diff options
Diffstat (limited to 'arch/arm64')
| -rw-r--r-- | arch/arm64/Kconfig.platforms | 2 | ||||
| -rw-r--r-- | arch/arm64/Makefile | 2 | ||||
| -rw-r--r-- | arch/arm64/include/asm/pgtable.h | 3 | ||||
| -rw-r--r-- | arch/arm64/include/asm/tlbflush.h | 3 | ||||
| -rw-r--r-- | arch/arm64/include/uapi/asm/kvm.h | 7 | ||||
| -rw-r--r-- | arch/arm64/include/uapi/asm/ptrace.h | 12 | ||||
| -rw-r--r-- | arch/arm64/include/uapi/asm/sigcontext.h | 14 | ||||
| -rw-r--r-- | arch/arm64/kernel/fpsimd.c | 42 | ||||
| -rw-r--r-- | arch/arm64/kernel/ssbd.c | 1 | ||||
| -rw-r--r-- | arch/arm64/kvm/guest.c | 65 |
10 files changed, 112 insertions, 39 deletions
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index c7ad684926c3..d07fc063c930 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -89,6 +89,7 @@ config ARCH_K3 bool "Texas Instruments Inc. K3 multicore SoC architecture" select PM_GENERIC_DOMAINS if PM select MAILBOX + select SOC_TI select TI_MESSAGE_MANAGER select TI_SCI_PROTOCOL select TI_SCI_INTR_IRQCHIP @@ -168,6 +169,7 @@ config ARCH_MXC select IMX_GPCV2_PM_DOMAINS select PM select PM_GENERIC_DOMAINS + select SOC_BUS help This enables support for the ARMv8 based SoCs in the NXP i.MX family. diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 8fbd583b18e1..e9d2e578cbe6 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -51,7 +51,7 @@ endif KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) $(brokengasinst) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -KBUILD_CFLAGS += -Wno-psabi +KBUILD_CFLAGS += $(call cc-disable-warning, psabi) KBUILD_AFLAGS += $(lseinstr) $(brokengasinst) KBUILD_CFLAGS += $(call cc-option,-mabi=lp64) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 2c41b04708fe..851c68dc6d61 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -812,8 +812,7 @@ extern int kern_addr_valid(unsigned long addr); #include <asm-generic/pgtable.h> -void pgd_cache_init(void); -#define pgtable_cache_init pgd_cache_init +static inline void pgtable_cache_init(void) { } /* * On AArch64, the cache coherency is handled via the set_pte_at() function. diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 3a1870228946..dff8f9ea5754 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -195,6 +195,9 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma, unsigned long asid = ASID(vma->vm_mm); unsigned long addr; + start = round_down(start, stride); + end = round_up(end, stride); + if ((end - start) >= (MAX_TLBI_OPS * stride)) { flush_tlb_mm(vma->vm_mm); return; diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 7b7ac0f6cec9..d819a3e8b552 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -260,6 +260,13 @@ struct kvm_vcpu_events { KVM_REG_SIZE_U256 | \ ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1))) +/* + * Register values for KVM_REG_ARM64_SVE_ZREG(), KVM_REG_ARM64_SVE_PREG() and + * KVM_REG_ARM64_SVE_FFR() are represented in memory in an endianness- + * invariant layout which differs from the layout used for the FPSIMD + * V-registers on big-endian systems: see sigcontext.h for more explanation. + */ + #define KVM_ARM64_SVE_VQ_MIN __SVE_VQ_MIN #define KVM_ARM64_SVE_VQ_MAX __SVE_VQ_MAX diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index d78623acb649..e932284993d4 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -65,8 +65,6 @@ #ifndef __ASSEMBLY__ -#include <linux/prctl.h> - /* * User structures for general purpose, floating point and debug registers. */ @@ -113,10 +111,10 @@ struct user_sve_header { /* * Common SVE_PT_* flags: - * These must be kept in sync with prctl interface in <linux/ptrace.h> + * These must be kept in sync with prctl interface in <linux/prctl.h> */ -#define SVE_PT_VL_INHERIT (PR_SVE_VL_INHERIT >> 16) -#define SVE_PT_VL_ONEXEC (PR_SVE_SET_VL_ONEXEC >> 16) +#define