diff options
Diffstat (limited to 'arch')
56 files changed, 905 insertions, 286 deletions
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 8e5ffb58f83e..b7afaa026842 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -31,6 +31,13 @@ .Lskip_hcrx_\@: .endm +/* Check if running in host at EL2 mode, i.e., (h)VHE. Jump to fail if not. */ +.macro __check_hvhe fail, tmp + mrs \tmp, hcr_el2 + and \tmp, \tmp, #HCR_E2H + cbz \tmp, \fail +.endm + /* * Allow Non-secure EL1 and EL0 to access physical timer and counter. * This is not necessary for VHE, since the host kernel runs in EL2, @@ -43,9 +50,7 @@ */ .macro __init_el2_timers mov x0, #3 // Enable EL1 physical timers - mrs x1, hcr_el2 - and x1, x1, #HCR_E2H - cbz x1, .LnVHE_\@ + __check_hvhe .LnVHE_\@, x1 lsl x0, x0, #10 .LnVHE_\@: msr cnthctl_el2, x0 @@ -139,15 +144,14 @@ /* Coprocessor traps */ .macro __init_el2_cptr - mrs x1, hcr_el2 - and x1, x1, #HCR_E2H - cbz x1, .LnVHE_\@ + __check_hvhe .LnVHE_\@, x1 mov x0, #(CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN) - b .Lset_cptr_\@ + msr cpacr_el1, x0 + b .Lskip_set_cptr_\@ .LnVHE_\@: mov x0, #0x33ff -.Lset_cptr_\@: msr cptr_el2, x0 // Disable copro. traps to EL2 +.Lskip_set_cptr_\@: .endm /* Disable any fine grained traps */ @@ -268,19 +272,19 @@ check_override id_aa64pfr0, ID_AA64PFR0_EL1_SVE_SHIFT, .Linit_sve_\@, .Lskip_sve_\@, x1, x2 .Linit_sve_\@: /* SVE register access */ - mrs x0, cptr_el2 // Disable SVE traps - mrs x1, hcr_el2 - and x1, x1, #HCR_E2H - cbz x1, .Lcptr_nvhe_\@ + __check_hvhe .Lcptr_nvhe_\@, x1 - // VHE case + // (h)VHE case + mrs x0, cpacr_el1 // Disable SVE traps orr x0, x0, #(CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN) - b .Lset_cptr_\@ + msr cpacr_el1, x0 + b .Lskip_set_cptr_\@ .Lcptr_nvhe_\@: // nVHE case + mrs x0, cptr_el2 // Disable SVE traps bic x0, x0, #CPTR_EL2_TZ -.Lset_cptr_\@: msr cptr_el2, x0 +.Lskip_set_cptr_\@: isb mov x1, #ZCR_ELx_LEN_MASK // SVE: Enable full vector msr_s SYS_ZCR_EL2, x1 // length for EL1. @@ -289,9 +293,19 @@ check_override id_aa64pfr1, ID_AA64PFR1_EL1_SME_SHIFT, .Linit_sme_\@, .Lskip_sme_\@, x1, x2 .Linit_sme_\@: /* SME register access and priority mapping */ + __check_hvhe .Lcptr_nvhe_sme_\@, x1 + + // (h)VHE case + mrs x0, cpacr_el1 // Disable SME traps + orr x0, x0, #(CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN) + msr cpacr_el1, x0 + b .Lskip_set_cptr_sme_\@ + +.Lcptr_nvhe_sme_\@: // nVHE case mrs x0, cptr_el2 // Disable SME traps bic x0, x0, #CPTR_EL2_TSM msr cptr_el2, x0 +.Lskip_set_cptr_sme_\@: isb mrs x1, sctlr_el2 diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 7d170aaa2db4..24e28bb2d95b 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -278,7 +278,7 @@ asmlinkage void __noreturn hyp_panic_bad_stack(void); asmlinkage void kvm_unexpected_el2_exception(void); struct kvm_cpu_context; void handle_trap(struct kvm_cpu_context *host_ctxt); -asmlinkage void __noreturn kvm_host_psci_cpu_entry(bool is_cpu_on); +asmlinkage void __noreturn __kvm_host_psci_cpu_entry(bool is_cpu_on); void __noreturn __pkvm_init_finalise(void); void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc); void kvm_patch_vector_branch(struct alt_instr *alt, diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index efc0b45d79c3..3d6725ff0bf6 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -571,6 +571,14 @@ static inline bool vcpu_has_feature(struct kvm_vcpu *vcpu, int feature) return test_bit(feature, vcpu->arch.features); } +static __always_inline void kvm_write_cptr_el2(u64 val) +{ + if (has_vhe() || has_hvhe()) + write_sysreg(val, cpacr_el1); + else + write_sysreg(val, cptr_el2); +} + static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu) { u64 val; @@ -578,8 +586,16 @@ static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu) if (has_vhe()) { val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN | CPACR_EL1_ZEN_EL1EN); + if (cpus_have_final_cap(ARM64_SME)) + val |= CPACR_EL1_SMEN_EL1EN; } else if (has_hvhe()) { val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN); + + if (!vcpu_has_sve(vcpu) || + (vcpu->arch.fp_state != FP_STATE_GUEST_OWNED)) + val |= CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN; + if (cpus_have_final_cap(ARM64_SME)) + val |= CPACR_EL1_SMEN_EL1EN | CPACR_EL1_SMEN_EL0EN; } else { val = CPTR_NVHE_EL2_RES1; @@ -597,9 +613,6 @@ static __always_inline void kvm_reset_cptr_el2(struct kvm_vcpu *vcpu) { u64 val = kvm_get_reset_cptr_el2(vcpu); - if (has_vhe() || has_hvhe()) - write_sysreg(val, cpacr_el1); - else - write_sysreg(val, cptr_el2); + kvm_write_cptr_el2(val); } #endif /* __ARM64_KVM_EMULATE_H__ */ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 72dc53a75d1c..d1cb298a58a0 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -55,7 +55,7 @@ DECLARE_KVM_NVHE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); static bool vgic_present, kvm_arm_initialised; -static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled); +static DEFINE_PER_CPU(unsigned char, kvm_hyp_initialized); DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use); bool is_kvm_arm_initialised(void) @@ -1864,18 +1864,24 @@ static void cpu_hyp_reinit(void) cpu_hyp_init_features(); } -static void _kvm_arch_hardware_enable(void *discard) +static void cpu_hyp_init(void *discard) { - if (!__this_cpu_read(kvm_arm_hardware_enabled)) { + if (!__this_cpu_read(kvm_hyp_initialized)) { cpu_hyp_reinit(); - __this_cpu_write(kvm_arm_hardware_enabled, 1); + __this_cpu_write(kvm_hyp_initialized, 1); } } -int kvm_arch_hardware_enable(void) +static void cpu_hyp_uninit(void *discard) { - int was_enabled; + if (__this_cpu_read(kvm_hyp_initialized)) { + cpu_hyp_reset(); + __this_cpu_write(kvm_hyp_initialized, 0); + } +} +int kvm_arch_hardware_enable(void) +{ /* * Most calls to this function are made with migration * disabled, but not with preemption disabled. The former is @@ -1884,36 +1890,23 @@ int kvm_arch_hardware_enable(void) */ preempt_disable(); - was_enabled = __this_cpu_read(kvm_arm_hardware_enabled); - _kvm_arch_hardware_enable(NULL); + cpu_hyp_init(NULL); - if (!was_enabled) { - kvm_vgic_cpu_up(); - kvm_timer_cpu_up(); - } + kvm_vgic_cpu_up(); + kvm_timer_cpu_up(); preempt_enable(); return 0; } -static void _kvm_arch_hardware_disable(void *discard) -{ - if (__this_cpu_read(kvm_arm_hardware_enabled)) { - cpu_hyp_reset(); - __this_cpu_write(kvm_arm_hardware_enabled, 0); - } -} - void kvm_arch_hardware_disable(void) { - if (__this_cpu_read(kvm_arm_hardware_enabled)) { - kvm_timer_cpu_down(); - kvm_vgic_cpu_down(); - } + kvm_timer_cpu_down(); + kvm_vgic_cpu_down(); if (!is_protected_kvm_enabled()) - _kvm_arch_hardware_disable(NULL); + cpu_hyp_uninit(NULL); } #ifdef CONFIG_CPU_PM @@ -1922,16 +1915,16 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self, void *v) { /* - * kvm_arm_hardware_enabled is left with its old value over + * kvm_hyp_initialized is left with its old value over * PM_ENTER->PM_EXIT. It is used to indicate PM_EXIT should * re-enable hyp. */ switch (cmd) { case CPU_PM_ENTER: - if (__this_cpu_read(kvm_arm_hardware_enabled)) + if (__this_cpu_read(kvm_hyp_initialized)) /* - * don't update kvm_arm_hardware_enabled here - * so that the hardware will be re-enabled + * don't update kvm_hyp_initialized here + * so that the hyp will be re-enabled * when we resume. See below. */ cpu_hyp_reset(); @@ -1939,8 +1932,8 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self, return NOTIFY_OK; case CPU_PM_ENTER_FAILED: case CPU_PM_EXIT: - if (__this_cpu_read(kvm_arm_hardware_enabled)) - /* The hardware was enabled before suspend. */ + if (__this_cpu_read(kvm_hyp_initialized)) + /* The hyp was enabled before suspend. */ cpu_hyp_reinit(); return NOTIFY_OK; @@ -2021,7 +2014,7 @@ static int __init init_subsystems(void) /* * Enable hardware so that subsystem initialisation can access EL2. */ - on_each_cpu(_kvm_arch_hardware_enable, NULL, 1); + on_each_cpu(cpu_hyp_init, NULL, 1); /* * Register CPU lower-power notifier @@ -2059,7 +2052,7 @@ out: hyp_cpu_pm_exit(); if (err || !is_protected_kvm_enabled()) - on_each_cpu(_kvm_arch_hardware_disable, NULL, 1); + on_each_cpu(cpu_hyp_uninit, NULL, 1); return err; } @@ -2097,7 +2090,7 @@ static int __init do_pkvm_init(u32 hyp_va_bits) * The stub hypercalls are now disabled, so set our local flag to * prevent a later re-init attempt in kvm_arch_hardware_enable(). */ - __this_cpu_write(kvm_arm_hardware_enabled, 1); + __this_cpu_write(kvm_hyp_initialized, 1); preempt_enable(); return ret; diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 4bddb8541bec..34f222af6165 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -457,6 +457,7 @@ static bool handle_ampere1_tcr(struct kvm_vcpu *vcpu) */ val &= ~(TCR_HD | TCR_HA); write_sysreg_el1(val, SYS_TCR); + __kvm_skip_instr(vcpu); return true; } diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c index 58dcd92bf346..ab4f5d160c58 100644 --- a/arch/arm64/kvm/hyp/nvhe/ffa.c +++ b/arch/arm64/kvm/hyp/nvhe/ffa.c @@ -705,7 +705,20 @@ int hyp_ffa_init(void *pages) if (res.a0 == FFA_RET_NOT_SUPPORTED) return 