diff options
Diffstat (limited to 'arch/x86')
251 files changed, 8946 insertions, 3175 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3604074a878b..a825bf031f49 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1502,7 +1502,7 @@ config X86_5LEVEL depends on X86_64 help 5-level paging enables access to larger address space: - upto 128 PiB of virtual address space and 4 PiB of + up to 128 PiB of virtual address space and 4 PiB of physical address space. It will be supported by future Intel CPUs. @@ -2609,8 +2609,8 @@ config CALL_THUNKS_DEBUG a noisy dmesg about callthunks generation and call patching for trouble shooting. The debug prints need to be enabled on the kernel command line with 'debug-callthunks'. - Only enable this, when you are debugging call thunks as this - creates a noticable runtime overhead. If unsure say N. + Only enable this when you are debugging call thunks as this + creates a noticeable runtime overhead. If unsure say N. config CPU_IBPB_ENTRY bool "Enable IBPB on kernel entry" diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler index 26b8c08e2fc4..b88f784cb02e 100644 --- a/arch/x86/Kconfig.assembler +++ b/arch/x86/Kconfig.assembler @@ -19,3 +19,8 @@ config AS_TPAUSE def_bool $(as-instr,tpause %ecx) help Supported by binutils >= 2.31.1 and LLVM integrated assembler >= V7 + +config AS_GFNI + def_bool $(as-instr,vgf2p8mulb %xmm0$(comma)%xmm1$(comma)%xmm2) + help + Supported by binutils >= 2.30 and LLVM integrated assembler diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 9cf07322875a..b39975977c03 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -3,10 +3,10 @@ # select defconfig based on actual architecture ifeq ($(ARCH),x86) - ifeq ($(shell uname -m),x86_64) - KBUILD_DEFCONFIG := x86_64_defconfig - else + ifeq ($(shell uname -m | sed -e 's/i.86/i386/'),i386) KBUILD_DEFCONFIG := i386_defconfig + else + KBUILD_DEFCONFIG := x86_64_defconfig endif else KBUILD_DEFCONFIG := $(ARCH)_defconfig @@ -14,13 +14,13 @@ endif ifdef CONFIG_CC_IS_GCC RETPOLINE_CFLAGS := $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) -RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix) RETPOLINE_VDSO_CFLAGS := $(call cc-option,-mindirect-branch=thunk-inline -mindirect-branch-register) endif ifdef CONFIG_CC_IS_CLANG RETPOLINE_CFLAGS := -mretpoline-external-thunk RETPOLINE_VDSO_CFLAGS := -mretpoline endif +RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix) ifdef CONFIG_RETHUNK RETHUNK_CFLAGS := -mfunction-return=thunk-extern diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 6589ddd4cfaf..987ae727cf9f 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -187,7 +187,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) leal boot_heap@GOTOFF(%ebx), %eax pushl %eax /* heap area */ pushl %esi /* real mode pointer */ - call extract_kernel /* returns kernel location in %eax */ + call extract_kernel /* returns kernel entry point in %eax */ addl $24, %esp /* diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index a75712991df3..03c4328a88cb 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -569,7 +569,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) movl input_len(%rip), %ecx /* input_len */ movq %rbp, %r8 /* output target address */ movl output_len(%rip), %r9d /* decompressed length, end of relocs */ - call extract_kernel /* returns kernel location in %rax */ + call extract_kernel /* returns kernel entry point in %rax */ popq %rsi /* diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index d4a314cc50d6..321a5011042d 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -180,6 +180,12 @@ void initialize_identity_maps(void *rmode) /* Load the new page-table. */ write_cr3(top_level_pgt); + + /* + * Now that the required page table mappings are established and a + * GHCB can be used, check for SNP guest/HV feature compatibility. + */ + snp_check_features(); } static pte_t *split_large_pmd(struct x86_mapping_info *info, diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index cf690d8712f4..014ff222bf4b 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -277,7 +277,7 @@ static inline void handle_relocations(void *output, unsigned long output_len, { } #endif -static void parse_elf(void *output) +static size_t parse_elf(void *output) { #ifdef CONFIG_X86_64 Elf64_Ehdr ehdr; @@ -293,10 +293,8 @@ static void parse_elf(void *output) if (ehdr.e_ident[EI_MAG0] != ELFMAG0 || ehdr.e_ident[EI_MAG1] != ELFMAG1 || ehdr.e_ident[EI_MAG2] != ELFMAG2 || - ehdr.e_ident[EI_MAG3] != ELFMAG3) { + ehdr.e_ident[EI_MAG3] != ELFMAG3) error("Kernel is not a valid ELF file"); - return; - } debug_putstr("Parsing ELF... "); @@ -328,6 +326,8 @@ static void parse_elf(void *output) } free(phdrs); + + return ehdr.e_entry - LOAD_PHYSICAL_ADDR; } /* @@ -356,6 +356,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, const unsigned long kernel_total_size = VO__end - VO__text; unsigned long virt_addr = LOAD_PHYSICAL_ADDR; unsigned long needed_size; + size_t entry_offset; /* Retain x86 boot parameters pointer passed from startup_32/64. */ boot_params = rmode; @@ -456,14 +457,17 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, debug_putstr("\nDecompressing Linux... "); __decompress(input_data, input_len, NULL, NULL, output, output_len, NULL, error); - parse_elf(output); + entry_offset = parse_elf(output); handle_relocations(output, output_len, virt_addr); - debug_putstr("done.\nBooting the kernel.\n"); + + debug_putstr("done.\nBooting the kernel (entry_offset: 0x"); + debug_puthex(entry_offset); + debug_putstr(").\n"); /* Disable exception handling before booting the kernel */ cleanup_exception_handling(); - return output; + return output + entry_offset; } void fortify_panic(const char *name) diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 62208ec04ca4..20118fb7c53b 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -126,6 +126,7 @@ static inline void console_init(void) #ifdef CONFIG_AMD_MEM_ENCRYPT void sev_enable(struct boot_params *bp); +void snp_check_features(void); void sev_es_shutdown_ghcb(void); extern bool sev_es_check_ghcb_fault(unsigned long address); void snp_set_page_private(unsigned long paddr); @@ -143,6 +144,7 @@ static inline void sev_enable(struct boot_params *bp) if (bp) bp->cc_blob_address = 0; } +static inline void snp_check_features(void) { } static inline void sev_es_shutdown_ghcb(void) { } static inline bool sev_es_check_ghcb_fault(unsigned long address) { diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index c93930d5ccbd..d63ad8f99f83 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -208,6 +208,23 @@ void sev_es_shutdown_ghcb(void) error("Can't unmap GHCB page"); } +static void __noreturn sev_es_ghcb_terminate(struct ghcb *ghcb, unsigned int set, + unsigned int reason, u64 exit_info_2) +{ + u64 exit_info_1 = SVM_VMGEXIT_TERM_REASON(set, reason); + + vc_ghcb_invalidate(ghcb); + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_TERM_REQUEST); + ghcb_set_sw_exit_info_1(ghcb, exit_info_1); + ghcb_set_sw_exit_info_2(ghcb, exit_info_2); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + while (true) + asm volatile("hlt\n" : : : "memory"); +} + bool sev_es_check_ghcb_fault(unsigned long address) { /* Check whether the fault was on the GHCB page */ @@ -270,6 +287,59 @@ static void enforce_vmpl0(void) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0); } +/* + * SNP_FEATURES_IMPL_REQ is the mask of SNP features that will need + * guest side implementation for proper functioning of the guest. If any + * of these features are enabled in the hypervisor but are lacking guest + * side implementation, the behavior of the guest will be undefined. The + * guest could fail in non-obvious way making it difficult to debug. + * + * As the behavior of reserved feature bits is unknown to be on the + * safe side add them to the required features mask. + */ +#define SNP_FEATURES_IMPL_REQ (MSR_AMD64_SNP_VTOM | \ + MSR_AMD64_SNP_REFLECT_VC | \ + MSR_AMD64_SNP_RESTRICTED_INJ | \ + MSR_AMD64_SNP_ALT_INJ | \ + MSR_AMD64_SNP_DEBUG_SWAP | \ + MSR_AMD64_SNP_VMPL_SSS | \ + MSR_AMD64_SNP_SECURE_TSC | \ + MSR_AMD64_SNP_VMGEXIT_PARAM | \ + MSR_AMD64_SNP_VMSA_REG_PROTECTION | \ + MSR_AMD64_SNP_RESERVED_BIT13 | \ + MSR_AMD64_SNP_RESERVED_BIT15 | \ + MSR_AMD64_SNP_RESERVED_MASK) + +/* + * SNP_FEATURES_PRESENT is the mask of SNP features that are implemented + * by the guest kernel. As and when a new feature is implemented in the + * guest kernel, a corresponding bit should be added to the mask. + */ +#define SNP_FEATURES_PRESENT (0) + +void snp_check_features(void) +{ + u64 unsupported; + + if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + return; + + /* + * Terminate the boot if hypervisor has enabled any feature lacking + * guest side implementation. Pass on the unsupported features mask through + * EXIT_INFO_2 of the GHCB protocol so that those features can be reported + * as part of the guest boot failure. + */ + unsupported = sev_status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT; + if (unsupported) { + if (ghcb_version < 2 || (!boot_ghcb && !early_setup_ghcb())) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + + sev_es_ghcb_terminate(boot_ghcb, SEV_TERM_SET_GEN, + GHCB_SNP_UNSUPPORTED, unsupported); + } +} + void sev_enable(struct boot_params *bp) { unsigned int eax, ebx, ecx, edx; diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index 112b2375d021..b22f34b8684a 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -34,6 +34,7 @@ SECTIONS _text = .; /* Text */ *(.text) *(.text.*) + *(.noinstr.text) _etext = . ; } .rodata : { diff --git a/arch/x86/coco/tdx/tdcall.S b/arch/x86/coco/tdx/tdcall.S index f9eb1134f22d..6a255e6809bc 100644 --- a/arch/x86/coco/tdx/tdcall.S +++ b/arch/x86/coco/tdx/tdcall.S @@ -13,6 +13,12 @@ /* * Bitmasks of exposed registers (with VMM). */ +#define TDX_RDX BIT(2) +#define TDX_RBX BIT(3) +#define TDX_RSI BIT(6) +#define TDX_RDI BIT(7) +#define TDX_R8 BIT(8) +#define TDX_R9 BIT(9) #define TDX_R10 BIT(10) #define TDX_R11 BIT(11) #define TDX_R12 BIT(12) @@ -27,9 +33,11 @@ * details can be found in TDX GHCI specification, section * titled "TDCALL [TDG.VP.VMCALL] leaf". */ -#define TDVMCALL_EXPOSE_REGS_MASK ( TDX_R10 | TDX_R11 | \ - TDX_R12 | TDX_R13 | \ - TDX_R14 | TDX_R15 ) +#define TDVMCALL_EXPOSE_REGS_MASK \ + ( TDX_RDX | TDX_RBX | TDX_RSI | TDX_RDI | TDX_R8 | TDX_R9 | \ + TDX_R10 | TDX_R11 | TDX_R12 | TDX_R13 | TDX_R14 | TDX_R15 ) + +.section .noinstr.text, "ax" /* * __tdx_module_call() - Used by TDX guests to request services from @@ -124,38 +132,38 @@ SYM_FUNC_START(__tdx_hypercall) push %r14 push %r13 push %r12 + push %rbx + + /* Free RDI and RSI to be used as TDVMCALL arguments */ + movq %rdi, %rax + push %rsi + + /* Copy hypercall registers from arg struct: */ + movq TDX_HYPERCALL_r8(%rax), %r8 + movq TDX_HYPERCALL_r9(%rax), %r9 + movq TDX_HYPERCALL_r10(%rax), %r10 + movq TDX_HYPERCALL_r11(%rax), %r11 + movq TDX_HYPERCALL_r12(%rax), %r12 + movq TDX_HYPERCALL_r13(%rax), %r13 + movq TDX_HYPERCALL_r14(%rax), %r14 + movq TDX_HYPERCALL_r15(%rax), %r15 + movq TDX_HYPERCALL_rdi(%rax), %rdi + movq TDX_HYPERCALL_rsi(%rax), %rsi + movq TDX_HYPERCALL_rbx(%rax), %rbx + movq TDX_HYPERCALL_rdx(%rax), %rdx + + push %rax /* Mangle function call ABI into TDCALL ABI: */ /* Set TDCALL leaf ID (TDVMCALL (0)) in RAX */ xor %eax, %eax - /* Copy hypercall registers from arg struct: */ - movq TDX_HYPERCALL_r10(%rdi), %r10 - movq TDX_HYPERCALL_r11(%rdi), %r11 - movq TDX_HYPERCALL_r12(%rdi), %r12 - movq TDX_HYPERCALL_r13(%rdi), %r13 - movq TDX_HYPERCALL_r14(%rdi), %r14 - movq TDX_HYPERCALL_r15(%rdi), %r15 - movl $TDVMCALL_EXPOSE_REGS_MASK, %ecx - /* - * For the idle loop STI needs to be called directly before the TDCALL - * that enters idle (EXIT_REASON_HLT case). STI instruction enables - * interrupts only one instruction later. If there is a window between - * STI and the instruction that emulates the HALT state, there is a - * chance for interrupts to happen in this window, which can delay the - * HLT operation indefinitely. Since this is the not the desired - * result, conditionally call STI before TDCALL. - */ - testq $TDX_HCALL_ISSUE_STI, %rsi - jz .Lskip_sti - sti -.Lskip_sti: tdcall /* - * RAX==0 indicates a failure of the TDVMCALL mechanism itself and that + * RAX!=0 indicates a failure of the TDVMCALL mechanism itself and that * something has gone horribly wrong with the TDX module. * * The return status of the hypercall operation is in a separate @@ -165,30 +173,46 @@ SYM_FUNC_START(__tdx_hypercall) testq %rax, %rax jne .Lpanic - /* TDVMCALL leaf return code is in R10 */ - movq %r10, %rax + pop %rax /* Copy hypercall result registers to arg struct if needed */ - testq $TDX_HCALL_HAS_OUTPUT, %rsi + testq $TDX_HCALL_HAS_OUTPUT, (%rsp) jz .Lout - movq %r10, TDX_HYPERCALL_r10(%rdi) - movq %r11, TDX_HYPERCALL_r11(%rdi) - movq %r12, TDX_HYPERCALL_r12(%rdi) - movq %r13, TDX_HYPERCALL_r13(%rdi) - movq %r14, TDX_HYPERCALL_r14(%rdi) - movq %r15, TDX_HYPERCALL_r15(%rdi) + movq %r8, TDX_HYPERCALL_r8(%rax) + movq %r9, TDX_HYPERCALL_r9(%rax) + movq %r10, TDX_HYPERCALL_r10(%rax) + movq %r11, TDX_HYPERCALL_r11(%rax) + movq %r12, TDX_HYPERCALL_r12(%rax) + movq %r13, TDX_HYPERCALL_r13(%rax) + movq %r14, TDX_HYPERCALL_r14(%rax) + movq %r15, TDX_HYPERCALL_r15(%rax) + movq %rdi, TDX_HYPERCALL_rdi(%rax) + movq %rsi, TDX_HYPERCALL_rsi(%rax) + movq %rbx, TDX_HYPERCALL_rbx(%rax) + movq %rdx, TDX_HYPERCALL_rdx(%rax) .Lout: + /* TDVMCALL leaf return code is in R10 */ + movq %r10, %rax + /* * Zero out registers exposed to the VMM to avoid speculative execution * with VMM-controlled values. This needs to include all registers - * present in TDVMCALL_EXPOSE_REGS_MASK (except R12-R15). R12-R15 - * context will be restored. + * present in TDVMCALL_EXPOSE_REGS_MASK, except RBX, and R12-R15 which + * will be restored. */ + xor %r8d, %r8d + xor %r9d, %r9d xor %r10d, %r10d xor %r11d, %r11d + xor %rdi, %rdi + xor %rdx, %rdx + + /* Remove TDX_HCALL_* flags from the stack */ + pop %rsi /* Restore callee-saved GPRs as mandated by the x86_64 ABI */ + pop %rbx pop %r12 pop %r13 pop %r14 diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 669d9e4f2901..055300e08fb3 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -19,9 +19,14 @@ #define TDX_GET_VEINFO 3 #define TDX_GET_REPORT 4 #define TDX_ACCEPT_PAGE 6 +#define TDX_WR 8 + +/* TDCS fields. To be used by TDG.VM.WR and TDG.VM.RD module calls */ +#define TDCS_NOTIFY_ENABLES 0x9100000000000010 /* TDX hypercall Leaf IDs */ #define TDVMCALL_MAP_GPA 0x10001 +#define TDVMCALL_REPORT_FATAL_ERROR 0x10003 /* MMIO direction */ #define EPT_READ 0 @@ -37,6 +42,7 @@ #define VE_GET_PORT_NUM(e) ((e) >> 16) #define VE_IS_IO_STRING(e) ((e) & BIT(4)) +#define ATTR_DEBUG BIT(0) #define ATTR_SEPT_VE_DISABLE BIT(28) /* TDX Module call error codes */ @@ -64,8 +70,9 @@ static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15) } /* Called from __tdx_hypercall() for unrecoverable failure */ -void __tdx_hypercall_failed(void) +noinstr void __tdx_hypercall_failed(void) { + instrumentation_begin(); panic("TDVMCALL failed. TDX module bug?"); } @@ -75,7 +82,7 @@ void __tdx_hypercall_failed(void) * Reusing the KVM EXIT_REASON macros makes it easier to connect the host and * guest sides of these calls. */ -static u64 hcall_func(u64 exit_reason) +static __always_inline u64 hcall_func(u64 exit_reason) { return exit_reason; } @@ -140,6 +147,41 @@ int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport) } EXPORT_SYMBOL_GPL(tdx_mcall_get_report0); +static void __noreturn tdx_panic(const char *msg) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = TDVMCALL_REPORT_FATAL_ERROR, + .r12 = 0, /* Error code: 0 is Panic */ + }; + union { + /* Define register order according to the GHCI */ + struct { u64 r14, r15, rbx, rdi, rsi, r8, r9, rdx; }; + + char str[64]; + } message; + + /* VMM assumes '\0' in byte 65, if the message took all 64 bytes */ + strncpy(message.str, msg, 64); + + args.r8 = message.r8; + args.r9 = message.r9; + args.r14 = message.r14; + args.r15 = message.r15; + args.rdi = message.rdi; + args.rsi = message.rsi; + args.rbx = message.rbx; + args.rdx = message.rdx; + + /* + * This hypercall should never return and it is not safe + * to keep the guest running. Call it forever if it + * happens to return. + */ + while (1) + __tdx_hypercall(&args, 0); +} + static void tdx_parse_tdinfo(u64 *cc_mask) { struct tdx_module_output out; @@ -171,8 +213,15 @@ static void tdx_parse_tdinfo(u64 *cc_mask) * TD-private memory. Only VMM-shared memory (MMIO) will #VE. */ td_attr = out.rdx; - if (!(td_attr & ATTR_SEPT_VE_DISABLE)) - panic("TD misconfiguration: SEPT_VE_DISABLE attibute must be set.\n"); + if (!(td_attr & ATTR_SEPT_VE_DISABLE)) { + const char *msg = "TD misconfiguration: SEPT_VE_DISABLE attribute must be set."; + + /* Relax SEPT_VE_DISABLE check for debug TD. */ + if (td_attr & ATTR_DEBUG) + pr_warn("%s\n", msg); + else + tdx_panic(msg); + } } /* @@ -220,7 +269,7 @@ static int ve_instr_len(struct ve_info *ve) } } -static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti) +static u64 __cpuidle __halt(const bool irq_disabled) { struct tdx_hypercall_args args = { .r10 = TDX_HYPERCALL_STANDARD, @@ -240,20 +289,14 @@ static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti) * can keep the vCPU in virtual HLT, even if an IRQ is * pending, without hanging/breaking the guest. */ - return __tdx_hypercall(&args, do_sti ? TDX_HCALL_ISSUE_STI : 0); + return __tdx_hypercall(&args, 0); } static int handle_halt(struct ve_info *ve) { - /* - * Since non safe halt is mainly used in CPU offlining - * and the guest will always stay in the halt state, don't - * call the STI instruction (set do_sti as false). - */ const bool irq_disabled = irqs_disabled(); - const bool do_sti = false; - if (__halt(irq_disabled, do_sti)) + if (__halt(irq_disabled)) return -EIO; return ve_instr_len(ve); @@ -261,18 +304,12 @@ static int handle_halt(struct ve_info *ve) void __cpuidle tdx_safe_halt(void) { - /* - * For do_sti=true case, __tdx_hypercall() function enables - * interrupts using the STI instruction before the TDCALL. So - * set irq_disabled as false. - */ const bool irq_disabled = false; - const bool do_sti = true; /* * Use WARN_ONCE() to report the failure. */ - if (__halt(irq_disabled, do_sti)) + if (__halt(irq_disabled)) WARN_ONCE(1, "HLT instruction emulation failed\n"); } @@ -628,6 +665,11 @@ static int virt_exception_user(struct pt_regs *regs, struct ve_info *ve) } } +static inline bool is_private_gpa(u64 gpa) +{ + return gpa == cc_mkenc(gpa); +} + /* * Handle the kernel #VE. * @@ -646,6 +688,8 @@ static int virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve) case EXIT_REASON_CPUID: return handle_cpuid(regs, ve); case EXIT_REASON_EPT_VIOLATION: + if (is_private_gpa(ve->gpa)) + panic("Unexpected EPT-violation on private memory."); return handle_mmio(regs, ve); case EXIT_REASON_IO_INSTRUCTION: return handle_io(regs, ve); @@ -812,6 +856,9 @@ void __init tdx_early_init(void) tdx_parse_tdinfo(&cc_mask); cc_set_mask(cc_mask); + /* Kernel does not use NOTIFY_ENABLES and does not need random #VEs */ + tdx_module_call(TDX_WR, 0, TDCS_NOTIFY_ENABLES, 0, -1ULL, NULL); + /* * All bits above GPA width are reserved and kernel treats shared bit * as flag, not as part of physical address. diff --git a/arch/x86/crypto/Kconfig b/arch/x86/crypto/Kconfig index 71c4c473d34b..9bbfd01cfa2f 100644 --- a/arch/x86/crypto/Kconfig +++ b/arch/x86/crypto/Kconfig @@ -304,6 +304,44 @@ config CRYPTO_ARIA_AESNI_AVX_X86_64 Processes 16 blocks in parallel. +config CRYPTO_ARIA_AESNI_AVX2_X86_64 + tristate "Ciphers: ARIA with modes: ECB, CTR (AES-NI/AVX2/GFNI)" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + select CRYPTO_SIMD + select CRYPTO_ALGAPI + select CRYPTO_ARIA + select CRYPTO_ARIA_AESNI_AVX_X86_64 + help + Length-preserving cipher: ARIA cipher algorithms + (RFC 5794) with ECB and CTR modes + + Architecture: x86_64 using: + - AES-NI (AES New Instructions) + - AVX2 (Advanced Vector Extensions) + - GFNI (Galois Field New Instructions) + + Processes 32 blocks in parallel. + +config CRYPTO_ARIA_GFNI_AVX512_X86_64 + tristate "Ciphers: ARIA with modes: ECB, CTR (AVX512/GFNI)" + depends on X86 && 64BIT && AS_AVX512 && AS_GFNI + select CRYPTO_SKCIPHER + select CRYPTO_SIMD + select CRYPTO_ALGAPI + select CRYPTO_ARIA + select CRYPTO_ARIA_AESNI_AVX_X86_64 + select CRYPTO_ARIA_AESNI_AVX2_X86_64 + help + Length-preserving cipher: ARIA cipher algorithms + (RFC 5794) with ECB and CTR modes + + Architecture: x86_64 using: + - AVX512 (Advanced Vector Extensions) + - GFNI (Galois Field New Instructions) + + Processes 64 blocks in parallel. + config CRYPTO_CHACHA20_X86_64 tristate "Ciphers: ChaCha20, XChaCha20, XChaCha12 (SSSE3/AVX2/AVX-512VL)" depends on X86 && 64BIT diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 3e7a329235bd..9aa46093c91b 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -103,6 +103,12 @@ sm4-aesni-avx2-x86_64-y := sm4-aesni-avx2-asm_64.o sm4_aesni_avx2_glue.o obj-$(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64) += aria-aesni-avx-x86_64.o aria-aesni-avx-x86_64-y := aria-aesni-avx-asm_64.o aria_aesni_avx_glue.o +obj-$(CONFIG_CRYPTO_ARIA_AESNI_AVX2_X86_64) += aria-aesni-avx2-x86_64.o +aria-aesni-avx2-x86_64-y := aria-aesni-avx2-asm_64.o aria_aesni_avx2_glue.o + +obj-$(CONFIG_CRYPTO_ARIA_GFNI_AVX512_X86_64) += aria-gfni-avx512-x86_64.o +aria-gfni-avx512-x86_64-y := aria-gfni-avx512-asm_64.o aria_gfni_avx512_glue.o + quiet_cmd_perlasm = PERLASM $@ cmd_perlasm = $(PERL) $< > $@ $(obj)/%.S: $(src)/%.pl FORCE diff --git a/arch/x86/crypto/aria-aesni-avx-asm_64.S b/arch/x86/crypto/aria-aesni-avx-asm_64.S index 03ae4cd1d976..9243f6289d34 100644 --- a/arch/x86/crypto/aria-aesni-avx-asm_64.S +++ b/arch/x86/crypto/aria-aesni-avx-asm_64.S @@ -8,13 +8,9 @@ #include <linux/linkage.h> #include <linux/cfi_types.h> +#include <asm/asm-offsets.h> #include <asm/frame.h> -/* struct aria_ctx: */ -#define enc_key 0 -#define dec_key 272 -#define rounds 544 - /* register macros */ #define CTX %rdi @@ -271,34 +267,44 @@ #define aria_ark_8way(x0, x1, x2, x3, \ x4, x5, x6, x7, \ - t0, rk, idx, round) \ + t0, t1, t2, rk, \ + idx, round) \ /* AddRoundKey */ \ - vpbroadcastb ((round * 16) + idx + 3)(rk), t0; \ - vpxor t0, x0, x0; \ - vpbroadcastb ((round * 16) + idx + 2)(rk), t0; \ - vpxor t0, x1, x1; \ - vpbroadcastb ((round * 16) + idx + 1)(rk), t0; \ - vpxor t0, x2, x2; \ - vpbroadcastb ((round * 16) + idx + 0)(rk), t0; \ - vpxor t0, x3, x3; \ - vpbroadcastb ((round * 16) + idx + 7)(rk), t0; \ - vpxor t0, x4, x4; \ - vpbroadcastb ((round * 16) + idx + 6)(rk), t0; \ - vpxor t0, x5, x5; \ - vpbroadcastb ((round * 16) + idx + 5)(rk), t0; \ - vpxor t0, x6, x6; \ - vpbroadcastb ((round * 16) + idx + 4)(rk), t0; \ - vpxor t0, x7, x7; - + vbroadcastss ((round * 16) + idx + 0)(rk), t0; \ + vpsrld $24, t0, t2; \ + vpshufb t1, t2, t2; \ + vpxor t2, x0, x0; \ + vpsrld $16, t0, t2; \ + vpshufb t1, t2, t2; \ + vpxor t2, x1, x1; \ + vpsrld $8, t0, t2; \ + vpshufb t1, t2, t2; \ + vpxor t2, x2, x2; \ + vpshufb t1, t0, t2; \ + vpxor t2, x3, x3; \ + vbroadcastss ((round * 16) + idx + 4)(rk), t0; \ + vpsrld $24, t0, t2; \ + vpshufb t1, t2, t2; \ + vpxor t2, x4, x4; \ + vpsrld $16, t0, t2; \ + vpshufb t1, t2, t2; \ + vpxor t2, x5, x5; \ + vpsrld $8, t0, t2; \ + vpshufb t1, t2, t2; \ + vpxor t2, x6, x6; \ + vpshufb t1, t0, t2; \ + vpxor t2, x7, x7; + +#ifdef CONFIG_AS_GFNI #define aria_sbox_8way_gfni(x0, x1, x2, x3, \ x4, x5, x6, x7, \ t0, t1, t2, t3, \ t4, t5, t6, t7) \ - vpbroadcastq .Ltf_s2_bitmatrix, t0; \ - vpbroadcastq .Ltf_inv_bitmatrix, t1; \ - vpbroadcastq .Ltf_id_bitmatrix, t2; \ - vpbroadcastq .Ltf_aff_bitmatrix, t3; \ - vpbroadcastq .Ltf_x2_bitmatrix, t4; \ + vmovdqa .Ltf_s2_bitmatrix, t0; \ + vmovdqa .Ltf_inv_bitmatrix, t1; \ + vmovdqa .Ltf_id_bitmatrix, t2; \ + vmovdqa .Ltf_aff_bitmatrix, t3; \ + vmovdqa .Ltf_x2_bitmatrix, t4; \ vgf2p8affineinvqb $(tf_s2_const), t0, x1, x1; \ vgf2p8affineinvqb $(tf_s2_const), t0, x5, x5; \ vgf2p8affineqb $(tf_inv_const), t1, x2, x2; \ @@ -312,14 +318,15 @@ vgf2p8affineinvqb $0, t2, x3, x3; \ vgf2p8affineinvqb $0, t2, x7, x7 +#endif /* CONFIG_AS_GFNI */ + #define aria_sbox_8way(x0, x1, x2, x3, \ x4, x5, x6, x7, \ t0, t1, t2, t3, \ t4, t5, t6, t7) \ - vpxor t7, t7, t7; \ vmovdqa .Linv_shift_row, t0; \ vmovdqa .Lshift_row, t1; \ - vpbroadcastd .L0f0f0f0f, t6; \ + vbroadcastss .L0f0f0f0f, t6; \ vmovdqa .Ltf_lo__inv_aff__and__s2, t2; \ vmovdqa .Ltf_hi__inv_aff__and__s2, t3; \ vmovdqa .Ltf_lo__x2__and__fwd_aff, t4; \ @@ -414,8 +421,9 @@ y0, y1, y2, y3, \ y4, y5, y6, y7, \ mem_tmp, rk, round) \ + vpxor y7, y7, y7; \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 8, round); \ + y0, y7, y2, rk, 8, round); \ \ aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \ y0, y1, y2, y3, y4, y5, y6, y7); \ @@ -430,7 +438,7 @@ x4, x5, x6, x7, \ mem_tmp, 0); \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 0, round); \ + y0, y7, y2, rk, 0, round); \ \ aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \ y0, y1, y2, y3, y4, y5, y6, y7); \ @@ -468,8 +476,9 @@ y0, y1, y2, y3, \ y4, y5, y6, y7, \ mem_tmp, rk, round) \ + vpxor y7, y7, y7; \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 8, round); \ + y0, y7, y2, rk, 8, round); \ \ aria_sbox_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ y0, y1, y2, y3, y4, y5, y6, y7); \ @@ -484,7 +493,7 @@ x4, x5, x6, x7, \ mem_tmp, 0); \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 0, round); \ + y0, y7, y2, rk, 0, round); \ \ aria_sbox_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ y0, y1, y2, y3, y4, y5, y6, y7); \ @@ -522,14 +531,15 @@ y0, y1, y2, y3, \ y4, y5, y6, y7, \ mem_tmp, rk, round, last_round) \ + vpxor y7, y7, y7; \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 8, round); \ + y0, y7, y2, rk, 8, round); \ \ aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \ y0, y1, y2, y3, y4, y5, y6, y7); \ \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 8, last_round); \ + y0, y7, y2, rk, 8, last_round); \ \ aria_store_state_8way(x0, x1, x2, x3, \ x4, x5, x6, x7, \ @@ -539,25 +549,27 @@ x4, x5, x6, x7, \ mem_tmp, 0); \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 0, round); \ + y0, y7, y2, rk, 0, round); \ \ aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \ y0, y1, y2, y3, y4, y5, y6, y7); \ \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 0, last_round); \ + y0, y7, y2, rk, 0, last_round); \ \ aria_load_state_8way(y0, y1, y2, y3, \ y4, y5, y6, y7, \ mem_tmp, 8); +#ifdef CONFIG_AS_GFNI #define aria_fe_gfni(x0, x1, x2, x3, \ x4, x5, x6, x7, \ y0, y1, y2, y3, \ y4, y5, y6, y7, \ mem_tmp, rk, round) \ + vpxor y7, y7, y7; \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 8, round); \ + y0, y7, y2, rk, 8, round); \ \ aria_sbox_8way_gfni(x2, x3, x0, x1, \ x6, x7, x4, x5, \ @@ -574,7 +586,7 @@ x4, x5, x6, x7, \ mem_tmp, 0); \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 0, round); \ + y0, y7, y2, rk, 0, round); \ \ aria_sbox_8way_gfni(x2, x3, x0, x1, \ x6, x7, x4, x5, \ @@ -614,8 +626,9 @@ y0, y1, y2, y3, \ y4, y5, y6, y7, \ mem_tmp, rk, round) \ + vpxor y7, y7, y7; \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 8, round); \ + y0, y7, y2, rk, 8, round); \ \ aria_sbox_8way_gfni(x0, x1, x2, x3, \ x4, x5, x6, x7, \ @@ -632,7 +645,7 @@ x4, x5, x6, x7, \ mem_tmp, 0); \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 0, round); \ + y0, y7, y2, rk, 0, round); \ \ aria_sbox_8way_gfni(x0, x1, x2, x3, \ x4, x5, x6, x7, \ @@ -672,8 +685,9 @@ y0, y1, y2, y3, \ y4, y5, y6, y7, \ mem_tmp, rk, round, last_round) \ + vpxor y7, y7, y7; \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 8, round); \ + y0, y7, y2, rk, 8, round); \ \ aria_sbox_8way_gfni(x2, x3, x0, x1, \ x6, x7, x4, x5, \ @@ -681,7 +695,7 @@ y4, y5, y6, y7); \ \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 8, last_round); \ + y0, y7, y2, rk, 8, last_round); \ \ aria_store_state_8way(x0, x1, x2, x3, \ x4, x5, x6, x7, \ @@ -691,7 +705,7 @@ x4, x5, x6, x7, \ mem_tmp, 0); \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 0, round); \ + y0, y7, y2, rk, 0, round); \ \ aria_sbox_8way_gfni(x2, x3, x0, x1, \ x6, x7, x4, x5, \ @@ -699,12 +713,14 @@ y4, y5, y6, y7); \ \ aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ - y0, rk, 0, last_round); \ + y0, y7, y2, rk, 0, last_round); \ \ aria_load_state_8way(y0, y1, y2, y3, \ y4, y5, y6, y7, \ mem_tmp, 8); +#endif /* CONFIG_AS_GFNI */ + /* NB: section is mergeable, all elements must be aligned 16-byte blocks */ .section .rodata.cst16, "aM", @progbits, 16 .align 16 @@ -756,6 +772,7 @@ .Ltf_hi__x2__and__fwd_aff: .octa 0x3F893781E95FE1576CDA64D2BA0CB204 +#ifdef CONFIG_AS_GFNI .section .rodata.cst8, "aM", @progbits, 8 .align 8 /* AES affine: */ @@ -769,6 +786,14 @@ BV8(0, 1, 1, 1, 1, 1, 0, 0), BV8(0, 0, 1, 1, 1, 1, 1, 0), BV8(0, 0, 0, 1, 1, 1, 1, 1)) + .quad BM8X8(BV8(1, 0, 0, 0, 1, 1, 1, 1), + BV8(1, 1, 0, 0, 0, 1, 1, 1), + BV8(1, 1, 1, 0, 0, 0, 1, 1), + BV8(1, 1, 1, 1, 0, 0, 0, 1), + BV8(1, 1, 1, 1, 1, 0, 0, 0), + BV8(0, 1, 1, 1, 1, 1, 0, 0), + BV8(0, 0, 1, 1, 1, 1, 1, 0), + BV8(0, 0, 0, 1, 1, 1, 1, 1)) /* AES inverse affine: */ #define tf_inv_const BV8(1, 0, 1, 0, 0, 0, 0, 0) @@ -781,6 +806,14 @@ BV8(0, 0, 1, 0, 1, 0, 0, 1), BV8(1, 0, 0, 1, 0, 1, 0, 0), BV8(0, 1, 0, 0, 1, 0, 1, 0)) + .quad BM8X8(BV8(0, 0, 1, 0, 0, 1, 0, 1), + BV8(1, 0, 0, 1, 0, 0, 1, 0), + BV8(0, 1, 0, 0, 1, 0, 0, 1), + BV8(1, 0, 1, 0, 0, 1, 0, 0), + BV8(0, 1, 0, 1, 0, 0, 1, 0), + BV8(0, 0, 1, 0, 1, 0, 0, 1), + BV8(1, 0, 0, 1, 0, 1, 0, 0), + BV8(0, 1, 0, 0, 1, 0, 1, 0)) /* S2: */ #define tf_s2_const BV8(0, 1, 0, 0, 0, 1, 1, 1) @@ -793,6 +826,14 @@ BV8(1, 1, 0, 0, 1, 1, 1, 0), BV8(0, 1, 1, 0, 0, 0, 1, 1), BV8(1, 1, 1, 1, 0, 1, 1, 0)) + .quad BM8X8(BV8(0, 1, 0, 1, 0, 1, 1, 1), + BV8(0, 0, 1, 1, 1, 1, 1, 1), + BV8(1, 1, 1, 0, 1, 1, 0, 1), + BV8(1, 1, 0, 0, 0, 0, 1, 1), + BV8(0, 1, 0, 0, 0, 0, 1, 1), + BV8(1, 1, 0, 0, 1, 1, 1, 0), + BV8(0, 1, 1, 0, 0, 0, 1, 1), + BV8(1, 1, 1, 1, 0, 1, 1, 0)) /* X2: */ #define tf_x2_const BV8(0, 0, 1, 1, 0, 1, 0, 0) @@ -805,6 +846,14 @@ BV8(0, 1, 1, 0, 1, 0, 1, 1), BV8(1, 0, 1, 1, 1, 1, 0, 1), BV8(1, 0, 0, 1, 0, 0, 1, 1)) + .quad BM8X8(BV8(0, 0, 0, 1, 1, 0, 0, 0), + BV8(0, 0, 1, 0, 0, 1, 1, 0), + BV8(0, 0, 0, 0, 1, 0, 1, 0), + BV8(1, 1, 1, 0, 0, 0, 1, 1), + BV8(1, 1, 1, 0, 1, 1, 0, 0), + BV8(0, 1, 1, 0, 1, 0, 1, 1), + BV8(1, 0, 1, 1, 1, 1, 0, 1), + BV8(1, 0, 0, 1, 0, 0, 1, 1)) /* Identity matrix: */ .Ltf_id_bitmatrix: @@ -816,6 +865,15 @@ BV8(0, 0, 0, 0, 0, 1, 0, 0), BV8(0, 0, 0, 0, 0, 0, 1, 0), BV8(0, 0, 0, 0, 0, 0, 0, 1)) + .quad BM8X8(BV8(1, 0, 0, 0, 0, 0, 0, 0), + BV8(0, 1, 0, 0, 0, 0, 0, 0), + BV8(0, 0, 1, 0, 0, 0, 0, 0), + BV8(0, 0, 0, 1, 0, 0, 0, 0), + BV8(0, 0, 0, 0, 1, 0, 0, 0), + BV8(0, 0, 0, 0, 0, 1, 0, 0), + BV8(0, 0, 0, 0, 0, 0, 1, 0), + BV8(0, 0, 0, 0, 0, 0, 0, 1)) +#endif /* CONFIG_AS_GFNI */ /* 4-bit mask */ .section .rodata.cst4.L0f0f0f0f, "aM", @progbits, 4 @@ -874,7 +932,7 @@ SYM_FUNC_START_LOCAL(__aria_aesni_avx_crypt_16way) aria_fo(%xmm9, %xmm8, %xmm11, %xmm10, %xmm12, %xmm13, %xmm14, %xmm15, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %rax, %r9, 10); - cmpl $12, rounds(CTX); + cmpl $12, ARIA_CTX_rounds(CTX); jne .Laria_192; aria_ff(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, @@ -887,7 +945,7 @@ SYM_FUNC_START_LOCAL(__aria_aesni_avx_crypt_16way) aria_fo(%xmm9, %xmm8, %xmm11, %xmm10, %xmm12, %xmm13, %xmm14, %xmm15, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %rax, %r9, 12); - cmpl $14, rounds(CTX); + cmpl $14, ARIA_CTX_rounds(CTX); jne .Laria_256; aria_ff(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, @@ -923,7 +981,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx_encrypt_16way) FRAME_BEGIN - leaq enc_key(CTX), %r9; + leaq ARIA_CTX_enc_key(CTX), %r9; inpack16_pre(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, @@ -948,7 +1006,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx_decrypt_16way) FRAME_BEGIN - leaq dec_key(CTX), %r9; + leaq ARIA_CTX_dec_key(CTX), %r9; inpack16_pre(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, @@ -1056,7 +1114,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx_ctr_crypt_16way) leaq (%rdx), %r11; leaq (%rcx), %rsi; leaq (%rcx), %rdx; - leaq enc_key(CTX), %r9; + leaq ARIA_CTX_enc_key(CTX), %r9; call __aria_aesni_avx_crypt_16way; @@ -1084,6 +1142,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx_ctr_crypt_16way) RET; SYM_FUNC_END(aria_aesni_avx_ctr_crypt_16way) +#ifdef CONFIG_AS_GFNI SYM_FUNC_START_LOCAL(__aria_aesni_avx_gfni_crypt_16way) /* input: * %r9: rk @@ -1157,7 +1216,7 @@ SYM_FUNC_START_LOCAL(__aria_aesni_avx_gfni_crypt_16way) %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %rax, %r9, 10); - cmpl $12, rounds(CTX); + cmpl $12, ARIA_CTX_rounds(CTX); jne .Laria_gfni_192; aria_ff_gfni(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, @@ -1174,7 +1233,7 @@ SYM_FUNC_START_LOCAL(__aria_aesni_avx_gfni_crypt_16way) %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %rax, %r9, 12); - cmpl $14, rounds(CTX); + cmpl $14, ARIA_CTX_rounds(CTX); jne .Laria_gfni_256; aria_ff_gfni(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, @@ -1218,7 +1277,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx_gfni_encrypt_16way) FRAME_BEGIN - leaq enc_key(CTX), %r9; + leaq ARIA_CTX_enc_key(CTX), %r9; inpack16_pre(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, @@ -1243,7 +1302,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx_gfni_decrypt_16way) FRAME_BEGIN - leaq dec_key(CTX), %r9; + leaq ARIA_CTX_dec_key(CTX), %r9; inpack16_pre(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, @@ -1275,7 +1334,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx_gfni_ctr_crypt_16way) leaq (%rdx), %r11; leaq (%rcx), %rsi; leaq (%rcx), %rdx; - leaq enc_key(CTX), %r9; + leaq ARIA_CTX_enc_key(CTX), %r9; call __aria_aesni_avx_gfni_crypt_16way; @@ -1302,3 +1361,4 @@ SYM_TYPED_FUNC_START(aria_aesni_avx_gfni_ctr_crypt_16way) FRAME_END RET; SYM_FUNC_END(aria_aesni_avx_gfni_ctr_crypt_16way) +#endif /* CONFIG_AS_GFNI */ diff --git a/arch/x86/crypto/aria-aesni-avx2-asm_64.S b/arch/x86/crypto/aria-aesni-avx2-asm_64.S new file mode 100644 index 000000000000..82a14b4ad920 --- /dev/null +++ b/arch/x86/crypto/aria-aesni-avx2-asm_64.S @@ -0,0 +1,1441 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * ARIA Cipher 32-way parallel algorithm (AVX2) + * + * Copyright (c) 2022 Taehee Yoo <ap420073@gmail.com> + * + */ + +#include <linux/linkage.h> +#include <asm/frame.h> +#include <asm/asm-offsets.h> +#include <linux/cfi_types.h> + +/* register macros */ +#define CTX %rdi + +#define ymm0_x xmm0 +#define ymm1_x xmm1 +#define ymm2_x xmm2 +#define ymm3_x xmm3 +#define ymm4_x xmm4 +#define ymm5_x xmm5 +#define ymm6_x xmm6 +#define ymm7_x xmm7 +#define ymm8_x xmm8 +#define ymm9_x xmm9 +#define ymm10_x xmm10 +#define ymm11_x xmm11 +#define ymm12_x xmm12 +#define ymm13_x xmm13 +#define ymm14_x xmm14 +#define ymm15_x xmm15 + +#define BV8(a0, a1, a2, a3, a4, a5, a6, a7) \ + ( (((a0) & 1) << 0) | \ + (((a1) & 1) << 1) | \ + (((a2) & 1) << 2) | \ + (((a3) & 1) << 3) | \ + (((a4) & 1) << 4) | \ + (((a5) & 1) << 5) | \ + (((a6) & 1) << 6) | \ + (((a7) & 1) << 7) ) + +#define BM8X8(l0, l1, l2, l3, l4, l5, l6, l7) \ + ( ((l7) << (0 * 8)) | \ + ((l6) << (1 * 8)) | \ + ((l5) << (2 * 8)) | \ + ((l4) << (3 * 8)) | \ + ((l3) << (4 * 8)) | \ + ((l2) << (5 * 8)) | \ + ((l1) << (6 * 8)) | \ + ((l0) << (7 * 8)) ) + +#define inc_le128(x, minus_one, tmp) \ + vpcmpeqq minus_one, x, tmp; \ + vpsubq minus_one, x, x; \ + vpslldq $8, tmp, tmp; \ + vpsubq tmp, x, x; + +#define filter_8bit(x, lo_t, hi_t, mask4bit, tmp0) \ + vpand x, mask4bit, tmp0; \ + vpandn x, mask4bit, x; \ + vpsrld $4, x, x; \ + \ + vpshufb tmp0, lo_t, tmp0; \ + vpshufb x, hi_t, x; \ + vpxor tmp0, x, x; + +#define transpose_4x4(x0, x1, x2, x3, t1, t2) \ + vpunpckhdq x1, x0, t2; \ + vpunpckldq x1, x0, x0; \ + \ + vpunpckldq x3, x2, t1; \ + vpunpckhdq x3, x2, x2; \ + \ + vpunpckhqdq t1, x0, x1; \ + vpunpcklqdq t1, x0, x0; \ + \ + vpunpckhqdq x2, t2, x3; \ + vpunpcklqdq x2, t2, x2; + +#define byteslice_16x16b(a0, b0, c0, d0, \ + a1, b1, c1, d1, \ + a2, b2, c2, d2, \ + a3, b3, c3, d3, \ + st0, st1) \ + vmovdqu d2, st0; \ + vmovdqu d3, st1; \ + transpose_4x4(a0, a1, a2, a3, d2, d3); \ + transpose_4x4(b0, b1, b2, b3, d2, d3); \ + vmovdqu st0, d2; \ + vmovdqu st1, d3; \ + \ + vmovdqu a0, st0; \ + vmovdqu a1, st1; \ + transpose_4x4(c0, c1, c2, c3, a0, a1); \ + transpose_4x4(d0, d1, d2, d3, a0, a1); \ + \ + vbroadcasti128 .Lshufb_16x16b, a0; \ + vmovdqu st1, a1; \ + vpshufb a0, a2, a2; \ + vpshufb a0, a3, a3; \ + vpshufb a0, b0, b0; \ + vpshufb a0, b1, b1; \ + vpshufb a0, b2, b2; \ + vpshufb a0, b3, b3; \ + vpshufb a0, a1, a1; \ + vpshufb a0, c0, c0; \ + vpshufb a0, c1, c1; \ + vpshufb a0, c2, c2; \ + vpshufb a0, c3, c3; \ + vpshufb a0, d0, d0; \ + vpshufb a0, d1, d1; \ + vpshufb a0, d2, d2; \ + vpshufb a0, d3, d3; \ + vmovdqu d3, st1; \ + vmovdqu st0, d3; \ + vpshufb a0, d3, a0; \ + vmovdqu d2, st0; \ + \ + transpose_4x4(a0, b0, c0, d0, d2, d3); \ + transpose_4x4(a1, b1, c1, d1, d2, d3); \ + vmovdqu st0, d2; \ + vmovdqu st1, d3; \ + \ + vmovdqu b0, st0; \ + vmovdqu b1, st1; \ + transpose_4x4(a2, b2, c2, d2, b0, b1); \ + transpose_4x4(a3, b3, c3, d3, b0, b1); \ + vmovdqu st0, b0; \ + vmovdqu st1, b1; \ + /* does not adjust output bytes inside vectors */ + +#define debyteslice_16x16b(a0, b0, c0, d0, \ + a1, b1, c1, d1, \ + a2, b2, c2, d2, \ + a3, b3, c3, d3, \ + st0, st1) \ + vmovdqu d2, st0; \ + vmovdqu d3, st1; \ + transpose_4x4(a0, a1, a2, a3, d2, d3); \ + transpose_4x4(b0, b1, b2, b3, d2, d3); \ + vmovdqu st0, d2; \ + vmovdqu st1, d3; \ + \ + vmovdqu a0, st0; \ + vmovdqu a1, st1; \ + transpose_4x4(c0, c1, c2, c3, a0, a1); \ + transpose_4x4(d0, d1, d2, d3, a0, a1); \ + \ + vbroadcasti128 .Lshufb_16x16b, a0; \ + vmovdqu st1, a1; \ + vpshufb a0, a2, a2; \ + vpshufb a0, a3, a3; \ + vpshufb a0, b0, b0; \ + vpshufb a0, b1, b1; \ + vpshufb a0, b2, b2; \ + vpshufb a0, b3, b3; \ + vpshufb a0, a1, a1; \ + vpshufb a0, c0, c0; \ + vpshufb a0, c1, c1; \ + vpshufb a0, c2, c2; \ + vpshufb a0, c3, c3; \ + vpshufb a0, d0, d0; \ + vpshufb a0, d1, d1; \ + vpshufb a0, d2, d2; \ + vpshufb a0, d3, d3; \ + vmovdqu d3, st1; \ + vmovdqu st0, d3; \ + vpshufb a0, d3, a0; \ + vmovdqu d2, st0; \ + \ + transpose_4x4(c0, d0, a0, b0, d2, d3); \ + transpose_4x4(c1, d1, a1, b1, d2, d3); \ + vmovdqu st0, d2; \ + vmovdqu st1, d3; \ + \ + vmovdqu b0, st0; \ + vmovdqu b1, st1; \ + transpose_4x4(c2, d2, a2, b2, b0, b1); \ + transpose_4x4(c3, d3, a3, b3, b0, b1); \ + vmovdqu st0, b0; \ + vmovdqu st1, b1; \ + /* does not adjust output bytes inside vectors */ + +/* load blocks to registers and apply pre-whitening */ +#define inpack16_pre(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + rio) \ + vmovdqu (0 * 32)(rio), x0; \ + vmovdqu (1 * 32)(rio), x1; \ + vmovdqu (2 * 32)(rio), x2; \ + vmovdqu (3 * 32)(rio), x3; \ + vmovdqu (4 * 32)(rio), x4; \ + vmovdqu (5 * 32)(rio), x5; \ + vmovdqu (6 * 32)(rio), x6; \ + vmovdqu (7 * 32)(rio), x7; \ + vmovdqu (8 * 32)(rio), y0; \ + vmovdqu (9 * 32)(rio), y1; \ + vmovdqu (10 * 32)(rio), y2; \ + vmovdqu (11 * 32)(rio), y3; \ + vmovdqu (12 * 32)(rio), y4; \ + vmovdqu (13 * 32)(rio), y5; \ + vmovdqu (14 * 32)(rio), y6; \ + vmovdqu (15 * 32)(rio), y7; + +/* byteslice pre-whitened blocks and store to temporary memory */ +#define inpack16_post(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_ab, mem_cd) \ + byteslice_16x16b(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + (mem_ab), (mem_cd)); \ + \ + vmovdqu x0, 0 * 32(mem_ab); \ + vmovdqu x1, 1 * 32(mem_ab); \ + vmovdqu x2, 2 * 32(mem_ab); \ + vmovdqu x3, 3 * 32(mem_ab); \ + vmovdqu x4, 4 * 32(mem_ab); \ + vmovdqu x5, 5 * 32(mem_ab); \ + vmovdqu x6, 6 * 32(mem_ab); \ + vmovdqu x7, 7 * 32(mem_ab); \ + vmovdqu y0, 0 * 32(mem_cd); \ + vmovdqu y1, 1 * 32(mem_cd); \ + vmovdqu y2, 2 * 32(mem_cd); \ + vmovdqu y3, 3 * 32(mem_cd); \ + vmovdqu y4, 4 * 32(mem_cd); \ + vmovdqu y5, 5 * 32(mem_cd); \ + vmovdqu y6, 6 * 32(mem_cd); \ + vmovdqu y7, 7 * 32(mem_cd); + +#define write_output(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem) \ + vmovdqu x0, 0 * 32(mem); \ + vmovdqu x1, 1 * 32(mem); \ + vmovdqu x2, 2 * 32(mem); \ + vmovdqu x3, 3 * 32(mem); \ + vmovdqu x4, 4 * 32(mem); \ + vmovdqu x5, 5 * 32(mem); \ + vmovdqu x6, 6 * 32(mem); \ + vmovdqu x7, 7 * 32(mem); \ + vmovdqu y0, 8 * 32(mem); \ + vmovdqu y1, 9 * 32(mem); \ + vmovdqu y2, 10 * 32(mem); \ + vmovdqu y3, 11 * 32(mem); \ + vmovdqu y4, 12 * 32(mem); \ + vmovdqu y5, 13 * 32(mem); \ + vmovdqu y6, 14 * 32(mem); \ + vmovdqu y7, 15 * 32(mem); \ + +#define aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, idx) \ + vmovdqu x0, ((idx + 0) * 32)(mem_tmp); \ + vmovdqu x1, ((idx + 1) * 32)(mem_tmp); \ + vmovdqu x2, ((idx + 2) * 32)(mem_tmp); \ + vmovdqu x3, ((idx + 3) * 32)(mem_tmp); \ + vmovdqu x4, ((idx + 4) * 32)(mem_tmp); \ + vmovdqu x5, ((idx + 5) * 32)(mem_tmp); \ + vmovdqu x6, ((idx + 6) * 32)(mem_tmp); \ + vmovdqu x7, ((idx + 7) * 32)(mem_tmp); + +#define aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, idx) \ + vmovdqu ((idx + 0) * 32)(mem_tmp), x0; \ + vmovdqu ((idx + 1) * 32)(mem_tmp), x1; \ + vmovdqu ((idx + 2) * 32)(mem_tmp), x2; \ + vmovdqu ((idx + 3) * 32)(mem_tmp), x3; \ + vmovdqu ((idx + 4) * 32)(mem_tmp), x4; \ + vmovdqu ((idx + 5) * 32)(mem_tmp), x5; \ + vmovdqu ((idx + 6) * 32)(mem_tmp), x6; \ + vmovdqu ((idx + 7) * 32)(mem_tmp), x7; + +#define aria_ark_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + t0, rk, idx, round) \ + /* AddRoundKey */ \ + vpbroadcastb ((round * 16) + idx + 3)(rk), t0; \ + vpxor t0, x0, x0; \ + vpbroadcastb ((round * 16) + idx + 2)(rk), t0; \ + vpxor t0, x1, x1; \ + vpbroadcastb ((round * 16) + idx + 1)(rk), t0; \ + vpxor t0, x2, x2; \ + vpbroadcastb ((round * 16) + idx + 0)(rk), t0; \ + vpxor t0, x3, x3; \ + vpbroadcastb ((round * 16) + idx + 7)(rk), t0; \ + vpxor t0, x4, x4; \ + vpbroadcastb ((round * 16) + idx + 6)(rk), t0; \ + vpxor t0, x5, x5; \ + vpbroadcastb ((round * 16) + idx + 5)(rk), t0; \ + vpxor t0, x6, x6; \ + vpbroadcastb ((round * 16) + idx + 4)(rk), t0; \ + vpxor t0, x7, x7; + +#ifdef CONFIG_AS_GFNI +#define aria_sbox_8way_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + t0, t1, t2, t3, \ + t4, t5, t6, t7) \ + vpbroadcastq .Ltf_s2_bitmatrix, t0; \ + vpbroadcastq .Ltf_inv_bitmatrix, t1; \ + vpbroadcastq .Ltf_id_bitmatrix, t2; \ + vpbroadcastq .Ltf_aff_bitmatrix, t3; \ + vpbroadcastq .Ltf_x2_bitmatrix, t4; \ + vgf2p8affineinvqb $(tf_s2_const), t0, x1, x1; \ + vgf2p8affineinvqb $(tf_s2_const), t0, x5, x5; \ + vgf2p8affineqb $(tf_inv_const), t1, x2, x2; \ + vgf2p8affineqb $(tf_inv_const), t1, x6, x6; \ + vgf2p8affineinvqb $0, t2, x2, x2; \ + vgf2p8affineinvqb $0, t2, x6, x6; \ + vgf2p8affineinvqb $(tf_aff_const), t3, x0, x0; \ + vgf2p8affineinvqb $(tf_aff_const), t3, x4, x4; \ + vgf2p8affineqb $(tf_x2_const), t4, x3, x3; \ + vgf2p8affineqb $(tf_x2_const), t4, x7, x7; \ + vgf2p8affineinvqb $0, t2, x3, x3; \ + vgf2p8affineinvqb $0, t2, x7, x7 + +#endif /* CONFIG_AS_GFNI */ +#define aria_sbox_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + t0, t1, t2, t3, \ + t4, t5, t6, t7) \ + vpxor t7, t7, t7; \ + vpxor t6, t6, t6; \ + vbroadcasti128 .Linv_shift_row, t0; \ + vbroadcasti128 .Lshift_row, t1; \ + vbroadcasti128 .Ltf_lo__inv_aff__and__s2, t2; \ + vbroadcasti128 .Ltf_hi__inv_aff__and__s2, t3; \ + vbroadcasti128 .Ltf_lo__x2__and__fwd_aff, t4; \ + vbroadcasti128 .Ltf_hi__x2__and__fwd_aff, t5; \ + \ + vextracti128 $1, x0, t6##_x; \ + vaesenclast t7##_x, x0##_x, x0##_x; \ + vaesenclast t7##_x, t6##_x, t6##_x; \ + vinserti128 $1, t6##_x, x0, x0; \ + \ + vextracti128 $1, x4, t6##_x; \ + vaesenclast t7##_x, x4##_x, x4##_x; \ + vaesenclast t7##_x, t6##_x, t6##_x; \ + vinserti128 $1, t6##_x, x4, x4; \ + \ + vextracti128 $1, x1, t6##_x; \ + vaesenclast t7##_x, x1##_x, x1##_x; \ + vaesenclast t7##_x, t6##_x, t6##_x; \ + vinserti128 $1, t6##_x, x1, x1; \ + \ + vextracti128 $1, x5, t6##_x; \ + vaesenclast t7##_x, x5##_x, x5##_x; \ + vaesenclast t7##_x, t6##_x, t6##_x; \ + vinserti128 $1, t6##_x, x5, x5; \ + \ + vextracti128 $1, x2, t6##_x; \ + vaesdeclast t7##_x, x2##_x, x2##_x; \ + vaesdeclast t7##_x, t6##_x, t6##_x; \ + vinserti128 $1, t6##_x, x2, x2; \ + \ + vextracti128 $1, x6, t6##_x; \ + vaesdeclast t7##_x, x6##_x, x6##_x; \ + vaesdeclast t7##_x, t6##_x, t6##_x; \ + vinserti128 $1, t6##_x, x6, x6; \ + \ + vpbroadcastd .L0f0f0f0f, t6; \ + \ + /* AES inverse shift rows */ \ + vpshufb t0, x0, x0; \ + vpshufb t0, x4, x4; \ + vpshufb t0, x1, x1; \ + vpshufb t0, x5, x5; \ + vpshufb t1, x3, x3; \ + vpshufb t1, x7, x7; \ + vpshufb t1, x2, x2; \ + vpshufb t1, x6, x6; \ + \ + /* affine transformation for S2 */ \ + filter_8bit(x1, t2, t3, t6, t0); \ + /* affine transformation for S2 */ \ + filter_8bit(x5, t2, t3, t6, t0); \ + \ + /* affine transformation for X2 */ \ + filter_8bit(x3, t4, t5, t6, t0); \ + /* affine transformation for X2 */ \ + filter_8bit(x7, t4, t5, t6, t0); \ + \ + vpxor t6, t6, t6; \ + vextracti128 $1, x3, t6##_x; \ + vaesdeclast t7##_x, x3##_x, x3##_x; \ + vaesdeclast t7##_x, t6##_x, t6##_x; \ + vinserti128 $1, t6##_x, x3, x3; \ + \ + vextracti128 $1, x7, t6##_x; \ + vaesdeclast t7##_x, x7##_x, x7##_x; \ + vaesdeclast t7##_x, t6##_x, t6##_x; \ + vinserti128 $1, t6##_x, x7, x7; \ + +#define aria_diff_m(x0, x1, x2, x3, \ + t0, t1, t2, t3) \ + /* T = rotr32(X, 8); */ \ + /* X ^= T */ \ + vpxor x0, x3, t0; \ + vpxor x1, x0, t1; \ + vpxor x2, x1, t2; \ + vpxor x3, x2, t3; \ + /* X = T ^ rotr(X, 16); */ \ + vpxor t2, x0, x0; \ + vpxor x1, t3, t3; \ + vpxor t0, x2, x2; \ + vpxor t1, x3, x1; \ + vmovdqu t3, x3; + +#define aria_diff_word(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7) \ + /* t1 ^= t2; */ \ + vpxor y0, x4, x4; \ + vpxor y1, x5, x5; \ + vpxor y2, x6, x6; \ + vpxor y3, x7, x7; \ + \ + /* t2 ^= t3; */ \ + vpxor y4, y0, y0; \ + vpxor y5, y1, y1; \ + vpxor y6, y2, y2; \ + vpxor y7, y3, y3; \ + \ + /* t0 ^= t1; */ \ + vpxor x4, x0, x0; \ + vpxor x5, x1, x1; \ + vpxor x6, x2, x2; \ + vpxor x7, x3, x3; \ + \ + /* t3 ^= t1; */ \ + vpxor x4, y4, y4; \ + vpxor x5, y5, y5; \ + vpxor x6, y6, y6; \ + vpxor x7, y7, y7; \ + \ + /* t2 ^= t0; */ \ + vpxor x0, y0, y0; \ + vpxor x1, y1, y1; \ + vpxor x2, y2, y2; \ + vpxor x3, y3, y3; \ + \ + /* t1 ^= t2; */ \ + vpxor y0, x4, x4; \ + vpxor y1, x5, x5; \ + vpxor y2, x6, x6; \ + vpxor y3, x7, x7; + +#define aria_fe(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, rk, round) \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, round); \ + \ + aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \ + y0, y1, y2, y3, y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 8); \ + \ + aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, round); \ + \ + aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \ + y0, y1, y2, y3, y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_load_state_8way(y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, 8); \ + aria_diff_word(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + /* aria_diff_byte() \ + * T3 = ABCD -> BADC \ + * T3 = y4, y5, y6, y7 -> y5, y4, y7, y6 \ + * T0 = ABCD -> CDAB \ + * T0 = x0, x1, x2, x3 -> x2, x3, x0, x1 \ + * T1 = ABCD -> DCBA \ + * T1 = x4, x5, x6, x7 -> x7, x6, x5, x4 \ + */ \ + aria_diff_word(x2, x3, x0, x1, \ + x7, x6, x5, x4, \ + y0, y1, y2, y3, \ + y5, y4, y7, y6); \ + aria_store_state_8way(x3, x2, x1, x0, \ + x6, x7, x4, x5, \ + mem_tmp, 0); + +#define aria_fo(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, rk, round) \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, round); \ + \ + aria_sbox_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, y1, y2, y3, y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 8); \ + \ + aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, round); \ + \ + aria_sbox_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, y1, y2, y3, y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_load_state_8way(y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, 8); \ + aria_diff_word(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + /* aria_diff_byte() \ + * T1 = ABCD -> BADC \ + * T1 = x4, x5, x6, x7 -> x5, x4, x7, x6 \ + * T2 = ABCD -> CDAB \ + * T2 = y0, y1, y2, y3, -> y2, y3, y0, y1 \ + * T3 = ABCD -> DCBA \ + * T3 = y4, y5, y6, y7 -> y7, y6, y5, y4 \ + */ \ + aria_diff_word(x0, x1, x2, x3, \ + x5, x4, x7, x6, \ + y2, y3, y0, y1, \ + y7, y6, y5, y4); \ + aria_store_state_8way(x3, x2, x1, x0, \ + x6, x7, x4, x5, \ + mem_tmp, 0); + +#define aria_ff(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, rk, round, last_round) \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, round); \ + \ + aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \ + y0, y1, y2, y3, y4, y5, y6, y7); \ + \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, last_round); \ + \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 8); \ + \ + aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, round); \ + \ + aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \ + y0, y1, y2, y3, y4, y5, y6, y7); \ + \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, last_round); \ + \ + aria_load_state_8way(y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, 8); +#ifdef CONFIG_AS_GFNI +#define aria_fe_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, rk, round) \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, round); \ + \ + aria_sbox_8way_gfni(x2, x3, x0, x1, \ + x6, x7, x4, x5, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 8); \ + \ + aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, round); \ + \ + aria_sbox_8way_gfni(x2, x3, x0, x1, \ + x6, x7, x4, x5, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_load_state_8way(y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, 8); \ + aria_diff_word(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + /* aria_diff_byte() \ + * T3 = ABCD -> BADC \ + * T3 = y4, y5, y6, y7 -> y5, y4, y7, y6 \ + * T0 = ABCD -> CDAB \ + * T0 = x0, x1, x2, x3 -> x2, x3, x0, x1 \ + * T1 = ABCD -> DCBA \ + * T1 = x4, x5, x6, x7 -> x7, x6, x5, x4 \ + */ \ + aria_diff_word(x2, x3, x0, x1, \ + x7, x6, x5, x4, \ + y0, y1, y2, y3, \ + y5, y4, y7, y6); \ + aria_store_state_8way(x3, x2, x1, x0, \ + x6, x7, x4, x5, \ + mem_tmp, 0); + +#define aria_fo_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, rk, round) \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, round); \ + \ + aria_sbox_8way_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 8); \ + \ + aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, round); \ + \ + aria_sbox_8way_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_load_state_8way(y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, 8); \ + aria_diff_word(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + /* aria_diff_byte() \ + * T1 = ABCD -> BADC \ + * T1 = x4, x5, x6, x7 -> x5, x4, x7, x6 \ + * T2 = ABCD -> CDAB \ + * T2 = y0, y1, y2, y3, -> y2, y3, y0, y1 \ + * T3 = ABCD -> DCBA \ + * T3 = y4, y5, y6, y7 -> y7, y6, y5, y4 \ + */ \ + aria_diff_word(x0, x1, x2, x3, \ + x5, x4, x7, x6, \ + y2, y3, y0, y1, \ + y7, y6, y5, y4); \ + aria_store_state_8way(x3, x2, x1, x0, \ + x6, x7, x4, x5, \ + mem_tmp, 0); + +#define aria_ff_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, rk, round, last_round) \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, round); \ + \ + aria_sbox_8way_gfni(x2, x3, x0, x1, \ + x6, x7, x4, x5, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, last_round); \ + \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 8); \ + \ + aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, round); \ + \ + aria_sbox_8way_gfni(x2, x3, x0, x1, \ + x6, x7, x4, x5, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, last_round); \ + \ + aria_load_state_8way(y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, 8); +#endif /* CONFIG_AS_GFNI */ + +.section .rodata.cst32.shufb_16x16b, "aM", @progbits, 32 +.align 32 +#define SHUFB_BYTES(idx) \ + 0 + (idx), 4 + (idx), 8 + (idx), 12 + (idx) +.Lshufb_16x16b: + .byte SHUFB_BYTES(0), SHUFB_BYTES(1), SHUFB_BYTES(2), SHUFB_BYTES(3) + .byte SHUFB_BYTES(0), SHUFB_BYTES(1), SHUFB_BYTES(2), SHUFB_BYTES(3) + +.section .rodata.cst16, "aM", @progbits, 16 +.align 16 +/* For isolating SubBytes from AESENCLAST, inverse shift row */ +.Linv_shift_row: + .byte 0x00, 0x0d, 0x0a, 0x07, 0x04, 0x01, 0x0e, 0x0b + .byte 0x08, 0x05, 0x02, 0x0f, 0x0c, 0x09, 0x06, 0x03 +.Lshift_row: + .byte 0x00, 0x05, 0x0a, 0x0f, 0x04, 0x09, 0x0e, 0x03 + .byte 0x08, 0x0d, 0x02, 0x07, 0x0c, 0x01, 0x06, 0x0b +/* For CTR-mode IV byteswap */ +.Lbswap128_mask: + .byte 0x0f, 0x0e, 0x0d, 0x0c, 0x0b, 0x0a, 0x09, 0x08 + .byte 0x07, 0x06, 0x05, 0x04, 0x03, 0x02, 0x01, 0x00 + +/* AES inverse affine and S2 combined: + * 1 1 0 0 0 0 0 1 x0 0 + * 0 1 0 0 1 0 0 0 x1 0 + * 1 1 0 0 1 1 1 1 x2 0 + * 0 1 1 0 1 0 0 1 x3 1 + * 0 1 0 0 1 1 0 0 * x4 + 0 + * 0 1 0 1 1 0 0 0 x5 0 + * 0 0 0 0 0 1 0 1 x6 0 + * 1 1 1 0 0 1 1 1 x7 1 + */ +.Ltf_lo__inv_aff__and__s2: + .octa 0x92172DA81A9FA520B2370D883ABF8500 +.Ltf_hi__inv_aff__and__s2: + .octa 0x2B15FFC1AF917B45E6D8320C625CB688 + +/* X2 and AES forward affine combined: + * 1 0 1 1 0 0 0 1 x0 0 + * 0 1 1 1 1 0 1 1 x1 0 + * 0 0 0 1 1 0 1 0 x2 1 + * 0 1 0 0 0 1 0 0 x3 0 + * 0 0 1 1 1 0 1 1 * x4 + 0 + * 0 1 0 0 1 0 0 0 x5 0 + * 1 1 0 1 0 0 1 1 x6 0 + * 0 1 0 0 1 0 1 0 x7 0 + */ +.Ltf_lo__x2__and__fwd_aff: + .octa 0xEFAE0544FCBD1657B8F95213ABEA4100 +.Ltf_hi__x2__and__fwd_aff: + .octa 0x3F893781E95FE1576CDA64D2BA0CB204 + +#ifdef CONFIG_AS_GFNI +.section .rodata.cst8, "aM", @progbits, 8 +.align 8 +/* AES affine: */ +#define tf_aff_const BV8(1, 1, 0, 0, 0, 1, 1, 0) +.Ltf_aff_bitmatrix: + .quad BM8X8(BV8(1, 0, 0, 0, 1, 1, 1, 1), + BV8(1, 1, 0, 0, 0, 1, 1, 1), + BV8(1, 1, 1, 0, 0, 0, 1, 1), + BV8(1, 1, 1, 1, 0, 0, 0, 1), + BV8(1, 1, 1, 1, 1, 0, 0, 0), + BV8(0, 1, 1, 1, 1, 1, 0, 0), + BV8(0, 0, 1, 1, 1, 1, 1, 0), + BV8(0, 0, 0, 1, 1, 1, 1, 1)) + +/* AES inverse affine: */ +#define tf_inv_const BV8(1, 0, 1, 0, 0, 0, 0, 0) +.Ltf_inv_bitmatrix: + .quad BM8X8(BV8(0, 0, 1, 0, 0, 1, 0, 1), + BV8(1, 0, 0, 1, 0, 0, 1, 0), + BV8(0, 1, 0, 0, 1, 0, 0, 1), + BV8(1, 0, 1, 0, 0, 1, 0, 0), + BV8(0, 1, 0, 1, 0, 0, 1, 0), + BV8(0, 0, 1, 0, 1, 0, 0, 1), + BV8(1, 0, 0, 1, 0, 1, 0, 0), + BV8(0, 1, 0, 0, 1, 0, 1, 0)) + +/* S2: */ +#define tf_s2_const BV8(0, 1, 0, 0, 0, 1, 1, 1) +.Ltf_s2_bitmatrix: + .quad BM8X8(BV8(0, 1, 0, 1, 0, 1, 1, 1), + BV8(0, 0, 1, 1, 1, 1, 1, 1), + BV8(1, 1, 1, 0, 1, 1, 0, 1), + BV8(1, 1, 0, 0, 0, 0, 1, 1), + BV8(0, 1, 0, 0, 0, 0, 1, 1), + BV8(1, 1, 0, 0, 1, 1, 1, 0), + BV8(0, 1, 1, 0, 0, 0, 1, 1), + BV8(1, 1, 1, 1, 0, 1, 1, 0)) + +/* X2: */ +#define tf_x2_const BV8(0, 0, 1, 1, 0, 1, 0, 0) +.Ltf_x2_bitmatrix: + .quad BM8X8(BV8(0, 0, 0, 1, 1, 0, 0, 0), + BV8(0, 0, 1, 0, 0, 1, 1, 0), + BV8(0, 0, 0, 0, 1, 0, 1, 0), + BV8(1, 1, 1, 0, 0, 0, 1, 1), + BV8(1, 1, 1, 0, 1, 1, 0, 0), + BV8(0, 1, 1, 0, 1, 0, 1, 1), + BV8(1, 0, 1, 1, 1, 1, 0, 1), + BV8(1, 0, 0, 1, 0, 0, 1, 1)) + +/* Identity matrix: */ +.Ltf_id_bitmatrix: + .quad BM8X8(BV8(1, 0, 0, 0, 0, 0, 0, 0), + BV8(0, 1, 0, 0, 0, 0, 0, 0), + BV8(0, 0, 1, 0, 0, 0, 0, 0), + BV8(0, 0, 0, 1, 0, 0, 0, 0), + BV8(0, 0, 0, 0, 1, 0, 0, 0), + BV8(0, 0, 0, 0, 0, 1, 0, 0), + BV8(0, 0, 0, 0, 0, 0, 1, 0), + BV8(0, 0, 0, 0, 0, 0, 0, 1)) + +#endif /* CONFIG_AS_GFNI */ + +/* 4-bit mask */ +.section .rodata.cst4.L0f0f0f0f, "aM", @progbits, 4 +.align 4 +.L0f0f0f0f: + .long 0x0f0f0f0f + +.text + +SYM_FUNC_START_LOCAL(__aria_aesni_avx2_crypt_32way) + /* input: + * %r9: rk + * %rsi: dst + * %rdx: src + * %ymm0..