First ARM pullreq of the 2.10 cycle... thanks -- PMM The following changes since commit 64c8ed97cceabac4fafe17fca8d88ef08183f439: Open 2.10 development tree (2017-04-20 15:42:31 +0100) are available in the git repository at: git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20170420 for you to fetch changes up to f4e8e4edda875cab9df91dc4ae9767f7cb1f50aa: arm: Remove workarounds for old M-profile exception return implementation (2017-04-20 17:39:17 +0100) ---------------------------------------------------------------- target-arm queue: * implement M profile exception return properly * cadence GEM: fix multiqueue handling bugs * pxa2xx.c: QOMify a device * arm/kvm: Remove trailing newlines from error_report() * stellaris: Don't hw_error() on bad register accesses * Add assertion about FSC format for syndrome registers * Move excnames[] array into arm_log_exceptions() * exynos: minor code cleanups * hw/arm/boot: take Linux/arm64 TEXT_OFFSET header field into account * Fix APSR writes via M profile MSR ---------------------------------------------------------------- Alistair Francis (5): cadence_gem: Read the correct queue descriptor cadence_gem: Correct the multi-queue can rx logic cadence_gem: Correct the interupt logic cadence_gem: Make the revision a property xlnx-zynqmp: Set the Cadence GEM revision Ard Biesheuvel (1): hw/arm/boot: take Linux/arm64 TEXT_OFFSET header field into account Ishani Chugh (1): arm/kvm: Remove trailing newlines from error_report() Krzysztof Kozlowski (3): hw/arm/exynos: Convert fprintf to qemu_log_mask/error_report hw/char/exynos4210_uart: Constify static array and few arguments hw/misc/exynos4210_pmu: Reorder local variables for readability Peter Maydell (13): target/arm: Add missing entries to excnames[] for log strings arm: Move excnames[] array into arm_log_exceptions() target/arm: Add assertion about FSC format for syndrome registers stellaris: Don't hw_error() on bad register accesses arm: Don't implement BXJ on M-profile CPUs arm: Thumb shift operations should not permit interworking branches arm: Factor out "generate right kind of step exception" arm: Move gen_set_condexec() and gen_set_pc_im() up in the file arm: Move condition-failed codepath generation out of if() arm: Abstract out "are we singlestepping" test to utility function arm: Track M profile handler mode state in TB flags arm: Implement M profile exception return properly arm: Remove workarounds for old M-profile exception return implementation Suramya Shah (1): hw/arm: Qomify pxa2xx.c include/hw/net/cadence_gem.h | 1 + target/arm/cpu.h | 10 +++ target/arm/internals.h | 21 ----- target/arm/translate.h | 5 ++ hw/arm/boot.c | 64 ++++++++++++--- hw/arm/exynos4_boards.c | 7 +- hw/arm/pxa2xx.c | 14 ++-- hw/arm/stellaris.c | 60 ++++++++------ hw/arm/xlnx-zynqmp.c | 6 +- hw/char/exynos4210_uart.c | 8 +- hw/misc/exynos4210_pmu.c | 4 +- hw/net/cadence_gem.c | 45 +++++++---- hw/timer/exynos4210_mct.c | 6 +- hw/timer/exynos4210_pwm.c | 13 ++-- hw/timer/exynos4210_rtc.c | 19 ++--- target/arm/cpu.c | 43 +--------- target/arm/helper.c | 19 +++++ target/arm/kvm64.c | 4 +- target/arm/op_helper.c | 23 ++++-- target/arm/translate.c | 181 +++++++++++++++++++++++++++++-------------- 20 files changed, 341 insertions(+), 212 deletions(-) From: Ard Biesheuvel <ard.biesheuvel@linaro.org> The arm64 boot protocol stipulates that the kernel must be loaded TEXT_OFFSET bytes beyond a 2 MB aligned base address, where TEXT_OFFSET could be any 4 KB multiple between 0 and 2 MB, and whose value can be found in the header of the Image file. So after attempts to load the arm64 kernel image as an ELF file or as a U-Boot image have failed (both of which have their own way of specifying the load offset), try to determine the TEXT_OFFSET from the image after loading it but before mapping it as a ROM mapping into the guest address space. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1489414630-21609-1-git-send-email-ard.biesheuvel@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/boot.c | 64 +++++++++++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 53 insertions(+), 11 deletions(-) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ #define KERNEL_LOAD_ADDR 0x00010000 #define KERNEL64_LOAD_ADDR 0x00080000 +#define ARM64_TEXT_OFFSET_OFFSET 8 +#define ARM64_MAGIC_OFFSET 56 + typedef enum { FIXUP_NONE = 0, /* do nothing */ FIXUP_TERMINATOR, /* end of insns */ @@ -XXX,XX +XXX,XX @@ static uint64_t arm_load_elf(struct arm_boot_info *info, uint64_t *pentry, return ret; } +static uint64_t load_aarch64_image(const char *filename, hwaddr mem_base, + hwaddr *entry) +{ + hwaddr kernel_load_offset = KERNEL64_LOAD_ADDR; + uint8_t *buffer; + int size; + + /* On aarch64, it's the bootloader's job to uncompress the kernel. */ + size = load_image_gzipped_buffer(filename, LOAD_IMAGE_MAX_GUNZIP_BYTES, + &buffer); + + if (size < 0) { + gsize len; + + /* Load as raw file otherwise */ + if (!g_file_get_contents(filename, (char **)&buffer, &len, NULL)) { + return -1; + } + size = len; + } + + /* check the arm64 magic header value -- very old kernels may not have it */ + if (memcmp(buffer + ARM64_MAGIC_OFFSET, "ARM\x64", 4) == 0) { + uint64_t hdrvals[2]; + + /* The arm64 Image header has text_offset and image_size fields at 8 and + * 16 bytes into the Image header, respectively. The text_offset field + * is only valid if the image_size is non-zero. + */ + memcpy(&hdrvals, buffer + ARM64_TEXT_OFFSET_OFFSET, sizeof(hdrvals)); + if (hdrvals[1] != 0) { + kernel_load_offset = le64_to_cpu(hdrvals[0]); + } + } + + *entry = mem_base + kernel_load_offset; + rom_add_blob_fixed(filename, buffer, size, *entry); + + g_free(buffer); + + return size; +} + static void arm_load_kernel_notify(Notifier *notifier, void *data) { CPUState *cs; @@ -XXX,XX +XXX,XX @@ static void arm_load_kernel_notify(Notifier *notifier, void *data) int is_linux = 0; uint64_t elf_entry, elf_low_addr, elf_high_addr; int elf_machine; - hwaddr entry, kernel_load_offset; + hwaddr entry; static const ARMInsnFixup *primary_loader; ArmLoadKernelNotifier *n = DO_UPCAST(ArmLoadKernelNotifier, notifier, notifier); @@ -XXX,XX +XXX,XX @@ static void arm_load_kernel_notify(Notifier *notifier, void *data) if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { primary_loader = bootloader_aarch64; - kernel_load_offset = KERNEL64_LOAD_ADDR; elf_machine = EM_AARCH64; } else { primary_loader = bootloader; if (!info->write_board_setup) { primary_loader += BOOTLOADER_NO_BOARD_SETUP_OFFSET; } - kernel_load_offset = KERNEL_LOAD_ADDR; elf_machine = EM_ARM; } @@ -XXX,XX +XXX,XX @@ static void arm_load_kernel_notify(Notifier *notifier, void *data) kernel_size = load_uimage(info->kernel_filename, &entry, NULL, &is_linux, NULL, NULL); } - /* On aarch64, it's the bootloader's job to uncompress the kernel. */ if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64) && kernel_size < 0) { - entry = info->loader_start + kernel_load_offset; - kernel_size = load_image_gzipped(info->kernel_filename, entry, - info->ram_size - kernel_load_offset); + kernel_size = load_aarch64_image(info->kernel_filename, + info->loader_start, &entry); is_linux = 1; - } - if (kernel_size < 0) { - entry = info->loader_start + kernel_load_offset; + } else if (kernel_size < 0) { + /* 32-bit ARM */ + entry = info->loader_start + KERNEL_LOAD_ADDR; kernel_size = load_image_targphys(info->kernel_filename, entry, - info->ram_size - kernel_load_offset); + info->ram_size - KERNEL_LOAD_ADDR); is_linux = 1; } if (kernel_size < 0) { -- 2.7.4 From: Krzysztof Kozlowski <krzk@kernel.org> qemu_log_mask() and error_report() are preferred over fprintf() for logging errors. Also remove square brackets [] and additional new line characters in printed messages. Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20170313184750.429-2-krzk@kernel.org [PMM: wrapped long line] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/exynos4_boards.c | 7 ++++--- hw/timer/exynos4210_mct.c | 6 ++++-- hw/timer/exynos4210_pwm.c | 13 +++++++------ hw/timer/exynos4210_rtc.c | 19 ++++++++++--------- 4 files changed, 25 insertions(+), 20 deletions(-) diff --git a/hw/arm/exynos4_boards.c b/hw/arm/exynos4_boards.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4_boards.c +++ b/hw/arm/exynos4_boards.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/error-report.h" #include "qemu-common.h" #include "cpu.h" #include "sysemu/sysemu.h" @@ -XXX,XX +XXX,XX @@ static Exynos4210State *exynos4_boards_init_common(MachineState *machine, MachineClass *mc = MACHINE_GET_CLASS(machine); if (smp_cpus != EXYNOS4210_NCPUS && !qtest_enabled()) { - fprintf(stderr, "%s board supports only %d CPU cores. Ignoring smp_cpus" - " value.\n", - mc->name, EXYNOS4210_NCPUS); + error_report("%s board supports only %d CPU cores, ignoring smp_cpus" + " value", + mc->name, EXYNOS4210_NCPUS); } exynos4_board_binfo.ram_size = exynos4_board_ram_size[board_type]; diff --git a/hw/timer/exynos4210_mct.c b/hw/timer/exynos4210_mct.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/exynos4210_mct.c +++ b/hw/timer/exynos4210_mct.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/log.h" #include "hw/sysbus.h" #include "qemu/timer.h" #include "qemu/main-loop.h" @@ -XXX,XX +XXX,XX @@ break; case L0_TCNTO: case L1_TCNTO: case L0_ICNTO: case L1_ICNTO: case L0_FRCNTO: case L1_FRCNTO: - fprintf(stderr, "\n[exynos4210.mct: write to RO register " - TARGET_FMT_plx "]\n\n", offset); + qemu_log_mask(LOG_GUEST_ERROR, + "exynos4210.mct: write to RO register " TARGET_FMT_plx, + offset); break; case L0_INT_CSTAT: case L1_INT_CSTAT: diff --git a/hw/timer/exynos4210_pwm.c b/hw/timer/exynos4210_pwm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/exynos4210_pwm.c +++ b/hw/timer/exynos4210_pwm.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/log.h" #include "hw/sysbus.h" #include "qemu/timer.h" #include "qemu-common.h" @@ -XXX,XX +XXX,XX @@ static uint64_t exynos4210_pwm_read(void *opaque, hwaddr offset, break; default: - fprintf(stderr, - "[exynos4210.pwm: bad read offset " TARGET_FMT_plx "]\n", - offset); + qemu_log_mask(LOG_GUEST_ERROR, + "exynos4210.pwm: bad read offset " TARGET_FMT_plx, + offset); break; } return value; @@ -XXX,XX +XXX,XX @@ static void exynos4210_pwm_write(void *opaque, hwaddr offset, break; default: - fprintf(stderr, - "[exynos4210.pwm: bad write offset " TARGET_FMT_plx "]\n", - offset); + qemu_log_mask(LOG_GUEST_ERROR, + "exynos4210.pwm: bad write offset " TARGET_FMT_plx, + offset); break; } diff --git a/hw/timer/exynos4210_rtc.c b/hw/timer/exynos4210_rtc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/exynos4210_rtc.c +++ b/hw/timer/exynos4210_rtc.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/log.h" #include "hw/sysbus.h" #include "qemu/timer.h" #include "qemu-common.h" @@ -XXX,XX +XXX,XX @@ static uint64_t exynos4210_rtc_read(void *opaque, hwaddr offset, break; default: - fprintf(stderr, - "[exynos4210.rtc: bad read offset " TARGET_FMT_plx "]\n", - offset); + qemu_log_mask(LOG_GUEST_ERROR, + "exynos4210.rtc: bad read offset " TARGET_FMT_plx, + offset); break; } return value; @@ -XXX,XX +XXX,XX @@ static void exynos4210_rtc_write(void *opaque, hwaddr offset, if (value > TICNT_THRESHOLD) { s->reg_ticcnt = value; } else { - fprintf(stderr, - "[exynos4210.rtc: bad TICNT value %u ]\n", - (uint32_t)value); + qemu_log_mask(LOG_GUEST_ERROR, + "exynos4210.rtc: bad TICNT value %u", + (uint32_t)value); } break; @@ -XXX,XX +XXX,XX @@ static void exynos4210_rtc_write(void *opaque, hwaddr offset, break; default: - fprintf(stderr, - "[exynos4210.rtc: bad write offset " TARGET_FMT_plx "]\n", - offset); + qemu_log_mask(LOG_GUEST_ERROR, + "exynos4210.rtc: bad write offset " TARGET_FMT_plx, + offset); break; } -- 2.7.4 From: Krzysztof Kozlowski <krzk@kernel.org> The static array exynos4210_uart_regs with register values is not modified so it can be made const. Few other functions accept driver or uart state as an argument but they do not change it and do not cast it so this can be made const for code safeness. Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org> Message-id: 20170313184750.429-3-krzk@kernel.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/exynos4210_uart.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/hw/char/exynos4210_uart.c b/hw/char/exynos4210_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/exynos4210_uart.c +++ b/hw/char/exynos4210_uart.c @@ -XXX,XX +XXX,XX @@ typedef struct Exynos4210UartReg { uint32_t reset_value; } Exynos4210UartReg; -static Exynos4210UartReg exynos4210_uart_regs[] = { +static const Exynos4210UartReg exynos4210_uart_regs[] = { {"ULCON", ULCON, 0x00000000}, {"UCON", UCON, 0x00003000}, {"UFCON", UFCON, 0x00000000}, @@ -XXX,XX +XXX,XX @@ static uint8_t fifo_retrieve(Exynos4210UartFIFO *q) return ret; } -static int fifo_elements_number(Exynos4210UartFIFO *q) +static int fifo_elements_number(const Exynos4210UartFIFO *q) { if (q->sp < q->rp) { return q->size - q->rp + q->sp; @@ -XXX,XX +XXX,XX @@ static int fifo_elements_number(Exynos4210UartFIFO *q) return q->sp - q->rp; } -static int fifo_empty_elements_number(Exynos4210UartFIFO *q) +static int fifo_empty_elements_number(const Exynos4210UartFIFO *q) { return q->size - fifo_elements_number(q); } @@ -XXX,XX +XXX,XX @@ static void fifo_reset(Exynos4210UartFIFO *q) q->rp = 0; } -static uint32_t exynos4210_uart_Tx_FIFO_trigger_level(Exynos4210UartState *s) +static uint32_t exynos4210_uart_Tx_FIFO_trigger_level(const Exynos4210UartState *s) { uint32_t level = 0; uint32_t reg; -- 2.7.4 From: Krzysztof Kozlowski <krzk@kernel.org> Short declaration of 'i' was in the middle of declarations with assignments. Make it a little bit more readable. Additionally switch from "unsigned" to "unsigned int" as this pattern is more widely used. No functional change. Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20170313184750.429-4-krzk@kernel.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/exynos4210_pmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/misc/exynos4210_pmu.c b/hw/misc/exynos4210_pmu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/exynos4210_pmu.c +++ b/hw/misc/exynos4210_pmu.c @@ -XXX,XX +XXX,XX @@ static uint64_t exynos4210_pmu_read(void *opaque, hwaddr offset, unsigned size) { Exynos4210PmuState *s = (Exynos4210PmuState *)opaque; - unsigned i; const Exynos4210PmuReg *reg_p = exynos4210_pmu_regs; + unsigned int i; for (i = 0; i < PMU_NUM_OF_REGISTERS; i++) { if (reg_p->offset == offset) { @@ -XXX,XX +XXX,XX @@ static void exynos4210_pmu_write(void *opaque, hwaddr offset, uint64_t val, unsigned size) { Exynos4210PmuState *s = (Exynos4210PmuState *)opaque; - unsigned i; const Exynos4210PmuReg *reg_p = exynos4210_pmu_regs; + unsigned int i; for (i = 0; i < PMU_NUM_OF_REGISTERS; i++) { if (reg_p->offset == offset) { -- 2.7.4 Recent changes have added new EXCP_ values to ARM but forgot to update the excnames[] array which is used to provide human-readable strings when printing information about the exception for debug logging. Add the missing entries, and add a comment to the list of #defines to help avoid the mistake being repeated in future. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 1491486340-25988-1-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.h | 1 + target/arm/internals.h | 2 ++ 2 files changed, 3 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 @@ #define EXCP_SEMIHOST 16 /* semihosting call */ #define EXCP_NOCP 17 /* v7M NOCP UsageFault */ #define EXCP_INVSTATE 18 /* v7M INVSTATE UsageFault */ +/* NB: new EXCP_ defines should be added to the excnames[] array too */ #define ARMV7M_EXCP_RESET 1 #define ARMV7M_EXCP_NMI 2 diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static const char * const excnames[] = { [EXCP_VIRQ] = "Virtual IRQ", [EXCP_VFIQ] = "Virtual FIQ", [EXCP_SEMIHOST] = "Semihosting call", + [EXCP_NOCP] = "v7M NOCP UsageFault", + [EXCP_INVSTATE] = "v7M INVSTATE UsageFault", }; /* Scale factor for generic timers, ie number of ns per tick. -- 2.7.4 The excnames[] array is defined in internals.h because we used to use it from two different source files for handling logging of AArch32 and AArch64 exception entry. Refactoring means that it's now used only in arm_log_exception() in helper.c, so move the array into that function. Suggested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1491821097-5647-1-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.h | 2 +- target/arm/internals.h | 23 ----------------------- target/arm/helper.c | 19 +++++++++++++++++++ 3 files changed, 20 insertions(+), 24 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 @@ #define EXCP_SEMIHOST 16 /* semihosting call */ #define EXCP_NOCP 17 /* v7M NOCP UsageFault */ #define EXCP_INVSTATE 18 /* v7M INVSTATE UsageFault */ -/* NB: new EXCP_ defines should be added to the excnames[] array too */ +/* NB: add new EXCP_ defines to the array in arm_log_exception() too */ #define ARMV7M_EXCP_RESET 1 #define ARMV7M_EXCP_NMI 2 diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline bool excp_is_internal(int excp) || excp == EXCP_SEMIHOST; } -/* Exception names for debug logging; note that not all of these - * precisely correspond to architectural exceptions. - */ -static const char * const excnames[] = { - [EXCP_UDEF] = "Undefined Instruction", - [EXCP_SWI] = "SVC", - [EXCP_PREFETCH_ABORT] = "Prefetch Abort", - [EXCP_DATA_ABORT] = "Data Abort", - [EXCP_IRQ] = "IRQ", - [EXCP_FIQ] = "FIQ", - [EXCP_BKPT] = "Breakpoint", - [EXCP_EXCEPTION_EXIT] = "QEMU v7M exception exit", - [EXCP_KERNEL_TRAP] = "QEMU intercept of kernel commpage", - [EXCP_HVC] = "Hypervisor Call", - [EXCP_HYP_TRAP] = "Hypervisor Trap", - [EXCP_SMC] = "Secure Monitor Call", - [EXCP_VIRQ] = "Virtual IRQ", - [EXCP_VFIQ] = "Virtual FIQ", - [EXCP_SEMIHOST] = "Semihosting call", - [EXCP_NOCP] = "v7M NOCP UsageFault", - [EXCP_INVSTATE] = "v7M INVSTATE UsageFault", -}; - /* Scale factor for generic timers, ie number of ns per tick. * This gives a 62.5MHz timer. */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void arm_log_exception(int idx) { if (qemu_loglevel_mask(CPU_LOG_INT)) { const char *exc = NULL; + static const char * const excnames[] = { + [EXCP_UDEF] = "Undefined Instruction", + [EXCP_SWI] = "SVC", + [EXCP_PREFETCH_ABORT] = "Prefetch Abort", + [EXCP_DATA_ABORT] = "Data Abort", + [EXCP_IRQ] = "IRQ", + [EXCP_FIQ] = "FIQ", + [EXCP_BKPT] = "Breakpoint", + [EXCP_EXCEPTION_EXIT] = "QEMU v7M exception exit", + [EXCP_KERNEL_TRAP] = "QEMU intercept of kernel commpage", + [EXCP_HVC] = "Hypervisor Call", + [EXCP_HYP_TRAP] = "Hypervisor Trap", + [EXCP_SMC] = "Secure Monitor Call", + [EXCP_VIRQ] = "Virtual IRQ", + [EXCP_VFIQ] = "Virtual FIQ", + [EXCP_SEMIHOST] = "Semihosting call", + [EXCP_NOCP] = "v7M NOCP UsageFault", + [EXCP_INVSTATE] = "v7M INVSTATE UsageFault", + }; if (idx >= 0 && idx < ARRAY_SIZE(excnames)) { exc = excnames[idx]; -- 2.7.4 In tlb_fill() we construct a syndrome register value from a fault status register value which is filled in by arm_tlb_fill(). arm_tlb_fill() returns FSR values which might be in the format used with short-format page descriptors, or the format used with long-format (LPAE) descriptors. The syndrome register always uses LPAE-format FSR status codes. It isn't actually possible to end up delivering a syndrome register value to the guest for a fault which is reported with a short-format FSR (that kind of stage 1 fault will only happen for an AArch32 translation regime which doesn't have a syndrome register, and can never be redirected to an AArch64 or Hyp exception level). Add an assertion which checks this, and adjust the code so that we construct a syndrome with an invalid status code, rather than allowing set bits in the FSR input to randomly corrupt other fields in the syndrome. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 1491486152-24304-1-git-send-email-peter.maydell@linaro.org --- target/arm/op_helper.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ void tlb_fill(CPUState *cs, target_ulong addr, MMUAccessType access_type, if (unlikely(ret)) { ARMCPU *cpu = ARM_CPU(cs); CPUARMState *env = &cpu->env; - uint32_t syn, exc; + uint32_t syn, exc, fsc; unsigned int target_el; bool same_el; @@ -XXX,XX +XXX,XX @@ void tlb_fill(CPUState *cs, target_ulong addr, MMUAccessType access_type, env->cp15.hpfar_el2 = extract64(fi.s2addr, 12, 47) << 4; } same_el = arm_current_el(env) == target_el; - /* AArch64 syndrome does not have an LPAE bit */ - syn = fsr & ~(1 << 9); + + if (fsr & (1 << 9)) { + /* LPAE format fault status register : bottom 6 bits are + * status code in the same form as needed for syndrome + */ + fsc = extract32(fsr, 0, 6); + } else { + /* Short format FSR : this fault will never actually be reported + * to an EL that uses a syndrome register. Check that here, + * and use a (currently) reserved FSR code in case the constructed + * syndrome does leak into the guest somehow. + */ + assert(target_el != 2 && !arm_el_is_aa64(env, target_el)); + fsc = 0x3f; + } /* For insn and data aborts we assume there is no instruction syndrome * information; this is always true for exceptions reported to EL1. */ if (access_type == MMU_INST_FETCH) { - syn = syn_insn_abort(same_el, 0, fi.s1ptw, syn); + syn = syn_insn_abort(same_el, 0, fi.s1ptw, fsc); exc = EXCP_PREFETCH_ABORT; } else { syn = merge_syn_data_abort(env->exception.syndrome, target_el, same_el, fi.s1ptw, - access_type == MMU_DATA_STORE, syn); + access_type == MMU_DATA_STORE, fsc); if (access_type == MMU_DATA_STORE && arm_feature(env, ARM_FEATURE_V6)) { fsr |= (1 << 11); -- 2.7.4 Current recommended style is to log a guest error on bad register accesses, not kill the whole system with hw_error(). Change the hw_error() calls to log as LOG_GUEST_ERROR or LOG_UNIMP or use g_assert_not_reached() as appropriate. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1491486314-25823-1-git-send-email-peter.maydell@linaro.org --- hw/arm/stellaris.c | 60 +++++++++++++++++++++++++++++++++--------------------- 1 file changed, 37 insertions(+), 23 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void gptm_reload(gptm_state *s, int n, int reset) } else if (s->mode[n] == 0xa) { /* PWM mode. Not implemented. */ } else { - hw_error("TODO: 16-bit timer mode 0x%x\n", s->mode[n]); + qemu_log_mask(LOG_UNIMP, + "GPTM: 16-bit timer mode unimplemented: 0x%x\n", + s->mode[n]); + return; } s->tick[n] = tick; timer_mod(s->timer[n], tick); @@ -XXX,XX +XXX,XX @@ static void gptm_tick(void *opaque) } else if (s->mode[n] == 0xa) { /* PWM mode. Not implemented. */ } else { - hw_error("TODO: 16-bit timer mode 0x%x\n", s->mode[n]); + qemu_log_mask(LOG_UNIMP, + "GPTM: 16-bit timer mode unimplemented: 0x%x\n", + s->mode[n]); } gptm_update_irq(s); } @@ -XXX,XX +XXX,XX @@ static void gptm_write(void *opaque, hwaddr offset, s->match_prescale[0] = value; break; default: - hw_error("gptm_write: Bad offset 0x%x\n", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, + "GPTM: read at bad offset 0x%x\n", (int)offset); } gptm_update_irq(s); } @@ -XXX,XX +XXX,XX @@ static int ssys_board_class(const ssys_state *s) } /* for unknown classes, fall through */ default: - hw_error("ssys_board_class: Unknown class 0x%08x\n", did0); + /* This can only happen if the hardwired constant did0 value + * in this board's stellaris_board_info struct is wrong. + */ + g_assert_not_reached(); } } @@ -XXX,XX +XXX,XX @@ static uint64_t ssys_read(void *opaque, hwaddr offset, case DID0_CLASS_SANDSTORM: return pllcfg_sandstorm[xtal]; default: - hw_error("ssys_read: Unhandled class for PLLCFG read.\n"); - return 0; + g_assert_not_reached(); } } case 0x070: /* RCC2 */ @@ -XXX,XX +XXX,XX @@ static uint64_t ssys_read(void *opaque, hwaddr offset, case 0x1e4: /* USER1 */ return s->user1; default: - hw_error("ssys_read: Bad offset 0x%x\n", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, + "SSYS: read at bad offset 0x%x\n", (int)offset); return 0; } } @@ -XXX,XX +XXX,XX @@ static void ssys_write(void *opaque, hwaddr offset, s->ldoarst = value; break; default: - hw_error("ssys_write: Bad offset 0x%x\n", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, + "SSYS: write at bad offset 0x%x\n", (int)offset); } ssys_update(s); } @@ -XXX,XX +XXX,XX @@ static uint64_t stellaris_i2c_read(void *opaque, hwaddr offset, case 0x20: /* MCR */ return s->mcr; default: - hw_error("strllaris_i2c_read: Bad offset 0x%x\n", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, + "stellaris_i2c: read at bad offset 0x%x\n", (int)offset); return 0; } } @@ -XXX,XX +XXX,XX @@ static void stellaris_i2c_write(void *opaque, hwaddr offset, s->mris &= ~value; break; case 0x20: /* MCR */ - if (value & 1) - hw_error( - "stellaris_i2c_write: Loopback not implemented\n"); - if (value & 0x20) - hw_error( - "stellaris_i2c_write: Slave mode not implemented\n"); + if (value & 1) { + qemu_log_mask(LOG_UNIMP, "stellaris_i2c: Loopback not implemented"); + } + if (value & 0x20) { + qemu_log_mask(LOG_UNIMP, + "stellaris_i2c: Slave mode not implemented"); + } s->mcr = value & 0x31; break; default: - hw_error("stellaris_i2c_write: Bad offset 0x%x\n", - (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, + "stellaris_i2c: write at bad offset 0x%x\n", (int)offset); } stellaris_i2c_update(s); } @@ -XXX,XX +XXX,XX @@ static uint64_t stellaris_adc_read(void *opaque, hwaddr offset, case 0x30: /* SAC */ return s->sac; default: - hw_error("strllaris_adc_read: Bad offset 0x%x\n", - (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, + "stellaris_adc: read at bad offset 0x%x\n", (int)offset); return 0; } } @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_write(void *opaque, hwaddr offset, return; case 0x04: /* SSCTL */ if (value != 6) { - hw_error("ADC: Unimplemented sequence %" PRIx64 "\n", - value); + qemu_log_mask(LOG_UNIMP, + "ADC: Unimplemented sequence %" PRIx64 "\n", + value); } s->ssctl[n] = value; return; @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_write(void *opaque, hwaddr offset, s->sspri = value; break; case 0x28: /* PSSI */ - hw_error("Not implemented: ADC sample initiate\n"); + qemu_log_mask(LOG_UNIMP, "ADC: sample initiate unimplemented"); break; case 0x30: /* SAC */ s->sac = value; break; default: - hw_error("stellaris_adc_write: Bad offset 0x%x\n", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, + "stellaris_adc: write at bad offset 0x%x\n", (int)offset); } stellaris_adc_update(s); } -- 2.7.4 From: Ishani Chugh <chugh.ishani@research.iiit.ac.in> Signed-off-by: Ishani Chugh <chugh.ishani@research.iiit.ac.in> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 1491629987-6826-1-git-send-email-chugh.ishani@research.iiit.ac.in Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ bool kvm_arm_handle_debug(CPUState *cs, struct kvm_debug_exit_arch *debug_exit) * single step at this point so something has gone wrong. */ error_report("%s: guest single-step while debugging unsupported" - " (%"PRIx64", %"PRIx32")\n", + " (%"PRIx64", %"PRIx32")", __func__, env->pc, debug_exit->hsr); return false; } @@ -XXX,XX +XXX,XX @@ bool kvm_arm_handle_debug(CPUState *cs, struct kvm_debug_exit_arch *debug_exit) break; } default: - error_report("%s: unhandled debug exit (%"PRIx32", %"PRIx64")\n", + error_report("%s: unhandled debug exit (%"PRIx32", %"PRIx64")", __func__, debug_exit->hsr, env->pc); } -- 2.7.4 From: Suramya Shah <shah.suramya@gmail.com> Signed-off-by: Suramya Shah <shah.suramya@gmail.com> Message-id: 20170415180316.2694-1-shah.suramya@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/pxa2xx.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -XXX,XX +XXX,XX @@ static void pxa2xx_ssp_reset(DeviceState *d) s->rx_start = s->rx_level = 0; } -static int pxa2xx_ssp_init(SysBusDevice *sbd) +static void pxa2xx_ssp_init(Object *obj) { - DeviceState *dev = DEVICE(sbd); - PXA2xxSSPState *s = PXA2XX_SSP(dev); - + DeviceState *dev = DEVICE(obj); + PXA2xxSSPState *s = PXA2XX_SSP(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); sysbus_init_irq(sbd, &s->irq); - memory_region_init_io(&s->iomem, OBJECT(s), &pxa2xx_ssp_ops, s, + memory_region_init_io(&s->iomem, obj, &pxa2xx_ssp_ops, s, "pxa2xx-ssp", 0x1000); sysbus_init_mmio(sbd, &s->iomem); s->bus = ssi_create_bus(dev, "ssi"); - return 0; } /* Real-Time Clock */ @@ -XXX,XX +XXX,XX @@ PXA2xxState *pxa255_init(MemoryRegion *address_space, unsigned int sdram_size) static void pxa2xx_ssp_class_init(ObjectClass *klass, void *data) { - SysBusDeviceClass *sdc = SYS_BUS_DEVICE_CLASS(klass); DeviceClass *dc = DEVICE_CLASS(klass); - sdc->init = pxa2xx_ssp_init; dc->reset = pxa2xx_ssp_reset; dc->vmsd = &vmstate_pxa2xx_ssp; } @@ -XXX,XX +XXX,XX @@ static const TypeInfo pxa2xx_ssp_info = { .name = TYPE_PXA2XX_SSP, .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(PXA2xxSSPState), + .instance_init = pxa2xx_ssp_init, .class_init = pxa2xx_ssp_class_init, }; -- 2.7.4 From: Alistair Francis <alistair.francis@xilinx.com> Read the correct descriptor instead of hardcoding the first (q=0). Signed-off-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 988b183dcf951856d8b3379f7e911ec95233bbf4.1491947224.git.alistair.francis@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static void gem_get_rx_desc(CadenceGEMState *s, int q) { DB_PRINT("read descriptor 0x%x\n", (unsigned)s->rx_desc_addr[q]); /* read current descriptor */ - cpu_physical_memory_read(s->rx_desc_addr[0], - (uint8_t *)s->rx_desc[0], sizeof(s->rx_desc[0])); + cpu_physical_memory_read(s->rx_desc_addr[q], + (uint8_t *)s->rx_desc[q], sizeof(s->rx_desc[q])); /* Descriptor owned by software ? */ if (rx_desc_get_ownership(s->rx_desc[q]) == 1) { -- 2.7.4 From: Alistair Francis <alistair.francis@xilinx.com> Correct the buffer descriptor busy logic to work correctly when using multiple queues. Signed-off-by: Alistair Francis <alistair.francis@xilinx.com> Message-id: 8a7e8059984e27d46a276a66299d035a0afd280f.1491947224.git.alistair.francis@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static int gem_can_receive(NetClientState *nc) } for (i = 0; i < s->num_priority_queues; i++) { - if (rx_desc_get_ownership(s->rx_desc[i]) == 1) { - if (s->can_rx_state != 2) { - s->can_rx_state = 2; - DB_PRINT("can't receive - busy buffer descriptor (q%d) 0x%x\n", - i, s->rx_desc_addr[i]); - } - return 0; + if (rx_desc_get_ownership(s->rx_desc[i]) != 1) { + break; + } + }; + + if (i == s->num_priority_queues) { + if (s->can_rx_state != 2) { + s->can_rx_state = 2; + DB_PRINT("can't receive - all the buffer descriptors are busy\n"); } + return 0; } if (s->can_rx_state != 0) { -- 2.7.4 From: Alistair Francis <alistair.francis@xilinx.com> This patch fixes two mistakes in the interrupt logic. First we only trigger single-queue or multi-queue interrupts if the status register is set. This logic was already used for non multi-queue interrupts but it also applies to multi-queue interrupts. Secondly we need to lower the interrupts if the ISR isn't set. As part of this we can remove the other interrupt lowering logic and consolidate it inside gem_update_int_status(). Signed-off-by: Alistair Francis <alistair.francis@xilinx.com> Message-id: 438bcc014f8f8a2f8f68f322cb6a53f4c04688c2.1491947224.git.alistair.francis@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static void gem_update_int_status(CadenceGEMState *s) { int i; - if ((s->num_priority_queues == 1) && s->regs[GEM_ISR]) { + if (!s->regs[GEM_ISR]) { + /* ISR isn't set, clear all the interrupts */ + for (i = 0; i < s->num_priority_queues; ++i) { + qemu_set_irq(s->irq[i], 0); + } + return; + } + + /* If we get here we know s->regs[GEM_ISR] is set, so we don't need to + * check it again. + */ + if (s->num_priority_queues == 1) { /* No priority queues, just trigger the interrupt */ DB_PRINT("asserting int.\n"); qemu_set_irq(s->irq[0], 1); @@ -XXX,XX +XXX,XX @@ static uint64_t gem_read(void *opaque, hwaddr offset, unsigned size) { CadenceGEMState *s; uint32_t retval; - int i; s = (CadenceGEMState *)opaque; offset >>= 2; @@ -XXX,XX +XXX,XX @@ static uint64_t gem_read(void *opaque, hwaddr offset, unsigned size) switch (offset) { case GEM_ISR: DB_PRINT("lowering irqs on ISR read\n"); - for (i = 0; i < s->num_priority_queues; ++i) { - qemu_set_irq(s->irq[i], 0); - } + /* The interrupts get updated at the end of the function. */ break; case GEM_PHYMNTNC: if (retval & GEM_PHYMNTNC_OP_R) { -- 2.7.4 From: Alistair Francis <alistair.francis@xilinx.com> Expose the Cadence GEM revision as a property. Signed-off-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 541324373cf87b50f8be0439a0cb89f5028b016f.1491947224.git.alistair.francis@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/net/cadence_gem.h | 1 + hw/net/cadence_gem.c | 6 +++++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/include/hw/net/cadence_gem.h b/include/hw/net/cadence_gem.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/net/cadence_gem.h +++ b/include/hw/net/cadence_gem.h @@ -XXX,XX +XXX,XX @@ typedef struct CadenceGEMState { uint8_t num_priority_queues; uint8_t num_type1_screeners; uint8_t num_type2_screeners; + uint32_t revision; /* GEM registers backing store */ uint32_t regs[CADENCE_GEM_MAXREG]; diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ #define DESC_1_RX_SOF 0x00004000 #define DESC_1_RX_EOF 0x00008000 +#define GEM_MODID_VALUE 0x00020118 + static inline unsigned tx_desc_get_buffer(unsigned *desc) { return desc[0]; @@ -XXX,XX +XXX,XX @@ static void gem_reset(DeviceState *d) s->regs[GEM_TXPAUSE] = 0x0000ffff; s->regs[GEM_TXPARTIALSF] = 0x000003ff; s->regs[GEM_RXPARTIALSF] = 0x000003ff; - s->regs[GEM_MODID] = 0x00020118; + s->regs[GEM_MODID] = s->revision; s->regs[GEM_DESCONF] = 0x02500111; s->regs[GEM_DESCONF2] = 0x2ab13fff; s->regs[GEM_DESCONF5] = 0x002f2145; @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_cadence_gem = { static Property gem_properties[] = { DEFINE_NIC_PROPERTIES(CadenceGEMState, conf), + DEFINE_PROP_UINT32("revision", CadenceGEMState, revision, + GEM_MODID_VALUE), DEFINE_PROP_UINT8("num-priority-queues", CadenceGEMState, num_priority_queues, 1), DEFINE_PROP_UINT8("num-type1-screeners", CadenceGEMState, -- 2.7.4 From: Alistair Francis <alistair.francis@xilinx.com> Signed-off-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 026dbe01a1d42619eee30ce3f2079741bf04bc73.1491947224.git.alistair.francis@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-zynqmp.