diff options
Diffstat (limited to 'arch')
37 files changed, 282 insertions, 148 deletions
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 5882b2415596..1095c6647e96 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -344,14 +344,14 @@ */ #define __HFGRTR_EL2_RES0 (GENMASK(63, 56) | GENMASK(53, 51)) #define __HFGRTR_EL2_MASK GENMASK(49, 0) -#define __HFGRTR_EL2_nMASK (GENMASK(55, 54) | BIT(50)) +#define __HFGRTR_EL2_nMASK (GENMASK(58, 57) | GENMASK(55, 54) | BIT(50)) #define __HFGWTR_EL2_RES0 (GENMASK(63, 56) | GENMASK(53, 51) | \ BIT(46) | BIT(42) | BIT(40) | BIT(28) | \ GENMASK(26, 25) | BIT(21) | BIT(18) | \ GENMASK(15, 14) | GENMASK(10, 9) | BIT(2)) #define __HFGWTR_EL2_MASK GENMASK(49, 0) -#define __HFGWTR_EL2_nMASK (GENMASK(55, 54) | BIT(50)) +#define __HFGWTR_EL2_nMASK (GENMASK(58, 57) | GENMASK(55, 54) | BIT(50)) #define __HFGITR_EL2_RES0 GENMASK(63, 57) #define __HFGITR_EL2_MASK GENMASK(54, 0) diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 6dcdae4d38cb..a1e24228aaaa 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -55,11 +55,6 @@ static struct irq_ops arch_timer_irq_ops = { .get_input_level = kvm_arch_timer_get_input_level, }; -static bool has_cntpoff(void) -{ - return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF)); -} - static int nr_timers(struct kvm_vcpu *vcpu) { if (!vcpu_has_nv(vcpu)) @@ -180,7 +175,7 @@ u64 kvm_phys_timer_read(void) return timecounter->cc->read(timecounter->cc); } -static void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map) +void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map) { if (vcpu_has_nv(vcpu)) { if (is_hyp_ctxt(vcpu)) { @@ -548,8 +543,7 @@ static void timer_save_state(struct arch_timer_context *ctx) timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL)); cval = read_sysreg_el0(SYS_CNTP_CVAL); - if (!has_cntpoff()) - cval -= timer_get_offset(ctx); + cval -= timer_get_offset(ctx); timer_set_cval(ctx, cval); @@ -636,8 +630,7 @@ static void timer_restore_state(struct arch_timer_context *ctx) cval = timer_get_cval(ctx); offset = timer_get_offset(ctx); set_cntpoff(offset); - if (!has_cntpoff()) - cval += offset; + cval += offset; write_sysreg_el0(cval, SYS_CNTP_CVAL); isb(); write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTP_CTL); diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index 9ced1bf0c2b7..ee902ff2a50f 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -977,6 +977,8 @@ enum fg_filter_id { static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = { /* HFGRTR_EL2, HFGWTR_EL2 */ + SR_FGT(SYS_PIR_EL1, HFGxTR, nPIR_EL1, 0), + SR_FGT(SYS_PIRE0_EL1, HFGxTR, nPIRE0_EL1, 0), SR_FGT(SYS_TPIDR2_EL0, HFGxTR, nTPIDR2_EL0, 0), SR_FGT(SYS_SMPRI_EL1, HFGxTR, nSMPRI_EL1, 0), SR_FGT(SYS_ACCDATA_EL1, HFGxTR, nACCDATA_EL1, 0), diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 6537f58b1a8c..448b17080d36 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -39,6 +39,26 @@ static void __activate_traps(struct kvm_vcpu *vcpu) ___activate_traps(vcpu); + if (has_cntpoff()) { + struct timer_map map; + + get_timer_map(vcpu, &map); + + /* + * We're entrering the guest. Reload the correct + * values from memory now that TGE is clear. + */ + if (map.direct_ptimer == vcpu_ptimer(vcpu)) + val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); + if (map.direct_ptimer == vcpu_hptimer(vcpu)) + val = __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2); + + if (map.direct_ptimer) { + write_sysreg_el0(val, SYS_CNTP_CVAL); + isb(); + } + } + val = read_sysreg(cpacr_el1); val |= CPACR_ELx_TTA; val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN | @@ -77,6 +97,30 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); + if (has_cntpoff()) { + struct timer_map map; + u64 val, offset; + + get_timer_map(vcpu, &map); + + /* + * We're exiting the guest. Save the latest CVAL value + * to memory and apply the offset now that TGE is set. + */ + val = read_sysreg_el0(SYS_CNTP_CVAL); + if (map.direct_ptimer == vcpu_ptimer(vcpu)) + __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = val; + if (map.direct_ptimer == vcpu_hptimer(vcpu)) + __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = val; + + offset = read_sysreg_s(SYS_CNTPOFF_EL2); + + if (map.direct_ptimer && offset) { + write_sysreg_el0(val + offset, SYS_CNTP_CVAL); + isb(); + } + } + /* * ARM errata 1165522 and 1530923 require the actual