The following changes since commit eae587e8e3694b1aceab23239493fb4c7e1a80f5: Merge remote-tracking branch 'remotes/armbru/tags/pull-qapi-2021-09-13' into staging (2021-09-13 11:00:30 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210913 for you to fetch changes up to 9a2b2ecf4d25a3943918c95d2db4508b304161b5: hw/arm/mps2.c: Mark internal-only I2C buses as 'full' (2021-09-13 17:09:28 +0100) ---------------------------------------------------------------- target-arm queue: * mark MPS2/MPS3 board-internal i2c buses as 'full' so that command line user-created devices are not plugged into them * Take an exception if PSTATE.IL is set * Support an emulated ITS in the virt board * Add support for kudo-bmc board * Probe for KVM_CAP_ARM_VM_IPA_SIZE when creating scratch VM * cadence_uart: Fix clock handling issues that prevented u-boot from running ---------------------------------------------------------------- Bin Meng (6): hw/misc: zynq_slcr: Correctly compute output clocks in the reset exit phase hw/char: cadence_uart: Disable transmit when input clock is disabled hw/char: cadence_uart: Move clock/reset check to uart_can_receive() hw/char: cadence_uart: Convert to memop_with_attrs() ops hw/char: cadence_uart: Ignore access when unclocked or in reset for uart_{read, write}() hw/char: cadence_uart: Log a guest error when device is unclocked or in reset Chris Rauer (1): hw/arm: Add support for kudo-bmc board. Marc Zyngier (1): hw/arm/virt: KVM: Probe for KVM_CAP_ARM_VM_IPA_SIZE when creating scratch VM Peter Maydell (5): target/arm: Take an exception if PSTATE.IL is set qdev: Support marking individual buses as 'full' hw/arm/mps2-tz.c: Add extra data parameter to MakeDevFn hw/arm/mps2-tz.c: Mark internal-only I2C buses as 'full' hw/arm/mps2.c: Mark internal-only I2C buses as 'full' Richard Henderson (1): target/arm: Merge disas_a64_insn into aarch64_tr_translate_insn Shashi Mallela (9): hw/intc: GICv3 ITS initial framework hw/intc: GICv3 ITS register definitions added hw/intc: GICv3 ITS command queue framework hw/intc: GICv3 ITS Command processing hw/intc: GICv3 ITS Feature enablement hw/intc: GICv3 redistributor ITS processing tests/data/acpi/virt: Add IORT files for ITS hw/arm/virt: add ITS support in virt GIC tests/data/acpi/virt: Update IORT files for ITS docs/system/arm/nuvoton.rst | 1 + hw/intc/gicv3_internal.h | 188 ++++- include/hw/arm/virt.h | 2 + include/hw/intc/arm_gicv3_common.h | 13 + include/hw/intc/arm_gicv3_its_common.h | 32 +- include/hw/qdev-core.h | 24 + target/arm/cpu.h | 1 + target/arm/kvm_arm.h | 4 +- target/arm/syndrome.h | 5 + target/arm/translate.h | 2 + hw/arm/mps2-tz.c | 92 ++- hw/arm/mps2.c | 12 +- hw/arm/npcm7xx_boards.c | 34 + hw/arm/virt.c | 29 +- hw/char/cadence_uart.c | 61 +- hw/intc/arm_gicv3.c | 14 + hw/intc/arm_gicv3_common.c | 13 + hw/intc/arm_gicv3_cpuif.c | 7 +- hw/intc/arm_gicv3_dist.c | 5 +- hw/intc/arm_gicv3_its.c | 1322 ++++++++++++++++++++++++++++++++ hw/intc/arm_gicv3_its_common.c | 7 +- hw/intc/arm_gicv3_its_kvm.c | 2 +- hw/intc/arm_gicv3_redist.c | 153 +++- hw/misc/zynq_slcr.c | 31 +- softmmu/qdev-monitor.c | 7 +- target/arm/helper-a64.c | 1 + target/arm/helper.c | 8 + target/arm/kvm.c | 7 +- target/arm/translate-a64.c | 255 +++--- target/arm/translate.c | 21 + hw/intc/meson.build | 1 + tests/data/acpi/virt/IORT | Bin 0 -> 124 bytes tests/data/acpi/virt/IORT.memhp | Bin 0 -> 124 bytes tests/data/acpi/virt/IORT.numamem | Bin 0 -> 124 bytes tests/data/acpi/virt/IORT.pxb | Bin 0 -> 124 bytes 35 files changed, 2144 insertions(+), 210 deletions(-) create mode 100644 hw/intc/arm_gicv3_its.c create mode 100644 tests/data/acpi/virt/IORT create mode 100644 tests/data/acpi/virt/IORT.memhp create mode 100644 tests/data/acpi/virt/IORT.numamem create mode 100644 tests/data/acpi/virt/IORT.pxb From: Bin Meng <bmeng.cn@gmail.com> As of today, when booting upstream U-Boot for Xilinx Zynq, the UART does not receive anything. Debugging shows that the UART input clock frequency is zero which prevents the UART from receiving anything as per the logic in uart_receive(). From zynq_slcr_reset_exit() comment, it intends to compute output clocks according to ps_clk and registers. zynq_slcr_compute_clocks() is called to accomplish the task, inside which device_is_in_reset() is called to actually make the attempt in vain. Rework reset_hold() and reset_exit() so that in the reset exit phase, the logic can really compute output clocks in reset_exit(). With this change, upstream U-Boot boots properly again with: $ qemu-system-arm -M xilinx-zynq-a9 -m 1G -display none -serial null -serial stdio \ -device loader,file=u-boot-dtb.bin,addr=0x4000000,cpu-num=0 Fixes: 38867cb7ec90 ("hw/misc/zynq_slcr: add clock generation for uarts") Signed-off-by: Bin Meng <bmeng.cn@gmail.com> Acked-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20210901124521.30599-2-bmeng.cn@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/zynq_slcr.c | 31 ++++++++++++++++++------------- 1 file changed, 18 insertions(+), 13 deletions(-) diff --git a/hw/misc/zynq_slcr.c b/hw/misc/zynq_slcr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/zynq_slcr.c +++ b/hw/misc/zynq_slcr.c @@ -XXX,XX +XXX,XX @@ static uint64_t zynq_slcr_compute_clock(const uint64_t periods[], zynq_slcr_compute_clock((plls), (state)->regs[reg], \ reg ## _ ## enable_field ## _SHIFT) +static void zynq_slcr_compute_clocks_internal(ZynqSLCRState *s, uint64_t ps_clk) +{ + uint64_t io_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_IO_PLL_CTRL]); + uint64_t arm_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_ARM_PLL_CTRL]); + uint64_t ddr_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_DDR_PLL_CTRL]); + + uint64_t uart_mux[4] = {io_pll, io_pll, arm_pll, ddr_pll}; + + /* compute uartX reference clocks */ + clock_set(s->uart0_ref_clk, + ZYNQ_COMPUTE_CLK(s, uart_mux, R_UART_CLK_CTRL, CLKACT0)); + clock_set(s->uart1_ref_clk, + ZYNQ_COMPUTE_CLK(s, uart_mux, R_UART_CLK_CTRL, CLKACT1)); +} + /** * Compute and set the ouputs clocks periods. * But do not propagate them further. Connected clocks @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_compute_clocks(ZynqSLCRState *s) ps_clk = 0; } - uint64_t io_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_IO_PLL_CTRL]); - uint64_t arm_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_ARM_PLL_CTRL]); - uint64_t ddr_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_DDR_PLL_CTRL]); - - uint64_t uart_mux[4] = {io_pll, io_pll, arm_pll, ddr_pll}; - - /* compute uartX reference clocks */ - clock_set(s->uart0_ref_clk, - ZYNQ_COMPUTE_CLK(s, uart_mux, R_UART_CLK_CTRL, CLKACT0)); - clock_set(s->uart1_ref_clk, - ZYNQ_COMPUTE_CLK(s, uart_mux, R_UART_CLK_CTRL, CLKACT1)); + zynq_slcr_compute_clocks_internal(s, ps_clk); } /** @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_reset_hold(Object *obj) ZynqSLCRState *s = ZYNQ_SLCR(obj); /* will disable all output clocks */ - zynq_slcr_compute_clocks(s); + zynq_slcr_compute_clocks_internal(s, 0); zynq_slcr_propagate_clocks(s); } @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_reset_exit(Object *obj) ZynqSLCRState *s = ZYNQ_SLCR(obj); /* will compute output clocks according to ps_clk and registers */ - zynq_slcr_compute_clocks(s); + zynq_slcr_compute_clocks_internal(s, clock_get(s->ps_clk)); zynq_slcr_propagate_clocks(s); } -- 2.20.1 From: Bin Meng <bmeng.cn@gmail.com> At present when input clock is disabled, any character transmitted to tx fifo can still show on the serial line, which is wrong. Fixes: b636db306e06 ("hw/char/cadence_uart: add clock support") Signed-off-by: Bin Meng <bmeng.cn@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20210901124521.30599-3-bmeng.cn@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/cadence_uart.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/hw/char/cadence_uart.c b/hw/char/cadence_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/cadence_uart.c +++ b/hw/char/cadence_uart.c @@ -XXX,XX +XXX,XX @@ static gboolean cadence_uart_xmit(void *do_not_use, GIOCondition cond, static void uart_write_tx_fifo(CadenceUARTState *s, const uint8_t *buf, int size) { + /* ignore characters when unclocked or in reset */ + if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + return; + } + if ((s->r[R_CR] & UART_CR_TX_DIS) || !(s->r[R_CR] & UART_CR_TX_EN)) { return; } -- 2.20.1 From: Bin Meng <bmeng.cn@gmail.com> Currently the clock/reset check is done in uart_receive(), but we can move the check to uart_can_receive() which is earlier. Signed-off-by: Bin Meng <bmeng.cn@gmail.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20210901124521.30599-4-bmeng.cn@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/cadence_uart.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/hw/char/cadence_uart.c b/hw/char/cadence_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/cadence_uart.c +++ b/hw/char/cadence_uart.c @@ -XXX,XX +XXX,XX @@ static void uart_parameters_setup(CadenceUARTState *s) static int uart_can_receive(void *opaque) { CadenceUARTState *s = opaque; - int ret = MAX(CADENCE_UART_RX_FIFO_SIZE, CADENCE_UART_TX_FIFO_SIZE); - uint32_t ch_mode = s->r[R_MR] & UART_MR_CHMODE; + int ret; + uint32_t ch_mode; + + /* ignore characters when unclocked or in reset */ + if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + return 0; + } + + ret = MAX(CADENCE_UART_RX_FIFO_SIZE, CADENCE_UART_TX_FIFO_SIZE); + ch_mode = s->r[R_MR] & UART_MR_CHMODE; if (ch_mode == NORMAL_MODE || ch_mode == ECHO_MODE) { ret = MIN(ret, CADENCE_UART_RX_FIFO_SIZE - s->rx_count); @@ -XXX,XX +XXX,XX @@ static void uart_receive(void *opaque, const uint8_t *buf, int size) CadenceUARTState *s = opaque; uint32_t ch_mode = s->r[R_MR] & UART_MR_CHMODE; - /* ignore characters when unclocked or in reset */ - if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { - return; - } - if (ch_mode == NORMAL_MODE || ch_mode == ECHO_MODE) { uart_write_rx_fifo(opaque, buf, size); } -- 2.20.1 From: Bin Meng <bmeng.cn@gmail.com> This converts uart_read() and uart_write() to memop_with_attrs() ops. Signed-off-by: Bin Meng <bmeng.cn@gmail.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20210901124521.30599-5-bmeng.cn@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/cadence_uart.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) diff --git a/hw/char/cadence_uart.c b/hw/char/cadence_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/cadence_uart.c +++ b/hw/char/cadence_uart.c @@ -XXX,XX +XXX,XX @@ static void uart_read_rx_fifo(CadenceUARTState *s, uint32_t *c) uart_update_status(s); } -static void uart_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) +static MemTxResult uart_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size, MemTxAttrs attrs) { CadenceUARTState *s = opaque; DB_PRINT(" offset:%x data:%08x\n", (unsigned)offset, (unsigned)value); offset >>= 2; if (offset >= CADENCE_UART_R_MAX) { - return; + return MEMTX_DECODE_ERROR; } switch (offset) { case R_IER: /* ier (wts imr) */ @@ -XXX,XX +XXX,XX @@ static void uart_write(void *opaque, hwaddr offset, break; } uart_update_status(s); + + return MEMTX_OK; } -static uint64_t uart_read(void *opaque, hwaddr offset, - unsigned size) +static MemTxResult uart_read(void *opaque, hwaddr offset, + uint64_t *value, unsigned size, MemTxAttrs attrs) { CadenceUARTState *s = opaque; uint32_t c = 0; offset >>= 2; if (offset >= CADENCE_UART_R_MAX) { - c = 0; - } else if (offset == R_TX_RX) { + return MEMTX_DECODE_ERROR; + } + if (offset == R_TX_RX) { uart_read_rx_fifo(s, &c); } else { - c = s->r[offset]; + c = s->r[offset]; } DB_PRINT(" offset:%x data:%08x\n", (unsigned)(offset << 2), (unsigned)c); - return c; + *value = c; + return MEMTX_OK; } static const MemoryRegionOps uart_ops = { - .read = uart_read, - .write = uart_write, + .read_with_attrs = uart_read, + .write_with_attrs = uart_write, .endianness = DEVICE_NATIVE_ENDIAN, }; -- 2.20.1 From: Bin Meng <bmeng.cn@gmail.com> Read or write to uart registers when unclocked or in reset should be ignored. Add the check there, and as a result of this, the check in uart_write_tx_fifo() is now unnecessary. Signed-off-by: Bin Meng <bmeng.cn@gmail.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20210901124521.30599-6-bmeng.cn@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/cadence_uart.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/hw/char/cadence_uart.c b/hw/char/cadence_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/cadence_uart.c +++ b/hw/char/cadence_uart.c @@ -XXX,XX +XXX,XX @@ static gboolean cadence_uart_xmit(void *do_not_use, GIOCondition cond, static void uart_write_tx_fifo(CadenceUARTState *s, const uint8_t *buf, int size) { - /* ignore characters when unclocked or in reset */ - if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { - return; - } - if ((s->r[R_CR] & UART_CR_TX_DIS) || !(s->r[R_CR] & UART_CR_TX_EN)) { return; } @@ -XXX,XX +XXX,XX @@ static MemTxResult uart_write(void *opaque, hwaddr offset, { CadenceUARTState *s = opaque; + /* ignore access when unclocked or in reset */ + if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + return MEMTX_ERROR; + } + DB_PRINT(" offset:%x data:%08x\n", (unsigned)offset, (unsigned)value); offset >>= 2; if (offset >= CADENCE_UART_R_MAX) { @@ -XXX,XX +XXX,XX @@ static MemTxResult uart_read(void *opaque, hwaddr offset, CadenceUARTState *s = opaque; uint32_t c = 0; + /* ignore access when unclocked or in reset */ + if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + return MEMTX_ERROR; + } + offset >>= 2; if (offset >= CADENCE_UART_R_MAX) { return MEMTX_DECODE_ERROR; -- 2.20.1 From: Bin Meng <bmeng.cn@gmail.com> We've got SW that expects FSBL (Bootlooader) to setup clocks and resets. It's quite common that users run that SW on QEMU without FSBL (FSBL typically requires the Xilinx tools installed). That's fine, since users can stil use -device loader to enable clocks etc. To help folks understand what's going, a log (guest-error) message would be helpful here. In particular with the serial port since things will go very quiet if they get things wrong. Suggested-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Signed-off-by: Bin Meng <bmeng.cn@gmail.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20210901124521.30599-7-bmeng.cn@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/cadence_uart.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/hw/char/cadence_uart.c b/hw/char/cadence_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/cadence_uart.c +++ b/hw/char/cadence_uart.c @@ -XXX,XX +XXX,XX @@ static int uart_can_receive(void *opaque) /* ignore characters when unclocked or in reset */ if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: uart is unclocked or in reset\n", + __func__); return 0; } @@ -XXX,XX +XXX,XX @@ static void uart_event(void *opaque, QEMUChrEvent event) /* ignore characters when unclocked or in reset */ if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: uart is unclocked or in reset\n", + __func__); return; } @@ -XXX,XX +XXX,XX @@ static MemTxResult uart_write(void *opaque, hwaddr offset, /* ignore access when unclocked or in reset */ if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: uart is unclocked or in reset\n", + __func__); return MEMTX_ERROR; } @@ -XXX,XX +XXX,XX @@ static MemTxResult uart_read(void *opaque, hwaddr offset, /* ignore access when unclocked or in reset */ if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: uart is unclocked or in reset\n", + __func__); return MEMTX_ERROR; } -- 2.20.1 From: Marc Zyngier <maz@kernel.org> Although we probe for the IPA limits imposed by KVM (and the hardware) when computing the memory map, we still use the old style '0' when creating a scratch VM in kvm_arm_create_scratch_host_vcpu(). On systems that are severely IPA challenged (such as the Apple M1), this results in a failure as KVM cannot use the default 40bit that '0' represents. Instead, probe for the extension and use the reported IPA limit if available. Cc: Andrew Jones <drjones@redhat.com> Cc: Eric Auger <eric.auger@redhat.com> Cc: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Marc Zyngier <maz@kernel.org> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20210822144441.1290891-2-maz@kernel.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/target/arm/kvm.c b/target/arm/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -XXX,XX +XXX,XX @@ bool kvm_arm_create_scratch_host_vcpu(const uint32_t *cpus_to_try, struct kvm_vcpu_init *init) { int ret = 0, kvmfd = -1, vmfd = -1, cpufd = -1; + int max_vm_pa_size; kvmfd = qemu_open_old("/dev/kvm", O_RDWR); if (kvmfd < 0) { goto err; } - vmfd = ioctl(kvmfd, KVM_CREATE_VM, 0); + max_vm_pa_size = ioctl(kvmfd, KVM_CHECK_EXTENSION, KVM_CAP_ARM_VM_IPA_SIZE); + if (max_vm_pa_size < 0) { + max_vm_pa_size = 0; + } + vmfd = ioctl(kvmfd, KVM_CREATE_VM, max_vm_pa_size); if (vmfd < 0) { goto err; } -- 2.20.1 From: Chris Rauer <crauer@google.com> kudo-bmc is a board supported by OpenBMC. https://github.com/openbmc/openbmc/tree/master/meta-fii/meta-kudo Since v1: - hyphenated Cortex-A9 Tested: Booted kudo firmware. Signed-off-by: Chris Rauer <crauer@google.com> Reviewed-by: Patrick Venture <venture@google.com> Message-id: 20210907223234.1165705-1-crauer@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/nuvoton.rst | 1 + hw/arm/npcm7xx_boards.c | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+) diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/nuvoton.rst +++ b/docs/system/arm/nuvoton.rst @@ -XXX,XX +XXX,XX @@ Hyperscale applications. The following machines are based on this chip : - ``quanta-gbs-bmc`` Quanta GBS server BMC - ``quanta-gsj`` Quanta GSJ server BMC +- ``kudo-bmc`` Fii USA Kudo server BMC There are also two more SoCs, NPCM710 and NPCM705, which are single-core variants of NPCM750 and NPCM730, respectively. These are currently not diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx_boards.c +++ b/hw/arm/npcm7xx_boards.c @@ -XXX,XX +XXX,XX @@ #define NPCM750_EVB_POWER_ON_STRAPS 0x00001ff7 #define QUANTA_GSJ_POWER_ON_STRAPS 0x00001fff #define QUANTA_GBS_POWER_ON_STRAPS 0x000017ff +#define KUDO_BMC_POWER_ON_STRAPS 0x00001fff static const char npcm7xx_default_bootrom[] = "npcm7xx_bootrom.bin"; @@ -XXX,XX +XXX,XX @@ static void quanta_gbs_init(MachineState *machine) npcm7xx_load_kernel(machine, soc); } +static void kudo_bmc_init(MachineState *machine) +{ + NPCM7xxState *soc; + + soc = npcm7xx_create_soc(machine, KUDO_BMC_POWER_ON_STRAPS); + npcm7xx_connect_dram(soc, machine->ram); + qdev_realize(DEVICE(soc), NULL, &error_fatal); + + npcm7xx_load_bootrom(machine, soc); + npcm7xx_connect_flash(&soc->fiu[0], 0, "mx66u51235f", + drive_get(IF_MTD, 0, 0)); + npcm7xx_connect_flash(&soc->fiu[1], 0, "mx66u51235f", + drive_get(IF_MTD, 3, 0)); + + npcm7xx_load_kernel(machine, soc); +} + static void npcm7xx_set_soc_type(NPCM7xxMachineClass *nmc, const char *type) { NPCM7xxClass *sc = NPCM7XX_CLASS(object_class_by_name(type)); @@ -XXX,XX +XXX,XX @@ static void gbs_bmc_machine_class_init(ObjectClass *oc, void *data) mc->default_ram_size = 1 * GiB; } +static void kudo_bmc_machine_class_init(ObjectClass *oc, void *data) +{ + NPCM7xxMachineClass *nmc = NPCM7XX_MACHINE_CLASS(oc); + MachineClass *mc = MACHINE_CLASS(oc); + + npcm7xx_set_soc_type(nmc, TYPE_NPCM730); + + mc->desc = "Kudo BMC (Cortex-A9)"; + mc->init = kudo_bmc_init; + mc->default_ram_size = 1 * GiB; +}; + static const TypeInfo npcm7xx_machine_types[] = { { .name = TYPE_NPCM7XX_MACHINE, @@ -XXX,XX +XXX,XX @@ static const TypeInfo npcm7xx_machine_types[] = { .name = MACHINE_TYPE_NAME("quanta-gbs-bmc"), .parent = TYPE_NPCM7XX_MACHINE, .class_init = gbs_bmc_machine_class_init, + }, { + .name = MACHINE_TYPE_NAME("kudo-bmc"), + .parent = TYPE_NPCM7XX_MACHINE, + .class_init = kudo_bmc_machine_class_init, }, }; -- 2.20.1 From: Shashi Mallela <shashi.mallela@linaro.org> Added register definitions relevant to ITS,implemented overall ITS device framework with stubs for ITS control and translater regions read/write,extended ITS common to handle mmio init between existing kvm device and newer qemu device. Signed-off-by: Shashi Mallela <shashi.mallela@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested-by: Neil Armstrong <narmstrong@baylibre.com> Message-id: 20210910143951.92242-2-shashi.mallela@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/gicv3_internal.h | 96 +++++++++- include/hw/intc/arm_gicv3_its_common.h | 9 +- hw/intc/arm_gicv3_its.c | 241 +++++++++++++++++++++++++ hw/intc/arm_gicv3_its_common.c | 7 +- hw/intc/arm_gicv3_its_kvm.c | 2 +- hw/intc/meson.build | 1 + 6 files changed, 342 insertions(+), 14 deletions(-) create mode 100644 hw/intc/arm_gicv3_its.c diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ #ifndef QEMU_ARM_GICV3_INTERNAL_H #define QEMU_ARM_GICV3_INTERNAL_H +#include "hw/registerfields.h" #include "hw/intc/arm_gicv3_common.h" /* Distributor registers, as offsets from the distributor base address */ @@ -XXX,XX +XXX,XX @@ #define GICD_CTLR_E1NWF (1U << 7) #define GICD_CTLR_RWP (1U << 31) +/* 16 bits EventId */ +#define GICD_TYPER_IDBITS 0xf + /* * Redistributor frame offsets from RD_base */ @@ -XXX,XX +XXX,XX @@ #define GICR_WAKER_ProcessorSleep (1U << 1) #define GICR_WAKER_ChildrenAsleep (1U << 2) -#define GICR_PROPBASER_OUTER_CACHEABILITY_MASK (7ULL << 56) -#define GICR_PROPBASER_ADDR_MASK (0xfffffffffULL << 12) -#define GICR_PROPBASER_SHAREABILITY_MASK (3U << 10) -#define GICR_PROPBASER_CACHEABILITY_MASK (7U << 7) -#define GICR_PROPBASER_IDBITS_MASK (0x1f) +FIELD(GICR_PROPBASER, IDBITS, 0, 5) +FIELD(GICR_PROPBASER, INNERCACHE, 7, 3) +FIELD(GICR_PROPBASER, SHAREABILITY, 10, 2) +FIELD(GICR_PROPBASER, PHYADDR, 12, 40) +FIELD(GICR_PROPBASER, OUTERCACHE, 56, 3) -#define GICR_PENDBASER_PTZ (1ULL << 62) -#define GICR_PENDBASER_OUTER_CACHEABILITY_MASK (7ULL << 56) -#define GICR_PENDBASER_ADDR_MASK (0xffffffffULL << 16) -#define GICR_PENDBASER_SHAREABILITY_MASK (3U << 10) -#define GICR_PENDBASER_CACHEABILITY_MASK (7U << 7) +FIELD(GICR_PENDBASER, INNERCACHE, 7, 3) +FIELD(GICR_PENDBASER, SHAREABILITY, 10, 2) +FIELD(GICR_PENDBASER, PHYADDR, 16, 36) +FIELD(GICR_PENDBASER, OUTERCACHE, 56, 3) +FIELD(GICR_PENDBASER, PTZ, 62, 1) #define ICC_CTLR_EL1_CBPR (1U << 0) #define ICC_CTLR_EL1_EOIMODE (1U << 1) @@ -XXX,XX +XXX,XX @@ #define ICH_VTR_EL2_PREBITS_SHIFT 26 #define ICH_VTR_EL2_PRIBITS_SHIFT 29 +/* ITS Registers */ + +FIELD(GITS_BASER, SIZE, 0, 8) +FIELD(GITS_BASER, PAGESIZE, 8, 2) +FIELD(GITS_BASER, SHAREABILITY, 10, 2) +FIELD(GITS_BASER, PHYADDR, 12, 36) +FIELD(GITS_BASER, PHYADDRL_64K, 16, 32) +FIELD(GITS_BASER, PHYADDRH_64K, 12, 4) +FIELD(GITS_BASER, ENTRYSIZE, 48, 5) +FIELD(GITS_BASER, OUTERCACHE, 53, 3) +FIELD(GITS_BASER, TYPE, 56, 3) +FIELD(GITS_BASER, INNERCACHE, 59, 3) +FIELD(GITS_BASER, INDIRECT, 62, 1) +FIELD(GITS_BASER, VALID, 63, 1) + +FIELD(GITS_CTLR, QUIESCENT, 31, 1) + +FIELD(GITS_TYPER, PHYSICAL, 0, 1) +FIELD(GITS_TYPER, ITT_ENTRY_SIZE, 4, 4) +FIELD(GITS_TYPER, IDBITS, 8, 5) +FIELD(GITS_TYPER, DEVBITS, 13, 5) +FIELD(GITS_TYPER, SEIS, 18, 1) +FIELD(GITS_TYPER, PTA, 19, 1) +FIELD(GITS_TYPER, CIDBITS, 32, 4) +FIELD(GITS_TYPER, CIL, 36, 1) + +#define GITS_BASER_PAGESIZE_4K 0 +#define GITS_BASER_PAGESIZE_16K 1 +#define GITS_BASER_PAGESIZE_64K 2 + +#define GITS_BASER_TYPE_DEVICE 1ULL +#define GITS_BASER_TYPE_COLLECTION 4ULL + +/** + * Default features advertised by this version of ITS + */ +/* Physical LPIs supported */ +#define GITS_TYPE_PHYSICAL (1U << 0) + +/* + * 12 bytes Interrupt translation Table Entry size + * as per Table 5.3 in GICv3 spec + * ITE Lower 8 Bytes + * Bits: | 49 ... 26 | 25 ... 2 | 1 | 0 | + * Values: | 1023 | IntNum | IntType | Valid | + * ITE Higher 4 Bytes + * Bits: | 31 ... 