0; - if (res.a0 != FFA_VERSION_1_0) + /* + * Firmware returns the maximum supported version of the FF-A + * implementation. Check that the returned version is + * backwards-compatible with the hyp according to the rules in DEN0077A + * v1.1 REL0 13.2.1. + * + * Of course, things are never simple when dealing with firmware. v1.1 + * broke ABI with v1.0 on several structures, which is itself + * incompatible with the aforementioned versioning scheme. The + * expectation is that v1.x implementations that do not support the v1.0 + * ABI return NOT_SUPPORTED rather than a version number, according to + * DEN0077A v1.1 REL0 18.6.4. + */ + if (FFA_MAJOR_VERSION(res.a0) != 1) return -EOPNOTSUPP; arm_smccc_1_1_smc(FFA_ID_GET, 0, 0, 0, 0, 0, 0, 0, &res); diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 0a6271052def..e89a23153e85 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -63,7 +63,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu) __activate_traps_fpsimd32(vcpu); } - write_sysreg(val, cptr_el2); + kvm_write_cptr_el2(val); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2); if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { diff --git a/arch/parisc/Kconfig.debug b/arch/parisc/Kconfig.debug index 1401e4c5fe5f..bf2b21b96f0b 100644 --- a/arch/parisc/Kconfig.debug +++ b/arch/parisc/Kconfig.debug @@ -2,7 +2,7 @@ # config LIGHTWEIGHT_SPINLOCK_CHECK bool "Enable lightweight spinlock checks" - depends on SMP && !DEBUG_SPINLOCK + depends on DEBUG_KERNEL && SMP && !DEBUG_SPINLOCK default y help Add checks with low performance impact to the spinlock functions diff --git a/arch/parisc/boot/compressed/misc.c b/arch/parisc/boot/compressed/misc.c index 7ee49f5881d1..d389359e22ac 100644 --- a/arch/parisc/boot/compressed/misc.c +++ b/arch/parisc/boot/compressed/misc.c @@ -117,7 +117,7 @@ char *strchr(const char *s, int c) return NULL; } -int puts(const char *s) +static int puts(const char *s) { const char *nuline = s; @@ -172,7 +172,7 @@ static int print_num(unsigned long num, int base) return 0; } -int printf(const char *fmt, ...) +static int printf(const char *fmt, ...) { va_list args; int i = 0; @@ -204,13 +204,13 @@ void abort(void) } #undef malloc -void *malloc(size_t size) +static void *malloc(size_t size) { return malloc_gzip(size); } #undef free -void free(void *ptr) +static void free(void *ptr) { return free_gzip(ptr); } @@ -278,7 +278,7 @@ static void parse_elf(void *output) free(phdrs); } -unsigned long decompress_kernel(unsigned int started_wide, +asmlinkage unsigned long __visible decompress_kernel(unsigned int started_wide, unsigned int command_line, const unsigned int rd_start, const unsigned int rd_end) diff --git a/arch/parisc/include/asm/dma.h b/arch/parisc/include/asm/dma.h index 9e8c101de902..582fb5d1a5d5 100644 --- a/arch/parisc/include/asm/dma.h +++ b/arch/parisc/include/asm/dma.h @@ -14,6 +14,8 @@ #define dma_outb outb #define dma_inb inb +extern unsigned long pcxl_dma_start; + /* ** DMA_CHUNK_SIZE is used by the SCSI mid-layer to break up ** (or rather not merge) DMAs into manageable chunks. diff --git a/arch/parisc/include/asm/ftrace.h b/arch/parisc/include/asm/ftrace.h index a7cf0d05ccf4..f1cc1ee3a647 100644 --- a/arch/parisc/include/asm/ftrace.h +++ b/arch/parisc/include/asm/ftrace.h @@ -12,6 +12,10 @@ extern void mcount(void); extern unsigned long sys_call_table[]; extern unsigned long return_address(unsigned int); +struct ftrace_regs; +extern void ftrace_function_trampoline(unsigned long parent, + unsigned long self_addr, unsigned long org_sp_gr3, + struct ftrace_regs *fregs); #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_caller(void); diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index edfcb9858bcb..0b326e52255e 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -7,8 +7,6 @@ #include <asm/processor.h> #include <asm/spinlock_types.h> -#define SPINLOCK_BREAK_INSN 0x0000c006 /* break 6,6 */ - static inline void arch_spin_val_check(int lock_val) { if (IS_ENABLED(CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK)) diff --git a/arch/parisc/include/asm/spinlock_types.h b/arch/parisc/include/asm/spinlock_types.h index d65934079ebd..efd06a897c6a 100644 --- a/arch/parisc/include/asm/spinlock_types.h +++ b/arch/parisc/include/asm/spinlock_types.h @@ -4,6 +4,10 @@ #define __ARCH_SPIN_LOCK_UNLOCKED_VAL 0x1a46 +#define SPINLOCK_BREAK_INSN 0x0000c006 /* break 6,6 */ + +#ifndef __ASSEMBLY__ + typedef struct { #ifdef CONFIG_PA20 volatile unsigned int slock; @@ -27,6 +31,8 @@ typedef struct { volatile unsigned int counter; } arch_rwlock_t; +#endif /* __ASSEMBLY__ */ + #define __ARCH_RW_LOCK_UNLOCKED__ 0x01000000 #define __ARCH_RW_LOCK_UNLOCKED { .lock_mutex = __ARCH_SPIN_LOCK_UNLOCKED, \ .counter = __ARCH_RW_LOCK_UNLOCKED__ } diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 6d1c781eb1db..8f37e75f2fb9 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -74,8 +74,8 @@ static DEFINE_SPINLOCK(pdc_lock); #endif -unsigned long pdc_result[NUM_PDC_RESULT] __aligned(8); -unsigned long pdc_result2[NUM_PDC_RESULT] __aligned(8); +static unsigned long pdc_result[NUM_PDC_RESULT] __aligned(8); +static unsigned long pdc_result2[NUM_PDC_RESULT] __aligned(8); #ifdef CONFIG_64BIT #define WIDE_FIRMWARE 0x1 @@ -334,7 +334,7 @@ int __pdc_cpu_rendezvous(void) /** * pdc_cpu_rendezvous_lock - Lock PDC while transitioning to rendezvous state */ -void pdc_cpu_rendezvous_lock(void) +void pdc_cpu_rendezvous_lock(void) __acquires(&pdc_lock) { spin_lock(&pdc_lock); } @@ -342,7 +342,7 @@ void pdc_cpu_rendezvous_lock(void) /** * pdc_cpu_rendezvous_unlock - Unlock PDC after reaching rendezvous state */ -void pdc_cpu_rendezvous_unlock(void) +void pdc_cpu_rendezvous_unlock(void) __releases(&pdc_lock) { spin_unlock(&pdc_lock); } diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index 4d392e4ed358..d1defb9ede70 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -53,7 +53,7 @@ static void __hot prepare_ftrace_return(unsigned long *parent, static ftrace_func_t ftrace_func; -void notrace __hot ftrace_function_trampoline(unsigned long parent, +asmlinkage void notrace __hot ftrace_function_trampoline(unsigned long parent, unsigned long self_addr, unsigned long org_sp_gr3, struct ftrace_regs *fregs) diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 00297e8e1c88..6f0c92e8149d 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/syscalls.h> +#include <linux/libgcc.h> #include <linux/string.h> EXPORT_SYMBOL(memset); @@ -92,12 +93,6 @@ EXPORT_SYMBOL($$divI_12); EXPORT_SYMBOL($$divI_14); EXPORT_SYMBOL($$divI_15); -extern void __ashrdi3(void); -extern void __ashldi3(void); -extern void __lshrdi3(void); -extern void __muldi3(void); -extern void __ucmpdi2(void); - EXPORT_SYMBOL(__ashrdi3); EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__lshrdi3); diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index 3f6b507970eb..bf9f192c826e 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -39,7 +39,7 @@ static struct proc_dir_entry * proc_gsc_root __read_mostly = NULL; static unsigned long pcxl_used_bytes __read_mostly; static unsigned long pcxl_used_pages __read_mostly; -extern unsigned long pcxl_dma_start; /* Start of pcxl dma mapping area */ +unsigned long pcxl_dma_start __ro_after_init; /* pcxl dma mapping area start */ static DEFINE_SPINLOCK(pcxl_res_lock); static char *pcxl_res_map; static int pcxl_res_hint; @@ -381,7 +381,7 @@ pcxl_dma_init(void) pcxl_res_map = (char *)__get_free_pages(GFP_KERNEL, get_order(pcxl_res_size)); memset(pcxl_res_map, 0, pcxl_res_size); - proc_gsc_root = proc_mkdir("gsc", NULL); + proc_gsc_root = proc_mkdir("bus/gsc", NULL); if (!proc_gsc_root) printk(KERN_WARNING "pcxl_dma_init: Unable to create gsc /proc dir entry\n"); diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c index 0d24735bd918..0f9b3b5914cf 100644 --- a/arch/parisc/kernel/pdt.c +++ b/arch/parisc/kernel/pdt.c @@ -354,10 +354,8 @@ static int __init pdt_initcall(void) return -ENODEV; kpdtd_task = kthread_run(pdt_mainloop, NULL, "kpdtd"); - if (IS_ERR(kpdtd_task)) - return PTR_ERR(kpdtd_task); - return 0; + return PTR_ERR_OR_ZERO(kpdtd_task); } late_initcall(pdt_initcall); diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c index 90b04d8af212..b0f0816879df 100644 --- a/arch/parisc/kernel/perf.c +++ b/arch/parisc/kernel/perf.c @@ -57,7 +57,7 @@ struct rdr_tbl_ent { static int perf_processor_interface __read_mostly = UNKNOWN_INTF; static int perf_enabled __read_mostly; static DEFINE_SPINLOCK(perf_lock); -struct parisc_device *cpu_device __read_mostly; +static struct parisc_device *cpu_device __read_mostly; /* RDRs to write for PCX-W */ static const int perf_rdrs_W[] = diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 00b0df97afb1..762289b9984e 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -26,6 +26,7 @@ #include <asm/processor.h> #include <asm/page.h> #include <asm/pdc.h> +#include <asm/smp.h> #include <asm/pdcpat.h> #include <asm/irq.h> /* for struct irq_region */ #include <asm/parisc-device.h> diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index 