execution of the * above before we can switch to the EL2/EL0 translation regime used by diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c index 0eea225fd09a..a243934c5568 100644 --- a/arch/arm64/kvm/pmu.c +++ b/arch/arm64/kvm/pmu.c @@ -39,7 +39,7 @@ void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) { struct kvm_pmu_events *pmu = kvm_get_pmu_events(); - if (!kvm_arm_support_pmu_v3() || !pmu || !kvm_pmu_switch_needed(attr)) + if (!kvm_arm_support_pmu_v3() || !kvm_pmu_switch_needed(attr)) return; if (!attr->exclude_host) @@ -55,7 +55,7 @@ void kvm_clr_pmu_events(u32 clr) { struct kvm_pmu_events *pmu = kvm_get_pmu_events(); - if (!kvm_arm_support_pmu_v3() || !pmu) + if (!kvm_arm_support_pmu_v3()) return; pmu->events_host &= ~clr; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index e92ec810d449..0afd6136e275 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -2122,8 +2122,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_PMMIR_EL1), trap_raz_wi }, { SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 }, - { SYS_DESC(SYS_PIRE0_EL1), access_vm_reg, reset_unknown, PIRE0_EL1 }, - { SYS_DESC(SYS_PIR_EL1), access_vm_reg, reset_unknown, PIR_EL1 }, + { SYS_DESC(SYS_PIRE0_EL1), NULL, reset_unknown, PIRE0_EL1 }, + { SYS_DESC(SYS_PIR_EL1), NULL, reset_unknown, PIR_EL1 }, { SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 }, { SYS_DESC(SYS_LORSA_EL1), trap_loregion }, diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index 0dcb36b32cb2..c486c2341b66 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -52,10 +52,9 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, * @offset: bus address of the memory * @size: size of the resource to map */ -extern pgprot_t pgprot_wc; - #define ioremap_wc(offset, size) \ - ioremap_prot((offset), (size), pgprot_val(pgprot_wc)) + ioremap_prot((offset), (size), \ + pgprot_val(wc_enabled ? PAGE_KERNEL_WUC : PAGE_KERNEL_SUC)) #define ioremap_cache(offset, size) \ ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL)) diff --git a/arch/loongarch/include/asm/linkage.h b/arch/loongarch/include/asm/linkage.h index 81b0c4cfbf4f..e2eca1a25b4e 100644 --- a/arch/loongarch/include/asm/linkage.h +++ b/arch/loongarch/include/asm/linkage.h @@ -33,4 +33,12 @@ .cfi_endproc; \ SYM_END(name, SYM_T_FUNC) +#define SYM_CODE_START(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) \ + .cfi_startproc; + +#define SYM_CODE_END(name) \ + .cfi_endproc; \ + SYM_END(name, SYM_T_NONE) + #endif diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h index 35348d4c4209..21319c1e045c 100644 --- a/arch/loongarch/include/asm/pgtable-bits.h +++ b/arch/loongarch/include/asm/pgtable-bits.h @@ -105,13 +105,15 @@ static inline pgprot_t pgprot_noncached(pgprot_t _prot) return __pgprot(prot); } +extern bool wc_enabled; + #define pgprot_writecombine pgprot_writecombine static inline pgprot_t pgprot_writecombine(pgprot_t _prot) { unsigned long prot = pgprot_val(_prot); - prot = (prot & ~_CACHE_MASK) | _CACHE_WUC; + prot = (prot & ~_CACHE_MASK) | (wc_enabled ? _CACHE_WUC : _CACHE_SUC); return __pgprot(prot); } diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S index 65518bb8f472..1ec8e4c4cc2b 100644 --- a/arch/loongarch/kernel/entry.S +++ b/arch/loongarch/kernel/entry.S @@ -18,7 +18,7 @@ .text .cfi_sections .debug_frame .align 5 -SYM_FUNC_START(handle_syscall) +SYM_CODE_START(handle_syscall) csrrd t0, PERCPU_BASE_KS la.pcrel t1, kernelsp add.d t1, t1, t0 @@ -71,7 +71,7 @@ SYM_FUNC_START(handle_syscall) bl do_syscall RESTORE_ALL_AND_RET -SYM_FUNC_END(handle_syscall) +SYM_CODE_END(handle_syscall) _ASM_NOKPROBE(handle_syscall) SYM_CODE_START(ret_from_fork) diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 78f066384657..2bb3aa2dcfcb 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -31,7 +31,7 @@ SYM_FUNC_START(__arch_cpu_idle) 1: jr ra SYM_FUNC_END(__arch_cpu_idle) -SYM_FUNC_START(handle_vint) +SYM_CODE_START(handle_vint) BACKUP_T0T1 SAVE_ALL la_abs t1, __arch_cpu_idle @@ -46,11 +46,11 @@ SYM_FUNC_START(handle_vint) la_abs t0, do_vint jirl ra, t0, 0 RESTORE_ALL_AND_RET -SYM_FUNC_END(handle_vint) +SYM_CODE_END(handle_vint) -SYM_FUNC_START(except_vec_cex) +SYM_CODE_START(except_vec_cex) b cache_parity_error -SYM_FUNC_END(except_vec_cex) +SYM_CODE_END(except_vec_cex) .macro build_prep_badv csrrd t0, LOONGARCH_CSR_BADV @@ -66,7 +66,7 @@ SYM_FUNC_END(except_vec_cex) .macro