XX +XXX,XX @@ static void sd_ocr_powerup(void *opaque) static void sd_set_scr(SDState *sd) { - sd->scr[0] = (0 << 4) /* SCR structure version 1.0 */ - | 1; /* Spec Version 1.10 */ + sd->scr[0] = 0 << 4; /* SCR structure version 1.0 */ + if (sd->spec_version == SD_PHY_SPECv1_10_VERS) { + sd->scr[0] |= 1; /* Spec Version 1.10 */ + } else { + sd->scr[0] |= 2; /* Spec Version 2.00 */ + } sd->scr[1] = (2 << 4) /* SDSC Card (Security Version 1.01) */ | 0b0101; /* 1-bit or 4-bit width bus modes */ sd->scr[2] = 0x00; /* Extended Security is not supported. */ @@ -XXX,XX +XXX,XX @@ static void sd_realize(DeviceState *dev, Error **errp) sd->proto_name = sd->spi ? "SPI" : "SD"; + switch (sd->spec_version) { + case SD_PHY_SPECv1_10_VERS + ... SD_PHY_SPECv2_00_VERS: + break; + default: + error_setg(errp, "Invalid SD card Spec version: %u", sd->spec_version); + return; + } + if (sd->blk && blk_is_read_only(sd->blk)) { error_setg(errp, "Cannot use read-only drive as SD card"); return; @@ -XXX,XX +XXX,XX @@ static void sd_realize(DeviceState *dev, Error **errp) } static Property sd_properties[] = { + DEFINE_PROP_UINT8("spec_version", SDState, + spec_version, SD_PHY_SPECv2_00_VERS), DEFINE_PROP_DRIVE("drive", SDState, blk), /* We do not model the chip select pin, so allow the board to select * whether card should be in SSI or MMC/SD mode. It is also up to the -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> CMD8 is "Reserved" in Spec v1.10. Spec v2.00 introduces the SEND_IF_COND command: 6.4.1 Power Up CMD8 is newly added in the Physical Layer Specification Version 2.00 to support multiple voltage ranges and used to check whether the card supports supplied voltage. The version 2.00 or later host shall issue CMD8 and verify voltage before card initialization. The host that does not support CMD8 shall supply high voltage range. Message-Id: 201204252110.20873.paul@codesourcery.com Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180607180641.874-5-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/sd.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/hw/sd/sd.c b/hw/sd/sd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/sd.c +++ b/hw/sd/sd.c @@ -XXX,XX +XXX,XX @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) break; case 8: /* CMD8: SEND_IF_COND */ - /* Physical Layer Specification Version 2.00 command */ + if (sd->spec_version < SD_PHY_SPECv2_00_VERS) { + break; + } if (sd->state != sd_idle_state) { break; } -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20180607180641.874-6-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/sd/sd.h | 1 + hw/sd/sd.c | 7 +++++-- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/include/hw/sd/sd.h b/include/hw/sd/sd.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/sd/sd.h +++ b/include/hw/sd/sd.h @@ -XXX,XX +XXX,XX @@ enum SDPhySpecificationVersion { SD_PHY_SPECv1_10_VERS = 1, SD_PHY_SPECv2_00_VERS = 2, + SD_PHY_SPECv3_01_VERS = 3, }; typedef enum { diff --git a/hw/sd/sd.c b/hw/sd/sd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/sd.c +++ b/hw/sd/sd.c @@ -XXX,XX +XXX,XX @@ static void sd_set_scr(SDState *sd) if (sd->spec_version == SD_PHY_SPECv1_10_VERS) { sd->scr[0] |= 1; /* Spec Version 1.10 */ } else { - sd->scr[0] |= 2; /* Spec Version 2.00 */ + sd->scr[0] |= 2; /* Spec Version 2.00 or Version 3.0X */ } sd->scr[1] = (2 << 4) /* SDSC Card (Security Version 1.01) */ | 0b0101; /* 1-bit or 4-bit width bus modes */ sd->scr[2] = 0x00; /* Extended Security is not supported. */ + if (sd->spec_version >= SD_PHY_SPECv3_01_VERS) { + sd->scr[2] |= 1 << 7; /* Spec Version 3.0X */ + } sd->scr[3] = 0x00; /* reserved for manufacturer usage */ sd->scr[4] = 0x00; @@ -XXX,XX +XXX,XX @@ static void sd_realize(DeviceState *dev, Error **errp) switch (sd->spec_version) { case SD_PHY_SPECv1_10_VERS - ... SD_PHY_SPECv2_00_VERS: + ... SD_PHY_SPECv3_01_VERS: break; default: error_setg(errp, "Invalid SD card Spec version: %u", sd->spec_version); -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> These commands got introduced by Spec v3 (see 0c3fb03f7ec and 4481bbc79d2). Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180607180641.874-7-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/sd.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/hw/sd/sd.c b/hw/sd/sd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/sd.c +++ b/hw/sd/sd.c @@ -XXX,XX +XXX,XX @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) break; case 19: /* CMD19: SEND_TUNING_BLOCK (SD) */ + if (sd->spec_version < SD_PHY_SPECv3_01_VERS) { + break; + } if (sd->state == sd_transfer_state) { sd->state = sd_sendingdata_state; sd->data_offset = 0; @@ -XXX,XX +XXX,XX @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) break; case 23: /* CMD23: SET_BLOCK_COUNT */ + if (sd->spec_version < SD_PHY_SPECv3_01_VERS) { + break; + } switch (sd->state) { case sd_transfer_state: sd->multi_blk_cnt = req.arg; -- 2.17.1 Small pile of bug fixes for rc1. I've included my patches to get our docs building with Sphinx 3, just for convenience... -- PMM The following changes since commit b149dea55cce97cb226683d06af61984a1c11e96: Merge remote-tracking branch 'remotes/cschoenebeck/tags/pull-9p-20201102' into staging (2020-11-02 10:57:48 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20201102 for you to fetch changes up to ffb4fbf90a2f63c9cb33e4bb9f854c79bf04ca4a: tests/qtest/npcm7xx_rng-test: Disable randomness tests (2020-11-02 16:52:18 +0000) ---------------------------------------------------------------- target-arm queue: * target/arm: Fix Neon emulation bugs on big-endian hosts * target/arm: fix handling of HCR.FB * target/arm: fix LORID_EL1 access check * disas/capstone: Fix monitor disassembly of >32 bytes * hw/arm/smmuv3: Fix potential integer overflow (CID 1432363) * hw/arm/boot: fix SVE for EL3 direct kernel boot * hw/display/omap_lcdc: Fix potential NULL pointer dereference * hw/display/exynos4210_fimd: Fix potential NULL pointer dereference * target/arm: Get correct MMU index for other-security-state * configure: Test that gio libs from pkg-config work * hw/intc/arm_gicv3_cpuif: Make GIC maintenance interrupts work * docs: Fix building with Sphinx 3 * tests/qtest/npcm7xx_rng-test: Disable randomness tests ---------------------------------------------------------------- AlexChen (2): hw/display/omap_lcdc: Fix potential NULL pointer dereference hw/display/exynos4210_fimd: Fix potential NULL pointer dereference Peter Maydell (9): target/arm: Fix float16 pairwise Neon ops on big-endian hosts target/arm: Fix VUDOT/VSDOT (scalar) on big-endian hosts disas/capstone: Fix monitor disassembly of >32 bytes target/arm: Get correct MMU index for other-security-state configure: Test that gio libs from pkg-config work hw/intc/arm_gicv3_cpuif: Make GIC maintenance interrupts work scripts/kerneldoc: For Sphinx 3 use c:macro for macros with arguments qemu-option-trace.rst.inc: Don't use option:: markup tests/qtest/npcm7xx_rng-test: Disable randomness tests Philippe Mathieu-Daudé (1): hw/arm/smmuv3: Fix potential integer overflow (CID 1432363) Richard Henderson (11): target/arm: Introduce neon_full_reg_offset target/arm: Move neon_element_offset to translate.c target/arm: Use neon_element_offset in neon_load/store_reg target/arm: Use neon_element_offset in vfp_reg_offset target/arm: Add read/write_neon_element32 target/arm: Expand read/write_neon_element32 to all MemOp target/arm: Rename neon_load_reg32 to vfp_load_reg32 target/arm: Add read/write_neon_element64 target/arm: Rename neon_load_reg64 to vfp_load_reg64 target/arm: Simplify do_long_3d and do_2scalar_long target/arm: Improve do_prewiden_3d Rémi Denis-Courmont (3): target/arm: fix handling of HCR.FB target/arm: fix LORID_EL1 access check hw/arm/boot: fix SVE for EL3 direct kernel boot docs/qemu-option-trace.rst.inc | 6 +- configure | 10 +- include/hw/intc/arm_gicv3_common.h | 1 - disas/capstone.c | 2 +- hw/arm/boot.c | 3 + hw/arm/smmuv3.c | 3 +- hw/display/exynos4210_fimd.c | 4 +- hw/display/omap_lcdc.c | 10 +- hw/intc/arm_gicv3_cpuif.c | 5 +- target/arm/helper.c | 24 +- target/arm/m_helper.c | 3 +- target/arm/translate.c | 153 +++++++++--- target/arm/vec_helper.c | 12 +- tests/qtest/npcm7xx_rng-test.c | 14 +- scripts/kernel-doc | 18 +- target/arm/translate-neon.c.inc | 472 ++++++++++++++++++++----------------- target/arm/translate-vfp.c.inc | 341 +++++++++++---------------- 17 files changed, 588 insertions(+), 493 deletions(-) From: Richard Henderson <richard.henderson@linaro.org> This function makes it clear that we're talking about the whole register, and not the 32-bit piece at index 0. This fixes a bug when running on a big-endian host. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 8 ++++++ target/arm/translate-neon.c.inc | 44 ++++++++++++++++----------------- target/arm/translate-vfp.c.inc | 2 +- 3 files changed, 31 insertions(+), 23 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void gen_hlt(DisasContext *s, int imm) unallocated_encoding(s); } +/* + * Return the offset of a "full" NEON Dreg. + */ +static long neon_full_reg_offset(unsigned reg) +{ + return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]); +} + static inline long vfp_reg_offset(bool dp, unsigned reg) { if (dp) { diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ neon_element_offset(int reg, int element, MemOp size) ofs ^= 8 - element_size; } #endif - return neon_reg_offset(reg, 0) + ofs; + return neon_full_reg_offset(reg) + ofs; } static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop) @@ -XXX,XX +XXX,XX @@ static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a) * We cannot write 16 bytes at once because the * destination is unaligned. */ - tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0), + tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(vd), 8, 8, tmp); - tcg_gen_gvec_mov(0, neon_reg_offset(vd + 1, 0), - neon_reg_offset(vd, 0), 8, 8); + tcg_gen_gvec_mov(0, neon_full_reg_offset(vd + 1), + neon_full_reg_offset(vd), 8, 8); } else { - tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0), + tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(vd), vec_size, vec_size, tmp); } tcg_gen_addi_i32(addr, addr, 1 << size); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a) static bool do_3same(DisasContext *s, arg_3same *a, GVecGen3Fn fn) { int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rn_ofs = neon_reg_offset(a->vn, 0); - int rm_ofs = neon_reg_offset(a->vm, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rn_ofs = neon_full_reg_offset(a->vn); + int rm_ofs = neon_full_reg_offset(a->vm); if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn) { /* Handle a 2-reg-shift insn which can be vectorized. */ int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rm_ofs = neon_reg_offset(a->vm, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rm_ofs = neon_full_reg_offset(a->vm); if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, { /* FP operations in 2-reg-and-shift group */ int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rm_ofs = neon_reg_offset(a->vm, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rm_ofs = neon_full_reg_offset(a->vm); TCGv_ptr fpst; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static bool do_1reg_imm(DisasContext *s, arg_1reg_imm *a, return true; } - reg_ofs = neon_reg_offset(a->vd, 0); + reg_ofs = neon_full_reg_offset(a->vd); vec_size = a->q ? 16 : 8; imm = asimd_imm_const(a->imm, a->cmode, a->op); @@ -XXX,XX +XXX,XX @@ static bool trans_VMULL_P_3d(DisasContext *s, arg_3diff *a) return true; } - tcg_gen_gvec_3_ool(neon_reg_offset(a->vd, 0), - neon_reg_offset(a->vn, 0), - neon_reg_offset(a->vm, 0), + tcg_gen_gvec_3_ool(neon_full_reg_offset(a->vd), + neon_full_reg_offset(a->vn), + neon_full_reg_offset(a->vm), 16, 16, 0, fn_gvec); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_fp_vec(DisasContext *s, arg_2scalar *a, { /* Two registers and a scalar, using gvec */ int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rn_ofs = neon_reg_offset(a->vn, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rn_ofs = neon_full_reg_offset(a->vn); int rm_ofs; int idx; TCGv_ptr fpstatus; @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_fp_vec(DisasContext *s, arg_2scalar *a, /* a->vm is M:Vm, which encodes both register and index */ idx = extract32(a->vm, a->size + 2, 2); a->vm = extract32(a->vm, 0, a->size + 2); - rm_ofs = neon_reg_offset(a->vm, 0); + rm_ofs = neon_full_reg_offset(a->vm); fpstatus = fpstatus_ptr(a->size == 1 ? FPST_STD_F16 : FPST_STD); tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpstatus, @@ -XXX,XX +XXX,XX @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a) return true; } - tcg_gen_gvec_dup_mem(a->size, neon_reg_offset(a->vd, 0), + tcg_gen_gvec_dup_mem(a->size, neon_full_reg_offset(a->vd), neon_element_offset(a->vm, a->index, a->size), a->q ? 16 : 8, a->q ? 