573f8303e2b0..211a4afdd282 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -40,11 +40,6 @@ static char __initdata command_line[COMMAND_LINE_SIZE]; -/* Intended for ccio/sba/cpu statistics under /proc/bus/{runway|gsc} */ -struct proc_dir_entry * proc_runway_root __read_mostly = NULL; -struct proc_dir_entry * proc_gsc_root __read_mostly = NULL; -struct proc_dir_entry * proc_mckinley_root __read_mostly = NULL; - static void __init setup_cmdline(char **cmdline_p) { extern unsigned int boot_args[]; @@ -196,48 +191,6 @@ const struct seq_operations cpuinfo_op = { .show = show_cpuinfo }; -static void __init parisc_proc_mkdir(void) -{ - /* - ** Can't call proc_mkdir() until after proc_root_init() has been - ** called by start_kernel(). In other words, this code can't - ** live in arch/.../setup.c because start_parisc() calls - ** start_kernel(). - */ - switch (boot_cpu_data.cpu_type) { - case pcxl: - case pcxl2: - if (NULL == proc_gsc_root) - { - proc_gsc_root = proc_mkdir("bus/gsc", NULL); - } - break; - case pcxt_: - case pcxu: - case pcxu_: - case pcxw: - case pcxw_: - case pcxw2: - if (NULL == proc_runway_root) - { - proc_runway_root = proc_mkdir("bus/runway", NULL); - } - break; - case mako: - case mako2: - if (NULL == proc_mckinley_root) - { - proc_mckinley_root = proc_mkdir("bus/mckinley", NULL); - } - break; - default: - /* FIXME: this was added to prevent the compiler - * complaining about missing pcx, pcxs and pcxt - * I'm assuming they have neither gsc nor runway */ - break; - } -} - static struct resource central_bus = { .name = "Central Bus", .start = F_EXTEND(0xfff80000), @@ -294,7 +247,6 @@ static int __init parisc_init(void) { u32 osid = (OS_ID_LINUX << 16); - parisc_proc_mkdir(); parisc_init_resources(); do_device_inventory(); /* probe for hardware */ diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index f886ff0c75df..e8d27def6c52 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -423,7 +423,7 @@ static void check_syscallno_in_delay_branch(struct pt_regs *regs) regs->gr[31] -= 8; /* delayed branching */ /* Get assembler opcode of code in delay branch */ - uaddr = (unsigned int *) ((regs->gr[31] & ~3) + 4); + uaddr = (u32 __user *) ((regs->gr[31] & ~3) + 4); err = get_user(opcode, uaddr); if (err) return; diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index ca2d537e25b1..9915062d5243 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -27,17 +27,12 @@ #include <linux/elf-randomize.h> /* - * Construct an artificial page offset for the mapping based on the virtual + * Construct an artificial page offset for the mapping based on the physical * address of the kernel file mapping variable. - * If filp is zero the calculated pgoff value aliases the memory of the given - * address. This is useful for io_uring where the mapping shall alias a kernel - * address and a userspace adress where both the kernel and the userspace - * access the same memory region. */ -#define GET_FILP_PGOFF(filp, addr) \ - ((filp ? (((unsigned long) filp->f_mapping) >> 8) \ - & ((SHM_COLOUR-1) >> PAGE_SHIFT) : 0UL) \ - + (addr >> PAGE_SHIFT)) +#define GET_FILP_PGOFF(filp) \ + (filp ? (((unsigned long) filp->f_mapping) >> 8) \ + & ((SHM_COLOUR-1) >> PAGE_SHIFT) : 0UL) static unsigned long shared_align_offset(unsigned long filp_pgoff, unsigned long pgoff) @@ -117,7 +112,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, do_color_align = 0; if (filp || (flags & MAP_SHARED)) do_color_align = 1; - filp_pgoff = GET_FILP_PGOFF(filp, addr); + filp_pgoff = GET_FILP_PGOFF(filp); if (flags & MAP_FIXED) { /* Even MAP_FIXED mappings must reside within TASK_SIZE */ diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 1373e5129868..1f51aa9c8230 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -39,6 +39,7 @@ registers). #include <asm/assembly.h> #include <asm/processor.h> #include <asm/cache.h> +#include <asm/spinlock_types.h> #include <linux/linkage.h> @@ -66,6 +67,16 @@ registers). stw \reg1, 0(%sr2,\reg2) .endm + /* raise exception if spinlock content is not zero or + * __ARCH_SPIN_LOCK_UNLOCKED_VAL */ + .macro spinlock_check spin_val,tmpreg +#ifdef CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK + ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, \tmpreg + andcm,= \spin_val, \tmpreg, %r0 + .word SPINLOCK_BREAK_INSN +#endif + .endm + .text .import syscall_exit,code @@ -508,7 +519,8 @@ lws_start: lws_exit_noerror: lws_pagefault_enable %r1,%r21 - stw,ma %r20, 0(%sr2,%r20) + ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, %r21 + stw,ma %r21, 0(%sr2,%r20) ssm PSW_SM_I, %r0 b lws_exit copy %r0, %r21 @@ -521,7 +533,8 @@ lws_wouldblock: lws_pagefault: lws_pagefault_enable %r1,%r21 - stw,ma %r20, 0(%sr2,%r20) + ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, %r21 + stw,ma %r21, 0(%sr2,%r20) ssm PSW_SM_I, %r0 ldo 3(%r0),%r28 b lws_exit @@ -619,6 +632,7 @@ lws_compare_and_swap: /* Try to acquire the lock */ LDCW 0(%sr2,%r20), %r28 + spinlock_check %r28, %r21 comclr,<> %r0, %r28, %r0 b,n lws_wouldblock @@ -772,6 +786,7 @@ cas2_lock_start: /* Try to acquire the lock */ LDCW 0(%sr2,%r20), %r28 + spinlock_check %r28, %r21 comclr,<> %r0, %r28, %r0 b,n lws_wouldblock @@ -1001,6 +1016,7 @@ atomic_xchg_start: /* Try to acquire the lock */ LDCW 0(%sr2,%r20), %r28 + spinlock_check %r28, %r21 comclr,<> %r0, %r28, %r0 b,n lws_wouldblock @@ -1199,6 +1215,7 @@ atomic_store_start: /* Try to acquire the lock */ LDCW 0(%sr2,%r20), %r28 + spinlock_check %r28, %r21 comclr,<> %r0, %r28, %r0 b,n lws_wouldblock @@ -1330,7 +1347,7 @@ ENTRY(lws_lock_start) /* lws locks */ .rept 256 /* Keep locks aligned at 16-bytes */ - .word 1 + .word __ARCH_SPIN_LOCK_UNLOCKED_VAL .word 0 .word 0 .word 0 diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index 813062701922..170d0dda4213 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -11,6 +11,7 @@ #include <linux/signal.h> #include <linux/ratelimit.h> #include <linux/uaccess.h> +#include <linux/sysctl.h> #include <asm/unaligned.h> #include <asm/hardirq.h> #include <asm/traps.h> diff --git a/arch/parisc/lib/ucmpdi2.c b/arch/parisc/lib/ucmpdi2.c index 8e6014a142ef..9d8b4dbae273 100644 --- a/arch/parisc/lib/ucmpdi2.c +++ b/arch/parisc/lib/ucmpdi2.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/module.h> +#include <linux/libgcc.h> union ull_union { unsigned long long ull; @@ -9,7 +10,7 @@ union ull_union { } ui; }; -int __ucmpdi2(unsigned long long a, unsigned long long b) +word_type __ucmpdi2(unsigned long long a, unsigned long long b) { union ull_union au = {.ull = a}; union ull_union bu = {.ull = b}; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index a4c7c7630f48..2fe5b44986e0 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -192,31 +192,31 @@ int fixup_exception(struct pt_regs *regs) * For implementation see handle_interruption() in traps.c */ static const char * const trap_description[] = { - [1] "High-priority machine check (HPMC)", - [2] "Power failure interrupt", - [3] "Recovery counter trap", - [5] "Low-priority machine check", - [6] "Instruction TLB miss fault", - [7] "Instruction access rights / protection trap", - [8] "Illegal instruction trap", - [9] "Break instruction trap", - [10] "Privileged operation trap", - [11] "Privileged register trap", - [12] "Overflow trap", - [13] "Conditional trap", - [14] "FP Assist Exception trap", - [15] "Data TLB miss fault", - [16] "Non-access ITLB miss fault", - [17] "Non-access DTLB miss fault", - [18] "Data memory protection/unaligned access trap", - [19] "Data memory break trap", - [20] "TLB dirty bit trap", - [21] "Page reference trap", - [22] "Assist emulation trap", - [25] "Taken branch trap", - [26] "Data memory access rights trap", - [27] "Data memory protection ID trap", - [28] "Unaligned data reference trap", + [1] = "High-priority machine check (HPMC)", + [2] = "Power failure interrupt", + [3] = "Recovery counter trap", + [5] = "Low-priority machine check", + [6] = "Instruction TLB miss fault", + [7] = "Instruction access rights / protection trap", + [8] = "Illegal instruction trap", + [9] = "Break instruction trap", + [10] = "Privileged operation trap", + [11] = "Privileged register trap", + [12] = "Overflow trap", + [13] = "Conditional trap", + [14] = "FP Assist Exception trap", + [15] = "Data TLB miss fault", + [16] = "Non-access ITLB miss fault", + [17] = "Non-access DTLB miss fault", + [18] = "Data memory protection/unaligned access trap", + [19] = "Data memory break trap", + [20] = "TLB dirty bit trap", + [21] = "Page reference trap", + [22] = "Assist emulation trap", + [25] = "Taken branch trap", + [26] = "Data memory access rights trap", + [27] = "Data memory protection ID trap", + [28] = "Unaligned data reference trap", }; const char *trap_name(unsigned long code) diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 389941c7f209..a088c243edea 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -523,10 +523,6 @@ void mark_rodata_ro(void) void *parisc_vmalloc_start __ro_after_init; EXPORT_SYMBOL(parisc_vmalloc_start); -#ifdef