diff options
author | Ingo Molnar <mingo@kernel.org> | 2024-04-09 10:28:41 +0300 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2024-04-09 10:28:41 +0300 |
commit | 0e6ebfd163645d300fdf4abedd1718195ad293bc (patch) | |
tree | 510614aa8a43af846e27c7581adda801eaf03fc6 /arch/x86 | |
parent | 186d7ef52c1f0c41450dedbdf6d6325d0a84e4c5 (diff) | |
parent | fec50db7033ea478773b159e0e2efb135270e3b7 (diff) | |
download | linux-0e6ebfd163645d300fdf4abedd1718195ad293bc.tar.xz |
Merge tag 'v6.9-rc3' into x86/cpu, to pick up fixes
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86')
75 files changed, 836 insertions, 494 deletions
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild index 6a1f36df6a18..cf0ad89f5639 100644 --- a/arch/x86/Kbuild +++ b/arch/x86/Kbuild @@ -28,7 +28,7 @@ obj-y += net/ obj-$(CONFIG_KEXEC_FILE) += purgatory/ -obj-y += virt/svm/ +obj-y += virt/ # for cleaning subdir- += boot tools diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7aed87cbf386..4fff6ed46e90 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -472,10 +472,6 @@ config X86_MPPARSE For old smp systems that do not have proper acpi support. Newer systems (esp with 64bit cpus) with acpi support, MADT and DSDT will override it -config GOLDFISH - def_bool y - depends on X86_GOLDFISH - config X86_CPU_RESCTRL bool "x86 CPU resource control support" depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD) @@ -2443,6 +2439,8 @@ config USE_X86_SEG_SUPPORT # with named address spaces - see GCC PR sanitizer/111736. # depends on !KASAN + # -fsanitize=thread (KCSAN) is also incompatible. + depends on !KCSAN config CC_HAS_SLS def_bool $(cc-option,-mharden-sls=all) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 662d9d4033e6..5ab93fcdd691 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -251,8 +251,6 @@ archheaders: libs-y += arch/x86/lib/ -core-y += arch/x86/virt/ - # drivers-y are linked after core-y drivers-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/ drivers-$(CONFIG_PCI) += arch/x86/pci/ diff --git a/arch/x86/boot/compressed/efi_mixed.S b/arch/x86/boot/compressed/efi_mixed.S index f4e22ef774ab..876fc6d46a13 100644 --- a/arch/x86/boot/compressed/efi_mixed.S +++ b/arch/x86/boot/compressed/efi_mixed.S @@ -15,10 +15,12 @@ */ #include <linux/linkage.h> +#include <asm/asm-offsets.h> #include <asm/msr.h> #include <asm/page_types.h> #include <asm/processor-flags.h> #include <asm/segment.h> +#include <asm/setup.h> .code64 .text @@ -49,6 +51,11 @@ SYM_FUNC_START(startup_64_mixed_mode) lea efi32_boot_args(%rip), %rdx mov 0(%rdx), %edi mov 4(%rdx), %esi + + /* Switch to the firmware's stack */ + movl efi32_boot_sp(%rip), %esp + andl $~7, %esp + #ifdef CONFIG_EFI_HANDOVER_PROTOCOL mov 8(%rdx), %edx // saved bootparams pointer test %edx, %edx @@ -144,6 +151,7 @@ SYM_FUNC_END(__efi64_thunk) SYM_FUNC_START(efi32_stub_entry) call 1f 1: popl %ecx + leal (efi32_boot_args - 1b)(%ecx), %ebx /* Clear BSS */ xorl %eax, %eax @@ -158,6 +166,7 @@ SYM_FUNC_START(efi32_stub_entry) popl %ecx popl %edx popl %esi + movl %esi, 8(%ebx) jmp efi32_entry SYM_FUNC_END(efi32_stub_entry) #endif @@ -234,8 +243,6 @@ SYM_FUNC_END(efi_enter32) * * Arguments: %ecx image handle * %edx EFI system table pointer - * %esi struct bootparams pointer (or NULL when not using - * the EFI handover protocol) * * Since this is the point of no return for ordinary execution, no registers * are considered live except for the function parameters. [Note that the EFI @@ -254,13 +261,25 @@ SYM_FUNC_START_LOCAL(efi32_entry) /* Store firmware IDT descriptor */ sidtl (efi32_boot_idt - 1b)(%ebx) + /* Store firmware stack pointer */ + movl %esp, (efi32_boot_sp - 1b)(%ebx) + /* Store boot arguments */ leal (efi32_boot_args - 1b)(%ebx), %ebx movl %ecx, 0(%ebx) movl %edx, 4(%ebx) - movl %esi, 8(%ebx) movb $0x0, 12(%ebx) // efi_is64 + /* + * Allocate some memory for a temporary struct boot_params, which only + * needs the minimal pieces that startup_32() relies on. + */ + subl $PARAM_SIZE, %esp + movl %esp, %esi + movl $PAGE_SIZE, BP_kernel_alignment(%esi) + movl $_end - 1b, BP_init_size(%esi) + subl $startup_32 - 1b, BP_init_size(%esi) + /* Disable paging */ movl %cr0, %eax btrl $X86_CR0_PG_BIT, %eax @@ -286,8 +305,7 @@ SYM_FUNC_START(efi32_pe_entry) movl 8(%ebp), %ecx // image_handle movl 12(%ebp), %edx // sys_table - xorl %esi, %esi - jmp efi32_entry // pass %ecx, %edx, %esi + jmp efi32_entry // pass %ecx, %edx // no other registers remain live 2: popl %edi // restore callee-save registers @@ -318,5 +336,6 @@ SYM_DATA_END(efi32_boot_idt) SYM_DATA_LOCAL(efi32_boot_cs, .word 0) SYM_DATA_LOCAL(efi32_boot_ds, .word 0) +SYM_DATA_LOCAL(efi32_boot_sp, .long 0) SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0) SYM_DATA(efi_is64, .byte 1) diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index d07be9d05cd0..b31ef2424d19 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -3,19 +3,28 @@ * Confidential Computing Platform Capability checks * * Copyright (C) 2021 Advanced Micro Devices, Inc. + * Copyright (C) 2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * * Author: Tom Lendacky <thomas.lendacky@amd.com> */ #include <linux/export.h> #include <linux/cc_platform.h> +#include <linux/string.h> +#include <linux/random.h> +#include <asm/archrandom.h> #include <asm/coco.h> #include <asm/processor.h> enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE; u64 cc_mask __ro_after_init; +static struct cc_attr_flags { + __u64 host_sev_snp : 1, + __resv : 63; +} cc_flags; + static bool noinstr intel_cc_platform_has(enum cc_attr attr) { switch (attr) { @@ -89,6 +98,9 @@ static bool noinstr amd_cc_platform_has(enum cc_attr attr) case CC_ATTR_GUEST_SEV_SNP: return sev_status & MSR_AMD64_SEV_SNP_ENABLED; + case CC_ATTR_HOST_SEV_SNP: + return cc_flags.host_sev_snp; + default: return false; } @@ -148,3 +160,84 @@ u64 cc_mkdec(u64 val) } } EXPORT_SYMBOL_GPL(cc_mkdec); + +static void amd_cc_platform_clear(enum cc_attr attr) +{ + switch (attr) { + case CC_ATTR_HOST_SEV_SNP: + cc_flags.host_sev_snp = 0; + break; + default: + break; + } +} + +void cc_platform_clear(enum cc_attr attr) +{ + switch (cc_vendor) { + case CC_VENDOR_AMD: + amd_cc_platform_clear(attr); + break; + default: + break; + } +} + +static void amd_cc_platform_set(enum cc_attr attr) +{ + switch (attr) { + case CC_ATTR_HOST_SEV_SNP: + cc_flags.host_sev_snp = 1; + break; + default: + break; + } +} + +void cc_platform_set(enum cc_attr attr) +{ + switch (cc_vendor) { + case CC_VENDOR_AMD: + amd_cc_platform_set(attr); + break; + default: + break; + } +} + +__init void cc_random_init(void) +{ + /* + * The seed is 32 bytes (in units of longs), which is 256 bits, which + * is the security level that the RNG is targeting. + */ + unsigned long rng_seed[32 / sizeof(long)]; + size_t i, longs; + + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + return; + + /* + * Since the CoCo threat model includes the host, the only reliable + * source of entropy that can be neither observed nor manipulated is + * RDRAND. Usually, RDRAND failure is considered tolerable, but since + * CoCo guests have no other unobservable source of entropy, it's + * important to at least ensure the RNG gets some initial random seeds. + */ + for (i = 0; i < ARRAY_SIZE(rng_seed); i += longs) { + longs = arch_get_random_longs(&rng_seed[i], ARRAY_SIZE(rng_seed) - i); + + /* + * A zero return value means that the guest doesn't have RDRAND + * or the CPU is physically broken, and in both cases that + * means most crypto inside of the CoCo instance will be + * broken, defeating the purpose of CoCo in the first place. So + * just panic here because it's absolutely unsafe to continue + * executing. + */ + if (longs == 0) + panic("RDRAND is defective."); + } + add_device_randomness(rng_seed, sizeof(rng_seed)); + memzero_explicit(rng_seed, sizeof(rng_seed)); +} diff --git a/arch/x86/configs/tiny.config b/arch/x86/configs/tiny.config index 66c9e2aab16c..be3ee4294903 100644 --- a/arch/x86/configs/tiny.config +++ b/arch/x86/configs/tiny.config @@ -1,5 +1,6 @@ CONFIG_NOHIGHMEM=y # CONFIG_HIGHMEM4G is not set # CONFIG_HIGHMEM64G is not set +# CONFIG_UNWINDER_ORC is not set CONFIG_UNWINDER_GUESS=y # CONFIG_UNWINDER_FRAME_POINTER is not set diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 620f6257bbe9..3d64bcc403cf 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -9,7 +9,9 @@ include $(srctree)/lib/vdso/Makefile # Sanitizer runtimes are unavailable and cannot be linked here. KASAN_SANITIZE := n KMSAN_SANITIZE_vclock_gettime.o := n +KMSAN_SANITIZE_vdso32/vclock_gettime.o := n KMSAN_SANITIZE_vgetcpu.o := n +KMSAN_SANITIZE_vdso32/vgetcpu.o := n UBSAN_SANITIZE := n KCSAN_SANITIZE := n @@ -39,6 +41,7 @@ obj-$(CONFIG_X86_X32_ABI) += vdso-image-x32.o obj-$(CONFIG_COMPAT_32) += vdso-image-32.o vdso32-setup.o OBJECT_FILES_NON_STANDARD_vdso-image-32.o := n +OBJECT_FILES_NON_STANDARD_vdso-image-x32.o := n OBJECT_FILES_NON_STANDARD_vdso-image-64.o := n OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index aec16e581f5b..985ef3b47919 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -250,7 +250,7 @@ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] = /* * AMD Performance Monitor Family 17h and later: */ -static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = +static const u64 amd_zen1_perfmon_event_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, @@ -262,10 +262,39 @@ static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187, }; +static const u64 amd_zen2_perfmon_event_map[PERF_COUNT_HW_MAX] = +{ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, + [PERF_COUNT_HW_CACHE_MISSES] = 0x0964, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a9, +}; + +static const u64 amd_zen4_perfmon_event_map[PERF_COUNT_HW_MAX] = +{ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, + [PERF_COUNT_HW_CACHE_MISSES] = 0x0964, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a9, + [PERF_COUNT_HW_REF_CPU_CYCLES] = 0x100000120, +}; + static u64 amd_pmu_event_map(int hw_event) { - if (boot_cpu_data.x86 >= 0x17) - return amd_f17h_perfmon_event_map[hw_event]; + if (cpu_feature_enabled(X86_FEATURE_ZEN4) || boot_cpu_data.x86 >= 0x1a) + return amd_zen4_perfmon_event_map[hw_event]; + + if (cpu_feature_enabled(X86_FEATURE_ZEN2) || boot_cpu_data.x86 >= 0x19) + return amd_zen2_perfmon_event_map[hw_event]; + + if (cpu_feature_enabled(X86_FEATURE_ZEN1)) + return amd_zen1_perfmon_event_map[hw_event]; return amd_perfmon_event_map[hw_event]; } @@ -904,8 +933,8 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) if (!status) goto done; - /* Read branch records before unfreezing */ - if (status & GLOBAL_STATUS_LBRS_FROZEN) { + /* Read branch records */ + if (x86_pmu.lbr_nr) { amd_pmu_lbr_read(); status &= ~GLOBAL_STATUS_LBRS_FROZEN; } diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c index 4a1e600314d5..5149830c7c4f 100644 --- a/arch/x86/events/amd/lbr.c +++ b/arch/x86/events/amd/lbr.c @@ -402,10 +402,12 @@ void amd_pmu_lbr_enable_all(void) wrmsrl(MSR_AMD64_LBR_SELECT, lbr_select); } - rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); - rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); + if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) { + rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); + wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + } - wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg | DBG_EXTN_CFG_LBRV2EN); } @@ -418,10 +420,12 @@ void