16 : 8); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_F32_F16(DisasContext *s, arg_2misc *a) static bool do_2misc_vec(DisasContext *s, arg_2misc *a, GVecGen2Fn *fn) { int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rm_ofs = neon_reg_offset(a->vm, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rm_ofs = neon_full_reg_offset(a->vm); if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VDUP(DisasContext *s, arg_VDUP *a) } tmp = load_reg(s, a->rt); - tcg_gen_gvec_dup_i32(size, neon_reg_offset(a->vn, 0), + tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(a->vn), vec_size, vec_size, tmp); tcg_temp_free_i32(tmp); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This will shortly have users outside of translate-neon.c.inc. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 20 ++++++++++++++++++++ target/arm/translate-neon.c.inc | 19 ------------------- 2 files changed, 20 insertions(+), 19 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static long neon_full_reg_offset(unsigned reg) return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]); } +/* + * Return the offset of a 2**SIZE piece of a NEON register, at index ELE, + * where 0 is the least significant end of the register. + */ +static long neon_element_offset(int reg, int element, MemOp size) +{ + int element_size = 1 << size; + int ofs = element * element_size; +#ifdef HOST_WORDS_BIGENDIAN + /* + * Calculate the offset assuming fully little-endian, + * then XOR to account for the order of the 8-byte units. + */ + if (element_size < 8) { + ofs ^= 8 - element_size; + } +#endif + return neon_full_reg_offset(reg) + ofs; +} + static inline long vfp_reg_offset(bool dp, unsigned reg) { if (dp) { diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static inline int neon_3same_fp_size(DisasContext *s, int x) #include "decode-neon-ls.c.inc" #include "decode-neon-shared.c.inc" -/* Return the offset of a 2**SIZE piece of a NEON register, at index ELE, - * where 0 is the least significant end of the register. - */ -static inline long -neon_element_offset(int reg, int element, MemOp size) -{ - int element_size = 1 << size; - int ofs = element * element_size; -#ifdef HOST_WORDS_BIGENDIAN - /* Calculate the offset assuming fully little-endian, - * then XOR to account for the order of the 8-byte units. - */ - if (element_size < 8) { - ofs ^= 8 - element_size; - } -#endif - return neon_full_reg_offset(reg) + ofs; -} - static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop) { long offset = neon_element_offset(reg, ele, mop & MO_SIZE); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> These are the only users of neon_reg_offset, so remove that. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-4-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline long vfp_reg_offset(bool dp, unsigned reg) } } -/* Return the offset of a 32-bit piece of a NEON register. - zero is the least significant end of the register. */ -static inline long -neon_reg_offset (int reg, int n) -{ - int sreg; - sreg = reg * 2 + n; - return vfp_reg_offset(0, sreg); -} - static TCGv_i32 neon_load_reg(int reg, int pass) { TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_ld_i32(tmp, cpu_env, neon_reg_offset(reg, pass)); + tcg_gen_ld_i32(tmp, cpu_env, neon_element_offset(reg, pass, MO_32)); return tmp; } static void neon_store_reg(int reg, int pass, TCGv_i32 var) { - tcg_gen_st_i32(var, cpu_env, neon_reg_offset(reg, pass)); + tcg_gen_st_i32(var, cpu_env, neon_element_offset(reg, pass, MO_32)); tcg_temp_free_i32(var); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This seems a bit more readable than using offsetof CPU_DoubleU. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static long neon_element_offset(int reg, int element, MemOp size) return neon_full_reg_offset(reg) + ofs; } -static inline long vfp_reg_offset(bool dp, unsigned reg) +/* Return the offset of a VFP Dreg (dp = true) or VFP Sreg (dp = false). */ +static long vfp_reg_offset(bool dp, unsigned reg) { if (dp) { - return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]); + return neon_element_offset(reg, 0, MO_64); } else { - long ofs = offsetof(CPUARMState, vfp.zregs[reg >> 2].d[(reg >> 1) & 1]); - if (reg & 1) { - ofs += offsetof(CPU_DoubleU, l.upper); - } else { - ofs += offsetof(CPU_DoubleU, l.lower); - } - return ofs; + return neon_element_offset(reg >> 1, reg & 1, MO_32); } } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Model these off the aa64 read/write_vec_element functions. Use it within translate-neon.c.inc. The new functions do not allocate or free temps, so this rearranges the calling code a bit. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-6-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 26 ++++ target/arm/translate-neon.c.inc | 256 ++++++++++++++++++++------------ 2 files changed, 183 insertions(+), 99 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void neon_store_reg32(TCGv_i32 var, int reg) tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); } +static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp size) +{ + long off = neon_element_offset(reg, ele, size); + + switch (size) { + case MO_32: + tcg_gen_ld_i32(dest, cpu_env, off); + break; + default: + g_assert_not_reached(); + } +} + +static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp size) +{ + long off = neon_element_offset(reg, ele, size); + + switch (size) { + case MO_32: + tcg_gen_st_i32(src, cpu_env, off); + break; + default: + g_assert_not_reached(); + } +} + static TCGv_ptr vfp_reg_ptr(bool dp, int reg) { TCGv_ptr ret = tcg_temp_new_ptr(); diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_3same_pair(DisasContext *s, arg_3same *a, NeonGenTwoOpFn *fn) * early. Since Q is 0 there are always just two passes, so instead * of a complicated loop over each pass we just unroll. */ - tmp = neon_load_reg(a->vn, 0); - tmp2 = neon_load_reg(a->vn, 1); + tmp = tcg_temp_new_i32(); + tmp2 = tcg_temp_new_i32(); + tmp3 = tcg_temp_new_i32(); + + read_neon_element32(tmp, a->vn, 0, MO_32); + read_neon_element32(tmp2, a->vn, 1, MO_32); fn(tmp, tmp, tmp2); - tcg_temp_free_i32(tmp2); - tmp3 = neon_load_reg(a->vm, 0); - tmp2 = neon_load_reg(a->vm, 1); + read_neon_element32(tmp3, a->vm, 0, MO_32); + read_neon_element32(tmp2, a->vm, 1, MO_32); fn(tmp3, tmp3, tmp2); - tcg_temp_free_i32(tmp2); - neon_store_reg(a->vd, 0, tmp); - neon_store_reg(a->vd, 1, tmp3); + write_neon_element32(tmp, a->vd, 0, MO_32); + write_neon_element32(tmp3, a->vd, 1, MO_32); + + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(tmp2); + tcg_temp_free_i32(tmp3); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a, * 2-reg-and-shift operations, size < 3 case, where the * helper needs to be passed cpu_env. */ - TCGv_i32 constimm; + TCGv_i32 constimm, tmp; int pass; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a, * by immediate using the variable shift operations. */ constimm = tcg_const_i32(dup_const(a->size, a->shift)); + tmp = tcg_temp_new_i32(); for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vm, pass); + read_neon_element32(tmp, a->vm, pass, MO_32); fn(tmp, cpu_env, tmp, constimm); - neon_store_reg(a->vd, pass, tmp); + write_neon_element32(tmp, a->vd, pass, MO_32); } + tcg_temp_free_i32(tmp); tcg_temp_free_i32(constimm); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a, constimm = tcg_const_i64(-a->shift); rm1 = tcg_temp_new_i64(); rm2 = tcg_temp_new_i64(); + rd = tcg_temp_new_i32(); /* Load both inputs first to avoid potential overwrite if rm == rd */ neon_load_reg64(rm1, a->vm); neon_load_reg64(rm2, a->vm + 1); shiftfn(rm1, rm1, constimm); - rd = tcg_temp_new_i32(); narrowfn(rd, cpu_env, rm1); - neon_store_reg(a->vd, 0, rd); + write_neon_element32(rd, a->vd, 0, MO_32); shiftfn(rm2, rm2, constimm); - rd = tcg_temp_new_i32(); narrowfn(rd, cpu_env, rm2); - neon_store_reg(a->vd, 1, rd); + write_neon_element32(rd, a->vd, 1, MO_32); + tcg_temp_free_i32(rd); tcg_temp_free_i64(rm1); tcg_temp_free_i64(rm2); tcg_temp_free_i64(constimm); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a, constimm = tcg_const_i32(imm); /* Load all inputs first to avoid potential overwrite */ - rm1 = neon_load_reg(a->vm, 0); - rm2 = neon_load_reg(a->vm, 1); - rm3 = neon_load_reg(a->vm + 1, 0); - rm4 = neon_load_reg(a->vm + 1, 1); + rm1 = tcg_temp_new_i32(); + rm2 = tcg_temp_new_i32(); + rm3 = tcg_temp_new_i32(); + rm4 = tcg_temp_new_i32(); + read_neon_element32(rm1, a->vm, 0, MO_32); + read_neon_element32(rm2, a->vm, 1, MO_32); + read_neon_element32(rm3, a->vm, 2, MO_32); + read_neon_element32(rm4, a->vm, 3, MO_32); rtmp = tcg_temp_new_i64(); shiftfn(rm1, rm1, constimm); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a, tcg_temp_free_i32(rm2); narrowfn(rm1, cpu_env, rtmp); - neon_store_reg(a->vd, 0, rm1); + write_neon_element32(rm1, a->vd, 0, MO_32); + tcg_temp_free_i32(rm1); shiftfn(rm3, rm3, constimm); shiftfn(rm4, rm4, constimm); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a, narrowfn(rm3, cpu_env, rtmp); tcg_temp_free_i64(rtmp); - neon_store_reg(a->vd, 1, rm3); + write_neon_element32(rm3, a->vd, 1, MO_32); + tcg_temp_free_i32(rm3); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a, widen_mask = dup_const(a->size + 1, widen_mask); } - rm0 = neon_load_reg(a->vm, 0); - rm1 = neon_load_reg(a->vm, 1); + rm0 = tcg_temp_new_i32(); + rm1 = tcg_temp_new_i32(); + read_neon_element32(rm0, a->vm, 0, MO_32); + read_neon_element32(rm1, a->vm, 1, MO_32); tmp = tcg_temp_new_i64(); widenfn(tmp, rm0); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, if (src1_wide) { neon_load_reg64(rn0_64, a->vn); } else { - TCGv_i32 tmp = neon_load_reg(a->vn, 0); + TCGv_i32 tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vn, 0, MO_32); widenfn(rn0_64, tmp); tcg_temp_free_i32(tmp); } - rm = neon_load_reg(a->vm, 0); + rm = tcg_temp_new_i32(); + read_neon_element32(rm, a->vm, 0, MO_32); widenfn(rm_64, rm); tcg_temp_free_i32(rm); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, if (src1_wide) { neon_load_reg64(rn1_64, a->vn + 1); } else { - TCGv_i32 tmp = neon_load_reg(a->vn, 1); + TCGv_i32 tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vn, 1, MO_32); widenfn(rn1_64, tmp); tcg_temp_free_i32(tmp); } - rm = neon_load_reg(a->vm, 1); + rm = tcg_temp_new_i32(); + read_neon_element32(rm, a->vm, 1, MO_32); neon_store_reg64(rn0_64, a->vd); @@ -XXX,XX +XXX,XX @@ static bool do_narrow_3d(DisasContext *s, arg_3diff *a, narrowfn(rd1, rn_64); - neon_store_reg(a->vd, 0, rd0); - neon_store_reg(a->vd, 1, rd1); + write_neon_element32(rd0, a->vd, 0, MO_32); + write_neon_element32(rd1, a->vd, 1, MO_32); + tcg_temp_free_i32(rd0); + tcg_temp_free_i32(rd1); tcg_temp_free_i64(rn_64); tcg_temp_free_i64(rm_64); @@ -XXX,XX +XXX,XX @@ static bool do_long_3d(DisasContext *s, arg_3diff *a, rd0 = tcg_temp_new_i64(); rd1 = tcg_temp_new_i64(); - rn = neon_load_reg(a->vn, 0); - rm = neon_load_reg(a->vm, 0); + rn = tcg_temp_new_i32(); + rm = tcg_temp_new_i32(); + read_neon_element32(rn, a->vn, 0, MO_32); + read_neon_element32(rm, a->vm, 0, MO_32); opfn(rd0, rn, rm); - tcg_temp_free_i32(rn); - tcg_temp_free_i32(rm); - rn = neon_load_reg(a->vn, 1); - rm = neon_load_reg(a->vm, 1); + read_neon_element32(rn, a->vn, 1, MO_32); + read_neon_element32(rm, a->vm, 1, MO_32); opfn(rd1, rn, rm); tcg_temp_free_i32(rn); tcg_temp_free_i32(rm); @@ -XXX,XX +XXX,XX @@ static void gen_neon_dup_high16(TCGv_i32 var) static inline TCGv_i32 neon_get_scalar(int size, int reg) { - TCGv_i32 tmp; - if (size == 1) { - tmp = neon_load_reg(reg & 7, reg >> 4); + TCGv_i32 tmp = tcg_temp_new_i32(); + if (size == MO_16) { + read_neon_element32(tmp, reg & 7, reg >> 4, MO_32); if (reg & 8) { gen_neon_dup_high16(tmp); } else { gen_neon_dup_low16(tmp); } } else { - tmp = neon_load_reg(reg & 15, reg >> 4); + read_neon_element32(tmp, reg & 15, reg >> 4, MO_32); } return tmp; } @@ -XXX,XX +XXX,XX @@ static bool do_2scalar(DisasContext *s, arg_2scalar *a, * perform an accumulation operation of that result into the * destination. */ - TCGv_i32 scalar; + TCGv_i32 scalar, tmp; int pass; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static bool do_2scalar(DisasContext *s, arg_2scalar *a, } scalar = neon_get_scalar(a->size, a->vm); + tmp = tcg_temp_new_i32(); for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vn, pass); + read_neon_element32(tmp, a->vn, pass, MO_32); opfn(tmp, tmp, scalar); if (accfn) { - TCGv_i32 rd = neon_load_reg(a->vd, pass); + TCGv_i32 rd = tcg_temp_new_i32(); + read_neon_element32(rd, a->vd, pass, MO_32); accfn(tmp, rd, tmp); tcg_temp_free_i32(rd); } - neon_store_reg(a->vd, pass, tmp); + write_neon_element32(tmp, a->vd, pass, MO_32); } + tcg_temp_free_i32(tmp); tcg_temp_free_i32(scalar); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_vqrdmlah_2sc(DisasContext *s, arg_2scalar *a, * performs a kind of fused op-then-accumulate using a helper * function that takes all of rd, rn and the scalar at once. */ - TCGv_i32 scalar; + TCGv_i32 scalar, rn, rd; int pass; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static bool do_vqrdmlah_2sc(DisasContext *s, arg_2scalar *a, } scalar = neon_get_scalar(a->size, a->vm); + rn = tcg_temp_new_i32(); + rd = tcg_temp_new_i32(); for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 rn = neon_load_reg(a->vn, pass); - TCGv_i32 rd = neon_load_reg(a->vd, pass); + read_neon_element32(rn, a->vn, pass, MO_32); + read_neon_element32(rd, a->vd, pass, MO_32); opfn(rd, cpu_env, rn, scalar, rd); - tcg_temp_free_i32(rn); - neon_store_reg(a->vd, pass, rd); + write_neon_element32(rd, a->vd, pass, MO_32); } + tcg_temp_free_i32(rn); + tcg_temp_free_i32(rd); tcg_temp_free_i32(scalar); return true; @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_long(DisasContext *s, arg_2scalar *a, scalar = neon_get_scalar(a->size, a->vm); /* Load all inputs before writing any outputs, in case of overlap */ - rn = neon_load_reg(a->vn, 0); + rn = tcg_temp_new_i32(); + read_neon_element32(rn, a->vn, 0, MO_32); rn0_64 = tcg_temp_new_i64(); opfn(rn0_64, rn, scalar); - tcg_temp_free_i32(rn); - rn = neon_load_reg(a->vn, 1); + read_neon_element32(rn, a->vn, 1, MO_32); rn1_64 = tcg_temp_new_i64(); opfn(rn1_64, rn, scalar); tcg_temp_free_i32(rn); @@ -XXX,XX +XXX,XX @@ static bool trans_VTBL(DisasContext *s, arg_VTBL *a) return false; } n <<= 3; + tmp = tcg_temp_new_i32(); if (a->op) { - tmp = neon_load_reg(a->vd, 0); + read_neon_element32(tmp, a->vd, 0, MO_32); } else { - tmp = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp, 0); } - tmp2 = neon_load_reg(a->vm, 0); + tmp2 = tcg_temp_new_i32(); + read_neon_element32(tmp2, a->vm, 0, MO_32); ptr1 = vfp_reg_ptr(true, a->vn); tmp4 = tcg_const_i32(n); gen_helper_neon_tbl(tmp2, tmp2, tmp, ptr1, tmp4); - tcg_temp_free_i32(tmp); + if (a->op) { - tmp = neon_load_reg(a->vd, 1); + read_neon_element32(tmp, a->vd, 1, MO_32); } else { - tmp = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp, 0); } - tmp3 = neon_load_reg(a->vm, 1); + tmp3 = tcg_temp_new_i32(); + read_neon_element32(tmp3, a->vm, 1, MO_32); gen_helper_neon_tbl(tmp3, tmp3, tmp, ptr1, tmp4); + tcg_temp_free_i32(tmp); tcg_temp_free_i32(tmp4); tcg_temp_free_ptr(ptr1); - neon_store_reg(a->vd, 0, tmp2); - neon_store_reg(a->vd, 1, tmp3); - tcg_temp_free_i32(tmp); + + write_neon_element32(tmp2, a->vd, 0, MO_32); + write_neon_element32(tmp3, a->vd, 1, MO_32); + tcg_temp_free_i32(tmp2); + tcg_temp_free_i32(tmp3); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a) static bool trans_VREV64(DisasContext *s, arg_VREV64 *a) { int pass, half; + TCGv_i32 tmp[2]; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VREV64(DisasContext *s, arg_VREV64 *a) return true; } - for (pass = 0; pass < (a->q ? 2 : 1); pass++) { - TCGv_i32 tmp[2]; + tmp[0] = tcg_temp_new_i32(); + tmp[1] = tcg_temp_new_i32(); + for (pass = 0; pass < (a->q ? 2 : 1); pass++) { for (half = 0; half < 2; half++) { - tmp[half] = neon_load_reg(a->vm, pass * 2 + half); + read_neon_element32(tmp[half], a->vm, pass * 2 + half, MO_32); switch (a->size) { case 0: tcg_gen_bswap32_i32(tmp[half], tmp[half]); @@ -XXX,XX +XXX,XX @@ static bool trans_VREV64(DisasContext *s, arg_VREV64 *a) g_assert_not_reached(); } } - neon_store_reg(a->vd, pass * 2, tmp[1]); - neon_store_reg(a->vd, pass * 2 + 1, tmp[0]); + write_neon_element32(tmp[1], a->vd, pass * 2, MO_32); + write_neon_element32(tmp[0], a->vd, pass * 2 + 1, MO_32); } + + tcg_temp_free_i32(tmp[0]); + tcg_temp_free_i32(tmp[1]); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2misc_pairwise(DisasContext *s, arg_2misc *a, rm0_64 = tcg_temp_new_i64(); rm1_64 = tcg_temp_new_i64(); rd_64 = tcg_temp_new_i64(); - tmp = neon_load_reg(a->vm, pass * 2); + + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, pass * 2, MO_32); widenfn(rm0_64, tmp); - tcg_temp_free_i32(tmp); - tmp = neon_load_reg(a->vm, pass * 2 + 1); + read_neon_element32(tmp, a->vm, pass * 2 + 1, MO_32); widenfn(rm1_64, tmp); tcg_temp_free_i32(tmp); + opfn(rd_64, rm0_64, rm1_64); tcg_temp_free_i64(rm0_64); tcg_temp_free_i64(rm1_64); @@ -XXX,XX +XXX,XX @@ static bool do_vmovn(DisasContext *s, arg_2misc *a, narrowfn(rd0, cpu_env, rm); neon_load_reg64(rm, a->vm + 1); narrowfn(rd1, cpu_env, rm); - neon_store_reg(a->vd, 0, rd0); - neon_store_reg(a->vd, 1, rd1); + write_neon_element32(rd0, a->vd, 0, MO_32); + write_neon_element32(rd1, a->vd, 1, MO_32); + tcg_temp_free_i32(rd0); + tcg_temp_free_i32(rd1); tcg_temp_free_i64(rm); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VSHLL(DisasContext *s, arg_2misc *a) } rd = tcg_temp_new_i64(); + rm0 = tcg_temp_new_i32(); + rm1 = tcg_temp_new_i32(); - rm0 = neon_load_reg(a->vm, 0); - rm1 = neon_load_reg(a->vm, 1); + read_neon_element32(rm0, a->vm, 0, MO_32); + read_neon_element32(rm1, a->vm, 1, MO_32); widenfn(rd, rm0); tcg_gen_shli_i64(rd, rd, 8 << a->size); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_F16_F32(DisasContext *s, arg_2misc *a) fpst = fpstatus_ptr(FPST_STD); ahp = get_ahp_flag(); - tmp = neon_load_reg(a->vm, 0); + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, 0, MO_32); gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp); - tmp2 = neon_load_reg(a->vm, 1); + tmp2 = tcg_temp_new_i32(); + read_neon_element32(tmp2, a->vm, 1, MO_32); gen_helper_vfp_fcvt_f32_to_f16(tmp2, tmp2, fpst, ahp); tcg_gen_shli_i32(tmp2, tmp2, 16); tcg_gen_or_i32(tmp2, tmp2, tmp); - tcg_temp_free_i32(tmp); - tmp = neon_load_reg(a->vm, 2); + read_neon_element32(tmp, a->vm, 2, MO_32); gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp); - tmp3 = neon_load_reg(a->vm, 3); - neon_store_reg(a->vd, 0, tmp2); + tmp3 = tcg_temp_new_i32(); + read_neon_element32(tmp3, a->vm, 3, MO_32); + write_neon_element32(tmp2, a->vd, 0, MO_32); + tcg_temp_free_i32(tmp2); gen_helper_vfp_fcvt_f32_to_f16(tmp3, tmp3, fpst, ahp); tcg_gen_shli_i32(tmp3, tmp3, 16); tcg_gen_or_i32(tmp3, tmp3, tmp); - neon_store_reg(a->vd, 1, tmp3); + write_neon_element32(tmp3, a->vd, 1, MO_32); + tcg_temp_free_i32(tmp3); tcg_temp_free_i32(tmp); tcg_temp_free_i32(ahp); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_F32_F16(DisasContext *s, arg_2misc *a) fpst = fpstatus_ptr(FPST_STD); ahp = get_ahp_flag(); tmp3 = tcg_temp_new_i32(); - tmp = neon_load_reg(a->vm, 0); - tmp2 = neon_load_reg(a->vm, 1); + tmp2 = tcg_temp_new_i32(); + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, 0, MO_32); + read_neon_element32(tmp2, a->vm, 1, MO_32); tcg_gen_ext16u_i32(tmp3, tmp); gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp); - neon_store_reg(a->vd, 0, tmp3); + write_neon_element32(tmp3, a->vd, 0, MO_32); tcg_gen_shri_i32(tmp, tmp, 16); gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp); - neon_store_reg(a->vd, 1, tmp); - tmp3 = tcg_temp_new_i32(); + write_neon_element32(tmp, a->vd, 1, MO_32); + tcg_temp_free_i32(tmp); tcg_gen_ext16u_i32(tmp3, tmp2); gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp); - neon_store_reg(a->vd, 2, tmp3); + write_neon_element32(tmp3, a->vd, 2, MO_32); + tcg_temp_free_i32(tmp3); tcg_gen_shri_i32(tmp2, tmp2, 16); gen_helper_vfp_fcvt_f16_to_f32(tmp2, tmp2, fpst, ahp); - neon_store_reg(a->vd, 3, tmp2); + write_neon_element32(tmp2, a->vd, 3, MO_32); + tcg_temp_free_i32(tmp2); tcg_temp_free_i32(ahp); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ DO_2M_CRYPTO(SHA256SU0, aa32_sha2, 2) static bool do_2misc(DisasContext *s, arg_2misc *a, NeonGenOneOpFn *fn) { + TCGv_i32 tmp; int pass; /* Handle a 2-reg-misc operation by iterating 32 bits at a time */ @@ -XXX,XX +XXX,XX @@ static bool do_2misc(DisasContext *s, arg_2misc *a, NeonGenOneOpFn *fn) return true; } + tmp = tcg_temp_new_i32(); for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vm, pass); + read_neon_element32(tmp, a->vm, pass, MO_32); fn(tmp, tmp); - neon_store_reg(a->vd, pass, tmp); + write_neon_element32(tmp, a->vd, pass, MO_32); } + tcg_temp_free_i32(tmp); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VTRN(DisasContext *s, arg_2misc *a) return true; } - if (a->size == 2) { + tmp = tcg_temp_new_i32(); + tmp2 = tcg_temp_new_i32(); + if (a->size == MO_32) { for (pass = 0; pass < (a->q ? 4 : 2); pass += 2) { - tmp = neon_load_reg(a->vm, pass); - tmp2 = neon_load_reg(a->vd, pass + 1); - neon_store_reg(a->vm, pass, tmp2); - neon_store_reg(a->vd, pass + 1, tmp); + read_neon_element32(tmp, a->vm, pass, MO_32); + read_neon_element32(tmp2, a->vd, pass + 1, MO_32); + write_neon_element32(tmp2, a->vm, pass, MO_32); + write_neon_element32(tmp, a->vd, pass + 1, MO_32); } } else { for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - tmp = neon_load_reg(a->vm, pass); - tmp2 = neon_load_reg(a->vd, pass); - if (a->size == 0) { + read_neon_element32(tmp, a->vm, pass, MO_32); + read_neon_element32(tmp2, a->vd, pass, MO_32); + if (a->size == MO_8) { gen_neon_trn_u8(tmp, tmp2); } else { gen_neon_trn_u16(tmp, tmp2); } - neon_store_reg(a->vm, pass, tmp2); - neon_store_reg(a->vd, pass, tmp); + write_neon_element32(tmp2, a->vm, pass, MO_32); + write_neon_element32(tmp, a->vd, pass, MO_32); } } + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(tmp2); return true; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We can then use this to improve VMOV (scalar to gp) and VMOV (gp to scalar) so that we simply perform the memory operation that we wanted, rather than inserting or extracting from a 32-bit quantity. These were the last uses of neon_load/store_reg, so remove them. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-7-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 50 +++++++++++++----------- target/arm/translate-vfp.c.inc | 71 +++++----------------------------- 2 files changed, 37 insertions(+), 84 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static long neon_full_reg_offset(unsigned reg) * Return the offset of a 2**SIZE piece of a NEON register, at index ELE, * where 0 is the least significant end of the register. */ -static long neon_element_offset(int reg, int element, MemOp size) +static long neon_element_offset(int reg, int element, MemOp memop) { - int element_size = 1 << size; + int element_size = 1 << (memop & MO_SIZE); int ofs = element * element_size; #ifdef HOST_WORDS_BIGENDIAN /* @@ -XXX,XX +XXX,XX @@ static long vfp_reg_offset(bool dp, unsigned reg) } } -static TCGv_i32 neon_load_reg(int reg, int pass) -{ - TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_ld_i32(tmp, cpu_env, neon_element_offset(reg, pass, MO_32)); - return tmp; -} - -static void neon_store_reg(int reg, int pass, TCGv_i32 var) -{ - tcg_gen_st_i32(var, cpu_env, neon_element_offset(reg, pass, MO_32)); - tcg_temp_free_i32(var); -} - static inline void neon_load_reg64(TCGv_i64 var, int reg) { tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(1, reg)); @@ -XXX,XX +XXX,XX @@ static inline void neon_store_reg32(TCGv_i32 var, int reg) tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); } -static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp size) +static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) { - long off = neon_element_offset(reg, ele, size); + long off = neon_element_offset(reg, ele, memop); - switch (size) { - case MO_32: + switch (memop) { + case MO_SB: + tcg_gen_ld8s_i32(dest, cpu_env, off); + break; + case MO_UB: + tcg_gen_ld8u_i32(dest, cpu_env, off); + break; + case MO_SW: + tcg_gen_ld16s_i32(dest, cpu_env, off); + break; + case MO_UW: + tcg_gen_ld16u_i32(dest, cpu_env, off); + break; + case MO_UL: + case MO_SL: tcg_gen_ld_i32(dest, cpu_env, off); break; default: @@ -XXX,XX +XXX,XX @@ static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp size) } } -static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp size) +static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) { - long off = neon_element_offset(reg, ele, size); + long off = neon_element_offset(reg, ele, memop); - switch (size) { + switch (memop) { + case MO_8: + tcg_gen_st8_i32(src, cpu_env, off); + break; + case MO_16: + tcg_gen_st16_i32(src, cpu_env, off); + break; case MO_32: tcg_gen_st_i32(src, cpu_env, off); break; diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a) { /* VMOV scalar to general purpose register */ TCGv_i32 tmp; - int pass; - uint32_t offset; - /* SIZE == 2 is a VFP instruction; otherwise NEON. */ - if (a->size == 2 + /* SIZE == MO_32 is a VFP instruction; otherwise NEON. */ + if (a->size == MO_32 ? !dc_isar_feature(aa32_fpsp_v2, s) : !arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a) return false; } - offset = a->index << a->size; - pass = extract32(offset, 2, 1); - offset = extract32(offset, 0, 2) * 8; - if (!vfp_access_check(s)) { return true; } - tmp = neon_load_reg(a->vn, pass); - switch (a->size) { - case 0: - if (offset) { - tcg_gen_shri_i32(tmp, tmp, offset); - } - if (a->u) { - gen_uxtb(tmp); - } else { - gen_sxtb(tmp); - } - break; - case 1: - if (a->u) { - if (offset) { - tcg_gen_shri_i32(tmp, tmp, 16); - } else { - gen_uxth(tmp); - } - } else { - if (offset) { - tcg_gen_sari_i32(tmp, tmp, 16); - } else { - gen_sxth(tmp); - } - } - break; - case 2: - break; - } + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vn, a->index, a->size | (a->u ? 