diff options
Diffstat (limited to 'arch/arm64')
26 files changed, 154 insertions, 105 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 7d95663c0160..07d1811aa03f 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -32,6 +32,7 @@ config ARM64 select GENERIC_CLOCKEVENTS_BROADCAST select GENERIC_CPU_AUTOPROBE select GENERIC_EARLY_IOREMAP + select GENERIC_IDLE_POLL_SETUP select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL @@ -331,6 +332,22 @@ config ARM64_ERRATUM_845719 If unsure, say Y. +config ARM64_ERRATUM_843419 + bool "Cortex-A53: 843419: A load or store might access an incorrect address" + depends on MODULES + default y + help + This option builds kernel modules using the large memory model in + order to avoid the use of the ADRP instruction, which can cause + a subsequent memory access to use an incorrect address on Cortex-A53 + parts up to r0p4. + + Note that the kernel itself must be linked with a version of ld + which fixes potentially affected ADRP instructions through the + use of veneers. + + If unsure, say Y. + endmenu diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 15ff5b4156fd..d10b5d483022 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -41,6 +41,10 @@ endif CHECKFLAGS += -D__aarch64__ +ifeq ($(CONFIG_ARM64_ERRATUM_843419), y) +KBUILD_CFLAGS_MODULE += -mcmodel=large +endif + # Default value head-y := arch/arm64/kernel/head.o diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi index d18ee4259ee5..06a15644be38 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi @@ -81,7 +81,7 @@ }; idle-states { - entry-method = "arm,psci"; + entry-method = "psci"; CPU_SLEEP_0: cpu-sleep-0 { compatible = "arm,idle-state"; diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index a712bea3bf2c..cc093a482aa4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -106,7 +106,7 @@ }; idle-states { - entry-method = "arm,psci"; + entry-method = "psci"; cpu_sleep: cpu-sleep-0 { compatible = "arm,idle-state"; diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h index 2bb7009bdac7..a57601f9d17c 100644 --- a/arch/arm64/include/asm/hardirq.h +++ b/arch/arm64/include/asm/hardirq.h @@ -43,9 +43,4 @@ static inline void ack_bad_irq(unsigned int irq) irq_err_count++; } -/* - * No arch-specific IRQ flags. - */ -#define set_irq_flags(irq, flags) - #endif /* __ASM_HARDIRQ_H */ diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 7605e095217f..9694f2654593 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -95,6 +95,7 @@ SCTLR_EL2_SA | SCTLR_EL2_I) /* TCR_EL2 Registers bits */ +#define TCR_EL2_RES1 ((1 << 31) | (1 << 23)) #define TCR_EL2_TBI (1 << 20) #define TCR_EL2_PS (7 << 16) #define TCR_EL2_PS_40B (2 << 16) @@ -106,9 +107,10 @@ #define TCR_EL2_MASK (TCR_EL2_TG0 | TCR_EL2_SH0 | \ TCR_EL2_ORGN0 | TCR_EL2_IRGN0 | TCR_EL2_T0SZ) -#define TCR_EL2_FLAGS (TCR_EL2_PS_40B) +#define TCR_EL2_FLAGS (TCR_EL2_RES1 | TCR_EL2_PS_40B) /* VTCR_EL2 Registers bits */ +#define VTCR_EL2_RES1 (1 << 31) #define VTCR_EL2_PS_MASK (7 << 16) #define VTCR_EL2_TG0_MASK (1 << 14) #define VTCR_EL2_TG0_4K (0 << 14) @@ -147,7 +149,8 @@ */ #define VTCR_EL2_FLAGS (VTCR_EL2_TG0_64K | VTCR_EL2_SH0_INNER | \ VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \ - VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B) + VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B | \ + VTCR_EL2_RES1) #define VTTBR_X (38 - VTCR_EL2_T0SZ_40B) #else /* @@ -158,7 +161,8 @@ */ #define VTCR_EL2_FLAGS (VTCR_EL2_TG0_4K | VTCR_EL2_SH0_INNER | \ VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \ - VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B) + VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B | \ + VTCR_EL2_RES1) #define VTTBR_X (37 - VTCR_EL2_T0SZ_40B) #endif @@ -168,7 +172,6 @@ #define