amd_pmu_lbr_disable_all(void) return; rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); - rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); - wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN); - wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + + if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) { + rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); + wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + } } __init int amd_pmu_lbr_init(void) diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 2641ba620f12..e010bfed8417 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1237,11 +1237,11 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu = event->pmu; /* - * Make sure we get updated with the first PEBS - * event. It will trigger also during removal, but - * that does not hurt: + * Make sure we get updated with the first PEBS event. + * During removal, ->pebs_data_cfg is still valid for + * the last PEBS event. Don't clear it. */ - if (cpuc->n_pebs == 1) + if ((cpuc->n_pebs == 1) && add) cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW; if (needed_cb != pebs_needs_sched_cb(cpuc)) { diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 8f3a4d16bb79..17a71e92a343 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -667,14 +667,14 @@ void hyperv_cleanup(void) hv_hypercall_pg = NULL; /* Reset the hypercall page */ - hypercall_msr.as_uint64 = hv_get_register(HV_X64_MSR_HYPERCALL); + hypercall_msr.as_uint64 = hv_get_msr(HV_X64_MSR_HYPERCALL); hypercall_msr.enable = 0; - hv_set_register(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + hv_set_msr(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); /* Reset the TSC page */ - tsc_msr.as_uint64 = hv_get_register(HV_X64_MSR_REFERENCE_TSC); + tsc_msr.as_uint64 = hv_get_msr(HV_X64_MSR_REFERENCE_TSC); tsc_msr.enable = 0; - hv_set_register(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64); + hv_set_msr(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die) diff --git a/arch/x86/hyperv/hv_spinlock.c b/arch/x86/hyperv/hv_spinlock.c index 737d6f7a6155..151e851bef09 100644 --- a/arch/x86/hyperv/hv_spinlock.c +++ b/arch/x86/hyperv/hv_spinlock.c @@ -16,7 +16,7 @@ #include <asm/paravirt.h> #include <asm/apic.h> -static bool __initdata hv_pvspin = true; +static bool hv_pvspin __initdata = true; static void hv_qlock_kick(int cpu) { @@ -64,6 +64,7 @@ __visible bool hv_vcpu_is_preempted(int vcpu) { return false; } + PV_CALLEE_SAVE_REGS_THUNK(hv_vcpu_is_preempted); void __init hv_init_spinlocks(void) diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index edd2f35b2a5e..5c7de79423b8 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -12,6 +12,7 @@ #include <asm/i8259.h> #include <asm/mshyperv.h> #include <asm/realmode.h> +#include <../kernel/smpboot.h> extern struct boot_params boot_params; static struct real_mode_header hv_vtl_real_mode_header; @@ -65,7 +66,7 @@ static void hv_vtl_ap_entry(void) ((secondary_startup_64_fn)secondary_startup_64)(&boot_params, &boot_params); } -static int hv_vtl_bringup_vcpu(u32 target_vp_index, u64 eip_ignored) +static int hv_vtl_bringup_vcpu(u32 target_vp_index, int cpu, u64 eip_ignored) { u64 status; int ret = 0; @@ -79,7 +80,9 @@ static int hv_vtl_bringup_vcpu(u32 target_vp_index, u64 eip_ignored) struct ldttss_desc *ldt; struct desc_struct *gdt; - u64 rsp = current->thread.sp; + struct task_struct *idle = idle_thread_get(cpu); + u64 rsp = (unsigned long)idle->thread.sp; + u64 rip = (u64)&hv_vtl_ap_entry; native_store_gdt(&gdt_ptr); @@ -206,7 +209,15 @@ static int hv_vtl_apicid_to_vp_id(u32 apic_id) static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) { - int vp_id; + int vp_id, cpu; + + /* Find the logical CPU for the APIC ID */ + for_each_present_cpu(cpu) { + if (arch_match_cpu_phys_id(cpu, apicid)) + break; + } + if (cpu >= nr_cpu_ids) + return -EINVAL; pr_debug("Bringing up CPU with APIC ID %d in VTL2...\n", apicid); vp_id = hv_vtl_apicid_to_vp_id(apicid); @@ -220,7 +231,7 @@ static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) return -EINVAL; } - return hv_vtl_bringup_vcpu(vp_id, start_eip); + return hv_vtl_bringup_vcpu(vp_id, cpu, start_eip); } int __init hv_vtl_early_init(void) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index fcd20c6dc7f9..67b68d0d17d1 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -117,7 +117,7 @@ extern void callthunks_patch_builtin_calls(void); extern void callthunks_patch_module_calls(struct callthunk_sites *sites, struct module *mod); extern void *callthunks_translate_call_dest(void *dest); -extern int x86_call_depth_emit_accounting(u8 **pprog, void *func); +extern int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip); #else static __always_inline void callthunks_patch_builtin_calls(void) {} static __always_inline void @@ -128,7 +128,7 @@ static __always_inline void *callthunks_translate_call_dest(void *dest) return dest; } static __always_inline int x86_call_depth_emit_accounting(u8 **pprog, - void *func) + void *func, void *ip) { return 0; } diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 076bf8dee702..25466c4d2134 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -14,6 +14,7 @@ #include <asm/asm.h> #include <asm/fred.h> #include <asm/gsseg.h> +#include <asm/nospec-branch.h> #ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h index fb7388bbc212..c086699b0d0c 100644 --- a/arch/x86/include/asm/coco.h +++ b/arch/x86/include/asm/coco.h @@ -22,6 +22,7 @@ static inline void cc_set_mask(u64 mask) u64 cc_mkenc(u64 val); u64 cc_mkdec(u64 val); +void cc_random_init(void); #else #define cc_vendor (CC_VENDOR_NONE) @@ -34,6 +35,7 @@ static inline u64 cc_mkdec(u64 val) { return val; } +static inline void cc_random_init(void) { } #endif #endif /* _ASM_X86_COCO_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index a1273698fc43..686e92d2663e 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -33,6 +33,8 @@ enum cpuid_leafs CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, + CPUID_LNX_5, + NR_CPUID_WORDS, }; #define X86_CAP_FMT_NUM "%d:%d" @@ -91,8 +93,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -116,8 +119,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index f0337f7bcf16..a38f8f9ba657 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 21 /* N 32-bit words worth of info */ +#define NCAPINTS 22 /* N 32-bit words worth of info */ #define NBUGINTS 2 /* N 32-bit bug flags */ /* @@ -460,6 +460,14 @@ #define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ /* + * Extended auxiliary flags: Linux defined - for features scattered in various + * CPUID levels like 0x80000022, etc. + * + * Reuse free bits when adding new feature flags! + */ +#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */ + +/* * BUG word(s) */ #define X86_BUG(x) (NCAPINTS*32 + (x)) diff --git a/arch/x86/include/asm/crash_reserve.h b/arch/x86/include/asm/crash_reserve.h index 152239f95541..7835b2cdff04 100644 --- a/arch/x86/include/asm/crash_reserve.h +++ b/arch/x86/include/asm/crash_reserve.h @@ -39,4 +39,6 @@ static inline unsigned long crash_low_size_default(void) #endif } +#define HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY + #endif /* _X86_CRASH_RESERVE_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index da4054fbf533..c492bdc97b05 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -155,6 +155,7 @@ #define DISABLED_MASK18 (DISABLE_IBT) #define DISABLED_MASK19 (DISABLE_SEV_SNP) #define DISABLED_MASK20 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define DISABLED_MASK21 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 2ff26f53cd62..3787d26810c1 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -182,7 +182,7 @@ enum hv_isolation_type { #define HV_X64_MSR_HYPERCALL 0x40000001 /* MSR used to provide vcpu index */ -#define HV_REGISTER_VP_INDEX 0x40000002 +#define HV_X64_MSR_VP_INDEX 0x40000002 /* MSR used to reset the guest OS. */ #define HV_X64_MSR_RESET 0x40000003 @@ -191,10 +191,10 @@ enum hv_isolation_type { #define HV_X64_MSR_VP_RUNTIME 0x40000010 /* MSR used to read the per-partition time reference counter */ -#define HV_REGISTER_TIME_REF_COUNT 0x40000020 +#define HV_X64_MSR_TIME_REF_COUNT 0x40000020 /* A partition's reference time stamp counter (TSC) page */ -#define HV_REGISTER_REFERENCE_TSC 0x40000021 +#define HV_X64_MSR_REFERENCE_TSC 0x40000021 /* MSR used to retrieve the TSC frequency */ #define HV_X64_MSR_TSC_FREQUENCY 0x40000022 @@ -209,61 +209,61 @@ enum hv_isolation_type { #define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073 /* Define synthetic interrupt controller model specific registers. */ -#define HV_REGISTER_SCONTROL 0x40000080 -#define HV_REGISTER_SVERSION 0x40000081 -#define HV_REGISTER_SIEFP 0x40000082 -#define HV_REGISTER_SIMP 0x40000083 -#define HV_REGISTER_EOM 0x40000084 -#define HV_REGISTER_SINT0 0x40000090 -#define HV_REGISTER_SINT1 0x40000091 -#define HV_REGISTER_SINT2 0x40000092 -#define HV_REGISTER_SINT3 0x40000093 -#define HV_REGISTER_SINT4 0x40000094 -#define HV_REGISTER_SINT5 0x40000095 -#define HV_REGISTER_SINT6 0x40000096 -#define HV_REGISTER_SINT7 0x40000097 -#define HV_REGISTER_SINT8 0x40000098 -#define HV_REGISTER_SINT9 0x40000099 -#define HV_REGISTER_SINT10 0x4000009A -#define HV_REGISTER_SINT11 0x4000009B -#define HV_REGISTER_SINT12 0x4000009C -#define HV_REGISTER_SINT13 0x4000009D -#define HV_REGISTER_SINT14 0x4000009E -#define HV_REGISTER_SINT15 0x4000009F +#define HV_X64_MSR_SCONTROL 0x40000080 +#define HV_X64_MSR_SVERSION 0x40000081 +#define HV_X64_MSR_SIEFP 0x40000082 +#define HV_X64_MSR_SIMP 0x40000083 +#define HV_X64_MSR_EOM 0x40000084 +#define HV_X64_MSR_SINT0 0x40000090 +#define HV_X64_MSR_SINT1 0x40000091 +#define HV_X64_MSR_SINT2 0x40000092 +#define HV_X64_MSR_SINT3 0x40000093 +#define HV_X64_MSR_SINT4 0x40000094 +#define HV_X64_MSR_SINT5 0x40000095 +#define HV_X64_MSR_SINT6 0x40000096 +#define HV_X64_MSR_SINT7 0x40000097 +#define HV_X64_MSR_SINT8 0x40000098 +#define HV_X64_MSR_SINT9 0x40000099 +#define HV_X64_MSR_SINT10 0x4000009A +#define HV_X64_MSR_SINT11 0x4000009B +#define HV_X64_MSR_SINT12 0x4000009C +#define HV_X64_MSR_SINT13 0x4000009D +#define HV_X64_MSR_SINT14 0x4000009E +#define HV_X64_MSR_SINT15 0x4000009F /* * Define synthetic interrupt controller model specific registers for * nested hypervisor. */ -#define HV_REGISTER_NESTED_SCONTROL 0x40001080 -#define HV_REGISTER_NESTED_SVERSION 0x40001081 -#define HV_REGISTER_NESTED_SIEFP 0x40001082 -#define HV_REGISTER_NESTED_SIMP 0x40001083 -#define HV_REGISTER_NESTED_EOM 0x40001084 -#define HV_REGISTER_NESTED_SINT0 0x40001090 +#define HV_X64_MSR_NESTED_SCONTROL 0x40001080 +#define HV_X64_MSR_NESTED_SVERSION 0x40001081 +#define HV_X64_MSR_NESTED_SIEFP 0x40001082 +#define HV_X64_MSR_NESTED_SIMP 0x40001083 +#define HV_X64_MSR_NESTED_EOM 0x40001084 +#define HV_X64_MSR_NESTED_SINT0 0x40001090 /* * Synthetic Timer MSRs. Four timers per vcpu. */ -#define HV_REGISTER_STIMER0_CONFIG 0x400000B0 -#define HV_REGISTER_STIMER0_COUNT 0x400000B1 -#define HV_REGISTER_STIMER1_CONFIG 0x400000B2 -#define HV_REGISTER_STIMER1_COUNT 0x400000B3 -#define HV_REGISTER_STIMER2_CONFIG 0x400000B4 -#define HV_REGISTER_STIMER2_COUNT 0x400000B5 -#define HV_REGISTER_STIMER3_CONFIG 0x400000B6 -#define HV_REGISTER_STIMER3_COUNT 0x400000B7 +#define HV_X64_MSR_STIMER0_CONFIG 0x400000B0 +#define HV_X64_MSR_STIMER0_COUNT 0x400000B1 +#define HV_X64_MSR_STIMER1_CONFIG 0x400000B2 +#define HV_X64_MSR_STIMER1_COUNT 0x400000B3 +#define HV_X64_MSR_STIMER2_CONFIG 0x400000B4 +#define HV_X64_MSR_STIMER2_COUNT 0x400000B5 +#define HV_X64_MSR_STIMER3_CONFIG 0x400000B6 +#define HV_X64_MSR_STIMER3_COUNT 0x400000B7 /* Hyper-V guest idle MSR */ #define HV_X64_MSR_GUEST_IDLE 0x400000F0 /* Hyper-V guest crash notification MSR's */ -#define HV_REGISTER_CRASH_P0 0x40000100 -#define HV_REGISTER_CRASH_P1 0x40000101 -#define HV_REGISTER_CRASH_P2 0x40000102 -#define HV_REGISTER_CRASH_P3 0x40000103 -#define HV_REGISTER_CRASH_P4 0x40000104 -#define HV_REGISTER_CRASH_CTL 0x40000105 +#define HV_X64_MSR_CRASH_P0 0x40000100 +#define HV_X64_MSR_CRASH_P1 0x40000101 +#define HV_X64_MSR_CRASH_P2 0x40000102 +#define HV_X64_MSR_CRASH_P3 0x40000103 +#define HV_X64_MSR_CRASH_P4 0x40000104 +#define HV_X64_MSR_CRASH_CTL 0x40000105 /* TSC emulation after migration */ #define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 @@ -276,31 +276,38 @@ enum hv_isolation_type { /* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ #define HV_EXPOSE_INVARIANT_TSC BIT_ULL(0) -/* Register name aliases for temporary compatibility */ -#define HV_X64_MSR_STIMER0_COUNT HV_REGISTER_STIMER0_COUNT -#define HV_X64_MSR_STIMER0_CONFIG HV_REGISTER_STIMER0_CONFIG -#define HV_X64_MSR_STIMER1_COUNT HV_REGISTER_STIMER1_COUNT -#define HV_X64_MSR_STIMER1_CONFIG HV_REGISTER_STIMER1_CONFIG -#define HV_X64_MSR_STIMER2_COUNT HV_REGISTER_STIMER2_COUNT -#define HV_X64_MSR_STIMER2_CONFIG HV_REGISTER_STIMER2_CONFIG -#define HV_X64_MSR_STIMER3_COUNT HV_REGISTER_STIMER3_COUNT -#define HV_X64_MSR_STIMER3_CONFIG HV_REGISTER_STIMER3_CONFIG -#define HV_X64_MSR_SCONTROL HV_REGISTER_SCONTROL -#define HV_X64_MSR_SVERSION HV_REGISTER_SVERSION -#define HV_X64_MSR_SIMP HV_REGISTER_SIMP -#define HV_X64_MSR_SIEFP HV_REGISTER_SIEFP -#define HV_X64_MSR_VP_INDEX HV_REGISTER_VP_INDEX -#define HV_X64_MSR_EOM HV_REGISTER_EOM -#define HV_X64_MSR_SINT0 HV_REGISTER_SINT0 -#define HV_X64_MSR_SINT15 HV_REGISTER_SINT15 -#define HV_X64_MSR_CRASH_P0 HV_REGISTER_CRASH_P0 -#define HV_X64_MSR_CRASH_P1 HV_REGISTER_CRASH_P1 -#define HV_X64_MSR_CRASH_P2 HV_REGISTER_CRASH_P2 -#define HV_X64_MSR_CRASH_P3 HV_REGISTER_CRASH_P3 -#define HV_X64_MSR_CRASH_P4 HV_REGISTER_CRASH_P4 -#define HV_X64_MSR_CRASH_CTL HV_REGISTER_CRASH_CTL -#define HV_X64_MSR_TIME_REF_COUNT HV_REGISTER_TIME_REF_COUNT -#define HV_X64_MSR_REFERENCE_TSC HV_REGISTER_REFERENCE_TSC +/* + * To support arch-generic code calling hv_set/get_register: + * - On x86, HV_MSR_ indicates an MSR accessed via rdmsrl/wrmsrl + * - On ARM, HV_MSR_ indicates a VP register accessed via hypercall + */ +#define HV_MSR_CRASH_P0 (HV_X64_MSR_CRASH_P0) +#define HV_MSR_CRASH_P1 (HV_X64_MSR_CRASH_P1) +#define HV_MSR_CRASH_P2 (HV_X64_MSR_CRASH_P2) +#define HV_MSR_CRASH_P3 (HV_X64_MSR_CRASH_P3) +#define HV_MSR_CRASH_P4 (HV_X64_MSR_CRASH_P4) +#define HV_MSR_CRASH_CTL (HV_X64_MSR_CRASH_CTL) + +#define HV_MSR_VP_INDEX (HV_X64_MSR_VP_INDEX) +#define HV_MSR_TIME_REF_COUNT (HV_X64_MSR_TIME_REF_COUNT) +#define HV_MSR_REFERENCE_TSC (HV_X64_MSR_REFERENCE_TSC) + +#define HV_MSR_SINT0 (HV_X64_MSR_SINT0) +#define HV_MSR_SVERSION (HV_X64_MSR_SVERSION) +#define HV_MSR_SCONTROL (HV_X64_MSR_SCONTROL) +#define HV_MSR_SIEFP (HV_X64_MSR_SIEFP) +#define HV_MSR_SIMP (HV_X64_MSR_SIMP) +#define HV_MSR_EOM (HV_X64_MSR_EOM) + +#define HV_MSR_NESTED_SCONTROL (HV_X64_MSR_NESTED_SCONTROL) +#define HV_MSR_NESTED_SVERSION (HV_X64_MSR_NESTED_SVERSION) +#define HV_MSR_NESTED_SIEFP (HV_X64_MSR_NESTED_SIEFP) +#define HV_MSR_NESTED_SIMP (HV_X64_MSR_NESTED_SIMP) +#define HV_MSR_NESTED_EOM (HV_X64_MSR_NESTED_EOM) +#define HV_MSR_NESTED_SINT0 (HV_X64_MSR_NESTED_SINT0) + +#define HV_MSR_STIMER0_CONFIG (HV_X64_MSR_STIMER0_CONFIG) +#define HV_MSR_STIMER0_COUNT (HV_X64_MSR_STIMER0_COUNT) /* * Registers are only accessible via HVCALL_GET_VP_REGISTERS hvcall and diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index b65e9c46b922..d0941f4c2724 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -127,6 +127,7 @@ #define INTEL_FAM6_ARROWLAKE_H 0xC5 #define INTEL_FAM6_ARROWLAKE 0xC6 +#define INTEL_FAM6_ARROWLAKE_U 0xB5 #define INTEL_FAM6_LUNARLAKE_M 0xBD diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index ce4ce8720d55..390c4d13956d 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -293,24 +293,24 @@ static inline void hv_ivm_msr_write(u64 msr, u64 value) {} static inline void hv_ivm_msr_read(u64 msr, u64 *value) {} #endif -static inline bool hv_is_synic_reg(unsigned int reg) +static inline bool hv_is_synic_msr(unsigned int reg) { - return (reg >= HV_REGISTER_SCONTROL) && - (reg <= HV_REGISTER_SINT15); + return (reg >= HV_X64_MSR_SCONTROL) && + (reg <= HV_X64_MSR_SINT15); } -static inline bool hv_is_sint_reg(unsigned int reg) +static inline bool hv_is_sint_msr(unsigned int reg) { - return (reg >= HV_REGISTER_SINT0) && - (reg <= HV_REGISTER_SINT15); + return (reg >= HV_X64_MSR_SINT0) && + (reg <= HV_X64_MSR_SINT15); } -u64 hv_get_register(unsigned int reg); -void hv_set_register(unsigned int reg, u64 value); -u64 hv_get_non_nested_register(unsigned int reg); -void hv_set_non_nested_register(unsigned int reg, u64 value); +u64 hv_get_msr(unsigned int reg); +void hv_set_msr(unsigned int reg, u64 value); +u64 hv_get_non_nested_msr(unsigned int reg); +void hv_set_non_nested_msr(unsigned int reg, u64 value); -static __always_inline u64 hv_raw_get_register(unsigned int reg) +static __always_inline u64 hv_raw_get_msr(unsigned int reg) { return __rdmsr(reg); } @@ -331,10 +331,10 @@ static inline int hyperv_flush_guest_mapping_range(u64 as, { return -1; } -static inline void hv_set_register(unsigned int reg, u64 value) { } -static inline u64 hv_get_register(unsigned int reg) { return 0; } -static inline void hv_set_non_nested_register(unsigned int reg, u64 value) { } -static inline u64 hv_get_non_nested_register(unsigned int reg) { return 0; } +static inline void hv_set_msr(unsigned int reg, u64 value) { } +static inline u64 hv_get_msr(unsigned int reg) { return 0; } +static inline void hv_set_non_nested_msr(unsigned int reg, u64 value) { } +static inline u64 hv_get_non_nested_msr(unsigned int reg) { return 0; } #endif /* CONFIG_HYPERV */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index fc3a8a3c7ffe..170c89ed22fc 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -262,11 +262,20 @@ .Lskip_rsb_\@: .endm +/* + * The CALL to srso_alias_untrain_ret() must be patched in directly at + * the spot where untraining must be done, ie., srso_alias_untrain_ret() + * must be the target of a CALL instruction instead of indirectly + * jumping to a wrapper which then calls it. Therefore, this macro is + * called outside of __UNTRAIN_RET below, for the time being, before the + * kernel can support nested alternatives with arbitrary nesting. + */ +.macro CALL_UNTRAIN_RET #if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO) -#define CALL_UNTRAIN_RET "call entry_untrain_ret" -#else -#define CALL_UNTRAIN_RET "" + ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \ + "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS #endif +.endm /* * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the @@ -282,8 +291,8 @@ .macro __UNTRAIN_RET ibpb_feature, call_depth_insns #if defined(CONFIG_MITIGATION_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY) VALIDATE_UNRET_END - ALTERNATIVE_3 "", \ - CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ + CALL_UNTRAIN_RET + ALTERNATIVE_2 "", \ "call entry_ibpb", \ibpb_feature, \ __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH #endif @@ -342,6 +351,8 @@ extern void retbleed_return_thunk(void); static inline void retbleed_return_thunk(void) {} #endif +extern void srso_alias_untrain_ret(void); + #ifdef CONFIG_MITIGATION_SRSO extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 7ba1726b71c7..e9187ddd3d1f 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -99,6 +99,7 @@ #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 #define REQUIRED_MASK20 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define REQUIRED_MASK21 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 9477b4053bce..7f57382afee4 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -218,17 +218,16 @@ void early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages); void early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned long npages); -void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op); void snp_set_memory_shared(unsigned long vaddr, unsigned long npages); void snp_set_memory_private(unsigned long vaddr, unsigned long npages); void snp_set_wakeup_secondary_cpu(void); bool snp_init(struct boot_params *bp); void __noreturn snp_abort(void); +void snp_dmi_setup(void); int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio); void snp_accept_memory(phys_addr_t start, phys_addr_t end); u64 snp_get_unsupported_features(u64 status); u64 sev_get_status(void); -void kdump_sev_callback(void); void sev_show_status(void); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } @@ -244,12 +243,12 @@ static inline void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { } static inline void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned long npages) { } -static inline void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) { } static inline void snp_set_memory_shared(unsigned long vaddr, unsigned long npages) { } static inline void snp_set_memory_private(unsigned long vaddr, unsigned long npages) { } static inline void snp_set_wakeup_secondary_cpu(void) { } static inline bool snp_init(struct boot_params *bp) { return false; } static inline void snp_abort(void) { } +static inline void snp_dmi_setup(void) { } static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio) { return -ENOTTY; @@ -258,7 +257,6 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { } static inline u64 snp_get_unsupported_features(u64 status) { return 0; } static inline u64 sev_get_status(void) { return 0; } -static inline void kdump_sev_callback(void) { } static inline void sev_show_status(void) { } #endif @@ -270,6 +268,7 @@ int psmash(u64 pfn); int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable); int rmp_make_shared(u64 pfn, enum pg_level level); void snp_leak_pages(u64 pfn, unsigned int npages); +void kdump_sev_callback(void); #else static inline bool snp_probe_rmptable_info(void) { return false; } static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; } @@ -282,6 +281,7 @@ static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 as } static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; } static inline void snp_leak_pages(u64 pfn, unsigned int npages) {} +static inline void kdump_sev_callback(void) { } #endif #endif diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index a800abb1a992..d8416b3bf832 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -12,11 +12,6 @@ /* image of the saved processor state */ struct saved_context { - /* - * On x86_32, all segment registers except gs are saved at kernel - * entry in pt_regs. - */ - u16 gs; unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; struct saved_msrs saved_msrs; @@ -27,6 +22,11 @@ struct saved_context { unsigned long tr; unsigned long safety; unsigned long return_address; + /* + * On x86_32, all segment registers except gs are saved at kernel + * entry in pt_regs. + */ + u16 gs; bool misc_enable_saved; } __attribute__((packed)); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index b89b40f250e6..6149eabe200f 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -30,12 +30,13 @@ struct x86_init_mpparse { * @reserve_resources: reserve the standard resources for the * platform * @memory_setup: platform specific memory setup - * + * @dmi_setup: platform specific DMI setup */ struct x86_init_resources { void (*probe_roms)(void); void (*reserve_resources)(void); char *(*memory_setup)(void); + void (*dmi_setup)(void); }; /** diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index a9088250770f..64fbd2dbc5b7 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -62,6 +62,11 @@ void xen_arch_unregister_cpu(int num); #ifdef CONFIG_PVH void __init xen_pvh_init(struct boot_params *boot_params); void __init mem_map_via_hcall(struct boot_params *boot_params_p); +#ifdef CONFIG_XEN_PVH +void __init xen_reserve_extra_memory(struct boot_params *bootp); +#else +static inline void xen_reserve_extra_memory(struct boot_params *bootp) { } +#endif #endif /* Lazy mode for batching updates / context switch */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index ad29984d5e39..ef11aa4cab42 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -694,6 +694,7 @@ enum sev_cmd_id { struct kvm_sev_cmd { __u32 id; + __u32 pad0; __u64 data; __u32 error; __u32 sev_fd; @@ -704,28 +705,35 @@ struct kvm_sev_launch_start { __u32 policy; __u64 dh_uaddr; __u32 dh_len; + __u32 pad0; __u64 session_uaddr; __u32 session_len; + __u32 pad1; }; struct kvm_sev_launch_update_data { __u64 uaddr; __u32 len; + __u32 pad0; }; struct kvm_sev_launch_secret { __u64 hdr_uaddr; __u32 hdr_len; + __u32 pad0; __u64 guest_uaddr; __u32 guest_len; + __u32 pad1; __u64 trans_uaddr; __u32 trans_len; + __u32 pad2; }; struct kvm_sev_launch_measure { __u64 uaddr; __u32 len; + __u32 pad0; }; struct kvm_sev_guest_status { @@ -738,33 +746,43 @@ struct kvm_sev_dbg { __u64 src_uaddr; __u64 dst_uaddr; __u32 len; + __u32 pad0; }; struct kvm_sev_attestation_report { __u8 mnonce[16]; __u64 uaddr; __u32 len; + __u32 pad0; }; struct kvm_sev_send_start { __u32 policy; + __u32 pad0; __u64 pdh_cert_uaddr; __u32 pdh_cert_len; + __u32 pad1; __u64 plat_certs_uaddr; __u32 plat_certs_len; + __u32 pad2; __u64 amd_certs_uaddr; __u32 amd_certs_len; + __u32 pad3; __u64 session_uaddr; __u32 session_len; + __u32 pad4; }; struct kvm_sev_send_update_data { __u64 hdr_uaddr; __u32 hdr_len; + __u32 pad0; __u64 guest_uaddr; __u32 guest_len; + __u32 pad1; __u64 trans_uaddr; __u32 trans_len; + __u32 pad2; }; struct kvm_sev_receive_start { @@ -772,17 +790,22 @@ struct kvm_sev_receive_start { __u32 policy; __u64 pdh_uaddr; __u32 pdh_len; + __u32 pad0; __u64 session_uaddr; __u32 session_len; + __u32 pad1; }; struct kvm_sev_receive_update_data { __u64 hdr_uaddr; __u32 hdr_len; + __u32 pad0; __u64 guest_uaddr; __u32 guest_len; + __u32 pad1; __u64 trans_uaddr; __u32 trans_len; + __u32 pad2; }; #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 6bc3456a8ebf..a1efa7907a0b 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -142,7 +142,6 @@ struct kvm_vcpu_pv_apf_data { __u32 token; __u8 pad[56]; - __u32 enabled; }; #define KVM_PV_EOI_BIT 0 diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 30335182b6b0..e92ff0c11db8 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -314,7 +314,7 @@ static bool is_callthunk(void *addr) return !bcmp(pad, insn_buff, tmpl_size); } -int x86_call_depth_emit_accounting(u8 **pprog, void *func) +int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip) { unsigned int tmpl_size = SKL_TMPL_SIZE; u8 insn_buff[MAX_PATCH_LEN]; @@ -327,7 +327,7 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func) return 0; memcpy(insn_buff, skl_call_thunk_template, tmpl_size); - apply_relocation(insn_buff, tmpl_size, *pprog, + apply_relocation(insn_buff, tmpl_size, ip, skl_call_thunk_template, tmpl_size); memcpy(*pprog, insn_buff, tmpl_size); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 873f0fdc2ef8..db9745e25816 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -346,6 +346,28 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } +static void bsp_determine_snp(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_ARCH_HAS_CC_PLATFORM + cc_vendor = CC_VENDOR_AMD; + + if (cpu_has(c, X86_FEATURE_SEV_SNP)) { + /* + * RMP table entry format is not architectural and is defined by the + * per-processor PPR. Restrict SNP support on the known CPU models + * for which the RMP table entry format is currently defined for. + */ + if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && + c->x86 >= 0x19 && snp_probe_rmptable_info()) { + cc_platform_set(CC_ATTR_HOST_SEV_SNP); + } else { + setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); + } + } +#endif +} + static void bsp_init_amd(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { @@ -453,21 +475,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) break; } - if (cpu_has(c, X86_FEATURE_SEV_SNP)) { - /* - * RMP table entry format is not architectural and it can vary by processor - * and is defined by the per-processor PPR. Restrict SNP support on the - * known CPU model and family for which the RMP table entry format is - * currently defined for. - */ - if (!boot_cpu_has(X86_FEATURE_ZEN3) && - !boot_cpu_has(X86_FEATURE_ZEN4) && - !boot_cpu_has(X86_FEATURE_ZEN5)) - setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); - else if (!snp_probe_rmptable_info()) - setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); - } - + bsp_determine_snp(c); return; warn: diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9a34651d24e7..07f1ac7f0f4a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2304,6 +2304,8 @@ void arch_smt_update(void) void __init arch_cpu_finalize_init(void) { + struct cpuinfo_x86 *c = this_cpu_ptr(&cpu_info); + identify_boot_cpu(); select_idle_routine(); @@ -2342,6 +2344,13 @@ void __init arch_cpu_finalize_init(void) fpu__init_system(); fpu__init_cpu(); + /* + * Ensure that access to the per CPU representation has the initial + * boot CPU configuration. + */ + *c = boot_cpu_data; + c->initialized = true; + alternative_instructions(); if (IS_ENABLED(CONFIG_X86_64)) { diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index b5cc557cfc37..84d41be6d06b 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -2500,12 +2500,14 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr, return -EINVAL; b = &per_cpu(mce_banks_array, s->id)[bank]; - if (!b->init) return -ENODEV; b->ctl = new; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); return size; } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 303fef824167..e0fd57a8ba84 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -45,70 +45,70 @@ bool hyperv_paravisor_present __ro_after_init; EXPORT_SYMBOL_GPL(hyperv_paravisor_present); #if IS_ENABLED(CONFIG_HYPERV) -static inline unsigned int hv_get_nested_reg(unsigned int reg) +static inline unsigned int hv_get_nested_msr(unsigned int reg) { - if (hv_is_sint_reg(reg)) - return reg - HV_REGISTER_SINT0 + HV_REGISTER_NESTED_SINT0; + if (hv_is_sint_msr(reg)) + return reg - HV_X64_MSR_SINT0 + HV_X64_MSR_NESTED_SINT0; switch (reg) { - case HV_REGISTER_SIMP: - return HV_REGISTER_NESTED_SIMP; - case HV_REGISTER_SIEFP: - return HV_REGISTER_NESTED_SIEFP; - case HV_REGISTER_SVERSION: - return HV_REGISTER_NESTED_SVERSION; - case HV_REGISTER_SCONTROL: - return HV_REGISTER_NESTED_SCONTROL; - case HV_REGISTER_EOM: - return HV_REGISTER_NESTED_EOM; + case HV_X64_MSR_SIMP: + return HV_X64_MSR_NESTED_SIMP; + case HV_X64_MSR_SIEFP: + return HV_X64_MSR_NESTED_SIEFP; + case HV_X64_MSR_SVERSION: + return HV_X64_MSR_NESTED_SVERSION; + case HV_X64_MSR_SCONTROL: + return HV_X64_MSR_NESTED_SCONTROL; + case HV_X64_MSR_EOM: + return HV_X64_MSR_NESTED_EOM; default: return reg; } } -u64 hv_get_non_nested_register(unsigned int reg) +u64 hv_get_non_nested_msr(unsigned int reg) { u64 value; - if (hv_is_synic_reg(reg) && ms_hyperv.paravisor_present) + if (hv_is_synic_msr(reg) && ms_hyperv.paravisor_present) hv_ivm_msr_read(reg, &value); else rdmsrl(reg, value); return value; } -EXPORT_SYMBOL_GPL(hv_get_non_nested_register); +EXPORT_SYMBOL_GPL(hv_get_non_nested_msr); -void hv_set_non_nested_register(unsigned int reg, u64 value) +void hv_set_non_nested_msr(unsigned int reg, u64 value) { - if (hv_is_synic_reg(reg) && ms_hyperv.paravisor_present) { + if (hv_is_synic_msr(reg) && ms_hyperv.paravisor_present) { hv_ivm_msr_write(reg, value); /* Write proxy bit via wrmsl instruction */ - if (hv_is_sint_reg(reg)) + if (hv_is_sint_msr(reg)) wrmsrl(reg, value | 1 << 20); } else { wrmsrl(reg, value); } } -EXPORT_SYMBOL_GPL(hv_set_non_nested_register); +EXPORT_SYMBOL_GPL(hv_set_non_nested_msr); -u64 hv_get_register(unsigned int reg) +u64 hv_get_msr(unsigned int reg) { if (hv_nested) - reg = hv_get_nested_reg(reg); + reg = hv_get_nested_msr(reg); - return hv_get_non_nested_register(reg); + return hv_get_non_nested_msr(reg); } -EXPORT_SYMBOL_GPL(hv_get_register); +EXPORT_SYMBOL_GPL(hv_get_msr); -void hv_set_register(unsigned int reg, u64 value) +void hv_set_msr(unsigned int reg, u64 value) { if (hv_nested) - reg = hv_get_nested_reg(reg); + reg = hv_get_nested_msr(reg); - hv_set_non_nested_register(reg, value); + hv_set_non_nested_msr(reg, value); } -EXPORT_SYMBOL_GPL(hv_set_register); +EXPORT_SYMBOL_GPL(hv_set_msr); static void (*vmbus_handler)(void); static void (*hv_stimer0_handler)(void); @@ -352,13 +352,24 @@ static void __init reduced_hw_init(void) x86_init.irqs.pre_vector_init = x86_init_noop; } +int hv_get_hypervisor_version(union hv_hypervisor_version_info *info) +{ + unsigned int hv_max_functions; + + hv_max_functions = cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS); + if (hv_max_functions < HYPERV_CPUID_VERSION) { + pr_err("%s: Could not detect Hyper-V version\n", __func__); + return -ENODEV; + } + + cpuid(HYPERV_CPUID_VERSION, &info->eax, &info->ebx, &info->ecx, &info->edx); + + return 0; +} + static void __init ms_hyperv_init_platform(void) { int hv_max_functions_eax; - int hv_host_info_eax; - int hv_host_info_ebx; - int hv_host_info_ecx; - int hv_host_info_edx; #ifdef CONFIG_PARAVIRT pv_info.name = "Hyper-V"; @@ -409,21 +420,6 @@ static void __init ms_hyperv_init_platform(void) pr_info("Hyper-V: running on a nested hypervisor\n"); } - /* - * Extract host information. - */ - if (hv_max_functions_eax >= HYPERV_CPUID_VERSION) { - hv_host_info_eax = cpuid_eax(HYPERV_CPUID_VERSION); - hv_host_info_ebx = cpuid_ebx(HYPERV_CPUID_VERSION); - hv_host_info_ecx = cpuid_ecx(HYPERV_CPUID_VERSION); - hv_host_info_edx = cpuid_edx(HYPERV_CPUID_VERSION); - - pr_info("Hyper-V: Host Build %d.%d.%d.