%ymm15: byte-sliced blocks + */ + + FRAME_BEGIN + + movq %rsi, %rax; + leaq 8 * 32(%rax), %r8; + + inpack16_post(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r8); + aria_fo(%ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 0); + aria_fe(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 1); + aria_fo(%ymm9, %ymm8, %ymm11, %ymm10, %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 2); + aria_fe(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 3); + aria_fo(%ymm9, %ymm8, %ymm11, %ymm10, %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 4); + aria_fe(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 5); + aria_fo(%ymm9, %ymm8, %ymm11, %ymm10, %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 6); + aria_fe(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 7); + aria_fo(%ymm9, %ymm8, %ymm11, %ymm10, %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 8); + aria_fe(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 9); + aria_fo(%ymm9, %ymm8, %ymm11, %ymm10, %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 10); + cmpl $12, ARIA_CTX_rounds(CTX); + jne .Laria_192; + aria_ff(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 11, 12); + jmp .Laria_end; +.Laria_192: + aria_fe(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 11); + aria_fo(%ymm9, %ymm8, %ymm11, %ymm10, %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 12); + cmpl $14, ARIA_CTX_rounds(CTX); + jne .Laria_256; + aria_ff(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 13, 14); + jmp .Laria_end; +.Laria_256: + aria_fe(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 13); + aria_fo(%ymm9, %ymm8, %ymm11, %ymm10, %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 14); + aria_ff(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 15, 16); +.Laria_end: + debyteslice_16x16b(%ymm8, %ymm12, %ymm1, %ymm4, + %ymm9, %ymm13, %ymm0, %ymm5, + %ymm10, %ymm14, %ymm3, %ymm6, + %ymm11, %ymm15, %ymm2, %ymm7, + (%rax), (%r8)); + + FRAME_END + RET; +SYM_FUNC_END(__aria_aesni_avx2_crypt_32way) + +SYM_TYPED_FUNC_START(aria_aesni_avx2_encrypt_32way) + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + */ + + FRAME_BEGIN + + leaq ARIA_CTX_enc_key(CTX), %r9; + + inpack16_pre(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rdx); + + call __aria_aesni_avx2_crypt_32way; + + write_output(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax); + + FRAME_END + RET; +SYM_FUNC_END(aria_aesni_avx2_encrypt_32way) + +SYM_TYPED_FUNC_START(aria_aesni_avx2_decrypt_32way) + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + */ + + FRAME_BEGIN + + leaq ARIA_CTX_dec_key(CTX), %r9; + + inpack16_pre(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rdx); + + call __aria_aesni_avx2_crypt_32way; + + write_output(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax); + + FRAME_END + RET; +SYM_FUNC_END(aria_aesni_avx2_decrypt_32way) + +SYM_FUNC_START_LOCAL(__aria_aesni_avx2_ctr_gen_keystream_32way) + /* input: + * %rdi: ctx + * %rsi: dst + * %rdx: src + * %rcx: keystream + * %r8: iv (big endian, 128bit) + */ + + FRAME_BEGIN + movq 8(%r8), %r11; + bswapq %r11; + + vbroadcasti128 .Lbswap128_mask (%rip), %ymm6; + vpcmpeqd %ymm0, %ymm0, %ymm0; + vpsrldq $8, %ymm0, %ymm0; /* ab: -1:0 ; cd: -1:0 */ + vpaddq %ymm0, %ymm0, %ymm5; /* ab: -2:0 ; cd: -2:0 */ + + /* load IV and byteswap */ + vmovdqu (%r8), %xmm7; + vpshufb %xmm6, %xmm7, %xmm7; + vmovdqa %xmm7, %xmm3; + inc_le128(%xmm7, %xmm0, %xmm4); + vinserti128 $1, %xmm7, %ymm3, %ymm3; + vpshufb %ymm6, %ymm3, %ymm8; /* +1 ; +0 */ + + /* check need for handling 64-bit overflow and carry */ + cmpq $(0xffffffffffffffff - 32), %r11; + ja .Lhandle_ctr_carry; + + /* construct IVs */ + vpsubq %ymm5, %ymm3, %ymm3; /* +3 ; +2 */ + vpshufb %ymm6, %ymm3, %ymm9; + vpsubq %ymm5, %ymm3, %ymm3; /* +5 ; +4 */ + vpshufb %ymm6, %ymm3, %ymm10; + vpsubq %ymm5, %ymm3, %ymm3; /* +7 ; +6 */ + vpshufb %ymm6, %ymm3, %ymm11; + vpsubq %ymm5, %ymm3, %ymm3; /* +9 ; +8 */ + vpshufb %ymm6, %ymm3, %ymm12; + vpsubq %ymm5, %ymm3, %ymm3; /* +11 ; +10 */ + vpshufb %ymm6, %ymm3, %ymm13; + vpsubq %ymm5, %ymm3, %ymm3; /* +13 ; +12 */ + vpshufb %ymm6, %ymm3, %ymm14; + vpsubq %ymm5, %ymm3, %ymm3; /* +15 ; +14 */ + vpshufb %ymm6, %ymm3, %ymm15; + vmovdqu %ymm8, (0 * 32)(%rcx); + vmovdqu %ymm9, (1 * 32)(%rcx); + vmovdqu %ymm10, (2 * 32)(%rcx); + vmovdqu %ymm11, (3 * 32)(%rcx); + vmovdqu %ymm12, (4 * 32)(%rcx); + vmovdqu %ymm13, (5 * 32)(%rcx); + vmovdqu %ymm14, (6 * 32)(%rcx); + vmovdqu %ymm15, (7 * 32)(%rcx); + + vpsubq %ymm5, %ymm3, %ymm3; /* +17 ; +16 */ + vpshufb %ymm6, %ymm3, %ymm8; + vpsubq %ymm5, %ymm3, %ymm3; /* +19 ; +18 */ + vpshufb %ymm6, %ymm3, %ymm9; + vpsubq %ymm5, %ymm3, %ymm3; /* +21 ; +20 */ + vpshufb %ymm6, %ymm3, %ymm10; + vpsubq %ymm5, %ymm3, %ymm3; /* +23 ; +22 */ + vpshufb %ymm6, %ymm3, %ymm11; + vpsubq %ymm5, %ymm3, %ymm3; /* +25 ; +24 */ + vpshufb %ymm6, %ymm3, %ymm12; + vpsubq %ymm5, %ymm3, %ymm3; /* +27 ; +26 */ + vpshufb %ymm6, %ymm3, %ymm13; + vpsubq %ymm5, %ymm3, %ymm3; /* +29 ; +28 */ + vpshufb %ymm6, %ymm3, %ymm14; + vpsubq %ymm5, %ymm3, %ymm3; /* +31 ; +30 */ + vpshufb %ymm6, %ymm3, %ymm15; + vpsubq %ymm5, %ymm3, %ymm3; /* +32 */ + vpshufb %xmm6, %xmm3, %xmm3; + vmovdqu %xmm3, (%r8); + vmovdqu (0 * 32)(%rcx), %ymm0; + vmovdqu (1 * 32)(%rcx), %ymm1; + vmovdqu (2 * 32)(%rcx), %ymm2; + vmovdqu (3 * 32)(%rcx), %ymm3; + vmovdqu (4 * 32)(%rcx), %ymm4; + vmovdqu (5 * 32)(%rcx), %ymm5; + vmovdqu (6 * 32)(%rcx), %ymm6; + vmovdqu (7 * 32)(%rcx), %ymm7; + jmp .Lctr_carry_done; + + .Lhandle_ctr_carry: + /* construct IVs */ + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm9; /* +3 ; +2 */ + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm10; /* +5 ; +4 */ + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm11; /* +7 ; +6 */ + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm12; /* +9 ; +8 */ + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm13; /* +11 ; +10 */ + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm14; /* +13 ; +12 */ + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm15; /* +15 ; +14 */ + vmovdqu %ymm8, (0 * 32)(%rcx); + vmovdqu %ymm9, (1 * 32)(%rcx); + vmovdqu %ymm10, (2 * 32)(%rcx); + vmovdqu %ymm11, (3 * 32)(%rcx); + vmovdqu %ymm12, (4 * 32)(%rcx); + vmovdqu %ymm13, (5 * 32)(%rcx); + vmovdqu %ymm14, (6 * 32)(%rcx); + vmovdqu %ymm15, (7 * 32)(%rcx); + + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm8; /* +17 ; +16 */ + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm9; /* +19 ; +18 */ + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm10; /* +21 ; +20 */ + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm11; /* +23 ; +22 */ + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm12; /* +25 ; +24 */ + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm13; /* +27 ; +26 */ + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm14; /* +29 ; +28 */ + inc_le128(%ymm3, %ymm0, %ymm4); + inc_le128(%ymm3, %ymm0, %ymm4); + vpshufb %ymm6, %ymm3, %ymm15; /* +31 ; +30 */ + inc_le128(%ymm3, %ymm0, %ymm4); + vextracti128 $1, %ymm3, %xmm3; + vpshufb %xmm6, %xmm3, %xmm3; /* +32 */ + vmovdqu %xmm3, (%r8); + vmovdqu (0 * 32)(%rcx), %ymm0; + vmovdqu (1 * 32)(%rcx), %ymm1; + vmovdqu (2 * 32)(%rcx), %ymm2; + vmovdqu (3 * 32)(%rcx), %ymm3; + vmovdqu (4 * 32)(%rcx), %ymm4; + vmovdqu (5 * 32)(%rcx), %ymm5; + vmovdqu (6 * 32)(%rcx), %ymm6; + vmovdqu (7 * 32)(%rcx), %ymm7; + + .Lctr_carry_done: + + FRAME_END + RET; +SYM_FUNC_END(__aria_aesni_avx2_ctr_gen_keystream_32way) + +SYM_TYPED_FUNC_START(aria_aesni_avx2_ctr_crypt_32way) + /* input: + * %rdi: ctx + * %rsi: dst + * %rdx: src + * %rcx: keystream + * %r8: iv (big endian, 128bit) + */ + FRAME_BEGIN + + call __aria_aesni_avx2_ctr_gen_keystream_32way; + + leaq (%rsi), %r10; + leaq (%rdx), %r11; + leaq (%rcx), %rsi; + leaq (%rcx), %rdx; + leaq ARIA_CTX_enc_key(CTX), %r9; + + call __aria_aesni_avx2_crypt_32way; + + vpxor (0 * 32)(%r11), %ymm1, %ymm1; + vpxor (1 * 32)(%r11), %ymm0, %ymm0; + vpxor (2 * 32)(%r11), %ymm3, %ymm3; + vpxor (3 * 32)(%r11), %ymm2, %ymm2; + vpxor (4 * 32)(%r11), %ymm4, %ymm4; + vpxor (5 * 32)(%r11), %ymm5, %ymm5; + vpxor (6 * 32)(%r11), %ymm6, %ymm6; + vpxor (7 * 32)(%r11), %ymm7, %ymm7; + vpxor (8 * 32)(%r11), %ymm8, %ymm8; + vpxor (9 * 32)(%r11), %ymm9, %ymm9; + vpxor (10 * 32)(%r11), %ymm10, %ymm10; + vpxor (11 * 32)(%r11), %ymm11, %ymm11; + vpxor (12 * 32)(%r11), %ymm12, %ymm12; + vpxor (13 * 32)(%r11), %ymm13, %ymm13; + vpxor (14 * 32)(%r11), %ymm14, %ymm14; + vpxor (15 * 32)(%r11), %ymm15, %ymm15; + write_output(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %r10); + + FRAME_END + RET; +SYM_FUNC_END(aria_aesni_avx2_ctr_crypt_32way) + +#ifdef CONFIG_AS_GFNI +SYM_FUNC_START_LOCAL(__aria_aesni_avx2_gfni_crypt_32way) + /* input: + * %r9: rk + * %rsi: dst + * %rdx: src + * %ymm0..%ymm15: 16 byte-sliced blocks + */ + + FRAME_BEGIN + + movq %rsi, %rax; + leaq 8 * 32(%rax), %r8; + + inpack16_post(%ymm0, %ymm1, %ymm2, %ymm3, + %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, + %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r8); + aria_fo_gfni(%ymm8, %ymm9, %ymm10, %ymm11, + %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, + %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 0); + aria_fe_gfni(%ymm1, %ymm0, %ymm3, %ymm2, + %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, + %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 1); + aria_fo_gfni(%ymm9, %ymm8, %ymm11, %ymm10, + %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, + %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 2); + aria_fe_gfni(%ymm1, %ymm0, %ymm3, %ymm2, + %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, + %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 3); + aria_fo_gfni(%ymm9, %ymm8, %ymm11, %ymm10, + %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, + %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 4); + aria_fe_gfni(%ymm1, %ymm0, %ymm3, %ymm2, + %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, + %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 5); + aria_fo_gfni(%ymm9, %ymm8, %ymm11, %ymm10, + %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, + %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 6); + aria_fe_gfni(%ymm1, %ymm0, %ymm3, %ymm2, + %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, + %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 7); + aria_fo_gfni(%ymm9, %ymm8, %ymm11, %ymm10, + %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, + %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 8); + aria_fe_gfni(%ymm1, %ymm0, %ymm3, %ymm2, + %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, + %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 9); + aria_fo_gfni(%ymm9, %ymm8, %ymm11, %ymm10, + %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, + %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 10); + cmpl $12, ARIA_CTX_rounds(CTX); + jne .Laria_gfni_192; + aria_ff_gfni(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 11, 12); + jmp .Laria_gfni_end; +.Laria_gfni_192: + aria_fe_gfni(%ymm1, %ymm0, %ymm3, %ymm2, + %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, + %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 11); + aria_fo_gfni(%ymm9, %ymm8, %ymm11, %ymm10, + %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, + %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 12); + cmpl $14, ARIA_CTX_rounds(CTX); + jne .Laria_gfni_256; + aria_ff_gfni(%ymm1, %ymm0, %ymm3, %ymm2, + %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, + %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 13, 14); + jmp .Laria_gfni_end; +.Laria_gfni_256: + aria_fe_gfni(%ymm1, %ymm0, %ymm3, %ymm2, + %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, + %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 13); + aria_fo_gfni(%ymm9, %ymm8, %ymm11, %ymm10, + %ymm12, %ymm13, %ymm14, %ymm15, + %ymm0, %ymm1, %ymm2, %ymm3, + %ymm4, %ymm5, %ymm6, %ymm7, + %rax, %r9, 14); + aria_ff_gfni(%ymm1, %ymm0, %ymm3, %ymm2, + %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, + %ymm12, %ymm13, %ymm14, + %ymm15, %rax, %r9, 15, 16); +.Laria_gfni_end: + debyteslice_16x16b(%ymm8, %ymm12, %ymm1, %ymm4, + %ymm9, %ymm13, %ymm0, %ymm5, + %ymm10, %ymm14, %ymm3, %ymm6, + %ymm11, %ymm15, %ymm2, %ymm7, + (%rax), (%r8)); + + FRAME_END + RET; +SYM_FUNC_END(__aria_aesni_avx2_gfni_crypt_32way) + +SYM_TYPED_FUNC_START(aria_aesni_avx2_gfni_encrypt_32way) + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + */ + + FRAME_BEGIN + + leaq ARIA_CTX_enc_key(CTX), %r9; + + inpack16_pre(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rdx); + + call __aria_aesni_avx2_gfni_crypt_32way; + + write_output(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax); + + FRAME_END + RET; +SYM_FUNC_END(aria_aesni_avx2_gfni_encrypt_32way) + +SYM_TYPED_FUNC_START(aria_aesni_avx2_gfni_decrypt_32way) + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + */ + + FRAME_BEGIN + + leaq ARIA_CTX_dec_key(CTX), %r9; + + inpack16_pre(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rdx); + + call __aria_aesni_avx2_gfni_crypt_32way; + + write_output(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %rax); + + FRAME_END + RET; +SYM_FUNC_END(aria_aesni_avx2_gfni_decrypt_32way) + +SYM_TYPED_FUNC_START(aria_aesni_avx2_gfni_ctr_crypt_32way) + /* input: + * %rdi: ctx + * %rsi: dst + * %rdx: src + * %rcx: keystream + * %r8: iv (big endian, 128bit) + */ + FRAME_BEGIN + + call __aria_aesni_avx2_ctr_gen_keystream_32way + + leaq (%rsi), %r10; + leaq (%rdx), %r11; + leaq (%rcx), %rsi; + leaq (%rcx), %rdx; + leaq ARIA_CTX_enc_key(CTX), %r9; + + call __aria_aesni_avx2_gfni_crypt_32way; + + vpxor (0 * 32)(%r11), %ymm1, %ymm1; + vpxor (1 * 32)(%r11), %ymm0, %ymm0; + vpxor (2 * 32)(%r11), %ymm3, %ymm3; + vpxor (3 * 32)(%r11), %ymm2, %ymm2; + vpxor (4 * 32)(%r11), %ymm4, %ymm4; + vpxor (5 * 32)(%r11), %ymm5, %ymm5; + vpxor (6 * 32)(%r11), %ymm6, %ymm6; + vpxor (7 * 32)(%r11), %ymm7, %ymm7; + vpxor (8 * 32)(%r11), %ymm8, %ymm8; + vpxor (9 * 32)(%r11), %ymm9, %ymm9; + vpxor (10 * 32)(%r11), %ymm10, %ymm10; + vpxor (11 * 32)(%r11), %ymm11, %ymm11; + vpxor (12 * 32)(%r11), %ymm12, %ymm12; + vpxor (13 * 32)(%r11), %ymm13, %ymm13; + vpxor (14 * 32)(%r11), %ymm14, %ymm14; + vpxor (15 * 32)(%r11), %ymm15, %ymm15; + write_output(%ymm1, %ymm0, %ymm3, %ymm2, %ymm4, %ymm5, %ymm6, %ymm7, + %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, + %ymm15, %r10); + + FRAME_END + RET; +SYM_FUNC_END(aria_aesni_avx2_gfni_ctr_crypt_32way) +#endif /* CONFIG_AS_GFNI */ diff --git a/arch/x86/crypto/aria-avx.h b/arch/x86/crypto/aria-avx.h index 01e9a01dc157..6e1b2d8a31ed 100644 --- a/arch/x86/crypto/aria-avx.h +++ b/arch/x86/crypto/aria-avx.h @@ -5,12 +5,58 @@ #include <linux/types.h> #define ARIA_AESNI_PARALLEL_BLOCKS 16 -#define ARIA_AESNI_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * 16) +#define ARIA_AESNI_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * ARIA_AESNI_PARALLEL_BLOCKS) + +#define ARIA_AESNI_AVX2_PARALLEL_BLOCKS 32 +#define ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * ARIA_AESNI_AVX2_PARALLEL_BLOCKS) + +#define ARIA_GFNI_AVX512_PARALLEL_BLOCKS 64 +#define ARIA_GFNI_AVX512_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * ARIA_GFNI_AVX512_PARALLEL_BLOCKS) + +asmlinkage void aria_aesni_avx_encrypt_16way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx_decrypt_16way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx_ctr_crypt_16way(const void *ctx, u8 *dst, + const u8 *src, + u8 *keystream, u8 *iv); +asmlinkage void aria_aesni_avx_gfni_encrypt_16way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx_gfni_decrypt_16way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx_gfni_ctr_crypt_16way(const void *ctx, u8 *dst, + const u8 *src, + u8 *keystream, u8 *iv); + +asmlinkage void aria_aesni_avx2_encrypt_32way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx2_decrypt_32way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx2_ctr_crypt_32way(const void *ctx, u8 *dst, + const u8 *src, + u8 *keystream, u8 *iv); +asmlinkage void aria_aesni_avx2_gfni_encrypt_32way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx2_gfni_decrypt_32way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx2_gfni_ctr_crypt_32way(const void *ctx, u8 *dst, + const u8 *src, + u8 *keystream, u8 *iv); struct aria_avx_ops { void (*aria_encrypt_16way)(const void *ctx, u8 *dst, const u8 *src); void (*aria_decrypt_16way)(const void *ctx, u8 *dst, const u8 *src); void (*aria_ctr_crypt_16way)(const void *ctx, u8 *dst, const u8 *src, u8 *keystream, u8 *iv); + void (*aria_encrypt_32way)(const void *ctx, u8 *dst, const u8 *src); + void (*aria_decrypt_32way)(const void *ctx, u8 *dst, const u8 *src); + void (*aria_ctr_crypt_32way)(const void *ctx, u8 *dst, const u8 *src, + u8 *keystream, u8 *iv); + void (*aria_encrypt_64way)(const void *ctx, u8 *dst, const u8 *src); + void (*aria_decrypt_64way)(const void *ctx, u8 *dst, const u8 *src); + void (*aria_ctr_crypt_64way)(const void *ctx, u8 *dst, const u8 *src, + u8 *keystream, u8 *iv); + + }; #endif diff --git a/arch/x86/crypto/aria-gfni-avx512-asm_64.S b/arch/x86/crypto/aria-gfni-avx512-asm_64.S new file mode 100644 index 000000000000..3193f0701450 --- /dev/null +++ b/arch/x86/crypto/aria-gfni-avx512-asm_64.S @@ -0,0 +1,971 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * ARIA Cipher 64-way parallel algorithm (AVX512) + * + * Copyright (c) 2022 Taehee Yoo <ap420073@gmail.com> + * + */ + +#include <linux/linkage.h> +#include <asm/frame.h> +#include <asm/asm-offsets.h> +#include <linux/cfi_types.h> + +/* register macros */ +#define CTX %rdi + + +#define BV8(a0, a1, a2, a3, a4, a5, a6, a7) \ + ( (((a0) & 1) << 0) | \ + (((a1) & 1) << 1) | \ + (((a2) & 1) << 2) | \ + (((a3) & 1) << 3) | \ + (((a4) & 1) << 4) | \ + (((a5) & 1) << 5) | \ + (((a6) & 1) << 6) | \ + (((a7) & 1) << 7) ) + +#define BM8X8(l0, l1, l2, l3, l4, l5, l6, l7) \ + ( ((l7) << (0 * 8)) | \ + ((l6) << (1 * 8)) | \ + ((l5) << (2 * 8)) | \ + ((l4) << (3 * 8)) | \ + ((l3) << (4 * 8)) | \ + ((l2) << (5 * 8)) | \ + ((l1) << (6 * 8)) | \ + ((l0) << (7 * 8)) ) + +#define add_le128(out, in, lo_counter, hi_counter1) \ + vpaddq lo_counter, in, out; \ + vpcmpuq $1, lo_counter, out, %k1; \ + kaddb %k1, %k1, %k1; \ + vpaddq hi_counter1, out, out{%k1}; + +#define filter_8bit(x, lo_t, hi_t, mask4bit, tmp0) \ + vpandq x, mask4bit, tmp0; \ + vpandqn x, mask4bit, x; \ + vpsrld $4, x, x; \ + \ + vpshufb tmp0, lo_t, tmp0; \ + vpshufb x, hi_t, x; \ + vpxorq tmp0, x, x; + +#define transpose_4x4(x0, x1, x2, x3, t1, t2) \ + vpunpckhdq x1, x0, t2; \ + vpunpckldq x1, x0, x0; \ + \ + vpunpckldq x3, x2, t1; \ + vpunpckhdq x3, x2, x2; \ + \ + vpunpckhqdq t1, x0, x1; \ + vpunpcklqdq t1, x0, x0; \ + \ + vpunpckhqdq x2, t2, x3; \ + vpunpcklqdq x2, t2, x2; + +#define byteslice_16x16b(a0, b0, c0, d0, \ + a1, b1, c1, d1, \ + a2, b2, c2, d2, \ + a3, b3, c3, d3, \ + st0, st1) \ + vmovdqu64 d2, st0; \ + vmovdqu64 d3, st1; \ + transpose_4x4(a0, a1, a2, a3, d2, d3); \ + transpose_4x4(b0, b1, b2, b3, d2, d3); \ + vmovdqu64 st0, d2; \ + vmovdqu64 st1, d3; \ + \ + vmovdqu64 a0, st0; \ + vmovdqu64 a1, st1; \ + transpose_4x4(c0, c1, c2, c3, a0, a1); \ + transpose_4x4(d0, d1, d2, d3, a0, a1); \ + \ + vbroadcasti64x2 .Lshufb_16x16b, a0; \ + vmovdqu64 st1, a1; \ + vpshufb a0, a2, a2; \ + vpshufb a0, a3, a3; \ + vpshufb a0, b0, b0; \ + vpshufb a0, b1, b1; \ + vpshufb a0, b2, b2; \ + vpshufb a0, b3, b3; \ + vpshufb a0, a1, a1; \ + vpshufb a0, c0, c0; \ + vpshufb a0, c1, c1; \ + vpshufb a0, c2, c2; \ + vpshufb a0, c3, c3; \ + vpshufb a0, d0, d0; \ + vpshufb a0, d1, d1; \ + vpshufb a0, d2, d2; \ + vpshufb a0, d3, d3; \ + vmovdqu64 d3, st1; \ + vmovdqu64 st0, d3; \ + vpshufb a0, d3, a0; \ + vmovdqu64 d2, st0; \ + \ + transpose_4x4(a0, b0, c0, d0, d2, d3); \ + transpose_4x4(a1, b1, c1, d1, d2, d3); \ + vmovdqu64 st0, d2; \ + vmovdqu64 st1, d3; \ + \ + vmovdqu64 b0, st0; \ + vmovdqu64 b1, st1; \ + transpose_4x4(a2, b2, c2, d2, b0, b1); \ + transpose_4x4(a3, b3, c3, d3, b0, b1); \ + vmovdqu64 st0, b0; \ + vmovdqu64 st1, b1; \ + /* does not adjust output bytes inside vectors */ + +#define debyteslice_16x16b(a0, b0, c0, d0, \ + a1, b1, c1, d1, \ + a2, b2, c2, d2, \ + a3, b3, c3, d3, \ + st0, st1) \ + vmovdqu64 d2, st0; \ + vmovdqu64 d3, st1; \ + transpose_4x4(a0, a1, a2, a3, d2, d3); \ + transpose_4x4(b0, b1, b2, b3, d2, d3); \ + vmovdqu64 st0, d2; \ + vmovdqu64 st1, d3; \ + \ + vmovdqu64 a0, st0; \ + vmovdqu64 a1, st1; \ + transpose_4x4(c0, c1, c2, c3, a0, a1); \ + transpose_4x4(d0, d1, d2, d3, a0, a1); \ + \ + vbroadcasti64x2 .Lshufb_16x16b, a0; \ + vmovdqu64 st1, a1; \ + vpshufb a0, a2, a2; \ + vpshufb a0, a3, a3; \ + vpshufb a0, b0, b0; \ + vpshufb a0, b1, b1; \ + vpshufb a0, b2, b2; \ + vpshufb a0, b3, b3; \ + vpshufb a0, a1, a1; \ + vpshufb a0, c0, c0; \ + vpshufb a0, c1, c1; \ + vpshufb a0, c2, c2; \ + vpshufb a0, c3, c3; \ + vpshufb a0, d0, d0; \ + vpshufb a0, d1, d1; \ + vpshufb a0, d2, d2; \ + vpshufb a0, d3, d3; \ + vmovdqu64 d3, st1; \ + vmovdqu64 st0, d3; \ + vpshufb a0, d3, a0; \ + vmovdqu64 d2, st0; \ + \ + transpose_4x4(c0, d0, a0, b0, d2, d3); \ + transpose_4x4(c1, d1, a1, b1, d2, d3); \ + vmovdqu64 st0, d2; \ + vmovdqu64 st1, d3; \ + \ + vmovdqu64 b0, st0; \ + vmovdqu64 b1, st1; \ + transpose_4x4(c2, d2, a2, b2, b0, b1); \ + transpose_4x4(c3, d3, a3, b3, b0, b1); \ + vmovdqu64 st0, b0; \ + vmovdqu64 st1, b1; \ + /* does not adjust output bytes inside vectors */ + +/* load blocks to registers and apply pre-whitening */ +#define inpack16_pre(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + rio) \ + vmovdqu64 (0 * 64)(rio), x0; \ + vmovdqu64 (1 * 64)(rio), x1; \ + vmovdqu64 (2 * 64)(rio), x2; \ + vmovdqu64 (3 * 64)(rio), x3; \ + vmovdqu64 (4 * 64)(rio), x4; \ + vmovdqu64 (5 * 64)(rio), x5; \ + vmovdqu64 (6 * 64)(rio), x6; \ + vmovdqu64 (7 * 64)(rio), x7; \ + vmovdqu64 (8 * 64)(rio), y0; \ + vmovdqu64 (9 * 64)(rio), y1; \ + vmovdqu64 (10 * 64)(rio), y2; \ + vmovdqu64 (11 * 64)(rio), y3; \ + vmovdqu64 (12 * 64)(rio), y4; \ + vmovdqu64 (13 * 64)(rio), y5; \ + vmovdqu64 (14 * 64)(rio), y6; \ + vmovdqu64 (15 * 64)(rio), y7; + +/* byteslice pre-whitened blocks and store to temporary memory */ +#define inpack16_post(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_ab, mem_cd) \ + byteslice_16x16b(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + (mem_ab), (mem_cd)); \ + \ + vmovdqu64 x0, 0 * 64(mem_ab); \ + vmovdqu64 x1, 1 * 64(mem_ab); \ + vmovdqu64 x2, 2 * 64(mem_ab); \ + vmovdqu64 x3, 3 * 64(mem_ab); \ + vmovdqu64 x4, 4 * 64(mem_ab); \ + vmovdqu64 x5, 5 * 64(mem_ab); \ + vmovdqu64 x6, 6 * 64(mem_ab); \ + vmovdqu64 x7, 7 * 64(mem_ab); \ + vmovdqu64 y0, 0 * 64(mem_cd); \ + vmovdqu64 y1, 1 * 64(mem_cd); \ + vmovdqu64 y2, 2 * 64(mem_cd); \ + vmovdqu64 y3, 3 * 64(mem_cd); \ + vmovdqu64 y4, 4 * 64(mem_cd); \ + vmovdqu64 y5, 5 * 64(mem_cd); \ + vmovdqu64 y6, 6 * 64(mem_cd); \ + vmovdqu64 y7, 7 * 64(mem_cd); + +#define write_output(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem) \ + vmovdqu64 x0, 0 * 64(mem); \ + vmovdqu64 x1, 1 * 64(mem); \ + vmovdqu64 x2, 2 * 64(mem); \ + vmovdqu64 x3, 3 * 64(mem); \ + vmovdqu64 x4, 4 * 64(mem); \ + vmovdqu64 x5, 5 * 64(mem); \ + vmovdqu64 x6, 6 * 64(mem); \ + vmovdqu64 x7, 7 * 64(mem); \ + vmovdqu64 y0, 8 * 64(mem); \ + vmovdqu64 y1, 9 * 64(mem); \ + vmovdqu64 y2, 10 * 64(mem); \ + vmovdqu64 y3, 11 * 64(mem); \ + vmovdqu64 y4, 12 * 64(mem); \ + vmovdqu64 y5, 13 * 64(mem); \ + vmovdqu64 y6, 14 * 64(mem); \ + vmovdqu64 y7, 15 * 64(mem); \ + +#define aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, idx) \ + vmovdqu64 x0, ((idx + 0) * 64)(mem_tmp); \ + vmovdqu64 x1, ((idx + 1) * 64)(mem_tmp); \ + vmovdqu64 x2, ((idx + 2) * 64)(mem_tmp); \ + vmovdqu64 x3, ((idx + 3) * 64)(mem_tmp); \ + vmovdqu64 x4, ((idx + 4) * 64)(mem_tmp); \ + vmovdqu64 x5, ((idx + 5) * 64)(mem_tmp); \ + vmovdqu64 x6, ((idx + 6) * 64)(mem_tmp); \ + vmovdqu64 x7, ((idx + 7) * 64)(mem_tmp); + +#define aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, idx) \ + vmovdqu64 ((idx + 0) * 64)(mem_tmp), x0; \ + vmovdqu64 ((idx + 1) * 64)(mem_tmp), x1; \ + vmovdqu64 ((idx + 2) * 64)(mem_tmp), x2; \ + vmovdqu64 ((idx + 3) * 64)(mem_tmp), x3; \ + vmovdqu64 ((idx + 4) * 64)(mem_tmp), x4; \ + vmovdqu64 ((idx + 5) * 64)(mem_tmp), x5; \ + vmovdqu64 ((idx + 6) * 64)(mem_tmp), x6; \ + vmovdqu64 ((idx + 7) * 64)(mem_tmp), x7; + +#define aria_ark_16way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + t0, rk, round) \ + /* AddRoundKey */ \ + vpbroadcastb ((round * 16) + 3)(rk), t0; \ + vpxorq t0, x0, x0; \ + vpbroadcastb ((round * 16) + 2)(rk), t0; \ + vpxorq t0, x1, x1; \ + vpbroadcastb ((round * 16) + 1)(rk), t0; \ + vpxorq t0, x2, x2; \ + vpbroadcastb ((round * 16) + 0)(rk), t0; \ + vpxorq t0, x3, x3; \ + vpbroadcastb ((round * 16) + 7)(rk), t0; \ + vpxorq t0, x4, x4; \ + vpbroadcastb ((round * 16) + 6)(rk), t0; \ + vpxorq t0, x5, x5; \ + vpbroadcastb ((round * 16) + 5)(rk), t0; \ + vpxorq t0, x6, x6; \ + vpbroadcastb ((round * 16) + 4)(rk), t0; \ + vpxorq t0, x7, x7; \ + vpbroadcastb ((round * 16) + 11)(rk), t0; \ + vpxorq t0, y0, y0; \ + vpbroadcastb ((round * 16) + 10)(rk), t0; \ + vpxorq t0, y1, y1; \ + vpbroadcastb ((round * 16) + 9)(rk), t0; \ + vpxorq t0, y2, y2; \ + vpbroadcastb ((round * 16) + 8)(rk), t0; \ + vpxorq t0, y3, y3; \ + vpbroadcastb ((round * 16) + 15)(rk), t0; \ + vpxorq t0, y4, y4; \ + vpbroadcastb ((round * 16) + 14)(rk), t0; \ + vpxorq t0, y5, y5; \ + vpbroadcastb ((round * 16) + 13)(rk), t0; \ + vpxorq t0, y6, y6; \ + vpbroadcastb ((round * 16) + 12)(rk), t0; \ + vpxorq t0, y7, y7; + +#define aria_sbox_8way_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + t0, t1, t2, t3, \ + t4, t5, t6, t7) \ + vpbroadcastq .Ltf_s2_bitmatrix, t0; \ + vpbroadcastq .Ltf_inv_bitmatrix, t1; \ + vpbroadcastq .Ltf_id_bitmatrix, t2; \ + vpbroadcastq .Ltf_aff_bitmatrix, t3; \ + vpbroadcastq .Ltf_x2_bitmatrix, t4; \ + vgf2p8affineinvqb $(tf_s2_const), t0, x1, x1; \ + vgf2p8affineinvqb $(tf_s2_const), t0, x5, x5; \ + vgf2p8affineqb $(tf_inv_const), t1, x2, x2; \ + vgf2p8affineqb $(tf_inv_const), t1, x6, x6; \ + vgf2p8affineinvqb $0, t2, x2, x2; \ + vgf2p8affineinvqb $0, t2, x6, x6; \ + vgf2p8affineinvqb $(tf_aff_const), t3, x0, x0; \ + vgf2p8affineinvqb $(tf_aff_const), t3, x4, x4; \ + vgf2p8affineqb $(tf_x2_const), t4, x3, x3; \ + vgf2p8affineqb $(tf_x2_const), t4, x7, x7; \ + vgf2p8affineinvqb $0, t2, x3, x3; \ + vgf2p8affineinvqb $0, t2, x7, x7; + +#define aria_sbox_16way_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + t0, t1, t2, t3, \ + t4, t5, t6, t7) \ + vpbroadcastq .Ltf_s2_bitmatrix, t0; \ + vpbroadcastq .Ltf_inv_bitmatrix, t1; \ + vpbroadcastq .Ltf_id_bitmatrix, t2; \ + vpbroadcastq .Ltf_aff_bitmatrix, t3; \ + vpbroadcastq .Ltf_x2_bitmatrix, t4; \ + vgf2p8affineinvqb $(tf_s2_const), t0, x1, x1; \ + vgf2p8affineinvqb $(tf_s2_const), t0, x5, x5; \ + vgf2p8affineqb $(tf_inv_const), t1, x2, x2; \ + vgf2p8affineqb $(tf_inv_const), t1, x6, x6; \ + vgf2p8affineinvqb $0, t2, x2, x2; \ + vgf2p8affineinvqb $0, t2, x6, x6; \ + vgf2p8affineinvqb $(tf_aff_const), t3, x0, x0; \ + vgf2p8affineinvqb $(tf_aff_const), t3, x4, x4; \ + vgf2p8affineqb $(tf_x2_const), t4, x3, x3; \ + vgf2p8affineqb $(tf_x2_const), t4, x7, x7; \ + vgf2p8affineinvqb $0, t2, x3, x3; \ + vgf2p8affineinvqb $0, t2, x7, x7; \ + vgf2p8affineinvqb $(tf_s2_const), t0, y1, y1; \ + vgf2p8affineinvqb $(tf_s2_const), t0, y5, y5; \ + vgf2p8affineqb $(tf_inv_const), t1, y2, y2; \ + vgf2p8affineqb $(tf_inv_const), t1, y6, y6; \ + vgf2p8affineinvqb $0, t2, y2, y2; \ + vgf2p8affineinvqb $0, t2, y6, y6; \ + vgf2p8affineinvqb $(tf_aff_const), t3, y0, y0; \ + vgf2p8affineinvqb $(tf_aff_const), t3, y4, y4; \ + vgf2p8affineqb $(tf_x2_const), t4, y3, y3; \ + vgf2p8affineqb $(tf_x2_const), t4, y7, y7; \ + vgf2p8affineinvqb $0, t2, y3, y3; \ + vgf2p8affineinvqb $0, t2, y7, y7; + + +#define aria_diff_m(x0, x1, x2, x3, \ + t0, t1, t2, t3) \ + /* T = rotr32(X, 8); */ \ + /* X ^= T */ \ + vpxorq x0, x3, t0; \ + vpxorq x1, x0, t1; \ + vpxorq x2, x1, t2; \ + vpxorq x3, x2, t3; \ + /* X = T ^ rotr(X, 16); */ \ + vpxorq t2, x0, x0; \ + vpxorq x1, t3, t3; \ + vpxorq t0, x2, x2; \ + vpxorq t1, x3, x1; \ + vmovdqu64 t3, x3; + +#define aria_diff_word(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7) \ + /* t1 ^= t2; */ \ + vpxorq y0, x4, x4; \ + vpxorq y1, x5, x5; \ + vpxorq y2, x6, x6; \ + vpxorq y3, x7, x7; \ + \ + /* t2 ^= t3; */ \ + vpxorq y4, y0, y0; \ + vpxorq y5, y1, y1; \ + vpxorq y6, y2, y2; \ + vpxorq y7, y3, y3; \ + \ + /* t0 ^= t1; */ \ + vpxorq x4, x0, x0; \ + vpxorq x5, x1, x1; \ + vpxorq x6, x2, x2; \ + vpxorq x7, x3, x3; \ + \ + /* t3 ^= t1; */ \ + vpxorq x4, y4, y4; \ + vpxorq x5, y5, y5; \ + vpxorq x6, y6, y6; \ + vpxorq x7, y7, y7; \ + \ + /* t2 ^= t0; */ \ + vpxorq x0, y0, y0; \ + vpxorq x1, y1, y1; \ + vpxorq x2, y2, y2; \ + vpxorq x3, y3, y3; \ + \ + /* t1 ^= t2; */ \ + vpxorq y0, x4, x4; \ + vpxorq y1, x5, x5; \ + vpxorq y2, x6, x6; \ + vpxorq y3, x7, x7; + +#define aria_fe_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + z0, z1, z2, z3, \ + z4, z5, z6, z7, \ + mem_tmp, rk, round) \ + aria_ark_16way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, y1, y2, y3, y4, y5, y6, y7, \ + z0, rk, round); \ + \ + aria_sbox_16way_gfni(x2, x3, x0, x1, \ + x6, x7, x4, x5, \ + y2, y3, y0, y1, \ + y6, y7, y4, y5, \ + z0, z1, z2, z3, \ + z4, z5, z6, z7); \ + \ + aria_diff_m(x0, x1, x2, x3, z0, z1, z2, z3); \ + aria_diff_m(x4, x5, x6, x7, z0, z1, z2, z3); \ + aria_diff_m(y0, y1, y2, y3, z0, z1, z2, z3); \ + aria_diff_m(y4, y5, y6, y7, z0, z1, z2, z3); \ + aria_diff_word(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + /* aria_diff_byte() \ + * T3 = ABCD -> BADC \ + * T3 = y4, y5, y6, y7 -> y5, y4, y7, y6 \ + * T0 = ABCD -> CDAB \ + * T0 = x0, x1, x2, x3 -> x2, x3, x0, x1 \ + * T1 = ABCD -> DCBA \ + * T1 = x4, x5, x6, x7 -> x7, x6, x5, x4 \ + */ \ + aria_diff_word(x2, x3, x0, x1, \ + x7, x6, x5, x4, \ + y0, y1, y2, y3, \ + y5, y4, y7, y6); \ + + +#define aria_fo_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + z0, z1, z2, z3, \ + z4, z5, z6, z7, \ + mem_tmp, rk, round) \ + aria_ark_16way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, y1, y2, y3, y4, y5, y6, y7, \ + z0, rk, round); \ + \ + aria_sbox_16way_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + z0, z1, z2, z3, \ + z4, z5, z6, z7); \ + \ + aria_diff_m(x0, x1, x2, x3, z0, z1, z2, z3); \ + aria_diff_m(x4, x5, x6, x7, z0, z1, z2, z3); \ + aria_diff_m(y0, y1, y2, y3, z0, z1, z2, z3); \ + aria_diff_m(y4, y5, y6, y7, z0, z1, z2, z3); \ + aria_diff_word(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + /* aria_diff_byte() \ + * T1 = ABCD -> BADC \ + * T1 = x4, x5, x6, x7 -> x5, x4, x7, x6 \ + * T2 = ABCD -> CDAB \ + * T2 = y0, y1, y2, y3, -> y2, y3, y0, y1 \ + * T3 = ABCD -> DCBA \ + * T3 = y4, y5, y6, y7 -> y7, y6, y5, y4 \ + */ \ + aria_diff_word(x0, x1, x2, x3, \ + x5, x4, x7, x6, \ + y2, y3, y0, y1, \ + y7, y6, y5, y4); + +#define aria_ff_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + z0, z1, z2, z3, \ + z4, z5, z6, z7, \ + mem_tmp, rk, round, last_round) \ + aria_ark_16way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + z0, rk, round); \ + aria_sbox_16way_gfni(x2, x3, x0, x1, \ + x6, x7, x4, x5, \ + y2, y3, y0, y1, \ + y6, y7, y4, y5, \ + z0, z1, z2, z3, \ + z4, z5, z6, z7); \ + aria_ark_16way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + z0, rk, last_round); + + +.section .rodata.cst64, "aM", @progbits, 64 +.align 64 +.Lcounter0123_lo: + .quad 0, 0 + .quad 1, 0 + .quad 2, 0 + .quad 3, 0 + +.section .rodata.cst32.shufb_16x16b, "aM", @progbits, 32 +.align 32 +#define SHUFB_BYTES(idx) \ + 0 + (idx), 4 + (idx), 8 + (idx), 12 + (idx) +.Lshufb_16x16b: + .byte SHUFB_BYTES(0), SHUFB_BYTES(1), SHUFB_BYTES(2), SHUFB_BYTES(3) + .byte SHUFB_BYTES(0), SHUFB_BYTES(1), SHUFB_BYTES(2), SHUFB_BYTES(3) + +.section .rodata.cst16, "aM", @progbits, 16 +.align 16 + +.Lcounter4444_lo: + .quad 4, 0 +.Lcounter8888_lo: + .quad 8, 0 +.Lcounter16161616_lo: + .quad 16, 0 +.Lcounter1111_hi: + .quad 0, 1 + +/* For CTR-mode IV byteswap */ +.Lbswap128_mask: + .byte 0x0f, 0x0e, 0x0d, 0x0c, 0x0b, 0x0a, 0x09, 0x08 + .byte 0x07, 0x06, 0x05, 0x04, 0x03, 0x02, 0x01, 0x00 + +.section .rodata.cst8, "aM", @progbits, 8 +.align 8 +/* AES affine: */ +#define tf_aff_const BV8(1, 1, 0, 0, 0, 1, 1, 0) +.Ltf_aff_bitmatrix: + .quad BM8X8(BV8(1, 0, 0, 0, 1, 1, 1, 1), + BV8(1, 1, 0, 0, 0, 1, 1, 1), + BV8(1, 1, 1, 0, 0, 0, 1, 1), + BV8(1, 1, 1, 1, 0, 0, 0, 1), + BV8(1, 1, 1, 1, 1, 0, 0, 0), + BV8(0, 1, 1, 1, 1, 1, 0, 0), + BV8(0, 0, 1, 1, 1, 1, 1, 0), + BV8(0, 0, 0, 1, 1, 1, 1, 1)) + +/* AES inverse affine: */ +#define tf_inv_const BV8(1, 0, 1, 0, 0, 0, 0, 0) +.Ltf_inv_bitmatrix: + .quad BM8X8(BV8(0, 0, 1, 0, 0, 1, 0, 1), + BV8(1, 0, 0, 1, 0, 0, 1, 0), + BV8(0, 1, 0, 0, 1, 0, 0, 1), + BV8(1, 0, 1, 0, 0, 1, 0, 0), + BV8(0, 1, 0, 1, 0, 0, 1, 0), + BV8(0, 0, 1, 0, 1, 0, 0, 1), + BV8(1, 0, 0, 1, 0, 1, 0, 0), + BV8(0, 1, 0, 0, 1, 0, 1, 0)) + +/* S2: */ +#define tf_s2_const BV8(0, 1, 0, 0, 0, 1, 1, 1) +.Ltf_s2_bitmatrix: + .quad BM8X8(BV8(0, 1, 0, 1, 0, 1, 1, 1), + BV8(0, 0, 1, 1, 1, 1, 1, 1), + BV8(1, 1, 1, 0, 1, 1, 0, 1), + BV8(1, 1, 0, 0, 0, 0, 1, 1), + BV8(0, 1, 0, 0, 0, 0, 1, 1), + BV8(1, 1, 0, 0, 1, 1, 1, 0), + BV8(0, 1, 1, 0, 0, 0, 1, 1), + BV8(1, 1, 1, 1, 0, 1, 1, 0)) + +/* X2: */ +#define tf_x2_const BV8(0, 0, 1, 1, 0, 1, 0, 0) +.Ltf_x2_bitmatrix: + .quad BM8X8(BV8(0, 0, 0, 1, 1, 0, 0, 0), + BV8(0, 0, 1, 0, 0, 1, 1, 0), + BV8(0, 0, 0, 0, 1, 0, 1, 0), + BV8(1, 1, 1, 0, 0, 0, 1, 1), + BV8(1, 1, 1, 0, 1, 1, 0, 0), + BV8(0, 1, 1, 0, 1, 0, 1, 1), + BV8(1, 0, 1, 1, 1, 1, 0, 1), + BV8(1, 0, 0, 1, 0, 0, 1, 1)) + +/* Identity matrix: */ +.Ltf_id_bitmatrix: + .quad BM8X8(BV8(1, 0, 0, 0, 0, 0, 0, 0), + BV8(0, 1, 0, 0, 0, 0, 0, 0), + BV8(0, 0, 1, 0, 0, 0, 0, 0), + BV8(0, 0, 0, 1, 0, 0, 0, 0), + BV8(0, 0, 0, 0, 1, 0, 0, 0), + BV8(0, 0, 0, 0, 0, 1, 0, 0), + BV8(0, 0, 0, 0, 0, 0, 1, 0), + BV8(0, 0, 0, 0, 0, 0, 0, 1)) + +.text +SYM_FUNC_START_LOCAL(__aria_gfni_avx512_crypt_64way) + /* input: + * %r9: rk + * %rsi: dst + * %rdx: src + * %zmm0..%zmm15: byte-sliced blocks + */ + + FRAME_BEGIN + + movq %rsi, %rax; + leaq 8 * 64(%rax), %r8; + + inpack16_post(%zmm0, %zmm1, %zmm2, %zmm3, + %zmm4, %zmm5, %zmm6, %zmm7, + %zmm8, %zmm9, %zmm10, %zmm11, + %zmm12, %zmm13, %zmm14, + %zmm15, %rax, %r8); + aria_fo_gfni(%zmm0, %zmm1, %zmm2, %zmm3, + %zmm4, %zmm5, %zmm6, %zmm7, + %zmm8, %zmm9, %zmm10, %zmm11, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 0); + aria_fe_gfni(%zmm3, %zmm2, %zmm1, %zmm0, + %zmm6, %zmm7, %zmm4, %zmm5, + %zmm9, %zmm8, %zmm11, %zmm10, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 1); + aria_fo_gfni(%zmm0, %zmm1, %zmm2, %zmm3, + %zmm4, %zmm5, %zmm6, %zmm7, + %zmm8, %zmm9, %zmm10, %zmm11, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 2); + aria_fe_gfni(%zmm3, %zmm2, %zmm1, %zmm0, + %zmm6, %zmm7, %zmm4, %zmm5, + %zmm9, %zmm8, %zmm11, %zmm10, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 3); + aria_fo_gfni(%zmm0, %zmm1, %zmm2, %zmm3, + %zmm4, %zmm5, %zmm6, %zmm7, + %zmm8, %zmm9, %zmm10, %zmm11, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 4); + aria_fe_gfni(%zmm3, %zmm2, %zmm1, %zmm0, + %zmm6, %zmm7, %zmm4, %zmm5, + %zmm9, %zmm8, %zmm11, %zmm10, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 5); + aria_fo_gfni(%zmm0, %zmm1, %zmm2, %zmm3, + %zmm4, %zmm5, %zmm6, %zmm7, + %zmm8, %zmm9, %zmm10, %zmm11, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 6); + aria_fe_gfni(%zmm3, %zmm2, %zmm1, %zmm0, + %zmm6, %zmm7, %zmm4, %zmm5, + %zmm9, %zmm8, %zmm11, %zmm10, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 7); + aria_fo_gfni(%zmm0, %zmm1, %zmm2, %zmm3, + %zmm4, %zmm5, %zmm6, %zmm7, + %zmm8, %zmm9, %zmm10, %zmm11, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 8); + aria_fe_gfni(%zmm3, %zmm2, %zmm1, %zmm0, + %zmm6, %zmm7, %zmm4, %zmm5, + %zmm9, %zmm8, %zmm11, %zmm10, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 9); + aria_fo_gfni(%zmm0, %zmm1, %zmm2, %zmm3, + %zmm4, %zmm5, %zmm6, %zmm7, + %zmm8, %zmm9, %zmm10, %zmm11, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 10); + cmpl $12, ARIA_CTX_rounds(CTX); + jne .Laria_gfni_192; + aria_ff_gfni(%zmm3, %zmm2, %zmm1, %zmm0, + %zmm6, %zmm7, %zmm4, %zmm5, + %zmm9, %zmm8, %zmm11, %zmm10, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 11, 12); + jmp .Laria_gfni_end; +.Laria_gfni_192: + aria_fe_gfni(%zmm3, %zmm2, %zmm1, %zmm0, + %zmm6, %zmm7, %zmm4, %zmm5, + %zmm9, %zmm8, %zmm11, %zmm10, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 11); + aria_fo_gfni(%zmm0, %zmm1, %zmm2, %zmm3, + %zmm4, %zmm5, %zmm6, %zmm7, + %zmm8, %zmm9, %zmm10, %zmm11, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 12); + cmpl $14, ARIA_CTX_rounds(CTX); + jne .Laria_gfni_256; + aria_ff_gfni(%zmm3, %zmm2, %zmm1, %zmm0, + %zmm6, %zmm7, %zmm4, %zmm5, + %zmm9, %zmm8, %zmm11, %zmm10, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 13, 14); + jmp .Laria_gfni_end; +.Laria_gfni_256: + aria_fe_gfni(%zmm3, %zmm2, %zmm1, %zmm0, + %zmm6, %zmm7, %zmm4, %zmm5, + %zmm9, %zmm8, %zmm11, %zmm10, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 13); + aria_fo_gfni(%zmm0, %zmm1, %zmm2, %zmm3, + %zmm4, %zmm5, %zmm6, %zmm7, + %zmm8, %zmm9, %zmm10, %zmm11, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 14); + aria_ff_gfni(%zmm3, %zmm2, %zmm1, %zmm0, + %zmm6, %zmm7, %zmm4, %zmm5, + %zmm9, %zmm8, %zmm11, %zmm10, + %zmm12, %zmm13, %zmm14, %zmm15, + %zmm24, %zmm25, %zmm26, %zmm27, + %zmm28, %zmm29, %zmm30, %zmm31, + %rax, %r9, 15, 16); +.Laria_gfni_end: + debyteslice_16x16b(%zmm9, %zmm12, %zmm3, %zmm6, + %zmm8, %zmm13, %zmm2, %zmm7, + %zmm11, %zmm14, %zmm1, %zmm4, + %zmm10, %zmm15, %zmm0, %zmm5, + (%rax), (%r8)); + FRAME_END + RET; +SYM_FUNC_END(__aria_gfni_avx512_crypt_64way) + +SYM_TYPED_FUNC_START(aria_gfni_avx512_encrypt_64way) + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + */ + + FRAME_BEGIN + + leaq ARIA_CTX_enc_key(CTX), %r9; + + inpack16_pre(%zmm0, %zmm1, %zmm2, %zmm3, %zmm4, %zmm5, %zmm6, %zmm7, + %zmm8, %zmm9, %zmm10, %zmm11, %zmm12, %zmm13, %zmm14, + %zmm15, %rdx); + + call __aria_gfni_avx512_crypt_64way; + + write_output(%zmm3, %zmm2, %zmm1, %zmm0, %zmm6, %zmm7, %zmm4, %zmm5, + %zmm9, %zmm8, %zmm11, %zmm10, %zmm12, %zmm13, %zmm14, + %zmm15, %rax); + + FRAME_END + RET; +SYM_FUNC_END(aria_gfni_avx512_encrypt_64way) + +SYM_TYPED_FUNC_START(aria_gfni_avx512_decrypt_64way) + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + */ + + FRAME_BEGIN + + leaq ARIA_CTX_dec_key(CTX), %r9; + + inpack16_pre(%zmm0, %zmm1, %zmm2, %zmm3, %zmm4, %zmm5, %zmm6, %zmm7, + %zmm8, %zmm9, %zmm10, %zmm11, %zmm12, %zmm13, %zmm14, + %zmm15, %rdx); + + call __aria_gfni_avx512_crypt_64way; + + write_output(%zmm3, %zmm2, %zmm1, %zmm0, %zmm6, %zmm7, %zmm4, %zmm5, + %zmm9, %zmm8, %zmm11, %zmm10, %zmm12, %zmm13, %zmm14, + %zmm15, %rax); + + FRAME_END + RET; +SYM_FUNC_END(aria_gfni_avx512_decrypt_64way) + +SYM_FUNC_START_LOCAL(__aria_gfni_avx512_ctr_gen_keystream_64way) + /* input: + * %rdi: ctx + * %rsi: dst + * %rdx: src + * %rcx: keystream + * %r8: iv (big endian, 128bit) + */ + + FRAME_BEGIN + + vbroadcasti64x2 .Lbswap128_mask (%rip), %zmm19; + vmovdqa64 .Lcounter0123_lo (%rip), %zmm21; + vbroadcasti64x2 .Lcounter4444_lo (%rip), %zmm22; + vbroadcasti64x2 .Lcounter8888_lo (%rip), %zmm23; + vbroadcasti64x2 .Lcounter16161616_lo (%rip), %zmm24; + vbroadcasti64x2 .Lcounter1111_hi (%rip), %zmm25; + + /* load IV and byteswap */ + movq 8(%r8), %r11; + movq (%r8), %r10; + bswapq %r11; + bswapq %r10; + vbroadcasti64x2 (%r8), %zmm20; + vpshufb %zmm19, %zmm20, %zmm20; + + /* check need for handling 64-bit overflow and carry */ + cmpq $(0xffffffffffffffff - 64), %r11; + ja .Lload_ctr_carry; + + /* construct IVs */ + vpaddq %zmm21, %zmm20, %zmm0; /* +0:+1:+2:+3 */ + vpaddq %zmm22, %zmm0, %zmm1; /* +4:+5:+6:+7 */ + vpaddq %zmm23, %zmm0, %zmm2; /* +8:+9:+10:+11 */ + vpaddq %zmm23, %zmm1, %zmm3; /* +12:+13:+14:+15 */ + vpaddq %zmm24, %zmm0, %zmm4; /* +16... */ + vpaddq %zmm24, %zmm1, %zmm5; /* +20... */ + vpaddq %zmm24, %zmm2, %zmm6; /* +24... */ + vpaddq %zmm24, %zmm3, %zmm7; /* +28... */ + vpaddq %zmm24, %zmm4, %zmm8; /* +32... */ + vpaddq %zmm24, %zmm5, %zmm9; /* +36... */ + vpaddq %zmm24, %zmm6, %zmm10; /* +40... */ + vpaddq %zmm24, %zmm7, %zmm11; /* +44... */ + vpaddq %zmm24, %zmm8, %zmm12; /* +48... */ + vpaddq %zmm24, %zmm9, %zmm13; /* +52... */ + vpaddq %zmm24, %zmm10, %zmm14; /* +56... */ + vpaddq %zmm24, %zmm11, %zmm15; /* +60... */ + jmp .Lload_ctr_done; + +.Lload_ctr_carry: + /* construct IVs */ + add_le128(%zmm0, %zmm20, %zmm21, %zmm25); /* +0:+1:+2:+3 */ + add_le128(%zmm1, %zmm0, %zmm22, %zmm25); /* +4:+5:+6:+7 */ + add_le128(%zmm2, %zmm0, %zmm23, %zmm25); /* +8:+9:+10:+11 */ + add_le128(%zmm3, %zmm1, %zmm23, %zmm25); /* +12:+13:+14:+15 */ + add_le128(%zmm4, %zmm0, %zmm24, %zmm25); /* +16... */ + add_le128(%zmm5, %zmm1, %zmm24, %zmm25); /* +20... */ + add_le128(%zmm6, %zmm2, %zmm24, %zmm25); /* +24... */ + add_le128(%zmm7, %zmm3, %zmm24, %zmm25); /* +28... */ + add_le128(%zmm8, %zmm4, %zmm24, %zmm25); /* +32... */ + add_le128(%zmm9, %zmm5, %zmm24, %zmm25); /* +36... */ + add_le128(%zmm10, %zmm6, %zmm24, %zmm25); /* +40... */ + add_le128(%zmm11, %zmm7, %zmm24, %zmm25); /* +44... */ + add_le128(%zmm12, %zmm8, %zmm24, %zmm25); /* +48... */ + add_le128(%zmm13, %zmm9, %zmm24, %zmm25); /* +52... */ + add_le128(%zmm14, %zmm10, %zmm24, %zmm25); /* +56... */ + add_le128(%zmm15, %zmm11, %zmm24, %zmm25); /* +60... */ + +.Lload_ctr_done: + /* Byte-swap IVs and update counter. */ + addq $64, %r11; + adcq $0, %r10; + vpshufb %zmm19, %zmm15, %zmm15; + vpshufb %zmm19, %zmm14, %zmm14; + vpshufb %zmm19, %zmm13, %zmm13; + vpshufb %zmm19, %zmm12, %zmm12; + vpshufb %zmm19, %zmm11, %zmm11; + vpshufb %zmm19, %zmm10, %zmm10; + vpshufb %zmm19, %zmm9, %zmm9; + vpshufb %zmm19, %zmm8, %zmm8; + bswapq %r11; + bswapq %r10; + vpshufb %zmm19, %zmm7, %zmm7; + vpshufb %zmm19, %zmm6, %zmm6; + vpshufb %zmm19, %zmm5, %zmm5; + vpshufb %zmm19, %zmm4, %zmm4; + vpshufb %zmm19, %zmm3, %zmm3; + vpshufb %zmm19, %zmm2, %zmm2; + vpshufb %zmm19, %zmm1, %zmm1; + vpshufb %zmm19, %zmm0, %zmm0; + movq %r11, 8(%r8); + movq %r10, (%r8); + + FRAME_END + RET; +SYM_FUNC_END(__aria_gfni_avx512_ctr_gen_keystream_64way) + +SYM_TYPED_FUNC_START(aria_gfni_avx512_ctr_crypt_64way) + /* input: + * %rdi: ctx + * %rsi: dst + * %rdx: src + * %rcx: keystream + * %r8: iv (big endian, 128bit) + */ + FRAME_BEGIN + + call __aria_gfni_avx512_ctr_gen_keystream_64way + + leaq (%rsi), %r10; + leaq (%rdx), %r11; + leaq (%rcx), %rsi; + leaq (%rcx), %rdx; + leaq ARIA_CTX_enc_key(CTX), %r9; + + call __aria_gfni_avx512_crypt_64way; + + vpxorq (0 * 64)(%r11), %zmm3, %zmm3; + vpxorq (1 * 64)(%r11), %zmm2, %zmm2; + vpxorq (2 * 64)(%r11), %zmm1, %zmm1; + vpxorq (3 * 64)(%r11), %zmm0, %zmm0; + vpxorq (4 * 64)(%r11), %zmm6, %zmm6; + vpxorq (5 * 64)(%r11), %zmm7, %zmm7; + vpxorq (6 * 64)(%r11), %zmm4, %zmm4; + vpxorq (7 * 64)(%r11), %zmm5, %zmm5; + vpxorq (8 * 64)(%r11), %zmm9, %zmm9; + vpxorq (9 * 64)(%r11), %zmm8, %zmm8; + vpxorq (10 * 64)(%r11), %zmm11, %zmm11; + vpxorq (11 * 64)(%r11), %zmm10, %zmm10; + vpxorq (12 * 64)(%r11), %zmm12, %zmm12; + vpxorq (13 * 64)(%r11), %zmm13, %zmm13; + vpxorq (14 * 64)(%r11), %zmm14, %zmm14; + vpxorq (15 * 64)(%r11), %zmm15, %zmm15; + write_output(%zmm3, %zmm2, %zmm1, %zmm0, %zmm6, %zmm7, %zmm4, %zmm5, + %zmm9, %zmm8, %zmm11, %zmm10, %zmm12, %zmm13, %zmm14, + %zmm15, %r10); + + FRAME_END + RET; +SYM_FUNC_END(aria_gfni_avx512_ctr_crypt_64way) diff --git a/arch/x86/crypto/aria_aesni_avx2_glue.c b/arch/x86/crypto/aria_aesni_avx2_glue.c new file mode 100644 index 000000000000..87a11804fc77 --- /dev/null +++ b/arch/x86/crypto/aria_aesni_avx2_glue.c @@ -0,0 +1,254 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Glue Code for the AVX2/AES-NI/GFNI assembler implementation of the ARIA Cipher + * + * Copyright (c) 2022 Taehee Yoo <ap420073@gmail.com> + */ + +#include <crypto/algapi.h> +#include <crypto/internal/simd.h> +#include <crypto/aria.h> +#include <linux/crypto.h> +#include <linux/err.h> +#include <linux/module.h> +#include <linux/types.h> + +#include "ecb_cbc_helpers.h" +#include "aria-avx.h" + +asmlinkage void aria_aesni_avx2_encrypt_32way(const void *ctx, u8 *dst, + const u8 *src); +EXPORT_SYMBOL_GPL(aria_aesni_avx2_encrypt_32way); +asmlinkage void aria_aesni_avx2_decrypt_32way(const void *ctx, u8 *dst, + const u8 *src); +EXPORT_SYMBOL_GPL(aria_aesni_avx2_decrypt_32way); +asmlinkage void aria_aesni_avx2_ctr_crypt_32way(const void *ctx, u8 *dst, + const u8 *src, + u8 *keystream, u8 *iv); +EXPORT_SYMBOL_GPL(aria_aesni_avx2_ctr_crypt_32way); +#ifdef CONFIG_AS_GFNI +asmlinkage void aria_aesni_avx2_gfni_encrypt_32way(const void *ctx, u8 *dst, + const u8 *src); +EXPORT_SYMBOL_GPL(aria_aesni_avx2_gfni_encrypt_32way); +asmlinkage void aria_aesni_avx2_gfni_decrypt_32way(const void *ctx, u8 *dst, + const u8 *src); +EXPORT_SYMBOL_GPL(aria_aesni_avx2_gfni_decrypt_32way); +asmlinkage void aria_aesni_avx2_gfni_ctr_crypt_32way(const void *ctx, u8 *dst, + const u8 *src, + u8 *keystream, u8 *iv); +EXPORT_SYMBOL_GPL(aria_aesni_avx2_gfni_ctr_crypt_32way); +#endif /* CONFIG_AS_GFNI */ + +static struct aria_avx_ops aria_ops; + +struct aria_avx2_request_ctx { + u8 keystream[ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE]; +}; + +static int ecb_do_encrypt(struct skcipher_request *req, const u32 *rkey) +{ + ECB_WALK_START(req, ARIA_BLOCK_SIZE, ARIA_AESNI_PARALLEL_BLOCKS); + ECB_BLOCK(ARIA_AESNI_AVX2_PARALLEL_BLOCKS, aria_ops.aria_encrypt_32way); + ECB_BLOCK(ARIA_AESNI_PARALLEL_BLOCKS, aria_ops.aria_encrypt_16way); + ECB_BLOCK(1, aria_encrypt); + ECB_WALK_END(); +} + +static int ecb_do_decrypt(struct skcipher_request *req, const u32 *rkey) +{ + ECB_WALK_START(req, ARIA_BLOCK_SIZE, ARIA_AESNI_PARALLEL_BLOCKS); + ECB_BLOCK(ARIA_AESNI_AVX2_PARALLEL_BLOCKS, aria_ops.aria_decrypt_32way); + ECB_BLOCK(ARIA_AESNI_PARALLEL_BLOCKS, aria_ops.aria_decrypt_16way); + ECB_BLOCK(1, aria_decrypt); + ECB_WALK_END(); +} + +static int aria_avx2_ecb_encrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct aria_ctx *ctx = crypto_skcipher_ctx(tfm); + + return ecb_do_encrypt(req, ctx->enc_key[0]); +} + +static int aria_avx2_ecb_decrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct aria_ctx *ctx = crypto_skcipher_ctx(tfm); + + return ecb_do_decrypt(req, ctx->dec_key[0]); +} + +static int aria_avx2_set_key(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keylen) +{ + return aria_set_key(&tfm->base, key, keylen); +} + +static int aria_avx2_ctr_encrypt(struct skcipher_request *req) +{ + struct aria_avx2_request_ctx *req_ctx = skcipher_request_ctx(req); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct aria_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; + int err; + + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes) > 0) { + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + + while (nbytes >= ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE) { + kernel_fpu_begin(); + aria_ops.aria_ctr_crypt_32way(ctx, dst, src, + &req_ctx->keystream[0], + walk.iv); + kernel_fpu_end(); + dst += ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE; + src += ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE; + nbytes -= ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE; + } + + while (nbytes >= ARIA_AESNI_PARALLEL_BLOCK_SIZE) { + kernel_fpu_begin(); + aria_ops.aria_ctr_crypt_16way(ctx, dst, src, + &req_ctx->keystream[0], + walk.iv); + kernel_fpu_end(); + dst += ARIA_AESNI_PARALLEL_BLOCK_SIZE; + src += ARIA_AESNI_PARALLEL_BLOCK_SIZE; + nbytes -= ARIA_AESNI_PARALLEL_BLOCK_SIZE; + } + + while (nbytes >= ARIA_BLOCK_SIZE) { + memcpy(&req_ctx->keystream[0], walk.iv, ARIA_BLOCK_SIZE); + crypto_inc(walk.iv, ARIA_BLOCK_SIZE); + + aria_encrypt(ctx, &req_ctx->keystream[0], + &req_ctx->keystream[0]); + + crypto_xor_cpy(dst, src, &req_ctx->keystream[0], + ARIA_BLOCK_SIZE); + dst += ARIA_BLOCK_SIZE; + src += ARIA_BLOCK_SIZE; + nbytes -= ARIA_BLOCK_SIZE; + } + + if (walk.nbytes == walk.total && nbytes > 0) { + memcpy(&req_ctx->keystream[0], walk.iv, + ARIA_BLOCK_SIZE); + crypto_inc(walk.iv, ARIA_BLOCK_SIZE); + + aria_encrypt(ctx, &req_ctx->keystream[0], + &req_ctx->keystream[0]); + + crypto_xor_cpy(dst, src, &req_ctx->keystream[0], + nbytes); + dst += nbytes; + src += nbytes; + nbytes = 0; + } + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} + +static int aria_avx2_init_tfm(struct crypto_skcipher *tfm) +{ + crypto_skcipher_set_reqsize(tfm, sizeof(struct aria_avx2_request_ctx)); + + return 0; +} + +static struct skcipher_alg aria_algs[] = { + { + .base.cra_name = "__ecb(aria)", + .base.cra_driver_name = "__ecb-aria-avx2", + .base.cra_priority = 500, + .base.cra_flags = CRYPTO_ALG_INTERNAL, + .base.cra_blocksize = ARIA_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct aria_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = ARIA_MIN_KEY_SIZE, + .max_keysize = ARIA_MAX_KEY_SIZE, + .setkey = aria_avx2_set_key, + .encrypt = aria_avx2_ecb_encrypt, + .decrypt = aria_avx2_ecb_decrypt, + }, { + .base.cra_name = "__ctr(aria)", + .base.cra_driver_name = "__ctr-aria-avx2", + .base.cra_priority = 500, + .base.cra_flags = CRYPTO_ALG_INTERNAL | + CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct aria_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = ARIA_MIN_KEY_SIZE, + .max_keysize = ARIA_MAX_KEY_SIZE, + .ivsize = ARIA_BLOCK_SIZE, + .chunksize = ARIA_BLOCK_SIZE, + .setkey = aria_avx2_set_key, + .encrypt = aria_avx2_ctr_encrypt, + .decrypt = aria_avx2_ctr_encrypt, + .init = aria_avx2_init_tfm, + } +}; + +static struct simd_skcipher_alg *aria_simd_algs[ARRAY_SIZE(aria_algs)]; + +static int __init aria_avx2_init(void) +{ + const char *feature_name; + + if (!boot_cpu_has(X86_FEATURE_AVX) || + !boot_cpu_has(X86_FEATURE_AVX2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE)) { + pr_info("AVX2 or AES-NI instructions are not detected.\n"); + return -ENODEV; + } + + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, + &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); + return -ENODEV; + } + + if (boot_cpu_has(X86_FEATURE_GFNI) && IS_ENABLED(CONFIG_AS_GFNI)) { + aria_ops.aria_encrypt_16way = aria_aesni_avx_gfni_encrypt_16way; + aria_ops.aria_decrypt_16way = aria_aesni_avx_gfni_decrypt_16way; + aria_ops.aria_ctr_crypt_16way = aria_aesni_avx_gfni_ctr_crypt_16way; + aria_ops.aria_encrypt_32way = aria_aesni_avx2_gfni_encrypt_32way; + aria_ops.aria_decrypt_32way = aria_aesni_avx2_gfni_decrypt_32way; + aria_ops.aria_ctr_crypt_32way = aria_aesni_avx2_gfni_ctr_crypt_32way; + } else { + aria_ops.aria_encrypt_16way = aria_aesni_avx_encrypt_16way; + aria_ops.aria_decrypt_16way = aria_aesni_avx_decrypt_16way; + aria_ops.aria_ctr_crypt_16way = aria_aesni_avx_ctr_crypt_16way; + aria_ops.aria_encrypt_32way = aria_aesni_avx2_encrypt_32way; + aria_ops.aria_decrypt_32way = aria_aesni_avx2_decrypt_32way; + aria_ops.aria_ctr_crypt_32way = aria_aesni_avx2_ctr_crypt_32way; + } + + return simd_register_skciphers_compat(aria_algs, + ARRAY_SIZE(aria_algs), + aria_simd_algs); +} + +static void __exit aria_avx2_exit(void) +{ + simd_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs), + aria_simd_algs); +} + +module_init(aria_avx2_init); +module_exit(aria_avx2_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Taehee Yoo <ap420073@gmail.com>"); +MODULE_DESCRIPTION("ARIA Cipher Algorithm, AVX2/AES-NI/GFNI optimized"); +MODULE_ALIAS_CRYPTO("aria"); +MODULE_ALIAS_CRYPTO("aria-aesni-avx2"); diff --git a/arch/x86/crypto/aria_aesni_avx_glue.c b/arch/x86/crypto/aria_aesni_avx_glue.c index c561ea4fefa5..4e1516b76669 100644 --- a/arch/x86/crypto/aria_aesni_avx_glue.c +++ b/arch/x86/crypto/aria_aesni_avx_glue.c @@ -18,21 +18,33 @@ asmlinkage void aria_aesni_avx_encrypt_16way(const void *ctx, u8 *dst, const u8 *src); +EXPORT_SYMBOL_GPL(aria_aesni_avx_encrypt_16way); asmlinkage void aria_aesni_avx_decrypt_16way(const void *ctx, u8 *dst, const u8 *src); +EXPORT_SYMBOL_GPL(aria_aesni_avx_decrypt_16way); asmlinkage void aria_aesni_avx_ctr_crypt_16way(const void *ctx, u8 *dst, const u8 *src, u8 *keystream, u8 *iv); +EXPORT_SYMBOL_GPL(aria_aesni_avx_ctr_crypt_16way); +#ifdef CONFIG_AS_GFNI asmlinkage void aria_aesni_avx_gfni_encrypt_16way(const void *ctx, u8 *dst, const u8 *src); +EXPORT_SYMBOL_GPL(aria_aesni_avx_gfni_encrypt_16way); asmlinkage void aria_aesni_avx_gfni_decrypt_16way(const void *ctx, u8 *dst, const u8 *src); +EXPORT_SYMBOL_GPL(aria_aesni_avx_gfni_decrypt_16way); asmlinkage void aria_aesni_avx_gfni_ctr_crypt_16way(const void *ctx, u8 *dst, const u8 *src, u8 *keystream, u8 *iv); +EXPORT_SYMBOL_GPL(aria_aesni_avx_gfni_ctr_crypt_16way); +#endif /* CONFIG_AS_GFNI */ static struct aria_avx_ops aria_ops; +struct aria_avx_request_ctx { + u8 keystream[ARIA_AESNI_PARALLEL_BLOCK_SIZE]; +}; + static int ecb_do_encrypt(struct skcipher_request *req, const u32 *rkey) { ECB_WALK_START(req, ARIA_BLOCK_SIZE, ARIA_AESNI_PARALLEL_BLOCKS); @@ -73,6 +85,7 @@ static int aria_avx_set_key(struct crypto_skcipher *tfm, const u8 *key, static int aria_avx_ctr_encrypt(struct skcipher_request *req) { + struct aria_avx_request_ctx *req_ctx = skcipher_request_ctx(req); struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct aria_ctx *ctx = crypto_skcipher_ctx(tfm); struct skcipher_walk walk; @@ -86,10 +99,9 @@ static int aria_avx_ctr_encrypt(struct skcipher_request *req) u8 *dst = walk.dst.virt.addr; while (nbytes >= ARIA_AESNI_PARALLEL_BLOCK_SIZE) { - u8 keystream[ARIA_AESNI_PARALLEL_BLOCK_SIZE]; - kernel_fpu_begin(); - aria_ops.aria_ctr_crypt_16way(ctx, dst, src, keystream, + aria_ops.aria_ctr_crypt_16way(ctx, dst, src, + &req_ctx->keystream[0], walk.iv); kernel_fpu_end(); dst += ARIA_AESNI_PARALLEL_BLOCK_SIZE; @@ -98,28 +110,29 @@ static int aria_avx_ctr_encrypt(struct skcipher_request *req) } while (nbytes >= ARIA_BLOCK_SIZE) { - u8 keystream[ARIA_BLOCK_SIZE]; - - memcpy(keystream, walk.iv, ARIA_BLOCK_SIZE); + memcpy(&req_ctx->keystream[0], walk.iv, ARIA_BLOCK_SIZE); crypto_inc(walk.iv, ARIA_BLOCK_SIZE); - aria_encrypt(ctx, keystream, keystream); + aria_encrypt(ctx, &req_ctx->keystream[0], + &req_ctx->keystream[0]); - crypto_xor_cpy(dst, src, keystream, ARIA_BLOCK_SIZE); + crypto_xor_cpy(dst, src, &req_ctx->keystream[0], + ARIA_BLOCK_SIZE); dst += ARIA_BLOCK_SIZE; src += ARIA_BLOCK_SIZE; nbytes -= ARIA_BLOCK_SIZE; } if (walk.nbytes == walk.total && nbytes > 0) { - u8 keystream[ARIA_BLOCK_SIZE]; - - memcpy(keystream, walk.iv, ARIA_BLOCK_SIZE); + memcpy(&req_ctx->keystream[0], walk.iv, + ARIA_BLOCK_SIZE); crypto_inc(walk.iv, ARIA_BLOCK_SIZE); - aria_encrypt(ctx, keystream, keystream); + aria_encrypt(ctx, &req_ctx->keystream[0], + &req_ctx->keystream[0]); - crypto_xor_cpy(dst, src, keystream, nbytes); + crypto_xor_cpy(dst, src, &req_ctx->keystream[0], + nbytes); dst += nbytes; src += nbytes; nbytes = 0; @@ -130,6 +143,13 @@ static int aria_avx_ctr_encrypt(struct skcipher_request *req) return err; } +static int aria_avx_init_tfm(struct crypto_skcipher *tfm) +{ + crypto_skcipher_set_reqsize(tfm, sizeof(struct aria_avx_request_ctx)); + + return 0; +} + static struct skcipher_alg aria_algs[] = { { .base.cra_name = "__ecb(aria)", @@ -160,6 +180,7 @@ static struct skcipher_alg aria_algs[] = { .setkey = aria_avx_set_key, .encrypt = aria_avx_ctr_encrypt, .decrypt = aria_avx_ctr_encrypt, + .init = aria_avx_init_tfm, } }; @@ -182,7 +203,7 @@ static int __init aria_avx_init(void) return -ENODEV; } - if (boot_cpu_has(X86_FEATURE_GFNI)) { + if (boot_cpu_has(X86_FEATURE_GFNI) && IS_ENABLED(CONFIG_AS_GFNI)) { aria_ops.aria_encrypt_16way = aria_aesni_avx_gfni_encrypt_16way; aria_ops.aria_decrypt_16way = aria_aesni_avx_gfni_decrypt_16way; aria_ops.aria_ctr_crypt_16way = aria_aesni_avx_gfni_ctr_crypt_16way; diff --git a/arch/x86/crypto/aria_gfni_avx512_glue.c b/arch/x86/crypto/aria_gfni_avx512_glue.c new file mode 100644 index 000000000000..f4a2208d2638 --- /dev/null +++ b/arch/x86/crypto/aria_gfni_avx512_glue.c @@ -0,0 +1,250 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Glue Code for the AVX512/GFNI assembler implementation of the ARIA Cipher + * + * Copyright (c) 2022 Taehee Yoo <ap420073@gmail.com> + */ + +#include <crypto/algapi.h> +#include <crypto/internal/simd.h> +#include <crypto/aria.h> +#include <linux/crypto.h> +#include <linux/err.h> +#include <linux/module.h> +#include <linux/types.h> + +#include "ecb_cbc_helpers.h" +#include "aria-avx.h" + +asmlinkage void aria_gfni_avx512_encrypt_64way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_gfni_avx512_decrypt_64way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_gfni_avx512_ctr_crypt_64way(const void *ctx, u8 *dst, + const u8 *src, + u8 *keystream, u8 *iv); + +static struct aria_avx_ops aria_ops; + +struct aria_avx512_request_ctx { + u8 keystream[ARIA_GFNI_AVX512_PARALLEL_BLOCK_SIZE]; +}; + +static int ecb_do_encrypt(struct skcipher_request *req, const u32 *rkey) +{ + ECB_WALK_START(req, ARIA_BLOCK_SIZE, ARIA_AESNI_PARALLEL_BLOCKS); + ECB_BLOCK(ARIA_GFNI_AVX512_PARALLEL_BLOCKS, aria_ops.aria_encrypt_64way); + ECB_BLOCK(ARIA_AESNI_AVX2_PARALLEL_BLOCKS, aria_ops.aria_encrypt_32way); + ECB_BLOCK(ARIA_AESNI_PARALLEL_BLOCKS, aria_ops.aria_encrypt_16way); + ECB_BLOCK(1, aria_encrypt); + ECB_WALK_END(); +} + +static int ecb_do_decrypt(struct skcipher_request *req, const u32 *rkey) +{ + ECB_WALK_START(req, ARIA_BLOCK_SIZE, ARIA_AESNI_PARALLEL_BLOCKS); + ECB_BLOCK(ARIA_GFNI_AVX512_PARALLEL_BLOCKS, aria_ops.aria_decrypt_64way); + ECB_BLOCK(ARIA_AESNI_AVX2_PARALLEL_BLOCKS, aria_ops.aria_decrypt_32way); + ECB_BLOCK(ARIA_AESNI_PARALLEL_BLOCKS, aria_ops.aria_decrypt_16way); + ECB_BLOCK(1, aria_decrypt); + ECB_WALK_END(); +} + +static int aria_avx512_ecb_encrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct aria_ctx *ctx = crypto_skcipher_ctx(tfm); + + return ecb_do_encrypt(req, ctx->enc_key[0]); +} + +static int aria_avx512_ecb_decrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct aria_ctx *ctx = crypto_skcipher_ctx(tfm); + + return ecb_do_decrypt(req, ctx->dec_key[0]); +} + +static int aria_avx512_set_key(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keylen) +{ + return aria_set_key(&tfm->base, key, keylen); +} + +static int aria_avx512_ctr_encrypt(struct skcipher_request *req) +{ + struct aria_avx512_request_ctx *req_ctx = skcipher_request_ctx(req); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct aria_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; + int err; + + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes) > 0) { + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + + while (nbytes >= ARIA_GFNI_AVX512_PARALLEL_BLOCK_SIZE) { + kernel_fpu_begin(); + aria_ops.aria_ctr_crypt_64way(ctx, dst, src, + &req_ctx->keystream[0], + walk.iv); + kernel_fpu_end(); + dst += ARIA_GFNI_AVX512_PARALLEL_BLOCK_SIZE; + src += ARIA_GFNI_AVX512_PARALLEL_BLOCK_SIZE; + nbytes -= ARIA_GFNI_AVX512_PARALLEL_BLOCK_SIZE; + } + + while (nbytes >= ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE) { + kernel_fpu_begin(); + aria_ops.aria_ctr_crypt_32way(ctx, dst, src, + &req_ctx->keystream[0], + walk.iv); + kernel_fpu_end(); + dst += ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE; + src += ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE; + nbytes -= ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE; + } + + while (nbytes >= ARIA_AESNI_PARALLEL_BLOCK_SIZE) { + kernel_fpu_begin(); + aria_ops.aria_ctr_crypt_16way(ctx, dst, src, + &req_ctx->keystream[0], + walk.iv); + kernel_fpu_end(); + dst += ARIA_AESNI_PARALLEL_BLOCK_SIZE; + src += ARIA_AESNI_PARALLEL_BLOCK_SIZE; + nbytes -= ARIA_AESNI_PARALLEL_BLOCK_SIZE; + } + + while (nbytes >= ARIA_BLOCK_SIZE) { + memcpy(&req_ctx->keystream[0], walk.iv, + ARIA_BLOCK_SIZE); + crypto_inc(walk.iv, ARIA_BLOCK_SIZE); + + aria_encrypt(ctx, &req_ctx->keystream[0], + &req_ctx->keystream[0]); + + crypto_xor_cpy(dst, src, &req_ctx->keystream[0], + ARIA_BLOCK_SIZE); + dst += ARIA_BLOCK_SIZE; + src += ARIA_BLOCK_SIZE; + nbytes -= ARIA_BLOCK_SIZE; + } + + if (walk.nbytes == walk.total && nbytes > 0) { + memcpy(&req_ctx->keystream[0], walk.iv, + ARIA_BLOCK_SIZE); + crypto_inc(walk.iv, ARIA_BLOCK_SIZE); + + aria_encrypt(ctx, &req_ctx->keystream[0], + &req_ctx->keystream[0]); + + crypto_xor_cpy(dst, src, &req_ctx->keystream[0], + nbytes); + dst += nbytes; + src += nbytes; + nbytes = 0; + } + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} + +static int aria_avx512_init_tfm(struct crypto_skcipher *tfm) +{ + crypto_skcipher_set_reqsize(tfm, + sizeof(struct aria_avx512_request_ctx)); + + return 0; +} + +static struct skcipher_alg aria_algs[] = { + { + .base.cra_name = "__ecb(aria)", + .base.cra_driver_name = "__ecb-aria-avx512", + .base.cra_priority = 600, + .base.cra_flags = CRYPTO_ALG_INTERNAL, + .base.cra_blocksize = ARIA_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct aria_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = ARIA_MIN_KEY_SIZE, + .max_keysize = ARIA_MAX_KEY_SIZE, + .setkey = aria_avx512_set_key, + .encrypt = aria_avx512_ecb_encrypt, + .decrypt = aria_avx512_ecb_decrypt, + }, { + .base.cra_name = "__ctr(aria)", + .base.cra_driver_name = "__ctr-aria-avx512", + .base.cra_priority = 600, + .base.cra_flags = CRYPTO_ALG_INTERNAL | + CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct aria_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = ARIA_MIN_KEY_SIZE, + .max_keysize = ARIA_MAX_KEY_SIZE, + .ivsize = ARIA_BLOCK_SIZE, + .chunksize = ARIA_BLOCK_SIZE, + .setkey = aria_avx512_set_key, + .encrypt = aria_avx512_ctr_encrypt, + .decrypt = aria_avx512_ctr_encrypt, + .init = aria_avx512_init_tfm, + } +}; + +static struct simd_skcipher_alg *aria_simd_algs[ARRAY_SIZE(aria_algs)]; + +static int __init aria_avx512_init(void) +{ + const char *feature_name; + + if (!boot_cpu_has(X86_FEATURE_AVX) || + !boot_cpu_has(X86_FEATURE_AVX2) || + !boot_cpu_has(X86_FEATURE_AVX512F) || + !boot_cpu_has(X86_FEATURE_AVX512VL) || + !boot_cpu_has(X86_FEATURE_GFNI) || + !boot_cpu_has(X86_FEATURE_OSXSAVE)) { + pr_info("AVX512/GFNI instructions are not detected.\n"); + return -ENODEV; + } + + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | + XFEATURE_MASK_AVX512, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); + return -ENODEV; + } + + aria_ops.aria_encrypt_16way = aria_aesni_avx_gfni_encrypt_16way; + aria_ops.aria_decrypt_16way = aria_aesni_avx_gfni_decrypt_16way; + aria_ops.aria_ctr_crypt_16way = aria_aesni_avx_gfni_ctr_crypt_16way; + aria_ops.aria_encrypt_32way = aria_aesni_avx2_gfni_encrypt_32way; + aria_ops.aria_decrypt_32way = aria_aesni_avx2_gfni_decrypt_32way; + aria_ops.aria_ctr_crypt_32way = aria_aesni_avx2_gfni_ctr_crypt_32way; + aria_ops.aria_encrypt_64way = aria_gfni_avx512_encrypt_64way; + aria_ops.aria_decrypt_64way = aria_gfni_avx512_decrypt_64way; + aria_ops.aria_ctr_crypt_64way = aria_gfni_avx512_ctr_crypt_64way; + + return simd_register_skciphers_compat(aria_algs, + ARRAY_SIZE(aria_algs), + aria_simd_algs); +} + +static void __exit aria_avx512_exit(void) +{ + simd_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs), + aria_simd_algs); +} + +module_init(aria_avx512_init); +module_exit(aria_avx512_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Taehee Yoo <ap420073@gmail.com>"); +MODULE_DESCRIPTION("ARIA Cipher Algorithm, AVX512/GFNI optimized"); +MODULE_ALIAS_CRYPTO("aria"); +MODULE_ALIAS_CRYPTO("aria-gfni-avx512"); diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S index 4a43e072d2d1..e88c8e4f013c 100644 --- a/arch/x86/crypto/blowfish-x86_64-asm_64.S +++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S @@ -6,7 +6,6 @@ */ #include <linux/linkage.h> -#include <linux/cfi_types.h> .file "blowfish-x86_64-asm.S" .text @@ -100,16 +99,11 @@ bswapq RX0; \ movq RX0, (RIO); -#define xor_block() \ - bswapq RX0; \ - xorq RX0, (RIO); - -SYM_FUNC_START(__blowfish_enc_blk) +SYM_FUNC_START(blowfish_enc_blk) /* input: * %rdi: ctx * %rsi: dst * %rdx: src - * %rcx: bool, if true: xor output */ movq %r12, %r11; @@ -130,19 +124,13 @@ SYM_FUNC_START(__blowfish_enc_blk) add_roundkey_enc(16); movq %r11, %r12; - movq %r10, RIO; - test %cl, %cl; - jnz .L__enc_xor; write_block(); RET; -.L__enc_xor: - xor_block(); - RET; -SYM_FUNC_END(__blowfish_enc_blk) +SYM_FUNC_END(blowfish_enc_blk) -SYM_TYPED_FUNC_START(blowfish_dec_blk) +SYM_FUNC_START(blowfish_dec_blk) /* input: * %rdi: ctx * %rsi: dst @@ -272,28 +260,26 @@ SYM_FUNC_END(blowfish_dec_blk) movq RX3, 24(RIO); #define xor_block4() \ - bswapq RX0; \ - xorq RX0, (RIO); \ + movq (RIO), RT0; \ + bswapq RT0; \ + xorq RT0, RX1; \ \ - bswapq RX1; \ - xorq RX1, 8(RIO); \ + movq 8(RIO), RT2; \ + bswapq RT2; \ + xorq RT2, RX2; \ \ - bswapq RX2; \ - xorq RX2, 16(RIO); \ - \ - bswapq RX3; \ - xorq RX3, 24(RIO); + movq 16(RIO), RT3; \ + bswapq RT3; \ + xorq RT3, RX3; -SYM_FUNC_START(__blowfish_enc_blk_4way) +SYM_FUNC_START(blowfish_enc_blk_4way) /* input: * %rdi: ctx * %rsi: dst * %rdx: src - * %rcx: bool, if true: xor output */ pushq %r12; pushq %rbx; - pushq %rcx; movq %rdi, CTX movq %rsi, %r11; @@ -313,37 +299,28 @@ SYM_FUNC_START(__blowfish_enc_blk_4way) round_enc4(14); add_preloaded_roundkey4(); - popq %r12; movq %r11, RIO; - - test %r12b, %r12b; - jnz .L__enc_xor4; - write_block4(); popq %rbx; popq %r12; RET; +SYM_FUNC_END(blowfish_enc_blk_4way) -.L__enc_xor4: - xor_block4(); - - popq %rbx; - popq %r12; - RET; -SYM_FUNC_END(__blowfish_enc_blk_4way) - -SYM_TYPED_FUNC_START(blowfish_dec_blk_4way) +SYM_FUNC_START(__blowfish_dec_blk_4way) /* input: * %rdi: ctx * %rsi: dst * %rdx: src + * %rcx: cbc (bool) */ pushq %r12; pushq %rbx; + pushq %rcx; + pushq %rdx; movq %rdi, CTX; - movq %rsi, %r11 + movq %rsi, %r11; movq %rdx, RIO; preload_roundkey_dec(17); @@ -359,6 +336,14 @@ SYM_TYPED_FUNC_START(blowfish_dec_blk_4way) round_dec4(3); add_preloaded_roundkey4(); + popq RIO; + popq %r12; + testq %r12, %r12; + jz .L_no_cbc_xor; + + xor_block4(); + +.L_no_cbc_xor: movq %r11, RIO; write_block4(); @@ -366,4 +351,4 @@ SYM_TYPED_FUNC_START(blowfish_dec_blk_4way) popq %r12; RET; -SYM_FUNC_END(blowfish_dec_blk_4way) +SYM_FUNC_END(__blowfish_dec_blk_4way) diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c index 019c64c1340a..552f2df0643f 100644 --- a/arch/x86/crypto/blowfish_glue.c +++ b/arch/x86/crypto/blowfish_glue.c @@ -16,26 +16,28 @@ #include <linux/module.h> #include <linux/types.h> +#include "ecb_cbc_helpers.h" + /* regular block cipher functions */ -asmlinkage void __blowfish_enc_blk(struct bf_ctx *ctx, u8 *dst, const u8 *src, - bool xor); +asmlinkage void blowfish_enc_blk(struct bf_ctx *ctx, u8 *dst, const u8 *src); asmlinkage void blowfish_dec_blk(struct bf_ctx *ctx, u8 *dst, const u8 *src); /* 4-way parallel cipher functions */ -asmlinkage void __blowfish_enc_blk_4way(struct bf_ctx *ctx, u8 *dst, - const u8 *src, bool xor); -asmlinkage void blowfish_dec_blk_4way(struct bf_ctx *ctx, u8 *dst, +asmlinkage void blowfish_enc_blk_4way(struct bf_ctx *ctx, u8 *dst, const u8 *src); +asmlinkage void __blowfish_dec_blk_4way(struct bf_ctx *ctx, u8 *dst, + const u8 *src, bool cbc); -static inline void blowfish_enc_blk(struct bf_ctx *ctx, u8 *dst, const u8 *src) +static inline void blowfish_dec_ecb_4way(struct bf_ctx *ctx, u8 *dst, + const u8 *src) { - __blowfish_enc_blk(ctx, dst, src, false); + return __blowfish_dec_blk_4way(ctx, dst, src, false); } -static inline void blowfish_enc_blk_4way(struct bf_ctx *ctx, u8 *dst, - const u8 *src) +static inline void blowfish_dec_cbc_4way(struct bf_ctx *ctx, u8 *dst, + const u8 *src) { - __blowfish_enc_blk_4way(ctx, dst, src, false); + return __blowfish_dec_blk_4way(ctx, dst, src, true); } static void blowfish_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) @@ -54,183 +56,35 @@ static int blowfish_setkey_skcipher(struct crypto_skcipher *tfm, return blowfish_setkey(&tfm->base, key, keylen); } -static int ecb_crypt(struct skcipher_request *req, - void (*fn)(struct bf_ctx *, u8 *, const u8 *), - void (*fn_4way)(struct bf_ctx *, u8 *, const u8 *)) -{ - unsigned int bsize = BF_BLOCK_SIZE; - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct bf_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes)) { - u8 *wsrc = walk.src.virt.addr; - u8 *wdst = walk.dst.virt.addr; - - /* Process four block batch */ - if (nbytes >= bsize * 4) { - do { - fn_4way(ctx, wdst, wsrc); - - wsrc += bsize * 4; - wdst += bsize * 4; - nbytes -= bsize * 4; - } while (nbytes >= bsize * 4); - - if (nbytes < bsize) - goto done; - } - - /* Handle leftovers */ - do { - fn(ctx, wdst, wsrc); - - wsrc += bsize; - wdst += bsize; - nbytes -= bsize; - } while (nbytes >= bsize); - -done: - err = skcipher_walk_done(&walk, nbytes); - } - - return err; -} - static int ecb_encrypt(struct skcipher_request *req) { - return ecb_crypt(req, blowfish_enc_blk, blowfish_enc_blk_4way); + ECB_WALK_START(req, BF_BLOCK_SIZE, -1); + ECB_BLOCK(4, blowfish_enc_blk_4way); + ECB_BLOCK(1, blowfish_enc_blk); + ECB_WALK_END(); } static int ecb_decrypt(struct skcipher_request *req) { - return ecb_crypt(req, blowfish_dec_blk, blowfish_dec_blk_4way); -} - -static unsigned int __cbc_encrypt(struct bf_ctx *ctx, - struct skcipher_walk *walk) -{ - unsigned int bsize = BF_BLOCK_SIZE; - unsigned int nbytes = walk->nbytes; - u64 *src = (u64 *)walk->src.virt.addr; - u64 *dst = (u64 *)walk->dst.virt.addr; - u64 *iv = (u64 *)walk->iv; - - do { - *dst = *src ^ *iv; - blowfish_enc_blk(ctx, (u8 *)dst, (u8 *)dst); - iv = dst; - - src += 1; - dst += 1; - nbytes -= bsize; - } while (nbytes >= bsize); - - *(u64 *)walk->iv = *iv; - return nbytes; + ECB_WALK_START(req, BF_BLOCK_SIZE, -1); + ECB_BLOCK(4, blowfish_dec_ecb_4way); + ECB_BLOCK(1, blowfish_dec_blk); + ECB_WALK_END(); } static int cbc_encrypt(struct skcipher_request *req) { - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct bf_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while (walk.nbytes) { - nbytes = __cbc_encrypt(ctx, &walk); - err = skcipher_walk_done(&walk, nbytes); - } - - return err; -} - -static unsigned int __cbc_decrypt(struct bf_ctx *ctx, - struct skcipher_walk *walk) -{ - unsigned int bsize = BF_BLOCK_SIZE; - unsigned int nbytes = walk->nbytes; - u64 *src = (u64 *)walk->src.virt.addr; - u64 *dst = (u64 *)walk->dst.virt.addr; - u64 ivs[4 - 1]; - u64 last_iv; - - /* Start of the last block. */ - src += nbytes / bsize - 1; - dst += nbytes / bsize - 1; - - last_iv = *src; - - /* Process four block batch */ - if (nbytes >= bsize * 4) { - do { - nbytes -= bsize * 4 - bsize; - src -= 4 - 1; - dst -= 4 - 1; - - ivs[0] = src[0]; - ivs[1] = src[1]; - ivs[2] = src[2]; - - blowfish_dec_blk_4way(ctx, (u8 *)dst, (u8 *)src); - - dst[1] ^= ivs[0]; - dst[2] ^= ivs[1]; - dst[3] ^= ivs[2]; - - nbytes -= bsize; - if (nbytes < bsize) - goto done; - - *dst ^= *(src - 1); - src -= 1; - dst -= 1; - } while (nbytes >= bsize * 4); - } - - /* Handle leftovers */ - for (;;) { - blowfish_dec_blk(ctx, (u8 *)dst, (u8 *)src); - - nbytes -= bsize; - if (nbytes < bsize) - break; - - *dst ^= *(src - 1); - src -= 1; - dst -= 1; - } - -done: - *dst ^= *(u64 *)walk->iv; - *(u64 *)walk->iv = last_iv; - - return nbytes; + CBC_WALK_START(req, BF_BLOCK_SIZE, -1); + CBC_ENC_BLOCK(blowfish_enc_blk); + CBC_WALK_END(); } static int cbc_decrypt(struct skcipher_request *req) { - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct bf_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while (walk.nbytes) { - nbytes = __cbc_decrypt(ctx, &walk); - err = skcipher_walk_done(&walk, nbytes); - } - - return err; + CBC_WALK_START(req, BF_BLOCK_SIZE, -1); + CBC_DEC_BLOCK(4, blowfish_dec_cbc_4way); + CBC_DEC_BLOCK(1, blowfish_dec_blk); + CBC_WALK_END(); } static struct crypto_alg bf_cipher_alg = { diff --git a/arch/x86/crypto/ecb_cbc_helpers.h b/arch/x86/crypto/ecb_cbc_helpers.h index eaa15c7b29d6..11955bd01af1 100644 --- a/arch/x86/crypto/ecb_cbc_helpers.h +++ b/arch/x86/crypto/ecb_cbc_helpers.h @@ -13,13 +13,14 @@ #define ECB_WALK_START(req, bsize, fpu_blocks) do { \ void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); \ + const int __fpu_blocks = (fpu_blocks); \ const int __bsize = (bsize); \ struct skcipher_walk walk; \ int err = skcipher_walk_virt(&walk, (req), false); \ while (walk.nbytes > 0) { \ unsigned int nbytes = walk.nbytes; \ - bool do_fpu = (fpu_blocks) != -1 && \ - nbytes >= (fpu_blocks) * __bsize; \ + bool do_fpu = __fpu_blocks != -1 && \ + nbytes >= __fpu_blocks * __bsize; \ const u8 *src = walk.src.virt.addr; \ u8 *dst = walk.dst.virt.addr; \ u8 __maybe_unused buf[(bsize)]; \ @@ -35,7 +36,12 @@ } while (0) #define ECB_BLOCK(blocks, func) do { \ - while (nbytes >= (blocks) * __bsize) { \ + const int __blocks = (blocks); \ + if (do_fpu && __blocks < __fpu_blocks) { \ + kernel_fpu_end(); \ + do_fpu = false; \ + } \ + while (nbytes >= __blocks * __bsize) { \ (func)(ctx, dst, src); \ ECB_WALK_ADVANCE(blocks); \ } \ @@ -53,7 +59,12 @@ } while (0) #define CBC_DEC_BLOCK(blocks, func) do { \ - while (nbytes >= (blocks) * __bsize) { \ + const int __blocks = (blocks); \ + if (do_fpu && __blocks < __fpu_blocks) { \ + kernel_fpu_end(); \ + do_fpu = false; \ + } \ + while (nbytes >= __blocks * __bsize) { \ const u8 *__iv = src + ((blocks) - 1) * __bsize; \ if (dst == src) \ __iv = memcpy(buf, __iv, __bsize); \ diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S index 2bf871899920..257ed9446f3e 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_asm.S +++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S @@ -4,7 +4,7 @@ * instructions. This file contains accelerated part of ghash * implementation. More information about PCLMULQDQ can be found at: * - * http://software.intel.com/en-us/articles/carry-less-multiplication-and-its-usage-for-computing-the-gcm-mode/ + * https://www.intel.com/content/dam/develop/external/us/en/documents/clmul-wp-rev-2-02-2014-04-20.pdf * * Copyright (c) 2009 Intel Corp. * Author: Huang Ying <ying.huang@intel.com> @@ -88,7 +88,7 @@ SYM_FUNC_START_LOCAL(__clmul_gf128mul_ble) RET SYM_FUNC_END(__clmul_gf128mul_ble) -/* void clmul_ghash_mul(char *dst, const u128 *shash) */ +/* void clmul_ghash_mul(char *dst, const le128 *shash) */ SYM_FUNC_START(clmul_ghash_mul) FRAME_BEGIN movups (%rdi), DATA @@ -104,7 +104,7 @@ SYM_FUNC_END(clmul_ghash_mul) /* * void clmul_ghash_update(char *dst, const char *src, unsigned int srclen, - * const u128 *shash); + * const le128 *shash); */ SYM_FUNC_START(clmul_ghash_update) FRAME_BEGIN diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 1f1a95f3dd0c..700ecaee9a08 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -19,21 +19,22 @@ #include <crypto/internal/simd.h> #include <asm/cpu_device_id.h> #include <asm/simd.h> +#include <asm/unaligned.h> #define GHASH_BLOCK_SIZE 16 #define GHASH_DIGEST_SIZE 16 -void clmul_ghash_mul(char *dst, const u128 *shash); +void clmul_ghash_mul(char *dst, const le128 *shash); void clmul_ghash_update(char *dst, const char *src, unsigned int srclen, - const u128 *shash); + const le128 *shash); struct ghash_async_ctx { struct cryptd_ahash *cryptd_tfm; }; struct ghash_ctx { - u128 shash; + le128 shash; }; struct ghash_desc_ctx { @@ -54,22 +55,40 @@ static int ghash_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { struct ghash_ctx *ctx = crypto_shash_ctx(tfm); - be128 *x = (be128 *)key; u64 a, b; if (keylen != GHASH_BLOCK_SIZE) return -EINVAL; - /* perform multiplication by 'x' in GF(2^128) */ - a = be64_to_cpu(x->a); - b = be64_to_cpu(x->b); - - ctx->shash.a = (b << 1) | (a >> 63); - ctx->shash.b = (a << 1) | (b >> 63); - + /* + * GHASH maps bits to polynomial coefficients backwards, which makes it + * hard to implement. But it can be shown that the GHASH multiplication + * + * D * K (mod x^128 + x^7 + x^2 + x + 1) + * + * (where D is a data block and K is the key) is equivalent to: + * + * bitreflect(D) * bitreflect(K) * x^(-127) + * (mod x^128 + x^127 + x^126 + x^121 + 1) + * + * So, the code below precomputes: + * + * bitreflect(K) * x^(-127) (mod x^128 + x^127 + x^126 + x^121 + 1) + * + * ... but in Montgomery form (so that Montgomery multiplication can be + * used), i.e. with an extra x^128 factor, which means actually: + * + * bitreflect(K) * x (mod x^128 + x^127 + x^126 + x^121 + 1) + * + * The within-a-byte part of bitreflect() cancels out GHASH's built-in + * reflection, and thus bitreflect() is actually a byteswap. + */ + a = get_unaligned_be64(key); + b = get_unaligned_be64(key + 8); + ctx->shash.a = cpu_to_le64((a << 1) | (b >> 63)); + ctx->shash.b = cpu_to_le64((b << 1) | (a >> 63)); if (a >> 63) - ctx->shash.b ^= ((u64)0xc2) << 56; - + ctx->shash.a ^= cpu_to_le64((u64)0xc2 << 56); return 0; } diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 15739a2c0983..7ecd2aeeeffc 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -782,7 +782,7 @@ _ASM_NOKPROBE(common_interrupt_return) /* * Reload gs selector with exception handling - * edi: new selector + * di: new selector * * Is in entry.text as it shouldn't be instrumented. */ diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 838613ac15b8..1506a22a4fb6 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -29,7 +29,7 @@ VDSO32-$(CONFIG_IA32_EMULATION) := y # files to link into the vdso vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vobjs32-y := vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o -vobjs32-y += vdso32/vclock_gettime.o +vobjs32-y += vdso32/vclock_gettime.o vdso32/vgetcpu.o vobjs-$(CONFIG_X86_SGX) += vsgx.o # files to link into kernel @@ -104,6 +104,7 @@ $(vobjs): KBUILD_AFLAGS += -DBUILD_VDSO CFLAGS_REMOVE_vclock_gettime.o = -pg CFLAGS_REMOVE_vdso32/vclock_gettime.o = -pg CFLAGS_REMOVE_vgetcpu.o = -pg +CFLAGS_REMOVE_vdso32/vgetcpu.o = -pg CFLAGS_REMOVE_vsgx.o = -pg # diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h index 5264daa8859f..67b3e37576a6 100644 --- a/arch/x86/entry/vdso/vdso2c.h +++ b/arch/x86/entry/vdso/vdso2c.h @@ -179,6 +179,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len, fprintf(outfile, "/* AUTOMATICALLY GENERATED -- DO NOT EDIT */\n\n"); fprintf(outfile, "#include <linux/linkage.h>\n"); + fprintf(outfile, "#include <linux/init.h>\n"); fprintf(outfile, "#include <asm/page_types.h>\n"); fprintf(outfile, "#include <asm/vdso.h>\n"); fprintf(outfile, "\n"); @@ -218,5 +219,10 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len, fprintf(outfile, "\t.sym_%s = %" PRIi64 ",\n", required_syms[i].name, (int64_t)syms[i]); } + fprintf(outfile, "};\n\n"); + fprintf(outfile, "static __init int init_%s(void) {\n", image_name); + fprintf(outfile, "\treturn init_vdso_image(&%s);\n", image_name); fprintf(outfile, "};\n"); + fprintf(outfile, "subsys_initcall(init_%s);\n", image_name); + } diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 43842fade8fa..3b300a773c7e 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -51,17 +51,8 @@ __setup("vdso32=", vdso32_setup); __setup_param("vdso=", vdso_setup, vdso32_setup, 0); #endif -int __init sysenter_setup(void) -{ - init_vdso_image(&vdso_image_32); - - return 0; -} - #ifdef CONFIG_X86_64 -subsys_initcall(sysenter_setup); - #ifdef CONFIG_SYSCTL /* Register vsyscall32 into the ABI table */ #include <linux/sysctl.h> diff --git a/arch/x86/entry/vdso/vdso32/fake_32bit_build.h b/arch/x86/entry/vdso/vdso32/fake_32bit_build.h new file mode 100644 index 000000000000..db1b15f686e3 --- /dev/null +++ b/arch/x86/entry/vdso/vdso32/fake_32bit_build.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifdef CONFIG_X86_64 + +/* + * in case of a 32 bit VDSO for a 64 bit kernel fake a 32 bit kernel + * configuration + */ +#undef CONFIG_64BIT +#undef CONFIG_X86_64 +#undef CONFIG_COMPAT +#undef CONFIG_PGTABLE_LEVELS +#undef CONFIG_ILLEGAL_POINTER_VALUE +#undef CONFIG_SPARSEMEM_VMEMMAP +#undef CONFIG_NR_CPUS +#undef CONFIG_PARAVIRT_XXL + +#define CONFIG_X86_32 1 +#define CONFIG_PGTABLE_LEVELS 2 +#define CONFIG_PAGE_OFFSET 0 +#define CONFIG_ILLEGAL_POINTER_VALUE 0 +#define CONFIG_NR_CPUS 1 + +#define BUILD_VDSO32_64 + +#endif diff --git a/arch/x86/entry/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c index 283ed9d00426..86981decfea8 100644 --- a/arch/x86/entry/vdso/vdso32/vclock_gettime.c +++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c @@ -1,29 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 #define BUILD_VDSO32 - -#ifdef CONFIG_X86_64 - -/* - * in case of a 32 bit VDSO for a 64 bit kernel fake a 32 bit kernel - * configuration - */ -#undef CONFIG_64BIT -#undef CONFIG_X86_64 -#undef CONFIG_COMPAT -#undef CONFIG_PGTABLE_LEVELS -#undef CONFIG_ILLEGAL_POINTER_VALUE -#undef CONFIG_SPARSEMEM_VMEMMAP -#undef CONFIG_NR_CPUS -#undef CONFIG_PARAVIRT_XXL - -#define CONFIG_X86_32 1 -#define CONFIG_PGTABLE_LEVELS 2 -#define CONFIG_PAGE_OFFSET 0 -#define CONFIG_ILLEGAL_POINTER_VALUE 0 -#define CONFIG_NR_CPUS 1 - -#define BUILD_VDSO32_64 - -#endif - +#include "fake_32bit_build.h" #include "../vclock_gettime.c" diff --git a/arch/x86/entry/vdso/vdso32/vdso32.lds.S b/arch/x86/entry/vdso/vdso32/vdso32.lds.S index c7720995ab1a..8a3be07006bb 100644 --- a/arch/x86/entry/vdso/vdso32/vdso32.lds.S +++ b/arch/x86/entry/vdso/vdso32/vdso32.lds.S @@ -28,6 +28,7 @@ VERSION __vdso_time; __vdso_clock_getres; __vdso_clock_gettime64; + __vdso_getcpu; }; LINUX_2.5 { diff --git a/arch/x86/entry/vdso/vdso32/vgetcpu.c b/arch/x86/entry/vdso/vdso32/vgetcpu.c new file mode 100644 index 000000000000..3a9791f5e998 --- /dev/null +++ b/arch/x86/entry/vdso/vdso32/vgetcpu.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "fake_32bit_build.h" +#include "../vgetcpu.c" diff --git a/arch/x86/entry/vdso/vgetcpu.c b/arch/x86/entry/vdso/vgetcpu.c index b88a82bbc359..0a9007c24056 100644 --- a/arch/x86/entry/vdso/vgetcpu.c +++ b/arch/x86/entry/vdso/vgetcpu.c @@ -7,8 +7,7 @@ #include <linux/kernel.h> #include <linux/getcpu.h> -#include <linux/time.h> -#include <asm/vgtod.h> +#include <asm/segment.h> notrace long __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index b8f3f9b9e53c..11a5c68d1218 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -44,13 +44,16 @@ unsigned int vclocks_used __read_mostly; unsigned int __read_mostly vdso64_enabled = 1; #endif -void __init init_vdso_image(const struct vdso_image *image) +int __init init_vdso_image(const struct vdso_image *image) { + BUILD_BUG_ON(VDSO_CLOCKMODE_MAX >= 32); BUG_ON(image->size % PAGE_SIZE != 0); apply_alternatives((struct alt_instr *)(image->data + image->alt), (struct alt_instr *)(image->data + image->alt + image->alt_len)); + + return 0; } static const struct vm_special_mapping vvar_mapping; @@ -113,10 +116,8 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) mmap_read_lock(mm); for_each_vma(vmi, vma) { - unsigned long size = vma->vm_end - vma->vm_start; - if (vma_is_special_mapping(vma, &vvar_mapping)) - zap_page_range(vma, vma->vm_start, size); + zap_vma_pages(vma); } mmap_read_unlock(mm); @@ -418,18 +419,4 @@ static __init int vdso_setup(char *s) return 1; } __setup("vdso=", vdso_setup); - -static int __init init_vdso(void) -{ - BUILD_BUG_ON(VDSO_CLOCKMODE_MAX >= 32); - - init_vdso_image(&vdso_image_64); - -#ifdef CONFIG_X86_X32_ABI - init_vdso_image(&vdso_image_x32); -#endif - - return 0; -} -subsys_initcall(init_vdso); #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 4af81df133ee..d234ca797e4a 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -391,7 +391,7 @@ void __init map_vsyscall(void) } if (vsyscall_mode == XONLY) - gate_vma.vm_flags = VM_EXEC; + vm_flags_init(&gate_vma, VM_EXEC); BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != (unsigned long)VSYSCALL_ADDR); diff --git a/arch/x86/events/amd/brs.c b/arch/x86/events/amd/brs.c index 58461fa18b6f..ed308719236c 100644 --- a/arch/x86/events/amd/brs.c +++ b/arch/x86/events/amd/brs.c @@ -41,18 +41,15 @@ static inline unsigned int brs_to(int idx) return MSR_AMD_SAMP_BR_FROM + 2 * idx + 1; } -static inline void set_debug_extn_cfg(u64 val) +static __always_inline void set_debug_extn_cfg(u64 val) { /* bits[4:3] must always be set to 11b */ - wrmsrl(MSR_AMD_DBG_EXTN_CFG, val | 3ULL << 3); + __wrmsr(MSR_AMD_DBG_EXTN_CFG, val | 3ULL << 3, val >> 32); } -static inline u64 get_debug_extn_cfg(void) +static __always_inline u64 get_debug_extn_cfg(void) { - u64 val; - - rdmsrl(MSR_AMD_DBG_EXTN_CFG, val); - return val; + return __rdmsr(MSR_AMD_DBG_EXTN_CFG); } static bool __init amd_brs_detect(void) @@ -405,7 +402,7 @@ void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_i * called from ACPI processor_idle.c or acpi_pad.c * with interrupts disabled */ -void perf_amd_brs_lopwr_cb(bool lopwr_in) +void noinstr perf_amd_brs_lopwr_cb(bool lopwr_in) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); union amd_debug_extn_cfg cfg; diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 4386b10682ce..8c45b198b62f 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -928,10 +928,8 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) if (!x86_perf_event_set_period(event)) continue; - if (has_branch_stack(event)) { - data.br_stack = &cpuc->lbr_stack; - data.sample_flags |= PERF_SAMPLE_BRANCH_STACK; - } + if (has_branch_stack(event)) + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index da3f5ebac4e1..64582954b5f6 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -1110,8 +1110,7 @@ fail: .data = ibs_data.data, }, }; - data.raw = &raw; - data.sample_flags |= PERF_SAMPLE_RAW; + perf_sample_save_raw_data(&data, &raw); } if (perf_ibs == &perf_ibs_op) @@ -1122,10 +1121,8 @@ fail: * recorded as part of interrupt regs. Thus we need to use rip from * interrupt regs while unwinding call stack. */ - if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { - data.callchain = perf_callchain(event, iregs); - data.sample_flags |= PERF_SAMPLE_CALLCHAIN; - } + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + perf_sample_save_callchain(&data, event, iregs); throttle = perf_event_overflow(event, &data, ®s); out: diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 85a63a41c471..d096b04bf80e 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2974,17 +2974,19 @@ unsigned long perf_misc_flags(struct pt_regs *regs) void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap) { - if (!x86_pmu_initialized()) { + /* This API doesn't currently support enumerating hybrid PMUs. */ + if (WARN_ON_ONCE(cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) || + !x86_pmu_initialized()) { memset(cap, 0, sizeof(*cap)); return; } - cap->version = x86_pmu.version; /* - * KVM doesn't support the hybrid PMU yet. - * Return the common value in global x86_pmu, - * which available for all cores. + * Note, hybrid CPU models get tracked as having hybrid PMUs even when + * all E-cores are disabled via BIOS. When E-cores are disabled, the + * base PMU holds the correct number of counters for P-cores. */ + cap->version = x86_pmu.version; cap->num_counters_gp = x86_pmu.num_counters; cap->num_counters_fixed = x86_pmu.num_counters_fixed; cap->bit_width_gp = x86_pmu.cntval_bits; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index dfd2c124cdf8..a3fb996a86a1 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2119,6 +2119,16 @@ static struct extra_reg intel_grt_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; +static struct extra_reg intel_cmt_extra_regs[] __read_mostly = { + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x800ff3ffffffffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xff3ffffffffffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x5d0), + INTEL_UEVENT_EXTRA_REG(0x0127, MSR_SNOOP_RSP_0, 0xffffffffffffffffull, SNOOP_0), + INTEL_UEVENT_EXTRA_REG(0x0227, MSR_SNOOP_RSP_1, 0xffffffffffffffffull, SNOOP_1), + EVENT_EXTRA_END +}; + #define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */ #define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */ #define KNL_MCDRAM_LOCAL BIT_ULL(21) @@ -3026,10 +3036,8 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) perf_sample_data_init(&data, 0, event->hw.last_period); - if (has_branch_stack(event)) { - data.br_stack = &cpuc->lbr_stack; - data.sample_flags |= PERF_SAMPLE_BRANCH_STACK; - } + if (has_branch_stack(event)) + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); @@ -4182,6 +4190,12 @@ static int hsw_hw_config(struct perf_event *event) static struct event_constraint counter0_constraint = INTEL_ALL_EVENT_CONSTRAINT(0, 0x1); +static struct event_constraint counter1_constraint = + INTEL_ALL_EVENT_CONSTRAINT(0, 0x2); + +static struct event_constraint counter0_1_constraint = + INTEL_ALL_EVENT_CONSTRAINT(0, 0x3); + static struct event_constraint counter2_constraint = EVENT_CONSTRAINT(0, 0x4, 0); @@ -4191,6 +4205,12 @@ static struct event_constraint fixed0_constraint = static struct event_constraint fixed0_counter0_constraint = INTEL_ALL_EVENT_CONSTRAINT(0, 0x100000001ULL); +static struct event_constraint fixed0_counter0_1_constraint = + INTEL_ALL_EVENT_CONSTRAINT(0, 0x100000003ULL); + +static struct event_constraint counters_1_7_constraint = + INTEL_ALL_EVENT_CONSTRAINT(0, 0xfeULL); + static struct event_constraint * hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) @@ -4322,6 +4342,78 @@ adl_get_event_constraints(struct cpu_hw_events *cpuc, int idx, return &emptyconstraint; } +static struct event_constraint * +cmt_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct event_constraint *c; + + c = intel_get_event_constraints(cpuc, idx, event); + + /* + * The :ppp indicates the Precise Distribution (PDist) facility, which + * is only supported on the GP counter 0 & 1 and Fixed counter 0. + * If a :ppp event which is not available on the above eligible counters, + * error out. + */ + if (event->attr.precise_ip == 3) { + /* Force instruction:ppp on PMC0, 1 and Fixed counter 0 */ + if (constraint_match(&fixed0_constraint, event->hw.config)) + return &fixed0_counter0_1_constraint; + + switch (c->idxmsk64 & 0x3ull) { + case 0x1: + return &counter0_constraint; + case 0x2: + return &counter1_constraint; + case 0x3: + return &counter0_1_constraint; + } + return &emptyconstraint; + } + + return c; +} + +static struct event_constraint * +rwc_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct event_constraint *c; + + c = spr_get_event_constraints(cpuc, idx, event); + + /* The Retire Latency is not supported by the fixed counter 0. */ + if (event->attr.precise_ip && + (event->attr.sample_type & PERF_SAMPLE_WEIGHT_TYPE) && + constraint_match(&fixed0_constraint, event->hw.config)) { + /* + * The Instruction PDIR is only available + * on the fixed counter 0. Error out for this case. + */ + if (event->attr.precise_ip == 3) + return &emptyconstraint; + return &counters_1_7_constraint; + } + + return c; +} + +static struct event_constraint * +mtl_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu); + + if (pmu->cpu_type == hybrid_big) + return rwc_get_event_constraints(cpuc, idx, event); + if (pmu->cpu_type == hybrid_small) + return cmt_get_event_constraints(cpuc, idx, event); + + WARN_ON(1); + return &emptyconstraint; +} + static int adl_hw_config(struct perf_event *event) { struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu); @@ -4494,6 +4586,25 @@ static void flip_smm_bit(void *data) } } +static void intel_pmu_check_num_counters(int *num_counters, + int *num_counters_fixed, + u64 *intel_ctrl, u64 fixed_mask); + +static void update_pmu_cap(struct x86_hybrid_pmu *pmu) +{ + unsigned int sub_bitmaps = cpuid_eax(ARCH_PERFMON_EXT_LEAF); + unsigned int eax, ebx, ecx, edx; + + if (sub_bitmaps & ARCH_PERFMON_NUM_COUNTER_LEAF_BIT) { + cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF, + &eax, &ebx, &ecx, &edx); + pmu->num_counters = fls(eax); + pmu->num_counters_fixed = fls(ebx); + intel_pmu_check_num_counters(&pmu->num_counters, &pmu->num_counters_fixed, + &pmu->intel_ctrl, ebx); + } +} + static bool init_hybrid_pmu(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); @@ -4519,6 +4630,9 @@ static bool init_hybrid_pmu(int cpu) if (!cpumask_empty(&pmu->supported_cpus)) goto end; + if (this_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT)) + update_pmu_cap(pmu); + if (!check_hw_exists(&pmu->pmu, pmu->num_counters, pmu->num_counters_fixed)) return false; @@ -5463,6 +5577,12 @@ static struct attribute *adl_hybrid_mem_attrs[] = { NULL, }; +static struct attribute *mtl_hybrid_mem_attrs[] = { + EVENT_PTR(mem_ld_adl), + EVENT_PTR(mem_st_adl), + NULL +}; + EVENT_ATTR_STR_HYBRID(tx-start, tx_start_adl, "event=0xc9,umask=0x1", hybrid_big); EVENT_ATTR_STR_HYBRID(tx-commit, tx_commit_adl, "event=0xc9,umask=0x2", hybrid_big); EVENT_ATTR_STR_HYBRID(tx-abort, tx_abort_adl, "event=0xc9,umask=0x4", hybrid_big); @@ -5490,20 +5610,40 @@ FORMAT_ATTR_HYBRID(offcore_rsp, hybrid_big_small); FORMAT_ATTR_HYBRID(ldlat, hybrid_big_small); FORMAT_ATTR_HYBRID(frontend, hybrid_big); +#define ADL_HYBRID_RTM_FORMAT_ATTR \ + FORMAT_HYBRID_PTR(in_tx), \ + FORMAT_HYBRID_PTR(in_tx_cp) + +#define ADL_HYBRID_FORMAT_ATTR \ + FORMAT_HYBRID_PTR(offcore_rsp), \ + FORMAT_HYBRID_PTR(ldlat), \ + FORMAT_HYBRID_PTR(frontend) + static struct attribute *adl_hybrid_extra_attr_rtm[] = { - FORMAT_HYBRID_PTR(in_tx), - FORMAT_HYBRID_PTR(in_tx_cp), - FORMAT_HYBRID_PTR(offcore_rsp), - FORMAT_HYBRID_PTR(ldlat), - FORMAT_HYBRID_PTR(frontend), - NULL, + ADL_HYBRID_RTM_FORMAT_ATTR, + ADL_HYBRID_FORMAT_ATTR, + NULL }; static struct attribute *adl_hybrid_extra_attr[] = { - FORMAT_HYBRID_PTR(offcore_rsp), - FORMAT_HYBRID_PTR(ldlat), - FORMAT_HYBRID_PTR(frontend), - NULL, + ADL_HYBRID_FORMAT_ATTR, + NULL +}; + +PMU_FORMAT_ATTR_SHOW(snoop_rsp, "config1:0-63"); +FORMAT_ATTR_HYBRID(snoop_rsp, hybrid_small); + +static struct attribute *mtl_hybrid_extra_attr_rtm[] = { + ADL_HYBRID_RTM_FORMAT_ATTR, + ADL_HYBRID_FORMAT_ATTR, + FORMAT_HYBRID_PTR(snoop_rsp), + NULL +}; + +static struct attribute *mtl_hybrid_extra_attr[] = { + ADL_HYBRID_FORMAT_ATTR, + FORMAT_HYBRID_PTR(snoop_rsp), + NULL }; static bool is_attr_for_this_pmu(struct kobject *kobj, struct attribute *attr) @@ -5725,6 +5865,12 @@ static void intel_pmu_check_hybrid_pmus(u64 fixed_mask) } } +static __always_inline bool is_mtl(u8 x86_model) +{ + return (x86_model == INTEL_FAM6_METEORLAKE) || + (x86_model == INTEL_FAM6_METEORLAKE_L); +} + __init int intel_pmu_init(void) { struct attribute **extra_skl_attr = &empty_attrs; @@ -6339,6 +6485,7 @@ __init int intel_pmu_init(void) break; case INTEL_FAM6_SAPPHIRERAPIDS_X: + case INTEL_FAM6_EMERALDRAPIDS_X: pmem = true; x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -6348,6 +6495,7 @@ __init int intel_pmu_init(void) x86_pmu.pebs_constraints = intel_spr_pebs_event_constraints; x86_pmu.extra_regs = intel_spr_extra_regs; x86_pmu.limit_period = spr_limit_period; + x86_pmu.pebs_ept = 1; x86_pmu.pebs_aliases = NULL; x86_pmu.pebs_prec_dist = true; x86_pmu.pebs_block = true; @@ -6381,6 +6529,8 @@ __init int intel_pmu_init(void) case INTEL_FAM6_RAPTORLAKE: case INTEL_FAM6_RAPTORLAKE_P: case INTEL_FAM6_RAPTORLAKE_S: + case INTEL_FAM6_METEORLAKE: + case INTEL_FAM6_METEORLAKE_L: /* * Alder Lake has 2 types of CPU, core and atom. * @@ -6400,9 +6550,7 @@ __init int intel_pmu_init(void) x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; x86_pmu.flags |= PMU_FL_INSTR_LATENCY; - x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; x86_pmu.lbr_pt_coexist = true; - intel_pmu_pebs_data_source_adl(); x86_pmu.pebs_latency_data = adl_latency_data_small; x86_pmu.num_topdown_events = 8; static_call_update(intel_pmu_update_topdown_event, @@ -6489,8 +6637,22 @@ __init int intel_pmu_init(void) pmu->event_constraints = intel_slm_event_constraints; pmu->pebs_constraints = intel_grt_pebs_event_constraints; pmu->extra_regs = intel_grt_extra_regs; - pr_cont("Alderlake Hybrid events, "); - name = "alderlake_hybrid"; + if (is_mtl(boot_cpu_data.x86_model)) { + x86_pmu.pebs_latency_data = mtl_latency_data_small; + extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? + mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr; + mem_attr = mtl_hybrid_mem_attrs; + intel_pmu_pebs_data_source_mtl(); + x86_pmu.get_event_constraints = mtl_get_event_constraints; + pmu->extra_regs = intel_cmt_extra_regs; + pr_cont("Meteorlake Hybrid events, "); + name = "meteorlake_hybrid"; + } else { + x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; + intel_pmu_pebs_data_source_adl(); + pr_cont("Alderlake Hybrid events, "); + name = "alderlake_hybrid"; + } break; default: @@ -6605,6 +6767,9 @@ __init int intel_pmu_init(void) if (is_hybrid()) intel_pmu_check_hybrid_pmus((u64)fixed_mask); + if (x86_pmu.intel_cap.pebs_timing_info) + x86_pmu.flags |= PMU_FL_RETIRE_LATENCY; + intel_aux_output_init(); return 0; diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 3019fb1926e3..551741e79e03 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -677,6 +677,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &icx_cstates), + X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates), diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 88e58b6ee73c..a2e566e53076 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -2,12 +2,14 @@ #include <linux/bitops.h> #include <linux/types.h> #include <linux/slab.h> +#include <linux/sched/clock.h> #include <asm/cpu_entry_area.h> #include <asm/perf_event.h> #include <asm/tlbflush.h> #include <asm/insn.h> #include <asm/io.h> +#include <asm/timer.h> #include "../perf_event.h" @@ -53,6 +55,13 @@ union intel_x86_pebs_dse { unsigned int st_lat_locked:1; unsigned int ld_reserved3:26; }; + struct { + unsigned int mtl_dse:5; + unsigned int mtl_locked:1; + unsigned int mtl_stlb_miss:1; + unsigned int mtl_fwd_blk:1; + unsigned int ld_reserved4:24; + }; }; @@ -135,6 +144,29 @@ void __init intel_pmu_pebs_data_source_adl(void) __intel_pmu_pebs_data_source_grt(data_source); } +static void __init intel_pmu_pebs_data_source_cmt(u64 *data_source) +{ + data_source[0x07] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD); + data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); + data_source[0x0a] = OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, NONE); + data_source[0x0b] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE); + data_source[0x0c] = OP_LH | LEVEL(RAM) | REM | P(SNOOPX, FWD); + data_source[0x0d] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, HITM); +} + +void __init intel_pmu_pebs_data_source_mtl(void) +{ + u64 *data_source; + + data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].pebs_data_source; + memcpy(data_source, pebs_data_source, sizeof(pebs_data_source)); + __intel_pmu_pebs_data_source_skl(false, data_source); + + data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source; + memcpy(data_source, pebs_data_source, sizeof(pebs_data_source)); + intel_pmu_pebs_data_source_cmt(data_source); +} + static u64 precise_store_data(u64 status) { union intel_x86_pebs_dse dse; @@ -219,24 +251,19 @@ static inline void pebs_set_tlb_lock(u64 *val, bool tlb, bool lock) } /* Retrieve the latency data for e-core of ADL */ -u64 adl_latency_data_small(struct perf_event *event, u64 status) +static u64 __adl_latency_data_small(struct perf_event *event, u64 status, + u8 dse, bool tlb, bool lock, bool blk) { - union intel_x86_pebs_dse dse; u64 val; WARN_ON_ONCE(hybrid_pmu(event->pmu)->cpu_type == hybrid_big); - dse.val = status; - - val = hybrid_var(event->pmu, pebs_data_source)[dse.ld_dse]; + dse &= PERF_PEBS_DATA_SOURCE_MASK; + val = hybrid_var(event->pmu, pebs_data_source)[dse]; - /* - * For the atom core on ADL, - * bit 4: lock, bit 5: TLB access. - */ - pebs_set_tlb_lock(&val, dse.ld_locked, dse.ld_stlb_miss); + pebs_set_tlb_lock(&val, tlb, lock); - if (dse.ld_data_blk) + if (blk) val |= P(BLK, DATA); else val |= P(BLK, NA); @@ -244,6 +271,29 @@ u64 adl_latency_data_small(struct perf_event *event, u64 status) return val; } +u64 adl_latency_data_small(struct perf_event *event, u64 status) +{ + union intel_x86_pebs_dse dse; + + dse.val = status; + + return __adl_latency_data_small(event, status, dse.ld_dse, + dse.ld_locked, dse.ld_stlb_miss, + dse.ld_data_blk); +} + +/* Retrieve the latency data for e-core of MTL */ +u64 mtl_latency_data_small(struct perf_event *event, u64 status) +{ + union intel_x86_pebs_dse dse; + + dse.val = status; + + return __adl_latency_data_small(event, status, dse.mtl_dse, + dse.mtl_stlb_miss, dse.mtl_locked, + dse.mtl_fwd_blk); +} + static u64 load_latency_data(struct perf_event *event, u64 status) { union intel_x86_pebs_dse dse; @@ -759,7 +809,8 @@ int intel_pmu_drain_bts_buffer(void) * the sample. */ rcu_read_lock(); - perf_prepare_sample(&header, &data, event, ®s); + perf_prepare_sample(&data, event, ®s); + perf_prepare_header(&header, &data, event, ®s); if (perf_output_begin(&handle, &data, event, header.size * (top - base - skip))) @@ -1519,6 +1570,27 @@ static u64 get_data_src(struct perf_event *event, u64 aux) return val; } +static void setup_pebs_time(struct perf_event *event, + struct perf_sample_data *data, + u64 tsc) +{ + /* Converting to a user-defined clock is not supported yet. */ + if (event->attr.use_clockid != 0) + return; + + /* + * Doesn't support the conversion when the TSC is unstable. + * The TSC unstable case is a corner case and very unlikely to + * happen. If it happens, the TSC in a PEBS record will be + * dropped and fall back to perf_event_clock(). + */ + if (!using_native_sched_clock() || !sched_clock_stable()) + return; + + data->time = native_sched_clock_from_tsc(tsc) + __sched_clock_offset; + data->sample_flags |= PERF_SAMPLE_TIME; +} + #define PERF_SAMPLE_ADDR_TYPE (PERF_SAMPLE_ADDR | \ PERF_SAMPLE_PHYS_ADDR | \ PERF_SAMPLE_DATA_PAGE_SIZE) @@ -1569,10 +1641,8 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, * previous PMI context or an (I)RET happened between the record and * PMI. */ - if (sample_type & PERF_SAMPLE_CALLCHAIN) { - data->callchain = perf_callchain(event, iregs); - data->sample_flags |= PERF_SAMPLE_CALLCHAIN; - } + if (sample_type & PERF_SAMPLE_CALLCHAIN) + perf_sample_save_callchain(data, event, iregs); /* * We use the interrupt regs as a base because the PEBS record does not @@ -1668,16 +1738,11 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, * * We can only do this for the default trace clock. */ - if (x86_pmu.intel_cap.pebs_format >= 3 && - event->attr.use_clockid == 0) { - data->time = native_sched_clock_from_tsc(pebs->tsc); - data->sample_flags |= PERF_SAMPLE_TIME; - } + if (x86_pmu.intel_cap.pebs_format >= 3) + setup_pebs_time(event, data, pebs->tsc); - if (has_branch_stack(event)) { - data->br_stack = &cpuc->lbr_stack; - data->sample_flags |= PERF_SAMPLE_BRANCH_STACK; - } + if (has_branch_stack(event)) + perf_sample_save_brstack(data, event, &cpuc->lbr_stack); } static void adaptive_pebs_save_regs(struct pt_regs *regs, @@ -1705,6 +1770,7 @@ static void adaptive_pebs_save_regs(struct pt_regs *regs, #define PEBS_LATENCY_MASK 0xffff #define PEBS_CACHE_LATENCY_OFFSET 32 +#define PEBS_RETIRE_LATENCY_OFFSET 32 /* * With adaptive PEBS the layout depends on what fields are configured. @@ -1735,10 +1801,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, perf_sample_data_init(data, 0, event->hw.last_period); data->period = event->hw.last_period; - if (event->attr.use_clockid == 0) { - data->time = native_sched_clock_from_tsc(basic->tsc); - data->sample_flags |= PERF_SAMPLE_TIME; - } + setup_pebs_time(event, data, basic->tsc); /* * We must however always use iregs for the unwinder to stay sane; the @@ -1746,16 +1809,17 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, * previous PMI context or an (I)RET happened between the record and * PMI. */ - if (sample_type & PERF_SAMPLE_CALLCHAIN) { - data->callchain = perf_callchain(event, iregs); - data->sample_flags |= PERF_SAMPLE_CALLCHAIN; - } + if (sample_type & PERF_SAMPLE_CALLCHAIN) + perf_sample_save_callchain(data, event, iregs); *regs = *iregs; /* The ip in basic is EventingIP */ set_linear_ip(regs, basic->ip); regs->flags = PERF_EFLAGS_EXACT; + if ((sample_type & PERF_SAMPLE_WEIGHT_STRUCT) && (x86_pmu.flags & PMU_FL_RETIRE_LATENCY)) + data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK; + /* * The record for MEMINFO is in front of GP * But PERF_SAMPLE_TRANSACTION needs gprs->ax. @@ -1835,8 +1899,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, if (has_branch_stack(event)) { intel_pmu_store_pebs_lbrs(lbr); - data->br_stack = &cpuc->lbr_stack; - data->sample_flags |= PERF_SAMPLE_BRANCH_STACK; + perf_sample_save_brstack(data, event, &cpuc->lbr_stack); } } @@ -2303,8 +2366,10 @@ void __init intel_ds_init(void) x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME; break; - case 4: case 5: + x86_pmu.pebs_ept = 1; + fallthrough; + case 4: x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl; x86_pmu.pebs_record_size = sizeof(struct pebs_basic); if (x86_pmu.intel_cap.pebs_baseline) { diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 1f21f576ca77..c3b0d15a9841 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1606,12 +1606,10 @@ clear_arch_lbr: */ void x86_perf_get_lbr(struct x86_pmu_lbr *lbr) { - int lbr_fmt = x86_pmu.intel_cap.lbr_format; - lbr->nr = x86_pmu.lbr_nr; lbr->from = x86_pmu.lbr_from; lbr->to = x86_pmu.lbr_to; - lbr->info = (lbr_fmt == LBR_FORMAT_INFO) ? x86_pmu.lbr_info : 0; + lbr->info = x86_pmu.lbr_info; } EXPORT_SYMBOL_GPL(x86_perf_get_lbr); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 459b1aafd4d4..bc226603ef3e 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -65,6 +65,21 @@ int uncore_die_to_segment(int die) return bus ? pci_domain_nr(bus) : -EINVAL; } +int uncore_device_to_die(struct pci_dev *dev) +{ + int node = pcibus_to_node(dev->bus); + int cpu; + + for_each_cpu(cpu, cpumask_of_pcibus(dev->bus)) { + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->initialized && cpu_to_node(cpu) == node) + return c->logical_die_id; + } + + return -1; +} + static void uncore_free_pcibus_map(void) { struct pci2phy_map *map, *tmp; @@ -842,6 +857,12 @@ static const struct attribute_group uncore_pmu_attr_group = { .attrs = uncore_pmu_attrs, }; +static inline int uncore_get_box_id(struct intel_uncore_type *type, + struct intel_uncore_pmu *pmu) +{ + return type->box_ids ? type->box_ids[pmu->pmu_idx] : pmu->pmu_idx; +} + void uncore_get_alias_name(char *pmu_name, struct intel_uncore_pmu *pmu) { struct intel_uncore_type *type = pmu->type; @@ -850,7 +871,7 @@ void uncore_get_alias_name(char *pmu_name, struct intel_uncore_pmu *pmu) sprintf(pmu_name, "uncore_type_%u", type->type_id); else { sprintf(pmu_name, "uncore_type_%u_%d", - type->type_id, type->box_ids[pmu->pmu_idx]); + type->type_id, uncore_get_box_id(type, pmu)); } } @@ -877,7 +898,7 @@ static void uncore_get_pmu_name(struct intel_uncore_pmu *pmu) * Use the box ID from the discovery table if applicable. */ sprintf(pmu->name, "uncore_%s_%d", type->name, - type->box_ids ? type->box_ids[pmu->pmu_idx] : pmu->pmu_idx); + uncore_get_box_id(type, pmu)); } } @@ -1674,7 +1695,10 @@ struct intel_uncore_init_fun { void (*cpu_init)(void); int (*pci_init)(void); void (*mmio_init)(void); + /* Discovery table is required */ bool use_discovery; + /* The units in the discovery table should be ignored. */ + int *uncore_units_ignore; }; static const struct intel_uncore_init_fun nhm_uncore_init __initconst = { @@ -1765,6 +1789,11 @@ static const struct intel_uncore_init_fun adl_uncore_init __initconst = { .mmio_init = adl_uncore_mmio_init, }; +static const struct intel_uncore_init_fun mtl_uncore_init __initconst = { + .cpu_init = mtl_uncore_cpu_init, + .mmio_init = adl_uncore_mmio_init, +}; + static const struct intel_uncore_init_fun icx_uncore_init __initconst = { .cpu_init = icx_uncore_cpu_init, .pci_init = icx_uncore_pci_init, @@ -1782,6 +1811,7 @@ static const struct intel_uncore_init_fun spr_uncore_init __initconst = { .pci_init = spr_uncore_pci_init, .mmio_init = spr_uncore_mmio_init, .use_discovery = true, + .uncore_units_ignore = spr_uncore_units_ignore, }; static const struct intel_uncore_init_fun generic_uncore_init __initconst = { @@ -1832,6 +1862,8 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &mtl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &mtl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), @@ -1853,7 +1885,7 @@ static int __init intel_uncore_init(void) id = x86_match_cpu(intel_uncore_match); if (!id) { - if (!uncore_no_discover && intel_uncore_has_discovery_tables()) + if (!uncore_no_discover && intel_uncore_has_discovery_tables(NULL)) uncore_init = (struct intel_uncore_init_fun *)&generic_uncore_init; else return -ENODEV; @@ -1861,7 +1893,8 @@ static int __init intel_uncore_init(void) uncore_init = (struct intel_uncore_init_fun *)id->driver_data; if (uncore_no_discover && uncore_init->use_discovery) return -ENODEV; - if (uncore_init->use_discovery && !intel_uncore_has_discovery_tables()) + if (uncore_init->use_discovery && + !intel_uncore_has_discovery_tables(uncore_init->uncore_units_ignore)) return -ENODEV; } diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index e278e2e7c051..c30fb5bb1222 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -34,6 +34,8 @@ #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) +#define UNCORE_IGNORE_END -1 + struct pci_extra_dev { struct pci_dev *dev[UNCORE_EXTRA_PCI_DEV_MAX]; }; @@ -208,6 +210,7 @@ struct pci2phy_map { struct pci2phy_map *__find_pci2phy_map(int segment); int uncore_pcibus_to_dieid(struct pci_bus *bus); int uncore_die_to_segment(int die); +int uncore_device_to_die(struct pci_dev *dev); ssize_t uncore_event_show(struct device *dev, struct device_attribute *attr, char *buf); @@ -589,6 +592,7 @@ extern raw_spinlock_t pci2phy_map_lock; extern struct list_head pci2phy_map_head; extern struct pci_extra_dev *uncore_extra_pci_dev; extern struct event_constraint uncore_constraint_empty; +extern int spr_uncore_units_ignore[]; /* uncore_snb.c */ int snb_uncore_pci_init(void); @@ -602,6 +606,7 @@ void skl_uncore_cpu_init(void); void icl_uncore_cpu_init(void); void tgl_uncore_cpu_init(void); void adl_uncore_cpu_init(void); +void mtl_uncore_cpu_init(void); void tgl_uncore_mmio_init(void); void tgl_l_uncore_mmio_init(void); void adl_uncore_mmio_init(void); diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c index 5fd72d4b8bbb..cb488e41807c 100644 --- a/arch/x86/events/intel/uncore_discovery.c +++ b/arch/x86/events/intel/uncore_discovery.c @@ -33,7 +33,7 @@ static int logical_die_id; static int get_device_die_id(struct pci_dev *dev) { - int cpu, node = pcibus_to_node(dev->bus); + int node = pcibus_to_node(dev->bus); /* * If the NUMA info is not available, assume that the logical die id is @@ -43,19 +43,7 @@ static int get_device_die_id(struct pci_dev *dev) if (node < 0) return logical_die_id++; - for_each_cpu(cpu, cpumask_of_node(node)) { - struct cpuinfo_x86 *c = &cpu_data(cpu); - - if (c->initialized && cpu_to_node(cpu) == node) - return c->logical_die_id; - } - - /* - * All CPUs of a node may be offlined. For this case, - * the PCI and MMIO type of uncore blocks which are - * enumerated by the device will be unavailable. - */ - return -1; + return uncore_device_to_die(dev); } #define __node_2_type(cur) \ @@ -140,13 +128,21 @@ uncore_insert_box_info(struct uncore_unit_discovery *unit, unsigned int *box_offset, *ids; int i; - if (WARN_ON_ONCE(!unit->ctl || !unit->ctl_offset || !unit->ctr_offset)) + if (!unit->ctl || !unit->ctl_offset || !unit->ctr_offset) { + pr_info("Invalid address is detected for uncore type %d box %d, " + "Disable the uncore unit.\n", + unit->box_type, unit->box_id); return; + } if (parsed) { type = search_uncore_discovery_type(unit->box_type); - if (WARN_ON_ONCE(!type)) + if (!type) { + pr_info("A spurious uncore type %d is detected, " + "Disable the uncore type.\n", + unit->box_type); return; + } /* Store the first box of each die */ if (!type->box_ctrl_die[die]) type->box_ctrl_die[die] = unit->ctl; @@ -181,8 +177,12 @@ uncore_insert_box_info(struct uncore_unit_discovery *unit, ids[i] = type->ids[i]; box_offset[i] = type->box_offset[i]; - if (WARN_ON_ONCE(unit->box_id == ids[i])) + if (unit->box_id == ids[i]) { + pr_info("Duplicate uncore type %d box ID %d is detected, " + "Drop the duplicate uncore unit.