0 : MO_SIGN)); store_reg(s, a->rt, tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a) static bool trans_VMOV_from_gp(DisasContext *s, arg_VMOV_from_gp *a) { /* VMOV general purpose register to scalar */ - TCGv_i32 tmp, tmp2; - int pass; - uint32_t offset; + TCGv_i32 tmp; - /* SIZE == 2 is a VFP instruction; otherwise NEON. */ - if (a->size == 2 + /* SIZE == MO_32 is a VFP instruction; otherwise NEON. */ + if (a->size == MO_32 ? !dc_isar_feature(aa32_fpsp_v2, s) : !arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_from_gp(DisasContext *s, arg_VMOV_from_gp *a) return false; } - offset = a->index << a->size; - pass = extract32(offset, 2, 1); - offset = extract32(offset, 0, 2) * 8; - if (!vfp_access_check(s)) { return true; } tmp = load_reg(s, a->rt); - switch (a->size) { - case 0: - tmp2 = neon_load_reg(a->vn, pass); - tcg_gen_deposit_i32(tmp, tmp2, tmp, offset, 8); - tcg_temp_free_i32(tmp2); - break; - case 1: - tmp2 = neon_load_reg(a->vn, pass); - tcg_gen_deposit_i32(tmp, tmp2, tmp, offset, 16); - tcg_temp_free_i32(tmp2); - break; - case 2: - break; - } - neon_store_reg(a->vn, pass, tmp); + write_neon_element32(tmp, a->vn, a->index, a->size); + tcg_temp_free_i32(tmp); return true; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The only uses of this function are for loading VFP single-precision values, and nothing to do with NEON. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-8-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 4 +- target/arm/translate-vfp.c.inc | 184 ++++++++++++++++----------------- 2 files changed, 94 insertions(+), 94 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void neon_store_reg64(TCGv_i64 var, int reg) tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(1, reg)); } -static inline void neon_load_reg32(TCGv_i32 var, int reg) +static inline void vfp_load_reg32(TCGv_i32 var, int reg) { tcg_gen_ld_i32(var, cpu_env, vfp_reg_offset(false, reg)); } -static inline void neon_store_reg32(TCGv_i32 var, int reg) +static inline void vfp_store_reg32(TCGv_i32 var, int reg) { tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); } diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) frn = tcg_temp_new_i32(); frm = tcg_temp_new_i32(); dest = tcg_temp_new_i32(); - neon_load_reg32(frn, rn); - neon_load_reg32(frm, rm); + vfp_load_reg32(frn, rn); + vfp_load_reg32(frm, rm); switch (a->cc) { case 0: /* eq: Z */ tcg_gen_movcond_i32(TCG_COND_EQ, dest, cpu_ZF, zero, @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) if (sz == 1) { tcg_gen_andi_i32(dest, dest, 0xffff); } - neon_store_reg32(dest, rd); + vfp_store_reg32(dest, rd); tcg_temp_free_i32(frn); tcg_temp_free_i32(frm); tcg_temp_free_i32(dest); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) TCGv_i32 tcg_res; tcg_op = tcg_temp_new_i32(); tcg_res = tcg_temp_new_i32(); - neon_load_reg32(tcg_op, rm); + vfp_load_reg32(tcg_op, rm); if (sz == 1) { gen_helper_rinth(tcg_res, tcg_op, fpst); } else { gen_helper_rints(tcg_res, tcg_op, fpst); } - neon_store_reg32(tcg_res, rd); + vfp_store_reg32(tcg_res, rd); tcg_temp_free_i32(tcg_op); tcg_temp_free_i32(tcg_res); } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) gen_helper_vfp_tould(tcg_res, tcg_double, tcg_shift, fpst); } tcg_gen_extrl_i64_i32(tcg_tmp, tcg_res); - neon_store_reg32(tcg_tmp, rd); + vfp_store_reg32(tcg_tmp, rd); tcg_temp_free_i32(tcg_tmp); tcg_temp_free_i64(tcg_res); tcg_temp_free_i64(tcg_double); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) TCGv_i32 tcg_single, tcg_res; tcg_single = tcg_temp_new_i32(); tcg_res = tcg_temp_new_i32(); - neon_load_reg32(tcg_single, rm); + vfp_load_reg32(tcg_single, rm); if (sz == 1) { if (is_signed) { gen_helper_vfp_toslh(tcg_res, tcg_single, tcg_shift, fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) gen_helper_vfp_touls(tcg_res, tcg_single, tcg_shift, fpst); } } - neon_store_reg32(tcg_res, rd); + vfp_store_reg32(tcg_res, rd); tcg_temp_free_i32(tcg_res); tcg_temp_free_i32(tcg_single); } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_half(DisasContext *s, arg_VMOV_single *a) if (a->l) { /* VFP to general purpose register */ tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vn); + vfp_load_reg32(tmp, a->vn); tcg_gen_andi_i32(tmp, tmp, 0xffff); store_reg(s, a->rt, tmp); } else { /* general purpose register to VFP */ tmp = load_reg(s, a->rt); tcg_gen_andi_i32(tmp, tmp, 0xffff); - neon_store_reg32(tmp, a->vn); + vfp_store_reg32(tmp, a->vn); tcg_temp_free_i32(tmp); } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_single(DisasContext *s, arg_VMOV_single *a) if (a->l) { /* VFP to general purpose register */ tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vn); + vfp_load_reg32(tmp, a->vn); if (a->rt == 15) { /* Set the 4 flag bits in the CPSR. */ gen_set_nzcv(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_single(DisasContext *s, arg_VMOV_single *a) } else { /* general purpose register to VFP */ tmp = load_reg(s, a->rt); - neon_store_reg32(tmp, a->vn); + vfp_store_reg32(tmp, a->vn); tcg_temp_free_i32(tmp); } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_64_sp(DisasContext *s, arg_VMOV_64_sp *a) if (a->op) { /* fpreg to gpreg */ tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); store_reg(s, a->rt, tmp); tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm + 1); + vfp_load_reg32(tmp, a->vm + 1); store_reg(s, a->rt2, tmp); } else { /* gpreg to fpreg */ tmp = load_reg(s, a->rt); - neon_store_reg32(tmp, a->vm); + vfp_store_reg32(tmp, a->vm); tcg_temp_free_i32(tmp); tmp = load_reg(s, a->rt2); - neon_store_reg32(tmp, a->vm + 1); + vfp_store_reg32(tmp, a->vm + 1); tcg_temp_free_i32(tmp); } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_dp *a) if (a->op) { /* fpreg to gpreg */ tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm * 2); + vfp_load_reg32(tmp, a->vm * 2); store_reg(s, a->rt, tmp); tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm * 2 + 1); + vfp_load_reg32(tmp, a->vm * 2 + 1); store_reg(s, a->rt2, tmp); } else { /* gpreg to fpreg */ tmp = load_reg(s, a->rt); - neon_store_reg32(tmp, a->vm * 2); + vfp_store_reg32(tmp, a->vm * 2); tcg_temp_free_i32(tmp); tmp = load_reg(s, a->rt2); - neon_store_reg32(tmp, a->vm * 2 + 1); + vfp_store_reg32(tmp, a->vm * 2 + 1); tcg_temp_free_i32(tmp); } @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_hp(DisasContext *s, arg_VLDR_VSTR_sp *a) tmp = tcg_temp_new_i32(); if (a->l) { gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); } else { - neon_load_reg32(tmp, a->vd); + vfp_load_reg32(tmp, a->vd); gen_aa32_st16(s, tmp, addr, get_mem_index(s)); } tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_sp(DisasContext *s, arg_VLDR_VSTR_sp *a) tmp = tcg_temp_new_i32(); if (a->l) { gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); } else { - neon_load_reg32(tmp, a->vd); + vfp_load_reg32(tmp, a->vd); gen_aa32_st32(s, tmp, addr, get_mem_index(s)); } tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDM_VSTM_sp(DisasContext *s, arg_VLDM_VSTM_sp *a) if (a->l) { /* load */ gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); - neon_store_reg32(tmp, a->vd + i); + vfp_store_reg32(tmp, a->vd + i); } else { /* store */ - neon_load_reg32(tmp, a->vd + i); + vfp_load_reg32(tmp, a->vd + i); gen_aa32_st32(s, tmp, addr, get_mem_index(s)); } tcg_gen_addi_i32(addr, addr, offset); @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_sp(DisasContext *s, VFPGen3OpSPFn *fn, fd = tcg_temp_new_i32(); fpst = fpstatus_ptr(FPST_FPCR); - neon_load_reg32(f0, vn); - neon_load_reg32(f1, vm); + vfp_load_reg32(f0, vn); + vfp_load_reg32(f1, vm); for (;;) { if (reads_vd) { - neon_load_reg32(fd, vd); + vfp_load_reg32(fd, vd); } fn(fd, f0, f1, fpst); - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_sp(DisasContext *s, VFPGen3OpSPFn *fn, veclen--; vd = vfp_advance_sreg(vd, delta_d); vn = vfp_advance_sreg(vn, delta_d); - neon_load_reg32(f0, vn); + vfp_load_reg32(f0, vn); if (delta_m) { vm = vfp_advance_sreg(vm, delta_m); - neon_load_reg32(f1, vm); + vfp_load_reg32(f1, vm); } } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_hp(DisasContext *s, VFPGen3OpSPFn *fn, fd = tcg_temp_new_i32(); fpst = fpstatus_ptr(FPST_FPCR_F16); - neon_load_reg32(f0, vn); - neon_load_reg32(f1, vm); + vfp_load_reg32(f0, vn); + vfp_load_reg32(f1, vm); if (reads_vd) { - neon_load_reg32(fd, vd); + vfp_load_reg32(fd, vd); } fn(fd, f0, f1, fpst); - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); tcg_temp_free_i32(f0); tcg_temp_free_i32(f1); @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) f0 = tcg_temp_new_i32(); fd = tcg_temp_new_i32(); - neon_load_reg32(f0, vm); + vfp_load_reg32(f0, vm); for (;;) { fn(fd, f0); - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) /* single source one-many */ while (veclen--) { vd = vfp_advance_sreg(vd, delta_d); - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); } break; } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) veclen--; vd = vfp_advance_sreg(vd, delta_d); vm = vfp_advance_sreg(vm, delta_m); - neon_load_reg32(f0, vm); + vfp_load_reg32(f0, vm); } tcg_temp_free_i32(f0); @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_hp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) } f0 = tcg_temp_new_i32(); - neon_load_reg32(f0, vm); + vfp_load_reg32(f0, vm); fn(f0, f0); - neon_store_reg32(f0, vd); + vfp_store_reg32(f0, vd); tcg_temp_free_i32(f0); return true; @@ -XXX,XX +XXX,XX @@ static bool do_vfm_hp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i32(); - neon_load_reg32(vn, a->vn); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vn, a->vn); + vfp_load_reg32(vm, a->vm); if (neg_n) { /* VFNMS, VFMS */ gen_helper_vfp_negh(vn, vn); } - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); if (neg_d) { /* VFNMA, VFNMS */ gen_helper_vfp_negh(vd, vd); } fpst = fpstatus_ptr(FPST_FPCR_F16); gen_helper_vfp_muladdh(vd, vn, vm, vd, fpst); - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(vn); @@ -XXX,XX +XXX,XX @@ static bool do_vfm_sp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i32(); - neon_load_reg32(vn, a->vn); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vn, a->vn); + vfp_load_reg32(vm, a->vm); if (neg_n) { /* VFNMS, VFMS */ gen_helper_vfp_negs(vn, vn); } - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); if (neg_d) { /* VFNMA, VFNMS */ gen_helper_vfp_negs(vd, vd); } fpst = fpstatus_ptr(FPST_FPCR); gen_helper_vfp_muladds(vd, vn, vm, vd, fpst); - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(vn); @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_hp(DisasContext *s, arg_VMOV_imm_sp *a) } fd = tcg_const_i32(vfp_expand_imm(MO_16, a->imm)); - neon_store_reg32(fd, a->vd); + vfp_store_reg32(fd, a->vd); tcg_temp_free_i32(fd); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_sp(DisasContext *s, arg_VMOV_imm_sp *a) fd = tcg_const_i32(vfp_expand_imm(MO_32, a->imm)); for (;;) { - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool trans_VCMP_hp(DisasContext *s, arg_VCMP_sp *a) vd = tcg_temp_new_i32(); vm = tcg_temp_new_i32(); - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); if (a->z) { tcg_gen_movi_i32(vm, 0); } else { - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); } if (a->e) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCMP_sp(DisasContext *s, arg_VCMP_sp *a) vd = tcg_temp_new_i32(); vm = tcg_temp_new_i32(); - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); if (a->z) { tcg_gen_movi_i32(vm, 0); } else { - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); } if (a->e) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f32_f16(DisasContext *s, arg_VCVT_f32_f16 *a) /* The T bit tells us if we want the low or high 16 bits of Vm */ tcg_gen_ld16u_i32(tmp, cpu_env, vfp_f16_offset(a->vm, a->t)); gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp_mode); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_i32(ahp_mode); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f16_f32(DisasContext *s, arg_VCVT_f16_f32 *a) ahp_mode = get_ahp_flag(); tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp_mode); tcg_gen_st16_i32(tmp, cpu_env, vfp_f16_offset(a->vd, a->t)); tcg_temp_free_i32(ahp_mode); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_hp(DisasContext *s, arg_VRINTR_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); gen_helper_rinth(tmp, tmp, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_sp(DisasContext *s, arg_VRINTR_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); gen_helper_rints(tmp, tmp, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_hp(DisasContext *s, arg_VRINTZ_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); tcg_rmode = tcg_const_i32(float_round_to_zero); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); gen_helper_rinth(tmp, tmp, fpst); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tcg_rmode); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_sp(DisasContext *s, arg_VRINTZ_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); tcg_rmode = tcg_const_i32(float_round_to_zero); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); gen_helper_rints(tmp, tmp, fpst); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tcg_rmode); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_hp(DisasContext *s, arg_VRINTX_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); gen_helper_rinth_exact(tmp, tmp, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_sp(DisasContext *s, arg_VRINTX_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); gen_helper_rints_exact(tmp, tmp, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp(DisasContext *s, arg_VCVT_sp *a) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i64(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); gen_helper_vfp_fcvtds(vd, vm, cpu_env); neon_store_reg64(vd, a->vd); tcg_temp_free_i32(vm); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a) vm = tcg_temp_new_i64(); neon_load_reg64(vm, a->vm); gen_helper_vfp_fcvtsd(vd, vm, cpu_env); - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); tcg_temp_free_i64(vm); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_hp(DisasContext *s, arg_VCVT_int_sp *a) } vm = tcg_temp_new_i32(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); if (a->s) { /* i32 -> f16 */ @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_hp(DisasContext *s, arg_VCVT_int_sp *a) /* u32 -> f16 */ gen_helper_vfp_uitoh(vm, vm, fpst); } - neon_store_reg32(vm, a->vd); + vfp_store_reg32(vm, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_ptr(fpst); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_sp(DisasContext *s, arg_VCVT_int_sp *a) } vm = tcg_temp_new_i32(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); fpst = fpstatus_ptr(FPST_FPCR); if (a->s) { /* i32 -> f32 */ @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_sp(DisasContext *s, arg_VCVT_int_sp *a) /* u32 -> f32 */ gen_helper_vfp_uitos(vm, vm, fpst); } - neon_store_reg32(vm, a->vd); + vfp_store_reg32(vm, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_ptr(fpst); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_dp(DisasContext *s, arg_VCVT_int_dp *a) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i64(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); fpst = fpstatus_ptr(FPST_FPCR); if (a->s) { /* i32 -> f64 */ @@ -XXX,XX +XXX,XX @@ static bool trans_VJCVT(DisasContext *s, arg_VJCVT *a) vd = tcg_temp_new_i32(); neon_load_reg64(vm, a->vm); gen_helper_vjcvt(vd, vm, cpu_env); - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i64(vm); tcg_temp_free_i32(vd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_hp(DisasContext *s, arg_VCVT_fix_sp *a) frac_bits = (a->opc & 1) ? (32 - a->imm) : (16 - a->imm); vd = tcg_temp_new_i32(); - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); fpst = fpstatus_ptr(FPST_FPCR_F16); shift = tcg_const_i32(frac_bits); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_hp(DisasContext *s, arg_VCVT_fix_sp *a) g_assert_not_reached(); } - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); tcg_temp_free_i32(shift); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_sp(DisasContext *s, arg_VCVT_fix_sp *a) frac_bits = (a->opc & 1) ? (32 - a->imm) : (16 - a->imm); vd = tcg_temp_new_i32(); - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); fpst = fpstatus_ptr(FPST_FPCR); shift = tcg_const_i32(frac_bits); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_sp(DisasContext *s, arg_VCVT_fix_sp *a) g_assert_not_reached(); } - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); tcg_temp_free_i32(shift); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_hp_int(DisasContext *s, arg_VCVT_sp_int *a) fpst = fpstatus_ptr(FPST_FPCR_F16); vm = tcg_temp_new_i32(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); if (a->s) { if (a->rz) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_hp_int(DisasContext *s, arg_VCVT_sp_int *a) gen_helper_vfp_touih(vm, vm, fpst); } } - neon_store_reg32(vm, a->vd); + vfp_store_reg32(vm, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_ptr(fpst); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp_int(DisasContext *s, arg_VCVT_sp_int *a) fpst = fpstatus_ptr(FPST_FPCR); vm = tcg_temp_new_i32(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); if (a->s) { if (a->rz) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp_int(DisasContext *s, arg_VCVT_sp_int *a) gen_helper_vfp_touis(vm, vm, fpst); } } - neon_store_reg32(vm, a->vd); + vfp_store_reg32(vm, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_ptr(fpst); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) gen_helper_vfp_touid(vd, vm, fpst); } } - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); tcg_temp_free_i64(vm); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VINS(DisasContext *s, arg_VINS *a) /* Insert low half of Vm into high half of Vd */ rm = tcg_temp_new_i32(); rd = tcg_temp_new_i32(); - neon_load_reg32(rm, a->vm); - neon_load_reg32(rd, a->vd); + vfp_load_reg32(rm, a->vm); + vfp_load_reg32(rd, a->vd); tcg_gen_deposit_i32(rd, rd, rm, 16, 16); - neon_store_reg32(rd, a->vd); + vfp_store_reg32(rd, a->vd); tcg_temp_free_i32(rm); tcg_temp_free_i32(rd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOVX(DisasContext *s, arg_VINS *a) /* Set Vd to high half of Vm */ rm = tcg_temp_new_i32(); - neon_load_reg32(rm, a->vm); + vfp_load_reg32(rm, a->vm); tcg_gen_shri_i32(rm, rm, 16); - neon_store_reg32(rm, a->vd); + vfp_store_reg32(rm, a->vd); tcg_temp_free_i32(rm); return true; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Replace all uses of neon_load/store_reg64 within translate-neon.c.inc. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-9-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 26 +++++++++ target/arm/translate-neon.c.inc | 94 ++++++++++++++++----------------- 2 files changed, 73 insertions(+), 47 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) } } +static void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop) +{ + long off = neon_element_offset(reg, ele, memop); + + switch (memop) { + case MO_Q: + tcg_gen_ld_i64(dest, cpu_env, off); + break; + default: + g_assert_not_reached(); + } +} + static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) { long off = neon_element_offset(reg, ele, memop); @@ -XXX,XX +XXX,XX @@ static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) } } +static void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) +{ + long off = neon_element_offset(reg, ele, memop); + + switch (memop) { + case MO_64: + tcg_gen_st_i64(src, cpu_env, off); + break; + default: + g_assert_not_reached(); + } +} + static TCGv_ptr vfp_reg_ptr(bool dp, int reg) { TCGv_ptr ret = tcg_temp_new_ptr(); diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_64(DisasContext *s, arg_2reg_shift *a, for (pass = 0; pass < a->q + 1; pass++) { TCGv_i64 tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vm + pass); + read_neon_element64(tmp, a->vm, pass, MO_64); fn(tmp, cpu_env, tmp, constimm); - neon_store_reg64(tmp, a->vd + pass); + write_neon_element64(tmp, a->vd, pass, MO_64); tcg_temp_free_i64(tmp); } tcg_temp_free_i64(constimm); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a, rd = tcg_temp_new_i32(); /* Load both inputs first to avoid potential overwrite if rm == rd */ - neon_load_reg64(rm1, a->vm); - neon_load_reg64(rm2, a->vm + 1); + read_neon_element64(rm1, a->vm, 0, MO_64); + read_neon_element64(rm2, a->vm, 1, MO_64); shiftfn(rm1, rm1, constimm); narrowfn(rd, cpu_env, rm1); @@ -XXX,XX +XXX,XX @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a, tcg_gen_shli_i64(tmp, tmp, a->shift); tcg_gen_andi_i64(tmp, tmp, ~widen_mask); } - neon_store_reg64(tmp, a->vd); + write_neon_element64(tmp, a->vd, 0, MO_64); widenfn(tmp, rm1); tcg_temp_free_i32(rm1); @@ -XXX,XX +XXX,XX @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a, tcg_gen_shli_i64(tmp, tmp, a->shift); tcg_gen_andi_i64(tmp, tmp, ~widen_mask); } - neon_store_reg64(tmp, a->vd + 1); + write_neon_element64(tmp, a->vd, 1, MO_64); tcg_temp_free_i64(tmp); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, rm_64 = tcg_temp_new_i64(); if (src1_wide) { - neon_load_reg64(rn0_64, a->vn); + read_neon_element64(rn0_64, a->vn, 0, MO_64); } else { TCGv_i32 tmp = tcg_temp_new_i32(); read_neon_element32(tmp, a->vn, 0, MO_32); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, * avoid incorrect results if a narrow input overlaps with the result. */ if (src1_wide) { - neon_load_reg64(rn1_64, a->vn + 1); + read_neon_element64(rn1_64, a->vn, 1, MO_64); } else { TCGv_i32 tmp = tcg_temp_new_i32(); read_neon_element32(tmp, a->vn, 1, MO_32); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, rm = tcg_temp_new_i32(); read_neon_element32(rm, a->vm, 1, MO_32); - neon_store_reg64(rn0_64, a->vd); + write_neon_element64(rn0_64, a->vd, 0, MO_64); widenfn(rm_64, rm); tcg_temp_free_i32(rm); opfn(rn1_64, rn1_64, rm_64); - neon_store_reg64(rn1_64, a->vd + 1); + write_neon_element64(rn1_64, a->vd, 1, MO_64); tcg_temp_free_i64(rn0_64); tcg_temp_free_i64(rn1_64); @@ -XXX,XX +XXX,XX @@ static bool do_narrow_3d(DisasContext *s, arg_3diff *a, rd0 = tcg_temp_new_i32(); rd1 = tcg_temp_new_i32(); - neon_load_reg64(rn_64, a->vn); - neon_load_reg64(rm_64, a->vm); + read_neon_element64(rn_64, a->vn, 0, MO_64); + read_neon_element64(rm_64, a->vm, 0, MO_64); opfn(rn_64, rn_64, rm_64); narrowfn(rd0, rn_64); - neon_load_reg64(rn_64, a->vn + 1); - neon_load_reg64(rm_64, a->vm + 1); + read_neon_element64(rn_64, a->vn, 1, MO_64); + read_neon_element64(rm_64, a->vm, 1, MO_64); opfn(rn_64, rn_64, rm_64); @@ -XXX,XX +XXX,XX @@ static bool do_long_3d(DisasContext *s, arg_3diff *a, /* Don't store results until after all loads: they might overlap */ if (accfn) { tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vd); + read_neon_element64(tmp, a->vd, 0, MO_64); accfn(tmp, tmp, rd0); - neon_store_reg64(tmp, a->vd); - neon_load_reg64(tmp, a->vd + 1); + write_neon_element64(tmp, a->vd, 0, MO_64); + read_neon_element64(tmp, a->vd, 1, MO_64); accfn(tmp, tmp, rd1); - neon_store_reg64(tmp, a->vd + 1); + write_neon_element64(tmp, a->vd, 1, MO_64); tcg_temp_free_i64(tmp); } else { - neon_store_reg64(rd0, a->vd); - neon_store_reg64(rd1, a->vd + 1); + write_neon_element64(rd0, a->vd, 0, MO_64); + write_neon_element64(rd1, a->vd, 1, MO_64); } tcg_temp_free_i64(rd0); @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_long(DisasContext *s, arg_2scalar *a, if (accfn) { TCGv_i64 t64 = tcg_temp_new_i64(); - neon_load_reg64(t64, a->vd); + read_neon_element64(t64, a->vd, 0, MO_64); accfn(t64, t64, rn0_64); - neon_store_reg64(t64, a->vd); - neon_load_reg64(t64, a->vd + 1); + write_neon_element64(t64, a->vd, 0, MO_64); + read_neon_element64(t64, a->vd, 1, MO_64); accfn(t64, t64, rn1_64); - neon_store_reg64(t64, a->vd + 1); + write_neon_element64(t64, a->vd, 1, MO_64); tcg_temp_free_i64(t64); } else { - neon_store_reg64(rn0_64, a->vd); - neon_store_reg64(rn1_64, a->vd + 1); + write_neon_element64(rn0_64, a->vd, 0, MO_64); + write_neon_element64(rn1_64, a->vd, 1, MO_64); } tcg_temp_free_i64(rn0_64); tcg_temp_free_i64(rn1_64); @@ -XXX,XX +XXX,XX @@ static bool trans_VEXT(DisasContext *s, arg_VEXT *a) right = tcg_temp_new_i64(); dest = tcg_temp_new_i64(); - neon_load_reg64(right, a->vn); - neon_load_reg64(left, a->vm); + read_neon_element64(right, a->vn, 0, MO_64); + read_neon_element64(left, a->vm, 0, MO_64); tcg_gen_extract2_i64(dest, right, left, a->imm * 8); - neon_store_reg64(dest, a->vd); + write_neon_element64(dest, a->vd, 0, MO_64); tcg_temp_free_i64(left); tcg_temp_free_i64(right); @@ -XXX,XX +XXX,XX @@ static bool trans_VEXT(DisasContext *s, arg_VEXT *a) destright = tcg_temp_new_i64(); if (a->imm < 8) { - neon_load_reg64(right, a->vn); - neon_load_reg64(middle, a->vn + 1); + read_neon_element64(right, a->vn, 0, MO_64); + read_neon_element64(middle, a->vn, 1, MO_64); tcg_gen_extract2_i64(destright, right, middle, a->imm * 8); - neon_load_reg64(left, a->vm); + read_neon_element64(left, a->vm, 0, MO_64); tcg_gen_extract2_i64(destleft, middle, left, a->imm * 8); } else { - neon_load_reg64(right, a->vn + 1); - neon_load_reg64(middle, a->vm); + read_neon_element64(right, a->vn, 1, MO_64); + read_neon_element64(middle, a->vm, 0, MO_64); tcg_gen_extract2_i64(destright, right, middle, (a->imm - 8) * 8); - neon_load_reg64(left, a->vm + 1); + read_neon_element64(left, a->vm, 1, MO_64); tcg_gen_extract2_i64(destleft, middle, left, (a->imm - 8) * 8); } - neon_store_reg64(destright, a->vd); - neon_store_reg64(destleft, a->vd + 1); + write_neon_element64(destright, a->vd, 0, MO_64); + write_neon_element64(destleft, a->vd, 1, MO_64); tcg_temp_free_i64(destright); tcg_temp_free_i64(destleft); @@ -XXX,XX +XXX,XX @@ static bool do_2misc_pairwise(DisasContext *s, arg_2misc *a, if (accfn) { TCGv_i64 tmp64 = tcg_temp_new_i64(); - neon_load_reg64(tmp64, a->vd + pass); + read_neon_element64(tmp64, a->vd, pass, MO_64); accfn(rd_64, tmp64, rd_64); tcg_temp_free_i64(tmp64); } - neon_store_reg64(rd_64, a->vd + pass); + write_neon_element64(rd_64, a->vd, pass, MO_64); tcg_temp_free_i64(rd_64); } return true; @@ -XXX,XX +XXX,XX @@ static bool do_vmovn(DisasContext *s, arg_2misc *a, rd0 = tcg_temp_new_i32(); rd1 = tcg_temp_new_i32(); - neon_load_reg64(rm, a->vm); + read_neon_element64(rm, a->vm, 0, MO_64); narrowfn(rd0, cpu_env, rm); - neon_load_reg64(rm, a->vm + 1); + read_neon_element64(rm, a->vm, 1, MO_64); narrowfn(rd1, cpu_env, rm); write_neon_element32(rd0, a->vd, 0, MO_32); write_neon_element32(rd1, a->vd, 1, MO_32); @@ -XXX,XX +XXX,XX @@ static bool trans_VSHLL(DisasContext *s, arg_2misc *a) widenfn(rd, rm0); tcg_gen_shli_i64(rd, rd, 8 << a->size); - neon_store_reg64(rd, a->vd); + write_neon_element64(rd, a->vd, 0, MO_64); widenfn(rd, rm1); tcg_gen_shli_i64(rd, rd, 8 << a->size); - neon_store_reg64(rd, a->vd + 1); + write_neon_element64(rd, a->vd, 1, MO_64); tcg_temp_free_i64(rd); tcg_temp_free_i32(rm0); @@ -XXX,XX +XXX,XX @@ static bool trans_VSWP(DisasContext *s, arg_2misc *a) rm = tcg_temp_new_i64(); rd = tcg_temp_new_i64(); for (pass = 0; pass < (a->q ? 