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) 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 @@ #define ARM_PHYS_TIMER_PPI 30 #define ARM_VIRT_TIMER_PPI 27 +#define GEM_REVISION 0x40070106 + #define GIC_BASE_ADDR 0xf9000000 #define GIC_DIST_ADDR 0xf9010000 #define GIC_CPU_ADDR 0xf9020000 @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp) qemu_check_nic_model(nd, TYPE_CADENCE_GEM); qdev_set_nic_properties(DEVICE(&s->gem[i]), nd); } + object_property_set_int(OBJECT(&s->gem[i]), GEM_REVISION, "revision", + &error_abort); object_property_set_int(OBJECT(&s->gem[i]), 2, "num-priority-queues", - &error_abort); + &error_abort); object_property_set_bool(OBJECT(&s->gem[i]), true, "realized", &err); if (err) { error_propagate(errp, err); -- 2.7.4 For M-profile CPUs, the BXJ instruction does not exist at all, and the encoding should always UNDEF. We were accidentally implementing it to behave like A-profile BXJ; correct the error. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <rth@twiddle.net> Message-id: 1491844419-12485-2-git-send-email-peter.maydell@linaro.org --- target/arm/translate.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) 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 int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw } break; case 4: /* bxj */ - /* Trivial implementation equivalent to bx. */ + /* Trivial implementation equivalent to bx. + * This instruction doesn't exist at all for M-profile. + */ + if (arm_dc_feature(s, ARM_FEATURE_M)) { + goto illegal_op; + } tmp = load_reg(s, rn); gen_bx(s, tmp); break; -- 2.7.4 In Thumb mode, the only instructions which can cause an interworking branch by writing the PC are BLX, BX, BXJ, LDR, POP and LDM. Unlike ARM mode, data processing instructions which target the PC do not cause interworking branches. When we added support for doing interworking branches on writes to PC from data processing instructions in commit 21aeb3430ce7ba, we accidentally changed a Thumb instruction to have interworking branch behaviour for writes to PC. (MOV, MOVS register-shifted register, encoding T2; this is the standard encoding for LSL/LSR/ASR/ROR (register).) For this encoding, behaviour with Rd == R15 is specified as UNPREDICTABLE, so allowing an interworking branch is within spec, but it's confusing and differs from our handling of this class of UNPREDICTABLE for other Thumb ALU operations. Make it perform a simple (non-interworking) branch like the others. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <rth@twiddle.net> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1491844419-12485-3-git-send-email-peter.maydell@linaro.org --- target/arm/translate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw gen_arm_shift_reg(tmp, op, tmp2, logic_cc); if (logic_cc) gen_logic_CC(tmp); - store_reg_bx(s, rd, tmp); + store_reg(s, rd, tmp); break; case 1: /* Sign/zero extend. */ op = (insn >> 20) & 7; -- 2.7.4 We currently have two places that do: if (dc->ss_active) { gen_step_complete_exception(dc); } else { gen_exception_internal(EXCP_DEBUG); } Factor this out into its own function, as we're about to add a third place that needs the same logic. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <rth@twiddle.net> Message-id: 1491844419-12485-4-git-send-email-peter.maydell@linaro.org --- target/arm/translate.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_step_complete_exception(DisasContext *s) s->is_jmp = DISAS_EXC; } +static void gen_singlestep_exception(DisasContext *s) +{ + /* Generate the right kind of exception for singlestep, which is + * either the architectural singlestep or EXCP_DEBUG for QEMU's + * gdb singlestepping. + */ + if (s->ss_active) { + gen_step_complete_exception(s); + } else { + gen_exception_internal(EXCP_DEBUG); + } +} + static void gen_smul_dual(TCGv_i32 a, TCGv_i32 b) { TCGv_i32 tmp1 = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb) gen_set_pc_im(dc, dc->pc); /* fall through */ default: - if (dc->ss_active) { - gen_step_complete_exception(dc); - } else { - /* FIXME: Single stepping a WFI insn will not halt - the CPU. */ - gen_exception_internal(EXCP_DEBUG); - } + /* FIXME: Single stepping a WFI insn will not halt the CPU. */ + gen_singlestep_exception(dc); } if (dc->condjmp) { /* "Condition failed" instruction codepath. */ gen_set_label(dc->condlabel); gen_set_condexec(dc); gen_set_pc_im(dc, dc->pc); - if (dc->ss_active) { - gen_step_complete_exception(dc); - } else { - gen_exception_internal(EXCP_DEBUG); - } + gen_singlestep_exception(dc); } } else { /* While branches must always occur at the end of an IT block, -- 2.7.4 Move the utility routines gen_set_condexec() and gen_set_pc_im() up in the file, as we will want to use them from a function placed earlier in the file than their current location. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <rth@twiddle.net> Message-id: 1491844419-12485-5-git-send-email-peter.maydell@linaro.org --- target/arm/translate.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 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 const uint8_t table_logic_cc[16] = { 1, /* mvn */ }; +static inline void gen_set_condexec(DisasContext *s) +{ + if (s->condexec_mask) { + uint32_t val = (s->condexec_cond << 4) | (s->condexec_mask >> 1); + TCGv_i32 tmp = tcg_temp_new_i32(); + tcg_gen_movi_i32(tmp, val); + store_cpu_field(tmp, condexec_bits); + } +} + +static inline void gen_set_pc_im(DisasContext *s, target_ulong val) +{ + tcg_gen_movi_i32(cpu_R[15], val); +} + /* Set PC and Thumb state from an immediate address. */ static inline void gen_bx_im(DisasContext *s, uint32_t addr) { @@ -XXX,XX +XXX,XX @@ DO_GEN_ST(8, MO_UB) DO_GEN_ST(16, MO_UW) DO_GEN_ST(32, MO_UL) -static inline void gen_set_pc_im(DisasContext *s, target_ulong val) -{ - tcg_gen_movi_i32(cpu_R[15], val); -} - static inline void gen_hvc(DisasContext *s, int imm16) { /* The pre HVC helper handles cases when HVC gets trapped @@ -XXX,XX +XXX,XX @@ static inline void gen_smc(DisasContext *s) s->is_jmp = DISAS_SMC; } -static inline void -gen_set_condexec (DisasContext *s) -{ - if (s->condexec_mask) { - uint32_t val = (s->condexec_cond << 4) | (s->condexec_mask >> 1); - TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp, val); - store_cpu_field(tmp, condexec_bits); - } -} - static void gen_exception_internal_insn(DisasContext *s, int offset, int excp) { gen_set_condexec(s); -- 2.7.4 Move the code to generate the "condition failed" instruction codepath out of the if (singlestepping) {} else {}. This will allow adding support for handling a new is_jmp type which can't be neatly split into "singlestepping case" versus "not singlestepping case". Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <rth@twiddle.net> Message-id: 1491844419-12485-6-git-send-email-peter.maydell@linaro.org --- target/arm/translate.c | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 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 @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb) /* At this stage dc->condjmp will only be set when the skipped instruction was a conditional branch or trap, and the PC has already been written. */ + gen_set_condexec(dc); if (unlikely(cs->singlestep_enabled || dc->ss_active)) { /* Unconditional and "condition passed" instruction codepath. */ - gen_set_condexec(dc); switch (dc->is_jmp) { case DISAS_SWI: gen_ss_advance(dc); @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb) /* FIXME: Single stepping a WFI insn will not halt the CPU. */ gen_singlestep_exception(dc); } - if (dc->condjmp) { - /* "Condition failed" instruction codepath. */ - gen_set_label(dc->condlabel); - gen_set_condexec(dc); - gen_set_pc_im(dc, dc->pc); - gen_singlestep_exception(dc); - } } else { /* While branches must always occur at the end of an IT block, there are a few other things that can cause us to terminate @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb) - Hardware watchpoints. Hardware breakpoints have already been handled and skip this code. */ - gen_set_condexec(dc); switch(dc->is_jmp) { case DISAS_NEXT: gen_goto_tb(dc, 1, dc->pc); @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb) gen_exception(EXCP_SMC, syn_aa32_smc(), 3); break; } - if (dc->condjmp) { - gen_set_label(dc->condlabel); - gen_set_condexec(dc); + } + + if (dc->condjmp) { + /* "Condition failed" instruction codepath for the branch/trap insn */ + gen_set_label(dc->condlabel); + gen_set_condexec(dc); + if (unlikely(cs->singlestep_enabled || dc->ss_active)) { + gen_set_pc_im(dc, dc->pc); + gen_singlestep_exception(dc); + } else { gen_goto_tb(dc, 1, dc->pc); - dc->condjmp = 0; } } -- 2.7.4 We now test for "are we singlestepping" in several places and it's not a trivial check because we need to care about both architectural singlestep and QEMU gdbstub singlestep. We're also about to add another place that needs to make this check, so pull the condition out into a function. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <rth@twiddle.net> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1491844419-12485-7-git-send-email-peter.maydell@linaro.org --- target/arm/translate.c | 20 +++++++++++++++----- 1 file changed, 15 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 void gen_singlestep_exception(DisasContext *s) } } +static inline bool is_singlestepping(DisasContext *s) +{ + /* Return true if we are singlestepping either because of + * architectural singlestep or QEMU gdbstub singlestep. This does + * not include the command line '-singlestep' mode which is rather + * misnamed as it only means "one instruction per TB" and doesn't + * affect the code we generate. + */ + return s->singlestep_enabled || s->ss_active; +} + static void gen_smul_dual(TCGv_i32 a, TCGv_i32 b) { TCGv_i32 tmp1 = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static inline void gen_goto_tb(DisasContext *s, int n, target_ulong dest) static inline void gen_jmp (DisasContext *s, uint32_t dest) { - if (unlikely(s->singlestep_enabled || s->ss_active)) { + if (unlikely(is_singlestepping(s))) { /* An indirect jump so that we still trigger the debug exception. */ if (s->thumb) dest |= 1; @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb) ((dc->pc >= next_page_start - 3) && insn_crosses_page(env, dc)); } while (!dc->is_jmp && !tcg_op_buf_full() && - !cs->singlestep_enabled && + !is_singlestepping(dc) && !singlestep && - !dc->ss_active && !end_of_page && num_insns < max_insns); @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb) instruction was a conditional branch or trap, and the PC has already been written. */ gen_set_condexec(dc); - if (unlikely(cs->singlestep_enabled || dc->ss_active)) { + if (unlikely(is_singlestepping(dc))) { /* Unconditional and "condition passed" instruction codepath. */ switch (dc->is_jmp) { case DISAS_SWI: @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb) /* "Condition failed" instruction codepath for the branch/trap insn */ gen_set_label(dc->condlabel); gen_set_condexec(dc); - if (unlikely(cs->singlestep_enabled || dc->ss_active)) { + if (unlikely(is_singlestepping(dc))) { gen_set_pc_im(dc, dc->pc); gen_singlestep_exception(dc); } else { -- 2.7.4 For M profile exception-return handling we'd like to generate different code for some instructions depending on whether we are in Handler mode or Thread mode. This isn't the same as "are we privileged or user", so we need an extra bit in the TB flags to distinguish. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <rth@twiddle.net> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1491844419-12485-8-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.h | 9 +++++++++ target/arm/translate.h | 1 + target/arm/translate.c | 1 + 3 files changed, 11 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 @@ static inline bool arm_cpu_data_is_big_endian(CPUARMState *env) #define ARM_TBFLAG_NS_MASK (1 << ARM_TBFLAG_NS_SHIFT) #define ARM_TBFLAG_BE_DATA_SHIFT 20 #define ARM_TBFLAG_BE_DATA_MASK (1 << ARM_TBFLAG_BE_DATA_SHIFT) +/* For M profile only, Handler (ie not Thread) mode */ +#define ARM_TBFLAG_HANDLER_SHIFT 21 +#define ARM_TBFLAG_HANDLER_MASK (1 << ARM_TBFLAG_HANDLER_SHIFT) /* Bit usage when in AArch64 state */ #define ARM_TBFLAG_TBI0_SHIFT 0 /* TBI0 for EL0/1 or TBI for EL2/3 */ @@ -XXX,XX +XXX,XX @@ static inline bool arm_cpu_data_is_big_endian(CPUARMState *env) (((F) & ARM_TBFLAG_NS_MASK) >> ARM_TBFLAG_NS_SHIFT) #define ARM_TBFLAG_BE_DATA(F) \ (((F) & ARM_TBFLAG_BE_DATA_MASK) >> ARM_TBFLAG_BE_DATA_SHIFT) +#define ARM_TBFLAG_HANDLER(F) \ + (((F) & ARM_TBFLAG_HANDLER_MASK) >> ARM_TBFLAG_HANDLER_SHIFT) #define ARM_TBFLAG_TBI0(F) \ (((F) & ARM_TBFLAG_TBI0_MASK) >> ARM_TBFLAG_TBI0_SHIFT) #define ARM_TBFLAG_TBI1(F) \ @@ -XXX,XX +XXX,XX @@ static inline void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, } *flags |= fp_exception_el(env) << ARM_TBFLAG_FPEXC_EL_SHIFT; + if (env->v7m.exception != 0) { + *flags |= ARM_TBFLAG_HANDLER_MASK; + } + *cs_base = 0; } diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { bool vfp_enabled; /* FP enabled via FPSCR.EN */ int vec_len; int vec_stride; + bool v7m_handler_mode; /* Immediate value in AArch32 SVC insn; must be set if is_jmp == DISAS_SWI * so that top level loop can generate correct syndrome information. */ 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 gen_intermediate_code(CPUARMState *env, TranslationBlock *tb) dc->vec_len = ARM_TBFLAG_VECLEN(tb->flags); dc->vec_stride = ARM_TBFLAG_VECSTRIDE(tb->flags); dc->c15_cpar = ARM_TBFLAG_XSCALE_CPAR(tb->flags); + dc->v7m_handler_mode = ARM_TBFLAG_HANDLER(tb->flags); dc->cp_regs = cpu->cp_regs; dc->features = env->features; -- 2.7.4 On M profile, return from exceptions happen when code in Handler mode executes one of the following function call return instructions: * POP or LDM which loads the PC * LDR to PC * BX register and the new PC value is 0xFFxxxxxx. QEMU tries to implement this by not treating the instruction specially but then catching the attempt to execute from the magic address value. This is not ideal, because: * there are guest visible differences from the architecturally specified behaviour (for instance jumping to 0xFFxxxxxx via a different instruction should not cause an exception return but it will in the QEMU implementation) * we have to account for it in various places (like refusing to take an interrupt if the PC is at a magic value, and making sure that the MPU doesn't deny execution at the magic value addresses) Drop these hacks, and instead implement exception return the way the architecture specifies -- by having the relevant instructions check for the magic value and raise the 'do an exception return' QEMU internal exception immediately. The effect on the generated code is minor: bx lr, old code (and new code for Thread mode): TCG: mov_i32 tmp5,r14 movi_i32 tmp6,$0xfffffffffffffffe and_i32 pc,tmp5,tmp6 movi_i32 tmp6,$0x1 and_i32 tmp5,tmp5,tmp6 st_i32 tmp5,env,$0x218 exit_tb $0x0 set_label $L0 exit_tb $0x7f2aabd61993 x86_64 generated code: 0x7f2aabe87019: mov %ebx,%ebp 0x7f2aabe8701b: and $0xfffffffffffffffe,%ebp 0x7f2aabe8701e: mov %ebp,0x3c(%r14) 0x7f2aabe87022: and $0x1,%ebx 0x7f2aabe87025: mov %ebx,0x218(%r14) 0x7f2aabe8702c: xor %eax,%eax 0x7f2aabe8702e: jmpq 0x7f2aabe7c016 bx lr, new code when in Handler mode: TCG: mov_i32 tmp5,r14 movi_i32 tmp6,$0xfffffffffffffffe and_i32 pc,tmp5,tmp6 movi_i32 tmp6,$0x1 and_i32 tmp5,tmp5,tmp6 st_i32 tmp5,env,$0x218 movi_i32 tmp5,$0xffffffffff000000 brcond_i32 pc,tmp5,geu,$L1 exit_tb $0x0 set_label $L1 movi_i32 tmp5,$0x8 call exception_internal,$0x0,$0,env,tmp5 x86_64 generated code: 0x7fe8fa1264e3: mov %ebp,%ebx 0x7fe8fa1264e5: and $0xfffffffffffffffe,%ebx 0x7fe8fa1264e8: mov %ebx,0x3c(%r14) 0x7fe8fa1264ec: and $0x1,%ebp 0x7fe8fa1264ef: mov %ebp,0x218(%r14) 0x7fe8fa1264f6: cmp $0xff000000,%ebx 0x7fe8fa1264fc: jae 0x7fe8fa126509 0x7fe8fa126502: xor %eax,%eax 0x7fe8fa126504: jmpq 0x7fe8fa122016 0x7fe8fa126509: mov %r14,%rdi 0x7fe8fa12650c: mov $0x8,%esi 0x7fe8fa126511: mov $0x56095dbeccf5,%r10 0x7fe8fa12651b: callq *%r10 which is a difference of one cmp/branch-not-taken. This will be lost in the noise of having to exit generated code and look up the next TB anyway. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <rth@twiddle.net> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1491844419-12485-9-git-send-email-peter.maydell@linaro.org --- target/arm/translate.h | 4 +++ target/arm/translate.c | 66 +++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 64 insertions(+), 6 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static void disas_set_insn_syndrome(DisasContext *s, uint32_t syn) #define DISAS_HVC 8 #define DISAS_SMC 9 #define DISAS_YIELD 10 +/* M profile branch which might be an exception return (and so needs + * custom end-of-TB code) + */ +#define DISAS_BX_EXCRET 11 #ifdef TARGET_AARCH64 void a64_translate_init(void); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void gen_bx(DisasContext *s, TCGv_i32 var) store_cpu_field(var, thumb); } +/* Set PC and Thumb state from var. var is marked as dead. + * For M-profile CPUs, include logic to detect exception-return + * branches and handle them. This is needed for Thumb POP/LDM to PC, LDR to PC, + * and BX reg, and no others, and happens only for code in Handler mode. + */ +static inline void gen_bx_excret(DisasContext *s, TCGv_i32 var) +{ + /* Generate the same code here as for a simple bx, but flag via + * s->is_jmp that we need to do the rest of the work later. + */ + gen_bx(s, var); + if (s->v7m_handler_mode && arm_dc_feature(s, ARM_FEATURE_M)) { + s->is_jmp = DISAS_BX_EXCRET; + } +} + +static inline void gen_bx_excret_final_code(DisasContext *s) +{ + /* Generate the code to finish possible exception return and end the TB */ + TCGLabel *excret_label = gen_new_label(); + + /* Is the new PC value in the magic range indicating exception return? */ + tcg_gen_brcondi_i32(TCG_COND_GEU, cpu_R[15], 0xff000000, excret_label); + /* No: end the TB as we would for a DISAS_JMP */ + if (is_singlestepping(s)) { + gen_singlestep_exception(s); + } else { + tcg_gen_exit_tb(0); + } + gen_set_label(excret_label); + /* Yes: this is an exception return. + * At this point in runtime env->regs[15] and env->thumb will hold + * the exception-return magic number, which do_v7m_exception_exit() + * will read. Nothing else will be able to see those values because + * the cpu-exec main loop guarantees that we will always go straight + * from raising the exception to the exception-handling code. + * + * gen_ss_advance(s) does nothing on M profile currently but + * calling it is conceptually the right thing as we have executed + * this instruction (compare SWI, HVC, SMC handling). + */ + gen_ss_advance(s); + gen_exception_internal(EXCP_EXCEPTION_EXIT); +} + /* Variant of store_reg which uses branch&exchange logic when storing to r15 in ARM architecture v7 and above. The source must be a temporary and will be marked as dead. */ @@ -XXX,XX +XXX,XX @@ static inline void store_reg_bx(DisasContext *s, int reg, TCGv_i32 var) static inline void store_reg_from_load(DisasContext *s, int reg, TCGv_i32 var) { if (reg == 15 && ENABLE_ARCH_5) { - gen_bx(s, var); + gen_bx_excret(s, var); } else { store_reg(s, reg, var); } @@ -XXX,XX +XXX,XX @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw tmp = tcg_temp_new_i32(); gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); if (i == 15) { - gen_bx(s, tmp); + gen_bx_excret(s, tmp); } else if (i == rn) { loaded_var = tmp; loaded_base = 1; @@ -XXX,XX +XXX,XX @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw goto illegal_op; } if (rs == 15) { - gen_bx(s, tmp); + gen_bx_excret(s, tmp); } else { store_reg(s, rs, tmp); } @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s) tmp2 = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp2, val); store_reg(s, 14, tmp2); + gen_bx(s, tmp); + } else { + /* Only BX works as exception-return, not BLX */ + gen_bx_excret(s, tmp); } - /* already thumb, no need to check */ - gen_bx(s, tmp); break; } break; @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb) instruction was a conditional branch or trap, and the PC has already been written. */ gen_set_condexec(dc); - if (unlikely(is_singlestepping(dc))) { + if (dc->is_jmp == DISAS_BX_EXCRET) { + /* Exception return branches need some special case code at the + * end of the TB, which is complex enough that it has to + * handle the single-step vs not and the condition-failed + * insn codepath itself. + */ + gen_bx_excret_final_code(dc); + } else if (unlikely(is_singlestepping(dc))) { /* Unconditional and "condition passed" instruction codepath. */ switch (dc->is_jmp) { case DISAS_SWI: -- 2.7.4 Now that we've rewritten M-profile exception return so that the magic PC values are not visible to other parts of QEMU, we can delete the special casing of them elsewhere. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <rth@twiddle.net> Message-id: 1491844419-12485-10-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.c | 43 ++----------------------------------------- target/arm/translate.c | 8 -------- 2 files changed, 2 insertions(+), 49 deletions(-) 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 @@ bool arm_cpu_exec_interrupt(CPUState *cs, int interrupt_request) } #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64) -static void arm_v7m_unassigned_access(CPUState *cpu, hwaddr addr, - bool is_write, bool is_exec, int opaque, - unsigned size) -{ - ARMCPU *arm = ARM_CPU(cpu); - CPUARMState *env = &arm->env; - - /* ARMv7-M interrupt return works by loading a magic value into the PC. - * On real hardware the load causes the return to occur. The qemu - * implementation performs the jump normally, then does the exception - * return by throwing a special exception when when the CPU tries to - * execute code at the magic address. - */ - if (env->v7m.exception != 0 && addr >= 0xfffffff0 && is_exec) { - cpu->exception_index = EXCP_EXCEPTION_EXIT; - cpu_loop_exit(cpu); - } - - /* In real hardware an attempt to access parts of the address space - * with nothing there will usually cause an external abort. - * However our QEMU board models are often missing device models where - * the guest can boot anyway with the default read-as-zero/writes-ignored - * behaviour that you get without a QEMU unassigned_access hook. - * So just return here to retain that default behaviour. - */ -} - static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { CPUClass *cc = CPU_GET_CLASS(cs); @@ -XXX,XX +XXX,XX @@ static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request) CPUARMState *env = &cpu->env; bool ret = false; - /* ARMv7-M interrupt return works by loading a magic value - * into the PC. On real hardware the load causes the - * return to occur. The qemu implementation performs the - * jump normally, then does the exception return when the - * CPU tries to execute code at the magic address. - * This will cause the magic PC value to be pushed to - * the stack if an interrupt occurred at the wrong time. - * We avoid this by disabling interrupts when - * pc contains a magic address. - * - * ARMv7-M interrupt masking works differently than -A or -R. + /* ARMv7-M interrupt masking works differently than -A or -R. * There is no FIQ/IRQ distinction. Instead of I and F bits * masking FIQ and IRQ interrupts, an exception is taken only * if it is higher priority than the current execution priority @@ -XXX,XX +XXX,XX @@ static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request) * currently active exception). */ if (interrupt_request & CPU_INTERRUPT_HARD - && (armv7m_nvic_can_take_pending_exception(env->nvic)) - && (env->regs[15] < 0xfffffff0)) { + && (armv7m_nvic_can_take_pending_exception(env->nvic))) { cs->exception_index = EXCP_IRQ; cc->do_interrupt(cs); ret = true; @@ -XXX,XX +XXX,XX @@ static void arm_v7m_class_init(ObjectClass *oc, void *data) cc->do_interrupt = arm_v7m_cpu_do_interrupt; #endif - cc->do_unassigned_access = arm_v7m_unassigned_access; cc->cpu_exec_interrupt = arm_v7m_cpu_exec_interrupt; } 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 gen_intermediate_code(CPUARMState *env, TranslationBlock *tb) dc->is_jmp = DISAS_EXC; break; } -#else - if (arm_dc_feature(dc, ARM_FEATURE_M)) { - /* Branches to the magic exception-return addresses should - * already have been caught via the arm_v7m_unassigned_access hook, - * and never get here. - */ - assert(dc->pc < 0xfffffff0); - } #endif if (unlikely(!QTAILQ_EMPTY(&cs->breakpoints))) { -- 2.7.4 target-arm queue. This has the "plumb txattrs through various bits of exec.c" patches, and a collection of bug fixes from various people. thanks -- PMM The following changes since commit a3ac12fba028df90f7b3dbec924995c126c41022: Merge remote-tracking branch 'remotes/ehabkost/tags/numa-next-pull-request' into staging (2018-05-31 11:12:36 +0100) are available in the Git repository at: git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20180531 for you to fetch changes up to 49d1dca0520ea71bc21867fab6647f474fcf857b: KVM: GIC: Fix memory leak due to calling kvm_init_irq_routing twice (2018-05-31 14:52:53 +0100) ---------------------------------------------------------------- target-arm queue: * target/arm: Honour FPCR.FZ in FRECPX * MAINTAINERS: Add entries for newer MPS2 boards and devices * hw/intc/arm_gicv3: Fix APxR<n> register dispatching * arm_gicv3_kvm: fix bug in writing zero bits back to the in-kernel GIC state * tcg: Fix helper function vs host abi for float16 * arm: fix qemu crash on startup with -bios option * arm: fix malloc type mismatch * xlnx-zdma: Correct mem leaks and memset to zero on desc unaligned errors * Correct CPACR reset value for v7 cores * memory.h: Improve IOMMU related documentation * exec: Plumb transaction attributes through various functions in preparation for allowing IOMMUs to see them * vmstate.h: Provide VMSTATE_BOOL_SUB_ARRAY * ARM: ACPI: Fix use-after-free due to memory realloc * KVM: GIC: Fix memory leak due to calling kvm_init_irq_routing twice ---------------------------------------------------------------- Francisco Iglesias (1): xlnx-zdma: Correct mem leaks and memset to zero on desc unaligned errors Igor Mammedov (1): arm: fix qemu crash on startup with -bios option Jan Kiszka (1): hw/intc/arm_gicv3: Fix APxR<n> register dispatching Paolo Bonzini (1): arm: fix malloc type mismatch Peter Maydell (17): target/arm: Honour FPCR.FZ in FRECPX MAINTAINERS: Add entries for newer MPS2 boards and devices Correct CPACR reset value for v7 cores memory.h: Improve IOMMU related documentation Make tb_invalidate_phys_addr() take a MemTxAttrs argument Make address_space_translate{, _cached}() take a MemTxAttrs argument Make address_space_map() take a MemTxAttrs argument Make address_space_access_valid() take a MemTxAttrs argument Make flatview_extend_translation() take a MemTxAttrs argument Make memory_region_access_valid() take a MemTxAttrs argument Make MemoryRegion valid.accepts callback take a MemTxAttrs argument Make flatview_access_valid() take a MemTxAttrs argument Make flatview_translate() take a MemTxAttrs argument Make address_space_get_iotlb_entry() take a MemTxAttrs argument Make flatview_do_translate() take a MemTxAttrs argument Make address_space_translate_iommu take a MemTxAttrs argument vmstate.h: Provide VMSTATE_BOOL_SUB_ARRAY Richard Henderson (1): tcg: Fix helper function vs host abi for float16 Shannon Zhao (3): arm_gicv3_kvm: increase clroffset accordingly ARM: ACPI: Fix use-after-free due to memory realloc KVM: GIC: Fix memory leak due to calling kvm_init_irq_routing twice include/exec/exec-all.h | 5 +- include/exec/helper-head.h | 2 +- include/exec/memory-internal.h | 3 +- include/exec/memory.h | 128 +++++++++++++++++++++++++++++++++++------ include/migration/vmstate.h | 3 + include/sysemu/dma.h | 6 +- accel/tcg/translate-all.c | 4 +- exec.c | 95 ++++++++++++++++++------------ hw/arm/boot.c | 18 +++--- hw/arm/virt-acpi-build.c | 20 +++++-- hw/dma/xlnx-zdma.c | 10 +++- hw/hppa/dino.c | 3 +- hw/intc/arm_gic_kvm.c | 1 - hw/intc/arm_gicv3_cpuif.c | 12 ++-- hw/intc/arm_gicv3_kvm.c | 2 +- hw/nvram/fw_cfg.c | 12 ++-- hw/s390x/s390-pci-inst.c | 3 +- hw/scsi/esp.c | 3 +- hw/vfio/common.c | 3 +- hw/virtio/vhost.c | 3 +- hw/xen/xen_pt_msi.c | 3 +- memory.c | 12 ++-- memory_ldst.inc.c | 18 +++--- target/arm/gdbstub.c | 3 +- target/arm/helper-a64.c | 41 +++++++------ target/arm/helper.c | 90 ++++++++++++++++------------- target/ppc/mmu-hash64.c | 3 +- target/riscv/helper.c | 2 +- target/s390x/diag.c | 6 +- target/s390x/excp_helper.c | 3 +- target/s390x/mmu_helper.c | 3 +- target/s390x/sigp.c | 3 +- target/xtensa/op_helper.c | 3 +- MAINTAINERS | 9 ++- 34 files changed, 353 insertions(+), 182 deletions(-) The FRECPX instructions should (like most other floating point operations) honour the FPCR.FZ bit which specifies whether input denormals should be flushed to zero (or FZ16 for the half-precision version). We forgot to implement this, which doesn't affect the results (since the calculation doesn't actually care about the mantissa bits) but did mean we were failing to set the FPSR.IDC bit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521172712.19930-1-peter.maydell@linaro.org --- target/arm/helper-a64.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ float16 HELPER(frecpx_f16)(float16 a, void *fpstp) return nan; } + a = float16_squash_input_denormal(a, fpst); + val16 = float16_val(a); sbit = 0x8000 & val16; exp = extract32(val16, 10, 5); @@ -XXX,XX +XXX,XX @@ float32 HELPER(frecpx_f32)(float32 a, void *fpstp) return nan; } + a = float32_squash_input_denormal(a, fpst); + val32 = float32_val(a); sbit = 0x80000000ULL & val32; exp = extract32(val32, 23, 8); @@ -XXX,XX +XXX,XX @@ float64 HELPER(frecpx_f64)(float64 a, void *fpstp) return nan; } + a = float64_squash_input_denormal(a, fpst); + val64 = float64_val(a); sbit = 0x8000000000000000ULL & val64; exp = extract64(float64_val(a), 52, 11); -- 2.17.1 Add entries to MAINTAINERS to cover the newer MPS2 boards and the new devices they use. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20180518153157.14899-1-peter.maydell@linaro.org --- MAINTAINERS | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/timer/cmsdk-apb-timer.c F: include/hw/timer/cmsdk-apb-timer.h F: hw/char/cmsdk-apb-uart.c F: include/hw/char/cmsdk-apb-uart.h +F: hw/misc/tz-ppc.c +F: include/hw/misc/tz-ppc.h ARM cores M: Peter Maydell <peter.maydell@linaro.org> @@ -XXX,XX +XXX,XX @@ M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org S: Maintained F: hw/arm/mps2.c -F: hw/misc/mps2-scc.c -F: include/hw/misc/mps2-scc.h +F: hw/arm/mps2-tz.c +F: hw/misc/mps2-*.c +F: include/hw/misc/mps2-*.h +F: hw/arm/iotkit.c +F: include/hw/arm/iotkit.h Musicpal M: Jan Kiszka <jan.kiszka@web.de> -- 2.17.1 From: Jan Kiszka <jan.kiszka@siemens.com> There was a nasty flip in identifying which register group an access is targeting. The issue caused spuriously raised priorities of the guest when handing CPUs over in the Jailhouse hypervisor. Cc: qemu-stable@nongnu.org Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com> Message-id: 28b927d3-da58-bce4-cc13-bfec7f9b1cb9@siemens.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gicv3_cpuif.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ static uint64_t icv_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) { GICv3CPUState *cs = icc_cs_from_env(env); int regno = ri->opc2 & 3; - int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1NS; + int grp = (ri->crm & 1) ? GICV3_G1NS : GICV3_G0; uint64_t value = cs->ich_apr[grp][regno]; trace_gicv3_icv_ap_read(ri->crm & 1, regno, gicv3_redist_affid(cs), value); @@ -XXX,XX +XXX,XX @@ static void icv_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, { GICv3CPUState *cs = icc_cs_from_env(env); int regno = ri->opc2 & 3; - int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1NS; + int grp = (ri->crm & 1) ? GICV3_G1NS : GICV3_G0; trace_gicv3_icv_ap_write(ri->crm & 1, regno, gicv3_redist_affid(cs), value); @@ -XXX,XX +XXX,XX @@ static uint64_t icc_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) uint64_t value; int regno = ri->opc2 & 3; - int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1; + int grp = (ri->crm & 1) ? GICV3_G1 : GICV3_G0; if (icv_access(env, grp == GICV3_G0 ? HCR_FMO : HCR_IMO)) { return icv_ap_read(env, ri); @@ -XXX,XX +XXX,XX @@ static void icc_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, GICv3CPUState *cs = icc_cs_from_env(env); int regno = ri->opc2 & 3; - int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1; + int grp = (ri->crm & 1) ? GICV3_G1 : GICV3_G0; if (icv_access(env, grp == GICV3_G0 ? HCR_FMO : HCR_IMO)) { icv_ap_write(env, ri, value); @@ -XXX,XX +XXX,XX @@ static uint64_t ich_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) { GICv3CPUState *cs = icc_cs_from_env(env); int regno = ri->opc2 & 3; - int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1NS; + int grp = (ri->crm & 1) ? GICV3_G1NS : GICV3_G0; uint64_t value; value = cs->ich_apr[grp][regno]; @@ -XXX,XX +XXX,XX @@ static void ich_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, { GICv3CPUState *cs = icc_cs_from_env(env); int regno = ri->opc2 & 3; - int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1NS; + int grp = (ri->crm & 1) ? GICV3_G1NS : GICV3_G0; trace_gicv3_ich_ap_write(ri->crm & 1, regno, gicv3_redist_affid(cs), value); -- 2.17.1 From: Shannon Zhao <zhaoshenglong@huawei.com> It forgot to increase clroffset during the loop. So it only clear the first 4 bytes. Fixes: 367b9f527becdd20ddf116e17a3c0c2bbc486920 Cc: qemu-stable@nongnu.org Signed-off-by: Shannon Zhao <zhaoshenglong@huawei.