diff options
Diffstat (limited to 'arch')
107 files changed, 685 insertions, 426 deletions
diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c index 8452753efebe..31927d2fe297 100644 --- a/arch/arm/boot/compressed/atags_to_fdt.c +++ b/arch/arm/boot/compressed/atags_to_fdt.c @@ -15,7 +15,8 @@ static int node_offset(void *fdt, const char *node_path) { int offset = fdt_path_offset(fdt, node_path); if (offset == -FDT_ERR_NOTFOUND) - offset = fdt_add_subnode(fdt, 0, node_path); + /* Add the node to root if not found, dropping the leading '/' */ + offset = fdt_add_subnode(fdt, 0, node_path + 1); return offset; } diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 60e901cd0de6..5a957a9a0984 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -371,7 +371,7 @@ static int __init xen_guest_init(void) } gnttab_init(); if (!xen_initial_domain()) - xenbus_probe(NULL); + xenbus_probe(); /* * Making sure board specific code will not set up ops for diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 05e17351e4f3..f39568b28ec1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -174,8 +174,6 @@ config ARM64 select HAVE_NMI select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS - select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI && HW_PERF_EVENTS - select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 015ddffaf6ca..b56a4b2bc248 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -17,7 +17,7 @@ #include <asm/lse.h> #define ATOMIC_OP(op) \ -static inline void arch_##op(int i, atomic_t *v) \ +static __always_inline void arch_##op(int i, atomic_t *v) \ { \ __lse_ll_sc_body(op, i, v); \ } @@ -32,7 +32,7 @@ ATOMIC_OP(atomic_sub) #undef ATOMIC_OP #define ATOMIC_FETCH_OP(name, op) \ -static inline int arch_##op##name(int i, atomic_t *v) \ +static __always_inline int arch_##op##name(int i, atomic_t *v) \ { \ return __lse_ll_sc_body(op##name, i, v); \ } @@ -56,7 +56,7 @@ ATOMIC_FETCH_OPS(atomic_sub_return) #undef ATOMIC_FETCH_OPS #define ATOMIC64_OP(op) \ -static inline void arch_##op(long i, atomic64_t *v) \ +static __always_inline void arch_##op(long i, atomic64_t *v) \ { \ __lse_ll_sc_body(op, i, v); \ } @@ -71,7 +71,7 @@ ATOMIC64_OP(atomic64_sub) #undef ATOMIC64_OP #define ATOMIC64_FETCH_OP(name, op) \ -static inline long arch_##op##name(long i, atomic64_t *v) \ +static __always_inline long arch_##op##name(long i, atomic64_t *v) \ { \ return __lse_ll_sc_body(op##name, i, v); \ } @@ -94,7 +94,7 @@ ATOMIC64_FETCH_OPS(atomic64_sub_return) #undef ATOMIC64_FETCH_OP #undef ATOMIC64_FETCH_OPS -static inline long arch_atomic64_dec_if_positive(atomic64_t *v) +static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v) { return __lse_ll_sc_body(atomic64_dec_if_positive, v); } diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 18fce223b67b..99d7e1494aaa 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -247,9 +247,11 @@ static inline const void *__tag_set(const void *addr, u8 tag) /* - * The linear kernel range starts at the bottom of the virtual address space. + * Check whether an arbitrary address is within the linear map, which + * lives in the [PAGE_OFFSET, PAGE_END) interval at the bottom of the + * kernel's TTBR1 address range. */ -#define __is_lm_address(addr) (((u64)(addr) & ~PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET)) +#define __is_lm_address(addr) (((u64)(addr) ^ PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET)) #define __lm_to_phys(addr) (((addr) & ~PAGE_OFFSET) + PHYS_OFFSET) #define __kimg_to_phys(addr) ((addr) - kimage_voffset) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 69ad25fbeae4..ca2cd75d3286 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -94,8 +94,7 @@ #endif /* CONFIG_ARM64_FORCE_52BIT */ extern phys_addr_t arm64_dma_phys_limit; -extern phys_addr_t arm64_dma32_phys_limit; -#define ARCH_LOW_ADDRESS_LIMIT ((arm64_dma_phys_limit ? : arm64_dma32_phys_limit) - 1) +#define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1) struct debug_info { #ifdef CONFIG_HAVE_HW_BREAKPOINT diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index f42fd9e33981..301784463587 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -75,7 +75,7 @@ int main(void) DEFINE(S_SDEI_TTBR1, offsetof(struct pt_regs, sdei_ttbr1)); DEFINE(S_PMR_SAVE, offsetof(struct pt_regs, pmr_save)); DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe)); - DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); + DEFINE(PT_REGS_SIZE, sizeof(struct pt_regs)); BLANK(); #ifdef CONFIG_COMPAT DEFINE(COMPAT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0)); diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index a338f40e64d3..b3e4f9a088b1 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -35,7 +35,7 @@ */ .macro ftrace_regs_entry, allregs=0 /* Make room for pt_regs, plus a callee frame */ - sub sp, sp, #(S_FRAME_SIZE + 16) + sub sp, sp, #(PT_REGS_SIZE + 16) /* Save function arguments (and x9 for simplicity) */ stp x0, x1, [sp, #S_X0] @@ -61,15 +61,15 @@ .endif /* Save the callsite's SP and LR */ - add x10, sp, #(S_FRAME_SIZE + 16) + add x10, sp, #(PT_REGS_SIZE + 16) stp x9, x10, [sp, #S_LR] /* Save the PC after the ftrace callsite */ str x30, [sp, #S_PC] /* Create a frame record for the callsite above pt_regs */ - stp x29, x9, [sp, #S_FRAME_SIZE] - add x29, sp, #S_FRAME_SIZE + stp x29, x9, [sp, #PT_REGS_SIZE] + add x29, sp, #PT_REGS_SIZE /* Create our frame record within pt_regs. */ stp x29, x30, [sp, #S_STACKFRAME] @@ -120,7 +120,7 @@ ftrace_common_return: ldr x9, [sp, #S_PC] /* Restore the callsite's SP */ - add sp, sp, #S_FRAME_SIZE + 16 + add sp, sp, #PT_REGS_SIZE + 16 ret x9 SYM_CODE_END(ftrace_common) @@ -130,7 +130,7 @@ SYM_CODE_START(ftrace_graph_caller) ldr x0, [sp, #S_PC] sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn) add x1, sp, #S_LR // parent_ip (callsite's LR) - ldr x2, [sp, #S_FRAME_SIZE] // parent fp (callsite's FP) + ldr x2, [sp, #PT_REGS_SIZE] // parent fp (callsite's FP) bl prepare_ftrace_return b ftrace_common_return SYM_CODE_END(ftrace_graph_caller) diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index a8c3e7aaca74..c9bae73f2621 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -75,7 +75,7 @@ alternative_else_nop_endif .endif #endif - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE #ifdef CONFIG_VMAP_STACK /* * Test whether the SP has overflowed, without corrupting a GPR. @@ -96,7 +96,7 @@ alternative_else_nop_endif * userspace, and can clobber EL0 registers to free up GPRs. */ - /* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */ + /* Stash the original SP (minus PT_REGS_SIZE) in tpidr_el0. */ msr tpidr_el0, x0 /* Recover the original x0 value and stash it in tpidrro_el0 */ @@ -253,7 +253,7 @@ alternative_else_nop_endif scs_load tsk, x20 .else - add x21, sp, #S_FRAME_SIZE + add x21, sp, #PT_REGS_SIZE get_current_task tsk .endif /* \el == 0 */ mrs x22, elr_el1 @@ -377,7 +377,7 @@ alternative_else_nop_endif ldp x26, x27, [sp, #16 * 13] ldp x28, x29, [sp, #16 * 14] ldr lr, [sp, #S_LR] - add sp, sp, #S_FRAME_SIZE // restore sp + add sp, sp, #PT_REGS_SIZE // restore sp .if \el == 0 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 @@ -580,12 +580,12 @@ __bad_stack: /* * Store the original GPRs to the new stack. The orginal SP (minus - * S_FRAME_SIZE) was stashed in tpidr_el0 by kernel_ventry. + * PT_REGS_SIZE) was stashed in tpidr_el0 by kernel_ventry. */ - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE kernel_entry 1 mrs x0, tpidr_el0 - add x0, x0, #S_FRAME_SIZE + add x0, x0, #PT_REGS_SIZE str x0, [sp, #S_SP] /* Stash the regs for handle_bad_stack */ diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 38bb07eff872..3605f77ad4df 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -23,8 +23,6 @@ #include <linux/platform_device.h> #include <linux/sched_clock.h> #include <linux/smp.h> -#include <linux/nmi.h> -#include <linux/cpufreq.h> /* ARMv8 Cortex-A53 specific event types. */ #define ARMV8_A53_PERFCTR_PREF_LINEFILL 0xC2 @@ -1250,21 +1248,10 @@ static struct platform_driver armv8_pmu_driver = { static int __init armv8_pmu_driver_init(void) { - int ret; - if (acpi_disabled) - ret = platform_driver_register(&armv8_pmu_driver); + return platform_driver_register(&armv8_pmu_driver); else - ret = arm_pmu_acpi_probe(armv8_pmuv3_init); - - /* - * Try to re-initialize lockup detector after PMU init in - * case PMU events are triggered via NMIs. - */ - if (ret == 0 && arm_pmu_irq_is_nmi()) - lockup_detector_init(); - - return ret; + return arm_pmu_acpi_probe(armv8_pmuv3_init); } device_initcall(armv8_pmu_driver_init) @@ -1322,27 +1309,3 @@ void arch_perf_update_userpage(struct perf_event *event, userpg->cap_user_time_zero = 1; userpg->cap_user_time_short = 1; } - -#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF -/* - * Safe maximum CPU frequency in case a particular platform doesn't implement - * cpufreq driver. Although, architecture doesn't put any restrictions on - * maximum frequency but 5 GHz seems to be safe maximum given the available - * Arm CPUs in the market which are clocked much less than 5 GHz. On the other - * hand, we can't make it much higher as it would lead to a large hard-lockup - * detection timeout on parts which are running slower (eg. 1GHz on - * Developerbox) and doesn't possess a cpufreq driver. - */ -#define SAFE_MAX_CPU_FREQ 5000000000UL // 5 GHz -u64 hw_nmi_get_sample_period(int watchdog_thresh) -{ - unsigned int cpu = smp_processor_id(); - unsigned long max_cpu_freq; - - max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL; - if (!max_cpu_freq) - max_cpu_freq = SAFE_MAX_CPU_FREQ; - - return (u64)max_cpu_freq * watchdog_thresh; -} -#endif diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 89c64ada8732..66aac2881ba8 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -352,8 +352,8 @@ kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr) unsigned long addr = instruction_pointer(regs); struct kprobe *cur = kprobe_running(); - if (cur && (kcb->kprobe_status == KPROBE_HIT_SS) - && ((unsigned long)&cur->ainsn.api.insn[1] == addr)) { + if (cur && (kcb->kprobe_status & (KPROBE_HIT_SS | KPROBE_REENTER)) && + ((unsigned long)&cur->ainsn.api.insn[1] == addr)) { kprobes_restore_local_irqflag(kcb, regs); post_kprobe_handler(cur, kcb, regs); diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S index 890ca72c5a51..288a84e253cc 100644 --- a/arch/arm64/kernel/probes/kprobes_trampoline.S +++ b/arch/arm64/kernel/probes/kprobes_trampoline.S @@ -25,7 +25,7 @@ stp x24, x25, [sp, #S_X24] stp x26, x27, [sp, #S_X26] stp x28, x29, [sp, #S_X28] - add x0, sp, #S_FRAME_SIZE + add x0, sp, #PT_REGS_SIZE stp lr, x0, [sp, #S_LR] /* * Construct a useful saved PSTATE @@ -62,7 +62,7 @@ .endm SYM_CODE_START(kretprobe_trampoline) - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE save_all_base_regs @@ -76,7 +76,7 @@ SYM_CODE_START(kretprobe_trampoline) restore_all_base_regs - add sp, sp, #S_FRAME_SIZE + add sp, sp, #PT_REGS_SIZE ret SYM_CODE_END(kretprobe_trampoline) diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index f71d6ce4673f..6237486ff6bb 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -914,13 +914,6 @@ static void do_signal(struct pt_regs *regs) asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) { - /* - * The assembly code enters us with IRQs off, but it hasn't - * informed the tracing code of that for efficiency reasons. - * Update the trace code with the current status. - */ - trace_hardirqs_off(); - do { if (thread_flags & _TIF_NEED_RESCHED) { /* Unmask Debug and SError