16 | 15 ...0 | + * Values: | vPEID | ICID | + */ +#define ITS_ITT_ENTRY_SIZE 0xC + +/* 16 bits EventId */ +#define ITS_IDBITS GICD_TYPER_IDBITS + +/* 16 bits DeviceId */ +#define ITS_DEVBITS 0xF + +/* 16 bits CollectionId */ +#define ITS_CIDBITS 0xF + +/* + * 8 bytes Device Table Entry size + * Valid = 1 bit,ITTAddr = 44 bits,Size = 5 bits + */ +#define GITS_DTE_SIZE (0x8ULL) + +/* + * 8 bytes Collection Table Entry size + * Valid = 1 bit,RDBase = 36 bits(considering max RDBASE) + */ +#define GITS_CTE_SIZE (0x8ULL) + /* Special interrupt IDs */ #define INTID_SECURE 1020 #define INTID_NONSECURE 1021 diff --git a/include/hw/intc/arm_gicv3_its_common.h b/include/hw/intc/arm_gicv3_its_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_its_common.h +++ b/include/hw/intc/arm_gicv3_its_common.h @@ -XXX,XX +XXX,XX @@ #include "hw/intc/arm_gicv3_common.h" #include "qom/object.h" +#define TYPE_ARM_GICV3_ITS "arm-gicv3-its" + #define ITS_CONTROL_SIZE 0x10000 #define ITS_TRANS_SIZE 0x10000 #define ITS_SIZE (ITS_CONTROL_SIZE + ITS_TRANS_SIZE) #define GITS_CTLR 0x0 #define GITS_IIDR 0x4 +#define GITS_TYPER 0x8 #define GITS_CBASER 0x80 #define GITS_CWRITER 0x88 #define GITS_CREADR 0x90 #define GITS_BASER 0x100 +#define GITS_TRANSLATER 0x0040 + struct GICv3ITSState { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct GICv3ITSState { /* Registers */ uint32_t ctlr; uint32_t iidr; + uint64_t typer; uint64_t cbaser; uint64_t cwriter; uint64_t creadr; @@ -XXX,XX +XXX,XX @@ struct GICv3ITSState { typedef struct GICv3ITSState GICv3ITSState; -void gicv3_its_init_mmio(GICv3ITSState *s, const MemoryRegionOps *ops); +void gicv3_its_init_mmio(GICv3ITSState *s, const MemoryRegionOps *ops, + const MemoryRegionOps *tops); #define TYPE_ARM_GICV3_ITS_COMMON "arm-gicv3-its-common" typedef struct GICv3ITSCommonClass GICv3ITSCommonClass; diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ +/* + * ITS emulation for a GICv3-based system + * + * Copyright Linaro.org 2021 + * + * Authors: + * Shashi Mallela <shashi.mallela@linaro.org> + * + * This work is licensed under the terms of the GNU GPL, version 2 or (at your + * option) any later version. See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "hw/qdev-properties.h" +#include "hw/intc/arm_gicv3_its_common.h" +#include "gicv3_internal.h" +#include "qom/object.h" +#include "qapi/error.h" + +typedef struct GICv3ITSClass GICv3ITSClass; +/* This is reusing the GICv3ITSState typedef from ARM_GICV3_ITS_COMMON */ +DECLARE_OBJ_CHECKERS(GICv3ITSState, GICv3ITSClass, + ARM_GICV3_ITS, TYPE_ARM_GICV3_ITS) + +struct GICv3ITSClass { + GICv3ITSCommonClass parent_class; + void (*parent_reset)(DeviceState *dev); +}; + +static MemTxResult gicv3_its_translation_write(void *opaque, hwaddr offset, + uint64_t data, unsigned size, + MemTxAttrs attrs) +{ + return MEMTX_OK; +} + +static bool its_writel(GICv3ITSState *s, hwaddr offset, + uint64_t value, MemTxAttrs attrs) +{ + bool result = true; + + return result; +} + +static bool its_readl(GICv3ITSState *s, hwaddr offset, + uint64_t *data, MemTxAttrs attrs) +{ + bool result = true; + + return result; +} + +static bool its_writell(GICv3ITSState *s, hwaddr offset, + uint64_t value, MemTxAttrs attrs) +{ + bool result = true; + + return result; +} + +static bool its_readll(GICv3ITSState *s, hwaddr offset, + uint64_t *data, MemTxAttrs attrs) +{ + bool result = true; + + return result; +} + +static MemTxResult gicv3_its_read(void *opaque, hwaddr offset, uint64_t *data, + unsigned size, MemTxAttrs attrs) +{ + GICv3ITSState *s = (GICv3ITSState *)opaque; + bool result; + + switch (size) { + case 4: + result = its_readl(s, offset, data, attrs); + break; + case 8: + result = its_readll(s, offset, data, attrs); + break; + default: + result = false; + break; + } + + if (!result) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid guest read at offset " TARGET_FMT_plx + "size %u\n", __func__, offset, size); + /* + * The spec requires that reserved registers are RAZ/WI; + * so use false returns from leaf functions as a way to + * trigger the guest-error logging but don't return it to + * the caller, or we'll cause a spurious guest data abort. + */ + *data = 0; + } + return MEMTX_OK; +} + +static MemTxResult gicv3_its_write(void *opaque, hwaddr offset, uint64_t data, + unsigned size, MemTxAttrs attrs) +{ + GICv3ITSState *s = (GICv3ITSState *)opaque; + bool result; + + switch (size) { + case 4: + result = its_writel(s, offset, data, attrs); + break; + case 8: + result = its_writell(s, offset, data, attrs); + break; + default: + result = false; + break; + } + + if (!result) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid guest write at offset " TARGET_FMT_plx + "size %u\n", __func__, offset, size); + /* + * The spec requires that reserved registers are RAZ/WI; + * so use false returns from leaf functions as a way to + * trigger the guest-error logging but don't return it to + * the caller, or we'll cause a spurious guest data abort. + */ + } + return MEMTX_OK; +} + +static const MemoryRegionOps gicv3_its_control_ops = { + .read_with_attrs = gicv3_its_read, + .write_with_attrs = gicv3_its_write, + .valid.min_access_size = 4, + .valid.max_access_size = 8, + .impl.min_access_size = 4, + .impl.max_access_size = 8, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static const MemoryRegionOps gicv3_its_translation_ops = { + .write_with_attrs = gicv3_its_translation_write, + .valid.min_access_size = 2, + .valid.max_access_size = 4, + .impl.min_access_size = 2, + .impl.max_access_size = 4, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static void gicv3_arm_its_realize(DeviceState *dev, Error **errp) +{ + GICv3ITSState *s = ARM_GICV3_ITS_COMMON(dev); + int i; + + for (i = 0; i < s->gicv3->num_cpu; i++) { + if (!(s->gicv3->cpu[i].gicr_typer & GICR_TYPER_PLPIS)) { + error_setg(errp, "Physical LPI not supported by CPU %d", i); + return; + } + } + + gicv3_its_init_mmio(s, &gicv3_its_control_ops, &gicv3_its_translation_ops); + + /* set the ITS default features supported */ + s->typer = FIELD_DP64(s->typer, GITS_TYPER, PHYSICAL, + GITS_TYPE_PHYSICAL); + s->typer = FIELD_DP64(s->typer, GITS_TYPER, ITT_ENTRY_SIZE, + ITS_ITT_ENTRY_SIZE - 1); + s->typer = FIELD_DP64(s->typer, GITS_TYPER, IDBITS, ITS_IDBITS); + s->typer = FIELD_DP64(s->typer, GITS_TYPER, DEVBITS, ITS_DEVBITS); + s->typer = FIELD_DP64(s->typer, GITS_TYPER, CIL, 1); + s->typer = FIELD_DP64(s->typer, GITS_TYPER, CIDBITS, ITS_CIDBITS); +} + +static void gicv3_its_reset(DeviceState *dev) +{ + GICv3ITSState *s = ARM_GICV3_ITS_COMMON(dev); + GICv3ITSClass *c = ARM_GICV3_ITS_GET_CLASS(s); + + c->parent_reset(dev); + + /* Quiescent bit reset to 1 */ + s->ctlr = FIELD_DP32(s->ctlr, GITS_CTLR, QUIESCENT, 1); + + /* + * setting GITS_BASER0.Type = 0b001 (Device) + * GITS_BASER1.Type = 0b100 (Collection Table) + * GITS_BASER<n>.Type,where n = 3 to 7 are 0b00 (Unimplemented) + * GITS_BASER<0,1>.Page_Size = 64KB + * and default translation table entry size to 16 bytes + */ + s->baser[0] = FIELD_DP64(s->baser[0], GITS_BASER, TYPE, + GITS_BASER_TYPE_DEVICE); + s->baser[0] = FIELD_DP64(s->baser[0], GITS_BASER, PAGESIZE, + GITS_BASER_PAGESIZE_64K); + s->baser[0] = FIELD_DP64(s->baser[0], GITS_BASER, ENTRYSIZE, + GITS_DTE_SIZE - 1); + + s->baser[1] = FIELD_DP64(s->baser[1], GITS_BASER, TYPE, + GITS_BASER_TYPE_COLLECTION); + s->baser[1] = FIELD_DP64(s->baser[1], GITS_BASER, PAGESIZE, + GITS_BASER_PAGESIZE_64K); + s->baser[1] = FIELD_DP64(s->baser[1], GITS_BASER, ENTRYSIZE, + GITS_CTE_SIZE - 1); +} + +static Property gicv3_its_props[] = { + DEFINE_PROP_LINK("parent-gicv3", GICv3ITSState, gicv3, "arm-gicv3", + GICv3State *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void gicv3_its_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + GICv3ITSClass *ic = ARM_GICV3_ITS_CLASS(klass); + + dc->realize = gicv3_arm_its_realize; + device_class_set_props(dc, gicv3_its_props); + device_class_set_parent_reset(dc, gicv3_its_reset, &ic->parent_reset); +} + +static const TypeInfo gicv3_its_info = { + .name = TYPE_ARM_GICV3_ITS, + .parent = TYPE_ARM_GICV3_ITS_COMMON, + .instance_size = sizeof(GICv3ITSState), + .class_init = gicv3_its_class_init, + .class_size = sizeof(GICv3ITSClass), +}; + +static void gicv3_its_register_types(void) +{ + type_register_static(&gicv3_its_info); +} + +type_init(gicv3_its_register_types) diff --git a/hw/intc/arm_gicv3_its_common.c b/hw/intc/arm_gicv3_its_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its_common.c +++ b/hw/intc/arm_gicv3_its_common.c @@ -XXX,XX +XXX,XX @@ static int gicv3_its_post_load(void *opaque, int version_id) static const VMStateDescription vmstate_its = { .name = "arm_gicv3_its", + .version_id = 1, + .minimum_version_id = 1, .pre_save = gicv3_its_pre_save, .post_load = gicv3_its_post_load, .priority = MIG_PRI_GICV3_ITS, @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps gicv3_its_trans_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -void gicv3_its_init_mmio(GICv3ITSState *s, const MemoryRegionOps *ops) +void gicv3_its_init_mmio(GICv3ITSState *s, const MemoryRegionOps *ops, + const MemoryRegionOps *tops) { SysBusDevice *sbd = SYS_BUS_DEVICE(s); memory_region_init_io(&s->iomem_its_cntrl, OBJECT(s), ops, s, "control", ITS_CONTROL_SIZE); memory_region_init_io(&s->iomem_its_translation, OBJECT(s), - &gicv3_its_trans_ops, s, + tops ? tops : &gicv3_its_trans_ops, s, "translation", ITS_TRANS_SIZE); /* Our two regions are always adjacent, therefore we now combine them diff --git a/hw/intc/arm_gicv3_its_kvm.c b/hw/intc/arm_gicv3_its_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its_kvm.c +++ b/hw/intc/arm_gicv3_its_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_arm_its_realize(DeviceState *dev, Error **errp) kvm_arm_register_device(&s->iomem_its_cntrl, -1, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_ITS_ADDR_TYPE, s->dev_fd, 0); - gicv3_its_init_mmio(s, NULL); + gicv3_its_init_mmio(s, NULL, NULL); if (!kvm_device_check_attr(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_ITS_REGS, GITS_CTLR)) { diff --git a/hw/intc/meson.build b/hw/intc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/meson.build +++ b/hw/intc/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_ARM_GIC', if_true: files( 'arm_gicv3_dist.c', 'arm_gicv3_its_common.c', 'arm_gicv3_redist.c', + 'arm_gicv3_its.c', )) softmmu_ss.add(when: 'CONFIG_ETRAXFS', if_true: files('etraxfs_pic.c')) softmmu_ss.add(when: 'CONFIG_HEATHROW_PIC', if_true: files('heathrow_pic.c')) -- 2.20.1 From: Shashi Mallela <shashi.mallela@linaro.org> Defined descriptors for ITS device table,collection table and ITS command queue entities.Implemented register read/write functions, extract ITS table parameters and command queue parameters,extended gicv3 common to capture qemu address space(which host the ITS table platform memories required for subsequent ITS processing) and initialize the same in ITS device. Signed-off-by: Shashi Mallela <shashi.mallela@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested-by: Neil Armstrong <narmstrong@baylibre.com> Message-id: 20210910143951.92242-3-shashi.mallela@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/gicv3_internal.h | 29 ++ include/hw/intc/arm_gicv3_common.h | 3 + include/hw/intc/arm_gicv3_its_common.h | 23 ++ hw/intc/arm_gicv3_its.c | 376 +++++++++++++++++++++++++ 4 files changed, 431 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(GITS_BASER, INNERCACHE, 59, 3) FIELD(GITS_BASER, INDIRECT, 62, 1) FIELD(GITS_BASER, VALID, 63, 1) +FIELD(GITS_CBASER, SIZE, 0, 8) +FIELD(GITS_CBASER, SHAREABILITY, 10, 2) +FIELD(GITS_CBASER, PHYADDR, 12, 40) +FIELD(GITS_CBASER, OUTERCACHE, 53, 3) +FIELD(GITS_CBASER, INNERCACHE, 59, 3) +FIELD(GITS_CBASER, VALID, 63, 1) + +FIELD(GITS_CREADR, STALLED, 0, 1) +FIELD(GITS_CREADR, OFFSET, 5, 15) + +FIELD(GITS_CWRITER, RETRY, 0, 1) +FIELD(GITS_CWRITER, OFFSET, 5, 15) + +FIELD(GITS_CTLR, ENABLED, 0, 1) FIELD(GITS_CTLR, QUIESCENT, 31, 1) FIELD(GITS_TYPER, PHYSICAL, 0, 1) @@ -XXX,XX +XXX,XX @@ FIELD(GITS_TYPER, PTA, 19, 1) FIELD(GITS_TYPER, CIDBITS, 32, 4) FIELD(GITS_TYPER, CIL, 36, 1) +#define GITS_IDREGS 0xFFD0 + +#define ITS_CTLR_ENABLED (1U) /* ITS Enabled */ + +#define GITS_BASER_RO_MASK (R_GITS_BASER_ENTRYSIZE_MASK | \ + R_GITS_BASER_TYPE_MASK) + #define GITS_BASER_PAGESIZE_4K 0 #define GITS_BASER_PAGESIZE_16K 1 #define GITS_BASER_PAGESIZE_64K 2 @@ -XXX,XX +XXX,XX @@ FIELD(GITS_TYPER, CIL, 36, 1) #define GITS_BASER_TYPE_DEVICE 1ULL #define GITS_BASER_TYPE_COLLECTION 4ULL +#define GITS_PAGE_SIZE_4K 0x1000 +#define GITS_PAGE_SIZE_16K 0x4000 +#define GITS_PAGE_SIZE_64K 0x10000 + +#define L1TABLE_ENTRY_SIZE 8 + +#define GITS_CMDQ_ENTRY_SIZE 32 + /** * Default features advertised by this version of ITS */ diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3State { int dev_fd; /* kvm device fd if backed by kvm vgic support */ Error *migration_blocker; + MemoryRegion *dma; + AddressSpace dma_as; + /* Distributor */ /* for a GIC with the security extensions the NS banked version of this diff --git a/include/hw/intc/arm_gicv3_its_common.h b/include/hw/intc/arm_gicv3_its_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_its_common.h +++ b/include/hw/intc/arm_gicv3_its_common.h @@ -XXX,XX +XXX,XX @@ #define GITS_TRANSLATER 0x0040 +typedef struct { + bool valid; + bool indirect; + uint16_t entry_sz; + uint32_t page_sz; + uint32_t max_entries; + union { + uint32_t max_devids; + uint32_t max_collids; + } maxids; + uint64_t base_addr; +} TableDesc; + +typedef struct { + bool valid; + uint32_t max_entries; + uint64_t base_addr; +} CmdQDesc; + struct GICv3ITSState { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct GICv3ITSState { uint64_t creadr; uint64_t baser[8]; + TableDesc dt; + TableDesc ct; + CmdQDesc cq; + Error *migration_blocker; }; diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ struct GICv3ITSClass { void (*parent_reset)(DeviceState *dev); }; +static uint64_t baser_base_addr(uint64_t value, uint32_t page_sz) +{ + uint64_t result = 0; + + switch (page_sz) { + case GITS_PAGE_SIZE_4K: + case GITS_PAGE_SIZE_16K: + result = FIELD_EX64(value, GITS_BASER, PHYADDR) << 12; + break; + + case GITS_PAGE_SIZE_64K: + result = FIELD_EX64(value, GITS_BASER, PHYADDRL_64K) << 16; + result |= FIELD_EX64(value, GITS_BASER, PHYADDRH_64K) << 48; + break; + + default: + break; + } + return result; +} + +/* + * This function extracts the ITS Device and Collection table specific + * parameters (like base_addr, size etc) from GITS_BASER register. + * It is called during ITS enable and also during post_load migration + */ +static void extract_table_params(GICv3ITSState *s) +{ + uint16_t num_pages = 0; + uint8_t page_sz_type; + uint8_t type; + uint32_t page_sz = 0; + uint64_t value; + + for (int i = 0; i < 8; i++) { + value = s->baser[i]; + + if (!value) { + continue; + } + + page_sz_type = FIELD_EX64(value, GITS_BASER, PAGESIZE); + + switch (page_sz_type) { + case 0: + page_sz = GITS_PAGE_SIZE_4K; + break; + + case 1: + page_sz = GITS_PAGE_SIZE_16K; + break; + + case 2: + case 3: + page_sz = GITS_PAGE_SIZE_64K; + break; + + default: + g_assert_not_reached(); + } + + num_pages = FIELD_EX64(value, GITS_BASER, SIZE) + 1; + + type = FIELD_EX64(value, GITS_BASER, TYPE); + + switch (type) { + + case GITS_BASER_TYPE_DEVICE: + memset(&s->dt, 0 , sizeof(s->dt)); + s->dt.valid = FIELD_EX64(value, GITS_BASER, VALID); + + if (!s->dt.valid) { + return; + } + + s->dt.page_sz = page_sz; + s->dt.indirect = FIELD_EX64(value, GITS_BASER, INDIRECT); + s->dt.entry_sz = FIELD_EX64(value, GITS_BASER, ENTRYSIZE); + + if (!s->dt.indirect) { + s->dt.max_entries = (num_pages * page_sz) / s->dt.entry_sz; + } else { + s->dt.max_entries = (((num_pages * page_sz) / + L1TABLE_ENTRY_SIZE) * + (page_sz / s->dt.entry_sz)); + } + + s->dt.maxids.max_devids = (1UL << (FIELD_EX64(s->typer, GITS_TYPER, + DEVBITS) + 1)); + + s->dt.base_addr = baser_base_addr(value, page_sz); + + break; + + case GITS_BASER_TYPE_COLLECTION: + memset(&s->ct, 0 , sizeof(s->ct)); + s->ct.valid = FIELD_EX64(value, GITS_BASER, VALID); + + /* + * GITS_TYPER.HCC is 0 for this implementation + * hence writes are discarded if ct.valid is 0 + */ + if (!s->ct.valid) { + return; + } + + s->ct.page_sz = page_sz; + s->ct.indirect = FIELD_EX64(value, GITS_BASER, INDIRECT); + s->ct.entry_sz = FIELD_EX64(value, GITS_BASER, ENTRYSIZE); + + if (!s->ct.indirect) { + s->ct.max_entries = (num_pages * page_sz) / s->ct.entry_sz; + } else { + s->ct.max_entries = (((num_pages * page_sz) / + L1TABLE_ENTRY_SIZE) * + (page_sz / s->ct.entry_sz)); + } + + if (FIELD_EX64(s->typer, GITS_TYPER, CIL)) { + s->ct.maxids.max_collids = (1UL << (FIELD_EX64(s->typer, + GITS_TYPER, CIDBITS) + 1)); + } else { + /* 16-bit CollectionId supported when CIL == 0 */ + s->ct.maxids.max_collids = (1UL << 16); + } + + s->ct.base_addr = baser_base_addr(value, page_sz); + + break; + + default: + break; + } + } +} + +static void extract_cmdq_params(GICv3ITSState *s) +{ + uint16_t num_pages = 0; + uint64_t value = s->cbaser; + + num_pages = FIELD_EX64(value, GITS_CBASER, SIZE) + 1; + + memset(&s->cq, 0 , sizeof(s->cq)); + s->cq.valid = FIELD_EX64(value, GITS_CBASER, VALID); + + if (s->cq.valid) { + s->cq.max_entries = (num_pages * GITS_PAGE_SIZE_4K) / + GITS_CMDQ_ENTRY_SIZE; + s->cq.base_addr = FIELD_EX64(value, GITS_CBASER, PHYADDR); + s->cq.base_addr <<= R_GITS_CBASER_PHYADDR_SHIFT; + } +} + static MemTxResult gicv3_its_translation_write(void *opaque, hwaddr offset, uint64_t data, unsigned size, MemTxAttrs attrs) @@ -XXX,XX +XXX,XX @@ static bool its_writel(GICv3ITSState *s, hwaddr offset, uint64_t value, MemTxAttrs attrs) { bool result = true; + int index; + switch (offset) { + case GITS_CTLR: + s->ctlr |= (value & ~(s->ctlr)); + + if (s->ctlr & ITS_CTLR_ENABLED) { + extract_table_params(s); + extract_cmdq_params(s); + s->creadr = 0; + } + break; + case GITS_CBASER: + /* + * IMPDEF choice:- GITS_CBASER register becomes RO if ITS is + * already enabled + */ + if (!(s->ctlr & ITS_CTLR_ENABLED)) { + s->cbaser = deposit64(s->cbaser, 0, 32, value); + s->creadr = 0; + s->cwriter = s->creadr; + } + break; + case GITS_CBASER + 4: + /* + * IMPDEF choice:- GITS_CBASER register becomes RO if ITS is + * already enabled + */ + if (!(s->ctlr & ITS_CTLR_ENABLED)) { + s->cbaser = deposit64(s->cbaser, 32, 32, value); + s->creadr = 0; + s->cwriter = s->creadr; + } + break; + case GITS_CWRITER: + s->cwriter = deposit64(s->cwriter, 0, 32, + (value & ~R_GITS_CWRITER_RETRY_MASK)); + break; + case GITS_CWRITER + 4: + s->cwriter = deposit64(s->cwriter, 32, 32, value); + break; + case GITS_CREADR: + if (s->gicv3->gicd_ctlr & GICD_CTLR_DS) { + s->creadr = deposit64(s->creadr, 0, 32, + (value & ~R_GITS_CREADR_STALLED_MASK)); + } else { + /* RO register, ignore the write */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid guest write to RO register at offset " + TARGET_FMT_plx "\n", __func__, offset); + } + break; + case GITS_CREADR + 4: + if (s->gicv3->gicd_ctlr & GICD_CTLR_DS) { + s->creadr = deposit64(s->creadr, 32, 32, value); + } else { + /* RO register, ignore the write */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid guest write to RO register at offset " + TARGET_FMT_plx "\n", __func__, offset); + } + break; + case GITS_BASER ... GITS_BASER + 0x3f: + /* + * IMPDEF choice:- GITS_BASERn register becomes RO if ITS is + * already enabled + */ + if (!(s->ctlr & ITS_CTLR_ENABLED)) { + index = (offset - GITS_BASER) / 8; + + if (offset & 7) { + value <<= 32; + value &= ~GITS_BASER_RO_MASK; + s->baser[index] &= GITS_BASER_RO_MASK | MAKE_64BIT_MASK(0, 32); + s->baser[index] |= value; + } else { + value &= ~GITS_BASER_RO_MASK; + s->baser[index] &= GITS_BASER_RO_MASK | MAKE_64BIT_MASK(32, 32); + s->baser[index] |= value; + } + } + break; + case GITS_IIDR: + case GITS_IDREGS ... GITS_IDREGS + 0x2f: + /* RO registers, ignore the write */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid guest write to RO register at offset " + TARGET_FMT_plx "\n", __func__, offset); + break; + default: + result = false; + break; + } return result; } @@ -XXX,XX +XXX,XX @@ static bool its_readl(GICv3ITSState *s, hwaddr offset, uint64_t *data, MemTxAttrs attrs) { bool result = true; + int index; + switch (offset) { + case GITS_CTLR: + *data = s->ctlr; + break; + case GITS_IIDR: + *data = gicv3_iidr(); + break; + case GITS_IDREGS ... GITS_IDREGS + 0x2f: + /* ID registers */ + *data = gicv3_idreg(offset - GITS_IDREGS); + break; + case GITS_TYPER: + *data = extract64(s->typer, 0, 32); + break; + case GITS_TYPER + 4: + *data = extract64(s->typer, 32, 32); + break; + case GITS_CBASER: + *data = extract64(s->cbaser, 0, 32); + break; + case GITS_CBASER + 4: + *data = extract64(s->cbaser, 32, 32); + break; + case GITS_CREADR: + *data = extract64(s->creadr, 0, 32); + break; + case GITS_CREADR + 4: + *data = extract64(s->creadr, 32, 32); + break; + case GITS_CWRITER: + *data = extract64(s->cwriter, 0, 32); + break; + case GITS_CWRITER + 4: + *data = extract64(s->cwriter, 32, 32); + break; + case GITS_BASER ... GITS_BASER + 0x3f: + index = (offset - GITS_BASER) / 8; + if (offset & 7) { + *data = extract64(s->baser[index], 32, 32); + } else { + *data = extract64(s->baser[index], 0, 32); + } + break; + default: + result = false; + break; + } return result; } @@ -XXX,XX +XXX,XX @@ static bool its_writell(GICv3ITSState *s, hwaddr offset, uint64_t value, MemTxAttrs attrs) { bool result = true; + int index; + switch (offset) { + case GITS_BASER ... GITS_BASER + 0x3f: + /* + * IMPDEF choice:- GITS_BASERn register becomes RO if ITS is + * already enabled + */ + if (!(s->ctlr & ITS_CTLR_ENABLED)) { + index = (offset - GITS_BASER) / 8; + s->baser[index] &= GITS_BASER_RO_MASK; + s->baser[index] |= (value & ~GITS_BASER_RO_MASK); + } + break; + case GITS_CBASER: + /* + * IMPDEF choice:- GITS_CBASER register becomes RO if ITS is + * already enabled + */ + if (!(s->ctlr & ITS_CTLR_ENABLED)) { + s->cbaser = value; + s->creadr = 0; + s->cwriter = s->creadr; + } + break; + case GITS_CWRITER: + s->cwriter = value & ~R_GITS_CWRITER_RETRY_MASK; + break; + case GITS_CREADR: + if (s->gicv3->gicd_ctlr & GICD_CTLR_DS) { + s->creadr = value & ~R_GITS_CREADR_STALLED_MASK; + } else { + /* RO register, ignore the write */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid guest write to RO register at offset " + TARGET_FMT_plx "\n", __func__, offset); + } + break; + case GITS_TYPER: + /* RO registers, ignore the write */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid guest write to RO register at offset " + TARGET_FMT_plx "\n", __func__, offset); + break; + default: + result = false; + break; + } return result; } @@ -XXX,XX +XXX,XX @@ static bool its_readll(GICv3ITSState *s, hwaddr offset, uint64_t *data, MemTxAttrs attrs) { bool result = true; + int index; + switch (offset) { + case GITS_TYPER: + *data = s->typer; + break; + case GITS_BASER ... GITS_BASER + 0x3f: + index = (offset - GITS_BASER) / 8; + *data = s->baser[index]; + break; + case GITS_CBASER: + *data = s->cbaser; + break; + case GITS_CREADR: + *data = s->creadr; + break; + case GITS_CWRITER: + *data = s->cwriter; + break; + default: + result = false; + break; + } return result; } @@ -XXX,XX +XXX,XX @@ static void gicv3_arm_its_realize(DeviceState *dev, Error **errp) gicv3_its_init_mmio(s, &gicv3_its_control_ops, &gicv3_its_translation_ops); + address_space_init(&s->gicv3->dma_as, s->gicv3->dma, + "gicv3-its-sysmem"); + /* set the ITS default features supported */ s->typer = FIELD_DP64(s->typer, GITS_TYPER, PHYSICAL, GITS_TYPE_PHYSICAL); @@ -XXX,XX +XXX,XX @@ static void gicv3_its_reset(DeviceState *dev) GITS_CTE_SIZE - 1); } +static void gicv3_its_post_load(GICv3ITSState *s) +{ + if (s->ctlr & ITS_CTLR_ENABLED) { + extract_table_params(s); + extract_cmdq_params(s); + } +} + static Property gicv3_its_props[] = { DEFINE_PROP_LINK("parent-gicv3", GICv3ITSState, gicv3, "arm-gicv3", GICv3State *), @@ -XXX,XX +XXX,XX @@ static void gicv3_its_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); GICv3ITSClass *ic = ARM_GICV3_ITS_CLASS(klass); + GICv3ITSCommonClass *icc = ARM_GICV3_ITS_COMMON_CLASS(klass); dc->realize = gicv3_arm_its_realize; device_class_set_props(dc, gicv3_its_props); device_class_set_parent_reset(dc, gicv3_its_reset, &ic->parent_reset); + icc->post_load = gicv3_its_post_load; } static const TypeInfo gicv3_its_info = { -- 2.20.1 From: Shashi Mallela <shashi.mallela@linaro.org> Added functionality to trigger ITS command queue processing on write to CWRITE register and process each command queue entry to identify the command type and handle commands like MAPD,MAPC,SYNC. Signed-off-by: Shashi Mallela <shashi.mallela@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested-by: Neil Armstrong <narmstrong@baylibre.com> Message-id: 20210910143951.92242-4-shashi.mallela@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/gicv3_internal.h | 40 +++++ hw/intc/arm_gicv3_its.c | 319 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 359 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(GITS_TYPER, CIL, 36, 1) #define L1TABLE_ENTRY_SIZE 8 #define GITS_CMDQ_ENTRY_SIZE 32 +#define NUM_BYTES_IN_DW 8 + +#define CMD_MASK 0xff + +/* ITS Commands */ +#define GITS_CMD_CLEAR 0x04 +#define GITS_CMD_DISCARD 0x0F +#define GITS_CMD_INT 0x03 +#define GITS_CMD_MAPC 0x09 +#define GITS_CMD_MAPD 0x08 +#define GITS_CMD_MAPI 0x0B +#define GITS_CMD_MAPTI 0x0A +#define GITS_CMD_INV 0x0C +#define GITS_CMD_INVALL 0x0D +#define GITS_CMD_SYNC 0x05 + +/* MAPC command fields */ +#define ICID_LENGTH 16 +#define ICID_MASK ((1U << ICID_LENGTH) - 1) +FIELD(MAPC, RDBASE, 16, 32) + +#define RDBASE_PROCNUM_LENGTH 16 +#define RDBASE_PROCNUM_MASK ((1ULL << RDBASE_PROCNUM_LENGTH) - 1) + +/* MAPD command fields */ +#define ITTADDR_LENGTH 44 +#define ITTADDR_SHIFT 8 +#define ITTADDR_MASK MAKE_64BIT_MASK(ITTADDR_SHIFT, ITTADDR_LENGTH) +#define SIZE_MASK 0x1f + +#define DEVID_SHIFT 32 +#define DEVID_MASK MAKE_64BIT_MASK(32, 32) + +#define VALID_SHIFT 63 +#define CMD_FIELD_VALID_MASK (1ULL << VALID_SHIFT) +#define L2_TABLE_VALID_MASK CMD_FIELD_VALID_MASK +#define TABLE_ENTRY_VALID_MASK (1ULL << 0) /** * Default features advertised by this version of ITS @@ -XXX,XX +XXX,XX @@ FIELD(GITS_TYPER, CIL, 36, 1) * Valid = 1 bit,ITTAddr = 44 bits,Size = 5 bits */ #define GITS_DTE_SIZE (0x8ULL) +#define GITS_DTE_ITTADDR_SHIFT 6 +#define GITS_DTE_ITTADDR_MASK MAKE_64BIT_MASK(GITS_DTE_ITTADDR_SHIFT, \ + ITTADDR_LENGTH) /* * 8 bytes Collection Table Entry size diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static uint64_t baser_base_addr(uint64_t value, uint32_t page_sz) return result; } +static bool update_cte(GICv3ITSState *s, uint16_t icid, bool valid, + uint64_t rdbase) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint64_t value; + uint64_t l2t_addr; + bool valid_l2t; + uint32_t l2t_id; + uint32_t max_l2_entries; + uint64_t cte = 0; + MemTxResult res = MEMTX_OK; + + if (!s->ct.valid) { + return true; + } + + if (valid) { + /* add mapping entry to collection table */ + cte = (valid & TABLE_ENTRY_VALID_MASK) | (rdbase << 1ULL); + } + + /* + * The specification defines the format of level 1 entries of a + * 2-level table, but the format of level 2 entries and the format + * of flat-mapped tables is IMPDEF. + */ + if (s->ct.indirect) { + l2t_id = icid / (s->ct.page_sz / L1TABLE_ENTRY_SIZE); + + value = address_space_ldq_le(as, + s->ct.base_addr + + (l2t_id * L1TABLE_ENTRY_SIZE), + MEMTXATTRS_UNSPECIFIED, &res); + + if (res != MEMTX_OK) { + return false; + } + + valid_l2t = (value & L2_TABLE_VALID_MASK) != 0; + + if (valid_l2t) { + max_l2_entries = s->ct.page_sz / s->ct.entry_sz; + + l2t_addr = value & ((1ULL << 51) - 1); + + address_space_stq_le(as, l2t_addr + + ((icid % max_l2_entries) * GITS_CTE_SIZE), + cte, MEMTXATTRS_UNSPECIFIED, &res); + } + } else { + /* Flat level table */ + address_space_stq_le(as, s->ct.base_addr + (icid * GITS_CTE_SIZE), + cte, MEMTXATTRS_UNSPECIFIED, &res); + } + if (res != MEMTX_OK) { + return false; + } else { + return true; + } +} + +static bool process_mapc(GICv3ITSState *s, uint32_t offset) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint16_t icid; + uint64_t rdbase; + bool valid; + MemTxResult res = MEMTX_OK; + bool result = false; + uint64_t value; + + offset += NUM_BYTES_IN_DW; + offset += NUM_BYTES_IN_DW; + + value = address_space_ldq_le(as, s->cq.base_addr + offset, + MEMTXATTRS_UNSPECIFIED, &res); + + if (res != MEMTX_OK) { + return result; + } + + icid = value & ICID_MASK; + + rdbase = (value & R_MAPC_RDBASE_MASK) >> R_MAPC_RDBASE_SHIFT; + rdbase &= RDBASE_PROCNUM_MASK; + + valid = (value & CMD_FIELD_VALID_MASK); + + if ((icid > s->ct.maxids.max_collids) || (rdbase > s->gicv3->num_cpu)) { + qemu_log_mask(LOG_GUEST_ERROR, + "ITS MAPC: invalid collection table attributes " + "icid %d rdbase %lu\n", icid, rdbase); + /* + * in this implementation, in case of error + * we ignore this command and move onto the next + * command in the queue + */ + } else { + result = update_cte(s, icid, valid, rdbase); + } + + return result; +} + +static bool update_dte(GICv3ITSState *s, uint32_t devid, bool valid, + uint8_t size, uint64_t itt_addr) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint64_t value; + uint64_t l2t_addr; + bool valid_l2t; + uint32_t l2t_id; + uint32_t max_l2_entries; + uint64_t dte = 0; + MemTxResult res = MEMTX_OK; + + if (s->dt.valid) { + if (valid) { + /* add mapping entry to device table */ + dte = (valid & TABLE_ENTRY_VALID_MASK) | + ((size & SIZE_MASK) << 1U) | + (itt_addr << GITS_DTE_ITTADDR_SHIFT); + } + } else { + return true; + } + + /* + * The specification defines the format of level 1 entries of a + * 2-level table, but the format of level 2 entries and the format + * of flat-mapped tables is IMPDEF. + */ + if (s->dt.indirect) { + l2t_id = devid / (s->dt.page_sz / L1TABLE_ENTRY_SIZE); + + value = address_space_ldq_le(as, + s->dt.base_addr + + (l2t_id * L1TABLE_ENTRY_SIZE), + MEMTXATTRS_UNSPECIFIED, &res); + + if (res != MEMTX_OK) { + return false; + } + + valid_l2t = (value & L2_TABLE_VALID_MASK) != 0; + + if (valid_l2t) { + max_l2_entries = s->dt.page_sz / s->dt.entry_sz; + + l2t_addr = value & ((1ULL << 51) - 1); + + address_space_stq_le(as, l2t_addr + + ((devid % max_l2_entries) * GITS_DTE_SIZE), + dte, MEMTXATTRS_UNSPECIFIED, &res); + } + } else { + /* Flat level table */ + address_space_stq_le(as, s->dt.base_addr + (devid * GITS_DTE_SIZE), + dte, MEMTXATTRS_UNSPECIFIED, &res); + } + if (res != MEMTX_OK) { + return false; + } else { + return true; + } +} + +static bool process_mapd(GICv3ITSState *s, uint64_t value, uint32_t offset) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint32_t devid; + uint8_t size; + uint64_t itt_addr; + bool valid; + MemTxResult res = MEMTX_OK; + bool result = false; + + devid = ((value & DEVID_MASK) >> DEVID_SHIFT); + + offset += NUM_BYTES_IN_DW; + value = address_space_ldq_le(as, s->cq.base_addr + offset, + MEMTXATTRS_UNSPECIFIED, &res); + + if (res != MEMTX_OK) { + return result; + } + + size = (value & SIZE_MASK); + + offset += NUM_BYTES_IN_DW; + value = address_space_ldq_le(as, s->cq.base_addr + offset, + MEMTXATTRS_UNSPECIFIED, &res); + + if (res != MEMTX_OK) { + return result; + } + + itt_addr = (value & ITTADDR_MASK) >> ITTADDR_SHIFT; + + valid = (value & CMD_FIELD_VALID_MASK); + + if ((devid > s->dt.maxids.max_devids) || + (size > FIELD_EX64(s->typer, GITS_TYPER, IDBITS))) { + qemu_log_mask(LOG_GUEST_ERROR, + "ITS MAPD: invalid device table attributes " + "devid %d or size %d\n", devid, size); + /* + * in this implementation, in case of error + * we ignore this command and move onto the next + * command in the queue + */ + } else { + result = update_dte(s, devid, valid, size, itt_addr); + } + + return result; +} + +/* + * Current implementation blocks until all + * commands are processed + */ +static void process_cmdq(GICv3ITSState *s) +{ + uint32_t wr_offset = 0; + uint32_t rd_offset = 0; + uint32_t cq_offset = 0; + uint64_t data; + AddressSpace *as = &s->gicv3->dma_as; + MemTxResult res = MEMTX_OK; + bool result = true; + uint8_t cmd; + + if (!