diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-06-30 09:37:26 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-06-30 09:37:26 -0700 |
| commit | 533925cb760431cb496a8c965cfd765a1a21d37e (patch) | |
| tree | c43ac0f7d69f9b9a3f1e18509a9a75654cbb3607 | |
| parent | d8b0bd57c2d68eb500f356f0f9228e6183da94ae (diff) | |
| parent | 488833ccdcac118da16701f4ee0673b20ba47fe3 (diff) | |
Merge tag 'riscv-for-linus-6.5-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux
Pull RISC-V updates from Palmer Dabbelt:
- Support for ACPI
- Various cleanups to the ISA string parsing, including making them
case-insensitive
- Support for the vector extension
- Support for independent irq/softirq stacks
- Our CPU DT binding now has "unevaluatedProperties: false"
* tag 'riscv-for-linus-6.5-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (78 commits)
riscv: hibernate: remove WARN_ON in save_processor_state
dt-bindings: riscv: cpus: switch to unevaluatedProperties: false
dt-bindings: riscv: cpus: add a ref the common cpu schema
riscv: stack: Add config of thread stack size
riscv: stack: Support HAVE_SOFTIRQ_ON_OWN_STACK
riscv: stack: Support HAVE_IRQ_EXIT_ON_IRQ_STACK
RISC-V: always report presence of extensions formerly part of the base ISA
dt-bindings: riscv: explicitly mention assumption of Zicntr & Zihpm support
RISC-V: remove decrement/increment dance in ISA string parser
RISC-V: rework comments in ISA string parser
RISC-V: validate riscv,isa at boot, not during ISA string parsing
RISC-V: split early & late of_node to hartid mapping
RISC-V: simplify register width check in ISA string parsing
perf: RISC-V: Limit the number of counters returned from SBI
riscv: replace deprecated scall with ecall
riscv: uprobes: Restore thread.bad_cause
riscv: mm: try VMA lock-based page fault handling first
riscv: mm: Pre-allocate PGD entries for vmalloc/modules area
RISC-V: hwprobe: Expose Zba, Zbb, and Zbs
RISC-V: Track ISA extensions per hart
...
78 files changed, 3077 insertions, 251 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 44bcaf791ce6..85fb0fa5d091 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1,17 +1,17 @@ - acpi= [HW,ACPI,X86,ARM64] + acpi= [HW,ACPI,X86,ARM64,RISCV64] Advanced Configuration and Power Interface Format: { force | on | off | strict | noirq | rsdt | copy_dsdt } force -- enable ACPI if default was off - on -- enable ACPI but allow fallback to DT [arm64] + on -- enable ACPI but allow fallback to DT [arm64,riscv64] off -- disable ACPI if default was on noirq -- do not use ACPI for IRQ routing strict -- Be less tolerant of platforms that are not strictly ACPI specification compliant. rsdt -- prefer RSDT over (default) XSDT copy_dsdt -- copy DSDT to memory - For ARM64, ONLY "acpi=off", "acpi=on" or "acpi=force" - are available + For ARM64 and RISCV64, ONLY "acpi=off", "acpi=on" or + "acpi=force" are available See also Documentation/power/runtime_pm.rst, pci=noacpi diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index 3d2934b15e80..67bd239ead0b 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -23,6 +23,9 @@ description: | two cores, each of which has two hyperthreads, could be described as having four harts. +allOf: + - $ref: /schemas/cpu.yaml# + properties: compatible: oneOf: @@ -61,7 +64,7 @@ properties: hart. These values originate from the RISC-V Privileged Specification document, available from https://riscv.org/specifications/ - $ref: "/schemas/types.yaml#/definitions/string" + $ref: /schemas/types.yaml#/definitions/string enum: - riscv,sv32 - riscv,sv39 @@ -89,15 +92,18 @@ properties: Due to revisions of the ISA specification, some deviations have arisen over time. Notably, riscv,isa was defined prior to the creation of the - Zicsr and Zifencei extensions and thus "i" implies - "zicsr_zifencei". + Zicntr, Zicsr, Zifencei and Zihpm extensions and thus "i" + implies "zicntr_zicsr_zifencei_zihpm". While the isa strings in ISA specification are case insensitive, letters in the riscv,isa string must be all - lowercase to simplify parsing. - $ref: "/schemas/types.yaml#/definitions/string" + lowercase. + $ref: /schemas/types.yaml#/definitions/string pattern: ^rv(?:64|32)imaf?d?q?c?b?k?j?p?v?h?(?:[hsxz](?:[a-z])+)?(?:_[hsxz](?:[a-z])+)*$ + # RISC-V has multiple properties for cache op block sizes as the sizes + # differ between individual CBO extensions + cache-op-block-size: false # RISC-V requires 'timebase-frequency' in /cpus, so disallow it here timebase-frequency: false @@ -120,7 +126,7 @@ properties: - interrupt-controller cpu-idle-states: - $ref: '/schemas/types.yaml#/definitions/phandle-array' + $ref: /schemas/types.yaml#/definitions/phandle-array items: maxItems: 1 description: | @@ -137,7 +143,7 @@ required: - riscv,isa - interrupt-controller -additionalProperties: true +unevaluatedProperties: false examples: - | diff --git a/Documentation/riscv/hwprobe.rst b/Documentation/riscv/hwprobe.rst index 9f0dd62dcb5d..19165ebd82ba 100644 --- a/Documentation/riscv/hwprobe.rst +++ b/Documentation/riscv/hwprobe.rst @@ -64,6 +64,19 @@ The following keys are defined: * :c:macro:`RISCV_HWPROBE_IMA_C`: The C extension is supported, as defined by version 2.2 of the RISC-V ISA manual. + * :c:macro:`RISCV_HWPROBE_IMA_V`: The V extension is supported, as defined by + version 1.0 of the RISC-V Vector extension manual. + + * :c:macro:`RISCV_HWPROBE_EXT_ZBA`: The Zba address generation extension is + supported, as defined in version 1.0 of the Bit-Manipulation ISA + extensions. + + * :c:macro:`RISCV_HWPROBE_EXT_ZBB`: The Zbb extension is supported, as defined + in version 1.0 of the Bit-Manipulation ISA extensions. + + * :c:macro:`RISCV_HWPROBE_EXT_ZBS`: The Zbs extension is supported, as defined + in version 1.0 of the Bit-Manipulation ISA extensions. + * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance information about the selected set of processors. diff --git a/Documentation/riscv/index.rst b/Documentation/riscv/index.rst index 175a91db0200..95cf9c1e1da1 100644 --- a/Documentation/riscv/index.rst +++ b/Documentation/riscv/index.rst @@ -10,6 +10,7 @@ RISC-V architecture hwprobe patch-acceptance uabi + vector features diff --git a/Documentation/riscv/vector.rst b/Documentation/riscv/vector.rst new file mode 100644 index 000000000000..48f189d79e41 --- /dev/null +++ b/Documentation/riscv/vector.rst @@ -0,0 +1,132 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================================= +Vector Extension Support for RISC-V Linux +========================================= + +This document briefly outlines the interface provided to userspace by Linux in +order to support the use of the RISC-V Vector Extension. + +1. prctl() Interface +--------------------- + +Two new prctl() calls are added to allow programs to manage the enablement +status for the use of Vector in userspace. The intended usage guideline for +these interfaces is to give init systems a way to modify the availability of V +for processes running under its domain. Calling thess interfaces is not +recommended in libraries routines because libraries should not override policies +configured from the parant process. Also, users must noted that these interfaces +are not portable to non-Linux, nor non-RISC-V environments, so it is discourage +to use in a portable code. To get the availability of V in an ELF program, +please read :c:macro:`COMPAT_HWCAP_ISA_V` bit of :c:macro:`ELF_HWCAP` in the +auxiliary vector. + +* prctl(PR_RISCV_V_SET_CONTROL, unsigned long arg) + + Sets the Vector enablement status of the calling thread, where the control + argument consists of two 2-bit enablement statuses and a bit for inheritance + mode. Other threads of the calling process are unaffected. + + Enablement status is a tri-state value each occupying 2-bit of space in + the control argument: + + * :c:macro:`PR_RISCV_V_VSTATE_CTRL_DEFAULT`: Use the system-wide default + enablement status on execve(). The system-wide default setting can be + controlled via sysctl interface (see sysctl section below). + + * :c:macro:`PR_RISCV_V_VSTATE_CTRL_ON`: Allow Vector to be run for the + thread. + + * :c:macro:`PR_RISCV_V_VSTATE_CTRL_OFF`: Disallow Vector. Executing Vector + instructions under such condition will trap and casuse the termination of the thread. + + arg: The control argument is a 5-bit value consisting of 3 parts, and + accessed by 3 masks respectively. + + The 3 masks, PR_RISCV_V_VSTATE_CTRL_CUR_MASK, + PR_RISCV_V_VSTATE_CTRL_NEXT_MASK, and PR_RISCV_V_VSTATE_CTRL_INHERIT + represents bit[1:0], bit[3:2], and bit[4]. bit[1:0] accounts for the + enablement status of current thread, and the setting at bit[3:2] takes place + at next execve(). bit[4] defines the inheritance mode of the setting in + bit[3:2]. + + * :c:macro:`PR_RISCV_V_VSTATE_CTRL_CUR_MASK`: bit[1:0]: Account for the + Vector enablement status for the calling thread. The calling thread is + not able to turn off Vector once it has been enabled. The prctl() call + fails with EPERM if the value in this mask is PR_RISCV_V_VSTATE_CTRL_OFF + but the current enablement status is not off. Setting + PR_RISCV_V_VSTATE_CTRL_DEFAULT here takes no effect but to set back + the original enablement status. + + * :c:macro:`PR_RISCV_V_VSTATE_CTRL_NEXT_MASK`: bit[3:2]: Account for the + Vector enablement setting for the calling thread at the next execve() + system call. If PR_RISCV_V_VSTATE_CTRL_DEFAULT is used in this mask, + then the enablement status will be decided by the system-wide + enablement status when execve() happen. + + * :c:macro:`PR_RISCV_V_VSTATE_CTRL_INHERIT`: bit[4]: the inheritance + mode for the setting at PR_RISCV_V_VSTATE_CTRL_NEXT_MASK. If the bit + is set then the following execve() will not clear the setting in both + PR_RISCV_V_VSTATE_CTRL_NEXT_MASK and PR_RISCV_V_VSTATE_CTRL_INHERIT. + This setting persists across changes in the system-wide default value. + + Return value: + * 0 on success; + * EINVAL: Vector not supported, invalid enablement status for current or + next mask; + * EPERM: Turning off Vector in PR_RISCV_V_VSTATE_CTRL_CUR_MASK if Vector + was enabled for the calling thread. + + On success: + * A valid setting for PR_RISCV_V_VSTATE_CTRL_CUR_MASK takes place + immediately. The enablement status specified in + PR_RISCV_V_VSTATE_CTRL_NEXT_MASK happens at the next execve() call, or + all following execve() calls if PR_RISCV_V_VSTATE_CTRL_INHERIT bit is + set. + * Every successful call overwrites a previous setting for the calling + thread. + +* prctl(PR_RISCV_V_GET_CONTROL) + + Gets the same Vector enablement status for the calling thread. Setting for + next execve() call and the inheritance bit are all OR-ed together. + + Note that ELF programs are able to get the availability of V for itself by + reading :c:macro:`COMPAT_HWCAP_ISA_V` bit of :c:macro:`ELF_HWCAP` in the + auxiliary vector. + + Return value: + * a nonnegative value on success; + * EINVAL: Vector not supported. + +2. System runtime configuration (sysctl) +----------------------------------------- + +To mitigate the ABI impact of expansion of the signal stack, a +policy mechanism is provided to the administrators, distro maintainers, and +developers to control the default Vector enablement status for userspace +processes in form of sysctl knob: + +* /proc/sys/abi/riscv_v_default_allow + + Writing the text representation of 0 or 1 to this file sets the default + system enablement status for new starting userspace programs. Valid values + are: + + * 0: Do not allow Vector code to be executed as the default for new processes. + * 1: Allow Vector code to be executed as the default for new processes. + + Reading this file returns the current system default enablement status. + + At every execve() call, a new enablement status of the new process is set to + the system default, unless: + + * PR_RISCV_V_VSTATE_CTRL_INHERIT is set for the calling process, and the + setting in PR_RISCV_V_VSTATE_CTRL_NEXT_MASK is not + PR_RISCV_V_VSTATE_CTRL_DEFAULT. Or, + + * The setting in PR_RISCV_V_VSTATE_CTRL_NEXT_MASK is not + PR_RISCV_V_VSTATE_CTRL_DEFAULT. + + Modifying the system default enablement status does not affect the enablement + status of any existing process of thread that do not make an execve() call. diff --git a/MAINTAINERS b/MAINTAINERS index 96e4a0dd3a6f..1545c55b9173 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -406,6 +406,13 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: drivers/acpi/arm64 +ACPI FOR RISC-V (ACPI/riscv) +M: Sunil V L <sunilvl@ventanamicro.com> +L: linux-acpi@vger.kernel.org +L: linux-riscv@lists.infradead.org +S: Maintained +F: drivers/acpi/riscv/ + ACPI PCC(Platform Communication Channel) MAILBOX DRIVER M: Sudeep Holla <sudeep.holla@arm.com> L: linux-acpi@vger.kernel.org diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index a08917f681af..08f3a01fa1ea 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -12,6 +12,8 @@ config 32BIT config RISCV def_bool y + select ACPI_GENERIC_GSI if ACPI + select ACPI_REDUCED_HARDWARE_ONLY if ACPI select ARCH_DMA_DEFAULT_COHERENT select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 @@ -43,6 +45,7 @@ config RISCV select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU select ARCH_SUPPORTS_HUGETLBFS if MMU select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU + select ARCH_SUPPORTS_PER_VMA_LOCK if MMU select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU @@ -265,6 +268,12 @@ config RISCV_DMA_NONCOHERENT config AS_HAS_INSN def_bool $(as-instr,.insn r 51$(comma) 0$(comma) 0$(comma) t0$(comma) t0$(comma) zero) +config AS_HAS_OPTION_ARCH + # https://reviews.llvm.org/D123515 + def_bool y + depends on $(as-instr, .option arch$(comma) +m) + depends on !$(as-instr, .option arch$(comma) -i) + source "arch/riscv/Kconfig.socs" source "arch/riscv/Kconfig.errata" @@ -463,13 +472,44 @@ config RISCV_ISA_SVPBMT If you don't know what to do here, say Y. +config TOOLCHAIN_HAS_V + bool + default y + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64iv) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32iv) + depends on LLD_VERSION >= 140000 || LD_VERSION >= 23800 + depends on AS_HAS_OPTION_ARCH + +config RISCV_ISA_V + bool "VECTOR extension support" + depends on TOOLCHAIN_HAS_V + depends on FPU + select DYNAMIC_SIGFRAME + default y + help + Say N here if you want to disable all vector related procedure + in the kernel. + + If you don't know what to do here, say Y. + +config RISCV_ISA_V_DEFAULT_ENABLE + bool "Enable userspace Vector by default" + depends on RISCV_ISA_V + default y + help + Say Y here if you want to enable Vector in userspace by default. + Otherwise, userspace has to make explicit prctl() call to enable + Vector, or enable it via the sysctl interface. + + If you don't know what to do here, say Y. + config TOOLCHAIN_HAS_ZBB bool default y depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zbb) depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zbb) depends on LLD_VERSION >= 150000 || LD_VERSION >= 23900 - depends on AS_IS_GNU + depends on AS_HAS_OPTION_ARCH config RISCV_ISA_ZBB bool "Zbb extension support for bit manipulation instructions" @@ -554,6 +594,25 @@ config FPU If you don't know what to do here, say Y. +config IRQ_STACKS + bool "Independent irq & softirq stacks" if EXPERT + default y + select HAVE_IRQ_EXIT_ON_IRQ_STACK + select HAVE_SOFTIRQ_ON_OWN_STACK + help + Add independent irq & softirq stacks for percpu to prevent kernel stack + overflows. We may save some memory footprint by disabling IRQ_STACKS. + +config THREAD_SIZE_ORDER + int "Kernel stack size (in power-of-two numbers of page size)" if VMAP_STACK && EXPERT + range 0 4 + default 1 if 32BIT && !KASAN + default 3 if 64BIT && KASAN + default 2 + help + Specify the Pages of thread stack size (from 4KB to 64KB), which also + affects irq stack size, which is equal to thread stack size. + endmenu # "Platform type" menu "Kernel features" @@ -710,6 +769,7 @@ config EFI depends on OF && !XIP_KERNEL depends on MMU default y + select ARCH_SUPPORTS_ACPI if 64BIT select EFI_GENERIC_STUB select EFI_PARAMS_FROM_FDT select EFI_RUNTIME_WRAPPERS @@ -822,3 +882,5 @@ source "drivers/cpufreq/Kconfig" endmenu # "CPU Power Management" source "arch/riscv/kvm/Kconfig" + +source "drivers/acpi/Kconfig" diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 0fb256bf8270..6ec6d52a4180 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -60,6 +60,7 @@ riscv-march-$(CONFIG_ARCH_RV32I) := rv32ima riscv-march-$(CONFIG_ARCH_RV64I) := rv64ima riscv-march-$(CONFIG_FPU) := $(riscv-march-y)fd riscv-march-$(CONFIG_RISCV_ISA_C) := $(riscv-march-y)c +riscv-march-$(CONFIG_RISCV_ISA_V) := $(riscv-march-y)v ifdef CONFIG_TOOLCHAIN_NEEDS_OLD_ISA_SPEC KBUILD_CFLAGS += -Wa,-misa-spec=2.2 @@ -71,7 +72,10 @@ endif # Check if the toolchain supports Zihintpause extension riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE) := $(riscv-march-y)_zihintpause -KBUILD_CFLAGS += -march=$(subst fd,,$(riscv-march-y)) +# Remove F,D,V from isa string for all. Keep extensions between "fd" and "v" by +# matching non-v and non-multi-letter extensions out with the filter ([^v_]*) +KBUILD_CFLAGS += -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)fd([^v_]*)v?/\1\2/') + KBUILD_AFLAGS += -march=$(riscv-march-y) KBUILD_CFLAGS += -mno-save-restore diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 109e4b5b003c..0a0107460a5c 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -38,6 +38,7 @@ CONFIG_PM=y CONFIG_CPU_IDLE=y CONFIG_VIRTUALIZATION=y CONFIG_KVM=m +CONFIG_ACPI=y CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y diff --git a/arch/riscv/include/asm/acenv.h b/arch/riscv/include/asm/acenv.h new file mode 100644 index 000000000000..43ae2e32c779 --- /dev/null +++ b/arch/riscv/include/asm/acenv.