diff options
| author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-18 18:47:48 +0000 |
|---|---|---|
| committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-18 18:47:48 +0000 |
| commit | a1865fbd182b17f2d2f465f557af5b45501c5f1c (patch) | |
| tree | 59da519ef2e59c763bb8efdbe67bc348cf833767 /arch/x86 | |
| parent | Adding upstream version 6.7.9. (diff) | |
| download | linux-a1865fbd182b17f2d2f465f557af5b45501c5f1c.tar.xz linux-a1865fbd182b17f2d2f465f557af5b45501c5f1c.zip | |
Adding upstream version 6.7.12.upstream/6.7.12
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'arch/x86')
52 files changed, 513 insertions, 233 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1566748f16..9241274858 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1539,19 +1539,6 @@ config AMD_MEM_ENCRYPT This requires an AMD processor that supports Secure Memory Encryption (SME). -config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT - bool "Activate AMD Secure Memory Encryption (SME) by default" - depends on AMD_MEM_ENCRYPT - help - Say yes to have system memory encrypted by default if running on - an AMD processor that supports Secure Memory Encryption (SME). - - If set to Y, then the encryption of system memory can be - deactivated with the mem_encrypt=off command line option. - - If set to N, then the encryption of system memory can be - activated with the mem_encrypt=on command line option. - # Common NUMA Features config NUMA bool "NUMA Memory Allocation and Scheduler Support" @@ -2609,6 +2596,17 @@ config GDS_FORCE_MITIGATION If in doubt, say N. +config MITIGATION_RFDS + bool "RFDS Mitigation" + depends on CPU_SUP_INTEL + default y + help + Enable mitigation for Register File Data Sampling (RFDS) by default. + RFDS is a hardware vulnerability which affects Intel Atom CPUs. It + allows unprivileged speculative access to stale data previously + stored in floating point, vector and integer registers. + See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst> + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/boot/compressed/efi_mixed.S b/arch/x86/boot/compressed/efi_mixed.S index f4e22ef774..876fc6d46a 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 eeec998657..d07be9d05c 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -14,7 +14,7 @@ #include <asm/processor.h> enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE; -static u64 cc_mask __ro_after_init; +u64 cc_mask __ro_after_init; static bool noinstr intel_cc_platform_has(enum cc_attr attr) { @@ -148,8 +148,3 @@ u64 cc_mkdec(u64 val) } } EXPORT_SYMBOL_GPL(cc_mkdec); - -__init void cc_set_mask(u64 mask) -{ - cc_mask = mask; -} diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index e24976593a..5365d6acbf 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -604,7 +604,6 @@ static void amd_pmu_cpu_dead(int cpu) kfree(cpuhw->lbr_sel); cpuhw->lbr_sel = NULL; - amd_pmu_cpu_reset(cpu); if (!x86_pmu.amd_nb_constraints) return; diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 96e6c51515..c8062975a5 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -12,10 +12,16 @@ #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; +static bool __init hv_vtl_msi_ext_dest_id(void) +{ + return true; +} + void __init hv_vtl_init_platform(void) { pr_info("Linux runs in Hyper-V Virtual Trust Level\n"); @@ -38,6 +44,8 @@ void __init hv_vtl_init_platform(void) x86_platform.legacy.warm_reset = 0; x86_platform.legacy.reserve_bios_regions = 0; x86_platform.legacy.devices.pnpbios = 0; + + x86_init.hyper.msi_ext_dest_id = hv_vtl_msi_ext_dest_id; } static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc) @@ -57,7 +65,7 @@ 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; @@ -71,7 +79,9 @@ 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); @@ -198,7 +208,15 @@ 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); @@ -212,7 +230,7 @@ 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/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index b1a98fa388..0e82074517 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -13,6 +13,7 @@ #include <asm/preempt.h> #include <asm/asm.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/asm.h b/arch/x86/include/asm/asm.h index fbcfec4dc4..ca8eed1d49 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -113,6 +113,20 @@ #endif +#ifndef __ASSEMBLY__ +#ifndef __pic__ +static __always_inline __pure void *rip_rel_ptr(void *p) +{ + asm("leaq %c1(%%rip), %0" : "=r"(p) : "i"(p)); + + return p; +} +#define RIP_REL_REF(var) (*(typeof(&(var)))rip_rel_ptr(&(var))) +#else +#define RIP_REL_REF(var) (var) +#endif +#endif + /* * Macros to generate condition code outputs from inline assembly, * The output operand must be type "bool". diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h index 6ae2d16a76..21940ef8d2 100644 --- a/arch/x86/include/asm/coco.h +++ b/arch/x86/include/asm/coco.h @@ -2,6 +2,7 @@ #ifndef _ASM_X86_COCO_H #define _ASM_X86_COCO_H +#include <asm/asm.h> #include <asm/types.h> enum cc_vendor { @@ -11,9 +12,14 @@ enum cc_vendor { }; extern enum cc_vendor cc_vendor; +extern u64 cc_mask; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM -void cc_set_mask(u64 mask); +static inline void cc_set_mask(u64 mask) +{ + RIP_REL_REF(cc_mask) = mask; +} + u64 cc_mkenc(u64 val); u64 cc_mkdec(u64 val); #else diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index caf4cf2e10..0e4f2da9f6 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -499,4 +499,5 @@ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/crash_core.h b/arch/x86/include/asm/crash_core.h index 76af98f4e8..041020da8d 100644 --- a/arch/x86/include/asm/crash_core.h +++ b/arch/x86/include/asm/crash_core.