VTTBR_VMID_MASK (UL(0xFF) << VTTBR_VMID_SHIFT) /* Hyp System Trap Register */ -#define HSTR_EL2_TTEE (1 << 16) #define HSTR_EL2_T(x) (1 << x) /* Hyp Coproccessor Trap Register Shifts */ diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 67fa0de3d483..5e377101f919 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -53,9 +53,7 @@ #define IFSR32_EL2 25 /* Instruction Fault Status Register */ #define FPEXC32_EL2 26 /* Floating-Point Exception Control Register */ #define DBGVCR32_EL2 27 /* Debug Vector Catch Register */ -#define TEECR32_EL1 28 /* ThumbEE Configuration Register */ -#define TEEHBR32_EL1 29 /* ThumbEE Handler Base Register */ -#define NR_SYS_REGS 30 +#define NR_SYS_REGS 28 /* 32bit mapping */ #define c0_MPIDR (MPIDR_EL1 * 2) /* MultiProcessor ID Register */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 415938dc45cf..ed039688c221 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -30,19 +30,16 @@ #define __KVM_HAVE_ARCH_INTC_INITIALIZED -#if defined(CONFIG_KVM_ARM_MAX_VCPUS) -#define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS -#else -#define KVM_MAX_VCPUS 0 -#endif - #define KVM_USER_MEM_SLOTS 32 #define KVM_PRIVATE_MEM_SLOTS 4 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 +#define KVM_HALT_POLL_NS_DEFAULT 500000 #include <kvm/arm_vgic.h> #include <kvm/arm_arch_timer.h> +#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS + #define KVM_VCPU_MAX_FEATURES 3 int __attribute_const__ kvm_target_cpu(void); @@ -195,6 +192,7 @@ struct kvm_vm_stat { struct kvm_vcpu_stat { u32 halt_successful_poll; + u32 halt_attempted_poll; u32 halt_wakeup; }; diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 6900b2d95371..26b066690593 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -26,13 +26,9 @@ * Software defined PTE bits definition. */ #define PTE_VALID (_AT(pteval_t, 1) << 0) +#define PTE_WRITE (PTE_DBM) /* same as DBM (51) */ #define PTE_DIRTY (_AT(pteval_t, 1) << 55) #define PTE_SPECIAL (_AT(pteval_t, 1) << 56) -#ifdef CONFIG_ARM64_HW_AFDBM -#define PTE_WRITE (PTE_DBM) /* same as DBM */ -#else -#define PTE_WRITE (_AT(pteval_t, 1) << 57) -#endif #define PTE_PROT_NONE (_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */ /* @@ -83,7 +79,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY) #define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN) -#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN) +#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_PXN | PTE_UXN) #define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) #define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) #define PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) @@ -146,7 +142,7 @@ extern struct page *empty_zero_page; #define pte_exec(pte) (!(pte_val(pte) & PTE_UXN)) #ifdef CONFIG_ARM64_HW_AFDBM -#define pte_hw_dirty(pte) (!(pte_val(pte) & PTE_RDONLY)) +#define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY)) #else #define pte_hw_dirty(pte) (0) #endif @@ -238,7 +234,7 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr); * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via * the page fault mechanism. Checking the dirty status of a pte becomes: * - * PTE_DIRTY || !PTE_RDONLY + * PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY) */ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) @@ -500,10 +496,10 @@ static inline pud_t *pud_offset(pgd_t *pgd, unsigned long addr) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | - PTE_PROT_NONE | PTE_WRITE | PTE_TYPE_MASK; + PTE_PROT_NONE | PTE_VALID | PTE_WRITE; /* preserve the hardware dirty information */ if (pte_hw_dirty(pte)) - newprot |= PTE_DIRTY; + pte = pte_mkdirty(pte); pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); return pte; } diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 