CONFIG_PA11 -unsigned long pcxl_dma_start __ro_after_init; -#endif - void __init mem_init(void) { /* Do sanity checks on IPC (compat) structures */ diff --git a/arch/parisc/mm/ioremap.c b/arch/parisc/mm/ioremap.c index 345ff0b66499..d7ee1f43d997 100644 --- a/arch/parisc/mm/ioremap.c +++ b/arch/parisc/mm/ioremap.c @@ -27,7 +27,7 @@ */ void __iomem *ioremap(unsigned long phys_addr, unsigned long size) { - void __iomem *addr; + uintptr_t addr; struct vm_struct *area; unsigned long offset, last_addr; pgprot_t pgprot; @@ -79,10 +79,9 @@ void __iomem *ioremap(unsigned long phys_addr, unsigned long size) if (!area) return NULL; - addr = (void __iomem *) area->addr; - if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size, - phys_addr, pgprot)) { - vunmap(addr); + addr = (uintptr_t) area->addr; + if (ioremap_page_range(addr, addr + size, phys_addr, pgprot)) { + vunmap(area->addr); return NULL; } diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 8091b8bf4883..b93ffddf8a61 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -37,6 +37,10 @@ static inline void flush_dcache_page(struct page *page) #define flush_icache_user_page(vma, pg, addr, len) \ flush_icache_mm(vma->vm_mm, 0) +#ifdef CONFIG_64BIT +#define flush_cache_vmap(start, end) flush_tlb_kernel_range(start, end) +#endif + #ifndef CONFIG_SMP #define flush_icache_all() local_flush_icache_all() diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h index aff6c33ab0c0..4c58ee7f95ec 100644 --- a/arch/riscv/include/asm/mmio.h +++ b/arch/riscv/include/asm/mmio.h @@ -101,9 +101,9 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) * Relaxed I/O memory access primitives. These follow the Device memory * ordering rules but do not guarantee any ordering relative to Normal memory * accesses. These are defined to order the indicated access (either a read or - * write) with all other I/O memory accesses. Since the platform specification - * defines that all I/O regions are strongly ordered on channel 2, no explicit - * fences are required to enforce this ordering. + * write) with all other I/O memory accesses to the same peripheral. Since the + * platform specification defines that all I/O regions are strongly ordered on + * channel 0, no explicit fences are required to enforce this ordering. */ /* FIXME: These are now the same as asm-generic */ #define __io_rbr() do {} while (0) @@ -125,14 +125,14 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) #endif /* - * I/O memory access primitives. Reads are ordered relative to any - * following Normal memory access. Writes are ordered relative to any prior - * Normal memory access. The memory barriers here are necessary as RISC-V + * I/O memory access primitives. Reads are ordered relative to any following + * Normal memory read and delay() loop. Writes are ordered relative to any + * prior Normal memory write. The memory barriers here are necessary as RISC-V * doesn't define any ordering between the memory space and the I/O space. */ #define __io_br() do {} while (0) -#define __io_ar(v) __asm__ __volatile__ ("fence i,r" : : : "memory") -#define __io_bw() __asm__ __volatile__ ("fence w,o" : : : "memory") +#define __io_ar(v) ({ __asm__ __volatile__ ("fence i,ir" : : : "memory"); }) +#define __io_bw() ({ __asm__ __volatile__ ("fence w,o" : : : "memory"); }) #define __io_aw() mmiowb_set_pending() #define readb(c) ({ u8 __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; }) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 75970ee2bda2..b5680c940c1e 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -188,6 +188,8 @@ extern struct pt_alloc_ops pt_ops __initdata; #define PAGE_KERNEL_IO __pgprot(_PAGE_IOREMAP) extern pgd_t swapper_pg_dir[]; +extern pgd_t trampoline_pg_dir[]; +extern pgd_t early_pg_dir[]; #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_present(pmd_t pmd) diff --git a/arch/riscv/include/asm/vmalloc.h b/arch/riscv/include/asm/vmalloc.h index 58d3e447f191..924d01b56c9a 100644 --- a/arch/riscv/include/asm/vmalloc.h +++ b/arch/riscv/include/asm/vmalloc.h @@ -3,12 +3,14 @@ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +extern bool pgtable_l4_enabled, pgtable_l5_enabled; + #define IOREMAP_MAX_ORDER (PUD_SHIFT) #define arch_vmap_pud_supported arch_vmap_pud_supported static inline bool arch_vmap_pud_supported(pgprot_t prot) { - return true; + return pgtable_l4_enabled || pgtable_l5_enabled; } #define arch_vmap_pmd_supported arch_vmap_pmd_supported diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index a2fc952318e9..35b854cf078e 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -17,6 +17,11 @@ #include <asm/smp.h> #include <asm/pgtable.h> +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return phys_id == cpuid_to_hartid_map(cpu); +} + /* * Returns the hart ID of the given device tree node, or -ENODEV if the node * isn't an enabled and valid RISC-V hart node. diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c index 5372b708fae2..c08bb5c3b385 100644 --- a/arch/riscv/kernel/elf_kexec.c +++ b/arch/riscv/kernel/elf_kexec.c @@ -281,7 +281,7 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf, kbuf.buffer = initrd; kbuf.bufsz = kbuf.memsz = initrd_len; kbuf.buf_align = PAGE_SIZE; - kbuf.top_down = false; + kbuf.top_down = true; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) @@ -425,6 +425,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, * sym, instead of searching the whole relsec. */ case R_RISCV_PCREL_HI20: + case R_RISCV_CALL_PLT: case R_RISCV_CALL: *(u64 *)loc = CLEAN_IMM(UITYPE, *(u64 *)loc) | ENCODE_UJTYPE_IMM(val - addr); diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 85bbce0f758c..40420afbb1a0 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -61,11 +61,6 @@ int riscv_hartid_to_cpuid(unsigned long hartid) return -ENOENT; } -bool arch_match_cpu_phys_id(int cpu, u64 phys_id) -{ - return phys_id == cpuid_to_hartid_map(cpu); -} - static void ipi_stop(void) { set_cpu_online(smp_processor_id(), false); diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 9ce504737d18..e4c35ac2357f 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -26,12 +26,13 @@ #include <linux/kfence.h> #include <asm/fixmap.h> -#include <asm/tlbflush.h> -#include <asm/sections.h> -#include <asm/soc.h> #include <asm/io.h> -#include <asm/ptdump.h> #include <asm/numa.h> +#include <asm/pgtable.h> +#include <asm/ptdump.h> +#include <asm/sections.h> +#include <asm/soc.h> +#include <asm/tlbflush.h> #include "../kernel/head.h" @@ -214,8 +215,13 @@ static void __init setup_bootmem(void) memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); phys_ram_end = memblock_end_of_DRAM(); + + /* + * Make sure we align the start of the memory on a PMD boundary so that + * at worst, we map the linear mapping with PMD mappings. + */ if (!IS_ENABLED(CONFIG_XIP_KERNEL)) - phys_ram_base = memblock_start_of_DRAM(); + phys_ram_base = memblock_start_of_DRAM() & PMD_MASK; /* * In 64-bit, any use of __va/__pa before this point is wrong as we diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 8fc0efcf905c..a01bc15dce24 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -22,7 +22,6 @@ * region is not and then we have to go down to the PUD level. */ -extern pgd_t early_pg_dir[PTRS_PER_PGD]; pgd_t tmp_pg_dir[PTRS_PER_PGD] __page_aligned_bss; p4d_t tmp_p4d[PTRS_PER_P4D] __page_aligned_bss; pud_t tmp_pud[PTRS_PER_PUD] __page_aligned_bss; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7422db409770..e36261b4ea14 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2593,6 +2593,13 @@ config CPU_IBRS_ENTRY This mitigates both spectre_v2 and retbleed at great cost to performance. +config CPU_SRSO + bool "Mitigate speculative RAS overflow on AMD" + depends on CPU_SUP_AMD && X86_64 && RETHUNK + default y + help + Enable the SRSO mitigation needed on AMD Zen1-4 machines. + config SLS bool "Mitigate Straight-Line-Speculation" depends on CC_HAS_SLS && X86_64 @@ -2603,6 +2610,25 @@ config SLS against straight line speculation. The kernel image might be slightly larger. +config GDS_FORCE_MITIGATION + bool "Force GDS Mitigation" + depends on CPU_SUP_INTEL + default n + help + Gather Data Sampling (GDS) is a hardware vulnerability which allows + unprivileged speculative access to data which was previously stored in + vector registers. + + This option is equivalent to setting gather_data_sampling=force on the + command line. The microcode mitigation is used if present, otherwise + AVX is disabled as a mitigation. On affected systems that are missing + the microcode any userspace code that unconditionally uses AVX will + break with this option set. + + Setting this option on systems not vulnerable to GDS has no effect. + + If in doubt, say N. + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index cb8ca46213be..b69b0d7756aa 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -14,7 +14,7 @@ * Defines x86 CPU feature bits */ #define NCAPINTS 21 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ +#define NBUGINTS 2 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used @@ -309,6 +309,10 @@ #define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ #define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ +#define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ +#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ +#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */ + /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -442,6 +446,10 @@ #define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ #define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */ +#define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */ +#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ +#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ + /* * BUG word(s) */ @@ -483,5 +491,9 @@ #define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ +#define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */ +/* BUG word 2 */ +#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ +#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index a00a53e15ab7..1d111350197f 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -57,6 +57,7 @@ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ +#define PRED_CMD_SBPB BIT(7) /* Selective Branch Prediction Barrier */ #define MSR_PPIN_CTL 0x0000004e #define MSR_PPIN 0x0000004f @@ -155,6 +156,15 @@ * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. */ +#define ARCH_CAP_GDS_CTRL BIT(25) /* + * CPU is vulnerable to Gather + * Data Sampling (GDS) and + * has controls for mitigation. + */ +#define ARCH_CAP_GDS_NO BIT(26) /* + * CPU is not vulnerable to Gather + * Data Sampling (GDS). + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR @@ -178,6 +188,8 @@ #define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ #define RTM_ALLOW BIT(1) /* TSX development mode */ #define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */ +#define GDS_MITG_DIS BIT(4) /* Disable GDS mitigation */ +#define GDS_MITG_LOCKED BIT(5) /* GDS mitigation locked */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 1a65cf4acb2b..3faf044569a5 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -211,7 +211,8 @@ * eventually turn into it's own annotation. */ .macro VALIDATE_UNRET_END -#if defined(CONFIG_NOINSTR_VALIDATION) && defined(CONFIG_CPU_UNRET_ENTRY) +#if defined(CONFIG_NOINSTR_VALIDATION) && \ + (defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)) ANNOTATE_RETPOLINE_SAFE nop #endif @@ -289,13 +290,18 @@ */ .macro UNTRAIN_RET #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ - defined(CONFIG_CALL_DEPTH_TRACKING) + defined(CONFIG_CALL_DEPTH_TRACKING) || defined(CONFIG_CPU_SRSO) VALIDATE_UNRET_END ALTERNATIVE_3 "", \ CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \ __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH #endif + +#ifdef CONFIG_CPU_SRSO + ALTERNATIVE_2 "", "call srso_untrain_ret", X86_FEATURE_SRSO, \ + "call srso_untrain_ret_alias", X86_FEATURE_SRSO_ALIAS +#endif .endm .macro UNTRAIN_RET_FROM_CALL @@ -307,6 +313,11 @@ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \ __stringify(RESET_CALL_DEPTH_FROM_CALL), X86_FEATURE_CALL_DEPTH #endif + +#ifdef CONFIG_CPU_SRSO + ALTERNATIVE_2 "", "call srso_untrain_ret", X86_FEATURE_SRSO, \ + "call srso_untrain_ret_alias", X86_FEATURE_SRSO_ALIAS +#endif .endm @@ -332,6 +343,8 @@ extern retpoline_thunk_t __x86_indirect_jump_thunk_array[]; extern void __x86_return_thunk(void); extern void zen_untrain_ret(void); +extern void srso_untrain_ret(void); +extern void srso_untrain_ret_alias(void); extern void entry_ibpb(void); #ifdef CONFIG_CALL_THUNKS @@ -479,11 +492,11 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) : "memory"); } +extern u64 x86_pred_cmd; + static inline void indirect_branch_prediction_barrier(void) { - u64 val = PRED_CMD_IBPB; - - alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB); + alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_USE_IBPB); } /* The Intel SPEC CTRL MSR base value cache */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d46300e94f85..973db0406528 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -682,9 +682,13 @@ extern u16 get_llc_id(unsigned int cpu); #ifdef CONFIG_CPU_SUP_AMD extern u32 amd_get_nodes_per_socket(void); extern u32 amd_get_highest_perf(void); +extern bool cpu_has_ibpb_brtype_microcode(void); +extern void amd_clear_divider(void); #else static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } +static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; } +static inline void amd_clear_divider(void) { } #endif extern unsigned long arch_align_stack(unsigned long sp); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 26ad7ca423e7..b55d8f82b621 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -75,6 +75,10 @@ static const int amd_zenbleed[] = AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf), AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf)); +static const int amd_div0[] = + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf), + AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf)); + static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { int osvw_id = *erratum++; @@ -1130,6 +1134,11 @@ static void init_amd(struct cpuinfo_x86 *c) WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS)); zenbleed_check(c); + + if (cpu_has_amd_erratum(c, amd_div0)) { + pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); + setup_force_cpu_bug(X86_BUG_DIV0); + } } #ifdef CONFIG_X86_32 @@ -1290,3 +1299,32 @@ void amd_check_microcode(void) { on_each_cpu(zenbleed_check_cpu, NULL, 1); } + +bool cpu_has_ibpb_brtype_microcode(void) +{ + switch (boot_cpu_data.x86) { + /* Zen1/2 IBPB flushes branch type predictions too. */ + case 0x17: + return boot_cpu_has(X86_FEATURE_AMD_IBPB); + case 0x19: + /* Poke the MSR bit on Zen3/4 to check its presence. */ + if (!wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) { + setup_force_cpu_cap(X86_FEATURE_SBPB); + return true; + } else { + return false; + } + default: + return false; + } +} + +/* + * Issue a DIV 0/1 insn to clear any division data from previous DIV + * operations. + */ +void noinstr amd_clear_divider(void) +{ + asm volatile(ALTERNATIVE("", "div %2\n\t", X86_BUG_DIV0) + :: "a" (0), "d" (0), "r" (1)); +} diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 95507448e781..d02f73c5339d 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -47,6 +47,8 @@ static void __init taa_select_mitigation(void); static void __init mmio_select_mitigation(void); static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); +static void __init srso_select_mitigation(void); +static void __init gds_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -56,6 +58,9 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); DEFINE_PER_CPU(u64, x86_spec_ctrl_current); EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); +u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; +EXPORT_SYMBOL_GPL(x86_pred_cmd); + static DEFINE_MUTEX(spec_ctrl_mutex); /* Update SPEC_CTRL MSR and its cached copy unconditionally */ @@ -160,6 +165,8 @@ void __init cpu_select_mitigations(void) md_clear_select_mitigation(); srbds_select_mitigation(); l1d_flush_select_mitigation(); + srso_select_mitigation(); + gds_select_mitigation(); } /* @@ -646,6 +653,149 @@ static int __init l1d_flush_parse_cmdline(char *str) early_param("l1d_flush", l1d_flush_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "GDS: " fmt + +enum gds_mitigations { + GDS_MITIGATION_OFF, + GDS_MITIGATION_UCODE_NEEDED, + GDS_MITIGATION_FORCE, + GDS_MITIGATION_FULL, + GDS_MITIGATION_FULL_LOCKED, + GDS_MITIGATION_HYPERVISOR, +}; + +#if IS_ENABLED(CONFIG_GDS_FORCE_MITIGATION) +static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FORCE; +#else +static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL; +#endif + +static const char * const gds_strings[] = { + [GDS_MITIGATION_OFF] = "Vulnerable", + [GDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [GDS_MITIGATION_FORCE] = "Mitigation: AVX disabled, no microcode", + [GDS_MITIGATION_FULL] = "Mitigation: Microcode", + [GDS_MITIGATION_FULL_LOCKED] = "Mitigation: Microcode (locked)", + [GDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", +}; + +bool gds_ucode_mitigated(void) +{ + return (gds_mitigation == GDS_MITIGATION_FULL || + gds_mitigation == GDS_MITIGATION_FULL_LOCKED); +} +EXPORT_SYMBOL_GPL(gds_ucode_mitigated); + +void update_gds_msr(void) +{ + u64 mcu_ctrl_after; + u64 mcu_ctrl; + + switch (gds_mitigation) { + case GDS_MITIGATION_OFF: + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + mcu_ctrl |= GDS_MITG_DIS; + break; + case GDS_MITIGATION_FULL_LOCKED: + /* + * The LOCKED state comes from the boot CPU. APs might not have + * the same state. Make sure the mitigation is enabled on all + * CPUs. + */ + case GDS_MITIGATION_FULL: + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + mcu_ctrl &= ~GDS_MITG_DIS; + break; + case GDS_MITIGATION_FORCE: + case GDS_MITIGATION_UCODE_NEEDED: + case GDS_MITIGATION_HYPERVISOR: + return; + }; + + wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + + /* + * Check to make sure that the WRMSR value was not ignored. Writes to + * GDS_MITG_DIS will be ignored if this processor is locked but the boot + * processor was not. + */ + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after); + WARN_ON_ONCE(mcu_ctrl != mcu_ctrl_after); +} + +static void __init gds_select_mitigation(void) +{ + u64 mcu_ctrl; + + if (!boot_cpu_has_bug(X86_BUG_GDS)) + return; + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + gds_mitigation = GDS_MITIGATION_HYPERVISOR; + goto out; + } + + if (cpu_mitigations_off()) + gds_mitigation = GDS_MITIGATION_OFF; + /* Will verify below that mitigation _can_ be disabled */ + + /* No microcode */ + if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) { + if (gds_mitigation == GDS_MITIGATION_FORCE) { + /* + * This only needs to be done on the boot CPU so do it + * here rather than in update_gds_msr() + */ + setup_clear_cpu_cap(X86_FEATURE_AVX); + pr_warn("Microcode update needed! Disabling AVX as mitigation.