BUILD_HANDLER exception handler prep .align 5 - SYM_FUNC_START(handle_\exception) + SYM_CODE_START(handle_\exception) 666: BACKUP_T0T1 SAVE_ALL @@ -76,7 +76,7 @@ SYM_FUNC_END(except_vec_cex) jirl ra, t0, 0 668: RESTORE_ALL_AND_RET - SYM_FUNC_END(handle_\exception) + SYM_CODE_END(handle_\exception) SYM_DATA(unwind_hint_\exception, .word 668b - 666b) .endm @@ -93,7 +93,7 @@ SYM_FUNC_END(except_vec_cex) BUILD_HANDLER watch watch none BUILD_HANDLER reserved reserved none /* others */ -SYM_FUNC_START(handle_sys) +SYM_CODE_START(handle_sys) la_abs t0, handle_syscall jr t0 -SYM_FUNC_END(handle_sys) +SYM_CODE_END(handle_sys) diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 7783f0a3d742..aed65915e932 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -161,19 +161,19 @@ static void __init smbios_parse(void) } #ifdef CONFIG_ARCH_WRITECOMBINE -pgprot_t pgprot_wc = PAGE_KERNEL_WUC; +bool wc_enabled = true; #else -pgprot_t pgprot_wc = PAGE_KERNEL_SUC; +bool wc_enabled = false; #endif -EXPORT_SYMBOL(pgprot_wc); +EXPORT_SYMBOL(wc_enabled); static int __init setup_writecombine(char *p) { if (!strcmp(p, "on")) - pgprot_wc = PAGE_KERNEL_WUC; + wc_enabled = true; else if (!strcmp(p, "off")) - pgprot_wc = PAGE_KERNEL_SUC; + wc_enabled = false; else pr_warn("Unknown writecombine setting \"%s\".\n", p); diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index f3fe8c06ba4d..4dd53427f657 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -43,11 +43,11 @@ void copy_user_highpage(struct page *to, struct page *from, { void *vfrom, *vto; - vto = kmap_atomic(to); - vfrom = kmap_atomic(from); + vfrom = kmap_local_page(from); + vto = kmap_local_page(to); copy_page(vto, vfrom); - kunmap_atomic(vfrom); - kunmap_atomic(vto); + kunmap_local(vfrom); + kunmap_local(vto); /* Make sure this page is cleared on other CPU's too before using it */ smp_wmb(); } @@ -240,6 +240,7 @@ pgd_t swapper_pg_dir[_PTRS_PER_PGD] __section(".bss..swapper_pg_dir"); pgd_t invalid_pg_dir[_PTRS_PER_PGD] __page_aligned_bss; #ifndef __PAGETABLE_PUD_FOLDED pud_t invalid_pud_table[PTRS_PER_PUD] __page_aligned_bss; +EXPORT_SYMBOL(invalid_pud_table); #endif #ifndef __PAGETABLE_PMD_FOLDED pmd_t invalid_pmd_table[PTRS_PER_PMD] __page_aligned_bss; diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index ca17dd3a1915..d5d682f3d29f 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -17,7 +17,7 @@ #define PTRS_PER_PTE_BITS (PAGE_SHIFT - 3) .macro tlb_do_page_fault, write - SYM_FUNC_START(tlb_do_page_fault_\write) + SYM_CODE_START(tlb_do_page_fault_\write) SAVE_ALL csrrd a2, LOONGARCH_CSR_BADV move a0, sp @@ -25,13 +25,13 @@ li.w a1, \write bl do_page_fault RESTORE_ALL_AND_RET - SYM_FUNC_END(tlb_do_page_fault_\write) + SYM_CODE_END(tlb_do_page_fault_\write) .endm tlb_do_page_fault 0 tlb_do_page_fault 1 -SYM_FUNC_START(handle_tlb_protect) +SYM_CODE_START(handle_tlb_protect) BACKUP_T0T1 SAVE_ALL move a0, sp @@ -41,9 +41,9 @@ SYM_FUNC_START(handle_tlb_protect) la_abs t0, do_page_fault jirl ra, t0, 0 RESTORE_ALL_AND_RET -SYM_FUNC_END(handle_tlb_protect) +SYM_CODE_END(handle_tlb_protect) -SYM_FUNC_START(handle_tlb_load) +SYM_CODE_START(handle_tlb_load) csrwr t0, EXCEPTION_KS0 csrwr t1, EXCEPTION_KS1 csrwr ra, EXCEPTION_KS2 @@ -187,16 +187,16 @@ nopage_tlb_load: csrrd ra, EXCEPTION_KS2 la_abs t0, tlb_do_page_fault_0 jr t0 -SYM_FUNC_END(handle_tlb_load) +SYM_CODE_END(handle_tlb_load) -SYM_FUNC_START(handle_tlb_load_ptw) +SYM_CODE_START(handle_tlb_load_ptw) csrwr t0, LOONGARCH_CSR_KS0 csrwr t1, LOONGARCH_CSR_KS1 la_abs t0, tlb_do_page_fault_0 jr t0 -SYM_FUNC_END(handle_tlb_load_ptw) +SYM_CODE_END(handle_tlb_load_ptw) -SYM_FUNC_START(handle_tlb_store) +SYM_CODE_START(handle_tlb_store) csrwr t0, EXCEPTION_KS0 csrwr t1, EXCEPTION_KS1 csrwr ra, EXCEPTION_KS2 @@ -343,16 +343,16 @@ nopage_tlb_store: csrrd ra, EXCEPTION_KS2 la_abs t0, tlb_do_page_fault_1 jr t0 -SYM_FUNC_END(handle_tlb_store) +SYM_CODE_END(handle_tlb_store) -SYM_FUNC_START(handle_tlb_store_ptw) +SYM_CODE_START(handle_tlb_store_ptw) csrwr t0, LOONGARCH_CSR_KS0 csrwr t1, LOONGARCH_CSR_KS1 la_abs t0, tlb_do_page_fault_1 jr t0 -SYM_FUNC_END(handle_tlb_store_ptw) +SYM_CODE_END(handle_tlb_store_ptw) -SYM_FUNC_START(handle_tlb_modify) +SYM_CODE_START(handle_tlb_modify) csrwr t0, EXCEPTION_KS0 csrwr t1, EXCEPTION_KS1 csrwr ra, EXCEPTION_KS2 @@ -497,16 +497,16 @@ nopage_tlb_modify: csrrd