target-arm queue; this one has a fair scattering of more miscellaneous things in it which I've sent out this week. I've shoved those in as well as it seemed the least-effort way of getting them into master; a few of them are dependencies on arm-related patches I have brewing. thanks -- PMM The following changes since commit 2702c2d3eb74e3908c0c5dbf3a71c8987595a86e: Merge remote-tracking branch 'remotes/stsquad/tags/pull-travis-updates-140618-1' into staging (2018-06-15 12:49:36 +0100) are available in the Git repository at: git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20180615 for you to fetch changes up to 14120108f87b3f9e1beacdf0a6096e464e62bb65: target/arm: Allow ARMv6-M Thumb2 instructions (2018-06-15 15:23:34 +0100) ---------------------------------------------------------------- target-arm and miscellaneous queue: * fix KVM state save/restore for GICv3 priority registers for high IRQ numbers * hw/arm/mps2-tz: Put ethernet controller behind PPC * hw/sh/sh7750: Convert away from old_mmio * hw/m68k/mcf5206: Convert away from old_mmio * hw/block/pflash_cfi02: Convert away from old_mmio * hw/watchdog/wdt_i6300esb: Convert away from old_mmio * hw/input/pckbd: Convert away from old_mmio * hw/char/parallel: Convert away from old_mmio * armv7m: refactor to get rid of armv7m_init() function * arm: Don't crash if user tries to use a Cortex-M CPU without an NVIC * hw/core/or-irq: Support more than 16 inputs to an OR gate * cpu-defs.h: Document CPUIOTLBEntry 'addr' field * cputlb: Pass cpu_transaction_failed() the correct physaddr * CODING_STYLE: Define our preferred form for multiline comments * Add and use new stn_*_p() and ldn_*_p() memory access functions * target/arm: More parts of the upcoming SVE support * aspeed_scu: Implement RNG register * m25p80: add support for two bytes WRSR for Macronix chips * exec.c: Handle IOMMUs being in the path of TCG CPU memory accesses * target/arm: Allow ARMv6-M Thumb2 instructions ---------------------------------------------------------------- Cédric Le Goater (1): m25p80: add support for two bytes WRSR for Macronix chips Joel Stanley (1): aspeed_scu: Implement RNG register Julia Suvorova (1): target/arm: Allow ARMv6-M Thumb2 instructions Peter Maydell (21): hw/arm/mps2-tz: Put ethernet controller behind PPC hw/sh/sh7750: Convert away from old_mmio hw/m68k/mcf5206: Convert away from old_mmio hw/block/pflash_cfi02: Convert away from old_mmio hw/watchdog/wdt_i6300esb: Convert away from old_mmio hw/input/pckbd: Convert away from old_mmio hw/char/parallel: Convert away from old_mmio stellaris: Stop using armv7m_init() hw/arm/armv7m: Remove unused armv7m_init() function arm: Don't crash if user tries to use a Cortex-M CPU without an NVIC hw/core/or-irq: Support more than 16 inputs to an OR gate cpu-defs.h: Document CPUIOTLBEntry 'addr' field cputlb: Pass cpu_transaction_failed() the correct physaddr CODING_STYLE: Define our preferred form for multiline comments bswap: Add new stn_*_p() and ldn_*_p() memory access functions exec.c: Don't accidentally sign-extend 4-byte loads in subpage_read() exec.c: Use stn_p() and ldn_p() instead of explicit switches iommu: Add IOMMU index concept to IOMMU API iommu: Add IOMMU index argument to notifier APIs iommu: Add IOMMU index argument to translate method exec.c: Handle IOMMUs in address_space_translate_for_iotlb() Richard Henderson (18): target/arm: Extend vec_reg_offset to larger sizes target/arm: Implement SVE Permute - Unpredicated Group target/arm: Implement SVE Permute - Predicates Group target/arm: Implement SVE Permute - Interleaving Group target/arm: Implement SVE compress active elements target/arm: Implement SVE conditionally broadcast/extract element target/arm: Implement SVE copy to vector (predicated) target/arm: Implement SVE reverse within elements target/arm: Implement SVE vector splice (predicated) target/arm: Implement SVE Select Vectors Group target/arm: Implement SVE Integer Compare - Vectors Group target/arm: Implement SVE Integer Compare - Immediate Group target/arm: Implement SVE Partition Break Group target/arm: Implement SVE Predicate Count Group target/arm: Implement SVE Integer Compare - Scalars Group target/arm: Implement FDUP/DUP target/arm: Implement SVE Integer Wide Immediate - Unpredicated Group target/arm: Implement SVE Floating Point Arithmetic - Unpredicated Group Shannon Zhao (1): arm_gicv3_kvm: kvm_dist_get/put_priority: skip the registers banked by GICR_IPRIORITYR include/exec/cpu-all.h | 4 + include/exec/cpu-defs.h | 9 + include/exec/exec-all.h | 16 +- include/exec/memory.h | 65 +- include/hw/arm/arm.h | 8 +- include/hw/or-irq.h | 5 +- include/qemu/bswap.h | 52 ++ include/qom/cpu.h | 3 + target/arm/helper-sve.h | 294 +++++++++ target/arm/helper.h | 19 + target/arm/translate-a64.h | 26 +- accel/tcg/cputlb.c | 59 +- exec.c | 263 ++++---- hw/alpha/typhoon.c | 3 +- hw/arm/armv7m.c | 28 +- hw/arm/mps2-tz.c | 32 +- hw/arm/smmuv3.c | 2 +- hw/arm/stellaris.c | 12 +- hw/block/m25p80.c | 1 + hw/block/pflash_cfi02.c | 97 +-- hw/char/parallel.c | 50 +- hw/core/or-irq.c | 39 +- hw/dma/rc4030.c | 2 +- hw/i386/amd_iommu.c | 2 +- hw/i386/intel_iommu.c | 8 +- hw/input/pckbd.c | 14 +- hw/intc/arm_gicv3_kvm.c | 18 +- hw/intc/armv7m_nvic.c | 6 +- hw/m68k/mcf5206.c | 48 +- hw/misc/aspeed_scu.c | 20 + hw/ppc/spapr_iommu.c | 5 +- hw/s390x/s390-pci-bus.c | 2 +- hw/s390x/s390-pci-inst.c | 4 +- hw/sh4/sh7750.c | 44 +- hw/sparc/sun4m_iommu.c | 3 +- hw/sparc64/sun4u_iommu.c | 2 +- hw/vfio/common.c | 6 +- hw/virtio/vhost.c | 7 +- hw/watchdog/wdt_i6300esb.c | 48 +- memory.c | 33 +- target/arm/cpu.c | 18 + target/arm/sve_helper.c | 1250 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 1458 +++++++++++++++++++++++++++++++++++++++++++ target/arm/translate.c | 43 +- target/arm/vec_helper.c | 69 ++ CODING_STYLE | 17 + docs/devel/loads-stores.rst | 15 + target/arm/sve.decode | 248 ++++++++ 48 files changed, 4114 insertions(+), 363 deletions(-) From: Shannon Zhao <zhaoshenglong@huawei.com> While for_each_dist_irq_reg loop starts from GIC_INTERNAL, it forgot to offset the date array and index. This will overlap the GICR registers value and leave the last GIC_INTERNAL irq's registers out of update. Fixes: 367b9f527becdd20ddf116e17a3c0c2bbc486920 Cc: qemu-stable@nongnu.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Shannon Zhao <zhaoshenglong@huawei.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gicv3_kvm.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) 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_priority(GICv3State *s, uint32_t offset, uint8_t *bmp) uint32_t reg, *field; int irq; - field = (uint32_t *)bmp; + /* For the KVM GICv3, affinity routing is always enabled, and the first 8 + * GICD_IPRIORITYR<n> registers are always RAZ/WI. The corresponding + * functionality is replaced by GICR_IPRIORITYR<n>. It doesn't need to + * sync them. So it needs to skip the field of GIC_INTERNAL irqs in bmp and + * offset. + */ + field = (uint32_t *)(bmp + GIC_INTERNAL); + offset += (GIC_INTERNAL * 8) / 8; for_each_dist_irq_reg(irq, s->num_irq, 8) { kvm_gicd_access(s, offset, &reg, false); *field = reg; @@ -XXX,XX +XXX,XX @@ static void kvm_dist_put_priority(GICv3State *s, uint32_t offset, uint8_t *bmp) uint32_t reg, *field; int irq; - field = (uint32_t *)bmp; + /* For the KVM GICv3, affinity routing is always enabled, and the first 8 + * GICD_IPRIORITYR<n> registers are always RAZ/WI. The corresponding + * functionality is replaced by GICR_IPRIORITYR<n>. It doesn't need to + * sync them. So it needs to skip the field of GIC_INTERNAL irqs in bmp and + * offset. + */ + field = (uint32_t *)(bmp + GIC_INTERNAL); + offset += (GIC_INTERNAL * 8) / 8; for_each_dist_irq_reg(irq, s->num_irq, 8) { reg = *field; kvm_gicd_access(s, offset, &reg, true); -- 2.17.1 The ethernet controller in the AN505 MPC FPGA image is behind the same AHB Peripheral Protection Controller that handles the graphics and GPIOs. (In the documentation this is clear in the block diagram but the ethernet controller was omitted from the table listing devices connected to the PPC.) The ethernet sits behind AHB PPCEXP0 interface 5. We had incorrectly claimed that this was a "gpio4", but there are only 4 GPIOs in this image. Correct the QEMU model to match the hardware. Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20180515171446.10834-1-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 32 +++++++++++++++++++++++--------- 1 file changed, 23 insertions(+), 9 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ typedef struct { UnimplementedDeviceState spi[5]; UnimplementedDeviceState i2c[4]; UnimplementedDeviceState i2s_audio; - UnimplementedDeviceState gpio[5]; + UnimplementedDeviceState gpio[4]; UnimplementedDeviceState dma[4]; UnimplementedDeviceState gfx; CMSDKAPBUART uart[5]; SplitIRQ sec_resp_splitter; qemu_or_irq uart_irq_orgate; + DeviceState *lan9118; } MPS2TZMachineState; #define TYPE_MPS2TZ_MACHINE "mps2tz" @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_fpgaio(MPS2TZMachineState *mms, void *opaque, return sysbus_mmio_get_region(SYS_BUS_DEVICE(fpgaio), 0); } +static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, + const char *name, hwaddr size) +{ + SysBusDevice *s; + DeviceState *iotkitdev = DEVICE(&mms->iotkit); + NICInfo *nd = &nd_table[0]; + + /* In hardware this is a LAN9220; the LAN9118 is software compatible + * except that it doesn't support the checksum-offload feature. + */ + qemu_check_nic_model(nd, "lan9118"); + mms->lan9118 = qdev_create(NULL, "lan9118"); + qdev_set_nic_properties(mms->lan9118, nd); + qdev_init_nofail(mms->lan9118); + + s = SYS_BUS_DEVICE(mms->lan9118); + sysbus_connect_irq(s, 0, qdev_get_gpio_in_named(iotkitdev, "EXP_IRQ", 16)); + return sysbus_mmio_get_region(s, 0); +} + static void mps2tz_common_init(MachineState *machine) { MPS2TZMachineState *mms = MPS2TZ_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) { "gpio1", make_unimp_dev, &mms->gpio[1], 0x40101000, 0x1000 }, { "gpio2", make_unimp_dev, &mms->gpio[2], 0x40102000, 0x1000 }, { "gpio3", make_unimp_dev, &mms->gpio[3], 0x40103000, 0x1000 }, - { "gpio4", make_unimp_dev, &mms->gpio[4], 0x40104000, 0x1000 }, + { "eth", make_eth_dev, NULL, 0x42000000, 0x100000 }, }, }, { .name = "ahb_ppcexp1", @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) "cfg_sec_resp", 0)); } - /* In hardware this is a LAN9220; the LAN9118 is software compatible - * except that it doesn't support the checksum-offload feature. - * The ethernet controller is not behind a PPC. - */ - lan9118_init(&nd_table[0], 0x42000000, - qdev_get_gpio_in_named(iotkitdev, "EXP_IRQ", 16)); - create_unimplemented_device("FPGA NS PC", 0x48007000, 0x1000); armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, 0x400000); -- 2.17.1 Convert the sh7750 device away from using the old_mmio field of MemoryRegionOps. This device is used by the sh4 r2d board. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180601141223.26630-2-peter.maydell@linaro.org --- hw/sh4/sh7750.c | 44 ++++++++++++++++++++++++++++++++++++-------- 1 file changed, 36 insertions(+), 8 deletions(-) diff --git a/hw/sh4/sh7750.c b/hw/sh4/sh7750.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sh4/sh7750.c +++ b/hw/sh4/sh7750.c @@ -XXX,XX +XXX,XX @@ static void sh7750_mem_writel(void *opaque, hwaddr addr, } } +static uint64_t sh7750_mem_readfn(void *opaque, hwaddr addr, unsigned size) +{ + switch (size) { + case 1: + return sh7750_mem_readb(opaque, addr); + case 2: + return sh7750_mem_readw(opaque, addr); + case 4: + return sh7750_mem_readl(opaque, addr); + default: + g_assert_not_reached(); + } +} + +static void sh7750_mem_writefn(void *opaque, hwaddr addr, + uint64_t value, unsigned size) +{ + switch (size) { + case 1: + sh7750_mem_writeb(opaque, addr, value); + break; + case 2: + sh7750_mem_writew(opaque, addr, value); + break; + case 4: + sh7750_mem_writel(opaque, addr, value); + break; + default: + g_assert_not_reached(); + } +} + static const MemoryRegionOps sh7750_mem_ops = { - .old_mmio = { - .read = {sh7750_mem_readb, - sh7750_mem_readw, - sh7750_mem_readl }, - .write = {sh7750_mem_writeb, - sh7750_mem_writew, - sh7750_mem_writel }, - }, + .read = sh7750_mem_readfn, + .write = sh7750_mem_writefn, + .valid.min_access_size = 1, + .valid.max_access_size = 4, .endianness = DEVICE_NATIVE_ENDIAN, }; -- 2.17.1 Convert the mcf5206 device away from using the old_mmio field of MemoryRegionOps. This device is used by the an5206 board. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Thomas Huth <huth@tuxfamily.org> Message-id: 20180601141223.26630-3-peter.maydell@linaro.org --- hw/m68k/mcf5206.c | 48 +++++++++++++++++++++++++++++++++++------------ 1 file changed, 36 insertions(+), 12 deletions(-) diff --git a/hw/m68k/mcf5206.c b/hw/m68k/mcf5206.c index XXXXXXX..XXXXXXX 100644 --- a/hw/m68k/mcf5206.c +++ b/hw/m68k/mcf5206.c @@ -XXX,XX +XXX,XX @@ static void m5206_mbar_writel(void *opaque, hwaddr offset, m5206_mbar_write(s, offset, value, 4); } +static uint64_t m5206_mbar_readfn(void *opaque, hwaddr addr, unsigned size) +{ + switch (size) { + case 1: + return m5206_mbar_readb(opaque, addr); + case 2: + return m5206_mbar_readw(opaque, addr); + case 4: + return m5206_mbar_readl(opaque, addr); + default: + g_assert_not_reached(); + } +} + +static void m5206_mbar_writefn(void *opaque, hwaddr addr, + uint64_t value, unsigned size) +{ + switch (size) { + case 1: + m5206_mbar_writeb(opaque, addr, value); + break; + case 2: + m5206_mbar_writew(opaque, addr, value); + break; + case 4: + m5206_mbar_writel(opaque, addr, value); + break; + default: + g_assert_not_reached(); + } +} + static const MemoryRegionOps m5206_mbar_ops = { - .old_mmio = { - .read = { - m5206_mbar_readb, - m5206_mbar_readw, - m5206_mbar_readl, - }, - .write = { - m5206_mbar_writeb, - m5206_mbar_writew, - m5206_mbar_writel, - }, - }, + .read = m5206_mbar_readfn, + .write = m5206_mbar_writefn, + .valid.min_access_size = 1, + .valid.max_access_size = 4, .endianness = DEVICE_NATIVE_ENDIAN, }; -- 2.17.1 Convert the pflash_cfi02 device away from using the old_mmio field of MemoryRegionOps. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Acked-by: Max Reitz <mreitz@redhat.com> Message-id: 20180601141223.26630-4-peter.maydell@linaro.org --- hw/block/pflash_cfi02.c | 97 ++++++++--------------------------------- 1 file changed, 18 insertions(+), 79 deletions(-) diff --git a/hw/block/pflash_cfi02.c b/hw/block/pflash_cfi02.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/pflash_cfi02.c +++ b/hw/block/pflash_cfi02.c @@ -XXX,XX +XXX,XX @@ static void pflash_write (pflash_t *pfl, hwaddr offset, pfl->cmd = 0; } - -static uint32_t pflash_readb_be(void *opaque, hwaddr addr) +static uint64_t pflash_be_readfn(void *opaque, hwaddr addr, unsigned size) { - return pflash_read(opaque, addr, 1, 1); + return pflash_read(opaque, addr, size, 1); } -static uint32_t pflash_readb_le(void *opaque, hwaddr addr) +static void pflash_be_writefn(void *opaque, hwaddr addr, + uint64_t value, unsigned size) { - return pflash_read(opaque, addr, 1, 0); + pflash_write(opaque, addr, value, size, 1); } -static uint32_t pflash_readw_be(void *opaque, hwaddr addr) +static uint64_t pflash_le_readfn(void *opaque, hwaddr addr, unsigned size) { - pflash_t *pfl = opaque; - - return pflash_read(pfl, addr, 2, 1); + return pflash_read(opaque, addr, size, 0); } -static uint32_t pflash_readw_le(void *opaque, hwaddr addr) +static void pflash_le_writefn(void *opaque, hwaddr addr, + uint64_t value, unsigned size) { - pflash_t *pfl = opaque; - - return pflash_read(pfl, addr, 2, 0); -} - -static uint32_t pflash_readl_be(void *opaque, hwaddr addr) -{ - pflash_t *pfl = opaque; - - return pflash_read(pfl, addr, 4, 1); -} - -static uint32_t pflash_readl_le(void *opaque, hwaddr addr) -{ - pflash_t *pfl = opaque; - - return pflash_read(pfl, addr, 4, 0); -} - -static void pflash_writeb_be(void *opaque, hwaddr addr, - uint32_t value) -{ - pflash_write(opaque, addr, value, 1, 1); -} - -static void pflash_writeb_le(void *opaque, hwaddr addr, - uint32_t value) -{ - pflash_write(opaque, addr, value, 1, 0); -} - -static void pflash_writew_be(void *opaque, hwaddr addr, - uint32_t value) -{ - pflash_t *pfl = opaque; - - pflash_write(pfl, addr, value, 2, 1); -} - -static void pflash_writew_le(void *opaque, hwaddr addr, - uint32_t value) -{ - pflash_t *pfl = opaque; - - pflash_write(pfl, addr, value, 2, 0); -} - -static void pflash_writel_be(void *opaque, hwaddr addr, - uint32_t value) -{ - pflash_t *pfl = opaque; - - pflash_write(pfl, addr, value, 4, 1); -} - -static void pflash_writel_le(void *opaque, hwaddr addr, - uint32_t value) -{ - pflash_t *pfl = opaque; - - pflash_write(pfl, addr, value, 4, 0); + pflash_write(opaque, addr, value, size, 0); } static const MemoryRegionOps pflash_cfi02_ops_be = { - .old_mmio = { - .read = { pflash_readb_be, pflash_readw_be, pflash_readl_be, }, - .write = { pflash_writeb_be, pflash_writew_be, pflash_writel_be, }, - }, + .read = pflash_be_readfn, + .write = pflash_be_writefn, + .valid.min_access_size = 1, + .valid.max_access_size = 4, .endianness = DEVICE_NATIVE_ENDIAN, }; static const MemoryRegionOps pflash_cfi02_ops_le = { - .old_mmio = { - .read = { pflash_readb_le, pflash_readw_le, pflash_readl_le, }, - .write = { pflash_writeb_le, pflash_writew_le, pflash_writel_le, }, - }, + .read = pflash_le_readfn, + .write = pflash_le_writefn, + .valid.min_access_size = 1, + .valid.max_access_size = 4, .endianness = DEVICE_NATIVE_ENDIAN, }; -- 2.17.1 Convert the wdt_i6300esb device away from using the old_mmio field of MemoryRegionOps. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180601141223.26630-5-peter.maydell@linaro.org --- hw/watchdog/wdt_i6300esb.c | 48 ++++++++++++++++++++++++++++---------- 1 file changed, 36 insertions(+), 12 deletions(-) diff --git a/hw/watchdog/wdt_i6300esb.c b/hw/watchdog/wdt_i6300esb.c index XXXXXXX..XXXXXXX 100644 --- a/hw/watchdog/wdt_i6300esb.c +++ b/hw/watchdog/wdt_i6300esb.c @@ -XXX,XX +XXX,XX @@ static void i6300esb_mem_writel(void *vp, hwaddr addr, uint32_t val) } } +static uint64_t i6300esb_mem_readfn(void *opaque, hwaddr addr, unsigned size) +{ + switch (size) { + case 1: + return i6300esb_mem_readb(opaque, addr); + case 2: + return i6300esb_mem_readw(opaque, addr); + case 4: + return i6300esb_mem_readl(opaque, addr); + default: + g_assert_not_reached(); + } +} + +static void i6300esb_mem_writefn(void *opaque, hwaddr addr, + uint64_t value, unsigned size) +{ + switch (size) { + case 1: + i6300esb_mem_writeb(opaque, addr, value); + break; + case 2: + i6300esb_mem_writew(opaque, addr, value); + break; + case 4: + i6300esb_mem_writel(opaque, addr, value); + break; + default: + g_assert_not_reached(); + } +} + static const MemoryRegionOps i6300esb_ops = { - .old_mmio = { - .read = { - i6300esb_mem_readb, - i6300esb_mem_readw, - i6300esb_mem_readl, - }, - .write = { - i6300esb_mem_writeb, - i6300esb_mem_writew, - i6300esb_mem_writel, - }, - }, + .read = i6300esb_mem_readfn, + .write = i6300esb_mem_writefn, + .valid.min_access_size = 1, + .valid.max_access_size = 4, .endianness = DEVICE_LITTLE_ENDIAN, }; -- 2.17.1 Convert the pckbd device away from using the old_mmio field of MemoryRegionOps. This change only affects the memory-mapped variant of the i8042, which is used by the Unicore32 'puv3' board and the MIPS Jazz boards 'magnum' and 'pica61'. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180601141223.26630-6-peter.maydell@linaro.org --- hw/input/pckbd.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/hw/input/pckbd.c b/hw/input/pckbd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/input/pckbd.c +++ b/hw/input/pckbd.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_kbd = { }; /* Memory mapped interface */ -static uint32_t kbd_mm_readb (void *opaque, hwaddr addr) +static uint64_t kbd_mm_readfn(void *opaque, hwaddr addr, unsigned size) { KBDState *s = opaque; @@ -XXX,XX +XXX,XX @@ static uint32_t kbd_mm_readb (void *opaque, hwaddr addr) return kbd_read_data(s, 0, 1) & 0xff; } -static void kbd_mm_writeb (void *opaque, hwaddr addr, uint32_t value) +static void kbd_mm_writefn(void *opaque, hwaddr addr, + uint64_t value, unsigned size) { KBDState *s = opaque; @@ -XXX,XX +XXX,XX @@ static void kbd_mm_writeb (void *opaque, hwaddr addr, uint32_t value) kbd_write_data(s, 0, value & 0xff, 1); } + static const MemoryRegionOps i8042_mmio_ops = { + .read = kbd_mm_readfn, + .write = kbd_mm_writefn, + .valid.min_access_size = 1, + .valid.max_access_size = 4, .endianness = DEVICE_NATIVE_ENDIAN, - .old_mmio = { - .read = { kbd_mm_readb, kbd_mm_readb, kbd_mm_readb }, - .write = { kbd_mm_writeb, kbd_mm_writeb, kbd_mm_writeb }, - }, }; void i8042_mm_init(qemu_irq kbd_irq, qemu_irq mouse_irq, -- 2.17.1 Convert the parallel device away from using the old_mmio field of MemoryRegionOps. This change only affects the memory-mapped variant, which is used by the MIPS Jazz boards 'magnum' and 'pica61'. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180601141223.26630-7-peter.maydell@linaro.org --- hw/char/parallel.c | 50 ++++++++++------------------------------------ 1 file changed, 11 insertions(+), 39 deletions(-) diff --git a/hw/char/parallel.c b/hw/char/parallel.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/parallel.c +++ b/hw/char/parallel.c @@ -XXX,XX +XXX,XX @@ static void parallel_isa_realizefn(DeviceState *dev, Error **errp) } /* Memory mapped interface */ -static uint32_t parallel_mm_readb (void *opaque, hwaddr addr) +static uint64_t parallel_mm_readfn(void *opaque, hwaddr addr, unsigned size) { ParallelState *s = opaque; - return parallel_ioport_read_sw(s, addr >> s->it_shift) & 0xFF; + return parallel_ioport_read_sw(s, addr >> s->it_shift) & + MAKE_64BIT_MASK(0, size * 8); } -static void parallel_mm_writeb (void *opaque, - hwaddr addr, uint32_t value) +static void parallel_mm_writefn(void *opaque, hwaddr addr, + uint64_t value, unsigned size) { ParallelState *s = opaque; - parallel_ioport_write_sw(s, addr >> s->it_shift, value & 0xFF); -} - -static uint32_t parallel_mm_readw (void *opaque, hwaddr addr) -{ - ParallelState *s = opaque; - - return parallel_ioport_read_sw(s, addr >> s->it_shift) & 0xFFFF; -} - -static void parallel_mm_writew (void *opaque, - hwaddr addr, uint32_t value) -{ - ParallelState *s = opaque; - - parallel_ioport_write_sw(s, addr >> s->it_shift, value & 0xFFFF); -} - -static uint32_t parallel_mm_readl (void *opaque, hwaddr addr) -{ - ParallelState *s = opaque; - - return parallel_ioport_read_sw(s, addr >> s->it_shift); -} - -static void parallel_mm_writel (void *opaque, - hwaddr addr, uint32_t value) -{ - ParallelState *s = opaque; - - parallel_ioport_write_sw(s, addr >> s->it_shift, value); + parallel_ioport_write_sw(s, addr >> s->it_shift, + value & MAKE_64BIT_MASK(0, size * 8)); } static const MemoryRegionOps parallel_mm_ops = { - .old_mmio = { - .read = { parallel_mm_readb, parallel_mm_readw, parallel_mm_readl }, - .write = { parallel_mm_writeb, parallel_mm_writew, parallel_mm_writel }, - }, + .read = parallel_mm_readfn, + .write = parallel_mm_writefn, + .valid.min_access_size = 1, + .valid.max_access_size = 4, .endianness = DEVICE_NATIVE_ENDIAN, }; -- 2.17.1 The stellaris board is still using the legacy armv7m_init() function, which predates conversion of the ARMv7M into a proper QOM container object. Make the board code directly create the ARMv7M object instead. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20180601144328.23817-2-peter.maydell@linaro.org --- hw/arm/stellaris.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 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 @@ #include "qemu/log.h" #include "exec/address-spaces.h" #include "sysemu/sysemu.h" +#include "hw/arm/armv7m.h" #include "hw/char/pl011.h" #include "hw/misc/unimp.h" #include "cpu.h" @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) &error_fatal); memory_region_add_subregion(system_memory, 0x20000000, sram); - nvic = armv7m_init(system_memory, flash_size, NUM_IRQ_LINES, - ms->kernel_filename, ms->cpu_type); + nvic = qdev_create(NULL, TYPE_ARMV7M); + qdev_prop_set_uint32(nvic, "num-irq", NUM_IRQ_LINES); + qdev_prop_set_string(nvic, "cpu-type", ms->cpu_type); + object_property_set_link(OBJECT(nvic), OBJECT(get_system_memory()), + "memory", &error_abort); + /* This will exit with an error if the user passed us a bad cpu_type */ + qdev_init_nofail(nvic); qdev_connect_gpio_out_named(nvic, "SYSRESETREQ", 0, qemu_allocate_irq(&do_sys_reset, NULL, 0)); @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) create_unimplemented_device("analogue-comparator", 0x4003c000, 0x1000); create_unimplemented_device("hibernation", 0x400fc000, 0x1000); create_unimplemented_device("flash-control", 0x400fd000, 0x1000); + + armv7m_load_kernel(ARM_CPU(first_cpu), ms->kernel_filename, flash_size); } /* FIXME: Figure out how to generate these from stellaris_boards. */ -- 2.17.1 Remove the now-unused armv7m_init() function. This was a legacy from before we properly QOMified ARMv7M, and it has some flaws: * it combines work that needs to be done by an SoC object (creating and initializing the TYPE_ARMV7M object) with work that needs to be done by the board model (setting the system up to load the ELF file specified with -kernel) * TYPE_ARMV7M creation failure is fatal, but an SoC object wants to arrange to propagate the failure outward * it uses allocate-and-create via qdev_create() whereas the current preferred style for SoC objects is to do creation in-place Board and SoC models can instead do the two jobs this function was doing themselves, in the right places and with whatever their preferred style/error handling is. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20180601144328.23817-3-peter.maydell@linaro.org --- include/hw/arm/arm.h | 8 ++------ hw/arm/armv7m.c | 21 --------------------- 2 files changed, 2 insertions(+), 27 deletions(-) diff --git a/include/hw/arm/arm.h b/include/hw/arm/arm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/arm.h +++ b/include/hw/arm/arm.h @@ -XXX,XX +XXX,XX @@ typedef enum { ARM_ENDIANNESS_BE32, } arm_endianness; -/* armv7m.c */ -DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq, - const char *kernel_filename, const char *cpu_type); /** * armv7m_load_kernel: * @cpu: CPU @@ -XXX,XX +XXX,XX @@ DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq, * @mem_size: mem_size: maximum image size to load * * Load the guest image for an ARMv7M system. This must be called by - * any ARMv7M board, either directly or via armv7m_init(). (This is - * necessary to ensure that the CPU resets correctly on system reset, - * as well as for kernel loading.) + * any ARMv7M board. (This is necessary to ensure that the CPU resets + * correctly on system reset, as well as for kernel loading.) */ void armv7m_load_kernel(ARMCPU *cpu, const char *kernel_filename, int mem_size); diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ static void armv7m_reset(void *opaque) cpu_reset(CPU(cpu)); } -/* Init CPU and memory for a v7-M based board. - mem_size is in bytes. - Returns the ARMv7M device. */ - -DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq, - const char *kernel_filename, const char *cpu_type) -{ - DeviceState *armv7m; - - armv7m = qdev_create(NULL, TYPE_ARMV7M); - qdev_prop_set_uint32(armv7m, "num-irq", num_irq); - qdev_prop_set_string(armv7m, "cpu-type", cpu_type); - object_property_set_link(OBJECT(armv7m), OBJECT(get_system_memory()), - "memory", &error_abort); - /* This will exit with an error if the user passed us a bad cpu_type */ - qdev_init_nofail(armv7m); - - armv7m_load_kernel(ARM_CPU(first_cpu), kernel_filename, mem_size); - return armv7m; -} - void armv7m_load_kernel(ARMCPU *cpu, const char *kernel_filename, int mem_size) { int image_size; -- 2.17.1 The Cortex-M CPU and its NVIC are two intimately intertwined parts of the same hardware; it is not possible to use one without the other. Unfortunately a lot of our board models don't do any sanity checking on the CPU type the user asks for, so a command line like qemu-system-arm -M versatilepb -cpu cortex-m3 will create an M3 without an NVIC, and coredump immediately. In the other direction, trying a non-M-profile CPU in an M-profile board won't blow up, but doesn't do anything useful either: qemu-system-arm -M lm3s6965evb -cpu arm926 Add some checking in the NVIC and CPU realize functions that the user isn't trying to use an NVIC without an M-profile CPU or an M-profile CPU without an NVIC, so we can produce a helpful error message rather than a core dump. Fixes: https://bugs.launchpad.net/qemu/+bug/1766896 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180601160355.15393-1-peter.maydell@linaro.org --- hw/arm/armv7m.c | 7 ++++++- hw/intc/armv7m_nvic.c | 6 +++++- target/arm/cpu.c | 18 ++++++++++++++++++ 3 files changed, 29 insertions(+), 2 deletions(-) diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) return; } } + + /* Tell the CPU where the NVIC is; it will fail realize if it doesn't + * have one. + */ + s->cpu->env.nvic = &s->nvic; + object_property_set_bool(OBJECT(s->cpu), true, "realized", &err); if (err != NULL) { error_propagate(errp, err); @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) sbd = SYS_BUS_DEVICE(&s->nvic); sysbus_connect_irq(sbd, 0, qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_IRQ)); - s->cpu->env.nvic = &s->nvic; memory_region_add_subregion(&s->container, 0xe000e000, sysbus_mmio_get_region(sbd, 0)); diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) int regionlen; s->cpu = ARM_CPU(qemu_get_cpu(0)); - assert(s->cpu); + + if (!s->cpu || !arm_feature(&s->cpu->env, ARM_FEATURE_M)) { + error_setg(errp, "The NVIC can only be used with a Cortex-M CPU"); + return; + } if (s->num_irq > NVIC_MAX_IRQ) { error_setg(errp, "num-irq %d exceeds NVIC maximum", s->num_irq); diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) return; } +#ifndef CONFIG_USER_ONLY + /* The NVIC and M-profile CPU are two halves of a single piece of + * hardware; trying to use one without the other is a command line + * error and will result in segfaults if not caught here. + */ + if (arm_feature(env, ARM_FEATURE_M)) { + if (!env->nvic) { + error_setg(errp, "This board cannot be used with Cortex-M CPUs"); + return; + } + } else { + if (env->nvic) { + error_setg(errp, "This board can only be used with Cortex-M CPUs"); + return; + } + } +#endif + cpu_exec_realizefn(cs, &local_err); if (local_err != NULL) { error_propagate(errp, local_err); -- 2.17.1 For the IoTKit MPC support, we need to wire together the interrupt outputs of 17 MPCs; this exceeds the current value of MAX_OR_LINES. Increase MAX_OR_LINES to 32 (which should be enough for anyone). The tricky part is retaining the migration compatibility for existing OR gates; we add a subsection which is only used for larger OR gates, and define it such that we can freely increase MAX_OR_LINES in future (or even move to a dynamically allocated levels[] array without an upper size limit) without breaking compatibility. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180604152941.20374-10-peter.maydell@linaro.org --- include/hw/or-irq.h | 5 ++++- hw/core/or-irq.c | 39 +++++++++++++++++++++++++++++++++++++-- 2 files changed, 41 insertions(+), 3 deletions(-) diff --git a/include/hw/or-irq.h b/include/hw/or-irq.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/or-irq.h +++ b/include/hw/or-irq.h @@ -XXX,XX +XXX,XX @@ #define TYPE_OR_IRQ "or-irq" -#define MAX_OR_LINES 16 +/* This can safely be increased if necessary without breaking + * migration compatibility (as long as it remains greater than 15). + */ +#define MAX_OR_LINES 32 typedef struct OrIRQState qemu_or_irq; diff --git a/hw/core/or-irq.c b/hw/core/or-irq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/or-irq.c +++ b/hw/core/or-irq.c @@ -XXX,XX +XXX,XX @@ static void or_irq_init(Object *obj) qdev_init_gpio_out(DEVICE(obj), &s->out_irq, 1); } +/* The original version of this device had a fixed 16 entries in its + * VMState array; devices with more inputs than this need to + * migrate the extra lines via a subsection. + * The subsection migrates as much of the levels[] array as is needed + * (including repeating the first 16 elements), to avoid the awkwardness + * of splitting it in two to meet the requirements of VMSTATE_VARRAY_UINT16. + */ +#define OLD_MAX_OR_LINES 16 +#if MAX_OR_LINES < OLD_MAX_OR_LINES +#error MAX_OR_LINES must be at least 16 for migration compatibility +#endif + +static bool vmstate_extras_needed(void *opaque) +{ + qemu_or_irq *s = OR_IRQ(opaque); + + return s->num_lines >= OLD_MAX_OR_LINES; +} + +static const VMStateDescription vmstate_or_irq_extras = { + .name = "or-irq-extras", + .version_id = 1, + .minimum_version_id = 1, + .needed = vmstate_extras_needed, + .fields = (VMStateField[]) { + VMSTATE_VARRAY_UINT16_UNSAFE(levels, qemu_or_irq, num_lines, 0, + vmstate_info_bool, bool), + VMSTATE_END_OF_LIST(), + }, +}; + static const VMStateDescription vmstate_or_irq = { .name = TYPE_OR_IRQ, .version_id = 1, .minimum_version_id = 1, .fields = (VMStateField[]) { - VMSTATE_BOOL_ARRAY(levels, qemu_or_irq, MAX_OR_LINES), + VMSTATE_BOOL_SUB_ARRAY(levels, qemu_or_irq, 0, OLD_MAX_OR_LINES), VMSTATE_END_OF_LIST(), - } + }, + .subsections = (const VMStateDescription*[]) { + &vmstate_or_irq_extras, + NULL + }, }; static Property or_irq_properties[] = { -- 2.17.1 The 'addr' field in the CPUIOTLBEntry struct has a rather non-obvious use; add a comment documenting it (reverse-engineered from what the code that sets it is doing). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180611125633.32755-2-peter.maydell@linaro.org --- include/exec/cpu-defs.h | 9 +++++++++ accel/tcg/cputlb.c | 12 ++++++++++++ 2 files changed, 21 insertions(+) diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -XXX,XX +XXX,XX @@ QEMU_BUILD_BUG_ON(sizeof(CPUTLBEntry) != (1 << CPU_TLB_ENTRY_BITS)); * structs into one.) */ typedef struct CPUIOTLBEntry { + /* + * @addr contains: + * - in the lower TARGET_PAGE_BITS, a physical section number + * - with the lower TARGET_PAGE_BITS masked off, an offset which + * must be added to the virtual address to obtain: + * + the ram_addr_t of the target RAM (if the physical section + * number is PHYS_SECTION_NOTDIRTY or PHYS_SECTION_ROM) + * + the offset within the target MemoryRegion (otherwise) + */ hwaddr addr; MemTxAttrs attrs; } CPUIOTLBEntry; diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, env->iotlb_v[mmu_idx][vidx] = env->iotlb[mmu_idx][index]; /* refill the tlb */ + /* + * At this point iotlb contains a physical section number in the lower + * TARGET_PAGE_BITS, and either + * + the ram_addr_t of the page base of the target RAM (if NOTDIRTY or ROM) + * + the offset within section->mr of the page base (otherwise) + * We subtract the vaddr (which is page aligned and thus won't + * disturb the low bits) to give an offset which can be added to the + * (non-page-aligned) vaddr of the eventual memory access to get + * the MemoryRegion offset for the access. Note that the vaddr we + * subtract here is that of the page base, and not the same as the + * vaddr we add back in io_readx()/io_writex()/get_page_addr_code(). + */ env->iotlb[mmu_idx][index].addr = iotlb - vaddr; env->iotlb[mmu_idx][index].attrs = attrs; -- 2.17.1 The API for cpu_transaction_failed() says that it takes the physical address for the failed transaction. However we were actually passing it the offset within the target MemoryRegion. We don't currently have any target CPU implementations of this hook that require the physical address; fix this bug so we don't get confused if we ever do add one. Suggested-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180611125633.32755-3-peter.maydell@linaro.org --- include/exec/exec-all.h | 13 ++++++++++-- accel/tcg/cputlb.c | 44 +++++++++++++++++++++++++++++------------ exec.c | 5 +++-- 3 files changed, 45 insertions(+), 17 deletions(-) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ void tb_lock_reset(void); #if !defined(CONFIG_USER_ONLY) -struct MemoryRegion *iotlb_to_region(CPUState *cpu, - hwaddr index, MemTxAttrs attrs); +/** + * iotlb_to_section: + * @cpu: CPU performing the access + * @index: TCG CPU IOTLB entry + * + * Given a TCG CPU IOTLB entry, return the MemoryRegionSection that + * it refers to. @index will have been initially created and returned + * by memory_region_section_get_iotlb(). + */ +struct MemoryRegionSection *iotlb_to_section(CPUState *cpu, + hwaddr index, MemTxAttrs attrs); void tlb_fill(CPUState *cpu, target_ulong addr, int size, MMUAccessType access_type, int mmu_idx, uintptr_t retaddr); diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry, target_ulong addr, uintptr_t retaddr, int size) { CPUState *cpu = ENV_GET_CPU(env); - hwaddr physaddr = iotlbentry->addr; - MemoryRegion *mr = iotlb_to_region(cpu, physaddr, iotlbentry->attrs); + hwaddr mr_offset; + MemoryRegionSection *section; + MemoryRegion *mr; uint64_t val; bool locked = false; MemTxResult r; - physaddr = (physaddr & TARGET_PAGE_MASK) + addr; + section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs); + mr = section->mr; + mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr; cpu->mem_io_pc = retaddr; if (mr != &io_mem_rom && mr != &io_mem_notdirty && !cpu->can_do_io) { cpu_io_recompile(cpu, retaddr); @@ -XXX,XX +XXX,XX @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry, qemu_mutex_lock_iothread(); locked = true; } - r = memory_region_dispatch_read(mr, physaddr, + r = memory_region_dispatch_read(mr, mr_offset, &val, size, iotlbentry->attrs); if (r != MEMTX_OK) { + hwaddr physaddr = mr_offset + + section->offset_within_address_space - + section->offset_within_region; + cpu_transaction_failed(cpu, physaddr, addr, size, MMU_DATA_LOAD, mmu_idx, iotlbentry->attrs, r, retaddr); } @@ -XXX,XX +XXX,XX @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry, uintptr_t retaddr, int size) { CPUState *cpu = ENV_GET_CPU(env); - hwaddr physaddr = iotlbentry->addr; - MemoryRegion *mr = iotlb_to_region(cpu, physaddr, iotlbentry->attrs); + hwaddr mr_offset; + MemoryRegionSection *section; + MemoryRegion *mr; bool locked = false; MemTxResult r; - physaddr = (physaddr & TARGET_PAGE_MASK) + addr; + section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs); + mr = section->mr; + mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr; if (mr != &io_mem_rom && mr != &io_mem_notdirty && !cpu->can_do_io) { cpu_io_recompile(cpu, retaddr); } @@ -XXX,XX +XXX,XX @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry, qemu_mutex_lock_iothread(); locked = true; } - r = memory_region_dispatch_write(mr, physaddr, + r = memory_region_dispatch_write(mr, mr_offset, val, size, iotlbentry->attrs); if (r != MEMTX_OK) { + hwaddr physaddr = mr_offset + + section->offset_within_address_space - + section->offset_within_region; + cpu_transaction_failed(cpu, physaddr, addr, size, MMU_DATA_STORE, mmu_idx, iotlbentry->attrs, r, retaddr); } @@ -XXX,XX +XXX,XX @@ static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index, */ tb_page_addr_t get_page_addr_code(CPUArchState *env, target_ulong addr) { - int mmu_idx, index, pd; + int mmu_idx, index; void *p; MemoryRegion *mr; + MemoryRegionSection *section; CPUState *cpu = ENV_GET_CPU(env); CPUIOTLBEntry *iotlbentry; - hwaddr physaddr; + hwaddr physaddr, mr_offset; index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1); mmu_idx = cpu_mmu_index(env, true); @@ -XXX,XX +XXX,XX @@ tb_page_addr_t get_page_addr_code(CPUArchState *env, target_ulong addr) } } iotlbentry = &env->iotlb[mmu_idx][index]; - pd = iotlbentry->addr & ~TARGET_PAGE_MASK; - mr = iotlb_to_region(cpu, pd, iotlbentry->attrs); + section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs); + mr = section->mr; if (memory_region_is_unassigned(mr)) { qemu_mutex_lock_iothread(); if (memory_region_request_mmio_ptr(mr, addr)) { @@ -XXX,XX +XXX,XX @@ tb_page_addr_t get_page_addr_code(CPUArchState *env, target_ulong addr) * and use the MemTXResult it produced). However it is the * simplest place we have currently available for the check. */ - physaddr = (iotlbentry->addr & TARGET_PAGE_MASK) + addr; + mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr; + physaddr = mr_offset + + section->offset_within_address_space - + section->offset_within_region; cpu_transaction_failed(cpu, physaddr, addr, 0, MMU_INST_FETCH, mmu_idx, iotlbentry->attrs, MEMTX_DECODE_ERROR, 0); diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps readonly_mem_ops = { }, }; -MemoryRegion *iotlb_to_region(CPUState *cpu, hwaddr index, MemTxAttrs attrs) +MemoryRegionSection *iotlb_to_section(CPUState *cpu, + hwaddr index, MemTxAttrs attrs) { int asidx = cpu_asidx_from_attrs(cpu, attrs); CPUAddressSpace *cpuas = &cpu->cpu_ases[asidx]; AddressSpaceDispatch *d = atomic_rcu_read(&cpuas->memory_dispatch); MemoryRegionSection *sections = d->map.sections; - return sections[index & ~TARGET_PAGE_MASK].mr; + return &sections[index & ~TARGET_PAGE_MASK]; } static void io_mem_init(void) -- 2.17.1 The codebase has a bit of a mix of different multiline comment styles. State a preference for the Linux kernel style: /* * Star on the left for each line. * Leading slash-star and trailing star-slash * each go on a line of their own. */ Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Alex Williamson <alex.williamson@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20180611141716.3813-1-peter.maydell@linaro.org --- CODING_STYLE | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/CODING_STYLE b/CODING_STYLE index XXXXXXX..XXXXXXX 100644 --- a/CODING_STYLE +++ b/CODING_STYLE @@ -XXX,XX +XXX,XX @@ We use traditional C-style /* */ comments and avoid // comments. Rationale: The // form is valid in C99, so this is purely a matter of consistency of style. The checkpatch script will warn you about this. +Multiline comment blocks should have a row of stars on the left, +and the initial /* and terminating */ both on their own lines: + /* + * like + * this + */ +This is the same format required by the Linux kernel coding style. + +(Some of the existing comments in the codebase use the GNU Coding +Standards form which does not have stars on the left, or other +variations; avoid these when writing new comments, but don't worry +about converting to the preferred form unless you're editing that +comment anyway.) + +Rationale: Consistency, and ease of visually picking out a multiline +comment from the surrounding code. + 8. trace-events style 8.1 0x prefix -- 2.17.1 There's a common pattern in QEMU where a function needs to perform a data load or store of an N byte integer in a particular endianness. At the moment this is handled by doing a switch() on the size and calling the appropriate ld*_p or st*_p function for each size. Provide a new family of functions ldn_*_p() and stn_*_p() which take the size as an argument and do the switch() themselves. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180611171007.4165-2-peter.maydell@linaro.org --- include/exec/cpu-all.h | 4 +++ include/qemu/bswap.h | 52 +++++++++++++++++++++++++++++++++++++ docs/devel/loads-stores.rst | 15 +++++++++++ 3 files changed, 71 insertions(+) diff --git a/include/exec/cpu-all.h b/include/exec/cpu-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-all.h +++ b/include/exec/cpu-all.h @@ -XXX,XX +XXX,XX @@ static inline void tswap64s(uint64_t *s) #define stq_p(p, v) stq_be_p(p, v) #define stfl_p(p, v) stfl_be_p(p, v) #define stfq_p(p, v) stfq_be_p(p, v) +#define ldn_p(p, sz) ldn_be_p(p, sz) +#define stn_p(p, sz, v) stn_be_p(p, sz, v) #else #define lduw_p(p) lduw_le_p(p) #define ldsw_p(p) ldsw_le_p(p) @@ -XXX,XX +XXX,XX @@ static inline void tswap64s(uint64_t *s) #define stq_p(p, v) stq_le_p(p, v) #define stfl_p(p, v) stfl_le_p(p, v) #define stfq_p(p, v) stfq_le_p(p, v) +#define ldn_p(p, sz) ldn_le_p(p, sz) +#define stn_p(p, sz, v) stn_le_p(p, sz, v) #endif /* MMU memory access macros */ diff --git a/include/qemu/bswap.h b/include/qemu/bswap.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/bswap.h +++ b/include/qemu/bswap.h @@ -XXX,XX +XXX,XX @@ typedef union { * For accessors that take a guest address rather than a * host address, see the cpu_{ld,st}_* accessors defined in * cpu_ldst.h. + * + * For cases where the size to be used is not fixed at compile time, + * there are + * stn{endian}_p(ptr, sz, val) + * which stores @val to @ptr as an @endian-order number @sz bytes in size + * and + * ldn{endian}_p(ptr, sz) + * which loads @sz bytes from @ptr as an unsigned @endian-order number + * and returns it in a uint64_t. */ static inline int ldub_p(const void *ptr) @@ -XXX,XX +XXX,XX @@ static inline unsigned long leul_to_cpu(unsigned long v) #endif } +/* Store v to p as a sz byte value in host order */ +#define DO_STN_LDN_P(END) \ + static inline void stn_## END ## _p(void *ptr, int sz, uint64_t v) \ + { \ + switch (sz) { \ + case 1: \ + stb_p(ptr, v); \ + break; \ + case 2: \ + stw_ ## END ## _p(ptr, v); \ + break; \ + case 4: \ + stl_ ## END ## _p(ptr, v); \ + break; \ + case 8: \ + stq_ ## END ## _p(ptr, v); \ + break; \ + default: \ + g_assert_not_reached(); \ + } \ + } \ + static inline uint64_t ldn_## END ## _p(const void *ptr, int sz) \ + { \ + switch (sz) { \ + case 1: \ + return ldub_p(ptr); \ + case 2: \ + return lduw_ ## END ## _p(ptr); \ + case 4: \ + return (uint32_t)ldl_ ## END ## _p(ptr); \ + case 8: \ + return ldq_ ## END ## _p(ptr); \ + default: \ + g_assert_not_reached(); \ + } \ + } + +DO_STN_LDN_P(he) +DO_STN_LDN_P(le) +DO_STN_LDN_P(be) + +#undef DO_STN_LDN_P + #undef le_bswap #undef be_bswap #undef le_bswaps diff --git a/docs/devel/loads-stores.rst b/docs/devel/loads-stores.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/loads-stores.rst +++ b/docs/devel/loads-stores.rst @@ -XXX,XX +XXX,XX @@ The ``_{endian}`` infix is omitted for target-endian accesses. The target endian accessors are only available to source files which are built per-target. +There are also functions which take the size as an argument: + +load: ``ldn{endian}_p(ptr, sz)`` + +which performs an unsigned load of ``sz`` bytes from ``ptr`` +as an ``{endian}`` order value and returns it in a uint64_t. + +store: ``stn{endian}_p(ptr, sz, val)`` + +which stores ``val`` to ``ptr`` as an ``{endian}`` order value +of size ``sz`` bytes. + + Regexes for git grep - ``\<ldf\?[us]\?[bwlq]\(_[hbl]e\)\?_p\>`` - ``\<stf\?[bwlq]\(_[hbl]e\)\?_p\>`` + - ``\<ldn_\([hbl]e\)?_p\>`` + - ``\<stn_\([hbl]e\)?_p\>`` ``cpu_{ld,st}_*`` ~~~~~~~~~~~~~~~~~ -- 2.17.1 In subpage_read() we perform a load of the data into a local buffer which we then access using ldub_p(), lduw_p(), ldl_p() or ldq_p() depending on its size, storing the result into the uint64_t *data. Since ldl_p() returns an 'int', this means that for the 4-byte case we will sign-extend the data, whereas for 1 and 2 byte reads we zero-extend it. This ought not to matter since the caller will likely ignore values in the high bytes of the data, but add a cast so that we're consistent. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180611171007.4165-3-peter.maydell@linaro.org --- exec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static MemTxResult subpage_read(void *opaque, hwaddr addr, uint64_t *data, *data = lduw_p(buf); return MEMTX_OK; case 4: - *data = ldl_p(buf); + *data = (uint32_t)ldl_p(buf); return MEMTX_OK; case 8: *data = ldq_p(buf); -- 2.17.1 Now we have stn_p() and ldn_p() we can use them in various functions in exec.c that used to have their own switch-on-size code. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180611171007.4165-4-peter.maydell@linaro.org --- exec.c | 112 +++++---------------------------------------------------- 1 file changed, 8 insertions(+), 104 deletions(-) diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static void notdirty_mem_write(void *opaque, hwaddr ram_addr, memory_notdirty_write_prepare(&ndi, current_cpu, current_cpu->mem_io_vaddr, ram_addr, size); - switch (size) { - case 1: - stb_p(qemu_map_ram_ptr(NULL, ram_addr), val); - break; - case 2: - stw_p(qemu_map_ram_ptr(NULL, ram_addr), val); - break; - case 4: - stl_p(qemu_map_ram_ptr(NULL, ram_addr), val); - break; - case 8: - stq_p(qemu_map_ram_ptr(NULL, ram_addr), val); - break; - default: - abort(); - } + stn_p(qemu_map_ram_ptr(NULL, ram_addr), size, val); memory_notdirty_write_complete(&ndi); } @@ -XXX,XX +XXX,XX @@ static MemTxResult subpage_read(void *opaque, hwaddr addr, uint64_t *data, if (res) { return res; } - switch (len) { - case 1: - *data = ldub_p(buf); - return MEMTX_OK; - case 2: - *data = lduw_p(buf); - return MEMTX_OK; - case 4: - *data = (uint32_t)ldl_p(buf); - return MEMTX_OK; - case 8: - *data = ldq_p(buf); - return MEMTX_OK; - default: - abort(); - } + *data = ldn_p(buf, len); + return MEMTX_OK; } static MemTxResult subpage_write(void *opaque, hwaddr addr, @@ -XXX,XX +XXX,XX @@ static MemTxResult subpage_write(void *opaque, hwaddr addr, " value %"PRIx64"\n", __func__, subpage, len, addr, value); #endif - switch (len) { - case 1: - stb_p(buf, value); - break; - case 2: - stw_p(buf, value); - break; - case 4: - stl_p(buf, value); - break; - case 8: - stq_p(buf, value); - break; - default: - abort(); - } + stn_p(buf, len, value); return flatview_write(subpage->fv, addr + subpage->base, attrs, buf, len); } @@ -XXX,XX +XXX,XX @@ static MemTxResult flatview_write_continue(FlatView *fv, hwaddr addr, l = memory_access_size(mr, l, addr1); /* XXX: could force current_cpu to NULL to avoid potential bugs */ - switch (l) { - case 8: - /* 64 bit write access */ - val = ldq_p(buf); - result |= memory_region_dispatch_write(mr, addr1, val, 8, - attrs); - break; - case 4: - /* 32 bit write access */ - val = (uint32_t)ldl_p(buf); - result |= memory_region_dispatch_write(mr, addr1, val, 4, - attrs); - break; - case 2: - /* 16 bit write access */ - val = lduw_p(buf); - result |= memory_region_dispatch_write(mr, addr1, val, 2, - attrs); - break; - case 1: - /* 8 bit write access */ - val = ldub_p(buf); - result |= memory_region_dispatch_write(mr, addr1, val, 1, - attrs); - break; - default: - abort(); - } + val = ldn_p(buf, l); + result |= memory_region_dispatch_write(mr, addr1, val, l, attrs); } else { /* RAM case */ ptr = qemu_ram_ptr_length(mr->ram_block, addr1, &l, false); @@ -XXX,XX +XXX,XX @@ MemTxResult flatview_read_continue(FlatView *fv, hwaddr addr, /* I/O case */ release_lock |= prepare_mmio_access(mr); l = memory_access_size(mr, l, addr1); - switch (l) { - case 8: - /* 64 bit read access */ - result |= memory_region_dispatch_read(mr, addr1, &val, 8, - attrs); - stq_p(buf, val); - break; - case 4: - /* 32 bit read access */ - result |= memory_region_dispatch_read(mr, addr1, &val, 4, - attrs); - stl_p(buf, val); - break; - case 2: - /* 16 bit read access */ - result |= memory_region_dispatch_read(mr, addr1, &val, 2, - attrs); - stw_p(buf, val); - break; - case 1: - /* 8 bit read access */ - result |= memory_region_dispatch_read(mr, addr1, &val, 1, - attrs); - stb_p(buf, val); - break; - default: - abort(); - } + result |= memory_region_dispatch_read(mr, addr1, &val, l, attrs); + stn_p(buf, l, val); } else { /* RAM case */ ptr = qemu_ram_ptr_length(mr->ram_block, addr1, &l, false); -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Rearrange the arithmetic so that we are agnostic about the total size of the vector and the size of the element. This will allow us to index up to the 32nd byte and with 16-byte elements. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ static inline void assert_fp_access_checked(DisasContext *s) static inline int vec_reg_offset(DisasContext *s, int regno, int element, TCGMemOp size) { - int offs = 0; + int element_size = 1 << size; + int offs = element * element_size; #ifdef HOST_WORDS_BIGENDIAN /* This is complicated slightly because vfp.zregs[n].d[0] is - * still the low half and vfp.zregs[n].d[1] the high half - * of the 128 bit vector, even on big endian systems. - * Calculate the offset assuming a fully bigendian 128 bits, - * then XOR to account for the order of the two 64 bit halves. + * still the lowest and vfp.zregs[n].d[15] the highest of the + * 256 byte vector, even on big endian systems. + * + * Calculate the offset assuming fully little-endian, + * then XOR to account for the order of the 8-byte units. + * + * For 16 byte elements, the two 8 byte halves will not form a + * host int128 if the host is bigendian, since they're in the + * wrong order. However the only 16 byte operation we have is + * a move, so we can ignore this for the moment. More complicated + * operations will have to special case loading and storing from + * the zregs array. */ - offs += (16 - ((element + 1) * (1 << size))); - offs ^= 8; -#else - offs += element * (1 << size); + if (element_size < 8) { + offs ^= 8 - element_size; + } #endif offs += offsetof(CPUARMState, vfp.zregs[regno]); assert_fp_access_checked(s); -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 23 +++++++ target/arm/sve_helper.c | 114 +++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 133 +++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 27 ++++++++ 4 files changed, 297 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_cpy_z_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_ext, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_insr_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_insr_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_insr_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_insr_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) + +DEF_HELPER_FLAGS_3(sve_rev_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve_rev_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve_rev_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve_rev_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_tbl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_tbl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_tbl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_tbl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve_sunpk_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve_sunpk_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve_sunpk_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve_uunpk_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve_uunpk_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve_uunpk_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_and_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_bic_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_eor_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_ext)(void *vd, void *vn, void *vm, uint32_t desc) memcpy(vd + n_siz, &tmp, n_ofs); } } + +#define DO_INSR(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, uint64_t val, uint32_t desc) \ +{ \ + intptr_t opr_sz = simd_oprsz(desc); \ + swap_memmove(vd + sizeof(TYPE), vn, opr_sz - sizeof(TYPE)); \ + *(TYPE *)(vd + H(0)) = val; \ +} + +DO_INSR(sve_insr_b, uint8_t, H1) +DO_INSR(sve_insr_h, uint16_t, H1_2) +DO_INSR(sve_insr_s, uint32_t, H1_4) +DO_INSR(sve_insr_d, uint64_t, ) + +#undef DO_INSR + +void HELPER(sve_rev_b)(void *vd, void *vn, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + for (i = 0, j = opr_sz - 8; i < opr_sz / 2; i += 8, j -= 8) { + uint64_t f = *(uint64_t *)(vn + i); + uint64_t b = *(uint64_t *)(vn + j); + *(uint64_t *)(vd + i) = bswap64(b); + *(uint64_t *)(vd + j) = bswap64(f); + } +} + +static inline uint64_t hswap64(uint64_t h) +{ + uint64_t m = 0x0000ffff0000ffffull; + h = rol64(h, 32); + return ((h & m) << 16) | ((h >> 16) & m); +} + +void HELPER(sve_rev_h)(void *vd, void *vn, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + for (i = 0, j = opr_sz - 8; i < opr_sz / 2; i += 8, j -= 8) { + uint64_t f = *(uint64_t *)(vn + i); + uint64_t b = *(uint64_t *)(vn + j); + *(uint64_t *)(vd + i) = hswap64(b); + *(uint64_t *)(vd + j) = hswap64(f); + } +} + +void HELPER(sve_rev_s)(void *vd, void *vn, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + for (i = 0, j = opr_sz - 8; i < opr_sz / 2; i += 8, j -= 8) { + uint64_t f = *(uint64_t *)(vn + i); + uint64_t b = *(uint64_t *)(vn + j); + *(uint64_t *)(vd + i) = rol64(b, 32); + *(uint64_t *)(vd + j) = rol64(f, 32); + } +} + +void HELPER(sve_rev_d)(void *vd, void *vn, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + for (i = 0, j = opr_sz - 8; i < opr_sz / 2; i += 8, j -= 8) { + uint64_t f = *(uint64_t *)(vn + i); + uint64_t b = *(uint64_t *)(vn + j); + *(uint64_t *)(vd + i) = b; + *(uint64_t *)(vd + j) = f; + } +} + +#define DO_TBL(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + uintptr_t elem = opr_sz / sizeof(TYPE); \ + TYPE *d = vd, *n = vn, *m = vm; \ + ARMVectorReg tmp; \ + if (unlikely(vd == vn)) { \ + n = memcpy(&tmp, vn, opr_sz); \ + } \ + for (i = 0; i < elem; i++) { \ + TYPE j = m[H(i)]; \ + d[H(i)] = j < elem ? n[H(j)] : 0; \ + } \ +} + +DO_TBL(sve_tbl_b, uint8_t, H1) +DO_TBL(sve_tbl_h, uint16_t, H2) +DO_TBL(sve_tbl_s, uint32_t, H4) +DO_TBL(sve_tbl_d, uint64_t, ) + +#undef TBL + +#define DO_UNPK(NAME, TYPED, TYPES, HD, HS) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + TYPED *d = vd; \ + TYPES *n = vn; \ + ARMVectorReg tmp; \ + if (unlikely(vn - vd < opr_sz)) { \ + n = memcpy(&tmp, n, opr_sz / 2); \ + } \ + for (i = 0; i < opr_sz / sizeof(TYPED); i++) { \ + d[HD(i)] = n[HS(i)]; \ + } \ +} + +DO_UNPK(sve_sunpk_h, int16_t, int8_t, H2, H1) +DO_UNPK(sve_sunpk_s, int32_t, int16_t, H4, H2) +DO_UNPK(sve_sunpk_d, int64_t, int32_t, , H4) + +DO_UNPK(sve_uunpk_h, uint16_t, uint8_t, H2, H1) +DO_UNPK(sve_uunpk_s, uint32_t, uint16_t, H4, H2) +DO_UNPK(sve_uunpk_d, uint64_t, uint32_t, , H4) + +#undef DO_UNPK diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_EXT(DisasContext *s, arg_EXT *a, uint32_t insn) return true; } +/* + *** SVE Permute - Unpredicated Group + */ + +static bool trans_DUP_s(DisasContext *s, arg_DUP_s *a, uint32_t insn) +{ + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_dup_i64(a->esz, vec_full_reg_offset(s, a->rd), + vsz, vsz, cpu_reg_sp(s, a->rn)); + } + return true; +} + +static bool trans_DUP_x(DisasContext *s, arg_DUP_x *a, uint32_t insn) +{ + if ((a->imm & 0x1f) == 0) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + unsigned dofs = vec_full_reg_offset(s, a->rd); + unsigned esz, index; + + esz = ctz32(a->imm); + index = a->imm >> (esz + 1); + + if ((index << esz) < vsz) { + unsigned nofs = vec_reg_offset(s, a->rn, index, esz); + tcg_gen_gvec_dup_mem(esz, dofs, nofs, vsz, vsz); + } else { + tcg_gen_gvec_dup64i(dofs, vsz, vsz, 0); + } + } + return true; +} + +static void do_insr_i64(DisasContext *s, arg_rrr_esz *a, TCGv_i64 val) +{ + typedef void gen_insr(TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_i32); + static gen_insr * const fns[4] = { + gen_helper_sve_insr_b, gen_helper_sve_insr_h, + gen_helper_sve_insr_s, gen_helper_sve_insr_d, + }; + unsigned vsz = vec_full_reg_size(s); + TCGv_i32 desc = tcg_const_i32(simd_desc(vsz, vsz, 0)); + TCGv_ptr t_zd = tcg_temp_new_ptr(); + TCGv_ptr t_zn = tcg_temp_new_ptr(); + + tcg_gen_addi_ptr(t_zd, cpu_env, vec_full_reg_offset(s, a->rd)); + tcg_gen_addi_ptr(t_zn, cpu_env, vec_full_reg_offset(s, a->rn)); + + fns[a->esz](t_zd, t_zn, val, desc); + + tcg_temp_free_ptr(t_zd); + tcg_temp_free_ptr(t_zn); + tcg_temp_free_i32(desc); +} + +static bool trans_INSR_f(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + if (sve_access_check(s)) { + TCGv_i64 t = tcg_temp_new_i64(); + tcg_gen_ld_i64(t, cpu_env, vec_reg_offset(s, a->rm, 0, MO_64)); + do_insr_i64(s, a, t); + tcg_temp_free_i64(t); + } + return true; +} + +static bool trans_INSR_r(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + if (sve_access_check(s)) { + do_insr_i64(s, a, cpu_reg(s, a->rm)); + } + return true; +} + +static bool trans_REV_v(DisasContext *s, arg_rr_esz *a, uint32_t insn) +{ + static gen_helper_gvec_2 * const fns[4] = { + gen_helper_sve_rev_b, gen_helper_sve_rev_h, + gen_helper_sve_rev_s, gen_helper_sve_rev_d + }; + + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vsz, vsz, 0, fns[a->esz]); + } + return true; +} + +static bool trans_TBL(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve_tbl_b, gen_helper_sve_tbl_h, + gen_helper_sve_tbl_s, gen_helper_sve_tbl_d + }; + + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vsz, vsz, 0, fns[a->esz]); + } + return true; +} + +static bool trans_UNPK(DisasContext *s, arg_UNPK *a, uint32_t insn) +{ + static gen_helper_gvec_2 * const fns[4][2] = { + { NULL, NULL }, + { gen_helper_sve_sunpk_h, gen_helper_sve_uunpk_h }, + { gen_helper_sve_sunpk_s, gen_helper_sve_uunpk_s }, + { gen_helper_sve_sunpk_d, gen_helper_sve_uunpk_d }, + }; + + if (a->esz == 0) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn) + + (a->h ? vsz / 2 : 0), + vsz, vsz, 0, fns[a->esz][a->u]); + } + return true; +} + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ %imm4_16_p1 16:4 !function=plus1 %imm6_22_5 22:1 5:5 +%imm7_22_16 22:2 16:5 %imm8_16_10 16:5 10:3 %imm9_16_10 16:s6 10:3 @@ -XXX,XX +XXX,XX @@ # Three operand, vector element size @rd_rn_rm ........ esz:2 . rm:5 ... ... rn:5 rd:5 &rrr_esz +@rdn_rm ........ esz:2 ...... ...... rm:5 rd:5 \ + &rrr_esz rn=%reg_movprfx # Three operand with "memory" size, aka immediate left shift @rd_rn_msz_rm ........ ... rm:5 .... imm:2 rn:5 rd:5 &rrri @@ -XXX,XX +XXX,XX @@ CPY_z_i 00000101 .. 01 .... 00 . ........ ..... @rdn_pg4 imm=%sh8_i8s EXT 00000101 001 ..... 000 ... rm:5 rd:5 \ &rrri rn=%reg_movprfx imm=%imm8_16_10 +### SVE Permute - Unpredicated Group + +# SVE broadcast general register +DUP_s 00000101 .. 1 00000 001110 ..... ..... @rd_rn + +# SVE broadcast indexed element +DUP_x 00000101 .. 1 ..... 001000 rn:5 rd:5 \ + &rri imm=%imm7_22_16 + +# SVE insert SIMD&FP scalar register +INSR_f 00000101 .. 1 10100 001110 ..... ..... @rdn_rm + +# SVE insert general register +INSR_r 00000101 .. 1 00100 001110 ..... ..... @rdn_rm + +# SVE reverse vector elements +REV_v 00000101 .. 1 11000 001110 ..... ..... @rd_rn + +# SVE vector table lookup +TBL 00000101 .. 1 ..... 001100 ..... ..... @rd_rn_rm + +# SVE unpack vector elements +UNPK 00000101 esz:2 1100 u:1 h:1 001110 rn:5 rd:5 + ### SVE Predicate Logical Operations Group # SVE predicate logical operations -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 6 + target/arm/sve_helper.c | 290 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 120 +++++++++++++++ target/arm/sve.decode | 18 +++ 4 files changed, 434 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve_uunpk_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_uunpk_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_uunpk_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_zip_p, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_uzp_p, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_trn_p, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve_rev_p, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve_punpk_p, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_and_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_bic_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_eor_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_UNPK(sve_uunpk_s, uint32_t, uint16_t, H4, H2) DO_UNPK(sve_uunpk_d, uint64_t, uint32_t, , H4) #undef DO_UNPK + +/* Mask of bits included in the even numbered predicates of width esz. + * We also use this for expand_bits/compress_bits, and so extend the + * same pattern out to 16-bit units. + */ +static const uint64_t even_bit_esz_masks[5] = { + 0x5555555555555555ull, + 0x3333333333333333ull, + 0x0f0f0f0f0f0f0f0full, + 0x00ff00ff00ff00ffull, + 0x0000ffff0000ffffull, +}; + +/* Zero-extend units of 2**N bits to units of 2**(N+1) bits. + * For N==0, this corresponds to the operation that in qemu/bitops.h + * we call half_shuffle64; this algorithm is from Hacker's Delight, + * section 7-2 Shuffling Bits. + */ +static uint64_t expand_bits(uint64_t x, int n) +{ + int i; + + x &= 0xffffffffu; + for (i = 4; i >= n; i--) { + int sh = 1 << i; + x = ((x << sh) | x) & even_bit_esz_masks[i]; + } + return x; +} + +/* Compress units of 2**(N+1) bits to units of 2**N bits. + * For N==0, this corresponds to the operation that in qemu/bitops.h + * we call half_unshuffle64; this algorithm is from Hacker's Delight, + * section 7-2 Shuffling Bits, where it is called an inverse half shuffle. + */ +static uint64_t compress_bits(uint64_t x, int n) +{ + int i; + + for (i = n; i <= 4; i++) { + int sh = 1 << i; + x &= even_bit_esz_masks[i]; + x = (x >> sh) | x; + } + return x & 0xffffffffu; +} + +void HELPER(sve_zip_p)(void *vd, void *vn, void *vm, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + int esz = extract32(pred_desc, SIMD_DATA_SHIFT, 2); + intptr_t high = extract32(pred_desc, SIMD_DATA_SHIFT + 2, 1); + uint64_t *d = vd; + intptr_t i; + + if (oprsz <= 8) { + uint64_t nn = *(uint64_t *)vn; + uint64_t mm = *(uint64_t *)vm; + int half = 4 * oprsz; + + nn = extract64(nn, high * half, half); + mm = extract64(mm, high * half, half); + nn = expand_bits(nn, esz); + mm = expand_bits(mm, esz); + d[0] = nn + (mm << (1 << esz)); + } else { + ARMPredicateReg tmp_n, tmp_m; + + /* We produce output faster than we consume input. + Therefore we must be mindful of possible overlap. */ + if ((vn - vd) < (uintptr_t)oprsz) { + vn = memcpy(&tmp_n, vn, oprsz); + } + if ((vm - vd) < (uintptr_t)oprsz) { + vm = memcpy(&tmp_m, vm, oprsz); + } + if (high) { + high = oprsz >> 1; + } + + if ((high & 3) == 0) { + uint32_t *n = vn, *m = vm; + high >>= 2; + + for (i = 0; i < DIV_ROUND_UP(oprsz, 8); i++) { + uint64_t nn = n[H4(high + i)]; + uint64_t mm = m[H4(high + i)]; + + nn = expand_bits(nn, esz); + mm = expand_bits(mm, esz); + d[i] = nn + (mm << (1 << esz)); + } + } else { + uint8_t *n = vn, *m = vm; + uint16_t *d16 = vd; + + for (i = 0; i < oprsz / 2; i++) { + uint16_t nn = n[H1(high + i)]; + uint16_t mm = m[H1(high + i)]; + + nn = expand_bits(nn, esz); + mm = expand_bits(mm, esz); + d16[H2(i)] = nn + (mm << (1 << esz)); + } + } + } +} + +void HELPER(sve_uzp_p)(void *vd, void *vn, void *vm, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + int esz = extract32(pred_desc, SIMD_DATA_SHIFT, 2); + int odd = extract32(pred_desc, SIMD_DATA_SHIFT + 2, 1) << esz; + uint64_t *d = vd, *n = vn, *m = vm; + uint64_t l, h; + intptr_t i; + + if (oprsz <= 8) { + l = compress_bits(n[0] >> odd, esz); + h = compress_bits(m[0] >> odd, esz); + d[0] = extract64(l + (h << (4 * oprsz)), 0, 8 * oprsz); + } else { + ARMPredicateReg tmp_m; + intptr_t oprsz_16 = oprsz / 16; + + if ((vm - vd) < (uintptr_t)oprsz) { + m = memcpy(&tmp_m, vm, oprsz); + } + + for (i = 0; i < oprsz_16; i++) { + l = n[2 * i + 0]; + h = n[2 * i + 1]; + l = compress_bits(l >> odd, esz); + h = compress_bits(h >> odd, esz); + d[i] = l + (h << 32); + } + + /* For VL which is not a power of 2, the results from M do not + align nicely with the uint64_t for D. Put the aligned results + from M into TMP_M and then copy it into place afterward. */ + if (oprsz & 15) { + d[i] = compress_bits(n[2 * i] >> odd, esz); + + for (i = 0; i < oprsz_16; i++) { + l = m[2 * i + 0]; + h = m[2 * i + 1]; + l = compress_bits(l >> odd, esz); + h = compress_bits(h >> odd, esz); + tmp_m.p[i] = l + (h << 32); + } + tmp_m.p[i] = compress_bits(m[2 * i] >> odd, esz); + + swap_memmove(vd + oprsz / 2, &tmp_m, oprsz / 2); + } else { + for (i = 0; i < oprsz_16; i++) { + l = m[2 * i + 0]; + h = m[2 * i + 1]; + l = compress_bits(l >> odd, esz); + h = compress_bits(h >> odd, esz); + d[oprsz_16 + i] = l + (h << 32); + } + } + } +} + +void HELPER(sve_trn_p)(void *vd, void *vn, void *vm, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + uintptr_t esz = extract32(pred_desc, SIMD_DATA_SHIFT, 2); + bool odd = extract32(pred_desc, SIMD_DATA_SHIFT + 2, 1); + uint64_t *d = vd, *n = vn, *m = vm; + uint64_t mask; + int shr, shl; + intptr_t i; + + shl = 1 << esz; + shr = 0; + mask = even_bit_esz_masks[esz]; + if (odd) { + mask <<= shl; + shr = shl; + shl = 0; + } + + for (i = 0; i < DIV_ROUND_UP(oprsz, 8); i++) { + uint64_t nn = (n[i] & mask) >> shr; + uint64_t mm = (m[i] & mask) << shl; + d[i] = nn + mm; + } +} + +/* Reverse units of 2**N bits. */ +static uint64_t reverse_bits_64(uint64_t x, int n) +{ + int i, sh; + + x = bswap64(x); + for (i = 2, sh = 4; i >= n; i--, sh >>= 1) { + uint64_t mask = even_bit_esz_masks[i]; + x = ((x & mask) << sh) | ((x >> sh) & mask); + } + return x; +} + +static uint8_t reverse_bits_8(uint8_t x, int n) +{ + static const uint8_t mask[3] = { 0x55, 0x33, 0x0f }; + int i, sh; + + for (i = 2, sh = 4; i >= n; i--, sh >>= 1) { + x = ((x & mask[i]) << sh) | ((x >> sh) & mask[i]); + } + return x; +} + +void HELPER(sve_rev_p)(void *vd, void *vn, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + int esz = extract32(pred_desc, SIMD_DATA_SHIFT, 2); + intptr_t i, oprsz_2 = oprsz / 2; + + if (oprsz <= 8) { + uint64_t l = *(uint64_t *)vn; + l = reverse_bits_64(l << (64 - 8 * oprsz), esz); + *(uint64_t *)vd = l; + } else if ((oprsz & 15) == 0) { + for (i = 0; i < oprsz_2; i += 8) { + intptr_t ih = oprsz - 8 - i; + uint64_t l = reverse_bits_64(*(uint64_t *)(vn + i), esz); + uint64_t h = reverse_bits_64(*(uint64_t *)(vn + ih), esz); + *(uint64_t *)(vd + i) = h; + *(uint64_t *)(vd + ih) = l; + } + } else { + for (i = 0; i < oprsz_2; i += 1) { + intptr_t il = H1(i); + intptr_t ih = H1(oprsz - 1 - i); + uint8_t l = reverse_bits_8(*(uint8_t *)(vn + il), esz); + uint8_t h = reverse_bits_8(*(uint8_t *)(vn + ih), esz); + *(uint8_t *)(vd + il) = h; + *(uint8_t *)(vd + ih) = l; + } + } +} + +void HELPER(sve_punpk_p)(void *vd, void *vn, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t high = extract32(pred_desc, SIMD_DATA_SHIFT + 2, 1); + uint64_t *d = vd; + intptr_t i; + + if (oprsz <= 8) { + uint64_t nn = *(uint64_t *)vn; + int half = 4 * oprsz; + + nn = extract64(nn, high * half, half); + nn = expand_bits(nn, 0); + d[0] = nn; + } else { + ARMPredicateReg tmp_n; + + /* We produce output faster than we consume input. + Therefore we must be mindful of possible overlap. */ + if ((vn - vd) < (uintptr_t)oprsz) { + vn = memcpy(&tmp_n, vn, oprsz); + } + if (high) { + high = oprsz >> 1; + } + + if ((high & 3) == 0) { + uint32_t *n = vn; + high >>= 2; + + for (i = 0; i < DIV_ROUND_UP(oprsz, 8); i++) { + uint64_t nn = n[H4(high + i)]; + d[i] = expand_bits(nn, 0); + } + } else { + uint16_t *d16 = vd; + uint8_t *n = vn; + + for (i = 0; i < oprsz / 2; i++) { + uint16_t nn = n[H1(high + i)]; + d16[H2(i)] = expand_bits(nn, 0); + } + } + } +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_UNPK(DisasContext *s, arg_UNPK *a, uint32_t insn) return true; } +/* + *** SVE Permute - Predicates Group + */ + +static bool do_perm_pred3(DisasContext *s, arg_rrr_esz *a, bool high_odd, + gen_helper_gvec_3 *fn) +{ + if (!sve_access_check(s)) { + return true; + } + + unsigned vsz = pred_full_reg_size(s); + + /* Predicate sizes may be smaller and cannot use simd_desc. + We cannot round up, as we do elsewhere, because we need + the exact size for ZIP2 and REV. We retain the style for + the other helpers for consistency. */ + TCGv_ptr t_d = tcg_temp_new_ptr(); + TCGv_ptr t_n = tcg_temp_new_ptr(); + TCGv_ptr t_m = tcg_temp_new_ptr(); + TCGv_i32 t_desc; + int desc; + + desc = vsz - 2; + desc = deposit32(desc, SIMD_DATA_SHIFT, 2, a->esz); + desc = deposit32(desc, SIMD_DATA_SHIFT + 2, 2, high_odd); + + tcg_gen_addi_ptr(t_d, cpu_env, pred_full_reg_offset(s, a->rd)); + tcg_gen_addi_ptr(t_n, cpu_env, pred_full_reg_offset(s, a->rn)); + tcg_gen_addi_ptr(t_m, cpu_env, pred_full_reg_offset(s, a->rm)); + t_desc = tcg_const_i32(desc); + + fn(t_d, t_n, t_m, t_desc); + + tcg_temp_free_ptr(t_d); + tcg_temp_free_ptr(t_n); + tcg_temp_free_ptr(t_m); + tcg_temp_free_i32(t_desc); + return true; +} + +static bool do_perm_pred2(DisasContext *s, arg_rr_esz *a, bool high_odd, + gen_helper_gvec_2 *fn) +{ + if (!sve_access_check(s)) { + return true; + } + + unsigned vsz = pred_full_reg_size(s); + TCGv_ptr t_d = tcg_temp_new_ptr(); + TCGv_ptr t_n = tcg_temp_new_ptr(); + TCGv_i32 t_desc; + int desc; + + tcg_gen_addi_ptr(t_d, cpu_env, pred_full_reg_offset(s, a->rd)); + tcg_gen_addi_ptr(t_n, cpu_env, pred_full_reg_offset(s, a->rn)); + + /* Predicate sizes may be smaller and cannot use simd_desc. + We cannot round up, as we do elsewhere, because we need + the exact size for ZIP2 and REV. We retain the style for + the other helpers for consistency. */ + + desc = vsz - 2; + desc = deposit32(desc, SIMD_DATA_SHIFT, 2, a->esz); + desc = deposit32(desc, SIMD_DATA_SHIFT + 2, 2, high_odd); + t_desc = tcg_const_i32(desc); + + fn(t_d, t_n, t_desc); + + tcg_temp_free_i32(t_desc); + tcg_temp_free_ptr(t_d); + tcg_temp_free_ptr(t_n); + return true; +} + +static bool trans_ZIP1_p(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + return do_perm_pred3(s, a, 0, gen_helper_sve_zip_p); +} + +static bool trans_ZIP2_p(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + return do_perm_pred3(s, a, 1, gen_helper_sve_zip_p); +} + +static bool trans_UZP1_p(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + return do_perm_pred3(s, a, 0, gen_helper_sve_uzp_p); +} + +static bool trans_UZP2_p(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + return do_perm_pred3(s, a, 1, gen_helper_sve_uzp_p); +} + +static bool trans_TRN1_p(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + return do_perm_pred3(s, a, 0, gen_helper_sve_trn_p); +} + +static bool trans_TRN2_p(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + return do_perm_pred3(s, a, 1, gen_helper_sve_trn_p); +} + +static bool trans_REV_p(DisasContext *s, arg_rr_esz *a, uint32_t insn) +{ + return do_perm_pred2(s, a, 0, gen_helper_sve_rev_p); +} + +static bool trans_PUNPKLO(DisasContext *s, arg_PUNPKLO *a, uint32_t insn) +{ + return do_perm_pred2(s, a, 0, gen_helper_sve_punpk_p); +} + +static bool trans_PUNPKHI(DisasContext *s, arg_PUNPKHI *a, uint32_t insn) +{ + return do_perm_pred2(s, a, 1, gen_helper_sve_punpk_p); +} + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ # Three operand, vector element size @rd_rn_rm ........ esz:2 . rm:5 ... ... rn:5 rd:5 &rrr_esz +@pd_pn_pm ........ esz:2 .. rm:4 ....... rn:4 . rd:4 &rrr_esz @rdn_rm ........ esz:2 ...... ...... rm:5 rd:5 \ &rrr_esz rn=%reg_movprfx @@ -XXX,XX +XXX,XX @@ TBL 00000101 .. 1 ..... 001100 ..... ..... @rd_rn_rm # SVE unpack vector elements UNPK 00000101 esz:2 1100 u:1 h:1 001110 rn:5 rd:5 +### SVE Permute - Predicates Group + +# SVE permute predicate elements +ZIP1_p 00000101 .. 10 .... 010 000 0 .... 0 .... @pd_pn_pm +ZIP2_p 00000101 .. 10 .... 010 001 0 .... 0 .... @pd_pn_pm +UZP1_p 00000101 .. 10 .... 010 010 0 .... 0 .... @pd_pn_pm +UZP2_p 00000101 .. 10 .... 010 011 0 .... 0 .... @pd_pn_pm +TRN1_p 00000101 .. 10 .... 010 100 0 .... 0 .... @pd_pn_pm +TRN2_p 00000101 .. 10 .... 010 101 0 .... 0 .... @pd_pn_pm + +# SVE reverse predicate elements +REV_p 00000101 .. 11 0100 010 000 0 .... 0 .... @pd_pn + +# SVE unpack predicate elements +PUNPKLO 00000101 00 11 0000 010 000 0 .... 0 .... @pd_pn_e0 +PUNPKHI 00000101 00 11 0001 010 000 0 .... 0 .... @pd_pn_e0 + ### SVE Predicate Logical Operations Group # SVE predicate logical operations -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 15 ++++++++ target/arm/sve_helper.c | 72 ++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 75 ++++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 10 +++++ 4 files changed, 172 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_trn_p, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_rev_p, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_punpk_p, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_zip_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_zip_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_zip_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_zip_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_uzp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_uzp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_uzp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_uzp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_trn_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_trn_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_trn_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_trn_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_and_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_bic_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_eor_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_punpk_p)(void *vd, void *vn, uint32_t pred_desc) } } } + +#define DO_ZIP(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t oprsz = simd_oprsz(desc); \ + intptr_t i, oprsz_2 = oprsz / 2; \ + ARMVectorReg tmp_n, tmp_m; \ + /* We produce output faster than we consume input. \ + Therefore we must be mindful of possible overlap. */ \ + if (unlikely((vn - vd) < (uintptr_t)oprsz)) { \ + vn = memcpy(&tmp_n, vn, oprsz_2); \ + } \ + if (unlikely((vm - vd) < (uintptr_t)oprsz)) { \ + vm = memcpy(&tmp_m, vm, oprsz_2); \ + } \ + for (i = 0; i < oprsz_2; i += sizeof(TYPE)) { \ + *(TYPE *)(vd + H(2 * i + 0)) = *(TYPE *)(vn + H(i)); \ + *(TYPE *)(vd + H(2 * i + sizeof(TYPE))) = *(TYPE *)(vm + H(i)); \ + } \ +} + +DO_ZIP(sve_zip_b, uint8_t, H1) +DO_ZIP(sve_zip_h, uint16_t, H1_2) +DO_ZIP(sve_zip_s, uint32_t, H1_4) +DO_ZIP(sve_zip_d, uint64_t, ) + +#define DO_UZP(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t oprsz = simd_oprsz(desc); \ + intptr_t oprsz_2 = oprsz / 2; \ + intptr_t odd_ofs = simd_data(desc); \ + intptr_t i; \ + ARMVectorReg tmp_m; \ + if (unlikely((vm - vd) < (uintptr_t)oprsz)) { \ + vm = memcpy(&tmp_m, vm, oprsz); \ + } \ + for (i = 0; i < oprsz_2; i += sizeof(TYPE)) { \ + *(TYPE *)(vd + H(i)) = *(TYPE *)(vn + H(2 * i + odd_ofs)); \ + } \ + for (i = 0; i < oprsz_2; i += sizeof(TYPE)) { \ + *(TYPE *)(vd + H(oprsz_2 + i)) = *(TYPE *)(vm + H(2 * i + odd_ofs)); \ + } \ +} + +DO_UZP(sve_uzp_b, uint8_t, H1) +DO_UZP(sve_uzp_h, uint16_t, H1_2) +DO_UZP(sve_uzp_s, uint32_t, H1_4) +DO_UZP(sve_uzp_d, uint64_t, ) + +#define DO_TRN(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t oprsz = simd_oprsz(desc); \ + intptr_t odd_ofs = simd_data(desc); \ + intptr_t i; \ + for (i = 0; i < oprsz; i += 2 * sizeof(TYPE)) { \ + TYPE ae = *(TYPE *)(vn + H(i + odd_ofs)); \ + TYPE be = *(TYPE *)(vm + H(i + odd_ofs)); \ + *(TYPE *)(vd + H(i + 0)) = ae; \ + *(TYPE *)(vd + H(i + sizeof(TYPE))) = be; \ + } \ +} + +DO_TRN(sve_trn_b, uint8_t, H1) +DO_TRN(sve_trn_h, uint16_t, H1_2) +DO_TRN(sve_trn_s, uint32_t, H1_4) +DO_TRN(sve_trn_d, uint64_t, ) + +#undef DO_ZIP +#undef DO_UZP +#undef DO_TRN diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_PUNPKHI(DisasContext *s, arg_PUNPKHI *a, uint32_t insn) return do_perm_pred2(s, a, 1, gen_helper_sve_punpk_p); } +/* + *** SVE Permute - Interleaving Group + */ + +static bool do_zip(DisasContext *s, arg_rrr_esz *a, bool high) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve_zip_b, gen_helper_sve_zip_h, + gen_helper_sve_zip_s, gen_helper_sve_zip_d, + }; + + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + unsigned high_ofs = high ? vsz / 2 : 0; + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn) + high_ofs, + vec_full_reg_offset(s, a->rm) + high_ofs, + vsz, vsz, 0, fns[a->esz]); + } + return true; +} + +static bool do_zzz_data_ool(DisasContext *s, arg_rrr_esz *a, int data, + gen_helper_gvec_3 *fn) +{ + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vsz, vsz, data, fn); + } + return true; +} + +static bool trans_ZIP1_z(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + return do_zip(s, a, false); +} + +static bool trans_ZIP2_z(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + return do_zip(s, a, true); +} + +static gen_helper_gvec_3 * const uzp_fns[4] = { + gen_helper_sve_uzp_b, gen_helper_sve_uzp_h, + gen_helper_sve_uzp_s, gen_helper_sve_uzp_d, +}; + +static bool trans_UZP1_z(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + return do_zzz_data_ool(s, a, 0, uzp_fns[a->esz]); +} + +static bool trans_UZP2_z(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + return do_zzz_data_ool(s, a, 1 << a->esz, uzp_fns[a->esz]); +} + +static gen_helper_gvec_3 * const trn_fns[4] = { + gen_helper_sve_trn_b, gen_helper_sve_trn_h, + gen_helper_sve_trn_s, gen_helper_sve_trn_d, +}; + +static bool trans_TRN1_z(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + return do_zzz_data_ool(s, a, 0, trn_fns[a->esz]); +} + +static bool trans_TRN2_z(DisasContext *s, arg_rrr_esz *a, uint32_t insn) +{ + return do_zzz_data_ool(s, a, 1 << a->esz, trn_fns[a->esz]); +} + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ REV_p 00000101 .. 11 0100 010 000 0 .... 0 .... @pd_pn PUNPKLO 00000101 00 11 0000 010 000 0 .... 0 .... @pd_pn_e0 PUNPKHI 00000101 00 11 0001 010 000 0 .... 0 .... @pd_pn_e0 +### SVE Permute - Interleaving Group + +# SVE permute vector elements +ZIP1_z 00000101 .. 1 ..... 011 000 ..... ..... @rd_rn_rm +ZIP2_z 00000101 .. 1 ..... 011 001 ..... ..... @rd_rn_rm +UZP1_z 00000101 .. 1 ..... 011 010 ..... ..... @rd_rn_rm +UZP2_z 00000101 .. 1 ..... 011 011 ..... ..... @rd_rn_rm +TRN1_z 00000101 .. 1 ..... 011 100 ..... ..... @rd_rn_rm +TRN2_z 00000101 .. 1 ..... 011 101 ..... ..... @rd_rn_rm + ### SVE Predicate Logical Operations Group # SVE predicate logical operations -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 3 +++ target/arm/sve_helper.c | 34 ++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 12 ++++++++++++ target/arm/sve.decode | 6 ++++++ 4 files changed, 55 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_trn_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_trn_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_trn_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_compact_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_compact_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_and_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_bic_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_eor_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_TRN(sve_trn_d, uint64_t, ) #undef DO_ZIP #undef DO_UZP #undef DO_TRN + +void HELPER(sve_compact_s)(void *vd, void *vn, void *vg, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc) / 4; + uint32_t *d = vd, *n = vn; + uint8_t *pg = vg; + + for (i = j = 0; i < opr_sz; i++) { + if (pg[H1(i / 2)] & (i & 1 ? 0x10 : 0x01)) { + d[H4(j)] = n[H4(i)]; + j++; + } + } + for (; j < opr_sz; j++) { + d[H4(j)] = 0; + } +} + +void HELPER(sve_compact_d)(void *vd, void *vn, void *vg, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn; + uint8_t *pg = vg; + + for (i = j = 0; i < opr_sz; i++) { + if (pg[H1(i)] & 1) { + d[j] = n[i]; + j++; + } + } + for (; j < opr_sz; j++) { + d[j] = 0; + } +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_TRN2_z(DisasContext *s, arg_rrr_esz *a, uint32_t insn) return do_zzz_data_ool(s, a, 1 << a->esz, trn_fns[a->esz]); } +/* + *** SVE Permute Vector - Predicated Group + */ + +static bool trans_COMPACT(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + static gen_helper_gvec_3 * const fns[4] = { + NULL, NULL, gen_helper_sve_compact_s, gen_helper_sve_compact_d + }; + return do_zpz_ool(s, a, fns[a->esz]); +} + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UZP2_z 00000101 .. 1 ..... 011 011 ..... ..... @rd_rn_rm TRN1_z 00000101 .. 1 ..... 