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 1527047633-12368-1-git-send-email-zhaoshenglong@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gicv3_kvm.c | 1 + 1 file changed, 1 insertion(+) 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_putbmp(GICv3State *s, uint32_t offset, if (clroffset != 0) { reg = 0; kvm_gicd_access(s, clroffset, &reg, true); + clroffset += 4; } reg = *gic_bmp_ptr32(bmp, irq); kvm_gicd_access(s, offset, &reg, true); -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Depending on the host abi, float16, aka uint16_t, values are passed and returned either zero-extended in the host register or with garbage at the top of the host register. The tcg code generator has so far been assuming garbage, as that matches the x86 abi, but this is incorrect for other host abis. Further, target/arm has so far been assuming zero-extended results, so that it may store the 16-bit value into a 32-bit slot with the high 16-bits already clear. Rectify both problems by mapping "f16" in the helper definition to uint32_t instead of (a typedef for) uint16_t. This forces the host compiler to assume garbage in the upper 16 bits on input and to zero-extend the result on output. Cc: qemu-stable@nongnu.org Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20180522175629.24932-1-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/exec/helper-head.h | 2 +- target/arm/helper-a64.c | 35 +++++++++-------- target/arm/helper.c | 80 +++++++++++++++++++------------------- 3 files changed, 59 insertions(+), 58 deletions(-) diff --git a/include/exec/helper-head.h b/include/exec/helper-head.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/helper-head.h +++ b/include/exec/helper-head.h @@ -XXX,XX +XXX,XX @@ #define dh_ctype_int int #define dh_ctype_i64 uint64_t #define dh_ctype_s64 int64_t -#define dh_ctype_f16 float16 +#define dh_ctype_f16 uint32_t #define dh_ctype_f32 float32 #define dh_ctype_f64 float64 #define dh_ctype_ptr void * diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t float_rel_to_flags(int res) return flags; } -uint64_t HELPER(vfp_cmph_a64)(float16 x, float16 y, void *fp_status) +uint64_t HELPER(vfp_cmph_a64)(uint32_t x, uint32_t y, void *fp_status) { return float_rel_to_flags(float16_compare_quiet(x, y, fp_status)); } -uint64_t HELPER(vfp_cmpeh_a64)(float16 x, float16 y, void *fp_status) +uint64_t HELPER(vfp_cmpeh_a64)(uint32_t x, uint32_t y, void *fp_status) { return float_rel_to_flags(float16_compare(x, y, fp_status)); } @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp) #define float64_three make_float64(0x4008000000000000ULL) #define float64_one_point_five make_float64(0x3FF8000000000000ULL) -float16 HELPER(recpsf_f16)(float16 a, float16 b, void *fpstp) +uint32_t HELPER(recpsf_f16)(uint32_t a, uint32_t b, void *fpstp) { float_status *fpst = fpstp; @@ -XXX,XX +XXX,XX @@ float64 HELPER(recpsf_f64)(float64 a, float64 b, void *fpstp) return float64_muladd(a, b, float64_two, 0, fpst); } -float16 HELPER(rsqrtsf_f16)(float16 a, float16 b, void *fpstp) +uint32_t HELPER(rsqrtsf_f16)(uint32_t a, uint32_t b, void *fpstp) { float_status *fpst = fpstp; @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_addlp_u16)(uint64_t a) } /* Floating-point reciprocal exponent - see FPRecpX in ARM ARM */ -float16 HELPER(frecpx_f16)(float16 a, void *fpstp) +uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp) { float_status *fpst = fpstp; uint16_t val16, sbit; @@ -XXX,XX +XXX,XX @@ void HELPER(casp_be_parallel)(CPUARMState *env, uint32_t rs, uint64_t addr, #define ADVSIMD_HELPER(name, suffix) HELPER(glue(glue(advsimd_, name), suffix)) #define ADVSIMD_HALFOP(name) \ -float16 ADVSIMD_HELPER(name, h)(float16 a, float16 b, void *fpstp) \ +uint32_t ADVSIMD_HELPER(name, h)(uint32_t a, uint32_t b, void *fpstp) \ { \ float_status *fpst = fpstp; \ return float16_ ## name(a, b, fpst); \ @@ -XXX,XX +XXX,XX @@ ADVSIMD_HALFOP(mulx) ADVSIMD_TWOHALFOP(mulx) /* fused multiply-accumulate */ -float16 HELPER(advsimd_muladdh)(float16 a, float16 b, float16 c, void *fpstp) +uint32_t HELPER(advsimd_muladdh)(uint32_t a, uint32_t b, uint32_t c, + void *fpstp) { float_status *fpst = fpstp; return float16_muladd(a, b, c, 0, fpst); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_muladd2h)(uint32_t two_a, uint32_t two_b, #define ADVSIMD_CMPRES(test) (test) ? 0xffff : 0 -uint32_t HELPER(advsimd_ceq_f16)(float16 a, float16 b, void *fpstp) +uint32_t HELPER(advsimd_ceq_f16)(uint32_t a, uint32_t b, void *fpstp) { float_status *fpst = fpstp; int compare = float16_compare_quiet(a, b, fpst); return ADVSIMD_CMPRES(compare == float_relation_equal); } -uint32_t HELPER(advsimd_cge_f16)(float16 a, float16 b, void *fpstp) +uint32_t HELPER(advsimd_cge_f16)(uint32_t a, uint32_t b, void *fpstp) { float_status *fpst = fpstp; int compare = float16_compare(a, b, fpst); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_cge_f16)(float16 a, float16 b, void *fpstp) compare == float_relation_equal); } -uint32_t HELPER(advsimd_cgt_f16)(float16 a, float16 b, void *fpstp) +uint32_t HELPER(advsimd_cgt_f16)(uint32_t a, uint32_t b, void *fpstp) { float_status *fpst = fpstp; int compare = float16_compare(a, b, fpst); return ADVSIMD_CMPRES(compare == float_relation_greater); } -uint32_t HELPER(advsimd_acge_f16)(float16 a, float16 b, void *fpstp) +uint32_t HELPER(advsimd_acge_f16)(uint32_t a, uint32_t b, void *fpstp) { float_status *fpst = fpstp; float16 f0 = float16_abs(a); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_acge_f16)(float16 a, float16 b, void *fpstp) compare == float_relation_equal); } -uint32_t HELPER(advsimd_acgt_f16)(float16 a, float16 b, void *fpstp) +uint32_t HELPER(advsimd_acgt_f16)(uint32_t a, uint32_t b, void *fpstp) { float_status *fpst = fpstp; float16 f0 = float16_abs(a); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_acgt_f16)(float16 a, float16 b, void *fpstp) } /* round to integral */ -float16 HELPER(advsimd_rinth_exact)(float16 x, void *fp_status) +uint32_t HELPER(advsimd_rinth_exact)(uint32_t x, void *fp_status) { return float16_round_to_int(x, fp_status); } -float16 HELPER(advsimd_rinth)(float16 x, void *fp_status) +uint32_t HELPER(advsimd_rinth)(uint32_t x, void *fp_status) { int old_flags = get_float_exception_flags(fp_status), new_flags; float16 ret; @@ -XXX,XX +XXX,XX @@ float16 HELPER(advsimd_rinth)(float16 x, void *fp_status) * setting the mode appropriately before calling the helper. */ -uint32_t HELPER(advsimd_f16tosinth)(float16 a, void *fpstp) +uint32_t HELPER(advsimd_f16tosinth)(uint32_t a, void *fpstp) { float_status *fpst = fpstp; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_f16tosinth)(float16 a, void *fpstp) return float16_to_int16(a, fpst); } -uint32_t HELPER(advsimd_f16touinth)(float16 a, void *fpstp) +uint32_t HELPER(advsimd_f16touinth)(uint32_t a, void *fpstp) { float_status *fpst = fpstp; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_f16touinth)(float16 a, void *fpstp) * Square Root and Reciprocal square root */ -float16 HELPER(sqrt_f16)(float16 a, void *fpstp) +uint32_t HELPER(sqrt_f16)(uint32_t a, void *fpstp) { float_status *s = fpstp; 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 @@ DO_VFP_cmp(d, float64) /* Integer to float and float to integer conversions */ -#define CONV_ITOF(name, fsz, sign) \ - float##fsz HELPER(name)(uint32_t x, void *fpstp) \ -{ \ - float_status *fpst = fpstp; \ - return sign##int32_to_##float##fsz((sign##int32_t)x, fpst); \ +#define CONV_ITOF(name, ftype, fsz, sign) \ +ftype HELPER(name)(uint32_t x, void *fpstp) \ +{ \ + float_status *fpst = fpstp; \ + return sign##int32_to_##float##fsz((sign##int32_t)x, fpst); \ } -#define CONV_FTOI(name, fsz, sign, round) \ -uint32_t HELPER(name)(float##fsz x, void *fpstp) \ -{ \ - float_status *fpst = fpstp; \ - if (float##fsz##_is_any_nan(x)) { \ - float_raise(float_flag_invalid, fpst); \ - return 0; \ - } \ - return float##fsz##_to_##sign##int32##round(x, fpst); \ +#define CONV_FTOI(name, ftype, fsz, sign, round) \ +uint32_t HELPER(name)(ftype x, void *fpstp) \ +{ \ + float_status *fpst = fpstp; \ + if (float##fsz##_is_any_nan(x)) { \ + float_raise(float_flag_invalid, fpst); \ + return 0; \ + } \ + return float##fsz##_to_##sign##int32##round(x, fpst); \ } -#define FLOAT_CONVS(name, p, fsz, sign) \ -CONV_ITOF(vfp_##name##to##p, fsz, sign) \ -CONV_FTOI(vfp_to##name##p, fsz, sign, ) \ -CONV_FTOI(vfp_to##name##z##p, fsz, sign, _round_to_zero) +#define FLOAT_CONVS(name, p, ftype, fsz, sign) \ + CONV_ITOF(vfp_##name##to##p, ftype, fsz, sign) \ + CONV_FTOI(vfp_to##name##p, ftype, fsz, sign, ) \ + CONV_FTOI(vfp_to##name##z##p, ftype, fsz, sign, _round_to_zero) -FLOAT_CONVS(si, h, 16, ) -FLOAT_CONVS(si, s, 32, ) -FLOAT_CONVS(si, d, 64, ) -FLOAT_CONVS(ui, h, 16, u) -FLOAT_CONVS(ui, s, 32, u) -FLOAT_CONVS(ui, d, 64, u) +FLOAT_CONVS(si, h, uint32_t, 16, ) +FLOAT_CONVS(si, s, float32, 32, ) +FLOAT_CONVS(si, d, float64, 64, ) +FLOAT_CONVS(ui, h, uint32_t, 16, u) +FLOAT_CONVS(ui, s, float32, 32, u) +FLOAT_CONVS(ui, d, float64, 64, u) #undef CONV_ITOF #undef CONV_FTOI @@ -XXX,XX +XXX,XX @@ static float16 do_postscale_fp16(float64 f, int shift, float_status *fpst) return float64_to_float16(float64_scalbn(f, -shift, fpst), true, fpst); } -float16 HELPER(vfp_sltoh)(uint32_t x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_sltoh)(uint32_t x, uint32_t shift, void *fpst) { return do_postscale_fp16(int32_to_float64(x, fpst), shift, fpst); } -float16 HELPER(vfp_ultoh)(uint32_t x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_ultoh)(uint32_t x, uint32_t shift, void *fpst) { return do_postscale_fp16(uint32_to_float64(x, fpst), shift, fpst); } -float16 HELPER(vfp_sqtoh)(uint64_t x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_sqtoh)(uint64_t x, uint32_t shift, void *fpst) { return do_postscale_fp16(int64_to_float64(x, fpst), shift, fpst); } -float16 HELPER(vfp_uqtoh)(uint64_t x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_uqtoh)(uint64_t x, uint32_t shift, void *fpst) { return do_postscale_fp16(uint64_to_float64(x, fpst), shift, fpst); } @@ -XXX,XX +XXX,XX @@ static float64 do_prescale_fp16(float16 f, int shift, float_status *fpst) } } -uint32_t HELPER(vfp_toshh)(float16 x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_toshh)(uint32_t x, uint32_t shift, void *fpst) { return float64_to_int16(do_prescale_fp16(x, shift, fpst), fpst); } -uint32_t HELPER(vfp_touhh)(float16 x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_touhh)(uint32_t x, uint32_t shift, void *fpst) { return float64_to_uint16(do_prescale_fp16(x, shift, fpst), fpst); } -uint32_t HELPER(vfp_toslh)(float16 x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_toslh)(uint32_t x, uint32_t shift, void *fpst) { return float64_to_int32(do_prescale_fp16(x, shift, fpst), fpst); } -uint32_t HELPER(vfp_toulh)(float16 x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_toulh)(uint32_t x, uint32_t shift, void *fpst) { return float64_to_uint32(do_prescale_fp16(x, shift, fpst), fpst); } -uint64_t HELPER(vfp_tosqh)(float16 x, uint32_t shift, void *fpst) +uint64_t HELPER(vfp_tosqh)(uint32_t x, uint32_t shift, void *fpst) { return float64_to_int64(do_prescale_fp16(x, shift, fpst), fpst); } -uint64_t HELPER(vfp_touqh)(float16 x, uint32_t shift, void *fpst) +uint64_t HELPER(vfp_touqh)(uint32_t x, uint32_t shift, void *fpst) { return float64_to_uint64(do_prescale_fp16(x, shift, fpst), fpst); } @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(set_neon_rmode)(uint32_t rmode, CPUARMState *env) } /* Half precision conversions. */ -float32 HELPER(vfp_fcvt_f16_to_f32)(float16 a, void *fpstp, uint32_t ahp_mode) +float32 HELPER(vfp_fcvt_f16_to_f32)(uint32_t a, void *fpstp, uint32_t ahp_mode) { /* Squash FZ16 to 0 for the duration of conversion. In this case, * it would affect flushing input denormals. @@ -XXX,XX +XXX,XX @@ float32 HELPER(vfp_fcvt_f16_to_f32)(float16 a, void *fpstp, uint32_t ahp_mode) return r; } -float16 HELPER(vfp_fcvt_f32_to_f16)(float32 a, void *fpstp, uint32_t ahp_mode) +uint32_t HELPER(vfp_fcvt_f32_to_f16)(float32 a, void *fpstp, uint32_t ahp_mode) { /* Squash FZ16 to 0 for the duration of conversion. In this case, * it would affect flushing output denormals. @@ -XXX,XX +XXX,XX @@ float16 HELPER(vfp_fcvt_f32_to_f16)(float32 a, void *fpstp, uint32_t ahp_mode) return r; } -float64 HELPER(vfp_fcvt_f16_to_f64)(float16 a, void *fpstp, uint32_t ahp_mode) +float64 HELPER(vfp_fcvt_f16_to_f64)(uint32_t a, void *fpstp, uint32_t ahp_mode) { /* Squash FZ16 to 0 for the duration of conversion. In this case, * it would affect flushing input denormals. @@ -XXX,XX +XXX,XX @@ float64 HELPER(vfp_fcvt_f16_to_f64)(float16 a, void *fpstp, uint32_t ahp_mode) return r; } -float16 HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode) +uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode) { /* Squash FZ16 to 0 for the duration of conversion. In this case, * it would affect flushing output denormals. @@ -XXX,XX +XXX,XX @@ static bool round_to_inf(float_status *fpst, bool sign_bit) g_assert_not_reached(); } -float16 HELPER(recpe_f16)(float16 input, void *fpstp) +uint32_t HELPER(recpe_f16)(uint32_t input, void *fpstp) { float_status *fpst = fpstp; float16 f16 = float16_squash_input_denormal(input, fpst); @@ -XXX,XX +XXX,XX @@ static uint64_t recip_sqrt_estimate(int *exp , int exp_off, uint64_t frac) return extract64(estimate, 0, 8) << 44; } -float16 HELPER(rsqrte_f16)(float16 input, void *fpstp) +uint32_t HELPER(rsqrte_f16)(uint32_t input, void *fpstp) { float_status *s = fpstp; float16 f16 = float16_squash_input_denormal(input, s); -- 2.17.1 From: Igor Mammedov <imammedo@redhat.com> When QEMU is started with following CLI -machine virt,gic-version=3,accel=kvm -cpu host -bios AAVMF_CODE.fd it crashes with abort at accel/kvm/kvm-all.c:2164: KVM_SET_DEVICE_ATTR failed: Group 6 attr 0x000000000000c665: Invalid argument Which is caused by implicit dependency of kvm_arm_gicv3_reset() on arm_gicv3_icc_reset() where the later is called by CPU reset reset callback. However commit: 3b77f6c arm/boot: split load_dtb() from arm_load_kernel() broke CPU reset callback registration in case arm_load_kernel() ... if (!info->kernel_filename || info->firmware_loaded) branch is taken, i.e. it's sufficient to provide a firmware or do not provide kernel on CLI to skip cpu reset callback registration, where before offending commit the callback has been registered unconditionally. Fix it by registering the callback right at the beginning of arm_load_kernel() unconditionally instead of doing it at the end. NOTE: we probably should eliminate that dependency anyways as well as separate arch CPU reset parts from arm_load_kernel() into CPU itself, but that refactoring that I probably would have to do anyways later for CPU hotplug to work. Reported-by: Auger Eric <eric.auger@redhat.com> Signed-off-by: Igor Mammedov <imammedo@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested-by: Eric Auger <eric.auger@redhat.com> Message-id: 1527070950-208350-1-git-send-email-imammedo@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/boot.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) static const ARMInsnFixup *primary_loader; AddressSpace *as = arm_boot_address_space(cpu, info); + /* CPU objects (unlike devices) are not automatically reset on system + * reset, so we must always register a handler to do so. If we're + * actually loading a kernel, the handler is also responsible for + * arranging that we start it correctly. + */ + for (cs = first_cpu; cs; cs = CPU_NEXT(cs)) { + qemu_register_reset(do_cpu_reset, ARM_CPU(cs)); + } + /* The board code is not supposed to set secure_board_setup unless * running its code in secure mode is actually possible, and KVM * doesn't support secure. @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) ARM_CPU(cs)->env.boot_info = info; } - /* CPU objects (unlike devices) are not automatically reset on system - * reset, so we must always register a handler to do so. If we're - * actually loading a kernel, the handler is also responsible for - * arranging that we start it correctly. - */ - for (cs = first_cpu; cs; cs = CPU_NEXT(cs)) { - qemu_register_reset(do_cpu_reset, ARM_CPU(cs)); - } - if (!info->skip_dtb_autoload && have_dtb(info)) { if (arm_load_dtb(info->dtb_start, info, info->dtb_limit, as) < 0) { exit(1); -- 2.17.1 From: Paolo Bonzini <pbonzini@redhat.com> cpregs_keys is an uint32_t* so the allocation should use uint32_t. g_new is even better because it is type-safe. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/gdbstub.