%d-%d-%d\n", - hv_host_info_ebx >> 16, hv_host_info_ebx & 0xFFFF, - hv_host_info_eax, hv_host_info_edx & 0xFFFFFF, - hv_host_info_ecx, hv_host_info_edx >> 24); - } - if (ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { x86_platform.calibrate_tsc = hv_get_tsc_khz; @@ -456,7 +452,7 @@ static void __init ms_hyperv_init_platform(void) /* To be supported: more work is required. */ ms_hyperv.features &= ~HV_MSR_REFERENCE_TSC_AVAILABLE; - /* HV_REGISTER_CRASH_CTL is unsupported. */ + /* HV_MSR_CRASH_CTL is unsupported. */ ms_hyperv.misc_features &= ~HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; /* Don't trust Hyper-V's TLB-flushing hypercalls. */ @@ -648,6 +644,7 @@ const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = { .init.x2apic_available = ms_hyperv_x2apic_available, .init.msi_ext_dest_id = ms_hyperv_msi_ext_dest_id, .init.init_platform = ms_hyperv_init_platform, + .init.guest_late_init = ms_hyperv_late_init, #ifdef CONFIG_AMD_MEM_ENCRYPT .runtime.sev_es_hcall_prepare = hv_sev_es_hcall_prepare, .runtime.sev_es_hcall_finish = hv_sev_es_hcall_finish, diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 422a4ddc2ab7..7b29ebda024f 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -108,7 +108,7 @@ static inline void k8_check_syscfg_dram_mod_en(void) (boot_cpu_data.x86 >= 0x0f))) return; - if (cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return; rdmsr(MSR_AMD64_SYSCFG, lo, hi); diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index c99f26ebe7a6..1a8687f8073a 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -78,7 +78,8 @@ cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu) else cpu = cpumask_any_but(mask, exclude_cpu); - if (!IS_ENABLED(CONFIG_NO_HZ_FULL)) + /* Only continue if tick_nohz_full_mask has been initialized. */ + if (!tick_nohz_full_enabled()) return cpu; /* If the CPU picked isn't marked nohz_full nothing more needs doing. */ diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 0dad49a09b7a..a515328d9d7d 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -49,6 +49,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 }, { X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 }, { X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 }, + { X86_FEATURE_AMD_LBR_PMC_FREEZE, CPUID_EAX, 2, 0x80000022, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 3259b1d4fefe..aaca8d235dc2 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -415,6 +415,17 @@ void __init topology_init_possible_cpus(void) unsigned int total = assigned + disabled; u32 apicid, firstid; + /* + * If there was no APIC registered, then fake one so that the + * topology bitmap is populated. That ensures that the code below + * is valid and the various query interfaces can be used + * unconditionally. This does not affect the actual APIC code in + * any way because either the local APIC address has not been + * registered or the local APIC was disabled on the command line. + */ + if (topo_info.boot_cpu_apic_id == BAD_APICID) + topology_register_boot_apic(0); + if (!restrict_to_up()) { if (WARN_ON_ONCE(assigned > nr_cpu_ids)) { disabled += assigned - nr_cpu_ids; diff --git a/arch/x86/kernel/cpu/topology_common.c b/arch/x86/kernel/cpu/topology_common.c index a50ae8d63d1c..9a6069e7133c 100644 --- a/arch/x86/kernel/cpu/topology_common.c +++ b/arch/x86/kernel/cpu/topology_common.c @@ -140,7 +140,7 @@ static void parse_topology(struct topo_scan *tscan, bool early) } } -static void topo_set_ids(struct topo_scan *tscan) +static void topo_set_ids(struct topo_scan *tscan, bool early) { struct cpuinfo_x86 *c = tscan->c; u32 apicid = c->topo.apicid; @@ -148,8 +148,10 @@ static void topo_set_ids(struct topo_scan *tscan) c->topo.pkg_id = topo_shift_apicid(apicid, TOPO_PKG_DOMAIN); c->topo.die_id = topo_shift_apicid(apicid, TOPO_DIE_DOMAIN); - c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN); - c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN); + if (!early) { + c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN); + c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN); + } /* Package relative core ID */ c->topo.core_id = (apicid & topo_domain_mask(TOPO_PKG_DOMAIN)) >> @@ -187,7 +189,7 @@ void cpu_parse_topology(struct cpuinfo_x86 *c) tscan.dom_shifts[dom], x86_topo_system.dom_shifts[dom]); } - topo_set_ids(&tscan); + topo_set_ids(&tscan, false); } void __init cpu_init_topology(struct cpuinfo_x86 *c) @@ -208,7 +210,7 @@ void __init cpu_init_topology(struct cpuinfo_x86 *c) x86_topo_system.dom_size[dom] = 1U << sft; } - topo_set_ids(&tscan); + topo_set_ids(&tscan, true); /* * AMD systems have Nodes per package which cannot be mapped to diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index b66f540de054..6f1b379e3b38 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1016,17 +1016,6 @@ void __init e820__reserve_setup_data(void) e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - /* - * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by - * kexec and do not need to be reserved. - */ - if (data->type != SETUP_EFI && - data->type != SETUP_IMA && - data->type != SETUP_RNG_SEED) - e820__range_update_kexec(pa_data, - sizeof(*data) + data->len, - E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - if (data->type == SETUP_INDIRECT) { len += data->len; early_memunmap(data, sizeof(*data)); @@ -1038,12 +1027,9 @@ void __init e820__reserve_setup_data(void) indirect = (struct setup_indirect *)data->data; - if (indirect->type != SETUP_INDIRECT) { + if (indirect->type != SETUP_INDIRECT) e820__range_update(indirect->addr, indirect->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - e820__range_update_kexec(indirect->addr, indirect->len, - E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - } } pa_data = pa_next; @@ -1051,7 +1037,6 @@ void __init e820__reserve_setup_data(void) } e820__update_table(e820_table); - e820__update_table(e820_table_kexec); pr_info("extended physical RAM map:\n"); e820__print_table("reserve setup_data"); diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c index e963344b0449..53935b4d62e3 100644 --- a/arch/x86/kernel/eisa.c +++ b/arch/x86/kernel/eisa.c @@ -2,6 +2,7 @@ /* * EISA specific code */ +#include <linux/cc_platform.h> #include <linux/ioport.h> #include <linux/eisa.h> #include <linux/io.h> @@ -12,7 +13,7 @@ static __init int eisa_bus_probe(void) { void __iomem *p; - if (xen_pv_domain() && !xen_initial_domain()) + if ((xen_pv_domain() && !xen_initial_domain()) || cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) return 0; p = ioremap(0x0FFFD9, 4); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 117e74c44e75..33a214b1a4ce 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -178,10 +178,11 @@ void fpu__init_cpu_xstate(void) * Must happen after CR4 setup and before xsetbv() to allow KVM * lazy passthrough. Write independent of the dynamic state static * key as that does not work on the boot CPU. This also ensures - * that any stale state is wiped out from XFD. + * that any stale state is wiped out from XFD. Reset the per CPU + * xfd cache too. */ if (cpu_feature_enabled(X86_FEATURE_XFD)) - wrmsrl(MSR_IA32_XFD, init_fpstate.xfd); + xfd_set_state(init_fpstate.xfd); /* * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index 3518fb26d06b..19ca623ffa2a 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -148,20 +148,26 @@ static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rs #endif #ifdef CONFIG_X86_64 +static inline void xfd_set_state(u64 xfd) +{ + wrmsrl(MSR_IA32_XFD, xfd); + __this_cpu_write(xfd_state, xfd); +} + static inline void xfd_update_state(struct fpstate *fpstate) { if (fpu_state_size_dynamic()) { u64 xfd = fpstate->xfd; - if (__this_cpu_read(xfd_state) != xfd) { - wrmsrl(MSR_IA32_XFD, xfd); - __this_cpu_write(xfd_state, xfd); - } + if (__this_cpu_read(xfd_state) != xfd) + xfd_set_state(xfd); } } extern int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu); #else +static inline void xfd_set_state(u64 xfd) { } + static inline void xfd_update_state(struct fpstate *fpstate) { } static inline int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu) { diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 212e8e06aeba..a817ed0724d1 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -81,6 +81,13 @@ static inline bool check_la57_support(void) if (!(native_read_cr4() & X86_CR4_LA57)) return false; + RIP_REL_REF(__pgtable_l5_enabled) = 1; + RIP_REL_REF(pgdir_shift) = 48; + RIP_REL_REF(ptrs_per_p4d) = 512; + RIP_REL_REF(page_offset_base) = __PAGE_OFFSET_BASE_L5; + RIP_REL_REF(vmalloc_base) = __VMALLOC_BASE_L5; + RIP_REL_REF(vmemmap_base) = __VMEMMAP_BASE_L5; + return true; } @@ -175,7 +182,7 @@ unsigned long __head __startup_64(unsigned long physaddr, p4d = (p4dval_t *)&RIP_REL_REF(level4_kernel_pgt); p4d[MAX_PTRS_PER_P4D - 1] += load_delta; - pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE_NOENC; + pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE; } RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 2].pud += load_delta; @@ -431,15 +438,6 @@ asmlinkage __visible void __init __noreturn x86_64_start_kernel(char * real_mode (__START_KERNEL & PGDIR_MASK))); BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END); - if (check_la57_support()) { - __pgtable_l5_enabled = 1; - pgdir_shift = 48; - ptrs_per_p4d = 512; - page_offset_base = __PAGE_OFFSET_BASE_L5; - vmalloc_base = __VMALLOC_BASE_L5; - vmemmap_base = __VMEMMAP_BASE_L5; - } - cr4_init_shadow(); /* Kill off the identity-map trampoline */ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 091b3ab76a18..d0e49bd7c6f3 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -373,7 +373,16 @@ out: kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset, bool *on_func_entry) { - if (is_endbr(*(u32 *)addr)) { + u32 insn; + + /* + * Since 'addr' is not guaranteed to be safe to access, use + * copy_from_kernel_nofault() to read the instruction: + */ + if (copy_from_kernel_nofault(&insn, (void *)addr, sizeof(u32))) + return NULL; + + if (is_endbr(insn)) { *on_func_entry = !offset || offset == 4; if (*on_func_entry) offset = 4; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 4cadfd606e8e..7f0732bc0ccd 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -65,6 +65,7 @@ static int __init parse_no_stealacc(char *arg) early_param("no-steal-acc", parse_no_stealacc); +static DEFINE_PER_CPU_READ_MOSTLY(bool, async_pf_enabled); static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64); DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible; static int has_steal_clock = 0; @@ -244,7 +245,7 @@ noinstr u32 kvm_read_and_reset_apf_flags(void) { u32 flags = 0; - if (__this_cpu_read(apf_reason.enabled)) { + if (__this_cpu_read(async_pf_enabled)) { flags = __this_cpu_read(apf_reason.flags); __this_cpu_write(apf_reason.flags, 0); } @@ -295,7 +296,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt) inc_irq_stat(irq_hv_callback_count); - if (__this_cpu_read(apf_reason.enabled)) { + if (__this_cpu_read(async_pf_enabled)) { token = __this_cpu_read(apf_reason.token); kvm_async_pf_task_wake(token); __this_cpu_write(apf_reason.token, 0); @@ -362,7 +363,7 @@ static void kvm_guest_cpu_init(void) wrmsrl(MSR_KVM_ASYNC_PF_INT, HYPERVISOR_CALLBACK_VECTOR); wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); - __this_cpu_write(apf_reason.enabled, 1); + __this_cpu_write(async_pf_enabled, true); pr_debug("setup async PF for cpu %d\n", smp_processor_id()); } @@ -383,11 +384,11 @@ static void kvm_guest_cpu_init(void) static void kvm_pv_disable_apf(void) { - if (!__this_cpu_read(apf_reason.enabled)) + if (!