011 100 ..... ..... @rd_rn_rm TRN2_z 00000101 .. 1 ..... 011 101 ..... ..... @rd_rn_rm +### SVE Permute - Predicated Group + +# SVE compress active elements +# Note esz >= 2 +COMPACT 00000101 .. 100001 100 ... ..... ..... @rd_pg_rn + ### SVE Predicate Logical Operations Group # SVE predicate logical operations -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 2 + target/arm/sve_helper.c | 12 ++ target/arm/translate-sve.c | 328 +++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 20 +++ 4 files changed, 362 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_trn_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_compact_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_compact_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_2(sve_last_active_element, TCG_CALL_NO_RWG, s32, ptr, i32) + DEF_HELPER_FLAGS_5(sve_and_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_bic_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_eor_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_compact_d)(void *vd, void *vn, void *vg, uint32_t desc) d[j] = 0; } } + +/* Similar to the ARM LastActiveElement pseudocode function, except the + * result is multiplied by the element size. This includes the not found + * indication; e.g. not found for esz=3 is -8. + */ +int32_t HELPER(sve_last_active_element)(void *vg, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t esz = extract32(pred_desc, SIMD_DATA_SHIFT, 2); + + return last_active_element(vg, DIV_ROUND_UP(oprsz, 8), esz); +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_COMPACT(DisasContext *s, arg_rpr_esz *a, uint32_t insn) return do_zpz_ool(s, a, fns[a->esz]); } +/* Call the helper that computes the ARM LastActiveElement pseudocode + * function, scaled by the element size. This includes the not found + * indication; e.g. not found for esz=3 is -8. + */ +static void find_last_active(DisasContext *s, TCGv_i32 ret, int esz, int pg) +{ + /* Predicate sizes may be smaller and cannot use simd_desc. We cannot + * round up, as we do elsewhere, because we need the exact size. + */ + TCGv_ptr t_p = tcg_temp_new_ptr(); + TCGv_i32 t_desc; + unsigned vsz = pred_full_reg_size(s); + unsigned desc; + + desc = vsz - 2; + desc = deposit32(desc, SIMD_DATA_SHIFT, 2, esz); + + tcg_gen_addi_ptr(t_p, cpu_env, pred_full_reg_offset(s, pg)); + t_desc = tcg_const_i32(desc); + + gen_helper_sve_last_active_element(ret, t_p, t_desc); + + tcg_temp_free_i32(t_desc); + tcg_temp_free_ptr(t_p); +} + +/* Increment LAST to the offset of the next element in the vector, + * wrapping around to 0. + */ +static void incr_last_active(DisasContext *s, TCGv_i32 last, int esz) +{ + unsigned vsz = vec_full_reg_size(s); + + tcg_gen_addi_i32(last, last, 1 << esz); + if (is_power_of_2(vsz)) { + tcg_gen_andi_i32(last, last, vsz - 1); + } else { + TCGv_i32 max = tcg_const_i32(vsz); + TCGv_i32 zero = tcg_const_i32(0); + tcg_gen_movcond_i32(TCG_COND_GEU, last, last, max, zero, last); + tcg_temp_free_i32(max); + tcg_temp_free_i32(zero); + } +} + +/* If LAST < 0, set LAST to the offset of the last element in the vector. */ +static void wrap_last_active(DisasContext *s, TCGv_i32 last, int esz) +{ + unsigned vsz = vec_full_reg_size(s); + + if (is_power_of_2(vsz)) { + tcg_gen_andi_i32(last, last, vsz - 1); + } else { + TCGv_i32 max = tcg_const_i32(vsz - (1 << esz)); + TCGv_i32 zero = tcg_const_i32(0); + tcg_gen_movcond_i32(TCG_COND_LT, last, last, zero, max, last); + tcg_temp_free_i32(max); + tcg_temp_free_i32(zero); + } +} + +/* Load an unsigned element of ESZ from BASE+OFS. */ +static TCGv_i64 load_esz(TCGv_ptr base, int ofs, int esz) +{ + TCGv_i64 r = tcg_temp_new_i64(); + + switch (esz) { + case 0: + tcg_gen_ld8u_i64(r, base, ofs); + break; + case 1: + tcg_gen_ld16u_i64(r, base, ofs); + break; + case 2: + tcg_gen_ld32u_i64(r, base, ofs); + break; + case 3: + tcg_gen_ld_i64(r, base, ofs); + break; + default: + g_assert_not_reached(); + } + return r; +} + +/* Load an unsigned element of ESZ from RM[LAST]. */ +static TCGv_i64 load_last_active(DisasContext *s, TCGv_i32 last, + int rm, int esz) +{ + TCGv_ptr p = tcg_temp_new_ptr(); + TCGv_i64 r; + + /* Convert offset into vector into offset into ENV. + * The final adjustment for the vector register base + * is added via constant offset to the load. + */ +#ifdef HOST_WORDS_BIGENDIAN + /* Adjust for element ordering. See vec_reg_offset. */ + if (esz < 3) { + tcg_gen_xori_i32(last, last, 8 - (1 << esz)); + } +#endif + tcg_gen_ext_i32_ptr(p, last); + tcg_gen_add_ptr(p, p, cpu_env); + + r = load_esz(p, vec_full_reg_offset(s, rm), esz); + tcg_temp_free_ptr(p); + + return r; +} + +/* Compute CLAST for a Zreg. */ +static bool do_clast_vector(DisasContext *s, arg_rprr_esz *a, bool before) +{ + TCGv_i32 last; + TCGLabel *over; + TCGv_i64 ele; + unsigned vsz, esz = a->esz; + + if (!sve_access_check(s)) { + return true; + } + + last = tcg_temp_local_new_i32(); + over = gen_new_label(); + + find_last_active(s, last, esz, a->pg); + + /* There is of course no movcond for a 2048-bit vector, + * so we must branch over the actual store. + */ + tcg_gen_brcondi_i32(TCG_COND_LT, last, 0, over); + + if (!before) { + incr_last_active(s, last, esz); + } + + ele = load_last_active(s, last, a->rm, esz); + tcg_temp_free_i32(last); + + vsz = vec_full_reg_size(s); + tcg_gen_gvec_dup_i64(esz, vec_full_reg_offset(s, a->rd), vsz, vsz, ele); + tcg_temp_free_i64(ele); + + /* If this insn used MOVPRFX, we may need a second move. */ + if (a->rd != a->rn) { + TCGLabel *done = gen_new_label(); + tcg_gen_br(done); + + gen_set_label(over); + do_mov_z(s, a->rd, a->rn); + + gen_set_label(done); + } else { + gen_set_label(over); + } + return true; +} + +static bool trans_CLASTA_z(DisasContext *s, arg_rprr_esz *a, uint32_t insn) +{ + return do_clast_vector(s, a, false); +} + +static bool trans_CLASTB_z(DisasContext *s, arg_rprr_esz *a, uint32_t insn) +{ + return do_clast_vector(s, a, true); +} + +/* Compute CLAST for a scalar. */ +static void do_clast_scalar(DisasContext *s, int esz, int pg, int rm, + bool before, TCGv_i64 reg_val) +{ + TCGv_i32 last = tcg_temp_new_i32(); + TCGv_i64 ele, cmp, zero; + + find_last_active(s, last, esz, pg); + + /* Extend the original value of last prior to incrementing. */ + cmp = tcg_temp_new_i64(); + tcg_gen_ext_i32_i64(cmp, last); + + if (!before) { + incr_last_active(s, last, esz); + } + + /* The conceit here is that while last < 0 indicates not found, after + * adjusting for cpu_env->vfp.zregs[rm], it is still a valid address + * from which we can load garbage. We then discard the garbage with + * a conditional move. + */ + ele = load_last_active(s, last, rm, esz); + tcg_temp_free_i32(last); + + zero = tcg_const_i64(0); + tcg_gen_movcond_i64(TCG_COND_GE, reg_val, cmp, zero, ele, reg_val); + + tcg_temp_free_i64(zero); + tcg_temp_free_i64(cmp); + tcg_temp_free_i64(ele); +} + +/* Compute CLAST for a Vreg. */ +static bool do_clast_fp(DisasContext *s, arg_rpr_esz *a, bool before) +{ + if (sve_access_check(s)) { + int esz = a->esz; + int ofs = vec_reg_offset(s, a->rd, 0, esz); + TCGv_i64 reg = load_esz(cpu_env, ofs, esz); + + do_clast_scalar(s, esz, a->pg, a->rn, before, reg); + write_fp_dreg(s, a->rd, reg); + tcg_temp_free_i64(reg); + } + return true; +} + +static bool trans_CLASTA_v(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_clast_fp(s, a, false); +} + +static bool trans_CLASTB_v(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_clast_fp(s, a, true); +} + +/* Compute CLAST for a Xreg. */ +static bool do_clast_general(DisasContext *s, arg_rpr_esz *a, bool before) +{ + TCGv_i64 reg; + + if (!sve_access_check(s)) { + return true; + } + + reg = cpu_reg(s, a->rd); + switch (a->esz) { + case 0: + tcg_gen_ext8u_i64(reg, reg); + break; + case 1: + tcg_gen_ext16u_i64(reg, reg); + break; + case 2: + tcg_gen_ext32u_i64(reg, reg); + break; + case 3: + break; + default: + g_assert_not_reached(); + } + + do_clast_scalar(s, a->esz, a->pg, a->rn, before, reg); + return true; +} + +static bool trans_CLASTA_r(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_clast_general(s, a, false); +} + +static bool trans_CLASTB_r(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_clast_general(s, a, true); +} + +/* Compute LAST for a scalar. */ +static TCGv_i64 do_last_scalar(DisasContext *s, int esz, + int pg, int rm, bool before) +{ + TCGv_i32 last = tcg_temp_new_i32(); + TCGv_i64 ret; + + find_last_active(s, last, esz, pg); + if (before) { + wrap_last_active(s, last, esz); + } else { + incr_last_active(s, last, esz); + } + + ret = load_last_active(s, last, rm, esz); + tcg_temp_free_i32(last); + return ret; +} + +/* Compute LAST for a Vreg. */ +static bool do_last_fp(DisasContext *s, arg_rpr_esz *a, bool before) +{ + if (sve_access_check(s)) { + TCGv_i64 val = do_last_scalar(s, a->esz, a->pg, a->rn, before); + write_fp_dreg(s, a->rd, val); + tcg_temp_free_i64(val); + } + return true; +} + +static bool trans_LASTA_v(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_last_fp(s, a, false); +} + +static bool trans_LASTB_v(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_last_fp(s, a, true); +} + +/* Compute LAST for a Xreg. */ +static bool do_last_general(DisasContext *s, arg_rpr_esz *a, bool before) +{ + if (sve_access_check(s)) { + TCGv_i64 val = do_last_scalar(s, a->esz, a->pg, a->rn, before); + tcg_gen_mov_i64(cpu_reg(s, a->rd), val); + tcg_temp_free_i64(val); + } + return true; +} + +static bool trans_LASTA_r(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_last_general(s, a, false); +} + +static bool trans_LASTB_r(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_last_general(s, a, true); +} + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ TRN2_z 00000101 .. 1 ..... 011 101 ..... ..... @rd_rn_rm # Note esz >= 2 COMPACT 00000101 .. 100001 100 ... ..... ..... @rd_pg_rn +# SVE conditionally broadcast element to vector +CLASTA_z 00000101 .. 10100 0 100 ... ..... ..... @rdn_pg_rm +CLASTB_z 00000101 .. 10100 1 100 ... ..... ..... @rdn_pg_rm + +# SVE conditionally copy element to SIMD&FP scalar +CLASTA_v 00000101 .. 10101 0 100 ... ..... ..... @rd_pg_rn +CLASTB_v 00000101 .. 10101 1 100 ... ..... ..... @rd_pg_rn + +# SVE conditionally copy element to general register +CLASTA_r 00000101 .. 11000 0 101 ... ..... ..... @rd_pg_rn +CLASTB_r 00000101 .. 11000 1 101 ... ..... ..... @rd_pg_rn + +# SVE copy element to SIMD&FP scalar register +LASTA_v 00000101 .. 10001 0 100 ... ..... ..... @rd_pg_rn +LASTB_v 00000101 .. 10001 1 100 ... ..... ..... @rd_pg_rn + +# SVE copy element to general register +LASTA_r 00000101 .. 10000 0 101 ... ..... ..... @rd_pg_rn +LASTB_r 00000101 .. 10000 1 101 ... ..... ..... @rd_pg_rn + ### SVE Predicate Logical Operations Group # SVE predicate logical operations -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 19 +++++++++++++++++++ target/arm/sve.decode | 6 ++++++ 2 files changed, 25 insertions(+) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LASTB_r(DisasContext *s, arg_rpr_esz *a, uint32_t insn) return do_last_general(s, a, true); } +static bool trans_CPY_m_r(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + if (sve_access_check(s)) { + do_cpy_m(s, a->esz, a->rd, a->rd, a->pg, cpu_reg_sp(s, a->rn)); + } + return true; +} + +static bool trans_CPY_m_v(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + if (sve_access_check(s)) { + int ofs = vec_reg_offset(s, a->rn, 0, a->esz); + TCGv_i64 t = load_esz(cpu_env, ofs, a->esz); + do_cpy_m(s, a->esz, a->rd, a->rd, a->pg, t); + tcg_temp_free_i64(t); + } + return true; +} + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ LASTB_v 00000101 .. 10001 1 100 ... ..... ..... @rd_pg_rn LASTA_r 00000101 .. 10000 0 101 ... ..... ..... @rd_pg_rn LASTB_r 00000101 .. 10000 1 101 ... ..... ..... @rd_pg_rn +# SVE copy element from SIMD&FP scalar register +CPY_m_v 00000101 .. 100000 100 ... ..... ..... @rd_pg_rn + +# SVE copy element from general register to vector (predicated) +CPY_m_r 00000101 .. 101000 101 ... ..... ..... @rd_pg_rn + ### SVE Predicate Logical Operations Group # SVE predicate logical operations -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 14 +++++++++++++ target/arm/sve_helper.c | 41 +++++++++++++++++++++++++++++++------- target/arm/translate-sve.c | 38 +++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 7 +++++++ 4 files changed, 93 insertions(+), 7 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_compact_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_2(sve_last_active_element, TCG_CALL_NO_RWG, s32, ptr, i32) +DEF_HELPER_FLAGS_4(sve_revb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_revb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_revb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_revh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_revh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_revw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_rbit_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_rbit_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_rbit_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_rbit_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_and_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_bic_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_eor_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint64_t expand_pred_s(uint8_t byte) return word[byte & 0x11]; } +/* Swap 16-bit words within a 32-bit word. */ +static inline uint32_t hswap32(uint32_t h) +{ + return rol32(h, 16); +} + +/* Swap 16-bit words within a 64-bit word. */ +static inline uint64_t hswap64(uint64_t h) +{ + uint64_t m = 0x0000ffff0000ffffull; + h = rol64(h, 32); + return ((h & m) << 16) | ((h >> 16) & m); +} + +/* Swap 32-bit words within a 64-bit word. */ +static inline uint64_t wswap64(uint64_t h) +{ + return rol64(h, 32); +} + #define LOGICAL_PPPP(NAME, FUNC) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \ { \ @@ -XXX,XX +XXX,XX @@ DO_ZPZ(sve_neg_h, uint16_t, H1_2, DO_NEG) DO_ZPZ(sve_neg_s, uint32_t, H1_4, DO_NEG) DO_ZPZ_D(sve_neg_d, uint64_t, DO_NEG) +DO_ZPZ(sve_revb_h, uint16_t, H1_2, bswap16) +DO_ZPZ(sve_revb_s, uint32_t, H1_4, bswap32) +DO_ZPZ_D(sve_revb_d, uint64_t, bswap64) + +DO_ZPZ(sve_revh_s, uint32_t, H1_4, hswap32) +DO_ZPZ_D(sve_revh_d, uint64_t, hswap64) + +DO_ZPZ_D(sve_revw_d, uint64_t, wswap64) + +DO_ZPZ(sve_rbit_b, uint8_t, H1, revbit8) +DO_ZPZ(sve_rbit_h, uint16_t, H1_2, revbit16) +DO_ZPZ(sve_rbit_s, uint32_t, H1_4, revbit32) +DO_ZPZ_D(sve_rbit_d, uint64_t, revbit64) + /* Three-operand expander, unpredicated, in which the third operand is "wide". */ #define DO_ZZW(NAME, TYPE, TYPEW, H, OP) \ @@ -XXX,XX +XXX,XX @@ void HELPER(sve_rev_b)(void *vd, void *vn, uint32_t desc) } } -static inline uint64_t hswap64(uint64_t h) -{ - uint64_t m = 0x0000ffff0000ffffull; - h = rol64(h, 32); - return ((h & m) << 16) | ((h >> 16) & m); -} - void HELPER(sve_rev_h)(void *vd, void *vn, uint32_t desc) { intptr_t i, j, opr_sz = simd_oprsz(desc); diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_CPY_m_v(DisasContext *s, arg_rpr_esz *a, uint32_t insn) return true; } +static bool trans_REVB(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + static gen_helper_gvec_3 * const fns[4] = { + NULL, + gen_helper_sve_revb_h, + gen_helper_sve_revb_s, + gen_helper_sve_revb_d, + }; + return do_zpz_ool(s, a, fns[a->esz]); +} + +static bool trans_REVH(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + static gen_helper_gvec_3 * const fns[4] = { + NULL, + NULL, + gen_helper_sve_revh_s, + gen_helper_sve_revh_d, + }; + return do_zpz_ool(s, a, fns[a->esz]); +} + +static bool trans_REVW(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ool(s, a, a->esz == 3 ? gen_helper_sve_revw_d : NULL); +} + +static bool trans_RBIT(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve_rbit_b, + gen_helper_sve_rbit_h, + gen_helper_sve_rbit_s, + gen_helper_sve_rbit_d, + }; + return do_zpz_ool(s, a, fns[a->esz]); +} + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ CPY_m_v 00000101 .. 100000 100 ... ..... ..... @rd_pg_rn # SVE copy element from general register to vector (predicated) CPY_m_r 00000101 .. 101000 101 ... ..... ..... @rd_pg_rn +# SVE reverse within elements +# Note esz >= operation size +REVB 00000101 .. 1001 00 100 ... ..... ..... @rd_pg_rn +REVH 00000101 .. 1001 01 100 ... ..... ..... @rd_pg_rn +REVW 00000101 .. 1001 10 100 ... ..... ..... @rd_pg_rn +RBIT 00000101 .. 1001 11 100 ... ..... ..... @rd_pg_rn + ### SVE Predicate Logical Operations Group # SVE predicate logical operations -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 2 ++ target/arm/sve_helper.c | 37 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 13 +++++++++++++ target/arm/sve.decode | 3 +++ 4 files changed, 55 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_rbit_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_rbit_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_rbit_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_splice, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_and_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_bic_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_eor_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ int32_t HELPER(sve_last_active_element)(void *vg, uint32_t pred_desc) return last_active_element(vg, DIV_ROUND_UP(oprsz, 8), esz); } + +void HELPER(sve_splice)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) +{ + intptr_t opr_sz = simd_oprsz(desc) / 8; + int esz = simd_data(desc); + uint64_t pg, first_g, last_g, len, mask = pred_esz_masks[esz]; + intptr_t i, first_i, last_i; + ARMVectorReg tmp; + + first_i = last_i = 0; + first_g = last_g = 0; + + /* Find the extent of the active elements within VG. */ + for (i = QEMU_ALIGN_UP(opr_sz, 8) - 8; i >= 0; i -= 8) { + pg = *(uint64_t *)(vg + i) & mask; + if (pg) { + if (last_g == 0) { + last_g = pg; + last_i = i; + } + first_g = pg; + first_i = i; + } + } + + len = 0; + if (first_g != 0) { + first_i = first_i * 8 + ctz64(first_g); + last_i = last_i * 8 + 63 - clz64(last_g); + len = last_i - first_i + (1 << esz); + if (vd == vm) { + vm = memcpy(&tmp, vm, opr_sz * 8); + } + swap_memmove(vd, vn + first_i, len); + } + swap_memmove(vd + len, vm, opr_sz * 8 - len); +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_RBIT(DisasContext *s, arg_rpr_esz *a, uint32_t insn) return do_zpz_ool(s, a, fns[a->esz]); } +static bool trans_SPLICE(DisasContext *s, arg_rprr_esz *a, uint32_t insn) +{ + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_4_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + pred_full_reg_offset(s, a->pg), + vsz, vsz, a->esz, gen_helper_sve_splice); + } + return true; +} + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ REVH 00000101 .. 1001 01 100 ... ..... ..... @rd_pg_rn REVW 00000101 .. 1001 10 100 ... ..... ..... @rd_pg_rn RBIT 00000101 .. 1001 11 100 ... ..... ..... @rd_pg_rn +# SVE vector splice (predicated) +SPLICE 00000101 .. 101 100 100 ... ..... ..... @rdn_pg_rm + ### SVE Predicate Logical Operations Group # SVE predicate logical operations -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 9 +++++++ target/arm/sve_helper.c | 55 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 2 ++ target/arm/sve.decode | 6 +++++ 4 files changed, 72 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_lsl_zpzz_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve_lsl_zpzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_sel_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_sel_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_sel_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_sel_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_asr_zpzw_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_asr_zpzw_h, TCG_CALL_NO_RWG, diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_splice)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) } swap_memmove(vd + len, vm, opr_sz * 8 - len); } + +void HELPER(sve_sel_zpzz_b)(void *vd, void *vn, void *vm, + void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn, *m = vm; + uint8_t *pg = vg; + + for (i = 0; i < opr_sz; i += 1) { + uint64_t nn = n[i], mm = m[i]; + uint64_t pp = expand_pred_b(pg[H1(i)]); + d[i] = (nn & pp) | (mm & ~pp); + } +} + +void HELPER(sve_sel_zpzz_h)(void *vd, void *vn, void *vm, + void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn, *m = vm; + uint8_t *pg = vg; + + for (i = 0; i < opr_sz; i += 1) { + uint64_t nn = n[i], mm = m[i]; + uint64_t pp = expand_pred_h(pg[H1(i)]); + d[i] = (nn & pp) | (mm & ~pp); + } +} + +void HELPER(sve_sel_zpzz_s)(void *vd, void *vn, void *vm, + void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn, *m = vm; + uint8_t *pg = vg; + + for (i = 0; i < opr_sz; i += 1) { + uint64_t nn = n[i], mm = m[i]; + uint64_t pp = expand_pred_s(pg[H1(i)]); + d[i] = (nn & pp) | (mm & ~pp); + } +} + +void HELPER(sve_sel_zpzz_d)(void *vd, void *vn, void *vm, + void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn, *m = vm; + uint8_t *pg = vg; + + for (i = 0; i < opr_sz; i += 1) { + uint64_t nn = n[i], mm = m[i]; + d[i] = (pg[H1(i)] & 1 ? nn : mm); + } +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_UDIV_zpzz(DisasContext *s, arg_rprr_esz *a, uint32_t insn) return do_zpzz_ool(s, a, fns[a->esz]); } +DO_ZPZZ(SEL, sel) + #undef DO_ZPZZ /* diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ &rprr_esz rn=%reg_movprfx @rdm_pg_rn ........ esz:2 ... ... ... pg:3 rn:5 rd:5 \ &rprr_esz rm=%reg_movprfx +@rd_pg4_rn_rm ........ esz:2 . rm:5 .. pg:4 rn:5 rd:5 &rprr_esz # Three register operand, with governing predicate, vector element size @rda_pg_rn_rm ........ esz:2 . rm:5 ... pg:3 rn:5 rd:5 \ @@ -XXX,XX +XXX,XX @@ RBIT 00000101 .. 1001 11 100 ... ..... ..... @rd_pg_rn # SVE vector splice (predicated) SPLICE 00000101 .. 101 100 100 ... ..... ..... @rdn_pg_rm +### SVE Select Vectors Group + +# SVE select vector elements (predicated) +SEL_zpzz 00000101 .. 1 ..... 11 .... ..... ..... @rd_pg4_rn_rm + ### SVE Predicate Logical Operations Group # SVE predicate logical operations -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 115 +++++++++++++++++++++++ target/arm/sve_helper.c | 187 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 91 ++++++++++++++++++ target/arm/sve.decode | 24 +++++ 4 files changed, 417 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_rbit_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_splice, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpeq_ppzz_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpne_ppzz_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpge_ppzz_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpgt_ppzz_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmphi_ppzz_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmphs_ppzz_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_cmpeq_ppzz_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpne_ppzz_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpge_ppzz_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpgt_ppzz_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmphi_ppzz_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmphs_ppzz_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_cmpeq_ppzz_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpne_ppzz_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpge_ppzz_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpgt_ppzz_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmphi_ppzz_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmphs_ppzz_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_cmpeq_ppzz_d, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpne_ppzz_d, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpge_ppzz_d, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpgt_ppzz_d, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmphi_ppzz_d, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmphs_ppzz_d, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_cmpeq_ppzw_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpne_ppzw_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpge_ppzw_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpgt_ppzw_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmphi_ppzw_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmphs_ppzw_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmple_ppzw_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmplt_ppzw_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmplo_ppzw_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpls_ppzw_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_cmpeq_ppzw_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpne_ppzw_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpge_ppzw_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpgt_ppzw_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmphi_ppzw_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmphs_ppzw_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmple_ppzw_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmplt_ppzw_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmplo_ppzw_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpls_ppzw_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_cmpeq_ppzw_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpne_ppzw_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpge_ppzw_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpgt_ppzw_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmphi_ppzw_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmphs_ppzw_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmple_ppzw_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmplt_ppzw_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmplo_ppzw_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_cmpls_ppzw_s, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_and_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_bic_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_eor_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ static uint32_t iter_predtest_fwd(uint64_t d, uint64_t g, uint32_t flags) return flags; } +/* This is an iterative function, called for each Pd and Pg word + * moving backward. + */ +static uint32_t iter_predtest_bwd(uint64_t d, uint64_t g, uint32_t flags) +{ + if (likely(g)) { + /* Compute C from first (i.e last) !(D & G). + Use bit 2 to signal first G bit seen. */ + if (!(flags & 4)) { + flags += 4 - 1; /* add bit 2, subtract C from PREDTEST_INIT */ + flags |= (d & pow2floor(g)) == 0; + } + + /* Accumulate Z from each D & G. */ + flags |= ((d & g) != 0) << 1; + + /* Compute N from last (i.e first) D & G. Replace previous. */ + flags = deposit32(flags, 31, 1, (d & (g & -g)) != 0); + } + return flags; +} + /* The same for a single word predicate. */ uint32_t HELPER(sve_predtest1)(uint64_t d, uint64_t g) { @@ -XXX,XX +XXX,XX @@ void HELPER(sve_sel_zpzz_d)(void *vd, void *vn, void *vm, d[i] = (pg[H1(i)] & 1 ? nn : mm); } } + +/* Two operand comparison controlled by a predicate. + * ??? It is very tempting to want to be able to expand this inline + * with x86 instructions, e.g. + * + * vcmpeqw zm, zn, %ymm0 + * vpmovmskb %ymm0, %eax + * and $0x5555, %eax + * and pg, %eax + * + * or even aarch64, e.g. + * + * // mask = 4000 1000 0400 0100 0040 0010 0004 0001 + * cmeq v0.8h, zn, zm + * and v0.8h, v0.8h, mask + * addv h0, v0.8h + * and v0.8b, pg + * + * However, coming up with an abstraction that allows vector inputs and + * a scalar output, and also handles the byte-ordering of sub-uint64_t + * scalar outputs, is tricky. + */ +#define DO_CMP_PPZZ(NAME, TYPE, OP, H, MASK) \ +uint32_t HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \ +{ \ + intptr_t opr_sz = simd_oprsz(desc); \ + uint32_t flags = PREDTEST_INIT; \ + intptr_t i = opr_sz; \ + do { \ + uint64_t out = 0, pg; \ + do { \ + i -= sizeof(TYPE), out <<= sizeof(TYPE); \ + TYPE nn = *(TYPE *)(vn + H(i)); \ + TYPE mm = *(TYPE *)(vm + H(i)); \ + out |= nn OP mm; \ + } while (i & 63); \ + pg = *(uint64_t *)(vg + (i >> 3)) & MASK; \ + out &= pg; \ + *(uint64_t *)(vd + (i >> 3)) = out; \ + flags = iter_predtest_bwd(out, pg, flags); \ + } while (i > 0); \ + return flags; \ +} + +#define DO_CMP_PPZZ_B(NAME, TYPE, OP) \ + DO_CMP_PPZZ(NAME, TYPE, OP, H1, 0xffffffffffffffffull) +#define DO_CMP_PPZZ_H(NAME, TYPE, OP) \ + DO_CMP_PPZZ(NAME, TYPE, OP, H1_2, 0x5555555555555555ull) +#define DO_CMP_PPZZ_S(NAME, TYPE, OP) \ + DO_CMP_PPZZ(NAME, TYPE, OP, H1_4, 0x1111111111111111ull) +#define DO_CMP_PPZZ_D(NAME, TYPE, OP) \ + DO_CMP_PPZZ(NAME, TYPE, OP, , 0x0101010101010101ull) + +DO_CMP_PPZZ_B(sve_cmpeq_ppzz_b, uint8_t, ==) +DO_CMP_PPZZ_H(sve_cmpeq_ppzz_h, uint16_t, ==) +DO_CMP_PPZZ_S(sve_cmpeq_ppzz_s, uint32_t, ==) +DO_CMP_PPZZ_D(sve_cmpeq_ppzz_d, uint64_t, ==) + +DO_CMP_PPZZ_B(sve_cmpne_ppzz_b, uint8_t, !=) +DO_CMP_PPZZ_H(sve_cmpne_ppzz_h, uint16_t, !=) +DO_CMP_PPZZ_S(sve_cmpne_ppzz_s, uint32_t, !=) +DO_CMP_PPZZ_D(sve_cmpne_ppzz_d, uint64_t, !=) + +DO_CMP_PPZZ_B(sve_cmpgt_ppzz_b, int8_t, >) +DO_CMP_PPZZ_H(sve_cmpgt_ppzz_h, int16_t, >) +DO_CMP_PPZZ_S(sve_cmpgt_ppzz_s, int32_t, >) +DO_CMP_PPZZ_D(sve_cmpgt_ppzz_d, int64_t, >) + +DO_CMP_PPZZ_B(sve_cmpge_ppzz_b, int8_t, >=) +DO_CMP_PPZZ_H(sve_cmpge_ppzz_h, int16_t, >=) +DO_CMP_PPZZ_S(sve_cmpge_ppzz_s, int32_t, >=) +DO_CMP_PPZZ_D(sve_cmpge_ppzz_d, int64_t, >=) + +DO_CMP_PPZZ_B(sve_cmphi_ppzz_b, uint8_t, >) +DO_CMP_PPZZ_H(sve_cmphi_ppzz_h, uint16_t, >) +DO_CMP_PPZZ_S(sve_cmphi_ppzz_s, uint32_t, >) +DO_CMP_PPZZ_D(sve_cmphi_ppzz_d, uint64_t, >) + +DO_CMP_PPZZ_B(sve_cmphs_ppzz_b, uint8_t, >=) +DO_CMP_PPZZ_H(sve_cmphs_ppzz_h, uint16_t, >=) +DO_CMP_PPZZ_S(sve_cmphs_ppzz_s, uint32_t, >=) +DO_CMP_PPZZ_D(sve_cmphs_ppzz_d, uint64_t, >=) + +#undef DO_CMP_PPZZ_B +#undef DO_CMP_PPZZ_H +#undef DO_CMP_PPZZ_S +#undef DO_CMP_PPZZ_D +#undef DO_CMP_PPZZ + +/* Similar, but the second source is "wide". */ +#define DO_CMP_PPZW(NAME, TYPE, TYPEW, OP, H, MASK) \ +uint32_t HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \ +{ \ + intptr_t opr_sz = simd_oprsz(desc); \ + uint32_t flags = PREDTEST_INIT; \ + intptr_t i = opr_sz; \ + do { \ + uint64_t out = 0, pg; \ + do { \ + TYPEW mm = *(TYPEW *)(vm + i - 8); \ + do { \ + i -= sizeof(TYPE), out <<= sizeof(TYPE); \ + TYPE nn = *(TYPE *)(vn + H(i)); \ + out |= nn OP mm; \ + } while (i & 7); \ + } while (i & 63); \ + pg = *(uint64_t *)(vg + (i >> 3)) & MASK; \ + out &= pg; \ + *(uint64_t *)(vd + (i >> 3)) = out; \ + flags = iter_predtest_bwd(out, pg, flags); \ + } while (i > 0); \ + return flags; \ +} + +#define DO_CMP_PPZW_B(NAME, TYPE, TYPEW, OP) \ + DO_CMP_PPZW(NAME, TYPE, TYPEW, OP, H1, 0xffffffffffffffffull) +#define DO_CMP_PPZW_H(NAME, TYPE, TYPEW, OP) \ + DO_CMP_PPZW(NAME, TYPE, TYPEW, OP, H1_2, 0x5555555555555555ull) +#define DO_CMP_PPZW_S(NAME, TYPE, TYPEW, OP) \ + DO_CMP_PPZW(NAME, TYPE, TYPEW, OP, H1_4, 0x1111111111111111ull) + +DO_CMP_PPZW_B(sve_cmpeq_ppzw_b, uint8_t, uint64_t, ==) +DO_CMP_PPZW_H(sve_cmpeq_ppzw_h, uint16_t, uint64_t, ==) +DO_CMP_PPZW_S(sve_cmpeq_ppzw_s, uint32_t, uint64_t, ==) + +DO_CMP_PPZW_B(sve_cmpne_ppzw_b, uint8_t, uint64_t, !=) +DO_CMP_PPZW_H(sve_cmpne_ppzw_h, uint16_t, uint64_t, !=) +DO_CMP_PPZW_S(sve_cmpne_ppzw_s, uint32_t, uint64_t, !=) + +DO_CMP_PPZW_B(sve_cmpgt_ppzw_b, int8_t, int64_t, >) +DO_CMP_PPZW_H(sve_cmpgt_ppzw_h, int16_t, int64_t, >) +DO_CMP_PPZW_S(sve_cmpgt_ppzw_s, int32_t, int64_t, >) + +DO_CMP_PPZW_B(sve_cmpge_ppzw_b, int8_t, int64_t, >=) +DO_CMP_PPZW_H(sve_cmpge_ppzw_h, int16_t, int64_t, >=) +DO_CMP_PPZW_S(sve_cmpge_ppzw_s, int32_t, int64_t, >=) + +DO_CMP_PPZW_B(sve_cmphi_ppzw_b, uint8_t, uint64_t, >) +DO_CMP_PPZW_H(sve_cmphi_ppzw_h, uint16_t, uint64_t, >) +DO_CMP_PPZW_S(sve_cmphi_ppzw_s, uint32_t, uint64_t, >) + +DO_CMP_PPZW_B(sve_cmphs_ppzw_b, uint8_t, uint64_t, >=) +DO_CMP_PPZW_H(sve_cmphs_ppzw_h, uint16_t, uint64_t, >=) +DO_CMP_PPZW_S(sve_cmphs_ppzw_s, uint32_t, uint64_t, >=) + +DO_CMP_PPZW_B(sve_cmplt_ppzw_b, int8_t, int64_t, <) +DO_CMP_PPZW_H(sve_cmplt_ppzw_h, int16_t, int64_t, <) +DO_CMP_PPZW_S(sve_cmplt_ppzw_s, int32_t, int64_t, <) + +DO_CMP_PPZW_B(sve_cmple_ppzw_b, int8_t, int64_t, <=) +DO_CMP_PPZW_H(sve_cmple_ppzw_h, int16_t, int64_t, <=) +DO_CMP_PPZW_S(sve_cmple_ppzw_s, int32_t, int64_t, <=) + +DO_CMP_PPZW_B(sve_cmplo_ppzw_b, uint8_t, uint64_t, <) +DO_CMP_PPZW_H(sve_cmplo_ppzw_h, uint16_t, uint64_t, <) +DO_CMP_PPZW_S(sve_cmplo_ppzw_s, uint32_t, uint64_t, <) + +DO_CMP_PPZW_B(sve_cmpls_ppzw_b, uint8_t, uint64_t, <=) +DO_CMP_PPZW_H(sve_cmpls_ppzw_h, uint16_t, uint64_t, <=) +DO_CMP_PPZW_S(sve_cmpls_ppzw_s, uint32_t, uint64_t, <=) + +#undef DO_CMP_PPZW_B +#undef DO_CMP_PPZW_H +#undef DO_CMP_PPZW_S +#undef DO_CMP_PPZW diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ #include "trace-tcg.h" #include "translate-a64.h" + +typedef void gen_helper_gvec_flags_4(TCGv_i32, TCGv_ptr, TCGv_ptr, + TCGv_ptr, TCGv_ptr, TCGv_i32); + /* * Helpers for extracting complex instruction fields. */ @@ -XXX,XX +XXX,XX @@ static bool trans_SPLICE(DisasContext *s, arg_rprr_esz *a, uint32_t insn) return true; } +/* + *** SVE Integer Compare - Vectors Group + */ + +static bool do_ppzz_flags(DisasContext *s, arg_rprr_esz *a, + gen_helper_gvec_flags_4 *gen_fn) +{ + TCGv_ptr pd, zn, zm, pg; + unsigned vsz; + TCGv_i32 t; + + if (gen_fn == NULL) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + vsz = vec_full_reg_size(s); + t = tcg_const_i32(simd_desc(vsz, vsz, 0)); + pd = tcg_temp_new_ptr(); + zn = tcg_temp_new_ptr(); + zm = tcg_temp_new_ptr(); + pg = tcg_temp_new_ptr(); + + tcg_gen_addi_ptr(pd, cpu_env, pred_full_reg_offset(s, a->rd)); + tcg_gen_addi_ptr(zn, cpu_env, vec_full_reg_offset(s, a->rn)); + tcg_gen_addi_ptr(zm, cpu_env, vec_full_reg_offset(s, a->rm)); + tcg_gen_addi_ptr(pg, cpu_env, pred_full_reg_offset(s, a->pg)); + + gen_fn(t, pd, zn, zm, pg, t); + + tcg_temp_free_ptr(pd); + tcg_temp_free_ptr(zn); + tcg_temp_free_ptr(zm); + tcg_temp_free_ptr(pg); + + do_pred_flags(t); + + tcg_temp_free_i32(t); + return true; +} + +#define DO_PPZZ(NAME, name) \ +static bool trans_##NAME##_ppzz(DisasContext *s, arg_rprr_esz *a, \ + uint32_t insn) \ +{ \ + static gen_helper_gvec_flags_4 * const fns[4] = { \ + gen_helper_sve_##name##_ppzz_b, gen_helper_sve_##name##_ppzz_h, \ + gen_helper_sve_##name##_ppzz_s, gen_helper_sve_##name##_ppzz_d, \ + }; \ + return do_ppzz_flags(s, a, fns[a->esz]); \ +} + +DO_PPZZ(CMPEQ, cmpeq) +DO_PPZZ(CMPNE, cmpne) +DO_PPZZ(CMPGT, cmpgt) +DO_PPZZ(CMPGE, cmpge) +DO_PPZZ(CMPHI, cmphi) +DO_PPZZ(CMPHS, cmphs) + +#undef DO_PPZZ + +#define DO_PPZW(NAME, name) \ +static bool trans_##NAME##_ppzw(DisasContext *s, arg_rprr_esz *a, \ + uint32_t insn) \ +{ \ + static gen_helper_gvec_flags_4 * const fns[4] = { \ + gen_helper_sve_##name##_ppzw_b, gen_helper_sve_##name##_ppzw_h, \ + gen_helper_sve_##name##_ppzw_s, NULL \ + }; \ + return do_ppzz_flags(s, a, fns[a->esz]); \ +} + +DO_PPZW(CMPEQ, cmpeq) +DO_PPZW(CMPNE, cmpne) +DO_PPZW(CMPGT, cmpgt) +DO_PPZW(CMPGE, cmpge) +DO_PPZW(CMPHI, cmphi) +DO_PPZW(CMPHS, cmphs) +DO_PPZW(CMPLT, cmplt) +DO_PPZW(CMPLE, cmple) +DO_PPZW(CMPLO, cmplo) +DO_PPZW(CMPLS, cmpls) + +#undef DO_PPZW + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ @rdm_pg_rn ........ esz:2 ... ... ... pg:3 rn:5 rd:5 \ &rprr_esz rm=%reg_movprfx @rd_pg4_rn_rm ........ esz:2 . rm:5 .. pg:4 rn:5 rd:5 &rprr_esz +@pd_pg_rn_rm ........ esz:2 . rm:5 ... pg:3 rn:5 . rd:4 &rprr_esz # Three register operand, with governing predicate, vector element size @rda_pg_rn_rm ........ esz:2 . rm:5 ... pg:3 rn:5 rd:5 \ @@ -XXX,XX +XXX,XX @@ SPLICE 00000101 .. 101 100 100 ... ..... ..... @rdn_pg_rm # SVE select vector elements (predicated) SEL_zpzz 00000101 .. 1 ..... 11 .... ..... ..... @rd_pg4_rn_rm +### SVE Integer Compare - Vectors Group + +# SVE integer compare_vectors +CMPHS_ppzz 00100100 .. 0 ..... 000 ... ..... 0 .... @pd_pg_rn_rm +CMPHI_ppzz 00100100 .. 0 ..... 000 ... ..... 1 .... @pd_pg_rn_rm +CMPGE_ppzz 00100100 .. 0 ..... 100 ... ..... 0 .... @pd_pg_rn_rm +CMPGT_ppzz 00100100 .. 0 ..... 100 ... ..... 1 .... @pd_pg_rn_rm +CMPEQ_ppzz 00100100 .. 0 ..... 101 ... ..... 0 .... @pd_pg_rn_rm +CMPNE_ppzz 00100100 .. 0 ..... 101 ... ..... 1 .... @pd_pg_rn_rm + +# SVE integer compare with wide elements +# Note these require esz != 3. +CMPEQ_ppzw 00100100 .. 0 ..... 001 ... ..... 0 .... @pd_pg_rn_rm +CMPNE_ppzw 00100100 .. 0 ..... 001 ... ..... 1 .... @pd_pg_rn_rm +CMPGE_ppzw 00100100 .. 0 ..... 010 ... ..... 0 .... @pd_pg_rn_rm +CMPGT_ppzw 00100100 .. 0 ..... 010 ... ..... 1 .... @pd_pg_rn_rm +CMPLT_ppzw 00100100 .. 0 ..... 011 ... ..... 0 .... @pd_pg_rn_rm +CMPLE_ppzw 00100100 .. 0 ..... 011 ... ..... 1 .... @pd_pg_rn_rm +CMPHS_ppzw 00100100 .. 0 ..... 110 ... ..... 0 .... @pd_pg_rn_rm +CMPHI_ppzw 00100100 .. 0 ..... 110 ... ..... 1 .... @pd_pg_rn_rm +CMPLO_ppzw 00100100 .. 0 ..... 111 ... ..... 0 .... @pd_pg_rn_rm +CMPLS_ppzw 00100100 .. 0 ..... 111 ... ..... 1 .... @pd_pg_rn_rm + ### SVE Predicate Logical Operations Group # SVE predicate logical operations -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 44 +++++++++++++++++++ target/arm/sve_helper.c | 88 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 66 ++++++++++++++++++++++++++++ target/arm/sve.decode | 23 ++++++++++ 4 files changed, 221 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_cmplo_ppzw_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve_cmpls_ppzw_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpeq_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpne_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpgt_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpge_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmplt_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmple_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmphs_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmphi_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmplo_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpls_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_cmpeq_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpne_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpgt_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpge_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmplt_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmple_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmphs_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmphi_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmplo_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpls_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_cmpeq_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpne_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpgt_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpge_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmplt_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmple_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmphs_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmphi_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmplo_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpls_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_cmpeq_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpne_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpgt_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpge_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmplt_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmple_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmphs_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmphi_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmplo_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_cmpls_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_and_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_bic_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_eor_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_CMP_PPZW_S(sve_cmpls_ppzw_s, uint32_t, uint64_t, <=) #undef DO_CMP_PPZW_H #undef DO_CMP_PPZW_S #undef DO_CMP_PPZW + +/* Similar, but the second source is immediate. */ +#define DO_CMP_PPZI(NAME, TYPE, OP, H, MASK) \ +uint32_t HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc) \ +{ \ + intptr_t opr_sz = simd_oprsz(desc); \ + uint32_t flags = PREDTEST_INIT; \ + TYPE mm = simd_data(desc); \ + intptr_t i = opr_sz; \ + do { \ + uint64_t out = 0, pg; \ + do { \ + i -= sizeof(TYPE), out <<= sizeof(TYPE); \ + TYPE nn = *(TYPE *)(vn + H(i)); \ + out |= nn OP mm; \ + } while (i & 63); \ + pg = *(uint64_t *)(vg + (i >> 3)) & MASK; \ + out &= pg; \ + *(uint64_t *)(vd + (i >> 3)) = out; \ + flags = iter_predtest_bwd(out, pg, flags); \ + } while (i > 0); \ + return flags; \ +} + +#define DO_CMP_PPZI_B(NAME, TYPE, OP) \ + DO_CMP_PPZI(NAME, TYPE, OP, H1, 0xffffffffffffffffull) +#define DO_CMP_PPZI_H(NAME, TYPE, OP) \ + DO_CMP_PPZI(NAME, TYPE, OP, H1_2, 0x5555555555555555ull) +#define DO_CMP_PPZI_S(NAME, TYPE, OP) \ + DO_CMP_PPZI(NAME, TYPE, OP, H1_4, 0x1111111111111111ull) +#define DO_CMP_PPZI_D(NAME, TYPE, OP) \ + DO_CMP_PPZI(NAME, TYPE, OP, , 0x0101010101010101ull) + +DO_CMP_PPZI_B(sve_cmpeq_ppzi_b, uint8_t, ==) +DO_CMP_PPZI_H(sve_cmpeq_ppzi_h, uint16_t, ==) +DO_CMP_PPZI_S(sve_cmpeq_ppzi_s, uint32_t, ==) +DO_CMP_PPZI_D(sve_cmpeq_ppzi_d, uint64_t, ==) + +DO_CMP_PPZI_B(sve_cmpne_ppzi_b, uint8_t, !=) +DO_CMP_PPZI_H(sve_cmpne_ppzi_h, uint16_t, !=) +DO_CMP_PPZI_S(sve_cmpne_ppzi_s, uint32_t, !=) +DO_CMP_PPZI_D(sve_cmpne_ppzi_d, uint64_t, !