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub.c +++ b/target/arm/gdbstub.c @@ -XXX,XX +XXX,XX @@ int arm_gen_dynamic_xml(CPUState *cs) RegisterSysregXmlParam param = {cs, s}; cpu->dyn_xml.num_cpregs = 0; - cpu->dyn_xml.cpregs_keys = g_malloc(sizeof(uint32_t *) * - g_hash_table_size(cpu->cp_regs)); + cpu->dyn_xml.cpregs_keys = g_new(uint32_t, g_hash_table_size(cpu->cp_regs)); g_string_printf(s, "<?xml version=\"1.0\"?>"); g_string_append_printf(s, "<!DOCTYPE target SYSTEM \"gdb-target.dtd\">"); g_string_append_printf(s, "<feature name=\"org.qemu.gdb.arm.sys.regs\">"); -- 2.17.1 From: Francisco Iglesias <frasse.iglesias@gmail.com> Coverity found that the string return by 'object_get_canonical_path' was not being freed at two locations in the model (CID 1391294 and CID 1391293) and also that a memset was being called with a value greater than the max of a byte on the second argument (CID 1391286). This patch corrects this by adding the freeing of the strings and also changing to memset to zero instead on descriptor unaligned errors. Signed-off-by: Francisco Iglesias <frasse.iglesias@gmail.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180528184859.3530-1-frasse.iglesias@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/dma/xlnx-zdma.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/hw/dma/xlnx-zdma.c b/hw/dma/xlnx-zdma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/xlnx-zdma.c +++ b/hw/dma/xlnx-zdma.c @@ -XXX,XX +XXX,XX @@ static bool zdma_load_descriptor(XlnxZDMA *s, uint64_t addr, void *buf) qemu_log_mask(LOG_GUEST_ERROR, "zdma: unaligned descriptor at %" PRIx64, addr); - memset(buf, 0xdeadbeef, sizeof(XlnxZDMADescr)); + memset(buf, 0x0, sizeof(XlnxZDMADescr)); s->error = true; return false; } @@ -XXX,XX +XXX,XX @@ static uint64_t zdma_read(void *opaque, hwaddr addr, unsigned size) RegisterInfo *r = &s->regs_info[addr / 4]; if (!r->data) { + gchar *path = object_get_canonical_path(OBJECT(s)); qemu_log("%s: Decode error: read from %" HWADDR_PRIx "\n", - object_get_canonical_path(OBJECT(s)), + path, addr); + g_free(path); ARRAY_FIELD_DP32(s->regs, ZDMA_CH_ISR, INV_APB, true); zdma_ch_imr_update_irq(s); return 0; @@ -XXX,XX +XXX,XX @@ static void zdma_write(void *opaque, hwaddr addr, uint64_t value, RegisterInfo *r = &s->regs_info[addr / 4]; if (!r->data) { + gchar *path = object_get_canonical_path(OBJECT(s)); qemu_log("%s: Decode error: write to %" HWADDR_PRIx "=%" PRIx64 "\n", - object_get_canonical_path(OBJECT(s)), + path, addr, value); + g_free(path); ARRAY_FIELD_DP32(s->regs, ZDMA_CH_ISR, INV_APB, true); zdma_ch_imr_update_irq(s); return; -- 2.17.1 In commit f0aff255700 we made cpacr_write() enforce that some CPACR bits are RAZ/WI and some are RAO/WI for ARMv7 cores. Unfortunately we forgot to also update the register's reset value. The effect was that (a) a guest that read CPACR on reset would not see ones in the RAO bits, and (b) if you did a migration before the guest did a write to the CPACR then the migration would fail because the destination would enforce the RAO bits and then complain that they didn't match the zero value from the source. Implement reset for the CPACR using a custom reset function that just calls cpacr_write(), to avoid having to duplicate the logic for which bits are RAO. This bug would affect migration for TCG CPUs which are ARMv7 with VFP but without one of Neon or VFPv3. Reported-by: Cédric Le Goater <clg@kaod.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Cédric Le Goater <clg@kaod.org> Message-id: 20180522173713.26282-1-peter.maydell@linaro.org --- target/arm/helper.c | 10 +++++++++- 1 file changed, 9 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 @@ static void cpacr_write(CPUARMState *env, const ARMCPRegInfo *ri, env->cp15.cpacr_el1 = value; } +static void cpacr_reset(CPUARMState *env, const ARMCPRegInfo *ri) +{ + /* Call cpacr_write() so that we reset with the correct RAO bits set + * for our CPU features. + */ + cpacr_write(env, ri, 0); +} + static CPAccessResult cpacr_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v6_cp_reginfo[] = { { .name = "CPACR", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .crn = 1, .crm = 0, .opc1 = 0, .opc2 = 2, .accessfn = cpacr_access, .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.cpacr_el1), - .resetvalue = 0, .writefn = cpacr_write }, + .resetfn = cpacr_reset, .writefn = cpacr_write }, REGINFO_SENTINEL }; -- 2.17.1 Add more detail to the documentation for memory_region_init_iommu() and other IOMMU-related functions and data structures. 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> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 20180521140402.23318-2-peter.maydell@linaro.org --- include/exec/memory.h | 105 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 95 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 @@ enum IOMMUMemoryRegionAttr { IOMMU_ATTR_SPAPR_TCE_FD }; +/** + * IOMMUMemoryRegionClass: + * + * All IOMMU implementations need to subclass TYPE_IOMMU_MEMORY_REGION + * and provide an implementation of at least the @translate method here + * to handle requests to the memory region. Other methods are optional. + * + * The IOMMU implementation must use the IOMMU notifier infrastructure + * 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). + */ typedef struct IOMMUMemoryRegionClass { /* private */ struct DeviceClass parent_class; /* - * Return a TLB entry that contains a given address. Flag should - * be the access permission of this translation operation. We can - * set flag to IOMMU_NONE to mean that we don't need any - * read/write permission checks, like, when for region replay. + * Return a TLB entry that contains a given address. + * + * The IOMMUAccessFlags indicated via @flag are optional and may + * be specified as IOMMU_NONE to indicate that the caller needs + * the full translation information for both reads and writes. If + * the access flags are specified then the IOMMU implementation + * may use this as an optimization, to stop doing a page table + * walk as soon as it knows that the requested permissions are not + * allowed. If IOMMU_NONE is passed then the IOMMU must do the + * full page table walk and report the permissions in the returned + * IOMMUTLBEntry. (Note that this implies that an IOMMU may not + * return different mappings for reads and writes.) + * + * The returned information remains valid while the caller is + * holding the big QEMU lock or is inside an RCU critical section; + * if the caller wishes to cache the mapping beyond that it must + * register an IOMMU notifier so it can invalidate its cached + * information when the IOMMU mapping changes. + * + * @iommu: the IOMMUMemoryRegion + * @hwaddr: address to be translated within the memory region + * @flag: requested access permissions */ IOMMUTLBEntry (*translate)(IOMMUMemoryRegion *iommu, hwaddr addr, IOMMUAccessFlags flag); - /* Returns minimum supported page size */ + /* Returns minimum supported page size in bytes. + * If this method is not provided then the minimum is assumed to + * be TARGET_PAGE_SIZE. + * + * @iommu: the IOMMUMemoryRegion + */ uint64_t (*get_min_page_size)(IOMMUMemoryRegion *iommu); - /* Called when IOMMU Notifier flag changed */ + /* Called when IOMMU Notifier flag changes (ie when the set of + * events which IOMMU users are requesting notification for changes). + * Optional method -- need not be provided if the IOMMU does not + * need to know exactly which events must be notified. + * + * @iommu: the IOMMUMemoryRegion + * @old_flags: events which previously needed to be notified + * @new_flags: events which now need to be notified + */ void (*notify_flag_changed)(IOMMUMemoryRegion *iommu, IOMMUNotifierFlag old_flags, IOMMUNotifierFlag new_flags); - /* Set this up to provide customized IOMMU replay function */ + /* Called to handle memory_region_iommu_replay(). + * + * The default implementation of memory_region_iommu_replay() is to + * call the IOMMU translate method for every page in the address space + * with flag == IOMMU_NONE and then call the notifier if translate + * returns a valid mapping. If this method is implemented then it + * overrides the default behaviour, and must provide the full semantics + * of memory_region_iommu_replay(), by calling @notifier for every + * translation present in the IOMMU. + * + * Optional method -- an IOMMU only needs to provide this method + * if the default is inefficient or produces undesirable side effects. + * + * Note: this is not related to record-and-replay functionality. + */ void (*replay)(IOMMUMemoryRegion *iommu, IOMMUNotifier *notifier); - /* Get IOMMU misc attributes */ - int (*get_attr)(IOMMUMemoryRegion *iommu, enum IOMMUMemoryRegionAttr, + /* Get IOMMU misc attributes. This is an optional method that + * can be used to allow users of the IOMMU to get implementation-specific + * information. The IOMMU implements this method to handle calls + * by IOMMU users to memory_region_iommu_get_attr() by filling in + * the arbitrary data pointer for any IOMMUMemoryRegionAttr values that + * the IOMMU supports. If the method is unimplemented then + * memory_region_iommu_get_attr() will always return -EINVAL. + * + * @iommu: the IOMMUMemoryRegion + * @attr: attribute being queried + * @data: memory to fill in with the attribute data + * + * Returns 0 on success, or a negative errno; in particular + * returns -EINVAL for unrecognized or unimplemented attribute types. + */ + int (*get_attr)(IOMMUMemoryRegion *iommu, enum IOMMUMemoryRegionAttr attr, void *data); } IOMMUMemoryRegionClass; @@ -XXX,XX +XXX,XX @@ static inline void memory_region_init_reservation(MemoryRegion *mr, * An IOMMU region translates addresses and forwards accesses to a target * memory region. * + * The IOMMU implementation must define a subclass of TYPE_IOMMU_MEMORY_REGION. + * @_iommu_mr should be a pointer to enough memory for an instance of + * that subclass, @instance_size is the size of that subclass, and + * @mrtypename is its name. This function will initialize @_iommu_mr as an + * instance of the subclass, and its methods will then be called to handle + * accesses to the memory region. See the documentation of + * #IOMMUMemoryRegionClass for further details. + * * @_iommu_mr: the #IOMMUMemoryRegion to be initialized * @instance_size: the IOMMUMemoryRegion subclass instance size * @mrtypename: the type name of the #IOMMUMemoryRegion @@ -XXX,XX +XXX,XX @@ void memory_region_register_iommu_notifier(MemoryRegion *mr, * a notifier with the minimum page granularity returned by * mr->iommu_ops->get_page_size(). * + * Note: this is not related to record-and-replay functionality. + * * @iommu_mr: the memory region to observe * @n: the notifier to which to replay iommu mappings */ @@ -XXX,XX +XXX,XX @@ void memory_region_iommu_replay(IOMMUMemoryRegion *iommu_mr, IOMMUNotifier *n); * memory_region_iommu_replay_all: replay existing IOMMU translations * to all the notifiers registered. * + * Note: this is not related to record-and-replay functionality. + * * @iommu_mr: the memory region to observe */ void memory_region_iommu_replay_all(IOMMUMemoryRegion *iommu_mr); @@ -XXX,XX +XXX,XX @@ void memory_region_unregister_iommu_notifier(MemoryRegion *mr, * memory_region_iommu_get_attr: return an IOMMU attr if get_attr() is * defined on the IOMMU. * - * Returns 0 if succeded, error code otherwise. + * Returns 0 on success, or a negative errno otherwise. In particular, + * -EINVAL indicates that the IOMMU does not support the requested + * attribute. * * @iommu_mr: the memory region * @attr: the requested attribute -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to tb_invalidate_phys_addr(). Its callers either have an attrs value to hand, or don't care and can use MEMTXATTRS_UNSPECIFIED. 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: 20180521140402.23318-3-peter.maydell@linaro.org --- include/exec/exec-all.h | 5 +++-- accel/tcg/translate-all.c | 2 +- exec.c | 2 +- target/xtensa/op_helper.c | 3 ++- 4 files changed, 7 insertions(+), 5 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 tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, void tlb_set_page(CPUState *cpu, target_ulong vaddr, hwaddr paddr, int prot, int mmu_idx, target_ulong size); -void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr); +void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr, MemTxAttrs attrs); void probe_write(CPUArchState *env, target_ulong addr, int size, int mmu_idx, uintptr_t retaddr); #else @@ -XXX,XX +XXX,XX @@ static inline void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *cpu, uint16_t idxmap) { } -static inline void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr) +static inline void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr, + MemTxAttrs attrs) { } #endif diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ static TranslationBlock *tb_find_pc(uintptr_t tc_ptr) } #if !defined(CONFIG_USER_ONLY) -void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr) +void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr, MemTxAttrs attrs) { ram_addr_t ram_addr; MemoryRegion *mr; diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static void breakpoint_invalidate(CPUState *cpu, target_ulong pc) if (phys != -1) { /* Locks grabbed by tb_invalidate_phys_addr */ tb_invalidate_phys_addr(cpu->cpu_ases[asidx].as, - phys | (pc & ~TARGET_PAGE_MASK)); + phys | (pc & ~TARGET_PAGE_MASK), attrs); } } #endif diff --git a/target/xtensa/op_helper.c b/target/xtensa/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/op_helper.c +++ b/target/xtensa/op_helper.c @@ -XXX,XX +XXX,XX @@ static void tb_invalidate_virtual_addr(CPUXtensaState *env, uint32_t vaddr) int ret = xtensa_get_physical_addr(env, false, vaddr, 2, 0, &paddr, &page_size, &access); if (ret == 0) { - tb_invalidate_phys_addr(&address_space_memory, paddr); + tb_invalidate_phys_addr(&address_space_memory, paddr, + MEMTXATTRS_UNSPECIFIED); } } -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to address_space_translate() and address_space_translate_cached(). Callers either have an attrs value to hand, or don't care and can use MEMTXATTRS_UNSPECIFIED. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-4-peter.maydell@linaro.org --- include/exec/memory.h | 4 +++- accel/tcg/translate-all.c | 2 +- exec.c | 14 +++++++++----- hw/vfio/common.c | 3 ++- memory_ldst.inc.c | 18 +++++++++--------- target/riscv/helper.c | 2 +- 6 files changed, 25 insertions(+), 18 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 @@ IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr, * #MemoryRegion. * @len: pointer to length * @is_write: indicates the transfer direction + * @attrs: memory attributes */ MemoryRegion *flatview_translate(FlatView *fv, hwaddr addr, hwaddr *xlat, @@ -XXX,XX +XXX,XX @@ MemoryRegion *flatview_translate(FlatView *fv, static inline MemoryRegion *address_space_translate(AddressSpace *as, hwaddr addr, hwaddr *xlat, - hwaddr *len, bool is_write) + hwaddr *len, bool is_write, + MemTxAttrs attrs) { return flatview_translate(address_space_to_flatview(as), addr, xlat, len, is_write); diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr, MemTxAttrs attrs) hwaddr l = 1; rcu_read_lock(); - mr = address_space_translate(as, addr, &addr, &l, false); + mr = address_space_translate(as, addr, &addr, &l, false, attrs); if (!(memory_region_is_ram(mr) || memory_region_is_romd(mr))) { rcu_read_unlock(); diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static inline void cpu_physical_memory_write_rom_internal(AddressSpace *as, rcu_read_lock(); while (len > 0) { l = len; - mr = address_space_translate(as, addr, &addr1, &l, true); + mr = address_space_translate(as, addr, &addr1, &l, true, + MEMTXATTRS_UNSPECIFIED); if (!(memory_region_is_ram(mr) || memory_region_is_romd(mr))) { @@ -XXX,XX +XXX,XX @@ void address_space_cache_destroy(MemoryRegionCache *cache) */ static inline MemoryRegion *address_space_translate_cached( MemoryRegionCache *cache, hwaddr addr, hwaddr *xlat, - hwaddr *plen, bool is_write) + hwaddr *plen, bool is_write, MemTxAttrs attrs) { MemoryRegionSection section; MemoryRegion *mr; @@ -XXX,XX +XXX,XX @@ address_space_read_cached_slow(MemoryRegionCache *cache, hwaddr addr, MemoryRegion *mr; l = len; - mr = address_space_translate_cached(cache, addr, &addr1, &l, false); + mr = address_space_translate_cached(cache, addr, &addr1, &l, false, + MEMTXATTRS_UNSPECIFIED); flatview_read_continue(cache->fv, addr, MEMTXATTRS_UNSPECIFIED, buf, len, addr1, l, mr); @@ -XXX,XX +XXX,XX @@ address_space_write_cached_slow(MemoryRegionCache *cache, hwaddr addr, MemoryRegion *mr; l = len; - mr = address_space_translate_cached(cache, addr, &addr1, &l, true); + mr = address_space_translate_cached(cache, addr, &addr1, &l, true, + MEMTXATTRS_UNSPECIFIED); flatview_write_continue(cache->fv, addr, MEMTXATTRS_UNSPECIFIED, buf, len, addr1, l, mr); @@ -XXX,XX +XXX,XX @@ bool cpu_physical_memory_is_io(hwaddr phys_addr) rcu_read_lock(); mr = address_space_translate(&address_space_memory, - phys_addr, &phys_addr, &l, false); + phys_addr, &phys_addr, &l, false, + MEMTXATTRS_UNSPECIFIED); res = !