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_CORE_H */ diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 359ada486f..b31eb9fd59 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -15,7 +15,8 @@ #include <linux/init.h> #include <linux/cc_platform.h> -#include <asm/bootparam.h> +#include <asm/asm.h> +struct boot_params; #ifdef CONFIG_X86_MEM_ENCRYPT void __init mem_encrypt_init(void); @@ -58,6 +59,11 @@ void __init mem_encrypt_free_decrypted_mem(void); void __init sev_es_init_vc_handling(void); +static inline u64 sme_get_me_mask(void) +{ + return RIP_REL_REF(sme_me_mask); +} + #define __bss_decrypted __section(".bss..decrypted") #else /* !CONFIG_AMD_MEM_ENCRYPT */ @@ -89,6 +95,8 @@ early_set_mem_enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool en static inline void mem_encrypt_free_decrypted_mem(void) { } +static inline u64 sme_get_me_mask(void) { return 0; } + #define __bss_decrypted #endif /* CONFIG_AMD_MEM_ENCRYPT */ @@ -106,11 +114,6 @@ void add_encrypt_protection_map(void); extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[]; -static inline u64 sme_get_me_mask(void) -{ - return sme_me_mask; -} - #endif /* __ASSEMBLY__ */ #endif /* __X86_MEM_ENCRYPT_H__ */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 1d51e1850e..857839df66 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -165,6 +165,14 @@ * CPU is not vulnerable to Gather * Data Sampling (GDS). */ +#define ARCH_CAP_RFDS_NO BIT(27) /* + * Not susceptible to Register + * File Data Sampling. + */ +#define ARCH_CAP_RFDS_CLEAR BIT(28) /* + * VERW clears CPU Register + * File. + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index d15b35815e..4e33cc834b 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -271,11 +271,20 @@ .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_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_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 @@ -291,8 +300,8 @@ .macro __UNTRAIN_RET ibpb_feature, call_depth_insns #if defined(CONFIG_RETHUNK) || defined(CONFIG_CPU_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 @@ -351,6 +360,8 @@ extern void retbleed_return_thunk(void); static inline void retbleed_return_thunk(void) {} #endif +extern void srso_alias_untrain_ret(void); + #ifdef CONFIG_CPU_SRSO extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h index d18e5c332c..1b93ff80b4 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -66,10 +66,14 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr, * virt_addr_valid(kaddr) returns true. */ #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) -#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) extern bool __virt_addr_valid(unsigned long kaddr); #define virt_addr_valid(kaddr) __virt_addr_valid((unsigned long) (kaddr)) +static __always_inline void *pfn_to_kaddr(unsigned long pfn) +{ + return __va(pfn << PAGE_SHIFT); +} + static __always_inline u64 __canonical_address(u64 vaddr, u8 vaddr_bits) { return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 5b4a1ce3d3..36f9057970 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -203,12 +203,12 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd unsigned long npages); void __init 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 __init __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); @@ -227,12 +227,12 @@ 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; diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index a800abb1a9..d8416b3bf8 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/vsyscall.h b/arch/x86/include/asm/vsyscall.h index ab60a71a8d..472f0263db 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -4,6 +4,7 @@ #include <linux/seqlock.h> #include <uapi/asm/vsyscall.h> +#include <asm/page_types.h> #ifdef CONFIG_X86_VSYSCALL_EMULATION extern void map_vsyscall(void); @@ -24,4 +25,13 @@ static inline bool emulate_vsyscall(unsigned long error_code, } #endif +/* + * The (legacy) vsyscall page is the long page in the kernel portion + * of the address space that has user-accessible permissions. + */ +static inline bool is_vsyscall_vaddr(unsigned long vaddr) +{ + return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); +} + #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index c878616a18..550dcbbbb1 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/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index 8d8752b44f..ff8f25faca 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -20,7 +20,7 @@ bool cpc_supported_by_cpu(void) (boot_cpu_data.x86_model >= 0x20 && boot_cpu_data.x86_model <= 0x2f))) return true; else if (boot_cpu_data.x86 == 0x17 && - boot_cpu_data.x86_model >= 0x70 && boot_cpu_data.x86_model <= 0x7f) + boot_cpu_data.x86_model >= 0x30 && boot_cpu_data.x86_model <= 0x7f) return true; return boot_cpu_has(X86_FEATURE_CPPC); } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 2055fb308f..77a1ceb717 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1002,11 +1002,11 @@ static bool cpu_has_zenbleed_microcode(void) u32 good_rev = 0; switch (boot_cpu_data.x86_model) { - case 0x30 ... 0x3f: good_rev = 0x0830107a; break; - case 0x60 ... 0x67: good_rev = 0x0860010b; break; - case 0x68 ... 0x6f: good_rev = 0x08608105; break; - case 0x70 ... 0x7f: good_rev = 0x08701032; break; - case 0xa0 ... 0xaf: good_rev = 0x08a00008; break; + case 0x30 ... 0x3f: good_rev = 0x0830107b; break; + case 0x60 ... 0x67: good_rev = 0x0860010c; break; + case 0x68 ... 0x6f: good_rev = 0x08608107; break; + case 0x70 ... 0x7f: good_rev = 0x08701033; break; + case 0xa0 ... 