__this_cpu_read(async_pf_enabled)) return; wrmsrl(MSR_KVM_ASYNC_PF_EN, 0); - __this_cpu_write(apf_reason.enabled, 0); + __this_cpu_write(async_pf_enabled, false); pr_debug("disable async PF for cpu %d\n", smp_processor_id()); } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 1ccd30c8246f..e89171b0347a 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -197,12 +197,12 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) if (!smp_check_mpc(mpc, oem, str)) return 0; - /* Initialize the lapic mapping */ - if (!acpi_lapic) - register_lapic_address(mpc->lapic); - - if (early) + if (early) { + /* Initialize the lapic mapping */ + if (!acpi_lapic) + register_lapic_address(mpc->lapic); return 1; + } /* Now process the configuration blocks. */ while (count < mpc->length) { diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 9a5b372c706f..ed163c8c8604 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -580,7 +580,7 @@ EXPORT_SYMBOL_GPL(asm_exc_nmi_kvm_vmx); static char *nmi_check_stall_msg[] = { /* */ -/* +--------- nsp->idt_seq_snap & 0x1: CPU is in NMI handler. */ +/* +--------- nmi_seq & 0x1: CPU is currently in NMI handler. */ /* | +------ cpu_is_offline(cpu) */ /* | | +--- nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls): */ /* | | | NMI handler has been invoked. */ @@ -628,22 +628,26 @@ void nmi_backtrace_stall_check(const struct cpumask *btp) nmi_seq = READ_ONCE(nsp->idt_nmi_seq); if (nsp->idt_nmi_seq_snap + 1 == nmi_seq && (nmi_seq & 0x1)) { msgp = "CPU entered NMI handler function, but has not exited"; - } else if ((nsp->idt_nmi_seq_snap & 0x1) != (nmi_seq & 0x1)) { - msgp = "CPU is handling NMIs"; - } else { - idx = ((nsp->idt_seq_snap & 0x1) << 2) | + } else if (nsp->idt_nmi_seq_snap == nmi_seq || + nsp->idt_nmi_seq_snap + 1 == nmi_seq) { + idx = ((nmi_seq & 0x1) << 2) | (cpu_is_offline(cpu) << 1) | (nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls)); msgp = nmi_check_stall_msg[idx]; if (nsp->idt_ignored_snap != READ_ONCE(nsp->idt_ignored) && (idx & 0x1)) modp = ", but OK because ignore_nmis was set"; - if (nmi_seq & 0x1) - msghp = " (CPU currently in NMI handler function)"; - else if (nsp->idt_nmi_seq_snap + 1 == nmi_seq) + if (nsp->idt_nmi_seq_snap + 1 == nmi_seq) msghp = " (CPU exited one NMI handler function)"; + else if (nmi_seq & 0x1) + msghp = " (CPU currently in NMI handler function)"; + else + msghp = " (CPU was never in an NMI handler function)"; + } else { + msgp = "CPU is handling NMIs"; } - pr_alert("%s: CPU %d: %s%s%s, last activity: %lu jiffies ago.\n", - __func__, cpu, msgp, modp, msghp, j - READ_ONCE(nsp->recv_jiffies)); + pr_alert("%s: CPU %d: %s%s%s\n", __func__, cpu, msgp, modp, msghp); + pr_alert("%s: last activity: %lu jiffies ago.\n", + __func__, j - READ_ONCE(nsp->recv_jiffies)); } } diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 319fef37d9dc..cc2c34ba7228 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -203,16 +203,6 @@ void __init probe_roms(void) unsigned char c; int i; - /* - * The ROM memory range is not part of the e820 table and is therefore not - * pre-validated by BIOS. The kernel page table maps the ROM region as encrypted - * memory, and SNP requires encrypted memory to be validated before access. - * Do that here. - */ - snp_prep_memory(video_rom_resource.start, - ((system_rom_resource.end + 1) - video_rom_resource.start), - SNP_PAGE_STATE_PRIVATE); - /* video rom */ upper = adapter_rom_resources[0].start; for (start = video_rom_resource.start; start < upper; start += 2048) { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d50b258a0290..678369e46263 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -10,7 +10,6 @@ #include <linux/cpu.h> #include <linux/crash_dump.h> #include <linux/dma-map-ops.h> -#include <linux/dmi.h> #include <linux/efi.h> #include <linux/ima.h> #include <linux/init_ohci1394_dma.h> @@ -37,6 +36,7 @@ #include <asm/bios_ebda.h> #include <asm/bugs.h> #include <asm/cacheinfo.h> +#include <asm/coco.h> #include <asm/cpu.h> #include <asm/efi.h> #include <asm/gart.h> @@ -903,7 +903,7 @@ void __init setup_arch(char **cmdline_p) efi_init(); reserve_ibft_region(); - dmi_setup(); + x86_init.resources.dmi_setup(); /* * VMware detection requires dmi to be available, so this @@ -993,6 +993,7 @@ void __init setup_arch(char **cmdline_p) * memory size. */ mem_encrypt_setup_arch(); + cc_random_init(); efi_fake_memmap(); efi_find_mirror(); @@ -1207,16 +1208,6 @@ void __init i386_reserve_resources(void) #endif /* CONFIG_X86_32 */ -#ifndef CONFIG_SMP -void __init smp_prepare_boot_cpu(void) -{ - struct cpuinfo_x86 *c = &cpu_data(0); - - *c = boot_cpu_data; - c->initialized = true; -} -#endif - static struct notifier_block kernel_offset_notifier = { .notifier_call = dump_kernel_offset }; diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index b59b09c2f284..38ad066179d8 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -23,6 +23,7 @@ #include <linux/platform_device.h> #include <linux/io.h> #include <linux/psp-sev.h> +#include <linux/dmi.h> #include <uapi/linux/sev-guest.h> #include <asm/init.h> @@ -795,21 +796,6 @@ void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED); } -void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) -{ - unsigned long vaddr, npages; - - vaddr = (unsigned long)__va(paddr); - npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; - - if (op == SNP_PAGE_STATE_PRIVATE) - early_snp_set_memory_private(vaddr, paddr, npages); - else if (op == SNP_PAGE_STATE_SHARED) - early_snp_set_memory_shared(vaddr, paddr, npages); - else - WARN(1, "invalid memory op %d\n", op); -} - static unsigned long __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr, unsigned long vaddr_end, int op) { @@ -2136,6 +2122,17 @@ void __head __noreturn snp_abort(void) sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); } +/* + * SEV-SNP guests should only execute dmi_setup() if EFI_CONFIG_TABLES are + * enabled, as the alternative (fallback) logic for DMI probing in the legacy + * ROM region can cause a crash since this region is not pre-validated. + */ +void __init snp_dmi_setup(void) +{ + if (efi_enabled(EFI_CONFIG_TABLES)) + dmi_setup(); +} + static void dump_cpuid_table(void) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); @@ -2287,16 +2284,6 @@ static int __init snp_init_platform_device(void) } device_initcall(snp_init_platform_device); -void kdump_sev_callback(void) -{ - /* - * Do wbinvd() on remote CPUs when SNP is enabled in order to - * safely do SNP_SHUTDOWN on the local CPU. - */ - if (cpu_feature_enabled(X86_FEATURE_SEV_SNP)) - wbinvd(); -} - void sev_show_status(void) { int i; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index fe355c89f6c1..76bb65045c64 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -313,14 +313,6 @@ static void notrace start_secondary(void *unused) cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } -static void __init smp_store_boot_cpu_info(void) -{ - struct cpuinfo_x86 *c = &cpu_data(0); - - *c = boot_cpu_data; - c->initialized = true; -} - /* * The bootstrap kernel entry code has set these up. Save them for * a given CPU @@ -1039,29 +1031,15 @@ static __init void disable_smp(void) cpumask_set_cpu(0, topology_die_cpumask(0)); } -static void __init smp_cpu_index_default(void) -{ - int i; - struct cpuinfo_x86 *c; - - for_each_possible_cpu(i) { - c = &cpu_data(i); - /* mark all to hotplug */ - c->cpu_index = nr_cpu_ids; - } -} - void __init smp_prepare_cpus_common(void) { unsigned int i; - smp_cpu_index_default(); - - /* - * Setup boot CPU information - */ - smp_store_boot_cpu_info(); /* Final full version of the data */ - mb(); + /* Mark all except the boot CPU as hotpluggable */ + for_each_possible_cpu(i) { + if (i) + per_cpu(cpu_info.cpu_index, i) = nr_cpu_ids; + } for_each_possible_cpu(i) { zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index a42830dc151b..d5dc5a92635a 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -3,6 +3,7 @@ * * For licencing details see kernel-base/COPYING */ +#include <linux/dmi.h> #include <linux/init.h> #include <linux/ioport.h> #include <linux/export.h> @@ -66,6 +67,7 @@ struct x86_init_ops x86_init __initdata = { .probe_roms = probe_roms, .reserve_resources = reserve_standard_io_resources, .memory_setup = e820__memory_setup_default, + .dmi_setup = dmi_setup, }, .mpparse = { diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 8c3032a96caf..0ebdd088f28b 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -118,10 +118,11 @@ config KVM_AMD will be called kvm-amd. config KVM_AMD_SEV - def_bool y bool "AMD Secure Encrypted Virtualization (SEV) support" + default y depends on KVM_AMD && X86_64 depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m) + select ARCH_HAS_CC_PLATFORM help Provides support for launching Encrypted VMs (SEV) and Encrypted VMs with Encrypted State (SEV-ES) on AMD processors. diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 475b5fa917a6..a88bb14266b6 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -4,7 +4,8 @@ ccflags-y += -I $(srctree)/arch/x86/kvm ccflags-$(CONFIG_KVM_WERROR) += -Werror ifeq ($(CONFIG_FRAME_POINTER),y) -OBJECT_FILES_NON_STANDARD_vmenter.o := y +OBJECT_FILES_NON_STANDARD_vmx/vmenter.o := y +OBJECT_FILES_NON_STANDARD_svm/vmenter.o := y endif include $(srctree)/virt/kvm/Makefile.kvm diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index adba49afb5fe..bfc0bfcb2bc6 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -189,15 +189,15 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 return 0; } -static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, - const char *sig) +static struct kvm_hypervisor_cpuid __kvm_get_hypervisor_cpuid(struct kvm_cpuid_entry2 *entries, + int nent, const char *sig) { struct kvm_hypervisor_cpuid cpuid = {}; struct kvm_cpuid_entry2 *entry; u32 base; for_each_possible_hypervisor_cpuid_base(base) { - entry = kvm_find_cpuid_entry(vcpu, base); + entry = cpuid_entry2_find(entries, nent, base, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (entry) { u32 signature[3]; @@ -217,22 +217,29 @@ static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcp return cpuid; } -static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu, - struct kvm_cpuid_entry2 *entries, int nent) +static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, + const char *sig) { - u32 base = vcpu->arch.kvm_cpuid.base; - - if (!base) - return NULL; + return __kvm_get_hypervisor_cpuid(vcpu->arch.cpuid_entries, + vcpu->arch.cpuid_nent, sig); +} - return cpuid_entry2_find(entries, nent, base | KVM_CPUID_FEATURES, +static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_cpuid_entry2 *entries, + int nent, u32 kvm_cpuid_base) +{ + return cpuid_entry2_find(entries, nent, kvm_cpuid_base | KVM_CPUID_FEATURES, KVM_CPUID_INDEX_NOT_SIGNIFICANT); } static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu) { - return __kvm_find_kvm_cpuid_features(vcpu, vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent); + u32 base = vcpu->arch.kvm_cpuid.base; + + if (!base) + return NULL; + + return __kvm_find_kvm_cpuid_features(vcpu->arch.cpuid_entries, + vcpu->arch.cpuid_nent, base); } void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) @@ -266,6 +273,7 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e int nent) { struct kvm_cpuid_entry2 *best; + struct kvm_hypervisor_cpuid kvm_cpuid; best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (best) { @@ -292,10 +300,12 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e cpuid_entry_has(best, X86_FEATURE_XSAVEC))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - best = __kvm_find_kvm_cpuid_features(vcpu, entries, nent); - if (kvm_hlt_in_guest(vcpu->kvm) && best && - (best->eax & (1 << KVM_FEATURE_PV_UNHALT))) - best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); + kvm_cpuid = __kvm_get_hypervisor_cpuid(entries, nent, KVM_SIGNATURE); + if (kvm_cpuid.base) { + best = __kvm_find_kvm_cpuid_features(entries, nent, kvm_cpuid.base); + if (kvm_hlt_in_guest(vcpu->kvm) && best) + best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); + } if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { best = cpuid_entry2_find(entries, nent, 0x1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index aadefcaa9561..58ac8d69c94b 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -102,10 +102,12 @@ static const struct cpuid_reg reverse_cpuid[] = { */ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) { + BUILD_BUG_ON(NR_CPUID_WORDS != NCAPINTS); BUILD_BUG_ON(x86_leaf == CPUID_LNX_1); BUILD_BUG_ON(x86_leaf == CPUID_LNX_2); BUILD_BUG_ON(x86_leaf == CPUID_LNX_3); BUILD_BUG_ON(x86_leaf == CPUID_LNX_4); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_5); BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid)); BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0); } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index ae0ac12382b9..61a7531d41b0 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -84,9 +84,10 @@ struct enc_region { }; /* Called with the sev_bitmap_lock held, or on shutdown */ -static int sev_flush_asids(int min_asid, int max_asid) +static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid) { - int ret, asid, error = 0; + int ret, error = 0; + unsigned int asid; /* Check if there are any ASIDs to reclaim before performing a flush */ asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid); @@ -116,7 +117,7 @@ static inline bool is_mirroring_enc_context(struct kvm *kvm) } /* Must be called with the sev_bitmap_lock held */ -static bool __sev_recycle_asids(int min_asid, int max_asid) +static bool __sev_recycle_asids(unsigned int min_asid, unsigned int max_asid) { if (sev_flush_asids(min_asid, max_asid)) return false; @@ -143,8 +144,20 @@ static void sev_misc_cg_uncharge(struct kvm_sev_info *sev) static int sev_asid_new(struct kvm_sev_info *sev) { - int asid, min_asid, max_asid, ret; + /* + * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. + * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. + * Note: min ASID can end up larger than the max if basic SEV support is + * effectively disabled by disallowing use of ASIDs for SEV guests. + */ + unsigned int min_asid = sev->es_active ? 