\n"); + } else { + gds_mitigation = GDS_MITIGATION_UCODE_NEEDED; + } + goto out; + } + + /* Microcode has mitigation, use it */ + if (gds_mitigation == GDS_MITIGATION_FORCE) + gds_mitigation = GDS_MITIGATION_FULL; + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + if (mcu_ctrl & GDS_MITG_LOCKED) { + if (gds_mitigation == GDS_MITIGATION_OFF) + pr_warn("Mitigation locked. Disable failed.\n"); + + /* + * The mitigation is selected from the boot CPU. All other CPUs + * _should_ have the same state. If the boot CPU isn't locked + * but others are then update_gds_msr() will WARN() of the state + * mismatch. If the boot CPU is locked update_gds_msr() will + * ensure the other CPUs have the mitigation enabled. + */ + gds_mitigation = GDS_MITIGATION_FULL_LOCKED; + } + + update_gds_msr(); +out: + pr_info("%s\n", gds_strings[gds_mitigation]); +} + +static int __init gds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_GDS)) + return 0; + + if (!strcmp(str, "off")) + gds_mitigation = GDS_MITIGATION_OFF; + else if (!strcmp(str, "force")) + gds_mitigation = GDS_MITIGATION_FORCE; + + return 0; +} +early_param("gather_data_sampling", gds_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -2188,6 +2338,165 @@ static int __init l1tf_cmdline(char *str) early_param("l1tf", l1tf_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "Speculative Return Stack Overflow: " fmt + +enum srso_mitigation { + SRSO_MITIGATION_NONE, + SRSO_MITIGATION_MICROCODE, + SRSO_MITIGATION_SAFE_RET, + SRSO_MITIGATION_IBPB, + SRSO_MITIGATION_IBPB_ON_VMEXIT, +}; + +enum srso_mitigation_cmd { + SRSO_CMD_OFF, + SRSO_CMD_MICROCODE, + SRSO_CMD_SAFE_RET, + SRSO_CMD_IBPB, + SRSO_CMD_IBPB_ON_VMEXIT, +}; + +static const char * const srso_strings[] = { + [SRSO_MITIGATION_NONE] = "Vulnerable", + [SRSO_MITIGATION_MICROCODE] = "Mitigation: microcode", + [SRSO_MITIGATION_SAFE_RET] = "Mitigation: safe RET", + [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB", + [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only" +}; + +static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE; +static enum srso_mitigation_cmd srso_cmd __ro_after_init = SRSO_CMD_SAFE_RET; + +static int __init srso_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + srso_cmd = SRSO_CMD_OFF; + else if (!strcmp(str, "microcode")) + srso_cmd = SRSO_CMD_MICROCODE; + else if (!strcmp(str, "safe-ret")) + srso_cmd = SRSO_CMD_SAFE_RET; + else if (!strcmp(str, "ibpb")) + srso_cmd = SRSO_CMD_IBPB; + else if (!strcmp(str, "ibpb-vmexit")) + srso_cmd = SRSO_CMD_IBPB_ON_VMEXIT; + else + pr_err("Ignoring unknown SRSO option (%s).", str); + + return 0; +} +early_param("spec_rstack_overflow", srso_parse_cmdline); + +#define SRSO_NOTICE "WARNING: See https://kernel.org/doc/html/latest/admin-guide/hw-vuln/srso.html for mitigation options." + +static void __init srso_select_mitigation(void) +{ + bool has_microcode; + + if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off()) + goto pred_cmd; + + /* + * The first check is for the kernel running as a guest in order + * for guests to verify whether IBPB is a viable mitigation. + */ + has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) || cpu_has_ibpb_brtype_microcode(); + if (!has_microcode) { + pr_warn("IBPB-extending microcode not applied!\n"); + pr_warn(SRSO_NOTICE); + } else { + /* + * Enable the synthetic (even if in a real CPUID leaf) + * flags for guests. + */ + setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); + + /* + * Zen1/2 with SMT off aren't vulnerable after the right + * IBPB microcode has been applied. + */ + if ((boot_cpu_data.x86 < 0x19) && + (!cpu_smt_possible() || (cpu_smt_control == CPU_SMT_DISABLED))) + setup_force_cpu_cap(X86_FEATURE_SRSO_NO); + } + + if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { + if (has_microcode) { + pr_err("Retbleed IBPB mitigation enabled, using same for SRSO\n"); + srso_mitigation = SRSO_MITIGATION_IBPB; + goto pred_cmd; + } + } + + switch (srso_cmd) { + case SRSO_CMD_OFF: + return; + + case SRSO_CMD_MICROCODE: + if (has_microcode) { + srso_mitigation = SRSO_MITIGATION_MICROCODE; + pr_warn(SRSO_NOTICE); + } + break; + + case SRSO_CMD_SAFE_RET: + if (IS_ENABLED(CONFIG_CPU_SRSO)) { + /* + * Enable the return thunk for generated code + * like ftrace, static_call, etc. + */ + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + + if (boot_cpu_data.x86 == 0x19) + setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); + else + setup_force_cpu_cap(X86_FEATURE_SRSO); + srso_mitigation = SRSO_MITIGATION_SAFE_RET; + } else { + pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + goto pred_cmd; + } + break; + + case SRSO_CMD_IBPB: + if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) { + if (has_microcode) { + setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + srso_mitigation = SRSO_MITIGATION_IBPB; + } + } else { + pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); + goto pred_cmd; + } + break; + + case SRSO_CMD_IBPB_ON_VMEXIT: + if (IS_ENABLED(CONFIG_CPU_SRSO)) { + if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { + setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); + srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; + } + } else { + pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + goto pred_cmd; + } + break; + + default: + break; + } + + pr_info("%s%s\n", srso_strings[srso_mitigation], (has_microcode ? "" : ", no microcode")); + +pred_cmd: + if ((boot_cpu_has(X86_FEATURE_SRSO_NO) || srso_cmd == SRSO_CMD_OFF) && + boot_cpu_has(X86_FEATURE_SBPB)) + x86_pred_cmd = PRED_CMD_SBPB; +} + +#undef pr_fmt #define pr_fmt(fmt) fmt #ifdef CONFIG_SYSFS @@ -2385,6 +2694,18 @@ static ssize_t retbleed_show_state(char *buf) return sysfs_emit(buf, "%s\n", retbleed_strings[retbleed_mitigation]); } +static ssize_t srso_show_state(char *buf) +{ + return sysfs_emit(buf, "%s%s\n", + srso_strings[srso_mitigation], + (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode")); +} + +static ssize_t gds_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -2434,6 +2755,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_RETBLEED: return retbleed_show_state(buf); + case X86_BUG_SRSO: + return srso_show_state(buf); + + case X86_BUG_GDS: + return gds_show_state(buf); + default: break; } @@ -2498,4 +2825,14 @@ ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, cha { return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED); } + +ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SRSO); +} + +ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_GDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0ba1067f4e5f..e3a65e9fc750 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1250,6 +1250,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define RETBLEED BIT(3) /* CPU is affected by SMT (cross-thread) return predictions */ #define SMT_RSB BIT(4) +/* CPU is affected by SRSO */ +#define SRSO BIT(5) +/* CPU is affected by GDS */ +#define GDS BIT(6) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1262,27 +1266,30 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED), - VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS), + VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(TIGERLAKE_L, X86_STEPPING_ANY, GDS), + VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), - VULNBL_AMD(0x17, RETBLEED | SMT_RSB), + VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), VULNBL_HYGON(0x18, RETBLEED | SMT_RSB), + VULNBL_AMD(0x19, SRSO), {} }; @@ -1406,6 +1413,21 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (cpu_matches(cpu_vuln_blacklist, SMT_RSB)) setup_force_cpu_bug(X86_BUG_SMT_RSB); + if (!cpu_has(c, X86_FEATURE_SRSO_NO)) { + if (cpu_matches(cpu_vuln_blacklist, SRSO)) + setup_force_cpu_bug(X86_BUG_SRSO); + } + + /* + * Check if CPU is vulnerable to GDS. If running in a virtual machine on + * an affected processor, the VMM may have disabled the use of GATHER by + * disabling AVX2. The only way to do this in HW is to clear XCR0[2], + * which means that AVX will be disabled. + */ + if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) && + boot_cpu_has(X86_FEATURE_AVX)) + setup_force_cpu_bug(X86_BUG_GDS); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; @@ -1962,6 +1984,8 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); update_srbds_msr(); + if (boot_cpu_has_bug(X86_BUG_GDS)) + update_gds_msr(); tsx_ap_init(); } diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 1c44630d4789..1dcd7d4e38ef 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -83,6 +83,7 @@ void cpu_select_mitigations(void); extern void x86_spec_ctrl_setup_ap(void); extern void update_srbds_msr(void); +extern void update_gds_msr(void); extern enum spectre_v2_mitigation spectre_v2_enabled; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 4a817d20ce3b..1885326a8f65 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -206,6 +206,8 @@ DEFINE_IDTENTRY(exc_divide_error) { do_error_trap(regs, 0, "divide error", X86_TRAP_DE, SIGFPE, FPE_INTDIV, error_get_trap_addr(regs)); + + amd_clear_divider(); } DEFINE_IDTENTRY(exc_overflow) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 03c885d3640f..e76813230192 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -134,13 +134,27 @@ SECTIONS SOFTIRQENTRY_TEXT #ifdef CONFIG_RETPOLINE __indirect_thunk_start = .; - *(.text.