(memory_region_is_ram(mr) || memory_region_is_romd(mr)); rcu_read_unlock(); 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 bool vfio_get_vaddr(IOMMUTLBEntry *iotlb, void **vaddr, */ mr = address_space_translate(&address_space_memory, iotlb->translated_addr, - &xlat, &len, writable); + &xlat, &len, writable, + MEMTXATTRS_UNSPECIFIED); if (!memory_region_is_ram(mr)) { error_report("iommu map to non memory area %"HWADDR_PRIx"", xlat); diff --git a/memory_ldst.inc.c b/memory_ldst.inc.c index XXXXXXX..XXXXXXX 100644 --- a/memory_ldst.inc.c +++ b/memory_ldst.inc.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t glue(address_space_ldl_internal, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, false); + mr = TRANSLATE(addr, &addr1, &l, false, attrs); if (l < 4 || !IS_DIRECT(mr, false)) { release_lock |= prepare_mmio_access(mr); @@ -XXX,XX +XXX,XX @@ static inline uint64_t glue(address_space_ldq_internal, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, false); + mr = TRANSLATE(addr, &addr1, &l, false, attrs); if (l < 8 || !IS_DIRECT(mr, false)) { release_lock |= prepare_mmio_access(mr); @@ -XXX,XX +XXX,XX @@ uint32_t glue(address_space_ldub, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, false); + mr = TRANSLATE(addr, &addr1, &l, false, attrs); if (!IS_DIRECT(mr, false)) { release_lock |= prepare_mmio_access(mr); @@ -XXX,XX +XXX,XX @@ static inline uint32_t glue(address_space_lduw_internal, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, false); + mr = TRANSLATE(addr, &addr1, &l, false, attrs); if (l < 2 || !IS_DIRECT(mr, false)) { release_lock |= prepare_mmio_access(mr); @@ -XXX,XX +XXX,XX @@ void glue(address_space_stl_notdirty, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, true); + mr = TRANSLATE(addr, &addr1, &l, true, attrs); if (l < 4 || !IS_DIRECT(mr, true)) { release_lock |= prepare_mmio_access(mr); @@ -XXX,XX +XXX,XX @@ static inline void glue(address_space_stl_internal, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, true); + mr = TRANSLATE(addr, &addr1, &l, true, attrs); if (l < 4 || !IS_DIRECT(mr, true)) { release_lock |= prepare_mmio_access(mr); @@ -XXX,XX +XXX,XX @@ void glue(address_space_stb, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, true); + mr = TRANSLATE(addr, &addr1, &l, true, attrs); if (!IS_DIRECT(mr, true)) { release_lock |= prepare_mmio_access(mr); r = memory_region_dispatch_write(mr, addr1, val, 1, attrs); @@ -XXX,XX +XXX,XX @@ static inline void glue(address_space_stw_internal, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, true); + mr = TRANSLATE(addr, &addr1, &l, true, attrs); if (l < 2 || !IS_DIRECT(mr, true)) { release_lock |= prepare_mmio_access(mr); @@ -XXX,XX +XXX,XX @@ static void glue(address_space_stq_internal, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, true); + mr = TRANSLATE(addr, &addr1, &l, true, attrs); if (l < 8 || !IS_DIRECT(mr, true)) { release_lock |= prepare_mmio_access(mr); diff --git a/target/riscv/helper.c b/target/riscv/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/helper.c +++ b/target/riscv/helper.c @@ -XXX,XX +XXX,XX @@ restart: MemoryRegion *mr; hwaddr l = sizeof(target_ulong), addr1; mr = address_space_translate(cs->as, pte_addr, - &addr1, &l, false); + &addr1, &l, false, MEMTXATTRS_UNSPECIFIED); if (memory_access_is_direct(mr, true)) { target_ulong *pte_pa = qemu_map_ram_ptr(mr->ram_block, addr1); -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to address_space_map(). Its callers either have an attrs value to hand, or don't care and can use MEMTXATTRS_UNSPECIFIED. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-5-peter.maydell@linaro.org --- include/exec/memory.h | 3 ++- include/sysemu/dma.h | 3 ++- exec.c | 6 ++++-- target/ppc/mmu-hash64.c | 3 ++- 4 files changed, 10 insertions(+), 5 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 @@ bool address_space_access_valid(AddressSpace *as, hwaddr addr, int len, bool is_ * @addr: address within that address space * @plen: pointer to length of buffer; updated on return * @is_write: indicates the transfer direction + * @attrs: memory attributes */ void *address_space_map(AddressSpace *as, hwaddr addr, - hwaddr *plen, bool is_write); + hwaddr *plen, bool is_write, MemTxAttrs attrs); /* address_space_unmap: Unmaps a memory region previously mapped by address_space_map() * diff --git a/include/sysemu/dma.h b/include/sysemu/dma.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/dma.h +++ b/include/sysemu/dma.h @@ -XXX,XX +XXX,XX @@ static inline void *dma_memory_map(AddressSpace *as, hwaddr xlen = *len; void *p; - p = address_space_map(as, addr, &xlen, dir == DMA_DIRECTION_FROM_DEVICE); + p = address_space_map(as, addr, &xlen, dir == DMA_DIRECTION_FROM_DEVICE, + MEMTXATTRS_UNSPECIFIED); *len = xlen; return p; } diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ flatview_extend_translation(FlatView *fv, hwaddr addr, void *address_space_map(AddressSpace *as, hwaddr addr, hwaddr *plen, - bool is_write) + bool is_write, + MemTxAttrs attrs) { hwaddr len = *plen; hwaddr l, xlat; @@ -XXX,XX +XXX,XX @@ void *cpu_physical_memory_map(hwaddr addr, hwaddr *plen, int is_write) { - return address_space_map(&address_space_memory, addr, plen, is_write); + return address_space_map(&address_space_memory, addr, plen, is_write, + MEMTXATTRS_UNSPECIFIED); } void cpu_physical_memory_unmap(void *buffer, hwaddr len, diff --git a/target/ppc/mmu-hash64.c b/target/ppc/mmu-hash64.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/mmu-hash64.c +++ b/target/ppc/mmu-hash64.c @@ -XXX,XX +XXX,XX @@ const ppc_hash_pte64_t *ppc_hash64_map_hptes(PowerPCCPU *cpu, return NULL; } - hptes = address_space_map(CPU(cpu)->as, base + pte_offset, &plen, false); + hptes = address_space_map(CPU(cpu)->as, base + pte_offset, &plen, false, + MEMTXATTRS_UNSPECIFIED); if (plen < (n * HASH_PTE_SIZE_64)) { hw_error("%s: Unable to map all requested HPTEs\n", __func__); } -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to address_space_access_valid(). Its callers either have an attrs value to hand, or don't care and can use MEMTXATTRS_UNSPECIFIED. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-6-peter.maydell@linaro.org --- include/exec/memory.h | 4 +++- include/sysemu/dma.h | 3 ++- exec.c | 3 ++- target/s390x/diag.c | 6 ++++-- target/s390x/excp_helper.c | 3 ++- target/s390x/mmu_helper.c | 3 ++- target/s390x/sigp.c | 3 ++- 7 files changed, 17 insertions(+), 8 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 @@ static inline MemoryRegion *address_space_translate(AddressSpace *as, * @addr: address within that address space * @len: length of the area to be checked * @is_write: indicates the transfer direction + * @attrs: memory attributes */ -bool address_space_access_valid(AddressSpace *as, hwaddr addr, int len, bool is_write); +bool address_space_access_valid(AddressSpace *as, hwaddr addr, int len, + bool is_write, MemTxAttrs attrs); /* address_space_map: map a physical memory region into a host virtual address * diff --git a/include/sysemu/dma.h b/include/sysemu/dma.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/dma.h +++ b/include/sysemu/dma.h @@ -XXX,XX +XXX,XX @@ static inline bool dma_memory_valid(AddressSpace *as, DMADirection dir) { return address_space_access_valid(as, addr, len, - dir == DMA_DIRECTION_FROM_DEVICE); + dir == DMA_DIRECTION_FROM_DEVICE, + MEMTXATTRS_UNSPECIFIED); } static inline int dma_memory_rw_relaxed(AddressSpace *as, dma_addr_t addr, diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, } bool address_space_access_valid(AddressSpace *as, hwaddr addr, - int len, bool is_write) + int len, bool is_write, + MemTxAttrs attrs) { FlatView *fv; bool result; diff --git a/target/s390x/diag.c b/target/s390x/diag.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/diag.c +++ b/target/s390x/diag.c @@ -XXX,XX +XXX,XX @@ void handle_diag_308(CPUS390XState *env, uint64_t r1, uint64_t r3, uintptr_t ra) return; } if (!address_space_access_valid(&address_space_memory, addr, - sizeof(IplParameterBlock), false)) { + sizeof(IplParameterBlock), false, + MEMTXATTRS_UNSPECIFIED)) { s390_program_interrupt(env, PGM_ADDRESSING, ILEN_AUTO, ra); return; } @@ -XXX,XX +XXX,XX @@ out: return; } if (!address_space_access_valid(&address_space_memory, addr, - sizeof(IplParameterBlock), true)) { + sizeof(IplParameterBlock), true, + MEMTXATTRS_UNSPECIFIED)) { s390_program_interrupt(env, PGM_ADDRESSING, ILEN_AUTO, ra); return; } diff --git a/target/s390x/excp_helper.c b/target/s390x/excp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/excp_helper.c +++ b/target/s390x/excp_helper.c @@ -XXX,XX +XXX,XX @@ int s390_cpu_handle_mmu_fault(CPUState *cs, vaddr orig_vaddr, int size, /* check out of RAM access */ if (!address_space_access_valid(&address_space_memory, raddr, - TARGET_PAGE_SIZE, rw)) { + TARGET_PAGE_SIZE, rw, + MEMTXATTRS_UNSPECIFIED)) { DPRINTF("%s: raddr %" PRIx64 " > ram_size %" PRIx64 "\n", __func__, (uint64_t)raddr, (uint64_t)ram_size); trigger_pgm_exception(env, PGM_ADDRESSING, ILEN_AUTO); diff --git a/target/s390x/mmu_helper.c b/target/s390x/mmu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/mmu_helper.c +++ b/target/s390x/mmu_helper.c @@ -XXX,XX +XXX,XX @@ static int translate_pages(S390CPU *cpu, vaddr addr, int nr_pages, return ret; } if (!address_space_access_valid(&address_space_memory, pages[i], - TARGET_PAGE_SIZE, is_write)) { + TARGET_PAGE_SIZE, is_write, + MEMTXATTRS_UNSPECIFIED)) { trigger_access_exception(env, PGM_ADDRESSING, ILEN_AUTO, 0); return -EFAULT; } diff --git a/target/s390x/sigp.c b/target/s390x/sigp.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/sigp.c +++ b/target/s390x/sigp.c @@ -XXX,XX +XXX,XX @@ static void sigp_set_prefix(CPUState *cs, run_on_cpu_data arg) cpu_synchronize_state(cs); if (!address_space_access_valid(&address_space_memory, addr, - sizeof(struct LowCore), false)) { + sizeof(struct LowCore), false, + MEMTXATTRS_UNSPECIFIED)) { set_sigp_status(si, SIGP_STAT_INVALID_PARAMETER); return; } -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to flatview_extend_translation(). Its callers either have an attrs value to hand, or don't care and can use MEMTXATTRS_UNSPECIFIED. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-7-peter.maydell@linaro.org --- exec.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ bool address_space_access_valid(AddressSpace *as, hwaddr addr, static hwaddr flatview_extend_translation(FlatView *fv, hwaddr addr, - hwaddr target_len, - MemoryRegion *mr, hwaddr base, hwaddr len, - bool is_write) + hwaddr target_len, + MemoryRegion *mr, hwaddr base, hwaddr len, + bool is_write, MemTxAttrs attrs) { hwaddr done = 0; hwaddr xlat; @@ -XXX,XX +XXX,XX @@ void *address_space_map(AddressSpace *as, memory_region_ref(mr); *plen = flatview_extend_translation(fv, addr, len, mr, xlat, - l, is_write); + l, is_write, attrs); ptr = qemu_ram_ptr_length(mr->ram_block, xlat, plen, true); rcu_read_unlock(); @@ -XXX,XX +XXX,XX @@ int64_t address_space_cache_init(MemoryRegionCache *cache, mr = cache->mrs.mr; memory_region_ref(mr); if (memory_access_is_direct(mr, is_write)) { + /* We don't care about the memory attributes here as we're only + * doing this if we found actual RAM, which behaves the same + * regardless of attributes; so UNSPECIFIED is fine. + */ l = flatview_extend_translation(cache->fv, addr, len, mr, - cache->xlat, l, is_write); + cache->xlat, l, is_write, + MEMTXATTRS_UNSPECIFIED); cache->ptr = qemu_ram_ptr_length(mr->ram_block, cache->xlat, &l, true); } else { cache->ptr = NULL; -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to memory_region_access_valid(). Its callers either have an attrs value to hand, or don't care and can use MEMTXATTRS_UNSPECIFIED. The callsite in flatview_access_valid() is part of a recursive loop flatview_access_valid() -> memory_region_access_valid() -> subpage_accepts() -> flatview_access_valid(); we make it pass MEMTXATTRS_UNSPECIFIED for now, until the next several commits have plumbed an attrs parameter through the rest of the loop and we can add an attrs parameter to flatview_access_valid(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-8-peter.maydell@linaro.org --- include/exec/memory-internal.h | 3 ++- exec.c | 4 +++- hw/s390x/s390-pci-inst.c | 3 ++- memory.c | 7 ++++--- 4 files changed, 11 insertions(+), 6 deletions(-) diff --git a/include/exec/memory-internal.h b/include/exec/memory-internal.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memory-internal.h +++ b/include/exec/memory-internal.h @@ -XXX,XX +XXX,XX @@ void flatview_unref(FlatView *view); extern const MemoryRegionOps unassigned_mem_ops; bool memory_region_access_valid(MemoryRegion *mr, hwaddr addr, - unsigned size, bool is_write); + unsigned size, bool is_write, + MemTxAttrs attrs); void flatview_add_to_dispatch(FlatView *fv, MemoryRegionSection *section); AddressSpaceDispatch *address_space_dispatch_new(FlatView *fv); diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, mr = flatview_translate(fv, addr, &xlat, &l, is_write); if (!memory_access_is_direct(mr, is_write)) { l = memory_access_size(mr, l, addr); - if (!memory_region_access_valid(mr, xlat, l, is_write)) { + /* When our callers all have attrs we'll pass them through here */ + if (!memory_region_access_valid(mr, xlat, l, is_write, + MEMTXATTRS_UNSPECIFIED)) { return false; } } 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 @@ int pcistb_service_call(S390CPU *cpu, uint8_t r1, uint8_t r3, uint64_t gaddr, mr = s390_get_subregion(mr, offset, len); offset -= mr->addr; - if (!memory_region_access_valid(mr, offset, len, true)) { + if (!memory_region_access_valid(mr, offset, len, true, + MEMTXATTRS_UNSPECIFIED)) { s390_program_interrupt(env, PGM_OPERAND, 6, ra); return 0; } diff --git a/memory.c b/memory.c index XXXXXXX..XXXXXXX 100644 --- a/memory.c +++ b/memory.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps ram_device_mem_ops = { bool memory_region_access_valid(MemoryRegion *mr, hwaddr addr, unsigned size, - bool is_write) + bool is_write, + MemTxAttrs attrs) { int access_size_min, access_size_max; int access_size, i; @@ -XXX,XX +XXX,XX @@ MemTxResult memory_region_dispatch_read(MemoryRegion *mr, { MemTxResult r; - if (!memory_region_access_valid(mr, addr, size, false)) { + if (!memory_region_access_valid(mr, addr, size, false, attrs)) { *pval = unassigned_mem_read(mr, addr, size); return MEMTX_DECODE_ERROR; } @@ -XXX,XX +XXX,XX @@ MemTxResult memory_region_dispatch_write(MemoryRegion *mr, unsigned size, MemTxAttrs attrs) { - if (!memory_region_access_valid(mr, addr, size, true)) { + if (!memory_region_access_valid(mr, addr, size, true, attrs)) { unassigned_mem_write(mr, addr, data, size); return MEMTX_DECODE_ERROR; } -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to the MemoryRegion valid.accepts callback. We'll need this for subpage_accepts(). We could take the approach we used with the read and write callbacks and add new a new _with_attrs version, but since there are so few implementations of the accepts hook we just change them all. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-9-peter.maydell@linaro.org --- include/exec/memory.h | 3 ++- exec.c | 9 ++++++--- hw/hppa/dino.c | 3 ++- hw/nvram/fw_cfg.c | 12 ++++++++---- hw/scsi/esp.c | 3 ++- hw/xen/xen_pt_msi.c | 3 ++- memory.c | 5 +++-- 7 files changed, 25 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 @@ struct MemoryRegionOps { * as a machine check exception). */ bool (*accepts)(void *opaque, hwaddr addr, - unsigned size, bool is_write); + unsigned size, bool is_write, + MemTxAttrs attrs); } valid; /* Internal implementation constraints: */ struct { 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, } static bool notdirty_mem_accepts(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return is_write; } @@ -XXX,XX +XXX,XX @@ static MemTxResult subpage_write(void *opaque, hwaddr addr, } static bool subpage_accepts(void *opaque, hwaddr addr, - unsigned len, bool is_write) + unsigned len, bool is_write, + MemTxAttrs attrs) { subpage_t *subpage = opaque; #if defined(DEBUG_SUBPAGE) @@ -XXX,XX +XXX,XX @@ static void readonly_mem_write(void *opaque, hwaddr addr, } static bool readonly_mem_accepts(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return is_write; } diff --git a/hw/hppa/dino.c b/hw/hppa/dino.c index XXXXXXX..XXXXXXX 100644 --- a/hw/hppa/dino.c +++ b/hw/hppa/dino.c @@ -XXX,XX +XXX,XX @@ static void gsc_to_pci_forwarding(DinoState *s) } static bool dino_chip_mem_valid(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { switch (addr) { case DINO_IAR0: diff --git a/hw/nvram/fw_cfg.c b/hw/nvram/fw_cfg.