=) + +DO_CMP_PPZI_B(sve_cmpgt_ppzi_b, int8_t, >) +DO_CMP_PPZI_H(sve_cmpgt_ppzi_h, int16_t, >) +DO_CMP_PPZI_S(sve_cmpgt_ppzi_s, int32_t, >) +DO_CMP_PPZI_D(sve_cmpgt_ppzi_d, int64_t, >) + +DO_CMP_PPZI_B(sve_cmpge_ppzi_b, int8_t, >=) +DO_CMP_PPZI_H(sve_cmpge_ppzi_h, int16_t, >=) +DO_CMP_PPZI_S(sve_cmpge_ppzi_s, int32_t, >=) +DO_CMP_PPZI_D(sve_cmpge_ppzi_d, int64_t, >=) + +DO_CMP_PPZI_B(sve_cmphi_ppzi_b, uint8_t, >) +DO_CMP_PPZI_H(sve_cmphi_ppzi_h, uint16_t, >) +DO_CMP_PPZI_S(sve_cmphi_ppzi_s, uint32_t, >) +DO_CMP_PPZI_D(sve_cmphi_ppzi_d, uint64_t, >) + +DO_CMP_PPZI_B(sve_cmphs_ppzi_b, uint8_t, >=) +DO_CMP_PPZI_H(sve_cmphs_ppzi_h, uint16_t, >=) +DO_CMP_PPZI_S(sve_cmphs_ppzi_s, uint32_t, >=) +DO_CMP_PPZI_D(sve_cmphs_ppzi_d, uint64_t, >=) + +DO_CMP_PPZI_B(sve_cmplt_ppzi_b, int8_t, <) +DO_CMP_PPZI_H(sve_cmplt_ppzi_h, int16_t, <) +DO_CMP_PPZI_S(sve_cmplt_ppzi_s, int32_t, <) +DO_CMP_PPZI_D(sve_cmplt_ppzi_d, int64_t, <) + +DO_CMP_PPZI_B(sve_cmple_ppzi_b, int8_t, <=) +DO_CMP_PPZI_H(sve_cmple_ppzi_h, int16_t, <=) +DO_CMP_PPZI_S(sve_cmple_ppzi_s, int32_t, <=) +DO_CMP_PPZI_D(sve_cmple_ppzi_d, int64_t, <=) + +DO_CMP_PPZI_B(sve_cmplo_ppzi_b, uint8_t, <) +DO_CMP_PPZI_H(sve_cmplo_ppzi_h, uint16_t, <) +DO_CMP_PPZI_S(sve_cmplo_ppzi_s, uint32_t, <) +DO_CMP_PPZI_D(sve_cmplo_ppzi_d, uint64_t, <) + +DO_CMP_PPZI_B(sve_cmpls_ppzi_b, uint8_t, <=) +DO_CMP_PPZI_H(sve_cmpls_ppzi_h, uint16_t, <=) +DO_CMP_PPZI_S(sve_cmpls_ppzi_s, uint32_t, <=) +DO_CMP_PPZI_D(sve_cmpls_ppzi_d, uint64_t, <=) + +#undef DO_CMP_PPZI_B +#undef DO_CMP_PPZI_H +#undef DO_CMP_PPZI_S +#undef DO_CMP_PPZI_D +#undef DO_CMP_PPZI diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ #include "translate-a64.h" +typedef void gen_helper_gvec_flags_3(TCGv_i32, TCGv_ptr, TCGv_ptr, + TCGv_ptr, TCGv_i32); typedef void gen_helper_gvec_flags_4(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); @@ -XXX,XX +XXX,XX @@ DO_PPZW(CMPLS, cmpls) #undef DO_PPZW +/* + *** SVE Integer Compare - Immediate Groups + */ + +static bool do_ppzi_flags(DisasContext *s, arg_rpri_esz *a, + gen_helper_gvec_flags_3 *gen_fn) +{ + TCGv_ptr pd, zn, pg; + unsigned vsz; + TCGv_i32 t; + + if (gen_fn == NULL) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + vsz = vec_full_reg_size(s); + t = tcg_const_i32(simd_desc(vsz, vsz, a->imm)); + pd = tcg_temp_new_ptr(); + zn = tcg_temp_new_ptr(); + pg = tcg_temp_new_ptr(); + + tcg_gen_addi_ptr(pd, cpu_env, pred_full_reg_offset(s, a->rd)); + tcg_gen_addi_ptr(zn, cpu_env, vec_full_reg_offset(s, a->rn)); + tcg_gen_addi_ptr(pg, cpu_env, pred_full_reg_offset(s, a->pg)); + + gen_fn(t, pd, zn, pg, t); + + tcg_temp_free_ptr(pd); + tcg_temp_free_ptr(zn); + tcg_temp_free_ptr(pg); + + do_pred_flags(t); + + tcg_temp_free_i32(t); + return true; +} + +#define DO_PPZI(NAME, name) \ +static bool trans_##NAME##_ppzi(DisasContext *s, arg_rpri_esz *a, \ + uint32_t insn) \ +{ \ + static gen_helper_gvec_flags_3 * const fns[4] = { \ + gen_helper_sve_##name##_ppzi_b, gen_helper_sve_##name##_ppzi_h, \ + gen_helper_sve_##name##_ppzi_s, gen_helper_sve_##name##_ppzi_d, \ + }; \ + return do_ppzi_flags(s, a, fns[a->esz]); \ +} + +DO_PPZI(CMPEQ, cmpeq) +DO_PPZI(CMPNE, cmpne) +DO_PPZI(CMPGT, cmpgt) +DO_PPZI(CMPGE, cmpge) +DO_PPZI(CMPHI, cmphi) +DO_PPZI(CMPHS, cmphs) +DO_PPZI(CMPLT, cmplt) +DO_PPZI(CMPLE, cmple) +DO_PPZI(CMPLO, cmplo) +DO_PPZI(CMPLS, cmpls) + +#undef DO_PPZI + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ @rdn_dbm ........ .. .... dbm:13 rd:5 \ &rr_dbm rn=%reg_movprfx +# Predicate output, vector and immediate input, +# controlling predicate, element size. +@pd_pg_rn_i7 ........ esz:2 . imm:7 . pg:3 rn:5 . rd:4 &rpri_esz +@pd_pg_rn_i5 ........ esz:2 . imm:s5 ... pg:3 rn:5 . rd:4 &rpri_esz + # Basic Load/Store with 9-bit immediate offset @pd_rn_i9 ........ ........ ...... rn:5 . rd:4 \ &rri imm=%imm9_16_10 @@ -XXX,XX +XXX,XX @@ CMPHI_ppzw 00100100 .. 0 ..... 110 ... ..... 1 .... @pd_pg_rn_rm CMPLO_ppzw 00100100 .. 0 ..... 111 ... ..... 0 .... @pd_pg_rn_rm CMPLS_ppzw 00100100 .. 0 ..... 111 ... ..... 1 .... @pd_pg_rn_rm +### SVE Integer Compare - Unsigned Immediate Group + +# SVE integer compare with unsigned immediate +CMPHS_ppzi 00100100 .. 1 ....... 0 ... ..... 0 .... @pd_pg_rn_i7 +CMPHI_ppzi 00100100 .. 1 ....... 0 ... ..... 1 .... @pd_pg_rn_i7 +CMPLO_ppzi 00100100 .. 1 ....... 1 ... ..... 0 .... @pd_pg_rn_i7 +CMPLS_ppzi 00100100 .. 1 ....... 1 ... ..... 1 .... @pd_pg_rn_i7 + +### SVE Integer Compare - Signed Immediate Group + +# SVE integer compare with signed immediate +CMPGE_ppzi 00100101 .. 0 ..... 000 ... ..... 0 .... @pd_pg_rn_i5 +CMPGT_ppzi 00100101 .. 0 ..... 000 ... ..... 1 .... @pd_pg_rn_i5 +CMPLT_ppzi 00100101 .. 0 ..... 001 ... ..... 0 .... @pd_pg_rn_i5 +CMPLE_ppzi 00100101 .. 0 ..... 001 ... ..... 1 .... @pd_pg_rn_i5 +CMPEQ_ppzi 00100101 .. 0 ..... 100 ... ..... 0 .... @pd_pg_rn_i5 +CMPNE_ppzi 00100101 .. 0 ..... 100 ... ..... 1 .... @pd_pg_rn_i5 + ### SVE Predicate Logical Operations Group # SVE predicate logical operations -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 18 +++ target/arm/sve_helper.c | 248 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 106 ++++++++++++++++ target/arm/sve.decode | 19 +++ 4 files changed, 391 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_orn_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_nor_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_nand_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_brkpa, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_brkpb, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_brkpas, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_brkpbs, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_brka_z, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_brkb_z, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_brka_m, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_brkb_m, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_brkas_z, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_brkbs_z, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_brkas_m, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_brkbs_m, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_brkn, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_brkns, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_CMP_PPZI_D(sve_cmpls_ppzi_d, uint64_t, <=) #undef DO_CMP_PPZI_S #undef DO_CMP_PPZI_D #undef DO_CMP_PPZI + +/* Similar to the ARM LastActive pseudocode function. */ +static bool last_active_pred(void *vd, void *vg, intptr_t oprsz) +{ + intptr_t i; + + for (i = QEMU_ALIGN_UP(oprsz, 8) - 8; i >= 0; i -= 8) { + uint64_t pg = *(uint64_t *)(vg + i); + if (pg) { + return (pow2floor(pg) & *(uint64_t *)(vd + i)) != 0; + } + } + return 0; +} + +/* Compute a mask into RETB that is true for all G, up to and including + * (if after) or excluding (if !after) the first G & N. + * Return true if BRK found. + */ +static bool compute_brk(uint64_t *retb, uint64_t n, uint64_t g, + bool brk, bool after) +{ + uint64_t b; + + if (brk) { + b = 0; + } else if ((g & n) == 0) { + /* For all G, no N are set; break not found. */ + b = g; + } else { + /* Break somewhere in N. Locate it. */ + b = g & n; /* guard true, pred true */ + b = b & -b; /* first such */ + if (after) { + b = b | (b - 1); /* break after same */ + } else { + b = b - 1; /* break before same */ + } + brk = true; + } + + *retb = b; + return brk; +} + +/* Compute a zeroing BRK. */ +static void compute_brk_z(uint64_t *d, uint64_t *n, uint64_t *g, + intptr_t oprsz, bool after) +{ + bool brk = false; + intptr_t i; + + for (i = 0; i < DIV_ROUND_UP(oprsz, 8); ++i) { + uint64_t this_b, this_g = g[i]; + + brk = compute_brk(&this_b, n[i], this_g, brk, after); + d[i] = this_b & this_g; + } +} + +/* Likewise, but also compute flags. */ +static uint32_t compute_brks_z(uint64_t *d, uint64_t *n, uint64_t *g, + intptr_t oprsz, bool after) +{ + uint32_t flags = PREDTEST_INIT; + bool brk = false; + intptr_t i; + + for (i = 0; i < DIV_ROUND_UP(oprsz, 8); ++i) { + uint64_t this_b, this_d, this_g = g[i]; + + brk = compute_brk(&this_b, n[i], this_g, brk, after); + d[i] = this_d = this_b & this_g; + flags = iter_predtest_fwd(this_d, this_g, flags); + } + return flags; +} + +/* Compute a merging BRK. */ +static void compute_brk_m(uint64_t *d, uint64_t *n, uint64_t *g, + intptr_t oprsz, bool after) +{ + bool brk = false; + intptr_t i; + + for (i = 0; i < DIV_ROUND_UP(oprsz, 8); ++i) { + uint64_t this_b, this_g = g[i]; + + brk = compute_brk(&this_b, n[i], this_g, brk, after); + d[i] = (this_b & this_g) | (d[i] & ~this_g); + } +} + +/* Likewise, but also compute flags. */ +static uint32_t compute_brks_m(uint64_t *d, uint64_t *n, uint64_t *g, + intptr_t oprsz, bool after) +{ + uint32_t flags = PREDTEST_INIT; + bool brk = false; + intptr_t i; + + for (i = 0; i < oprsz / 8; ++i) { + uint64_t this_b, this_d = d[i], this_g = g[i]; + + brk = compute_brk(&this_b, n[i], this_g, brk, after); + d[i] = this_d = (this_b & this_g) | (this_d & ~this_g); + flags = iter_predtest_fwd(this_d, this_g, flags); + } + return flags; +} + +static uint32_t do_zero(ARMPredicateReg *d, intptr_t oprsz) +{ + /* It is quicker to zero the whole predicate than loop on OPRSZ. + * The compiler should turn this into 4 64-bit integer stores. + */ + memset(d, 0, sizeof(ARMPredicateReg)); + return PREDTEST_INIT; +} + +void HELPER(sve_brkpa)(void *vd, void *vn, void *vm, void *vg, + uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + if (last_active_pred(vn, vg, oprsz)) { + compute_brk_z(vd, vm, vg, oprsz, true); + } else { + do_zero(vd, oprsz); + } +} + +uint32_t HELPER(sve_brkpas)(void *vd, void *vn, void *vm, void *vg, + uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + if (last_active_pred(vn, vg, oprsz)) { + return compute_brks_z(vd, vm, vg, oprsz, true); + } else { + return do_zero(vd, oprsz); + } +} + +void HELPER(sve_brkpb)(void *vd, void *vn, void *vm, void *vg, + uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + if (last_active_pred(vn, vg, oprsz)) { + compute_brk_z(vd, vm, vg, oprsz, false); + } else { + do_zero(vd, oprsz); + } +} + +uint32_t HELPER(sve_brkpbs)(void *vd, void *vn, void *vm, void *vg, + uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + if (last_active_pred(vn, vg, oprsz)) { + return compute_brks_z(vd, vm, vg, oprsz, false); + } else { + return do_zero(vd, oprsz); + } +} + +void HELPER(sve_brka_z)(void *vd, void *vn, void *vg, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + compute_brk_z(vd, vn, vg, oprsz, true); +} + +uint32_t HELPER(sve_brkas_z)(void *vd, void *vn, void *vg, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + return compute_brks_z(vd, vn, vg, oprsz, true); +} + +void HELPER(sve_brkb_z)(void *vd, void *vn, void *vg, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + compute_brk_z(vd, vn, vg, oprsz, false); +} + +uint32_t HELPER(sve_brkbs_z)(void *vd, void *vn, void *vg, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + return compute_brks_z(vd, vn, vg, oprsz, false); +} + +void HELPER(sve_brka_m)(void *vd, void *vn, void *vg, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + compute_brk_m(vd, vn, vg, oprsz, true); +} + +uint32_t HELPER(sve_brkas_m)(void *vd, void *vn, void *vg, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + return compute_brks_m(vd, vn, vg, oprsz, true); +} + +void HELPER(sve_brkb_m)(void *vd, void *vn, void *vg, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + compute_brk_m(vd, vn, vg, oprsz, false); +} + +uint32_t HELPER(sve_brkbs_m)(void *vd, void *vn, void *vg, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + return compute_brks_m(vd, vn, vg, oprsz, false); +} + +void HELPER(sve_brkn)(void *vd, void *vn, void *vg, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + + if (!last_active_pred(vn, vg, oprsz)) { + do_zero(vd, oprsz); + } +} + +/* As if PredTest(Ones(PL), D, esz). */ +static uint32_t predtest_ones(ARMPredicateReg *d, intptr_t oprsz, + uint64_t esz_mask) +{ + uint32_t flags = PREDTEST_INIT; + intptr_t i; + + for (i = 0; i < oprsz / 8; i++) { + flags = iter_predtest_fwd(d->p[i], esz_mask, flags); + } + if (oprsz & 7) { + uint64_t mask = ~(-1ULL << (8 * (oprsz & 7))); + flags = iter_predtest_fwd(d->p[i], esz_mask & mask, flags); + } + return flags; +} + +uint32_t HELPER(sve_brkns)(void *vd, void *vn, void *vg, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + + if (last_active_pred(vn, vg, oprsz)) { + return predtest_ones(vd, oprsz, -1); + } else { + return do_zero(vd, oprsz); + } +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_PPZI(CMPLS, cmpls) #undef DO_PPZI +/* + *** SVE Partition Break Group + */ + +static bool do_brk3(DisasContext *s, arg_rprr_s *a, + gen_helper_gvec_4 *fn, gen_helper_gvec_flags_4 *fn_s) +{ + if (!sve_access_check(s)) { + return true; + } + + unsigned vsz = pred_full_reg_size(s); + + /* Predicate sizes may be smaller and cannot use simd_desc. */ + TCGv_ptr d = tcg_temp_new_ptr(); + TCGv_ptr n = tcg_temp_new_ptr(); + TCGv_ptr m = tcg_temp_new_ptr(); + TCGv_ptr g = tcg_temp_new_ptr(); + TCGv_i32 t = tcg_const_i32(vsz - 2); + + tcg_gen_addi_ptr(d, cpu_env, pred_full_reg_offset(s, a->rd)); + tcg_gen_addi_ptr(n, cpu_env, pred_full_reg_offset(s, a->rn)); + tcg_gen_addi_ptr(m, cpu_env, pred_full_reg_offset(s, a->rm)); + tcg_gen_addi_ptr(g, cpu_env, pred_full_reg_offset(s, a->pg)); + + if (a->s) { + fn_s(t, d, n, m, g, t); + do_pred_flags(t); + } else { + fn(d, n, m, g, t); + } + tcg_temp_free_ptr(d); + tcg_temp_free_ptr(n); + tcg_temp_free_ptr(m); + tcg_temp_free_ptr(g); + tcg_temp_free_i32(t); + return true; +} + +static bool do_brk2(DisasContext *s, arg_rpr_s *a, + gen_helper_gvec_3 *fn, gen_helper_gvec_flags_3 *fn_s) +{ + if (!sve_access_check(s)) { + return true; + } + + unsigned vsz = pred_full_reg_size(s); + + /* Predicate sizes may be smaller and cannot use simd_desc. */ + TCGv_ptr d = tcg_temp_new_ptr(); + TCGv_ptr n = tcg_temp_new_ptr(); + TCGv_ptr g = tcg_temp_new_ptr(); + TCGv_i32 t = tcg_const_i32(vsz - 2); + + tcg_gen_addi_ptr(d, cpu_env, pred_full_reg_offset(s, a->rd)); + tcg_gen_addi_ptr(n, cpu_env, pred_full_reg_offset(s, a->rn)); + tcg_gen_addi_ptr(g, cpu_env, pred_full_reg_offset(s, a->pg)); + + if (a->s) { + fn_s(t, d, n, g, t); + do_pred_flags(t); + } else { + fn(d, n, g, t); + } + tcg_temp_free_ptr(d); + tcg_temp_free_ptr(n); + tcg_temp_free_ptr(g); + tcg_temp_free_i32(t); + return true; +} + +static bool trans_BRKPA(DisasContext *s, arg_rprr_s *a, uint32_t insn) +{ + return do_brk3(s, a, gen_helper_sve_brkpa, gen_helper_sve_brkpas); +} + +static bool trans_BRKPB(DisasContext *s, arg_rprr_s *a, uint32_t insn) +{ + return do_brk3(s, a, gen_helper_sve_brkpb, gen_helper_sve_brkpbs); +} + +static bool trans_BRKA_m(DisasContext *s, arg_rpr_s *a, uint32_t insn) +{ + return do_brk2(s, a, gen_helper_sve_brka_m, gen_helper_sve_brkas_m); +} + +static bool trans_BRKB_m(DisasContext *s, arg_rpr_s *a, uint32_t insn) +{ + return do_brk2(s, a, gen_helper_sve_brkb_m, gen_helper_sve_brkbs_m); +} + +static bool trans_BRKA_z(DisasContext *s, arg_rpr_s *a, uint32_t insn) +{ + return do_brk2(s, a, gen_helper_sve_brka_z, gen_helper_sve_brkas_z); +} + +static bool trans_BRKB_z(DisasContext *s, arg_rpr_s *a, uint32_t insn) +{ + return do_brk2(s, a, gen_helper_sve_brkb_z, gen_helper_sve_brkbs_z); +} + +static bool trans_BRKN(DisasContext *s, arg_rpr_s *a, uint32_t insn) +{ + return do_brk2(s, a, gen_helper_sve_brkn, gen_helper_sve_brkns); +} + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ &rri_esz rd rn imm esz &rrr_esz rd rn rm esz &rpr_esz rd pg rn esz +&rpr_s rd pg rn s &rprr_s rd pg rn rm s &rprr_esz rd pg rn rm esz &rprrr_esz rd pg rn rm ra esz @@ -XXX,XX +XXX,XX @@ @pd_pn ........ esz:2 .. .... ....... rn:4 . rd:4 &rr_esz @rd_rn ........ esz:2 ...... ...... rn:5 rd:5 &rr_esz +# Two operand with governing predicate, flags setting +@pd_pg_pn_s ........ . s:1 ...... .. pg:4 . rn:4 . rd:4 &rpr_s + # Three operand with unused vector element size @rd_rn_rm_e0 ........ ... rm:5 ... ... rn:5 rd:5 &rrr_esz esz=0 @@ -XXX,XX +XXX,XX @@ PFIRST 00100101 01 011 000 11000 00 .... 0 .... @pd_pn_e0 # SVE predicate next active PNEXT 00100101 .. 011 001 11000 10 .... 0 .... @pd_pn +### SVE Partition Break Group + +# SVE propagate break from previous partition +BRKPA 00100101 0. 00 .... 11 .... 0 .... 0 .... @pd_pg_pn_pm_s +BRKPB 00100101 0. 00 .... 11 .... 0 .... 1 .... @pd_pg_pn_pm_s + +# SVE partition break condition +BRKA_z 00100101 0. 01000001 .... 0 .... 0 .... @pd_pg_pn_s +BRKB_z 00100101 1. 01000001 .... 0 .... 0 .... @pd_pg_pn_s +BRKA_m 00100101 0. 01000001 .... 0 .... 1 .... @pd_pg_pn_s +BRKB_m 00100101 1. 01000001 .... 0 .... 1 .... @pd_pg_pn_s + +# SVE propagate break to next partition +BRKN 00100101 0. 01100001 .... 0 .... 0 .... @pd_pg_pn_s + ### SVE Memory - 32-bit Gather and Unsized Contiguous Group # SVE load predicate register -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 2 + target/arm/sve_helper.c | 14 ++++ target/arm/translate-sve.c | 133 +++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 27 ++++++++ 4 files changed, 176 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_brkbs_m, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_brkn, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_brkns, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_brkns)(void *vd, void *vn, void *vg, uint32_t pred_desc) return do_zero(vd, oprsz); } } + +uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) +{ + intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t esz = extract32(pred_desc, SIMD_DATA_SHIFT, 2); + uint64_t *n = vn, *g = vg, sum = 0, mask = pred_esz_masks[esz]; + intptr_t i; + + for (i = 0; i < DIV_ROUND_UP(oprsz, 8); ++i) { + uint64_t t = n[i] & g[i] & mask; + sum += ctpop64(t); + } + return sum; +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ #include "translate-a64.h" +typedef void GVecGen2sFn(unsigned, uint32_t, uint32_t, + TCGv_i64, uint32_t, uint32_t); + typedef void gen_helper_gvec_flags_3(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void gen_helper_gvec_flags_4(TCGv_i32, TCGv_ptr, TCGv_ptr, @@ -XXX,XX +XXX,XX @@ static bool trans_BRKN(DisasContext *s, arg_rpr_s *a, uint32_t insn) return do_brk2(s, a, gen_helper_sve_brkn, gen_helper_sve_brkns); } +/* + *** SVE Predicate Count Group + */ + +static void do_cntp(DisasContext *s, TCGv_i64 val, int esz, int pn, int pg) +{ + unsigned psz = pred_full_reg_size(s); + + if (psz <= 8) { + uint64_t psz_mask; + + tcg_gen_ld_i64(val, cpu_env, pred_full_reg_offset(s, pn)); + if (pn != pg) { + TCGv_i64 g = tcg_temp_new_i64(); + tcg_gen_ld_i64(g, cpu_env, pred_full_reg_offset(s, pg)); + tcg_gen_and_i64(val, val, g); + tcg_temp_free_i64(g); + } + + /* Reduce the pred_esz_masks value simply to reduce the + * size of the code generated here. + */ + psz_mask = MAKE_64BIT_MASK(0, psz * 8); + tcg_gen_andi_i64(val, val, pred_esz_masks[esz] & psz_mask); + + tcg_gen_ctpop_i64(val, val); + } else { + TCGv_ptr t_pn = tcg_temp_new_ptr(); + TCGv_ptr t_pg = tcg_temp_new_ptr(); + unsigned desc; + TCGv_i32 t_desc; + + desc = psz - 2; + desc = deposit32(desc, SIMD_DATA_SHIFT, 2, esz); + + tcg_gen_addi_ptr(t_pn, cpu_env, pred_full_reg_offset(s, pn)); + tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg)); + t_desc = tcg_const_i32(desc); + + gen_helper_sve_cntp(val, t_pn, t_pg, t_desc); + tcg_temp_free_ptr(t_pn); + tcg_temp_free_ptr(t_pg); + tcg_temp_free_i32(t_desc); + } +} + +static bool trans_CNTP(DisasContext *s, arg_CNTP *a, uint32_t insn) +{ + if (sve_access_check(s)) { + do_cntp(s, cpu_reg(s, a->rd), a->esz, a->rn, a->pg); + } + return true; +} + +static bool trans_INCDECP_r(DisasContext *s, arg_incdec_pred *a, + uint32_t insn) +{ + if (sve_access_check(s)) { + TCGv_i64 reg = cpu_reg(s, a->rd); + TCGv_i64 val = tcg_temp_new_i64(); + + do_cntp(s, val, a->esz, a->pg, a->pg); + if (a->d) { + tcg_gen_sub_i64(reg, reg, val); + } else { + tcg_gen_add_i64(reg, reg, val); + } + tcg_temp_free_i64(val); + } + return true; +} + +static bool trans_INCDECP_z(DisasContext *s, arg_incdec2_pred *a, + uint32_t insn) +{ + if (a->esz == 0) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_i64 val = tcg_temp_new_i64(); + GVecGen2sFn *gvec_fn = a->d ? tcg_gen_gvec_subs : tcg_gen_gvec_adds; + + do_cntp(s, val, a->esz, a->pg, a->pg); + gvec_fn(a->esz, vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), val, vsz, vsz); + } + return true; +} + +static bool trans_SINCDECP_r_32(DisasContext *s, arg_incdec_pred *a, + uint32_t insn) +{ + if (sve_access_check(s)) { + TCGv_i64 reg = cpu_reg(s, a->rd); + TCGv_i64 val = tcg_temp_new_i64(); + + do_cntp(s, val, a->esz, a->pg, a->pg); + do_sat_addsub_32(reg, val, a->u, a->d); + } + return true; +} + +static bool trans_SINCDECP_r_64(DisasContext *s, arg_incdec_pred *a, + uint32_t insn) +{ + if (sve_access_check(s)) { + TCGv_i64 reg = cpu_reg(s, a->rd); + TCGv_i64 val = tcg_temp_new_i64(); + + do_cntp(s, val, a->esz, a->pg, a->pg); + do_sat_addsub_64(reg, val, a->u, a->d); + } + return true; +} + +static bool trans_SINCDECP_z(DisasContext *s, arg_incdec2_pred *a, + uint32_t insn) +{ + if (a->esz == 0) { + return false; + } + if (sve_access_check(s)) { + TCGv_i64 val = tcg_temp_new_i64(); + do_cntp(s, val, a->esz, a->pg, a->pg); + do_sat_addsub_vec(s, a->esz, a->rd, a->rn, val, a->u, a->d); + } + return true; +} + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ &ptrue rd esz pat s &incdec_cnt rd pat esz imm d u &incdec2_cnt rd rn pat esz imm d u +&incdec_pred rd pg esz d u +&incdec2_pred rd rn pg esz d u ########################################################################### # Named instruction formats. These are generally used to @@ -XXX,XX +XXX,XX @@ # One register operand, with governing predicate, vector element size @rd_pg_rn ........ esz:2 ... ... ... pg:3 rn:5 rd:5 &rpr_esz +@rd_pg4_pn ........ esz:2 ... ... .. pg:4 . rn:4 rd:5 &rpr_esz # Two register operands with a 6-bit signed immediate. @rd_rn_i6 ........ ... rn:5 ..... imm:s6 rd:5 &rri @@ -XXX,XX +XXX,XX @@ @incdec2_cnt ........ esz:2 .. .... ...... pat:5 rd:5 \ &incdec2_cnt imm=%imm4_16_p1 rn=%reg_movprfx +# One register, predicate. +# User must fill in U and D. +@incdec_pred ........ esz:2 .... .. ..... .. pg:4 rd:5 &incdec_pred +@incdec2_pred ........ esz:2 .... .. ..... .. pg:4 rd:5 \ + &incdec2_pred rn=%reg_movprfx + ########################################################################### # Instruction patterns. Grouped according to the SVE encodingindex.xhtml. @@ -XXX,XX +XXX,XX @@ BRKB_m 00100101 1. 01000001 .... 0 .... 1 .... @pd_pg_pn_s # SVE propagate break to next partition BRKN 00100101 0. 01100001 .... 0 .... 0 .... @pd_pg_pn_s +### SVE Predicate Count Group + +# SVE predicate count +CNTP 00100101 .. 100 000 10 .... 0 .... ..... @rd_pg4_pn + +# SVE inc/dec register by predicate count +INCDECP_r 00100101 .. 10110 d:1 10001 00 .... ..... @incdec_pred u=1 + +# SVE inc/dec vector by predicate count +INCDECP_z 00100101 .. 10110 d:1 10000 00 .... ..... @incdec2_pred u=1 + +# SVE saturating inc/dec register by predicate count +SINCDECP_r_32 00100101 .. 1010 d:1 u:1 10001 00 .... ..... @incdec_pred +SINCDECP_r_64 00100101 .. 1010 d:1 u:1 10001 10 .... ..... @incdec_pred + +# SVE saturating inc/dec vector by predicate count +SINCDECP_z 00100101 .. 1010 d:1 u:1 10000 00 .... ..... @incdec2_pred + ### SVE Memory - 32-bit Gather and Unsized Contiguous Group # SVE load predicate register -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-16-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 2 + target/arm/sve_helper.c | 31 ++++++++++++ target/arm/translate-sve.c | 99 ++++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 8 +++ 4 files changed, 140 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_brkn, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_brkns, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve_while, TCG_CALL_NO_RWG, i32, ptr, i32, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) } return sum; } + +uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uintptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t esz = extract32(pred_desc, SIMD_DATA_SHIFT, 2); + uint64_t esz_mask = pred_esz_masks[esz]; + ARMPredicateReg *d = vd; + uint32_t flags; + intptr_t i; + + /* Begin with a zero predicate register. */ + flags = do_zero(d, oprsz); + if (count == 0) { + return flags; + } + + /* Scale from predicate element count to bits. */ + count <<= esz; + /* Bound to the bits in the predicate. */ + count = MIN(count, oprsz * 8); + + /* Set all of the requested bits. */ + for (i = 0; i < count / 64; ++i) { + d->p[i] = esz_mask; + } + if (count & 63) { + d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask; + } + + return predtest_ones(d, oprsz, esz_mask); +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SINCDECP_z(DisasContext *s, arg_incdec2_pred *a, return true; } +/* + *** SVE Integer Compare Scalars Group + */ + +static bool trans_CTERM(DisasContext *s, arg_CTERM *a, uint32_t insn) +{ + if (!sve_access_check(s)) { + return true; + } + + TCGCond cond = (a->ne ? TCG_COND_NE : TCG_COND_EQ); + TCGv_i64 rn = read_cpu_reg(s, a->rn, a->sf); + TCGv_i64 rm = read_cpu_reg(s, a->rm, a->sf); + TCGv_i64 cmp = tcg_temp_new_i64(); + + tcg_gen_setcond_i64(cond, cmp, rn, rm); + tcg_gen_extrl_i64_i32(cpu_NF, cmp); + tcg_temp_free_i64(cmp); + + /* VF = !NF & !CF. */ + tcg_gen_xori_i32(cpu_VF, cpu_NF, 1); + tcg_gen_andc_i32(cpu_VF, cpu_VF, cpu_CF); + + /* Both NF and VF actually look at bit 31. */ + tcg_gen_neg_i32(cpu_NF, cpu_NF); + tcg_gen_neg_i32(cpu_VF, cpu_VF); + return true; +} + +static bool trans_WHILE(DisasContext *s, arg_WHILE *a, uint32_t insn) +{ + if (!sve_access_check(s)) { + return true; + } + + TCGv_i64 op0 = read_cpu_reg(s, a->rn, 1); + TCGv_i64 op1 = read_cpu_reg(s, a->rm, 1); + TCGv_i64 t0 = tcg_temp_new_i64(); + TCGv_i64 t1 = tcg_temp_new_i64(); + TCGv_i32 t2, t3; + TCGv_ptr ptr; + unsigned desc, vsz = vec_full_reg_size(s); + TCGCond cond; + + if (!a->sf) { + if (a->u) { + tcg_gen_ext32u_i64(op0, op0); + tcg_gen_ext32u_i64(op1, op1); + } else { + tcg_gen_ext32s_i64(op0, op0); + tcg_gen_ext32s_i64(op1, op1); + } + } + + /* For the helper, compress the different conditions into a computation + * of how many iterations for which the condition is true. + * + * This is slightly complicated by 0 <= UINT64_MAX, which is nominally + * 2**64 iterations, overflowing to 0. Of course, predicate registers + * aren't that large, so any value >= predicate size is sufficient. + */ + tcg_gen_sub_i64(t0, op1, op0); + + /* t0 = MIN(op1 - op0, vsz). */ + tcg_gen_movi_i64(t1, vsz); + tcg_gen_umin_i64(t0, t0, t1); + if (a->eq) { + /* Equality means one more iteration. */ + tcg_gen_addi_i64(t0, t0, 1); + } + + /* t0 = (condition true ? t0 : 0). */ + cond = (a->u + ? (a->eq ? TCG_COND_LEU : TCG_COND_LTU) + : (a->eq ? TCG_COND_LE : TCG_COND_LT)); + tcg_gen_movi_i64(t1, 0); + tcg_gen_movcond_i64(cond, t0, op0, op1, t0, t1); + + t2 = tcg_temp_new_i32(); + tcg_gen_extrl_i64_i32(t2, t0); + tcg_temp_free_i64(t0); + tcg_temp_free_i64(t1); + + desc = (vsz / 8) - 2; + desc = deposit32(desc, SIMD_DATA_SHIFT, 2, a->esz); + t3 = tcg_const_i32(desc); + + ptr = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(ptr, cpu_env, pred_full_reg_offset(s, a->rd)); + + gen_helper_sve_while(t2, ptr, t2, t3); + do_pred_flags(t2); + + tcg_temp_free_ptr(ptr); + tcg_temp_free_i32(t2); + tcg_temp_free_i32(t3); + return true; +} + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SINCDECP_r_64 00100101 .. 1010 d:1 u:1 10001 10 .... ..... @incdec_pred # SVE saturating inc/dec vector by predicate count SINCDECP_z 00100101 .. 1010 d:1 u:1 10000 00 .... ..... @incdec2_pred +### SVE Integer Compare - Scalars Group + +# SVE conditionally terminate scalars +CTERM 00100101 1 sf:1 1 rm:5 001000 rn:5 ne:1 0000 + +# SVE integer compare scalar count and limit +WHILE 00100101 esz:2 1 rm:5 000 sf:1 u:1 1 rn:5 eq:1 rd:4 + ### SVE Memory - 32-bit Gather and Unsized Contiguous Group # SVE load predicate register -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 37 +++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 8 ++++++++ 2 files changed, 45 insertions(+) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a, uint32_t insn) return true; } +/* + *** SVE Integer Wide Immediate - Unpredicated Group + */ + +static bool trans_FDUP(DisasContext *s, arg_FDUP *a, uint32_t insn) +{ + if (a->esz == 0) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + int dofs = vec_full_reg_offset(s, a->rd); + uint64_t imm; + + /* Decode the VFP immediate. */ + imm = vfp_expand_imm(a->esz, a->imm); + imm = dup_const(a->esz, imm); + + tcg_gen_gvec_dup64i(dofs, vsz, vsz, imm); + } + return true; +} + +static bool trans_DUP_i(DisasContext *s, arg_DUP_i *a, uint32_t insn) +{ + if (a->esz == 0 && extract32(insn, 13, 1)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + int dofs = vec_full_reg_offset(s, a->rd); + + tcg_gen_gvec_dup64i(dofs, vsz, vsz, dup_const(a->esz, a->imm)); + } + return true; +} + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ CTERM 00100101 1 sf:1 1 rm:5 001000 rn:5 ne:1 0000 # SVE integer compare scalar count and limit WHILE 00100101 esz:2 1 rm:5 000 sf:1 u:1 1 rn:5 eq:1 rd:4 +### SVE Integer Wide Immediate - Unpredicated Group + +# SVE broadcast floating-point immediate (unpredicated) +FDUP 00100101 esz:2 111 00 1110 imm:8 rd:5 + +# SVE broadcast integer immediate (unpredicated) +DUP_i 00100101 esz:2 111 00 011 . ........ rd:5 imm=%sh8_i8s + ### SVE Memory - 32-bit Gather and Unsized Contiguous Group # SVE load predicate register -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 25 +++++++ target/arm/sve_helper.c | 41 +++++++++++ target/arm/translate-sve.c | 144 +++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 26 +++++++ 4 files changed, 236 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_brkns, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_while, TCG_CALL_NO_RWG, i32, ptr, i32, i32) + +DEF_HELPER_FLAGS_4(sve_subri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_subri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_subri_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_subri_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) + +DEF_HELPER_FLAGS_4(sve_smaxi_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_smaxi_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_smaxi_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_smaxi_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) + +DEF_HELPER_FLAGS_4(sve_smini_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_smini_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_smini_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_smini_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) + +DEF_HELPER_FLAGS_4(sve_umaxi_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_umaxi_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_umaxi_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_umaxi_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) + +DEF_HELPER_FLAGS_4(sve_umini_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_umini_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_umini_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(sve_umini_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VPZ_D(sve_uminv_d, uint64_t, uint64_t, -1, DO_MIN) #undef DO_VPZ #undef DO_VPZ_D +/* Two vector operand, one scalar operand, unpredicated. */ +#define DO_ZZI(NAME, TYPE, OP) \ +void HELPER(NAME)(void *vd, void *vn, uint64_t s64, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc) / sizeof(TYPE); \ + TYPE s = s64, *d = vd, *n = vn; \ + for (i = 0; i < opr_sz; ++i) { \ + d[i] = OP(n[i], s); \ + } \ +} + +#define DO_SUBR(X, Y) (Y - X) + +DO_ZZI(sve_subri_b, uint8_t, DO_SUBR) +DO_ZZI(sve_subri_h, uint16_t, DO_SUBR) +DO_ZZI(sve_subri_s, uint32_t, DO_SUBR) +DO_ZZI(sve_subri_d, uint64_t, DO_SUBR) + +DO_ZZI(sve_smaxi_b, int8_t, DO_MAX) +DO_ZZI(sve_smaxi_h, int16_t, DO_MAX) +DO_ZZI(sve_smaxi_s, int32_t, DO_MAX) +DO_ZZI(sve_smaxi_d, int64_t, DO_MAX) + +DO_ZZI(sve_smini_b, int8_t, DO_MIN) +DO_ZZI(sve_smini_h, int16_t, DO_MIN) +DO_ZZI(sve_smini_s, int32_t, DO_MIN) +DO_ZZI(sve_smini_d, int64_t, DO_MIN) + +DO_ZZI(sve_umaxi_b, uint8_t, DO_MAX) +DO_ZZI(sve_umaxi_h, uint16_t, DO_MAX) +DO_ZZI(sve_umaxi_s, uint32_t, DO_MAX) +DO_ZZI(sve_umaxi_d, uint64_t, DO_MAX) + +DO_ZZI(sve_umini_b, uint8_t, DO_MIN) +DO_ZZI(sve_umini_h, uint16_t, DO_MIN) +DO_ZZI(sve_umini_s, uint32_t, DO_MIN) +DO_ZZI(sve_umini_d, uint64_t, DO_MIN) + +#undef DO_ZZI + #undef DO_AND #undef DO_ORR #undef DO_EOR @@ -XXX,XX +XXX,XX @@ DO_VPZ_D(sve_uminv_d, uint64_t, uint64_t, -1, DO_MIN) #undef DO_ASR #undef DO_LSR #undef DO_LSL +#undef DO_SUBR /* Similar to the ARM LastActiveElement pseudocode function, except the result is multiplied by the element size. This includes the not found diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static inline int expand_imm_sh8s(int x) return (int8_t)x << (x & 0x100 ? 8 : 0); } +static inline int expand_imm_sh8u(int x) +{ + return (uint8_t)x << (x & 0x100 ? 8 : 0); +} + /* * Include the generated decoder. */ @@ -XXX,XX +XXX,XX @@ static bool trans_DUP_i(DisasContext *s, arg_DUP_i *a, uint32_t insn) return true; } +static bool trans_ADD_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn) +{ + if (a->esz == 0 && extract32(insn, 13, 1)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_addi(a->esz, vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), a->imm, vsz, vsz); + } + return true; +} + +static bool trans_SUB_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn) +{ + a->imm = -a->imm; + return trans_ADD_zzi(s, a, insn); +} + +static bool trans_SUBR_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn) +{ + static const GVecGen2s op[4] = { + { .fni8 = tcg_gen_vec_sub8_i64, + .fniv = tcg_gen_sub_vec, + .fno = gen_helper_sve_subri_b, + .opc = INDEX_op_sub_vec, + .vece = MO_8, + .scalar_first = true }, + { .fni8 = tcg_gen_vec_sub16_i64, + .fniv = tcg_gen_sub_vec, + .fno = gen_helper_sve_subri_h, + .opc = INDEX_op_sub_vec, + .vece = MO_16, + .scalar_first = true }, + { .fni4 = tcg_gen_sub_i32, + .fniv = tcg_gen_sub_vec, + .fno = gen_helper_sve_subri_s, + .opc = INDEX_op_sub_vec, + .vece = MO_32, + .scalar_first = true }, + { .fni8 = tcg_gen_sub_i64, + .fniv = tcg_gen_sub_vec, + .fno = gen_helper_sve_subri_d, + .opc = INDEX_op_sub_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64, + .scalar_first = true } + }; + + if (a->esz == 0 && extract32(insn, 13, 1)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_i64 c = tcg_const_i64(a->imm); + tcg_gen_gvec_2s(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vsz, vsz, c, &op[a->esz]); + tcg_temp_free_i64(c); + } + return true; +} + +static bool trans_MUL_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn) +{ + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_muli(a->esz, vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), a->imm, vsz, vsz); + } + return true; +} + +static bool do_zzi_sat(DisasContext *s, arg_rri_esz *a, uint32_t insn, + bool u, bool d) +{ + if (a->esz == 0 && extract32(insn, 13, 1)) { + return false; + } + if (sve_access_check(s)) { + TCGv_i64 val = tcg_const_i64(a->imm); + do_sat_addsub_vec(s, a->esz, a->rd, a->rn, val, u, d); + tcg_temp_free_i64(val); + } + return true; +} + +static bool trans_SQADD_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn) +{ + return do_zzi_sat(s, a, insn, false, false); +} + +static bool trans_UQADD_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn) +{ + return do_zzi_sat(s, a, insn, true, false); +} + +static bool trans_SQSUB_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn) +{ + return do_zzi_sat(s, a, insn, false, true); +} + +static bool trans_UQSUB_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn) +{ + return do_zzi_sat(s, a, insn, true, true); +} + +static bool do_zzi_ool(DisasContext *s, arg_rri_esz *a, gen_helper_gvec_2i *fn) +{ + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_i64 c = tcg_const_i64(a->imm); + + tcg_gen_gvec_2i_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + c, vsz, vsz, 0, fn); + tcg_temp_free_i64(c); + } + return true; +} + +#define DO_ZZI(NAME, name) \ +static bool trans_##NAME##_zzi(DisasContext *s, arg_rri_esz *a, \ + uint32_t insn) \ +{ \ + static gen_helper_gvec_2i * const fns[4] = { \ + gen_helper_sve_##name##i_b, gen_helper_sve_##name##i_h, \ + gen_helper_sve_##name##i_s, gen_helper_sve_##name##i_d, \ + }; \ + return do_zzi_ool(s, a, fns[a->esz]); \ +} + +DO_ZZI(SMAX, smax) +DO_ZZI(UMAX, umax) +DO_ZZI(SMIN, smin) +DO_ZZI(UMIN, umin) + +#undef DO_ZZI + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ # Signed 8-bit immediate, optionally shifted left by 8. %sh8_i8s 5:9 !function=expand_imm_sh8s +# Unsigned 8-bit immediate, optionally shifted left by 8. +%sh8_i8u 5:9 !function=expand_imm_sh8u # Either a copy of rd (at bit 0), or a different source # as propagated via the MOVPRFX instruction. @@ -XXX,XX +XXX,XX @@ @pd_pn_pm ........ esz:2 .. rm:4 ....... rn:4 . rd:4 &rrr_esz @rdn_rm ........ esz:2 ...... ...... rm:5 rd:5 \ &rrr_esz rn=%reg_movprfx +@rdn_sh_i8u ........ esz:2 ...... ...... ..... rd:5 \ + &rri_esz rn=%reg_movprfx imm=%sh8_i8u +@rdn_i8u ........ esz:2 ...... ... imm:8 rd:5 \ + &rri_esz rn=%reg_movprfx +@rdn_i8s ........ esz:2 ...... ... imm:s8 rd:5 \ + &rri_esz rn=%reg_movprfx # Three operand with "memory" size, aka immediate left shift @rd_rn_msz_rm ........ ... rm:5 .... imm:2 rn:5 rd:5 &rrri @@ -XXX,XX +XXX,XX @@ FDUP 00100101 esz:2 111 00 1110 imm:8 rd:5 # SVE broadcast integer immediate (unpredicated) DUP_i 00100101 esz:2 111 00 011 . ........ rd:5 imm=%sh8_i8s +# SVE integer add/subtract immediate (unpredicated) +ADD_zzi 00100101 .. 100 000 11 . ........ ..... @rdn_sh_i8u +SUB_zzi 00100101 .. 100 001 11 . ........ ..... @rdn_sh_i8u +SUBR_zzi 00100101 .. 100 011 11 . ........ ..... @rdn_sh_i8u +SQADD_zzi 00100101 .. 100 100 11 . ........ ..... @rdn_sh_i8u +UQADD_zzi 00100101 .. 100 101 11 . ........ ..... @rdn_sh_i8u +SQSUB_zzi 00100101 .. 100 110 11 . ........ ..... @rdn_sh_i8u +UQSUB_zzi 00100101 .. 100 111 11 . ........ ..... @rdn_sh_i8u + +# SVE integer min/max immediate (unpredicated) +SMAX_zzi 00100101 .. 101 000 110 ........ ..... @rdn_i8s +UMAX_zzi 00100101 .. 101 001 110 ........ ..... @rdn_i8u +SMIN_zzi 00100101 .. 101 010 110 ........ ..... @rdn_i8s +UMIN_zzi 00100101 .. 101 011 110 ........ ..... @rdn_i8u + +# SVE integer multiply immediate (unpredicated) +MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s + ### SVE Memory - 32-bit Gather and Unsized Contiguous Group # SVE load predicate register -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180613015641.5667-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 14 ++++++++ target/arm/helper.h | 19 +++++++++++ target/arm/translate-sve.c | 42 +++++++++++++++++++++++ target/arm/vec_helper.c | 69 ++++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 10 ++++++ 5 files changed, 154 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_umini_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_umini_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_umini_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_umini_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) + +DEF_HELPER_FLAGS_5(gvec_recps_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_recps_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_recps_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_rsqrts_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_rsqrts_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_rsqrts_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fcmlas_idx, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_fcmlad, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fsub_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fsub_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fsub_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmul_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmul_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_ftsmul_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_ZZI(UMIN, umin) #undef DO_ZZI +/* + *** SVE Floating Point Arithmetic - Unpredicated Group + */ + +static bool do_zzz_fp(DisasContext *s, arg_rrr_esz *a, + gen_helper_gvec_3_ptr *fn) +{ + if (fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16); + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + status, vsz, vsz, 0, fn); + tcg_temp_free_ptr(status); + } + return true; +} + + +#define DO_FP3(NAME, name) \ +static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a, uint32_t insn) \ +{ \ + static gen_helper_gvec_3_ptr * const fns[4] = { \ + NULL, gen_helper_gvec_##name##_h, \ + gen_helper_gvec_##name##_s, gen_helper_gvec_##name##_d \ + }; \ + return do_zzz_fp(s, a, fns[a->esz]); \ +} + +DO_FP3(FADD_zzz, fadd) +DO_FP3(FSUB_zzz, fsub) +DO_FP3(FMUL_zzz, fmul) +DO_FP3(FTSMUL, ftsmul) +DO_FP3(FRECPS, recps) +DO_FP3(FRSQRTS, rsqrts) + +#undef DO_FP3 + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ 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_fcmlad)(void *vd, void *vn, void *vm, } clear_tail(d, opr_sz, simd_maxsz(desc)); } + +/* Floating-point trigonometric starting value. + * See the ARM ARM pseudocode function FPTrigSMul. + */ +static float16 float16_ftsmul(float16 op1, uint16_t op2, float_status *stat) +{ + float16 result = float16_mul(op1, op1, stat); + if (!float16_is_any_nan(result)) { + result = float16_set_sign(result, op2 & 1); + } + return result; +} + +static float32 float32_ftsmul(float32 op1, uint32_t op2, float_status *stat) +{ + float32 result = float32_mul(op1, op1, stat); + if (!float32_is_any_nan(result)) { + result = float32_set_sign(result, op2 & 1); + } + return result; +} + +static float64 float64_ftsmul(float64 op1, uint64_t op2, float_status *stat) +{ + float64 result = float64_mul(op1, op1, stat); + if (!float64_is_any_nan(result)) { + result = float64_set_sign(result, op2 & 1); + } + return result; +} + +#define DO_3OP(NAME, FUNC, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + TYPE *d = vd, *n = vn, *m = vm; \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + d[i] = FUNC(n[i], m[i], stat); \ + } \ +} + +DO_3OP(gvec_fadd_h, float16_add, float16) +DO_3OP(gvec_fadd_s, float32_add, float32) +DO_3OP(gvec_fadd_d, float64_add, float64) + +DO_3OP(gvec_fsub_h, float16_sub, float16) +DO_3OP(gvec_fsub_s, float32_sub, float32) +DO_3OP(gvec_fsub_d, float64_sub, float64) + +DO_3OP(gvec_fmul_h, float16_mul, float16) +DO_3OP(gvec_fmul_s, float32_mul, float32) +DO_3OP(gvec_fmul_d, float64_mul, float64) + +DO_3OP(gvec_ftsmul_h, float16_ftsmul, float16) +DO_3OP(gvec_ftsmul_s, float32_ftsmul, float32) +DO_3OP(gvec_ftsmul_d, float64_ftsmul, float64) + +#ifdef TARGET_AARCH64 + +DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) +DO_3OP(gvec_recps_s, helper_recpsf_f32, float32) +DO_3OP(gvec_recps_d, helper_recpsf_f64, float64) + +DO_3OP(gvec_rsqrts_h, helper_rsqrtsf_f16, float16) +DO_3OP(gvec_rsqrts_s, helper_rsqrtsf_f32, float32) +DO_3OP(gvec_rsqrts_d, helper_rsqrtsf_f64, float64) + +#endif +#undef DO_3OP diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UMIN_zzi 00100101 .. 