0xaf: good_rev = 0x08a00009; break; default: return false; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 48d049cd74..01ac18f561 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -422,6 +422,13 @@ static void __init mmio_select_mitigation(void) if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM))) setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + + /* + * X86_FEATURE_CLEAR_CPU_BUF could be enabled by other VERW based + * mitigations, disable KVM-only mitigation in that case. + */ + if (boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) + static_branch_disable(&mmio_stale_data_clear); else static_branch_enable(&mmio_stale_data_clear); @@ -474,6 +481,57 @@ static int __init mmio_stale_data_parse_cmdline(char *str) early_param("mmio_stale_data", mmio_stale_data_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "Register File Data Sampling: " fmt + +enum rfds_mitigations { + RFDS_MITIGATION_OFF, + RFDS_MITIGATION_VERW, + RFDS_MITIGATION_UCODE_NEEDED, +}; + +/* Default mitigation for Register File Data Sampling */ +static enum rfds_mitigations rfds_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF; + +static const char * const rfds_strings[] = { + [RFDS_MITIGATION_OFF] = "Vulnerable", + [RFDS_MITIGATION_VERW] = "Mitigation: Clear Register File", + [RFDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", +}; + +static void __init rfds_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_RFDS) || cpu_mitigations_off()) { + rfds_mitigation = RFDS_MITIGATION_OFF; + return; + } + if (rfds_mitigation == RFDS_MITIGATION_OFF) + return; + + if (x86_read_arch_cap_msr() & ARCH_CAP_RFDS_CLEAR) + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + else + rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED; +} + +static __init int rfds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + return 0; + + if (!strcmp(str, "off")) + rfds_mitigation = RFDS_MITIGATION_OFF; + else if (!strcmp(str, "on")) + rfds_mitigation = RFDS_MITIGATION_VERW; + + return 0; +} +early_param("reg_file_data_sampling", rfds_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "" fmt static void __init md_clear_update_mitigation(void) @@ -498,11 +556,19 @@ static void __init md_clear_update_mitigation(void) taa_mitigation = TAA_MITIGATION_VERW; taa_select_mitigation(); } - if (mmio_mitigation == MMIO_MITIGATION_OFF && - boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { + /* + * MMIO_MITIGATION_OFF is not checked here so that mmio_stale_data_clear + * gets updated correctly as per X86_FEATURE_CLEAR_CPU_BUF state. + */ + if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { mmio_mitigation = MMIO_MITIGATION_VERW; mmio_select_mitigation(); } + if (rfds_mitigation == RFDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_RFDS)) { + rfds_mitigation = RFDS_MITIGATION_VERW; + rfds_select_mitigation(); + } out: if (boot_cpu_has_bug(X86_BUG_MDS)) pr_info("MDS: %s\n", mds_strings[mds_mitigation]); @@ -512,6 +578,8 @@ out: pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) pr_info("MMIO Stale Data: Unknown: No mitigations\n"); + if (boot_cpu_has_bug(X86_BUG_RFDS)) + pr_info("Register File Data Sampling: %s\n", rfds_strings[rfds_mitigation]); } static void __init md_clear_select_mitigation(void) @@ -519,11 +587,12 @@ static void __init md_clear_select_mitigation(void) mds_select_mitigation(); taa_select_mitigation(); mmio_select_mitigation(); + rfds_select_mitigation(); /* - * As MDS, TAA and MMIO Stale Data mitigations are inter-related, update - * and print their mitigation after MDS, TAA and MMIO Stale Data - * mitigation selection is done. + * As these mitigations are inter-related and rely on VERW instruction + * to clear the microarchitural buffers, update and print their status + * after mitigation selection is done for each of these vulnerabilities. */ md_clear_update_mitigation(); } @@ -2612,6 +2681,11 @@ static ssize_t mmio_stale_data_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t rfds_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]); +} + static char *stibp_state(void) { if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && @@ -2771,6 +2845,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_GDS: return gds_show_state(buf); + case X86_BUG_RFDS: + return rfds_show_state(buf); + default: break; } @@ -2845,4 +2922,9 @@ ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_GDS); } + +ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 34cac9ea19..97ea52a4e8 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1274,6 +1274,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define SRSO BIT(5) /* CPU is affected by GDS */ #define GDS BIT(6) +/* CPU is affected by Register File Data Sampling */ +#define RFDS BIT(7) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1301,9 +1303,18 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE_L, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_P, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_S, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GRACEMONT, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), @@ -1337,6 +1348,24 @@ static bool arch_cap_mmio_immune(u64 ia32_cap) ia32_cap & ARCH_CAP_SBDR_SSDP_NO); } +static bool __init vulnerable_to_rfds(u64 ia32_cap) +{ + /* The "immunity" bit trumps everything else: */ + if (ia32_cap & ARCH_CAP_RFDS_NO) + return false; + + /* + * VMMs set ARCH_CAP_RFDS_CLEAR for processors not in the blacklist to + * indicate that mitigation is needed because guest is running on a + * vulnerable hardware or may migrate to such hardware: + */ + if (ia32_cap & ARCH_CAP_RFDS_CLEAR) + return true; + + /* Only