1 : min_sev_asid; + unsigned int max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; + unsigned int asid; bool retry = true; + int ret; + + if (min_asid > max_asid) + return -ENOTTY; WARN_ON(sev->misc_cg); sev->misc_cg = get_current_misc_cg(); @@ -157,12 +170,6 @@ static int sev_asid_new(struct kvm_sev_info *sev) mutex_lock(&sev_bitmap_lock); - /* - * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. - * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. - */ - min_asid = sev->es_active ? 1 : min_sev_asid; - max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; again: asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid); if (asid > max_asid) { @@ -179,7 +186,8 @@ again: mutex_unlock(&sev_bitmap_lock); - return asid; + sev->asid = asid; + return 0; e_uncharge: sev_misc_cg_uncharge(sev); put_misc_cg(sev->misc_cg); @@ -187,7 +195,7 @@ e_uncharge: return ret; } -static int sev_get_asid(struct kvm *kvm) +static unsigned int sev_get_asid(struct kvm *kvm) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; @@ -247,21 +255,19 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_platform_init_args init_args = {0}; - int asid, ret; + int ret; if (kvm->created_vcpus) return -EINVAL; - ret = -EBUSY; if (unlikely(sev->active)) - return ret; + return -EINVAL; sev->active = true; sev->es_active = argp->id == KVM_SEV_ES_INIT; - asid = sev_asid_new(sev); - if (asid < 0) + ret = sev_asid_new(sev); + if (ret) goto e_no_asid; - sev->asid = asid; init_args.probe = false; ret = sev_platform_init(&init_args); @@ -287,8 +293,8 @@ e_no_asid: static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) { + unsigned int asid = sev_get_asid(kvm); struct sev_data_activate activate; - int asid = sev_get_asid(kvm); int ret; /* activate ASID on the given handle */ @@ -2240,8 +2246,10 @@ void __init sev_hardware_setup(void) goto out; } - sev_asid_count = max_sev_asid - min_sev_asid + 1; - WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); + if (min_sev_asid <= max_sev_asid) { + sev_asid_count = max_sev_asid - min_sev_asid + 1; + WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); + } sev_supported = true; /* SEV-ES support requested? */ @@ -2272,7 +2280,9 @@ void __init sev_hardware_setup(void) out: if (boot_cpu_has(X86_FEATURE_SEV)) pr_info("SEV %s (ASIDs %u - %u)\n", - sev_supported ? "enabled" : "disabled", + sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" : + "unusable" : + "disabled", min_sev_asid, max_sev_asid); if (boot_cpu_has(X86_FEATURE_SEV_ES)) pr_info("SEV-ES %s (ASIDs %u - %u)\n", @@ -2320,7 +2330,7 @@ int sev_cpu_init(struct svm_cpu_data *sd) */ static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va) { - int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid; + unsigned int asid = sev_get_asid(vcpu->kvm); /* * Note! The address must be a kernel address, as regular page walk @@ -2638,7 +2648,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) void pre_sev_run(struct vcpu_svm *svm, int cpu) { struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); - int asid = sev_get_asid(svm->vcpu.kvm); + unsigned int asid = sev_get_asid(svm->vcpu.kvm); /* Assign the asid allocated with this SEV guest */ svm->asid = asid; @@ -3174,7 +3184,7 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) unsigned long pfn; struct page *p; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); /* diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 88659de4d2a7..c6b4b1728006 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -735,13 +735,13 @@ TRACE_EVENT(kvm_nested_intr_vmexit, * Tracepoint for nested #vmexit because of interrupt pending */ TRACE_EVENT(kvm_invlpga, - TP_PROTO(__u64 rip, int asid, u64 address), + TP_PROTO(__u64 rip, unsigned int asid, u64 address), TP_ARGS(rip, asid, address), TP_STRUCT__entry( - __field( __u64, rip ) - __field( int, asid ) - __field( __u64, address ) + __field( __u64, rip ) + __field( unsigned int, asid ) + __field( __u64, address ) ), TP_fast_assign( @@ -750,7 +750,7 @@ TRACE_EVENT(kvm_invlpga, __entry->address = address; ), - TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx", + TP_printk("rip: 0x%016llx asid: %u address: 0x%016llx", __entry->rip, __entry->asid, __entry->address) ); diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 721b528da9ac..e674ccf720b9 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -163,6 +163,7 @@ SYM_CODE_START_NOALIGN(srso_alias_untrain_ret) lfence jmp srso_alias_return_thunk SYM_FUNC_END(srso_alias_untrain_ret) +__EXPORT_THUNK(srso_alias_untrain_ret) .popsection .pushsection .text..__x86.rethunk_safe @@ -224,10 +225,16 @@ SYM_CODE_START(srso_return_thunk) SYM_CODE_END(srso_return_thunk) #define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret" -#define JMP_SRSO_ALIAS_UNTRAIN_RET "jmp srso_alias_untrain_ret" #else /* !CONFIG_MITIGATION_SRSO */ +/* Dummy for the alternative in CALL_UNTRAIN_RET. */ +SYM_CODE_START(srso_alias_untrain_ret) + ANNOTATE_UNRET_SAFE + ANNOTATE_NOENDBR + ret + int3 +SYM_FUNC_END(srso_alias_untrain_ret) +__EXPORT_THUNK(srso_alias_untrain_ret) #define JMP_SRSO_UNTRAIN_RET "ud2" -#define JMP_SRSO_ALIAS_UNTRAIN_RET "ud2" #endif /* CONFIG_MITIGATION_SRSO */ #ifdef CONFIG_MITIGATION_UNRET_ENTRY @@ -319,9 +326,7 @@ SYM_FUNC_END(retbleed_untrain_ret) #if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO) SYM_FUNC_START(entry_untrain_ret) - ALTERNATIVE_2 JMP_RETBLEED_UNTRAIN_RET, \ - JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO, \ - JMP_SRSO_ALIAS_UNTRAIN_RET, X86_FEATURE_SRSO_ALIAS + ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO SYM_FUNC_END(entry_untrain_ret) __EXPORT_THUNK(entry_untrain_ret) diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index a204a332c71f..968d7005f4a7 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -26,31 +26,18 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, for (; addr < end; addr = next) { pud_t *pud = pud_page + pud_index(addr); pmd_t *pmd; - bool use_gbpage; next = (addr & PUD_MASK) + PUD_SIZE; if (next > end) next = end; - /* if this is already a gbpage, this portion is already mapped */ - if (pud_leaf(*pud)) - continue; - - /* Is using a gbpage allowed? */ - use_gbpage = info->direct_gbpages; - - /* Don't use gbpage if it maps more than the requested region. */ - /* at the begining: */ - use_gbpage &= ((addr & ~PUD_MASK) == 0); - /* ... or at the end: */ - use_gbpage &= ((next & ~PUD_MASK) == 0); - - /* Never overwrite existing mappings */ - use_gbpage &= !pud_present(*pud); - - if (use_gbpage) { + if (info->direct_gbpages) { pud_t pudval; + if (pud_present(*pud)) + continue; + + addr &= PUD_MASK; pudval = __pud((addr - info->offset) | info->page_flag); set_pud(pud, pudval); continue; diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 70b91de2e053..422602f6039b 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -492,6 +492,24 @@ void __init sme_early_init(void) */ if (sev_status & MSR_AMD64_SEV_ENABLED) ia32_disable(); + + /* + * Override init functions that scan the ROM region in SEV-SNP guests, + * as this memory is not pre-validated and would thus cause a crash. + */ + if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) { + x86_init.mpparse.find_mptable = x86_init_noop; + x86_init.pci.init_irq = x86_init_noop; + x86_init.resources.probe_roms = x86_init_noop; + + /* + * DMI setup behavior for SEV-SNP guests depends on + * efi_enabled(EFI_CONFIG_TABLES), which hasn't been + * parsed yet. snp_dmi_setup() will run after that + * parsing has happened. + */ + x86_init.resources.dmi_setup = snp_dmi_setup; + } } void __init mem_encrypt_free_decrypted_mem(void) diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 104544359d69..025fd7ea5d69 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -24,6 +24,7 @@ #include <linux/memblock.h> #include <linux/init.h> +#include <asm/pgtable_areas.h> #include "numa_internal.h" diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 0d72183b5dd0..36b603d0cdde 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -947,6 +947,38 @@ static void free_pfn_range(u64 paddr, unsigned long size) memtype_free(paddr, paddr + size); } +static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, + pgprot_t *pgprot) +{ + unsigned long prot; + + VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT)); + + /* + * We need the starting PFN and cachemode used for track_pfn_remap() + * that covered the whole VMA. For most mappings, we can obtain that + * information from the page tables. For COW mappings, we might now + * suddenly have anon folios mapped and follow_phys() will fail. + * + * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to + * detect the PFN. If we need the cachemode as well, we're out of luck + * for now and have to fail fork(). + */ + if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) { + if (pgprot) + *pgprot = __pgprot(prot); + return 0; + } + if (is_cow_mapping(vma->vm_flags)) { + if (pgprot) + return -EINVAL; + *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; + return 0; + } + WARN_ON_ONCE(1); + return -EINVAL; +} + /* * track_pfn_copy is called when vma that is covering the pfnmap gets * copied through copy_page_range(). @@ -957,20 +989,13 @@ static void free_pfn_range(u64 paddr, unsigned long size) int track_pfn_copy(struct vm_area_struct *vma) { resource_size_t paddr; - unsigned long prot; unsigned long vma_size = vma->vm_end - vma->vm_start; pgprot_t pgprot; if (vma->vm_flags & VM_PAT) { - /* - * reserve the whole chunk covered by vma. We need the - * starting address and protection from pte. - */ - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, &pgprot)) return -EINVAL; - } - pgprot = __pgprot(prot); + /* reserve the whole chunk covered by vma. */ return reserve_pfn_range(paddr, vma_size, &pgprot, 1); } @@ -1045,7 +1070,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size, bool mm_wr_locked) { resource_size_t paddr; - unsigned long prot; if (vma && !