SVE_PT_VL_INHERIT ((1 << 17) /* PR_SVE_VL_INHERIT */ >> 16) +#define SVE_PT_VL_ONEXEC ((1 << 18) /* PR_SVE_SET_VL_ONEXEC */ >> 16) /* @@ -176,6 +174,10 @@ struct user_sve_header { * FPCR uint32_t FPCR * * Additional data might be appended in the future. + * + * The Z-, P- and FFR registers are represented in memory in an endianness- + * invariant layout which differs from the layout used for the FPSIMD + * V-registers on big-endian systems: see sigcontext.h for more explanation. */ #define SVE_PT_SVE_ZREG_SIZE(vq) __SVE_ZREG_SIZE(vq) diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index 5f3c0cec5af9..3d448a0bb225 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -77,6 +77,15 @@ struct fpsimd_context { __uint128_t vregs[32]; }; +/* + * Note: similarly to all other integer fields, each V-register is stored in an + * endianness-dependent format, with the byte at offset i from the start of the + * in-memory representation of the register value containing + * + * bits [(7 + 8 * i) : (8 * i)] of the register on little-endian hosts; or + * bits [(127 - 8 * i) : (120 - 8 * i)] on big-endian hosts. + */ + /* ESR_EL1 context */ #define ESR_MAGIC 0x45535201 @@ -204,6 +213,11 @@ struct sve_context { * FFR uint16_t[vq] first-fault status register * * Additional data might be appended in the future. + * + * Unlike vregs[] in fpsimd_context, each SVE scalable register (Z-, P- or FFR) + * is encoded in memory in an endianness-invariant format, with the byte at + * offset i from the start of the in-memory representation containing bits + * [(7 + 8 * i) : (8 * i)] of the register value. */ #define SVE_SIG_ZREG_SIZE(vq) __SVE_ZREG_SIZE(vq) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index a38bf74bcca8..bb42cd04baec 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -39,6 +39,7 @@ #include <linux/slab.h> #include <linux/stddef.h> #include <linux/sysctl.h> +#include <linux/swab.h> #include <asm/esr.h> #include <asm/fpsimd.h> @@ -352,6 +353,23 @@ static int __init sve_sysctl_init(void) { return 0; } #define ZREG(sve_state, vq, n) ((char *)(sve_state) + \ (SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET)) +#ifdef CONFIG_CPU_BIG_ENDIAN +static __uint128_t arm64_cpu_to_le128(__uint128_t x) +{ + u64 a = swab64(x); + u64 b = swab64(x >> 64); + + return ((__uint128_t)a << 64) | b; +} +#else +static __uint128_t arm64_cpu_to_le128(__uint128_t x) +{ + return x; +} +#endif + +#define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x) + /* * Transfer the FPSIMD state in task->thread.uw.fpsimd_state to * task->thread.sve_state. @@ -369,14 +387,16 @@ static void fpsimd_to_sve(struct task_struct *task) void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; unsigned int i; + __uint128_t *p; if (!system_supports_sve()) return; vq = sve_vq_from_vl(task->thread.sve_vl); - for (i = 0; i < 32; ++i) - memcpy(ZREG(sst, vq, i), &fst->vregs[i], - sizeof(fst->vregs[i])); + for (i = 0; i < 32; ++i) { + p = (__uint128_t *)ZREG(sst, vq, i); + *p = arm64_cpu_to_le128(fst->vregs[i]); + } } /* @@ -395,14 +415,16 @@ static void sve_to_fpsimd(struct task_struct *task) void const *sst = task->thread.sve_state; struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state; unsigned int i; + __uint128_t const *p; if (!system_supports_sve()) return; vq = sve_vq_from_vl(task->thread.sve_vl); - for (i = 0; i < 32; ++i) - memcpy(&fst->vregs[i], ZREG(sst, vq, i), - sizeof(fst->vregs[i])); + for (i = 0; i < 32; ++i) { + p = (__uint128_t const *)ZREG(sst, vq, i); + fst->vregs[i] = arm64_le128_to_cpu(*p); + } } #ifdef CONFIG_ARM64_SVE @@ -491,6 +513,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; unsigned int i; + __uint128_t *p; if (!test_tsk_thread_flag(task, TIF_SVE)) return; @@ -499,9 +522,10 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) memset(sst, 0, SVE_SIG_REGS_SIZE(vq)); - for (i = 0; i < 32; ++i) - memcpy(ZREG(sst, vq, i), &fst->vregs[i], - sizeof(fst->vregs[i])); + for (i = 0; i < 32; ++i) { + p = (__uint128_t *)ZREG(sst, vq, i); + *p = arm64_cpu_to_le128(fst->vregs[i]); + } } int sve_set_vector_length(struct task_struct *task, diff --git a/arch/arm64/kernel/ssbd.c b/arch/arm64/kernel/ssbd.c index 885f13e58708..52cfc6148355 100644 --- a/arch/arm64/kernel/ssbd.c +++ b/arch/arm64/kernel/ssbd.c @@ -5,6 +5,7 @@ #include <linux/compat.h> #include <linux/errno.h> +#include <linux/prctl.