ra, EXCEPTION_KS2 la_abs t0, tlb_do_page_fault_1 jr t0 -SYM_FUNC_END(handle_tlb_modify) +SYM_CODE_END(handle_tlb_modify) -SYM_FUNC_START(handle_tlb_modify_ptw) +SYM_CODE_START(handle_tlb_modify_ptw) csrwr t0, LOONGARCH_CSR_KS0 csrwr t1, LOONGARCH_CSR_KS1 la_abs t0, tlb_do_page_fault_1 jr t0 -SYM_FUNC_END(handle_tlb_modify_ptw) +SYM_CODE_END(handle_tlb_modify_ptw) -SYM_FUNC_START(handle_tlb_refill) +SYM_CODE_START(handle_tlb_refill) csrwr t0, LOONGARCH_CSR_TLBRSAVE csrrd t0, LOONGARCH_CSR_PGD lddir t0, t0, 3 @@ -521,4 +521,4 @@ SYM_FUNC_START(handle_tlb_refill) tlbfill csrrd t0, LOONGARCH_CSR_TLBRSAVE ertn -SYM_FUNC_END(handle_tlb_refill) +SYM_CODE_END(handle_tlb_refill) diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 7b2ac1319d70..467ee6b95ae1 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -592,7 +592,7 @@ static int kvm_mips_map_page(struct kvm_vcpu *vcpu, unsigned long gpa, gfn_t gfn = gpa >> PAGE_SHIFT; int srcu_idx, err; kvm_pfn_t pfn; - pte_t *ptep, entry, old_pte; + pte_t *ptep, entry; bool writeable; unsigned long prot_bits; unsigned long mmu_seq; @@ -664,7 +664,6 @@ retry: entry = pfn_pte(pfn, __pgprot(prot_bits)); /* Write the PTE */ - old_pte = *ptep; set_pte(ptep, entry); err = 0; diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 01257ce3b89c..442a74f113cb 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -57,6 +57,7 @@ static void kasan_populate_shadow(void) pmd_t pmd_z = __pmd(__pa(kasan_early_shadow_pte) | _SEGMENT_ENTRY); pud_t pud_z = __pud(__pa(kasan_early_shadow_pmd) | _REGION3_ENTRY); p4d_t p4d_z = __p4d(__pa(kasan_early_shadow_pud) | _REGION2_ENTRY); + unsigned long memgap_start = 0; unsigned long untracked_end; unsigned long start, end; int i; @@ -101,8 +102,12 @@ static void kasan_populate_shadow(void) * +- shadow end ----+---------+- shadow end ---+ */ - for_each_physmem_usable_range(i, &start, &end) + for_each_physmem_usable_range(i, &start, &end) { kasan_populate(start, end, POPULATE_KASAN_MAP_SHADOW); + if (memgap_start && physmem_info.info_source == MEM_DETECT_DIAG260) + kasan_populate(memgap_start, start, POPULATE_KASAN_ZERO_SHADOW); + memgap_start = end; + } if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { untracked_end = VMALLOC_START; /* shallowly populate kasan shadow for vmalloc and modules */ diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index c1b47d608a2b..efaebba5ee19 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -303,11 +303,6 @@ static inline u8 gisa_get_ipm_or_restore_iam(struct kvm_s390_gisa_interrupt *gi) return 0; } -static inline int gisa_in_alert_list(struct kvm_s390_gisa *gisa) -{ - return READ_ONCE(gisa->next_alert) != (u32)virt_to_phys(gisa); -} - static inline void gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) { set_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa); @@ -3216,11 +3211,12 @@ void kvm_s390_gisa_destroy(struct kvm *kvm) if (!gi->origin) return; - if (gi->alert.mask) - KVM_EVENT(3, "vm 0x%pK has unexpected iam 0x%02x", - kvm, gi->alert.mask); - while (gisa_in_alert_list(gi->origin)) - cpu_relax(); + WARN(gi->alert.mask != 0x00, + "unexpected non zero alert.mask 0x%02x", + gi->alert.mask); + gi->alert.mask = 0x00; + if (gisa_set_iam(gi->origin, gi->alert.mask)) + process_gib_alert_list(); hrtimer_cancel(&gi->timer); gi->origin = NULL; VM_EVENT(kvm, 3, "gisa 0x%pK destroyed", gisa); diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 2d9b01d7ca4c..99209085c75b 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -564,6 +564,17 @@ static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg, s->dma_length = 0; } } + +static unsigned long *bitmap_vzalloc(size_t bits, gfp_t flags) +{ + size_t n = BITS_TO_LONGS(bits); + size_t bytes; + + if (unlikely(check_mul_overflow(n, sizeof(unsigned long), &bytes))) + return NULL; + + return vzalloc(bytes); +} int zpci_dma_init_device(struct zpci_dev *zdev) { @@ -604,13 +615,13 @@ int zpci_dma_init_device(struct zpci_dev *zdev) zdev->end_dma - zdev->start_dma + 1); zdev->end_dma = zdev->start_dma + zdev->iommu_size - 1; zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT; - zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8); + zdev->iommu_bitmap = bitmap_vzalloc(zdev->iommu_pages, GFP_KERNEL); if (!zdev->iommu_bitmap) { rc = -ENOMEM; goto free_dma_table; } if (!s390_iommu_strict) { - zdev->lazy_bitmap = vzalloc(zdev->iommu_pages / 8); + zdev->lazy_bitmap = bitmap_vzalloc(zdev->iommu_pages, GFP_KERNEL); if (!zdev->lazy_bitmap) { rc = -ENOMEM; goto free_bitmap; diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index dc8c876fbd8f..80d76aea1f7b 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -103,6 +103,16 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, return ES_OK; } +static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size) +{ + return ES_OK; +} + +static bool fault_in_kernel_space(unsigned long address) +{ + return false; +} + #undef __init #define __init diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index 31089b851c4f..a2be3aefff9f 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -157,7 +157,8 @@ static inline void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) { static inline void fpu_sync_guest_vmexit_xfd_state(void) { } #endif -extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u32 pkru); +extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, + unsigned int size, u64 xfeatures, u32 pkru); extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru); static inline void fpstate_set_confidential(struct fpu_guest *gfpu) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 17715cb8731d..70d139406bc8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -528,7 +528,6 @@ struct kvm_pmu { u64 raw_event_mask; struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC]; struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED]; - struct irq_work irq_work; /* * Overlay the bitmap with a 64-bit atomic so that all bits can be diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 19bf955b67e0..3ac0ffc4f3e2 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -268,6 +268,7 @@ enum avic_ipi_failure_cause { AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, AVIC_IPI_FAILURE_INVALID_TARGET, AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, + AVIC_IPI_FAILURE_INVALID_IPI_VECTOR, }; #define AVIC_PHYSICAL_MAX_INDEX_MASK GENMASK_ULL(8, 0) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index a86d37052a64..a21a4d0ecc34 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -369,14 +369,15 @@ int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest) EXPORT_SYMBOL_GPL(fpu_swap_kvm_fpstate); void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, - unsigned int size, u32 pkru) + unsigned int size, u64 xfeatures, u32 pkru) { struct fpstate *kstate = gfpu->fpstate; union fpregs_state *ustate = buf; struct membuf mb = { .p = buf, .left = size }; if (cpu_feature_enabled(X86_FEATURE_XSAVE)) { - __copy_xstate_to_uabi_buf(mb, kstate, pkru, XSTATE_COPY_XSAVE); + __copy_xstate_to_uabi_buf(mb, kstate, xfeatures, pkru, + XSTATE_COPY_XSAVE); } else { memcpy(&ustate->fxsave, &kstate->regs.fxsave, sizeof(ustate->fxsave)); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index cadf68737e6b..ef6906107c54 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1049,6 +1049,7 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, * __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer * @to: membuf descriptor * @fpstate: The fpstate buffer from which to copy + * @xfeatures: The mask of xfeatures to save (XSAVE mode only) * @pkru_val: The PKRU value to store in the PKRU component * @copy_mode: The requested copy mode * @@ -1059,7 +1060,8 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, * It supports partial copy but @to.pos always starts from zero. */ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, - u32 pkru_val, enum xstate_copy_mode copy_mode) + u64 xfeatures, u32 pkru_val, + enum xstate_copy_mode copy_mode) { const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr); struct xregs_state *xinit = &init_fpstate.regs.xsave; @@ -1083,7 +1085,7 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, break; case XSTATE_COPY_XSAVE: - header.xfeatures &= fpstate->user_xfeatures; + header.xfeatures &= fpstate->user_xfeatures & xfeatures; break; } @@ -1185,6 +1187,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode copy_mode) { __copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate, + tsk->thread.fpu.fpstate->user_xfeatures, tsk->thread.pkru, copy_mode); } @@ -1536,10 +1539,7 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize, fpregs_restore_userregs(); newfps->xfeatures = curfps->xfeatures | xfeatures; - - if (!guest_fpu) - newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; - + newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; newfps->xfd = curfps->xfd & ~xfeatures; /* Do the final updates within the locked region */ diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index a4ecb04d8d64..3518fb26d06b 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -43,7 +43,8 @@ enum xstate_copy_mode { struct membuf; extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, - u32 pkru_val, enum xstate_copy_mode copy_mode); + u64 xfeatures, u32 pkru_val, + enum xstate_copy_mode copy_mode); extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode mode); extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru); diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index dcf325b7b022..ccb0915e84e1 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -632,6 +632,23 @@ fail: sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); } +static enum es_result vc_insn_string_check(struct es_em_ctxt *ctxt, + unsigned long address, + bool write) +{ + if (user_mode(ctxt->regs) && fault_in_kernel_space(address)) { + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.error_code = X86_PF_USER; + ctxt->fi.cr2 = address; + if (write) + ctxt->fi.error_code |= X86_PF_WRITE; + + return ES_EXCEPTION; + } + + return ES_OK; +} + static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt, void *src, char *buf, unsigned int data_size, @@ -639,7 +656,12 @@ static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt, bool backwards) { int i, b = backwards ? -1 : 1; - enum es_result ret = ES_OK; + unsigned long address = (unsigned long)src; + enum es_result ret; + + ret = vc_insn_string_check(ctxt, address, false); + if (ret != ES_OK) + return ret; for (i = 0; i < count; i++) { void *s = src + (i * data_size * b); @@ -660,7 +682,12 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt, bool backwards) { int i, s = backwards ? -1 : 1; - enum es_result ret = ES_OK; + unsigned long address = (unsigned long)dst; + enum es_result ret; + + ret = vc_insn_string_check(ctxt, address, true); + if (ret != ES_OK) + return ret; for (i = 0; i < count; i++) { void *d = dst + (i * data_size * s); @@ -696,6 +723,9 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt, static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) { struct insn *insn = &ctxt->insn; + size_t size; + u64 port; + *exitinfo = 0; switch (insn->opcode.bytes[0]) { @@ -704,7 +734,7 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) case 0x6d: *exitinfo |= IOIO_TYPE_INS; *exitinfo |= IOIO_SEG_ES; - *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + port = ctxt->regs->dx & 0xffff; break; /* OUTS opcodes */ @@ -712,41 +742,43 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) case 0x6f: *exitinfo |= IOIO_TYPE_OUTS; *exitinfo |= IOIO_SEG_DS; - *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + port = ctxt->regs->dx & 0xffff; break; /* IN immediate opcodes */ case 0xe4: case 0xe5: *exitinfo |= IOIO_TYPE_IN; - *exitinfo |= (u8)insn->immediate.value << 16; + port = (u8)insn->immediate.value & 0xffff; break; /* OUT immediate opcodes */ case 0xe6: case 0xe7: *exitinfo |= IOIO_TYPE_OUT; - *exitinfo |= (u8)insn->immediate.value << 16; + port = (u8)insn->immediate.value & 0xffff; break; /* IN register opcodes */ case 0xec: case 0xed: *exitinfo |= IOIO_TYPE_IN; - *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + port = ctxt->regs->dx & 0xffff; break; /* OUT register opcodes */ case 0xee: case 0xef: *exitinfo |= IOIO_TYPE_OUT; - *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + port = ctxt->regs->dx & 0xffff; break; default: return ES_DECODE_FAILED; } + *exitinfo |= port << 16; + switch (insn->opcode.bytes[0]) { case 0x6c: case 0x6e: @@ -756,12 +788,15 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) case 0xee: /* Single byte opcodes */ *exitinfo |= IOIO_DATA_8; + size = 1; break; default: /* Length determined by instruction parsing */ *exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16 : IOIO_DATA_32; + size = (insn->opnd_bytes == 2) ? 