(s->ctlr & ITS_CTLR_ENABLED)) { + return; + } + + wr_offset = FIELD_EX64(s->cwriter, GITS_CWRITER, OFFSET); + + if (wr_offset > s->cq.max_entries) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid write offset " + "%d\n", __func__, wr_offset); + return; + } + + rd_offset = FIELD_EX64(s->creadr, GITS_CREADR, OFFSET); + + if (rd_offset > s->cq.max_entries) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid read offset " + "%d\n", __func__, rd_offset); + return; + } + + while (wr_offset != rd_offset) { + cq_offset = (rd_offset * GITS_CMDQ_ENTRY_SIZE); + data = address_space_ldq_le(as, s->cq.base_addr + cq_offset, + MEMTXATTRS_UNSPECIFIED, &res); + if (res != MEMTX_OK) { + result = false; + } + cmd = (data & CMD_MASK); + + switch (cmd) { + case GITS_CMD_INT: + break; + case GITS_CMD_CLEAR: + break; + case GITS_CMD_SYNC: + /* + * Current implementation makes a blocking synchronous call + * for every command issued earlier, hence the internal state + * is already consistent by the time SYNC command is executed. + * Hence no further processing is required for SYNC command. + */ + break; + case GITS_CMD_MAPD: + result = process_mapd(s, data, cq_offset); + break; + case GITS_CMD_MAPC: + result = process_mapc(s, cq_offset); + break; + case GITS_CMD_MAPTI: + break; + case GITS_CMD_MAPI: + break; + case GITS_CMD_DISCARD: + break; + case GITS_CMD_INV: + case GITS_CMD_INVALL: + break; + default: + break; + } + if (result) { + rd_offset++; + rd_offset %= s->cq.max_entries; + s->creadr = FIELD_DP64(s->creadr, GITS_CREADR, OFFSET, rd_offset); + } else { + /* + * in this implementation, in case of dma read/write error + * we stall the command processing + */ + s->creadr = FIELD_DP64(s->creadr, GITS_CREADR, STALLED, 1); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: %x cmd processing failed\n", __func__, cmd); + break; + } + } +} + /* * This function extracts the ITS Device and Collection table specific * parameters (like base_addr, size etc) from GITS_BASER register. @@ -XXX,XX +XXX,XX @@ static bool its_writel(GICv3ITSState *s, hwaddr offset, extract_table_params(s); extract_cmdq_params(s); s->creadr = 0; + process_cmdq(s); } break; case GITS_CBASER: @@ -XXX,XX +XXX,XX @@ static bool its_writel(GICv3ITSState *s, hwaddr offset, case GITS_CWRITER: s->cwriter = deposit64(s->cwriter, 0, 32, (value & ~R_GITS_CWRITER_RETRY_MASK)); + if (s->cwriter != s->creadr) { + process_cmdq(s); + } break; case GITS_CWRITER + 4: s->cwriter = deposit64(s->cwriter, 32, 32, value); @@ -XXX,XX +XXX,XX @@ static bool its_writell(GICv3ITSState *s, hwaddr offset, break; case GITS_CWRITER: s->cwriter = value & ~R_GITS_CWRITER_RETRY_MASK; + if (s->cwriter != s->creadr) { + process_cmdq(s); + } break; case GITS_CREADR: if (s->gicv3->gicd_ctlr & GICD_CTLR_DS) { -- 2.20.1 From: Shashi Mallela <shashi.mallela@linaro.org> Added ITS command queue handling for MAPTI,MAPI commands,handled ITS translation which triggers an LPI via INT command as well as write to GITS_TRANSLATER register,defined enum to differentiate between ITS command interrupt trigger and GITS_TRANSLATER based interrupt trigger. Each of these commands make use of other functionalities implemented to get device table entry,collection table entry or interrupt translation table entry required for their processing. Signed-off-by: Shashi Mallela <shashi.mallela@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210910143951.92242-5-shashi.mallela@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/gicv3_internal.h | 12 + include/hw/intc/arm_gicv3_common.h | 2 + hw/intc/arm_gicv3_its.c | 365 ++++++++++++++++++++++++++++- 3 files changed, 378 insertions(+), 1 deletion(-) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(MAPC, RDBASE, 16, 32) #define ITTADDR_MASK MAKE_64BIT_MASK(ITTADDR_SHIFT, ITTADDR_LENGTH) #define SIZE_MASK 0x1f +/* MAPI command fields */ +#define EVENTID_MASK ((1ULL << 32) - 1) + +/* MAPTI command fields */ +#define pINTID_SHIFT 32 +#define pINTID_MASK MAKE_64BIT_MASK(32, 32) + #define DEVID_SHIFT 32 #define DEVID_MASK MAKE_64BIT_MASK(32, 32) @@ -XXX,XX +XXX,XX @@ FIELD(MAPC, RDBASE, 16, 32) * Values: | vPEID | ICID | */ #define ITS_ITT_ENTRY_SIZE 0xC +#define ITE_ENTRY_INTTYPE_SHIFT 1 +#define ITE_ENTRY_INTID_SHIFT 2 +#define ITE_ENTRY_INTID_MASK MAKE_64BIT_MASK(2, 24) +#define ITE_ENTRY_INTSP_SHIFT 26 +#define ITE_ENTRY_ICID_MASK MAKE_64BIT_MASK(0, 16) /* 16 bits EventId */ #define ITS_IDBITS GICD_TYPER_IDBITS diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ #define GICV3_MAXIRQ 1020 #define GICV3_MAXSPI (GICV3_MAXIRQ - GIC_INTERNAL) +#define GICV3_LPI_INTID_START 8192 + #define GICV3_REDIST_SIZE 0x20000 /* Number of SGI target-list bits */ diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ struct GICv3ITSClass { void (*parent_reset)(DeviceState *dev); }; +/* + * This is an internal enum used to distinguish between LPI triggered + * via command queue and LPI triggered via gits_translater write. + */ +typedef enum ItsCmdType { + NONE = 0, /* internal indication for GITS_TRANSLATER write */ + CLEAR = 1, + DISCARD = 2, + INT = 3, +} ItsCmdType; + +typedef struct { + uint32_t iteh; + uint64_t itel; +} IteEntry; + static uint64_t baser_base_addr(uint64_t value, uint32_t page_sz) { uint64_t result = 0; @@ -XXX,XX +XXX,XX @@ static uint64_t baser_base_addr(uint64_t value, uint32_t page_sz) return result; } +static bool get_cte(GICv3ITSState *s, uint16_t icid, uint64_t *cte, + MemTxResult *res) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint64_t l2t_addr; + uint64_t value; + bool valid_l2t; + uint32_t l2t_id; + uint32_t max_l2_entries; + + if (s->ct.indirect) { + l2t_id = icid / (s->ct.page_sz / L1TABLE_ENTRY_SIZE); + + value = address_space_ldq_le(as, + s->ct.base_addr + + (l2t_id * L1TABLE_ENTRY_SIZE), + MEMTXATTRS_UNSPECIFIED, res); + + if (*res == MEMTX_OK) { + valid_l2t = (value & L2_TABLE_VALID_MASK) != 0; + + if (valid_l2t) { + max_l2_entries = s->ct.page_sz / s->ct.entry_sz; + + l2t_addr = value & ((1ULL << 51) - 1); + + *cte = address_space_ldq_le(as, l2t_addr + + ((icid % max_l2_entries) * GITS_CTE_SIZE), + MEMTXATTRS_UNSPECIFIED, res); + } + } + } else { + /* Flat level table */ + *cte = address_space_ldq_le(as, s->ct.base_addr + + (icid * GITS_CTE_SIZE), + MEMTXATTRS_UNSPECIFIED, res); + } + + return (*cte & TABLE_ENTRY_VALID_MASK) != 0; +} + +static bool update_ite(GICv3ITSState *s, uint32_t eventid, uint64_t dte, + IteEntry ite) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint64_t itt_addr; + MemTxResult res = MEMTX_OK; + + itt_addr = (dte & GITS_DTE_ITTADDR_MASK) >> GITS_DTE_ITTADDR_SHIFT; + itt_addr <<= ITTADDR_SHIFT; /* 256 byte aligned */ + + address_space_stq_le(as, itt_addr + (eventid * (sizeof(uint64_t) + + sizeof(uint32_t))), ite.itel, MEMTXATTRS_UNSPECIFIED, + &res); + + if (res == MEMTX_OK) { + address_space_stl_le(as, itt_addr + (eventid * (sizeof(uint64_t) + + sizeof(uint32_t))) + sizeof(uint32_t), ite.iteh, + MEMTXATTRS_UNSPECIFIED, &res); + } + if (res != MEMTX_OK) { + return false; + } else { + return true; + } +} + +static bool get_ite(GICv3ITSState *s, uint32_t eventid, uint64_t dte, + uint16_t *icid, uint32_t *pIntid, MemTxResult *res) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint64_t itt_addr; + bool status = false; + IteEntry ite = {}; + + itt_addr = (dte & GITS_DTE_ITTADDR_MASK) >> GITS_DTE_ITTADDR_SHIFT; + itt_addr <<= ITTADDR_SHIFT; /* 256 byte aligned */ + + ite.itel = address_space_ldq_le(as, itt_addr + + (eventid * (sizeof(uint64_t) + + sizeof(uint32_t))), MEMTXATTRS_UNSPECIFIED, + res); + + if (*res == MEMTX_OK) { + ite.iteh = address_space_ldl_le(as, itt_addr + + (eventid * (sizeof(uint64_t) + + sizeof(uint32_t))) + sizeof(uint32_t), + MEMTXATTRS_UNSPECIFIED, res); + + if (*res == MEMTX_OK) { + if (ite.itel & TABLE_ENTRY_VALID_MASK) { + if ((ite.itel >> ITE_ENTRY_INTTYPE_SHIFT) & + GITS_TYPE_PHYSICAL) { + *pIntid = (ite.itel & ITE_ENTRY_INTID_MASK) >> + ITE_ENTRY_INTID_SHIFT; + *icid = ite.iteh & ITE_ENTRY_ICID_MASK; + status = true; + } + } + } + } + return status; +} + +static uint64_t get_dte(GICv3ITSState *s, uint32_t devid, MemTxResult *res) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint64_t l2t_addr; + uint64_t value; + bool valid_l2t; + uint32_t l2t_id; + uint32_t max_l2_entries; + + if (s->dt.indirect) { + l2t_id = devid / (s->dt.page_sz / L1TABLE_ENTRY_SIZE); + + value = address_space_ldq_le(as, + s->dt.base_addr + + (l2t_id * L1TABLE_ENTRY_SIZE), + MEMTXATTRS_UNSPECIFIED, res); + + if (*res == MEMTX_OK) { + valid_l2t = (value & L2_TABLE_VALID_MASK) != 0; + + if (valid_l2t) { + max_l2_entries = s->dt.page_sz / s->dt.entry_sz; + + l2t_addr = value & ((1ULL << 51) - 1); + + value = address_space_ldq_le(as, l2t_addr + + ((devid % max_l2_entries) * GITS_DTE_SIZE), + MEMTXATTRS_UNSPECIFIED, res); + } + } + } else { + /* Flat level table */ + value = address_space_ldq_le(as, s->dt.base_addr + + (devid * GITS_DTE_SIZE), + MEMTXATTRS_UNSPECIFIED, res); + } + + return value; +} + +/* + * This function handles the processing of following commands based on + * the ItsCmdType parameter passed:- + * 1. triggering of lpi interrupt translation via ITS INT command + * 2. triggering of lpi interrupt translation via gits_translater register + * 3. handling of ITS CLEAR command + * 4. handling of ITS DISCARD command + */ +static bool process_its_cmd(GICv3ITSState *s, uint64_t value, uint32_t offset, + ItsCmdType cmd) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint32_t devid, eventid; + MemTxResult res = MEMTX_OK; + bool dte_valid; + uint64_t dte = 0; + uint32_t max_eventid; + uint16_t icid = 0; + uint32_t pIntid = 0; + bool ite_valid = false; + uint64_t cte = 0; + bool cte_valid = false; + bool result = false; + + if (cmd == NONE) { + devid = offset; + } else { + devid = ((value & DEVID_MASK) >> DEVID_SHIFT); + + offset += NUM_BYTES_IN_DW; + value = address_space_ldq_le(as, s->cq.base_addr + offset, + MEMTXATTRS_UNSPECIFIED, &res); + } + + if (res != MEMTX_OK) { + return result; + } + + eventid = (value & EVENTID_MASK); + + dte = get_dte(s, devid, &res); + + if (res != MEMTX_OK) { + return result; + } + dte_valid = dte & TABLE_ENTRY_VALID_MASK; + + if (dte_valid) { + max_eventid = (1UL << (((dte >> 1U) & SIZE_MASK) + 1)); + + ite_valid = get_ite(s, eventid, dte, &icid, &pIntid, &res); + + if (res != MEMTX_OK) { + return result; + } + + if (ite_valid) { + cte_valid = get_cte(s, icid, &cte, &res); + } + + if (res != MEMTX_OK) { + return result; + } + } + + if ((devid > s->dt.maxids.max_devids) || !dte_valid || !ite_valid || + !cte_valid || (eventid > max_eventid)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid command attributes " + "devid %d or eventid %d or invalid dte %d or" + "invalid cte %d or invalid ite %d\n", + __func__, devid, eventid, dte_valid, cte_valid, + ite_valid); + /* + * in this implementation, in case of error + * we ignore this command and move onto the next + * command in the queue + */ + } else { + /* + * Current implementation only supports rdbase == procnum + * Hence rdbase physical address is ignored + */ + if (cmd == DISCARD) { + IteEntry ite = {}; + /* remove mapping from interrupt translation table */ + result = update_ite(s, eventid, dte, ite); + } + } + + return result; +} + +static bool process_mapti(GICv3ITSState *s, uint64_t value, uint32_t offset, + bool ignore_pInt) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint32_t devid, eventid; + uint32_t pIntid = 0; + uint32_t max_eventid, max_Intid; + bool dte_valid; + MemTxResult res = MEMTX_OK; + uint16_t icid = 0; + uint64_t dte = 0; + IteEntry ite; + uint32_t int_spurious = INTID_SPURIOUS; + bool result = false; + + devid = ((value & DEVID_MASK) >> DEVID_SHIFT); + offset += NUM_BYTES_IN_DW; + value = address_space_ldq_le(as, s->cq.base_addr + offset, + MEMTXATTRS_UNSPECIFIED, &res); + + if (res != MEMTX_OK) { + return result; + } + + eventid = (value & EVENTID_MASK); + + if (!ignore_pInt) { + pIntid = ((value & pINTID_MASK) >> pINTID_SHIFT); + } + + offset += NUM_BYTES_IN_DW; + value = address_space_ldq_le(as, s->cq.base_addr + offset, + MEMTXATTRS_UNSPECIFIED, &res); + + if (res != MEMTX_OK) { + return result; + } + + icid = value & ICID_MASK; + + dte = get_dte(s, devid, &res); + + if (res != MEMTX_OK) { + return result; + } + dte_valid = dte & TABLE_ENTRY_VALID_MASK; + + max_eventid = (1UL << (((dte >> 1U) & SIZE_MASK) + 1)); + + if (!ignore_pInt) { + max_Intid = (1ULL << (GICD_TYPER_IDBITS + 1)) - 1; + } + + if ((devid > s->dt.maxids.max_devids) || (icid > s->ct.maxids.max_collids) + || !dte_valid || (eventid > max_eventid) || + (!ignore_pInt && (((pIntid < GICV3_LPI_INTID_START) || + (pIntid > max_Intid)) && (pIntid != INTID_SPURIOUS)))) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid command attributes " + "devid %d or icid %d or eventid %d or pIntid %d or" + "unmapped dte %d\n", __func__, devid, icid, eventid, + pIntid, dte_valid); + /* + * in this implementation, in case of error + * we ignore this command and move onto the next + * command in the queue + */ + } else { + /* add ite entry to interrupt translation table */ + ite.itel = (dte_valid & TABLE_ENTRY_VALID_MASK) | + (GITS_TYPE_PHYSICAL << ITE_ENTRY_INTTYPE_SHIFT); + + if (ignore_pInt) { + ite.itel |= (eventid << ITE_ENTRY_INTID_SHIFT); + } else { + ite.itel |= (pIntid << ITE_ENTRY_INTID_SHIFT); + } + ite.itel |= (int_spurious << ITE_ENTRY_INTSP_SHIFT); + ite.iteh = icid; + + result = update_ite(s, eventid, dte, ite); + } + + return result; +} + static bool update_cte(GICv3ITSState *s, uint16_t icid, bool valid, uint64_t rdbase) { @@ -XXX,XX +XXX,XX @@ static void process_cmdq(GICv3ITSState *s) switch (cmd) { case GITS_CMD_INT: + res = process_its_cmd(s, data, cq_offset, INT); break; case GITS_CMD_CLEAR: + res = process_its_cmd(s, data, cq_offset, CLEAR); break; case GITS_CMD_SYNC: /* @@ -XXX,XX +XXX,XX @@ static void process_cmdq(GICv3ITSState *s) result = process_mapc(s, cq_offset); break; case GITS_CMD_MAPTI: + result = process_mapti(s, data, cq_offset, false); break; case GITS_CMD_MAPI: + result = process_mapti(s, data, cq_offset, true); break; case GITS_CMD_DISCARD: + result = process_its_cmd(s, data, cq_offset, DISCARD); break; case GITS_CMD_INV: case GITS_CMD_INVALL: @@ -XXX,XX +XXX,XX @@ static MemTxResult gicv3_its_translation_write(void *opaque, hwaddr offset, uint64_t data, unsigned size, MemTxAttrs attrs) { - return MEMTX_OK; + GICv3ITSState *s = (GICv3ITSState *)opaque; + bool result = true; + uint32_t devid = 0; + + switch (offset) { + case GITS_TRANSLATER: + if (s->ctlr & ITS_CTLR_ENABLED) { + devid = attrs.requester_id; + result = process_its_cmd(s, data, devid, NONE); + } + break; + default: + break; + } + + if (result) { + return MEMTX_OK; + } else { + return MEMTX_ERROR; + } } static bool its_writel(GICv3ITSState *s, hwaddr offset, -- 2.20.1 From: Shashi Mallela <shashi.mallela@linaro.org> Added properties to enable ITS feature and define qemu system address space memory in gicv3 common,setup distributor and redistributor registers to indicate LPI support. Signed-off-by: Shashi Mallela <shashi.mallela@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Neil Armstrong <narmstrong@baylibre.com> Message-id: 20210910143951.92242-6-shashi.mallela@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/gicv3_internal.h | 2 ++ include/hw/intc/arm_gicv3_common.h | 1 + hw/intc/arm_gicv3_common.c | 12 ++++++++++++ hw/intc/arm_gicv3_dist.c | 5 ++++- hw/intc/arm_gicv3_redist.c | 12 +++++++++--- 5 files changed, 28 insertions(+), 4 deletions(-) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ #define GICD_CTLR_E1NWF (1U << 7) #define GICD_CTLR_RWP (1U << 31) +#define GICD_TYPER_LPIS_SHIFT 17 + /* 16 bits EventId */ #define GICD_TYPER_IDBITS 0xf diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3State { uint32_t num_cpu; uint32_t num_irq; uint32_t revision; + bool lpi_enable; bool security_extn; bool irq_reset_nonsecure; bool gicd_no_migration_shift_bug; diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_common_realize(DeviceState *dev, Error **errp) return; } + if (s->lpi_enable && !s->dma) { + error_setg(errp, "Redist-ITS: Guest 'sysmem' reference link not set"); + return; + } + s->cpu = g_new0(GICv3CPUState, s->num_cpu); for (i = 0; i < s->num_cpu; i++) { @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_common_realize(DeviceState *dev, Error **errp) (1 << 24) | (i << 8) | (last << 4); + + if (s->lpi_enable) { + s->cpu[i].gicr_typer |= GICR_TYPER_PLPIS; + } } } @@ -XXX,XX +XXX,XX @@ static Property arm_gicv3_common_properties[] = { DEFINE_PROP_UINT32("num-cpu", GICv3State, num_cpu, 1), DEFINE_PROP_UINT32("num-irq", GICv3State, num_irq, 32), DEFINE_PROP_UINT32("revision", GICv3State, revision, 3), + DEFINE_PROP_BOOL("has-lpi", GICv3State, lpi_enable, 0), DEFINE_PROP_BOOL("has-security-extensions", GICv3State, security_extn, 0), DEFINE_PROP_ARRAY("redist-region-count", GICv3State, nb_redist_regions, redist_region_count, qdev_prop_uint32, uint32_t), + DEFINE_PROP_LINK("sysmem", GICv3State, dma, TYPE_MEMORY_REGION, + MemoryRegion *), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/intc/arm_gicv3_dist.c b/hw/intc/arm_gicv3_dist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_dist.c +++ b/hw/intc/arm_gicv3_dist.c @@ -XXX,XX +XXX,XX @@ static bool gicd_readl(GICv3State *s, hwaddr offset, * A3V == 1 (non-zero values of Affinity level 3 supported) * IDbits == 0xf (we support 16-bit interrupt identifiers) * DVIS == 0 (Direct virtual LPI injection not supported) - * LPIS == 0 (LPIs not supported) + * LPIS == 1 (LPIs are supported if affinity routing is enabled) + * num_LPIs == 0b00000 (bits [15:11],Number of LPIs as indicated + * by GICD_TYPER.IDbits) * MBIS == 0 (message-based SPIs not supported) * SecurityExtn == 1 if security extns supported * CPUNumber == 0 since for us ARE is always 1 @@ -XXX,XX +XXX,XX @@ static bool gicd_readl(GICv3State *s, hwaddr offset, bool sec_extn = !(s->gicd_ctlr & GICD_CTLR_DS); *data = (1 << 25) | (1 << 24) | (sec_extn << 10) | + (s->lpi_enable << GICD_TYPER_LPIS_SHIFT) | (0xf << 19) | itlinesnumber; return true; } diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ static MemTxResult gicr_writel(GICv3CPUState *cs, hwaddr offset, case GICR_CTLR: /* For our implementation, GICR_TYPER.DPGS is 0 and so all * the DPG bits are RAZ/WI. We don't do anything asynchronously, - * so UWP and RWP are RAZ/WI. And GICR_TYPER.LPIS is 0 (we don't - * implement LPIs) so Enable_LPIs is RES0. So there are no writable - * bits for us. + * so UWP and RWP are RAZ/WI. GICR_TYPER.LPIS is 1 (we + * implement LPIs) so Enable_LPIs is programmable. */ + if (cs->gicr_typer & GICR_TYPER_PLPIS) { + if (value & GICR_CTLR_ENABLE_LPIS) { + cs->gicr_ctlr |= GICR_CTLR_ENABLE_LPIS; + } else { + cs->gicr_ctlr &= ~GICR_CTLR_ENABLE_LPIS; + } + } return MEMTX_OK; case GICR_STATUSR: /* RAZ/WI for our implementation */ -- 2.20.1 From: Shashi Mallela <shashi.mallela@linaro.org> Implemented lpi processing at redistributor to get lpi config info from lpi configuration table,determine priority,set pending state in lpi pending table and forward the lpi to cpuif.Added logic to invoke redistributor lpi processing with translated LPI which set/clear LPI from ITS device as part of ITS INT,CLEAR,DISCARD command and GITS_TRANSLATER processing. Signed-off-by: Shashi Mallela <shashi.mallela@linaro.org> Tested-by: Neil Armstrong <narmstrong@baylibre.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210910143951.92242-7-shashi.mallela@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/gicv3_internal.h | 9 ++ include/hw/intc/arm_gicv3_common.h | 7 ++ hw/intc/arm_gicv3.c | 14 +++ hw/intc/arm_gicv3_common.c | 1 + hw/intc/arm_gicv3_cpuif.c | 7 +- hw/intc/arm_gicv3_its.c | 23 +++++ hw/intc/arm_gicv3_redist.c | 141 +++++++++++++++++++++++++++++ 7 files changed, 200 insertions(+), 2 deletions(-) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(GICR_PENDBASER, PHYADDR, 16, 36) FIELD(GICR_PENDBASER, OUTERCACHE, 56, 3) FIELD(GICR_PENDBASER, PTZ, 62, 1) +#define GICR_PROPBASER_IDBITS_THRESHOLD 0xd + #define ICC_CTLR_EL1_CBPR (1U << 0) #define ICC_CTLR_EL1_EOIMODE (1U << 1) #define ICC_CTLR_EL1_PMHE (1U << 6) @@ -XXX,XX +XXX,XX @@ FIELD(GITS_TYPER, CIL, 36, 1) #define L1TABLE_ENTRY_SIZE 8 +#define LPI_CTE_ENABLED TABLE_ENTRY_VALID_MASK +#define LPI_PRIORITY_MASK 0xfc + #define GITS_CMDQ_ENTRY_SIZE 32 #define NUM_BYTES_IN_DW 8 @@ -XXX,XX +XXX,XX @@ FIELD(MAPC, RDBASE, 16, 32) * Valid = 1 bit,RDBase = 36 bits(considering max RDBASE) */ #define GITS_CTE_SIZE (0x8ULL) +#define GITS_CTE_RDBASE_PROCNUM_MASK MAKE_64BIT_MASK(1, RDBASE_PROCNUM_LENGTH) /* Special interrupt IDs */ #define INTID_SECURE 1020 @@ -XXX,XX +XXX,XX @@ MemTxResult gicv3_redist_write(void *opaque, hwaddr offset, uint64_t data, unsigned size, MemTxAttrs attrs); void gicv3_dist_set_irq(GICv3State *s, int irq, int level); void gicv3_redist_set_irq(GICv3CPUState *cs, int irq, int level); +void gicv3_redist_process_lpi(GICv3CPUState *cs, int irq, int level); +void gicv3_redist_lpi_pending(GICv3CPUState *cs, int irq, int level); +void gicv3_redist_update_lpi(GICv3CPUState *cs); void gicv3_redist_send_sgi(GICv3CPUState *cs, int grp, int irq, bool ns); void gicv3_init_cpuif(GICv3State *s); diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3CPUState { * real state above; it doesn't need to be migrated. */ PendingIrq hppi; + + /* + * Cached information recalculated from LPI tables + * in guest memory + */ + PendingIrq hpplpi; + /* This is temporary working state, to avoid a malloc in gicv3_update() */ bool seenbetter; }; diff --git a/hw/intc/arm_gicv3.c b/hw/intc/arm_gicv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3.c +++ b/hw/intc/arm_gicv3.c @@ -XXX,XX +XXX,XX @@ static void gicv3_redist_update_noirqset(GICv3CPUState *cs) cs->hppi.grp = gicv3_irq_group(cs->gic, cs, cs->hppi.irq); } + if ((cs->gicr_ctlr & GICR_CTLR_ENABLE_LPIS) && cs->gic->lpi_enable && + (cs->hpplpi.prio != 0xff)) { + if (irqbetter(cs, cs->hpplpi.irq, cs->hpplpi.prio)) { + cs->hppi.irq = cs->hpplpi.irq; + cs->hppi.prio = cs->hpplpi.prio; + cs->hppi.grp = cs->hpplpi.grp; + seenbetter = true; + } + } + /* If the best interrupt we just found would preempt whatever * was the previous best interrupt before this update, then * we know it's definitely the best one now. @@ -XXX,XX +XXX,XX @@ static void gicv3_set_irq(void *opaque, int irq, int level) static void arm_gicv3_post_load(GICv3State *s) { + int i; /* Recalculate our cached idea of the current highest priority * pending interrupt, but don't set IRQ or FIQ lines. */ + for (i = 0; i < s->num_cpu; i++) { + gicv3_redist_update_lpi(&s->cpu[i]); + } gicv3_full_update_noirqset(s); /* Repopulate the cache of GICv3CPUState pointers for target CPUs */ gicv3_cache_all_target_cpustates(s); diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_common_reset(DeviceState *dev) memset(cs->gicr_ipriorityr, 0, sizeof(cs->gicr_ipriorityr)); cs->hppi.prio = 0xff; + cs->hpplpi.prio = 0xff; /* State in the CPU interface must *not* be reset here, because it * is part of the CPU's reset domain, not the GIC device's. diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ static void icc_activate_irq(GICv3CPUState *cs, int irq) cs->gicr_iactiver0 = deposit32(cs->gicr_iactiver0, irq, 1, 1); cs->gicr_ipendr0 = deposit32(cs->gicr_ipendr0, irq, 1, 0); gicv3_redist_update(cs); - } else { + } else if (irq < GICV3_LPI_INTID_START) { gicv3_gicd_active_set(cs->gic, irq); gicv3_gicd_pending_clear(cs->gic, irq); gicv3_update(cs->gic, irq, 1); + } else { + gicv3_redist_lpi_pending(cs, irq, 0); } } @@ -XXX,XX +XXX,XX @@ static void icc_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, trace_gicv3_icc_eoir_write(is_eoir0 ? 