2 : 1); pass++) { - neon_load_reg64(rm, a->vm + pass); - neon_load_reg64(rd, a->vd + pass); - neon_store_reg64(rm, a->vd + pass); - neon_store_reg64(rd, a->vm + pass); + read_neon_element64(rm, a->vm, pass, MO_64); + read_neon_element64(rd, a->vd, pass, MO_64); + write_neon_element64(rm, a->vd, pass, MO_64); + write_neon_element64(rd, a->vm, pass, MO_64); } tcg_temp_free_i64(rm); tcg_temp_free_i64(rd); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The only uses of this function are for loading VFP double-precision values, and nothing to do with NEON. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-10-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 8 ++-- target/arm/translate-vfp.c.inc | 84 +++++++++++++++++----------------- 2 files changed, 46 insertions(+), 46 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static long vfp_reg_offset(bool dp, unsigned reg) } } -static inline void neon_load_reg64(TCGv_i64 var, int reg) +static inline void vfp_load_reg64(TCGv_i64 var, int reg) { - tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(1, reg)); + tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(true, reg)); } -static inline void neon_store_reg64(TCGv_i64 var, int reg) +static inline void vfp_store_reg64(TCGv_i64 var, int reg) { - tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(1, reg)); + tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(true, reg)); } static inline void vfp_load_reg32(TCGv_i32 var, int reg) diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) tcg_gen_ext_i32_i64(nf, cpu_NF); tcg_gen_ext_i32_i64(vf, cpu_VF); - neon_load_reg64(frn, rn); - neon_load_reg64(frm, rm); + vfp_load_reg64(frn, rn); + vfp_load_reg64(frm, rm); switch (a->cc) { case 0: /* eq: Z */ tcg_gen_movcond_i64(TCG_COND_EQ, dest, zf, zero, @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) tcg_temp_free_i64(tmp); break; } - neon_store_reg64(dest, rd); + vfp_store_reg64(dest, rd); tcg_temp_free_i64(frn); tcg_temp_free_i64(frm); tcg_temp_free_i64(dest); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) TCGv_i64 tcg_res; tcg_op = tcg_temp_new_i64(); tcg_res = tcg_temp_new_i64(); - neon_load_reg64(tcg_op, rm); + vfp_load_reg64(tcg_op, rm); gen_helper_rintd(tcg_res, tcg_op, fpst); - neon_store_reg64(tcg_res, rd); + vfp_store_reg64(tcg_res, rd); tcg_temp_free_i64(tcg_op); tcg_temp_free_i64(tcg_res); } else { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) tcg_double = tcg_temp_new_i64(); tcg_res = tcg_temp_new_i64(); tcg_tmp = tcg_temp_new_i32(); - neon_load_reg64(tcg_double, rm); + vfp_load_reg64(tcg_double, rm); if (is_signed) { gen_helper_vfp_tosld(tcg_res, tcg_double, tcg_shift, fpst); } else { @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_dp(DisasContext *s, arg_VLDR_VSTR_dp *a) tmp = tcg_temp_new_i64(); if (a->l) { gen_aa32_ld64(s, tmp, addr, get_mem_index(s)); - neon_store_reg64(tmp, a->vd); + vfp_store_reg64(tmp, a->vd); } else { - neon_load_reg64(tmp, a->vd); + vfp_load_reg64(tmp, a->vd); gen_aa32_st64(s, tmp, addr, get_mem_index(s)); } tcg_temp_free_i64(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDM_VSTM_dp(DisasContext *s, arg_VLDM_VSTM_dp *a) if (a->l) { /* load */ gen_aa32_ld64(s, tmp, addr, get_mem_index(s)); - neon_store_reg64(tmp, a->vd + i); + vfp_store_reg64(tmp, a->vd + i); } else { /* store */ - neon_load_reg64(tmp, a->vd + i); + vfp_load_reg64(tmp, a->vd + i); gen_aa32_st64(s, tmp, addr, get_mem_index(s)); } tcg_gen_addi_i32(addr, addr, offset); @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn, fd = tcg_temp_new_i64(); fpst = fpstatus_ptr(FPST_FPCR); - neon_load_reg64(f0, vn); - neon_load_reg64(f1, vm); + vfp_load_reg64(f0, vn); + vfp_load_reg64(f1, vm); for (;;) { if (reads_vd) { - neon_load_reg64(fd, vd); + vfp_load_reg64(fd, vd); } fn(fd, f0, f1, fpst); - neon_store_reg64(fd, vd); + vfp_store_reg64(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn, veclen--; vd = vfp_advance_dreg(vd, delta_d); vn = vfp_advance_dreg(vn, delta_d); - neon_load_reg64(f0, vn); + vfp_load_reg64(f0, vn); if (delta_m) { vm = vfp_advance_dreg(vm, delta_m); - neon_load_reg64(f1, vm); + vfp_load_reg64(f1, vm); } } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) f0 = tcg_temp_new_i64(); fd = tcg_temp_new_i64(); - neon_load_reg64(f0, vm); + vfp_load_reg64(f0, vm); for (;;) { fn(fd, f0); - neon_store_reg64(fd, vd); + vfp_store_reg64(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) /* single source one-many */ while (veclen--) { vd = vfp_advance_dreg(vd, delta_d); - neon_store_reg64(fd, vd); + vfp_store_reg64(fd, vd); } break; } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) veclen--; vd = vfp_advance_dreg(vd, delta_d); vd = vfp_advance_dreg(vm, delta_m); - neon_load_reg64(f0, vm); + vfp_load_reg64(f0, vm); } tcg_temp_free_i64(f0); @@ -XXX,XX +XXX,XX @@ static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d) vm = tcg_temp_new_i64(); vd = tcg_temp_new_i64(); - neon_load_reg64(vn, a->vn); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vn, a->vn); + vfp_load_reg64(vm, a->vm); if (neg_n) { /* VFNMS, VFMS */ gen_helper_vfp_negd(vn, vn); } - neon_load_reg64(vd, a->vd); + vfp_load_reg64(vd, a->vd); if (neg_d) { /* VFNMA, VFNMS */ gen_helper_vfp_negd(vd, vd); } fpst = fpstatus_ptr(FPST_FPCR); gen_helper_vfp_muladdd(vd, vn, vm, vd, fpst); - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i64(vn); @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) fd = tcg_const_i64(vfp_expand_imm(MO_64, a->imm)); for (;;) { - neon_store_reg64(fd, vd); + vfp_store_reg64(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool trans_VCMP_dp(DisasContext *s, arg_VCMP_dp *a) vd = tcg_temp_new_i64(); vm = tcg_temp_new_i64(); - neon_load_reg64(vd, a->vd); + vfp_load_reg64(vd, a->vd); if (a->z) { tcg_gen_movi_i64(vm, 0); } else { - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); } if (a->e) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f64_f16(DisasContext *s, arg_VCVT_f64_f16 *a) tcg_gen_ld16u_i32(tmp, cpu_env, vfp_f16_offset(a->vm, a->t)); vd = tcg_temp_new_i64(); gen_helper_vfp_fcvt_f16_to_f64(vd, tmp, fpst, ahp_mode); - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_i32(ahp_mode); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f16_f64(DisasContext *s, arg_VCVT_f16_f64 *a) tmp = tcg_temp_new_i32(); vm = tcg_temp_new_i64(); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); gen_helper_vfp_fcvt_f64_to_f16(tmp, vm, fpst, ahp_mode); tcg_temp_free_i64(vm); tcg_gen_st16_i32(tmp, cpu_env, vfp_f16_offset(a->vd, a->t)); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_dp(DisasContext *s, arg_VRINTR_dp *a) } tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vm); + vfp_load_reg64(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); gen_helper_rintd(tmp, tmp, fpst); - neon_store_reg64(tmp, a->vd); + vfp_store_reg64(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i64(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_dp(DisasContext *s, arg_VRINTZ_dp *a) } tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vm); + vfp_load_reg64(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); tcg_rmode = tcg_const_i32(float_round_to_zero); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); gen_helper_rintd(tmp, tmp, fpst); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); - neon_store_reg64(tmp, a->vd); + vfp_store_reg64(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i64(tmp); tcg_temp_free_i32(tcg_rmode); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_dp(DisasContext *s, arg_VRINTX_dp *a) } tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vm); + vfp_load_reg64(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); gen_helper_rintd_exact(tmp, tmp, fpst); - neon_store_reg64(tmp, a->vd); + vfp_store_reg64(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i64(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp(DisasContext *s, arg_VCVT_sp *a) vd = tcg_temp_new_i64(); vfp_load_reg32(vm, a->vm); gen_helper_vfp_fcvtds(vd, vm, cpu_env); - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_i64(vd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a) vd = tcg_temp_new_i32(); vm = tcg_temp_new_i64(); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); gen_helper_vfp_fcvtsd(vd, vm, cpu_env); vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_dp(DisasContext *s, arg_VCVT_int_dp *a) /* u32 -> f64 */ gen_helper_vfp_uitod(vd, vm, fpst); } - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_i64(vd); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VJCVT(DisasContext *s, arg_VJCVT *a) vm = tcg_temp_new_i64(); vd = tcg_temp_new_i32(); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); gen_helper_vjcvt(vd, vm, cpu_env); vfp_store_reg32(vd, a->vd); tcg_temp_free_i64(vm); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) frac_bits = (a->opc & 1) ? (32 - a->imm) : (16 - a->imm); vd = tcg_temp_new_i64(); - neon_load_reg64(vd, a->vd); + vfp_load_reg64(vd, a->vd); fpst = fpstatus_ptr(FPST_FPCR); shift = tcg_const_i32(frac_bits); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) g_assert_not_reached(); } - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_i64(vd); tcg_temp_free_i32(shift); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) fpst = fpstatus_ptr(FPST_FPCR); vm = tcg_temp_new_i64(); vd = tcg_temp_new_i32(); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); if (a->s) { if (a->rz) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> In both cases, we can sink the write-back and perform the accumulate into the normal destination temps. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-11-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-neon.c.inc | 23 +++++++++-------------- 1 file changed, 9 insertions(+), 14 deletions(-) diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_long_3d(DisasContext *s, arg_3diff *a, if (accfn) { tmp = tcg_temp_new_i64(); read_neon_element64(tmp, a->vd, 0, MO_64); - accfn(tmp, tmp, rd0); - write_neon_element64(tmp, a->vd, 0, MO_64); + accfn(rd0, tmp, rd0); read_neon_element64(tmp, a->vd, 1, MO_64); - accfn(tmp, tmp, rd1); - write_neon_element64(tmp, a->vd, 1, MO_64); + accfn(rd1, tmp, rd1); tcg_temp_free_i64(tmp); - } else { - write_neon_element64(rd0, a->vd, 0, MO_64); - write_neon_element64(rd1, a->vd, 1, MO_64); } + write_neon_element64(rd0, a->vd, 0, MO_64); + write_neon_element64(rd1, a->vd, 1, MO_64); tcg_temp_free_i64(rd0); tcg_temp_free_i64(rd1); @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_long(DisasContext *s, arg_2scalar *a, if (accfn) { TCGv_i64 t64 = tcg_temp_new_i64(); read_neon_element64(t64, a->vd, 0, MO_64); - accfn(t64, t64, rn0_64); - write_neon_element64(t64, a->vd, 0, MO_64); + accfn(rn0_64, t64, rn0_64); read_neon_element64(t64, a->vd, 1, MO_64); - accfn(t64, t64, rn1_64); - write_neon_element64(t64, a->vd, 1, MO_64); + accfn(rn1_64, t64, rn1_64); tcg_temp_free_i64(t64); - } else { - write_neon_element64(rn0_64, a->vd, 0, MO_64); - write_neon_element64(rn1_64, a->vd, 1, MO_64); } + + write_neon_element64(rn0_64, a->vd, 0, MO_64); + write_neon_element64(rn1_64, a->vd, 1, MO_64); tcg_temp_free_i64(rn0_64); tcg_temp_free_i64(rn1_64); return true; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We can use proper widening loads to extend 32-bit inputs, and skip the "widenfn" step. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-12-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 6 +++ target/arm/translate-neon.c.inc | 66 ++++++++++++++++++--------------- 2 files changed, 43 insertions(+), 29 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop) long off = neon_element_offset(reg, ele, memop); switch (memop) { + case MO_SL: + tcg_gen_ld32s_i64(dest, cpu_env, off); + break; + case MO_UL: + tcg_gen_ld32u_i64(dest, cpu_env, off); + break; case MO_Q: tcg_gen_ld_i64(dest, cpu_env, off); break; diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_Vimm_1r(DisasContext *s, arg_1reg_imm *a) static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, NeonGenWidenFn *widenfn, NeonGenTwo64OpFn *opfn, - bool src1_wide) + int src1_mop, int src2_mop) { /* 3-regs different lengths, prewidening case (VADDL/VSUBL/VAADW/VSUBW) */ TCGv_i64 rn0_64, rn1_64, rm_64; - TCGv_i32 rm; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, return false; } - if (!widenfn || !opfn) { + if (!opfn) { /* size == 3 case, which is an entirely different insn group */ return false; } - if ((a->vd & 1) || (src1_wide && (a->vn & 1))) { + if ((a->vd & 1) || (src1_mop == MO_Q && (a->vn & 1))) { return false; } @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, rn1_64 = tcg_temp_new_i64(); rm_64 = tcg_temp_new_i64(); - if (src1_wide) { - read_neon_element64(rn0_64, a->vn, 0, MO_64); + if (src1_mop >= 0) { + read_neon_element64(rn0_64, a->vn, 0, src1_mop); } else { TCGv_i32 tmp = tcg_temp_new_i32(); read_neon_element32(tmp, a->vn, 0, MO_32); widenfn(rn0_64, tmp); tcg_temp_free_i32(tmp); } - rm = tcg_temp_new_i32(); - read_neon_element32(rm, a->vm, 0, MO_32); + if (src2_mop >= 0) { + read_neon_element64(rm_64, a->vm, 0, src2_mop); + } else { + TCGv_i32 tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, 0, MO_32); + widenfn(rm_64, tmp); + tcg_temp_free_i32(tmp); + } - widenfn(rm_64, rm); - tcg_temp_free_i32(rm); opfn(rn0_64, rn0_64, rm_64); /* * Load second pass inputs before storing the first pass result, to * avoid incorrect results if a narrow input overlaps with the result. */ - if (src1_wide) { - read_neon_element64(rn1_64, a->vn, 1, MO_64); + if (src1_mop >= 0) { + read_neon_element64(rn1_64, a->vn, 1, src1_mop); } else { TCGv_i32 tmp = tcg_temp_new_i32(); read_neon_element32(tmp, a->vn, 1, MO_32); widenfn(rn1_64, tmp); tcg_temp_free_i32(tmp); } - rm = tcg_temp_new_i32(); - read_neon_element32(rm, a->vm, 1, MO_32); + if (src2_mop >= 0) { + read_neon_element64(rm_64, a->vm, 1, src2_mop); + } else { + TCGv_i32 tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, 1, MO_32); + widenfn(rm_64, tmp); + tcg_temp_free_i32(tmp); + } write_neon_element64(rn0_64, a->vd, 0, MO_64); - widenfn(rm_64, rm); - tcg_temp_free_i32(rm); opfn(rn1_64, rn1_64, rm_64); write_neon_element64(rn1_64, a->vd, 1, MO_64); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, return true; } -#define DO_PREWIDEN(INSN, S, EXT, OP, SRC1WIDE) \ +#define DO_PREWIDEN(INSN, S, OP, SRC1WIDE, SIGN) \ static bool trans_##INSN##_3d(DisasContext *s, arg_3diff *a) \ { \ static NeonGenWidenFn * const widenfn[] = { \ gen_helper_neon_widen_##S##8, \ gen_helper_neon_widen_##S##16, \ - tcg_gen_##EXT##_i32_i64, \ - NULL, \ + NULL, NULL, \ }; \ static NeonGenTwo64OpFn * const addfn[] = { \ gen_helper_neon_##OP##l_u16, \ @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, tcg_gen_##OP##_i64, \ NULL, \ }; \ - return do_prewiden_3d(s, a, widenfn[a->size], \ - addfn[a->size], SRC1WIDE); \ + int narrow_mop = a->size == MO_32 ? MO_32 | SIGN : -1; \ + return do_prewiden_3d(s, a, widenfn[a->size], addfn[a->size], \ + SRC1WIDE ? MO_Q : narrow_mop, \ + narrow_mop); \ } -DO_PREWIDEN(VADDL_S, s, ext, add, false) -DO_PREWIDEN(VADDL_U, u, extu, add, false) -DO_PREWIDEN(VSUBL_S, s, ext, sub, false) -DO_PREWIDEN(VSUBL_U, u, extu, sub, false) -DO_PREWIDEN(VADDW_S, s, ext, add, true) -DO_PREWIDEN(VADDW_U, u, extu, add, true) -DO_PREWIDEN(VSUBW_S, s, ext, sub, true) -DO_PREWIDEN(VSUBW_U, u, extu, sub, true) +DO_PREWIDEN(VADDL_S, s, add, false, MO_SIGN) +DO_PREWIDEN(VADDL_U, u, add, false, 0) +DO_PREWIDEN(VSUBL_S, s, sub, false, MO_SIGN) +DO_PREWIDEN(VSUBL_U, u, sub, false, 0) +DO_PREWIDEN(VADDW_S, s, add, true, MO_SIGN) +DO_PREWIDEN(VADDW_U, u, add, true, 0) +DO_PREWIDEN(VSUBW_S, s, sub, true, MO_SIGN) +DO_PREWIDEN(VSUBW_U, u, sub, true, 0) static bool do_narrow_3d(DisasContext *s, arg_3diff *a, NeonGenTwo64OpFn *opfn, NeonGenNarrowFn *narrowfn) -- 2.20.1 In the neon_padd/pmax/pmin helpers for float16, a cut-and-paste error meant we were using the H4() address swizzler macro rather than the H2() which is required for 2-byte data. This had no effect on little-endian hosts but meant we put the result data into the destination Dreg in the wrong order on big-endian hosts. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20201028191712.4910-2-peter.maydell@linaro.org --- target/arm/vec_helper.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ DO_ABA(gvec_uaba_d, uint64_t) r2 = float16_##OP(m[H2(0)], m[H2(1)], fpst); \ r3 = float16_##OP(m[H2(2)], m[H2(3)], fpst); \ \ - d[H4(0)] = r0; \ - d[H4(1)] = r1; \ - d[H4(2)] = r2; \ - d[H4(3)] = r3; \ + d[H2(0)] = r0; \ + d[H2(1)] = r1; \ + d[H2(2)] = r2; \ + d[H2(3)] = r3; \ } DO_NEON_PAIRWISE(neon_padd, add) -- 2.20.1 The helper functions for performing the udot/sdot operations against a scalar were not using an address-swizzling macro when converting the index of the scalar element into a pointer into the vm array. This had no effect on little-endian hosts but meant we generated incorrect results on big-endian hosts. For these insns, the index is indexing over group of 4 8-bit values, so 32 bits per indexed entity, and H4() is therefore what we want. (For Neon the only possible input indexes are 0 and 1.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20201028191712.4910-3-peter.maydell@linaro.org --- target/arm/vec_helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) intptr_t index = simd_data(desc); uint32_t *d = vd; int8_t *n = vn; - int8_t *m_indexed = (int8_t *)vm + index * 4; + int8_t *m_indexed = (int8_t *)vm + H4(index) * 4; /* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd. * Otherwise opr_sz is a multiple of 16. @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) intptr_t index = simd_data(desc); uint32_t *d = vd; uint8_t *n = vn; - uint8_t *m_indexed = (uint8_t *)vm + index * 4; + uint8_t *m_indexed = (uint8_t *)vm + H4(index) * 4; /* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd. * Otherwise opr_sz is a multiple of 16. -- 2.20.1 From: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> HCR should be applied when NS is set, not when it is cleared. Signed-off-by: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void tlbimvaa_is_write(CPUARMState *env, const ARMCPRegInfo *ri, /* * Non-IS variants of TLB operations are upgraded to - * IS versions if we are at NS EL1 and HCR_EL2.FB is set to + * IS versions if we are at EL1 and HCR_EL2.FB is effectively set to * force broadcast of these operations. */ static bool tlb_force_broadcast(CPUARMState *env) { - return (env->cp15.hcr_el2 & HCR_FB) && - arm_current_el(env) == 1 && arm_is_secure_below_el3(env); + return arm_current_el(env) == 1 && (arm_hcr_el2_eff(env) & HCR_FB); } static void tlbiall_write(CPUARMState *env, const ARMCPRegInfo *ri, -- 2.20.1 From: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Secure mode is not exempted from checking SCR_EL3.TLOR, and in the future HCR_EL2.TLOR when S-EL2 is enabled. Signed-off-by: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t id_aa64pfr0_read(CPUARMState *env, const ARMCPRegInfo *ri) #endif /* Shared logic between LORID and the rest of the LOR* registers. - * Secure state has already been delt with. + * Secure state exclusion has already been dealt with. */ -static CPAccessResult access_lor_ns(CPUARMState *env) +static CPAccessResult access_lor_ns(CPUARMState *env, + const ARMCPRegInfo *ri, bool isread) { int el = arm_current_el(env); @@ -XXX,XX +XXX,XX @@ static CPAccessResult access_lor_ns(CPUARMState *env) return CP_ACCESS_OK; } -static CPAccessResult access_lorid(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread) -{ - if (arm_is_secure_below_el3(env)) { - /* Access ok in secure mode. */ - return CP_ACCESS_OK; - } - return access_lor_ns(env); -} - static CPAccessResult access_lor_other(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { @@ -XXX,XX +XXX,XX @@ static CPAccessResult access_lor_other(CPUARMState *env, /* Access denied in secure mode. */ return CP_ACCESS_TRAP; } - return access_lor_ns(env); + return access_lor_ns(env, ri, isread); } /* @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo lor_reginfo[] = { .type = ARM_CP_CONST, .resetvalue = 0 }, { .name = "LORID_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 7, - .access = PL1_R, .accessfn = access_lorid, + .access = PL1_R, .accessfn = access_lor_ns, .type = ARM_CP_CONST, .resetvalue = 0 }, REGINFO_SENTINEL }; -- 2.20.1 If we're using the capstone disassembler, disassembly of a run of instructions more than 32 bytes long disassembles the wrong data for instructions beyond the 32 byte mark: (qemu) xp /16x 0x100 0000000000000100: 0x00000005 0x54410001 0x00000001 0x00001000 0000000000000110: 0x00000000 0x00000004 0x54410002 0x3c000000 0000000000000120: 0x00000000 0x00000004 0x54410009 0x74736574 0000000000000130: 0x00000000 0x00000000 0x00000000 0x00000000 (qemu) xp /16i 0x100 0x00000100: 00000005 andeq r0, r0, r5 0x00000104: 54410001 strbpl r0, [r1], #-1 0x00000108: 00000001 andeq r0, r0, r1 0x0000010c: 00001000 andeq r1, r0, r0 0x00000110: 00000000 andeq r0, r0, r0 0x00000114: 00000004 andeq r0, r0, r4 0x00000118: 54410002 strbpl r0, [r1], #-2 0x0000011c: 3c000000 .byte 0x00, 0x00, 0x00, 0x3c 0x00000120: 54410001 strbpl r0, [r1], #-1 0x00000124: 00000001 andeq r0, r0, r1 0x00000128: 00001000 andeq r1, r0, r0 0x0000012c: 00000000 andeq r0, r0, r0 0x00000130: 00000004 andeq r0, r0, r4 0x00000134: 54410002 strbpl r0, [r1], #-2 0x00000138: 3c000000 .byte 0x00, 0x00, 0x00, 0x3c 0x0000013c: 00000000 andeq r0, r0, r0 Here the disassembly of 0x120..0x13f is using the data that is in 0x104..0x123. This is caused by passing the wrong value to the read_memory_func(). The intention is that at this point in the loop the 'cap_buf' buffer already contains 'csize' bytes of data for the instruction at guest addr 'pc', and we want to read in an extra 'tsize' bytes. Those extra bytes are therefore at 'pc + csize', not 'pc'. On the first time through the loop 'csize' happens to be zero, so the initial read of 32 bytes into cap_buf is correct and as long as the disassembly never needs to read more data we return the correct information. Use the correct guest address in the call to read_memory_func(). Cc: qemu-stable@nongnu.org Fixes: https://bugs.launchpad.net/qemu/+bug/1900779 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20201022132445.25039-1-peter.maydell@linaro.org --- disas/capstone.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/disas/capstone.c b/disas/capstone.c index XXXXXXX..XXXXXXX 100644 --- a/disas/capstone.c +++ b/disas/capstone.c @@ -XXX,XX +XXX,XX @@ bool cap_disas_monitor(disassemble_info *info, uint64_t pc, int count) /* Make certain that we can make progress. */ assert(tsize != 0); - info->read_memory_func(pc, cap_buf + csize, tsize, info); + info->read_memory_func(pc + csize, cap_buf + csize, tsize, info); csize += tsize; if (cs_disasm_iter(handle, &cbuf, &csize, &pc, insn)) { -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Use the BIT_ULL() macro to ensure we use 64-bit arithmetic. This fixes the following Coverity issue (OVERFLOW_BEFORE_WIDEN): CID 1432363 (#1 of 1): Unintentional integer overflow: overflow_before_widen: Potentially overflowing expression 1 << scale with type int (32 bits, signed) is evaluated using 32-bit arithmetic, and then used in a context that expects an expression of type hwaddr (64 bits, unsigned). Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Acked-by: Eric Auger <eric.auger@redhat.com> Message-id: 20201030144617.1535064-1-philmd@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/smmuv3.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/bitops.h" #include "hw/irq.h" #include "hw/sysbus.h" #include "migration/vmstate.h" @@ -XXX,XX +XXX,XX @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd) scale = CMD_SCALE(cmd); num = CMD_NUM(cmd); ttl = CMD_TTL(cmd); - num_pages = (num + 1) * (1 << (scale)); + num_pages = (num + 1) * BIT_ULL(scale); } if (type == SMMU_CMD_TLBI_NH_VA) { -- 2.20.1 From: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> When booting a CPU with EL3 using the -kernel flag, set up CPTR_EL3 so that SVE will not trap to EL3. Signed-off-by: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030151541.11976-1-remi@remlab.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/boot.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ static void do_cpu_reset(void *opaque) if (cpu_isar_feature(aa64_mte, cpu)) { env->cp15.scr_el3 |= SCR_ATA; } + if (cpu_isar_feature(aa64_sve, cpu)) { + env->cp15.cptr_el[3] |= CPTR_EZ; + } /* AArch64 kernels never boot in secure mode */ assert(!info->secure_boot); /* This hook is only supported for AArch32 currently: -- 2.20.1 From: AlexChen <alex.chen@huawei.com> In omap_lcd_interrupts(), the pointer omap_lcd is dereferinced before being check if it is valid, which may lead to NULL pointer dereference. So move the assignment to surface after checking that the omap_lcd is valid and move surface_bits_per_pixel(surface) to after the surface assignment. Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: AlexChen <alex.chen@huawei.com> Message-id: 5F9CDB8A.9000001@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/display/omap_lcdc.