consult the blacklist when there is no enumeration: */ + return cpu_matches(cpu_vuln_blacklist, RFDS); +} + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = x86_read_arch_cap_msr(); @@ -1448,6 +1477,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) boot_cpu_has(X86_FEATURE_AVX)) setup_force_cpu_bug(X86_BUG_GDS); + if (vulnerable_to_rfds(ia32_cap)) + setup_force_cpu_bug(X86_BUG_RFDS); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 19e0681f04..d04371e851 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -231,9 +231,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r) static bool __rdt_get_mem_config_amd(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - union cpuid_0x10_3_eax eax; - union cpuid_0x10_x_edx edx; - u32 ebx, ecx, subleaf; + u32 eax, ebx, ecx, edx, subleaf; /* * Query CPUID_Fn80000020_EDX_x01 for MBA and @@ -241,9 +239,9 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r) */ subleaf = (r->rid == RDT_RESOURCE_SMBA) ? 2 : 1; - cpuid_count(0x80000020, subleaf, &eax.full, &ebx, &ecx, &edx.full); - hw_res->num_closid = edx.split.cos_max + 1; - r->default_ctrl = MAX_MBA_BW_AMD; + cpuid_count(0x80000020, subleaf, &eax, &ebx, &ecx, &edx); + hw_res->num_closid = edx + 1; + r->default_ctrl = 1 << eax; /* AMD does not use delay */ r->membw.delay_linear = false; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index a4f1aa15f0..52e7e7deee 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -18,7 +18,6 @@ #define MBM_OVERFLOW_INTERVAL 1000 #define MAX_MBA_BW 100u #define MBA_IS_LINEAR 0x4 -#define MAX_MBA_BW_AMD 0x800 #define MBM_CNTR_WIDTH_OFFSET_AMD 20 #define RMID_VAL_ERROR BIT_ULL(63) @@ -296,14 +295,10 @@ struct rftype { * struct mbm_state - status for each MBM counter in each domain * @prev_bw_bytes: Previous bytes value read for bandwidth calculation * @prev_bw: The most recent bandwidth in MBps - * @delta_bw: Difference between the current and previous bandwidth - * @delta_comp: Indicates whether to compute the delta_bw */ struct mbm_state { u64 prev_bw_bytes; u32 prev_bw; - u32 delta_bw; - bool delta_comp; }; /** @@ -395,6 +390,8 @@ struct rdt_parse_data { * @msr_update: Function pointer to update QOS MSRs * @mon_scale: cqm counter * mon_scale = occupancy in bytes * @mbm_width: Monitor width, to detect and correct for overflow. + * @mbm_cfg_mask: Bandwidth sources that can be tracked when Bandwidth + * Monitoring Event Configuration (BMEC) is supported. * @cdp_enabled: CDP state of this resource * * Members of this structure are either private to the architecture @@ -409,6 +406,7 @@ struct rdt_hw_resource { struct rdt_resource *r); unsigned int mon_scale; unsigned int mbm_width; + unsigned int mbm_cfg_mask; bool cdp_enabled; }; diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index f136ac0468..3a6c069614 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -440,9 +440,6 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) cur_bw = bytes / SZ_1M; - if (m->delta_comp) - m->delta_bw = abs(cur_bw - m->prev_bw); - m->delta_comp = false; m->prev_bw = cur_bw; } @@ -520,11 +517,11 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) { u32 closid, rmid, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; - u32 cur_bw, delta_bw, user_bw; struct rdt_resource *r_mba; struct rdt_domain *dom_mba; struct list_head *head; struct rdtgroup *entry; + u32 cur_bw, user_bw; if (!is_mbm_local_enabled()) return; @@ -543,7 +540,6 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) cur_bw = pmbm_data->prev_bw; user_bw = dom_mba->mbps_val[closid]; - delta_bw = pmbm_data->delta_bw; /* MBA resource doesn't support CDP */ cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE); @@ -555,49 +551,31 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) list_for_each_entry(entry, head, mon.crdtgrp_list) { cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; cur_bw += cmbm_data->prev_bw; - delta_bw += cmbm_data->delta_bw; } /* * Scale up/down the bandwidth linearly for the ctrl group. The * bandwidth step is the bandwidth granularity specified by the * hardware. - * - * The delta_bw is used when increasing the bandwidth so that we - * dont alternately increase and decrease the control values - * continuously. - * - * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if - * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep - * switching between 90 and 110 continuously if we only check - * cur_bw < user_bw. + * Always increase throttling if current bandwidth is above the + * target set by user. + * But avoid thrashing up and down on every poll by checking + * whether a decrease in throttling is likely to push the group + * back over target. E.g. if currently throttling to 30% of bandwidth + * on a system with 10% granularity steps, check whether moving to + * 40% would go past the limit by multiplying current bandwidth by + * "(30 + 10) / 30". */ if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) { new_msr_val = cur_msr_val - r_mba->membw.bw_gran; } else if (cur_msr_val < MAX_MBA_BW && - (user_bw > (cur_bw + delta_bw))) { + (user_bw > (cur_bw * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) { new_msr_val = cur_msr_val + r_mba->membw.bw_gran; } else { return; } resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); - - /* - * Delta values are updated dynamically package wise for each - * rdtgrp every time the throttle MSR changes value. - * - * This is because (1)the increase in bandwidth is not perfectly - * linear and only "approximately" linear even when the hardware - * says it is linear.