0 : 1, gicv3_redist_affid(cs), value); - if (irq >= cs->gic->num_irq) { + if ((irq >= cs->gic->num_irq) && + !(cs->gic->lpi_enable && (irq >= GICV3_LPI_INTID_START))) { /* This handles two cases: * 1. If software writes the ID of a spurious interrupt [ie 1020-1023] * to the GICC_EOIR, the GIC ignores that write. diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static bool process_its_cmd(GICv3ITSState *s, uint64_t value, uint32_t offset, uint64_t cte = 0; bool cte_valid = false; bool result = false; + uint64_t rdbase; if (cmd == NONE) { devid = offset; @@ -XXX,XX +XXX,XX @@ static bool process_its_cmd(GICv3ITSState *s, uint64_t value, uint32_t offset, * Current implementation only supports rdbase == procnum * Hence rdbase physical address is ignored */ + rdbase = (cte & GITS_CTE_RDBASE_PROCNUM_MASK) >> 1U; + + if (rdbase > s->gicv3->num_cpu) { + return result; + } + + if ((cmd == CLEAR) || (cmd == DISCARD)) { + gicv3_redist_process_lpi(&s->gicv3->cpu[rdbase], pIntid, 0); + } else { + gicv3_redist_process_lpi(&s->gicv3->cpu[rdbase], pIntid, 1); + } + if (cmd == DISCARD) { IteEntry ite = {}; /* remove mapping from interrupt translation table */ @@ -XXX,XX +XXX,XX @@ static void process_cmdq(GICv3ITSState *s) MemTxResult res = MEMTX_OK; bool result = true; uint8_t cmd; + int i; if (!(s->ctlr & ITS_CTLR_ENABLED)) { return; @@ -XXX,XX +XXX,XX @@ static void process_cmdq(GICv3ITSState *s) break; case GITS_CMD_INV: case GITS_CMD_INVALL: + /* + * Current implementation doesn't cache any ITS tables, + * but the calculated lpi priority information. We only + * need to trigger lpi priority re-calculation to be in + * sync with LPI config table or pending table changes. + */ + for (i = 0; i < s->gicv3->num_cpu; i++) { + gicv3_redist_update_lpi(&s->gicv3->cpu[i]); + } break; default: break; diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ static MemTxResult gicr_writel(GICv3CPUState *cs, hwaddr offset, if (cs->gicr_typer & GICR_TYPER_PLPIS) { if (value & GICR_CTLR_ENABLE_LPIS) { cs->gicr_ctlr |= GICR_CTLR_ENABLE_LPIS; + /* Check for any pending interr in pending table */ + gicv3_redist_update_lpi(cs); + gicv3_redist_update(cs); } else { cs->gicr_ctlr &= ~GICR_CTLR_ENABLE_LPIS; } @@ -XXX,XX +XXX,XX @@ MemTxResult gicv3_redist_write(void *opaque, hwaddr offset, uint64_t data, return r; } +static void gicv3_redist_check_lpi_priority(GICv3CPUState *cs, int irq) +{ + AddressSpace *as = &cs->gic->dma_as; + uint64_t lpict_baddr; + uint8_t lpite; + uint8_t prio; + + lpict_baddr = cs->gicr_propbaser & R_GICR_PROPBASER_PHYADDR_MASK; + + address_space_read(as, lpict_baddr + ((irq - GICV3_LPI_INTID_START) * + sizeof(lpite)), MEMTXATTRS_UNSPECIFIED, &lpite, + sizeof(lpite)); + + if (!(lpite & LPI_CTE_ENABLED)) { + return; + } + + if (cs->gic->gicd_ctlr & GICD_CTLR_DS) { + prio = lpite & LPI_PRIORITY_MASK; + } else { + prio = ((lpite & LPI_PRIORITY_MASK) >> 1) | 0x80; + } + + if ((prio < cs->hpplpi.prio) || + ((prio == cs->hpplpi.prio) && (irq <= cs->hpplpi.irq))) { + cs->hpplpi.irq = irq; + cs->hpplpi.prio = prio; + /* LPIs are always non-secure Grp1 interrupts */ + cs->hpplpi.grp = GICV3_G1NS; + } +} + +void gicv3_redist_update_lpi(GICv3CPUState *cs) +{ + /* + * This function scans the LPI pending table and for each pending + * LPI, reads the corresponding entry from LPI configuration table + * to extract the priority info and determine if the current LPI + * priority is lower than the last computed high priority lpi interrupt. + * If yes, replace current LPI as the new high priority lpi interrupt. + */ + AddressSpace *as = &cs->gic->dma_as; + uint64_t lpipt_baddr; + uint32_t pendt_size = 0; + uint8_t pend; + int i, bit; + uint64_t idbits; + + idbits = MIN(FIELD_EX64(cs->gicr_propbaser, GICR_PROPBASER, IDBITS), + GICD_TYPER_IDBITS); + + if (!(cs->gicr_ctlr & GICR_CTLR_ENABLE_LPIS) || !cs->gicr_propbaser || + !cs->gicr_pendbaser) { + return; + } + + cs->hpplpi.prio = 0xff; + + lpipt_baddr = cs->gicr_pendbaser & R_GICR_PENDBASER_PHYADDR_MASK; + + /* Determine the highest priority pending interrupt among LPIs */ + pendt_size = (1ULL << (idbits + 1)); + + for (i = GICV3_LPI_INTID_START / 8; i < pendt_size / 8; i++) { + address_space_read(as, lpipt_baddr + i, MEMTXATTRS_UNSPECIFIED, &pend, + sizeof(pend)); + + while (pend) { + bit = ctz32(pend); + gicv3_redist_check_lpi_priority(cs, i * 8 + bit); + pend &= ~(1 << bit); + } + } +} + +void gicv3_redist_lpi_pending(GICv3CPUState *cs, int irq, int level) +{ + /* + * This function updates the pending bit in lpi pending table for + * the irq being activated or deactivated. + */ + AddressSpace *as = &cs->gic->dma_as; + uint64_t lpipt_baddr; + bool ispend = false; + uint8_t pend; + + /* + * get the bit value corresponding to this irq in the + * lpi pending table + */ + lpipt_baddr = cs->gicr_pendbaser & R_GICR_PENDBASER_PHYADDR_MASK; + + address_space_read(as, lpipt_baddr + ((irq / 8) * sizeof(pend)), + MEMTXATTRS_UNSPECIFIED, &pend, sizeof(pend)); + + ispend = extract32(pend, irq % 8, 1); + + /* no change in the value of pending bit, return */ + if (ispend == level) { + return; + } + pend = deposit32(pend, irq % 8, 1, level ? 1 : 0); + + address_space_write(as, lpipt_baddr + ((irq / 8) * sizeof(pend)), + MEMTXATTRS_UNSPECIFIED, &pend, sizeof(pend)); + + /* + * check if this LPI is better than the current hpplpi, if yes + * just set hpplpi.prio and .irq without doing a full rescan + */ + if (level) { + gicv3_redist_check_lpi_priority(cs, irq); + } else { + if (irq == cs->hpplpi.irq) { + gicv3_redist_update_lpi(cs); + } + } +} + +void gicv3_redist_process_lpi(GICv3CPUState *cs, int irq, int level) +{ + uint64_t idbits; + + idbits = MIN(FIELD_EX64(cs->gicr_propbaser, GICR_PROPBASER, IDBITS), + GICD_TYPER_IDBITS); + + if (!(cs->gicr_ctlr & GICR_CTLR_ENABLE_LPIS) || !cs->gicr_propbaser || + !cs->gicr_pendbaser || (irq > (1ULL << (idbits + 1)) - 1) || + irq < GICV3_LPI_INTID_START) { + return; + } + + /* set/clear the pending bit for this irq */ + gicv3_redist_lpi_pending(cs, irq, level); + + gicv3_redist_update(cs); +} + void gicv3_redist_set_irq(GICv3CPUState *cs, int irq, int level) { /* Update redistributor state for a change in an external PPI input line */ -- 2.20.1 From: Shashi Mallela <shashi.mallela@linaro.org> Added expected IORT files applicable with latest GICv3 ITS changes.Temporarily differences in these files are okay. Signed-off-by: Shashi Mallela <shashi.mallela@linaro.org> Acked-by: Igor Mammedov <imammedo@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210910143951.92242-8-shashi.mallela@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/bios-tables-test-allowed-diff.h | 4 ++++ tests/data/acpi/virt/IORT | 0 tests/data/acpi/virt/IORT.memhp | 0 tests/data/acpi/virt/IORT.numamem | 0 tests/data/acpi/virt/IORT.pxb | 0 5 files changed, 4 insertions(+) create mode 100644 tests/data/acpi/virt/IORT create mode 100644 tests/data/acpi/virt/IORT.memhp create mode 100644 tests/data/acpi/virt/IORT.numamem create mode 100644 tests/data/acpi/virt/IORT.pxb diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/bios-tables-test-allowed-diff.h +++ b/tests/qtest/bios-tables-test-allowed-diff.h @@ -1 +1,5 @@ /* List of comma-separated changed AML files to ignore */ +"tests/data/acpi/virt/IORT", +"tests/data/acpi/virt/IORT.memhp", +"tests/data/acpi/virt/IORT.numamem", +"tests/data/acpi/virt/IORT.pxb", diff --git a/tests/data/acpi/virt/IORT b/tests/data/acpi/virt/IORT new file mode 100644 index XXXXXXX..XXXXXXX diff --git a/tests/data/acpi/virt/IORT.memhp b/tests/data/acpi/virt/IORT.memhp new file mode 100644 index XXXXXXX..XXXXXXX diff --git a/tests/data/acpi/virt/IORT.numamem b/tests/data/acpi/virt/IORT.numamem new file mode 100644 index XXXXXXX..XXXXXXX diff --git a/tests/data/acpi/virt/IORT.pxb b/tests/data/acpi/virt/IORT.pxb new file mode 100644 index XXXXXXX..XXXXXXX -- 2.20.1 From: Shashi Mallela <shashi.mallela@linaro.org> Included creation of ITS as part of virt platform GIC initialization. This Emulated ITS model now co-exists with kvm ITS and is enabled in absence of kvm irq kernel support in a platform. Signed-off-by: Shashi Mallela <shashi.mallela@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210910143951.92242-9-shashi.mallela@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/virt.h | 2 ++ target/arm/kvm_arm.h | 4 ++-- hw/arm/virt.c | 29 +++++++++++++++++++++++++++-- 3 files changed, 31 insertions(+), 4 deletions(-) diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -XXX,XX +XXX,XX @@ struct VirtMachineClass { MachineClass parent; bool disallow_affinity_adjustment; bool no_its; + bool no_tcg_its; bool no_pmu; bool claim_edge_triggered_timers; bool smbios_old_sys_ver; @@ -XXX,XX +XXX,XX @@ struct VirtMachineState { bool highmem; bool highmem_ecam; bool its; + bool tcg_its; bool virt; bool ras; bool mte; diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm_arm.h +++ b/target/arm/kvm_arm.h @@ -XXX,XX +XXX,XX @@ static inline const char *its_class_name(void) /* KVM implementation requires this capability */ return kvm_direct_msi_enabled() ? "arm-its-kvm" : NULL; } else { - /* Software emulation is not implemented yet */ - return NULL; + /* Software emulation based model */ + return "arm-gicv3-its"; } } diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void create_its(VirtMachineState *vms) const char *itsclass = its_class_name(); DeviceState *dev; + if (!strcmp(itsclass, "arm-gicv3-its")) { + if (!vms->tcg_its) { + itsclass = NULL; + } + } + if (!itsclass) { /* Do nothing if not supported */ return; @@ -XXX,XX +XXX,XX @@ static void create_v2m(VirtMachineState *vms) vms->msi_controller = VIRT_MSI_CTRL_GICV2M; } -static void create_gic(VirtMachineState *vms) +static void create_gic(VirtMachineState *vms, MemoryRegion *mem) { MachineState *ms = MACHINE(vms); /* We create a standalone GIC */ @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms) nb_redist_regions); qdev_prop_set_uint32(vms->gic, "redist-region-count[0]", redist0_count); + if (!kvm_irqchip_in_kernel()) { + if (vms->tcg_its) { + object_property_set_link(OBJECT(vms->gic), "sysmem", + OBJECT(mem), &error_fatal); + qdev_prop_set_bit(vms->gic, "has-lpi", true); + } + } + if (nb_redist_regions == 2) { uint32_t redist1_capacity = vms->memmap[VIRT_HIGH_GIC_REDIST2].size / GICV3_REDIST_SIZE; @@ -XXX,XX +XXX,XX @@ static void machvirt_init(MachineState *machine) virt_flash_fdt(vms, sysmem, secure_sysmem ?: sysmem); - create_gic(vms); + create_gic(vms, sysmem); virt_cpu_post_init(vms, sysmem); @@ -XXX,XX +XXX,XX @@ static void virt_instance_init(Object *obj) } else { /* Default allows ITS instantiation */ vms->its = true; + + if (vmc->no_tcg_its) { + vms->tcg_its = false; + } else { + vms->tcg_its = true; + } } /* Default disallows iommu instantiation */ @@ -XXX,XX +XXX,XX @@ DEFINE_VIRT_MACHINE_AS_LATEST(6, 2) static void virt_machine_6_1_options(MachineClass *mc) { + VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc)); + virt_machine_6_2_options(mc); compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len); + + /* qemu ITS was introduced with 6.2 */ + vmc->no_tcg_its = true; } DEFINE_VIRT_MACHINE(6, 1) -- 2.20.1 From: Shashi Mallela <shashi.mallela@linaro.org> Updated expected IORT files applicable with latest GICv3 ITS changes. Full diff of new file disassembly: /* * Intel ACPI Component Architecture * AML/ASL+ Disassembler version 20180629 (64-bit version) * Copyright (c) 2000 - 2018 Intel Corporation * * Disassembly of tests/data/acpi/virt/IORT.pxb, Tue Jun 29 17:35:38 2021 * * ACPI Data Table [IORT] * * Format: [HexOffset DecimalOffset ByteLength] FieldName : FieldValue */ [000h 0000 4] Signature : "IORT" [IO Remapping Table] [004h 0004 4] Table Length : 0000007C [008h 0008 1] Revision : 00 [009h 0009 1] Checksum : 07 [00Ah 0010 6] Oem ID : "BOCHS " [010h 0016 8] Oem Table ID : "BXPC " [018h 0024 4] Oem Revision : 00000001 [01Ch 0028 4] Asl Compiler ID : "BXPC" [020h 0032 4] Asl Compiler Revision : 00000001 [024h 0036 4] Node Count : 00000002 [028h 0040 4] Node Offset : 00000030 [02Ch 0044 4] Reserved : 00000000 [030h 0048 1] Type : 00 [031h 0049 2] Length : 0018 [033h 0051 1] Revision : 00 [034h 0052 4] Reserved : 00000000 [038h 0056 4] Mapping Count : 00000000 [03Ch 0060 4] Mapping Offset : 00000000 [040h 0064 4] ItsCount : 00000001 [044h 0068 4] Identifiers : 00000000 [048h 0072 1] Type : 02 [049h 0073 2] Length : 0034 [04Bh 0075 1] Revision : 00 [04Ch 0076 4] Reserved : 00000000 [050h 0080 4] Mapping Count : 00000001 [054h 0084 4] Mapping Offset : 00000020 [058h 0088 8] Memory Properties : [IORT Memory Access Properties] [058h 0088 4] Cache Coherency : 00000001 [05Ch 0092 1] Hints (decoded below) : 00 Transient : 0 Write Allocate : 0 Read Allocate : 0 Override : 0 [05Dh 0093 2] Reserved : 0000 [05Fh 0095 1] Memory Flags (decoded below) : 03 Coherency : 1 Device Attribute : 1 [060h 0096 4] ATS Attribute : 00000000 [064h 0100 4] PCI Segment Number : 00000000 [068h 0104 1] Memory Size Limit : 00 [069h 0105 3] Reserved : 000000 [068h 0104 4] Input base : 00000000 [06Ch 0108 4] ID Count : 0000FFFF [070h 0112 4] Output Base : 00000000 [074h 0116 4] Output Reference : 00000030 [078h 0120 4] Flags (decoded below) : 00000000 Single Mapping : 0 Raw Table Data: Length 124 (0x7C) 0000: 49 4F 52 54 7C 00 00 00 00 07 42 4F 43 48 53 20 // IORT|.....BOCHS 0010: 42 58 50 43 20 20 20 20 01 00 00 00 42 58 50 43 // BXPC ....BXPC 0020: 01 00 00 00 02 00 00 00 30 00 00 00 00 00 00 00 // ........0....... 0030: 00 18 00 00 00 00 00 00 00 00 00 00 00 00 00 00 // ................ 0040: 01 00 00 00 00 00 00 00 02 34 00 00 00 00 00 00 // .........4...... 0050: 01 00 00 00 20 00 00 00 01 00 00 00 00 00 00 03 // .... ........... 0060: 00 00 00 00 00 00 00 00 00 00 00 00 FF FF 00 00 // ................ 0070: 00 00 00 00 30 00 00 00 00 00 00 00 // ....0....... Signed-off-by: Shashi Mallela <shashi.mallela@linaro.org> Acked-by: Igor Mammedov <imammedo@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210910143951.92242-10-shashi.mallela@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/bios-tables-test-allowed-diff.h | 4 ---- tests/data/acpi/virt/IORT | Bin 0 -> 124 bytes tests/data/acpi/virt/IORT.memhp | Bin 0 -> 124 bytes tests/data/acpi/virt/IORT.numamem | Bin 0 -> 124 bytes tests/data/acpi/virt/IORT.pxb | Bin 0 -> 124 bytes 5 files changed, 4 deletions(-) diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/bios-tables-test-allowed-diff.h +++ b/tests/qtest/bios-tables-test-allowed-diff.h @@ -1,5 +1 @@ /* List of comma-separated changed AML files to ignore */ -"tests/data/acpi/virt/IORT", -"tests/data/acpi/virt/IORT.memhp", -"tests/data/acpi/virt/IORT.numamem", -"tests/data/acpi/virt/IORT.pxb", diff --git a/tests/data/acpi/virt/IORT b/tests/data/acpi/virt/IORT index XXXXXXX..XXXXXXX 100644 GIT binary patch literal 124 zcmebD4+^Pa00MR=e`k+i1*eDrX9XZ&1PX!JAesq?4S*O7Bw!2(4Uz`|CKCt^;wu0# QRGb+i3L*dhhtM#y0PN=p0RR91 literal 0 HcmV?d00001 diff --git a/tests/data/acpi/virt/IORT.memhp b/tests/data/acpi/virt/IORT.memhp index XXXXXXX..XXXXXXX 100644 GIT binary patch literal 124 zcmebD4+^Pa00MR=e`k+i1*eDrX9XZ&1PX!JAesq?4S*O7Bw!2(4Uz`|CKCt^;wu0# QRGb+i3L*dhhtM#y0PN=p0RR91 literal 0 HcmV?d00001 diff --git a/tests/data/acpi/virt/IORT.numamem b/tests/data/acpi/virt/IORT.numamem index XXXXXXX..XXXXXXX 100644 GIT binary patch literal 124 zcmebD4+^Pa00MR=e`k+i1*eDrX9XZ&1PX!JAesq?4S*O7Bw!2(4Uz`|CKCt^;wu0# QRGb+i3L*dhhtM#y0PN=p0RR91 literal 0 HcmV?d00001 diff --git a/tests/data/acpi/virt/IORT.pxb b/tests/data/acpi/virt/IORT.pxb index XXXXXXX..XXXXXXX 100644 GIT binary patch literal 124 zcmebD4+^Pa00MR=e`k+i1*eDrX9XZ&1PX!JAesq?4S*O7Bw!2(4Uz`|CKCt^;wu0# QRGb+i3L*dhhtM#y0PN=p0RR91 literal 0 HcmV?d00001 -- 2.20.1 In v8A, the PSTATE.IL bit is set for various kinds of illegal exception return or mode-change attempts. We already set PSTATE.IL (or its AArch32 equivalent CPSR.IL) in all those cases, but we weren't implementing the part of the behaviour where attempting to execute an instruction with PSTATE.IL takes an immediate exception with an appropriate syndrome value. Add a new TB flags bit tracking PSTATE.IL/CPSR.IL, and generate code to take an exception instead of whatever the instruction would have been. PSTATE.IL and CPSR.IL change only on exception entry, attempted exception exit, and various AArch32 mode changes via cpsr_write(). These places generally already rebuild the hflags, so the only place we need an extra rebuild_hflags call is in the illegal-return codepath of the AArch64 exception_return helper. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210821195958.41312-2-richard.henderson@linaro.org Message-Id: <20210817162118.24319-1-peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> [rth: Added missing returns; set IL bit in syndrome] Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/cpu.h | 1 + target/arm/syndrome.h | 5 +++++ target/arm/translate.h | 2 ++ target/arm/helper-a64.c | 1 + target/arm/helper.c | 8 ++++++++ target/arm/translate-a64.c | 11 +++++++++++ target/arm/translate.c | 21 +++++++++++++++++++++ 7 files changed, 49 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_ANY, FPEXC_EL, 8, 2) FIELD(TBFLAG_ANY, DEBUG_TARGET_EL, 10, 2) /* Memory operations require alignment: SCTLR_ELx.A or CCR.UNALIGN_TRP */ FIELD(TBFLAG_ANY, ALIGN_MEM, 12, 1) +FIELD(TBFLAG_ANY, PSTATE__IL, 13, 1) /* * Bit usage when in AArch32 state, both A- and M-profile. diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit) (cv << 24) | (cond << 20) | ti; } +static inline uint32_t syn_illegalstate(void) +{ + return (EC_ILLEGALSTATE << ARM_EL_EC_SHIFT) | ARM_EL_IL; +} + #endif /* TARGET_ARM_SYNDROME_H */ 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 hstr_active; /* True if memory operations require alignment */ bool align_mem; + /* True if PSTATE.IL is set */ + bool pstate_il; /* * >= 0, a copy of PSTATE.BTYPE, which will be 0 without v8.5-BTI. * < 0, set by the current instruction. 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 @@ illegal_return: if (!arm_singlestep_active(env)) { env->pstate &= ~PSTATE_SS; } + helper_rebuild_hflags_a64(env, cur_el); qemu_log_mask(LOG_GUEST_ERROR, "Illegal exception return at EL%d: " "resuming execution at 0x%" PRIx64 "\n", cur_el, env->pc); } 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 CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el, DP_TBFLAG_A32(flags, HSTR_ACTIVE, 1); } + if (env->uncached_cpsr & CPSR_IL) { + DP_TBFLAG_ANY(flags, PSTATE__IL, 1); + } + return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); } @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, } } + if (env->pstate & PSTATE_IL) { + DP_TBFLAG_ANY(flags, PSTATE__IL, 1); + } + if (cpu_isar_feature(aa64_mte, env_archcpu(env))) { /* * Set MTE_ACTIVE if any access may be Checked, and leave clear diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_a64_insn(CPUARMState *env, DisasContext *s) s->fp_access_checked = false; s->sve_access_checked = false; + if (s->pstate_il) { + /* + * Illegal execution state. This has priority over BTI + * exceptions, but comes after instruction abort exceptions. + */ + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_illegalstate(), default_exception_el(s)); + return; + } + if (dc_isar_feature(aa64_bti, s)) { if (s->base.num_insns == 1) { /* @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, #endif dc->fp_excp_el = EX_TBFLAG_ANY(tb_flags, FPEXC_EL); dc->align_mem = EX_TBFLAG_ANY(tb_flags, ALIGN_MEM); + dc->pstate_il = EX_TBFLAG_ANY(tb_flags, PSTATE__IL); dc->sve_excp_el = EX_TBFLAG_A64(tb_flags, SVEEXC_EL); dc->sve_len = (EX_TBFLAG_A64(tb_flags, ZCR_LEN) + 1) * 16; dc->pauth_active = EX_TBFLAG_A64(tb_flags, PAUTH_ACTIVE); 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 disas_arm_insn(DisasContext *s, unsigned int insn) return; } + if (s->pstate_il) { + /* + * Illegal execution state. This has priority over BTI + * exceptions, but comes after instruction abort exceptions. + */ + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_illegalstate(), default_exception_el(s)); + return; + } + if (cond == 0xf) { /* In ARMv3 and v4 the NV condition is UNPREDICTABLE; we * choose to UNDEF. In ARMv5 and above the space is used @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) #endif dc->fp_excp_el = EX_TBFLAG_ANY(tb_flags, FPEXC_EL); dc->align_mem = EX_TBFLAG_ANY(tb_flags, ALIGN_MEM); + dc->pstate_il = EX_TBFLAG_ANY(tb_flags, PSTATE__IL); if (arm_feature(env, ARM_FEATURE_M)) { dc->vfp_enabled = 1; @@ -XXX,XX +XXX,XX @@ static void thumb_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) } dc->insn = insn; + if (dc->pstate_il) { + /* + * Illegal execution state. This has priority over BTI + * exceptions, but comes after instruction abort exceptions. + */ + gen_exception_insn(dc, dc->pc_curr, EXCP_UDEF, + syn_illegalstate(), default_exception_el(dc)); + return; + } + if (dc->eci) { /* * For M-profile continuable instructions, ECI/ICI handling -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> It is confusing to have different exits from translation for various conditions in separate functions. Merge disas_a64_insn into its only caller. Standardize on the "s" name for the DisasContext, as the code from disas_a64_insn had more instances. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210821195958.41312-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 224 ++++++++++++++++++------------------- 1 file changed, 109 insertions(+), 115 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool btype_destination_ok(uint32_t insn, bool bt, int btype) return false; } -/* C3.1 A64 instruction index by encoding */ -static void disas_a64_insn(CPUARMState *env, DisasContext *s) -{ - uint32_t insn; - - s->pc_curr = s->base.pc_next; - insn = arm_ldl_code(env, s->base.pc_next, s->sctlr_b); - s->insn = insn; - s->base.pc_next += 4; - - s->fp_access_checked = false; - s->sve_access_checked = false; - - if (s->pstate_il) { - /* - * Illegal execution state. This has priority over BTI - * exceptions, but comes after instruction abort exceptions. - */ - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, - syn_illegalstate(), default_exception_el(s)); - return; - } - - if (dc_isar_feature(aa64_bti, s)) { - if (s->base.num_insns == 1) { - /* - * At the first insn of the TB, compute s->guarded_page. - * We delayed computing this until successfully reading - * the first insn of the TB, above. This (mostly) ensures - * that the softmmu tlb entry has been populated, and the - * page table GP bit is available. - * - * Note that we need to compute this even if btype == 0, - * because this value is used for BR instructions later - * where ENV is not available. - */ - s->guarded_page = is_guarded_page(env, s); - - /* First insn can have btype set to non-zero. */ - tcg_debug_assert(s->btype >= 0); - - /* - * Note that the Branch Target Exception has fairly high - * priority -- below debugging exceptions but above most - * everything else. This allows us to handle this now - * instead of waiting until the insn is otherwise decoded. - */ - if (s->btype != 0 - && s->guarded_page - && !btype_destination_ok(insn, s->bt, s->btype)) { - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, - syn_btitrap(s->btype), - default_exception_el(s)); - return; - } - } else { - /* Not the first insn: btype must be 0. */ - tcg_debug_assert(s->btype == 0); - } - } - - switch (extract32(insn, 25, 4)) { - case 0x0: case 0x1: case 0x3: /* UNALLOCATED */ - unallocated_encoding(s); - break; - case 0x2: - if (!dc_isar_feature(aa64_sve, s) || !disas_sve(s, insn)) { - unallocated_encoding(s); - } - break; - case 0x8: case 0x9: /* Data processing - immediate */ - disas_data_proc_imm(s, insn); - break; - case 0xa: case 0xb: /* Branch, exception generation and system insns */ - disas_b_exc_sys(s, insn); - break; - case 0x4: - case 0x6: - case 0xc: - case 0xe: /* Loads and stores */ - disas_ldst(s, insn); - break; - case 0x5: - case 0xd: /* Data processing - register */ - disas_data_proc_reg(s, insn); - break; - case 0x7: - case 0xf: /* Data processing - SIMD and floating point */ - disas_data_proc_simd_fp(s, insn); - break; - default: - assert(FALSE); /* all 15 cases should be handled above */ - break; - } - - /* if we allocated any temporaries, free them here */ - free_tmp_a64(s); - - /* - * After execution of most insns, btype is reset to 0. - * Note that we set btype == -1 when the insn sets btype. - */ - if (s->btype > 0 && s->base.is_jmp != DISAS_NORETURN) { - reset_btype(s); - } -} - static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cpu) { @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu) static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) { - DisasContext *dc = container_of(dcbase, DisasContext, base); + DisasContext *s = container_of(dcbase, DisasContext, base); CPUARMState *env = cpu->env_ptr; + uint32_t insn; - if (dc->ss_active && !dc->pstate_ss) { + if (s->ss_active && !s->pstate_ss) { /* Singlestep state is Active-pending. * If we're in this state at the start of a TB then either * a) we just took an exception to an EL which is being debugged @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) * "did not step an insn" case, and so the syndrome ISV and EX * bits should be zero. */ - assert(dc->base.num_insns == 1); - gen_swstep_exception(dc, 0, 0); - dc->base.is_jmp = DISAS_NORETURN; - } else { - disas_a64_insn(env, dc); + assert(s->base.num_insns == 1); + gen_swstep_exception(s, 0, 0); + s->base.is_jmp = DISAS_NORETURN; + return; } - translator_loop_temp_check(&dc->base); + s->pc_curr = s->base.pc_next; + insn = arm_ldl_code(env, s->base.pc_next, s->sctlr_b); + s->insn = insn; + s->base.pc_next += 4; + + s->fp_access_checked = false; + s->sve_access_checked = false; + + if (s->pstate_il) { + /* + * Illegal execution state. This has priority over BTI + * exceptions, but comes after instruction abort exceptions. + */ + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_illegalstate(), default_exception_el(s)); + return; + } + + if (dc_isar_feature(aa64_bti, s)) { + if (s->base.num_insns == 1) { + /* + * At the first insn of the TB, compute s->guarded_page. + * We delayed computing this until successfully reading + * the first insn of the TB, above. This (mostly) ensures + * that the softmmu tlb entry has been populated, and the + * page table GP bit is available. + * + * Note that we need to compute this even if btype == 0, + * because this value is used for BR instructions later + * where ENV is not available. + */ + s->guarded_page = is_guarded_page(env, s); + + /* First insn can have btype set to non-zero. */ + tcg_debug_assert(s->btype >= 0); + + /* + * Note that the Branch Target Exception has fairly high + * priority -- below debugging exceptions but above most + * everything else. This allows us to handle this now + * instead of waiting until the insn is otherwise decoded. + */ + if (s->btype != 0 + && s->guarded_page + && !btype_destination_ok(insn, s->bt, s->btype)) { + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_btitrap(s->btype), + default_exception_el(s)); + return; + } + } else { + /* Not the first insn: btype must be 0. */ + tcg_debug_assert(s->btype == 0); + } + } + + switch (extract32(insn, 25, 4)) { + case 0x0: case 0x1: case 0x3: /* UNALLOCATED */ + unallocated_encoding(s); + break; + case 0x2: + if (!dc_isar_feature(aa64_sve, s) || !disas_sve(s, insn)) { + unallocated_encoding(s); + } + break; + case 0x8: case 0x9: /* Data processing - immediate */ + disas_data_proc_imm(s, insn); + break; + case 0xa: case 0xb: /* Branch, exception generation and system insns */ + disas_b_exc_sys(s, insn); + break; + case 0x4: + case 0x6: + case 0xc: + case 0xe: /* Loads and stores */ + disas_ldst(s, insn); + break; + case 0x5: + case 0xd: /* Data processing - register */ + disas_data_proc_reg(s, insn); + break; + case 0x7: + case 0xf: /* Data processing - SIMD and floating point */ + disas_data_proc_simd_fp(s, insn); + break; + default: + assert(FALSE); /* all 15 cases should be handled above */ + break; + } + + /* if we allocated any temporaries, free them here */ + free_tmp_a64(s); + + /* + * After execution of most insns, btype is reset to 0. + * Note that we set btype == -1 when the insn sets btype. + */ + if (s->btype > 0 && s->base.is_jmp != DISAS_NORETURN) { + reset_btype(s); + } + + translator_loop_temp_check(&s->base); } static void aarch64_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu) -- 2.20.1 By default, QEMU will allow devices to be plugged into a bus up to the bus class's device count limit. If the user creates a device on the command line or via the monitor and doesn't explicitly specify the bus to plug it in, QEMU will plug it into the first non-full bus that it finds. This is fine in most cases, but some machines have multiple buses of a given type, some of which are dedicated to on-board devices and some of which have an externally exposed connector for user-pluggable devices. One example is I2C buses. Provide a new function qbus_mark_full() so that a machine model can mark this kind of "internal only" bus as 'full' after it has created all the devices that should be plugged into that bus. The "find a non-full bus" algorithm will then skip the internal-only bus when looking for a place to plug in user-created devices. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210903151435.22379-2-peter.maydell@linaro.org --- include/hw/qdev-core.h | 24 ++++++++++++++++++++++++ softmmu/qdev-monitor.c | 7 ++++++- 2 files changed, 30 insertions(+), 1 deletion(-) diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/qdev-core.h +++ b/include/hw/qdev-core.h @@ -XXX,XX +XXX,XX @@ struct BusState { HotplugHandler *hotplug_handler; int max_index; bool realized; + bool full; int num_children; /* @@ -XXX,XX +XXX,XX @@ static inline bool qbus_is_hotpluggable(BusState *bus) return bus->hotplug_handler; } +/** + * qbus_mark_full: Mark this bus as full, so no more devices can be attached + * @bus: Bus to mark as full + * + * By default, QEMU will allow devices to be plugged into a bus up + * to the bus class's device count limit. Calling this function + * marks a particular bus as full, so that no more devices can be + * plugged into it. In particular this means that the bus will not + * be considered as a candidate for plugging in devices created by + * the user on the commandline or via the monitor. + * If a machine has multiple buses of a given type, such as I2C, + * where some of those buses in the real hardware are used only for + * internal devices and some are exposed via expansion ports, you + * can use this function to mark the internal-only buses as full + * after you have created all their internal devices. Then user + * created devices will appear on the expansion-port bus where + * guest software expects them. + */ +static inline void qbus_mark_full(BusState *bus) +{ + bus->full = true; +} + void device_listener_register(DeviceListener *listener); void device_listener_unregister(DeviceListener *listener); diff --git a/softmmu/qdev-monitor.c b/softmmu/qdev-monitor.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/qdev-monitor.c +++ b/softmmu/qdev-monitor.c @@ -XXX,XX +XXX,XX @@ static DeviceState *qbus_find_dev(BusState *bus, char *elem) static inline bool qbus_is_full(BusState *bus) { - BusClass *bus_class = BUS_GET_CLASS(bus); + BusClass *bus_class; + + if (bus->full) { + return true; + } + bus_class = BUS_GET_CLASS(bus); return bus_class->max_dev && bus->num_children >= bus_class->max_dev; } -- 2.20.1 The mps2-tz boards use a data-driven structure to create the devices that sit behind peripheral protection controllers. Currently the functions which create these devices are passed an 'opaque' pointer which is always the address within the machine struct of the device to create, and some "all devices need this" information like irqs and addresses. If a specific device needs more information than this, it is currently not possible to pass that through from the PPCInfo data structure. Add support for passing an extra data parameter, so that we can more flexibly handle the needs of specific device types. To provide some type-safety we make this extra parameter a pointer to a union (which initially has no members). In particular, we would like to be able to indicate which of the i2c controllers are for on-board devices only and which are connected to the external 'shield' expansion port; a subsequent patch will use this mechanism for that purpose. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210903151435.22379-3-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 35 ++++++++++++++++++++++------------- 1 file changed, 22 insertions(+), 13 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static qemu_irq get_sse_irq_in(MPS2TZMachineState *mms, int irqno) } } +/* Union describing the device-specific extra data we pass to the devfn. */ +typedef union PPCExtraData { +} PPCExtraData; + /* Most of the devices in the AN505 FPGA image sit behind * Peripheral Protection Controllers. These data structures * define the layout of which devices sit behind which PPCs. @@ -XXX,XX +XXX,XX @@ static qemu_irq get_sse_irq_in(MPS2TZMachineState *mms, int irqno) */ typedef MemoryRegion *MakeDevFn(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs); + const int *irqs, + const PPCExtraData *extradata); typedef struct PPCPortInfo { const char *name; @@ -XXX,XX +XXX,XX @@ typedef struct PPCPortInfo { hwaddr addr; hwaddr size; int irqs[3]; /* currently no device needs more IRQ lines than this */ + PPCExtraData extradata; /* to pass device-specific info to the devfn */ } PPCPortInfo; typedef struct PPCInfo { @@ -XXX,XX +XXX,XX @@ typedef struct PPCInfo { static MemoryRegion *make_unimp_dev(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, + const PPCExtraData *extradata) { /* Initialize, configure and realize a TYPE_UNIMPLEMENTED_DEVICE, * and return a pointer to its MemoryRegion. @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_unimp_dev(MPS2TZMachineState *mms, static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { /* The irq[] array is tx, rx, combined, in that order */ MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { MPS2SCC *scc = opaque; DeviceState *sccdev; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_fpgaio(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { MPS2FPGAIO *fpgaio = opaque; MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_fpgaio(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, + const PPCExtraData *extradata) { SysBusDevice *s; NICInfo *nd = &nd_table[0]; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_eth_usb(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, + const PPCExtraData *extradata) { /* * The AN524 makes the ethernet and USB share a PPC port. @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_eth_usb(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_mpc(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { TZMPC *mpc = opaque; int i = mpc - &mms->mpc[0]; @@ -XXX,XX +XXX,XX @@ static void remap_irq_fn(void *opaque, int n, int level) static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { /* The irq[] array is DMACINTR, DMACINTERR, DMACINTTC, in that order */ PL080State *dma = opaque; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_spi(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { /* * The AN505 has five PL022 SPI controllers. @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_spi(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_i2c(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { ArmSbconI2CState *i2c = opaque; SysBusDevice *s; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_i2c(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_rtc(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { PL031State *pl031 = opaque; SysBusDevice *s; @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) } mr = pinfo->devfn(mms, pinfo->opaque, pinfo->name, pinfo->size, - pinfo->irqs); + pinfo->irqs, &pinfo->extradata); portname = g_strdup_printf("port[%d]", port); object_property_set_link(OBJECT(ppc), portname, OBJECT(mr), &error_fatal); -- 2.20.1 The various MPS2 boards have multiple I2C buses: typically a bus dedicated to the audio configuration, one for the LCD touchscreen controller, one for a DDR4 EEPROM, and two which are connected to the external Shield expansion connector. Mark the buses which are used only for board-internal devices as 'full' so that if the user creates i2c devices on the commandline without specifying a bus name then they will be connected to the I2C controller used for the Shield connector, where guest software will expect them. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210903151435.22379-4-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 57 ++++++++++++++++++++++++++++++++++++------------ 1 file changed, 43 insertions(+), 14 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static qemu_irq get_sse_irq_in(MPS2TZMachineState *mms, int irqno) /* Union describing the device-specific extra data we pass to the devfn. */ typedef union PPCExtraData { + bool i2c_internal; } PPCExtraData; /* Most of the devices in the AN505 FPGA image sit behind @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_i2c(MPS2TZMachineState *mms, void *opaque, object_initialize_child(OBJECT(mms), name, i2c, TYPE_ARM_SBCON_I2C); s = SYS_BUS_DEVICE(i2c); sysbus_realize(s, &error_fatal); + + /* + * If this is an internal-use-only i2c bus, mark it full + * so that user-created i2c devices are not plugged into it. + * If we implement models of any on-board i2c devices that + * plug in to one of the internal-use-only buses, then we will + * need to create and plugging those in here before we mark the + * bus as full. + */ + if (extradata->i2c_internal) { + BusState *qbus = qdev_get_child_bus(DEVICE(i2c), "i2c"); + qbus_mark_full(qbus); + } + return sysbus_mmio_get_region(s, 0); } @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) { "uart2", make_uart, &mms->uart[2], 0x40202000, 0x1000, { 36, 37, 44 } }, { "uart3", make_uart, &mms->uart[3], 0x40203000, 0x1000, { 38, 39, 45 } }, { "uart4", make_uart, &mms->uart[4], 0x40204000, 0x1000, { 40, 41, 46 } }, - { "i2c0", make_i2c, &mms->i2c[0], 0x40207000, 0x1000 }, - { "i2c1", make_i2c, &mms->i2c[1], 0x40208000, 0x1000 }, - { "i2c2", make_i2c, &mms->i2c[2], 0x4020c000, 0x1000 }, - { "i2c3", make_i2c, &mms->i2c[3], 0x4020d000, 0x1000 }, + { "i2c0", make_i2c, &mms->i2c[0], 0x40207000, 0x1000, {}, + { .i2c_internal = true /* touchscreen */ } }, + { "i2c1", make_i2c, &mms->i2c[1], 0x40208000, 0x1000, {}, + { .i2c_internal = true /* audio conf */ } }, + { "i2c2", make_i2c, &mms->i2c[2], 0x4020c000, 0x1000, {}, + { .i2c_internal = false /* shield 0 */ } }, + { "i2c3", make_i2c, &mms->i2c[3], 0x4020d000, 0x1000, {}, + { .i2c_internal = false /* shield 1 */ } }, }, }, { .name = "apb_ppcexp2", @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) }, { .name = "apb_ppcexp1", .ports = { - { "i2c0", make_i2c, &mms->i2c[0], 0x41200000, 0x1000 }, - { "i2c1", make_i2c, &mms->i2c[1], 0x41201000, 0x1000 }, + { "i2c0", make_i2c, &mms->i2c[0], 0x41200000, 0x1000, {}, + { .i2c_internal = true /* touchscreen */ } }, + { "i2c1", make_i2c, &mms->i2c[1], 0x41201000, 0x1000, {}, + { .i2c_internal = true /* audio conf */ } }, { "spi0", make_spi, &mms->spi[0], 0x41202000, 0x1000, { 52 } }, { "spi1", make_spi, &mms->spi[1], 0x41203000, 0x1000, { 53 } }, { "spi2", make_spi, &mms->spi[2], 0x41204000, 0x1000, { 54 } }, - { "i2c2", make_i2c, &mms->i2c[2], 0x41205000, 0x1000 }, - { "i2c3", make_i2c, &mms->i2c[3], 0x41206000, 0x1000 }, + { "i2c2", make_i2c, &mms->i2c[2], 0x41205000, 0x1000, {}, + { .i2c_internal = false /* shield 0 */ } }, + { "i2c3", make_i2c, &mms->i2c[3], 0x41206000, 0x1000, {}, + { .i2c_internal = false /* shield 1 */ } }, { /* port 7 reserved */ }, - { "i2c4", make_i2c, &mms->i2c[4], 0x41208000, 0x1000 }, + { "i2c4", make_i2c, &mms->i2c[4], 0x41208000, 0x1000, {}, + { .i2c_internal = true /* DDR4 EEPROM */ } }, }, }, { .name = "apb_ppcexp2", @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) }, { .name = "apb_ppcexp1", .ports = { - { "i2c0", make_i2c, &mms->i2c[0], 0x49200000, 0x1000 }, - { "i2c1", make_i2c, &mms->i2c[1], 0x49201000, 0x1000 }, + { "i2c0", make_i2c, &mms->i2c[0], 0x49200000, 0x1000, {}, + { .i2c_internal = true /* touchscreen */ } }, + { "i2c1", make_i2c, &mms->i2c[1], 0x49201000, 0x1000, {}, + { .i2c_internal = true /* audio conf */ } }, { "spi0", make_spi, &mms->spi[0], 0x49202000, 0x1000, { 53 } }, { "spi1", make_spi, &mms->spi[1], 0x49203000, 0x1000, { 54 } }, { "spi2", make_spi, &mms->spi[2], 0x49204000, 0x1000, { 55 } }, - { "i2c2", make_i2c, &mms->i2c[2], 0x49205000, 0x1000 }, - { "i2c3", make_i2c, &mms->i2c[3], 0x49206000, 0x1000 }, + { "i2c2", make_i2c, &mms->i2c[2], 0x49205000, 0x1000, {}, + { .i2c_internal = false /* shield 0 */ } }, + { "i2c3", make_i2c, &mms->i2c[3], 0x49206000, 0x1000, {}, + { .i2c_internal = false /* shield 1 */ } }, { /* port 7 reserved */ }, - { "i2c4", make_i2c, &mms->i2c[4], 0x49208000, 0x1000 }, + { "i2c4", make_i2c, &mms->i2c[4], 0x49208000, 0x1000, {}, + { .i2c_internal = true /* DDR4 EEPROM */ } }, }, }, { .name = "apb_ppcexp2", -- 2.20.1 The various MPS2 boards implemented in mps2.c have multiple I2C buses: a bus dedicated to the audio configuration, one for the LCD touchscreen controller, and two which are connected to the external Shield expansion connector. Mark the buses which are used only for board-internal devices as 'full' so that if the user creates i2c devices on the commandline without specifying a bus name then they will be connected to the I2C controller used for the Shield connector, where guest software will expect them. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210903151435.22379-5-peter.maydell@linaro.org --- hw/arm/mps2.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2.c +++ b/hw/arm/mps2.c @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) 0x40023000, /* Audio */ 0x40029000, /* Shield0 */ 0x4002a000}; /* Shield1 */ - sysbus_create_simple(TYPE_ARM_SBCON_I2C, i2cbase[i], NULL); + DeviceState *dev; + + dev = sysbus_create_simple(TYPE_ARM_SBCON_I2C, i2cbase[i], NULL); + if (i < 2) { + /* + * internal-only bus: mark it full to avoid user-created + * i2c devices being plugged into it. + */ + BusState *qbus = qdev_get_child_bus(dev, "i2c"); + qbus_mark_full(qbus); + } } create_unimplemented_device("i2s", 0x40024000, 0x400); -- 2.20.1 Hi; this is the latest target-arm queue. Most of the patches here are RTH's FEAT_HAFDBS finally landing. I've also included the RNG-seed randomization patches from Jason, as well as a few more minor things. The patches include a couple of regression fixes: * the resettable patch fixes a SCSI reset regression * the 'do not re-randomize on snapshot load' patches fix record-and-replay regressions thanks -- PMM The following changes since commit e750a7ace492f0b450653d4ad368a77d6f660fb8: Merge tag 'pull-9p-20221024' of https://github.com/cschoenebeck/qemu into staging (2022-10-24 14:27:12 -0400) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20221025 for you to fetch changes up to e2114f701c78f76246e4b1872639dad94a6bdd21: rx: re-randomize rng-seed on reboot (2022-10-25 17:32:24 +0100) ---------------------------------------------------------------- target-arm queue: * Implement FEAT_E0PD * Implement FEAT_HAFDBS * honor HCR_E2H and HCR_TGE in arm_excp_unmasked() * hw/arm/virt: Fix devicetree warnings about the virtio-iommu node * hw/core/resettable: fix reset level counting * hw/hyperv/hyperv.c: Use device_cold_reset() instead of device_legacy_reset() * imx: reload cmp timer outside of the reload ptimer transaction * x86: do not re-randomize RNG seed on snapshot load * m68k/virt: do not re-randomize RNG seed on snapshot load * m68k/q800: do not re-randomize RNG seed on snapshot load * arm: re-randomize rng-seed on reboot * riscv: re-randomize rng-seed on reboot * mips/boston: re-randomize rng-seed on reboot * openrisc: re-randomize rng-seed on reboot * rx: re-randomize rng-seed on reboot ---------------------------------------------------------------- Ake Koomsin (1): target/arm: honor HCR_E2H and HCR_TGE in arm_excp_unmasked() Axel Heider (1): target/imx: reload cmp timer outside of the reload ptimer transaction Damien Hedde (1): hw/core/resettable: fix reset level counting Jason A. Donenfeld (10): reset: allow registering handlers that aren't called by snapshot loading device-tree: add re-randomization helper function x86: do not re-randomize RNG seed on snapshot load arm: re-randomize rng-seed on reboot riscv: re-randomize rng-seed on reboot m68k/virt: do not re-randomize RNG seed on snapshot load m68k/q800: do not re-randomize RNG seed on snapshot load mips/boston: re-randomize rng-seed on reboot openrisc: re-randomize rng-seed on reboot rx: re-randomize rng-seed on reboot Jean-Philippe Brucker (1): hw/arm/virt: Fix devicetree warnings about the virtio-iommu node Peter Maydell (2): target/arm: Implement FEAT_E0PD hw/hyperv/hyperv.c: Use device_cold_reset() instead of device_legacy_reset() Richard Henderson (14): target/arm: Introduce regime_is_stage2 target/arm: Add ptw_idx to S1Translate target/arm: Add isar predicates for FEAT_HAFDBS target/arm: Extract HA and HD in aa64_va_parameters target/arm: Move S1_ptw_translate outside arm_ld[lq]_ptw target/arm: Add ARMFault_UnsuppAtomicUpdate target/arm: Remove loop from get_phys_addr_lpae target/arm: Fix fault reporting in get_phys_addr_lpae target/arm: Don't shift attrs in get_phys_addr_lpae target/arm: Consider GP an attribute in get_phys_addr_lpae target/arm: Tidy merging of attributes from descriptor and table target/arm: Implement FEAT_HAFDBS, access flag portion target/arm: Implement FEAT_HAFDBS, dirty bit portion target/arm: Use the max page size in a 2-stage ptw docs/devel/reset.rst | 8 +- docs/system/arm/emulation.rst | 2 + qapi/run-state.json | 6 +- include/hw/boards.h | 2 +- include/sysemu/device_tree.h | 9 + include/sysemu/reset.h | 5 +- target/arm/cpu.h | 15 ++ target/arm/internals.h | 30 +++ hw/arm/aspeed.c | 4 +- hw/arm/boot.c | 2 + hw/arm/mps2-tz.c | 4 +- hw/arm/virt.c | 5 +- hw/core/reset.c | 17 +- hw/core/resettable.c | 3 +- hw/hppa/machine.c | 4 +- hw/hyperv/hyperv.c | 2 +- hw/i386/microvm.c | 4 +- hw/i386/pc.c | 6 +- hw/i386/x86.c | 2 +- hw/m68k/q800.c | 33 ++- hw/m68k/virt.c | 20 +- hw/mips/boston.c | 3 + hw/openrisc/boot.c | 3 + hw/ppc/pegasos2.c | 4 +- hw/ppc/pnv.c | 4 +- hw/ppc/spapr.c | 4 +- hw/riscv/boot.c | 3 + hw/rx/rx-gdbsim.c | 3 + hw/s390x/s390-virtio-ccw.c | 4 +- hw/timer/imx_epit.c | 9 +- migration/savevm.c | 2 +- softmmu/device_tree.c | 21 ++ softmmu/runstate.c | 11 +- target/arm/cpu.c | 24 +- target/arm/cpu64.c | 2 + target/arm/helper.c | 31 ++- target/arm/ptw.c | 524 +++++++++++++++++++++++++++--------------- 37 files changed, 572 insertions(+), 263 deletions(-) FEAT_E0PD adds new bits E0PD0 and E0PD1 to TCR_EL1, which allow the OS to forbid EL0 access to half of the address space. Since this is an EL0-specific variation on the existing TCR_ELx.{EPD0,EPD1}, we can implement it entirely in aa64_va_parameters(). This requires moving the existing regime_is_user() to internals.h so that the code in helper.c can get at it. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20221021160131.3531787-1-peter.maydell@linaro.org --- docs/system/arm/emulation.rst | 1 + target/arm/cpu.h | 5 +++++ target/arm/internals.h | 19 +++++++++++++++++++ target/arm/cpu64.c | 1 + target/arm/helper.c | 9 +++++++++ target/arm/ptw.c | 19 ------------------- 6 files changed, 35 insertions(+), 19 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_Debugv8p4 (Debug changes for v8.4) - FEAT_DotProd (Advanced SIMD dot product instructions) - FEAT_DoubleFault (Double Fault Extension) +- FEAT_E0PD (Preventing EL0 access to halves of address maps) - FEAT_ETS (Enhanced Translation Synchronization) - FEAT_FCMA (Floating-point complex number instructions) - FEAT_FHM (Floating-point half-precision multiplication instructions) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_lva(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, VARANGE) != 0; } +static inline bool isar_feature_aa64_e0pd(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, E0PD) != 0; +} + static inline bool isar_feature_aa64_tts2uxn(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0; 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 uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx) } } +static inline bool regime_is_user(CPUARMState *env, ARMMMUIdx mmu_idx) +{ + switch (mmu_idx) { + case ARMMMUIdx_E20_0: + case ARMMMUIdx_Stage1_E0: + case ARMMMUIdx_MUser: + case ARMMMUIdx_MSUser: + case ARMMMUIdx_MUserNegPri: + case ARMMMUIdx_MSUserNegPri: + return true; + default: + return false; + case ARMMMUIdx_E10_0: + case ARMMMUIdx_E10_1: + case ARMMMUIdx_E10_1_PAN: + g_assert_not_reached(); + } +} + /* Return the SCTLR value which controls this address translation regime */ static inline uint64_t regime_sctlr(CPUARMState *env, ARMMMUIdx mmu_idx) { diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64MMFR2, FWB, 1); /* FEAT_S2FWB */ t = FIELD_DP64(t, ID_AA64MMFR2, TTL, 1); /* FEAT_TTL */ t = FIELD_DP64(t, ID_AA64MMFR2, BBM, 2); /* FEAT_BBM at level 2 */ + t = FIELD_DP64(t, ID_AA64MMFR2, E0PD, 1); /* FEAT_E0PD */ cpu->isar.id_aa64mmfr2 = t; t = cpu->isar.id_aa64zfr0; 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 @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, ps = extract32(tcr, 16, 3); ds = extract64(tcr, 32, 1); } else { + bool e0pd; + /* * Bit 55 is always between the two regions, and is canonical for * determining if address tagging is enabled. @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, epd = extract32(tcr, 7, 1); sh = extract32(tcr, 12, 2); hpd = extract64(tcr, 41, 1); + e0pd = extract64(tcr, 55, 1); } else { tsz = extract32(tcr, 16, 6); gran = tg1_to_gran_size(extract32(tcr, 30, 2)); epd = extract32(tcr, 23, 1); sh = extract32(tcr, 28, 2); hpd = extract64(tcr, 42, 1); + e0pd = extract64(tcr, 56, 1); } ps = extract64(tcr, 32, 3); ds = extract64(tcr, 59, 1); + + if (e0pd && cpu_isar_feature(aa64_e0pd, cpu) && + regime_is_user(env, mmu_idx)) { + epd = true; + } } gran = sanitize_gran_size(cpu, gran, stage2); diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ static bool regime_translation_big_endian(CPUARMState *env, ARMMMUIdx mmu_idx) return (regime_sctlr(env, mmu_idx) & SCTLR_EE) != 0; } -static bool regime_is_user(CPUARMState *env, ARMMMUIdx mmu_idx) -{ - switch (mmu_idx) { - case ARMMMUIdx_E20_0: - case ARMMMUIdx_Stage1_E0: - case ARMMMUIdx_MUser: - case ARMMMUIdx_MSUser: - case ARMMMUIdx_MUserNegPri: - case ARMMMUIdx_MSUserNegPri: - return true; - default: - return false; - case ARMMMUIdx_E10_0: - case ARMMMUIdx_E10_1: - case ARMMMUIdx_E10_1_PAN: - g_assert_not_reached(); - } -} - /* Return the TTBR associated with this translation regime */ static uint64_t regime_ttbr(CPUARMState *env, ARMMMUIdx mmu_idx, int ttbrn) { -- 2.25.1 From: Jean-Philippe Brucker <jean-philippe@linaro.org> The "PCI Bus Binding to: IEEE Std 1275-1994" defines the compatible string for a PCIe bus or endpoint as "pci<vendorid>,<deviceid>" or similar. Since the initial binding for PCI virtio-iommu didn't follow this rule, it was modified to accept both strings and ensure backward compatibility. Also, the unit-name for the node should be "device,function". Fix corresponding dt-validate and dtc warnings: pcie@10000000: virtio_iommu@16:compatible: ['virtio,pci-iommu'] does not contain items matching the given schema pcie@10000000: Unevaluated properties are not allowed (... 