__x86.*) + *(.text.__x86.indirect_thunk) + *(.text.__x86.return_thunk) __indirect_thunk_end = .; #endif STATIC_CALL_TEXT ALIGN_ENTRY_TEXT_BEGIN +#ifdef CONFIG_CPU_SRSO + *(.text.__x86.rethunk_untrain) +#endif + ENTRY_TEXT + +#ifdef CONFIG_CPU_SRSO + /* + * See the comment above srso_untrain_ret_alias()'s + * definition. + */ + . = srso_untrain_ret_alias | (1 << 2) | (1 << 8) | (1 << 14) | (1 << 20); + *(.text.__x86.rethunk_safe) +#endif ALIGN_ENTRY_TEXT_END *(.gnu.warning) @@ -509,7 +523,18 @@ INIT_PER_CPU(irq_stack_backing_store); #endif #ifdef CONFIG_RETHUNK -. = ASSERT((__x86_return_thunk & 0x3f) == 0, "__x86_return_thunk not cacheline-aligned"); +. = ASSERT((__ret & 0x3f) == 0, "__ret not cacheline-aligned"); +. = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned"); +#endif + +#ifdef CONFIG_CPU_SRSO +/* + * GNU ld cannot do XOR so do: (A | B) - (A & B) in order to compute the XOR + * of the two function addresses: + */ +. = ASSERT(((srso_untrain_ret_alias | srso_safe_ret_alias) - + (srso_untrain_ret_alias & srso_safe_ret_alias)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)), + "SRSO function pair won't alias"); #endif #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 7f4d13383cf2..d3432687c9e6 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -729,6 +729,9 @@ void kvm_set_cpu_caps(void) F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ ); + if (cpu_feature_enabled(X86_FEATURE_SRSO_NO)) + kvm_cpu_cap_set(X86_FEATURE_SRSO_NO); + kvm_cpu_cap_init_kvm_defined(CPUID_8000_0022_EAX, F(PERFMON_V2) ); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 07756b7348ae..d3aec1f2cad2 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2417,15 +2417,18 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) */ memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); - vcpu->arch.regs[VCPU_REGS_RAX] = ghcb_get_rax_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RBX] = ghcb_get_rbx_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RCX] = ghcb_get_rcx_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RDX] = ghcb_get_rdx_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RSI] = ghcb_get_rsi_if_valid(ghcb); + BUILD_BUG_ON(sizeof(svm->sev_es.valid_bitmap) != sizeof(ghcb->save.valid_bitmap)); + memcpy(&svm->sev_es.valid_bitmap, &ghcb->save.valid_bitmap, sizeof(ghcb->save.valid_bitmap)); - svm->vmcb->save.cpl = ghcb_get_cpl_if_valid(ghcb); + vcpu->arch.regs[VCPU_REGS_RAX] = kvm_ghcb_get_rax_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RBX] = kvm_ghcb_get_rbx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RCX] = kvm_ghcb_get_rcx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RDX] = kvm_ghcb_get_rdx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RSI] = kvm_ghcb_get_rsi_if_valid(svm, ghcb); - if (ghcb_xcr0_is_valid(ghcb)) { + svm->vmcb->save.cpl = kvm_ghcb_get_cpl_if_valid(svm, ghcb); + + if (kvm_ghcb_xcr0_is_valid(svm)) { vcpu->arch.xcr0 = ghcb_get_xcr0(ghcb); kvm_update_cpuid_runtime(vcpu); } @@ -2436,84 +2439,88 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) control->exit_code_hi = upper_32_bits(exit_code); control->exit_info_1 = ghcb_get_sw_exit_info_1(ghcb); control->exit_info_2 = ghcb_get_sw_exit_info_2(ghcb); + svm->sev_es.sw_scratch = kvm_ghcb_get_sw_scratch_if_valid(svm, ghcb); /* Clear the valid entries fields */ memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } +static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control) +{ + return (((u64)control->exit_code_hi) << 32) | control->exit_code; +} + static int sev_es_validate_vmgexit(struct vcpu_svm *svm) { - struct kvm_vcpu *vcpu; - struct ghcb *ghcb; + struct vmcb_control_area *control = &svm->vmcb->control; + struct kvm_vcpu *vcpu = &svm->vcpu; u64 exit_code; u64 reason; - ghcb = svm->sev_es.ghcb; - /* * Retrieve the exit code now even though it may not be marked valid * as it could help with debugging. */ - exit_code = ghcb_get_sw_exit_code(ghcb); + exit_code = kvm_ghcb_get_sw_exit_code(control); /* Only GHCB Usage code 0 is supported */ - if (ghcb->ghcb_usage) { + if (svm->sev_es.ghcb->ghcb_usage) { reason = GHCB_ERR_INVALID_USAGE; goto vmgexit_err; } reason = GHCB_ERR_MISSING_INPUT; - if (!ghcb_sw_exit_code_is_valid(ghcb) || - !ghcb_sw_exit_info_1_is_valid(ghcb) || - !ghcb_sw_exit_info_2_is_valid(ghcb)) + if (!kvm_ghcb_sw_exit_code_is_valid(svm) || + !kvm_ghcb_sw_exit_info_1_is_valid(svm) || + !kvm_ghcb_sw_exit_info_2_is_valid(svm)) goto vmgexit_err; - switch (ghcb_get_sw_exit_code(ghcb)) { + switch (exit_code) { case SVM_EXIT_READ_DR7: break; case SVM_EXIT_WRITE_DR7: - if (!ghcb_rax_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_RDTSC: break; case SVM_EXIT_RDPMC: - if (!ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_CPUID: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; - if (ghcb_get_rax(ghcb) == 0xd) - if (!ghcb_xcr0_is_valid(ghcb)) + if (vcpu->arch.regs[VCPU_REGS_RAX] == 0xd) + if (!kvm_ghcb_xcr0_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_INVD: break; case SVM_EXIT_IOIO: - if (ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_STR_MASK) { - if (!ghcb_sw_scratch_is_valid(ghcb)) + if (control->exit_info_1 & SVM_IOIO_STR_MASK) { + if (!kvm_ghcb_sw_scratch_is_valid(svm)) goto vmgexit_err; } else { - if (!(ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_TYPE_MASK)) - if (!ghcb_rax_is_valid(ghcb)) + if (!(control->exit_info_1 & SVM_IOIO_TYPE_MASK)) + if (!kvm_ghcb_rax_is_valid(svm)) goto vmgexit_err; } break; case SVM_EXIT_MSR: - if (!ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; - if (ghcb_get_sw_exit_info_1(ghcb)) { - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rdx_is_valid(ghcb)) + if (control->exit_info_1) { + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rdx_is_valid(svm)) goto vmgexit_err; } break; case SVM_EXIT_VMMCALL: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_cpl_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_cpl_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_RDTSCP: @@ -2521,19 +2528,19 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) case SVM_EXIT_WBINVD: break; case SVM_EXIT_MONITOR: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rcx_is_valid(ghcb) || - !ghcb_rdx_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm) || + !kvm_ghcb_rdx_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_MWAIT: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; break; case SVM_VMGEXIT_MMIO_READ: case SVM_VMGEXIT_MMIO_WRITE: - if (!ghcb_sw_scratch_is_valid(ghcb)) + if (!kvm_ghcb_sw_scratch_is_valid(svm)) goto vmgexit_err; break; case SVM_VMGEXIT_NMI_COMPLETE: @@ -2549,11 +2556,9 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) return 0; vmgexit_err: - vcpu = &svm->vcpu; - if (reason == GHCB_ERR_INVALID_USAGE) { vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n", - ghcb->ghcb_usage); + svm->sev_es.ghcb->ghcb_usage); } else if (reason == GHCB_ERR_INVALID_EVENT) { vcpu_unimpl(vcpu, "vmgexit: exit code %#llx is not valid\n", exit_code); @@ -2563,11 +2568,8 @@ vmgexit_err: dump_ghcb(svm); } - /* Clear the valid entries fields */ - memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); - - ghcb_set_sw_exit_info_1(ghcb, 2); - ghcb_set_sw_exit_info_2(ghcb, reason); + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, reason); /* Resume the guest to "return" the error code. */ return 1; @@ -2586,7 +2588,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) */ if (svm->sev_es.ghcb_sa_sync) { kvm_write_guest(svm->vcpu.kvm, - ghcb_get_sw_scratch(svm->sev_es.ghcb), + svm->sev_es.sw_scratch, svm->sev_es.ghcb_sa, svm->sev_es.ghcb_sa_len); svm->sev_es.ghcb_sa_sync = false; @@ -2632,12 +2634,11 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu) static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) { struct