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/thread_info.h> diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 3ae2f82fca46..c8aa00179363 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -70,10 +70,8 @@ static u64 core_reg_offset_from_id(u64 id) return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE); } -static int validate_core_offset(const struct kvm_vcpu *vcpu, - const struct kvm_one_reg *reg) +static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off) { - u64 off = core_reg_offset_from_id(reg->id); int size; switch (off) { @@ -103,8 +101,7 @@ static int validate_core_offset(const struct kvm_vcpu *vcpu, return -EINVAL; } - if (KVM_REG_SIZE(reg->id) != size || - !IS_ALIGNED(off, size / sizeof(__u32))) + if (!IS_ALIGNED(off, size / sizeof(__u32))) return -EINVAL; /* @@ -115,6 +112,21 @@ static int validate_core_offset(const struct kvm_vcpu *vcpu, if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(off)) return -EINVAL; + return size; +} + +static int validate_core_offset(const struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + u64 off = core_reg_offset_from_id(reg->id); + int size = core_reg_size_from_offset(vcpu, off); + + if (size < 0) + return -EINVAL; + + if (KVM_REG_SIZE(reg->id) != size) + return -EINVAL; + return 0; } @@ -207,13 +219,7 @@ out: #define vq_word(vq) (((vq) - SVE_VQ_MIN) / 64) #define vq_mask(vq) ((u64)1 << ((vq) - SVE_VQ_MIN) % 64) - -static bool vq_present( - const u64 (*const vqs)[KVM_ARM64_SVE_VLS_WORDS], - unsigned int vq) -{ - return (*vqs)[vq_word(vq)] & vq_mask(vq); -} +#define vq_present(vqs, vq) ((vqs)[vq_word(vq)] & vq_mask(vq)) static int get_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { @@ -258,7 +264,7 @@ static int set_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) max_vq = 0; for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; ++vq) - if (vq_present(&vqs, vq)) + if (vq_present(vqs, vq)) max_vq = vq; if (max_vq > sve_vq_from_vl(kvm_sve_max_vl)) @@ -272,7 +278,7 @@ static int set_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) * maximum: */ for (vq = SVE_VQ_MIN; vq <= max_vq; ++vq) - if (vq_present(&vqs, vq) != sve_vq_available(vq)) + if (vq_present(vqs, vq) != sve_vq_available(vq)) return -EINVAL; /* Can't run with no vector lengths at all: */ @@ -453,19 +459,34 @@ static int copy_core_reg_indices(const struct kvm_vcpu *vcpu, { unsigned int i; int n = 0; - const u64 core_reg = KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE; for (i = 0; i < sizeof(struct kvm_regs) / sizeof(__u32); i++) { - /* - * The KVM_REG_ARM64_SVE regs must be used instead of - * KVM_REG_ARM_CORE for accessing the FPSIMD V-registers on - * SVE-enabled vcpus: - */ - if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(i)) + u64 reg = KVM_REG_ARM64 | KVM_REG_ARM_CORE | i; + int size = core_reg_size_from_offset(vcpu, i); + + if (size < 0) + continue; + + switch (size) { + case sizeof(__u32): + reg |= KVM_REG_SIZE_U32; + break; + + case sizeof(__u64): + reg |= KVM_REG_SIZE_U64; + break; + + case sizeof(__uint128_t): + reg |= KVM_REG_SIZE_U128; + break; + + default: + WARN_ON(1); continue; + } if (uindices) { - if (put_user(core_reg | i, uindices)) + if (put_user(reg, uindices)) return -EFAULT; uindices++; } |