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * RISC-V specific ACPICA environments and implementation + */ + +#ifndef _ASM_ACENV_H +#define _ASM_ACENV_H + +/* This header is required unconditionally by the ACPI core */ + +#endif /* _ASM_ACENV_H */ diff --git a/arch/riscv/include/asm/acpi.h b/arch/riscv/include/asm/acpi.h new file mode 100644 index 000000000000..f71ce21ff684 --- /dev/null +++ b/arch/riscv/include/asm/acpi.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2013-2014, Linaro Ltd. + * Author: Al Stone <al.stone@linaro.org> + * Author: Graeme Gregory <graeme.gregory@linaro.org> + * Author: Hanjun Guo <hanjun.guo@linaro.org> + * + * Copyright (C) 2021-2023, Ventana Micro Systems Inc. + * Author: Sunil V L <sunilvl@ventanamicro.com> + */ + +#ifndef _ASM_ACPI_H +#define _ASM_ACPI_H + +/* Basic configuration for ACPI */ +#ifdef CONFIG_ACPI + +typedef u64 phys_cpuid_t; +#define PHYS_CPUID_INVALID INVALID_HARTID + +/* ACPI table mapping after acpi_permanent_mmap is set */ +void *acpi_os_ioremap(acpi_physical_address phys, acpi_size size); +#define acpi_os_ioremap acpi_os_ioremap + +#define acpi_strict 1 /* No out-of-spec workarounds on RISC-V */ +extern int acpi_disabled; +extern int acpi_noirq; +extern int acpi_pci_disabled; + +static inline void disable_acpi(void) +{ + acpi_disabled = 1; + acpi_pci_disabled = 1; + acpi_noirq = 1; +} + +static inline void enable_acpi(void) +{ + acpi_disabled = 0; + acpi_pci_disabled = 0; + acpi_noirq = 0; +} + +/* + * The ACPI processor driver for ACPI core code needs this macro + * to find out whether this cpu was already mapped (mapping from CPU hardware + * ID to CPU logical ID) or not. + */ +#define cpu_physical_id(cpu) cpuid_to_hartid_map(cpu) + +/* + * Since MADT must provide at least one RINTC structure, the + * CPU will be always available in MADT on RISC-V. + */ +static inline bool acpi_has_cpu_in_madt(void) +{ + return true; +} + +static inline void arch_fix_phys_package_id(int num, u32 slot) { } + +void acpi_init_rintc_map(void); +struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu); +u32 get_acpi_id_for_cpu(int cpu); +int acpi_get_riscv_isa(struct acpi_table_header *table, + unsigned int cpu, const char **isa); + +static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; } +#else +static inline void acpi_init_rintc_map(void) { } +static inline struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu) +{ + return NULL; +} + +static inline int acpi_get_riscv_isa(struct acpi_table_header *table, + unsigned int cpu, const char **isa) +{ + return -EINVAL; +} + +#endif /* CONFIG_ACPI */ + +#endif /*_ASM_ACPI_H*/ diff --git a/arch/riscv/include/asm/asm-extable.h b/arch/riscv/include/asm/asm-extable.h index 14be0673f5b5..00a96e7a9664 100644 --- a/arch/riscv/include/asm/asm-extable.h +++ b/arch/riscv/include/asm/asm-extable.h @@ -7,6 +7,8 @@ #define EX_TYPE_BPF 2 #define EX_TYPE_UACCESS_ERR_ZERO 3 +#ifdef CONFIG_MMU + #ifdef __ASSEMBLY__ #define __ASM_EXTABLE_RAW(insn, fixup, type, data) \ @@ -62,4 +64,8 @@ #endif /* __ASSEMBLY__ */ +#else /* CONFIG_MMU */ + #define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err) +#endif /* CONFIG_MMU */ + #endif /* __ASM_ASM_EXTABLE_H */ diff --git a/arch/riscv/include/asm/cpu.h b/arch/riscv/include/asm/cpu.h new file mode 100644 index 000000000000..28d45a6678ce --- /dev/null +++ b/arch/riscv/include/asm/cpu.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ASM_CPU_H +#define _ASM_CPU_H + +/* This header is required unconditionally by the ACPI core */ + +#endif /* _ASM_CPU_H */ diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index 808d5403f2ac..23fed53b8815 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -6,6 +6,9 @@ #ifndef _ASM_CPUFEATURE_H #define _ASM_CPUFEATURE_H +#include <linux/bitmap.h> +#include <asm/hwcap.h> + /* * These are probed via a device_initcall(), via either the SBI or directly * from the corresponding CSRs. @@ -16,8 +19,15 @@ struct riscv_cpuinfo { unsigned long mimpid; }; +struct riscv_isainfo { + DECLARE_BITMAP(isa, RISCV_ISA_EXT_MAX); +}; + DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); DECLARE_PER_CPU(long, misaligned_access_speed); +/* Per-cpu ISA extensions. */ +extern struct riscv_isainfo hart_isa[NR_CPUS]; + #endif diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index b6acb7ed115f..b98b3b6c9da2 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -24,16 +24,24 @@ #define SR_FS_CLEAN _AC(0x00004000, UL) #define SR_FS_DIRTY _AC(0x00006000, UL) +#define SR_VS _AC(0x00000600, UL) /* Vector Status */ +#define SR_VS_OFF _AC(0x00000000, UL) +#define SR_VS_INITIAL _AC(0x00000200, UL) +#define SR_VS_CLEAN _AC(0x00000400, UL) +#define SR_VS_DIRTY _AC(0x00000600, UL) + #define SR_XS _AC(0x00018000, UL) /* Extension Status */ #define SR_XS_OFF _AC(0x00000000, UL) #define SR_XS_INITIAL _AC(0x00008000, UL) #define SR_XS_CLEAN _AC(0x00010000, UL) #define SR_XS_DIRTY _AC(0x00018000, UL) +#define SR_FS_VS (SR_FS | SR_VS) /* Vector and Floating-Point Unit */ + #ifndef CONFIG_64BIT -#define SR_SD _AC(0x80000000, UL) /* FS/XS dirty */ +#define SR_SD _AC(0x80000000, UL) /* FS/VS/XS dirty */ #else -#define SR_SD _AC(0x8000000000000000, UL) /* FS/XS dirty */ +#define SR_SD _AC(0x8000000000000000, UL) /* FS/VS/XS dirty */ #endif #ifdef CONFIG_64BIT @@ -375,6 +383,12 @@ #define CSR_MVIPH 0x319 #define CSR_MIPH 0x354 +#define CSR_VSTART 0x8 +#define CSR_VCSR 0xf +#define CSR_VL 0xc20 +#define CSR_VTYPE 0xc21 +#define CSR_VLENB 0xc22 + #ifdef CONFIG_RISCV_M_MODE # define CSR_STATUS CSR_MSTATUS # define CSR_IE CSR_MIE diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h index 30e7d2455960..c24280774caf 100644 --- a/arch/riscv/include/asm/elf.h +++ b/arch/riscv/include/asm/elf.h @@ -66,7 +66,7 @@ extern bool compat_elf_check_arch(Elf32_Ehdr *hdr); * via a bitmap that coorespends to each single-letter ISA extension. This is * essentially defunct, but will remain for compatibility with userspace. */ -#define ELF_HWCAP (elf_hwcap & ((1UL << RISCV_ISA_EXT_BASE) - 1)) +#define ELF_HWCAP riscv_get_elf_hwcap() extern unsigned long elf_hwcap; /* @@ -105,6 +105,15 @@ do { \ get_cache_size(3, CACHE_TYPE_UNIFIED)); \ NEW_AUX_ENT(AT_L3_CACHEGEOMETRY, \ get_cache_geometry(3, CACHE_TYPE_UNIFIED)); \ + /* \ + * Should always be nonzero unless there's a kernel bug. \ + * If we haven't determined a sensible value to give to \ + * userspace, omit the entry: \ + */ \ + if (likely(signal_minsigstksz)) \ + NEW_AUX_ENT(AT_MINSIGSTKSZ, signal_minsigstksz); \ + else \ + NEW_AUX_ENT(AT_IGNORE, 0); \ } while (0) #define ARCH_HAS_SETUP_ADDITIONAL_PAGES struct linux_binprm; diff --git a/arch/riscv/include/asm/extable.h b/arch/riscv/include/asm/extable.h index 512012d193dc..3eb5c1f7bf34 100644 --- a/arch/riscv/include/asm/extable.h +++ b/arch/riscv/include/asm/extable.h @@ -32,7 +32,11 @@ do { \ (b)->data = (tmp).data; \ } while (0) +#ifdef CONFIG_MMU bool fixup_exception(struct pt_regs *regs); +#else +static inline bool fixup_exception(struct pt_regs *regs) { return false; } +#endif #if defined(CONFIG_BPF_JIT) && defined(CONFIG_ARCH_RV64I) bool ex_handler_bpf(const struct exception_table_entry *ex, struct pt_regs *regs); diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index e0c40a4c63d5..f041bfa7f6a0 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -22,6 +22,7 @@ #define RISCV_ISA_EXT_m ('m' - 'a') #define RISCV_ISA_EXT_s ('s' - 'a') #define RISCV_ISA_EXT_u ('u' - 'a') +#define RISCV_ISA_EXT_v ('v' - 'a') /* * These macros represent the logical IDs of each multi-letter RISC-V ISA @@ -46,6 +47,12 @@ #define RISCV_ISA_EXT_ZICBOZ 34 #define RISCV_ISA_EXT_SMAIA 35 #define RISCV_ISA_EXT_SSAIA 36 +#define RISCV_ISA_EXT_ZBA 37 +#define RISCV_ISA_EXT_ZBS 38 +#define RISCV_ISA_EXT_ZICNTR 39 +#define RISCV_ISA_EXT_ZICSR 40 +#define RISCV_ISA_EXT_ZIFENCEI 41 +#define RISCV_ISA_EXT_ZIHPM 42 #define RISCV_ISA_EXT_MAX 64 #define RISCV_ISA_EXT_NAME_LEN_MAX 32 @@ -60,6 +67,8 @@ #include <linux/jump_label.h> +unsigned long riscv_get_elf_hwcap(void); + struct riscv_isa_ext_data { /* Name of the extension displayed to userspace via /proc/cpuinfo */ char uprop[RISCV_ISA_EXT_NAME_LEN_MAX]; diff --git a/arch/riscv/include/asm/insn.h b/arch/riscv/include/asm/insn.h index 8d5c84f2d5ef..4e1505cef8aa 100644 --- a/arch/riscv/include/asm/insn.h +++ b/arch/riscv/include/asm/insn.h @@ -137,6 +137,26 @@ #define RVG_OPCODE_JALR 0x67 #define RVG_OPCODE_JAL 0x6f #define RVG_OPCODE_SYSTEM 0x73 +#define RVG_SYSTEM_CSR_OFF 20 +#define RVG_SYSTEM_CSR_MASK GENMASK(12, 0) + +/* parts of opcode for RVF, RVD and RVQ */ +#define RVFDQ_FL_FS_WIDTH_OFF 12 +#define RVFDQ_FL_FS_WIDTH_MASK GENMASK(3, 0) +#define RVFDQ_FL_FS_WIDTH_W 2 +#define RVFDQ_FL_FS_WIDTH_D 3 +#define RVFDQ_LS_FS_WIDTH_Q 4 +#define RVFDQ_OPCODE_FL 0x07 +#define RVFDQ_OPCODE_FS 0x27 + +/* parts of opcode for RVV */ +#define RVV_OPCODE_VECTOR 0x57 +#define RVV_VL_VS_WIDTH_8 0 +#define RVV_VL_VS_WIDTH_16 5 +#define RVV_VL_VS_WIDTH_32 6 +#define RVV_VL_VS_WIDTH_64 7 +#define RVV_OPCODE_VL RVFDQ_OPCODE_FL +#define RVV_OPCODE_VS RVFDQ_OPCODE_FS /* parts of opcode for RVC*/ #define RVC_OPCODE_C0 0x0 @@ -304,6 +324,15 @@ static __always_inline bool riscv_insn_is_branch(u32 code) (RVC_X(x_, RVC_B_IMM_7_6_OPOFF, RVC_B_IMM_7_6_MASK) << RVC_B_IMM_7_6_OFF) | \ (RVC_IMM_SIGN(x_) << RVC_B_IMM_SIGN_OFF); }) +#define RVG_EXTRACT_SYSTEM_CSR(x) \ + ({typeof(x) x_ = (x); RV_X(x_, RVG_SYSTEM_CSR_OFF, RVG_SYSTEM_CSR_MASK); }) + +#define RVFDQ_EXTRACT_FL_FS_WIDTH(x) \ + ({typeof(x) x_ = (x); RV_X(x_, RVFDQ_FL_FS_WIDTH_OFF, \ + RVFDQ_FL_FS_WIDTH_MASK); }) + +#define RVV_EXRACT_VL_VS_WIDTH(x) RVFDQ_EXTRACT_FL_FS_WIDTH(x) + /* * Get the immediate from a J-type instruction. * diff --git a/arch/riscv/include/asm/irq_stack.h b/arch/riscv/include/asm/irq_stack.h new file mode 100644 index 000000000000..e4042d297580 --- /dev/null +++ b/arch/riscv/include/asm/irq_stack.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_RISCV_IRQ_STACK_H +#define _ASM_RISCV_IRQ_STACK_H + +#include <linux/bug.h> +#include <linux/gfp.h> +#include <linux/kconfig.h> +#include <linux/vmalloc.h> +#include <linux/pgtable.h> +#include <asm/thread_info.h> + +DECLARE_PER_CPU(ulong *, irq_stack_ptr); + +#ifdef CONFIG_VMAP_STACK +/* + * To ensure that VMAP'd stack overflow detection works correctly, all VMAP'd + * stacks need to have the same alignment. + */ +static inline unsigned long *arch_alloc_vmap_stack(size_t stack_size, int node) +{ + void *p; + + p = __vmalloc_node(stack_size, THREAD_ALIGN, THREADINFO_GFP, node, + __builtin_return_address(0)); + return kasan_reset_tag(p); +} +#endif /* CONFIG_VMAP_STACK */ + +#endif /* _ASM_RISCV_IRQ_STACK_H */ diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index ee0acccb1d3b..bd47a1dc2ff8 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -15,6 +15,7 @@ #include <linux/spinlock.h> #include <asm/hwcap.h> #include <asm/kvm_aia.h> +#include <asm/ptrace.h> #include <asm/kvm_vcpu_fp.h> #include <asm/kvm_vcpu_insn.h> #include <asm/kvm_vcpu_sbi.h> @@ -145,6 +146,7 @@ struct kvm_cpu_context { unsigned long sstatus; unsigned long hstatus; union __riscv_fp_state fp; + struct __riscv_v_ext_state vector; }; struct kvm_vcpu_csr { diff --git a/arch/riscv/include/asm/kvm_vcpu_vector.h b/arch/riscv/include/asm/kvm_vcpu_vector.h new file mode 100644 index 000000000000..ff994fdd6d0d --- /dev/null +++ b/arch/riscv/include/asm/kvm_vcpu_vector.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022 SiFive + * + * Authors: + * Vincent Chen <vincent.chen@sifive.com> + * Greentime Hu <greentime.hu@sifive.com> + */ + +#ifndef __KVM_VCPU_RISCV_VECTOR_H +#define __KVM_VCPU_RISCV_VECTOR_H + +#include <linux/types.h> + +#ifdef CONFIG_RISCV_ISA_V +#include <asm/vector.h> +#include <asm/kvm_host.h> + +static __always_inline void __kvm_riscv_vector_save(struct kvm_cpu_context *context) +{ + __riscv_v_vstate_save(&context->vector, context->vector.datap); +} + +static __always_inline void __kvm_riscv_vector_restore(struct kvm_cpu_context *context) +{ + __riscv_v_vstate_restore(&context->vector, context->vector.datap); +} + +void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_guest_vector_save(struct kvm_cpu_context *cntx, + unsigned long *isa); +void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx, + unsigned long *isa); +void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx); +void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx); +int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu, + struct kvm_cpu_context *cntx); +void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu); +#else + +struct kvm_cpu_context; + +static inline void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu) +{ +} + +static inline void kvm_riscv_vcpu_guest_vector_save(struct kvm_cpu_context *cntx, + unsigned long *isa) +{ +} + +static inline void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx, + unsigned long *isa) +{ +} + +static inline void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx) +{ +} + +static inline void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx) +{ +} + +static inline int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu, + struct kvm_cpu_context *cntx) +{ + return 0; +} + +static inline void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu) +{ +} +#endif + +int kvm_riscv_vcpu_get_reg_vector(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg, + unsigned long rtype); +int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg, + unsigned long rtype); +#endif diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 94a0590c6971..c950a8d9edef 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -7,6 +7,7 @@ #define _ASM_RISCV_PROCESSOR_H #include <linux/const.h> +#include <linux/cache.h> #include <vdso/processor.h> @@ -39,6 +40,8 @@ struct thread_struct { unsigned long s[12]; /* s[0]: frame pointer */ struct __riscv_d_ext_state fstate; unsigned long bad_cause; + unsigned long vstate_ctrl; + struct __riscv_v_ext_state vstate; }; /* Whitelist the fstate from the task_struct for hardened usercopy */ @@ -75,11 +78,22 @@ static inline void wait_for_interrupt(void) struct device_node; int riscv_of_processor_hartid(struct device_node *node, unsigned long *hartid); +int riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hartid); int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid); extern void riscv_fill_hwcap(void); extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); +extern unsigned long signal_minsigstksz __ro_after_init; + +#ifdef CONFIG_RISCV_ISA_V +/* Userspace interface for PR_RISCV_V_{SET,GET}_VS prctl()s: */ +#define RISCV_V_SET_CONTROL(arg) riscv_v_vstate_ctrl_set_current(arg) +#define RISCV_V_GET_CONTROL() riscv_v_vstate_ctrl_get_current() +extern long riscv_v_vstate_ctrl_set_current(unsigned long arg); +extern long riscv_v_vstate_ctrl_get_current(void); +#endif /* CONFIG_RISCV_ISA_V */ + #endif /* __ASSEMBLY__ */ #endif /* _ASM_RISCV_PROCESSOR_H */ diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h index 60f8ca01d36e..a727be723c56 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -8,6 +8,7 @@ #include <linux/jump_label.h> #include <linux/sched/task_stack.h> +#include <asm/vector.h> #include <asm/hwcap.h> #include <asm/processor.h> #include <asm/ptrace.h> @@ -46,7 +47,7 @@ static inline void fstate_restore(struct task_struct *task, } } -static inline void __switch_to_aux(struct task_struct *prev, +static inline void __switch_to_fpu(struct task_struct *prev, struct task_struct *next) { struct pt_regs *regs; @@ -66,7 +67,7 @@ static __always_inline bool has_fpu(void) static __always_inline bool has_fpu(void) { return false; } #define fstate_save(task, regs) do { } while (0) #define fstate_restore(task, regs) do { } while (0) -#define __switch_to_aux(__prev, __next) do { } while (0) +#define __switch_to_fpu(__prev, __next) do { } while (0) #endif extern struct task_struct *__switch_to(struct task_struct *, @@ -77,7 +78,9 @@ do { \ struct task_struct *__prev = (prev); \ struct task_struct *__next = (next); \ if (has_fpu()) \ - __switch_to_aux(__prev, __next); \ + __switch_to_fpu(__prev, __next); \ + if (has_vector()) \ + __switch_to_vector(__prev, __next); \ ((last) = __switch_to(__prev, __next)); \ } while (0) diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index e0d202134b44..1833beb00489 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -11,18 +11,8 @@ #include <asm/page.h> #include <linux/const.h> -#ifdef CONFIG_KASAN -#define KASAN_STACK_ORDER 1 -#else -#define KASAN_STACK_ORDER 0 -#endif - /* thread information allocation */ -#ifdef CONFIG_64BIT -#define THREAD_SIZE_ORDER (2 + KASAN_STACK_ORDER) -#else -#define THREAD_SIZE_ORDER (1 + KASAN_STACK_ORDER) -#endif +#define THREAD_SIZE_ORDER CONFIG_THREAD_SIZE_ORDER #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) /* @@ -40,6 +30,8 @@ #define OVERFLOW_STACK_SIZE SZ_4K #define SHADOW_OVERFLOW_STACK_SIZE (1024) +#define IRQ_STACK_SIZE THREAD_SIZE + #ifndef __ASSEMBLY__ extern long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE / sizeof(long)]; @@ -81,6 +73,9 @@ struct thread_info { .preempt_count = INIT_PREEMPT_COUNT, \ } +void arch_release_task_struct(struct task_struct *tsk); +int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); + #endif /* !