for the next task */ diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index f61e9d8cc55a..c2877c332f2d 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -9,6 +9,7 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> +#include <asm/exception.h> #include <asm/fpsimd.h> #include <asm/syscall.h> #include <asm/thread_info.h> @@ -165,15 +166,8 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) { local_daif_mask(); flags = current_thread_info()->flags; - if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) { - /* - * We're off to userspace, where interrupts are - * always enabled after we restore the flags from - * the SPSR. - */ - trace_hardirqs_on(); + if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) return; - } local_daif_restore(DAIF_PROCCTX); } diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 04c44853b103..fe60d25c000e 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1396,8 +1396,9 @@ static void cpu_init_hyp_mode(void) * Calculate the raw per-cpu offset without a translation from the * kernel's mapping to the linear mapping, and store it in tpidr_el2 * so that we can use adr_l to access per-cpu variables in EL2. + * Also drop the KASAN tag which gets in the way... */ - params->tpidr_el2 = (unsigned long)this_cpu_ptr_nvhe_sym(__per_cpu_start) - + params->tpidr_el2 = (unsigned long)kasan_reset_tag(this_cpu_ptr_nvhe_sym(__per_cpu_start)) - (unsigned long)kvm_ksym_ref(CHOOSE_NVHE_SYM(__per_cpu_start)); params->mair_el2 = read_sysreg(mair_el1); diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c index e3947846ffcb..8e7128cb7667 100644 --- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c +++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c @@ -77,12 +77,6 @@ static unsigned long psci_forward(struct kvm_cpu_context *host_ctxt) cpu_reg(host_ctxt, 2), cpu_reg(host_ctxt, 3)); } -static __noreturn unsigned long psci_forward_noreturn(struct kvm_cpu_context *host_ctxt) -{ - psci_forward(host_ctxt); - hyp_panic(); /* unreachable */ -} - static unsigned int find_cpu_id(u64 mpidr) { unsigned int i; @@ -251,10 +245,13 @@ static unsigned long psci_0_2_handler(u64 func_id, struct kvm_cpu_context *host_ case PSCI_0_2_FN_MIGRATE_INFO_TYPE: case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU: return psci_forward(host_ctxt); + /* + * SYSTEM_OFF/RESET should not return according to the spec. + * Allow it so as to stay robust to broken firmware. + */ case PSCI_0_2_FN_SYSTEM_OFF: case PSCI_0_2_FN_SYSTEM_RESET: - psci_forward_noreturn(host_ctxt); - unreachable(); + return psci_forward(host_ctxt); case PSCI_0_2_FN64_CPU_SUSPEND: return psci_cpu_suspend(func_id, host_ctxt); case PSCI_0_2_FN64_CPU_ON: diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 4ad66a532e38..247422ac78a9 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -788,7 +788,7 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) { unsigned long *bmap = vcpu->kvm->arch.pmu_filter; u64 val, mask = 0; - int base, i; + int base, i, nr_events; if (!pmceid1) { val = read_sysreg(pmceid0_el0); @@ -801,13 +801,17 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) if (!bmap) return val; + nr_events = kvm_pmu_event_mask(vcpu->kvm) + 1; + for (i = 0; i < 32; i += 8) { u64 byte; byte = bitmap_get_value8(bmap, base + i); mask |= byte << i; - byte = bitmap_get_value8(bmap, 0x4000 + base + i); - mask |= byte << (32 + i); + if (nr_events >= (0x4000 + base + 32)) { + byte = bitmap_get_value8(bmap, 0x4000 + base + i); + mask |= byte << (32 + i); + } } return val & mask; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 42ccc27fb684..7c4f79532406 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -43,6 +43,10 @@ * 64bit interface. */ +#define reg_to_encoding(x) \ + sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \ + (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2) + static bool read_from_write_only(struct kvm_vcpu *vcpu, struct sys_reg_params *params, const struct sys_reg_desc *r) @@ -273,8 +277,7 @@ static bool trap_loregion(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 val = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); - u32 sr = sys_reg((u32)r->Op0, (u32)r->Op1, - (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + u32 sr = reg_to_encoding(r); if (!(val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))) { kvm_inject_undefined(vcpu); @@ -590,6 +593,15 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) vcpu_write_sys_reg(vcpu, (1ULL << 31) | mpidr, MPIDR_EL1); } +static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) +{ + if (kvm_vcpu_has_pmu(vcpu)) + return 0; + + return REG_HIDDEN; +} + static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 pmcr, val; @@ -613,9 +625,8 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags) { u64 reg = __vcpu_sys_reg(vcpu, PMUSERENR_EL0); - bool enabled = kvm_vcpu_has_pmu(vcpu); + bool enabled = (reg & flags) || vcpu_mode_priv(vcpu); - enabled &= (reg & flags) || vcpu_mode_priv(vcpu); if (!enabled) kvm_inject_undefined(vcpu); @@ -900,11 +911,6 @@ static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p, static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - if (!kvm_vcpu_has_pmu(vcpu)) { - kvm_inject_undefined(vcpu); - return false; - } - if (p->is_write) { if (!vcpu_mode_priv(vcpu)) { kvm_inject_undefined(vcpu); @@ -921,10 +927,6 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, return true; } -#define reg_to_encoding(x) \ - sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \ - (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2) - /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */ #define DBG_BCR_BVR_WCR_WVR_EL1(n) \ { SYS_DESC(SYS_DBGBVRn_EL1(n)), \ @@ -936,15 +938,18 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { SYS_DESC(SYS_DBGWCRn_EL1(n)), \ trap_wcr, reset_wcr, 0, 0, get_wcr, set_wcr } +#define PMU_SYS_REG(r) \ + SYS_DESC(r), .reset = reset_unknown, .visibility = pmu_visibility + /* Macro to expand the PMEVCNTRn_EL0 register */ #define PMU_PMEVCNTR_EL0(n) \ - { SYS_DESC(SYS_PMEVCNTRn_EL0(n)), \ - access_pmu_evcntr, reset_unknown, (PMEVCNTR0_EL0 + n), } + { PMU_SYS_REG(SYS_PMEVCNTRn_EL0(n)), \ + .access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), } /* Macro to expand the PMEVTYPERn_EL0 register */ #define PMU_PMEVTYPER_EL0(n) \ - { SYS_DESC(SYS_PMEVTYPERn_EL0(n)), \ - access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), } + { PMU_SYS_REG(SYS_PMEVTYPERn_EL0(n)), \ + .access = access_pmu_evtyper, .reg = (PMEVTYPER0_EL0 + n), } static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) @@ -1020,8 +1025,7 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu, static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r, bool raz) { - u32 id = sys_reg((u32)r->Op0, (u32)r->Op1, - (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + u32 id = reg_to_encoding(r); u64 val = raz ? 0 : read_sanitised_ftr_reg(id); if (id == SYS_ID_AA64PFR0_EL1) { @@ -1062,8 +1066,7 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, static unsigned int id_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { - u32 id = sys_reg((u32)r->Op0, (u32)r->Op1, - (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + u32 id = reg_to_encoding(r); switch (id) { case SYS_ID_AA64ZFR0_EL1: @@ -1486,8 +1489,10 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 }, { SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 }, - { SYS_DESC(SYS_PMINTENSET_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 }, - { SYS_DESC(SYS_PMINTENCLR_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 }, + { PMU_SYS_REG(SYS_PMINTENSET_EL1), + .access = access_pminten, .reg = PMINTENSET_EL1 }, + { PMU_SYS_REG(SYS_PMINTENCLR_EL1), + .access = access_pminten, .reg = PMINTENSET_EL1 }, { SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 }, { SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 }, @@ -1526,23 +1531,36 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, { SYS_DESC(SYS_CTR_EL0), access_ctr }, - { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, PMCR_EL0 }, - { SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 }, - { SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 }, - { SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, reset_unknown, PMOVSSET_EL0 }, - { SYS_DESC(SYS_PMSWINC_EL0), access_pmswinc, reset_unknown, PMSWINC_EL0 }, - { SYS_DESC(SYS_PMSELR_EL0), access_pmselr, reset_unknown, PMSELR_EL0 }, - { SYS_DESC(SYS_PMCEID0_EL0), access_pmceid }, - { SYS_DESC(SYS_PMCEID1_EL0), access_pmceid }, - { SYS_DESC(SYS_PMCCNTR_EL0), access_pmu_evcntr, reset_unknown, PMCCNTR_EL0 }, - { SYS_DESC(SYS_PMXEVTYPER_EL0), access_pmu_evtyper }, - { SYS_DESC(SYS_PMXEVCNTR_EL0), access_pmu_evcntr }, + { PMU_SYS_REG(SYS_PMCR_EL0), .access = access_pmcr, + .reset = reset_pmcr, .reg = PMCR_EL0 }, + { PMU_SYS_REG(SYS_PMCNTENSET_EL0), + .access = access_pmcnten, .reg = PMCNTENSET_EL0 }, + { PMU_SYS_REG(SYS_PMCNTENCLR_EL0), + .access = access_pmcnten, .reg = PMCNTENSET_EL0 }, + { PMU_SYS_REG(SYS_PMOVSCLR_EL0), + .access = access_pmovs, .reg = PMOVSSET_EL0 }, + { PMU_SYS_REG(SYS_PMSWINC_EL0), + .access = access_pmswinc, .reg = PMSWINC_EL0 }, + { PMU_SYS_REG(SYS_PMSELR_EL0), + .access = access_pmselr, .reg = PMSELR_EL0 }, + { PMU_SYS_REG(SYS_PMCEID0_EL0), + .access = access_pmceid, .reset = NULL }, + { PMU_SYS_REG(SYS_PMCEID1_EL0), + .access = access_pmceid, .reset = NULL }, + { PMU_SYS_REG(SYS_PMCCNTR_EL0), + .access = access_pmu_evcntr, .reg = PMCCNTR_EL0 }, + { PMU_SYS_REG(SYS_PMXEVTYPER_EL0), + .access = access_pmu_evtyper, .reset = NULL }, + { PMU_SYS_REG(SYS_PMXEVCNTR_EL0), + .access = access_pmu_evcntr, .reset = NULL }, /* * PMUSERENR_EL0 resets as unknown in 64bit mode while it resets as zero * in 32bit mode. Here we choose to reset it as zero for consistency. */ - { SYS_DESC(SYS_PMUSERENR_EL0), access_pmuserenr, reset_val, PMUSERENR_EL0, 0 }, - { SYS_DESC(SYS_PMOVSSET_EL0), access_pmovs, reset_unknown, PMOVSSET_EL0 }, + { PMU_SYS_REG(SYS_PMUSERENR_EL0), .access = access_pmuserenr, + .reset = reset_val, .reg = PMUSERENR_EL0, .val = 0 }, + { PMU_SYS_REG(SYS_PMOVSSET_EL0), + .access = access_pmovs, .reg = PMOVSSET_EL0 }, { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, @@ -1694,7 +1712,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { * PMCCFILTR_EL0 resets as unknown in 64bit mode while it resets as zero * in 32bit mode. Here we choose to reset it as zero for consistency. */ - { SYS_DESC(SYS_PMCCFILTR_EL0), access_pmu_evtyper, reset_val, PMCCFILTR_EL0, 0 }, + { PMU_SYS_REG(SYS_PMCCFILTR_EL0), .access = access_pmu_evtyper, + .reset = reset_val, .reg = PMCCFILTR_EL0, .val = 0 }, { SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 }, { SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 }, diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 3c40da479899..35d75c60e2b8 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -709,10 +709,11 @@ static int do_tag_check_fault(unsigned long far, unsigned int esr, struct pt_regs *regs) { /* - * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN for tag - * check faults. Mask them out now so that userspace doesn't see them. + * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN + * for tag check faults. Set them to corresponding bits in the untagged + * address. */ - far &= (1UL << 60) - 1; + far = (__untagged_addr(far) & ~MTE_TAG_MASK) | (far & MTE_TAG_MASK); do_bad_area(far, esr, regs); return 0; } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 7deddf56f7c3..709d98fea90c 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -53,13 +53,13 @@ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); /* - * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of - * memory as some devices, namely the Raspberry Pi 4, have peripherals with - * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32 - * bit addressable memory area. + * If the corresponding config options are enabled, we create both ZONE_DMA + * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory + * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4). + * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory, + * otherwise it is empty. */ phys_addr_t arm64_dma_phys_limit __ro_after_init; -phys_addr_t arm64_dma32_phys_limit __ro_after_init; #ifdef CONFIG_KEXEC_CORE /* @@ -84,7 +84,7 @@ static void __init reserve_crashkernel(void) if (crash_base == 0) { /* Current arm64 boot protocol requires 2MB alignment */ - crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit, + crash_base = memblock_find_in_range(0, arm64_dma_phys_limit, crash_size, SZ_2M); if (crash_base == 0) { pr_warn("cannot allocate crashkernel (size:0x%llx)\n", @@ -196,6 +196,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; unsigned int __maybe_unused acpi_zone_dma_bits; unsigned int __maybe_unused dt_zone_dma_bits; + phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32); #ifdef CONFIG_ZONE_DMA acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address()); @@ -205,8 +206,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); #endif #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit); + if (!arm64_dma_phys_limit) + arm64_dma_phys_limit = dma32_phys_limit; #endif + if (!arm64_dma_phys_limit) + arm64_dma_phys_limit = PHYS_MASK + 1; max_zone_pfns[ZONE_NORMAL] = max; free_area_init(max_zone_pfns); @@ -394,16 +399,9 @@ void __init arm64_memblock_init(void) early_init_fdt_scan_reserved_mem(); - if (IS_ENABLED(CONFIG_ZONE_DMA32)) - arm64_dma32_phys_limit = max_zone_phys(32); - else - arm64_dma32_phys_limit = PHYS_MASK + 1; - reserve_elfcorehdr(); high_memory = __va(memblock_end_of_DRAM() - 1) + 1; - - dma_contiguous_reserve(arm64_dma32_phys_limit); } void __init bootmem_init(void) @@ -439,6 +437,11 @@ void __init bootmem_init(void) zone_sizes_init(min, max); /* + * Reserve the CMA area after arm64_dma_phys_limit was initialised. + */ + dma_contiguous_reserve(arm64_dma_phys_limit); + + /* * request_standard_resources() depends on crashkernel's memory being * reserved, so do it here. */ @@ -455,7 +458,7 @@ void __init bootmem_init(void) void __init mem_init(void) { if (swiotlb_force == SWIOTLB_FORCE || - max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit)) + max_pfn > PFN_DOWN(arm64_dma_phys_limit)) swiotlb_init(1); else swiotlb_force = SWIOTLB_NO_FORCE; diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h index dd8c166ffd7b..42ed5248fae9 100644 --- a/arch/ia64/include/asm/sparsemem.h +++ b/arch/ia64/include/asm/sparsemem.h @@ -3,6 +3,7 @@ #define _ASM_IA64_SPARSEMEM_H #ifdef CONFIG_SPARSEMEM +#include <asm/page.h> /* * SECTION_SIZE_BITS 2^N: how big each section will be * MAX_PHYSMEM_BITS 2^N: how much memory we can have in that space diff --git a/arch/ia64/include/uapi/asm/cmpxchg.h b/arch/ia64/include/uapi/asm/cmpxchg.h index d69c979936d4..5d90307fd6e0 100644 --- a/arch/ia64/include/uapi/asm/cmpxchg.h +++ b/arch/ia64/include/uapi/asm/cmpxchg.h @@ -54,7 +54,7 @@ extern void ia64_xchg_called_with_bad_pointer(void); }) #define xchg(ptr, x) \ -((__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr)))) +({(__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr)));}) /* * Atomic compare and exchange. Compare OLD with MEM, if identical, diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index ed9fc3d057a6..43e8050145be 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -171,29 +171,34 @@ void vtime_account_hardirq(struct task_struct *tsk) static irqreturn_t timer_interrupt (int irq, void *dev_id) { - unsigned long cur_itm, new_itm, ticks; + unsigned long new_itm; if (cpu_is_offline(smp_processor_id())) { return IRQ_HANDLED; } new_itm = local_cpu_data->itm_next; - cur_itm = ia64_get_itc(); - if (!time_after(cur_itm, new_itm)) { + if (!time_after(ia64_get_itc(), new_itm)) printk(KERN_ERR "Oops: timer tick before it's due (itc=%lx,itm=%lx)\n", - cur_itm, new_itm); - ticks = 1; - } else { - ticks = DIV_ROUND_UP(cur_itm - new_itm, - local_cpu_data->itm_delta); - new_itm += ticks * local_cpu_data->itm_delta; - } + ia64_get_itc(), new_itm); + + while (1) { + new_itm += local_cpu_data->itm_delta; + + legacy_timer_tick(smp_processor_id() == time_keeper_id); - if (smp_processor_id() != time_keeper_id) - ticks = 0; + local_cpu_data->itm_next = new_itm; - legacy_timer_tick(ticks); + if (time_after(new_itm, ia64_get_itc())) + break; + + /* + * Allow IPIs to interrupt the timer loop. + */ + local_irq_enable(); + local_irq_disable(); + } do { /* diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c index c61c641674e6..e3946b06e840 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -13,6 +13,7 @@ #include <linux/libfdt.h> #include <asm/addrspace.h> +#include <asm/unaligned.h> /* * These two variables specify the free mem region @@ -117,7 +118,7 @@ void decompress_kernel(unsigned long boot_heap_start) dtb_size = fdt_totalsize((void *)&__appended_dtb); /* last four bytes is always image size in little endian */ - image_size = le32_to_cpup((void *)&__image_end - 4); + image_size = get_unaligned_le32((void *)&__image_end - 4); /* copy dtb to where the booted kernel will expect it */ memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size, diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index bd47e15d02c7..be5d4afcd30f 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -1444,7 +1444,7 @@ static void octeon_irq_setup_secondary_ciu2(void) static int __init octeon_irq_init_ciu( struct device_node *ciu_node, struct device_node *parent) { - unsigned int i, r; + int i, r; struct irq_chip *chip; struct irq_chip *chip_edge; struct irq_chip *chip_mbox; diff --git a/arch/mips/include/asm/highmem.h b/arch/mips/include/asm/highmem.h index 19edf8e69971..292d0425717f 100644 --- a/arch/mips/include/asm/highmem.h +++ b/arch/mips/include/asm/highmem.h @@ -51,6 +51,7 @@ extern void kmap_flush_tlb(unsigned long addr); #define flush_cache_kmaps() BUG_ON(cpu_has_dc_aliases) +#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) set_pte(ptep, ptev) #define arch_kmap_local_post_map(vaddr, pteval) local_flush_tlb_one(vaddr) #define arch_kmap_local_post_unmap(vaddr) local_flush_tlb_one(vaddr) diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c index 6ee3f7218c67..c4441416e96b 100644 --- a/arch/mips/kernel/binfmt_elfn32.c +++ b/arch/mips/kernel/binfmt_elfn32.c @@ -103,4 +103,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) #undef ns_to_kernel_old_timeval #define ns_to_kernel_old_timeval ns_to_old_timeval32 +/* + * Some data types as stored in coredump. + */ +#define user_long_t compat_long_t +#define user_siginfo_t compat_siginfo_t +#define copy_siginfo_to_external copy_siginfo_to_external32 + #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c index 6dd103d3cebb..7b2a23f48c1a 100644 --- a/arch/mips/kernel/binfmt_elfo32.c +++ b/arch/mips/kernel/binfmt_elfo32.c @@ -106,4 +106,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) #undef ns_to_kernel_old_timeval #define ns_to_kernel_old_timeval ns_to_old_timeval32 +/* + * Some data types as stored in coredump. + */ +#define user_long_t compat_long_t +#define user_siginfo_t compat_siginfo_t +#define copy_siginfo_to_external copy_siginfo_to_external32 + #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c index 47aeb3350a76..0e365b7c742d 100644 --- a/arch/mips/kernel/relocate.c +++ b/arch/mips/kernel/relocate.c @@ -187,8 +187,14 @@ static int __init relocate_exception_table(long offset) static inline __init unsigned long rotate_xor(unsigned long hash, const void *area, size_t size) { - size_t i; - unsigned long *ptr = (unsigned long *)area; + const typeof(hash) *ptr = PTR_ALIGN(area, sizeof(hash)); + size_t diff, i; + + diff = (void *)ptr - area; + if (unlikely(size < diff + sizeof(hash))) + return hash; + + size = ALIGN_DOWN(size - diff, sizeof(hash)); for (i = 0; i < size / sizeof(hash); i++) { /* Rotate by odd number of bits and XOR. */ diff --git a/arch/openrisc/include/asm/io.h b/arch/openrisc/include/asm/io.h index 7d6b4a77b379..c298061c70a7 100644 --- a/arch/openrisc/include/asm/io.h +++ b/arch/openrisc/include/asm/io.h @@ -31,7 +31,7 @@ void __iomem *ioremap(phys_addr_t offset, unsigned long size); #define iounmap iounmap -extern void iounmap(void *addr); +extern void iounmap(void __iomem *addr); #include <asm-generic/io.h> diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c index 5aed97a18bac..daae13a76743 100644 --- a/arch/openrisc/mm/ioremap.c +++ b/arch/openrisc/mm/ioremap.c @@ -77,7 +77,7 @@ void __iomem *__ref ioremap(phys_addr_t addr, unsigned long size) } EXPORT_SYMBOL(ioremap); -void iounmap(void *addr) +void iounmap(void __iomem *addr) { /* If the page is from the fixmap pool then we just clear out * the fixmap mapping. diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 78b17621ee4a..278462186ac4 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -202,9 +202,8 @@ config PREFETCH depends on PA8X00 || PA7200 config MLONGCALLS - bool "Enable the -mlong-calls compiler option for big kernels" - default y if !MODULES || UBSAN || FTRACE - default n + def_bool y if !MODULES || UBSAN || FTRACE + bool "Enable the -mlong-calls compiler option for big kernels" if MODULES && !UBSAN && !FTRACE depends on PA8X00 help If you configure the kernel to include many drivers built-in instead diff --git a/arch/parisc/include/asm/irq.h b/arch/parisc/include/asm/irq.h index 959e79cd2c14..378f63c4015b 100644 --- a/arch/parisc/include/asm/irq.h +++ b/arch/parisc/include/asm/irq.h @@ -47,7 +47,4 @@ extern unsigned long txn_affinity_addr(unsigned int irq, int cpu); extern int cpu_claim_irq(unsigned int irq, struct irq_chip *, void *); extern int cpu_check_affinity(struct irq_data *d, const struct cpumask *dest); -/* soft power switch support (power.c) */ -extern struct tasklet_struct power_tasklet; - #endif /* _ASM_PARISC_IRQ_H */ diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index beba9816cc6c..4d37cc9cba37 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -997,10 +997,17 @@ intr_do_preempt: bb,<,n %r20, 31 - PSW_SM_I, intr_restore nop + /* ssm PSW_SM_I done later in intr_restore */ +#ifdef CONFIG_MLONGCALLS + ldil L%intr_restore, %r2 + load32 preempt_schedule_irq, %r1 + bv %r0(%r1) + ldo R%intr_restore(%r2), %r2 +#else + ldil L%intr_restore, %r1 BL preempt_schedule_irq, %r2 - nop - - b,n intr_restore /* ssm PSW_SM_I done by intr_restore */ + ldo R%intr_restore(%r1), %r2 +#endif #endif /* CONFIG_PREEMPTION */ /* diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 1d32b174ab6a..c1a8aac01cf9 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -63,6 +63,12 @@ nop; \ nop; +#define SCV_ENTRY_FLUSH_SLOT \ + SCV_ENTRY_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop; + /* * r10 must be free to use, r13 must be paca */ @@ -71,6 +77,13 @@ ENTRY_FLUSH_SLOT /* + * r10, ctr must be free to use, r13 must be paca + */ +#define SCV_INTERRUPT_TO_KERNEL \ + STF_ENTRY_BARRIER_SLOT; \ + SCV_ENTRY_FLUSH_SLOT + +/* * Macros for annotating the expected destination of (h)rfid * * The nop instructions allow us to insert one or more instructions to flush the diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index f6d2acb57425..ac605fc369c4 