(2)Also since MBA is a core specific - * mechanism, the delta values vary based on number of cores used - * by the rdtgrp. - */ - pmbm_data->delta_comp = true; - list_for_each_entry(entry, head, mon.crdtgrp_list) { - cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; - cmbm_data->delta_comp = true; - } } static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) @@ -813,6 +791,12 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) return ret; if (rdt_cpu_has(X86_FEATURE_BMEC)) { + u32 eax, ebx, ecx, edx; + + /* Detect list of bandwidth sources that can be tracked */ + cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx); + hw_res->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS; + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { mbm_total_event.configurable = true; mbm_config_rftype_init("mbm_total_bytes_config"); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 69a1de9238..2b69e560b0 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1620,12 +1620,6 @@ static int mbm_config_write_domain(struct rdt_resource *r, struct mon_config_info mon_info = {0}; int ret = 0; - /* mon_config cannot be more than the supported set of events */ - if (val > MAX_EVT_CONFIG_BITS) { - rdt_last_cmd_puts("Invalid event configuration\n"); - return -EINVAL; - } - /* * Read the current config value first. If both are the same then * no need to write it again. @@ -1663,6 +1657,7 @@ out: static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); char *dom_str = NULL, *id_str; unsigned long dom_id, val; struct rdt_domain *d; @@ -1686,6 +1681,13 @@ next: return -EINVAL; } + /* Value from user cannot be more than the supported set of events */ + if ((val & hw_res->mbm_cfg_mask) != val) { + rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n", + hw_res->mbm_cfg_mask); + return -EINVAL; + } + list_for_each_entry(d, &r->domains, list) { if (d->id == dom_id) { ret = mbm_config_write_domain(r, d, evtid, val); diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c index e963344b04..53935b4d62 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 117e74c44e..33a214b1a4 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 3518fb26d0..19ca623ffa 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/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index a0ce46c0a2..a6a3475e1d 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -335,7 +335,16 @@ 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/mpparse.c b/arch/x86/kernel/mpparse.c index b223922248..15c700d358 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -196,12 +196,12 @@ 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 3082cf24b6..6da2cfa23c 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -636,7 +636,7 @@ void nmi_backtrace_stall_check(const struct cpumask *btp) 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) + if (nmi_seq & 0x1) msghp = " (CPU currently in NMI handler function)"; else if (nsp->idt_nmi_seq_snap + 1 == nmi_seq) msghp = " (CPU exited one NMI handler function)"; diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 319fef37d9..cc2c34ba72 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 1526747bed..b002ebf024 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -9,7 +9,6 @@ #include <linux/console.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> @@ -904,7 +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 diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index ccb0915e84..466fe09898 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -556,9 +556,9 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0; /* Skip post-processing for out-of-range zero leafs. */ - if (!(leaf->fn <= cpuid_std_range_max || - (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) || - (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max))) + if (!(leaf->fn <= RIP_REL_REF(cpuid_std_range_max) || + (leaf->fn >= 0x40000000 && leaf->fn <= RIP_REL_REF(cpuid_hyp_range_max)) || + (leaf->fn >= 0x80000000 && leaf->fn <= RIP_REL_REF(cpuid_ext_range_max)))) return 0; } @@ -1063,11 +1063,11 @@ static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info) const struct snp_cpuid_fn *fn = &cpuid_table->fn[i]; if (fn->eax_in == 0x0) - cpuid_std_range_max = fn->eax; + RIP_REL_REF(cpuid_std_range_max) = fn->eax; else if (fn->eax_in == 0x40000000) - cpuid_hyp_range_max = fn->eax; + RIP_REL_REF(cpuid_hyp_range_max) = fn->eax; else if (fn->eax_in == 0x80000000) - cpuid_ext_range_max = fn->eax; + RIP_REL_REF(cpuid_ext_range_max) = fn->eax; } } diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index c67285824e..0f58242b54 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/cpu_entry_area.h> @@ -748,7 +749,7 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd * This eliminates worries about jump tables or checking boot_cpu_data * in the cc_platform_has() function. */ - if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED)) return; /* @@ -767,28 +768,13 @@ void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr * This eliminates worries about jump tables or checking boot_cpu_data * in the cc_platform_has() function. */ - if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED)) return; /* Ask hypervisor to mark the memory pages shared in the RMP table. */ 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) { @@ -2112,6 +2098,17 @@ void __init __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(); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index a37ebd3b47..3f0718b4a7 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/cpuid.c b/arch/x86/kvm/cpuid.c index dda6fc4cfa..1811a9ddfe 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -679,6 +679,11 @@ void