'virtio_iommu@16' were unexpected) From schema: linux/Documentation/devicetree/bindings/pci/host-generic-pci.yaml virtio_iommu@16: compatible: 'oneOf' conditional failed, one must be fixed: ['virtio,pci-iommu'] is too short 'pci1af4,1057' was expected From schema: dtschema/schemas/pci/pci-bus.yaml Warning (pci_device_reg): /pcie@10000000/virtio_iommu@16: PCI unit address format error, expected "2,0" Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void create_smmu(const VirtMachineState *vms, static void create_virtio_iommu_dt_bindings(VirtMachineState *vms) { - const char compat[] = "virtio,pci-iommu"; + const char compat[] = "virtio,pci-iommu\0pci1af4,1057"; uint16_t bdf = vms->virtio_iommu_bdf; MachineState *ms = MACHINE(vms); char *node; vms->iommu_phandle = qemu_fdt_alloc_phandle(ms->fdt); - node = g_strdup_printf("%s/virtio_iommu@%d", vms->pciehb_nodename, bdf); + node = g_strdup_printf("%s/virtio_iommu@%x,%x", vms->pciehb_nodename, + PCI_SLOT(bdf), PCI_FUNC(bdf)); qemu_fdt_add_subnode(ms->fdt, node); qemu_fdt_setprop(ms->fdt, node, "compatible", compat, sizeof(compat)); qemu_fdt_setprop_sized_cells(ms->fdt, node, "reg", -- 2.25.1 From: Ake Koomsin <ake@igel.co.jp> An exception targeting EL2 from lower EL is actually maskable when HCR_E2H and HCR_TGE are both set. This applies to both secure and non-secure Security state. We can remove the conditions that try to suppress masking of interrupts when we are Secure and the exception targets EL2 and Secure EL2 is disabled. This is OK because in that situation arm_phys_excp_target_el() will never return 2 as the target EL. The 'not if secure' check in this function was originally written before arm_hcr_el2_eff(), and back then the target EL returned by arm_phys_excp_target_el() could be 2 even if we were in Secure EL0/EL1; but it is no longer needed. Signed-off-by: Ake Koomsin <ake@igel.co.jp> Message-id: 20221017092432.546881-1-ake@igel.co.jp [PMM: Add commit message paragraph explaining why it's OK to remove the checks on secure and SCR_EEL2] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 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 @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, if ((target_el > cur_el) && (target_el != 1)) { /* Exceptions targeting a higher EL may not be maskable */ if (arm_feature(env, ARM_FEATURE_AARCH64)) { - /* - * 64-bit masking rules are simple: exceptions to EL3 - * can't be masked, and exceptions to EL2 can only be - * masked from Secure state. The HCR and SCR settings - * don't affect the masking logic, only the interrupt routing. - */ - if (target_el == 3 || !secure || (env->cp15.scr_el3 & SCR_EEL2)) { + switch (target_el) { + case 2: + /* + * According to ARM DDI 0487H.a, an interrupt can be masked + * when HCR_E2H and HCR_TGE are both set regardless of the + * current Security state. Note that we need to revisit this + * part again once we need to support NMI. + */ + if ((hcr_el2 & (HCR_E2H | HCR_TGE)) != (HCR_E2H | HCR_TGE)) { + unmasked = true; + } + break; + case 3: + /* Interrupt cannot be masked when the target EL is 3 */ unmasked = true; + break; + default: + g_assert_not_reached(); } } else { /* -- 2.25.1 From: Damien Hedde <damien.hedde@greensocs.com> The code for handling the reset level count in the Resettable code has two issues: The reset count is only decremented for the 1->0 case. This means that if there's ever a nested reset that takes the count to 2 then it will never again be decremented. Eventually the count will exceed the '50' limit in resettable_phase_enter() and QEMU will trip over the assertion failure. The repro case in issue 1266 is an example of this that happens now the SCSI subsystem uses three-phase reset. Secondly, the count is decremented only after the exit phase handler is called. Moving the reset count decrement from "just after" to "just before" calling the exit phase handler allows resettable_is_in_reset() to return false during the handler execution. This simplifies reset handling in resettable devices. Typically, a function that updates the device state will just need to read the current reset state and not anymore treat the "in a reset-exit transition" as a special case. Note that the semantics change to the *_is_in_reset() functions will have no effect on the current codebase, because only two devices (hw/char/cadence_uart.c and hw/misc/zynq_sclr.c) currently call those functions, and in neither case do they do it from the device's exit phase methed. Fixes: 4a5fc890 ("scsi: Use device_cold_reset() and bus_cold_reset()") Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1266 Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reported-by: Michael Peter <michael.peter@hensoldt-cyber.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20221020142749.3357951-1-peter.maydell@linaro.org Buglink: https://bugs.launchpad.net/qemu/+bug/1905297 Reported-by: Michael Peter <michael.peter@hensoldt-cyber.com> [PMM: adjust the docs paragraph changed to get the name of the 'enter' phase right and to clarify exactly when the count is adjusted; rewrite the commit message] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/devel/reset.rst | 8 +++++--- hw/core/resettable.c | 3 +-- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/docs/devel/reset.rst b/docs/devel/reset.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/reset.rst +++ b/docs/devel/reset.rst @@ -XXX,XX +XXX,XX @@ Polling the reset state Resettable interface provides the ``resettable_is_in_reset()`` function. This function returns true if the object parameter is currently under reset. -An object is under reset from the beginning of the *init* phase to the end of -the *exit* phase. During all three phases, the function will return that the -object is in reset. +An object is under reset from the beginning of the *enter* phase (before +either its children or its own enter method is called) to the *exit* +phase. During *enter* and *hold* phase only, the function will return that the +object is in reset. The state is changed after the *exit* is propagated to +its children and just before calling the object's own *exit* method. This function may be used if the object behavior has to be adapted while in reset state. For example if a device has an irq input, diff --git a/hw/core/resettable.c b/hw/core/resettable.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/resettable.c +++ b/hw/core/resettable.c @@ -XXX,XX +XXX,XX @@ static void resettable_phase_exit(Object *obj, void *opaque, ResetType type) resettable_child_foreach(rc, obj, resettable_phase_exit, NULL, type); assert(s->count > 0); - if (s->count == 1) { + if (--s->count == 0) { trace_resettable_phase_exit_exec(obj, obj_typename, !!rc->phases.exit); if (rc->phases.exit && !resettable_get_tr_func(rc, obj)) { rc->phases.exit(obj); } - s->count = 0; } s->exit_phase_in_progress = false; trace_resettable_phase_exit_end(obj, obj_typename, s->count); -- 2.25.1 The semantic difference between the deprecated device_legacy_reset() function and the newer device_cold_reset() function is that the new function resets both the device itself and any qbuses it owns, whereas the legacy function resets just the device itself and nothing else. In hyperv_synic_reset() we reset a SynICState, which has no qbuses, so for this purpose the two functions behave identically and we can stop using the deprecated one. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com> Message-id: 20221013171817.1447562-1-peter.maydell@linaro.org --- hw/hyperv/hyperv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/hyperv/hyperv.c b/hw/hyperv/hyperv.c index XXXXXXX..XXXXXXX 100644 --- a/hw/hyperv/hyperv.c +++ b/hw/hyperv/hyperv.c @@ -XXX,XX +XXX,XX @@ void hyperv_synic_reset(CPUState *cs) SynICState *synic = get_synic(cs); if (synic) { - device_legacy_reset(DEVICE(synic)); + device_cold_reset(DEVICE(synic)); } } -- 2.25.1 From: Axel Heider <axel.heider@hensoldt.net> When running seL4 tests (https://docs.sel4.systems/projects/sel4test) on the sabrelight platform, the timer tests fail. The arm/imx6 EPIT timer interrupt does not fire properly, instead of a e.g. second in can take up to a minute to finally see the interrupt. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1263 Signed-off-by: Axel Heider <axel.heider@hensoldt.net> Message-id: 166663118138.13362.1229967229046092876-0@git.sr.ht Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/imx_epit.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/hw/timer/imx_epit.c b/hw/timer/imx_epit.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/imx_epit.c +++ b/hw/timer/imx_epit.c @@ -XXX,XX +XXX,XX @@ static void imx_epit_write(void *opaque, hwaddr offset, uint64_t value, /* If IOVW bit is set then set the timer value */ ptimer_set_count(s->timer_reload, s->lr); } - + /* + * Commit the change to s->timer_reload, so it can propagate. Otherwise + * the timer interrupt may not fire properly. The commit must happen + * before calling imx_epit_reload_compare_timer(), which reads + * s->timer_reload internally again. + */ + ptimer_transaction_commit(s->timer_reload); imx_epit_reload_compare_timer(s); ptimer_transaction_commit(s->timer_cmp); - ptimer_transaction_commit(s->timer_reload); break; case 3: /* CMP */ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reduce the amount of typing required for this check. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20221024051851.3074715-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 5 +++++ target/arm/helper.c | 14 +++++--------- target/arm/ptw.c | 14 ++++++-------- 3 files changed, 16 insertions(+), 17 deletions(-) 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 regime_is_pan(CPUARMState *env, ARMMMUIdx mmu_idx) } } +static inline bool regime_is_stage2(ARMMMUIdx mmu_idx) +{ + return mmu_idx == ARMMMUIdx_Stage2 || mmu_idx == ARMMMUIdx_Stage2_S; +} + /* Return the exception level which controls this address translation regime */ static inline uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx) { 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 @@ int aa64_va_parameter_tbi(uint64_t tcr, ARMMMUIdx mmu_idx) { if (regime_has_2_ranges(mmu_idx)) { return extract64(tcr, 37, 2); - } else if (mmu_idx == ARMMMUIdx_Stage2 || mmu_idx == ARMMMUIdx_Stage2_S) { + } else if (regime_is_stage2(mmu_idx)) { return 0; /* VTCR_EL2 */ } else { /* Replicate the single TBI bit so we always have 2 bits. */ @@ -XXX,XX +XXX,XX @@ int aa64_va_parameter_tbid(uint64_t tcr, ARMMMUIdx mmu_idx) { if (regime_has_2_ranges(mmu_idx)) { return extract64(tcr, 51, 2); - } else if (mmu_idx == ARMMMUIdx_Stage2 || mmu_idx == ARMMMUIdx_Stage2_S) { + } else if (regime_is_stage2(mmu_idx)) { return 0; /* VTCR_EL2 */ } else { /* Replicate the single TBID bit so we always have 2 bits. */ @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, int select, tsz, tbi, max_tsz, min_tsz, ps, sh; ARMGranuleSize gran; ARMCPU *cpu = env_archcpu(env); - bool stage2 = mmu_idx == ARMMMUIdx_Stage2 || mmu_idx == ARMMMUIdx_Stage2_S; + bool stage2 = regime_is_stage2(mmu_idx); if (!regime_has_2_ranges(mmu_idx)) { select = 0; @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, } ds = false; } else if (ds) { - switch (mmu_idx) { - case ARMMMUIdx_Stage2: - case ARMMMUIdx_Stage2_S: + if (regime_is_stage2(mmu_idx)) { if (gran == Gran16K) { ds = cpu_isar_feature(aa64_tgran16_2_lpa2, cpu); } else { ds = cpu_isar_feature(aa64_tgran4_2_lpa2, cpu); } - break; - default: + } else { if (gran == Gran16K) { ds = cpu_isar_feature(aa64_tgran16_lpa2, cpu); } else { ds = cpu_isar_feature(aa64_tgran4_lpa2, cpu); } - break; } if (ds) { min_tsz = 12; diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ static int get_S1prot(CPUARMState *env, ARMMMUIdx mmu_idx, bool is_aa64, bool have_wxn; int wxn = 0; - assert(mmu_idx != ARMMMUIdx_Stage2); - assert(mmu_idx != ARMMMUIdx_Stage2_S); + assert(!regime_is_stage2(mmu_idx)); user_rw = simple_ap_to_rw_prot_is_user(ap, true); if (is_user) { @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, goto do_fault; } - if (mmu_idx != ARMMMUIdx_Stage2 && mmu_idx != ARMMMUIdx_Stage2_S) { + if (!regime_is_stage2(mmu_idx)) { /* * The starting level depends on the virtual address size (which can * be up to 48 bits) and the translation granule size. It indicates @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, attrs = extract64(descriptor, 2, 10) | (extract64(descriptor, 52, 12) << 10); - if (mmu_idx == ARMMMUIdx_Stage2 || mmu_idx == ARMMMUIdx_Stage2_S) { + if (regime_is_stage2(mmu_idx)) { /* Stage 2 table descriptors do not include any attribute fields */ break; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, ap = extract32(attrs, 4, 2); - if (mmu_idx == ARMMMUIdx_Stage2 || mmu_idx == ARMMMUIdx_Stage2_S) { + if (regime_is_stage2(mmu_idx)) { ns = mmu_idx == ARMMMUIdx_Stage2; xn = extract32(attrs, 11, 2); result->f.prot = get_S2prot(env, ap, xn, s1_is_el0); @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, result->f.guarded = guarded; } - if (mmu_idx == ARMMMUIdx_Stage2 || mmu_idx == ARMMMUIdx_Stage2_S) { + if (regime_is_stage2(mmu_idx)) { result->cacheattrs.is_s2_format = true; result->cacheattrs.attrs = extract32(attrs, 0, 4); } else { @@ -XXX,XX +XXX,XX @@ do_fault: fi->type = fault_type; fi->level = level; /* Tag the error as S2 for failed S1 PTW at S2 or ordinary S2. */ - fi->stage2 = fi->s1ptw || (mmu_idx == ARMMMUIdx_Stage2 || - mmu_idx == ARMMMUIdx_Stage2_S); + fi->stage2 = fi->s1ptw || regime_is_stage2(mmu_idx); fi->s1ns = mmu_idx == ARMMMUIdx_Stage2; return true; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Hoist the computation of the mmu_idx for the ptw up to get_phys_addr_with_struct and get_phys_addr_twostage. This removes the duplicate check for stage2 disabled from the middle of the walk, performing it only once. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20221024051851.3074715-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/ptw.c | 71 ++++++++++++++++++++++++++++++++++++------------ 1 file changed, 54 insertions(+), 17 deletions(-) diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ typedef struct S1Translate { ARMMMUIdx in_mmu_idx; + ARMMMUIdx in_ptw_idx; bool in_secure; bool in_debug; bool out_secure; @@ -XXX,XX +XXX,XX @@ static bool S1_ptw_translate(CPUARMState *env, S1Translate *ptw, { bool is_secure = ptw->in_secure; ARMMMUIdx mmu_idx = ptw->in_mmu_idx; - ARMMMUIdx s2_mmu_idx = is_secure ? ARMMMUIdx_Stage2_S : ARMMMUIdx_Stage2; - bool s2_phys = false; + ARMMMUIdx s2_mmu_idx = ptw->in_ptw_idx; uint8_t pte_attrs; bool pte_secure; - if (!arm_mmu_idx_is_stage1_of_2(mmu_idx) - || regime_translation_disabled(env, s2_mmu_idx, is_secure)) { - s2_mmu_idx = is_secure ? ARMMMUIdx_Phys_S : ARMMMUIdx_Phys_NS; - s2_phys = true; - } - if (unlikely(ptw->in_debug)) { /* * From gdbstub, do not use softmmu so that we don't modify the * state of the cpu at all, including softmmu tlb contents. */ - if (s2_phys) { - ptw->out_phys = addr; - pte_attrs = 0; - pte_secure = is_secure; - } else { + if (regime_is_stage2(s2_mmu_idx)) { S1Translate s2ptw = { .in_mmu_idx = s2_mmu_idx, + .in_ptw_idx = is_secure ? ARMMMUIdx_Phys_S : ARMMMUIdx_Phys_NS, .in_secure = is_secure, .in_debug = true, }; GetPhysAddrResult s2 = { }; + if (!get_phys_addr_lpae(env, &s2ptw, addr, MMU_DATA_LOAD, false, &s2, fi)) { goto fail; @@ -XXX,XX +XXX,XX @@ static bool S1_ptw_translate(CPUARMState *env, S1Translate *ptw, ptw->out_phys = s2.f.phys_addr; pte_attrs = s2.cacheattrs.attrs; pte_secure = s2.f.attrs.secure; + } else { + /* Regime is physical. */ + ptw->out_phys = addr; + pte_attrs = 0; + pte_secure = is_secure; } ptw->out_host = NULL; } else { @@ -XXX,XX +XXX,XX @@ static bool S1_ptw_translate(CPUARMState *env, S1Translate *ptw, pte_secure = full->attrs.secure; } - if (!s2_phys) { + if (regime_is_stage2(s2_mmu_idx)) { uint64_t hcr = arm_hcr_el2_eff_secstate(env, is_secure); if ((hcr & HCR_PTW) && S2_attrs_are_device(hcr, pte_attrs)) { @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, descaddr |= (address >> (stride * (4 - level))) & indexmask; descaddr &= ~7ULL; nstable = extract32(tableattrs, 4, 1); - ptw->in_secure = !nstable; + if (!nstable) { + /* + * Stage2_S -> Stage2 or Phys_S -> Phys_NS + * Assert that the non-secure idx are even, and relative order. + */ + QEMU_BUILD_BUG_ON((ARMMMUIdx_Phys_NS & 1) != 0); + QEMU_BUILD_BUG_ON((ARMMMUIdx_Stage2 & 1) != 0); + QEMU_BUILD_BUG_ON(ARMMMUIdx_Phys_NS + 1 != ARMMMUIdx_Phys_S); + QEMU_BUILD_BUG_ON(ARMMMUIdx_Stage2 + 1 != ARMMMUIdx_Stage2_S); + ptw->in_ptw_idx &= ~1; + ptw->in_secure = false; + } descriptor = arm_ldq_ptw(env, ptw, descaddr, fi); if (fi->type != ARMFault_None) { goto do_fault; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_twostage(CPUARMState *env, S1Translate *ptw, is_el0 = ptw->in_mmu_idx == ARMMMUIdx_Stage1_E0; ptw->in_mmu_idx = s2walk_secure ? ARMMMUIdx_Stage2_S : ARMMMUIdx_Stage2; + ptw->in_ptw_idx = s2walk_secure ? ARMMMUIdx_Phys_S : ARMMMUIdx_Phys_NS; ptw->in_secure = s2walk_secure; /* @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_with_struct(CPUARMState *env, S1Translate *ptw, ARMMMUFaultInfo *fi) { ARMMMUIdx mmu_idx = ptw->in_mmu_idx; - ARMMMUIdx s1_mmu_idx = stage_1_mmu_idx(mmu_idx); bool is_secure = ptw->in_secure; + ARMMMUIdx s1_mmu_idx; - if (mmu_idx != s1_mmu_idx) { + switch (mmu_idx) { + case ARMMMUIdx_Phys_S: + case ARMMMUIdx_Phys_NS: + /* Checking Phys early avoids special casing later vs regime_el. */ + return get_phys_addr_disabled(env, address, access_type, mmu_idx, + is_secure, result, fi); + + case ARMMMUIdx_Stage1_E0: + case ARMMMUIdx_Stage1_E1: + case ARMMMUIdx_Stage1_E1_PAN: + /* First stage lookup uses second stage for ptw. */ + ptw->in_ptw_idx = is_secure ? ARMMMUIdx_Stage2_S : ARMMMUIdx_Stage2; + break; + + case ARMMMUIdx_E10_0: + s1_mmu_idx = ARMMMUIdx_Stage1_E0; + goto do_twostage; + case ARMMMUIdx_E10_1: + s1_mmu_idx = ARMMMUIdx_Stage1_E1; + goto do_twostage; + case ARMMMUIdx_E10_1_PAN: + s1_mmu_idx = ARMMMUIdx_Stage1_E1_PAN; + do_twostage: /* * Call ourselves recursively to do the stage 1 and then stage 2 * translations if mmu_idx is a two-stage regime, and EL2 present. @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_with_struct(CPUARMState *env, S1Translate *ptw, return get_phys_addr_twostage(env, ptw, address, access_type, result, fi); } + /* fall through */ + + default: + /* Single stage and second stage uses physical for ptw. */ + ptw->in_ptw_idx = is_secure ? ARMMMUIdx_Phys_S : ARMMMUIdx_Phys_NS; + break; } /* -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> The MMFR1 field may indicate support for hardware update of access flag alone, or access flag and dirty bit. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20221024051851.3074715-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 10 ++++++++++ 1 file changed, 10 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 isar_feature_aa64_e0pd(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, E0PD) != 0; } +static inline bool isar_feature_aa64_hafs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) != 0; +} + +static inline bool isar_feature_aa64_hdbs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) >= 2; +} + static inline bool isar_feature_aa64_tts2uxn(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20221024051851.3074715-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 2 ++ target/arm/helper.c | 8 +++++++- 2 files changed, 9 insertions(+), 1 deletion(-) 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 @@ typedef struct ARMVAParameters { bool hpd : 1; bool tsz_oob : 1; /* tsz has been clamped to legal range */ bool ds : 1; + bool ha : 1; + bool hd : 1; ARMGranuleSize gran : 2; } ARMVAParameters; 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 @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, ARMMMUIdx mmu_idx, bool data) { uint64_t tcr = regime_tcr(env, mmu_idx); - bool epd, hpd, tsz_oob, ds; + bool epd, hpd, tsz_oob, ds, ha, hd; int select, tsz, tbi, max_tsz, min_tsz, ps, sh; ARMGranuleSize gran; ARMCPU *cpu = env_archcpu(env); @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, epd = false; sh = extract32(tcr, 12, 2); ps = extract32(tcr, 16, 3); + ha = extract32(tcr, 21, 1) && cpu_isar_feature(aa64_hafs, cpu); + hd = extract32(tcr, 22, 1) && cpu_isar_feature(aa64_hdbs, cpu); ds = extract64(tcr, 32, 1); } else { bool e0pd; @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, e0pd = extract64(tcr, 56, 1); } ps = extract64(tcr, 32, 3); + ha = extract64(tcr, 39, 1) && cpu_isar_feature(aa64_hafs, cpu); + hd = extract64(tcr, 40, 1) && cpu_isar_feature(aa64_hdbs, cpu); ds = extract64(tcr, 59, 1); if (e0pd && cpu_isar_feature(aa64_e0pd, cpu) && @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, .hpd = hpd, .tsz_oob = tsz_oob, .ds = ds, + .ha = ha, + .hd = ha && hd, .gran = gran, }; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Separate S1 translation from the actual lookup. Will enable lpae hardware updates. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20221024051851.3074715-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/ptw.c | 41 ++++++++++++++++++++++------------------- 1 file changed, 22 insertions(+), 19 deletions(-) diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ static bool S1_ptw_translate(CPUARMState *env, S1Translate *ptw, } /* All loads done in the course of a page table walk go through here. */ -static uint32_t arm_ldl_ptw(CPUARMState *env, S1Translate *ptw, hwaddr addr, +static uint32_t arm_ldl_ptw(CPUARMState *env, S1Translate *ptw, ARMMMUFaultInfo *fi) { CPUState *cs = env_cpu(env); uint32_t data; - if (!S1_ptw_translate(env, ptw, addr, fi)) { - /* Failure. */ - assert(fi->s1ptw); - return 0; - } - if (likely(ptw->out_host)) { /* Page tables are in RAM, and we have the host address. */ if (ptw->out_be) { @@ -XXX,XX +XXX,XX @@ static uint32_t arm_ldl_ptw(CPUARMState *env, S1Translate *ptw, hwaddr addr, return data; } -static uint64_t arm_ldq_ptw(CPUARMState *env, S1Translate *ptw, hwaddr addr, +static uint64_t arm_ldq_ptw(CPUARMState *env, S1Translate *ptw, ARMMMUFaultInfo *fi) { CPUState *cs = env_cpu(env); uint64_t data; - if (!S1_ptw_translate(env, ptw, addr, fi)) { - /* Failure. */ - assert(fi->s1ptw); - return 0; - } - if (likely(ptw->out_host)) { /* Page tables are in RAM, and we have the host address. */ if (ptw->out_be) { @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_v5(CPUARMState *env, S1Translate *ptw, fi->type = ARMFault_Translation; goto do_fault; } - desc = arm_ldl_ptw(env, ptw, table, fi); + if (!S1_ptw_translate(env, ptw, table, fi)) { + goto do_fault; + } + desc = arm_ldl_ptw(env, ptw, fi); if (fi->type != ARMFault_None) { goto do_fault; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_v5(CPUARMState *env, S1Translate *ptw, /* Fine pagetable. */ table = (desc & 0xfffff000) | ((address >> 8) & 0xffc); } - desc = arm_ldl_ptw(env, ptw, table, fi); + if (!S1_ptw_translate(env, ptw, table, fi)) { + goto do_fault; + } + desc = arm_ldl_ptw(env, ptw, fi); if (fi->type != ARMFault_None) { goto do_fault; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_v6(CPUARMState *env, S1Translate *ptw, fi->type = ARMFault_Translation; goto do_fault; } - desc = arm_ldl_ptw(env, ptw, table, fi); + if (!S1_ptw_translate(env, ptw, table, fi)) { + goto do_fault; + } + desc = arm_ldl_ptw(env, ptw, fi); if (fi->type != ARMFault_None) { goto do_fault; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_v6(CPUARMState *env, S1Translate *ptw, ns = extract32(desc, 3, 1); /* Lookup l2 entry. */ table = (desc & 0xfffffc00) | ((address >> 10) & 0x3fc); - desc = arm_ldl_ptw(env, ptw, table, fi); + if (!S1_ptw_translate(env, ptw, table, fi)) { + goto do_fault; + } + desc = arm_ldl_ptw(env, ptw, fi); if (fi->type != ARMFault_None) { goto do_fault; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, ptw->in_ptw_idx &= ~1; ptw->in_secure = false; } - descriptor = arm_ldq_ptw(env, ptw, descaddr, fi); + if (!S1_ptw_translate(env, ptw, descaddr, fi)) { + goto do_fault; + } + descriptor = arm_ldq_ptw(env, ptw, fi); if (fi->type != ARMFault_None) { goto do_fault; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This fault type is to be used with FEAT_HAFDBS when the guest enables hw updates, but places the tables in memory where atomic updates are unsupported. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20221024051851.3074715-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 4 ++++ 1 file changed, 4 insertions(+) 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 @@ typedef enum ARMFaultType { ARMFault_AsyncExternal, ARMFault_Debug, ARMFault_TLBConflict, + ARMFault_UnsuppAtomicUpdate, ARMFault_Lockdown, ARMFault_Exclusive, ARMFault_ICacheMaint, @@ -XXX,XX +XXX,XX @@ static inline uint32_t arm_fi_to_lfsc(ARMMMUFaultInfo *fi) case ARMFault_TLBConflict: fsc = 0x30; break; + case ARMFault_UnsuppAtomicUpdate: + fsc = 0x31; + break; case ARMFault_Lockdown: fsc = 0x34; break; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> The unconditional loop was used both to iterate over levels and to control parsing of attributes. Use an explicit goto in both cases. While this appears less clean for iterating over levels, we will need to jump back into the middle of this loop for atomic updates, which is even uglier. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20221024051851.3074715-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/ptw.c | 192 +++++++++++++++++++++++------------------------ 1 file changed, 96 insertions(+), 96 deletions(-) diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, uint64_t descaddrmask; bool aarch64 = arm_el_is_aa64(env, el); bool guarded = false; + uint64_t descriptor; + bool nstable; /* TODO: This code does not support shareability levels. */ if (aarch64) { @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, * bits at each step. */ tableattrs = is_secure ? 0 : (1 << 4); - for (;;) { - uint64_t descriptor; - bool nstable; - - descaddr |= (address >> (stride * (4 - level))) & indexmask; - descaddr &= ~7ULL; - nstable = extract32(tableattrs, 4, 1); - if (!nstable) { - /* - * Stage2_S -> Stage2 or Phys_S -> Phys_NS - * Assert that the non-secure idx are even, and relative order. - */ - QEMU_BUILD_BUG_ON((ARMMMUIdx_Phys_NS & 1) != 0); - QEMU_BUILD_BUG_ON((ARMMMUIdx_Stage2 & 1) != 0); - QEMU_BUILD_BUG_ON(ARMMMUIdx_Phys_NS + 1 != ARMMMUIdx_Phys_S); - QEMU_BUILD_BUG_ON(ARMMMUIdx_Stage2 + 1 != ARMMMUIdx_Stage2_S); - ptw->in_ptw_idx &= ~1; - ptw->in_secure = false; - } - if (!S1_ptw_translate(env, ptw, descaddr, fi)) { - goto do_fault; - } - descriptor = arm_ldq_ptw(env, ptw, fi); - if (fi->type != ARMFault_None) { - goto do_fault; - } - - if (!