vmcb_control_area *control = &svm->vmcb->control; - struct ghcb *ghcb = svm->sev_es.ghcb; u64 ghcb_scratch_beg, ghcb_scratch_end; u64 scratch_gpa_beg, scratch_gpa_end; void *scratch_va; - scratch_gpa_beg = ghcb_get_sw_scratch(ghcb); + scratch_gpa_beg = svm->sev_es.sw_scratch; if (!scratch_gpa_beg) { pr_err("vmgexit: scratch gpa not provided\n"); goto e_scratch; @@ -2708,8 +2709,8 @@ static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) return 0; e_scratch: - ghcb_set_sw_exit_info_1(ghcb, 2); - ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_SCRATCH_AREA); + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_SCRATCH_AREA); return 1; } @@ -2822,7 +2823,6 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); struct vmcb_control_area *control = &svm->vmcb->control; u64 ghcb_gpa, exit_code; - struct ghcb *ghcb; int ret; /* Validate the GHCB */ @@ -2847,20 +2847,18 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) } svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva; - ghcb = svm->sev_es.ghcb_map.hva; - trace_kvm_vmgexit_enter(vcpu->vcpu_id, ghcb); - - exit_code = ghcb_get_sw_exit_code(ghcb); + trace_kvm_vmgexit_enter(vcpu->vcpu_id, svm->sev_es.ghcb); + sev_es_sync_from_ghcb(svm); ret = sev_es_validate_vmgexit(svm); if (ret) return ret; - sev_es_sync_from_ghcb(svm); - ghcb_set_sw_exit_info_1(ghcb, 0); - ghcb_set_sw_exit_info_2(ghcb, 0); + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 0); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 0); + exit_code = kvm_ghcb_get_sw_exit_code(control); switch (exit_code) { case SVM_VMGEXIT_MMIO_READ: ret = setup_vmgexit_scratch(svm, true, control->exit_info_2); @@ -2898,13 +2896,13 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) break; case 1: /* Get AP jump table address */ - ghcb_set_sw_exit_info_2(ghcb, sev->ap_jump_table); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, sev->ap_jump_table); break; default: pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n", control->exit_info_1); - ghcb_set_sw_exit_info_1(ghcb, 2); - ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_INPUT); + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT); } ret = 1; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 956726d867aa..03e852dedcc1 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1498,7 +1498,9 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (sd->current_vmcb != svm->vmcb) { sd->current_vmcb = svm->vmcb; - indirect_branch_prediction_barrier(); + + if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT)) + indirect_branch_prediction_barrier(); } if (kvm_vcpu_apicv_active(vcpu)) avic_vcpu_load(vcpu, cpu); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 18af7e712a5a..8239c8de45ac 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -190,10 +190,12 @@ struct vcpu_sev_es_state { /* SEV-ES support */ struct sev_es_save_area *vmsa; struct ghcb *ghcb; + u8 valid_bitmap[16]; struct kvm_host_map ghcb_map; bool received_first_sipi; /* SEV-ES scratch area support */ + u64 sw_scratch; void *ghcb_sa; u32 ghcb_sa_len; bool ghcb_sa_sync; @@ -744,4 +746,28 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm); void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); +#define DEFINE_KVM_GHCB_ACCESSORS(field) \ + static __always_inline bool kvm_ghcb_##field##_is_valid(const struct vcpu_svm *svm) \ + { \ + return test_bit(GHCB_BITMAP_IDX(field), \ + (unsigned long *)&svm->sev_es.valid_bitmap); \ + } \ + \ + static __always_inline u64 kvm_ghcb_get_##field##_if_valid(struct vcpu_svm *svm, struct ghcb *ghcb) \ + { \ + return kvm_ghcb_##field##_is_valid(svm) ? ghcb->save.field : 0; \ + } \ + +DEFINE_KVM_GHCB_ACCESSORS(cpl) +DEFINE_KVM_GHCB_ACCESSORS(rax) +DEFINE_KVM_GHCB_ACCESSORS(rcx) +DEFINE_KVM_GHCB_ACCESSORS(rdx) +DEFINE_KVM_GHCB_ACCESSORS(rbx) +DEFINE_KVM_GHCB_ACCESSORS(rsi) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_code) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_info_1) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_info_2) +DEFINE_KVM_GHCB_ACCESSORS(sw_scratch) +DEFINE_KVM_GHCB_ACCESSORS(xcr0) + #endif diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 8e8295e774f0..265452fc9ebe 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -224,6 +224,9 @@ SYM_FUNC_START(__svm_vcpu_run) */ UNTRAIN_RET + /* SRSO */ + ALTERNATIVE "", "call entry_ibpb", X86_FEATURE_IBPB_ON_VMEXIT + /* * Clear all general purpose registers except RSP and RAX to prevent * speculative use of the guest's values, even those that are reloaded diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 278dbd37dab2..19d9ff92d699 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -314,6 +314,8 @@ u64 __read_mostly host_xcr0; static struct kmem_cache *x86_emulator_cache; +extern bool gds_ucode_mitigated(void); + /* * When called, it means the previous get/set msr reached an invalid msr. * Return true if we want to ignore/silent this failed msr access. @@ -1616,7 +1618,7 @@ static bool kvm_is_immutable_feature_msr(u32 msr) ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ - ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO) + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1673,6 +1675,9 @@ static u64 kvm_get_arch_capabilities(void) */ } + if (!boot_cpu_has_bug(X86_BUG_GDS) || gds_ucode_mitigated()) + data |= ARCH_CAP_GDS_NO; + return data; } diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 3fd066d42ec0..2cff585f22f2 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -11,6 +11,7 @@ #include <asm/unwind_hints.h> #include <asm/percpu.h> #include <asm/frame.h> +#include <asm/nops.h> .section .text.__x86.indirect_thunk @@ -131,6 +132,46 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) */ #ifdef CONFIG_RETHUNK +/* + * srso_untrain_ret_alias() and srso_safe_ret_alias() are placed at + * special addresses: + * + * - srso_untrain_ret_alias() is 2M aligned + * - srso_safe_ret_alias() is also in the same 2M page but bits 2, 8, 14 + * and 20 in its virtual address are set (while those bits in the + * srso_untrain_ret_alias() function are cleared). + * + * This guarantees that those two addresses will alias in the branch + * target buffer of Zen3/4 generations, leading to any potential + * poisoned entries at that BTB slot to get evicted. + * + * As a result, srso_safe_ret_alias() becomes a safe return. + */ +#ifdef CONFIG_CPU_SRSO + .section .text.__x86.rethunk_untrain + +SYM_START(srso_untrain_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) + ANNOTATE_NOENDBR + ASM_NOP2 + lfence + jmp __x86_return_thunk +SYM_FUNC_END(srso_untrain_ret_alias) +__EXPORT_THUNK(srso_untrain_ret_alias) + + .section .text.__x86.rethunk_safe +#endif + +/* Needs a definition for the __x86_return_thunk alternative below. */ +SYM_START(srso_safe_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) +#ifdef CONFIG_CPU_SRSO + add $8, %_ASM_SP + UNWIND_HINT_FUNC +#endif + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_FUNC_END(srso_safe_ret_alias) + .section .text.__x86.return_thunk /* @@ -143,7 +184,7 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) * from re-poisioning the BTB prediction. */ .align 64 - .skip 64 - (__x86_return_thunk - zen_untrain_ret), 0xcc + .skip 64 - (__ret - zen_untrain_ret), 0xcc SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) ANNOTATE_NOENDBR /* @@ -175,10 +216,10 @@ SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) * evicted, __x86_return_thunk will suffer Straight Line Speculation * which will be contained safely by the INT3. */ -SYM_INNER_LABEL(__x86_return_thunk, SYM_L_GLOBAL) +SYM_INNER_LABEL(__ret, SYM_L_GLOBAL) ret int3 -SYM_CODE_END(__x86_return_thunk) +SYM_CODE_END(__ret) /* * Ensure the TEST decoding / BTB invalidation is complete. @@ -189,11 +230,45 @@ SYM_CODE_END(__x86_return_thunk) * Jump back and execute the RET in the middle of the TEST instruction. * INT3 is for SLS protection. */ - jmp __x86_return_thunk + jmp __ret int3 SYM_FUNC_END(zen_untrain_ret) __EXPORT_THUNK(zen_untrain_ret) +/* + * SRSO untraining sequence for Zen1/2, similar to zen_untrain_ret() + * above. On kernel entry, srso_untrain_ret() is executed which is a + * + * movabs $0xccccccc308c48348,%rax + * + * and when the return thunk executes the inner label srso_safe_ret() + * later, it is a stack manipulation and a RET which is mispredicted and + * thus a "safe" one to use. + */ + .align 64 + .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc +SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) + ANNOTATE_NOENDBR + .byte 0x48, 0xb8 + +SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) + add $8, %_ASM_SP + ret + int3 + int3 + int3 + lfence + call srso_safe_ret + int3 +SYM_CODE_END(srso_safe_ret) +SYM_FUNC_END(srso_untrain_ret) +__EXPORT_THUNK(srso_untrain_ret) + +SYM_FUNC_START(__x86_return_thunk) + ALTERNATIVE_2 "jmp __ret", "call srso_safe_ret", X86_FEATURE_SRSO, \ + "call srso_safe_ret_alias", X86_FEATURE_SRSO_ALIAS + int3 +SYM_CODE_END(__x86_return_thunk) EXPORT_SYMBOL(__x86_return_thunk) #endif /* CONFIG_RETHUNK */ |