kvm_set_cpu_caps(void) F(AMX_COMPLEX) ); + kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX, + F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) | + F(BHI_CTRL) | F(MCDT_NO) + ); + kvm_cpu_cap_mask(CPUID_D_1_EAX, F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd ); @@ -960,13 +965,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) break; /* function 7 has additional index. */ case 7: - entry->eax = min(entry->eax, 1u); + max_idx = entry->eax = min(entry->eax, 2u); cpuid_entry_override(entry, CPUID_7_0_EBX); cpuid_entry_override(entry, CPUID_7_ECX); cpuid_entry_override(entry, CPUID_7_EDX); - /* KVM only supports 0x7.0 and 0x7.1, capped above via min(). */ - if (entry->eax == 1) { + /* KVM only supports up to 0x7.2, capped above via min(). */ + if (max_idx >= 1) { entry = do_host_cpuid(array, function, 1); if (!entry) goto out; @@ -976,6 +981,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ebx = 0; entry->ecx = 0; } + if (max_idx >= 2) { + entry = do_host_cpuid(array, function, 2); + if (!entry) + goto out; + + cpuid_entry_override(entry, CPUID_7_2_EDX); + entry->ecx = 0; + entry->ebx = 0; + entry->eax = 0; + } break; case 0xa: { /* Architectural Performance Monitoring */ union cpuid10_eax eax; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 238afd7335..4943f6b2bb 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -2388,7 +2388,7 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *h if (!eventfd) return HV_STATUS_INVALID_PORT_ID; - eventfd_signal(eventfd, 1); + eventfd_signal(eventfd); return HV_STATUS_SUCCESS; } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 245b20973c..23fab75993 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -41,6 +41,7 @@ #include "ioapic.h" #include "trace.h" #include "x86.h" +#include "xen.h" #include "cpuid.h" #include "hyperv.h" #include "smm.h" @@ -499,8 +500,10 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) } /* Check if there are APF page ready requests pending */ - if (enabled) + if (enabled) { kvm_make_request(KVM_REQ_APF_READY, apic->vcpu); + kvm_xen_sw_enable_lapic(apic->vcpu); + } } static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id) diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index b816506783..aadefcaa95 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -16,6 +16,7 @@ enum kvm_only_cpuid_leafs { CPUID_7_1_EDX, CPUID_8000_0007_EDX, CPUID_8000_0022_EAX, + CPUID_7_2_EDX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, @@ -46,6 +47,14 @@ enum kvm_only_cpuid_leafs { #define X86_FEATURE_AMX_COMPLEX KVM_X86_FEATURE(CPUID_7_1_EDX, 8) #define X86_FEATURE_PREFETCHITI KVM_X86_FEATURE(CPUID_7_1_EDX, 14) +/* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */ +#define X86_FEATURE_INTEL_PSFD KVM_X86_FEATURE(CPUID_7_2_EDX, 0) +#define X86_FEATURE_IPRED_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 1) +#define KVM_X86_FEATURE_RRSBA_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 2) +#define X86_FEATURE_DDPD_U KVM_X86_FEATURE(CPUID_7_2_EDX, 3) +#define X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) +#define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5) + /* CPUID level 0x80000007 (EDX). */ #define KVM_X86_FEATURE_CONSTANT_TSC KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8) @@ -80,6 +89,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_0007_EDX] = {0x80000007, 0, CPUID_EDX}, [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, [CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX}, + [CPUID_7_2_EDX] = { 7, 2, CPUID_EDX}, }; /* @@ -106,18 +116,19 @@ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) */ static __always_inline u32 __feature_translate(int x86_feature) { - if (x86_feature == X86_FEATURE_SGX1) - return KVM_X86_FEATURE_SGX1; - else if (x86_feature == X86_FEATURE_SGX2) - return KVM_X86_FEATURE_SGX2; - else if (x86_feature == X86_FEATURE_SGX_EDECCSSA) - return KVM_X86_FEATURE_SGX_EDECCSSA; - else if (x86_feature == X86_FEATURE_CONSTANT_TSC) - return KVM_X86_FEATURE_CONSTANT_TSC; - else if (x86_feature == X86_FEATURE_PERFMON_V2) - return KVM_X86_FEATURE_PERFMON_V2; - - return x86_feature; +#define KVM_X86_TRANSLATE_FEATURE(f) \ + case X86_FEATURE_##f: return KVM_X86_FEATURE_##f + + switch (x86_feature) { + KVM_X86_TRANSLATE_FEATURE(SGX1); + KVM_X86_TRANSLATE_FEATURE(SGX2); + KVM_X86_TRANSLATE_FEATURE(SGX_EDECCSSA); + KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC); + KVM_X86_TRANSLATE_FEATURE(PERFMON_V2); + KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL); + default: + return x86_feature; + } } static __always_inline u32 __feature_leaf(int x86_feature) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 6ee925d666..1226bb2151 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -57,7 +57,7 @@ static bool sev_es_enabled = true; module_param_named(sev_es, sev_es_enabled, bool, 0444); /* enable/disable SEV-ES DebugSwap support */ -static bool sev_es_debug_swap_enabled = true; +static bool sev_es_debug_swap_enabled = false; module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444); #else #define sev_enabled false @@ -612,8 +612,11 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) save->xss = svm->vcpu.arch.ia32_xss; save->dr6 = svm->vcpu.arch.dr6; - if (sev_es_debug_swap_enabled) + if (sev_es_debug_swap_enabled) { save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP; + pr_warn_once("Enabling DebugSwap with KVM_SEV_ES_INIT. " + "This will not work starting with Linux 6.10\n"); + } pr_debug("Virtual Machine Save Area (VMSA):\n"); print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false); @@ -1975,20 +1978,22 @@ int sev_mem_enc_register_region(struct