2 : 4; } + switch (insn->addr_bytes) { case 2: *exitinfo |= IOIO_ADDR_16; @@ -777,7 +812,7 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) if (insn_has_rep_prefix(insn)) *exitinfo |= IOIO_REP; - return ES_OK; + return vc_ioio_check(ctxt, (u16)port, size); } static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index d8c1e3be74c0..6395bfd87b68 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -524,6 +524,33 @@ static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt return ES_OK; } +static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size) +{ + BUG_ON(size > 4); + + if (user_mode(ctxt->regs)) { + struct thread_struct *t = ¤t->thread; + struct io_bitmap *iobm = t->io_bitmap; + size_t idx; + + if (!iobm) + goto fault; + + for (idx = port; idx < port + size; ++idx) { + if (test_bit(idx, iobm->bitmap)) + goto fault; + } + } + + return ES_OK; + +fault: + ctxt->fi.vector = X86_TRAP_GP; + ctxt->fi.error_code = 0; + + return ES_EXCEPTION; +} + /* Include code shared with pre-decompression boot stage */ #include "sev-shared.c" @@ -1508,6 +1535,9 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ES_DECODE_FAILED; } + if (user_mode(ctxt->regs)) + return ES_UNSUPPORTED; + switch (mmio) { case INSN_MMIO_WRITE: memcpy(ghcb->shared_buffer, reg_data, bytes); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 0544e30b4946..773132c3bf5a 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -360,14 +360,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); - /* - * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if - * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't - * supported by the host. - */ - vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0 | - XFEATURE_MASK_FPSSE; - kvm_update_pv_runtime(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index dcd60b39e794..3e977dbbf993 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2759,13 +2759,17 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) { u32 reg = kvm_lapic_get_reg(apic, lvt_type); int vector, mode, trig_mode; + int r; if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) { vector = reg & APIC_VECTOR_MASK; mode = reg & APIC_MODE_MASK; trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; - return __apic_accept_irq(apic, mode, vector, 1, trig_mode, - NULL); + + r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); + if (r && lvt_type == APIC_LVTPC) + kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); + return r; } return 0; } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index edb89b51b383..9ae07db6f0f6 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -93,14 +93,6 @@ void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops) #undef __KVM_X86_PMU_OP } -static void kvm_pmi_trigger_fn(struct irq_work *irq_work) -{ - struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work); - struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); - - kvm_pmu_deliver_pmi(vcpu); -} - static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); @@ -124,20 +116,7 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); } - if (!pmc->intr || skip_pmi) - return; - - /* - * Inject PMI. If vcpu was in a guest mode during NMI PMI - * can be ejected on a guest mode re-entry. Otherwise we can't - * be sure that vcpu wasn't executing hlt instruction at the - * time of vmexit and is not going to re-enter guest mode until - * woken up. So we should wake it, but this is impossible from - * NMI context. Do it from irq work instead. - */ - if (in_pmi && !kvm_handling_nmi_from_guest(pmc->vcpu)) - irq_work_queue(&pmc_to_pmu(pmc)->irq_work); - else + if (pmc->intr && !skip_pmi) kvm_make_request(KVM_REQ_PMI, pmc->vcpu); } @@ -675,9 +654,6 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) void kvm_pmu_reset(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - - irq_work_sync(&pmu->irq_work); static_call(kvm_x86_pmu_reset)(vcpu); } @@ -687,7 +663,6 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) memset(pmu, 0, sizeof(*pmu)); static_call(kvm_x86_pmu_init)(vcpu); - init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); pmu->event_count = 0; pmu->need_cleanup = false; kvm_pmu_refresh(vcpu); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 7d9ba301c090..1d64113de488 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -74,6 +74,12 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc) return counter & pmc_bitmask(pmc); } +static inline void pmc_write_counter(struct kvm_pmc *pmc, u64 val) +{ + pmc->counter += val - pmc_read_counter(pmc); + pmc->counter &= pmc_bitmask(pmc); +} + static inline void pmc_release_perf_event(struct kvm_pmc *pmc) { if (pmc->perf_event) { diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 