\n", + unit->box_type, unit->box_id); goto free_ids; + } } ids[i] = unit->box_id; box_offset[i] = unit->ctl - type->box_ctrl; @@ -202,8 +202,25 @@ free_box_offset: } +static bool +uncore_ignore_unit(struct uncore_unit_discovery *unit, int *ignore) +{ + int i; + + if (!ignore) + return false; + + for (i = 0; ignore[i] != UNCORE_IGNORE_END ; i++) { + if (unit->box_type == ignore[i]) + return true; + } + + return false; +} + static int parse_discovery_table(struct pci_dev *dev, int die, - u32 bar_offset, bool *parsed) + u32 bar_offset, bool *parsed, + int *ignore) { struct uncore_global_discovery global; struct uncore_unit_discovery unit; @@ -258,6 +275,9 @@ static int parse_discovery_table(struct pci_dev *dev, int die, if (unit.access_type >= UNCORE_ACCESS_MAX) continue; + if (uncore_ignore_unit(&unit, ignore)) + continue; + uncore_insert_box_info(&unit, die, *parsed); } @@ -266,7 +286,7 @@ static int parse_discovery_table(struct pci_dev *dev, int die, return 0; } -bool intel_uncore_has_discovery_tables(void) +bool intel_uncore_has_discovery_tables(int *ignore) { u32 device, val, entry_id, bar_offset; int die, dvsec = 0, ret = true; @@ -302,7 +322,7 @@ bool intel_uncore_has_discovery_tables(void) if (die < 0) continue; - parse_discovery_table(dev, die, bar_offset, &parsed); + parse_discovery_table(dev, die, bar_offset, &parsed, ignore); } } diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h index f4439357779a..6ee80ad3423e 100644 --- a/arch/x86/events/intel/uncore_discovery.h +++ b/arch/x86/events/intel/uncore_discovery.h @@ -21,9 +21,15 @@ /* Global discovery table size */ #define UNCORE_DISCOVERY_GLOBAL_MAP_SIZE 0x20 -#define UNCORE_DISCOVERY_PCI_DOMAIN(data) ((data >> 28) & 0x7) -#define UNCORE_DISCOVERY_PCI_BUS(data) ((data >> 20) & 0xff) -#define UNCORE_DISCOVERY_PCI_DEVFN(data) ((data >> 12) & 0xff) +#define UNCORE_DISCOVERY_PCI_DOMAIN_OFFSET 28 +#define UNCORE_DISCOVERY_PCI_DOMAIN(data) \ + ((data >> UNCORE_DISCOVERY_PCI_DOMAIN_OFFSET) & 0x7) +#define UNCORE_DISCOVERY_PCI_BUS_OFFSET 20 +#define UNCORE_DISCOVERY_PCI_BUS(data) \ + ((data >> UNCORE_DISCOVERY_PCI_BUS_OFFSET) & 0xff) +#define UNCORE_DISCOVERY_PCI_DEVFN_OFFSET 12 +#define UNCORE_DISCOVERY_PCI_DEVFN(data) \ + ((data >> UNCORE_DISCOVERY_PCI_DEVFN_OFFSET) & 0xff) #define UNCORE_DISCOVERY_PCI_BOX_CTRL(data) (data & 0xfff) @@ -122,7 +128,7 @@ struct intel_uncore_discovery_type { unsigned int *box_offset; /* Box offset */ }; -bool intel_uncore_has_discovery_tables(void); +bool intel_uncore_has_discovery_tables(int *ignore); void intel_uncore_clear_discovery_tables(void); void intel_uncore_generic_uncore_cpu_init(void); int intel_uncore_generic_uncore_pci_init(void); diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 1f4869227efb..7fd4334e12a1 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -109,6 +109,19 @@ #define PCI_DEVICE_ID_INTEL_RPL_23_IMC 0xA728 #define PCI_DEVICE_ID_INTEL_RPL_24_IMC 0xA729 #define PCI_DEVICE_ID_INTEL_RPL_25_IMC 0xA72A +#define PCI_DEVICE_ID_INTEL_MTL_1_IMC 0x7d00 +#define PCI_DEVICE_ID_INTEL_MTL_2_IMC 0x7d01 +#define PCI_DEVICE_ID_INTEL_MTL_3_IMC 0x7d02 +#define PCI_DEVICE_ID_INTEL_MTL_4_IMC 0x7d05 +#define PCI_DEVICE_ID_INTEL_MTL_5_IMC 0x7d10 +#define PCI_DEVICE_ID_INTEL_MTL_6_IMC 0x7d14 +#define PCI_DEVICE_ID_INTEL_MTL_7_IMC 0x7d15 +#define PCI_DEVICE_ID_INTEL_MTL_8_IMC 0x7d16 +#define PCI_DEVICE_ID_INTEL_MTL_9_IMC 0x7d21 +#define PCI_DEVICE_ID_INTEL_MTL_10_IMC 0x7d22 +#define PCI_DEVICE_ID_INTEL_MTL_11_IMC 0x7d23 +#define PCI_DEVICE_ID_INTEL_MTL_12_IMC 0x7d24 +#define PCI_DEVICE_ID_INTEL_MTL_13_IMC 0x7d28 #define IMC_UNCORE_DEV(a) \ @@ -205,6 +218,32 @@ #define ADL_UNC_ARB_PERFEVTSEL0 0x2FD0 #define ADL_UNC_ARB_MSR_OFFSET 0x8 +/* MTL Cbo register */ +#define MTL_UNC_CBO_0_PER_CTR0 0x2448 +#define MTL_UNC_CBO_0_PERFEVTSEL0 0x2442 + +/* MTL HAC_ARB register */ +#define MTL_UNC_HAC_ARB_CTR 0x2018 +#define MTL_UNC_HAC_ARB_CTRL 0x2012 + +/* MTL ARB register */ +#define MTL_UNC_ARB_CTR 0x2418 +#define MTL_UNC_ARB_CTRL 0x2412 + +/* MTL cNCU register */ +#define MTL_UNC_CNCU_FIXED_CTR 0x2408 +#define MTL_UNC_CNCU_FIXED_CTRL 0x2402 +#define MTL_UNC_CNCU_BOX_CTL 0x240e + +/* MTL sNCU register */ +#define MTL_UNC_SNCU_FIXED_CTR 0x2008 +#define MTL_UNC_SNCU_FIXED_CTRL 0x2002 +#define MTL_UNC_SNCU_BOX_CTL 0x200e + +/* MTL HAC_CBO register */ +#define MTL_UNC_HBO_CTR 0x2048 +#define MTL_UNC_HBO_CTRL 0x2042 + DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); DEFINE_UNCORE_FORMAT_ATTR(chmask, chmask, "config:8-11"); @@ -598,6 +637,115 @@ void adl_uncore_cpu_init(void) uncore_msr_uncores = adl_msr_uncores; } +static struct intel_uncore_type mtl_uncore_cbox = { + .name = "cbox", + .num_counters = 2, + .perf_ctr_bits = 48, + .perf_ctr = MTL_UNC_CBO_0_PER_CTR0, + .event_ctl = MTL_UNC_CBO_0_PERFEVTSEL0, + .event_mask = ADL_UNC_RAW_EVENT_MASK, + .msr_offset = SNB_UNC_CBO_MSR_OFFSET, + .ops = &icl_uncore_msr_ops, + .format_group = &adl_uncore_format_group, +}; + +static struct intel_uncore_type mtl_uncore_hac_arb = { + .name = "hac_arb", + .num_counters = 2, + .num_boxes = 2, + .perf_ctr_bits = 48, + .perf_ctr = MTL_UNC_HAC_ARB_CTR, + .event_ctl = MTL_UNC_HAC_ARB_CTRL, + .event_mask = ADL_UNC_RAW_EVENT_MASK, + .msr_offset = SNB_UNC_CBO_MSR_OFFSET, + .ops = &icl_uncore_msr_ops, + .format_group = &adl_uncore_format_group, +}; + +static struct intel_uncore_type mtl_uncore_arb = { + .name = "arb", + .num_counters = 2, + .num_boxes = 2, + .perf_ctr_bits = 48, + .perf_ctr = MTL_UNC_ARB_CTR, + .event_ctl = MTL_UNC_ARB_CTRL, + .event_mask = ADL_UNC_RAW_EVENT_MASK, + .msr_offset = SNB_UNC_CBO_MSR_OFFSET, + .ops = &icl_uncore_msr_ops, + .format_group = &adl_uncore_format_group, +}; + +static struct intel_uncore_type mtl_uncore_hac_cbox = { + .name = "hac_cbox", + .num_counters = 2, + .num_boxes = 2, + .perf_ctr_bits = 48, + .perf_ctr = MTL_UNC_HBO_CTR, + .event_ctl = MTL_UNC_HBO_CTRL, + .event_mask = ADL_UNC_RAW_EVENT_MASK, + .msr_offset = SNB_UNC_CBO_MSR_OFFSET, + .ops = &icl_uncore_msr_ops, + .format_group = &adl_uncore_format_group, +}; + +static void mtl_uncore_msr_init_box(struct intel_uncore_box *box) +{ + wrmsrl(uncore_msr_box_ctl(box), SNB_UNC_GLOBAL_CTL_EN); +} + +static struct intel_uncore_ops mtl_uncore_msr_ops = { + .init_box = mtl_uncore_msr_init_box, + .disable_event = snb_uncore_msr_disable_event, + .enable_event = snb_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, +}; + +static struct intel_uncore_type mtl_uncore_cncu = { + .name = "cncu", + .num_counters = 1, + .num_boxes = 1, + .box_ctl = MTL_UNC_CNCU_BOX_CTL, + .fixed_ctr_bits = 48, + .fixed_ctr = MTL_UNC_CNCU_FIXED_CTR, + .fixed_ctl = MTL_UNC_CNCU_FIXED_CTRL, + .single_fixed = 1, + .event_mask = SNB_UNC_CTL_EV_SEL_MASK, + .format_group = &icl_uncore_clock_format_group, + .ops = &mtl_uncore_msr_ops, + .event_descs = icl_uncore_events, +}; + +static struct intel_uncore_type mtl_uncore_sncu = { + .name = "sncu", + .num_counters = 1, + .num_boxes = 1, + .box_ctl = MTL_UNC_SNCU_BOX_CTL, + .fixed_ctr_bits = 48, + .fixed_ctr = MTL_UNC_SNCU_FIXED_CTR, + .fixed_ctl = MTL_UNC_SNCU_FIXED_CTRL, + .single_fixed = 1, + .event_mask = SNB_UNC_CTL_EV_SEL_MASK, + .format_group = &icl_uncore_clock_format_group, + .ops = &mtl_uncore_msr_ops, + .event_descs = icl_uncore_events, +}; + +static struct intel_uncore_type *mtl_msr_uncores[] = { + &mtl_uncore_cbox, + &mtl_uncore_hac_arb, + &mtl_uncore_arb, + &mtl_uncore_hac_cbox, + &mtl_uncore_cncu, + &mtl_uncore_sncu, + NULL +}; + +void mtl_uncore_cpu_init(void) +{ + mtl_uncore_cbox.num_boxes = icl_get_cbox_num(); + uncore_msr_uncores = mtl_msr_uncores; +} + enum { SNB_PCI_UNCORE_IMC, }; @@ -1264,6 +1412,19 @@ static const struct pci_device_id tgl_uncore_pci_ids[] = { IMC_UNCORE_DEV(RPL_23), IMC_UNCORE_DEV(RPL_24), IMC_UNCORE_DEV(RPL_25), + IMC_UNCORE_DEV(MTL_1), + IMC_UNCORE_DEV(MTL_2), + IMC_UNCORE_DEV(MTL_3), + IMC_UNCORE_DEV(MTL_4), + IMC_UNCORE_DEV(MTL_5), + IMC_UNCORE_DEV(MTL_6), + IMC_UNCORE_DEV(MTL_7), + IMC_UNCORE_DEV(MTL_8), + IMC_UNCORE_DEV(MTL_9), + IMC_UNCORE_DEV(MTL_10), + IMC_UNCORE_DEV(MTL_11), + IMC_UNCORE_DEV(MTL_12), + IMC_UNCORE_DEV(MTL_13), { /* end: all zeroes */ } }; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 44c2f879f708..7d1199554fe3 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1453,9 +1453,6 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool } raw_spin_unlock(&pci2phy_map_lock); } else { - int node = pcibus_to_node(ubox_dev->bus); - int cpu; - segment = pci_domain_nr(ubox_dev->bus); raw_spin_lock(&pci2phy_map_lock); map = __find_pci2phy_map(segment); @@ -1465,15 +1462,8 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool break; } - die_id = -1; - for_each_cpu(cpu, cpumask_of_pcibus(ubox_dev->bus)) { - struct cpuinfo_x86 *c = &cpu_data(cpu); + map->pbus_to_dieid[bus] = die_id = uncore_device_to_die(ubox_dev); - if (c->initialized && cpu_to_node(cpu) == node) { - map->pbus_to_dieid[bus] = die_id = c->logical_die_id; - break; - } - } raw_spin_unlock(&pci2phy_map_lock); if (WARN_ON_ONCE(die_id == -1)) { @@ -6142,24 +6132,6 @@ static int spr_upi_get_topology(struct intel_uncore_type *type) return discover_upi_topology(type, SPR_UBOX_DID, SPR_UPI_REGS_ADDR_DEVICE_LINK0); } -static struct intel_uncore_type spr_uncore_upi = { - .event_mask = SNBEP_PMON_RAW_EVENT_MASK, - .event_mask_ext = SPR_RAW_EVENT_MASK_EXT, - .format_group = &spr_uncore_raw_format_group, - .ops = &spr_uncore_pci_ops, - .name = "upi", - .attr_update = spr_upi_attr_update, - .get_topology = spr_upi_get_topology, - .set_mapping = spr_upi_set_mapping, - .cleanup_mapping = spr_upi_cleanup_mapping, -}; - -static struct intel_uncore_type spr_uncore_m3upi = { - SPR_UNCORE_PCI_COMMON_FORMAT(), - .name = "m3upi", - .constraints = icx_uncore_m3upi_constraints, -}; - static struct intel_uncore_type spr_uncore_mdf = { SPR_UNCORE_COMMON_FORMAT(), .name = "mdf", @@ -6168,7 +6140,13 @@ static struct intel_uncore_type spr_uncore_mdf = { #define UNCORE_SPR_NUM_UNCORE_TYPES 12 #define UNCORE_SPR_IIO 1 #define UNCORE_SPR_IMC 6 +#define UNCORE_SPR_UPI 8 +#define UNCORE_SPR_M3UPI 9 +/* + * The uncore units, which are supported by the discovery table, + * are defined here. + */ static struct intel_uncore_type *spr_uncores[UNCORE_SPR_NUM_UNCORE_TYPES] = { &spr_uncore_chabox, &spr_uncore_iio, @@ -6178,12 +6156,56 @@ static struct intel_uncore_type *spr_uncores[UNCORE_SPR_NUM_UNCORE_TYPES] = { NULL, &spr_uncore_imc, &spr_uncore_m2m, - &spr_uncore_upi, - &spr_uncore_m3upi, + NULL, + NULL, NULL, &spr_uncore_mdf, }; +/* + * The uncore units, which are not supported by the discovery table, + * are implemented from here. + */ +#define SPR_UNCORE_UPI_NUM_BOXES 4 + +static unsigned int spr_upi_pci_offsets[SPR_UNCORE_UPI_NUM_BOXES] = { + 0, 0x8000, 0x10000, 0x18000 +}; + +static struct intel_uncore_type spr_uncore_upi = { + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .event_mask_ext = SPR_RAW_EVENT_MASK_EXT, + .format_group = &spr_uncore_raw_format_group, + .ops = &spr_uncore_pci_ops, + .name = "upi", + .attr_update = spr_upi_attr_update, + .get_topology = spr_upi_get_topology, + .set_mapping = spr_upi_set_mapping, + .cleanup_mapping = spr_upi_cleanup_mapping, + .type_id = UNCORE_SPR_UPI, + .num_counters = 4, + .num_boxes = SPR_UNCORE_UPI_NUM_BOXES, + .perf_ctr_bits = 48, + .perf_ctr = ICX_UPI_PCI_PMON_CTR0, + .event_ctl = ICX_UPI_PCI_PMON_CTL0, + .box_ctl = ICX_UPI_PCI_PMON_BOX_CTL, + .pci_offsets = spr_upi_pci_offsets, +}; + +static struct intel_uncore_type spr_uncore_m3upi = { + SPR_UNCORE_PCI_COMMON_FORMAT(), + .name = "m3upi", + .type_id = UNCORE_SPR_M3UPI, + .num_counters = 4, + .num_boxes = SPR_UNCORE_UPI_NUM_BOXES, + .perf_ctr_bits = 48, + .perf_ctr = ICX_M3UPI_PCI_PMON_CTR0, + .event_ctl = ICX_M3UPI_PCI_PMON_CTL0, + .box_ctl = ICX_M3UPI_PCI_PMON_BOX_CTL, + .pci_offsets = spr_upi_pci_offsets, + .constraints = icx_uncore_m3upi_constraints, +}; + enum perf_uncore_spr_iio_freerunning_type_id { SPR_IIO_MSR_IOCLK, SPR_IIO_MSR_BW_IN, @@ -6314,6 +6336,7 @@ static struct intel_uncore_type spr_uncore_imc_free_running = { #define UNCORE_SPR_MSR_EXTRA_UNCORES 1 #define UNCORE_SPR_MMIO_EXTRA_UNCORES 1 +#define UNCORE_SPR_PCI_EXTRA_UNCORES 2 static struct intel_uncore_type *spr_msr_uncores[UNCORE_SPR_MSR_EXTRA_UNCORES] = { &spr_uncore_iio_free_running, @@ -6323,6 +6346,17 @@ static struct intel_uncore_type *spr_mmio_uncores[UNCORE_SPR_MMIO_EXTRA_UNCORES] &spr_uncore_imc_free_running, }; +static struct intel_uncore_type *spr_pci_uncores[UNCORE_SPR_PCI_EXTRA_UNCORES] = { + &spr_uncore_upi, + &spr_uncore_m3upi +}; + +int spr_uncore_units_ignore[] = { + UNCORE_SPR_UPI, + UNCORE_SPR_M3UPI, + UNCORE_IGNORE_END +}; + static void uncore_type_customized_copy(struct intel_uncore_type *to_type, struct intel_uncore_type *from_type) { @@ -6423,9 +6457,69 @@ void spr_uncore_cpu_init(void) spr_uncore_iio_free_running.num_boxes = uncore_type_max_boxes(uncore_msr_uncores, UNCORE_SPR_IIO); } +#define SPR_UNCORE_UPI_PCIID 0x3241 +#define SPR_UNCORE_UPI0_DEVFN 0x9 +#define SPR_UNCORE_M3UPI_PCIID 0x3246 +#define SPR_UNCORE_M3UPI0_DEVFN 0x29 + +static void spr_update_device_location(int type_id) +{ + struct intel_uncore_type *type; + struct pci_dev *dev = NULL; + u32 device, devfn; + u64 *ctls; + int die; + + if (type_id == UNCORE_SPR_UPI) { + type = &spr_uncore_upi; + device = SPR_UNCORE_UPI_PCIID; + devfn = SPR_UNCORE_UPI0_DEVFN; + } else if (type_id == UNCORE_SPR_M3UPI) { + type = &spr_uncore_m3upi; + device = SPR_UNCORE_M3UPI_PCIID; + devfn = SPR_UNCORE_M3UPI0_DEVFN; + } else + return; + + ctls = kcalloc(__uncore_max_dies, sizeof(u64), GFP_KERNEL); + if (!ctls) { + type->num_boxes = 0; + return; + } + + while ((dev = pci_get_device(PCI_VENDOR_ID_INTEL, device, dev)) != NULL) { + if (devfn != dev->devfn) + continue; + + die = uncore_device_to_die(dev); + if (die < 0) + continue; + + ctls[die] = pci_domain_nr(dev->bus) << UNCORE_DISCOVERY_PCI_DOMAIN_OFFSET | + dev->bus->number << UNCORE_DISCOVERY_PCI_BUS_OFFSET | + devfn << UNCORE_DISCOVERY_PCI_DEVFN_OFFSET | + type->box_ctl; + } + + type->box_ctls = ctls; +} + int spr_uncore_pci_init(void) { - uncore_pci_uncores = uncore_get_uncores(UNCORE_ACCESS_PCI, 0, NULL); + /* + * The discovery table of UPI on some SPR variant is broken, + * which impacts the detection of both UPI and M3UPI uncore PMON. + * Use the pre-defined UPI and M3UPI table to replace. + * + * The accurate location, e.g., domain and BUS number, + * can only be retrieved at load time. + * Update the location of UPI and M3UPI. + */ + spr_update_device_location(UNCORE_SPR_UPI); + spr_update_device_location(UNCORE_SPR_M3UPI); + uncore_pci_uncores = uncore_get_uncores(UNCORE_ACCESS_PCI, + UNCORE_SPR_PCI_EXTRA_UNCORES, + spr_pci_uncores); return 0; } diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 0e849f28a5c1..d6de4487348c 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -35,15 +35,17 @@ * per-core reg tables. */ enum extra_reg_type { - EXTRA_REG_NONE = -1, /* not used */ + EXTRA_REG_NONE = -1, /* not used */ - EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */ - EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ - EXTRA_REG_LBR = 2, /* lbr_select */ - EXTRA_REG_LDLAT = 3, /* ld_lat_threshold */ - EXTRA_REG_FE = 4, /* fe_* */ + EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */ + EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ + EXTRA_REG_LBR = 2, /* lbr_select */ + EXTRA_REG_LDLAT = 3, /* ld_lat_threshold */ + EXTRA_REG_FE = 4, /* fe_* */ + EXTRA_REG_SNOOP_0 = 5, /* snoop response 0 */ + EXTRA_REG_SNOOP_1 = 6, /* snoop response 1 */ - EXTRA_REG_MAX /* number of entries needed */ + EXTRA_REG_MAX /* number of entries needed */ }; struct event_constraint { @@ -606,6 +608,7 @@ union perf_capabilities { u64 pebs_baseline:1; u64 perf_metrics:1; u64 pebs_output_pt_available:1; + u64 pebs_timing_info:1; u64 anythread_deprecated:1; }; u64 capabilities; @@ -647,6 +650,7 @@ enum { }; #define PERF_PEBS_DATA_SOURCE_MAX 0x10 +#define PERF_PEBS_DATA_SOURCE_MASK (PERF_PEBS_DATA_SOURCE_MAX - 1) struct x86_hybrid_pmu { struct pmu pmu; @@ -1000,6 +1004,7 @@ do { \ #define PMU_FL_PAIR 0x40 /* merge counters for large incr. events */ #define PMU_FL_INSTR_LATENCY 0x80 /* Support Instruction Latency in PEBS Memory Info Record */ #define PMU_FL_MEM_LOADS_AUX 0x100 /* Require an auxiliary event for the complete memory info */ +#define PMU_FL_RETIRE_LATENCY 0x200 /* Support Retire Latency in PEBS */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr @@ -1486,6 +1491,8 @@ int intel_pmu_drain_bts_buffer(void); u64 adl_latency_data_small(struct perf_event *event, u64 status); +u64 mtl_latency_data_small(struct perf_event *event, u64 status); + extern struct event_constraint intel_core2_pebs_event_constraints[]; extern struct event_constraint intel_atom_pebs_event_constraints[]; @@ -1597,6 +1604,8 @@ void intel_pmu_pebs_data_source_adl(void); void intel_pmu_pebs_data_source_grt(void); +void intel_pmu_pebs_data_source_mtl(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c index 949d845c922b..3e9acdaeed1e 100644 --- a/arch/x86/events/zhaoxin/core.c +++ b/arch/x86/events/zhaoxin/core.c @@ -541,7 +541,13 @@ __init int zhaoxin_pmu_init(void) switch (boot_cpu_data.x86) { case 0x06: - if (boot_cpu_data.x86_model == 0x0f || boot_cpu_data.x86_model == 0x19) { + /* + * Support Zhaoxin CPU from ZXC series, exclude Nano series through FMS. + * Nano FMS: Family=6, Model=F, Stepping=[0-A][C-D] + * ZXC FMS: Family=6, Model=F, Stepping=E-F OR Family=6, Model=0x19, Stepping=0-3 + */ + if ((boot_cpu_data.x86_model == 0x0f && boot_cpu_data.x86_stepping >= 0x0e) || + boot_cpu_data.x86_model == 0x19) { x86_pmu.max_period = x86_pmu.cntval_mask >> 1; diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 65064d9f7fa6..8eb74cf386db 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -14,6 +14,7 @@ #include <asm/mmu.h> #include <asm/mpspec.h> #include <asm/x86_init.h> +#include <asm/cpufeature.h> #ifdef CONFIG_ACPI_APEI # include <asm/pgtable_types.h> @@ -63,6 +64,13 @@ extern int (*acpi_suspend_lowlevel)(void); /* Physical address to resume after wakeup */ unsigned long acpi_get_wakeup_address(void); +static inline bool acpi_skip_set_wakeup_address(void) +{ + return cpu_feature_enabled(X86_FEATURE_XENPV); +} + +#define acpi_skip_set_wakeup_address acpi_skip_set_wakeup_address + /* * Check if the CPU can handle C2 and deeper */ diff --git a/arch/x86/include/asm/agp.h b/arch/x86/include/asm/agp.h index cd7b14322035..c8c111d8fbd7 100644 --- a/arch/x86/include/asm/agp.h +++ b/arch/x86/include/asm/agp.h @@ -23,10 +23,4 @@ */ #define flush_agp_cache() wbinvd() -/* GATT allocation. Returns/accepts GATT kernel virtual address. */ -#define alloc_gatt_pages(order) \ - ((char *)__get_free_pages(GFP_KERNEL, (order))) -#define free_gatt_pages(table, order) \ - free_pages((unsigned long)(table), (order)) - #endif /* _ASM_X86_AGP_H */ diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 7659217f4d49..e2975a32d443 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -6,8 +6,10 @@ #include <linux/stringify.h> #include <asm/asm.h> -#define ALTINSTR_FLAG_INV (1 << 15) -#define ALT_NOT(feat) ((feat) | ALTINSTR_FLAG_INV) +#define ALT_FLAGS_SHIFT 16 + +#define ALT_FLAG_NOT BIT(0) +#define ALT_NOT(feature) ((ALT_FLAG_NOT << ALT_FLAGS_SHIFT) | (feature)) #ifndef __ASSEMBLY__ @@ -59,10 +61,27 @@ ".long 999b - .\n\t" \ ".popsection\n\t" +/* + * The patching flags are part of the upper bits of the @ft_flags parameter when + * specifying them. The split is currently like this: + * + * [31... flags ...16][15... CPUID feature bit ...0] + * + * but since this is all hidden in the macros argument being split, those fields can be + * extended in the future to fit in a u64 or however the need arises. + */ struct alt_instr { s32 instr_offset; /* original instruction */ s32 repl_offset; /* offset to replacement instruction */ - u16 cpuid; /* cpuid bit set for replacement */ + + union { + struct { + u32 cpuid: 16; /* CPUID bit set for replacement */ + u32 flags: 16; /* patching control flags */ + }; + u32 ft_flags; + }; + u8 instrlen; /* length of original instruction */ u8 replacementlen; /* length of new instruction */ } __packed; @@ -182,10 +201,10 @@ static inline int alternatives_text_reserved(void *start, void *end) " - (" alt_slen ")), 0x90\n" \ alt_end_marker ":\n" -#define ALTINSTR_ENTRY(feature, num) \ +#define ALTINSTR_ENTRY(ft_flags, num) \ " .long 661b - .\n" /* label */ \ " .long " b_replacement(num)"f - .\n" /* new instruction */ \ - " .word " __stringify(feature) "\n" /* feature bit */ \ + " .4byte " __stringify(ft_flags) "\n" /* feature + flags */ \ " .byte " alt_total_slen "\n" /* source len */ \ " .byte " alt_rlen(num) "\n" /* replacement len */ @@ -194,20 +213,20 @@ static inline int alternatives_text_reserved(void *start, void *end) b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n" /* alternative assembly primitive: */ -#define ALTERNATIVE(oldinstr, newinstr, feature) \ +#define ALTERNATIVE(oldinstr, newinstr, ft_flags) \ OLDINSTR(oldinstr, 1) \ ".pushsection .altinstructions,\"a\"\n" \ - ALTINSTR_ENTRY(feature, 1) \ + ALTINSTR_ENTRY(ft_flags, 1) \ ".popsection\n" \ ".pushsection .altinstr_replacement, \"ax\"\n" \ ALTINSTR_REPLACEMENT(newinstr, 1) \ ".popsection\n" -#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\ +#define ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) \ OLDINSTR_2(oldinstr, 1, 2) \ ".pushsection .altinstructions,\"a\"\n" \ - ALTINSTR_ENTRY(feature1, 1) \ - ALTINSTR_ENTRY(feature2, 2) \ + ALTINSTR_ENTRY(ft_flags1, 1) \ + ALTINSTR_ENTRY(ft_flags2, 2) \ ".popsection\n" \ ".pushsection .altinstr_replacement, \"ax\"\n" \ ALTINSTR_REPLACEMENT(newinstr1, 1) \ @@ -215,21 +234,22 @@ static inline int alternatives_text_reserved(void *start, void *end) ".popsection\n" /* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */ -#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \ +#define ALTERNATIVE_TERNARY(oldinstr, ft_flags, newinstr_yes, newinstr_no) \ ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS, \ - newinstr_yes, feature) - -#define ALTERNATIVE_3(oldinsn, newinsn1, feat1, newinsn2, feat2, newinsn3, feat3) \ - OLDINSTR_3(oldinsn, 1, 2, 3) \ - ".pushsection .altinstructions,\"a\"\n" \ - ALTINSTR_ENTRY(feat1, 1) \ - ALTINSTR_ENTRY(feat2, 2) \ - ALTINSTR_ENTRY(feat3, 3) \ - ".popsection\n" \ - ".pushsection .altinstr_replacement, \"ax\"\n" \ - ALTINSTR_REPLACEMENT(newinsn1, 1) \ - ALTINSTR_REPLACEMENT(newinsn2, 2) \ - ALTINSTR_REPLACEMENT(newinsn3, 3) \ + newinstr_yes, ft_flags) + +#define ALTERNATIVE_3(oldinsn, newinsn1, ft_flags1, newinsn2, ft_flags2, \ + newinsn3, ft_flags3) \ + OLDINSTR_3(oldinsn, 1, 2, 3) \ + ".pushsection .altinstructions,\"a\"\n" \ + ALTINSTR_ENTRY(ft_flags1, 1) \ + ALTINSTR_ENTRY(ft_flags2, 2) \ + ALTINSTR_ENTRY(ft_flags3, 3) \ + ".popsection\n" \ + ".pushsection .altinstr_replacement, \"ax\"\n" \ + ALTINSTR_REPLACEMENT(newinsn1, 1) \ + ALTINSTR_REPLACEMENT(newinsn2, 2) \ + ALTINSTR_REPLACEMENT(newinsn3, 3) \ ".popsection\n" /* @@ -244,14 +264,14 @@ static inline int alternatives_text_reserved(void *start, void *end) * For non barrier like inlines please define new variants * without volatile and memory clobber. */ -#define alternative(oldinstr, newinstr, feature) \ - asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, feature) : : : "memory") +#define alternative(oldinstr, newinstr, ft_flags) \ + asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags) : : : "memory") -#define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \ - asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory") +#define alternative_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) \ + asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) ::: "memory") -#define alternative_ternary(oldinstr, feature, newinstr_yes, newinstr_no) \ - asm_inline volatile(ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) ::: "memory") +#define alternative_ternary(oldinstr, ft_flags, newinstr_yes, newinstr_no) \ + asm_inline volatile(ALTERNATIVE_TERNARY(oldinstr, ft_flags, newinstr_yes, newinstr_no) ::: "memory") /* * Alternative inline assembly with input. @@ -261,8 +281,8 @@ static inline int alternatives_text_reserved(void *start, void *end) * Argument numbers start with 1. * Leaving an unused argument 0 to keep API compatibility. */ -#define alternative_input(oldinstr, newinstr, feature, input...) \ - asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, feature) \ +#define alternative_input(oldinstr, newinstr, ft_flags, input...) \ + asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags) \ : : "i" (0), ## input) /* @@ -273,20 +293,20 @@ static inline int alternatives_text_reserved(void *start, void *end) * Otherwise, if CPU has feature1, newinstr1 is used. * Otherwise, oldinstr is used. */ -#define alternative_input_2(oldinstr, newinstr1, feature1, newinstr2, \ - feature2, input...) \ - asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, \ - newinstr2, feature2) \ +#define alternative_input_2(oldinstr, newinstr1, ft_flags1, newinstr2, \ + ft_flags2, input...) \ + asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, \ + newinstr2, ft_flags2) \ : : "i" (0), ## input) /* Like alternative_input, but with a single output argument */ -#define alternative_io(oldinstr, newinstr, feature, output, input...) \ - asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, feature) \ +#define alternative_io(oldinstr, newinstr, ft_flags, output, input...) \ + asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags) \ : output : "i" (0), ## input) /* Like alternative_io, but for replacing a direct call with another one. */ -#define alternative_call(oldfunc, newfunc, feature, output, input...) \ - asm_inline volatile (ALTERNATIVE("call %P[old]", "call %P[new]", feature) \ +#define alternative_call(oldfunc, newfunc, ft_flags, output, input...) \ + asm_inline volatile (ALTERNATIVE("call %P[old]", "call %P[new]", ft_flags) \ : output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input) /* @@ -295,10 +315,10 @@ static inline int alternatives_text_reserved(void *start, void *end) * Otherwise, if CPU has feature1, function1 is used. * Otherwise, old function is used. */ -#define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \ +#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \ output, input...) \ - asm_inline volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\ - "call %P[new2]", feature2) \ + asm_inline volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", ft_flags1,\ + "call %P[new2]", ft_flags2) \ : output, ASM_CALL_CONSTRAINT \ : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ [new2] "i" (newfunc2), ## input) @@ -347,10 +367,10 @@ static inline int alternatives_text_reserved(void *start, void *end) * enough information for the alternatives patching code to patch an * instruction. See apply_alternatives(). */ -.macro altinstruction_entry orig alt feature orig_len alt_len +.macro altinstr_entry orig alt ft_flags orig_len alt_len .long \orig - . .long \alt - . - .word \feature + .4byte \ft_flags .byte \orig_len .byte \alt_len .endm @@ -361,7 +381,7 @@ static inline int alternatives_text_reserved(void *start, void *end) * @newinstr. ".skip" directive takes care of proper instruction padding * in case @newinstr is longer than @oldinstr. */ -.macro ALTERNATIVE oldinstr, newinstr, feature +.macro ALTERNATIVE oldinstr, newinstr, ft_flags 140: \oldinstr 141: @@ -369,7 +389,7 @@ static inline int alternatives_text_reserved(void *start, void *end) 142: .pushsection .altinstructions,"a" - altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f + altinstr_entry 140b,143f,\ft_flags,142b-140b,144f-143f .popsection .pushsection .altinstr_replacement,"ax" @@ -399,7 +419,7 @@ static inline int alternatives_text_reserved(void *start, void *end) * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has * @feature2, it replaces @oldinstr with @feature2. */ -.