kvm *kvm, goto e_free; } - region->uaddr = range->addr; - region->size = range->size; - - list_add_tail(®ion->list, &sev->regions_list); - mutex_unlock(&kvm->lock); - /* * The guest may change the memory encryption attribute from C=0 -> C=1 * or vice versa for this memory range. Lets make sure caches are * flushed to ensure that guest data gets written into memory with - * correct C-bit. + * correct C-bit. Note, this must be done before dropping kvm->lock, + * as region and its array of pages can be freed by a different task + * once kvm->lock is released. */ sev_clflush_pages(region->pages, region->npages); + region->uaddr = range->addr; + region->size = range->size; + + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + return ret; e_free: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 468870450b..365caf7328 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1620,7 +1620,8 @@ static bool kvm_is_immutable_feature_msr(u32 msr) ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ - ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO) + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR) static u64 kvm_get_arch_capabilities(void) { @@ -1652,6 +1653,8 @@ static u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_SSB_NO; if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + data |= ARCH_CAP_RFDS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* @@ -7948,6 +7951,16 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (r < 0) return X86EMUL_UNHANDLEABLE; + + /* + * Mark the page dirty _before_ checking whether or not the CMPXCHG was + * successful, as the old value is written back on failure. Note, for + * live migration, this is unnecessarily conservative as CMPXCHG writes + * back the original value and the access is atomic, but KVM's ABI is + * that all writes are dirty logged, regardless of the value written. + */ + kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa)); + if (r) return X86EMUL_CMPXCHG_FAILED; diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index e53fad915a..c069521f24 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -493,7 +493,7 @@ void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) kvm_xen_update_runstate_guest(v, state == RUNSTATE_runnable); } -static void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) +void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) { struct kvm_lapic_irq irq = { }; int r; @@ -2088,7 +2088,7 @@ static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r) if (ret < 0 && ret != -ENOTCONN) return false; } else { - eventfd_signal(evtchnfd->deliver.eventfd.ctx, 1); + eventfd_signal(evtchnfd->deliver.eventfd.ctx); } *r = 0; diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index f8f1fe22d0..f5841d9000 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -18,6 +18,7 @@ extern struct static_key_false_deferred kvm_xen_enabled; int __kvm_xen_has_interrupt(struct kvm_vcpu *vcpu); void kvm_xen_inject_pending_events(struct kvm_vcpu *vcpu); +void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *vcpu); int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data); @@ -36,6 +37,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm, const struct kvm_irq_routing_entry *ue); void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu); +static inline void kvm_xen_sw_enable_lapic(struct kvm_vcpu *vcpu) +{ + /* + * The local APIC is being enabled. If the per-vCPU upcall vector is + * set and the vCPU's evtchn_upcall_pending flag is set, inject the + * interrupt. + */ + if (static_branch_unlikely(&kvm_xen_enabled.key) && + vcpu->arch.xen.vcpu_info_cache.active && + vcpu->arch.xen.upcall_vector && __kvm_xen_has_interrupt(vcpu)) + kvm_xen_inject_vcpu_vector(vcpu); +} + static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { return static_branch_unlikely(&kvm_xen_enabled.key) && @@ -101,6 +115,10 @@ static inline void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) { } +static inline void kvm_xen_sw_enable_lapic(struct kvm_vcpu *vcpu) +{ +} + static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { return false; diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 7b2589877d..1e59367b46 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 +225,12 @@ 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_CPU_SRSO */ #define JMP_SRSO_UNTRAIN_RET "ud2" -#define JMP_SRSO_ALIAS_UNTRAIN_RET "ud2" +/* Dummy for the alternative in CALL_UNTRAIN_RET. */ +SYM_CODE_START(srso_alias_untrain_ret) + RET +SYM_FUNC_END(srso_alias_untrain_ret) #endif /* CONFIG_CPU_SRSO */ #ifdef CONFIG_CPU_UNRET_ENTRY @@ -319,9 +322,7 @@ SYM_FUNC_END(retbleed_untrain_ret) #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_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/fault.c b/arch/x86/mm/fault.c index 679b09cfe2..d6375b3c63 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -798,15 +798,6 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, show_opcodes(regs, loglvl); } -/* - * The (legacy) vsyscall page is the long page in the kernel portion - * of the address space that has user-accessible permissions. - */ -static bool is_vsyscall_vaddr(unsigned long vaddr) -{ - return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); -} - static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c index 6993f026ad..42115ac079 100644 --- a/arch/x86/mm/maccess.c +++ b/arch/x86/mm/maccess.c @@ -3,6 +3,8 @@ #include <linux/uaccess.h> #include <linux/kernel.h> +#include <asm/vsyscall.h> + #ifdef CONFIG_X86_64 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { @@ -16,6 +18,14 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) return