101 011 110 ........ ..... @rdn_i8u # SVE integer multiply immediate (unpredicated) MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s +### SVE Floating Point Arithmetic - Unpredicated Group + +# SVE floating-point arithmetic (unpredicated) +FADD_zzz 01100101 .. 0 ..... 000 000 ..... ..... @rd_rn_rm +FSUB_zzz 01100101 .. 0 ..... 000 001 ..... ..... @rd_rn_rm +FMUL_zzz 01100101 .. 0 ..... 000 010 ..... ..... @rd_rn_rm +FTSMUL 01100101 .. 0 ..... 000 011 ..... ..... @rd_rn_rm +FRECPS 01100101 .. 0 ..... 000 110 ..... ..... @rd_rn_rm +FRSQRTS 01100101 .. 0 ..... 000 111 ..... ..... @rd_rn_rm + ### SVE Memory - 32-bit Gather and Unsized Contiguous Group # SVE load predicate register -- 2.17.1 From: Joel Stanley <joel@jms.id.au> The ASPEED SoCs contain a single register that returns random data when read. This models that register so that guests can use it. The random number data register has a corresponding control register, however it returns data regardless of the state of the enabled bit, so the model follows this behaviour. When the qcrypto call fails we exit as the guest uses the random number device to feed it's entropy pool, which is used for cryptographic purposes. Reviewed-by: Cédric Le Goater <clg@kaod.org> Signed-off-by: Joel Stanley <joel@jms.id.au> Message-id: 20180613114836.9265-1-joel@jms.id.au Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/aspeed_scu.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/hw/misc/aspeed_scu.c b/hw/misc/aspeed_scu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/aspeed_scu.c +++ b/hw/misc/aspeed_scu.c @@ -XXX,XX +XXX,XX @@ #include "qapi/visitor.h" #include "qemu/bitops.h" #include "qemu/log.h" +#include "crypto/random.h" #include "trace.h" #define TO_REG(offset) ((offset) >> 2) @@ -XXX,XX +XXX,XX @@ static const uint32_t ast2500_a1_resets[ASPEED_SCU_NR_REGS] = { [BMC_DEV_ID] = 0x00002402U }; +static uint32_t aspeed_scu_get_random(void) +{ + Error *err = NULL; + uint32_t num; + + if (qcrypto_random_bytes((uint8_t *)&num, sizeof(num), &err)) { + error_report_err(err); + exit(1); + } + + return num; +} + static uint64_t aspeed_scu_read(void *opaque, hwaddr offset, unsigned size) { AspeedSCUState *s = ASPEED_SCU(opaque); @@ -XXX,XX +XXX,XX @@ static uint64_t aspeed_scu_read(void *opaque, hwaddr offset, unsigned size) } switch (reg) { + case RNG_DATA: + /* On hardware, RNG_DATA works regardless of + * the state of the enable bit in RNG_CTRL + */ + s->regs[RNG_DATA] = aspeed_scu_get_random(); + break; case WAKEUP_EN: qemu_log_mask(LOG_GUEST_ERROR, "%s: Read of write-only offset 0x%" HWADDR_PRIx "\n", -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> On Macronix chips, two bytes can written to the WRSR. First byte will configure the status register and the second the configuration register. It is important to save the configuration value as it contains the dummy cycle setting when using dual or quad IO mode. Signed-off-by: Cédric Le Goater <clg@kaod.org> Acked-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/block/m25p80.c | 1 + 1 file changed, 1 insertion(+) diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/m25p80.c +++ b/hw/block/m25p80.c @@ -XXX,XX +XXX,XX @@ static void complete_collecting_data(Flash *s) case MAN_MACRONIX: s->quad_enable = extract32(s->data[0], 6, 1); if (s->len > 1) { + s->volatile_cfg = s->data[1]; s->four_bytes_address_mode = extract32(s->data[1], 5, 1); } break; -- 2.17.1 If an IOMMU supports mappings that care about the memory transaction attributes, then it no longer has a unique address -> output mapping, but more than one. We can represent these using an IOMMU index, analogous to TCG's mmu indexes. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180604152941.20374-2-peter.maydell@linaro.org --- include/exec/memory.h | 55 +++++++++++++++++++++++++++++++++++++++++++ memory.c | 23 ++++++++++++++++++ 2 files changed, 78 insertions(+) diff --git a/include/exec/memory.h b/include/exec/memory.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -XXX,XX +XXX,XX @@ enum IOMMUMemoryRegionAttr { * to report whenever mappings are changed, by calling * memory_region_notify_iommu() (or, if necessary, by calling * memory_region_notify_one() for each registered notifier). + * + * Conceptually an IOMMU provides a mapping from input address + * to an output TLB entry. If the IOMMU is aware of memory transaction + * attributes and the output TLB entry depends on the transaction + * attributes, we represent this using IOMMU indexes. Each index + * selects a particular translation table that the IOMMU has: + * @attrs_to_index returns the IOMMU index for a set of transaction attributes + * @translate takes an input address and an IOMMU index + * and the mapping returned can only depend on the input address and the + * IOMMU index. + * + * Most IOMMUs don't care about the transaction attributes and support + * only a single IOMMU index. A more complex IOMMU might have one index + * for secure transactions and one for non-secure transactions. */ typedef struct IOMMUMemoryRegionClass { /* private */ @@ -XXX,XX +XXX,XX @@ typedef struct IOMMUMemoryRegionClass { */ int (*get_attr)(IOMMUMemoryRegion *iommu, enum IOMMUMemoryRegionAttr attr, void *data); + + /* Return the IOMMU index to use for a given set of transaction attributes. + * + * Optional method: if an IOMMU only supports a single IOMMU index then + * the default implementation of memory_region_iommu_attrs_to_index() + * will return 0. + * + * The indexes supported by an IOMMU must be contiguous, starting at 0. + * + * @iommu: the IOMMUMemoryRegion + * @attrs: memory transaction attributes + */ + int (*attrs_to_index)(IOMMUMemoryRegion *iommu, MemTxAttrs attrs); + + /* Return the number of IOMMU indexes this IOMMU supports. + * + * Optional method: if this method is not provided, then + * memory_region_iommu_num_indexes() will return 1, indicating that + * only a single IOMMU index is supported. + * + * @iommu: the IOMMUMemoryRegion + */ + int (*num_indexes)(IOMMUMemoryRegion *iommu); } IOMMUMemoryRegionClass; typedef struct CoalescedMemoryRange CoalescedMemoryRange; @@ -XXX,XX +XXX,XX @@ int memory_region_iommu_get_attr(IOMMUMemoryRegion *iommu_mr, enum IOMMUMemoryRegionAttr attr, void *data); +/** + * memory_region_iommu_attrs_to_index: return the IOMMU index to + * use for translations with the given memory transaction attributes. + * + * @iommu_mr: the memory region + * @attrs: the memory transaction attributes + */ +int memory_region_iommu_attrs_to_index(IOMMUMemoryRegion *iommu_mr, + MemTxAttrs attrs); + +/** + * memory_region_iommu_num_indexes: return the total number of IOMMU + * indexes that this IOMMU supports. + * + * @iommu_mr: the memory region + */ +int memory_region_iommu_num_indexes(IOMMUMemoryRegion *iommu_mr); + /** * memory_region_name: get a memory region's name * diff --git a/memory.c b/memory.c index XXXXXXX..XXXXXXX 100644 --- a/memory.c +++ b/memory.c @@ -XXX,XX +XXX,XX @@ int memory_region_iommu_get_attr(IOMMUMemoryRegion *iommu_mr, return imrc->get_attr(iommu_mr, attr, data); } +int memory_region_iommu_attrs_to_index(IOMMUMemoryRegion *iommu_mr, + MemTxAttrs attrs) +{ + IOMMUMemoryRegionClass *imrc = IOMMU_MEMORY_REGION_GET_CLASS(iommu_mr); + + if (!imrc->attrs_to_index) { + return 0; + } + + return imrc->attrs_to_index(iommu_mr, attrs); +} + +int memory_region_iommu_num_indexes(IOMMUMemoryRegion *iommu_mr) +{ + IOMMUMemoryRegionClass *imrc = IOMMU_MEMORY_REGION_GET_CLASS(iommu_mr); + + if (!imrc->num_indexes) { + return 1; + } + + return imrc->num_indexes(iommu_mr); +} + void memory_region_set_log(MemoryRegion *mr, bool log, unsigned client) { uint8_t mask = 1 << client; -- 2.17.1 Add support for multiple IOMMU indexes to the IOMMU notifier APIs. When initializing a notifier with iommu_notifier_init(), the caller must pass the IOMMU index that it is interested in. When a change happens, the IOMMU implementation must pass memory_region_notify_iommu() the IOMMU index that has changed and that notifiers must be called for. IOMMUs which support only a single index don't need to change. Callers which only really support working with IOMMUs with a single index can use the result of passing MEMTXATTRS_UNSPECIFIED to memory_region_iommu_attrs_to_index(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180604152941.20374-3-peter.maydell@linaro.org --- include/exec/memory.h | 7 ++++++- hw/i386/intel_iommu.c | 6 +++--- hw/ppc/spapr_iommu.c | 2 +- hw/s390x/s390-pci-inst.c | 4 ++-- hw/vfio/common.c | 6 +++++- hw/virtio/vhost.c | 7 ++++++- memory.c | 8 +++++++- 7 files changed, 30 insertions(+), 10 deletions(-) diff --git a/include/exec/memory.h b/include/exec/memory.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -XXX,XX +XXX,XX @@ struct IOMMUNotifier { /* Notify for address space range start <= addr <= end */ hwaddr start; hwaddr end; + int iommu_idx; QLIST_ENTRY(IOMMUNotifier) node; }; typedef struct IOMMUNotifier IOMMUNotifier; static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn, IOMMUNotifierFlag flags, - hwaddr start, hwaddr end) + hwaddr start, hwaddr end, + int iommu_idx) { n->notify = fn; n->notifier_flags = flags; n->start = start; n->end = end; + n->iommu_idx = iommu_idx; } /* @@ -XXX,XX +XXX,XX @@ uint64_t memory_region_iommu_get_min_page_size(IOMMUMemoryRegion *iommu_mr); * should be notified with an UNMAP followed by a MAP. * * @iommu_mr: the memory region that was changed + * @iommu_idx: the IOMMU index for the translation table which has changed * @entry: the new entry in the IOMMU translation table. The entry * replaces all old entries for the same virtual I/O address range. * Deleted entries have .@perm == 0. */ void memory_region_notify_iommu(IOMMUMemoryRegion *iommu_mr, + int iommu_idx, IOMMUTLBEntry entry); /** diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -XXX,XX +XXX,XX @@ static int vtd_dev_to_context_entry(IntelIOMMUState *s, uint8_t bus_num, static int vtd_sync_shadow_page_hook(IOMMUTLBEntry *entry, void *private) { - memory_region_notify_iommu((IOMMUMemoryRegion *)private, *entry); + memory_region_notify_iommu((IOMMUMemoryRegion *)private, 0, *entry); return 0; } @@ -XXX,XX +XXX,XX @@ static void vtd_iotlb_page_invalidate_notify(IntelIOMMUState *s, .addr_mask = size - 1, .perm = IOMMU_NONE, }; - memory_region_notify_iommu(&vtd_as->iommu, entry); + memory_region_notify_iommu(&vtd_as->iommu, 0, entry); } } } @@ -XXX,XX +XXX,XX @@ static bool vtd_process_device_iotlb_desc(IntelIOMMUState *s, entry.iova = addr; entry.perm = IOMMU_NONE; entry.translated_addr = 0; - memory_region_notify_iommu(&vtd_dev_as->iommu, entry); + memory_region_notify_iommu(&vtd_dev_as->iommu, 0, entry); done: return true; diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ppc/spapr_iommu.c +++ b/hw/ppc/spapr_iommu.c @@ -XXX,XX +XXX,XX @@ static target_ulong put_tce_emu(sPAPRTCETable *tcet, target_ulong ioba, entry.translated_addr = tce & page_mask; entry.addr_mask = ~page_mask; entry.perm = spapr_tce_iommu_access_flags(tce); - memory_region_notify_iommu(&tcet->iommu, entry); + memory_region_notify_iommu(&tcet->iommu, 0, entry); return H_SUCCESS; } diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c index XXXXXXX..XXXXXXX 100644 --- a/hw/s390x/s390-pci-inst.c +++ b/hw/s390x/s390-pci-inst.c @@ -XXX,XX +XXX,XX @@ static void s390_pci_update_iotlb(S390PCIIOMMU *iommu, S390IOTLBEntry *entry) } notify.perm = IOMMU_NONE; - memory_region_notify_iommu(&iommu->iommu_mr, notify); + memory_region_notify_iommu(&iommu->iommu_mr, 0, notify); notify.perm = entry->perm; } @@ -XXX,XX +XXX,XX @@ static void s390_pci_update_iotlb(S390PCIIOMMU *iommu, S390IOTLBEntry *entry) g_hash_table_replace(iommu->iotlb, &cache->iova, cache); } - memory_region_notify_iommu(&iommu->iommu_mr, notify); + memory_region_notify_iommu(&iommu->iommu_mr, 0, notify); } int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -XXX,XX +XXX,XX @@ static void vfio_listener_region_add(MemoryListener *listener, if (memory_region_is_iommu(section->mr)) { VFIOGuestIOMMU *giommu; IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr); + int iommu_idx; trace_vfio_listener_region_add_iommu(iova, end); /* @@ -XXX,XX +XXX,XX @@ static void vfio_listener_region_add(MemoryListener *listener, llend = int128_add(int128_make64(section->offset_within_region), section->size); llend = int128_sub(llend, int128_one()); + iommu_idx = memory_region_iommu_attrs_to_index(iommu_mr, + MEMTXATTRS_UNSPECIFIED); iommu_notifier_init(&giommu->n, vfio_iommu_map_notify, IOMMU_NOTIFIER_ALL, section->offset_within_region, - int128_get64(llend)); + int128_get64(llend), + iommu_idx); QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next); memory_region_register_iommu_notifier(section->mr, &giommu->n); diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index XXXXXXX..XXXXXXX 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -XXX,XX +XXX,XX @@ static void vhost_iommu_region_add(MemoryListener *listener, iommu_listener); struct vhost_iommu *iommu; Int128 end; + int iommu_idx; + IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr); if (!memory_region_is_iommu(section->mr)) { return; @@ -XXX,XX +XXX,XX @@ static void vhost_iommu_region_add(MemoryListener *listener, end = int128_add(int128_make64(section->offset_within_region), section->size); end = int128_sub(end, int128_one()); + iommu_idx = memory_region_iommu_attrs_to_index(iommu_mr, + MEMTXATTRS_UNSPECIFIED); iommu_notifier_init(&iommu->n, vhost_iommu_unmap_notify, IOMMU_NOTIFIER_UNMAP, section->offset_within_region, - int128_get64(end)); + int128_get64(end), + iommu_idx); iommu->mr = section->mr; iommu->iommu_offset = section->offset_within_address_space - section->offset_within_region; diff --git a/memory.c b/memory.c index XXXXXXX..XXXXXXX 100644 --- a/memory.c +++ b/memory.c @@ -XXX,XX +XXX,XX @@ void memory_region_register_iommu_notifier(MemoryRegion *mr, iommu_mr = IOMMU_MEMORY_REGION(mr); assert(n->notifier_flags != IOMMU_NOTIFIER_NONE); assert(n->start <= n->end); + assert(n->iommu_idx >= 0 && + n->iommu_idx < memory_region_iommu_num_indexes(iommu_mr)); + QLIST_INSERT_HEAD(&iommu_mr->iommu_notify, n, node); memory_region_update_iommu_notify_flags(iommu_mr); } @@ -XXX,XX +XXX,XX @@ void memory_region_notify_one(IOMMUNotifier *notifier, } void memory_region_notify_iommu(IOMMUMemoryRegion *iommu_mr, + int iommu_idx, IOMMUTLBEntry entry) { IOMMUNotifier *iommu_notifier; @@ -XXX,XX +XXX,XX @@ void memory_region_notify_iommu(IOMMUMemoryRegion *iommu_mr, assert(memory_region_is_iommu(MEMORY_REGION(iommu_mr))); IOMMU_NOTIFIER_FOREACH(iommu_notifier, iommu_mr) { - memory_region_notify_one(iommu_notifier, &entry); + if (iommu_notifier->iommu_idx == iommu_idx) { + memory_region_notify_one(iommu_notifier, &entry); + } } } -- 2.17.1 Add an IOMMU index argument to the translate method of IOMMUs. Since all of our current IOMMU implementations support only a single IOMMU index, this has no effect on the behaviour. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180604152941.20374-4-peter.maydell@linaro.org --- include/exec/memory.h | 3 ++- exec.c | 11 +++++++++-- hw/alpha/typhoon.c | 3 ++- hw/arm/smmuv3.c | 2 +- hw/dma/rc4030.c | 2 +- hw/i386/amd_iommu.c | 2 +- hw/i386/intel_iommu.c | 2 +- hw/ppc/spapr_iommu.c | 3 ++- hw/s390x/s390-pci-bus.c | 2 +- hw/sparc/sun4m_iommu.c | 3 ++- hw/sparc64/sun4u_iommu.c | 2 +- memory.c | 2 +- 12 files changed, 24 insertions(+), 13 deletions(-) diff --git a/include/exec/memory.h b/include/exec/memory.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -XXX,XX +XXX,XX @@ typedef struct IOMMUMemoryRegionClass { * @iommu: the IOMMUMemoryRegion * @hwaddr: address to be translated within the memory region * @flag: requested access permissions + * @iommu_idx: IOMMU index for the translation */ IOMMUTLBEntry (*translate)(IOMMUMemoryRegion *iommu, hwaddr addr, - IOMMUAccessFlags flag); + IOMMUAccessFlags flag, int iommu_idx); /* Returns minimum supported page size in bytes. * If this method is not provided then the minimum is assumed to * be TARGET_PAGE_SIZE. diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static MemoryRegionSection address_space_translate_iommu(IOMMUMemoryRegion *iomm do { hwaddr addr = *xlat; IOMMUMemoryRegionClass *imrc = memory_region_get_iommu_class_nocheck(iommu_mr); - IOMMUTLBEntry iotlb = imrc->translate(iommu_mr, addr, is_write ? - IOMMU_WO : IOMMU_RO); + int iommu_idx = 0; + IOMMUTLBEntry iotlb; + + if (imrc->attrs_to_index) { + iommu_idx = imrc->attrs_to_index(iommu_mr, attrs); + } + + iotlb = imrc->translate(iommu_mr, addr, is_write ? + IOMMU_WO : IOMMU_RO, iommu_idx); if (!(iotlb.perm & (1 << is_write))) { goto unassigned; diff --git a/hw/alpha/typhoon.c b/hw/alpha/typhoon.c index XXXXXXX..XXXXXXX 100644 --- a/hw/alpha/typhoon.c +++ b/hw/alpha/typhoon.c @@ -XXX,XX +XXX,XX @@ static bool window_translate(TyphoonWindow *win, hwaddr addr, Pchip and generate a machine check interrupt. */ static IOMMUTLBEntry typhoon_translate_iommu(IOMMUMemoryRegion *iommu, hwaddr addr, - IOMMUAccessFlags flag) + IOMMUAccessFlags flag, + int iommu_idx) { TyphoonPchip *pchip = container_of(iommu, TyphoonPchip, iommu); IOMMUTLBEntry ret; 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 @@ static int smmuv3_decode_config(IOMMUMemoryRegion *mr, SMMUTransCfg *cfg, } static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr, - IOMMUAccessFlags flag) + IOMMUAccessFlags flag, int iommu_idx) { SMMUDevice *sdev = container_of(mr, SMMUDevice, iommu); SMMUv3State *s = sdev->smmu; diff --git a/hw/dma/rc4030.c b/hw/dma/rc4030.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/rc4030.c +++ b/hw/dma/rc4030.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps jazzio_ops = { }; static IOMMUTLBEntry rc4030_dma_translate(IOMMUMemoryRegion *iommu, hwaddr addr, - IOMMUAccessFlags flag) + IOMMUAccessFlags flag, int iommu_idx) { rc4030State *s = container_of(iommu, rc4030State, dma_mr); IOMMUTLBEntry ret = { diff --git a/hw/i386/amd_iommu.c b/hw/i386/amd_iommu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i386/amd_iommu.c +++ b/hw/i386/amd_iommu.c @@ -XXX,XX +XXX,XX @@ static inline bool amdvi_is_interrupt_addr(hwaddr addr) } static IOMMUTLBEntry amdvi_translate(IOMMUMemoryRegion *iommu, hwaddr addr, - IOMMUAccessFlags flag) + IOMMUAccessFlags flag, int iommu_idx) { AMDVIAddressSpace *as = container_of(iommu, AMDVIAddressSpace, iommu); AMDVIState *s = as->iommu_state; diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -XXX,XX +XXX,XX @@ static void vtd_mem_write(void *opaque, hwaddr addr, } static IOMMUTLBEntry vtd_iommu_translate(IOMMUMemoryRegion *iommu, hwaddr addr, - IOMMUAccessFlags flag) + IOMMUAccessFlags flag, int iommu_idx) { VTDAddressSpace *vtd_as = container_of(iommu, VTDAddressSpace, iommu); IntelIOMMUState *s = vtd_as->iommu_state; diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ppc/spapr_iommu.c +++ b/hw/ppc/spapr_iommu.c @@ -XXX,XX +XXX,XX @@ static void spapr_tce_free_table(uint64_t *table, int fd, uint32_t nb_table) /* Called from RCU critical section */ static IOMMUTLBEntry spapr_tce_translate_iommu(IOMMUMemoryRegion *iommu, hwaddr addr, - IOMMUAccessFlags flag) + IOMMUAccessFlags flag, + int iommu_idx) { sPAPRTCETable *tcet = container_of(iommu, sPAPRTCETable, iommu); uint64_t tce; diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c index XXXXXXX..XXXXXXX 100644 --- a/hw/s390x/s390-pci-bus.c +++ b/hw/s390x/s390-pci-bus.c @@ -XXX,XX +XXX,XX @@ uint16_t s390_guest_io_table_walk(uint64_t g_iota, hwaddr addr, } static IOMMUTLBEntry s390_translate_iommu(IOMMUMemoryRegion *mr, hwaddr addr, - IOMMUAccessFlags flag) + IOMMUAccessFlags flag, int iommu_idx) { S390PCIIOMMU *iommu = container_of(mr, S390PCIIOMMU, iommu_mr); S390IOTLBEntry *entry; diff --git a/hw/sparc/sun4m_iommu.c b/hw/sparc/sun4m_iommu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sparc/sun4m_iommu.c +++ b/hw/sparc/sun4m_iommu.c @@ -XXX,XX +XXX,XX @@ static void iommu_bad_addr(IOMMUState *s, hwaddr addr, /* Called from RCU critical section */ static IOMMUTLBEntry sun4m_translate_iommu(IOMMUMemoryRegion *iommu, hwaddr addr, - IOMMUAccessFlags flags) + IOMMUAccessFlags flags, + int iommu_idx) { IOMMUState *is = container_of(iommu, IOMMUState, iommu); hwaddr page, pa; diff --git a/hw/sparc64/sun4u_iommu.c b/hw/sparc64/sun4u_iommu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sparc64/sun4u_iommu.c +++ b/hw/sparc64/sun4u_iommu.c @@ -XXX,XX +XXX,XX @@ /* Called from RCU critical section */ static IOMMUTLBEntry sun4u_translate_iommu(IOMMUMemoryRegion *iommu, hwaddr addr, - IOMMUAccessFlags flag) + IOMMUAccessFlags flag, int iommu_idx) { IOMMUState *is = container_of(iommu, IOMMUState, iommu); hwaddr baseaddr, offset; diff --git a/memory.c b/memory.c index XXXXXXX..XXXXXXX 100644 --- a/memory.c +++ b/memory.c @@ -XXX,XX +XXX,XX @@ void memory_region_iommu_replay(IOMMUMemoryRegion *iommu_mr, IOMMUNotifier *n) granularity = memory_region_iommu_get_min_page_size(iommu_mr); for (addr = 0; addr < memory_region_size(mr); addr += granularity) { - iotlb = imrc->translate(iommu_mr, addr, IOMMU_NONE); + iotlb = imrc->translate(iommu_mr, addr, IOMMU_NONE, n->iommu_idx); if (iotlb.perm != IOMMU_NONE) { n->notify(n, &iotlb); } -- 2.17.1 Currently we don't support board configurations that put an IOMMU in the path of the CPU's memory transactions, and instead just assert() if the memory region fonud in address_space_translate_for_iotlb() is an IOMMUMemoryRegion. Remove this limitation by having the function handle IOMMUs. This is mostly straightforward, but we must make sure we have a notifier registered for every IOMMU that a transaction has passed through, so that we can flush the TLB appropriately when any of the IOMMUs change their mappings. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180604152941.20374-5-peter.maydell@linaro.org --- include/exec/exec-all.h | 3 +- include/qom/cpu.h | 3 + accel/tcg/cputlb.c | 3 +- exec.c | 135 +++++++++++++++++++++++++++++++++++++++- 4 files changed, 140 insertions(+), 4 deletions(-) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ void tb_flush_jmp_cache(CPUState *cpu, target_ulong addr); MemoryRegionSection * address_space_translate_for_iotlb(CPUState *cpu, int asidx, hwaddr addr, - hwaddr *xlat, hwaddr *plen); + hwaddr *xlat, hwaddr *plen, + MemTxAttrs attrs, int *prot); hwaddr memory_region_section_get_iotlb(CPUState *cpu, MemoryRegionSection *section, target_ulong vaddr, diff --git a/include/qom/cpu.h b/include/qom/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/include/qom/cpu.h +++ b/include/qom/cpu.h @@ -XXX,XX +XXX,XX @@ struct CPUState { uint16_t pending_tlb_flush; int hvf_fd; + + /* track IOMMUs whose translations we've cached in the TCG TLB */ + GArray *iommu_notifiers; }; QTAILQ_HEAD(CPUTailQ, CPUState); diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, } sz = size; - section = address_space_translate_for_iotlb(cpu, asidx, paddr, &xlat, &sz); + section = address_space_translate_for_iotlb(cpu, asidx, paddr, &xlat, &sz, + attrs, &prot); assert(sz >= TARGET_PAGE_SIZE); tlb_debug("vaddr=" TARGET_FMT_lx " paddr=0x" TARGET_FMT_plx diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ MemoryRegion *flatview_translate(FlatView *fv, hwaddr addr, hwaddr *xlat, return mr; } +typedef struct TCGIOMMUNotifier { + IOMMUNotifier n; + MemoryRegion *mr; + CPUState *cpu; + int iommu_idx; + bool active; +} TCGIOMMUNotifier; + +static void tcg_iommu_unmap_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) +{ + TCGIOMMUNotifier *notifier = container_of(n, TCGIOMMUNotifier, n); + + if (!notifier->active) { + return; + } + tlb_flush(notifier->cpu); + notifier->active = false; + /* We leave the notifier struct on the list to avoid reallocating it later. + * Generally the number of IOMMUs a CPU deals with will be small. + * In any case we can't unregister the iommu notifier from a notify + * callback. + */ +} + +static void tcg_register_iommu_notifier(CPUState *cpu, + IOMMUMemoryRegion *iommu_mr, + int iommu_idx) +{ + /* Make sure this CPU has an IOMMU notifier registered for this + * IOMMU/IOMMU index combination, so that we can flush its TLB + * when the IOMMU tells us the mappings we've cached have changed. + */ + MemoryRegion *mr = MEMORY_REGION(iommu_mr); + TCGIOMMUNotifier *notifier; + int i; + + for (i = 0; i < cpu->iommu_notifiers->len; i++) { + notifier = &g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier, i); + if (notifier->mr == mr && notifier->iommu_idx == iommu_idx) { + break; + } + } + if (i == cpu->iommu_notifiers->len) { + /* Not found, add a new entry at the end of the array */ + cpu->iommu_notifiers = g_array_set_size(cpu->iommu_notifiers, i + 1); + notifier = &g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier, i); + + notifier->mr = mr; + notifier->iommu_idx = iommu_idx; + notifier->cpu = cpu; + /* Rather than trying to register interest in the specific part + * of the iommu's address space that we've accessed and then + * expand it later as subsequent accesses touch more of it, we + * just register interest in the whole thing, on the assumption + * that iommu reconfiguration will be rare. + */ + iommu_notifier_init(&notifier->n, + tcg_iommu_unmap_notify, + IOMMU_NOTIFIER_UNMAP, + 0, + HWADDR_MAX, + iommu_idx); + memory_region_register_iommu_notifier(notifier->mr, &notifier->n); + } + + if (!notifier->active) { + notifier->active = true; + } +} + +static void tcg_iommu_free_notifier_list(CPUState *cpu) +{ + /* Destroy the CPU's notifier list */ + int i; + TCGIOMMUNotifier *notifier; + + for (i = 0; i < cpu->iommu_notifiers->len; i++) { + notifier = &g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier, i); + memory_region_unregister_iommu_notifier(notifier->mr, &notifier->n); + } + g_array_free(cpu->iommu_notifiers, true); +} + /* Called from RCU critical section */ MemoryRegionSection * address_space_translate_for_iotlb(CPUState *cpu, int asidx, hwaddr addr, - hwaddr *xlat, hwaddr *plen) + hwaddr *xlat, hwaddr *plen, + MemTxAttrs attrs, int *prot) { MemoryRegionSection *section; + IOMMUMemoryRegion *iommu_mr; + IOMMUMemoryRegionClass *imrc; + IOMMUTLBEntry iotlb; + int iommu_idx; AddressSpaceDispatch *d = atomic_rcu_read(&cpu->cpu_ases[asidx].memory_dispatch); - section = address_space_translate_internal(d, addr, xlat, plen, false); + for (;;) { + section = address_space_translate_internal(d, addr, &addr, plen, false); + + iommu_mr = memory_region_get_iommu(section->mr); + if (!iommu_mr) { + break; + } + + imrc = memory_region_get_iommu_class_nocheck(iommu_mr); + + iommu_idx = imrc->attrs_to_index(iommu_mr, attrs); + tcg_register_iommu_notifier(cpu, iommu_mr, iommu_idx); + /* We need all the permissions, so pass IOMMU_NONE so the IOMMU + * doesn't short-cut its translation table walk. + */ + iotlb = imrc->translate(iommu_mr, addr, IOMMU_NONE, iommu_idx); + addr = ((iotlb.translated_addr & ~iotlb.addr_mask) + | (addr & iotlb.addr_mask)); + /* Update the caller's prot bits to remove permissions the IOMMU + * is giving us a failure response for. If we get down to no + * permissions left at all we can give up now. + */ + if (!(iotlb.perm & IOMMU_RO)) { + *prot &= ~(PAGE_READ | PAGE_EXEC); + } + if (!(iotlb.perm & IOMMU_WO)) { + *prot &= ~PAGE_WRITE; + } + + if (!*prot) { + goto translate_fail; + } + + d = flatview_to_dispatch(address_space_to_flatview(iotlb.target_as)); + } assert(!memory_region_is_iommu(section->mr)); + *xlat = addr; return section; + +translate_fail: + return &d->map.sections[PHYS_SECTION_UNASSIGNED]; } #endif @@ -XXX,XX +XXX,XX @@ void cpu_exec_unrealizefn(CPUState *cpu) if (qdev_get_vmsd(DEVICE(cpu)) == NULL) { vmstate_unregister(NULL, &vmstate_cpu_common, cpu); } +#ifndef CONFIG_USER_ONLY + tcg_iommu_free_notifier_list(cpu); +#endif } Property cpu_common_props[] = { @@ -XXX,XX +XXX,XX @@ void cpu_exec_realizefn(CPUState *cpu, Error **errp) if (cc->vmsd != NULL) { vmstate_register(NULL, cpu->cpu_index, cc->vmsd, cpu); } + + cpu->iommu_notifiers = g_array_new(false, true, sizeof(TCGIOMMUNotifier)); #endif } -- 2.17.1 From: Julia Suvorova <jusual@mail.ru> ARMv6-M supports 6 Thumb2 instructions. This patch checks for these instructions and allows their execution. Like Thumb2 cores, ARMv6-M always interprets BL instruction as 32-bit. This patch is required for future Cortex-M0 support. Signed-off-by: Julia Suvorova <jusual@mail.ru> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20180612204632.28780-1-jusual@mail.ru [PMM: move armv6m_insn[] and armv6m_mask[] closer to point of use, and mark 'const'. Check for M-and-not-v7 rather than M-and-6.] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 43 +++++++++++++++++++++++++++++++++++++----- 1 file changed, 38 insertions(+), 5 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 bool thumb_insn_is_16bit(DisasContext *s, uint32_t insn) * end up actually treating this as two 16-bit insns, though, * if it's half of a bl/blx pair that might span a page boundary. */ - if (arm_dc_feature(s, ARM_FEATURE_THUMB2)) { + if (arm_dc_feature(s, ARM_FEATURE_THUMB2) || + arm_dc_feature(s, ARM_FEATURE_M)) { /* Thumb2 cores (including all M profile ones) always treat * 32-bit insns as 32-bit. */ @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) int conds; int logic_cc; - /* The only 32 bit insn that's allowed for Thumb1 is the combined - * BL/BLX prefix and suffix. + /* + * ARMv6-M supports a limited subset of Thumb2 instructions. + * Other Thumb1 architectures allow only 32-bit + * combined BL/BLX prefix and suffix. */ - if ((insn & 0xf800e800) != 0xf000e800) { + if (arm_dc_feature(s, ARM_FEATURE_M) && + !arm_dc_feature(s, ARM_FEATURE_V7)) { + int i; + bool found = false; + const uint32_t armv6m_insn[] = {0xf3808000 /* msr */, + 0xf3b08040 /* dsb */, + 0xf3b08050 /* dmb */, + 0xf3b08060 /* isb */, + 0xf3e08000 /* mrs */, + 0xf000d000 /* bl */}; + const uint32_t armv6m_mask[] = {0xffe0d000, + 0xfff0d0f0, + 0xfff0d0f0, + 0xfff0d0f0, + 0xffe0d000, + 0xf800d000}; + + for (i = 0; i < ARRAY_SIZE(armv6m_insn); i++) { + if ((insn & armv6m_mask[i]) == armv6m_insn[i]) { + found = true; + break; + } + } + if (!found) { + goto illegal_op; + } + } else if ((insn & 0xf800e800) != 0xf000e800) { ARCH(6T2); } @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) } break; case 3: /* Special control operations. */ - ARCH(7); + if (!arm_dc_feature(s, ARM_FEATURE_V7) && + !(arm_dc_feature(s, ARM_FEATURE_V6) && + arm_dc_feature(s, ARM_FEATURE_M))) { + goto illegal_op; + } op = (insn >> 4) & 0xf; switch (op) { case 2: /* clrex */ -- 2.17.1 First pullreq for 6.0: mostly my v8.1M work, plus some other bits and pieces. (I still have a lot of stuff in my to-review folder, which I may or may not get to before the Christmas break...) thanks -- PMM The following changes since commit 5e7b204dbfae9a562fc73684986f936b97f63877: Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging (2020-12-09 20:08:54 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20201210 for you to fetch changes up to 71f916be1c7e9ede0e37d9cabc781b5a9e8638ff: hw/arm/armv7m: Correct typo in QOM object name (2020-12-10 11:44:56 +0000) ---------------------------------------------------------------- target-arm queue: * hw/arm/smmuv3: Fix up L1STD_SPAN decoding * xlnx-zynqmp: Support Xilinx ZynqMP CAN controllers * sbsa-ref: allow to use Cortex-A53/57/72 cpus * Various minor code cleanups * hw/intc/armv7m_nvic: Make all of system PPB range be RAZWI/BusFault * Implement more pieces of ARMv8.1M support ---------------------------------------------------------------- Alex Chen (4): i.MX25: Fix bad printf format specifiers i.MX31: Fix bad printf format specifiers i.MX6: Fix bad printf format specifiers i.MX6ul: Fix bad printf format specifiers Havard Skinnemoen (1): tests/qtest/npcm7xx_rng-test: dump random data on failure Kunkun Jiang (1): hw/arm/smmuv3: Fix up L1STD_SPAN decoding Marcin Juszkiewicz (1): sbsa-ref: allow to use Cortex-A53/57/72 cpus Peter Maydell (25): hw/intc/armv7m_nvic: Make all of system PPB range be RAZWI/BusFault target/arm: Implement v8.1M PXN extension target/arm: Don't clobber ID_PFR1.Security on M-profile cores target/arm: Implement VSCCLRM insn target/arm: Implement CLRM instruction target/arm: Enforce M-profile VMRS/VMSR register restrictions target/arm: Refactor M-profile VMSR/VMRS handling target/arm: Move general-use constant expanders up in translate.c target/arm: Implement VLDR/VSTR system register target/arm: Implement M-profile FPSCR_nzcvqc target/arm: Use new FPCR_NZCV_MASK constant target/arm: Factor out preserve-fp-state from full_vfp_access_check() target/arm: Implement FPCXT_S fp system register hw/intc/armv7m_nvic: Update FPDSCR masking for v8.1M target/arm: For v8.1M, always clear R0-R3, R12, APSR, EPSR on exception entry target/arm: In v8.1M, don't set HFSR.FORCED on vector table fetch failures target/arm: Implement v8.1M REVIDR register target/arm: Implement new v8.1M NOCP check for exception return target/arm: Implement new v8.1M VLLDM and VLSTM encodings hw/intc/armv7m_nvic: Support v8.1M CCR.TRD bit target/arm: Implement CCR_S.TRD behaviour for SG insns hw/intc/armv7m_nvic: Fix "return from inactive handler" check target/arm: Implement M-profile "minimal RAS implementation" hw/intc/armv7m_nvic: Implement read/write for RAS register block hw/arm/armv7m: Correct typo in QOM object name Vikram Garhwal (4): hw/net/can: Introduce Xilinx ZynqMP CAN controller xlnx-zynqmp: Connect Xilinx ZynqMP CAN controllers tests/qtest: Introduce tests for Xilinx ZynqMP CAN controller MAINTAINERS: Add maintainer entry for Xilinx ZynqMP CAN controller meson.build | 1 + hw/arm/smmuv3-internal.h | 2 +- hw/net/can/trace.h | 1 + include/hw/arm/xlnx-zynqmp.h | 8 + include/hw/intc/armv7m_nvic.h | 2 + include/hw/net/xlnx-zynqmp-can.h | 78 +++ target/arm/cpu.h | 46 ++ target/arm/m-nocp.decode | 10 +- target/arm/t32.decode | 10 +- target/arm/vfp.decode | 14 + hw/arm/armv7m.c | 4 +- hw/arm/sbsa-ref.c | 23 +- hw/arm/xlnx-zcu102.c | 20 + hw/arm/xlnx-zynqmp.c | 34 ++ hw/intc/armv7m_nvic.c | 246 ++++++-- hw/misc/imx25_ccm.c | 12 +- hw/misc/imx31_ccm.c | 14 +- hw/misc/imx6_ccm.c | 20 +- hw/misc/imx6_src.c | 2 +- hw/misc/imx6ul_ccm.c | 4 +- hw/misc/imx_ccm.c | 4 +- hw/net/can/xlnx-zynqmp-can.c | 1161 ++++++++++++++++++++++++++++++++++++++ target/arm/cpu.c | 5 +- target/arm/helper.c | 7 +- target/arm/m_helper.c | 130 ++++- target/arm/translate.c | 105 +++- tests/qtest/npcm7xx_rng-test.c | 12 + tests/qtest/xlnx-can-test.c | 360 ++++++++++++ MAINTAINERS | 8 + hw/Kconfig | 1 + hw/net/can/meson.build | 1 + hw/net/can/trace-events | 9 + target/arm/translate-vfp.c.inc | 511 ++++++++++++++++- tests/qtest/meson.build | 1 + 34 files changed, 2713 insertions(+), 153 deletions(-) create mode 100644 hw/net/can/trace.h create mode 100644 include/hw/net/xlnx-zynqmp-can.h create mode 100644 hw/net/can/xlnx-zynqmp-can.c create mode 100644 tests/qtest/xlnx-can-test.c create mode 100644 hw/net/can/trace-events From: Kunkun Jiang <jiangkunkun@huawei.com> Accroding to the SMMUv3 spec, the SPAN field of Level1 Stream Table Descriptor is 5 bits([4:0]). Fixes: 9bde7f0674f(hw/arm/smmuv3: Implement translate callback) Signed-off-by: Kunkun Jiang <jiangkunkun@huawei.com> Message-id: 20201124023711.1184-1-jiangkunkun@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/smmuv3-internal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/smmuv3-internal.h b/hw/arm/smmuv3-internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3-internal.h +++ b/hw/arm/smmuv3-internal.h @@ -XXX,XX +XXX,XX @@ static inline uint64_t l1std_l2ptr(STEDesc *desc) return hi << 32 | lo; } -#define L1STD_SPAN(stm) (extract32((stm)->word[0], 0, 4)) +#define L1STD_SPAN(stm) (extract32((stm)->word[0], 0, 5)) #endif -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> The Xilinx ZynqMP CAN controller is developed based on SocketCAN, QEMU CAN bus implementation. Bus connection and socketCAN connection for each CAN module can be set through command lines. Example for using single CAN: -object can-bus,id=canbus0 \ -machine xlnx-zcu102.canbus0=canbus0 \ -object can-host-socketcan,id=socketcan0,if=vcan0,canbus=canbus0 Example for connecting both CAN to same virtual CAN on host machine: -object can-bus,id=canbus0 -object can-bus,id=canbus1 \ -machine xlnx-zcu102.canbus0=canbus0 \ -machine xlnx-zcu102.canbus1=canbus1 \ -object can-host-socketcan,id=socketcan0,if=vcan0,canbus=canbus0 \ -object can-host-socketcan,id=socketcan1,if=vcan0,canbus=canbus1 To create virtual CAN on the host machine, please check the QEMU CAN docs: https://github.com/qemu/qemu/blob/master/docs/can.txt Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Message-id: 1605728926-352690-2-git-send-email-fnu.vikram@xilinx.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- meson.build | 1 + hw/net/can/trace.h | 1 + include/hw/net/xlnx-zynqmp-can.h | 78 ++ hw/net/can/xlnx-zynqmp-can.c | 1161 ++++++++++++++++++++++++++++++ hw/Kconfig | 1 + hw/net/can/meson.build | 1 + hw/net/can/trace-events | 9 + 7 files changed, 1252 insertions(+) create mode 100644 hw/net/can/trace.h create mode 100644 include/hw/net/xlnx-zynqmp-can.h create mode 100644 hw/net/can/xlnx-zynqmp-can.c create mode 100644 hw/net/can/trace-events diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ if have_system 'hw/misc', 'hw/misc/macio', 'hw/net', + 'hw/net/can', 'hw/nvram', 'hw/pci', 'hw/pci-host', diff --git a/hw/net/can/trace.h b/hw/net/can/trace.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/can/trace.h @@ -0,0 +1 @@ +#include "trace/trace-hw_net_can.h" diff --git a/include/hw/net/xlnx-zynqmp-can.h b/include/hw/net/xlnx-zynqmp-can.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/net/xlnx-zynqmp-can.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Xilinx ZynqMP CAN controller. + * + * Copyright (c) 2020 Xilinx Inc. + * + * Written-by: Vikram Garhwal<fnu.vikram@xilinx.com> + * + * Based on QEMU CAN Device emulation implemented by Jin Yang, Deniz Eren and + * Pavel Pisa. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef XLNX_ZYNQMP_CAN_H +#define XLNX_ZYNQMP_CAN_H + +#include "hw/register.h" +#include "net/can_emu.h" +#include "net/can_host.h" +#include "qemu/fifo32.h" +#include "hw/ptimer.h" +#include "hw/qdev-clock.h" + +#define TYPE_XLNX_ZYNQMP_CAN "xlnx.zynqmp-can" + +#define XLNX_ZYNQMP_CAN(obj) \ + OBJECT_CHECK(XlnxZynqMPCANState, (obj), TYPE_XLNX_ZYNQMP_CAN) + +#define MAX_CAN_CTRLS 2 +#define XLNX_ZYNQMP_CAN_R_MAX (0x84 / 4) +#define MAILBOX_CAPACITY 64 +#define CAN_TIMER_MAX 0XFFFFUL +#define CAN_DEFAULT_CLOCK (24 * 1000 * 1000) + +/* Each CAN_FRAME will have 4 * 32bit size. */ +#define CAN_FRAME_SIZE 4 +#define RXFIFO_SIZE (MAILBOX_CAPACITY * CAN_FRAME_SIZE) + +typedef struct XlnxZynqMPCANState { + SysBusDevice parent_obj; + MemoryRegion iomem; + + qemu_irq irq; + + CanBusClientState bus_client; + CanBusState *canbus; + + struct { + uint32_t ext_clk_freq; + } cfg; + + RegisterInfo reg_info[XLNX_ZYNQMP_CAN_R_MAX]; + uint32_t regs[XLNX_ZYNQMP_CAN_R_MAX]; + + Fifo32 rx_fifo; + Fifo32 tx_fifo; + Fifo32 txhpb_fifo; + + ptimer_state *can_timer; +} XlnxZynqMPCANState; + +#endif diff --git a/hw/net/can/xlnx-zynqmp-can.c b/hw/net/can/xlnx-zynqmp-can.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/can/xlnx-zynqmp-can.