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/fw_cfg.c +++ b/hw/nvram/fw_cfg.c @@ -XXX,XX +XXX,XX @@ static void fw_cfg_dma_mem_write(void *opaque, hwaddr addr, } static bool fw_cfg_dma_mem_valid(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return !is_write || ((size == 4 && (addr == 0 || addr == 4)) || (size == 8 && addr == 0)); } static bool fw_cfg_data_mem_valid(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return addr == 0; } @@ -XXX,XX +XXX,XX @@ static void fw_cfg_ctl_mem_write(void *opaque, hwaddr addr, } static bool fw_cfg_ctl_mem_valid(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return is_write && size == 2; } @@ -XXX,XX +XXX,XX @@ static void fw_cfg_comb_write(void *opaque, hwaddr addr, } static bool fw_cfg_comb_valid(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return (size == 1) || (is_write && size == 2); } diff --git a/hw/scsi/esp.c b/hw/scsi/esp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/scsi/esp.c +++ b/hw/scsi/esp.c @@ -XXX,XX +XXX,XX @@ void esp_reg_write(ESPState *s, uint32_t saddr, uint64_t val) } static bool esp_mem_accepts(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return (size == 1) || (is_write && size == 4); } diff --git a/hw/xen/xen_pt_msi.c b/hw/xen/xen_pt_msi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/xen/xen_pt_msi.c +++ b/hw/xen/xen_pt_msi.c @@ -XXX,XX +XXX,XX @@ static uint64_t pci_msix_read(void *opaque, hwaddr addr, } static bool pci_msix_accepts(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return !(addr & (size - 1)); } diff --git a/memory.c b/memory.c index XXXXXXX..XXXXXXX 100644 --- a/memory.c +++ b/memory.c @@ -XXX,XX +XXX,XX @@ static void unassigned_mem_write(void *opaque, hwaddr addr, } static bool unassigned_mem_accepts(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return false; } @@ -XXX,XX +XXX,XX @@ bool memory_region_access_valid(MemoryRegion *mr, access_size = MAX(MIN(size, access_size_max), access_size_min); for (i = 0; i < size; i += access_size) { if (!mr->ops->valid.accepts(mr->opaque, addr + i, access_size, - is_write)) { + is_write, attrs)) { return false; } } -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to flatview_access_valid(). Its callers now all have an attrs value to hand, so we can correct our earlier temporary use of MEMTXATTRS_UNSPECIFIED. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-10-peter.maydell@linaro.org --- exec.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static MemTxResult flatview_read(FlatView *fv, hwaddr addr, static MemTxResult flatview_write(FlatView *fv, hwaddr addr, MemTxAttrs attrs, const uint8_t *buf, int len); static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, - bool is_write); + bool is_write, MemTxAttrs attrs); static MemTxResult subpage_read(void *opaque, hwaddr addr, uint64_t *data, unsigned len, MemTxAttrs attrs) @@ -XXX,XX +XXX,XX @@ static bool subpage_accepts(void *opaque, hwaddr addr, #endif return flatview_access_valid(subpage->fv, addr + subpage->base, - len, is_write); + len, is_write, attrs); } static const MemoryRegionOps subpage_ops = { @@ -XXX,XX +XXX,XX @@ static void cpu_notify_map_clients(void) } static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, - bool is_write) + bool is_write, MemTxAttrs attrs) { MemoryRegion *mr; hwaddr l, xlat; @@ -XXX,XX +XXX,XX @@ static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, mr = flatview_translate(fv, addr, &xlat, &l, is_write); if (!memory_access_is_direct(mr, is_write)) { l = memory_access_size(mr, l, addr); - /* When our callers all have attrs we'll pass them through here */ - if (!memory_region_access_valid(mr, xlat, l, is_write, - MEMTXATTRS_UNSPECIFIED)) { + if (!memory_region_access_valid(mr, xlat, l, is_write, attrs)) { return false; } } @@ -XXX,XX +XXX,XX @@ bool address_space_access_valid(AddressSpace *as, hwaddr addr, rcu_read_lock(); fv = address_space_to_flatview(as); - result = flatview_access_valid(fv, addr, len, is_write); + result = flatview_access_valid(fv, addr, len, is_write, attrs); rcu_read_unlock(); return result; } -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to flatview_translate(); all its callers now have attrs available. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-11-peter.maydell@linaro.org --- include/exec/memory.h | 7 ++++--- exec.c | 17 +++++++++-------- 2 files changed, 13 insertions(+), 11 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 @@ IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr, */ MemoryRegion *flatview_translate(FlatView *fv, hwaddr addr, hwaddr *xlat, - hwaddr *len, bool is_write); + hwaddr *len, bool is_write, + MemTxAttrs attrs); static inline MemoryRegion *address_space_translate(AddressSpace *as, hwaddr addr, hwaddr *xlat, @@ -XXX,XX +XXX,XX @@ static inline MemoryRegion *address_space_translate(AddressSpace *as, MemTxAttrs attrs) { return flatview_translate(address_space_to_flatview(as), - addr, xlat, len, is_write); + addr, xlat, len, is_write, attrs); } /* address_space_access_valid: check for validity of accessing an address @@ -XXX,XX +XXX,XX @@ MemTxResult address_space_read(AddressSpace *as, hwaddr addr, rcu_read_lock(); fv = address_space_to_flatview(as); l = len; - mr = flatview_translate(fv, addr, &addr1, &l, false); + mr = flatview_translate(fv, addr, &addr1, &l, false, attrs); if (len == l && memory_access_is_direct(mr, false)) { ptr = qemu_map_ram_ptr(mr->ram_block, addr1); memcpy(buf, ptr, len); diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ iotlb_fail: /* Called from RCU critical section */ MemoryRegion *flatview_translate(FlatView *fv, hwaddr addr, hwaddr *xlat, - hwaddr *plen, bool is_write) + hwaddr *plen, bool is_write, + MemTxAttrs attrs) { MemoryRegion *mr; MemoryRegionSection section; @@ -XXX,XX +XXX,XX @@ static MemTxResult flatview_write_continue(FlatView *fv, hwaddr addr, } l = len; - mr = flatview_translate(fv, addr, &addr1, &l, true); + mr = flatview_translate(fv, addr, &addr1, &l, true, attrs); } return result; @@ -XXX,XX +XXX,XX @@ static MemTxResult flatview_write(FlatView *fv, hwaddr addr, MemTxAttrs attrs, MemTxResult result = MEMTX_OK; l = len; - mr = flatview_translate(fv, addr, &addr1, &l, true); + mr = flatview_translate(fv, addr, &addr1, &l, true, attrs); result = flatview_write_continue(fv, addr, attrs, buf, len, addr1, l, mr); @@ -XXX,XX +XXX,XX @@ MemTxResult flatview_read_continue(FlatView *fv, hwaddr addr, } l = len; - mr = flatview_translate(fv, addr, &addr1, &l, false); + mr = flatview_translate(fv, addr, &addr1, &l, false, attrs); } return result; @@ -XXX,XX +XXX,XX @@ static MemTxResult flatview_read(FlatView *fv, hwaddr addr, MemoryRegion *mr; l = len; - mr = flatview_translate(fv, addr, &addr1, &l, false); + mr = flatview_translate(fv, addr, &addr1, &l, false, attrs); return flatview_read_continue(fv, addr, attrs, buf, len, addr1, l, mr); } @@ -XXX,XX +XXX,XX @@ static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, while (len > 0) { l = len; - mr = flatview_translate(fv, addr, &xlat, &l, is_write); + mr = flatview_translate(fv, addr, &xlat, &l, is_write, attrs); if (!memory_access_is_direct(mr, is_write)) { l = memory_access_size(mr, l, addr); if (!memory_region_access_valid(mr, xlat, l, is_write, attrs)) { @@ -XXX,XX +XXX,XX @@ flatview_extend_translation(FlatView *fv, hwaddr addr, len = target_len; this_mr = flatview_translate(fv, addr, &xlat, - &len, is_write); + &len, is_write, attrs); if (this_mr != mr || xlat != base + done) { return done; } @@ -XXX,XX +XXX,XX @@ void *address_space_map(AddressSpace *as, l = len; rcu_read_lock(); fv = address_space_to_flatview(as); - mr = flatview_translate(fv, addr, &xlat, &l, is_write); + mr = flatview_translate(fv, addr, &xlat, &l, is_write, attrs); if (!memory_access_is_direct(mr, is_write)) { if (atomic_xchg(&bounce.in_use, true)) { -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to address_space_get_iotlb_entry(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-12-peter.maydell@linaro.org --- include/exec/memory.h | 2 +- exec.c | 2 +- hw/virtio/vhost.c | 3 ++- 3 files changed, 4 insertions(+), 3 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 @@ void address_space_cache_destroy(MemoryRegionCache *cache); * entry. Should be called from an RCU critical section. */ IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr, - bool is_write); + bool is_write, MemTxAttrs attrs); /* address_space_translate: translate an address range into an address space * into a MemoryRegion and an address range into that section. Should be diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static MemoryRegionSection flatview_do_translate(FlatView *fv, /* Called from RCU critical section */ IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr, - bool is_write) + bool is_write, MemTxAttrs attrs) { MemoryRegionSection section; hwaddr xlat, page_mask; 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 @@ int vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write) trace_vhost_iotlb_miss(dev, 1); iotlb = address_space_get_iotlb_entry(dev->vdev->dma_as, - iova, write); + iova, write, + MEMTXATTRS_UNSPECIFIED); if (iotlb.target_as != NULL) { ret = vhost_memory_region_lookup(dev, iotlb.translated_addr, &uaddr, &len); -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to flatview_do_translate(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-13-peter.maydell@linaro.org --- exec.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ unassigned: * @is_write: whether the translation operation is for write * @is_mmio: whether this can be MMIO, set true if it can * @target_as: the address space targeted by the IOMMU + * @attrs: memory transaction attributes * * This function is called from RCU critical section */ @@ -XXX,XX +XXX,XX @@ static MemoryRegionSection flatview_do_translate(FlatView *fv, hwaddr *page_mask_out, bool is_write, bool is_mmio, - AddressSpace **target_as) + AddressSpace **target_as, + MemTxAttrs attrs) { MemoryRegionSection *section; IOMMUMemoryRegion *iommu_mr; @@ -XXX,XX +XXX,XX @@ IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr, * but page mask. */ section = flatview_do_translate(address_space_to_flatview(as), addr, &xlat, - NULL, &page_mask, is_write, false, &as); + NULL, &page_mask, is_write, false, &as, + attrs); /* Illegal translation */ if (section.mr == &io_mem_unassigned) { @@ -XXX,XX +XXX,XX @@ MemoryRegion *flatview_translate(FlatView *fv, hwaddr addr, hwaddr *xlat, /* This can be MMIO, so setup MMIO bit. */ section = flatview_do_translate(fv, addr, xlat, plen, NULL, - is_write, true, &as); + is_write, true, &as, attrs); mr = section.mr; if (xen_enabled() && memory_access_is_direct(mr, is_write)) { -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to address_space_translate_iommu(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-14-peter.maydell@linaro.org --- exec.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ address_space_translate_internal(AddressSpaceDispatch *d, hwaddr addr, hwaddr *x * @is_write: whether the translation operation is for write * @is_mmio: whether this can be MMIO, set true if it can * @target_as: the address space targeted by the IOMMU + * @attrs: transaction attributes * * This function is called from RCU critical section. It is the common * part of flatview_do_translate and address_space_translate_cached. @@ -XXX,XX +XXX,XX @@ static MemoryRegionSection address_space_translate_iommu(IOMMUMemoryRegion *iomm hwaddr *page_mask_out, bool is_write, bool is_mmio, - AddressSpace **target_as) + AddressSpace **target_as, + MemTxAttrs attrs) { MemoryRegionSection *section; hwaddr page_mask = (hwaddr)-1; @@ -XXX,XX +XXX,XX @@ static MemoryRegionSection flatview_do_translate(FlatView *fv, return address_space_translate_iommu(iommu_mr, xlat, plen_out, page_mask_out, is_write, is_mmio, - target_as); + target_as, attrs); } if (page_mask_out) { /* Not behind an IOMMU, use default page size. */ @@ -XXX,XX +XXX,XX @@ static inline MemoryRegion *address_space_translate_cached( section = address_space_translate_iommu(iommu_mr, xlat, plen, NULL, is_write, true, - &target_as); + &target_as, attrs); return section.mr; } -- 2.17.1 Provide a VMSTATE_BOOL_SUB_ARRAY to go with VMSTATE_UINT8_SUB_ARRAY and friends. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180521140402.23318-23-peter.maydell@linaro.org --- include/migration/vmstate.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h index XXXXXXX..XXXXXXX 100644 --- a/include/migration/vmstate.h +++ b/include/migration/vmstate.h @@ -XXX,XX +XXX,XX @@ extern const VMStateInfo vmstate_info_qtailq; #define VMSTATE_BOOL_ARRAY(_f, _s, _n) \ VMSTATE_BOOL_ARRAY_V(_f, _s, _n, 0) +#define VMSTATE_BOOL_SUB_ARRAY(_f, _s, _start, _num) \ + VMSTATE_SUB_ARRAY(_f, _s, _start, _num, 0, vmstate_info_bool, bool) + #define VMSTATE_UINT16_ARRAY_V(_f, _s, _n, _v) \ VMSTATE_ARRAY(_f, _s, _n, _v, vmstate_info_uint16, uint16_t) -- 2.17.1 From: Shannon Zhao <zhaoshenglong@huawei.com> acpi_data_push uses g_array_set_size to resize the memory size. If there is no enough contiguous memory, the address will be changed. So previous pointer could not be used any more. It must update the pointer and use the new one. Also, previous codes wrongly use le32 conversion of iort->node_offset for subsequent computations that will result incorrect value if host is not litlle endian. So use the non-converted one instead. Signed-off-by: Shannon Zhao <zhaoshenglong@huawei.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 1527663951-14552-1-git-send-email-zhaoshenglong@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt-acpi-build.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -XXX,XX +XXX,XX @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) AcpiIortItsGroup *its; AcpiIortTable *iort; AcpiIortSmmu3 *smmu; - size_t node_size, iort_length, smmu_offset = 0; + size_t node_size, iort_node_offset, iort_length, smmu_offset = 0; AcpiIortRC *rc; iort = acpi_data_push(table_data, sizeof(*iort)); @@ -XXX,XX +XXX,XX @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) iort_length = sizeof(*iort); iort->node_count = cpu_to_le32(nb_nodes); - iort->node_offset = cpu_to_le32(sizeof(*iort)); + /* + * Use a copy in case table_data->data moves during acpi_data_push + * operations. + */ + iort_node_offset = sizeof(*iort); + iort->node_offset = cpu_to_le32(iort_node_offset); /* ITS group node */ node_size = sizeof(*its) + sizeof(uint32_t); @@ -XXX,XX +XXX,XX @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) int irq = vms->irqmap[VIRT_SMMU]; /* SMMUv3 node */ - smmu_offset = iort->node_offset + node_size; + smmu_offset = iort_node_offset + node_size; node_size = sizeof(*smmu) + sizeof(*idmap); iort_length += node_size; smmu = acpi_data_push(table_data, node_size); @@ -XXX,XX +XXX,XX @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) idmap->id_count = cpu_to_le32(0xFFFF); idmap->output_base = 0; /* output IORT node is the ITS group node (the first node) */ - idmap->output_reference = cpu_to_le32(iort->node_offset); + idmap->output_reference = cpu_to_le32(iort_node_offset); } /* Root Complex Node */ @@ -XXX,XX +XXX,XX @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) idmap->output_reference = cpu_to_le32(smmu_offset); } else { /* output IORT node is the ITS group node (the first node) */ - idmap->output_reference = cpu_to_le32(iort->node_offset); + idmap->output_reference = cpu_to_le32(iort_node_offset); } + /* + * Update the pointer address in case table_data->data moves during above + * acpi_data_push operations. + */ + iort = (AcpiIortTable *)(table_data->data + iort_start); iort->length = cpu_to_le32(iort_length); build_header(linker, table_data, (void *)(table_data->data + iort_start), -- 2.17.1 From: Shannon Zhao <zhaoshenglong@huawei.com> kvm_irqchip_create called by kvm_init will call kvm_init_irq_routing to initialize global capability variables. If we call kvm_init_irq_routing in GIC realize function, previous allocated memory will leak. Fix this by deleting the unnecessary call. Signed-off-by: Shannon Zhao <zhaoshenglong@huawei.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 1527750994-14360-1-git-send-email-zhaoshenglong@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gic_kvm.c | 1 - hw/intc/arm_gicv3_kvm.c | 1 - 2 files changed, 2 deletions(-) diff --git a/hw/intc/arm_gic_kvm.c b/hw/intc/arm_gic_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gic_kvm.c +++ b/hw/intc/arm_gic_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gic_realize(DeviceState *dev, Error **errp) if (kvm_has_gsi_routing()) { /* set up irq routing */ - kvm_init_irq_routing(kvm_state); for (i = 0; i < s->num_irq - GIC_INTERNAL; ++i) { kvm_irqchip_add_irq_route(kvm_state, i, 0, i); } 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_arm_gicv3_realize(DeviceState *dev, Error **errp) if (kvm_has_gsi_routing()) { /* set up irq routing */ - kvm_init_irq_routing(kvm_state); for (i = 0; i < s->num_irq - GIC_INTERNAL; ++i) { kvm_irqchip_add_irq_route(kvm_state, i, 0, i); } -- 2.17.1