3bc498c250dc..41e58fe3c041 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -44,7 +44,7 @@ #define __ARM_NR_compat_cacheflush (__ARM_NR_COMPAT_BASE+2) #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE+5) -#define __NR_compat_syscalls 388 +#define __NR_compat_syscalls 390 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index cef934a90f17..5b925b761a2a 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -797,3 +797,12 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create) __SYSCALL(__NR_bpf, sys_bpf) #define __NR_execveat 387 __SYSCALL(__NR_execveat, compat_sys_execveat) +#define __NR_userfaultfd 388 +__SYSCALL(__NR_userfaultfd, sys_userfaultfd) +#define __NR_membarrier 389 +__SYSCALL(__NR_membarrier, sys_membarrier) + +/* + * Please add new compat syscalls above this comment and update + * __NR_compat_syscalls in asm/unistd.h. + */ diff --git a/arch/arm64/include/uapi/asm/signal.h b/arch/arm64/include/uapi/asm/signal.h index 8d1e7236431b..991bf5db2ca1 100644 --- a/arch/arm64/include/uapi/asm/signal.h +++ b/arch/arm64/include/uapi/asm/signal.h @@ -19,6 +19,9 @@ /* Required for AArch32 compatibility. */ #define SA_RESTORER 0x04000000 +#define MINSIGSTKSZ 5120 +#define SIGSTKSZ 16384 + #include <asm-generic/signal.h> #endif diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 9b3b62ac9c24..253021ef2769 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -134,7 +134,7 @@ static int os_lock_notify(struct notifier_block *self, unsigned long action, void *data) { int cpu = (unsigned long)data; - if (action == CPU_ONLINE) + if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE) smp_call_function_single(cpu, clear_os_lock, NULL, 1); return NOTIFY_OK; } @@ -201,7 +201,7 @@ void unregister_step_hook(struct step_hook *hook) } /* - * Call registered single step handers + * Call registered single step handlers * There is no Syndrome info to check for determining the handler. * So we call all the registered handlers, until the right handler is * found which returns zero. @@ -271,20 +271,21 @@ static int single_step_handler(unsigned long addr, unsigned int esr, * Use reader/writer locks instead of plain spinlock. */ static LIST_HEAD(break_hook); -static DEFINE_RWLOCK(break_hook_lock); +static DEFINE_SPINLOCK(break_hook_lock); void register_break_hook(struct break_hook *hook) { - write_lock(&break_hook_lock); - list_add(&hook->node, &break_hook); - write_unlock(&break_hook_lock); + spin_lock(&break_hook_lock); + list_add_rcu(&hook->node, &break_hook); + spin_unlock(&break_hook_lock); } void unregister_break_hook(struct break_hook *hook) { - write_lock(&break_hook_lock); - list_del(&hook->node); - write_unlock(&break_hook_lock); + spin_lock(&break_hook_lock); + list_del_rcu(&hook->node); + spin_unlock(&break_hook_lock); + synchronize_rcu(); } static int call_break_hook(struct pt_regs *regs, unsigned int esr) @@ -292,11 +293,11 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr) struct break_hook *hook; int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL; - read_lock(&break_hook_lock); - list_for_each_entry(hook, &break_hook, node) + rcu_read_lock(); + list_for_each_entry_rcu(hook, &break_hook, node) if ((esr & hook->esr_mask) == hook->esr_val) fn = hook->fn; - read_unlock(&break_hook_lock); + rcu_read_unlock(); return fn ? fn(regs, esr) : DBG_HOOK_ERROR; } diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index e8ca6eaedd02..13671a9cf016 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -258,7 +258,8 @@ static bool __init efi_virtmap_init(void) */ if (!is_normal_ram(md)) prot = __pgprot(PROT_DEVICE_nGnRE); - else if (md->type == EFI_RUNTIME_SERVICES_CODE) + else if (md->type == EFI_RUNTIME_SERVICES_CODE || + !PAGE_ALIGNED(md->phys_addr)) prot = PAGE_KERNEL_EXEC; else prot = PAGE_KERNEL; diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 08cafc518b9a..0f03a8fe2314 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -178,6 +178,24 @@ ENTRY(ftrace_stub) ENDPROC(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER + /* save return value regs*/ + .macro save_return_regs + sub sp, sp, #64 + stp x0, x1, [sp] + stp x2, x3, [sp, #16] + stp x4, x5, [sp, #32] + stp x6, x7, [sp, #48] + .endm + + /* restore return value regs*/ + .macro restore_return_regs + ldp x0, x1, [sp] + ldp x2, x3, [sp, #16] + ldp x4, x5, [sp, #32] + ldp x6, x7, [sp, #48] + add sp, sp, #64 + .endm + /* * void ftrace_graph_caller(void) * @@ -204,11 +222,11 @@ ENDPROC(ftrace_graph_caller) * only when CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST is enabled. */ ENTRY(return_to_handler) - str x0, [sp, #-16]! + save_return_regs mov x0, x29 // parent's fp bl ftrace_return_to_handler// addr = ftrace_return_to_hander(fp); mov x30, x0 // restore the original return address - ldr x0, [sp], #16 + restore_return_regs ret END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index a055be6125cf..90d09eddd5b2 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -523,6 +523,11 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems msr hstr_el2, xzr // Disable CP15 traps to EL2 #endif + /* EL2 debug */ + mrs x0, pmcr_el0 // Disable debug access traps + ubfx x0, x0, #11, #5 // to EL2 and allow access to + msr mdcr_el2, x0 // all PMU counters from EL1 + /* Stage-2 translation */ msr vttbr_el2, xzr diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index c97040ecf838..bba85c8f8037 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -872,7 +872,7 @@ static int hw_breakpoint_reset_notify(struct notifier_block *self, void *hcpu) { int cpu = (long)hcpu; - if (action == CPU_ONLINE) + if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE) smp_call_function_single(cpu, hw_breakpoint_reset, NULL, 1); return NOTIFY_OK; } diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index f341866aa810..c08b9ad6f429 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -85,7 +85,7 @@ bool aarch64_insn_is_branch_imm(u32 insn) aarch64_insn_is_bcond(insn)); } -static DEFINE_SPINLOCK(patch_lock); +static DEFINE_RAW_SPINLOCK(patch_lock); static void __kprobes *patch_map(void *addr, int fixmap) { @@ -131,13 +131,13 @@ static int __kprobes __aarch64_insn_write(void *addr, u32 insn) unsigned long flags = 0; int ret; - spin_lock_irqsave(&patch_lock, flags); + raw_spin_lock_irqsave(&patch_lock, flags); waddr = patch_map(addr, FIX_TEXT_POKE0); ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE); patch_unmap(FIX_TEXT_POKE0); - spin_unlock_irqrestore(&patch_lock, flags); + raw_spin_unlock_irqrestore(&patch_lock, flags); return ret; } diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 67bf4107f6ef..876eb8df50bf 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -332,12 +332,14 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 0, 21, AARCH64_INSN_IMM_ADR); break; +#ifndef CONFIG_ARM64_ERRATUM_843419 case R_AARCH64_ADR_PREL_PG_HI21_NC: overflow_check = false; case R_AARCH64_ADR_PREL_PG_HI21: ovf = reloc_insn_imm(RELOC_OP_PAGE, loc, val, 12, 21, AARCH64_INSN_IMM_ADR); break; +#endif case R_AARCH64_ADD_ABS_LO12_NC: case R_AARCH64_LDST8_ABS_LO12_NC: overflow_check = false; diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 6bab21f84a9f..232247945b1c 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -364,6 +364,8 @@ static void __init relocate_initrd(void) to_free = ram_end - orig_start; size = orig_end - orig_start; + if (!size) + return; /* initrd needs to be relocated completely inside linear mapping */ new_start = memblock_find_in_range(0, PFN_PHYS(max_pfn), diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 948f0ad2de23..71ef6dc89ae5 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -212,14 +212,32 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) /* * VFP save/restore code. + * + * We have to be careful with endianness, since the fpsimd context-switch + * code operates on 128-bit (Q) register values whereas the compat ABI + * uses an array of 64-bit (D) registers. Consequently, we need to swap + * the two halves of each Q register when running on a big-endian CPU. */ +union __fpsimd_vreg { + __uint128_t raw; + struct { +#ifdef __AARCH64EB__ + u64 hi; + u64 lo; +#else + u64 lo; + u64 hi; +#endif + }; +}; + static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame) { struct fpsimd_state *fpsimd = ¤t->thread.fpsimd_state; compat_ulong_t magic = VFP_MAGIC; compat_ulong_t size = VFP_STORAGE_SIZE; compat_ulong_t fpscr, fpexc; - int err = 0; + int i, err = 0; /* * Save the hardware registers to the fpsimd_state structure. @@ -235,10 +253,15 @@ static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame) /* * Now copy the FP registers. Since the registers are packed, * we can copy the prefix we want (V0-V15) as it is. - * FIXME: Won't work if big endian. */ - err |= __copy_to_user(&frame->ufp.fpregs, fpsimd->vregs, - sizeof(frame->ufp.fpregs)); + for (i = 0; i < ARRAY_SIZE(frame->ufp.fpregs); i += 2) { + union __fpsimd_vreg vreg = { + .raw = fpsimd->vregs[i >> 1], + }; + + __put_user_error(vreg.lo, &frame->ufp.fpregs[i], err); + __put_user_error(vreg.hi, &frame->ufp.fpregs[i + 1], err); + } /* Create an AArch32 fpscr from the fpsr and the fpcr. */ fpscr = (fpsimd->fpsr & VFP_FPSCR_STAT_MASK) | @@ -263,7 +286,7 @@ static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame) compat_ulong_t magic = VFP_MAGIC; compat_ulong_t size = VFP_STORAGE_SIZE; compat_ulong_t fpscr; - int err = 0; + int i, err = 0; __get_user_error(magic, &frame->magic, err); __get_user_error(size, &frame->size, err); @@ -273,12 +296,14 @@ static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame) if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE) return -EINVAL; - /* - * Copy the FP registers into the start of the fpsimd_state. - * FIXME: Won't work if big endian. - */ - err |= __copy_from_user(fpsimd.vregs, frame->ufp.fpregs, - sizeof(frame->ufp.fpregs)); + /* Copy the FP registers into the start of the fpsimd_state. */ + for (i = 0; i < ARRAY_SIZE(frame->ufp.fpregs); i += 2) { + union __fpsimd_vreg vreg; + + __get_user_error(vreg.lo, &frame->ufp.fpregs[i], err); + __get_user_error(vreg.hi, &frame->ufp.fpregs[i + 1], err); + fpsimd.vregs[i >> 1] = vreg.raw; + } /* Extract the fpsr and the fpcr from the fpscr */ __get_user_error(fpscr, &frame->ufp.fpscr, err); diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index bfffe8f4bd53..5c7e920e4861 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -41,15 +41,4 @@ config KVM_ARM_HOST ---help--- Provides host support for ARM processors. -config KVM_ARM_MAX_VCPUS - int "Number maximum supported virtual CPUs per VM" - depends on KVM_ARM_HOST - default 4 - help - Static number of max supported virtual CPUs per VM. - - If you choose a high number, the vcpu structures will be quite - large, so only choose a reasonable number that you expect to - actually use. - endif # VIRTUALIZATION diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 37c89ea2c572..e5836138ec42 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -433,20 +433,13 @@ mrs x5, ifsr32_el2 stp x4, x5, [x3] - skip_fpsimd_state x8, 3f + skip_fpsimd_state x8, 2f mrs x6, fpexc32_el2 str x6, [x3, #16] -3: - skip_debug_state x8, 2f +2: + skip_debug_state x8, 1f mrs x7, dbgvcr32_el2 str x7, [x3, #24] -2: - skip_tee_state x8, 1f - - add