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/hw/display/omap_lcdc.c b/hw/display/omap_lcdc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcdc.c +++ b/hw/display/omap_lcdc.c @@ -XXX,XX +XXX,XX @@ static void omap_lcd_interrupts(struct omap_lcd_panel_s *s) static void omap_update_display(void *opaque) { struct omap_lcd_panel_s *omap_lcd = (struct omap_lcd_panel_s *) opaque; - DisplaySurface *surface = qemu_console_surface(omap_lcd->con); + DisplaySurface *surface; draw_line_func draw_line; int size, height, first, last; int width, linesize, step, bpp, frame_offset; hwaddr frame_base; - if (!omap_lcd || omap_lcd->plm == 1 || !omap_lcd->enable || - !surface_bits_per_pixel(surface)) { + if (!omap_lcd || omap_lcd->plm == 1 || !omap_lcd->enable) { + return; + } + + surface = qemu_console_surface(omap_lcd->con); + if (!surface_bits_per_pixel(surface)) { return; } -- 2.20.1 From: AlexChen <alex.chen@huawei.com> In exynos4210_fimd_update(), the pointer s is dereferinced before being check if it is valid, which may lead to NULL pointer dereference. So move the assignment to global_width after checking that the s is valid. Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 5F9F8D88.9030102@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/display/exynos4210_fimd.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/hw/display/exynos4210_fimd.c b/hw/display/exynos4210_fimd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/exynos4210_fimd.c +++ b/hw/display/exynos4210_fimd.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_fimd_update(void *opaque) bool blend = false; uint8_t *host_fb_addr; bool is_dirty = false; - const int global_width = (s->vidtcon[2] & FIMD_VIDTCON2_SIZE_MASK) + 1; + int global_width; if (!s || !s->console || !s->enabled || surface_bits_per_pixel(qemu_console_surface(s->console)) == 0) { return; } + + global_width = (s->vidtcon[2] & FIMD_VIDTCON2_SIZE_MASK) + 1; exynos4210_update_resolution(s); surface = qemu_console_surface(s->console); -- 2.20.1 In arm_v7m_mmu_idx_for_secstate() we get the 'priv' level to pass to armv7m_mmu_idx_for_secstate_and_priv() by calling arm_current_el(). This is incorrect when the security state being queried is not the current one, because arm_current_el() uses the current security state to determine which of the banked CONTROL.nPRIV bits to look at. The effect was that if (for instance) Secure state was in privileged mode but Non-Secure was not then we would return the wrong MMU index. The only places where we are using this function in a way that could trigger this bug are for the stack loads during a v8M function-return and for the instruction fetch of a v8M SG insn. Fix the bug by expanding out the M-profile version of the arm_current_el() logic inline so it can use the passed in secstate rather than env->v7m.secure. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201022164408.13214-1-peter.maydell@linaro.org --- target/arm/m_helper.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -XXX,XX +XXX,XX @@ ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env, /* Return the MMU index for a v7M CPU in the specified security state */ ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate) { - bool priv = arm_current_el(env) != 0; + bool priv = arm_v7m_is_handler_mode(env) || + !(env->v7m.control[secstate] & 1); return arm_v7m_mmu_idx_for_secstate_and_priv(env, secstate, priv); } -- 2.20.1 On some hosts (eg Ubuntu Bionic) pkg-config returns a set of libraries for gio-2.0 which don't actually work when compiling statically. (Specifically, the returned library string includes -lmount, but not -lblkid which -lmount depends upon, so linking fails due to missing symbols.) Check that the libraries work, and don't enable gio if they don't, in the same way we do for gnutls. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200928160402.7961-1-peter.maydell@linaro.org --- configure | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ if test "$static" = yes && test "$mingw32" = yes; then fi if $pkg_config --atleast-version=$glib_req_ver gio-2.0; then - gio=yes gio_cflags=$($pkg_config --cflags gio-2.0) gio_libs=$($pkg_config --libs gio-2.0) gdbus_codegen=$($pkg_config --variable=gdbus_codegen gio-2.0) if [ ! -x "$gdbus_codegen" ]; then gdbus_codegen= fi + # Check that the libraries actually work -- Ubuntu 18.04 ships + # with pkg-config --static --libs data for gio-2.0 that is missing + # -lblkid and will give a link error. + write_c_skeleton + if compile_prog "" "gio_libs" ; then + gio=yes + else + gio=no + fi else gio=no fi -- 2.20.1 In gicv3_init_cpuif() we copy the ARMCPU gicv3_maintenance_interrupt into the GICv3CPUState struct's maintenance_irq field. This will only work if the board happens to have already wired up the CPU maintenance IRQ before the GIC was realized. Unfortunately this is not the case for the 'virt' board, and so the value that gets copied is NULL (since a qemu_irq is really a pointer to an IRQState struct under the hood). The effect is that the CPU interface code never actually raises the maintenance interrupt line. Instead, since the GICv3CPUState has a pointer to the CPUState, make the dereference at the point where we want to raise the interrupt, to avoid an implicit requirement on board code to wire things up in a particular order. Reported-by: Jose Martins <josemartins90@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20201009153904.28529-1-peter.maydell@linaro.org Reviewed-by: Luc Michel <luc@lmichel.fr> --- include/hw/intc/arm_gicv3_common.h | 1 - hw/intc/arm_gicv3_cpuif.c | 5 ++--- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3CPUState { qemu_irq parent_fiq; qemu_irq parent_virq; qemu_irq parent_vfiq; - qemu_irq maintenance_irq; /* Redistributor */ uint32_t level; /* Current IRQ level */ diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ static void gicv3_cpuif_virt_update(GICv3CPUState *cs) int irqlevel = 0; int fiqlevel = 0; int maintlevel = 0; + ARMCPU *cpu = ARM_CPU(cs->cpu); idx = hppvi_index(cs); trace_gicv3_cpuif_virt_update(gicv3_redist_affid(cs), idx); @@ -XXX,XX +XXX,XX @@ static void gicv3_cpuif_virt_update(GICv3CPUState *cs) qemu_set_irq(cs->parent_vfiq, fiqlevel); qemu_set_irq(cs->parent_virq, irqlevel); - qemu_set_irq(cs->maintenance_irq, maintlevel); + qemu_set_irq(cpu->gicv3_maintenance_interrupt, maintlevel); } static uint64_t icv_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) @@ -XXX,XX +XXX,XX @@ void gicv3_init_cpuif(GICv3State *s) && cpu->gic_num_lrs) { int j; - cs->maintenance_irq = cpu->gicv3_maintenance_interrupt; - cs->num_list_regs = cpu->gic_num_lrs; cs->vpribits = cpu->gic_vpribits; cs->vprebits = cpu->gic_vprebits; -- 2.20.1 The kerneldoc script currently emits Sphinx markup for a macro with arguments that uses the c:function directive. This is correct for Sphinx versions earlier than Sphinx 3, where c:macro doesn't allow documentation of macros with arguments and c:function is not picky about the syntax of what it is passed. However, in Sphinx 3 the c:macro directive was enhanced to support macros with arguments, and c:function was made more picky about what syntax it accepted. When kerneldoc is told that it needs to produce output for Sphinx 3 or later, make it emit c:function only for functions and c:macro for macros with arguments. We assume that anything with a return type is a function and anything without is a macro. This fixes the Sphinx error: /home/petmay01/linaro/qemu-from-laptop/qemu/docs/../include/qom/object.h:155:Error in declarator If declarator-id with parameters (e.g., 'void f(int arg)'): Invalid C declaration: Expected identifier in nested name. [error at 25] DECLARE_INSTANCE_CHECKER ( InstanceType, OBJ_NAME, TYPENAME) -------------------------^ If parenthesis in noptr-declarator (e.g., 'void (*f(int arg))(double)'): Error in declarator or parameters Invalid C declaration: Expecting "(" in parameters. [error at 39] DECLARE_INSTANCE_CHECKER ( InstanceType, OBJ_NAME, TYPENAME) ---------------------------------------^ Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Tested-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20201030174700.7204-2-peter.maydell@linaro.org --- scripts/kernel-doc | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index XXXXXXX..XXXXXXX 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -XXX,XX +XXX,XX @@ sub output_function_rst(%) { output_highlight_rst($args{'purpose'}); $start = "\n\n**Syntax**\n\n ``"; } else { - print ".. c:function:: "; + if ((split(/\./, $sphinx_version))[0] >= 3) { + # Sphinx 3 and later distinguish macros and functions and + # complain if you use c:function with something that's not + # syntactically valid as a function declaration. + # We assume that anything with a return type is a function + # and anything without is a macro. + if ($args{'functiontype'} ne "") { + print ".. c:function:: "; + } else { + print ".. c:macro:: "; + } + } else { + # Older Sphinx don't support documenting macros that take + # arguments with c:macro, and don't complain about the use + # of c:function for this. + print ".. c:function:: "; + } } if ($args{'functiontype'} ne "") { $start .= $args{'functiontype'} . " " . $args{'function'} . " ("; -- 2.20.1 Sphinx 3.2 is pickier than earlier versions about the option:: markup, and complains about our usage in qemu-option-trace.rst: ../../docs/qemu-option-trace.rst.inc:4:Malformed option description '[enable=]PATTERN', should look like "opt", "-opt args", "--opt args", "/opt args" or "+opt args" In this file, we're really trying to document the different parts of the top-level --trace option, which qemu-nbd.rst and qemu-img.rst have already introduced with an option:: markup. So it's not right to use option:: here anyway. Switch to a different markup (definition lists) which gives about the same formatted output. (Unlike option::, this markup doesn't produce index entries; but at the moment we don't do anything much with indexes anyway, and in any case I think it doesn't make much sense to have individual index entries for the sub-parts of the --trace option.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Tested-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20201030174700.7204-3-peter.maydell@linaro.org --- docs/qemu-option-trace.rst.inc | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/qemu-option-trace.rst.inc b/docs/qemu-option-trace.rst.inc index XXXXXXX..XXXXXXX 100644 --- a/docs/qemu-option-trace.rst.inc +++ b/docs/qemu-option-trace.rst.inc @@ -XXX,XX +XXX,XX @@ Specify tracing options. -.. option:: [enable=]PATTERN +``[enable=]PATTERN`` Immediately enable events matching *PATTERN* (either event name or a globbing pattern). This option is only @@ -XXX,XX +XXX,XX @@ Specify tracing options. Use :option:`-trace help` to print a list of names of trace points. -.. option:: events=FILE +``events=FILE`` Immediately enable events listed in *FILE*. The file must contain one event name (as listed in the ``trace-events-all`` @@ -XXX,XX +XXX,XX @@ Specify tracing options. available if QEMU has been compiled with the ``simple``, ``log`` or ``ftrace`` tracing backend. -.. option:: file=FILE +``file=FILE`` Log output traces to *FILE*. This option is only available if QEMU has been compiled with -- 2.20.1 The randomness tests in the NPCM7xx RNG test fail intermittently but fairly frequently. On my machine running the test in a loop: while QTEST_QEMU_BINARY=./qemu-system-aarch64 ./tests/qtest/npcm7xx_rng-test; do true; done will fail in less than a minute with an error like: ERROR:../../tests/qtest/npcm7xx_rng-test.c:256:test_first_byte_runs: assertion failed (calc_runs_p(buf.l, sizeof(buf) * BITS_PER_BYTE) > 0.01): (0.00286205989 > 0.01) (Failures have been observed on all 4 of the randomness tests, not just first_byte_runs.) It's not clear why these tests are failing like this, but intermittent failures make CI and merge testing awkward, so disable running them unless a developer specifically sets QEMU_TEST_FLAKY_RNG_TESTS when running the test suite, until we work out the cause. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20201102152454.8287-1-peter.maydell@linaro.org Reviewed-by: Havard Skinnemoen <hskinnemoen@google.com> --- tests/qtest/npcm7xx_rng-test.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/tests/qtest/npcm7xx_rng-test.c b/tests/qtest/npcm7xx_rng-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/npcm7xx_rng-test.c +++ b/tests/qtest/npcm7xx_rng-test.c @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) qtest_add_func("npcm7xx_rng/enable_disable", test_enable_disable); qtest_add_func("npcm7xx_rng/rosel", test_rosel); - qtest_add_func("npcm7xx_rng/continuous/monobit", test_continuous_monobit); - qtest_add_func("npcm7xx_rng/continuous/runs", test_continuous_runs); - qtest_add_func("npcm7xx_rng/first_byte/monobit", test_first_byte_monobit); - qtest_add_func("npcm7xx_rng/first_byte/runs", test_first_byte_runs); + /* + * These tests fail intermittently; only run them on explicit + * request until we figure out why. + */ + if (getenv("QEMU_TEST_FLAKY_RNG_TESTS")) { + qtest_add_func("npcm7xx_rng/continuous/monobit", test_continuous_monobit); + qtest_add_func("npcm7xx_rng/continuous/runs", test_continuous_runs); + qtest_add_func("npcm7xx_rng/first_byte/monobit", test_first_byte_monobit); + qtest_add_func("npcm7xx_rng/first_byte/runs", test_first_byte_runs); + } qtest_start("-machine npcm750-evb"); ret = g_test_run(); -- 2.20.1