false; /* + * Reading from the vsyscall page may cause an unhandled fault in + * certain cases. Though it is at an address above TASK_SIZE_MAX, it is + * usually considered as a user space address. + */ + if (is_vsyscall_vaddr(vaddr)) + return false; + + /* * Allow everything during early boot before 'x86_virt_bits' * is initialized. Needed for instruction decoding in early * exception handlers. diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 70b91de2e0..94cd06d4b0 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_smp_config = 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/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index d73aeb1641..0166ab1780 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -97,7 +97,6 @@ static char sme_workarea[2 * PMD_SIZE] __section(".init.scratch"); static char sme_cmdline_arg[] __initdata = "mem_encrypt"; static char sme_cmdline_on[] __initdata = "on"; -static char sme_cmdline_off[] __initdata = "off"; static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) { @@ -305,7 +304,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * instrumentation or checking boot_cpu_data in the cc_platform_has() * function. */ - if (!sme_get_me_mask() || sev_status & MSR_AMD64_SEV_ENABLED) + if (!sme_get_me_mask() || + RIP_REL_REF(sev_status) & MSR_AMD64_SEV_ENABLED) return; /* @@ -504,10 +504,9 @@ void __init sme_encrypt_kernel(struct boot_params *bp) void __init sme_enable(struct boot_params *bp) { - const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off; + const char *cmdline_ptr, *cmdline_arg, *cmdline_on; unsigned int eax, ebx, ecx, edx; unsigned long feature_mask; - bool active_by_default; unsigned long me_mask; char buffer[16]; bool snp; @@ -543,11 +542,11 @@ void __init sme_enable(struct boot_params *bp) me_mask = 1UL << (ebx & 0x3f); /* Check the SEV MSR whether SEV or SME is enabled */ - sev_status = __rdmsr(MSR_AMD64_SEV); - feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; + RIP_REL_REF(sev_status) = msr = __rdmsr(MSR_AMD64_SEV); + feature_mask = (msr & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; /* The SEV-SNP CC blob should never be present unless SEV-SNP is enabled. */ - if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (snp && !(msr & MSR_AMD64_SEV_SNP_ENABLED)) snp_abort(); /* Check if memory encryption is enabled */ @@ -573,7 +572,6 @@ void __init sme_enable(struct boot_params *bp) return; } else { /* SEV state cannot be controlled by a command line option */ - sme_me_mask = me_mask; goto out; } @@ -588,31 +586,17 @@ void __init sme_enable(struct boot_params *bp) asm ("lea sme_cmdline_on(%%rip), %0" : "=r" (cmdline_on) : "p" (sme_cmdline_on)); - asm ("lea sme_cmdline_off(%%rip), %0" - : "=r" (cmdline_off) - : "p" (sme_cmdline_off)); - - if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT)) - active_by_default = true; - else - active_by_default = false; cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr | ((u64)bp->ext_cmd_line_ptr << 32)); - if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0) + if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0 || + strncmp(buffer, cmdline_on, sizeof(buffer))) return; - if (!strncmp(buffer, cmdline_on, sizeof(buffer))) - sme_me_mask = me_mask; - else if (!strncmp(buffer, cmdline_off, sizeof(buffer))) - sme_me_mask = 0; - else - sme_me_mask = active_by_default ? me_mask : 0; out: - if (sme_me_mask) { - physical_mask &= ~sme_me_mask; - cc_vendor = CC_VENDOR_AMD; - cc_set_mask(sme_me_mask); - } + RIP_REL_REF(sme_me_mask) = me_mask; + physical_mask &= ~me_mask; + cc_vendor = CC_VENDOR_AMD; + cc_set_mask(me_mask); } diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index d30949e25e..e701328364 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -653,6 +653,14 @@ static void print_absolute_relocs(void) if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) { continue; } + /* + * Do not perform relocations in .notes section; any + * values there are meant for pre-boot consumption (e.g. + * startup_xen). + */ + if (sec_applies->shdr.sh_type == SHT_NOTE) { + continue; + } sh_symtab = sec_symtab->symtab; sym_strtab = sec_symtab->link->strtab; for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) { diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 4b0d6fff88..1fb9a1644d 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -65,6 +65,8 @@ int xen_smp_intr_init(unsigned int cpu) char *resched_name, *callfunc_name, *debug_name; resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu); + if (!resched_name) + goto fail_mem; per_cpu(xen_resched_irq, cpu).name = resched_name; rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, cpu, @@ -77,6 +79,8 @@ int xen_smp_intr_init(unsigned int cpu) per_cpu(xen_resched_irq, cpu).irq = rc; callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu); + if (!callfunc_name) + goto fail_mem; per_cpu(xen_callfunc_irq, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR, cpu, @@ -90,6 +94,9 @@ int xen_smp_intr_init(unsigned int cpu) if (!xen_fifo_events) { debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu); + if (!debug_name) + goto fail_mem; + per_cpu(xen_debug_irq, cpu).name = debug_name; rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt, @@ -101,6 +108,9 @@ int xen_smp_intr_init(unsigned int cpu) } callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu); + if (!callfunc_name) + goto fail_mem; + per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR, cpu, @@ -114,6 +124,8 @@ int xen_smp_intr_init(unsigned int cpu) return 0; + fail_mem: + rc = -ENOMEM; fail: xen_smp_intr_free(cpu); return rc; |