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Xilinx ZynqMP CAN controller. + * This implementation is based on the following datasheet: + * https://www.xilinx.com/support/documentation/user_guides/ug1085-zynq-ultrascale-trm.pdf + * + * Copyright (c) 2020 Xilinx Inc. + * + * Written-by: Vikram Garhwal<fnu.vikram@xilinx.com> + * + * Based on QEMU CAN Device emulation implemented by Jin Yang, Deniz Eren and + * Pavel Pisa + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "hw/sysbus.h" +#include "hw/register.h" +#include "hw/irq.h" +#include "qapi/error.h" +#include "qemu/bitops.h" +#include "qemu/log.h" +#include "qemu/cutils.h" +#include "sysemu/sysemu.h" +#include "migration/vmstate.h" +#include "hw/qdev-properties.h" +#include "net/can_emu.h" +#include "net/can_host.h" +#include "qemu/event_notifier.h" +#include "qom/object_interfaces.h" +#include "hw/net/xlnx-zynqmp-can.h" +#include "trace.h" + +#ifndef XLNX_ZYNQMP_CAN_ERR_DEBUG +#define XLNX_ZYNQMP_CAN_ERR_DEBUG 0 +#endif + +#define MAX_DLC 8 +#undef ERROR + +REG32(SOFTWARE_RESET_REGISTER, 0x0) + FIELD(SOFTWARE_RESET_REGISTER, CEN, 1, 1) + FIELD(SOFTWARE_RESET_REGISTER, SRST, 0, 1) +REG32(MODE_SELECT_REGISTER, 0x4) + FIELD(MODE_SELECT_REGISTER, SNOOP, 2, 1) + FIELD(MODE_SELECT_REGISTER, LBACK, 1, 1) + FIELD(MODE_SELECT_REGISTER, SLEEP, 0, 1) +REG32(ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, 0x8) + FIELD(ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, BRP, 0, 8) +REG32(ARBITRATION_PHASE_BIT_TIMING_REGISTER, 0xc) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, SJW, 7, 2) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, TS2, 4, 3) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, TS1, 0, 4) +REG32(ERROR_COUNTER_REGISTER, 0x10) + FIELD(ERROR_COUNTER_REGISTER, REC, 8, 8) + FIELD(ERROR_COUNTER_REGISTER, TEC, 0, 8) +REG32(ERROR_STATUS_REGISTER, 0x14) + FIELD(ERROR_STATUS_REGISTER, ACKER, 4, 1) + FIELD(ERROR_STATUS_REGISTER, BERR, 3, 1) + FIELD(ERROR_STATUS_REGISTER, STER, 2, 1) + FIELD(ERROR_STATUS_REGISTER, FMER, 1, 1) + FIELD(ERROR_STATUS_REGISTER, CRCER, 0, 1) +REG32(STATUS_REGISTER, 0x18) + FIELD(STATUS_REGISTER, SNOOP, 12, 1) + FIELD(STATUS_REGISTER, ACFBSY, 11, 1) + FIELD(STATUS_REGISTER, TXFLL, 10, 1) + FIELD(STATUS_REGISTER, TXBFLL, 9, 1) + FIELD(STATUS_REGISTER, ESTAT, 7, 2) + FIELD(STATUS_REGISTER, ERRWRN, 6, 1) + FIELD(STATUS_REGISTER, BBSY, 5, 1) + FIELD(STATUS_REGISTER, BIDLE, 4, 1) + FIELD(STATUS_REGISTER, NORMAL, 3, 1) + FIELD(STATUS_REGISTER, SLEEP, 2, 1) + FIELD(STATUS_REGISTER, LBACK, 1, 1) + FIELD(STATUS_REGISTER, CONFIG, 0, 1) +REG32(INTERRUPT_STATUS_REGISTER, 0x1c) + FIELD(INTERRUPT_STATUS_REGISTER, TXFEMP, 14, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXFWMEMP, 13, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXFWMFLL, 12, 1) + FIELD(INTERRUPT_STATUS_REGISTER, WKUP, 11, 1) + FIELD(INTERRUPT_STATUS_REGISTER, SLP, 10, 1) + FIELD(INTERRUPT_STATUS_REGISTER, BSOFF, 9, 1) + FIELD(INTERRUPT_STATUS_REGISTER, ERROR, 8, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXNEMP, 7, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXOFLW, 6, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXUFLW, 5, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXOK, 4, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXBFLL, 3, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXFLL, 2, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXOK, 1, 1) + FIELD(INTERRUPT_STATUS_REGISTER, ARBLST, 0, 1) +REG32(INTERRUPT_ENABLE_REGISTER, 0x20) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXFEMP, 14, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXFWMEMP, 13, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXFWMFLL, 12, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EWKUP, 11, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ESLP, 10, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EBSOFF, 9, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EERROR, 8, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXNEMP, 7, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXOFLW, 6, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXUFLW, 5, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXOK, 4, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXBFLL, 3, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXFLL, 2, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXOK, 1, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EARBLST, 0, 1) +REG32(INTERRUPT_CLEAR_REGISTER, 0x24) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXFEMP, 14, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXFWMEMP, 13, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXFWMFLL, 12, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CWKUP, 11, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CSLP, 10, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CBSOFF, 9, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CERROR, 8, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXNEMP, 7, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXOFLW, 6, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXUFLW, 5, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXOK, 4, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXBFLL, 3, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXFLL, 2, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXOK, 1, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CARBLST, 0, 1) +REG32(TIMESTAMP_REGISTER, 0x28) + FIELD(TIMESTAMP_REGISTER, CTS, 0, 1) +REG32(WIR, 0x2c) + FIELD(WIR, EW, 8, 8) + FIELD(WIR, FW, 0, 8) +REG32(TXFIFO_ID, 0x30) + FIELD(TXFIFO_ID, IDH, 21, 11) + FIELD(TXFIFO_ID, SRRRTR, 20, 1) + FIELD(TXFIFO_ID, IDE, 19, 1) + FIELD(TXFIFO_ID, IDL, 1, 18) + FIELD(TXFIFO_ID, RTR, 0, 1) +REG32(TXFIFO_DLC, 0x34) + FIELD(TXFIFO_DLC, DLC, 28, 4) +REG32(TXFIFO_DATA1, 0x38) + FIELD(TXFIFO_DATA1, DB0, 24, 8) + FIELD(TXFIFO_DATA1, DB1, 16, 8) + FIELD(TXFIFO_DATA1, DB2, 8, 8) + FIELD(TXFIFO_DATA1, DB3, 0, 8) +REG32(TXFIFO_DATA2, 0x3c) + FIELD(TXFIFO_DATA2, DB4, 24, 8) + FIELD(TXFIFO_DATA2, DB5, 16, 8) + FIELD(TXFIFO_DATA2, DB6, 8, 8) + FIELD(TXFIFO_DATA2, DB7, 0, 8) +REG32(TXHPB_ID, 0x40) + FIELD(TXHPB_ID, IDH, 21, 11) + FIELD(TXHPB_ID, SRRRTR, 20, 1) + FIELD(TXHPB_ID, IDE, 19, 1) + FIELD(TXHPB_ID, IDL, 1, 18) + FIELD(TXHPB_ID, RTR, 0, 1) +REG32(TXHPB_DLC, 0x44) + FIELD(TXHPB_DLC, DLC, 28, 4) +REG32(TXHPB_DATA1, 0x48) + FIELD(TXHPB_DATA1, DB0, 24, 8) + FIELD(TXHPB_DATA1, DB1, 16, 8) + FIELD(TXHPB_DATA1, DB2, 8, 8) + FIELD(TXHPB_DATA1, DB3, 0, 8) +REG32(TXHPB_DATA2, 0x4c) + FIELD(TXHPB_DATA2, DB4, 24, 8) + FIELD(TXHPB_DATA2, DB5, 16, 8) + FIELD(TXHPB_DATA2, DB6, 8, 8) + FIELD(TXHPB_DATA2, DB7, 0, 8) +REG32(RXFIFO_ID, 0x50) + FIELD(RXFIFO_ID, IDH, 21, 11) + FIELD(RXFIFO_ID, SRRRTR, 20, 1) + FIELD(RXFIFO_ID, IDE, 19, 1) + FIELD(RXFIFO_ID, IDL, 1, 18) + FIELD(RXFIFO_ID, RTR, 0, 1) +REG32(RXFIFO_DLC, 0x54) + FIELD(RXFIFO_DLC, DLC, 28, 4) + FIELD(RXFIFO_DLC, RXT, 0, 16) +REG32(RXFIFO_DATA1, 0x58) + FIELD(RXFIFO_DATA1, DB0, 24, 8) + FIELD(RXFIFO_DATA1, DB1, 16, 8) + FIELD(RXFIFO_DATA1, DB2, 8, 8) + FIELD(RXFIFO_DATA1, DB3, 0, 8) +REG32(RXFIFO_DATA2, 0x5c) + FIELD(RXFIFO_DATA2, DB4, 24, 8) + FIELD(RXFIFO_DATA2, DB5, 16, 8) + FIELD(RXFIFO_DATA2, DB6, 8, 8) + FIELD(RXFIFO_DATA2, DB7, 0, 8) +REG32(AFR, 0x60) + FIELD(AFR, UAF4, 3, 1) + FIELD(AFR, UAF3, 2, 1) + FIELD(AFR, UAF2, 1, 1) + FIELD(AFR, UAF1, 0, 1) +REG32(AFMR1, 0x64) + FIELD(AFMR1, AMIDH, 21, 11) + FIELD(AFMR1, AMSRR, 20, 1) + FIELD(AFMR1, AMIDE, 19, 1) + FIELD(AFMR1, AMIDL, 1, 18) + FIELD(AFMR1, AMRTR, 0, 1) +REG32(AFIR1, 0x68) + FIELD(AFIR1, AIIDH, 21, 11) + FIELD(AFIR1, AISRR, 20, 1) + FIELD(AFIR1, AIIDE, 19, 1) + FIELD(AFIR1, AIIDL, 1, 18) + FIELD(AFIR1, AIRTR, 0, 1) +REG32(AFMR2, 0x6c) + FIELD(AFMR2, AMIDH, 21, 11) + FIELD(AFMR2, AMSRR, 20, 1) + FIELD(AFMR2, AMIDE, 19, 1) + FIELD(AFMR2, AMIDL, 1, 18) + FIELD(AFMR2, AMRTR, 0, 1) +REG32(AFIR2, 0x70) + FIELD(AFIR2, AIIDH, 21, 11) + FIELD(AFIR2, AISRR, 20, 1) + FIELD(AFIR2, AIIDE, 19, 1) + FIELD(AFIR2, AIIDL, 1, 18) + FIELD(AFIR2, AIRTR, 0, 1) +REG32(AFMR3, 0x74) + FIELD(AFMR3, AMIDH, 21, 11) + FIELD(AFMR3, AMSRR, 20, 1) + FIELD(AFMR3, AMIDE, 19, 1) + FIELD(AFMR3, AMIDL, 1, 18) + FIELD(AFMR3, AMRTR, 0, 1) +REG32(AFIR3, 0x78) + FIELD(AFIR3, AIIDH, 21, 11) + FIELD(AFIR3, AISRR, 20, 1) + FIELD(AFIR3, AIIDE, 19, 1) + FIELD(AFIR3, AIIDL, 1, 18) + FIELD(AFIR3, AIRTR, 0, 1) +REG32(AFMR4, 0x7c) + FIELD(AFMR4, AMIDH, 21, 11) + FIELD(AFMR4, AMSRR, 20, 1) + FIELD(AFMR4, AMIDE, 19, 1) + FIELD(AFMR4, AMIDL, 1, 18) + FIELD(AFMR4, AMRTR, 0, 1) +REG32(AFIR4, 0x80) + FIELD(AFIR4, AIIDH, 21, 11) + FIELD(AFIR4, AISRR, 20, 1) + FIELD(AFIR4, AIIDE, 19, 1) + FIELD(AFIR4, AIIDL, 1, 18) + FIELD(AFIR4, AIRTR, 0, 1) + +static void can_update_irq(XlnxZynqMPCANState *s) +{ + uint32_t irq; + + /* Watermark register interrupts. */ + if ((fifo32_num_free(&s->tx_fifo) / CAN_FRAME_SIZE) > + ARRAY_FIELD_EX32(s->regs, WIR, EW)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXFWMEMP, 1); + } + + if ((fifo32_num_used(&s->rx_fifo) / CAN_FRAME_SIZE) > + ARRAY_FIELD_EX32(s->regs, WIR, FW)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXFWMFLL, 1); + } + + /* RX Interrupts. */ + if (fifo32_num_used(&s->rx_fifo) >= CAN_FRAME_SIZE) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXNEMP, 1); + } + + /* TX interrupts. */ + if (fifo32_is_empty(&s->tx_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXFEMP, 1); + } + + if (fifo32_is_full(&s->tx_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXFLL, 1); + } + + if (fifo32_is_full(&s->txhpb_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXBFLL, 1); + } + + irq = s->regs[R_INTERRUPT_STATUS_REGISTER]; + irq &= s->regs[R_INTERRUPT_ENABLE_REGISTER]; + + trace_xlnx_can_update_irq(s->regs[R_INTERRUPT_STATUS_REGISTER], + s->regs[R_INTERRUPT_ENABLE_REGISTER], irq); + qemu_set_irq(s->irq, irq); +} + +static void can_ier_post_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + can_update_irq(s); +} + +static uint64_t can_icr_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + s->regs[R_INTERRUPT_STATUS_REGISTER] &= ~val; + can_update_irq(s); + + return 0; +} + +static void can_config_reset(XlnxZynqMPCANState *s) +{ + /* Reset all the configuration registers. */ + register_reset(&s->reg_info[R_SOFTWARE_RESET_REGISTER]); + register_reset(&s->reg_info[R_MODE_SELECT_REGISTER]); + register_reset( + &s->reg_info[R_ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER]); + register_reset(&s->reg_info[R_ARBITRATION_PHASE_BIT_TIMING_REGISTER]); + register_reset(&s->reg_info[R_STATUS_REGISTER]); + register_reset(&s->reg_info[R_INTERRUPT_STATUS_REGISTER]); + register_reset(&s->reg_info[R_INTERRUPT_ENABLE_REGISTER]); + register_reset(&s->reg_info[R_INTERRUPT_CLEAR_REGISTER]); + register_reset(&s->reg_info[R_WIR]); +} + +static void can_config_mode(XlnxZynqMPCANState *s) +{ + register_reset(&s->reg_info[R_ERROR_COUNTER_REGISTER]); + register_reset(&s->reg_info[R_ERROR_STATUS_REGISTER]); + + /* Put XlnxZynqMPCAN in configuration mode. */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, CONFIG, 1); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, WKUP, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, SLP, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, BSOFF, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, ERROR, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOFLW, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOK, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXOK, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, ARBLST, 0); + + can_update_irq(s); +} + +static void update_status_register_mode_bits(XlnxZynqMPCANState *s) +{ + bool sleep_status = ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP); + bool sleep_mode = ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SLEEP); + /* Wake up interrupt bit. */ + bool wakeup_irq_val = sleep_status && (sleep_mode == 0); + /* Sleep interrupt bit. */ + bool sleep_irq_val = sleep_mode && (sleep_status == 0); + + /* Clear previous core mode status bits. */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, LBACK, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SLEEP, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SNOOP, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, NORMAL, 0); + + /* set current mode bit and generate irqs accordingly. */ + if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, LBACK)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, LBACK, 1); + } else if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SLEEP)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SLEEP, 1); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, SLP, + sleep_irq_val); + } else if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SNOOP)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SNOOP, 1); + } else { + /* + * If all bits are zero then XlnxZynqMPCAN is set in normal mode. + */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, NORMAL, 1); + /* Set wakeup interrupt bit. */ + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, WKUP, + wakeup_irq_val); + } + + can_update_irq(s); +} + +static void can_exit_sleep_mode(XlnxZynqMPCANState *s) +{ + ARRAY_FIELD_DP32(s->regs, MODE_SELECT_REGISTER, SLEEP, 0); + update_status_register_mode_bits(s); +} + +static void generate_frame(qemu_can_frame *frame, uint32_t *data) +{ + frame->can_id = data[0]; + frame->can_dlc = FIELD_EX32(data[1], TXFIFO_DLC, DLC); + + frame->data[0] = FIELD_EX32(data[2], TXFIFO_DATA1, DB3); + frame->data[1] = FIELD_EX32(data[2], TXFIFO_DATA1, DB2); + frame->data[2] = FIELD_EX32(data[2], TXFIFO_DATA1, DB1); + frame->data[3] = FIELD_EX32(data[2], TXFIFO_DATA1, DB0); + + frame->data[4] = FIELD_EX32(data[3], TXFIFO_DATA2, DB7); + frame->data[5] = FIELD_EX32(data[3], TXFIFO_DATA2, DB6); + frame->data[6] = FIELD_EX32(data[3], TXFIFO_DATA2, DB5); + frame->data[7] = FIELD_EX32(data[3], TXFIFO_DATA2, DB4); +} + +static bool tx_ready_check(XlnxZynqMPCANState *s) +{ + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, SRST)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer data while" + " data while controller is in reset mode.\n", + path); + return false; + } + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer" + " data while controller is in configuration mode. Reset" + " the core so operations can start fresh.\n", + path); + return false; + } + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SNOOP)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer" + " data while controller is in SNOOP MODE.\n", + path); + return false; + } + + return true; +} + +static void transfer_fifo(XlnxZynqMPCANState *s, Fifo32 *fifo) +{ + qemu_can_frame frame; + uint32_t data[CAN_FRAME_SIZE]; + int i; + bool can_tx = tx_ready_check(s); + + if (!can_tx) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Controller is not enabled for data" + " transfer.\n", path); + can_update_irq(s); + return; + } + + while (!fifo32_is_empty(fifo)) { + for (i = 0; i < CAN_FRAME_SIZE; i++) { + data[i] = fifo32_pop(fifo); + } + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, LBACK)) { + /* + * Controller is in loopback. In Loopback mode, the CAN core + * transmits a recessive bitstream on to the XlnxZynqMPCAN Bus. + * Any message transmitted is looped back to the RX line and + * acknowledged. The XlnxZynqMPCAN core receives any message + * that it transmits. + */ + if (fifo32_is_full(&s->rx_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOFLW, 1); + } else { + for (i = 0; i < CAN_FRAME_SIZE; i++) { + fifo32_push(&s->rx_fifo, data[i]); + } + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOK, 1); + } + } else { + /* Normal mode Tx. */ + generate_frame(&frame, data); + + trace_xlnx_can_tx_data(frame.can_id, frame.can_dlc, + frame.data[0], frame.data[1], + frame.data[2], frame.data[3], + frame.data[4], frame.data[5], + frame.data[6], frame.data[7]); + can_bus_client_send(&s->bus_client, &frame, 1); + } + } + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXOK, 1); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, TXBFLL, 0); + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP)) { + can_exit_sleep_mode(s); + } + + can_update_irq(s); +} + +static uint64_t can_srr_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + ARRAY_FIELD_DP32(s->regs, SOFTWARE_RESET_REGISTER, CEN, + FIELD_EX32(val, SOFTWARE_RESET_REGISTER, CEN)); + + if (FIELD_EX32(val, SOFTWARE_RESET_REGISTER, SRST)) { + trace_xlnx_can_reset(val); + + /* First, core will do software reset then will enter in config mode. */ + can_config_reset(s); + } + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + can_config_mode(s); + } else { + /* + * Leave config mode. Now XlnxZynqMPCAN core will enter normal, + * sleep, snoop or loopback mode depending upon LBACK, SLEEP, SNOOP + * register states. + */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, CONFIG, 0); + + ptimer_transaction_begin(s->can_timer); + ptimer_set_count(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); + + /* XlnxZynqMPCAN is out of config mode. It will send pending data. */ + transfer_fifo(s, &s->txhpb_fifo); + transfer_fifo(s, &s->tx_fifo); + } + + update_status_register_mode_bits(s); + + return s->regs[R_SOFTWARE_RESET_REGISTER]; +} + +static uint64_t can_msr_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint8_t multi_mode; + + /* + * Multiple mode set check. This is done to make sure user doesn't set + * multiple modes. + */ + multi_mode = FIELD_EX32(val, MODE_SELECT_REGISTER, LBACK) + + FIELD_EX32(val, MODE_SELECT_REGISTER, SLEEP) + + FIELD_EX32(val, MODE_SELECT_REGISTER, SNOOP); + + if (multi_mode > 1) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to config" + " several modes simultaneously. One mode will be selected" + " according to their priority: LBACK > SLEEP > SNOOP.\n", + path); + } + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + /* We are in configuration mode, any mode can be selected. */ + s->regs[R_MODE_SELECT_REGISTER] = val; + } else { + bool sleep_mode_bit = FIELD_EX32(val, MODE_SELECT_REGISTER, SLEEP); + + ARRAY_FIELD_DP32(s->regs, MODE_SELECT_REGISTER, SLEEP, sleep_mode_bit); + + if (FIELD_EX32(val, MODE_SELECT_REGISTER, LBACK)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to set" + " LBACK mode without setting CEN bit as 0.\n", + path); + } else if (FIELD_EX32(val, MODE_SELECT_REGISTER, SNOOP)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to set" + " SNOOP mode without setting CEN bit as 0.\n", + path); + } + + update_status_register_mode_bits(s); + } + + return s->regs[R_MODE_SELECT_REGISTER]; +} + +static uint64_t can_brpr_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + /* Only allow writes when in config mode. */ + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) { + return s->regs[R_ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER]; + } + + return val; +} + +static uint64_t can_btr_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + /* Only allow writes when in config mode. */ + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) { + return s->regs[R_ARBITRATION_PHASE_BIT_TIMING_REGISTER]; + } + + return val; +} + +static uint64_t can_tcr_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + if (FIELD_EX32(val, TIMESTAMP_REGISTER, CTS)) { + ptimer_transaction_begin(s->can_timer); + ptimer_set_count(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); + } + + return 0; +} + +static void update_rx_fifo(XlnxZynqMPCANState *s, const qemu_can_frame *frame) +{ + bool filter_pass = false; + uint16_t timestamp = 0; + + /* If no filter is enabled. Message will be stored in FIFO. */ + if (!((ARRAY_FIELD_EX32(s->regs, AFR, UAF1)) | + (ARRAY_FIELD_EX32(s->regs, AFR, UAF2)) | + (ARRAY_FIELD_EX32(s->regs, AFR, UAF3)) | + (ARRAY_FIELD_EX32(s->regs, AFR, UAF4)))) { + filter_pass = true; + } + + /* + * Messages that pass any of the acceptance filters will be stored in + * the RX FIFO. + */ + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF1)) { + uint32_t id_masked = s->regs[R_AFMR1] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR1] & s->regs[R_AFIR1]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF2)) { + uint32_t id_masked = s->regs[R_AFMR2] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR2] & s->regs[R_AFIR2]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF3)) { + uint32_t id_masked = s->regs[R_AFMR3] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR3] & s->regs[R_AFIR3]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF4)) { + uint32_t id_masked = s->regs[R_AFMR4] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR4] & s->regs[R_AFIR4]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + if (!filter_pass) { + trace_xlnx_can_rx_fifo_filter_reject(frame->can_id, frame->can_dlc); + return; + } + + /* Store the message in fifo if it passed through any of the filters. */ + if (filter_pass && frame->can_dlc <= MAX_DLC) { + + if (fifo32_is_full(&s->rx_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOFLW, 1); + } else { + timestamp = CAN_TIMER_MAX - ptimer_get_count(s->can_timer); + + fifo32_push(&s->rx_fifo, frame->can_id); + + fifo32_push(&s->rx_fifo, deposit32(0, R_RXFIFO_DLC_DLC_SHIFT, + R_RXFIFO_DLC_DLC_LENGTH, + frame->can_dlc) | + deposit32(0, R_RXFIFO_DLC_RXT_SHIFT, + R_RXFIFO_DLC_RXT_LENGTH, + timestamp)); + + /* First 32 bit of the data. */ + fifo32_push(&s->rx_fifo, deposit32(0, R_TXFIFO_DATA1_DB3_SHIFT, + R_TXFIFO_DATA1_DB3_LENGTH, + frame->data[0]) | + deposit32(0, R_TXFIFO_DATA1_DB2_SHIFT, + R_TXFIFO_DATA1_DB2_LENGTH, + frame->data[1]) | + deposit32(0, R_TXFIFO_DATA1_DB1_SHIFT, + R_TXFIFO_DATA1_DB1_LENGTH, + frame->data[2]) | + deposit32(0, R_TXFIFO_DATA1_DB0_SHIFT, + R_TXFIFO_DATA1_DB0_LENGTH, + frame->data[3])); + /* Last 32 bit of the data. */ + fifo32_push(&s->rx_fifo, deposit32(0, R_TXFIFO_DATA2_DB7_SHIFT, + R_TXFIFO_DATA2_DB7_LENGTH, + frame->data[4]) | + deposit32(0, R_TXFIFO_DATA2_DB6_SHIFT, + R_TXFIFO_DATA2_DB6_LENGTH, + frame->data[5]) | + deposit32(0, R_TXFIFO_DATA2_DB5_SHIFT, + R_TXFIFO_DATA2_DB5_LENGTH, + frame->data[6]) | + deposit32(0, R_TXFIFO_DATA2_DB4_SHIFT, + R_TXFIFO_DATA2_DB4_LENGTH, + frame->data[7])); + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOK, 1); + trace_xlnx_can_rx_data(frame->can_id, frame->can_dlc, + frame->data[0], frame->data[1], + frame->data[2], frame->data[3], + frame->data[4], frame->data[5], + frame->data[6], frame->data[7]); + } + + can_update_irq(s); + } +} + +static uint64_t can_rxfifo_pre_read(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + if (!fifo32_is_empty(&s->rx_fifo)) { + val = fifo32_pop(&s->rx_fifo); + } else { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXUFLW, 1); + } + + can_update_irq(s); + return val; +} + +static void can_filter_enable_post_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF1) && + ARRAY_FIELD_EX32(s->regs, AFR, UAF2) && + ARRAY_FIELD_EX32(s->regs, AFR, UAF3) && + ARRAY_FIELD_EX32(s->regs, AFR, UAF4)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, ACFBSY, 1); + } else { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, ACFBSY, 0); + } +} + +static uint64_t can_filter_mask_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t reg_idx = (reg->access->addr) / 4; + uint32_t filter_number = (reg_idx - R_AFMR1) / 2; + + /* modify an acceptance filter, the corresponding UAF bit should be '0'. */ + if (!(s->regs[R_AFR] & (1 << filter_number))) { + s->regs[reg_idx] = val; + + trace_xlnx_can_filter_mask_pre_write(filter_number, s->regs[reg_idx]); + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Acceptance filter %d" + " mask is not set as corresponding UAF bit is not 0.\n", + path, filter_number + 1); + } + + return s->regs[reg_idx]; +} + +static uint64_t can_filter_id_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t reg_idx = (reg->access->addr) / 4; + uint32_t filter_number = (reg_idx - R_AFIR1) / 2; + + if (!(s->regs[R_AFR] & (1 << filter_number))) { + s->regs[reg_idx] = val; + + trace_xlnx_can_filter_id_pre_write(filter_number, s->regs[reg_idx]); + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Acceptance filter %d" + " id is not set as corresponding UAF bit is not 0.\n", + path, filter_number + 1); + } + + return s->regs[reg_idx]; +} + +static void can_tx_post_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + bool is_txhpb = reg->access->addr > A_TXFIFO_DATA2; + + bool initiate_transfer = (reg->access->addr == A_TXFIFO_DATA2) || + (reg->access->addr == A_TXHPB_DATA2); + + Fifo32 *f = is_txhpb ? &s->txhpb_fifo : &s->tx_fifo; + + if (!fifo32_is_full(f)) { + fifo32_push(f, val); + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: TX FIFO is full.\n", path); + } + + /* Initiate the message send if TX register is written. */ + if (initiate_transfer && + ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) { + transfer_fifo(s, f); + } + + can_update_irq(s); +} + +static const RegisterAccessInfo can_regs_info[] = { + { .name = "SOFTWARE_RESET_REGISTER", + .addr = A_SOFTWARE_RESET_REGISTER, + .rsvd = 0xfffffffc, + .pre_write = can_srr_pre_write, + },{ .name = "MODE_SELECT_REGISTER", + .addr = A_MODE_SELECT_REGISTER, + .rsvd = 0xfffffff8, + .pre_write = can_msr_pre_write, + },{ .name = "ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER", + .addr = A_ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, + .rsvd = 0xffffff00, + .pre_write = can_brpr_pre_write, + },{ .name = "ARBITRATION_PHASE_BIT_TIMING_REGISTER", + .addr = A_ARBITRATION_PHASE_BIT_TIMING_REGISTER, + .rsvd = 0xfffffe00, + .pre_write = can_btr_pre_write, + },{ .name = "ERROR_COUNTER_REGISTER", + .addr = A_ERROR_COUNTER_REGISTER, + .rsvd = 0xffff0000, + .ro = 0xffffffff, + },{ .name = "ERROR_STATUS_REGISTER", + .addr = A_ERROR_STATUS_REGISTER, + .rsvd = 0xffffffe0, + .w1c = 0x1f, + },{ .name = "STATUS_REGISTER", .addr = A_STATUS_REGISTER, + .reset = 0x1, + .rsvd = 0xffffe000, + .ro = 0x1fff, + },{ .name = "INTERRUPT_STATUS_REGISTER", + .addr = A_INTERRUPT_STATUS_REGISTER, + .reset = 0x6000, + .rsvd = 0xffff8000, + .ro = 0x7fff, + },{ .name = "INTERRUPT_ENABLE_REGISTER", + .addr = A_INTERRUPT_ENABLE_REGISTER, + .rsvd = 0xffff8000, + .post_write = can_ier_post_write, + },{ .name = "INTERRUPT_CLEAR_REGISTER", + .addr = A_INTERRUPT_CLEAR_REGISTER, + .rsvd = 0xffff8000, + .pre_write = can_icr_pre_write, + },{ .name = "TIMESTAMP_REGISTER", + .addr = A_TIMESTAMP_REGISTER, + .rsvd = 0xfffffffe, + .pre_write = can_tcr_pre_write, + },{ .name = "WIR", .addr = A_WIR, + .reset = 0x3f3f, + .rsvd = 0xffff0000, + },{ .name = "TXFIFO_ID", .addr = A_TXFIFO_ID, + .post_write = can_tx_post_write, + },{ .name = "TXFIFO_DLC", .addr = A_TXFIFO_DLC, + .rsvd = 0xfffffff, + .post_write = can_tx_post_write, + },{ .name = "TXFIFO_DATA1", .addr = A_TXFIFO_DATA1, + .post_write = can_tx_post_write, + },{ .name = "TXFIFO_DATA2", .addr = A_TXFIFO_DATA2, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_ID", .addr = A_TXHPB_ID, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_DLC", .addr = A_TXHPB_DLC, + .rsvd = 0xfffffff, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_DATA1", .addr = A_TXHPB_DATA1, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_DATA2", .addr = A_TXHPB_DATA2, + .post_write = can_tx_post_write, + },{ .name = "RXFIFO_ID", .addr = A_RXFIFO_ID, + .ro = 0xffffffff, + .post_read = can_rxfifo_pre_read, + },{ .name = "RXFIFO_DLC", .addr = A_RXFIFO_DLC, + .rsvd = 0xfff0000, + .post_read = can_rxfifo_pre_read, + },{ .name = "RXFIFO_DATA1", .addr = A_RXFIFO_DATA1, + .post_read = can_rxfifo_pre_read, + },{ .name = "RXFIFO_DATA2", .addr = A_RXFIFO_DATA2, + .post_read = can_rxfifo_pre_read, + },{ .name = "AFR", .addr = A_AFR, + .rsvd = 0xfffffff0, + .post_write = can_filter_enable_post_write, + },{ .name = "AFMR1", .addr = A_AFMR1, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR1", .addr = A_AFIR1, + .pre_write = can_filter_id_pre_write, + },{ .name = "AFMR2", .addr = A_AFMR2, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR2", .addr = A_AFIR2, + .pre_write = can_filter_id_pre_write, + },{ .name = "AFMR3", .addr = A_AFMR3, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR3", .addr = A_AFIR3, + .pre_write = can_filter_id_pre_write, + },{ .name = "AFMR4", .addr = A_AFMR4, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR4", .addr = A_AFIR4, + .pre_write = can_filter_id_pre_write, + } +}; + +static void xlnx_zynqmp_can_ptimer_cb(void *opaque) +{ + /* No action required on the timer rollover. */ +} + +static const MemoryRegionOps can_ops = { + .read = register_read_memory, + .write = register_write_memory, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void xlnx_zynqmp_can_reset_init(Object *obj, ResetType type) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(obj); + unsigned int i; + + for (i = R_RXFIFO_ID; i < ARRAY_SIZE(s->reg_info); ++i) { + register_reset(&s->reg_info[i]); + } + + ptimer_transaction_begin(s->can_timer); + ptimer_set_count(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); +} + +static void xlnx_zynqmp_can_reset_hold(Object *obj) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(obj); + unsigned int i; + + for (i = 0; i < R_RXFIFO_ID; ++i) { + register_reset(&s->reg_info[i]); + } + + /* + * Reset FIFOs when CAN model is reset. This will clear the fifo writes + * done by post_write which gets called from register_reset function, + * post_write handle will not be able to trigger tx because CAN will be + * disabled when software_reset_register is cleared first. + */ + fifo32_reset(&s->rx_fifo); + fifo32_reset(&s->tx_fifo); + fifo32_reset(&s->txhpb_fifo); +} + +static bool xlnx_zynqmp_can_can_receive(CanBusClientState *client) +{ + XlnxZynqMPCANState *s = container_of(client, XlnxZynqMPCANState, + bus_client); + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, SRST)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Controller is in reset state.\n", + path); + return false; + } + + if ((ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) == 0) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Controller is disabled. Incoming" + " messages will be discarded.\n", path); + return false; + } + + return true; +} + +static ssize_t xlnx_zynqmp_can_receive(CanBusClientState *client, + const qemu_can_frame *buf, size_t buf_size) { + XlnxZynqMPCANState *s = container_of(client, XlnxZynqMPCANState, + bus_client); + const qemu_can_frame *frame = buf; + + if (buf_size <= 0) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Error in the data received.\n", + path); + return 0; + } + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SNOOP)) { + /* Snoop Mode: Just keep the data. no response back. */ + update_rx_fifo(s, frame); + } else if ((ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP))) { + /* + * XlnxZynqMPCAN is in sleep mode. Any data on bus will bring it to wake + * up state. + */ + can_exit_sleep_mode(s); + update_rx_fifo(s, frame); + } else if ((ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP)) == 0) { + update_rx_fifo(s, frame); + } else { + /* + * XlnxZynqMPCAN will not participate in normal bus communication + * and will not receive any messages transmitted by other CAN nodes. + */ + trace_xlnx_can_rx_discard(s->regs[R_STATUS_REGISTER]); + } + + return 1; +} + +static CanBusClientInfo can_xilinx_bus_client_info = { + .can_receive = xlnx_zynqmp_can_can_receive, + .receive = xlnx_zynqmp_can_receive, +}; + +static int xlnx_zynqmp_can_connect_to_bus(XlnxZynqMPCANState *s, + CanBusState *bus) +{ + s->bus_client.info = &can_xilinx_bus_client_info; + + if (can_bus_insert_client(bus, &s->bus_client) < 0) { + return -1; + } + return 0; +} + +static void xlnx_zynqmp_can_realize(DeviceState *dev, Error **errp) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(dev); + + if (s->canbus) { + if (xlnx_zynqmp_can_connect_to_bus(s, s->canbus) < 0) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + error_setg(errp, "%s: xlnx_zynqmp_can_connect_to_bus" + " failed.", path); + return; + } + } + + /* Create RX FIFO, TXFIFO, TXHPB storage. */ + fifo32_create(&s->rx_fifo, RXFIFO_SIZE); + fifo32_create(&s->tx_fifo, RXFIFO_SIZE); + fifo32_create(&s->txhpb_fifo, CAN_FRAME_SIZE); + + /* Allocate a new timer. */ + s->can_timer = ptimer_init(xlnx_zynqmp_can_ptimer_cb, s, + PTIMER_POLICY_DEFAULT); + + ptimer_transaction_begin(s->can_timer); + + ptimer_set_freq(s->can_timer, s->cfg.ext_clk_freq); + ptimer_set_limit(s->can_timer, CAN_TIMER_MAX, 1); + ptimer_run(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); +} + +static void xlnx_zynqmp_can_init(Object *obj) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + + RegisterInfoArray *reg_array; + + memory_region_init(&s->iomem, obj, TYPE_XLNX_ZYNQMP_CAN, + XLNX_ZYNQMP_CAN_R_MAX * 4); + reg_array = register_init_block32(DEVICE(obj), can_regs_info, + ARRAY_SIZE(can_regs_info), + s->reg_info, s->regs, + &can_ops, + XLNX_ZYNQMP_CAN_ERR_DEBUG, + XLNX_ZYNQMP_CAN_R_MAX * 4); + + memory_region_add_subregion(&s->iomem, 0x00, &reg_array->mem); + sysbus_init_mmio(sbd, &s->iomem); + sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq); +} + +static const VMStateDescription vmstate_can = { + .name = TYPE_XLNX_ZYNQMP_CAN, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_FIFO32(rx_fifo, XlnxZynqMPCANState), + VMSTATE_FIFO32(tx_fifo, XlnxZynqMPCANState), + VMSTATE_FIFO32(txhpb_fifo, XlnxZynqMPCANState), + VMSTATE_UINT32_ARRAY(regs, XlnxZynqMPCANState, XLNX_ZYNQMP_CAN_R_MAX), + VMSTATE_PTIMER(can_timer, XlnxZynqMPCANState), + VMSTATE_END_OF_LIST(), + } +}; + +static Property xlnx_zynqmp_can_properties[] = { + DEFINE_PROP_UINT32("ext_clk_freq", XlnxZynqMPCANState, cfg.ext_clk_freq, + CAN_DEFAULT_CLOCK), + DEFINE_PROP_LINK("canbus", XlnxZynqMPCANState, canbus, TYPE_CAN_BUS, + CanBusState *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void xlnx_zynqmp_can_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.enter = xlnx_zynqmp_can_reset_init; + rc->phases.hold = xlnx_zynqmp_can_reset_hold; + dc->realize = xlnx_zynqmp_can_realize; + device_class_set_props(dc, xlnx_zynqmp_can_properties); + dc->vmsd = &vmstate_can; +} + +static const TypeInfo can_info = { + .name = TYPE_XLNX_ZYNQMP_CAN, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(XlnxZynqMPCANState), + .class_init = xlnx_zynqmp_can_class_init, + .instance_init = xlnx_zynqmp_can_init, +}; + +static void can_register_types(void) +{ + type_register_static(&can_info); +} + +type_init(can_register_types) diff --git a/hw/Kconfig b/hw/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/Kconfig +++ b/hw/Kconfig @@ -XXX,XX +XXX,XX @@ config XILINX_AXI config XLNX_ZYNQMP bool select REGISTER + select CAN_BUS diff --git a/hw/net/can/meson.build b/hw/net/can/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/net/can/meson.build +++ b/hw/net/can/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_CAN_PCI', if_true: files('can_pcm3680_pci.c')) softmmu_ss.add(when: 'CONFIG_CAN_PCI', if_true: files('can_mioe3680_pci.c')) softmmu_ss.add(when: 'CONFIG_CAN_CTUCANFD', if_true: files('ctucan_core.c')) softmmu_ss.add(when: 'CONFIG_CAN_CTUCANFD_PCI', if_true: files('ctucan_pci.c')) +softmmu_ss.add(when: 'CONFIG_XLNX_ZYNQMP', if_true: files('xlnx-zynqmp-can.c')) diff --git a/hw/net/can/trace-events b/hw/net/can/trace-events new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/can/trace-events @@ -XXX,XX +XXX,XX @@ +# xlnx-zynqmp-can.c +xlnx_can_update_irq(uint32_t isr, uint32_t ier, uint32_t irq) "ISR: 0x%08x IER: 0x%08x IRQ: 0x%08x" +xlnx_can_reset(uint32_t val) "Resetting controller with value = 0x%08x" +xlnx_can_rx_fifo_filter_reject(uint32_t id, uint8_t dlc) "Frame: ID: 0x%08x DLC: 0x%02x" +xlnx_can_filter_id_pre_write(uint8_t filter_num, uint32_t value) "Filter%d ID: 0x%08x" +xlnx_can_filter_mask_pre_write(uint8_t filter_num, uint32_t value) "Filter%d MASK: 0x%08x" +xlnx_can_tx_data(uint32_t id, uint8_t dlc, uint8_t db0, uint8_t db1, uint8_t db2, uint8_t db3, uint8_t db4, uint8_t db5, uint8_t db6, uint8_t db7) "Frame: ID: 0x%08x DLC: 0x%02x DATA: 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x" +xlnx_can_rx_data(uint32_t id, uint32_t dlc, uint8_t db0, uint8_t db1, uint8_t db2, uint8_t db3, uint8_t db4, uint8_t db5, uint8_t db6, uint8_t db7) "Frame: ID: 0x%08x DLC: 0x%02x DATA: 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x" +xlnx_can_rx_discard(uint32_t status) "Controller is not enabled for bus communication. Status Register: 0x%08x" -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> Connect CAN0 and CAN1 on the ZynqMP. Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Message-id: 1605728926-352690-3-git-send-email-fnu.vikram@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-zynqmp.h | 8 ++++++++ hw/arm/xlnx-zcu102.c | 20 ++++++++++++++++++++ hw/arm/xlnx-zynqmp.c | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 62 insertions(+) diff --git a/include/hw/arm/xlnx-zynqmp.h b/include/hw/arm/xlnx-zynqmp.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-zynqmp.h +++ b/include/hw/arm/xlnx-zynqmp.h @@ -XXX,XX +XXX,XX @@ #include "hw/intc/arm_gic.h" #include "hw/net/cadence_gem.h" #include "hw/char/cadence_uart.h" +#include "hw/net/xlnx-zynqmp-can.h" #include "hw/ide/ahci.h" #include "hw/sd/sdhci.h" #include "hw/ssi/xilinx_spips.h" @@ -XXX,XX +XXX,XX @@ #include "hw/cpu/cluster.h" #include "target/arm/cpu.h" #include "qom/object.h" +#include "net/can_emu.h" #define TYPE_XLNX_ZYNQMP "xlnx,zynqmp" OBJECT_DECLARE_SIMPLE_TYPE(XlnxZynqMPState, XLNX_ZYNQMP) @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(XlnxZynqMPState, XLNX_ZYNQMP) #define XLNX_ZYNQMP_NUM_RPU_CPUS 2 #define XLNX_ZYNQMP_NUM_GEMS 4 #define XLNX_ZYNQMP_NUM_UARTS 2 +#define XLNX_ZYNQMP_NUM_CAN 2 +#define XLNX_ZYNQMP_CAN_REF_CLK (24 * 1000 * 1000) #define XLNX_ZYNQMP_NUM_SDHCI 2 #define XLNX_ZYNQMP_NUM_SPIS 2 #define XLNX_ZYNQMP_NUM_GDMA_CH 8 @@ -XXX,XX +XXX,XX @@ struct XlnxZynqMPState { CadenceGEMState gem[XLNX_ZYNQMP_NUM_GEMS]; CadenceUARTState uart[XLNX_ZYNQMP_NUM_UARTS]; + XlnxZynqMPCANState can[XLNX_ZYNQMP_NUM_CAN]; SysbusAHCIState sata; SDHCIState sdhci[XLNX_ZYNQMP_NUM_SDHCI]; XilinxSPIPS spi[XLNX_ZYNQMP_NUM_SPIS]; @@ -XXX,XX +XXX,XX @@ struct XlnxZynqMPState { bool virt; /* Has the RPU subsystem? */ bool has_rpu; + + /* CAN bus. */ + CanBusState *canbus[XLNX_ZYNQMP_NUM_CAN]; }; #endif 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 @@ #include "sysemu/qtest.h" #include "sysemu/device_tree.h" #include "qom/object.h" +#include "net/can_emu.h" struct XlnxZCU102 { MachineState parent_obj; @@ -XXX,XX +XXX,XX @@ struct XlnxZCU102 { bool secure; bool virt; + CanBusState *canbus[XLNX_ZYNQMP_NUM_CAN]; + struct arm_boot_info binfo; }; @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_init(MachineState *machine) object_property_set_bool(OBJECT(&s->soc), "virtualization", s->virt, &error_fatal); + for (i = 0; i < XLNX_ZYNQMP_NUM_CAN; i++) { + gchar *bus_name = g_strdup_printf("canbus%d", i); + + object_property_set_link(OBJECT(&s->soc), bus_name, + OBJECT(s->canbus[i]), &error_fatal); + g_free(bus_name); + } + qdev_realize(DEVICE(&s->soc), NULL, &error_fatal); /* Create and plug in the SD cards */ @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_machine_instance_init(Object *obj) s->secure = false; /* Default to virt (EL2) being disabled */ s->virt = false; + object_property_add_link(obj, "xlnx-zcu102.canbus0", TYPE_CAN_BUS, + (Object **)&s->canbus[0], + object_property_allow_set_link, + 0); + + object_property_add_link(obj, "xlnx-zcu102.canbus1", TYPE_CAN_BUS, + (Object **)&s->canbus[1], + object_property_allow_set_link, + 0); } static void xlnx_zcu102_machine_class_init(ObjectClass *oc, void *data) diff --git a/hw/arm/xlnx-zynqmp.c b/hw/arm/xlnx-zynqmp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zynqmp.c +++ b/hw/arm/xlnx-zynqmp.c @@ -XXX,XX +XXX,XX @@ static const int uart_intr[XLNX_ZYNQMP_NUM_UARTS] = { 21, 22, }; +static const uint64_t can_addr[XLNX_ZYNQMP_NUM_CAN] = { + 0xFF060000, 0xFF070000, +}; + +static const int can_intr[XLNX_ZYNQMP_NUM_CAN] = { + 23, 24, +}; + static const uint64_t sdhci_addr[XLNX_ZYNQMP_NUM_SDHCI] = { 0xFF160000, 0xFF170000, }; @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_init(Object *obj) TYPE_CADENCE_UART); } + for (i = 0; i < XLNX_ZYNQMP_NUM_CAN; i++) { + object_initialize_child(obj, "can[*]", &s->can[i], + TYPE_XLNX_ZYNQMP_CAN); + } + object_initialize_child(obj, "sata", &s->sata, TYPE_SYSBUS_AHCI); for (i = 0; i < XLNX_ZYNQMP_NUM_SDHCI; i++) { @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp) gic_spi[uart_intr[i]]); } + for (i = 0; i < XLNX_ZYNQMP_NUM_CAN; i++) { + object_property_set_int(OBJECT(&s->can[i]), "ext_clk_freq", + XLNX_ZYNQMP_CAN_REF_CLK, &error_abort); + + object_property_set_link(OBJECT(&s->can[i]), "canbus", + OBJECT(s->canbus[i]), &error_fatal); + + sysbus_realize(SYS_BUS_DEVICE(&s->can[i]), &err); + if (err) { + error_propagate(errp, err); + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->can[i]), 0, can_addr[i]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->can[i]), 0, + gic_spi[can_intr[i]]); + } + object_property_set_int(OBJECT(&s->sata), "num-ports", SATA_NUM_PORTS, &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->sata), errp)) { @@ -XXX,XX +XXX,XX @@ static Property xlnx_zynqmp_props[] = { DEFINE_PROP_BOOL("has_rpu", XlnxZynqMPState, has_rpu, false), DEFINE_PROP_LINK("ddr-ram", XlnxZynqMPState, ddr_ram, TYPE_MEMORY_REGION, MemoryRegion *), + DEFINE_PROP_LINK("canbus0", XlnxZynqMPState, canbus[0], TYPE_CAN_BUS, + CanBusState *), + DEFINE_PROP_LINK("canbus1", XlnxZynqMPState, canbus[1], TYPE_CAN_BUS, + CanBusState *), DEFINE_PROP_END_OF_LIST() }; -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> The QTests perform five tests on the Xilinx ZynqMP CAN controller: Tests the CAN controller in loopback, sleep and snoop mode. Tests filtering of incoming CAN messages. Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Message-id: 1605728926-352690-4-git-send-email-fnu.vikram@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/xlnx-can-test.c | 360 ++++++++++++++++++++++++++++++++++++ tests/qtest/meson.build | 1 + 2 files changed, 361 insertions(+) create mode 100644 tests/qtest/xlnx-can-test.c diff --git a/tests/qtest/xlnx-can-test.c b/tests/qtest/xlnx-can-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/xlnx-can-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTests for the Xilinx ZynqMP CAN controller. + * + * Copyright (c) 2020 Xilinx Inc. + * + * Written-by: Vikram Garhwal<fnu.vikram@xilinx.