x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1) - mrs x4, teecr32_el1 - mrs x5, teehbr32_el1 - stp x4, x5, [x3] 1: .endm @@ -466,16 +459,9 @@ msr dacr32_el2, x4 msr ifsr32_el2, x5 - skip_debug_state x8, 2f + skip_debug_state x8, 1f ldr x7, [x3, #24] msr dbgvcr32_el2, x7 -2: - skip_tee_state x8, 1f - - add x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1) - ldp x4, x5, [x3] - msr teecr32_el1, x4 - msr teehbr32_el1, x5 1: .endm @@ -570,8 +556,6 @@ alternative_endif mrs x3, cntv_ctl_el0 and x3, x3, #3 str w3, [x0, #VCPU_TIMER_CNTV_CTL] - bic x3, x3, #1 // Clear Enable - msr cntv_ctl_el0, x3 isb @@ -579,6 +563,9 @@ alternative_endif str x3, [x0, #VCPU_TIMER_CNTV_CVAL] 1: + // Disable the virtual timer + msr cntv_ctl_el0, xzr + // Allow physical timer/counter access for the host mrs x2, cnthctl_el2 orr x2, x2, #3 @@ -753,6 +740,9 @@ ENTRY(__kvm_vcpu_run) // Guest context add x2, x0, #VCPU_CONTEXT + // We must restore the 32-bit state before the sysregs, thanks + // to Cortex-A57 erratum #852523. + restore_guest_32bit_state bl __restore_sysregs skip_debug_state x3, 1f @@ -760,7 +750,6 @@ ENTRY(__kvm_vcpu_run) kern_hyp_va x3 bl __restore_debug 1: - restore_guest_32bit_state restore_guest_regs // That's it, no more messing around. diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index b41607d270ac..d03d3af17e7e 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -272,7 +272,7 @@ static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, { __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; - if (copy_from_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) + if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; return 0; } @@ -314,7 +314,7 @@ static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, { __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; - if (copy_from_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) + if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; return 0; @@ -358,7 +358,7 @@ static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, { __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; - if (copy_from_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) + if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; return 0; } @@ -400,7 +400,7 @@ static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, { __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; - if (copy_from_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) + if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; return 0; } @@ -539,13 +539,6 @@ static const struct sys_reg_desc sys_reg_descs[] = { { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b110), trap_dbgauthstatus_el1 }, - /* TEECR32_EL1 */ - { Op0(0b10), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000), - NULL, reset_val, TEECR32_EL1, 0 }, - /* TEEHBR32_EL1 */ - { Op0(0b10), Op1(0b010), CRn(0b0001), CRm(0b0000), Op2(0b000), - NULL, reset_val, TEEHBR32_EL1, 0 }, - /* MDCCSR_EL1 */ { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0001), Op2(0b000), trap_raz_wi }, diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 0bcc4bc94b4a..99224dcebdc5 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -100,7 +100,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, if (IS_ENABLED(CONFIG_ZONE_DMA) && dev->coherent_dma_mask <= DMA_BIT_MASK(32)) flags |= GFP_DMA; - if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) { + if (dev_get_cma_area(dev) && (flags & __GFP_WAIT)) { struct page *page; void *addr; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index aba9ead1384c..9fadf6d7039b 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -287,6 +287,7 @@ retry: * starvation. */ mm_flags &= ~FAULT_FLAG_ALLOW_RETRY; + mm_flags |= FAULT_FLAG_TRIED; goto retry; } } |