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -240,6 +240,14 @@ label##3: \ FTR_ENTRY_OFFSET 957b-958b; \ .popsection; +#define SCV_ENTRY_FLUSH_FIXUP_SECTION \ +957: \ + .pushsection __scv_entry_flush_fixup,"a"; \ + .align 2; \ +958: \ + FTR_ENTRY_OFFSET 957b-958b; \ + .popsection; + #define RFI_FLUSH_FIXUP_SECTION \ 951: \ .pushsection __rfi_flush_fixup,"a"; \ @@ -273,10 +281,12 @@ label##3: \ extern long stf_barrier_fallback; extern long entry_flush_fallback; +extern long scv_entry_flush_fallback; extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup; extern long __start___entry_flush_fixup, __stop___entry_flush_fixup; +extern long __start___scv_entry_flush_fixup, __stop___scv_entry_flush_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h index 80a5ae771c65..c0fcd1bbdba9 100644 --- a/arch/powerpc/include/asm/highmem.h +++ b/arch/powerpc/include/asm/highmem.h @@ -58,6 +58,8 @@ extern pte_t *pkmap_page_table; #define flush_cache_kmaps() flush_cache_all() +#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) \ + __set_pte_at(mm, vaddr, ptep, ptev, 1) #define arch_kmap_local_post_map(vaddr, pteval) \ local_flush_tlb_page(NULL, vaddr) #define arch_kmap_local_post_unmap(vaddr) \ diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h index 81671aa365b3..77c635c2c90d 100644 --- a/arch/powerpc/include/asm/vdso/gettimeofday.h +++ b/arch/powerpc/include/asm/vdso/gettimeofday.h @@ -103,6 +103,8 @@ int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz return do_syscall_2(__NR_gettimeofday, (unsigned long)_tv, (unsigned long)_tz); } +#ifdef __powerpc64__ + static __always_inline int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) { @@ -115,11 +117,23 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts); } -#ifdef CONFIG_VDSO32 +#else #define BUILD_VDSO32 1 static __always_inline +int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_gettime64, _clkid, (unsigned long)_ts); +} + +static __always_inline +int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_getres_time64, _clkid, (unsigned long)_ts); +} + +static __always_inline int clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) { return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index aa1af139d947..33ddfeef4fe9 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -75,7 +75,7 @@ BEGIN_FTR_SECTION bne .Ltabort_syscall END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif - INTERRUPT_TO_KERNEL + SCV_INTERRUPT_TO_KERNEL mr r10,r1 ld r1,PACAKSAVE(r13) std r10,0(r1) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index e02ad6fefa46..6e53f7638737 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2993,6 +2993,25 @@ TRAMP_REAL_BEGIN(entry_flush_fallback) ld r11,PACA_EXRFI+EX_R11(r13) blr +/* + * The SCV entry flush happens with interrupts enabled, so it must disable + * to prevent EXRFI being clobbered by NMIs (e.g., soft_nmi_common). r10 + * (containing LR) does not need to be preserved here because scv entry + * puts 0 in the pt_regs, CTR can be clobbered for the same reason. + */ +TRAMP_REAL_BEGIN(scv_entry_flush_fallback) + li r10,0 + mtmsrd r10,1 + lbz r10,PACAIRQHAPPENED(r13) + ori r10,r10,PACA_IRQ_HARD_DIS + stb r10,PACAIRQHAPPENED(r13) + std r11,PACA_EXRFI+EX_R11(r13) + L1D_DISPLACEMENT_FLUSH + ld r11,PACA_EXRFI+EX_R11(r13) + li r10,MSR_RI + mtmsrd r10,1 + blr + TRAMP_REAL_BEGIN(rfi_flush_fallback) SET_SCRATCH0(r13); GET_PACA(r13); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 6b1eca53e36c..cc7a6271b6b4 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -180,13 +180,18 @@ void notrace restore_interrupts(void) void replay_soft_interrupts(void) { + struct pt_regs regs; + /* - * We use local_paca rather than get_paca() to avoid all - * the debug_smp_processor_id() business in this low level - * function + * Be careful here, calling these interrupt handlers can cause + * softirqs to be raised, which they may run when calling irq_exit, + * which will cause local_irq_enable() to be run, which can then + * recurse into this function. Don't keep any state across + * interrupt handler calls which may change underneath us. + * + * We use local_paca rather than get_paca() to avoid all the + * debug_smp_processor_id() business in this low level function. */ - unsigned char happened = local_paca->irq_happened; - struct pt_regs regs; ppc_save_regs(®s); regs.softe = IRQS_ENABLED; @@ -209,7 +214,7 @@ again: * This is a higher priority interrupt than the others, so * replay it first. */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (happened & PACA_IRQ_HMI)) { + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_HMI)) { local_paca->irq_happened &= ~PACA_IRQ_HMI; regs.trap = 0xe60; handle_hmi_exception(®s); @@ -217,7 +222,7 @@ again: hard_irq_disable(); } - if (happened & PACA_IRQ_DEC) { + if (local_paca->irq_happened & PACA_IRQ_DEC) { local_paca->irq_happened &= ~PACA_IRQ_DEC; regs.trap = 0x900; timer_interrupt(®s); @@ -225,7 +230,7 @@ again: hard_irq_disable(); } - if (happened & PACA_IRQ_EE) { + if (local_paca->irq_happened & PACA_IRQ_EE) { local_paca->irq_happened &= ~PACA_IRQ_EE; regs.trap = 0x500; do_IRQ(®s); @@ -233,7 +238,7 @@ again: hard_irq_disable(); } - if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (happened & PACA_IRQ_DBELL)) { + if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (local_paca->irq_happened & PACA_IRQ_DBELL)) { local_paca->irq_happened &= ~PACA_IRQ_DBELL; if (IS_ENABLED(CONFIG_PPC_BOOK3E)) regs.trap = 0x280; @@ -245,7 +250,7 @@ again: } /* Book3E does not support soft-masking PMI interrupts */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (happened & PACA_IRQ_PMI)) { + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_PMI)) { local_paca->irq_happened &= ~PACA_IRQ_PMI; regs.trap = 0xf00; performance_monitor_exception(®s); @@ -253,8 +258,7 @@ again: hard_irq_disable(); } - happened = local_paca->irq_happened; - if (happened & ~PACA_IRQ_HARD_DIS) { + if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) { /* * We are responding to the next interrupt, so interrupt-off * latencies should be reset here. diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 8e0b1298bf19..72fa3c00229a 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -146,6 +146,13 @@ SECTIONS } . = ALIGN(8); + __scv_entry_flush_fixup : AT(ADDR(__scv_entry_flush_fixup) - LOAD_OFFSET) { + __start___scv_entry_flush_fixup = .; + *(__scv_entry_flush_fixup) + __stop___scv_entry_flush_fixup = .; + } + + . = ALIGN(8); __stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) { __start___stf_exit_barrier_fixup = .; *(__stf_exit_barrier_fixup) @@ -187,6 +194,12 @@ SECTIONS .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) { _sinittext = .; INIT_TEXT + + /* + *.init.text might be RO so we must ensure this section ends on + * a page boundary. + */ + . = ALIGN(PAGE_SIZE); _einittext = .; #ifdef CONFIG_PPC64 *(.tramp.ftrace.init); @@ -200,6 +213,8 @@ SECTIONS EXIT_TEXT } + . = ALIGN(PAGE_SIZE); + INIT_DATA_SECTION(16) . = ALIGN(8); diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 47821055b94c..1fd31b4b0e13 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -290,9 +290,6 @@ void do_entry_flush_fixups(enum l1d_flush_type types) long *start, *end; int i; - start = PTRRELOC(&__start___entry_flush_fixup); - end = PTRRELOC(&__stop___entry_flush_fixup); - instrs[0] = 0x60000000; /* nop */ instrs[1] = 0x60000000; /* nop */ instrs[2] = 0x60000000; /* nop */ @@ -312,6 +309,8 @@ void do_entry_flush_fixups(enum l1d_flush_type types) if (types & L1D_FLUSH_MTTRIG) instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + start = PTRRELOC(&__start___entry_flush_fixup); + end = PTRRELOC(&__stop___entry_flush_fixup); for (i = 0; start < end; start++, i++) { dest = (void *)start + *start; @@ -328,6 +327,25 @@ void do_entry_flush_fixups(enum l1d_flush_type types) patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); } + start = PTRRELOC(&__start___scv_entry_flush_fixup); + end = PTRRELOC(&__stop___scv_entry_flush_fixup); + for (; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + + if (types == L1D_FLUSH_FALLBACK) + patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&scv_entry_flush_fallback, + BRANCH_SET_LINK); + else + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + } + + printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i, (types == L1D_FLUSH_NONE) ? "no" : (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 81b76d44725d..e9e2c1f0a690 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -137,7 +137,7 @@ config PA_BITS config PAGE_OFFSET hex - default 0xC0000000 if 32BIT && MAXPHYSMEM_2GB + default 0xC0000000 if 32BIT && MAXPHYSMEM_1GB default 0x80000000 if 64BIT && !MMU default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB @@ -247,10 +247,12 @@ config MODULE_SECTIONS choice prompt "Maximum Physical Memory" - default MAXPHYSMEM_2GB if 32BIT + default MAXPHYSMEM_1GB if 32BIT default MAXPHYSMEM_2GB if 64BIT && CMODEL_MEDLOW default MAXPHYSMEM_128GB if 64BIT && CMODEL_MEDANY + config MAXPHYSMEM_1GB + bool "1GiB" config MAXPHYSMEM_2GB bool "2GiB" config MAXPHYSMEM_128GB diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 4a2729f5ca3f..24d75a146e02 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -88,7 +88,9 @@ phy-mode = "gmii"; phy-handle = <&phy0>; phy0: ethernet-phy@0 { + compatible = "ethernet-phy-id0007.0771"; reg = <0>; + reset-gpios = <&gpio 12 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index d222d353d86d..8c3d1e451703 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -64,6 +64,8 @@ CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y CONFIG_SPI=y CONFIG_SPI_SIFIVE=y +CONFIG_GPIOLIB=y +CONFIG_GPIO_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_POWER_RESET=y CONFIG_DRM=y diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 41a72861987c..251e1db088fa 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -99,7 +99,6 @@ | _PAGE_DIRTY) #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) -#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) #define PAGE_KERNEL_READ_EXEC __pgprot((_PAGE_KERNEL & ~_PAGE_WRITE) \ diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index 8454f746bbfd..1453a2f563bc 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -10,7 +10,7 @@ #include <linux/types.h> -#ifndef GENERIC_TIME_VSYSCALL +#ifndef CONFIG_GENERIC_TIME_VSYSCALL struct vdso_data { }; #endif diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index de59dd457b41..d86781357044 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -26,7 +26,16 @@ cache_get_priv_group(struct cacheinfo *this_leaf) static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type) { - struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(smp_processor_id()); + /* + * Using raw_smp_processor_id() elides a preemptability check, but this + * is really indicative of a larger problem: the cacheinfo UABI assumes + * that cores have a homonogenous view of the cache hierarchy. That + * happens to be the case for the current set of RISC-V systems, but + * likely won't be true in general. Since there's no way to provide + * correct information for these systems via the current UABI we're + * just eliding the check for now. + */ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id()); struct cacheinfo *this_leaf; int index; diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 524d918f3601..744f3209c48d 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -124,15 +124,15 @@ skip_context_tracking: REG_L a1, (a1) jr a1 1: -#ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_on -#endif /* * Exceptions run with interrupts enabled or disabled depending on the * state of SR_PIE in m/sstatus. */ andi t0, s1, SR_PIE beqz t0, 1f +#ifdef CONFIG_TRACE_IRQFLAGS + call trace_hardirqs_on +#endif csrs CSR_STATUS, SR_IE 1: @@ -155,6 +155,15 @@ skip_context_tracking: tail do_trap_unknown handle_syscall: +#ifdef CONFIG_RISCV_M_MODE + /* + * When running is M-Mode (no MMU config), MPIE does not get set. + * As a result, we need to force enable interrupts here because + * handle_exception did not do set SR_IE as it always sees SR_PIE + * being cleared. + */ + csrs CSR_STATUS, SR_IE +#endif #if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING) /* Recover a0 - a7 for system calls */ REG_L a0, PT_A0(sp) @@ -186,14 +195,7 @@ check_syscall_nr: * Syscall number held in a7. * If syscall number is above allowed value, redirect to ni_syscall. */ - bge a7, t0, 1f - /* - * Check if syscall is rejected by tracer, i.e., a7 == -1. - * If yes, we pretend it was executed. - */ - li t1, -1 - beq a7, t1, ret_from_syscall_rejected - blt a7, t1, 1f + bgeu a7, t0, 1f /* Call syscall */ la s0, sys_call_table slli t0, a7, RISCV_LGPTR diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 1d85e9bf783c..3fa3f26dde85 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -127,7 +127,9 @@ static void __init init_resources(void) { struct memblock_region *region = NULL; struct resource *res = NULL; - int ret = 0; + struct resource *mem_res = NULL; + size_t mem_res_sz = 0; + int ret = 0, i = 0; code_res.start = __pa_symbol(_text); code_res.end = __pa_symbol(_etext) - 1; @@ -145,16 +147,17 @@ static void __init init_resources(void) bss_res.end = __pa_symbol(__bss_stop) - 1; bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res); + mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES); + if (!mem_res) + panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz); /* * Start by adding the reserved regions, if they overlap * with /memory regions, insert_resource later on will take * care of it. */ for_each_reserved_mem_region(region) { - res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); + res = &mem_res[i++]; res->name = "Reserved"; res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; @@ -171,8 +174,10 @@ static void __init init_resources(void) * Ignore any other reserved regions within * system memory. */ - if (memblock_is_memory(res->start)) + if (memblock_is_memory(res->start)) { + memblock_free((phys_addr_t) res, sizeof(struct resource)); continue; + } ret = add_resource(&iomem_resource, res); if (ret < 0) @@ -181,10 +186,7 @@ static void __init init_resources(void) /* Add /memory regions to the resource tree */ for_each_mem_region(region) { - res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); + res = &mem_res[i++]; if (unlikely(memblock_is_nomap(region))) { res->name = "Reserved"; @@ -205,9 +207,9 @@ static void __init init_resources(void) return; error: - memblock_free((phys_addr_t) res, sizeof(struct resource)); /* Better an empty resource tree than an inconsistent one */ release_child_resources(&iomem_resource); + memblock_free((phys_addr_t) mem_res, mem_res_sz); } diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 48b870a685b3..df5d2da7c40b 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -14,7 +14,7 @@ #include <asm/stacktrace.h> -register unsigned long sp_in_global __asm__("sp"); +register const unsigned long sp_in_global __asm__("sp"); #ifdef CONFIG_FRAME_POINTER @@ -28,9 +28,8 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, sp = user_stack_pointer(regs); pc = instruction_pointer(regs); } else if (task == NULL || task == current) { - const register unsigned long current_sp = sp_in_global; fp = (unsigned long)__builtin_frame_address(0); - sp = current_sp; + sp = sp_in_global; pc = (unsigned long)walk_stackframe; } else { /* task blocked in __switch_to */ diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index 4d3a1048ad8b..8a5cf99c0776 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -4,6 +4,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/of_clk.h> #include <linux/clocksource.h> #include <linux/delay.h> #include <asm/sbi.h> @@ -24,6 +25,8 @@ void __init time_init(void) riscv_timebase = prop; lpj_fine = riscv_timebase / HZ; + + of_clk_init(NULL); timer_probe(); } diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 678204231700..3f1d35e7c98a 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -12,7 +12,7 @@ #include <linux/binfmts.h> #include <linux/err.h> #include <asm/page.h> -#ifdef GENERIC_TIME_VSYSCALL +#ifdef CONFIG_GENERIC_TIME_VSYSCALL #include <vdso/datapage.h> #else #include <asm/vdso.h> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index bf5379135e39..f9f9568d689e 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -157,9 +157,10 @@ disable: void __init setup_bootmem(void) { phys_addr_t mem_start = 0; - phys_addr_t start, end = 0; + phys_addr_t start, dram_end, end = 0; phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); + phys_addr_t max_mapped_addr = __pa(~(ulong)0); u64 i; /* Find the memory region containing the kernel */ @@ -181,10 +182,21 @@ void __init setup_bootmem(void) /* Reserve from the start of the kernel to the end of the kernel */ memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); - max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + dram_end = memblock_end_of_DRAM(); + + /* + * memblock allocator is not aware of the fact that last 4K bytes of + * the addressable memory can not be mapped because of IS_ERR_VALUE + * macro. Make sure that last 4k bytes are not usable by memblock + * if end of dram is equal to maximum addressable memory. + */ + if (max_mapped_addr == (dram_end - 1)) + memblock_set_current_limit(max_mapped_addr - 4096); + + max_pfn = PFN_DOWN(dram_end); max_low_pfn = max_pfn; dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); - set_max_mapnr(max_low_pfn); + set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET); #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 12ddd1f6bf70..a8a2ffd9114a 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -93,8 +93,8 @@ void __init kasan_init(void) VMALLOC_END)); for_each_mem_range(i, &_start, &_end) { - void *start = (void *)_start; - void *end = (void *)_end; + void *start = (void *)__va(_start); + void *end = (void *)__va(_end); if (start >= end) break; diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c index a15c033f53ca..87641dd65ccf 100644 --- a/arch/s390/boot/uv.c +++ b/arch/s390/boot/uv.c @@ -35,7 +35,7 @@ void uv_query_info(void) uv_info.guest_cpu_stor_len = uvcb.cpu_stor_len; uv_info.max_sec_stor_addr = ALIGN(uvcb.max_guest_stor_addr, PAGE_SIZE); uv_info.max_num_sec_conf = uvcb.max_num_sec_conf; - uv_info.max_guest_cpus = uvcb.max_guest_cpus; + uv_info.max_guest_cpu_id = uvcb.max_guest_cpu_id; } #ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 0325fc0469b7..7b98d4caee77 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -96,7 +96,7 @@ struct uv_cb_qui { u32 max_num_sec_conf; u64 max_guest_stor_addr; u8 reserved88[158 - 136]; - u16 max_guest_cpus; + u16 max_guest_cpu_id; u8 reserveda0[200 - 160]; } __packed __aligned(8); @@ -273,7 +273,7 @@ struct uv_info { unsigned long guest_cpu_stor_len; unsigned long max_sec_stor_addr; unsigned int max_num_sec_conf; - unsigned short max_guest_cpus; + unsigned short max_guest_cpu_id; }; extern struct uv_info uv_info; diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 883bfed9f5c2..b2d2ad153067 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -368,7 +368,7 @@ static ssize_t uv_query_max_guest_cpus(struct kobject *kobj, struct kobj_attribute *attr, char *page) { return scnprintf(page, PAGE_SIZE, "%d\n", - uv_info.max_guest_cpus); + uv_info.max_guest_cpu_id + 1); } static struct kobj_attribute uv_query_max_guest_cpus_attr = diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 5fa580219a86..52646f52f130 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -29,7 +29,6 @@ config SUPERH select HAVE_ARCH_KGDB select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK - select HAVE_COPY_THREAD_TLS select HAVE_DEBUG_BUGVERBOSE select HAVE_DEBUG_KMEMLEAK select HAVE_DYNAMIC_FTRACE diff --git a/arch/sh/boards/mach-sh03/rtc.c b/arch/sh/boards/mach-sh03/rtc.c index 8b23ed7c201c..7fb474844a2d 100644 --- a/arch/sh/boards/mach-sh03/rtc.c +++ b/arch/sh/boards/mach-sh03/rtc.c @@ -11,7 +11,6 @@ #include <linux/sched.h> #include <linux/time.h> #include <linux/bcd.h> -#include <linux/rtc.h> #include <linux/spinlock.h> #include <linux/io.h> #include <linux/rtc.h> diff --git a/arch/sh/configs/landisk_defconfig b/arch/sh/configs/landisk_defconfig index ba6ec042606f..e6c5ddf070c0 100644 --- a/arch/sh/configs/landisk_defconfig +++ b/arch/sh/configs/landisk_defconfig @@ -27,13 +27,12 @@ CONFIG_NETFILTER=y CONFIG_ATALK=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_OFFBOARD=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_AEC62XX=y +CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_ATP867X=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y +CONFIG_BLK_DEV_SR=y CONFIG_SCSI_MULTI_LUN=y CONFIG_MD=y CONFIG_BLK_DEV_MD=m diff --git a/arch/sh/configs/microdev_defconfig b/arch/sh/configs/microdev_defconfig index c65667d00313..e9825196dd66 100644 --- a/arch/sh/configs/microdev_defconfig +++ b/arch/sh/configs/microdev_defconfig @@ -20,8 +20,6 @@ CONFIG_IP_PNP=y # CONFIG_IPV6 is not set # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y CONFIG_SMC91X=y diff --git a/arch/sh/configs/sdk7780_defconfig b/arch/sh/configs/sdk7780_defconfig index d10a0414123a..d00376eb044f 100644 --- a/arch/sh/configs/sdk7780_defconfig +++ b/arch/sh/configs/sdk7780_defconfig @@ -44,16 +44,14 @@ CONFIG_NET_SCHED=y CONFIG_PARPORT=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_PLATFORM=y -CONFIG_BLK_DEV_GENERIC=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_SPI_ATTRS=y CONFIG_SCSI_FC_ATTRS=y CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_PLATFORM=y CONFIG_MD=y CONFIG_BLK_DEV_DM=y CONFIG_NETDEVICES=y diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig index 61bec46ebd66..4a44cac640bc 100644 --- a/arch/sh/configs/sdk7786_defconfig +++ b/arch/sh/configs/sdk7786_defconfig @@ -116,9 +116,6 @@ CONFIG_MTD_UBI_GLUEBI=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_CRYPTOLOOP=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_PLATFORM=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_SCSI_MULTI_LUN=y diff --git a/arch/sh/configs/se7750_defconfig b/arch/sh/configs/se7750_defconfig index 3f1c13799d79..4defc7628a49 100644 --- a/arch/sh/configs/se7750_defconfig +++ b/arch/sh/configs/se7750_defconfig @@ -29,7 +29,6 @@ CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_ROM=y -CONFIG_IDE=y CONFIG_SCSI=y CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig index f0073ed39947..48b457d59e79 100644 --- a/arch/sh/configs/sh03_defconfig +++ b/arch/sh/configs/sh03_defconfig @@ -39,9 +39,6 @@ CONFIG_IP_PNP_RARP=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=m -CONFIG_BLK_DEV_IDETAPE=m CONFIG_SCSI=m CONFIG_BLK_DEV_SD=m CONFIG_BLK_DEV_SR=m diff --git a/arch/sh/drivers/dma/Kconfig b/arch/sh/drivers/dma/Kconfig index d0de378beefe..7d54f284ce10 100644 --- a/arch/sh/drivers/dma/Kconfig +++ b/arch/sh/drivers/dma/Kconfig @@ -63,8 +63,7 @@ config PVR2_DMA config G2_DMA tristate "G2 Bus DMA support" - depends on SH_DREAMCAST - select SH_DMA_API + depends on SH_DREAMCAST && SH_DMA_API help This enables support for the DMA controller for the Dreamcast's G2 bus. Drivers that