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "libqos/libqtest.h" + +/* Base address. */ +#define CAN0_BASE_ADDR 0xFF060000 +#define CAN1_BASE_ADDR 0xFF070000 + +/* Register addresses. */ +#define R_SRR_OFFSET 0x00 +#define R_MSR_OFFSET 0x04 +#define R_SR_OFFSET 0x18 +#define R_ISR_OFFSET 0x1C +#define R_ICR_OFFSET 0x24 +#define R_TXID_OFFSET 0x30 +#define R_TXDLC_OFFSET 0x34 +#define R_TXDATA1_OFFSET 0x38 +#define R_TXDATA2_OFFSET 0x3C +#define R_RXID_OFFSET 0x50 +#define R_RXDLC_OFFSET 0x54 +#define R_RXDATA1_OFFSET 0x58 +#define R_RXDATA2_OFFSET 0x5C +#define R_AFR 0x60 +#define R_AFMR1 0x64 +#define R_AFIR1 0x68 +#define R_AFMR2 0x6C +#define R_AFIR2 0x70 +#define R_AFMR3 0x74 +#define R_AFIR3 0x78 +#define R_AFMR4 0x7C +#define R_AFIR4 0x80 + +/* CAN modes. */ +#define CONFIG_MODE 0x00 +#define NORMAL_MODE 0x00 +#define LOOPBACK_MODE 0x02 +#define SNOOP_MODE 0x04 +#define SLEEP_MODE 0x01 +#define ENABLE_CAN (1 << 1) +#define STATUS_NORMAL_MODE (1 << 3) +#define STATUS_LOOPBACK_MODE (1 << 1) +#define STATUS_SNOOP_MODE (1 << 12) +#define STATUS_SLEEP_MODE (1 << 2) +#define ISR_TXOK (1 << 1) +#define ISR_RXOK (1 << 4) + +static void match_rx_tx_data(const uint32_t *buf_tx, const uint32_t *buf_rx, + uint8_t can_timestamp) +{ + uint16_t size = 0; + uint8_t len = 4; + + while (size < len) { + if (R_RXID_OFFSET + 4 * size == R_RXDLC_OFFSET) { + g_assert_cmpint(buf_rx[size], ==, buf_tx[size] + can_timestamp); + } else { + g_assert_cmpint(buf_rx[size], ==, buf_tx[size]); + } + + size++; + } +} + +static void read_data(QTestState *qts, uint64_t can_base_addr, uint32_t *buf_rx) +{ + uint32_t int_status; + + /* Read the interrupt on CAN rx. */ + int_status = qtest_readl(qts, can_base_addr + R_ISR_OFFSET) & ISR_RXOK; + + g_assert_cmpint(int_status, ==, ISR_RXOK); + + /* Read the RX register data for CAN. */ + buf_rx[0] = qtest_readl(qts, can_base_addr + R_RXID_OFFSET); + buf_rx[1] = qtest_readl(qts, can_base_addr + R_RXDLC_OFFSET); + buf_rx[2] = qtest_readl(qts, can_base_addr + R_RXDATA1_OFFSET); + buf_rx[3] = qtest_readl(qts, can_base_addr + R_RXDATA2_OFFSET); + + /* Clear the RX interrupt. */ + qtest_writel(qts, CAN1_BASE_ADDR + R_ICR_OFFSET, ISR_RXOK); +} + +static void send_data(QTestState *qts, uint64_t can_base_addr, + const uint32_t *buf_tx) +{ + uint32_t int_status; + + /* Write the TX register data for CAN. */ + qtest_writel(qts, can_base_addr + R_TXID_OFFSET, buf_tx[0]); + qtest_writel(qts, can_base_addr + R_TXDLC_OFFSET, buf_tx[1]); + qtest_writel(qts, can_base_addr + R_TXDATA1_OFFSET, buf_tx[2]); + qtest_writel(qts, can_base_addr + R_TXDATA2_OFFSET, buf_tx[3]); + + /* Read the interrupt on CAN for tx. */ + int_status = qtest_readl(qts, can_base_addr + R_ISR_OFFSET) & ISR_TXOK; + + g_assert_cmpint(int_status, ==, ISR_TXOK); + + /* Clear the interrupt for tx. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_ICR_OFFSET, ISR_TXOK); +} + +/* + * This test will be transferring data from CAN0 and CAN1 through canbus. CAN0 + * initiate the data transfer to can-bus, CAN1 receives the data. Test compares + * the data sent from CAN0 with received on CAN1. + */ +static void test_can_bus(void) +{ + const uint32_t buf_tx[4] = { 0xFF, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0 and CAN1. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 and CAN1 are in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + send_data(qts, CAN0_BASE_ADDR, buf_tx); + + read_data(qts, CAN1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +/* + * This test is performing loopback mode on CAN0 and CAN1. Data sent from TX of + * each CAN0 and CAN1 are compared with RX register data for respective CAN. + */ +static void test_can_loopback(void) +{ + uint32_t buf_tx[4] = { 0xFF, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0 in loopback mode. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, LOOPBACK_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + /* Check here if CAN0 is set in loopback mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + + g_assert_cmpint(status, ==, STATUS_LOOPBACK_MODE); + + send_data(qts, CAN0_BASE_ADDR, buf_tx); + read_data(qts, CAN0_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, 0); + + /* Configure the CAN1 in loopback mode. */ + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, LOOPBACK_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + /* Check here if CAN1 is set in loopback mode. */ + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + + g_assert_cmpint(status, ==, STATUS_LOOPBACK_MODE); + + send_data(qts, CAN1_BASE_ADDR, buf_tx); + read_data(qts, CAN1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, 0); + + qtest_quit(qts); +} + +/* + * Enable filters for CAN1. This will filter incoming messages with ID. In this + * test message will pass through filter 2. + */ +static void test_can_filter(void) +{ + uint32_t buf_tx[4] = { 0x14, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0 and CAN1. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 and CAN1 are in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + /* Set filter for CAN1 for incoming messages. */ + qtest_writel(qts, CAN1_BASE_ADDR + R_AFR, 0x0); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR1, 0xF7); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR1, 0x121F); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR2, 0x5431); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR2, 0x14); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR3, 0x1234); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR3, 0x5431); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR4, 0xFFF); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR4, 0x1234); + + qtest_writel(qts, CAN1_BASE_ADDR + R_AFR, 0xF); + + send_data(qts, CAN0_BASE_ADDR, buf_tx); + + read_data(qts, CAN1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +/* Testing sleep mode on CAN0 while CAN1 is in normal mode. */ +static void test_can_sleepmode(void) +{ + uint32_t buf_tx[4] = { 0x14, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, SLEEP_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 is in SLEEP mode and CAN1 in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_SLEEP_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + send_data(qts, CAN1_BASE_ADDR, buf_tx); + + /* + * Once CAN1 sends data on can-bus. CAN0 should exit sleep mode. + * Check the CAN0 status now. It should exit the sleep mode and receive the + * incoming data. + */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + read_data(qts, CAN0_BASE_ADDR, buf_rx); + + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +/* Testing Snoop mode on CAN0 while CAN1 is in normal mode. */ +static void test_can_snoopmode(void) +{ + uint32_t buf_tx[4] = { 0x14, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, SNOOP_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 is in SNOOP mode and CAN1 in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_SNOOP_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + send_data(qts, CAN1_BASE_ADDR, buf_tx); + + read_data(qts, CAN0_BASE_ADDR, buf_rx); + + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +int main(int argc, char **argv) +{ + g_test_init(&argc, &argv, NULL); + + qtest_add_func("/net/can/can_bus", test_can_bus); + qtest_add_func("/net/can/can_loopback", test_can_loopback); + qtest_add_func("/net/can/can_filter", test_can_filter); + qtest_add_func("/net/can/can_test_snoopmode", test_can_snoopmode); + qtest_add_func("/net/can/can_test_sleepmode", test_can_sleepmode); + + return g_test_run(); +} diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qtests_aarch64 = \ ['arm-cpu-features', 'numa-test', 'boot-serial-test', + 'xlnx-can-test', 'migration-test'] qtests_s390x = \ -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Message-id: 1605728926-352690-5-git-send-email-fnu.vikram@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/net/opencores_eth.c Devices ------- +Xilinx CAN +M: Vikram Garhwal <fnu.vikram@xilinx.com> +M: Francisco Iglesias <francisco.iglesias@xilinx.com> +S: Maintained +F: hw/net/can/xlnx-* +F: include/hw/net/xlnx-* +F: tests/qtest/xlnx-can-test* + EDU M: Jiri Slaby <jslaby@suse.cz> S: Maintained -- 2.20.1 From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Trusted Firmware now supports A72 on sbsa-ref by default [1] so enable it for QEMU as well. A53 was already enabled there. 1. https://review.trustedfirmware.org/c/TF-A/trusted-firmware-a/+/7117 Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201120141705.246690-1-marcin.juszkiewicz@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ static const int sbsa_ref_irqmap[] = { [SBSA_GWDT] = 16, }; +static const char * const valid_cpus[] = { + ARM_CPU_TYPE_NAME("cortex-a53"), + ARM_CPU_TYPE_NAME("cortex-a57"), + ARM_CPU_TYPE_NAME("cortex-a72"), +}; + +static bool cpu_type_valid(const char *cpu) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(valid_cpus); i++) { + if (strcmp(cpu, valid_cpus[i]) == 0) { + return true; + } + } + return false; +} + static uint64_t sbsa_ref_cpu_mp_affinity(SBSAMachineState *sms, int idx) { uint8_t clustersz = ARM_DEFAULT_CPUS_PER_CLUSTER; @@ -XXX,XX +XXX,XX @@ static void sbsa_ref_init(MachineState *machine) const CPUArchIdList *possible_cpus; int n, sbsa_max_cpus; - if (strcmp(machine->cpu_type, ARM_CPU_TYPE_NAME("cortex-a57"))) { - error_report("sbsa-ref: CPU type other than the built-in " - "cortex-a57 not supported"); + if (!cpu_type_valid(machine->cpu_type)) { + error_report("mach-virt: CPU type %s not supported", machine->cpu_type); exit(1); } -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> Dump the collected random data after a randomness test failure. Note that this relies on the test having called g_test_set_nonfatal_assertions() so we don't abort immediately on the assertion failure. Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: minor commit message tweak] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/npcm7xx_rng-test.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) 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 @@ #include "libqtest-single.h" #include "qemu/bitops.h" +#include "qemu-common.h" #define RNG_BASE_ADDR 0xf000b000 @@ -XXX,XX +XXX,XX @@ /* Number of bits to collect for randomness tests. */ #define TEST_INPUT_BITS (128) +static void dump_buf_if_failed(const uint8_t *buf, size_t size) +{ + if (g_test_failed()) { + qemu_hexdump(stderr, "", buf, size); + } +} + static void rng_writeb(unsigned int offset, uint8_t value) { writeb(RNG_BASE_ADDR + offset, value); @@ -XXX,XX +XXX,XX @@ static void test_continuous_monobit(void) } g_assert_cmpfloat(calc_monobit_p(buf, sizeof(buf)), >, 0.01); + dump_buf_if_failed(buf, sizeof(buf)); } /* @@ -XXX,XX +XXX,XX @@ static void test_continuous_runs(void) } g_assert_cmpfloat(calc_runs_p(buf.l, sizeof(buf) * BITS_PER_BYTE), >, 0.01); + dump_buf_if_failed(buf.c, sizeof(buf)); } /* @@ -XXX,XX +XXX,XX @@ static void test_first_byte_monobit(void) } g_assert_cmpfloat(calc_monobit_p(buf, sizeof(buf)), >, 0.01); + dump_buf_if_failed(buf, sizeof(buf)); } /* @@ -XXX,XX +XXX,XX @@ static void test_first_byte_runs(void) } g_assert_cmpfloat(calc_runs_p(buf.l, sizeof(buf) * BITS_PER_BYTE), >, 0.01); + dump_buf_if_failed(buf.c, sizeof(buf)); } int main(int argc, char **argv) -- 2.20.1 From: Alex Chen <alex.chen@huawei.com> We should use printf format specifier "%u" instead of "%d" for argument of type "unsigned int". Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Message-id: 20201126111109.112238-2-alex.chen@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/imx25_ccm.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/hw/misc/imx25_ccm.c b/hw/misc/imx25_ccm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/imx25_ccm.c +++ b/hw/misc/imx25_ccm.c @@ -XXX,XX +XXX,XX @@ static const char *imx25_ccm_reg_name(uint32_t reg) case IMX25_CCM_LPIMR1_REG: return "lpimr1"; default: - sprintf(unknown, "[%d ?]", reg); + sprintf(unknown, "[%u ?]", reg); return unknown; } } @@ -XXX,XX +XXX,XX @@ static uint32_t imx25_ccm_get_mpll_clk(IMXCCMState *dev) freq = imx_ccm_calc_pll(s->reg[IMX25_CCM_MPCTL_REG], CKIH_FREQ); } - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx25_ccm_get_mcu_clk(IMXCCMState *dev) freq = freq / (1 + EXTRACT(s->reg[IMX25_CCM_CCTL_REG], ARM_CLK_DIV)); - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx25_ccm_get_ahb_clk(IMXCCMState *dev) freq = imx25_ccm_get_mcu_clk(dev) / (1 + EXTRACT(s->reg[IMX25_CCM_CCTL_REG], AHB_CLK_DIV)); - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx25_ccm_get_ipg_clk(IMXCCMState *dev) freq = imx25_ccm_get_ahb_clk(dev) / 2; - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx25_ccm_get_clock_frequency(IMXCCMState *dev, IMXClk clock) break; } - DPRINTF("Clock = %d) = %d\n", clock, freq); + DPRINTF("Clock = %d) = %u\n", clock, freq); return freq; } -- 2.20.1 From: Alex Chen <alex.chen@huawei.com> We should use printf format specifier "%u" instead of "%d" for argument of type "unsigned int". Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Message-id: 20201126111109.112238-3-alex.chen@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/imx31_ccm.c | 14 +++++++------- hw/misc/imx_ccm.c | 4 ++-- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/hw/misc/imx31_ccm.c b/hw/misc/imx31_ccm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/imx31_ccm.c +++ b/hw/misc/imx31_ccm.c @@ -XXX,XX +XXX,XX @@ static const char *imx31_ccm_reg_name(uint32_t reg) case IMX31_CCM_PDR2_REG: return "PDR2"; default: - sprintf(unknown, "[%d ?]", reg); + sprintf(unknown, "[%u ?]", reg); return unknown; } } @@ -XXX,XX +XXX,XX @@ static uint32_t imx31_ccm_get_pll_ref_clk(IMXCCMState *dev) freq = CKIH_FREQ; } - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx31_ccm_get_mpll_clk(IMXCCMState *dev) freq = imx_ccm_calc_pll(s->reg[IMX31_CCM_MPCTL_REG], imx31_ccm_get_pll_ref_clk(dev)); - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx31_ccm_get_mcu_main_clk(IMXCCMState *dev) freq = imx31_ccm_get_mpll_clk(dev); } - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx31_ccm_get_hclk_clk(IMXCCMState *dev) freq = imx31_ccm_get_mcu_main_clk(dev) / (1 + EXTRACT(s->reg[IMX31_CCM_PDR0_REG], MAX)); - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx31_ccm_get_ipg_clk(IMXCCMState *dev) freq = imx31_ccm_get_hclk_clk(dev) / (1 + EXTRACT(s->reg[IMX31_CCM_PDR0_REG], IPG)); - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx31_ccm_get_clock_frequency(IMXCCMState *dev, IMXClk clock) break; } - DPRINTF("Clock = %d) = %d\n", clock, freq); + DPRINTF("Clock = %d) = %u\n", clock, freq); return freq; } diff --git a/hw/misc/imx_ccm.c b/hw/misc/imx_ccm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/imx_ccm.c +++ b/hw/misc/imx_ccm.c @@ -XXX,XX +XXX,XX @@ uint32_t imx_ccm_get_clock_frequency(IMXCCMState *dev, IMXClk clock) freq = klass->get_clock_frequency(dev, clock); } - DPRINTF("(clock = %d) = %d\n", clock, freq); + DPRINTF("(clock = %d) = %u\n", clock, freq); return freq; } @@ -XXX,XX +XXX,XX @@ uint32_t imx_ccm_calc_pll(uint32_t pllreg, uint32_t base_freq) freq = ((2 * (base_freq >> 10) * (mfi * mfd + mfn)) / (mfd * pd)) << 10; - DPRINTF("(pllreg = 0x%08x, base_freq = %d) = %d\n", pllreg, base_freq, + DPRINTF("(pllreg = 0x%08x, base_freq = %u) = %d\n", pllreg, base_freq, freq); return freq; -- 2.20.1 From: Alex Chen <alex.chen@huawei.com> We should use printf format specifier "%u" instead of "%d" for argument of type "unsigned int". Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Message-id: 20201126111109.112238-4-alex.chen@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/imx6_ccm.c | 20 ++++++++++---------- hw/misc/imx6_src.c | 2 +- 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/hw/misc/imx6_ccm.c b/hw/misc/imx6_ccm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/imx6_ccm.c +++ b/hw/misc/imx6_ccm.c @@ -XXX,XX +XXX,XX @@ static const char *imx6_ccm_reg_name(uint32_t reg) case CCM_CMEOR: return "CMEOR"; default: - sprintf(unknown, "%d ?", reg); + sprintf(unknown, "%u ?", reg); return unknown; } } @@ -XXX,XX +XXX,XX @@ static const char *imx6_analog_reg_name(uint32_t reg) case USB_ANALOG_DIGPROG: return "USB_ANALOG_DIGPROG"; default: - sprintf(unknown, "%d ?", reg); + sprintf(unknown, "%u ?", reg); return unknown; } } @@ -XXX,XX +XXX,XX @@ static uint64_t imx6_analog_get_pll2_clk(IMX6CCMState *dev) freq *= 20; } - DPRINTF("freq = %d\n", (uint32_t)freq); + DPRINTF("freq = %u\n", (uint32_t)freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint64_t imx6_analog_get_pll2_pfd0_clk(IMX6CCMState *dev) freq = imx6_analog_get_pll2_clk(dev) * 18 / EXTRACT(dev->analog[CCM_ANALOG_PFD_528], PFD0_FRAC); - DPRINTF("freq = %d\n", (uint32_t)freq); + DPRINTF("freq = %u\n", (uint32_t)freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint64_t imx6_analog_get_pll2_pfd2_clk(IMX6CCMState *dev) freq = imx6_analog_get_pll2_clk(dev) * 18 / EXTRACT(dev->analog[CCM_ANALOG_PFD_528], PFD2_FRAC); - DPRINTF("freq = %d\n", (uint32_t)freq); + DPRINTF("freq = %u\n", (uint32_t)freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint64_t imx6_analog_get_periph_clk(IMX6CCMState *dev) break; } - DPRINTF("freq = %d\n", (uint32_t)freq); + DPRINTF("freq = %u\n", (uint32_t)freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint64_t imx6_ccm_get_ahb_clk(IMX6CCMState *dev) freq = imx6_analog_get_periph_clk(dev) / (1 + EXTRACT(dev->ccm[CCM_CBCDR], AHB_PODF)); - DPRINTF("freq = %d\n", (uint32_t)freq); + DPRINTF("freq = %u\n", (uint32_t)freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint64_t imx6_ccm_get_ipg_clk(IMX6CCMState *dev) freq = imx6_ccm_get_ahb_clk(dev) / (1 + EXTRACT(dev->ccm[CCM_CBCDR], IPG_PODF)); - DPRINTF("freq = %d\n", (uint32_t)freq); + DPRINTF("freq = %u\n", (uint32_t)freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint64_t imx6_ccm_get_per_clk(IMX6CCMState *dev) freq = imx6_ccm_get_ipg_clk(dev) / (1 + EXTRACT(dev->ccm[CCM_CSCMR1], PERCLK_PODF)); - DPRINTF("freq = %d\n", (uint32_t)freq); + DPRINTF("freq = %u\n", (uint32_t)freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx6_ccm_get_clock_frequency(IMXCCMState *dev, IMXClk clock) break; } - DPRINTF("Clock = %d) = %d\n", clock, freq); + DPRINTF("Clock = %d) = %u\n", clock, freq); return freq; } diff --git a/hw/misc/imx6_src.c b/hw/misc/imx6_src.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/imx6_src.c +++ b/hw/misc/imx6_src.c @@ -XXX,XX +XXX,XX @@ static const char *imx6_src_reg_name(uint32_t reg) case SRC_GPR10: return "SRC_GPR10"; default: - sprintf(unknown, "%d ?", reg); + sprintf(unknown, "%u ?", reg); return unknown; } } -- 2.20.1 From: Alex Chen <alex.chen@huawei.com> We should use printf format specifier "%u" instead of "%d" for argument of type "unsigned int". Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Message-id: 20201126111109.112238-5-alex.chen@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/imx6ul_ccm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/misc/imx6ul_ccm.c b/hw/misc/imx6ul_ccm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/imx6ul_ccm.c +++ b/hw/misc/imx6ul_ccm.c @@ -XXX,XX +XXX,XX @@ static const char *imx6ul_ccm_reg_name(uint32_t reg) case CCM_CMEOR: return "CMEOR"; default: - sprintf(unknown, "%d ?", reg); + sprintf(unknown, "%u ?", reg); return unknown; } } @@ -XXX,XX +XXX,XX @@ static const char *imx6ul_analog_reg_name(uint32_t reg) case USB_ANALOG_DIGPROG: return "USB_ANALOG_DIGPROG"; default: - sprintf(unknown, "%d ?", reg); + sprintf(unknown, "%u ?", reg); return unknown; } } -- 2.20.1 For M-profile CPUs, the range from 0xe0000000 to 0xe00fffff is the Private Peripheral Bus range, which includes all of the memory mapped devices and registers that are part of the CPU itself, including the NVIC, systick timer, and debug and trace components like the Data Watchpoint and Trace unit (DWT). Within this large region, the range 0xe000e000 to 0xe000efff is the System Control Space (NVIC, system registers, systick) and 0xe002e000 to 0exe002efff is its Non-secure alias. The architecture is clear that within the SCS unimplemented registers should be RES0 for privileged accesses and generate BusFault for unprivileged accesses, and we currently implement this. It is less clear about how to handle accesses to unimplemented regions of the wider PPB. Unprivileged accesses should definitely cause BusFaults (R_DQQS), but the behaviour of privileged accesses is not given as a general rule. However, the register definitions of individual registers for components like the DWT all state that they are RES0 if the relevant component is not implemented, so the simplest way to provide that is to provide RAZ/WI for the whole range for privileged accesses. (The v7M Arm ARM does say that reserved registers should be UNK/SBZP.) Expand the container MemoryRegion that the NVIC exposes so that it covers the whole PPB space. This means: * moving the address that the ARMV7M device maps it to down by 0xe000 bytes * moving the off and the offsets within the container of all the subregions forward by 0xe000 bytes * adding a new default MemoryRegion that covers the whole container at a lower priority than anything else and which provides the RAZWI/BusFault behaviour Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-2-peter.maydell@linaro.org --- include/hw/intc/armv7m_nvic.h | 1 + hw/arm/armv7m.c | 2 +- hw/intc/armv7m_nvic.c | 78 ++++++++++++++++++++++++++++++----- 3 files changed, 69 insertions(+), 12 deletions(-) diff --git a/include/hw/intc/armv7m_nvic.h b/include/hw/intc/armv7m_nvic.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/armv7m_nvic.h +++ b/include/hw/intc/armv7m_nvic.h @@ -XXX,XX +XXX,XX @@ struct NVICState { MemoryRegion systickmem; MemoryRegion systick_ns_mem; MemoryRegion container; + MemoryRegion defaultmem; uint32_t num_irq; qemu_irq excpout; diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(sbd, 0, qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_IRQ)); - memory_region_add_subregion(&s->container, 0xe000e000, + memory_region_add_subregion(&s->container, 0xe0000000, sysbus_mmio_get_region(sbd, 0)); for (i = 0; i < ARRAY_SIZE(s->bitband); i++) { diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps nvic_systick_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; +/* + * Unassigned portions of the PPB space are RAZ/WI for privileged + * accesses, and fault for non-privileged accesses. + */ +static MemTxResult ppb_default_read(void *opaque, hwaddr addr, + uint64_t *data, unsigned size, + MemTxAttrs attrs) +{ + qemu_log_mask(LOG_UNIMP, "Read of unassigned area of PPB: offset 0x%x\n", + (uint32_t)addr); + if (attrs.user) { + return MEMTX_ERROR; + } + *data = 0; + return MEMTX_OK; +} + +static MemTxResult ppb_default_write(void *opaque, hwaddr addr, + uint64_t value, unsigned size, + MemTxAttrs attrs) +{ + qemu_log_mask(LOG_UNIMP, "Write of unassigned area of PPB: offset 0x%x\n", + (uint32_t)addr); + if (attrs.user) { + return MEMTX_ERROR; + } + return MEMTX_OK; +} + +static const MemoryRegionOps ppb_default_ops = { + .read_with_attrs = ppb_default_read, + .write_with_attrs = ppb_default_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid.min_access_size = 1, + .valid.max_access_size = 8, +}; + static int nvic_post_load(void *opaque, int version_id) { NVICState *s = opaque; @@ -XXX,XX +XXX,XX @@ static void nvic_systick_trigger(void *opaque, int n, int level) static void armv7m_nvic_realize(DeviceState *dev, Error **errp) { NVICState *s = NVIC(dev); - int regionlen; /* The armv7m container object will have set our CPU pointer */ if (!s->cpu || !arm_feature(&s->cpu->env, ARM_FEATURE_M)) { @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) M_REG_S)); } - /* The NVIC and System Control Space (SCS) starts at 0xe000e000 + /* + * This device provides a single sysbus memory region which + * represents the whole of the "System PPB" space. This is the + * range from 0xe0000000 to 0xe00fffff and includes the NVIC, + * the System Control Space (system registers), the systick timer, + * and for CPUs with the Security extension an NS banked version + * of all of these. + * + * The default behaviour for unimplemented registers/ranges + * (for instance the Data Watchpoint and Trace unit at 0xe0001000) + * is to RAZ/WI for privileged access and BusFault for non-privileged + * access. + * + * The NVIC and System Control Space (SCS) starts at 0xe000e000 * and looks like this: * 0x004 - ICTR * 0x010 - 0xff - systick @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) * generally code determining which banked register to use should * use attrs.secure; code determining actual behaviour of the system * should use env->v7m.secure. + * + * The container covers the whole PPB space. Within it the priority + * of overlapping regions is: + * - default region (for RAZ/WI and BusFault) : -1 + * - system register regions : 0 + * - systick : 1 + * This is because the systick device is a small block of registers + * in the middle of the other system control registers. */ - regionlen = arm_feature(&s->cpu->env, ARM_FEATURE_V8) ? 0x21000 : 0x1000; - memory_region_init(&s->container, OBJECT(s), "nvic", regionlen); - /* The system register region goes at the bottom of the priority - * stack as it covers the whole page. - */ + memory_region_init(&s->container, OBJECT(s), "nvic", 0x100000); + memory_region_init_io(&s->defaultmem, OBJECT(s), &ppb_default_ops, s, + "nvic-default", 0x100000); + memory_region_add_subregion_overlap(&s->container, 0, &s->defaultmem, -1); memory_region_init_io(&s->sysregmem, OBJECT(s), &nvic_sysreg_ops, s, "nvic_sysregs", 0x1000); - memory_region_add_subregion(&s->container, 0, &s->sysregmem); + memory_region_add_subregion(&s->container, 0xe000, &s->sysregmem); memory_region_init_io(&s->systickmem, OBJECT(s), &nvic_systick_ops, s, "nvic_systick", 0xe0); - memory_region_add_subregion_overlap(&s->container, 0x10, + memory_region_add_subregion_overlap(&s->container, 0xe010, &s->systickmem, 1); if (arm_feature(&s->cpu->env, ARM_FEATURE_V8)) { memory_region_init_io(&s->sysreg_ns_mem, OBJECT(s), &nvic_sysreg_ns_ops, &s->sysregmem, "nvic_sysregs_ns", 0x1000); - memory_region_add_subregion(&s->container, 0x20000, &s->sysreg_ns_mem); + memory_region_add_subregion(&s->container, 0x2e000, &s->sysreg_ns_mem); memory_region_init_io(&s->systick_ns_mem, OBJECT(s), &nvic_sysreg_ns_ops, &s->systickmem, "nvic_systick_ns", 0xe0); - memory_region_add_subregion_overlap(&s->container, 0x20010, + memory_region_add_subregion_overlap(&s->container, 0x2e010, &s->systick_ns_mem, 1); } -- 2.20.1 In v8.1M the PXN architecture extension adds a new PXN bit to the MPU_RLAR registers, which forbids execution of code in the region from a privileged mode. This is another feature which is just in the generic "in v8.1M" set and has no ID register field indicating its presence. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-3-peter.maydell@linaro.org --- target/arm/helper.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) 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 @@ bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, } else { uint32_t ap = extract32(env->pmsav8.rbar[secure][matchregion], 1, 2); uint32_t xn = extract32(env->pmsav8.rbar[secure][matchregion], 0, 1); + bool pxn = false; + + if (arm_feature(env, ARM_FEATURE_V8_1M)) { + pxn = extract32(env->pmsav8.rlar[secure][matchregion], 4, 1); + } if (m_is_system_region(env, address)) { /* System space is always execute never */ @@ -XXX,XX +XXX,XX @@ bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, } *prot = simple_ap_to_rw_prot(env, mmu_idx, ap); - if (*prot && !xn) { + if (*prot && !xn && !(pxn && !is_user)) { *prot |= PAGE_EXEC; } /* We don't need to look the attribute up in the MAIR0/MAIR1 -- 2.20.1 In arm_cpu_realizefn() we check whether the board code disabled EL3 via the has_el3 CPU object property, which we create if the CPU starts with the ARM_FEATURE_EL3 feature bit. If it is disabled, then we turn off ARM_FEATURE_EL3 and also zero out the relevant fields in the ID_PFR1 and ID_AA64PFR0 registers. This codepath was incorrectly being taken for M-profile CPUs, which do not have an EL3 and don't set ARM_FEATURE_EL3, but which may have the M-profile Security extension and so should have non-zero values in the ID_PFR1.Security field. Restrict the handling of the feature flag to A/R-profile cores. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-4-peter.maydell@linaro.org --- target/arm/cpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) } } - if (!cpu->has_el3) { + if (!arm_feature(env, ARM_FEATURE_M) && !cpu->has_el3) { /* If the has_el3 CPU property is disabled then we need to disable the * feature. */ -- 2.20.1 Implement the v8.1M VSCCLRM insn, which zeros floating point registers if there is an active floating point context. This requires support in write_neon_element32() for the MO_32 element size, so add it. Because we want to use arm_gen_condlabel(), we need to move the definition of that function up in translate.c so it is before the #include of translate-vfp.c.inc. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-5-peter.maydell@linaro.org --- target/arm/cpu.h | 9 ++++ target/arm/m-nocp.decode | 8 +++- target/arm/translate.c | 21 +++++---- target/arm/translate-vfp.c.inc | 84 ++++++++++++++++++++++++++++++++++ 4 files changed, 111 insertions(+), 11 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_mprofile(const ARMISARegisters *id) return FIELD_EX32(id->id_pfr1, ID_PFR1, MPROGMOD) != 0; } +static inline bool isar_feature_aa32_m_sec_state(const ARMISARegisters *id) +{ + /* + * Return true if M-profile state handling insns + * (VSCCLRM, CLRM, FPCTX access insns) are implemented + */ + return FIELD_EX32(id->id_pfr1, ID_PFR1, SECURITY) >= 3; +} + static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id) { /* Sadly this is encoded differently for A-profile and M-profile */ diff --git a/target/arm/m-nocp.decode b/target/arm/m-nocp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m-nocp.decode +++ b/target/arm/m-nocp.decode @@ -XXX,XX +XXX,XX @@ # If the coprocessor is not present or disabled then we will generate # the NOCP exception; otherwise we let the insn through to the main decode. +%vd_dp 22:1 12:4 +%vd_sp 12:4 22:1 + &nocp cp { # Special cases which do not take an early NOCP: VLLDM and VLSTM VLLDM_VLSTM 1110 1100 001 l:1 rn:4 0000 1010 0000 0000 - # TODO: VSCCLRM (new in v8.1M) is similar: - #VSCCLRM 1110 1100 1-01 1111 ---- 1011 ---- ---0 + # VSCCLRM (new in v8.1M) is similar: + VSCCLRM 1110 1100 1.01 1111 .... 1011 imm:7 0 vd=%vd_dp size=3 + VSCCLRM 1110 1100 1.01 1111 .... 1010 imm:8 vd=%vd_sp size=2 NOCP 111- 1110 ---- ---- ---- cp:4 ---- ---- &nocp NOCP 111- 110- ---- ---- ---- cp:4 ---- ---- &nocp 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 @@ void arm_translate_init(void) a64_translate_init(); } +/* Generate a label used for skipping this instruction */ +static void arm_gen_condlabel(DisasContext *s) +{ + if (!s->condjmp) { + s->condlabel = gen_new_label(); + s->condjmp = 1; + } +} + /* Flags for the disas_set_da_iss info argument: * lower bits hold the Rt register number, higher bits are flags. */ @@ -XXX,XX +XXX,XX @@ 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_32: + tcg_gen_st32_i64(src, cpu_env, off); + break; case MO_64: tcg_gen_st_i64(src, cpu_env, off); break; @@ -XXX,XX +XXX,XX @@ static void gen_srs(DisasContext *s, s->base.is_jmp = DISAS_UPDATE_EXIT; } -/* Generate a label used for skipping this instruction */ -static void arm_gen_condlabel(DisasContext *s) -{ - if (!s->condjmp) { - s->condlabel = gen_new_label(); - s->condjmp = 1; - } -} - /* Skip this instruction if the ARM condition is false */ static void arm_skip_unless(DisasContext *s, uint32_t cond) { 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_VLLDM_VLSTM(DisasContext *s, arg_VLLDM_VLSTM *a) return true; } +static bool trans_VSCCLRM(DisasContext *s, arg_VSCCLRM *a) +{ + int btmreg, topreg; + TCGv_i64 zero; + TCGv_i32 aspen, sfpa; + + if (!dc_isar_feature(aa32_m_sec_state, s)) { + /* Before v8.1M, fall through in decode to NOCP check */ + return false; + } + + /* Explicitly UNDEF because this takes precedence over NOCP */ + if (!arm_dc_feature(s, ARM_FEATURE_M_MAIN) || !s->v8m_secure) { + unallocated_encoding(s); + return true; + } + + if (!dc_isar_feature(aa32_vfp_simd, s)) { + /* NOP if we have neither FP nor MVE */ + return true; + } + + /* + * If FPCCR.ASPEN != 0 && CONTROL_S.SFPA == 0 then there is no + * active floating point context so we must NOP (without doing + * any lazy state preservation or the NOCP check). + */ + aspen = load_cpu_field(v7m.fpccr[M_REG_S]); + sfpa = load_cpu_field(v7m.control[M_REG_S]); + tcg_gen_andi_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); + tcg_gen_xori_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); + tcg_gen_andi_i32(sfpa, sfpa, R_V7M_CONTROL_SFPA_MASK); + tcg_gen_or_i32(sfpa, sfpa, aspen); + arm_gen_condlabel(s); + tcg_gen_brcondi_i32(TCG_COND_EQ, sfpa, 0, s->condlabel); + + if (s->fp_excp_el != 0) { + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, + syn_uncategorized(), s->fp_excp_el); + return true; + } + + topreg = a->vd + a->imm - 1; + btmreg = a->vd; + + /* Convert to Sreg numbers if the insn specified in Dregs */ + if (a->size == 3) { + topreg = topreg * 2 + 1; + btmreg *= 2; + } + + if (topreg > 63 || (topreg > 31 && !(topreg & 1))) { + /* UNPREDICTABLE: we choose to undef */ + unallocated_encoding(s); + return true; + } + + /* Silently ignore requests to clear D16-D31 if they don't exist */ + if (topreg > 31 && !dc_isar_feature(aa32_simd_r32, s)) { + topreg = 31; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* Zero the Sregs from btmreg to topreg inclusive. */ + zero = tcg_const_i64(0); + if (btmreg & 1) { + write_neon_element64(zero, btmreg >> 1, 1, MO_32); + btmreg++; + } + for (; btmreg + 1 <= topreg; btmreg += 2) { + write_neon_element64(zero, btmreg >> 1, 0, MO_64); + } + if (btmreg == topreg) { + write_neon_element64(zero, btmreg >> 1, 0, MO_32); + btmreg++; + } + assert(btmreg == topreg + 1); + /* TODO: when MVE is implemented, zero VPR here */ + return true; +} + static bool trans_NOCP(DisasContext *s, arg_nocp *a) { /* -- 2.20.1 In v8.1M the new CLRM instruction allows zeroing an arbitrary set of the general-purpose registers and APSR. Implement this. The encoding is a subset of the LDMIA T2 encoding, using what would be Rn=0b1111 (which UNDEFs for LDMIA). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-6-peter.maydell@linaro.org --- target/arm/t32.decode | 6 +++++- target/arm/translate.c | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+), 1 deletion(-) diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ UXTAB 1111 1010 0101 .... 1111 .... 10.. .... @rrr_rot STM_t32 1110 1000 10.0 .... ................ @ldstm i=1 b=0 STM_t32 1110 1001 00.0 .... ................ @ldstm i=0 b=1 -LDM_t32 1110 1000 10.1 .... ................ @ldstm i=1 b=0 +{ + # Rn=15 UNDEFs for LDM; M-profile CLRM uses that encoding + CLRM 1110 1000 1001 1111 list:16 + LDM_t32 1110 1000 10.1 .... ................ @ldstm i=1 b=0 +} LDM_t32 1110 1001 00.1 .... ................ @ldstm i=0 b=1 &rfe !extern rn w pu 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 bool trans_LDM_t16(DisasContext *s, arg_ldst_block *a) return do_ldm(s, a, 1); } +static bool trans_CLRM(DisasContext *s, arg_CLRM *a) +{ + int i; + TCGv_i32 zero; + + if (!dc_isar_feature(aa32_m_sec_state, s)) { + return false; + } + + if (extract32(a->list, 13, 1)) { + return false; + } + + if (!a->list) { + /* UNPREDICTABLE; we choose to UNDEF */ + return false; + } + + zero = tcg_const_i32(0); + for (i = 0; i < 15; i++) { + if (extract32(a->list, i, 1)) { + /* Clear R[i] */ + tcg_gen_mov_i32(cpu_R[i], zero); + } + } + if (extract32(a->list, 15, 1)) { + /* + * Clear APSR (by calling the MSR helper with the same argument + * as for "MSR APSR_nzcvqg, Rn": mask = 0b1100, SYSM=0) + */ + TCGv_i32 maskreg = tcg_const_i32(0xc << 8); + gen_helper_v7m_msr(cpu_env, maskreg, zero); + tcg_temp_free_i32(maskreg); + } + tcg_temp_free_i32(zero); + return true; +} + /* * Branch, branch with link */ -- 2.20.1 For M-profile before v8.1M, the only valid register for VMSR/VMRS is the FPSCR. We have a comment that states this, but the actual logic to forbid accesses for any other register value is missing, so we would end up with A-profile style behaviour. Add the missing check. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-7-peter.maydell@linaro.org --- target/arm/translate-vfp.c.inc | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) 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_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) * Accesses to R15 are UNPREDICTABLE; we choose to undef. * (FPSCR -> r15 is a special case which writes to the PSR flags.) */ - if (a->rt == 15 && (!a->l || a->reg != ARM_VFP_FPSCR)) { + if (a->reg != ARM_VFP_FPSCR) { + return false; + } + if (a->rt == 15 && !a->l) { return false; } } -- 2.20.1 Currently M-profile borrows the A-profile code for VMSR and VMRS (access to the FP system registers), because all it needs to support is the FPSCR. In v8.1M things become significantly more complicated in two ways: * there are several new FP system registers; some have side effects on read, and one (FPCXT_NS) needs to avoid the usual vfp_access_check() and the "only if FPU implemented" check * all sysregs are now accessible both by VMRS/VMSR (which reads/writes a general purpose register) and also by VLDR/VSTR (which reads/writes them directly to memory) Refactor the structure of how we handle VMSR/VMRS to cope with this: * keep the M-profile code entirely separate from the A-profile code * abstract out the "read or write the general purpose register" part of the code into a loadfn or storefn function pointer, so we can reuse it for VLDR/VSTR. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-8-peter.maydell@linaro.org --- target/arm/cpu.h | 3 + target/arm/translate-vfp.c.inc | 182 ++++++++++++++++++++++++++++++--- 2 files changed, 171 insertions(+), 14 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ enum arm_cpu_mode { #define ARM_VFP_FPINST 9 #define ARM_VFP_FPINST2 10 +/* QEMU-internal value meaning "FPSCR, but we care only about NZCV" */ +#define QEMU_VFP_FPSCR_NZCV 0xffff + /* iwMMXt coprocessor control registers. */ #define ARM_IWMMXT_wCID 0 #define ARM_IWMMXT_wCon 1 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) return true; } +/* + * M-profile provides two different sets of instructions that can + * access floating point system registers: VMSR/VMRS (which move + * to/from a general purpose register) and VLDR/VSTR sysreg (which + * move directly to/from memory). In some cases there are also side + * effects which must happen after any write to memory (which could + * cause an exception). So we implement the common logic for the + * sysreg access in gen_M_fp_sysreg_write() and gen_M_fp_sysreg_read(), + * which take pointers to callback functions which will perform the + * actual "read/write general purpose register" and "read/write + * memory" operations. + */ + +/* + * Emit code to store the sysreg to its final destination; frees the + * TCG temp 'value' it is passed. + */ +typedef void fp_sysreg_storefn(DisasContext *s, void *opaque, TCGv_i32 value); +/* + * Emit code to load the value to be copied to the sysreg; returns + * a new TCG temporary + */ +typedef TCGv_i32 fp_sysreg_loadfn(DisasContext *s, void *opaque); + +/* Common decode/access checks for fp sysreg read/write */ +typedef enum FPSysRegCheckResult { + FPSysRegCheckFailed, /* caller should return false */ + FPSysRegCheckDone, /* caller should return true */ + FPSysRegCheckContinue, /* caller should continue generating code */ +} FPSysRegCheckResult; + +static FPSysRegCheckResult fp_sysreg_checks(DisasContext *s, int regno) +{ + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return FPSysRegCheckFailed; + } + + switch (regno) { + case ARM_VFP_FPSCR: + case QEMU_VFP_FPSCR_NZCV: + break; + default: + return FPSysRegCheckFailed; + } + + if (!vfp_access_check(s)) { + return FPSysRegCheckDone; + } + + return FPSysRegCheckContinue; +} + +static bool gen_M_fp_sysreg_write(DisasContext *s, int regno, + + fp_sysreg_loadfn *loadfn, + void *opaque) +{ + /* Do a write to an M-profile floating point system register */ + TCGv_i32 tmp; + + switch (fp_sysreg_checks(s, regno)) { + case FPSysRegCheckFailed: + return false; + case FPSysRegCheckDone: + return true; + case FPSysRegCheckContinue: + break; + } + + switch (regno) { + case ARM_VFP_FPSCR: + tmp = loadfn(s, opaque); + gen_helper_vfp_set_fpscr(cpu_env, tmp); + tcg_temp_free_i32(tmp); + gen_lookup_tb(s); + break; + default: + g_assert_not_reached(); + } + return true; +} + +static bool gen_M_fp_sysreg_read(DisasContext *s, int regno, + fp_sysreg_storefn *storefn, + void *opaque) +{ + /* Do a read from an M-profile floating point system register */ + TCGv_i32 tmp; + + switch (fp_sysreg_checks(s, regno)) { + case FPSysRegCheckFailed: + return false; + case FPSysRegCheckDone: + return true; + case FPSysRegCheckContinue: + break; + } + + switch (regno) { + case ARM_VFP_FPSCR: + tmp = tcg_temp_new_i32(); + gen_helper_vfp_get_fpscr(tmp, cpu_env); + storefn(s, opaque, tmp); + break; + case QEMU_VFP_FPSCR_NZCV: + /* + * Read just NZCV; this is a special case to avoid the + * helper call for the "VMRS to CPSR.NZCV" insn. + */ + tmp = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]); + tcg_gen_andi_i32(tmp, tmp, 0xf0000000); + storefn(s, opaque, tmp); + break; + default: + g_assert_not_reached(); + } + return true; +} + +static void fp_sysreg_to_gpr(DisasContext *s, void *opaque, TCGv_i32 value) +{ + arg_VMSR_VMRS *a = opaque; + + if (a->rt == 15) { + /* Set the 4 flag bits in the CPSR */ + gen_set_nzcv(value); + tcg_temp_free_i32(value); + } else { + store_reg(s, a->rt, value); + } +} + +static TCGv_i32 gpr_to_fp_sysreg(DisasContext *s, void *opaque) +{ + arg_VMSR_VMRS *a = opaque; + + return load_reg(s, a->rt); +} + +static bool gen_M_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) +{ + /* + * Accesses to R15 are UNPREDICTABLE; we choose to undef. + * FPSCR -> r15 is a special case which writes to the PSR flags; + * set a->reg to a special value to tell gen_M_fp_sysreg_read() + * we only care about the top 4 bits of FPSCR there. + */ + if (a->rt == 15) { + if (a->l && a->reg == ARM_VFP_FPSCR) { + a->reg = QEMU_VFP_FPSCR_NZCV; + } else { + return false; + } + } + + if (a->l) { + /* VMRS, move FP system register to gp register */ + return gen_M_fp_sysreg_read(s, a->reg, fp_sysreg_to_gpr, a); + } else { + /* VMSR, move gp register to FP system register */ + return gen_M_fp_sysreg_write(s, a->reg, gpr_to_fp_sysreg, a); + } +} + static bool trans_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) { TCGv_i32 tmp; bool ignore_vfp_enabled = false; - if (!dc_isar_feature(aa32_fpsp_v2, s)) { - return false; + if (arm_dc_feature(s, ARM_FEATURE_M)) { + return gen_M_VMSR_VMRS(s, a); } - if (arm_dc_feature(s, ARM_FEATURE_M)) { - /* - * The only M-profile VFP vmrs/vmsr sysreg is FPSCR. - * Accesses to R15 are UNPREDICTABLE; we choose to undef. - * (FPSCR -> r15 is a special case which writes to the PSR flags.) - */ - if (a->reg != ARM_VFP_FPSCR) { - return false; - } - if (a->rt == 15 && !a->l) { - return false; - } + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; } switch (a->reg) { -- 2.20.1 The constant-expander functions like negate, plus_2, etc, are generally useful; move them up in translate.c so we can use them in the VFP/Neon decoders as well as in the A32/T32/T16 decoders. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-9-peter.maydell@linaro.org --- target/arm/translate.c | 46 +++++++++++++++++++++++------------------- 1 file changed, 25 insertions(+), 21 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 arm_gen_condlabel(DisasContext *s) } } +/* + * Constant expanders for the decoders. + */ + +static int negate(DisasContext *s, int x) +{ + return -x; +} + +static int plus_2(DisasContext *s, int x) +{ + return x + 2; +} + +static int times_2(DisasContext *s, int x) +{ + return x * 2; +} + +static int times_4(DisasContext *s, int x) +{ + return x * 4; +} + /* Flags for the disas_set_da_iss info argument: * lower bits hold the Rt register number, higher bits are flags. */ @@ -XXX,XX +XXX,XX @@ static void arm_skip_unless(DisasContext *s, uint32_t cond) /* - * Constant expanders for the decoders. + * Constant expanders used by T16/T32 decode */ -static int negate(DisasContext *s, int x) -{ - return -x; -} - -static int plus_2(DisasContext *s, int x) -{ - return x + 2; -} - -static int times_2(DisasContext *s, int x) -{ - return x * 2; -} - -static int times_4(DisasContext *s, int x) -{ - return x * 4; -} - /* Return only the rotation part of T32ExpandImm. */ static int t32_expandimm_rot(DisasContext *s, int x) { -- 2.20.1 Implement the new-in-v8.1M VLDR/VSTR variants which directly read or write FP system registers to memory. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-10-peter.maydell@linaro.org --- target/arm/vfp.decode | 14 ++++++ target/arm/translate-vfp.c.inc | 91 ++++++++++++++++++++++++++++++++++ 2 files changed, 105 insertions(+) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VLDR_VSTR_hp ---- 1101 u:1 .0 l:1 rn:4 .... 1001 imm:8 vd=%vd_sp VLDR_VSTR_sp ---- 1101 u:1 .0 l:1 rn:4 .... 1010 imm:8 vd=%vd_sp VLDR_VSTR_dp ---- 1101 u:1 .0 l:1 rn:4 .... 1011 imm:8 vd=%vd_dp +# M-profile VLDR/VSTR to sysreg +%vldr_sysreg 22:1 13:3 +%imm7_0x4 0:7 !function=times_4 + +&vldr_sysreg rn reg imm a w p +@vldr_sysreg .... ... . a:1 . . . rn:4 ... . ... .. ....... \ + reg=%vldr_sysreg imm=%imm7_0x4 &vldr_sysreg + +# P=0 W=0 is SEE "Related encodings", so split into two patterns +VLDR_sysreg ---- 110 1 . . w:1 1 .... ... 0 111 11 ....... @vldr_sysreg p=1 +VLDR_sysreg ---- 110 0 . . 1 1 .... ... 0 111 11 ....... @vldr_sysreg p=0 w=1 +VSTR_sysreg ---- 110 1 . . w:1 0 .... ... 0 111 11 ....... @vldr_sysreg p=1 +VSTR_sysreg ---- 110 0 . . 1 0 .... ... 0 111 11 ....... @vldr_sysreg p=0 w=1 + # We split the load/store multiple up into two patterns to avoid # overlap with other insns in the "Advanced SIMD load/store and 64-bit move" # grouping: 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_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) return true; } +static void fp_sysreg_to_memory(DisasContext *s, void *opaque, TCGv_i32 value) +{ + arg_vldr_sysreg *a = opaque; + uint32_t offset = a->imm; + TCGv_i32 addr; + + if (!a->a) { + offset = - offset; + } + + addr = load_reg(s, a->rn); + if (a->p) { + tcg_gen_addi_i32(addr, addr, offset); + } + + if (s->v8m_stackcheck && a->rn == 13 && a->w) { + gen_helper_v8m_stackcheck(cpu_env, addr); + } + + gen_aa32_st_i32(s, value, addr, get_mem_index(s), + MO_UL | MO_ALIGN | s->be_data); + tcg_temp_free_i32(value); + + if (a->w) { + /* writeback */ + if (!a->p) { + tcg_gen_addi_i32(addr, addr, offset); + } + store_reg(s, a->rn, addr); + } else { + tcg_temp_free_i32(addr); + } +} + +static TCGv_i32 memory_to_fp_sysreg(DisasContext *s, void *opaque) +{ + arg_vldr_sysreg *a = opaque; + uint32_t offset = a->imm; + TCGv_i32 addr; + TCGv_i32 value = tcg_temp_new_i32(); + + if (!a->a) { + offset = - offset; + } + + addr = load_reg(s, a->rn); + if (a->p) { + tcg_gen_addi_i32(addr, addr, offset); + } + + if (s->v8m_stackcheck && a->rn == 13 && a->w) { + gen_helper_v8m_stackcheck(cpu_env, addr); + } + + gen_aa32_ld_i32(s, value, addr, get_mem_index(s), + MO_UL | MO_ALIGN | s->be_data); + + if (a->w) { + /* writeback */ + if (!a->p) { + tcg_gen_addi_i32(addr, addr, offset); + } + store_reg(s, a->rn, addr); + } else { + tcg_temp_free_i32(addr); + } + return value; +} + +static bool trans_VLDR_sysreg(DisasContext *s, arg_vldr_sysreg *a) +{ + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + return false; + } + if (a->rn == 15) { + return false; + } + return gen_M_fp_sysreg_write(s, a->reg, memory_to_fp_sysreg, a); +} + +static bool trans_VSTR_sysreg(DisasContext *s, arg_vldr_sysreg *a) +{ + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + return false; + } + if (a->rn == 15) { + return false; + } + return gen_M_fp_sysreg_read(s, a->reg, fp_sysreg_to_memory, a); +} + static bool trans_VMOV_half(DisasContext *s, arg_VMOV_single *a) { TCGv_i32 tmp; -- 2.20.1 v8.1M defines a new FP system register FPSCR_nzcvqc; this behaves like the existing FPSCR, except that it reads and writes only bits [31:27] of the FPSCR (the N, Z, C, V and QC flag bits). (Unlike the FPSCR, the special case for Rt=15 of writing the CPSR.NZCV is not permitted.) Implement the register. Since we don't yet implement MVE, we handle the QC bit as RES0, with todo comments for where we will need to add support later. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-11-peter.maydell@linaro.org --- target/arm/cpu.h | 13 +++++++++++++ target/arm/translate-vfp.c.inc | 27 +++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val); #define FPCR_FZ (1 << 24) /* Flush-to-zero enable bit */ #define FPCR_DN (1 << 25) /* Default NaN enable bit */ #define FPCR_QC (1 << 27) /* Cumulative saturation bit */ +#define FPCR_V (1 << 28) /* FP overflow flag */ +#define FPCR_C (1 << 29) /* FP carry flag */ +#define FPCR_Z (1 << 30) /* FP zero flag */ +#define FPCR_N (1 << 31) /* FP negative flag */ + +#define FPCR_NZCV_MASK (FPCR_N | FPCR_Z | FPCR_C | FPCR_V) +#define FPCR_NZCVQC_MASK (FPCR_NZCV_MASK | FPCR_QC) static inline uint32_t vfp_get_fpsr(CPUARMState *env) { @@ -XXX,XX +XXX,XX @@ enum arm_cpu_mode { #define ARM_VFP_FPEXC 8 #define ARM_VFP_FPINST 9 #define ARM_VFP_FPINST2 10 +/* These ones are M-profile only */ +#define ARM_VFP_FPSCR_NZCVQC 2 +#define ARM_VFP_VPR 12 +#define ARM_VFP_P0 13 +#define ARM_VFP_FPCXT_NS 14 +#define ARM_VFP_FPCXT_S 15 /* QEMU-internal value meaning "FPSCR, but we care only about NZCV" */ #define QEMU_VFP_FPSCR_NZCV 0xffff 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 FPSysRegCheckResult fp_sysreg_checks(DisasContext *s, int regno) case ARM_VFP_FPSCR: case QEMU_VFP_FPSCR_NZCV: break; + case ARM_VFP_FPSCR_NZCVQC: + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + return false; + } + break; default: return FPSysRegCheckFailed; } @@ -XXX,XX +XXX,XX @@ static bool gen_M_fp_sysreg_write(DisasContext *s, int regno, tcg_temp_free_i32(tmp); gen_lookup_tb(s); break; + case ARM_VFP_FPSCR_NZCVQC: + { + TCGv_i32 fpscr; + tmp = loadfn(s, opaque); + /* + * TODO: when we implement MVE, write the QC bit. + * For non-MVE, QC is RES0. + */ + tcg_gen_andi_i32(tmp, tmp, FPCR_NZCV_MASK); + fpscr = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]); + tcg_gen_andi_i32(fpscr, fpscr, ~FPCR_NZCV_MASK); + tcg_gen_or_i32(fpscr, fpscr, tmp); + store_cpu_field(fpscr, vfp.xregs[ARM_VFP_FPSCR]); + tcg_temp_free_i32(tmp); + break; + } default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static bool gen_M_fp_sysreg_read(DisasContext *s, int regno, gen_helper_vfp_get_fpscr(tmp, cpu_env); storefn(s, opaque, tmp); break; + case ARM_VFP_FPSCR_NZCVQC: + /* + * TODO: MVE has a QC bit, which we probably won't store + * in the xregs[] field. For non-MVE, where QC is RES0, + * we can just fall through to the FPSCR_NZCV case. + */ case QEMU_VFP_FPSCR_NZCV: /* * Read just NZCV; this is a special case to avoid the -- 2.20.1 We defined a constant name for the mask of NZCV bits in the FPCR/FPSCR in the previous commit; use it in a couple of places in existing code, where we're masking out everything except NZCV for the "load to Rt=15 sets CPSR.NZCV" special case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-12-peter.maydell@linaro.org --- target/arm/translate-vfp.c.inc | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) 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 gen_M_fp_sysreg_read(DisasContext *s, int regno, * helper call for the "VMRS to CPSR.NZCV" insn. */ tmp = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]); - tcg_gen_andi_i32(tmp, tmp, 0xf0000000); + tcg_gen_andi_i32(tmp, tmp, FPCR_NZCV_MASK); storefn(s, opaque, tmp); break; default: @@ -XXX,XX +XXX,XX @@ static bool trans_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) case ARM_VFP_FPSCR: if (a->rt == 15) { tmp = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]); - tcg_gen_andi_i32(tmp, tmp, 0xf0000000); + tcg_gen_andi_i32(tmp, tmp, FPCR_NZCV_MASK); } else { tmp = tcg_temp_new_i32(); gen_helper_vfp_get_fpscr(tmp, cpu_env); -- 2.20.1 Factor out the code which handles M-profile lazy FP state preservation from full_vfp_access_check(); accesses to the FPCXT_NS register are a special case which need to do just this part (corresponding in the pseudocode to the PreserveFPState() function), and not the full set of actions matching the pseudocode ExecuteFPCheck() which normal FP instructions need to do. 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: 20201119215617.29887-13-peter.maydell@linaro.org --- target/arm/translate-vfp.c.inc | 45 ++++++++++++++++++++-------------- 1 file changed, 27 insertions(+), 18 deletions(-) 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 inline long vfp_f16_offset(unsigned reg, bool top) return offs; } +/* + * Generate code for M-profile lazy FP state preservation if needed; + * this corresponds to the pseudocode PreserveFPState() function. + */ +static void gen_preserve_fp_state(DisasContext *s) +{ + if (s->v7m_lspact) { + /* + * Lazy state saving affects external memory and also the NVIC, + * so we must mark it as an IO operation for icount (and cause + * this to be the last insn in the TB). + */ + if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { + s->base.is_jmp = DISAS_UPDATE_EXIT; + gen_io_start(); + } + gen_helper_v7m_preserve_fp_state(cpu_env); + /* + * If the preserve_fp_state helper doesn't throw an exception + * then it will clear LSPACT; we don't need to repeat this for + * any further FP insns in this TB. + */ + s->v7m_lspact = false; + } +} + /* * Check that VFP access is enabled. If it is, do the necessary * M-profile lazy-FP handling and then return true. @@ -XXX,XX +XXX,XX @@ static bool full_vfp_access_check(DisasContext *s, bool ignore_vfp_enabled) /* Handle M-profile lazy FP state mechanics */ /* Trigger lazy-state preservation if necessary */ - if (s->v7m_lspact) { - /* - * Lazy state saving affects external memory and also the NVIC, - * so we must mark it as an IO operation for icount (and cause - * this to be the last insn in the TB). - */ - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - s->base.is_jmp = DISAS_UPDATE_EXIT; - gen_io_start(); - } - gen_helper_v7m_preserve_fp_state(cpu_env); - /* - * If the preserve_fp_state helper doesn't throw an exception - * then it will clear LSPACT; we don't need to repeat this for - * any further FP insns in this TB. - */ - s->v7m_lspact = false; - } + gen_preserve_fp_state(s); /* Update ownership of FP context: set FPCCR.S to match current state */ if (s->v8m_fpccr_s_wrong) { -- 2.20.1 Implement the new-in-v8.1M FPCXT_S floating point system register. This is for saving and restoring the secure floating point context, and it reads and writes bits [27:0] from the FPSCR and the CONTROL.SFPA bit in bit [31]. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-14-peter.maydell@linaro.org --- target/arm/translate-vfp.c.inc | 58 ++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) 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 FPSysRegCheckResult fp_sysreg_checks(DisasContext *s, int regno) return false; } break; + case ARM_VFP_FPCXT_S: + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + return false; + } + if (!s->v8m_secure) { + return false; + } + break; default: return FPSysRegCheckFailed; } @@ -XXX,XX +XXX,XX @@ static bool gen_M_fp_sysreg_write(DisasContext *s, int regno, tcg_temp_free_i32(tmp); break; } + case ARM_VFP_FPCXT_S: + { + TCGv_i32 sfpa, control, fpscr; + /* Set FPSCR[27:0] and CONTROL.SFPA from value */ + tmp = loadfn(s, opaque); + sfpa = tcg_temp_new_i32(); + tcg_gen_shri_i32(sfpa, tmp, 31); + control = load_cpu_field(v7m.control[M_REG_S]); + tcg_gen_deposit_i32(control, control, sfpa, + R_V7M_CONTROL_SFPA_SHIFT, 1); + store_cpu_field(control, v7m.control[M_REG_S]); + fpscr = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]); + tcg_gen_andi_i32(fpscr, fpscr, FPCR_NZCV_MASK); + tcg_gen_andi_i32(tmp, tmp, ~FPCR_NZCV_MASK); + tcg_gen_or_i32(fpscr, fpscr, tmp); + store_cpu_field(fpscr, vfp.xregs[ARM_VFP_FPSCR]); + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(sfpa); + break; + } default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static bool gen_M_fp_sysreg_read(DisasContext *s, int regno, tcg_gen_andi_i32(tmp, tmp, FPCR_NZCV_MASK); storefn(s, opaque, tmp); break; + case ARM_VFP_FPCXT_S: + { + TCGv_i32 control, sfpa, fpscr; + /* Bits [27:0] from FPSCR, bit [31] from CONTROL.SFPA */ + tmp = tcg_temp_new_i32(); + sfpa = tcg_temp_new_i32(); + gen_helper_vfp_get_fpscr(tmp, cpu_env); + tcg_gen_andi_i32(tmp, tmp, ~FPCR_NZCV_MASK); + control = load_cpu_field(v7m.control[M_REG_S]); + tcg_gen_andi_i32(sfpa, control, R_V7M_CONTROL_SFPA_MASK); + tcg_gen_shli_i32(sfpa, sfpa, 31 - R_V7M_CONTROL_SFPA_SHIFT); + tcg_gen_or_i32(tmp, tmp, sfpa); + tcg_temp_free_i32(sfpa); + /* + * Store result before updating FPSCR etc, in case + * it is a memory write which causes an exception. + */ + storefn(s, opaque, tmp); + /* + * Now we must reset FPSCR from FPDSCR_NS, and clear + * CONTROL.SFPA; so we'll end the TB here. + */ + tcg_gen_andi_i32(control, control, ~R_V7M_CONTROL_SFPA_MASK); + store_cpu_field(control, v7m.control[M_REG_S]); + fpscr = load_cpu_field(v7m.fpdscr[M_REG_NS]); + gen_helper_vfp_set_fpscr(cpu_env, fpscr); + tcg_temp_free_i32(fpscr); + gen_lookup_tb(s); + break; + } default: g_assert_not_reached(); } -- 2.20.1 The FPDSCR register has a similar layout to the FPSCR. In v8.1M it gains new fields FZ16 (if half-precision floating point is supported) and LTPSIZE (always reads as 4). Update the reset value and the code that handles writes to this register accordingly. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-16-peter.maydell@linaro.org --- target/arm/cpu.h | 5 +++++ hw/intc/armv7m_nvic.c | 9 ++++++++- target/arm/cpu.c | 3 +++ 3 files changed, 16 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val); #define FPCR_IXE (1 << 12) /* Inexact exception trap enable */ #define FPCR_IDE (1 << 15) /* Input Denormal exception trap enable */ #define FPCR_FZ16 (1 << 19) /* ARMv8.2+, FP16 flush-to-zero */ +#define FPCR_RMODE_MASK (3 << 22) /* Rounding mode */ #define FPCR_FZ (1 << 24) /* Flush-to-zero enable bit */ #define FPCR_DN (1 << 25) /* Default NaN enable bit */ +#define FPCR_AHP (1 << 26) /* Alternative half-precision */ #define FPCR_QC (1 << 27) /* Cumulative saturation bit */ #define FPCR_V (1 << 28) /* FP overflow flag */ #define FPCR_C (1 << 29) /* FP carry flag */ #define FPCR_Z (1 << 30) /* FP zero flag */ #define FPCR_N (1 << 31) /* FP negative flag */ +#define FPCR_LTPSIZE_SHIFT 16 /* LTPSIZE, M-profile only */ +#define FPCR_LTPSIZE_MASK (7 << FPCR_LTPSIZE_SHIFT) + #define FPCR_NZCV_MASK (FPCR_N | FPCR_Z | FPCR_C | FPCR_V) #define FPCR_NZCVQC_MASK (FPCR_NZCV_MASK | FPCR_QC) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, break; case 0xf3c: /* FPDSCR */ if (cpu_isar_feature(aa32_vfp_simd, cpu)) { - value &= 0x07c00000; + uint32_t mask = FPCR_AHP | FPCR_DN | FPCR_FZ | FPCR_RMODE_MASK; + if (cpu_isar_feature(any_fp16, cpu)) { + mask |= FPCR_FZ16; + } + value &= mask; + if (cpu_isar_feature(aa32_lob, cpu)) { + value |= 4 << FPCR_LTPSIZE_SHIFT; + } cpu->env.v7m.fpdscr[attrs.secure] = value; } break; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(DeviceState *dev) * always reset to 4. */ env->v7m.ltpsize = 4; + /* The LTPSIZE field in FPDSCR is constant and reads as 4. */ + env->v7m.fpdscr[M_REG_NS] = 4 << FPCR_LTPSIZE_SHIFT; + env->v7m.fpdscr[M_REG_S] = 4 << FPCR_LTPSIZE_SHIFT; } if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { -- 2.20.1 In v8.0M, on exception entry the registers R0-R3, R12, APSR and EPSR are zeroed for an exception taken to Non-secure state; for an exception taken to Secure state they become UNKNOWN, and we chose to leave them at their previous values. In v8.1M the behaviour is specified more tightly and these registers are always zeroed regardless of the security state that the exception targets (see rule R_KPZV). Implement this. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-17-peter.maydell@linaro.org --- target/arm/m_helper.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) 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 @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, * Clear registers if necessary to prevent non-secure exception * code being able to see register values from secure code. * Where register values become architecturally UNKNOWN we leave - * them with their previous values. + * them with their previous values. v8.1M is tighter than v8.0M + * here and always zeroes the caller-saved registers regardless + * of the security state the exception is targeting. */ if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { - if (!targets_secure) { + if (!targets_secure || arm_feature(env, ARM_FEATURE_V8_1M)) { /* * Always clear the caller-saved registers (they have been * pushed to the stack earlier in v7m_push_stack()). @@ -XXX,XX +XXX,XX @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, * v7m_push_callee_stack()). */ int i; + /* + * r4..r11 are callee-saves, zero only if background + * state was Secure (EXCRET.S == 1) and exception + * targets Non-secure state + */ + bool zero_callee_saves = !targets_secure && + (lr & R_V7M_EXCRET_S_MASK); for (i = 0; i < 13; i++) { - /* r4..r11 are callee-saves, zero only if EXCRET.S == 1 */ - if (i < 4 || i > 11 || (lr & R_V7M_EXCRET_S_MASK)) { + if (i < 4 || i > 11 || zero_callee_saves) { env->regs[i] = 0; } } -- 2.20.1 In v8.1M, vector table fetch failures don't set HFSR.FORCED (see rule R_LLRP). (In previous versions of the architecture this was either required or IMPDEF.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-18-peter.maydell@linaro.org --- target/arm/m_helper.c | 6 +++++- 1 file changed, 5 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 @@ load_fail: * The HardFault is Secure if BFHFNMINS is 0 (meaning that all HFs are * secure); otherwise it targets the same security state as the * underlying exception. + * In v8.1M HardFaults from vector table fetch fails don't set FORCED. */ if (!(cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK)) { exc_secure = true; } - env->v7m.hfsr |= R_V7M_HFSR_VECTTBL_MASK | R_V7M_HFSR_FORCED_MASK; + env->v7m.hfsr |= R_V7M_HFSR_VECTTBL_MASK; + if (!arm_feature(env, ARM_FEATURE_V8_1M)) { + env->v7m.hfsr |= R_V7M_HFSR_FORCED_MASK; + } armv7m_nvic_set_pending_derived(env->nvic, ARMV7M_EXCP_HARD, exc_secure); return false; } -- 2.20.1 In v8.1M a REVIDR register is defined, which is at address 0xe00ecfc and is a read-only IMPDEF register providing implementation specific minor revision information, like the v8A REVIDR_EL1. Implement this. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-19-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) } return val; } + case 0xcfc: + if (!arm_feature(&cpu->env, ARM_FEATURE_V8_1M)) { + goto bad_offset; + } + return cpu->revidr; case 0xd00: /* CPUID Base. */ return cpu->midr; case 0xd04: /* Interrupt Control State (ICSR) */ -- 2.20.1 In v8.1M a new exception return check is added which may cause a NOCP UsageFault (see rule R_XLTP): before we clear s0..s15 and the FPSCR we must check whether access to CP10 from the Security state of the returning exception is disabled; if it is then we must take a fault. (Note that for our implementation CPPWR is always RAZ/WI and so can never cause CP10 accesses to fail.) The other v8.1M change to this register-clearing code is that if MVE is implemented VPR must also be cleared, so add a TODO comment to that effect. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-20-peter.maydell@linaro.org --- target/arm/m_helper.c | 22 +++++++++++++++++++++- 1 file changed, 21 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 @@ static void do_v7m_exception_exit(ARMCPU *cpu) v7m_exception_taken(cpu, excret, true, false); return; } else { - /* Clear s0..s15 and FPSCR */ + if (arm_feature(env, ARM_FEATURE_V8_1M)) { + /* v8.1M adds this NOCP check */ + bool nsacr_pass = exc_secure || + extract32(env->v7m.nsacr, 10, 1); + bool cpacr_pass = v7m_cpacr_pass(env, exc_secure, true); + if (!nsacr_pass) { + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, true); + env->v7m.cfsr[M_REG_S] |= R_V7M_CFSR_NOCP_MASK; + qemu_log_mask(CPU_LOG_INT, "...taking UsageFault on existing " + "stackframe: NSACR prevents clearing FPU registers\n"); + v7m_exception_taken(cpu, excret, true, false); + } else if (!cpacr_pass) { + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, + exc_secure); + env->v7m.cfsr[exc_secure] |= R_V7M_CFSR_NOCP_MASK; + qemu_log_mask(CPU_LOG_INT, "...taking UsageFault on existing " + "stackframe: CPACR prevents clearing FPU registers\n"); + v7m_exception_taken(cpu, excret, true, false); + } + } + /* Clear s0..s15 and FPSCR; TODO also VPR when MVE is implemented */ int i; for (i = 0; i < 16; i += 2) { -- 2.20.1 v8.1M adds new encodings of VLLDM and VLSTM (where bit 7 is set). The only difference is that: * the old T1 encodings UNDEF if the implementation implements 32 Dregs (this is currently architecturally impossible for M-profile) * the new T2 encodings have the implementation-defined option to read from memory (discarding the data) or write UNKNOWN values to memory for the stack slots that would be D16-D31 We choose not to make those accesses, so for us the two instructions behave identically assuming they don't UNDEF. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-21-peter.maydell@linaro.org --- target/arm/m-nocp.decode | 2 +- target/arm/translate-vfp.c.inc | 25 +++++++++++++++++++++++++ 2 files changed, 26 insertions(+), 1 deletion(-) diff --git a/target/arm/m-nocp.decode b/target/arm/m-nocp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m-nocp.decode +++ b/target/arm/m-nocp.decode @@ -XXX,XX +XXX,XX @@ { # Special cases which do not take an early NOCP: VLLDM and VLSTM - VLLDM_VLSTM 1110 1100 001 l:1 rn:4 0000 1010 0000 0000 + VLLDM_VLSTM 1110 1100 001 l:1 rn:4 0000 1010 op:1 000 0000 # VSCCLRM (new in v8.1M) is similar: VSCCLRM 1110 1100 1.01 1111 .... 1011 imm:7 0 vd=%vd_dp size=3 VSCCLRM 1110 1100 1.01 1111 .... 1010 imm:8 vd=%vd_sp size=2 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_VLLDM_VLSTM(DisasContext *s, arg_VLLDM_VLSTM *a) !arm_dc_feature(s, ARM_FEATURE_V8)) { return false; } + + if (a->op) { + /* + * T2 encoding ({D0-D31} reglist): v8.1M and up. We choose not + * to take the IMPDEF option to make memory accesses to the stack + * slots that correspond to the D16-D31 registers (discarding + * read data and writing UNKNOWN values), so for us the T2 + * encoding behaves identically to the T1 encoding. + */ + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + return false; + } + } else { + /* + * T1 encoding ({D0-D15} reglist); undef if we have 32 Dregs. + * This is currently architecturally impossible, but we add the + * check to stay in line with the pseudocode. Note that we must + * emit code for the UNDEF so it takes precedence over the NOCP. + */ + if (dc_isar_feature(aa32_simd_r32, s)) { + unallocated_encoding(s); + return true; + } + } + /* * If not secure, UNDEF. We must emit code for this * rather than returning false so that this takes -- 2.20.1 v8.1M introduces a new TRD flag in the CCR register, which enables checking for stack frame integrity signatures on SG instructions. This bit is not banked, and is always RAZ/WI to Non-secure code. Adjust the code for handling CCR reads and writes to handle this. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-23-peter.maydell@linaro.org --- target/arm/cpu.h | 2 ++ hw/intc/armv7m_nvic.c | 26 ++++++++++++++++++-------- 2 files changed, 20 insertions(+), 8 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(V7M_CCR, STKOFHFNMIGN, 10, 1) FIELD(V7M_CCR, DC, 16, 1) FIELD(V7M_CCR, IC, 17, 1) FIELD(V7M_CCR, BP, 18, 1) +FIELD(V7M_CCR, LOB, 19, 1) +FIELD(V7M_CCR, TRD, 20, 1) /* V7M SCR bits */ FIELD(V7M_SCR, SLEEPONEXIT, 1, 1) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) } return cpu->env.v7m.scr[attrs.secure]; case 0xd14: /* Configuration Control. */ - /* The BFHFNMIGN bit is the only non-banked bit; we - * keep it in the non-secure copy of the register. + /* + * Non-banked bits: BFHFNMIGN (stored in the NS copy of the register) + * and TRD (stored in the S copy of the register) */ val = cpu->env.v7m.ccr[attrs.secure]; val |= cpu->env.v7m.ccr[M_REG_NS] & R_V7M_CCR_BFHFNMIGN_MASK; @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, cpu->env.v7m.scr[attrs.secure] = value; break; case 0xd14: /* Configuration Control. */ + { + uint32_t mask; + if (!arm_feature(&cpu->env, ARM_FEATURE_M_MAIN)) { goto bad_offset; } /* Enforce RAZ/WI on reserved and must-RAZ/WI bits */ - value &= (R_V7M_CCR_STKALIGN_MASK | - R_V7M_CCR_BFHFNMIGN_MASK | - R_V7M_CCR_DIV_0_TRP_MASK | - R_V7M_CCR_UNALIGN_TRP_MASK | - R_V7M_CCR_USERSETMPEND_MASK | - R_V7M_CCR_NONBASETHRDENA_MASK); + mask = R_V7M_CCR_STKALIGN_MASK | + R_V7M_CCR_BFHFNMIGN_MASK | + R_V7M_CCR_DIV_0_TRP_MASK | + R_V7M_CCR_UNALIGN_TRP_MASK | + R_V7M_CCR_USERSETMPEND_MASK | + R_V7M_CCR_NONBASETHRDENA_MASK; + if (arm_feature(&cpu->env, ARM_FEATURE_V8_1M) && attrs.secure) { + /* TRD is always RAZ/WI from NS */ + mask |= R_V7M_CCR_TRD_MASK; + } + value &= mask; if (arm_feature(&cpu->env, ARM_FEATURE_V8)) { /* v8M makes NONBASETHRDENA and STKALIGN be RES1 */ @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, cpu->env.v7m.ccr[attrs.secure] = value; break; + } case 0xd24: /* System Handler Control and State (SHCSR) */ if (!arm_feature(&cpu->env, ARM_FEATURE_V7)) { goto bad_offset; -- 2.20.1 v8.1M introduces a new TRD flag in the CCR register, which enables checking for stack frame integrity signatures on SG instructions. Add the code in the SG insn implementation for the new behaviour. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-24-peter.maydell@linaro.org --- target/arm/m_helper.c | 86 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) 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 @@ static bool v7m_read_half_insn(ARMCPU *cpu, ARMMMUIdx mmu_idx, return true; } +static bool v7m_read_sg_stack_word(ARMCPU *cpu, ARMMMUIdx mmu_idx, + uint32_t addr, uint32_t *spdata) +{ + /* + * Read a word of data from the stack for the SG instruction, + * writing the value into *spdata. If the load succeeds, return + * true; otherwise pend an appropriate exception and return false. + * (We can't use data load helpers here that throw an exception + * because of the context we're called in, which is halfway through + * arm_v7m_cpu_do_interrupt().) + */ + CPUState *cs = CPU(cpu); + CPUARMState *env = &cpu->env; + MemTxAttrs attrs = {}; + MemTxResult txres; + target_ulong page_size; + hwaddr physaddr; + int prot; + ARMMMUFaultInfo fi = {}; + ARMCacheAttrs cacheattrs = {}; + uint32_t value; + + if (get_phys_addr(env, addr, MMU_DATA_LOAD, mmu_idx, &physaddr, + &attrs, &prot, &page_size, &fi, &cacheattrs)) { + /* MPU/SAU lookup failed */ + if (fi.type == ARMFault_QEMU_SFault) { + qemu_log_mask(CPU_LOG_INT, + "...SecureFault during stack word read\n"); + env->v7m.sfsr |= R_V7M_SFSR_AUVIOL_MASK | R_V7M_SFSR_SFARVALID_MASK; + env->v7m.sfar = addr; + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SECURE, false); + } else { + qemu_log_mask(CPU_LOG_INT, + "...MemManageFault during stack word read\n"); + env->v7m.cfsr[M_REG_S] |= R_V7M_CFSR_DACCVIOL_MASK | + R_V7M_CFSR_MMARVALID_MASK; + env->v7m.mmfar[M_REG_S] = addr; + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_MEM, false); + } + return false; + } + value = address_space_ldl(arm_addressspace(cs, attrs), physaddr, + attrs, &txres); + if (txres != MEMTX_OK) { + /* BusFault trying to read the data */ + qemu_log_mask(CPU_LOG_INT, + "...BusFault during stack word read\n"); + env->v7m.cfsr[M_REG_NS] |= + (R_V7M_CFSR_PRECISERR_MASK | R_V7M_CFSR_BFARVALID_MASK); + env->v7m.bfar = addr; + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_BUS, false); + return false; + } + + *spdata = value; + return true; +} + static bool v7m_handle_execute_nsc(ARMCPU *cpu) { /* @@ -XXX,XX +XXX,XX @@ static bool v7m_handle_execute_nsc(ARMCPU *cpu) */ qemu_log_mask(CPU_LOG_INT, "...really an SG instruction at 0x%08" PRIx32 ", executing it\n", env->regs[15]); + + if (cpu_isar_feature(aa32_m_sec_state, cpu) && + !arm_v7m_is_handler_mode(env)) { + /* + * v8.1M exception stack frame integrity check. Note that we + * must perform the memory access even if CCR_S.TRD is zero + * and we aren't going to check what the data loaded is. + */ + uint32_t spdata, sp; + + /* + * We know we are currently NS, so the S stack pointers must be + * in other_ss_{psp,msp}, not in regs[13]/other_sp. + */ + sp = v7m_using_psp(env) ? env->v7m.other_ss_psp : env->v7m.other_ss_msp; + if (!v7m_read_sg_stack_word(cpu, mmu_idx, sp, &spdata)) { + /* Stack access failed and an exception has been pended */ + return false; + } + + if (env->v7m.ccr[M_REG_S] & R_V7M_CCR_TRD_MASK) { + if (((spdata & ~1) == 0xfefa125a) || + !(env->v7m.control[M_REG_S] & 1)) { + goto gen_invep; + } + } + } + env->regs[14] &= ~1; env->v7m.control[M_REG_S] &= ~R_V7M_CONTROL_SFPA_MASK; switch_v7m_security_state(env, true); -- 2.20.1 In commit 077d7449100d824a4 we added code to handle the v8M requirement that returns from NMI or HardFault forcibly deactivate those exceptions regardless of what interrupt the guest is trying to deactivate. Unfortunately this broke the handling of the "illegal exception return because the returning exception number is not active" check for those cases. In the pseudocode this test is done on the exception the guest asks to return from, but because our implementation was doing this in armv7m_nvic_complete_irq() after the new "deactivate NMI/HardFault regardless" code we ended up doing the test on the VecInfo for that exception instead, which usually meant failing to raise the illegal exception return fault. In the case for "configurable exception targeting the opposite security state" we detected the illegal-return case but went ahead and deactivated the VecInfo anyway, which is wrong because that is the VecInfo for the other security state. Rearrange the code so that we first identify the illegal return cases, then see if we really need to deactivate NMI or HardFault instead, and finally do the deactivation. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-25-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 59 +++++++++++++++++++++++-------------------- 1 file changed, 32 insertions(+), 27 deletions(-) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ int armv7m_nvic_complete_irq(void *opaque, int irq, bool secure) { NVICState *s = (NVICState *)opaque; VecInfo *vec = NULL; - int ret; + int ret = 0; assert(irq > ARMV7M_EXCP_RESET && irq < s->num_irq); + trace_nvic_complete_irq(irq, secure); + + if (secure && exc_is_banked(irq)) { + vec = &s->sec_vectors[irq]; + } else { + vec = &s->vectors[irq]; + } + + /* + * Identify illegal exception return cases. We can't immediately + * return at this point because we still need to deactivate + * (either this exception or NMI/HardFault) first. + */ + if (!exc_is_banked(irq) && exc_targets_secure(s, irq) != secure) { + /* + * Return from a configurable exception targeting the opposite + * security state from the one we're trying to complete it for. + * Clear vec because it's not really the VecInfo for this + * (irq, secstate) so we mustn't deactivate it. + */ + ret = -1; + vec = NULL; + } else if (!vec->active) { + /* Return from an inactive interrupt */ + ret = -1; + } else { + /* Legal return, we will return the RETTOBASE bit value to the caller */ + ret = nvic_rettobase(s); + } + /* * For negative priorities, v8M will forcibly deactivate the appropriate * NMI or HardFault regardless of what interrupt we're being asked to @@ -XXX,XX +XXX,XX @@ int armv7m_nvic_complete_irq(void *opaque, int irq, bool secure) } if (!vec) { - if (secure && exc_is_banked(irq)) { - vec = &s->sec_vectors[irq]; - } else { - vec = &s->vectors[irq]; - } - } - - trace_nvic_complete_irq(irq, secure); - - if (!vec->active) { - /* Tell the caller this was an illegal exception return */ - return -1; - } - - /* - * If this is a configurable exception and it is currently - * targeting the opposite security state from the one we're trying - * to complete it for, this counts as an illegal exception return. - * We still need to deactivate whatever vector the logic above has - * selected, though, as it might not be the same as the one for the - * requested exception number. - */ - if (!exc_is_banked(irq) && exc_targets_secure(s, irq) != secure) { - ret = -1; - } else { - ret = nvic_rettobase(s); + return ret; } vec->active = 0; -- 2.20.1 For v8.1M the architecture mandates that CPUs must provide at least the "minimal RAS implementation" from the Reliability, Availability and Serviceability extension. This consists of: * an ESB instruction which is a NOP -- since it is in the HINT space we need only add a comment * an RFSR register which will RAZ/WI * a RAZ/WI AIRCR.IESB bit -- the code which handles writes to AIRCR does not allow setting of RES0 bits, so we already treat this as RAZ/WI; add a comment noting that this is deliberate * minimal implementation of the RAS register block at 0xe0005000 -- this will be in a subsequent commit * setting the ID_PFR0.RAS field to 0b0010 -- we will do this when we add the Cortex-M55 CPU model Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-26-peter.maydell@linaro.org --- target/arm/cpu.h | 14 ++++++++++++++ target/arm/t32.decode | 4 ++++ hw/intc/armv7m_nvic.c | 13 +++++++++++++ 3 files changed, 31 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(ID_MMFR4, LSM, 20, 4) FIELD(ID_MMFR4, CCIDX, 24, 4) FIELD(ID_MMFR4, EVT, 28, 4) +FIELD(ID_PFR0, STATE0, 0, 4) +FIELD(ID_PFR0, STATE1, 4, 4) +FIELD(ID_PFR0, STATE2, 8, 4) +FIELD(ID_PFR0, STATE3, 12, 4) +FIELD(ID_PFR0, CSV2, 16, 4) +FIELD(ID_PFR0, AMU, 20, 4) +FIELD(ID_PFR0, DIT, 24, 4) +FIELD(ID_PFR0, RAS, 28, 4) + FIELD(ID_PFR1, PROGMOD, 0, 4) FIELD(ID_PFR1, SECURITY, 4, 4) FIELD(ID_PFR1, MPROGMOD, 8, 4) @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_predinv(const ARMISARegisters *id) return FIELD_EX32(id->id_isar6, ID_ISAR6, SPECRES) != 0; } +static inline bool isar_feature_aa32_ras(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_pfr0, ID_PFR0, RAS) != 0; +} + static inline bool isar_feature_aa32_mprofile(const ARMISARegisters *id) { return FIELD_EX32(id->id_pfr1, ID_PFR1, MPROGMOD) != 0; diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ CLZ 1111 1010 1011 ---- 1111 .... 1000 .... @rdm # SEV 1111 0011 1010 1111 1000 0000 0000 0100 # SEVL 1111 0011 1010 1111 1000 0000 0000 0101 + # For M-profile minimal-RAS ESB can be a NOP, which is the + # default behaviour since it is in the hint space. + # ESB 1111 0011 1010 1111 1000 0000 0001 0000 + # The canonical nop ends in 0000 0000, but the whole rest # of the space is "reserved hint, behaves as nop". NOP 1111 0011 1010 1111 1000 0000 ---- ---- diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) return 0; } return cpu->env.v7m.sfar; + case 0xf04: /* RFSR */ + if (!cpu_isar_feature(aa32_ras, cpu)) { + goto bad_offset; + } + /* We provide minimal-RAS only: RFSR is RAZ/WI */ + return 0; case 0xf34: /* FPCCR */ if (!cpu_isar_feature(aa32_vfp_simd, cpu)) { return 0; @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, R_V7M_AIRCR_PRIGROUP_SHIFT, R_V7M_AIRCR_PRIGROUP_LENGTH); } + /* AIRCR.IESB is RAZ/WI because we implement only minimal RAS */ if (attrs.secure) { /* These bits are only writable by secure */ cpu->env.v7m.aircr = value & @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, } break; } + case 0xf04: /* RFSR */ + if (!cpu_isar_feature(aa32_ras, cpu)) { + goto bad_offset; + } + /* We provide minimal-RAS only: RFSR is RAZ/WI */ + break; case 0xf34: /* FPCCR */ if (cpu_isar_feature(aa32_vfp_simd, cpu)) { /* Not all bits here are banked. */ -- 2.20.1 The RAS feature has a block of memory-mapped registers at offset 0x5000 within the PPB. For a "minimal RAS" implementation we provide no error records and so the only registers that exist in the block are ERRIIDR and ERRDEVID. The "RAZ/WI for privileged, BusFault for nonprivileged" behaviour of the "nvic-default" region is actually valid for minimal-RAS, so the main benefit of providing an explicit implementation of the register block is more accurate LOG_UNIMP messages, and a framework for where we could add a real RAS implementation later if necessary. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-27-peter.maydell@linaro.org --- include/hw/intc/armv7m_nvic.h | 1 + hw/intc/armv7m_nvic.c | 56 +++++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) diff --git a/include/hw/intc/armv7m_nvic.h b/include/hw/intc/armv7m_nvic.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/armv7m_nvic.h +++ b/include/hw/intc/armv7m_nvic.h @@ -XXX,XX +XXX,XX @@ struct NVICState { MemoryRegion sysreg_ns_mem; MemoryRegion systickmem; MemoryRegion systick_ns_mem; + MemoryRegion ras_mem; MemoryRegion container; MemoryRegion defaultmem; diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps nvic_systick_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; + +static MemTxResult ras_read(void *opaque, hwaddr addr, + uint64_t *data, unsigned size, + MemTxAttrs attrs) +{ + if (attrs.user) { + return MEMTX_ERROR; + } + + switch (addr) { + case 0xe10: /* ERRIIDR */ + /* architect field = Arm; product/variant/revision 0 */ + *data = 0x43b; + break; + case 0xfc8: /* ERRDEVID */ + /* Minimal RAS: we implement 0 error record indexes */ + *data = 0; + break; + default: + qemu_log_mask(LOG_UNIMP, "Read RAS register offset 0x%x\n", + (uint32_t)addr); + *data = 0; + break; + } + return MEMTX_OK; +} + +static MemTxResult ras_write(void *opaque, hwaddr addr, + uint64_t value, unsigned size, + MemTxAttrs attrs) +{ + if (attrs.user) { + return MEMTX_ERROR; + } + + switch (addr) { + default: + qemu_log_mask(LOG_UNIMP, "Write to RAS register offset 0x%x\n", + (uint32_t)addr); + break; + } + return MEMTX_OK; +} + +static const MemoryRegionOps ras_ops = { + .read_with_attrs = ras_read, + .write_with_attrs = ras_write, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + /* * Unassigned portions of the PPB space are RAZ/WI for privileged * accesses, and fault for non-privileged accesses. @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) &s->systick_ns_mem, 1); } + if (cpu_isar_feature(aa32_ras, s->cpu)) { + memory_region_init_io(&s->ras_mem, OBJECT(s), + &ras_ops, s, "nvic_ras", 0x1000); + memory_region_add_subregion(&s->container, 0x5000, &s->ras_mem); + } + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->container); } -- 2.20.1 Correct a typo in the name we give the NVIC object. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-28-peter.maydell@linaro.org --- hw/arm/armv7m.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ static void armv7m_instance_init(Object *obj) memory_region_init(&s->container, obj, "armv7m-container", UINT64_MAX); - object_initialize_child(obj, "nvnic", &s->nvic, TYPE_NVIC); + object_initialize_child(obj, "nvic", &s->nvic, TYPE_NVIC); object_property_add_alias(obj, "num-irq", OBJECT(&s->nvic), "num-irq"); -- 2.20.1