(vma->vm_flags & VM_PAT)) return; @@ -1053,11 +1077,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, /* free the chunk starting from pfn or the whole chunk */ paddr = (resource_size_t)pfn << PAGE_SHIFT; if (!paddr && !size) { - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, NULL)) return; - } - size = vma->vm_end - vma->vm_start; } free_pfn_range(paddr, size); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index a7ba8e178645..df5fac428408 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -480,7 +480,7 @@ static int emit_call(u8 **pprog, void *func, void *ip) static int emit_rsb_call(u8 **pprog, void *func, void *ip) { OPTIMIZER_HIDE_VAR(func); - x86_call_depth_emit_accounting(pprog, func); + ip += x86_call_depth_emit_accounting(pprog, func, ip); return emit_patch(pprog, func, ip, 0xE8); } @@ -1972,20 +1972,17 @@ populate_extable: /* call */ case BPF_JMP | BPF_CALL: { - int offs; + u8 *ip = image + addrs[i - 1]; func = (u8 *) __bpf_call_base + imm32; if (tail_call_reachable) { RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stack_depth); - if (!imm32) - return -EINVAL; - offs = 7 + x86_call_depth_emit_accounting(&prog, func); - } else { - if (!imm32) - return -EINVAL; - offs = x86_call_depth_emit_accounting(&prog, func); + ip += 7; } - if (emit_call(&prog, func, image + addrs[i - 1] + offs)) + if (!imm32) + return -EINVAL; + ip += x86_call_depth_emit_accounting(&prog, func, ip); + if (emit_call(&prog, func, ip)) return -EINVAL; break; } @@ -2835,7 +2832,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im * Direct-call fentry stub, as such it needs accounting for the * __fentry__ call. */ - x86_call_depth_emit_accounting(&prog, NULL); + x86_call_depth_emit_accounting(&prog, NULL, image); } EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 944e0290f2c0..8c2d4b8de25d 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -75,6 +75,9 @@ static void __init init_pvh_bootparams(bool xen_guest) } else xen_raw_printk("Warning: Can fit ISA range into e820\n"); + if (xen_guest) + xen_reserve_extra_memory(&pvh_bootparams); + pvh_bootparams.hdr.cmd_line_ptr = pvh_start_info.cmdline_paddr; diff --git a/arch/x86/virt/Makefile b/arch/x86/virt/Makefile index 1e36502cd738..ea343fc392dc 100644 --- a/arch/x86/virt/Makefile +++ b/arch/x86/virt/Makefile @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-y += vmx/ +obj-y += svm/ vmx/ diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c index cffe1157a90a..ab0e8448bb6e 100644 --- a/arch/x86/virt/svm/sev.c +++ b/arch/x86/virt/svm/sev.c @@ -77,7 +77,7 @@ static int __mfd_enable(unsigned int cpu) { u64 val; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return 0; rdmsrl(MSR_AMD64_SYSCFG, val); @@ -98,7 +98,7 @@ static int __snp_enable(unsigned int cpu) { u64 val; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return 0; rdmsrl(MSR_AMD64_SYSCFG, val); @@ -174,11 +174,11 @@ static int __init snp_rmptable_init(void) u64 rmptable_size; u64 val; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return 0; if (!amd_iommu_snp_en) - return 0; + goto nosnp; if (!probed_rmp_size) goto nosnp; @@ -225,7 +225,7 @@ skip_enable: return 0; nosnp: - setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); return -ENOSYS; } @@ -246,7 +246,7 @@ static struct rmpentry *__snp_lookup_rmpentry(u64 pfn, int *level) { struct rmpentry *large_entry, *entry; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return ERR_PTR(-ENODEV); entry = get_rmpentry(pfn); @@ -363,7 +363,7 @@ int psmash(u64 pfn) unsigned long paddr = pfn << PAGE_SHIFT; int ret; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return -ENODEV; if (!pfn_valid(pfn)) @@ -472,7 +472,7 @@ static int rmpupdate(u64 pfn, struct rmp_state *state) unsigned long paddr = pfn << PAGE_SHIFT; int ret, level; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return -ENODEV; level = RMP_TO_PG_LEVEL(state->pagesize); @@ -558,3 +558,13 @@ void snp_leak_pages(u64 pfn, unsigned int npages) spin_unlock(&snp_leaked_pages_list_lock); } EXPORT_SYMBOL_GPL(snp_leak_pages); + +void kdump_sev_callback(void) +{ + /* + * Do wbinvd() on remote CPUs when SNP is enabled in order to + * safely do SNP_SHUTDOWN on the local CPU. + */ + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + wbinvd(); +} diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index a65fc2ae15b4..77e788e928cd 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -81,7 +81,6 @@ config XEN_PVH bool "Xen PVH guest support" depends on XEN && XEN_PVHVM && ACPI select PVH - def_bool n help Support for running as a Xen PVH guest. diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 3c61bb98c10e..a01ca255b0c6 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -6,6 +6,7 @@ #include <linux/console.h> #include <linux/cpu.h> #include <linux/kexec.h> +#include <linux/memblock.h> #include <linux/slab.h> #include <linux/panic_notifier.h> @@ -350,3 +351,34 @@ void xen_arch_unregister_cpu(int num) } EXPORT_SYMBOL(xen_arch_unregister_cpu); #endif + +/* Amount of extra memory space we add to the e820 ranges */ +struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; + +void __init xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns) +{ + unsigned int i; + + /* + * No need to check for zero size, should happen rarely and will only + * write a new entry regarded to be unused due to zero size. + */ + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + /* Add new region. */ + if (xen_extra_mem[i].n_pfns == 0) { + xen_extra_mem[i].start_pfn = start_pfn; + xen_extra_mem[i].n_pfns = n_pfns; + break; + } + /* Append to existing region. */ + if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns == + start_pfn) { + xen_extra_mem[i].n_pfns += n_pfns; + break; + } + } + if (i == XEN_EXTRA_MEM_MAX_REGIONS) + printk(KERN_WARNING "Warning: not enough extra memory regions\n"); + + memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); +} diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index 9e9db601bd52..27a2a02ef8fb 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/acpi.h> #include <linux/export.h> +#include <linux/mm.h> #include <xen/hvc-console.h> @@ -73,3 +74,70 @@ void __init mem_map_via_hcall(struct boot_params *boot_params_p) } boot_params_p->e820_entries = memmap.nr_entries; } + +/* + * Reserve e820 UNUSABLE regions to inflate the memory balloon. + * + * On PVH dom0 the host memory map is used, RAM regions available to dom0 are + * located as the same place as in the native memory map, but since dom0 gets + * less memory than the total amount of host RAM the ranges that can't be + * populated are converted from RAM -> UNUSABLE. Use such regions (up to the + * ratio signaled in EXTRA_MEM_RATIO) in order to inflate the balloon driver at + * boot. Doing so prevents the guest (even if just temporary) from using holes + * in the memory map in order to map grants or foreign addresses, and + * hopefully limits the risk of a clash with a device MMIO region. Ideally the + * hypervisor should notify us which memory ranges are suitable for creating + * foreign mappings, but that's not yet implemented. + */ +void __init xen_reserve_extra_memory(struct boot_params *bootp) +{ + unsigned int i, ram_pages = 0, extra_pages; + + for (i = 0; i < bootp->e820_entries; i++) { + struct boot_e820_entry *e = &bootp->e820_table[i]; + + if (e->type != E820_TYPE_RAM) + continue; + ram_pages += PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr); + } + + /* Max amount of extra memory. */ + extra_pages = EXTRA_MEM_RATIO * ram_pages; + + /* + * Convert UNUSABLE ranges to RAM and reserve them for foreign mapping + * purposes. + */ + for (i = 0; i < bootp->e820_entries && extra_pages; i++) { + struct boot_e820_entry *e = &bootp->e820_table[i]; + unsigned long pages; + + if (e->type != E820_TYPE_UNUSABLE) + continue; + + pages = min(extra_pages, + PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr)); + + if (pages != (PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr))) { + struct boot_e820_entry *next; + + if (bootp->e820_entries == + ARRAY_SIZE(bootp->e820_table)) + /* No space left to split - skip region. */ + continue; + + /* Split entry. */ + next = e + 1; + memmove(next, e, + (bootp->e820_entries - i) * sizeof(*e)); + bootp->e820_entries++; + next->addr = PAGE_ALIGN(e->addr) + PFN_PHYS(pages); + e->size = next->addr - e->addr; + next->size -= e->size; + } + e->type = E820_TYPE_RAM; + extra_pages -= pages; + + xen_add_extra_mem(PFN_UP(e->addr), pages); + } +} diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index b3e37961065a..380591028cb8 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -38,9 +38,6 @@ #define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024) -/* Amount of extra memory space we add to the e820 ranges */ -struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; - /* Number of pages released from the initial allocation. */ unsigned long xen_released_pages; @@ -64,18 +61,6 @@ static struct { } xen_remap_buf __initdata __aligned(PAGE_SIZE); static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY; -/* - * The maximum amount of extra memory compared to the base size. The - * main scaling factor is the size of struct page. At extreme ratios - * of base:extra, all the base memory can be filled with page - * structures for the extra memory, leaving no space for anything - * else. - * - * 10x seems like a reasonable balance between scaling flexibility and - * leaving a practically usable system. - */ -#define EXTRA_MEM_RATIO (10) - static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB); static void __init xen_parse_512gb(void) @@ -96,35 +81,6 @@ static void __init xen_parse_512gb(void) xen_512gb_limit = val; } -static void __init xen_add_extra_mem(unsigned long start_pfn, - unsigned long n_pfns) -{ - int i; - - /* - * No need to check for zero size, should happen rarely and will only - * write a new entry regarded to be unused due to zero size. - */ - for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { - /* Add new region. */ - if (xen_extra_mem[i].n_pfns == 0) { - xen_extra_mem[i].start_pfn = start_pfn; - xen_extra_mem[i].n_pfns = n_pfns; - break; - } - /* Append to existing region. */ - if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns == - start_pfn) { - xen_extra_mem[i].n_pfns += n_pfns; - break; - } - } - if (i == XEN_EXTRA_MEM_MAX_REGIONS) - printk(KERN_WARNING "Warning: not enough extra memory regions\n"); - - memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); -} - static void __init xen_del_extra_mem(unsigned long start_pfn, unsigned long n_pfns) { diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index a87ab36889e7..79cf93f2c92f 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -163,4 +163,18 @@ void xen_hvm_post_suspend(int suspend_cancelled); static inline void xen_hvm_post_suspend(int suspend_cancelled) {} #endif +/* + * The maximum amount of extra memory compared to the base size. The + * main scaling factor is the size of struct page. At extreme ratios + * of base:extra, all the base memory can be filled with page + * structures for the extra memory, leaving no space for anything + * else. + * + * 10x seems like a reasonable balance between scaling flexibility and + * leaving a practically usable system. + */ +#define EXTRA_MEM_RATIO (10) + +void xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns); + #endif /* XEN_OPS_H */ |