(descriptor & 1) || - (!(descriptor & 2) && (level == 3))) { - /* Invalid, or the Reserved level 3 encoding */ - goto do_fault; - } - - descaddr = descriptor & descaddrmask; + next_level: + descaddr |= (address >> (stride * (4 - level))) & indexmask; + descaddr &= ~7ULL; + nstable = extract32(tableattrs, 4, 1); + if (!nstable) { /* - * For FEAT_LPA and PS=6, bits [51:48] of descaddr are in [15:12] - * of descriptor. For FEAT_LPA2 and effective DS, bits [51:50] of - * descaddr are in [9:8]. Otherwise, if descaddr is out of range, - * raise AddressSizeFault. + * Stage2_S -> Stage2 or Phys_S -> Phys_NS + * Assert that the non-secure idx are even, and relative order. */ - if (outputsize > 48) { - if (param.ds) { - descaddr |= extract64(descriptor, 8, 2) << 50; - } else { - descaddr |= extract64(descriptor, 12, 4) << 48; - } - } else if (descaddr >> outputsize) { - fault_type = ARMFault_AddressSize; - goto do_fault; - } - - if ((descriptor & 2) && (level < 3)) { - /* - * Table entry. The top five bits are attributes which may - * propagate down through lower levels of the table (and - * which are all arranged so that 0 means "no effect", so - * we can gather them up by ORing in the bits at each level). - */ - tableattrs |= extract64(descriptor, 59, 5); - level++; - indexmask = indexmask_grainsize; - continue; - } - /* - * Block entry at level 1 or 2, or page entry at level 3. - * These are basically the same thing, although the number - * of bits we pull in from the vaddr varies. Note that although - * descaddrmask masks enough of the low bits of the descriptor - * to give a correct page or table address, the address field - * in a block descriptor is smaller; so we need to explicitly - * clear the lower bits here before ORing in the low vaddr bits. - */ - page_size = (1ULL << ((stride * (4 - level)) + 3)); - descaddr &= ~(hwaddr)(page_size - 1); - descaddr |= (address & (page_size - 1)); - /* Extract attributes from the descriptor */ - attrs = extract64(descriptor, 2, 10) - | (extract64(descriptor, 52, 12) << 10); - - if (regime_is_stage2(mmu_idx)) { - /* Stage 2 table descriptors do not include any attribute fields */ - break; - } - /* Merge in attributes from table descriptors */ - attrs |= nstable << 3; /* NS */ - guarded = extract64(descriptor, 50, 1); /* GP */ - if (param.hpd) { - /* HPD disables all the table attributes except NSTable. */ - break; - } - attrs |= extract32(tableattrs, 0, 2) << 11; /* XN, PXN */ - /* - * The sense of AP[1] vs APTable[0] is reversed, as APTable[0] == 1 - * means "force PL1 access only", which means forcing AP[1] to 0. - */ - attrs &= ~(extract32(tableattrs, 2, 1) << 4); /* !APT[0] => AP[1] */ - attrs |= extract32(tableattrs, 3, 1) << 5; /* APT[1] => AP[2] */ - break; + QEMU_BUILD_BUG_ON((ARMMMUIdx_Phys_NS & 1) != 0); + QEMU_BUILD_BUG_ON((ARMMMUIdx_Stage2 & 1) != 0); + QEMU_BUILD_BUG_ON(ARMMMUIdx_Phys_NS + 1 != ARMMMUIdx_Phys_S); + QEMU_BUILD_BUG_ON(ARMMMUIdx_Stage2 + 1 != ARMMMUIdx_Stage2_S); + ptw->in_ptw_idx &= ~1; + ptw->in_secure = false; } + if (!S1_ptw_translate(env, ptw, descaddr, fi)) { + goto do_fault; + } + descriptor = arm_ldq_ptw(env, ptw, fi); + if (fi->type != ARMFault_None) { + goto do_fault; + } + + if (!(descriptor & 1) || (!(descriptor & 2) && (level == 3))) { + /* Invalid, or the Reserved level 3 encoding */ + goto do_fault; + } + + descaddr = descriptor & descaddrmask; + + /* + * For FEAT_LPA and PS=6, bits [51:48] of descaddr are in [15:12] + * of descriptor. For FEAT_LPA2 and effective DS, bits [51:50] of + * descaddr are in [9:8]. Otherwise, if descaddr is out of range, + * raise AddressSizeFault. + */ + if (outputsize > 48) { + if (param.ds) { + descaddr |= extract64(descriptor, 8, 2) << 50; + } else { + descaddr |= extract64(descriptor, 12, 4) << 48; + } + } else if (descaddr >> outputsize) { + fault_type = ARMFault_AddressSize; + goto do_fault; + } + + if ((descriptor & 2) && (level < 3)) { + /* + * Table entry. The top five bits are attributes which may + * propagate down through lower levels of the table (and + * which are all arranged so that 0 means "no effect", so + * we can gather them up by ORing in the bits at each level). + */ + tableattrs |= extract64(descriptor, 59, 5); + level++; + indexmask = indexmask_grainsize; + goto next_level; + } + + /* + * Block entry at level 1 or 2, or page entry at level 3. + * These are basically the same thing, although the number + * of bits we pull in from the vaddr varies. Note that although + * descaddrmask masks enough of the low bits of the descriptor + * to give a correct page or table address, the address field + * in a block descriptor is smaller; so we need to explicitly + * clear the lower bits here before ORing in the low vaddr bits. + */ + page_size = (1ULL << ((stride * (4 - level)) + 3)); + descaddr &= ~(hwaddr)(page_size - 1); + descaddr |= (address & (page_size - 1)); + /* Extract attributes from the descriptor */ + attrs = extract64(descriptor, 2, 10) + | (extract64(descriptor, 52, 12) << 10); + + if (regime_is_stage2(mmu_idx)) { + /* Stage 2 table descriptors do not include any attribute fields */ + goto skip_attrs; + } + /* Merge in attributes from table descriptors */ + attrs |= nstable << 3; /* NS */ + guarded = extract64(descriptor, 50, 1); /* GP */ + if (param.hpd) { + /* HPD disables all the table attributes except NSTable. */ + goto skip_attrs; + } + attrs |= extract32(tableattrs, 0, 2) << 11; /* XN, PXN */ + /* + * The sense of AP[1] vs APTable[0] is reversed, as APTable[0] == 1 + * means "force PL1 access only", which means forcing AP[1] to 0. + */ + attrs &= ~(extract32(tableattrs, 2, 1) << 4); /* !APT[0] => AP[1] */ + attrs |= extract32(tableattrs, 3, 1) << 5; /* APT[1] => AP[2] */ + skip_attrs: + /* * Here descaddr is the final physical address, and attributes * are all in attrs. -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Always overriding fi->type was incorrect, as we would not properly propagate the fault type from S1_ptw_translate, or arm_ldq_ptw. Simplify things by providing a new label for a translation fault. For other faults, store into fi directly. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20221024051851.3074715-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/ptw.c | 31 +++++++++++++------------------ 1 file changed, 13 insertions(+), 18 deletions(-) diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, ARMCPU *cpu = env_archcpu(env); ARMMMUIdx mmu_idx = ptw->in_mmu_idx; bool is_secure = ptw->in_secure; - /* Read an LPAE long-descriptor translation table. */ - ARMFaultType fault_type = ARMFault_Translation; uint32_t level; ARMVAParameters param; uint64_t ttbr; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, * so our choice is to always raise the fault. */ if (param.tsz_oob) { - fault_type = ARMFault_Translation; - goto do_fault; + goto do_translation_fault; } addrsize = 64 - 8 * param.tbi; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, addrsize - inputsize); if (-top_bits != param.select) { /* The gap between the two regions is a Translation fault */ - fault_type = ARMFault_Translation; - goto do_fault; + goto do_translation_fault; } } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, * Translation table walk disabled => Translation fault on TLB miss * Note: This is always 0 on 64-bit EL2 and EL3. */ - goto do_fault; + goto do_translation_fault; } if (!regime_is_stage2(mmu_idx)) { @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, if (param.ds && stride == 9 && sl2) { if (sl0 != 0) { level = 0; - fault_type = ARMFault_Translation; - goto do_fault; + goto do_translation_fault; } startlevel = -1; } else if (!aarch64 || stride == 9) { @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, ok = check_s2_mmu_setup(cpu, aarch64, startlevel, inputsize, stride, outputsize); if (!ok) { - fault_type = ARMFault_Translation; - goto do_fault; + goto do_translation_fault; } level = startlevel; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, descaddr |= extract64(ttbr, 2, 4) << 48; } else if (descaddr >> outputsize) { level = 0; - fault_type = ARMFault_AddressSize; + fi->type = ARMFault_AddressSize; goto do_fault; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, if (!(descriptor & 1) || (!(descriptor & 2) && (level == 3))) { /* Invalid, or the Reserved level 3 encoding */ - goto do_fault; + goto do_translation_fault; } descaddr = descriptor & descaddrmask; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, descaddr |= extract64(descriptor, 12, 4) << 48; } } else if (descaddr >> outputsize) { - fault_type = ARMFault_AddressSize; + fi->type = ARMFault_AddressSize; goto do_fault; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, * Here descaddr is the final physical address, and attributes * are all in attrs. */ - fault_type = ARMFault_AccessFlag; if ((attrs & (1 << 8)) == 0) { /* Access flag */ + fi->type = ARMFault_AccessFlag; goto do_fault; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, result->f.prot = get_S1prot(env, mmu_idx, aarch64, ap, ns, xn, pxn); } - fault_type = ARMFault_Permission; if (!(result->f.prot & (1 << access_type))) { + fi->type = ARMFault_Permission; goto do_fault; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, result->f.lg_page_size = ctz64(page_size); return false; -do_fault: - fi->type = fault_type; + do_translation_fault: + fi->type = ARMFault_Translation; + do_fault: fi->level = level; /* Tag the error as S2 for failed S1 PTW at S2 or ordinary S2. */ fi->stage2 = fi->s1ptw || regime_is_stage2(mmu_idx); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Leave the upper and lower attributes in the place they originate from in the descriptor. Shifting them around is confusing, since one cannot read the bit numbers out of the manual. Also, new attributes have been added which would alter the shifts. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20221024051851.3074715-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/ptw.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, hwaddr descaddr, indexmask, indexmask_grainsize; uint32_t tableattrs; target_ulong page_size; - uint32_t attrs; + uint64_t attrs; int32_t stride; int addrsize, inputsize, outputsize; uint64_t tcr = regime_tcr(env, mmu_idx); @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, descaddr &= ~(hwaddr)(page_size - 1); descaddr |= (address & (page_size - 1)); /* Extract attributes from the descriptor */ - attrs = extract64(descriptor, 2, 10) - | (extract64(descriptor, 52, 12) << 10); + attrs = descriptor & (MAKE_64BIT_MASK(2, 10) | MAKE_64BIT_MASK(52, 12)); if (regime_is_stage2(mmu_idx)) { /* Stage 2 table descriptors do not include any attribute fields */ goto skip_attrs; } /* Merge in attributes from table descriptors */ - attrs |= nstable << 3; /* NS */ + attrs |= nstable << 5; /* NS */ guarded = extract64(descriptor, 50, 1); /* GP */ if (param.hpd) { /* HPD disables all the table attributes except NSTable. */ goto skip_attrs; } - attrs |= extract32(tableattrs, 0, 2) << 11; /* XN, PXN */ + attrs |= extract64(tableattrs, 0, 2) << 53; /* XN, PXN */ /* * The sense of AP[1] vs APTable[0] is reversed, as APTable[0] == 1 * means "force PL1 access only", which means forcing AP[1] to 0. */ - attrs &= ~(extract32(tableattrs, 2, 1) << 4); /* !APT[0] => AP[1] */ - attrs |= extract32(tableattrs, 3, 1) << 5; /* APT[1] => AP[2] */ + attrs &= ~(extract64(tableattrs, 2, 1) << 6); /* !APT[0] => AP[1] */ + attrs |= extract32(tableattrs, 3, 1) << 7; /* APT[1] => AP[2] */ skip_attrs: /* * Here descaddr is the final physical address, and attributes * are all in attrs. */ - if ((attrs & (1 << 8)) == 0) { + if ((attrs & (1 << 10)) == 0) { /* Access flag */ fi->type = ARMFault_AccessFlag; goto do_fault; } - ap = extract32(attrs, 4, 2); + ap = extract32(attrs, 6, 2); if (regime_is_stage2(mmu_idx)) { ns = mmu_idx == ARMMMUIdx_Stage2; - xn = extract32(attrs, 11, 2); + xn = extract64(attrs, 53, 2); result->f.prot = get_S2prot(env, ap, xn, s1_is_el0); } else { - ns = extract32(attrs, 3, 1); - xn = extract32(attrs, 12, 1); - pxn = extract32(attrs, 11, 1); + ns = extract32(attrs, 5, 1); + xn = extract64(attrs, 54, 1); + pxn = extract64(attrs, 53, 1); result->f.prot = get_S1prot(env, mmu_idx, aarch64, ap, ns, xn, pxn); } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, if (regime_is_stage2(mmu_idx)) { result->cacheattrs.is_s2_format = true; - result->cacheattrs.attrs = extract32(attrs, 0, 4); + result->cacheattrs.attrs = extract32(attrs, 2, 4); } else { /* Index into MAIR registers for cache attributes */ - uint8_t attrindx = extract32(attrs, 0, 3); + uint8_t attrindx = extract32(attrs, 2, 3); uint64_t mair = env->cp15.mair_el[regime_el(env, mmu_idx)]; assert(attrindx <= 7); result->cacheattrs.is_s2_format = false; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, if (param.ds) { result->cacheattrs.shareability = param.sh; } else { - result->cacheattrs.shareability = extract32(attrs, 6, 2); + result->cacheattrs.shareability = extract32(attrs, 8, 2); } result->f.phys_addr = descaddr; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Both GP and DBM are in the upper attribute block. Extend the computation of attrs to include them, then simplify the setting of guarded. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20221024051851.3074715-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/ptw.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, uint32_t el = regime_el(env, mmu_idx); uint64_t descaddrmask; bool aarch64 = arm_el_is_aa64(env, el); - bool guarded = false; uint64_t descriptor; bool nstable; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, descaddr &= ~(hwaddr)(page_size - 1); descaddr |= (address & (page_size - 1)); /* Extract attributes from the descriptor */ - attrs = descriptor & (MAKE_64BIT_MASK(2, 10) | MAKE_64BIT_MASK(52, 12)); + attrs = descriptor & (MAKE_64BIT_MASK(2, 10) | MAKE_64BIT_MASK(50, 14)); if (regime_is_stage2(mmu_idx)) { /* Stage 2 table descriptors do not include any attribute fields */ @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, } /* Merge in attributes from table descriptors */ attrs |= nstable << 5; /* NS */ - guarded = extract64(descriptor, 50, 1); /* GP */ if (param.hpd) { /* HPD disables all the table attributes except NSTable. */ goto skip_attrs; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, /* When in aarch64 mode, and BTI is enabled, remember GP in the TLB. */ if (aarch64 && cpu_isar_feature(aa64_bti, cpu)) { - result->f.guarded = guarded; + result->f.guarded = extract64(attrs, 50, 1); /* GP */ } if (regime_is_stage2(mmu_idx)) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Replace some gotos with some nested if statements. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20221024051851.3074715-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/ptw.c | 34 ++++++++++++++++------------------ 1 file changed, 16 insertions(+), 18 deletions(-) diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, page_size = (1ULL << ((stride * (4 - level)) + 3)); descaddr &= ~(hwaddr)(page_size - 1); descaddr |= (address & (page_size - 1)); - /* Extract attributes from the descriptor */ - attrs = descriptor & (MAKE_64BIT_MASK(2, 10) | MAKE_64BIT_MASK(50, 14)); - if (regime_is_stage2(mmu_idx)) { - /* Stage 2 table descriptors do not include any attribute fields */ - goto skip_attrs; - } - /* Merge in attributes from table descriptors */ - attrs |= nstable << 5; /* NS */ - if (param.hpd) { - /* HPD disables all the table attributes except NSTable. */ - goto skip_attrs; - } - attrs |= extract64(tableattrs, 0, 2) << 53; /* XN, PXN */ /* - * The sense of AP[1] vs APTable[0] is reversed, as APTable[0] == 1 - * means "force PL1 access only", which means forcing AP[1] to 0. + * Extract attributes from the descriptor, and apply table descriptors. + * Stage 2 table descriptors do not include any attribute fields. + * HPD disables all the table attributes except NSTable. */ - attrs &= ~(extract64(tableattrs, 2, 1) << 6); /* !APT[0] => AP[1] */ - attrs |= extract32(tableattrs, 3, 1) << 7; /* APT[1] => AP[2] */ - skip_attrs: + attrs = descriptor & (MAKE_64BIT_MASK(2, 10) | MAKE_64BIT_MASK(50, 14)); + if (!regime_is_stage2(mmu_idx)) { + attrs |= nstable << 5; /* NS */ + if (!param.hpd) { + attrs |= extract64(tableattrs, 0, 2) << 53; /* XN, PXN */ + /* + * The sense of AP[1] vs APTable[0] is reversed, as APTable[0] == 1 + * means "force PL1 access only", which means forcing AP[1] to 0. + */ + attrs &= ~(extract64(tableattrs, 2, 1) << 6); /* !APT[0] => AP[1] */ + attrs |= extract32(tableattrs, 3, 1) << 7; /* APT[1] => AP[2] */ + } + } /* * Here descaddr is the final physical address, and attributes -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Perform the atomic update for hardware management of the access flag. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20221024051851.3074715-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/cpu64.c | 1 + target/arm/ptw.c | 176 +++++++++++++++++++++++++++++----- 3 files changed, 156 insertions(+), 22 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_FlagM (Flag manipulation instructions v2) - FEAT_FlagM2 (Enhancements to flag manipulation instructions) - FEAT_GTG (Guest translation granule size) +- FEAT_HAFDBS (Hardware management of the access flag and dirty bit state) - FEAT_HCX (Support for the HCRX_EL2 register) - FEAT_HPDS (Hierarchical permission disables) - FEAT_I8MM (AArch64 Int8 matrix multiplication instructions) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) cpu->isar.id_aa64mmfr0 = t; t = cpu->isar.id_aa64mmfr1; + t = FIELD_DP64(t, ID_AA64MMFR1, HAFDBS, 1); /* FEAT_HAFDBS, AF only */ t = FIELD_DP64(t, ID_AA64MMFR1, VMIDBITS, 2); /* FEAT_VMID16 */ t = FIELD_DP64(t, ID_AA64MMFR1, VH, 1); /* FEAT_VHE */ t = FIELD_DP64(t, ID_AA64MMFR1, HPDS, 1); /* FEAT_HPDS */ diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ typedef struct S1Translate { bool in_secure; bool in_debug; bool out_secure; + bool out_rw; bool out_be; + hwaddr out_virt; hwaddr out_phys; void *out_host; } S1Translate; @@ -XXX,XX +XXX,XX @@ static bool S1_ptw_translate(CPUARMState *env, S1Translate *ptw, uint8_t pte_attrs; bool pte_secure; + ptw->out_virt = addr; + if (unlikely(ptw->in_debug)) { /* * From gdbstub, do not use softmmu so that we don't modify the @@ -XXX,XX +XXX,XX @@ static bool S1_ptw_translate(CPUARMState *env, S1Translate *ptw, pte_secure = is_secure; } ptw->out_host = NULL; + ptw->out_rw = false; } else { CPUTLBEntryFull *full; int flags; @@ -XXX,XX +XXX,XX @@ static bool S1_ptw_translate(CPUARMState *env, S1Translate *ptw, goto fail; } ptw->out_phys = full->phys_addr; + ptw->out_rw = full->prot & PROT_WRITE; pte_attrs = full->pte_attrs; pte_secure = full->attrs.secure; } @@ -XXX,XX +XXX,XX @@ static uint32_t arm_ldl_ptw(CPUARMState *env, S1Translate *ptw, ARMMMUFaultInfo *fi) { CPUState *cs = env_cpu(env); + void *host = ptw->out_host; uint32_t data; - if (likely(ptw->out_host)) { + if (likely(host)) { /* Page tables are in RAM, and we have the host address. */ + data = qatomic_read((uint32_t *)host); if (ptw->out_be) { - data = ldl_be_p(ptw->out_host); + data = be32_to_cpu(data); } else { - data = ldl_le_p(ptw->out_host); + data = le32_to_cpu(data); } } else { /* Page tables are in MMIO. */ @@ -XXX,XX +XXX,XX @@ static uint64_t arm_ldq_ptw(CPUARMState *env, S1Translate *ptw, ARMMMUFaultInfo *fi) { CPUState *cs = env_cpu(env); + void *host = ptw->out_host; uint64_t data; - if (likely(ptw->out_host)) { + if (likely(host)) { /* Page tables are in RAM, and we have the host address. */ +#ifdef CONFIG_ATOMIC64 + data = qatomic_read__nocheck((uint64_t *)host); if (ptw->out_be) { - data = ldq_be_p(ptw->out_host); + data = be64_to_cpu(data); } else { - data = ldq_le_p(ptw->out_host); + data = le64_to_cpu(data); } +#else + if (ptw->out_be) { + data = ldq_be_p(host); + } else { + data = ldq_le_p(host); + } +#endif } else { /* Page tables are in MMIO. */ MemTxAttrs attrs = { .secure = ptw->out_secure }; @@ -XXX,XX +XXX,XX @@ static uint64_t arm_ldq_ptw(CPUARMState *env, S1Translate *ptw, return data; } +static uint64_t arm_casq_ptw(CPUARMState *env, uint64_t old_val, + uint64_t new_val, S1Translate *ptw, + ARMMMUFaultInfo *fi) +{ + uint64_t cur_val; + void *host = ptw->out_host; + + if (unlikely(!host)) { + fi->type = ARMFault_UnsuppAtomicUpdate; + fi->s1ptw = true; + return 0; + } + + /* + * Raising a stage2 Protection fault for an atomic update to a read-only + * page is delayed until it is certain that there is a change to make. + */ + if (unlikely(!ptw->out_rw)) { + int flags; + void *discard; + + env->tlb_fi = fi; + flags = probe_access_flags(env, ptw->out_virt, MMU_DATA_STORE, + arm_to_core_mmu_idx(ptw->in_ptw_idx), + true, &discard, 0); + env->tlb_fi = NULL; + + if (unlikely(flags & TLB_INVALID_MASK)) { + assert(fi->type != ARMFault_None); + fi->s2addr = ptw->out_virt; + fi->stage2 = true; + fi->s1ptw = true; + fi->s1ns = !ptw->in_secure; + return 0; + } + + /* In case CAS mismatches and we loop, remember writability. */ + ptw->out_rw = true; + } + +#ifdef CONFIG_ATOMIC64 + if (ptw->out_be) { + old_val = cpu_to_be64(old_val); + new_val = cpu_to_be64(new_val); + cur_val = qatomic_cmpxchg__nocheck((uint64_t *)host, old_val, new_val); + cur_val = be64_to_cpu(cur_val); + } else { + old_val = cpu_to_le64(old_val); + new_val = cpu_to_le64(new_val); + cur_val = qatomic_cmpxchg__nocheck((uint64_t *)host, old_val, new_val); + cur_val = le64_to_cpu(cur_val); + } +#else + /* + * We can't support the full 64-bit atomic cmpxchg on the host. + * Because this is only used for FEAT_HAFDBS, which is only for AA64, + * we know that TCG_OVERSIZED_GUEST is set, which means that we are + * running in round-robin mode and could only race with dma i/o. + */ +#ifndef TCG_OVERSIZED_GUEST +# error "Unexpected configuration" +#endif + bool locked = qemu_mutex_iothread_locked(); + if (!locked) { + qemu_mutex_lock_iothread(); + } + if (ptw->out_be) { + cur_val = ldq_be_p(host); + if (cur_val == old_val) { + stq_be_p(host, new_val); + } + } else { + cur_val = ldq_le_p(host); + if (cur_val == old_val) { + stq_le_p(host, new_val); + } + } + if (!locked) { + qemu_mutex_unlock_iothread(); + } +#endif + + return cur_val; +} + static bool get_level1_table_address(CPUARMState *env, ARMMMUIdx mmu_idx, uint32_t *table, uint32_t address) { @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, uint32_t el = regime_el(env, mmu_idx); uint64_t descaddrmask; bool aarch64 = arm_el_is_aa64(env, el); - uint64_t descriptor; + uint64_t descriptor, new_descriptor; bool nstable; /* TODO: This code does not support shareability levels. */ @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, if (fi->type != ARMFault_None) { goto do_fault; } + new_descriptor = descriptor; + restart_atomic_update: if (!(descriptor & 1) || (!(descriptor & 2) && (level == 3))) { /* Invalid, or the Reserved level 3 encoding */ goto do_translation_fault; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, * to give a correct page or table address, the address field * in a block descriptor is smaller; so we need to explicitly * clear the lower bits here before ORing in the low vaddr bits. + * + * Afterward, descaddr is the final physical address. */ page_size = (1ULL << ((stride * (4 - level)) + 3)); descaddr &= ~(hwaddr)(page_size - 1); descaddr |= (address & (page_size - 1)); + if (likely(!ptw->in_debug)) { + /* + * Access flag. + * If HA is enabled, prepare to update the descriptor below. + * Otherwise, pass the access fault on to software. + */ + if (!(descriptor & (1 << 10))) { + if (param.ha) { + new_descriptor |= 1 << 10; /* AF */ + } else { + fi->type = ARMFault_AccessFlag; + goto do_fault; + } + } + } + /* - * Extract attributes from the descriptor, and apply table descriptors. - * Stage 2 table descriptors do not include any attribute fields. - * HPD disables all the table attributes except NSTable. + * Extract attributes from the (modified) descriptor, and apply + * table descriptors. Stage 2 table descriptors do not include + * any attribute fields. HPD disables all the table attributes + * except NSTable. */ - attrs = descriptor & (MAKE_64BIT_MASK(2, 10) | MAKE_64BIT_MASK(50, 14)); + attrs = new_descriptor & (MAKE_64BIT_MASK(2, 10) | MAKE_64BIT_MASK(50, 14)); if (!regime_is_stage2(mmu_idx)) { attrs |= nstable << 5; /* NS */ if (!param.hpd) { @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, } } - /* - * Here descaddr is the final physical address, and attributes - * are all in attrs. - */ - if ((attrs & (1 << 10)) == 0) { - /* Access flag */ - fi->type = ARMFault_AccessFlag; - goto do_fault; - } - ap = extract32(attrs, 6, 2); - if (regime_is_stage2(mmu_idx)) { ns = mmu_idx == ARMMMUIdx_Stage2; xn = extract64(attrs, 53, 2); @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, goto do_fault; } + /* If FEAT_HAFDBS has made changes, update the PTE. */ + if (new_descriptor != descriptor) { + new_descriptor = arm_casq_ptw(env, descriptor, new_descriptor, ptw, fi); + if (fi->type != ARMFault_None) { + goto do_fault; + } + /* + * I_YZSVV says that if the in-memory descriptor has changed, + * then we must use the information in that new value + * (which might include a different output address, different + * attributes, or generate a fault). + * Restart the handling of the descriptor value from scratch. + */ + if (new_descriptor != descriptor) { + descriptor = new_descriptor; + goto restart_atomic_update; + } + } + if (ns) { /* * The NS bit will (as required by the architecture) have no effect if -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Perform the atomic update for hardware management of the dirty bit. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20221024051851.3074715-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 2 +- target/arm/ptw.c | 16 ++++++++++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) cpu->isar.id_aa64mmfr0 = t; t = cpu->isar.id_aa64mmfr1; - t = FIELD_DP64(t, ID_AA64MMFR1, HAFDBS, 1); /* FEAT_HAFDBS, AF only */ + t = FIELD_DP64(t, ID_AA64MMFR1, HAFDBS, 2); /* FEAT_HAFDBS */ t = FIELD_DP64(t, ID_AA64MMFR1, VMIDBITS, 2); /* FEAT_VMID16 */ t = FIELD_DP64(t, ID_AA64MMFR1, VH, 1); /* FEAT_VHE */ t = FIELD_DP64(t, ID_AA64MMFR1, HPDS, 1); /* FEAT_HPDS */ diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, goto do_fault; } } + + /* + * Dirty Bit. + * If HD is enabled, pre-emptively set/clear the appropriate AP/S2AP + * bit for writeback. The actual write protection test may still be + * overridden by tableattrs, to be merged below. + */ + if (param.hd + && extract64(descriptor, 51, 1) /* DBM */ + && access_type == MMU_DATA_STORE) { + if (regime_is_stage2(mmu_idx)) { + new_descriptor |= 1ull << 7; /* set S2AP[1] */ + } else { + new_descriptor &= ~(1ull << 7); /* clear AP[2] */ + } + } } /* -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We had only been reporting the stage2 page size. This causes problems if stage1 is using a larger page size (16k, 2M, etc), but stage2 is using a smaller page size, because cputlb does not set large_page_{addr,mask} properly. Fix by using the max of the two page sizes. Reported-by: Marc Zyngier <maz@kernel.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20221024051851.3074715-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/ptw.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_twostage(CPUARMState *env, S1Translate *ptw, ARMMMUFaultInfo *fi) { hwaddr ipa; - int s1_prot; + int s1_prot, s1_lgpgsz; bool is_secure = ptw->in_secure; bool ret, ipa_secure, s2walk_secure; ARMCacheAttrs cacheattrs1; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_twostage(CPUARMState *env, S1Translate *ptw, * Save the stage1 results so that we may merge prot and cacheattrs later. */ s1_prot = result->f.prot; + s1_lgpgsz = result->f.lg_page_size; cacheattrs1 = result->cacheattrs; memset(result, 0, sizeof(*result)); @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_twostage(CPUARMState *env, S1Translate *ptw, return ret; } + /* + * Use the maximum of the S1 & S2 page size, so that invalidation + * of pages > TARGET_PAGE_SIZE works correctly. + */ + if (result->f.lg_page_size < s1_lgpgsz) { + result->f.lg_page_size = s1_lgpgsz; + } + /* Combine the S1 and S2 cache attributes. */ hcr = arm_hcr_el2_eff_secstate(env, is_secure); if (hcr & HCR_DC) { -- 2.25.1 From: "Jason A. Donenfeld" <Jason@zx2c4.com> Snapshot loading only expects to call deterministic handlers, not non-deterministic ones. So introduce a way of registering handlers that won't be called when reseting for snapshots. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Message-id: 20221025004327.568476-2-Jason@zx2c4.com [PMM: updated json doc comment with Markus' text; fixed checkpatch style nit] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- qapi/run-state.json | 6 +++++- include/hw/boards.h | 2 +- include/sysemu/reset.h | 5 ++++- hw/arm/aspeed.c | 4 ++-- hw/arm/mps2-tz.c | 4 ++-- hw/core/reset.c | 17 ++++++++++++++++- hw/hppa/machine.c | 4 ++-- hw/i386/microvm.c | 4 ++-- hw/i386/pc.c | 6 +++--- hw/ppc/pegasos2.c | 4 ++-- hw/ppc/pnv.c | 4 ++-- hw/ppc/spapr.c | 4 ++-- hw/s390x/s390-virtio-ccw.c | 4 ++-- migration/savevm.c | 2 +- softmmu/runstate.c | 11 ++++++++--- 15 files changed, 54 insertions(+), 27 deletions(-) diff --git a/qapi/run-state.json b/qapi/run-state.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/run-state.json +++ b/qapi/run-state.json @@ -XXX,XX +XXX,XX @@ # ignores --no-reboot. This is useful for sanitizing # hypercalls on s390 that are used during kexec/kdump/boot # +# @snapshot-load: A snapshot is being loaded by the record & replay +# subsystem. This value is used only within QEMU. It +# doesn't occur in QMP. (since 7.2) +# ## { 'enum': 'ShutdownCause', # Beware, shutdown_caused_by_guest() depends on enumeration order 'data': [ 'none', 'host-error', 'host-qmp-quit', 'host-qmp-system-reset', 'host-signal', 'host-ui', 'guest-shutdown', 'guest-reset', - 'guest-panic', 'subsystem-reset'] } + 'guest-panic', 'subsystem-reset', 'snapshot-load'] } ## # @StatusInfo: diff --git a/include/hw/boards.h b/include/hw/boards.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -XXX,XX +XXX,XX @@ struct MachineClass { const char *deprecation_reason; void (*init)(MachineState *state); - void (*reset)(MachineState *state); + void (*reset)(MachineState *state, ShutdownCause reason); void (*wakeup)(MachineState *state); int (*kvm_type)(MachineState *machine, const char *arg); diff --git a/include/sysemu/reset.h b/include/sysemu/reset.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/reset.h +++ b/include/sysemu/reset.h @@ -XXX,XX +XXX,XX @@ #ifndef QEMU_SYSEMU_RESET_H #define QEMU_SYSEMU_RESET_H +#include "qapi/qapi-events-run-state.h" + typedef void QEMUResetHandler(void *opaque); void qemu_register_reset(QEMUResetHandler *func, void *opaque); +void qemu_register_reset_nosnapshotload(QEMUResetHandler *func, void *opaque); void qemu_unregister_reset(QEMUResetHandler *func, void *opaque); -void qemu_devices_reset(void); +void qemu_devices_reset(ShutdownCause reason); #endif diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ static void aspeed_machine_bletchley_class_init(ObjectClass *oc, void *data) aspeed_soc_num_cpus(amc->soc_name); } -static void fby35_reset(MachineState *state) +static void fby35_reset(MachineState *state, ShutdownCause reason) { AspeedMachineState *bmc = ASPEED_MACHINE(state); AspeedGPIOState *gpio = &bmc->soc.gpio; - qemu_devices_reset(); + qemu_devices_reset(reason); /* Board ID: 7 (Class-1, 4 slots) */ object_property_set_bool(OBJECT(gpio), "gpioV4", true, &error_fatal); diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void mps2_set_remap(Object *obj, const char *value, Error **errp) } } -static void mps2_machine_reset(MachineState *machine) +static void mps2_machine_reset(MachineState *machine, ShutdownCause reason) { MPS2TZMachineState *mms = MPS2TZ_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void mps2_machine_reset(MachineState *machine) * reset see the correct mapping. */ remap_memory(mms, mms->remap); - qemu_devices_reset(); + qemu_devices_reset(reason); } static void mps2tz_class_init(ObjectClass *oc, void *data) diff --git a/hw/core/reset.c b/hw/core/reset.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/reset.c +++ b/hw/core/reset.c @@ -XXX,XX +XXX,XX @@ typedef struct QEMUResetEntry { QTAILQ_ENTRY(QEMUResetEntry) entry; QEMUResetHandler *func; void *opaque; + bool skip_on_snapshot_load; } QEMUResetEntry; static QTAILQ_HEAD(, QEMUResetEntry) reset_handlers = @@ -XXX,XX +XXX,XX @@ void qemu_register_reset(QEMUResetHandler *func, void *opaque) QTAILQ_INSERT_TAIL(&reset_handlers, re, entry); } +void qemu_register_reset_nosnapshotload(QEMUResetHandler *func, void *opaque) +{ + QEMUResetEntry *re = g_new0(QEMUResetEntry, 1); + + re->func = func; + re->opaque = opaque; + re->skip_on_snapshot_load = true; + QTAILQ_INSERT_TAIL(&reset_handlers, re, entry); +} + void qemu_unregister_reset(QEMUResetHandler *func, void *opaque) { QEMUResetEntry *re; @@ -XXX,XX +XXX,XX @@ void qemu_unregister_reset(QEMUResetHandler *func, void *opaque) } } -void qemu_devices_reset(void) +void qemu_devices_reset(ShutdownCause reason) { QEMUResetEntry *re, *nre; /* reset all devices */ QTAILQ_FOREACH_SAFE(re, &reset_handlers, entry, nre) { + if (reason == SHUTDOWN_CAUSE_SNAPSHOT_LOAD && + re->skip_on_snapshot_load) { + continue; + } re->func(re->opaque); } } diff --git a/hw/hppa/machine.c b/hw/hppa/machine.c index XXXXXXX..XXXXXXX 100644 --- a/hw/hppa/machine.c +++ b/hw/hppa/machine.c @@ -XXX,XX +XXX,XX @@ static void machine_hppa_init(MachineState *machine) cpu[0]->env.gr[19] = FW_CFG_IO_BASE; } -static void hppa_machine_reset(MachineState *ms) +static void hppa_machine_reset(MachineState *ms, ShutdownCause reason) { unsigned int smp_cpus = ms->smp.cpus; int i; - qemu_devices_reset(); + qemu_devices_reset(reason); /* Start all CPUs at the firmware entry point. * Monarch CPU will initialize firmware, secondary CPUs diff --git a/hw/i386/microvm.c b/hw/i386/microvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i386/microvm.c +++ b/hw/i386/microvm.c @@ -XXX,XX +XXX,XX @@ static void microvm_machine_state_init(MachineState *machine) microvm_devices_init(mms); } -static void microvm_machine_reset(MachineState *machine) +static void microvm_machine_reset(MachineState *machine, ShutdownCause reason) { MicrovmMachineState *mms = MICROVM_MACHINE(machine); CPUState *cs; @@ -XXX,XX +XXX,XX @@ static void microvm_machine_reset(MachineState *machine) mms->kernel_cmdline_fixed = true; } - qemu_devices_reset(); + qemu_devices_reset(reason); CPU_FOREACH(cs) { cpu = X86_CPU(cs); diff --git a/hw/i386/pc.c b/hw/i386/pc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -XXX,XX +XXX,XX @@ static void pc_machine_initfn(Object *obj) cxl_machine_init(obj, &pcms->cxl_devices_state); } -static void pc_machine_reset(MachineState *machine) +static void pc_machine_reset(MachineState *machine, ShutdownCause reason) { CPUState *cs; X86CPU *cpu; - qemu_devices_reset(); + qemu_devices_reset(reason); /* Reset APIC after devices have been reset to cancel * any changes that qemu_devices_reset() might have done. @@ -XXX,XX +XXX,XX @@ static void pc_machine_reset(MachineState *machine) static void pc_machine_wakeup(MachineState *machine) { cpu_synchronize_all_states(); - pc_machine_reset(machine); + pc_machine_reset(machine, SHUTDOWN_CAUSE_NONE); cpu_synchronize_all_post_reset(); } diff --git a/hw/ppc/pegasos2.c b/hw/ppc/pegasos2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ppc/pegasos2.c +++ b/hw/ppc/pegasos2.c @@ -XXX,XX +XXX,XX @@ static void pegasos2_pci_config_write(Pegasos2MachineState *pm, int bus, pegasos2_mv_reg_write(pm, pcicfg + 4, len, val); } -static void pegasos2_machine_reset(MachineState *machine) +static void pegasos2_machine_reset(MachineState *machine, ShutdownCause reason) { Pegasos2MachineState *pm = PEGASOS2_MACHINE(machine); void *fdt; uint64_t d[2]; int sz; - qemu_devices_reset(); + qemu_devices_reset(reason); if (!pm->vof) { return; /* Firmware should set up machine so nothing to do */ } diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ppc/pnv.c +++ b/hw/ppc/pnv.c @@ -XXX,XX +XXX,XX @@ static void pnv_powerdown_notify(Notifier *n, void *opaque) } } -static void pnv_reset(MachineState *machine) +static void pnv_reset(MachineState *machine, ShutdownCause reason) { PnvMachineState *pnv = PNV_MACHINE(machine); IPMIBmc *bmc; void *fdt; - qemu_devices_reset(); + qemu_devices_reset(reason); /* * The machine should provide by default an internal BMC simulator. diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -XXX,XX +XXX,XX @@ void spapr_check_mmu_mode(bool guest_radix) } } -static void spapr_machine_reset(MachineState *machine) +static void spapr_machine_reset(MachineState *machine, ShutdownCause reason) { SpaprMachineState *spapr = SPAPR_MACHINE(machine); PowerPCCPU *first_ppc_cpu; @@ -XXX,XX +XXX,XX @@ static void spapr_machine_reset(MachineState *machine) spapr_setup_hpt(spapr); } - qemu_devices_reset(); + qemu_devices_reset(reason); spapr_ovec_cleanup(spapr->ov5_cas); spapr->ov5_cas = spapr_ovec_new(); diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index XXXXXXX..XXXXXXX 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -XXX,XX +XXX,XX @@ static void s390_pv_prepare_reset(S390CcwMachineState *ms) s390_pv_prep_reset(); } -static void s390_machine_reset(MachineState *machine) +static void s390_machine_reset(MachineState *machine, ShutdownCause reason) { S390CcwMachineState *ms = S390_CCW_MACHINE(machine); enum s390_reset reset_type; @@ -XXX,XX +XXX,XX @@ static void s390_machine_reset(MachineState *machine) s390_machine_unprotect(ms); } - qemu_devices_reset(); + qemu_devices_reset(reason); s390_crypto_reset(); /* configure and start the ipl CPU only */ diff --git a/migration/savevm.c b/migration/savevm.c index XXXXXXX..XXXXXXX 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -XXX,XX +XXX,XX @@ bool load_snapshot(const char *name, const char *vmstate, goto err_drain; } - qemu_system_reset(SHUTDOWN_CAUSE_NONE); + qemu_system_reset(SHUTDOWN_CAUSE_SNAPSHOT_LOAD); mis->from_src_file = f; if (!yank_register_instance(MIGRATION_YANK_INSTANCE, errp)) { diff --git a/softmmu/runstate.c b/softmmu/runstate.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/runstate.c +++ b/softmmu/runstate.c @@ -XXX,XX +XXX,XX @@ void qemu_system_reset(ShutdownCause reason) cpu_synchronize_all_states(); if (mc && mc->reset) { - mc->reset(current_machine); + mc->reset(current_machine, reason); } else { - qemu_devices_reset(); + qemu_devices_reset(reason); } - if (reason && reason != SHUTDOWN_CAUSE_SUBSYSTEM_RESET) { + switch (reason) { + case SHUTDOWN_CAUSE_NONE: + case SHUTDOWN_CAUSE_SUBSYSTEM_RESET: + case SHUTDOWN_CAUSE_SNAPSHOT_LOAD: + break; + default: qapi_event_send_reset(shutdown_caused_by_guest(reason), reason); } cpu_synchronize_all_post_reset(); -- 2.25.1 From: "Jason A. Donenfeld" <Jason@zx2c4.com> When the system reboots, the rng-seed that the FDT has should be re-randomized, so that the new boot gets a new seed. Several architectures require this functionality, so export a function for injecting a new seed into the given FDT. Cc: Alistair Francis <alistair.francis@wdc.com> Cc: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20221025004327.568476-3-Jason@zx2c4.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/sysemu/device_tree.h | 9 +++++++++ softmmu/device_tree.c | 21 +++++++++++++++++++++ 2 files changed, 30 insertions(+) diff --git a/include/sysemu/device_tree.h b/include/sysemu/device_tree.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/device_tree.h +++ b/include/sysemu/device_tree.h @@ -XXX,XX +XXX,XX @@ int qemu_fdt_setprop_sized_cells_from_array(void *fdt, qdt_tmp); \ }) + +/** + * qemu_fdt_randomize_seeds: + * @fdt: device tree blob + * + * Re-randomize all "rng-seed" properties with new seeds. + */ +void qemu_fdt_randomize_seeds(void *fdt); + #define FDT_PCI_RANGE_RELOCATABLE 0x80000000 #define FDT_PCI_RANGE_PREFETCHABLE 0x40000000 #define FDT_PCI_RANGE_ALIASED 0x20000000 diff --git a/softmmu/device_tree.c b/softmmu/device_tree.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/device_tree.c +++ b/softmmu/device_tree.c @@ -XXX,XX +XXX,XX @@ #include "qemu/option.h" #include "qemu/bswap.h" #include "qemu/cutils.h" +#include "qemu/guest-random.h" #include "sysemu/device_tree.h" #include "hw/loader.h" #include "hw/boards.h" @@ -XXX,XX +XXX,XX @@ void hmp_dumpdtb(Monitor *mon, const QDict *qdict) info_report("dtb dumped to %s", filename); } + +void qemu_fdt_randomize_seeds(void *fdt) +{ + int noffset, poffset, len; + const char *name; + uint8_t *data; + + for (noffset = fdt_next_node(fdt, 0, NULL); + noffset >= 0; + noffset = fdt_next_node(fdt, noffset, NULL)) { + for (poffset = fdt_first_property_offset(fdt, noffset); + poffset >= 0; + poffset = fdt_next_property_offset(fdt, poffset)) { + data = (uint8_t *)fdt_getprop_by_offset(fdt, poffset, &name, &len); + if (!data || strcmp(name, "rng-seed")) + continue; + qemu_guest_getrandom_nofail(data, len); + } + } +} -- 2.25.1 From: "Jason A. Donenfeld" <Jason@zx2c4.com> Snapshot loading is supposed to be deterministic, so we shouldn't re-randomize the various seeds used. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Message-id: 20221025004327.568476-4-Jason@zx2c4.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/i386/x86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/i386/x86.c b/hw/i386/x86.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i386/x86.c +++ b/hw/i386/x86.c @@ -XXX,XX +XXX,XX @@ void x86_load_linux(X86MachineState *x86ms, setup_data->type = cpu_to_le32(SETUP_RNG_SEED); setup_data->len = cpu_to_le32(RNG_SEED_LENGTH); qemu_guest_getrandom_nofail(setup_data->data, RNG_SEED_LENGTH); - qemu_register_reset(reset_rng_seed, setup_data); + qemu_register_reset_nosnapshotload(reset_rng_seed, setup_data); fw_cfg_add_bytes_callback(fw_cfg, FW_CFG_KERNEL_DATA, reset_rng_seed, NULL, setup_data, kernel, kernel_size, true); } else { -- 2.25.1 From: "Jason A. Donenfeld" <Jason@zx2c4.com> When the system reboots, the rng-seed that the FDT has should be re-randomized, so that the new boot gets a new seed. Since the FDT is in the ROM region at this point, we add a hook right after the ROM has been added, so that we have a pointer to that copy of the FDT. Cc: Peter Maydell <peter.maydell@linaro.org> Cc: qemu-arm@nongnu.org Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Message-id: 20221025004327.568476-5-Jason@zx2c4.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/boot.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ int arm_load_dtb(hwaddr addr, const struct arm_boot_info *binfo, * the DTB is copied again upon reset, even if addr points into RAM. */ rom_add_blob_fixed_as("dtb", fdt, size, addr, as); + qemu_register_reset_nosnapshotload(qemu_fdt_randomize_seeds, + rom_ptr_for_as(as, addr, size)); g_free(fdt); -- 2.25.1 From: "Jason A. Donenfeld" <Jason@zx2c4.com> When the system reboots, the rng-seed that the FDT has should be re-randomized, so that the new boot gets a new seed. Since the FDT is in the ROM region at this point, we add a hook right after the ROM has been added, so that we have a pointer to that copy of the FDT. Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Alistair Francis <alistair.francis@wdc.com> Cc: Bin Meng <bin.meng@windriver.com> Cc: qemu-riscv@nongnu.org Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20221025004327.568476-6-Jason@zx2c4.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/riscv/boot.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/hw/riscv/boot.c b/hw/riscv/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/riscv/boot.c +++ b/hw/riscv/boot.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/device_tree.h" #include "sysemu/qtest.h" #include "sysemu/kvm.h" +#include "sysemu/reset.h" #include <libfdt.h> @@ -XXX,XX +XXX,XX @@ uint64_t riscv_load_fdt(hwaddr dram_base, uint64_t mem_size, void *fdt) rom_add_blob_fixed_as("fdt", fdt, fdtsize, fdt_addr, &address_space_memory); + qemu_register_reset_nosnapshotload(qemu_fdt_randomize_seeds, + rom_ptr_for_as(&address_space_memory, fdt_addr, fdtsize)); return fdt_addr; } -- 2.25.1 From: "Jason A. Donenfeld" <Jason@zx2c4.com> Snapshot loading is supposed to be deterministic, so we shouldn't re-randomize the various seeds used. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Message-id: 20221025004327.568476-7-Jason@zx2c4.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/m68k/virt.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/hw/m68k/virt.c b/hw/m68k/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/m68k/virt.c +++ b/hw/m68k/virt.c @@ -XXX,XX +XXX,XX @@ typedef struct { M68kCPU *cpu; hwaddr initial_pc; hwaddr initial_stack; - struct bi_record *rng_seed; } ResetInfo; static void main_cpu_reset(void *opaque) @@ -XXX,XX +XXX,XX @@ static void main_cpu_reset(void *opaque) M68kCPU *cpu = reset_info->cpu; CPUState *cs = CPU(cpu); - if (reset_info->rng_seed) { - qemu_guest_getrandom_nofail((void *)reset_info->rng_seed->data + 2, - be16_to_cpu(*(uint16_t *)reset_info->rng_seed->data)); - } - cpu_reset(cs); cpu->env.aregs[7] = reset_info->initial_stack; cpu->env.pc = reset_info->initial_pc; } +static void rerandomize_rng_seed(void *opaque) +{ + struct bi_record *rng_seed = opaque; + qemu_guest_getrandom_nofail((void *)rng_seed->data + 2, + be16_to_cpu(*(uint16_t *)rng_seed->data)); +} + static void virt_init(MachineState *machine) { M68kCPU *cpu = NULL; @@ -XXX,XX +XXX,XX @@ static void virt_init(MachineState *machine) BOOTINFO0(param_ptr, BI_LAST); rom_add_blob_fixed_as("bootinfo", param_blob, param_ptr - param_blob, parameters_base, cs->as); - reset_info->rng_seed = rom_ptr_for_as(cs->as, parameters_base, - param_ptr - param_blob) + - (param_rng_seed - param_blob); + qemu_register_reset_nosnapshotload(rerandomize_rng_seed, + rom_ptr_for_as(cs->as, parameters_base, + param_ptr - param_blob) + + (param_rng_seed - param_blob)); g_free(param_blob); } } -- 2.25.1 From: "Jason A. Donenfeld" <Jason@zx2c4.com> Snapshot loading is supposed to be deterministic, so we shouldn't re-randomize the various seeds used. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Message-id: 20221025004327.568476-8-Jason@zx2c4.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/m68k/q800.c | 33 +++++++++++++-------------------- 1 file changed, 13 insertions(+), 20 deletions(-) diff --git a/hw/m68k/q800.c b/hw/m68k/q800.c index XXXXXXX..XXXXXXX 100644 --- a/hw/m68k/q800.c +++ b/hw/m68k/q800.c @@ -XXX,XX +XXX,XX @@ static const TypeInfo glue_info = { }, }; -typedef struct { - M68kCPU *cpu; - struct bi_record *rng_seed; -} ResetInfo; - static void main_cpu_reset(void *opaque) { - ResetInfo *reset_info = opaque; - M68kCPU *cpu = reset_info->cpu; + M68kCPU *cpu = opaque; CPUState *cs = CPU(cpu); - if (reset_info->rng_seed) { - qemu_guest_getrandom_nofail((void *)reset_info->rng_seed->data + 2, - be16_to_cpu(*(uint16_t *)reset_info->rng_seed->data)); - } - cpu_reset(cs); cpu->env.aregs[7] = ldl_phys(cs->as, 0); cpu->env.pc = ldl_phys(cs->as, 4); } +static void rerandomize_rng_seed(void *opaque) +{ + struct bi_record *rng_seed = opaque; + qemu_guest_getrandom_nofail((void *)rng_seed->data + 2, + be16_to_cpu(*(uint16_t *)rng_seed->data)); +} + static uint8_t fake_mac_rom[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, @@ -XXX,XX +XXX,XX @@ static void q800_init(MachineState *machine) NubusBus *nubus; DeviceState *glue; DriveInfo *dinfo; - ResetInfo *reset_info; uint8_t rng_seed[32]; linux_boot = (kernel_filename != NULL); @@ -XXX,XX +XXX,XX @@ static void q800_init(MachineState *machine) exit(1); } - reset_info = g_new0(ResetInfo, 1); - /* init CPUs */ cpu = M68K_CPU(cpu_create(machine->cpu_type)); - reset_info->cpu = cpu; - qemu_register_reset(main_cpu_reset, reset_info); + qemu_register_reset(main_cpu_reset, cpu); /* RAM */ memory_region_add_subregion(get_system_memory(), 0, machine->ram); @@ -XXX,XX +XXX,XX @@ static void q800_init(MachineState *machine) BOOTINFO0(param_ptr, BI_LAST); rom_add_blob_fixed_as("bootinfo", param_blob, param_ptr - param_blob, parameters_base, cs->as); - reset_info->rng_seed = rom_ptr_for_as(cs->as, parameters_base, - param_ptr - param_blob) + - (param_rng_seed - param_blob); + qemu_register_reset_nosnapshotload(rerandomize_rng_seed, + rom_ptr_for_as(cs->as, parameters_base, + param_ptr - param_blob) + + (param_rng_seed - param_blob)); g_free(param_blob); } else { uint8_t *ptr; -- 2.25.1 From: "Jason A. Donenfeld" <Jason@zx2c4.com> When the system reboots, the rng-seed that the FDT has should be re-randomized, so that the new boot gets a new seed. Since the FDT is in the ROM region at this point, we add a hook right after the ROM has been added, so that we have a pointer to that copy of the FDT. Cc: Aleksandar Rikalo <aleksandar.rikalo@syrmia.com> Cc: Paul Burton <paulburton@kernel.org> Cc: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Message-id: 20221025004327.568476-9-Jason@zx2c4.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/mips/boston.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/hw/mips/boston.c b/hw/mips/boston.c index XXXXXXX..XXXXXXX 100644 --- a/hw/mips/boston.c +++ b/hw/mips/boston.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "sysemu/qtest.h" #include "sysemu/runstate.h" +#include "sysemu/reset.h" #include <libfdt.h> #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ static void boston_mach_init(MachineState *machine) /* Calculate real fdt size after filter */ dt_size = fdt_totalsize(dtb_load_data); rom_add_blob_fixed("dtb", dtb_load_data, dt_size, dtb_paddr); + qemu_register_reset_nosnapshotload(qemu_fdt_randomize_seeds, + rom_ptr(dtb_paddr, dt_size)); } else { /* Try to load file as FIT */ fit_err = load_fit(&boston_fit_loader, machine->kernel_filename, s); -- 2.25.1 From: "Jason A. Donenfeld" <Jason@zx2c4.com> When the system reboots, the rng-seed that the FDT has should be re-randomized, so that the new boot gets a new seed. Since the FDT is in the ROM region at this point, we add a hook right after the ROM has been added, so that we have a pointer to that copy of the FDT. Cc: Stafford Horne <shorne@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Message-id: 20221025004327.568476-11-Jason@zx2c4.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/openrisc/boot.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/hw/openrisc/boot.c b/hw/openrisc/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/openrisc/boot.c +++ b/hw/openrisc/boot.c @@ -XXX,XX +XXX,XX @@ #include "hw/openrisc/boot.h" #include "sysemu/device_tree.h" #include "sysemu/qtest.h" +#include "sysemu/reset.h" #include <libfdt.h> @@ -XXX,XX +XXX,XX @@ uint32_t openrisc_load_fdt(void *fdt, hwaddr load_start, rom_add_blob_fixed_as("fdt", fdt, fdtsize, fdt_addr, &address_space_memory); + qemu_register_reset_nosnapshotload(qemu_fdt_randomize_seeds, + rom_ptr_for_as(&address_space_memory, fdt_addr, fdtsize)); return fdt_addr; } -- 2.25.1 From: "Jason A. Donenfeld" <Jason@zx2c4.com> When the system reboots, the rng-seed that the FDT has should be re-randomized, so that the new boot gets a new seed. Since the FDT is in the ROM region at this point, we add a hook right after the ROM has been added, so that we have a pointer to that copy of the FDT. Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Message-id: 20221025004327.568476-12-Jason@zx2c4.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/rx/rx-gdbsim.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/hw/rx/rx-gdbsim.c b/hw/rx/rx-gdbsim.c index XXXXXXX..XXXXXXX 100644 --- a/hw/rx/rx-gdbsim.c +++ b/hw/rx/rx-gdbsim.c @@ -XXX,XX +XXX,XX @@ #include "hw/rx/rx62n.h" #include "sysemu/qtest.h" #include "sysemu/device_tree.h" +#include "sysemu/reset.h" #include "hw/boards.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ static void rx_gdbsim_init(MachineState *machine) dtb_offset = ROUND_DOWN(machine->ram_size - dtb_size, 16); rom_add_blob_fixed("dtb", dtb, dtb_size, SDRAM_BASE + dtb_offset); + qemu_register_reset_nosnapshotload(qemu_fdt_randomize_seeds, + rom_ptr(SDRAM_BASE + dtb_offset, dtb_size)); /* Set dtb address to R1 */ RX_CPU(first_cpu)->env.regs[1] = SDRAM_BASE + dtb_offset; } -- 2.25.1