__ASSEMBLY__ */ /* diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h new file mode 100644 index 000000000000..04c0b07bf6cd --- /dev/null +++ b/arch/riscv/include/asm/vector.h @@ -0,0 +1,184 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2020 SiFive + */ + +#ifndef __ASM_RISCV_VECTOR_H +#define __ASM_RISCV_VECTOR_H + +#include <linux/types.h> +#include <uapi/asm-generic/errno.h> + +#ifdef CONFIG_RISCV_ISA_V + +#include <linux/stringify.h> +#include <linux/sched.h> +#include <linux/sched/task_stack.h> +#include <asm/ptrace.h> +#include <asm/hwcap.h> +#include <asm/csr.h> +#include <asm/asm.h> + +extern unsigned long riscv_v_vsize; +int riscv_v_setup_vsize(void); +bool riscv_v_first_use_handler(struct pt_regs *regs); + +static __always_inline bool has_vector(void) +{ + return riscv_has_extension_unlikely(RISCV_ISA_EXT_v); +} + +static inline void __riscv_v_vstate_clean(struct pt_regs *regs) +{ + regs->status = (regs->status & ~SR_VS) | SR_VS_CLEAN; +} + +static inline void riscv_v_vstate_off(struct pt_regs *regs) +{ + regs->status = (regs->status & ~SR_VS) | SR_VS_OFF; +} + +static inline void riscv_v_vstate_on(struct pt_regs *regs) +{ + regs->status = (regs->status & ~SR_VS) | SR_VS_INITIAL; +} + +static inline bool riscv_v_vstate_query(struct pt_regs *regs) +{ + return (regs->status & SR_VS) != 0; +} + +static __always_inline void riscv_v_enable(void) +{ + csr_set(CSR_SSTATUS, SR_VS); +} + +static __always_inline void riscv_v_disable(void) +{ + csr_clear(CSR_SSTATUS, SR_VS); +} + +static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest) +{ + asm volatile ( + "csrr %0, " __stringify(CSR_VSTART) "\n\t" + "csrr %1, " __stringify(CSR_VTYPE) "\n\t" + "csrr %2, " __stringify(CSR_VL) "\n\t" + "csrr %3, " __stringify(CSR_VCSR) "\n\t" + : "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl), + "=r" (dest->vcsr) : :); +} + +static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src) +{ + asm volatile ( + ".option push\n\t" + ".option arch, +v\n\t" + "vsetvl x0, %2, %1\n\t" + ".option pop\n\t" + "csrw " __stringify(CSR_VSTART) ", %0\n\t" + "csrw " __stringify(CSR_VCSR) ", %3\n\t" + : : "r" (src->vstart), "r" (src->vtype), "r" (src->vl), + "r" (src->vcsr) :); +} + +static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to, + void *datap) +{ + unsigned long vl; + + riscv_v_enable(); + __vstate_csr_save(save_to); + asm volatile ( + ".option push\n\t" + ".option arch, +v\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + "vse8.v v0, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v8, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v16, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v24, (%1)\n\t" + ".option pop\n\t" + : "=&r" (vl) : "r" (datap) : "memory"); + riscv_v_disable(); +} + +static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_from, + void *datap) +{ + unsigned long vl; + + riscv_v_enable(); + asm volatile ( + ".option push\n\t" + ".option arch, +v\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + "vle8.v v0, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v8, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v16, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v24, (%1)\n\t" + ".option pop\n\t" + : "=&r" (vl) : "r" (datap) : "memory"); + __vstate_csr_restore(restore_from); + riscv_v_disable(); +} + +static inline void riscv_v_vstate_save(struct task_struct *task, + struct pt_regs *regs) +{ + if ((regs->status & SR_VS) == SR_VS_DIRTY) { + struct __riscv_v_ext_state *vstate = &task->thread.vstate; + + __riscv_v_vstate_save(vstate, vstate->datap); + __riscv_v_vstate_clean(regs); + } +} + +static inline void riscv_v_vstate_restore(struct task_struct *task, + struct pt_regs *regs) +{ + if ((regs->status & SR_VS) != SR_VS_OFF) { + struct __riscv_v_ext_state *vstate = &task->thread.vstate; + + __riscv_v_vstate_restore(vstate, vstate->datap); + __riscv_v_vstate_clean(regs); + } +} + +static inline void __switch_to_vector(struct task_struct *prev, + struct task_struct *next) +{ + struct pt_regs *regs; + + regs = task_pt_regs(prev); + riscv_v_vstate_save(prev, regs); + riscv_v_vstate_restore(next, task_pt_regs(next)); +} + +void riscv_v_vstate_ctrl_init(struct task_struct *tsk); +bool riscv_v_vstate_ctrl_user_allowed(void); + +#else /* ! CONFIG_RISCV_ISA_V */ + +struct pt_regs; + +static inline int riscv_v_setup_vsize(void) { return -EOPNOTSUPP; } +static __always_inline bool has_vector(void) { return false; } +static inline bool riscv_v_first_use_handler(struct pt_regs *regs) { return false; } +static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; } +static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; } +#define riscv_v_vsize (0) +#define riscv_v_vstate_save(task, regs) do {} while (0) +#define riscv_v_vstate_restore(task, regs) do {} while (0) +#define __switch_to_vector(__prev, __next) do {} while (0) +#define riscv_v_vstate_off(regs) do {} while (0) +#define riscv_v_vstate_on(regs) do {} while (0) + +#endif /* CONFIG_RISCV_ISA_V */ + +#endif /* ! __ASM_RISCV_VECTOR_H */ diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h index fb187a33ce58..10aaa83db89e 100644 --- a/arch/riscv/include/uapi/asm/auxvec.h +++ b/arch/riscv/include/uapi/asm/auxvec.h @@ -35,5 +35,6 @@ /* entries in ARCH_DLINFO */ #define AT_VECTOR_SIZE_ARCH 9 +#define AT_MINSIGSTKSZ 51 #endif /* _UAPI_ASM_RISCV_AUXVEC_H */ diff --git a/arch/riscv/include/uapi/asm/hwcap.h b/arch/riscv/include/uapi/asm/hwcap.h index 46dc3f5ee99f..c52bb7bbbabe 100644 --- a/arch/riscv/include/uapi/asm/hwcap.h +++ b/arch/riscv/include/uapi/asm/hwcap.h @@ -21,5 +21,6 @@ #define COMPAT_HWCAP_ISA_F (1 << ('F' - 'A')) #define COMPAT_HWCAP_ISA_D (1 << ('D' - 'A')) #define COMPAT_HWCAP_ISA_C (1 << ('C' - 'A')) +#define COMPAT_HWCAP_ISA_V (1 << ('V' - 'A')) #endif /* _UAPI_ASM_RISCV_HWCAP_H */ diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h index 8d745a4ad8a2..006bfb48343d 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -25,6 +25,10 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_KEY_IMA_EXT_0 4 #define RISCV_HWPROBE_IMA_FD (1 << 0) #define RISCV_HWPROBE_IMA_C (1 << 1) +#define RISCV_HWPROBE_IMA_V (1 << 2) +#define RISCV_HWPROBE_EXT_ZBA (1 << 3) +#define RISCV_HWPROBE_EXT_ZBB (1 << 4) +#define RISCV_HWPROBE_EXT_ZBS (1 << 5) #define RISCV_HWPROBE_KEY_CPUPERF_0 5 #define RISCV_HWPROBE_MISALIGNED_UNKNOWN (0 << 0) #define RISCV_HWPROBE_MISALIGNED_EMULATED (1 << 0) diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h index f92790c9481a..855c047e86d4 100644 --- a/arch/riscv/include/uapi/asm/kvm.h +++ b/arch/riscv/include/uapi/asm/kvm.h @@ -121,6 +121,7 @@ enum KVM_RISCV_ISA_EXT_ID { KVM_RISCV_ISA_EXT_ZICBOZ, KVM_RISCV_ISA_EXT_ZBB, KVM_RISCV_ISA_EXT_SSAIA, + KVM_RISCV_ISA_EXT_V, KVM_RISCV_ISA_EXT_MAX, }; @@ -203,6 +204,13 @@ enum KVM_RISCV_SBI_EXT_ID { #define KVM_REG_RISCV_SBI_MULTI_REG_LAST \ KVM_REG_RISCV_SBI_MULTI_REG(KVM_RISCV_SBI_EXT_MAX - 1) +/* V extension registers are mapped as type 9 */ +#define KVM_REG_RISCV_VECTOR (0x09 << KVM_REG_RISCV_TYPE_SHIFT) +#define KVM_REG_RISCV_VECTOR_CSR_REG(name) \ + (offsetof(struct __riscv_v_ext_state, name) / sizeof(unsigned long)) +#define KVM_REG_RISCV_VECTOR_REG(n) \ + ((n) + sizeof(struct __riscv_v_ext_state) / sizeof(unsigned long)) + #endif #endif /* __LINUX_KVM_RISCV_H */ diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h index 882547f6bd5c..e17c550986a6 100644 --- a/arch/riscv/include/uapi/asm/ptrace.h +++ b/arch/riscv/include/uapi/asm/ptrace.h @@ -71,12 +71,51 @@ struct __riscv_q_ext_state { __u32 reserved[3]; }; +struct __riscv_ctx_hdr { + __u32 magic; + __u32 size; +}; + +struct __riscv_extra_ext_header { + __u32 __padding[129] __attribute__((aligned(16))); + /* + * Reserved for expansion of sigcontext structure. Currently zeroed + * upon signal, and must be zero upon sigreturn. + */ + __u32 reserved; + struct __riscv_ctx_hdr hdr; +}; + union __riscv_fp_state { struct __riscv_f_ext_state f; struct __riscv_d_ext_state d; struct __riscv_q_ext_state q; }; +struct __riscv_v_ext_state { + unsigned long vstart; + unsigned long vl; + unsigned long vtype; + unsigned long vcsr; + void *datap; + /* + * In signal handler, datap will be set a correct user stack offset + * and vector registers will be copied to the address of datap + * pointer. + * + * In ptrace syscall, datap will be set to zero and the vector + * registers will be copied to the address right after this + * structure. + */ +}; + +/* + * According to spec: The number of bits in a single vector register, + * VLEN >= ELEN, which must be a power of 2, and must be no greater than + * 2^16 = 65536bits = 8192bytes + */ +#define RISCV_MAX_VLENB (8192) + #endif /* __ASSEMBLY__ */ #endif /* _UAPI_ASM_RISCV_PTRACE_H */ diff --git a/arch/riscv/include/uapi/asm/sigcontext.h b/arch/riscv/include/uapi/asm/sigcontext.h index 84f2dfcfdbce..8b8a8541673a 100644 --- a/arch/riscv/include/uapi/asm/sigcontext.h +++ b/arch/riscv/include/uapi/asm/sigcontext.h @@ -8,6 +8,17 @@ #include <asm/ptrace.h> +/* The Magic number for signal context frame header. */ +#define RISCV_V_MAGIC 0x53465457 +#define END_MAGIC 0x0 + +/* The size of END signal context header. */ +#define END_HDR_SIZE 0x0 + +struct __sc_riscv_v_state { + struct __riscv_v_ext_state v_state; +} __attribute__((aligned(16))); + /* * Signal context structure * @@ -16,7 +27,10 @@ */ struct sigcontext { struct user_regs_struct sc_regs; - union __riscv_fp_state sc_fpregs; + union { + union __riscv_fp_state sc_fpregs; + struct __riscv_extra_ext_header sc_extdesc; + }; }; #endif /* _UAPI_ASM_RISCV_SIGCONTEXT_H */ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 153864e4f399..506cc4a9a45a 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -60,6 +60,7 @@ obj-$(CONFIG_MMU) += vdso.o vdso/ obj-$(CONFIG_RISCV_M_MODE) += traps_misaligned.o obj-$(CONFIG_FPU) += fpu.o +obj-$(CONFIG_RISCV_ISA_V) += vector.o obj-$(CONFIG_SMP) += smpboot.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SMP) += cpu_ops.o @@ -96,3 +97,4 @@ obj-$(CONFIG_COMPAT) += compat_signal.o obj-$(CONFIG_COMPAT) += compat_vdso/ obj-$(CONFIG_64BIT) += pi/ +obj-$(CONFIG_ACPI) += acpi.o diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c new file mode 100644 index 000000000000..5ee03ebab80e --- /dev/null +++ b/arch/riscv/kernel/acpi.c @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * RISC-V Specific Low-Level ACPI Boot Support + * + * Copyright (C) 2013-2014, Linaro Ltd. + * Author: Al Stone <al.stone@linaro.org> + * Author: Graeme Gregory <graeme.gregory@linaro.org> + * Author: Hanjun Guo <hanjun.guo@linaro.org> + * Author: Tomasz Nowicki <tomasz.nowicki@linaro.org> + * Author: Naresh Bhat <naresh.bhat@linaro.org> + * + * Copyright (C) 2021-2023, Ventana Micro Systems Inc. + * Author: Sunil V L <sunilvl@ventanamicro.com> + */ + +#include <linux/acpi.h> +#include <linux/io.h> +#include <linux/pci.h> +#include <linux/efi.h> + +int acpi_noirq = 1; /* skip ACPI IRQ initialization */ +int acpi_disabled = 1; +EXPORT_SYMBOL(acpi_disabled); + +int acpi_pci_disabled = 1; /* skip ACPI PCI scan and IRQ initialization */ +EXPORT_SYMBOL(acpi_pci_disabled); + +static bool param_acpi_off __initdata; +static bool param_acpi_on __initdata; +static bool param_acpi_force __initdata; + +static struct acpi_madt_rintc cpu_madt_rintc[NR_CPUS]; + +static int __init parse_acpi(char *arg) +{ + if (!arg) + return -EINVAL; + + /* "acpi=off" disables both ACPI table parsing and interpreter */ + if (strcmp(arg, "off") == 0) + param_acpi_off = true; + else if (strcmp(arg, "on") == 0) /* prefer ACPI over DT */ + param_acpi_on = true; + else if (strcmp(arg, "force") == 0) /* force ACPI to be enabled */ + param_acpi_force = true; + else + return -EINVAL; /* Core will print when we return error */ + + return 0; +} +early_param("acpi", parse_acpi); + +/* + * acpi_fadt_sanity_check() - Check FADT presence and carry out sanity + * checks on it + * + * Return 0 on success, <0 on failure + */ +static int __init acpi_fadt_sanity_check(void) +{ + struct acpi_table_header *table; + struct acpi_table_fadt *fadt; + acpi_status status; + int ret = 0; + + /* + * FADT is required on riscv; retrieve it to check its presence + * and carry out revision and ACPI HW reduced compliancy tests + */ + status = acpi_get_table(ACPI_SIG_FADT, 0, &table); + if (ACPI_FAILURE(status)) { + const char *msg = acpi_format_exception(status); + + pr_err("Failed to get FADT table, %s\n", msg); + return -ENODEV; + } + + fadt = (struct acpi_table_fadt *)table; + + /* + * The revision in the table header is the FADT's Major revision. The + * FADT also has a minor revision, which is stored in the FADT itself. + * + * TODO: Currently, we check for 6.5 as the minimum version to check + * for HW_REDUCED flag. However, once RISC-V updates are released in + * the ACPI spec, we need to update this check for exact minor revision + */ + if (table->revision < 6 || (table->revision == 6 && fadt->minor_revision < 5)) + pr_err(FW_BUG "Unsupported FADT revision %d.%d, should be 6.5+\n", + table->revision, fadt->minor_revision); + + if (!(fadt->flags & ACPI_FADT_HW_REDUCED)) { + pr_err("FADT not ACPI hardware reduced compliant\n"); + ret = -EINVAL; + } + + /* + * acpi_get_table() creates FADT table mapping that + * should be released after parsing and before resuming boot + */ + acpi_put_table(table); + return ret; +} + +/* + * acpi_boot_table_init() called from setup_arch(), always. + * 1. find RSDP and get its address, and then find XSDT + * 2. extract all tables and checksums them all + * 3. check ACPI FADT HW reduced flag + * + * We can parse ACPI boot-time tables such as MADT after + * this function is called. + * + * On return ACPI is enabled if either: + * + * - ACPI tables are initialized and sanity checks passed + * - acpi=force was passed in the command line and ACPI was not disabled + * explicitly through acpi=off command line parameter + * + * ACPI is disabled on function return otherwise + */ +void __init acpi_boot_table_init(void) +{ + /* + * Enable ACPI instead of device tree unless + * - ACPI has been disabled explicitly (acpi=off), or + * - firmware has not populated ACPI ptr in EFI system table + * and ACPI has not been [force] enabled (acpi=on|force) + */ + if (param_acpi_off || + (!param_acpi_on && !param_acpi_force && + efi.acpi20 == EFI_INVALID_TABLE_ADDR)) + return; + + /* + * ACPI is disabled at this point. Enable it in order to parse + * the ACPI tables and carry out sanity checks + */ + enable_acpi(); + + /* + * If ACPI tables are initialized and FADT sanity checks passed, + * leave ACPI enabled and carry on booting; otherwise disable ACPI + * on initialization error. + * If acpi=force was passed on the command line it forces ACPI + * to be enabled even if its initialization failed. + */ + if (acpi_table_init() || acpi_fadt_sanity_check()) { + pr_err("Failed to init ACPI tables\n"); + if (!param_acpi_force) + disable_acpi(); + } +} + +static int acpi_parse_madt_rintc(union acpi_subtable_headers *header, const unsigned long end) +{ + struct acpi_madt_rintc *rintc = (struct acpi_madt_rintc *)header; + int cpuid; + + if (!(rintc->flags & ACPI_MADT_ENABLED)) + return 0; + + cpuid = riscv_hartid_to_cpuid(rintc->hart_id); + /* + * When CONFIG_SMP is disabled, mapping won't be created for + * all cpus. + * CPUs more than num_possible_cpus, will be ignored. + */ + if (cpuid >= 0 && cpuid < num_possible_cpus()) + cpu_madt_rintc[cpuid] = *rintc; + + return 0; +} + +/* + * Instead of parsing (and freeing) the ACPI table, cache + * the RINTC structures since they are frequently used + * like in cpuinfo. + */ +void __init acpi_init_rintc_map(void) +{ + if (acpi_table_parse_madt(ACPI_MADT_TYPE_RINTC, acpi_parse_madt_rintc, 0) <= 0) { + pr_err("No valid RINTC entries exist\n"); + BUG(); + } +} + +struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu) +{ + return &cpu_madt_rintc[cpu]; +} + +u32 get_acpi_id_for_cpu(int cpu) +{ + return acpi_cpu_get_madt_rintc(cpu)->uid; +} + +/* + * __acpi_map_table() will be called before paging_init(), so early_ioremap() + * or early_memremap() should be called here to for ACPI table mapping. + */ +void __init __iomem *__acpi_map_table(unsigned long phys, unsigned long size) +{ + if (!size) + return NULL; + + return early_ioremap(phys, size); +} + +void __init __acpi_unmap_table(void __iomem *map, unsigned long size) +{ + if (!map || !size) + return; + + early_iounmap(map, size); +} + +void *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) +{ + return memremap(phys, size, MEMREMAP_WB); +} + +#ifdef CONFIG_PCI + +/* + * These interfaces are defined just to enable building ACPI core. + * TODO: Update it with actual implementation when external interrupt + * controller support is added in RISC-V ACPI. + */ +int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn, + int reg, int len, u32 *val) +{ + return PCIBIOS_DEVICE_NOT_FOUND; +} + +int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn, + int reg, int len, u32 val) +{ + return PCIBIOS_DEVICE_NOT_FOUND; +} + +int acpi_pci_bus_find_domain_nr(struct pci_bus *bus) +{ + return -1; +} + +struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) +{ + return NULL; +} +#endif /* CONFIG_PCI */ diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index c96aa56cf1c7..a2fc952318e9 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -3,10 +3,13 @@ * Copyright (C) 2012 Regents of the University of California */ +#include <linux/acpi.h> #include <linux/cpu.h> +#include <linux/ctype.h> #include <linux/init.h> #include <linux/seq_file.h> #include <linux/of.h> +#include <asm/acpi.h> #include <asm/cpufeature.h> #include <asm/csr.h> #include <asm/hwcap.h> @@ -20,6 +23,26 @@ */ int riscv_of_processor_hartid(struct device_node *node, unsigned long *hart) { + int cpu; + + *hart = (unsigned long)of_get_cpu_hwid(node, 0); + if (*hart == ~0UL) { + pr_warn("Found CPU without hart ID\n"); + return -ENODEV; + } + + cpu = riscv_hartid_to_cpuid(*hart); + if (cpu < 0) + return cpu; + + if (!cpu_possible(cpu)) + return -ENODEV; + + return 0; +} + +int riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hart) +{ const char *isa; if (!of_device_is_compatible(node, "riscv")) { @@ -27,7 +50,7 @@ int riscv_of_processor_hartid(struct device_node *node, unsigned long *hart) return -ENODEV; } - *hart = (unsigned long) of_get_cpu_hwid(node, 0); + *hart = (unsigned long)of_get_cpu_hwid(node, 0); if (*hart == ~0UL) { pr_warn("Found CPU without hart ID\n"); return -ENODEV; @@ -42,10 +65,12 @@ int riscv_of_processor_hartid(struct device_node *node, unsigned long *hart) pr_warn("CPU with hartid=%lu has no \"riscv,isa\" property\n", *hart); return -ENODEV; } - if (isa[0] != 'r' || isa[1] != 'v') { - pr_warn("CPU with hartid=%lu has an invalid ISA of \"%s\"\n", *hart, isa); + + if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32ima", 7)) + return -ENODEV; + + if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64ima", 7)) return -ENODEV; - } return 0; } @@ -183,8 +208,14 @@ arch_initcall(riscv_cpuinfo_init); static struct riscv_isa_ext_data isa_ext_arr[] = { __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM), __RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ), + __RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR), + __RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR), + __RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI), __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE), + __RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM), + __RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA), __RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB), + __RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS), __RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA), __RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA), __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF), @@ -283,23 +314,35 @@ static void c_stop(struct seq_file *m, void *v) static int c_show(struct seq_file *m, void *v) { unsigned long cpu_id = (unsigned long)v - 1; - struct device_node *node = of_get_cpu_node(cpu_id, NULL); struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); + struct device_node *node; const char *compat, *isa; seq_printf(m, "processor\t: %lu\n", cpu_id); seq_printf(m, "hart\t\t: %lu\n", cpuid_to_hartid_map(cpu_id)); - if (!of_property_read_string(node, "riscv,isa", &isa)) - print_isa(m, isa); - print_mmu(m); - if (!of_property_read_string(node, "compatible", &compat) - && strcmp(compat, "riscv")) - seq_printf(m, "uarch\t\t: %s\n", compat); + + if (acpi_disabled) { + node = of_get_cpu_node(cpu_id, NULL); + if (!of_property_read_string(node, "riscv,isa", &isa)) + print_isa(m, isa); + + print_mmu(m); + if (!of_property_read_string(node, "compatible", &compat) && + strcmp(compat, "riscv")) + seq_printf(m, "uarch\t\t: %s\n", compat); + + of_node_put(node); + } else { + if (!acpi_get_riscv_isa(NULL, cpu_id, &isa)) + print_isa(m, isa); + + print_mmu(m); + } + seq_printf(m, "mvendorid\t: 0x%lx\n", ci->mvendorid); seq_printf(m, "marchid\t\t: 0x%lx\n", ci->marchid); seq_printf(m, "mimpid\t\t: 0x%lx\n", ci->mimpid); seq_puts(m, "\n"); - of_node_put(node); return 0; } diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index b1d6b7e4b829..bdcf460ea53d 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -6,18 +6,22 @@ * Copyright (C) 2017 SiFive */ +#include <linux/acpi.h> #include <linux/bitmap.h> #include <linux/ctype.h> #include <linux/log2.h> #include <linux/memory.h> #include <linux/module.h> #include <linux/of.h> +#include <linux/of_device.h> +#include <asm/acpi.h> #include <asm/alternative.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/hwcap.h> #include <asm/patch.h> #include <asm/processor.h> +#include <asm/vector.h> #define NUM_ALPHA_EXTS ('z' - 'a' + 1) @@ -26,6 +30,9 @@ unsigned long elf_hwcap __read_mostly; /* Host ISA bitmap */ static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly; +/* Per-cpu ISA extensions. */ +struct riscv_isainfo hart_isa[NR_CPUS]; + /* Performance information */ DEFINE_PER_CPU(long, misaligned_access_speed); @@ -71,10 +78,10 @@ static bool riscv_isa_extension_check(int id) switch (id) { case RISCV_ISA_EXT_ZICBOM: if (!riscv_cbom_block_size) { - pr_err("Zicbom detected in ISA string, but no cbom-block-size found\n"); + pr_err("Zicbom detected in ISA string, disabling as no cbom-block-size found\n"); return false; } else if (!is_power_of_2(riscv_cbom_block_size)) { - pr_err("cbom-block-size present, but is not a power-of-2\n"); + pr_err("Zicbom disabled as cbom-block-size present, but is not a power-of-2\n"); return false; } return true; @@ -99,7 +106,9 @@ void __init riscv_fill_hwcap(void) char print_str[NUM_ALPHA_EXTS + 1]; int i, j, rc; unsigned long isa2hwcap[26] = {0}; - unsigned long hartid; + struct acpi_table_header *rhct; + acpi_status status; + unsigned int cpu; isa2hwcap['i' - 'a'] = COMPAT_HWCAP_ISA_I; isa2hwcap['m' - 'a'] = COMPAT_HWCAP_ISA_M; @@ -107,45 +116,59 @@ void __init riscv_fill_hwcap(void) isa2hwcap['f' - 'a'] = COMPAT_HWCAP_ISA_F; isa2hwcap['d' - 'a'] = COMPAT_HWCAP_ISA_D; isa2hwcap['c' - 'a'] = COMPAT_HWCAP_ISA_C; + isa2hwcap['v' - 'a'] = COMPAT_HWCAP_ISA_V; elf_hwcap = 0; bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX); - for_each_of_cpu_node(node) { + if (!acpi_disabled) { + status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct); + if (ACPI_FAILURE(status)) + return; + } + + for_each_possible_cpu(cpu) { + struct riscv_isainfo *isainfo = &hart_isa[cpu]; unsigned long this_hwcap = 0; - DECLARE_BITMAP(this_isa, RISCV_ISA_EXT_MAX); - const char *temp; - rc = riscv_of_processor_hartid(node, &hartid); - if (rc < 0) - continue; + if (acpi_disabled) { + node = of_cpu_device_node_get(cpu); + if (!node) { + pr_warn("Unable to find cpu node\n"); + continue; + } - if (of_property_read_string(node, "riscv,isa", &isa)) { - pr_warn("Unable to find \"riscv,isa\" devicetree entry\n"); - continue; + rc = of_property_read_string(node, "riscv,isa", &isa); + of_node_put(node); + if (rc) { + pr_warn("Unable to find \"riscv,isa\" devicetree entry\n"); + continue; + } + } else { + rc = acpi_get_riscv_isa(rhct, cpu, &isa); + if (rc < 0) { + pr_warn("Unable to get ISA for the hart - %d\n", cpu); + continue; + } } - temp = isa; -#if IS_ENABLED(CONFIG_32BIT) - if (!strncmp(isa, "rv32", 4)) - isa += 4; -#elif IS_ENABLED(CONFIG_64BIT) - if (!strncmp(isa, "rv64", 4)) - isa += 4; -#endif - /* The riscv,isa DT property must start with rv64 or rv32 */ - if (temp == isa) - continue; - bitmap_zero(this_isa, RISCV_ISA_EXT_MAX); - for (; *isa; ++isa) { + /* + * For all possible cpus, we have already validated in + * the boot process that they at least contain "rv" and + * whichever of "32"/"64" this kernel supports, and so this + * section can be skipped. + */ + isa += 4; + + while (*isa) { const char *ext = isa++; const char *ext_end = isa; bool ext_long = false, ext_err = false; switch (*ext) { case 's': - /** + /* * Workaround for invalid single-letter 's' & 'u'(QEMU). * No need to set the bit in riscv_isa as 's' & 'u' are * not valid ISA extensions. It works until multi-letter @@ -157,75 +180,123 @@ void __init riscv_fill_hwcap(void) break; } fallthrough; + case 'S': case 'x': + case 'X': case 'z': + case 'Z': + /* + * Before attempting to parse the extension itself, we find its end. + * As multi-letter extensions must be split from other multi-letter + * extensions with an "_", the end of a multi-letter extension will + * either be the null character or the "_" at the start of the next + * multi-letter extension. + * + * Next, as the extensions version is currently ignored, we + * eliminate that portion. This is done by parsing backwards from + * the end of the extension, removing any numbers. This may be a + * major or minor number however, so the process is repeated if a + * minor number was found. + * + * ext_end is intended to represent the first character *after* the + * name portion of an extension, but will be decremented to the last + * character itself while eliminating the extensions version number. + * A simple re-increment solves this problem. + */ ext_long = true; - /* Multi-letter extension must be delimited */ for (; *isa && *isa != '_'; ++isa) - if (unlikely(!islower(*isa) - && !isdigit(*isa))) + if (unlikely(!isalnum(*isa))) ext_err = true; - /* Parse backwards */ + ext_end = isa; if (unlikely(ext_err)) break; + if (!isdigit(ext_end[-1])) break; - /* Skip the minor version */ + while (isdigit(*--ext_end)) ; - if (ext_end[0] != 'p' - || !isdigit(ext_end[-1])) { - /* Advance it to offset the pre-decrement */ + + if (tolower(ext_end[0]) != 'p' || !isdigit(ext_end[-1])) { ++ext_end; break; } - /* Skip the major version */ + while (isdigit(*--ext_end)) ; + ++ext_end; break; default: - if (unlikely(!islower(*ext))) { + /* + * Things are a little easier for single-letter extensions, as they + * are parsed forwards. + * + * After checking that our starting position is valid, we need to + * ensure that, when isa was incremented at the start of the loop, + * that it arrived at the start of the next extension. + * + * If we are already on a non-digit, there is nothing to do. Either + * we have a multi-letter extension's _, or the start of an + * extension. + * + * Otherwise we have found the current extension's major version + * number. Parse past it, and a subsequent p/minor version number + * if present. The `p` extension must not appear immediately after + * a number, so there is no fear of missing it. + * + */ + if (unlikely(!isalpha(*ext))) { ext_err = true; break; } - /* Find next extension */ + if (!isdigit(*isa)) break; - /* Skip the minor version */ + while (isdigit(*++isa)) ; - if (*isa != 'p') + + if (tolower(*isa) != 'p') break; + if (!isdigit(*++isa)) { --isa; break; } - /* Skip the major version */ + while (isdigit(*++isa)) ; + break; } - if (*isa != '_') - --isa; -#define SET_ISA_EXT_MAP(name, bit) \ - do { \ - if ((ext_end - ext == sizeof(name) - 1) && \ - !memcmp(ext, name, sizeof(name) - 1) && \ - riscv_isa_extension_check(bit)) \ - set_bit(bit, this_isa); \ - } while (false) \ + /* + * The parser expects that at the start of an iteration isa points to the + * first character of the next extension. As we stop parsing an extension + * on meeting a non-alphanumeric character, an extra increment is needed + * where the succeeding extension is a multi-letter prefixed with an "_". + */ + if (*isa == '_') + ++isa; + +#define SET_ISA_EXT_MAP(name, bit) \ + do { \ + if ((ext_end - ext == sizeof(name) - 1) && \ + !strncasecmp(ext, name, sizeof(name) - 1) && \ + riscv_isa_extension_check(bit)) \ + set_bit(bit, isainfo->isa); \ + } while (false) \ if (unlikely(ext_err)) continue; if (!ext_long) { - int nr = *ext - 'a'; + int nr = tolower(*ext) - 'a'; if (riscv_isa_extension_check(nr)) { this_hwcap |= isa2hwcap[nr]; - set_bit(nr, this_isa); + set_bit(nr, isainfo->isa); } } else { /* sorted alphabetically */ @@ -236,7 +307,9 @@ void __init riscv_fill_hwcap(void) SET_ISA_EXT_MAP("svinval", RISCV_ISA_EXT_SVINVAL); SET_ISA_EXT_MAP("svnapot", RISCV_ISA_EXT_SVNAPOT); SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT); + SET_ISA_EXT_MAP("zba", RISCV_ISA_EXT_ZBA); SET_ISA_EXT_MAP("zbb", RISCV_ISA_EXT_ZBB); + SET_ISA_EXT_MAP("zbs", RISCV_ISA_EXT_ZBS); SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM); SET_ISA_EXT_MAP("zicboz", RISCV_ISA_EXT_ZICBOZ); SET_ISA_EXT_MAP("zihintpause", RISCV_ISA_EXT_ZIHINTPAUSE); @@ -245,6 +318,23 @@ void __init riscv_fill_hwcap(void) } /* + * Linux requires the following extensions, so we may as well + * always set them. + */ + set_bit(RISCV_ISA_EXT_ZICSR, isainfo->isa); + set_bit(RISCV_ISA_EXT_ZIFENCEI, isainfo->isa); + + /* + * These ones were as they were part of the base ISA when the + * port & dt-bindings were upstreamed, and so can be set + * unconditionally where `i` is in riscv,isa on DT systems. + */ + if (acpi_disabled) { + set_bit(RISCV_ISA_EXT_ZICNTR, isainfo->isa); + set_bit(RISCV_ISA_EXT_ZIHPM, isainfo->isa); + } + + /* * All "okay" hart should have same isa. Set HWCAP based on * common capabilities of every "okay" hart, in case they don't * have. @@ -255,11 +345,14 @@ void __init riscv_fill_hwcap(void) elf_hwcap = this_hwcap; if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX)) - bitmap_copy(riscv_isa, this_isa, RISCV_ISA_EXT_MAX); + bitmap_copy(riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX); else - bitmap_and(riscv_isa, riscv_isa, this_isa, RISCV_ISA_EXT_MAX); + bitmap_and(riscv_isa, riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX); } + if (!acpi_disabled && rhct) + acpi_put_table((struct acpi_table_header *)rhct); + /* We don't support systems with F but without D, so mask those out * here. */ if ((elf_hwcap & COMPAT_HWCAP_ISA_F) && !(elf_hwcap & COMPAT_HWCAP_ISA_D)) { @@ -267,6 +360,17 @@ void __init riscv_fill_hwcap(void) elf_hwcap &= ~COMPAT_HWCAP_ISA_F; } + if (elf_hwcap & COMPAT_HWCAP_ISA_V) { + riscv_v_setup_vsize(); + /* + * ISA string in device tree might have 'v' flag, but + * CONFIG_RISCV_ISA_V is disabled in kernel. + * Clear V flag in elf_hwcap if CONFIG_RISCV_ISA_V is disabled. + */ + if (!IS_ENABLED(CONFIG_RISCV_ISA_V)) + elf_hwcap &= ~COMPAT_HWCAP_ISA_V; + } + memset(print_str, 0, sizeof(print_str)); for (i = 0, j = 0; i < NUM_ALPHA_EXTS; i++) if (riscv_isa[0] & BIT_MASK(i)) @@ -280,6 +384,18 @@ void __init riscv_fill_hwcap(void) pr_info("riscv: ELF capabilities %s\n", print_str); } +unsigned long riscv_get_elf_hwcap(void) +{ + unsigned long hwcap; + + hwcap = (elf_hwcap & ((1UL << RISCV_ISA_EXT_BASE) - 1)); + + if (!riscv_v_vstate_ctrl_user_allowed()) + hwcap &= ~COMPAT_HWCAP_ISA_V; + + return hwcap; +} + #ifdef CONFIG_RISCV_ALTERNATIVE /* * Alternative patch sites consider 48 bits when determining when to patch diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 3fbb100bc9e4..143a2bb3e697 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -48,10 +48,10 @@ _save_context: * Disable user-mode memory access as it should only be set in the * actual user copy routines. * - * Disable the FPU to detect illegal usage of floating point in kernel - * space. + * Disable the FPU/Vector to detect illegal usage of floating point + * or vector in kernel space. */ - li t0, SR_SUM | SR_FS + li t0, SR_SUM | SR_FS_VS REG_L s0, TASK_TI_USER_SP(tp) csrrc s1, CSR_STATUS, t0 @@ -348,6 +348,6 @@ SYM_CODE_END(excp_vect_table) #ifndef CONFIG_MMU SYM_CODE_START(__user_rt_sigreturn) li a7, __NR_rt_sigreturn - scall + ecall SYM_CODE_END(__user_rt_sigreturn) #endif diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 4bf6c449d78b..11c3b94c4534 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -140,10 +140,10 @@ secondary_start_sbi: .option pop /* - * Disable FPU to detect illegal usage of - * floating point in kernel space + * Disable FPU & VECTOR to detect illegal usage of + * floating point or vector in kernel space */ - li t0, SR_FS + li t0, SR_FS_VS csrc CSR_STATUS, t0 /* Set trap vector to spin forever to help debug */ @@ -234,10 +234,10 @@ pmp_done: .option pop /* - * Disable FPU to detect illegal usage of - * floating point in kernel space + * Disable FPU & VECTOR to detect illegal usage of + * floating point or vector in kernel space */ - li t0, SR_FS + li t0, SR_FS_VS csrc CSR_STATUS, t0 #ifdef CONFIG_RISCV_BOOT_SPINWAIT @@ -301,6 +301,7 @@ clear_bss_done: la tp, init_task la sp, init_thread_union + THREAD_SIZE XIP_FIXUP_OFFSET sp + addi sp, sp, -PT_SIZE_ON_STACK #ifdef CONFIG_BUILTIN_DTB la a0, __dtb_start XIP_FIXUP_OFFSET a0 @@ -318,6 +319,7 @@ clear_bss_done: /* Restore C environment */ la tp, init_task la sp, init_thread_union + THREAD_SIZE + addi sp, sp, -PT_SIZE_ON_STACK #ifdef CONFIG_KASAN call kasan_early_init @@ -392,7 +394,7 @@ ENTRY(reset_regs) #ifdef CONFIG_FPU csrr t0, CSR_MISA andi t0, t0, (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D) - beqz t0, .Lreset_regs_done + beqz t0, .Lreset_regs_done_fpu li t1, SR_FS csrs CSR_STATUS, t1 @@ -430,8 +432,31 @@ ENTRY(reset_regs) fmv.s.x f31, zero csrw fcsr, 0 /* note that the caller must clear SR_FS */ +.Lreset_regs_done_fpu: #endif /* CONFIG_FPU */ -.Lreset_regs_done: + +#ifdef CONFIG_RISCV_ISA_V + csrr t0, CSR_MISA + li t1, COMPAT_HWCAP_ISA_V + and t0, t0, t1 + beqz t0, .Lreset_regs_done_vector + + /* + * Clear vector registers and reset vcsr + * VLMAX has a defined value, VLEN is a constant, + * and this form of vsetvli is defined to set vl to VLMAX. + */ + li t1, SR_VS + csrs CSR_STATUS, t1 + csrs CSR_VCSR, x0 + vsetvli t1, x0, e8, m8, ta, ma + vmv.v.i v0, 0 + vmv.v.i v8, 0 + vmv.v.i v16, 0 + vmv.v.i v24, 0 + /* note that the caller must clear SR_VS */ +.Lreset_regs_done_vector: +#endif /* CONFIG_RISCV_ISA_V */ ret END(reset_regs) #endif /* CONFIG_RISCV_M_MODE */ diff --git a/arch/riscv/kernel/hibernate-asm.S b/arch/riscv/kernel/hibernate-asm.S index effaf5ca5da0..d698dd7df637 100644 --- a/arch/riscv/kernel/hibernate-asm.S +++ b/arch/riscv/kernel/hibernate-asm.S @@ -28,7 +28,6 @@ ENTRY(__hibernate_cpu_resume) REG_L a0, hibernate_cpu_context - suspend_restore_csrs suspend_restore_regs /* Return zero value. */ @@ -50,7 +49,7 @@ ENTRY(hibernate_restore_image) REG_L s4, restore_pblist REG_L a1, relocated_restore_code - jalr a1 + jr a1 END(hibernate_restore_image) /* @@ -73,5 +72,5 @@ ENTRY(hibernate_core_restore_code) REG_L s4, HIBERN_PBE_NEXT(s4) bnez s4, .Lcopy - jalr s2 + jr s2 END(hibernate_core_restore_code) diff --git a/arch/riscv/kernel/hibernate.c b/arch/riscv/kernel/hibernate.c index 264b2dcdd67e..671b686c0158 100644 --- a/arch/riscv/kernel/hibernate.c +++ b/arch/riscv/kernel/hibernate.c @@ -80,7 +80,6 @@ int pfn_is_nosave(unsigned long pfn) void notrace save_processor_state(void) { - WARN_ON(num_online_cpus() != 1); } void notrace restore_processor_state(void) diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c index eb9a68a539e6..d0577cc6a081 100644 --- a/arch/riscv/kernel/irq.c +++ b/arch/riscv/kernel/irq.c @@ -11,6 +11,9 @@ #include <linux/module.h> #include <linux/seq_file.h> #include <asm/sbi.h> +#include <asm/smp.h> +#include <asm/softirq_stack.h> +#include <asm/stacktrace.h> static struct fwnode_handle *(*__get_intc_node)(void); @@ -28,6 +31,70 @@ struct fwnode_handle *riscv_get_intc_hwnode(void) } EXPORT_SYMBOL_GPL(riscv_get_intc_hwnode); +#ifdef CONFIG_IRQ_STACKS +#include <asm/irq_stack.h> + +DEFINE_PER_CPU(ulong *, irq_stack_ptr); + +#ifdef CONFIG_VMAP_STACK +static void init_irq_stacks(void) +{ + int cpu; + ulong *p; + + for_each_possible_cpu(cpu) { + p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, cpu_to_node(cpu)); + per_cpu(irq_stack_ptr, cpu) = p; + } +} +#else +/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */ +DEFINE_PER_CPU_ALIGNED(ulong [IRQ_STACK_SIZE/sizeof(ulong)], irq_stack); + +static void init_irq_stacks(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + per_cpu(irq_stack_ptr, cpu) = per_cpu(irq_stack, cpu); +} +#endif /* CONFIG_VMAP_STACK */ + +#ifdef CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK +void do_softirq_own_stack(void) +{ +#ifdef CONFIG_IRQ_STACKS + if (on_thread_stack()) { + ulong *sp = per_cpu(irq_stack_ptr, smp_processor_id()) + + IRQ_STACK_SIZE/sizeof(ulong); + __asm__ __volatile( + "addi sp, sp, -"RISCV_SZPTR "\n" + REG_S" ra, (sp) \n" + "addi sp, sp, -"RISCV_SZPTR "\n" + REG_S" s0, (sp) \n" + "addi s0, sp, 2*"RISCV_SZPTR "\n" + "move sp, %[sp] \n" + "call __do_softirq \n" + "addi sp, s0, -2*"RISCV_SZPTR"\n" + REG_L" s0, (sp) \n" + "addi sp, sp, "RISCV_SZPTR "\n" + REG_L" ra, (sp) \n" + "addi sp, sp, "RISCV_SZPTR "\n" + : + : [sp] "r" (sp) + : "a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7", + "t0", "t1", "t2", "t3", "t4", "t5", "t6", + "memory"); + } else +#endif + __do_softirq(); +} +#endif /* CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK */ + +#else +static void init_irq_stacks(void) {} +#endif /* CONFIG_IRQ_STACKS */ + int arch_show_interrupts(struct seq_file *p, int prec) { show_ipi_stats(p, prec); @@ -36,6 +103,7 @@ int arch_show_interrupts(struct seq_file *p, int prec) void __init init_IRQ(void) { + init_irq_stacks(); irqchip_init(); if (!handle_arch_irq) panic("No interrupt controller found."); diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c index c976a21cd4bd..194f166b2cc4 100644 --- a/arch/riscv/kernel/probes/uprobes.c +++ b/arch/riscv/kernel/probes/uprobes.c @@ -67,6 +67,7 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) struct uprobe_task *utask = current->utask; WARN_ON_ONCE(current->thread.bad_cause != UPROBE_TRAP_NR); + current->thread.bad_cause = utask->autask.saved_cause; instruction_pointer_set(regs, utask->vaddr + auprobe->insn_size); @@ -102,6 +103,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { struct uprobe_task *utask = current->utask; + current->thread.bad_cause = utask->autask.saved_cause; /* * Task has received a fatal signal, so reset back to probbed * address. diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index e2a060066730..e32d737e039f 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -24,6 +24,7 @@ #include <asm/switch_to.h> #include <asm/thread_info.h> #include <asm/cpuidle.h> +#include <asm/vector.h> register unsigned long gp_in_global __asm__("gp"); @@ -146,12 +147,29 @@ void flush_thread(void) fstate_off(current, task_pt_regs(current)); memset(¤t->thread.fstate, 0, sizeof(current->thread.fstate)); #endif +#ifdef CONFIG_RISCV_ISA_V + /* Reset vector state */ + riscv_v_vstate_ctrl_init(current); + riscv_v_vstate_off(task_pt_regs(current)); + kfree(current->thread.vstate.datap); + memset(¤t->thread.vstate, 0, sizeof(struct __riscv_v_ext_state)); +#endif +} + +void arch_release_task_struct(struct task_struct *tsk) +{ + /* Free the vector context of datap. */ + if (has_vector()) + kfree(tsk->thread.vstate.datap); } int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { fstate_save(src, task_pt_regs(src)); *dst = *src; + /* clear entire V context, including datap for a new task */ + memset(&dst->thread.vstate, 0, sizeof(struct __riscv_v_ext_state)); + return 0; } @@ -176,6 +194,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.s[1] = (unsigned long)args->fn_arg; } else { *childregs = *(current_pt_regs()); + /* Turn off status.VS */ + riscv_v_vstate_off(childregs); if (usp) /* User fork */ childregs->sp = usp; if (clone_flags & CLONE_SETTLS) diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 23c48b14a0e7..1d572cf3140f 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -7,6 +7,7 @@ * Copied from arch/tile/kernel/ptrace.c */ +#include <asm/vector.h> #include <asm/ptrace.h> #include <asm/syscall.h> #include <asm/thread_info.h> @@ -24,6 +25,9 @@ enum riscv_regset { #ifdef CONFIG_FPU REGSET_F, #endif +#ifdef CONFIG_RISCV_ISA_V + REGSET_V, +#endif }; static int riscv_gpr_get(struct task_struct *target, @@ -80,6 +84,61 @@ static int riscv_fpr_set(struct task_struct *target, } #endif +#ifdef CONFIG_RISCV_ISA_V +static int riscv_vr_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct __riscv_v_ext_state *vstate = &target->thread.vstate; + + if (!riscv_v_vstate_query(task_pt_regs(target))) + return -EINVAL; + + /* + * Ensure the vector registers have been saved to the memory before + * copying them to membuf. + */ + if (target == current) + riscv_v_vstate_save(current, task_pt_regs(current)); + + /* Copy vector header from vstate. */ + membuf_write(&to, vstate, offsetof(struct __riscv_v_ext_state, datap)); + membuf_zero(&to, sizeof(vstate->datap)); + + /* Copy all the vector registers from vstate. */ + return membuf_write(&to, vstate->datap, riscv_v_vsize); +} + +static int riscv_vr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret, size; + struct __riscv_v_ext_state *vstate = &target->thread.vstate; + + if (!riscv_v_vstate_query(task_pt_regs(target))) + return -EINVAL; + + /* Copy rest of the vstate except datap */ + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vstate, 0, + offsetof(struct __riscv_v_ext_state, datap)); + if (unlikely(ret)) + return ret; + + /* Skip copy datap. */ + size = sizeof(vstate->datap); + count -= size; + ubuf += size; + + /* Copy all the vector registers. */ + pos = 0; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vstate->datap, + 0, riscv_v_vsize); + return ret; +} +#endif + static const struct user_regset riscv_user_regset[] = { [REGSET_X] = { .core_note_type = NT_PRSTATUS, @@ -99,6 +158,17 @@ static const struct user_regset riscv_user_regset[] = { .set = riscv_fpr_set, }, #endif +#ifdef CONFIG_RISCV_ISA_V + [REGSET_V] = { + .core_note_type = NT_RISCV_VECTOR, + .align = 16, + .n = ((32 * RISCV_MAX_VLENB) + + sizeof(struct __riscv_v_ext_state)) / sizeof(__u32), + .size = sizeof(__u32), + .regset_get = riscv_vr_get, + .set = riscv_vr_set, + }, +#endif }; static const struct user_regset_view riscv_user_native_view = { diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 36b026057503..971fe776e2f8 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -8,6 +8,7 @@ * Nick Kossifidis <mick@ics.forth.gr> */ +#include <linux/acpi.h> #include <linux/cpu.h> #include <linux/init.h> #include <linux/mm.h> @@ -21,6 +22,7 @@ #include <linux/efi.h> #include <linux/crash_dump.h> +#include <asm/acpi.h> #include <asm/alternative.h> #include <asm/cacheflush.h> #include <asm/cpu_ops.h> @@ -262,6 +264,8 @@ static void __init parse_dtb(void) #endif } +extern void __init init_rt_signal_env(void); + void __init setup_arch(char **cmdline_p) { parse_dtb(); @@ -270,11 +274,16 @@ void __init setup_arch(char **cmdline_p) *cmdline_p = boot_command_line; early_ioremap_setup(); + sbi_init(); jump_label_init(); parse_early_param(); efi_init(); paging_init(); + + /* Parse the ACPI tables for possible boot-time configuration */ + acpi_boot_table_init(); + #if IS_ENABLED(CONFIG_BUILTIN_DTB) unflatten_and_copy_device_tree(); #else @@ -283,7 +292,6 @@ void __init setup_arch(char **cmdline_p) misc_mem_init(); init_resources(); - sbi_init(); #ifdef CONFIG_KASAN kasan_init(); @@ -293,8 +301,12 @@ void __init setup_arch(char **cmdline_p) setup_smp(); #endif + if (!acpi_disabled) + acpi_init_rintc_map(); + riscv_init_cbo_blocksizes(); riscv_fill_hwcap(); + init_rt_signal_env(); apply_boot_alternatives(); if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) && riscv_isa_extension_available(NULL, ZICBOM)) diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 9aff9d720590..180d951d3624 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -19,10 +19,14 @@ #include <asm/signal.h> #include <asm/signal32.h> #include <asm/switch_to.h> +#include <asm/vector.h> #include <asm/csr.h> #include <asm/cacheflush.h> +unsigned long signal_minsigstksz __ro_after_init; + extern u32 __user_rt_sigreturn[2]; +static size_t riscv_v_sc_size __ro_after_init; #define DEBUG_SIG 0 @@ -40,26 +44,13 @@ static long restore_fp_state(struct pt_regs *regs, { long err; struct __riscv_d_ext_state __user *state = &sc_fpregs->d; - size_t i; err = __copy_from_user(¤t->thread.fstate, state, sizeof(*state)); if (unlikely(err)) return err; fstate_restore(current, regs); - - /* We support no other extension state at this time. */ - for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) { - u32 value; - - err = __get_user(value, &sc_fpregs->q.reserved[i]); - if (unlikely(err)) - break; - if (value != 0) - return -EINVAL; - } - - return err; + return 0; } static long save_fp_state(struct pt_regs *regs, @@ -67,52 +58,186 @@ static long save_fp_state(struct pt_regs *regs, { long err; struct __riscv_d_ext_state __user *state = &sc_fpregs->d; - size_t i; fstate_save(current, regs); err = __copy_to_user(state, ¤t->thread.fstate, sizeof(*state)); + return err; +} +#else +#define save_fp_state(task, regs) (0) +#define restore_fp_state(task, regs) (0) +#endif + +#ifdef CONFIG_RISCV_ISA_V + +static long save_v_state(struct pt_regs *regs, void __user **sc_vec) +{ + struct __riscv_ctx_hdr __user *hdr; + struct __sc_riscv_v_state __user *state; + void __user *datap; + long err; + + hdr = *sc_vec; + /* Place state to the user's signal context space after the hdr */ + state = (struct __sc_riscv_v_state __user *)(hdr + 1); + /* Point datap right after the end of __sc_riscv_v_state */ + datap = state + 1; + + /* datap is designed to be 16 byte aligned for better performance */ + WARN_ON(unlikely(!IS_ALIGNED((unsigned long)datap, 16))); + + riscv_v_vstate_save(current, regs); + /* Copy everything of vstate but datap. */ + err = __copy_to_user(&state->v_state, ¤t->thread.vstate, + offsetof(struct __riscv_v_ext_state, datap)); + /* Copy the pointer datap itself. */ + err |= __put_user(datap, &state->v_state.datap); + /* Copy the whole vector content to user space datap. */ + err |= __copy_to_user(datap, current->thread.vstate.datap, riscv_v_vsize); + /* Copy magic to the user space after saving all vector conetext */ + err |= __put_user(RISCV_V_MAGIC, &hdr->magic); + err |= __put_user(riscv_v_sc_size, &hdr->size); if (unlikely(err)) return err; - /* We support no other extension state at this time. */ - for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) { - err = __put_user(0, &sc_fpregs->q.reserved[i]); - if (unlikely(err)) - break; - } + /* Only progress the sv_vec if everything has done successfully */ + *sc_vec += riscv_v_sc_size; + return 0; +} + +/* + * Restore Vector extension context from the user's signal frame. This function + * assumes a valid extension header. So magic and size checking must be done by + * the caller. + */ +static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec) +{ + long err; + struct __sc_riscv_v_state __user *state = sc_vec; + void __user *datap; + + /* Copy everything of __sc_riscv_v_state except datap. */ + err = __copy_from_user(¤t->thread.vstate, &state->v_state, + offsetof(struct __riscv_v_ext_state, datap)); + if (unlikely(err)) + return err; + + /* Copy the pointer datap itself. */ + err = __get_user(datap, &state->v_state.datap); + if (unlikely(err)) + return err; + /* + * Copy the whole vector content from user space datap. Use + * copy_from_user to prevent information leak. + */ + err = copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize); + if (unlikely(err)) + return err; + + riscv_v_vstate_restore(current, regs); return err; } #else -#define save_fp_state(task, regs) (0) -#define restore_fp_state(task, regs) (0) +#define save_v_state(task, regs) (0) +#define __restore_v_state(task, regs) (0) #endif static long restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) { + void __user *sc_ext_ptr = &sc->sc_extdesc.hdr; + __u32 rsvd; long err; /* sc_regs is structured the same as the start of pt_regs */ err = __copy_from_user(regs, &sc->sc_regs, sizeof(sc->sc_regs)); + if (unlikely(err)) + return err; + /* Restore the floating-point state. */ - if (has_fpu()) - err |= restore_fp_state(regs, &sc->sc_fpregs); + if (has_fpu()) { + err = restore_fp_state(regs, &sc->sc_fpregs); + if (unlikely(err)) + return err; + } + + /* Check the reserved word before extensions parsing */ + err = __get_user(rsvd, &sc->sc_extdesc.reserved); + if (unlikely(err)) + return err; + if (unlikely(rsvd)) + return -EINVAL; + + while (!err) { + __u32 magic, size; + struct __riscv_ctx_hdr __user *head = sc_ext_ptr; + + err |= __get_user(magic, &head->magic); + err |= __get_user(size, &head->size); + if (unlikely(err)) + return err; + + sc_ext_ptr += sizeof(*head); + switch (magic) { + case END_MAGIC: + if (size != END_HDR_SIZE) + return -EINVAL; + + return 0; + case RISCV_V_MAGIC: + if (!has_vector() || !riscv_v_vstate_query(regs) || + size != riscv_v_sc_size) + return -EINVAL; + + err = __restore_v_state(regs, sc_ext_ptr); + break; + default: + return -EINVAL; + } + sc_ext_ptr = (void __user *)head + size; + } return err; } +static size_t get_rt_frame_size(bool cal_all) +{ + struct rt_sigframe __user *frame; + size_t frame_size; + size_t total_context_size = 0; + + frame_size = sizeof(*frame); + + if (has_vector()) { + if (cal_all || riscv_v_vstate_query(task_pt_regs(current))) + total_context_size += riscv_v_sc_size; + } + /* + * Preserved a __riscv_ctx_hdr for END signal context header if an + * extension uses __riscv_extra_ext_header + */ + if (total_context_size) + total_context_size += sizeof(struct __riscv_ctx_hdr); + + frame_size += total_context_size; + + frame_size = round_up(frame_size, 16); + return frame_size; +} + SYSCALL_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; struct task_struct *task; sigset_t set; + size_t frame_size = get_rt_frame_size(false); /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; frame = (struct rt_sigframe __user *)regs->sp; - if (!access_ok(frame, sizeof(*frame))) + if (!access_ok(frame, frame_size)) goto badframe; if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) @@ -146,12 +271,23 @@ static long setup_sigcontext(struct rt_sigframe __user *frame, struct pt_regs *regs) { struct sigcontext __user *sc = &frame->uc.uc_mcontext; + struct __riscv_ctx_hdr __user *sc_ext_ptr = &sc->sc_extdesc.hdr; long err; + /* sc_regs is structured the same as the start of pt_regs */ err = __copy_to_user(&sc->sc_regs, regs, sizeof(sc->sc_regs)); /* Save the floating-point state. */ if (has_fpu()) err |= save_fp_state(regs, &sc->sc_fpregs); + /* Save the vector state. */ + if (has_vector() && riscv_v_vstate_query(regs)) + err |= save_v_state(regs, (void __user **)&sc_ext_ptr); + /* Write zero to fp-reserved space and check it on restore_sigcontext */ + err |= __put_user(0, &sc->sc_extdesc.reserved); + /* And put END __riscv_ctx_hdr at the end. */ + err |= __put_user(END_MAGIC, &sc_ext_ptr->magic); + err |= __put_user(END_HDR_SIZE, &sc_ext_ptr->size); + return err; } @@ -175,6 +311,13 @@ static inline void __user *get_sigframe(struct ksignal *ksig, /* Align the stack frame. */ sp &= ~0xfUL; + /* + * Fail if the size of the altstack is not large enough for the + * sigframe construction. + */ + if (current->sas_ss_size && sp < current->sas_ss_sp) + return (void __user __force *)-1UL; + return (void __user *)sp; } @@ -184,9 +327,10 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct rt_sigframe __user *frame; long err = 0; unsigned long __maybe_unused addr; + size_t frame_size = get_rt_frame_size(false); - frame = get_sigframe(ksig, regs, sizeof(*frame)); - if (!access_ok(frame, sizeof(*frame))) + frame = get_sigframe(ksig, regs, frame_size); + if (!access_ok(frame, frame_size)) return -EFAULT; err |= copy_siginfo_to_user(&frame->info, &ksig->info); @@ -319,3 +463,23 @@ void arch_do_signal_or_restart(struct pt_regs *regs) */ restore_saved_sigmask(); } + +void init_rt_signal_env(void); +void __init init_rt_signal_env(void) +{ + riscv_v_sc_size = sizeof(struct __riscv_ctx_hdr) + + sizeof(struct __sc_riscv_v_state) + riscv_v_vsize; + /* + * Determine the stack space required for guaranteed signal delivery. + * The signal_minsigstksz will be populated into the AT_MINSIGSTKSZ entry + * in the auxiliary array at process startup. + */ + signal_minsigstksz = get_rt_frame_size(true); +} + +#ifdef CONFIG_DYNAMIC_SIGFRAME +bool sigaltstack_size_valid(size_t ss_size) +{ + return ss_size > get_rt_frame_size(false); +} +#endif /* CONFIG_DYNAMIC_SIGFRAME */ diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 445a4efee267..bb0b76e1a6d4 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -8,6 +8,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/acpi.h> #include <linux/arch_topology.h> #include <linux/module.h> #include <linux/init.h> @@ -31,6 +32,8 @@ #include <asm/tlbflush.h> #include <asm/sections.h> #include <asm/smp.h> +#include <uapi/asm/hwcap.h> +#include <asm/vector.h> #include "head.h" @@ -70,7 +73,73 @@ void __init smp_prepare_cpus(unsigned int max_cpus) } } -void __init setup_smp(void) +#ifdef CONFIG_ACPI +static unsigned int cpu_count = 1; + +static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const unsigned long end) +{ + unsigned long hart; + static bool found_boot_cpu; + struct acpi_madt_rintc *processor = (struct acpi_madt_rintc *)header; + + /* + * Each RINTC structure in MADT will have a flag. If ACPI_MADT_ENABLED + * bit in the flag is not enabled, it means OS should not try to enable + * the cpu to which RINTC belongs. + */ + if (!