want this will generally enable this on diff --git a/arch/sh/include/asm/gpio.h b/arch/sh/include/asm/gpio.h index 351918894e86..d643250f0a0f 100644 --- a/arch/sh/include/asm/gpio.h +++ b/arch/sh/include/asm/gpio.h @@ -16,7 +16,6 @@ #include <cpu/gpio.h> #endif -#define ARCH_NR_GPIOS 512 #include <asm-generic/gpio.h> #ifdef CONFIG_GPIOLIB diff --git a/arch/sh/kernel/cpu/sh3/entry.S b/arch/sh/kernel/cpu/sh3/entry.S index 25eb80905416..e48b3dd996f5 100644 --- a/arch/sh/kernel/cpu/sh3/entry.S +++ b/arch/sh/kernel/cpu/sh3/entry.S @@ -14,7 +14,6 @@ #include <cpu/mmu_context.h> #include <asm/page.h> #include <asm/cache.h> -#include <asm/thread_info.h> ! NOTE: ! GNU as (as of 2.9.1) changes bf/s into bt/s and bra, when the address diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig index 703d3069997c..77aa2f802d8d 100644 --- a/arch/sh/mm/Kconfig +++ b/arch/sh/mm/Kconfig @@ -105,7 +105,7 @@ config VSYSCALL (the default value) say Y. config NUMA - bool "Non Uniform Memory Access (NUMA) Support" + bool "Non-Uniform Memory Access (NUMA) Support" depends on MMU && SYS_SUPPORTS_NUMA select ARCH_WANT_NUMA_VARIABLE_LOCALITY default n diff --git a/arch/sh/mm/asids-debugfs.c b/arch/sh/mm/asids-debugfs.c index 4c1ca197e9c5..d16d6f5ec774 100644 --- a/arch/sh/mm/asids-debugfs.c +++ b/arch/sh/mm/asids-debugfs.c @@ -26,7 +26,7 @@ #include <asm/processor.h> #include <asm/mmu_context.h> -static int asids_seq_show(struct seq_file *file, void *iter) +static int asids_debugfs_show(struct seq_file *file, void *iter) { struct task_struct *p; @@ -48,18 +48,7 @@ static int asids_seq_show(struct seq_file *file, void *iter) return 0; } -static int asids_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, asids_seq_show, inode->i_private); -} - -static const struct file_operations asids_debugfs_fops = { - .owner = THIS_MODULE, - .open = asids_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(asids_debugfs); static int __init asids_debugfs_init(void) { diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c index 17d780794497..b0f185169dfa 100644 --- a/arch/sh/mm/cache-debugfs.c +++ b/arch/sh/mm/cache-debugfs.c @@ -22,7 +22,7 @@ enum cache_type { CACHE_TYPE_UNIFIED, }; -static int cache_seq_show(struct seq_file *file, void *iter) +static int cache_debugfs_show(struct seq_file *file, void *iter) { unsigned int cache_type = (unsigned int)file->private; struct cache_info *cache; @@ -94,18 +94,7 @@ static int cache_seq_show(struct seq_file *file, void *iter) return 0; } -static int cache_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, cache_seq_show, inode->i_private); -} - -static const struct file_operations cache_debugfs_fops = { - .owner = THIS_MODULE, - .open = cache_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(cache_debugfs); static int __init cache_debugfs_init(void) { diff --git a/arch/sh/mm/pmb.c b/arch/sh/mm/pmb.c index b20aba6e1b37..68eb7cc6e564 100644 --- a/arch/sh/mm/pmb.c +++ b/arch/sh/mm/pmb.c @@ -812,7 +812,7 @@ bool __in_29bit_mode(void) return (__raw_readl(PMB_PASCR) & PASCR_SE) == 0; } -static int pmb_seq_show(struct seq_file *file, void *iter) +static int pmb_debugfs_show(struct seq_file *file, void *iter) { int i; @@ -846,18 +846,7 @@ static int pmb_seq_show(struct seq_file *file, void *iter) return 0; } -static int pmb_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, pmb_seq_show, NULL); -} - -static const struct file_operations pmb_debugfs_fops = { - .owner = THIS_MODULE, - .open = pmb_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(pmb_debugfs); static int __init pmb_debugfs_init(void) { diff --git a/arch/sparc/include/asm/highmem.h b/arch/sparc/include/asm/highmem.h index 875116209ec1..c7b2e208328b 100644 --- a/arch/sparc/include/asm/highmem.h +++ b/arch/sparc/include/asm/highmem.h @@ -50,10 +50,11 @@ extern pte_t *pkmap_page_table; #define flush_cache_kmaps() flush_cache_all() -/* FIXME: Use __flush_tlb_one(vaddr) instead of flush_cache_all() -- Anton */ -#define arch_kmap_local_post_map(vaddr, pteval) flush_cache_all() -#define arch_kmap_local_post_unmap(vaddr) flush_cache_all() - +/* FIXME: Use __flush_*_one(vaddr) instead of flush_*_all() -- Anton */ +#define arch_kmap_local_pre_map(vaddr, pteval) flush_cache_all() +#define arch_kmap_local_pre_unmap(vaddr) flush_cache_all() +#define arch_kmap_local_post_map(vaddr, pteval) flush_tlb_all() +#define arch_kmap_local_post_unmap(vaddr) flush_tlb_all() #endif /* __KERNEL__ */ diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 18d8f17f755c..0904f5676e4d 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -73,10 +73,8 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, unsigned int nr) { if (likely(nr < IA32_NR_syscalls)) { - instrumentation_begin(); nr = array_index_nospec(nr, IA32_NR_syscalls); regs->ax = ia32_sys_call_table[nr](regs); - instrumentation_end(); } } @@ -91,8 +89,11 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) * or may not be necessary, but it matches the old asm behavior. */ nr = (unsigned int)syscall_enter_from_user_mode(regs, nr); + instrumentation_begin(); do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); syscall_exit_to_user_mode(regs); } @@ -121,11 +122,12 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) res = get_user(*(u32 *)®s->bp, (u32 __user __force *)(unsigned long)(u32)regs->sp); } - instrumentation_end(); if (res) { /* User code screwed up. */ regs->ax = -EFAULT; + + instrumentation_end(); syscall_exit_to_user_mode(regs); return false; } @@ -135,6 +137,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) /* Now this is just like a normal syscall. */ do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); syscall_exit_to_user_mode(regs); return true; } diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index ccd32877a3c4..496b11ec469d 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -10,7 +10,7 @@ #include <asm/export.h> /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ - .macro THUNK name, func, put_ret_addr_in_rdi=0 + .macro THUNK name, func SYM_FUNC_START_NOALIGN(\name) pushq %rbp movq %rsp, %rbp @@ -25,13 +25,8 @@ SYM_FUNC_START_NOALIGN(\name) pushq %r10 pushq %r11 - .if \put_ret_addr_in_rdi - /* 8(%rbp) is return addr on stack */ - movq 8(%rbp), %rdi - .endif - call \func - jmp .L_restore + jmp __thunk_restore SYM_FUNC_END(\name) _ASM_NOKPROBE(\name) .endm @@ -44,7 +39,7 @@ SYM_FUNC_END(\name) #endif #ifdef CONFIG_PREEMPTION -SYM_CODE_START_LOCAL_NOALIGN(.L_restore) +SYM_CODE_START_LOCAL_NOALIGN(__thunk_restore) popq %r11 popq %r10 popq %r9 @@ -56,6 +51,6 @@ SYM_CODE_START_LOCAL_NOALIGN(.L_restore) popq %rdi popq %rbp ret - _ASM_NOKPROBE(.L_restore) -SYM_CODE_END(.L_restore) + _ASM_NOKPROBE(__thunk_restore) +SYM_CODE_END(__thunk_restore) #endif diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index e04d90af4c27..6375967a8244 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -16,6 +16,7 @@ #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> #include <asm/idtentry.h> +#include <linux/kexec.h> #include <linux/version.h> #include <linux/vmalloc.h> #include <linux/mm.h> @@ -26,6 +27,8 @@ #include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> +int hyperv_init_cpuhp; + void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); @@ -312,6 +315,25 @@ static struct syscore_ops hv_syscore_ops = { .resume = hv_resume, }; +static void (* __initdata old_setup_percpu_clockev)(void); + +static void __init hv_stimer_setup_percpu_clockev(void) +{ + /* + * Ignore any errors in setting up stimer clockevents + * as we can run with the LAPIC timer as a fallback. + */ + (void)hv_stimer_alloc(); + + /* + * Still register the LAPIC timer, because the direct-mode STIMER is + * not supported by old versions of Hyper-V. This also allows users + * to switch to LAPIC timer via /sys, if they want to. + */ + if (old_setup_percpu_clockev) + old_setup_percpu_clockev(); +} + /* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. @@ -390,10 +412,14 @@ void __init hyperv_init(void) wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); /* - * Ignore any errors in setting up stimer clockevents - * as we can run with the LAPIC timer as a fallback. + * hyperv_init() is called before LAPIC is initialized: see + * apic_intr_mode_init() -> x86_platform.apic_post_init() and + * apic_bsp_setup() -> setup_local_APIC(). The direct-mode STIMER + * depends on LAPIC, so hv_stimer_alloc() should be called from + * x86_init.timers.setup_percpu_clockev. */ - (void)hv_stimer_alloc(); + old_setup_percpu_clockev = x86_init.timers.setup_percpu_clockev; + x86_init.timers.setup_percpu_clockev = hv_stimer_setup_percpu_clockev; hv_apic_init(); @@ -401,6 +427,7 @@ void __init hyperv_init(void) register_syscore_ops(&hv_syscore_ops); + hyperv_init_cpuhp = cpuhp; return; remove_cpuhp_state: diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 5208ba49c89a..2c87350c1fb0 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -66,11 +66,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, if (!hv_hypercall_pg) goto do_native; - if (cpumask_empty(cpus)) - return; - local_irq_save(flags); + /* + * Only check the mask _after_ interrupt has been disabled to avoid the + * mask changing under our feet. + */ + if (cpumask_empty(cpus)) { + local_irq_restore(flags); + return; + } + flush_pcpu = (struct hv_tlb_flush **) this_cpu_ptr(hyperv_pcpu_input_arg); diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index a5aba4ab0224..67a4f1cb2aac 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -16,14 +16,25 @@ * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It * disables preemption so be careful if you intend to use it for long periods * of time. - * If you intend to use the FPU in softirq you need to check first with + * If you intend to use the FPU in irq/softirq you need to check first with * irq_fpu_usable() if it is possible. */ -extern void kernel_fpu_begin(void); + +/* Kernel FPU states to initialize in kernel_fpu_begin_mask() */ +#define KFPU_387 _BITUL(0) /* 387 state will be initialized */ +#define KFPU_MXCSR _BITUL(1) /* MXCSR will be initialized */ + +extern void kernel_fpu_begin_mask(unsigned int kfpu_mask); extern void kernel_fpu_end(void); extern bool irq_fpu_usable(void); extern void fpregs_mark_activate(void); +/* Code that is unaware of kernel_fpu_begin_mask() can use this */ +static inline void kernel_fpu_begin(void) +{ + kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR); +} + /* * Use fpregs_lock() while editing CPU's FPU registers or fpu->state. * A context switch will (and softirq might) save CPU's FPU registers to diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 247a60a47331..f656aabd1545 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -613,6 +613,7 @@ DECLARE_IDTENTRY_VC(X86_TRAP_VC, exc_vmm_communication); #ifdef CONFIG_XEN_PV DECLARE_IDTENTRY_XENCB(X86_TRAP_OTHER, exc_xen_hypervisor_callback); +DECLARE_IDTENTRY_RAW(X86_TRAP_OTHER, exc_xen_unknown_trap); #endif /* Device interrupts common/spurious */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 5e658ba2654a..9abe842dbd84 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -97,6 +97,7 @@ #define INTEL_FAM6_LAKEFIELD 0x8A #define INTEL_FAM6_ALDERLAKE 0x97 +#define INTEL_FAM6_ALDERLAKE_L 0x9A /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index ffc289992d1b..30f76b966857 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -74,6 +74,8 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {} #if IS_ENABLED(CONFIG_HYPERV) +extern int hyperv_init_cpuhp; + extern void *hv_hypercall_pg; extern void __percpu **hyperv_pcpu_input_arg; diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 0b4920a7238e..e16cccdd0420 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -86,7 +86,7 @@ static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {} * think of extending them - you will be slapped with a stinking trout or a frozen * shark will reach you, wherever you are! You've been warned. */ -static inline unsigned long long notrace __rdmsr(unsigned int msr) +static __always_inline unsigned long long __rdmsr(unsigned int msr) { DECLARE_ARGS(val, low, high); @@ -98,7 +98,7 @@ static inline unsigned long long notrace __rdmsr(unsigned int msr) return EAX_EDX_VAL(val, low, high); } -static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high) +static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) { asm volatile("1: wrmsr\n" "2:\n" diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 488a8e848754..9239399e5491 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -110,6 +110,8 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); #define topology_die_id(cpu) (cpu_data(cpu).cpu_die_id) #define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) +extern unsigned int __max_die_per_package; + #ifdef CONFIG_SMP #define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu)) #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) @@ -118,8 +120,6 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); extern unsigned int __max_logical_packages; #define topology_max_packages() (__max_logical_packages) -extern unsigned int __max_die_per_package; - static inline int topology_max_die_per_package(void) { return __max_die_per_package; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f8ca66f3d861..347a956f71ca 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -542,12 +542,12 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) u32 ecx; ecx = cpuid_ecx(0x8000001e); - nodes_per_socket = ((ecx >> 8) & 7) + 1; + __max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1; } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - nodes_per_socket = ((value >> 3) & 7) + 1; + __max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1; } if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 13d3f1cbda17..e133ce1e562b 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1992,10 +1992,9 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) * that out because it's an indirect call. Annotate it. */ instrumentation_begin(); - trace_hardirqs_off_finish(); + machine_check_vector(regs); - if (regs->flags & X86_EFLAGS_IF) - trace_hardirqs_on_prepare(); + instrumentation_end(); irqentry_nmi_exit(regs, irq_state); } @@ -2004,7 +2003,9 @@ static __always_inline void exc_machine_check_user(struct pt_regs *regs) { irqentry_enter_from_user_mode(regs); instrumentation_begin(); + machine_check_vector(regs); + instrumentation_end(); irqentry_exit_to_user_mode(regs); } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index f628e3dc150f..43b54bef5448 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -135,14 +135,32 @@ static void hv_machine_shutdown(void) { if (kexec_in_progress && hv_kexec_handler) hv_kexec_handler(); + + /* + * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor + * corrupts the old VP Assist Pages and can crash the kexec kernel. + */ + if (kexec_in_progress && hyperv_init_cpuhp > 0) + cpuhp_remove_state(hyperv_init_cpuhp); + + /* The function calls stop_other_cpus(). */ native_machine_shutdown(); + + /* Disable the hypercall page when there is only 1 active CPU. */ + if (kexec_in_progress) + hyperv_cleanup(); } static void hv_machine_crash_shutdown(struct pt_regs *regs) { if (hv_crash_handler) hv_crash_handler(regs); + + /* The function calls crash_smp_send_stop(). */ native_machine_crash_shutdown(regs); + + /* Disable the hypercall page when there is only 1 active CPU. */ + hyperv_cleanup(); } #endif /* CONFIG_KEXEC_CORE */ #endif /* CONFIG_HYPERV */ diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 1068002c8532..8678864ce712 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -25,10 +25,10 @@ #define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f) #define LEVEL_MAX_SIBLINGS(ebx) ((ebx) & 0xffff) -#ifdef CONFIG_SMP unsigned int __max_die_per_package __read_mostly = 1; EXPORT_SYMBOL(__max_die_per_package); +#ifdef CONFIG_SMP /* * Check if given CPUID extended toplogy "leaf" is implemented */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index eb86a2b831b1..571220ac8bea 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -121,7 +121,7 @@ int copy_fpregs_to_fpstate(struct fpu *fpu) } EXPORT_SYMBOL(copy_fpregs_to_fpstate); -void kernel_fpu_begin(void) +void kernel_fpu_begin_mask(unsigned int kfpu_mask) { preempt_disable(); @@ -141,13 +141,14 @@ void kernel_fpu_begin(void) } __cpu_invalidate_fpregs_state(); - if (boot_cpu_has(X86_FEATURE_XMM)) + /* Put sane initial values into the control registers. */ + if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM)) ldmxcsr(MXCSR_DEFAULT); - if (boot_cpu_has(X86_FEATURE_FPU)) + if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU)) asm volatile ("fninit"); } -EXPORT_SYMBOL_GPL(kernel_fpu_begin); +EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 740f3bdb3f61..3412c4595efd 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -661,17 +661,6 @@ static void __init trim_platform_memory_ranges(void) static void __init trim_bios_range(void) { /* - * A special case is the first 4Kb of memory; - * This is a BIOS owned area, not kernel ram, but generally - * not listed as such in the E820 table. - * - * This typically reserves additional memory (64KiB by default) - * since some BIOSes are known to corrupt low memory. See the - * Kconfig help text for X86_RESERVE_LOW. - */ - e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); - - /* * special case: Some BIOSes report the PC BIOS * area (640Kb -> 1Mb) as RAM even though it is not. * take them out. @@ -728,6 +717,15 @@ early_param("reservelow", parse_reservelow); static void __init trim_low_memory_range(void) { + /* + * A special case is the first 4Kb of memory; + * This is a BIOS owned area, not kernel ram, but generally + * not listed as such in the E820 table. + * + * This typically reserves additional memory (64KiB by default) + * since some BIOSes are known to corrupt low memory. See the + * Kconfig help text for X86_RESERVE_LOW. + */ memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE)); } diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 0bd1a0fc587e..84c1821819af 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -225,7 +225,7 @@ static inline u64 sev_es_rd_ghcb_msr(void) return __rdmsr(MSR_AMD64_SEV_ES_GHCB); } -static inline void sev_es_wr_ghcb_msr(u64 val) +static __always_inline void sev_es_wr_ghcb_msr(u64 val) { u32 low, high; @@ -286,6 +286,12 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; + /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ + if (!user_mode(ctxt->regs) && !access_ok(target, size)) { + memcpy(dst, buf, size); + return ES_OK; + } + switch (size) { case 1: memcpy(&d1, buf, 1); @@ -335,6 +341,12 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; + /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ + if (!user_mode(ctxt->regs) && !access_ok(s, size)) { + memcpy(buf, src, size); + return ES_OK; + } + switch (size) { case 1: if (get_user(d1, s)) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 8ca66af96a54..117e24fbfd8a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -56,6 +56,7 @@ #include <linux/numa.h> #include <linux/pgtable.h> #include <linux/overflow.h> +#include <linux/syscore_ops.h> #include <asm/acpi.h> #include <asm/desc.h> @@ -2083,6 +2084,23 @@ static void init_counter_refs(void) this_cpu_write(arch_prev_mperf, mperf); } +#ifdef CONFIG_PM_SLEEP +static struct syscore_ops freq_invariance_syscore_ops = { + .resume = init_counter_refs, +}; + +static void register_freq_invariance_syscore_ops(void) +{ + /* Bail out if registered already. */ + if (freq_invariance_syscore_ops.node.prev) + return; + + register_syscore_ops(&freq_invariance_syscore_ops); +} +#else +static inline void register_freq_invariance_syscore_ops(void) {} +#endif + static void init_freq_invariance(bool secondary, bool cppc_ready) { bool ret = false; @@ -2109,6 +2127,7 @@ static void init_freq_invariance(bool secondary, bool cppc_ready) if (ret) { init_counter_refs(); static_branch_enable(&arch_scale_freq_key); + register_freq_invariance_syscore_ops(); pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); } else { pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index f15bc16de07c..a889563ad02d 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -9,31 +9,6 @@ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE) -static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); -} - -static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); -} - -static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); -} - -static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); -} - #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ { \ @@ -43,7 +18,6 @@ static __always_inline void kvm_##lname##_write(struct kvm_vcpu *vcpu, \ unsigned long val) \ { \ vcpu->arch.regs[VCPU_REGS_##uname] = val; \ - kvm_register_mark_dirty(vcpu, VCPU_REGS_##uname); \ } BUILD_KVM_GPR_ACCESSORS(rax, RAX) BUILD_KVM_GPR_ACCESSORS(rbx, RBX) @@ -63,6 +37,31 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14) BUILD_KVM_GPR_ACCESSORS(r15, R15) #endif +static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + +static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg) { if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS)) diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 581925e476d6..261be1d2032b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -44,8 +44,15 @@ #define PT32_ROOT_LEVEL 2 #define PT32E_ROOT_LEVEL 3 -static inline u64 rsvd_bits(int s, int e) +static __always_inline u64 rsvd_bits(int s, int e) { + BUILD_BUG_ON(__builtin_constant_p(e) && __builtin_constant_p(s) && e < s); + + if (__builtin_constant_p(e)) + BUILD_BUG_ON(e > 63); + else + e &= 63; + if (e < s) return 0; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index cb4c6ee10029..7a605ad8254d 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -200,6 +200,9 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + if (WARN_ON(!is_guest_mode(vcpu))) + return true; + if (!nested_svm_vmrun_msrpm(svm)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index c8ffdbc81709..ac652bc476ae 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1415,16 +1415,13 @@ static void sev_es_sync_to_ghcb(struct vcpu_svm *svm) * to be returned: * GPRs RAX, RBX, RCX, RDX * - * Copy their values to the GHCB if they are dirty. + * Copy their values, even if they may not have been written during the + * VM-Exit. It's the guest's responsibility to not consume random data. */ - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RAX)) - ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]); - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RBX)) - ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]); - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RCX)) - ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]); - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RDX)) - ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]); + ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]); + ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]); + ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]); + ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]); } static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 7ef171790d02..f923e14e87df 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3739,6 +3739,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + trace_kvm_entry(vcpu); + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 0fbb46990dfc..f2b9bfb58206 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3124,13 +3124,9 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) return 0; } -static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) +static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) { - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_host_map *map; - struct page *page; - u64 hpa; /* * hv_evmcs may end up being not mapped after migration (when @@ -3153,6 +3149,17 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) } } + return true; +} + +static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct kvm_host_map *map; + struct page *page; + u64 hpa; + if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { /* * Translate L1 physical address to host physical @@ -3221,6 +3228,18 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS); else exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS); + + return true; +} + +static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) +{ + if (!nested_get_evmcs_page(vcpu)) + return false; + + if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu)) + return false; + return true; } @@ -6077,11 +6096,14 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu)) { sync_vmcs02_to_vmcs12(vcpu, vmcs12); sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - } else if (!vmx->nested.need_vmcs12_to_shadow_sync) { - if (vmx->nested.hv_evmcs) - copy_enlightened_to_vmcs12(vmx); - else if (enable_shadow_vmcs) - copy_shadow_to_vmcs12(vmx); + } else { + copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu)); + if (!vmx->nested.need_vmcs12_to_shadow_sync) { + if (vmx->nested.hv_evmcs) + copy_enlightened_to_vmcs12(vmx); + else if (enable_shadow_vmcs) + copy_shadow_to_vmcs12(vmx); + } } BUILD_BUG_ON(sizeof(user_vmx_nested_state->vmcs12) < VMCS12_SIZE); @@ -6602,7 +6624,7 @@ struct kvm_x86_nested_ops vmx_nested_ops = { .hv_timer_pending = nested_vmx_preemption_timer_pending, .get_state = vmx_get_nested_state, .set_state = vmx_set_nested_state, - .get_nested_state_pages = nested_get_vmcs12_pages, + .get_nested_state_pages = vmx_get_nested_state_pages, .write_log_dirty = nested_vmx_write_pml_buffer, .enable_evmcs = nested_enable_evmcs, .get_evmcs_version = nested_get_evmcs_version, diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index a886a47daebd..cdf5f34518f4 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -29,7 +29,7 @@ static struct kvm_event_hw_type_mapping intel_arch_events[] = { [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, - [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES }, + [7] = { 0x00, 0x03, PERF_COUNT_HW_REF_CPU_CYCLES }, }; /* mapping between fixed pmc index and intel_arch_events array */ @@ -345,7 +345,9 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, x86_pmu.num_counters_gp); + eax.split.bit_width = min_t(int, eax.split.bit_width, x86_pmu.bit_width_gp); pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1; + eax.split.mask_length = min_t(int, eax.split.mask_length, x86_pmu.events_mask_len); pmu->available_event_types = ~entry->ebx & ((1ull << eax.split.mask_length) - 1); @@ -355,6 +357,8 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->nr_arch_fixed_counters = min_t(int, edx.split.num_counters_fixed, x86_pmu.num_counters_fixed); + edx.split.bit_width_fixed = min_t(int, + edx.split.bit_width_fixed, x86_pmu.bit_width_fixed); pmu->counter_bitmask[KVM_PMC_FIXED] = ((u64)1 << edx.split.bit_width_fixed) - 1; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 2af05d3b0590..cc60b1fc3ee7 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6653,6 +6653,8 @@ reenter_guest: if (vmx->emulation_required) return EXIT_FASTPATH_NONE; + trace_kvm_entry(vcpu); + if (vmx->ple_window_dirty) { vmx->ple_window_dirty = false; vmcs_write32(PLE_WINDOW, vmx->ple_window); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9a8969a6dd06..76bce832cade 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -105,6 +105,7 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; static void update_cr8_intercept(struct kvm_vcpu *vcpu); static void process_nmi(struct kvm_vcpu *vcpu); +static void process_smi(struct kvm_vcpu *vcpu); static void enter_smm(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); @@ -4230,6 +4231,9 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, { process_nmi(vcpu); + if (kvm_check_request(KVM_REQ_SMI, vcpu)) + process_smi(vcpu); + /* * In guest mode, payload delivery should be deferred, * so that the L1 hypervisor can intercept #PF before @@ -8802,9 +8806,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { - if (WARN_ON_ONCE(!is_guest_mode(vcpu))) - ; - else if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { + if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { r = 0; goto out; } @@ -8988,8 +8990,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_x86_ops.request_immediate_exit(vcpu); } - trace_kvm_entry(vcpu); - fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) switch_fpu_return(); @@ -11556,6 +11556,7 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size, } EXPORT_SYMBOL_GPL(kvm_sev_es_string_io); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_entry); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c index 4321fa02e18d..419365c48b2a 100644 --- a/arch/x86/lib/mmx_32.c +++ b/arch/x86/lib/mmx_32.c @@ -26,6 +26,16 @@ #include <asm/fpu/api.h> #include <asm/asm.h> +/* + * Use KFPU_387. MMX instructions are not affected by MXCSR, + * but both AMD and Intel documentation states that even integer MMX + * operations will result in #MF if an exception is pending in FCW. + * + * EMMS is not needed afterwards because, after calling kernel_fpu_end(), + * any subsequent user of the 387 stack will reinitialize it using + * KFPU_387. + */ + void *_mmx_memcpy(void *to, const void *from, size_t len) { void *p; @@ -37,7 +47,7 @@ void *_mmx_memcpy(void *to, const void *from, size_t len) p = to; i = len >> 6; /* len/64 */ - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( "1: prefetch (%0)\n" /* This set is 28 bytes */ @@ -127,7 +137,7 @@ static void fast_clear_page(void *page) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( " pxor %%mm0, %%mm0\n" : : @@ -160,7 +170,7 @@ static void fast_copy_page(void *to, void *from) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); /* * maybe the prefetch stuff can go before the expensive fnsave... @@ -247,7 +257,7 @@ static void fast_clear_page(void *page) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( " pxor %%mm0, %%mm0\n" : : @@ -282,7 +292,7 @@ static void fast_copy_page(void *to, void *from) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( "1: prefetch (%0)\n" diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 9e87ab010c82..e68ea5f4ad1c 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -164,10 +164,10 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu) else per_cpu(xen_vcpu_id, cpu) = cpu; rc = xen_vcpu_setup(cpu); - if (rc) + if (rc || !xen_have_vector_callback) return rc; - if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock)) + if (xen_feature(XENFEAT_hvm_safe_pvclock)) xen_setup_timer(cpu); rc = xen_smp_intr_init(cpu); @@ -188,6 +188,8 @@ static int xen_cpu_dead_hvm(unsigned int cpu) return 0; } +static bool no_vector_callback __initdata; + static void __init xen_hvm_guest_init(void) { if (xen_pv_domain()) @@ -207,7 +209,7 @@ static void __init xen_hvm_guest_init(void) xen_panic_handler_init(); - if (xen_feature(XENFEAT_hvm_callback_vector)) + if (!no_vector_callback && xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; xen_hvm_smp_init(); @@ -233,6 +235,13 @@ static __init int xen_parse_nopv(char *arg) } early_param("xen_nopv", xen_parse_nopv); +static __init int xen_parse_no_vector_callback(char *arg) +{ + no_vector_callback = true; + return 0; +} +early_param("xen_no_vector_callback", xen_parse_no_vector_callback); + bool __init xen_hvm_need_lapic(void) { if (xen_pv_domain()) diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 4409306364dc..9a5a50cdaab5 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -583,6 +583,13 @@ DEFINE_IDTENTRY_RAW(xenpv_exc_debug) exc_debug(regs); } +DEFINE_IDTENTRY_RAW(exc_xen_unknown_trap) +{ + /* This should never happen and there is no way to handle it. */ + pr_err("Unknown trap in Xen PV mode."); + BUG(); +} + struct trap_array_entry { void (*orig)(void); void (*xen)(void); @@ -631,6 +638,7 @@ static bool __ref get_trap_addr(void **addr, unsigned int ist) { unsigned int nr; bool ist_okay = false; + bool found = false; /* * Replace trap handler addresses by Xen specific ones. @@ -645,6 +653,7 @@ static bool __ref get_trap_addr(void **addr, unsigned int ist) if (*addr == entry->orig) { *addr = entry->xen; ist_okay = entry->ist_okay; + found = true; break; } } @@ -655,9 +664,13 @@ static bool __ref get_trap_addr(void **addr, unsigned int ist) nr = (*addr - (void *)early_idt_handler_array[0]) / EARLY_IDT_HANDLER_SIZE; *addr = (void *)xen_early_idt_handler_array[nr]; + found = true; } - if (WARN_ON(ist != 0 && !ist_okay)) + if (!found) + *addr = (void *)xen_asm_exc_xen_unknown_trap; + + if (WARN_ON(found && ist != 0 && !ist_okay)) return false; return true; diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c index f5e7db4f82ab..6ff3c887e0b9 100644 --- a/arch/x86/xen/smp_hvm.c +++ b/arch/x86/xen/smp_hvm.c @@ -33,9 +33,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) int cpu; native_smp_prepare_cpus(max_cpus); - WARN_ON(xen_smp_intr_init(0)); - xen_init_lock_cpu(0); + if (xen_have_vector_callback) { + WARN_ON(xen_smp_intr_init(0)); + xen_init_lock_cpu(0); + } for_each_possible_cpu(cpu) { if (cpu == 0) @@ -50,9 +52,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) static void xen_hvm_cpu_die(unsigned int cpu) { if (common_cpu_die(cpu) == 0) { - xen_smp_intr_free(cpu); - xen_uninit_lock_cpu(cpu); - xen_teardown_timer(cpu); + if (xen_have_vector_callback) { + xen_smp_intr_free(cpu); + xen_uninit_lock_cpu(cpu); + xen_teardown_timer(cpu); + } } } #else @@ -64,14 +68,19 @@ static void xen_hvm_cpu_die(unsigned int cpu) void __init xen_hvm_smp_init(void) { - if (!xen_have_vector_callback) + smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu; + smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; + smp_ops.smp_cpus_done = xen_smp_cpus_done; + smp_ops.cpu_die = xen_hvm_cpu_die; + + if (!xen_have_vector_callback) { +#ifdef CONFIG_PARAVIRT_SPINLOCKS + nopvspin = true; +#endif return; + } - smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; smp_ops.smp_send_reschedule = xen_smp_send_reschedule; - smp_ops.cpu_die = xen_hvm_cpu_die; smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi; smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi; - smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu; - smp_ops.smp_cpus_done = xen_smp_cpus_done; } diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 1cb0e84b9161..53cf8aa35032 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -178,6 +178,7 @@ xen_pv_trap asm_exc_simd_coprocessor_error #ifdef CONFIG_IA32_EMULATION xen_pv_trap entry_INT80_compat #endif +xen_pv_trap asm_exc_xen_unknown_trap xen_pv_trap asm_exc_xen_hypervisor_callback __INIT |