2092db892d7d..4b74ea91f4e6 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -529,8 +529,11 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: WARN_ONCE(1, "Invalid backing page\n"); break; + case AVIC_IPI_FAILURE_INVALID_IPI_VECTOR: + /* Invalid IPI with vector < 16 */ + break; default: - pr_err("Unknown IPI interception\n"); + vcpu_unimpl(vcpu, "Unknown avic incomplete IPI interception\n"); } return 1; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index dd496c9e5f91..3fea8c47679e 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1253,6 +1253,9 @@ void svm_leave_nested(struct kvm_vcpu *vcpu) nested_svm_uninit_mmu_context(vcpu); vmcb_mark_all_dirty(svm->vmcb); + + if (kvm_apicv_activated(vcpu->kvm)) + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); } kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index cef5a3d0abd0..373ff6a6687b 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -160,7 +160,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* MSR_PERFCTRn */ pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); if (pmc) { - pmc->counter += data - pmc_read_counter(pmc); + pmc_write_counter(pmc, data); pmc_update_sample_period(pmc); return 0; } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9507df93f410..beea99c8e8e0 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -691,7 +691,7 @@ static int svm_hardware_enable(void) */ if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { struct sev_es_save_area *hostsa; - u32 msr_hi; + u32 __maybe_unused msr_hi; hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); @@ -913,8 +913,7 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) if (intercept == svm->x2avic_msrs_intercepted) return; - if (!x2avic_enabled || - !apic_x2apic_mode(svm->vcpu.arch.apic)) + if (!x2avic_enabled) return; for (i = 0; i < MAX_DIRECT_ACCESS_MSRS; i++) { diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index f2efa0bf7ae8..820d3e1f6b4f 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -436,11 +436,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated && !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; - pmc->counter += data - pmc_read_counter(pmc); + pmc_write_counter(pmc, data); pmc_update_sample_period(pmc); break; } else if ((pmc = get_fixed_pmc(pmu, msr))) { - pmc->counter += data - pmc_read_counter(pmc); + pmc_write_counter(pmc, data); pmc_update_sample_period(pmc); break; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9f18b06bbda6..41cce5031126 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5382,26 +5382,37 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, return 0; } -static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, - struct kvm_xsave *guest_xsave) -{ - if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return; - - fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, - guest_xsave->region, - sizeof(guest_xsave->region), - vcpu->arch.pkru); -} static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, u8 *state, unsigned int size) { + /* + * Only copy state for features that are enabled for the guest. The + * state itself isn't problematic, but setting bits in the header for + * features that are supported in *this* host but not exposed to the + * guest can result in KVM_SET_XSAVE failing when live migrating to a + * compatible host without the features that are NOT exposed to the + * guest. + * + * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if + * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't + * supported by the host. + */ + u64 supported_xcr0 = vcpu->arch.guest_supported_xcr0 | + XFEATURE_MASK_FPSSE; + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return; - fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, - state, size, vcpu->arch.pkru); + fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size, + supported_xcr0, vcpu->arch.pkru); +} + +static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) +{ + return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region, + sizeof(guest_xsave->region)); } static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, @@ -12843,6 +12854,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) return true; #endif + if (kvm_test_request(KVM_REQ_PMI, vcpu)) + return true; + if (kvm_arch_interrupt_allowed(vcpu) && (kvm_cpu_has_interrupt(vcpu) || kvm_guest_apic_has_interrupt(vcpu))) |