(processor->flags & ACPI_MADT_ENABLED)) + return 0; + + if (BAD_MADT_ENTRY(processor, end)) + return -EINVAL; + + acpi_table_print_madt_entry(&header->common); + + hart = processor->hart_id; + if (hart == INVALID_HARTID) { + pr_warn("Invalid hartid\n"); + return 0; + } + + if (hart == cpuid_to_hartid_map(0)) { + BUG_ON(found_boot_cpu); + found_boot_cpu = true; + early_map_cpu_to_node(0, acpi_numa_get_nid(cpu_count)); + return 0; + } + + if (cpu_count >= NR_CPUS) { + pr_warn("NR_CPUS is too small for the number of ACPI tables.\n"); + return 0; + } + + cpuid_to_hartid_map(cpu_count) = hart; + early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count)); + cpu_count++; + + return 0; +} + +static void __init acpi_parse_and_init_cpus(void) +{ + int cpuid; + + cpu_set_ops(0); + + acpi_table_parse_madt(ACPI_MADT_TYPE_RINTC, acpi_parse_rintc, 0); + + for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) { + if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) { + cpu_set_ops(cpuid); + set_cpu_possible(cpuid, true); + } + } +} +#else +#define acpi_parse_and_init_cpus(...) do { } while (0) +#endif + +static void __init of_parse_and_init_cpus(void) { struct device_node *dn; unsigned long hart; @@ -81,7 +150,7 @@ void __init setup_smp(void) cpu_set_ops(0); for_each_of_cpu_node(dn) { - rc = riscv_of_processor_hartid(dn, &hart); + rc = riscv_early_of_processor_hartid(dn, &hart); if (rc < 0) continue; @@ -116,6 +185,14 @@ void __init setup_smp(void) } } +void __init setup_smp(void) +{ + if (acpi_disabled) + of_parse_and_init_cpus(); + else + acpi_parse_and_init_cpus(); +} + static int start_secondary_cpu(int cpu, struct task_struct *tidle) { if (cpu_ops[cpu]->cpu_start) @@ -169,6 +246,11 @@ asmlinkage __visible void smp_callin(void) set_cpu_online(curr_cpuid, 1); probe_vendor_features(curr_cpuid); + if (has_vector()) { + if (riscv_v_setup_vsize()) + elf_hwcap &= ~COMPAT_HWCAP_ISA_V; + } + /* * Remote TLB flushes are ignored while the CPU is offline, so emit * a local TLB flush right now just in case. diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 5db29683ebee..26ef5526bfb4 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -10,6 +10,7 @@ #include <asm/cpufeature.h> #include <asm/hwprobe.h> #include <asm/sbi.h> +#include <asm/vector.h> #include <asm/switch_to.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -121,6 +122,49 @@ static void hwprobe_arch_id(struct riscv_hwprobe *pair, pair->value = id; } +static void hwprobe_isa_ext0(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + int cpu; + u64 missing = 0; + + pair->value = 0; + if (has_fpu()) + pair->value |= RISCV_HWPROBE_IMA_FD; + + if (riscv_isa_extension_available(NULL, c)) + pair->value |= RISCV_HWPROBE_IMA_C; + + if (has_vector()) + pair->value |= RISCV_HWPROBE_IMA_V; + + /* + * Loop through and record extensions that 1) anyone has, and 2) anyone + * doesn't have. + */ + for_each_cpu(cpu, cpus) { + struct riscv_isainfo *isainfo = &hart_isa[cpu]; + + if (riscv_isa_extension_available(isainfo->isa, ZBA)) + pair->value |= RISCV_HWPROBE_EXT_ZBA; + else + missing |= RISCV_HWPROBE_EXT_ZBA; + + if (riscv_isa_extension_available(isainfo->isa, ZBB)) + pair->value |= RISCV_HWPROBE_EXT_ZBB; + else + missing |= RISCV_HWPROBE_EXT_ZBB; + + if (riscv_isa_extension_available(isainfo->isa, ZBS)) + pair->value |= RISCV_HWPROBE_EXT_ZBS; + else + missing |= RISCV_HWPROBE_EXT_ZBS; + } + + /* Now turn off reporting features if any CPU is missing it. */ + pair->value &= ~missing; +} + static u64 hwprobe_misaligned(const struct cpumask *cpus) { int cpu; @@ -164,13 +208,7 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair, break; case RISCV_HWPROBE_KEY_IMA_EXT_0: - pair->value = 0; - if (has_fpu()) - pair->value |= RISCV_HWPROBE_IMA_FD; - - if (riscv_isa_extension_available(NULL, c)) - pair->value |= RISCV_HWPROBE_IMA_C; - + hwprobe_isa_ext0(pair, cpus); break; case RISCV_HWPROBE_KEY_CPUPERF_0: diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index babaf3b48ba8..23641e82a9df 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -4,6 +4,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/acpi.h> #include <linux/of_clk.h> #include <linux/clockchips.h> #include <linux/clocksource.h> @@ -18,17 +19,29 @@ EXPORT_SYMBOL_GPL(riscv_timebase); void __init time_init(void) { struct device_node *cpu; + struct acpi_table_rhct *rhct; + acpi_status status; u32 prop; - cpu = of_find_node_by_path("/cpus"); - if (!cpu || of_property_read_u32(cpu, "timebase-frequency", &prop)) - panic(KERN_WARNING "RISC-V system with no 'timebase-frequency' in DTS\n"); - of_node_put(cpu); - riscv_timebase = prop; + if (acpi_disabled) { + cpu = of_find_node_by_path("/cpus"); + if (!cpu || of_property_read_u32(cpu, "timebase-frequency", &prop)) + panic("RISC-V system with no 'timebase-frequency' in DTS\n"); + + of_node_put(cpu); + riscv_timebase = prop; + of_clk_init(NULL); + } else { + status = acpi_get_table(ACPI_SIG_RHCT, 0, (struct acpi_table_header **)&rhct); + if (ACPI_FAILURE(status)) + panic("RISC-V ACPI system with no RHCT table\n"); + + riscv_timebase = rhct->time_base_freq; + acpi_put_table((struct acpi_table_header *)rhct); + } lpj_fine = riscv_timebase / HZ; - of_clk_init(NULL); timer_probe(); tick_setup_hrtimer_broadcast(); diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 8c258b78c925..5158961ea977 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -26,6 +26,8 @@ #include <asm/ptrace.h> #include <asm/syscall.h> #include <asm/thread_info.h> +#include <asm/vector.h> +#include <asm/irq_stack.h> int show_unhandled_signals = 1; @@ -145,8 +147,29 @@ DO_ERROR_INFO(do_trap_insn_misaligned, SIGBUS, BUS_ADRALN, "instruction address misaligned"); DO_ERROR_INFO(do_trap_insn_fault, SIGSEGV, SEGV_ACCERR, "instruction access fault"); -DO_ERROR_INFO(do_trap_insn_illegal, - SIGILL, ILL_ILLOPC, "illegal instruction"); + +asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *regs) +{ + if (user_mode(regs)) { + irqentry_enter_from_user_mode(regs); + + local_irq_enable(); + + if (!riscv_v_first_use_handler(regs)) + do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc, + "Oops - illegal instruction"); + + irqentry_exit_to_user_mode(regs); + } else { + irqentry_state_t state = irqentry_nmi_enter(regs); + + do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc, + "Oops - illegal instruction"); + + irqentry_nmi_exit(regs, state); + } +} + DO_ERROR_INFO(do_trap_load_fault, SIGSEGV, SEGV_ACCERR, "load access fault"); #ifndef CONFIG_RISCV_M_MODE @@ -305,16 +328,46 @@ asmlinkage __visible noinstr void do_page_fault(struct pt_regs *regs) } #endif -asmlinkage __visible noinstr void do_irq(struct pt_regs *regs) +static void noinstr handle_riscv_irq(struct pt_regs *regs) { struct pt_regs *old_regs; - irqentry_state_t state = irqentry_enter(regs); irq_enter_rcu(); old_regs = set_irq_regs(regs); handle_arch_irq(regs); set_irq_regs(old_regs); irq_exit_rcu(); +} + +asmlinkage void noinstr do_irq(struct pt_regs *regs) +{ + irqentry_state_t state = irqentry_enter(regs); +#ifdef CONFIG_IRQ_STACKS + if (on_thread_stack()) { + ulong *sp = per_cpu(irq_stack_ptr, smp_processor_id()) + + IRQ_STACK_SIZE/sizeof(ulong); + __asm__ __volatile( + "addi sp, sp, -"RISCV_SZPTR "\n" + REG_S" ra, (sp) \n" + "addi sp, sp, -"RISCV_SZPTR "\n" + REG_S" s0, (sp) \n" + "addi s0, sp, 2*"RISCV_SZPTR "\n" + "move sp, %[sp] \n" + "move a0, %[regs] \n" + "call handle_riscv_irq \n" + "addi sp, s0, -2*"RISCV_SZPTR"\n" + REG_L" s0, (sp) \n" + "addi sp, sp, "RISCV_SZPTR "\n" + REG_L" ra, (sp) \n" + "addi sp, sp, "RISCV_SZPTR "\n" + : + : [sp] "r" (sp), [regs] "r" (regs) + : "a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7", + "t0", "t1", "t2", "t3", "t4", "t5", "t6", + "memory"); + } else +#endif + handle_riscv_irq(regs); irqentry_exit(regs, state); } diff --git a/arch/riscv/kernel/vdso/rt_sigreturn.S b/arch/riscv/kernel/vdso/rt_sigreturn.S index 0573705eac76..10438c7c626a 100644 --- a/arch/riscv/kernel/vdso/rt_sigreturn.S +++ b/arch/riscv/kernel/vdso/rt_sigreturn.S @@ -11,6 +11,6 @@ ENTRY(__vdso_rt_sigreturn) .cfi_startproc .cfi_signal_frame li a7, __NR_rt_sigreturn - scall + ecall .cfi_endproc ENDPROC(__vdso_rt_sigreturn) diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c new file mode 100644 index 000000000000..f9c8e19ab301 --- /dev/null +++ b/arch/riscv/kernel/vector.c @@ -0,0 +1,276 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2023 SiFive + * Author: Andy Chiu <andy.chiu@sifive.com> + */ +#include <linux/export.h> +#include <linux/sched/signal.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/uaccess.h> +#include <linux/prctl.h> + +#include <asm/thread_info.h> +#include <asm/processor.h> +#include <asm/insn.h> +#include <asm/vector.h> +#include <asm/csr.h> +#include <asm/elf.h> +#include <asm/ptrace.h> +#include <asm/bug.h> + +static bool riscv_v_implicit_uacc = IS_ENABLED(CONFIG_RISCV_ISA_V_DEFAULT_ENABLE); + +unsigned long riscv_v_vsize __read_mostly; +EXPORT_SYMBOL_GPL(riscv_v_vsize); + +int riscv_v_setup_vsize(void) +{ + unsigned long this_vsize; + + /* There are 32 vector registers with vlenb length. */ + riscv_v_enable(); + this_vsize = csr_read(CSR_VLENB) * 32; + riscv_v_disable(); + + if (!riscv_v_vsize) { + riscv_v_vsize = this_vsize; + return 0; + } + + if (riscv_v_vsize != this_vsize) { + WARN(1, "RISCV_ISA_V only supports one vlenb on SMP systems"); + return -EOPNOTSUPP; + } + + return 0; +} + +static bool insn_is_vector(u32 insn_buf) +{ + u32 opcode = insn_buf & __INSN_OPCODE_MASK; + u32 width, csr; + + /* + * All V-related instructions, including CSR operations are 4-Byte. So, + * do not handle if the instruction length is not 4-Byte. + */ + if (unlikely(GET_INSN_LENGTH(insn_buf) != 4)) + return false; + + switch (opcode) { + case RVV_OPCODE_VECTOR: + return true; + case RVV_OPCODE_VL: + case RVV_OPCODE_VS: + width = RVV_EXRACT_VL_VS_WIDTH(insn_buf); + if (width == RVV_VL_VS_WIDTH_8 || width == RVV_VL_VS_WIDTH_16 || + width == RVV_VL_VS_WIDTH_32 || width == RVV_VL_VS_WIDTH_64) + return true; + + break; + case RVG_OPCODE_SYSTEM: + csr = RVG_EXTRACT_SYSTEM_CSR(insn_buf); + if ((csr >= CSR_VSTART && csr <= CSR_VCSR) || + (csr >= CSR_VL && csr <= CSR_VLENB)) + return true; + } + + return false; +} + +static int riscv_v_thread_zalloc(void) +{ + void *datap; + + datap = kzalloc(riscv_v_vsize, GFP_KERNEL); + if (!datap) + return -ENOMEM; + + current->thread.vstate.datap = datap; + memset(¤t->thread.vstate, 0, offsetof(struct __riscv_v_ext_state, + datap)); + return 0; +} + +#define VSTATE_CTRL_GET_CUR(x) ((x) & PR_RISCV_V_VSTATE_CTRL_CUR_MASK) +#define VSTATE_CTRL_GET_NEXT(x) (((x) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) >> 2) +#define VSTATE_CTRL_MAKE_NEXT(x) (((x) << 2) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) +#define VSTATE_CTRL_GET_INHERIT(x) (!!((x) & PR_RISCV_V_VSTATE_CTRL_INHERIT)) +static inline int riscv_v_ctrl_get_cur(struct task_struct *tsk) +{ + return VSTATE_CTRL_GET_CUR(tsk->thread.vstate_ctrl); +} + +static inline int riscv_v_ctrl_get_next(struct task_struct *tsk) +{ + return VSTATE_CTRL_GET_NEXT(tsk->thread.vstate_ctrl); +} + +static inline bool riscv_v_ctrl_test_inherit(struct task_struct *tsk) +{ + return VSTATE_CTRL_GET_INHERIT(tsk->thread.vstate_ctrl); +} + +static inline void riscv_v_ctrl_set(struct task_struct *tsk, int cur, int nxt, + bool inherit) +{ + unsigned long ctrl; + + ctrl = cur & PR_RISCV_V_VSTATE_CTRL_CUR_MASK; + ctrl |= VSTATE_CTRL_MAKE_NEXT(nxt); + if (inherit) + ctrl |= PR_RISCV_V_VSTATE_CTRL_INHERIT; + tsk->thread.vstate_ctrl = ctrl; +} + +bool riscv_v_vstate_ctrl_user_allowed(void) +{ + return riscv_v_ctrl_get_cur(current) == PR_RISCV_V_VSTATE_CTRL_ON; +} +EXPORT_SYMBOL_GPL(riscv_v_vstate_ctrl_user_allowed); + +bool riscv_v_first_use_handler(struct pt_regs *regs) +{ + u32 __user *epc = (u32 __user *)regs->epc; + u32 insn = (u32)regs->badaddr; + + /* Do not handle if V is not supported, or disabled */ + if (!(ELF_HWCAP & COMPAT_HWCAP_ISA_V)) + return false; + + /* If V has been enabled then it is not the first-use trap */ + if (riscv_v_vstate_query(regs)) + return false; + + /* Get the instruction */ + if (!insn) { + if (__get_user(insn, epc)) + return false; + } + + /* Filter out non-V instructions */ + if (!insn_is_vector(insn)) + return false; + + /* Sanity check. datap should be null by the time of the first-use trap */ + WARN_ON(current->thread.vstate.datap); + + /* + * Now we sure that this is a V instruction. And it executes in the + * context where VS has been off. So, try to allocate the user's V + * context and resume execution. + */ + if (riscv_v_thread_zalloc()) { + force_sig(SIGBUS); + return true; + } + riscv_v_vstate_on(regs); + return true; +} + +void riscv_v_vstate_ctrl_init(struct task_struct *tsk) +{ + bool inherit; + int cur, next; + + if (!has_vector()) + return; + + next = riscv_v_ctrl_get_next(tsk); + if (!next) { + if (READ_ONCE(riscv_v_implicit_uacc)) + cur = PR_RISCV_V_VSTATE_CTRL_ON; + else + cur = PR_RISCV_V_VSTATE_CTRL_OFF; + } else { + cur = next; + } + /* Clear next mask if inherit-bit is not set */ + inherit = riscv_v_ctrl_test_inherit(tsk); + if (!inherit) + next = PR_RISCV_V_VSTATE_CTRL_DEFAULT; + + riscv_v_ctrl_set(tsk, cur, next, inherit); +} + +long riscv_v_vstate_ctrl_get_current(void) +{ + if (!has_vector()) + return -EINVAL; + + return current->thread.vstate_ctrl & PR_RISCV_V_VSTATE_CTRL_MASK; +} + +long riscv_v_vstate_ctrl_set_current(unsigned long arg) +{ + bool inherit; + int cur, next; + + if (!has_vector()) + return -EINVAL; + + if (arg & ~PR_RISCV_V_VSTATE_CTRL_MASK) + return -EINVAL; + + cur = VSTATE_CTRL_GET_CUR(arg); + switch (cur) { + case PR_RISCV_V_VSTATE_CTRL_OFF: + /* Do not allow user to turn off V if current is not off */ + if (riscv_v_ctrl_get_cur(current) != PR_RISCV_V_VSTATE_CTRL_OFF) + return -EPERM; + + break; + case PR_RISCV_V_VSTATE_CTRL_ON: + break; + case PR_RISCV_V_VSTATE_CTRL_DEFAULT: + cur = riscv_v_ctrl_get_cur(current); + break; + default: + return -EINVAL; + } + + next = VSTATE_CTRL_GET_NEXT(arg); + inherit = VSTATE_CTRL_GET_INHERIT(arg); + switch (next) { + case PR_RISCV_V_VSTATE_CTRL_DEFAULT: + case PR_RISCV_V_VSTATE_CTRL_OFF: + case PR_RISCV_V_VSTATE_CTRL_ON: + riscv_v_ctrl_set(current, cur, next, inherit); + return 0; + } + + return -EINVAL; +} + +#ifdef CONFIG_SYSCTL + +static struct ctl_table riscv_v_default_vstate_table[] = { + { + .procname = "riscv_v_default_allow", + .data = &riscv_v_implicit_uacc, + .maxlen = sizeof(riscv_v_implicit_uacc), + .mode = 0644, + .proc_handler = proc_dobool, + }, + { } +}; + +static int __init riscv_v_sysctl_init(void) +{ + if (has_vector()) + if (!register_sysctl("abi", riscv_v_default_vstate_table)) + return -EINVAL; + return 0; +} + +#else /* ! CONFIG_SYSCTL */ +static int __init riscv_v_sysctl_init(void) { return 0; } +#endif /* ! CONFIG_SYSCTL */ + +static int riscv_v_init(void) +{ + return riscv_v_sysctl_init(); +} +core_initcall(riscv_v_init); diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 8031b8912a0d..7b4c21f9aa6a 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -17,6 +17,7 @@ kvm-y += mmu.o kvm-y += vcpu.o kvm-y += vcpu_exit.o kvm-y += vcpu_fp.o +kvm-y += vcpu_vector.o kvm-y += vcpu_insn.o kvm-y += vcpu_switch.o kvm-y += vcpu_sbi.o diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 8bd9f2a8a0b9..de24127e7e93 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -22,6 +22,8 @@ #include <asm/cacheflush.h> #include <asm/hwcap.h> #include <asm/sbi.h> +#include <asm/vector.h> +#include <asm/kvm_vcpu_vector.h> const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), @@ -57,6 +59,7 @@ static const unsigned long kvm_isa_ext_arr[] = { [KVM_RISCV_ISA_EXT_H] = RISCV_ISA_EXT_h, [KVM_RISCV_ISA_EXT_I] = RISCV_ISA_EXT_i, [KVM_RISCV_ISA_EXT_M] = RISCV_ISA_EXT_m, + [KVM_RISCV_ISA_EXT_V] = RISCV_ISA_EXT_v, KVM_ISA_EXT_ARR(SSAIA), KVM_ISA_EXT_ARR(SSTC), @@ -85,6 +88,8 @@ static bool kvm_riscv_vcpu_isa_enable_allowed(unsigned long ext) switch (ext) { case KVM_RISCV_ISA_EXT_H: return false; + case KVM_RISCV_ISA_EXT_V: + return riscv_v_vstate_ctrl_user_allowed(); default: break; } @@ -138,6 +143,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) kvm_riscv_vcpu_fp_reset(vcpu); + kvm_riscv_vcpu_vector_reset(vcpu); + kvm_riscv_vcpu_timer_reset(vcpu); kvm_riscv_vcpu_aia_reset(vcpu); @@ -198,6 +205,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) cntx->hstatus |= HSTATUS_SPVP; cntx->hstatus |= HSTATUS_SPV; + if (kvm_riscv_vcpu_alloc_vector_context(vcpu, cntx)) + return -ENOMEM; + /* By default, make CY, TM, and IR counters accessible in VU mode */ reset_csr->scounteren = 0x7; @@ -241,6 +251,9 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) /* Free unused pages pre-allocated for G-stage page table mappings */ kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); + + /* Free vector context space for host and guest kernel */ + kvm_riscv_vcpu_free_vector_context(vcpu); } int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) @@ -679,6 +692,9 @@ static int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu, return kvm_riscv_vcpu_set_reg_isa_ext(vcpu, reg); case KVM_REG_RISCV_SBI_EXT: return kvm_riscv_vcpu_set_reg_sbi_ext(vcpu, reg); + case KVM_REG_RISCV_VECTOR: + return kvm_riscv_vcpu_set_reg_vector(vcpu, reg, + KVM_REG_RISCV_VECTOR); default: break; } @@ -708,6 +724,9 @@ static int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu, return kvm_riscv_vcpu_get_reg_isa_ext(vcpu, reg); case KVM_REG_RISCV_SBI_EXT: return kvm_riscv_vcpu_get_reg_sbi_ext(vcpu, reg); + case KVM_REG_RISCV_VECTOR: + return kvm_riscv_vcpu_get_reg_vector(vcpu, reg, + KVM_REG_RISCV_VECTOR); default: break; } @@ -1002,6 +1021,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_riscv_vcpu_host_fp_save(&vcpu->arch.host_context); kvm_riscv_vcpu_guest_fp_restore(&vcpu->arch.guest_context, vcpu->arch.isa); + kvm_riscv_vcpu_host_vector_save(&vcpu->arch.host_context); + kvm_riscv_vcpu_guest_vector_restore(&vcpu->arch.guest_context, + vcpu->arch.isa); kvm_riscv_vcpu_aia_load(vcpu, cpu); @@ -1021,6 +1043,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) kvm_riscv_vcpu_host_fp_restore(&vcpu->arch.host_context); kvm_riscv_vcpu_timer_save(vcpu); + kvm_riscv_vcpu_guest_vector_save(&vcpu->arch.guest_context, + vcpu->arch.isa); + kvm_riscv_vcpu_host_vector_restore(&vcpu->arch.host_context); csr->vsstatus = csr_read(CSR_VSSTATUS); csr->vsie = csr_read(CSR_VSIE); diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c new file mode 100644 index 000000000000..edd2eecbddc2 --- /dev/null +++ b/arch/riscv/kvm/vcpu_vector.c @@ -0,0 +1,186 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022 SiFive + * + * Authors: + * Vincent Chen <vincent.chen@sifive.com> + * Greentime Hu <greentime.hu@sifive.com> + */ + +#include <linux/errno.h> +#include <linux/err.h> +#include <linux/kvm_host.h> +#include <linux/uaccess.h> +#include <asm/hwcap.h> +#include <asm/kvm_vcpu_vector.h> +#include <asm/vector.h> + +#ifdef CONFIG_RISCV_ISA_V +void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu) +{ + unsigned long *isa = vcpu->arch.isa; + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + + cntx->sstatus &= ~SR_VS; + if (riscv_isa_extension_available(isa, v)) { + cntx->sstatus |= SR_VS_INITIAL; + WARN_ON(!cntx->vector.datap); + memset(cntx->vector.datap, 0, riscv_v_vsize); + } else { + cntx->sstatus |= SR_VS_OFF; + } +} + +static void kvm_riscv_vcpu_vector_clean(struct kvm_cpu_context *cntx) +{ + cntx->sstatus &= ~SR_VS; + cntx->sstatus |= SR_VS_CLEAN; +} + +void kvm_riscv_vcpu_guest_vector_save(struct kvm_cpu_context *cntx, + unsigned long *isa) +{ + if ((cntx->sstatus & SR_VS) == SR_VS_DIRTY) { + if (riscv_isa_extension_available(isa, v)) + __kvm_riscv_vector_save(cntx); + kvm_riscv_vcpu_vector_clean(cntx); + } +} + +void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx, + unsigned long *isa) +{ + if ((cntx->sstatus & SR_VS) != SR_VS_OFF) { + if (riscv_isa_extension_available(isa, v)) + __kvm_riscv_vector_restore(cntx); + kvm_riscv_vcpu_vector_clean(cntx); + } +} + +void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx) +{ + /* No need to check host sstatus as it can be modified outside */ + if (riscv_isa_extension_available(NULL, v)) + __kvm_riscv_vector_save(cntx); +} + +void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx) +{ + if (riscv_isa_extension_available(NULL, v)) + __kvm_riscv_vector_restore(cntx); +} + +int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu, + struct kvm_cpu_context *cntx) +{ + cntx->vector.datap = kmalloc(riscv_v_vsize, GFP_KERNEL); + if (!cntx->vector.datap) + return -ENOMEM; + + vcpu->arch.host_context.vector.datap = kzalloc(riscv_v_vsize, GFP_KERNEL); + if (!vcpu->arch.host_context.vector.datap) + return -ENOMEM; + + return 0; +} + +void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu) +{ + kfree(vcpu->arch.guest_reset_context.vector.datap); + kfree(vcpu->arch.host_context.vector.datap); +} +#endif + +static void *kvm_riscv_vcpu_vreg_addr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + size_t reg_size) +{ + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + void *reg_val; + size_t vlenb = riscv_v_vsize / 32; + + if (reg_num < KVM_REG_RISCV_VECTOR_REG(0)) { + if (reg_size != sizeof(unsigned long)) + return NULL; + switch (reg_num) { + case KVM_REG_RISCV_VECTOR_CSR_REG(vstart): + reg_val = &cntx->vector.vstart; + break; + case KVM_REG_RISCV_VECTOR_CSR_REG(vl): + reg_val = &cntx->vector.vl; + break; + case KVM_REG_RISCV_VECTOR_CSR_REG(vtype): + reg_val = &cntx->vector.vtype; + break; + case KVM_REG_RISCV_VECTOR_CSR_REG(vcsr): + reg_val = &cntx->vector.vcsr; + break; + case KVM_REG_RISCV_VECTOR_CSR_REG(datap): + default: + return NULL; + } + } else if (reg_num <= KVM_REG_RISCV_VECTOR_REG(31)) { + if (reg_size != vlenb) + return NULL; + reg_val = cntx->vector.datap + + (reg_num - KVM_REG_RISCV_VECTOR_REG(0)) * vlenb; + } else { + return NULL; + } + + return reg_val; +} + +int kvm_riscv_vcpu_get_reg_vector(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg, + unsigned long rtype) +{ + unsigned long *isa = vcpu->arch.isa; + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + rtype); + void *reg_val = NULL; + size_t reg_size = KVM_REG_SIZE(reg->id); + + if (rtype == KVM_REG_RISCV_VECTOR && + riscv_isa_extension_available(isa, v)) { + reg_val = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size); + } + + if (!reg_val) + return -EINVAL; + + if (copy_to_user(uaddr, reg_val, reg_size)) + return -EFAULT; + + return 0; +} + +int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg, + unsigned long rtype) +{ + unsigned long *isa = vcpu->arch.isa; + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + rtype); + void *reg_val = NULL; + size_t reg_size = KVM_REG_SIZE(reg->id); + + if (rtype == KVM_REG_RISCV_VECTOR && + riscv_isa_extension_available(isa, v)) { + reg_val = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size); + } + + if (!reg_val) + return -EINVAL; + + if (copy_from_user(reg_val, uaddr, reg_size)) + return -EFAULT; + + return 0; +} diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile index b85e9e82f082..9c454f90fd3d 100644 --- a/arch/riscv/mm/Makefile +++ b/arch/riscv/mm/Makefile @@ -13,8 +13,7 @@ endif KCOV_INSTRUMENT_init.o := n obj-y += init.o -obj-y += extable.o -obj-$(CONFIG_MMU) += fault.o pageattr.o +obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o obj-y += cacheflush.o obj-y += context.o obj-y += pgtable.o diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 35a84ec69a9f..6ea2cce4cc17 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -247,24 +247,12 @@ void handle_page_fault(struct pt_regs *regs) * only copy the information from the master page table, * nothing more. */ - if (unlikely((addr >= VMALLOC_START) && (addr < VMALLOC_END))) { + if ((!IS_ENABLED(CONFIG_MMU) || !IS_ENABLED(CONFIG_64BIT)) && + unlikely(addr >= VMALLOC_START && addr < VMALLOC_END)) { vmalloc_fault(regs, code, addr); return; } -#ifdef CONFIG_64BIT - /* - * Modules in 64bit kernels lie in their own virtual region which is not - * in the vmalloc region, but dealing with page faults in this region - * or the vmalloc region amounts to doing the same thing: checking that - * the mapping exists in init_mm.pgd and updating user page table, so - * just use vmalloc_fault. - */ - if (unlikely(addr >= MODULES_VADDR && addr < MODULES_END)) { - vmalloc_fault(regs, code, addr); - return; - } -#endif /* Enable interrupts if they were enabled in the parent context. */ if (!regs_irqs_disabled(regs)) local_irq_enable(); @@ -295,6 +283,36 @@ void handle_page_fault(struct pt_regs *regs) flags |= FAULT_FLAG_WRITE; else if (cause == EXC_INST_PAGE_FAULT) flags |= FAULT_FLAG_INSTRUCTION; +#ifdef CONFIG_PER_VMA_LOCK + if (!(flags & FAULT_FLAG_USER)) + goto lock_mmap; + + vma = lock_vma_under_rcu(mm, addr); + if (!vma) + goto lock_mmap; + + if (unlikely(access_error(cause, vma))) { + vma_end_read(vma); + goto lock_mmap; + } + + fault = handle_mm_fault(vma, addr, flags | FAULT_FLAG_VMA_LOCK, regs); + vma_end_read(vma); + + if (!(fault & VM_FAULT_RETRY)) { + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + goto done; + } + count_vm_vma_lock_event(VMA_LOCK_RETRY); + + if (fault_signal_pending(fault, regs)) { + if (!user_mode(regs)) + no_context(regs, addr); + return; + } +lock_mmap: +#endif /* CONFIG_PER_VMA_LOCK */ + retry: vma = lock_mm_and_find_vma(mm, addr, regs); if (unlikely(!vma)) { @@ -350,6 +368,9 @@ retry: mmap_read_unlock(mm); +#ifdef CONFIG_PER_VMA_LOCK +done: +#endif if (unlikely(fault & VM_FAULT_ERROR)) { tsk->thread.bad_cause = cause; mm_fault_error(regs, addr, fault); diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 4fa420faa780..3b1e927a06b7 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -1389,3 +1389,61 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, return vmemmap_populate_basepages(start, end, node, NULL); } #endif + +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) +/* + * Pre-allocates page-table pages for a specific area in the kernel + * page-table. Only the level which needs to be synchronized between + * all page-tables is allocated because the synchronization can be + * expensive. + */ +static void __init preallocate_pgd_pages_range(unsigned long start, unsigned long end, + const char *area) +{ + unsigned long addr; + const char *lvl; + + for (addr = start; addr < end && addr >= start; addr = ALIGN(addr + 1, PGDIR_SIZE)) { + pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + lvl = "p4d"; + p4d = p4d_alloc(&init_mm, pgd, addr); + if (!p4d) + goto failed; + + if (pgtable_l5_enabled) + continue; + + lvl = "pud"; + pud = pud_alloc(&init_mm, p4d, addr); + if (!pud) + goto failed; + + if (pgtable_l4_enabled) + continue; + + lvl = "pmd"; + pmd = pmd_alloc(&init_mm, pud, addr); + if (!pmd) + goto failed; + } + return; + +failed: + /* + * The pages have to be there now or they will be missing in + * process page-tables later. + */ + panic("Failed to pre-allocate %s pages for %s area\n", lvl, area); +} + +void __init pgtable_cache_init(void) +{ + preallocate_pgd_pages_range(VMALLOC_START, VMALLOC_END, "vmalloc"); + if (IS_ENABLED(CONFIG_MODULES)) + preallocate_pgd_pages_range(MODULES_VADDR, MODULES_END, "bpf/modules"); +} +#endif diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index feb36c0b9446..3fc5a0d54f6e 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -131,3 +131,5 @@ obj-y += dptf/ obj-$(CONFIG_ARM64) += arm64/ obj-$(CONFIG_ACPI_VIOT) += viot.o + +obj-$(CONFIG_RISCV) += riscv/ diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 3269a888fb7a..f725813d0cce 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -276,7 +276,7 @@ acpi_map_lookup_virt(void __iomem *virt, acpi_size size) return NULL; } -#if defined(CONFIG_IA64) || defined(CONFIG_ARM64) +#if defined(CONFIG_IA64) || defined(CONFIG_ARM64) || defined(CONFIG_RISCV) /* ioremap will take care of cache attributes */ #define should_use_kmap(pfn) 0 #else diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index 2ac48cda5b20..d6606a9f2da6 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -106,6 +106,32 @@ static int map_gicc_mpidr(struct acpi_subtable_header *entry, return -EINVAL; } +/* + * Retrieve the RISC-V hartid for the processor + */ +static int map_rintc_hartid(struct acpi_subtable_header *entry, + int device_declaration, u32 acpi_id, + phys_cpuid_t *hartid) +{ + struct acpi_madt_rintc *rintc = + container_of(entry, struct acpi_madt_rintc, header); + + if (!(rintc->flags & ACPI_MADT_ENABLED)) + return -ENODEV; + + /* device_declaration means Device object in DSDT, in the + * RISC-V, logical processors are required to + * have a Processor Device object in the DSDT, so we should + * check device_declaration here + */ + if (device_declaration && rintc->uid == acpi_id) { + *hartid = rintc->hart_id; + return 0; + } + + return -EINVAL; +} + static phys_cpuid_t map_madt_entry(struct acpi_table_madt *madt, int type, u32 acpi_id) { @@ -136,6 +162,9 @@ static phys_cpuid_t map_madt_entry(struct acpi_table_madt *madt, } else if (header->type == ACPI_MADT_TYPE_GENERIC_INTERRUPT) { if (!map_gicc_mpidr(header, type, acpi_id, &phys_id)) break; + } else if (header->type == ACPI_MADT_TYPE_RINTC) { + if (!map_rintc_hartid(header, type, acpi_id, &phys_id)) + break; } entry += header->length; } diff --git a/drivers/acpi/riscv/Makefile b/drivers/acpi/riscv/Makefile new file mode 100644 index 000000000000..8b3b126e0b94 --- /dev/null +++ b/drivers/acpi/riscv/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-y += rhct.o diff --git a/drivers/acpi/riscv/rhct.c b/drivers/acpi/riscv/rhct.c new file mode 100644 index 000000000000..b280b3e9c7d9 --- /dev/null +++ b/drivers/acpi/riscv/rhct.c @@ -0,0 +1,83 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2022-2023, Ventana Micro Systems Inc + * Author: Sunil V L <sunilvl@ventanamicro.com> + * + */ + +#define pr_fmt(fmt) "ACPI: RHCT: " fmt + +#include <linux/acpi.h> + +static struct acpi_table_header *acpi_get_rhct(void) +{ + static struct acpi_table_header *rhct; + acpi_status status; + + /* + * RHCT will be used at runtime on every CPU, so we + * don't need to call acpi_put_table() to release the table mapping. + */ + if (!rhct) { + status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct); + if (ACPI_FAILURE(status)) { + pr_warn_once("No RHCT table found\n"); + return NULL; + } + } + + return rhct; +} + +/* + * During early boot, the caller should call acpi_get_table() and pass its pointer to + * these functions(and free up later). At run time, since this table can be used + * multiple times, NULL may be passed in order to use the cached table. + */ +int acpi_get_riscv_isa(struct acpi_table_header *table, unsigned int cpu, const char **isa) +{ + struct acpi_rhct_node_header *node, *ref_node, *end; + u32 size_hdr = sizeof(struct acpi_rhct_node_header); + u32 size_hartinfo = sizeof(struct acpi_rhct_hart_info); + struct acpi_rhct_hart_info *hart_info; + struct acpi_rhct_isa_string *isa_node; + struct acpi_table_rhct *rhct; + u32 *hart_info_node_offset; + u32 acpi_cpu_id = get_acpi_id_for_cpu(cpu); + + BUG_ON(acpi_disabled); + + if (!table) { + rhct = (struct acpi_table_rhct *)acpi_get_rhct(); + if (!rhct) + return -ENOENT; + } else { + rhct = (struct acpi_table_rhct *)table; + } + + end = ACPI_ADD_PTR(struct acpi_rhct_node_header, rhct, rhct->header.length); + + for (node = ACPI_ADD_PTR(struct acpi_rhct_node_header, rhct, rhct->node_offset); + node < end; + node = ACPI_ADD_PTR(struct acpi_rhct_node_header, node, node->length)) { + if (node->type == ACPI_RHCT_NODE_TYPE_HART_INFO) { + hart_info = ACPI_ADD_PTR(struct acpi_rhct_hart_info, node, size_hdr); + hart_info_node_offset = ACPI_ADD_PTR(u32, hart_info, size_hartinfo); + if (acpi_cpu_id != hart_info->uid) + continue; + + for (int i = 0; i < hart_info->num_offsets; i++) { + ref_node = ACPI_ADD_PTR(struct acpi_rhct_node_header, + rhct, hart_info_node_offset[i]); + if (ref_node->type == ACPI_RHCT_NODE_TYPE_ISA_STRING) { + isa_node = ACPI_ADD_PTR(struct acpi_rhct_isa_string, + ref_node, size_hdr); + *isa = isa_node->isa; + return 0; + } + } + } + } + + return -1; +} diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index 7b4680da57d7..8ab0a82b4da4 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -220,6 +220,16 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) } break; + case ACPI_MADT_TYPE_RINTC: + { + struct acpi_madt_rintc *p = (struct acpi_madt_rintc *)header; + + pr_debug("RISC-V INTC (acpi_uid[0x%04x] hart_id[0x%llx] %s)\n", + p->uid, p->hart_id, + (p->flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled"); + } + break; + default: pr_warn("Found unsupported MADT entry (type = 0x%x)\n", header->type); diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c index 5f0f10c7e222..da3071b387eb 100644 --- a/drivers/clocksource/timer-riscv.c +++ b/drivers/clocksource/timer-riscv.c @@ -10,6 +10,7 @@ #define pr_fmt(fmt) "riscv-timer: " fmt +#include <linux/acpi.h> #include <linux/clocksource.h> #include <linux/clockchips.h> #include <linux/cpu.h> @@ -124,61 +125,28 @@ static irqreturn_t riscv_timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static int __init riscv_timer_init_dt(struct device_node *n) +static int __init riscv_timer_init_common(void) { - int cpuid, error; - unsigned long hartid; - struct device_node *child; + int error; struct irq_domain *domain; + struct fwnode_handle *intc_fwnode = riscv_get_intc_hwnode(); - error = riscv_of_processor_hartid(n, &hartid); - if (error < 0) { - pr_warn("Not valid hartid for node [%pOF] error = [%lu]\n", - n, hartid); - return error; - } - - cpuid = riscv_hartid_to_cpuid(hartid); - if (cpuid < 0) { - pr_warn("Invalid cpuid for hartid [%lu]\n", hartid); - return cpuid; - } - - if (cpuid != smp_processor_id()) - return 0; - - child = of_find_compatible_node(NULL, NULL, "riscv,timer"); - if (child) { - riscv_timer_cannot_wake_cpu = of_property_read_bool(child, - "riscv,timer-cannot-wake-cpu"); - of_node_put(child); - } - - domain = NULL; - child = of_get_compatible_child(n, "riscv,cpu-intc"); - if (!child) { - pr_err("Failed to find INTC node [%pOF]\n", n); - return -ENODEV; - } - domain = irq_find_host(child); - of_node_put(child); + domain = irq_find_matching_fwnode(intc_fwnode, DOMAIN_BUS_ANY); if (!domain) { - pr_err("Failed to find IRQ domain for node [%pOF]\n", n); + pr_err("Failed to find irq_domain for INTC node [%pfwP]\n", + intc_fwnode); return -ENODEV; } riscv_clock_event_irq = irq_create_mapping(domain, RV_IRQ_TIMER); if (!riscv_clock_event_irq) { - pr_err("Failed to map timer interrupt for node [%pOF]\n", n); + pr_err("Failed to map timer interrupt for node [%pfwP]\n", intc_fwnode); return -ENODEV; } - pr_info("%s: Registering clocksource cpuid [%d] hartid [%lu]\n", - __func__, cpuid, hartid); error = clocksource_register_hz(&riscv_clocksource, riscv_timebase); if (error) { - pr_err("RISCV timer register failed [%d] for cpu = [%d]\n", - error, cpuid); + pr_err("RISCV timer registration failed [%d]\n", error); return error; } @@ -207,4 +175,46 @@ static int __init riscv_timer_init_dt(struct device_node *n) return error; } +static int __init riscv_timer_init_dt(struct device_node *n) +{ + int cpuid, error; + unsigned long hartid; + struct device_node *child; + + error = riscv_of_processor_hartid(n, &hartid); + if (error < 0) { + pr_warn("Invalid hartid for node [%pOF] error = [%lu]\n", + n, hartid); + return error; + } + + cpuid = riscv_hartid_to_cpuid(hartid); + if (cpuid < 0) { + pr_warn("Invalid cpuid for hartid [%lu]\n", hartid); + return cpuid; + } + + if (cpuid != smp_processor_id()) + return 0; + + child = of_find_compatible_node(NULL, NULL, "riscv,timer"); + if (child) { + riscv_timer_cannot_wake_cpu = of_property_read_bool(child, + "riscv,timer-cannot-wake-cpu"); + of_node_put(child); + } + + return riscv_timer_init_common(); +} + TIMER_OF_DECLARE(riscv_timer, "riscv", riscv_timer_init_dt); + +#ifdef CONFIG_ACPI +static int __init riscv_timer_acpi_init(struct acpi_table_header *table) +{ + return riscv_timer_init_common(); +} + +TIMER_ACPI_DECLARE(aclint_mtimer, ACPI_SIG_RHCT, riscv_timer_acpi_init); + +#endif diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index ad0c042b5e66..edc6fd44e7ca 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -610,7 +610,10 @@ EXPORT_SYMBOL_GPL(hisi_qm_wait_mb_ready); static void qm_mb_write(struct hisi_qm *qm, const void *src) { void __iomem *fun_base = qm->io_base + QM_MB_CMD_SEND_BASE; + +#if IS_ENABLED(CONFIG_ARM64) unsigned long tmp0 = 0, tmp1 = 0; +#endif if (!IS_ENABLED(CONFIG_ARM64)) { memcpy_toio(fun_base, src, 16); @@ -618,6 +621,7 @@ static void qm_mb_write(struct hisi_qm *qm, const void *src) return; } +#if IS_ENABLED(CONFIG_ARM64) asm volatile("ldp %0, %1, %3\n" "stp %0, %1, %2\n" "dmb oshst\n" @@ -626,6 +630,7 @@ static void qm_mb_write(struct hisi_qm *qm, const void *src) "+Q" (*((char __iomem *)fun_base)) : "Q" (*((char *)src)) : "memory"); +#endif } static int qm_mb_nolock(struct hisi_qm *qm, struct qm_mailbox *mailbox) diff --git a/drivers/irqchip/irq-riscv-intc.c b/drivers/irqchip/irq-riscv-intc.c index f229e3e66387..4adeee1bc391 100644 --- a/drivers/irqchip/irq-riscv-intc.c +++ b/drivers/irqchip/irq-riscv-intc.c @@ -6,6 +6,7 @@ */ #define pr_fmt(fmt) "riscv-intc: " fmt +#include <linux/acpi.h> #include <linux/atomic.h> #include <linux/bits.h> #include <linux/cpu.h> @@ -112,6 +113,30 @@ static struct fwnode_handle *riscv_intc_hwnode(void) return intc_domain->fwnode; } +static int __init riscv_intc_init_common(struct fwnode_handle *fn) +{ + int rc; + + intc_domain = irq_domain_create_linear(fn, BITS_PER_LONG, + &riscv_intc_domain_ops, NULL); + if (!intc_domain) { + pr_err("unable to add IRQ domain\n"); + return -ENXIO; + } + + rc = set_handle_irq(&riscv_intc_irq); + if (rc) { + pr_err("failed to set irq handler\n"); + return rc; + } + + riscv_set_intc_hwnode_fn(riscv_intc_hwnode); + + pr_info("%d local interrupts mapped\n", BITS_PER_LONG); + + return 0; +} + static int __init riscv_intc_init(struct device_node *node, struct device_node *parent) { @@ -133,24 +158,39 @@ static int __init riscv_intc_init(struct device_node *node, if (riscv_hartid_to_cpuid(hartid) != smp_processor_id()) return 0; - intc_domain = irq_domain_add_linear(node, BITS_PER_LONG, - &riscv_intc_domain_ops, NULL); - if (!intc_domain) { - pr_err("unable to add IRQ domain\n"); - return -ENXIO; - } + return riscv_intc_init_common(of_node_to_fwnode(node)); +} - rc = set_handle_irq(&riscv_intc_irq); - if (rc) { - pr_err("failed to set irq handler\n"); - return rc; - } +IRQCHIP_DECLARE(riscv, "riscv,cpu-intc", riscv_intc_init); - riscv_set_intc_hwnode_fn(riscv_intc_hwnode); +#ifdef CONFIG_ACPI - pr_info("%d local interrupts mapped\n", BITS_PER_LONG); +static int __init riscv_intc_acpi_init(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct fwnode_handle *fn; + struct acpi_madt_rintc *rintc; - return 0; + rintc = (struct acpi_madt_rintc *)header; + + /* + * The ACPI MADT will have one INTC for each CPU (or HART) + * so riscv_intc_acpi_init() function will be called once + * for each INTC. We only do INTC initialization + * for the INTC belonging to the boot CPU (or boot HART). + */ + if (riscv_hartid_to_cpuid(rintc->hart_id) != smp_processor_id()) + return 0; + + fn = irq_domain_alloc_named_fwnode("RISCV-INTC"); + if (!fn) { + pr_err("unable to allocate INTC FW node\n"); + return -ENOMEM; + } + + return riscv_intc_init_common(fn); } -IRQCHIP_DECLARE(riscv, "riscv,cpu-intc", riscv_intc_init); +IRQCHIP_ACPI_DECLARE(riscv_intc, ACPI_MADT_TYPE_RINTC, NULL, + ACPI_MADT_RINTC_VERSION_V1, riscv_intc_acpi_init); +#endif diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 4f3ac296b3e2..4163ff517471 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -739,7 +739,6 @@ static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu, struct platform_device *pde { int ret; struct cpu_hw_events __percpu *hw_events = pmu->hw_events; - struct device_node *cpu, *child; struct irq_domain *domain = NULL; if (riscv_isa_extension_available(NULL, SSCOFPMF)) { @@ -756,20 +755,8 @@ static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu, struct platform_device *pde if (!riscv_pmu_use_irq) return -EOPNOTSUPP; - for_each_of_cpu_node(cpu) { - child = of_get_compatible_child(cpu, "riscv,cpu-intc"); - if (!child) { - pr_err("Failed to find INTC node\n"); - of_node_put(cpu); - return -ENODEV; - } - domain = irq_find_host(child); - of_node_put(child); - if (domain) { - of_node_put(cpu); - break; - } - } + domain = irq_find_matching_fwnode(riscv_get_intc_hwnode(), + DOMAIN_BUS_ANY); if (!domain) { pr_err("Failed to find INTC IRQ root domain\n"); return -ENODEV; @@ -868,6 +855,12 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) goto out_free; } + /* It is possible to get from SBI more than max number of counters */ + if (num_counters > RISCV_MAX_COUNTERS) { + num_counters = RISCV_MAX_COUNTERS; + pr_info("SBI returned more than maximum number of counters. Limiting the number of counters to %d\n", num_counters); + } + /* cache all the information about counters now */ if (pmu_sbi_get_ctrinfo(num_counters, &cmask)) goto out_free; diff --git a/drivers/platform/surface/aggregator/Kconfig b/drivers/platform/surface/aggregator/Kconfig index c114f9dd5fe1..88afc38ffdc5 100644 --- a/drivers/platform/surface/aggregator/Kconfig +++ b/drivers/platform/surface/aggregator/Kconfig @@ -4,7 +4,7 @@ menuconfig SURFACE_AGGREGATOR tristate "Microsoft Surface System Aggregator Module Subsystem and Drivers" depends on SERIAL_DEV_BUS - depends on ACPI + depends on ACPI && !RISCV select CRC_CCITT help The Surface System Aggregator Module (Surface SAM or SSAM) is an diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index e0e159138331..0c8cf359ea5b 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -443,6 +443,7 @@ typedef struct elf64_shdr { #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ #define NT_MIPS_FP_MODE 0x801 /* MIPS floating-point mode */ #define NT_MIPS_MSA 0x802 /* MIPS SIMD registers */ +#define NT_RISCV_VECTOR 0x900 /* RISC-V vector registers */ #define NT_LOONGARCH_CPUCFG 0xa00 /* LoongArch CPU config registers */ #define NT_LOONGARCH_CSR 0xa01 /* LoongArch control and status registers */ #define NT_LOONGARCH_LSX 0xa02 /* LoongArch Loongson SIMD Extension registers */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index f23d9a16507f..3c36aeade991 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -294,4 +294,15 @@ struct prctl_mm_map { #define PR_SET_MEMORY_MERGE 67 #define PR_GET_MEMORY_MERGE 68 + +#define PR_RISCV_V_SET_CONTROL 69 +#define PR_RISCV_V_GET_CONTROL 70 +# define PR_RISCV_V_VSTATE_CTRL_DEFAULT 0 +# define PR_RISCV_V_VSTATE_CTRL_OFF 1 +# define PR_RISCV_V_VSTATE_CTRL_ON 2 +# define PR_RISCV_V_VSTATE_CTRL_INHERIT (1 << 4) +# define PR_RISCV_V_VSTATE_CTRL_CUR_MASK 0x3 +# define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK 0xc +# define PR_RISCV_V_VSTATE_CTRL_MASK 0x1f + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sys.c b/kernel/sys.c index 339fee3eff6a..05f838929e72 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -140,6 +140,12 @@ #ifndef GET_TAGGED_ADDR_CTRL # define GET_TAGGED_ADDR_CTRL() (-EINVAL) #endif +#ifndef RISCV_V_SET_CONTROL +# define RISCV_V_SET_CONTROL(a) (-EINVAL) +#endif +#ifndef RISCV_V_GET_CONTROL +# define RISCV_V_GET_CONTROL() (-EINVAL) +#endif /* * this is where the system-wide overflow UID and GID are defined, for @@ -2708,6 +2714,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = !!test_bit(MMF_VM_MERGE_ANY, &me->mm->flags); break; #endif + case PR_RISCV_V_SET_CONTROL: + error = RISCV_V_SET_CONTROL(arg2); + break; + case PR_RISCV_V_GET_CONTROL: + error = RISCV_V_GET_CONTROL(); + break; default: error = -EINVAL; break; diff --git a/tools/testing/selftests/riscv/Makefile b/tools/testing/selftests/riscv/Makefile index 32a72902d045..9dd629cc86aa 100644 --- a/tools/testing/selftests/riscv/Makefile +++ b/tools/testing/selftests/riscv/Makefile @@ -5,7 +5,7 @@ ARCH ?= $(shell uname -m 2>/dev/null || echo not) ifneq (,$(filter $(ARCH),riscv)) -RISCV_SUBTARGETS ?= hwprobe +RISCV_SUBTARGETS ?= hwprobe vector else RISCV_SUBTARGETS := endif diff --git a/tools/testing/selftests/riscv/hwprobe/.gitignore b/tools/testing/selftests/riscv/hwprobe/.gitignore new file mode 100644 index 000000000000..8113dc3bdd03 --- /dev/null +++ b/tools/testing/selftests/riscv/hwprobe/.gitignore @@ -0,0 +1 @@ +hwprobe diff --git a/tools/testing/selftests/riscv/vector/.gitignore b/tools/testing/selftests/riscv/vector/.gitignore new file mode 100644 index 000000000000..4f2b4e8a3b08 --- /dev/null +++ b/tools/testing/selftests/riscv/vector/.gitignore @@ -0,0 +1,2 @@ +vstate_exec_nolibc +vstate_prctl diff --git a/tools/testing/selftests/riscv/vector/Makefile b/tools/testing/selftests/riscv/vector/Makefile new file mode 100644 index 000000000000..cd6e80bf995d --- /dev/null +++ b/tools/testing/selftests/riscv/vector/Makefile @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2021 ARM Limited +# Originally tools/testing/arm64/abi/Makefile + +TEST_GEN_PROGS := vstate_prctl +TEST_GEN_PROGS_EXTENDED := vstate_exec_nolibc + +include ../../lib.mk + +$(OUTPUT)/vstate_prctl: vstate_prctl.c ../hwprobe/sys_hwprobe.S + $(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^ + +$(OUTPUT)/vstate_exec_nolibc: vstate_exec_nolibc.c + $(CC) -nostdlib -static -include ../../../../include/nolibc/nolibc.h \ + -Wall $(CFLAGS) $(LDFLAGS) $^ -o $@ -lgcc diff --git a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c new file mode 100644 index 000000000000..5cbc392944a6 --- /dev/null +++ b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <sys/prctl.h> + +#define THIS_PROGRAM "./vstate_exec_nolibc" + +int main(int argc, char **argv) +{ + int rc, pid, status, test_inherit = 0; + long ctrl, ctrl_c; + char *exec_argv[2], *exec_envp[2]; + + if (argc > 1) + test_inherit = 1; + + ctrl = my_syscall1(__NR_prctl, PR_RISCV_V_GET_CONTROL); + if (ctrl < 0) { + puts("PR_RISCV_V_GET_CONTROL is not supported\n"); + return ctrl; + } + + if (test_inherit) { + pid = fork(); + if (pid == -1) { + puts("fork failed\n"); + exit(-1); + } + + /* child */ + if (!pid) { + exec_argv[0] = THIS_PROGRAM; + exec_argv[1] = NULL; + exec_envp[0] = NULL; + exec_envp[1] = NULL; + /* launch the program again to check inherit */ + rc = execve(THIS_PROGRAM, exec_argv, exec_envp); + if (rc) { + puts("child execve failed\n"); + exit(-1); + } + } + + } else { + pid = fork(); + if (pid == -1) { + puts("fork failed\n"); + exit(-1); + } + + if (!pid) { + rc = my_syscall1(__NR_prctl, PR_RISCV_V_GET_CONTROL); + if (rc != ctrl) { + puts("child's vstate_ctrl not equal to parent's\n"); + exit(-1); + } + asm volatile (".option push\n\t" + ".option arch, +v\n\t" + "vsetvli x0, x0, e32, m8, ta, ma\n\t" + ".option pop\n\t" + ); + exit(ctrl); + } + } + + rc = waitpid(-1, &status, 0); + + if (WIFEXITED(status) && WEXITSTATUS(status) == -1) { + puts("child exited abnormally\n"); + exit(-1); + } + + if (WIFSIGNALED(status)) { + if (WTERMSIG(status) != SIGILL) { + puts("child was terminated by unexpected signal\n"); + exit(-1); + } + + if ((ctrl & PR_RISCV_V_VSTATE_CTRL_CUR_MASK) != PR_RISCV_V_VSTATE_CTRL_OFF) { + puts("child signaled by illegal V access but vstate_ctrl is not off\n"); + exit(-1); + } + + /* child terminated, and its vstate_ctrl is off */ + exit(ctrl); + } + + ctrl_c = WEXITSTATUS(status); + if (test_inherit) { + if (ctrl & PR_RISCV_V_VSTATE_CTRL_INHERIT) { + if (!(ctrl_c & PR_RISCV_V_VSTATE_CTRL_INHERIT)) { + puts("parent has inherit bit, but child has not\n"); + exit(-1); + } + } + rc = (ctrl & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) >> 2; + if (rc != PR_RISCV_V_VSTATE_CTRL_DEFAULT) { + if (rc != (ctrl_c & PR_RISCV_V_VSTATE_CTRL_CUR_MASK)) { + puts("parent's next setting does not equal to child's\n"); + exit(-1); + } + + if (!(ctrl & PR_RISCV_V_VSTATE_CTRL_INHERIT)) { + if ((ctrl_c & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) != + PR_RISCV_V_VSTATE_CTRL_DEFAULT) { + puts("must clear child's next vstate_ctrl if !inherit\n"); + exit(-1); + } + } + } + } + return ctrl; +} diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c new file mode 100644 index 000000000000..b348b475be57 --- /dev/null +++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c @@ -0,0 +1,189 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <sys/prctl.h> +#include <unistd.h> +#include <asm/hwprobe.h> +#include <errno.h> +#include <sys/wait.h> + +#include "../../kselftest.h" + +/* + * Rather than relying on having a new enough libc to define this, just do it + * ourselves. This way we don't need to be coupled to a new-enough libc to + * contain the call. + */ +long riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpu_count, unsigned long *cpus, unsigned int flags); + +#define NEXT_PROGRAM "./vstate_exec_nolibc" +static int launch_test(int test_inherit) +{ + char *exec_argv[3], *exec_envp[1]; + int rc, pid, status; + + pid = fork(); + if (pid < 0) { + ksft_test_result_fail("fork failed %d", pid); + return -1; + } + + if (!pid) { + exec_argv[0] = NEXT_PROGRAM; + exec_argv[1] = test_inherit != 0 ? "x" : NULL; + exec_argv[2] = NULL; + exec_envp[0] = NULL; + /* launch the program again to check inherit */ + rc = execve(NEXT_PROGRAM, exec_argv, exec_envp); + if (rc) { + perror("execve"); + ksft_test_result_fail("child execve failed %d\n", rc); + exit(-1); + } + } + + rc = waitpid(-1, &status, 0); + if (rc < 0) { + ksft_test_result_fail("waitpid failed\n"); + return -3; + } + + if ((WIFEXITED(status) && WEXITSTATUS(status) == -1) || + WIFSIGNALED(status)) { + ksft_test_result_fail("child exited abnormally\n"); + return -4; + } + + return WEXITSTATUS(status); +} + +int test_and_compare_child(long provided, long expected, int inherit) +{ + int rc; + + rc = prctl(PR_RISCV_V_SET_CONTROL, provided); + if (rc != 0) { + ksft_test_result_fail("prctl with provided arg %lx failed with code %d\n", + provided, rc); + return -1; + } + rc = launch_test(inherit); + if (rc != expected) { + ksft_test_result_fail("Test failed, check %d != %d\n", rc, + expected); + return -2; + } + return 0; +} + +#define PR_RISCV_V_VSTATE_CTRL_CUR_SHIFT 0 +#define PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT 2 + +int main(void) +{ + struct riscv_hwprobe pair; + long flag, expected; + long rc; + + pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0; + rc = riscv_hwprobe(&pair, 1, 0, NULL, 0); + if (rc < 0) { + ksft_test_result_fail("hwprobe() failed with %d\n", rc); + return -1; + } + + if (pair.key != RISCV_HWPROBE_KEY_IMA_EXT_0) { + ksft_test_result_fail("hwprobe cannot probe RISCV_HWPROBE_KEY_IMA_EXT_0\n"); + return -2; + } + + if (!(pair.value & RISCV_HWPROBE_IMA_V)) { + rc = prctl(PR_RISCV_V_GET_CONTROL); + if (rc != -1 || errno != EINVAL) { + ksft_test_result_fail("GET_CONTROL should fail on kernel/hw without V\n"); + return -3; + } + + rc = prctl(PR_RISCV_V_SET_CONTROL, PR_RISCV_V_VSTATE_CTRL_ON); + if (rc != -1 || errno != EINVAL) { + ksft_test_result_fail("GET_CONTROL should fail on kernel/hw without V\n"); + return -4; + } + + ksft_test_result_skip("Vector not supported\n"); + return 0; + } + + flag = PR_RISCV_V_VSTATE_CTRL_ON; + rc = prctl(PR_RISCV_V_SET_CONTROL, flag); + if (rc != 0) { + ksft_test_result_fail("Enabling V for current should always success\n"); + return -5; + } + + flag = PR_RISCV_V_VSTATE_CTRL_OFF; + rc = prctl(PR_RISCV_V_SET_CONTROL, flag); + if (rc != -1 || errno != EPERM) { + ksft_test_result_fail("Disabling current's V alive must fail with EPERM(%d)\n", + errno); + return -5; + } + + /* Turn on next's vector explicitly and test */ + flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; + if (test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_ON, 0)) + return -6; + + /* Turn off next's vector explicitly and test */ + flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; + if (test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_OFF, 0)) + return -7; + + /* Turn on next's vector explicitly and test inherit */ + flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; + flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; + expected = flag | PR_RISCV_V_VSTATE_CTRL_ON; + if (test_and_compare_child(flag, expected, 0)) + return -8; + + if (test_and_compare_child(flag, expected, 1)) + return -9; + + /* Turn off next's vector explicitly and test inherit */ + flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; + flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; + expected = flag | PR_RISCV_V_VSTATE_CTRL_OFF; + if (test_and_compare_child(flag, expected, 0)) + return -10; + + if (test_and_compare_child(flag, expected, 1)) + return -11; + + /* arguments should fail with EINVAL */ + rc = prctl(PR_RISCV_V_SET_CONTROL, 0xff0); + if (rc != -1 || errno != EINVAL) { + ksft_test_result_fail("Undefined control argument should return EINVAL\n"); + return -12; + } + + rc = prctl(PR_RISCV_V_SET_CONTROL, 0x3); + if (rc != -1 || errno != EINVAL) { + ksft_test_result_fail("Undefined control argument should return EINVAL\n"); + return -12; + } + + rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc); + if (rc != -1 || errno != EINVAL) { + ksft_test_result_fail("Undefined control argument should return EINVAL\n"); + return -12; + } + + rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc); + if (rc != -1 || errno != EINVAL) { + ksft_test_result_fail("Undefined control argument should return EINVAL\n"); + return -12; + } + + ksft_test_result_pass("tests for riscv_v_vstate_ctrl pass\n"); + ksft_exit_pass(); + return 0; +} |