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2 +.macro ALTERNATIVE_2 oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2 140: \oldinstr 141: @@ -408,8 +428,8 @@ static inline int alternatives_text_reserved(void *start, void *end) 142: .pushsection .altinstructions,"a" - altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f - altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f + altinstr_entry 140b,143f,\ft_flags1,142b-140b,144f-143f + altinstr_entry 140b,144f,\ft_flags2,142b-140b,145f-144f .popsection .pushsection .altinstr_replacement,"ax" @@ -421,7 +441,7 @@ static inline int alternatives_text_reserved(void *start, void *end) .popsection .endm -.macro ALTERNATIVE_3 oldinstr, newinstr1, feature1, newinstr2, feature2, newinstr3, feature3 +.macro ALTERNATIVE_3 oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2, newinstr3, ft_flags3 140: \oldinstr 141: @@ -430,9 +450,9 @@ static inline int alternatives_text_reserved(void *start, void *end) 142: .pushsection .altinstructions,"a" - altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f - altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f - altinstruction_entry 140b,145f,\feature3,142b-140b,146f-145f + altinstr_entry 140b,143f,\ft_flags1,142b-140b,144f-143f + altinstr_entry 140b,144f,\ft_flags2,142b-140b,145f-144f + altinstr_entry 140b,145f,\ft_flags3,142b-140b,146f-145f .popsection .pushsection .altinstr_replacement,"ax" @@ -447,9 +467,9 @@ static inline int alternatives_text_reserved(void *start, void *end) .endm /* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */ -#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \ +#define ALTERNATIVE_TERNARY(oldinstr, ft_flags, newinstr_yes, newinstr_no) \ ALTERNATIVE_2 oldinstr, newinstr_no, X86_FEATURE_ALWAYS, \ - newinstr_yes, feature + newinstr_yes, ft_flags #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 8f80de627c60..b1a98fa38828 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -12,6 +12,7 @@ #include <asm/special_insns.h> #include <asm/preempt.h> #include <asm/asm.h> +#include <asm/gsseg.h> #ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 5efd01b548d1..808b4eece251 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -71,7 +71,7 @@ ATOMIC64_DECL(add_unless); * the old value. */ -static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n) +static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n) { return arch_cmpxchg64(&v->counter, o, n); } @@ -85,7 +85,7 @@ static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n) * Atomically xchgs the value of @v to @n and returns * the old value. */ -static inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n) +static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n) { s64 o; unsigned high = (unsigned)(n >> 32); @@ -104,7 +104,7 @@ static inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n) * * Atomically sets the value of @v to @n. */ -static inline void arch_atomic64_set(atomic64_t *v, s64 i) +static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i) { unsigned high = (unsigned)(i >> 32); unsigned low = (unsigned)i; @@ -119,7 +119,7 @@ static inline void arch_atomic64_set(atomic64_t *v, s64 i) * * Atomically reads the value of @v and returns it. */ -static inline s64 arch_atomic64_read(const atomic64_t *v) +static __always_inline s64 arch_atomic64_read(const atomic64_t *v) { s64 r; alternative_atomic64(read, "=&A" (r), "c" (v) : "memory"); @@ -133,7 +133,7 @@ static inline s64 arch_atomic64_read(const atomic64_t *v) * * Atomically adds @i to @v and returns @i + *@v */ -static inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v) { alternative_atomic64(add_return, ASM_OUTPUT2("+A" (i), "+c" (v)), @@ -145,7 +145,7 @@ static inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v) /* * Other variants with different arithmetic operators: */ -static inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v) { alternative_atomic64(sub_return, ASM_OUTPUT2("+A" (i), "+c" (v)), @@ -154,7 +154,7 @@ static inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v) } #define arch_atomic64_sub_return arch_atomic64_sub_return -static inline s64 arch_atomic64_inc_return(atomic64_t *v) +static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v) { s64 a; alternative_atomic64(inc_return, "=&A" (a), @@ -163,7 +163,7 @@ static inline s64 arch_atomic64_inc_return(atomic64_t *v) } #define arch_atomic64_inc_return arch_atomic64_inc_return -static inline s64 arch_atomic64_dec_return(atomic64_t *v) +static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v) { s64 a; alternative_atomic64(dec_return, "=&A" (a), @@ -179,7 +179,7 @@ static inline s64 arch_atomic64_dec_return(atomic64_t *v) * * Atomically adds @i to @v. */ -static inline s64 arch_atomic64_add(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_add(s64 i, atomic64_t *v) { __alternative_atomic64(add, add_return, ASM_OUTPUT2("+A" (i), "+c" (v)), @@ -194,7 +194,7 @@ static inline s64 arch_atomic64_add(s64 i, atomic64_t *v) * * Atomically subtracts @i from @v. */ -static inline s64 arch_atomic64_sub(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_sub(s64 i, atomic64_t *v) { __alternative_atomic64(sub, sub_return, ASM_OUTPUT2("+A" (i), "+c" (v)), @@ -208,7 +208,7 @@ static inline s64 arch_atomic64_sub(s64 i, atomic64_t *v) * * Atomically increments @v by 1. */ -static inline void arch_atomic64_inc(atomic64_t *v) +static __always_inline void arch_atomic64_inc(atomic64_t *v) { __alternative_atomic64(inc, inc_return, /* no output */, "S" (v) : "memory", "eax", "ecx", "edx"); @@ -221,7 +221,7 @@ static inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ -static inline void arch_atomic64_dec(atomic64_t *v) +static __always_inline void arch_atomic64_dec(atomic64_t *v) { __alternative_atomic64(dec, dec_return, /* no output */, "S" (v) : "memory", "eax", "ecx", "edx"); @@ -237,7 +237,7 @@ static inline void arch_atomic64_dec(atomic64_t *v) * Atomically adds @a to @v, so long as it was not @u. * Returns non-zero if the add was done, zero otherwise. */ -static inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) +static __always_inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { unsigned low = (unsigned)u; unsigned high = (unsigned)(u >> 32); @@ -248,7 +248,7 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) } #define arch_atomic64_add_unless arch_atomic64_add_unless -static inline int arch_atomic64_inc_not_zero(atomic64_t *v) +static __always_inline int arch_atomic64_inc_not_zero(atomic64_t *v) { int r; alternative_atomic64(inc_not_zero, "=&a" (r), @@ -257,7 +257,7 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v) } #define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero -static inline s64 arch_atomic64_dec_if_positive(atomic64_t *v) +static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v) { s64 r; alternative_atomic64(dec_if_positive, "=&A" (r), @@ -269,7 +269,7 @@ static inline s64 arch_atomic64_dec_if_positive(atomic64_t *v) #undef alternative_atomic64 #undef __alternative_atomic64 -static inline void arch_atomic64_and(s64 i, atomic64_t *v) +static __always_inline void arch_atomic64_and(s64 i, atomic64_t *v) { s64 old, c = 0; @@ -277,7 +277,7 @@ static inline void arch_atomic64_and(s64 i, atomic64_t *v) c = old; } -static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v) { s64 old, c = 0; @@ -288,7 +288,7 @@ static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v) } #define arch_atomic64_fetch_and arch_atomic64_fetch_and -static inline void arch_atomic64_or(s64 i, atomic64_t *v) +static __always_inline void arch_atomic64_or(s64 i, atomic64_t *v) { s64 old, c = 0; @@ -296,7 +296,7 @@ static inline void arch_atomic64_or(s64 i, atomic64_t *v) c = old; } -static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v) { s64 old, c = 0; @@ -307,7 +307,7 @@ static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v) } #define arch_atomic64_fetch_or arch_atomic64_fetch_or -static inline void arch_atomic64_xor(s64 i, atomic64_t *v) +static __always_inline void arch_atomic64_xor(s64 i, atomic64_t *v) { s64 old, c = 0; @@ -315,7 +315,7 @@ static inline void arch_atomic64_xor(s64 i, atomic64_t *v) c = old; } -static inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v) { s64 old, c = 0; @@ -326,7 +326,7 @@ static inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v) } #define arch_atomic64_fetch_xor arch_atomic64_fetch_xor -static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v) { s64 old, c = 0; diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 7886d0578fc9..c496595bf601 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -17,7 +17,7 @@ * Atomically reads the value of @v. * Doesn't imply a read memory barrier. */ -static inline s64 arch_atomic64_read(const atomic64_t *v) +static __always_inline s64 arch_atomic64_read(const atomic64_t *v) { return __READ_ONCE((v)->counter); } @@ -29,7 +29,7 @@ static inline s64 arch_atomic64_read(const atomic64_t *v) * * Atomically sets the value of @v to @i. */ -static inline void arch_atomic64_set(atomic64_t *v, s64 i) +static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i) { __WRITE_ONCE(v->counter, i); } @@ -55,7 +55,7 @@ static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v) * * Atomically subtracts @i from @v. */ -static inline void arch_atomic64_sub(s64 i, atomic64_t *v) +static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v) { asm volatile(LOCK_PREFIX "subq %1,%0" : "=m" (v->counter) @@ -71,7 +71,7 @@ static inline void arch_atomic64_sub(s64 i, atomic64_t *v) * true if the result is zero, or false for all * other cases. */ -static inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v) +static __always_inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v) { return GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, e, "er", i); } @@ -113,7 +113,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ -static inline bool arch_atomic64_dec_and_test(atomic64_t *v) +static __always_inline bool arch_atomic64_dec_and_test(atomic64_t *v) { return GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, e); } @@ -127,7 +127,7 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ -static inline bool arch_atomic64_inc_and_test(atomic64_t *v) +static __always_inline bool arch_atomic64_inc_and_test(atomic64_t *v) { return GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, e); } @@ -142,7 +142,7 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -static inline bool arch_atomic64_add_negative(s64 i, atomic64_t *v) +static __always_inline bool arch_atomic64_add_negative(s64 i, atomic64_t *v) { return GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, s, "er", i); } @@ -161,25 +161,25 @@ static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v) } #define arch_atomic64_add_return arch_atomic64_add_return -static inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v) { return arch_atomic64_add_return(-i, v); } #define arch_atomic64_sub_return arch_atomic64_sub_return -static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v) { return xadd(&v->counter, i); } #define arch_atomic64_fetch_add arch_atomic64_fetch_add -static inline s64 arch_atomic64_fetch_sub(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_fetch_sub(s64 i, atomic64_t *v) { return xadd(&v->counter, -i); } #define arch_atomic64_fetch_sub arch_atomic64_fetch_sub -static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) +static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { return arch_cmpxchg(&v->counter, old, new); } @@ -191,13 +191,13 @@ static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s } #define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg -static inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new) +static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new) { return arch_xchg(&v->counter, new); } #define arch_atomic64_xchg arch_atomic64_xchg -static inline void arch_atomic64_and(s64 i, atomic64_t *v) +static __always_inline void arch_atomic64_and(s64 i, atomic64_t *v) { asm volatile(LOCK_PREFIX "andq %1,%0" : "+m" (v->counter) @@ -205,7 +205,7 @@ static inline void arch_atomic64_and(s64 i, atomic64_t *v) : "memory"); } -static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v) { s64 val = arch_atomic64_read(v); @@ -215,7 +215,7 @@ static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v) } #define arch_atomic64_fetch_and arch_atomic64_fetch_and -static inline void arch_atomic64_or(s64 i, atomic64_t *v) +static __always_inline void arch_atomic64_or(s64 i, atomic64_t *v) { asm volatile(LOCK_PREFIX "orq %1,%0" : "+m" (v->counter) @@ -223,7 +223,7 @@ static inline void arch_atomic64_or(s64 i, atomic64_t *v) : "memory"); } -static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v) { s64 val = arch_atomic64_read(v); @@ -233,7 +233,7 @@ static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v) } #define arch_atomic64_fetch_or arch_atomic64_fetch_or -static inline void arch_atomic64_xor(s64 i, atomic64_t *v) +static __always_inline void arch_atomic64_xor(s64 i, atomic64_t *v) { asm volatile(LOCK_PREFIX "xorq %1,%0" : "+m" (v->counter) @@ -241,7 +241,7 @@ static inline void arch_atomic64_xor(s64 i, atomic64_t *v) : "memory"); } -static inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v) { s64 val = arch_atomic64_read(v); diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h index 407beebadaf4..4d4a47a3a8ab 100644 --- a/arch/x86/include/asm/checksum_64.h +++ b/arch/x86/include/asm/checksum_64.h @@ -9,7 +9,6 @@ */ #include <linux/compiler.h> -#include <linux/uaccess.h> #include <asm/byteorder.h> /** diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 1a85e1fb0922..ce0c8f7d3218 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -32,6 +32,7 @@ enum cpuid_leafs CPUID_8000_0007_EBX, CPUID_7_EDX, CPUID_8000_001F_EAX, + CPUID_8000_0021_EAX, }; #define X86_CAP_FMT_NUM "%d:%d" @@ -94,8 +95,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ 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) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 20)) + BUILD_BUG_ON_ZERO(NCAPINTS != 21)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -118,8 +120,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ 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) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 20)) + BUILD_BUG_ON_ZERO(NCAPINTS != 21)) #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 61012476d66e..73c9672c123b 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 20 /* N 32-bit words worth of info */ +#define NCAPINTS 21 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -97,7 +97,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ +/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ @@ -307,11 +307,18 @@ #define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* "" SGX EDECCSSA user leaf function */ #define X86_FEATURE_CALL_DEPTH (11*32+19) /* "" Call depth tracking for RSB stuffing */ #define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ +#define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ #define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ +#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* "" Intel Architectural PerfMon Extension */ +#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ +#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ +#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ +#define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ @@ -426,6 +433,13 @@ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ +#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ +#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ +#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */ + /* * BUG word(s) */ @@ -466,5 +480,6 @@ #define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ #define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index b049d950612f..66eb5e1ac4fb 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -39,7 +39,20 @@ static __always_inline unsigned long native_get_debugreg(int regno) asm("mov %%db6, %0" :"=r" (val)); break; case 7: - asm("mov %%db7, %0" :"=r" (val)); + /* + * Apply __FORCE_ORDER to DR7 reads to forbid re-ordering them + * with other code. + * + * This is needed because a DR7 access can cause a #VC exception + * when running under SEV-ES. Taking a #VC exception is not a + * safe thing to do just anywhere in the entry code and + * re-ordering might place the access into an unsafe location. + * + * This happened in the NMI handler, where the DR7 read was + * re-ordered to happen before the call to sev_es_ist_enter(), + * causing stack recursion. + */ + asm volatile("mov %%db7, %0" : "=r" (val) : __FORCE_ORDER); break; default: BUG(); @@ -66,7 +79,16 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value) asm("mov %0, %%db6" ::"r" (value)); break; case 7: - asm("mov %0, %%db7" ::"r" (value)); + /* + * Apply __FORCE_ORDER to DR7 writes to forbid re-ordering them + * with other code. + * + * While is didn't happen with a DR7 write (see the DR7 read + * comment above which explains where it happened), add the + * __FORCE_ORDER here too to avoid similar problems in the + * future. + */ + asm volatile("mov %0, %%db7" ::"r" (value), __FORCE_ORDER); break; default: BUG(); @@ -126,9 +148,14 @@ static __always_inline void local_db_restore(unsigned long dr7) } #ifdef CONFIG_CPU_SUP_AMD -extern void set_dr_addr_mask(unsigned long mask, int dr); +extern void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr); +extern unsigned long amd_get_dr_addr_mask(unsigned int dr); #else -static inline void set_dr_addr_mask(unsigned long mask, int dr) { } +static inline void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr) { } +static inline unsigned long amd_get_dr_addr_mask(unsigned int dr) +{ + return 0; +} #endif #endif /* _ASM_X86_DEBUGREG_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index c44b56f7ffba..5dfa4fb76f4b 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -124,6 +124,7 @@ #define DISABLED_MASK17 0 #define DISABLED_MASK18 0 #define DISABLED_MASK19 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) +#define DISABLED_MASK20 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 1c66708e3062..d1dac96ee30b 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -4,7 +4,7 @@ extern const struct dma_map_ops *dma_ops; -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) +static inline const struct dma_map_ops *get_arch_dma_ops(void) { return dma_ops; } diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index a63154e049d7..419280d263d2 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -106,6 +106,8 @@ static inline void efi_fpu_end(void) extern asmlinkage u64 __efi_call(void *fp, ...); +extern bool efi_disable_ibt_for_runtime; + #define efi_call(...) ({ \ __efi_nargs_check(efi_call, 7, __VA_ARGS__); \ __efi_call(__VA_ARGS__); \ @@ -121,7 +123,7 @@ extern asmlinkage u64 __efi_call(void *fp, ...); #undef arch_efi_call_virt #define arch_efi_call_virt(p, f, args...) ({ \ - u64 ret, ibt = ibt_save(); \ + u64 ret, ibt = ibt_save(efi_disable_ibt_for_runtime); \ ret = efi_call((void *)p->f, args); \ ibt_restore(ibt); \ ret; \ @@ -335,6 +337,16 @@ static inline u32 efi64_convert_status(efi_status_t status) #define __efi64_argmap_open_volume(prot, file) \ ((prot), efi64_zero_upper(file)) +/* Memory Attribute Protocol */ +#define __efi64_argmap_get_memory_attributes(protocol, phys, size, flags) \ + ((protocol), __efi64_split(phys), __efi64_split(size), (flags)) + +#define __efi64_argmap_set_memory_attributes(protocol, phys, size, flags) \ + ((protocol), __efi64_split(phys), __efi64_split(size), __efi64_split(flags)) + +#define __efi64_argmap_clear_memory_attributes(protocol, phys, size, flags) \ + ((protocol), __efi64_split(phys), __efi64_split(size), __efi64_split(flags)) + /* * The macros below handle the plumbing for the argument mapping. To add a * mapping for a specific EFI method, simply define a macro diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h index b2486b2cbc6e..c2d6cd78ed0c 100644 --- a/arch/x86/include/asm/fpu/sched.h +++ b/arch/x86/include/asm/fpu/sched.h @@ -39,7 +39,7 @@ extern void fpu_flush_thread(void); static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { if (cpu_feature_enabled(X86_FEATURE_FPU) && - !(current->flags & PF_KTHREAD)) { + !(current->flags & (PF_KTHREAD | PF_IO_WORKER))) { save_fpregs_to_fpstate(old_fpu); /* * The save operation preserved register state, so the diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index eb7cd1139d97..7f6d858ff47a 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -321,7 +321,7 @@ struct xstate_header { struct xregs_state { struct fxregs_state i387; struct xstate_header header; - u8 extended_state_area[0]; + u8 extended_state_area[]; } __attribute__ ((packed, aligned (64))); /* diff --git a/arch/x86/include/asm/fpu/xcr.h b/arch/x86/include/asm/fpu/xcr.h index 9656a5bc6fea..9a710c060445 100644 --- a/arch/x86/include/asm/fpu/xcr.h +++ b/arch/x86/include/asm/fpu/xcr.h @@ -5,7 +5,7 @@ #define XCR_XFEATURE_ENABLED_MASK 0x00000000 #define XCR_XFEATURE_IN_USE_MASK 0x00000001 -static inline u64 xgetbv(u32 index) +static __always_inline u64 xgetbv(u32 index) { u32 eax, edx; @@ -27,7 +27,7 @@ static inline void xsetbv(u32 index, u64 value) * * Callers should check X86_FEATURE_XGETBV1. */ -static inline u64 xfeatures_in_use(void) +static __always_inline u64 xfeatures_in_use(void) { return xgetbv(XCR_XFEATURE_IN_USE_MASK); } diff --git a/arch/x86/include/asm/gsseg.h b/arch/x86/include/asm/gsseg.h new file mode 100644 index 000000000000..ab6a595cea70 --- /dev/null +++ b/arch/x86/include/asm/gsseg.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_X86_GSSEG_H +#define _ASM_X86_GSSEG_H + +#include <linux/types.h> + +#include <asm/asm.h> +#include <asm/cpufeature.h> +#include <asm/alternative.h> +#include <asm/processor.h> +#include <asm/nops.h> + +#ifdef CONFIG_X86_64 + +extern asmlinkage void asm_load_gs_index(u16 selector); + +/* Replace with "lkgs %di" once binutils support LKGS instruction */ +#define LKGS_DI _ASM_BYTES(0xf2,0x0f,0x00,0xf7) + +static inline void native_lkgs(unsigned int selector) +{ + u16 sel = selector; + asm_inline volatile("1: " LKGS_DI + _ASM_EXTABLE_TYPE_REG(1b, 1b, EX_TYPE_ZERO_REG, %k[sel]) + : [sel] "+D" (sel)); +} + +static inline void native_load_gs_index(unsigned int selector) +{ + if (cpu_feature_enabled(X86_FEATURE_LKGS)) { + native_lkgs(selector); + } else { + unsigned long flags; + + local_irq_save(flags); + asm_load_gs_index(selector); + local_irq_restore(flags); + } +} + +#endif /* CONFIG_X86_64 */ + +static inline void __init lkgs_init(void) +{ +#ifdef CONFIG_PARAVIRT_XXL +#ifdef CONFIG_X86_64 + if (cpu_feature_enabled(X86_FEATURE_LKGS)) + pv_ops.cpu.load_gs_index = native_lkgs; +#endif +#endif +} + +#ifndef CONFIG_PARAVIRT_XXL + +static inline void load_gs_index(unsigned int selector) +{ +#ifdef CONFIG_X86_64 + native_load_gs_index(selector); +#else + loadsegment(gs, selector); +#endif +} + +#endif /* CONFIG_PARAVIRT_XXL */ + +#endif /* _ASM_X86_GSSEG_H */ diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 08e822bd7aa6..0b73a809e9e1 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -116,6 +116,9 @@ /* Recommend using the newer ExProcessorMasks interface */ #define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED BIT(11) +/* Indicates that the hypervisor is nested within a Hyper-V partition. */ +#define HV_X64_HYPERV_NESTED BIT(12) + /* Recommend using enlightened VMCS */ #define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) @@ -225,6 +228,17 @@ enum hv_isolation_type { #define HV_REGISTER_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 + +/* * Synthetic Timer MSRs. Four timers per vcpu. */ #define HV_REGISTER_STIMER0_CONFIG 0x400000B0 @@ -255,6 +269,9 @@ enum hv_isolation_type { /* TSC invariant control */ #define HV_X64_MSR_TSC_INVARIANT_CONTROL 0x40000118 +/* 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 @@ -368,7 +385,8 @@ struct hv_nested_enlightenments_control { __u32 reserved:31; } features; struct { - __u32 reserved; + __u32 inter_partition_comm:1; + __u32 reserved:31; } hypercallControls; } __packed; diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h index 9b08082a5d9f..baae6b4fea23 100644 --- a/arch/x86/include/asm/ibt.h +++ b/arch/x86/include/asm/ibt.h @@ -74,7 +74,7 @@ static inline bool is_endbr(u32 val) return val == gen_endbr(); } -extern __noendbr u64 ibt_save(void); +extern __noendbr u64 ibt_save(bool disable); extern __noendbr void ibt_restore(u64 save); #else /* __ASSEMBLY__ */ @@ -100,7 +100,7 @@ extern __noendbr void ibt_restore(u64 save); static inline bool is_endbr(u32 val) { return false; } -static inline u64 ibt_save(void) { return 0; } +static inline u64 ibt_save(bool disable) { return 0; } static inline void ibt_restore(u64 save) { } #else /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 72184b0b2219..b241af4ce9b4 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -582,18 +582,14 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_MC, xenpv_exc_machine_check); /* NMI */ -#if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL) +#if IS_ENABLED(CONFIG_KVM_INTEL) /* - * Special NOIST entry point for VMX which invokes this on the kernel - * stack. asm_exc_nmi() requires an IST to work correctly vs. the NMI - * 'executing' marker. - * - * On 32bit this just uses the regular NMI entry point because 32-bit does - * not have ISTs. + * Special entry point for VMX which invokes this on the kernel stack, even for + * 64-bit, i.e. without using an IST. asm_exc_nmi() requires an IST to work + * correctly vs. the NMI 'executing' marker. Used for 32-bit kernels as well + * to avoid more ifdeffery. */ -DECLARE_IDTENTRY(X86_TRAP_NMI, exc_nmi_noist); -#else -#define asm_exc_nmi_noist asm_exc_nmi +DECLARE_IDTENTRY(X86_TRAP_NMI, exc_nmi_kvm_vmx); #endif DECLARE_IDTENTRY_NMI(X86_TRAP_NMI, exc_nmi); diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 347707d459c6..cbaf174d8efd 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -123,6 +123,8 @@ #define INTEL_FAM6_METEORLAKE 0xAC #define INTEL_FAM6_METEORLAKE_L 0xAA +#define INTEL_FAM6_LUNARLAKE_M 0xBD + /* "Small Core" Processors (Atom/E-Core) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 7793e52d6237..8c5ae649d2df 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -8,9 +8,6 @@ #include <asm/nospec-branch.h> -/* Provide __cpuidle; we can't safely include <linux/cpu.h> */ -#define __cpuidle __section(".cpuidle.text") - /* * Interrupt control: */ @@ -45,13 +42,13 @@ static __always_inline void native_irq_enable(void) asm volatile("sti": : :"memory"); } -static inline __cpuidle void native_safe_halt(void) +static __always_inline void native_safe_halt(void) { mds_idle_clear_cpu_buffers(); asm volatile("sti; hlt": : :"memory"); } -static inline __cpuidle void native_halt(void) +static __always_inline void native_halt(void) { mds_idle_clear_cpu_buffers(); asm volatile("hlt": : :"memory"); @@ -84,7 +81,7 @@ static __always_inline void arch_local_irq_enable(void) * Used in the idle loop; sti takes one instruction cycle * to complete: */ -static inline __cpuidle void arch_safe_halt(void) +static __always_inline void arch_safe_halt(void) { native_safe_halt(); } @@ -93,7 +90,7 @@ static inline __cpuidle void arch_safe_halt(void) * Used when interrupts are already enabled or to * shutdown the processor: */ -static inline __cpuidle void halt(void) +static __always_inline void halt(void) { native_halt(); } diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index abccd51dcfca..8dc345cc6318 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -14,6 +14,7 @@ BUILD_BUG_ON(1) * to make a definition optional, but in this case the default will * be __static_call_return0. */ +KVM_X86_OP(check_processor_compatibility) KVM_X86_OP(hardware_enable) KVM_X86_OP(hardware_disable) KVM_X86_OP(hardware_unsetup) @@ -76,7 +77,6 @@ KVM_X86_OP(set_nmi_mask) KVM_X86_OP(enable_nmi_window) KVM_X86_OP(enable_irq_window) KVM_X86_OP_OPTIONAL(update_cr8_intercept) -KVM_X86_OP(check_apicv_inhibit_reasons) KVM_X86_OP(refresh_apicv_exec_ctrl) KVM_X86_OP_OPTIONAL(hwapic_irr_update) KVM_X86_OP_OPTIONAL(hwapic_isr_update) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6aaae18f1854..808c292ad3f4 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -134,8 +134,6 @@ #define INVALID_PAGE (~(hpa_t)0) #define VALID_PAGE(x) ((x) != INVALID_PAGE) -#define INVALID_GPA (~(gpa_t)0) - /* KVM Hugepage definitions for x86 */ #define KVM_MAX_HUGEPAGE_LEVEL PG_LEVEL_1G #define KVM_NR_PAGE_SIZES (KVM_MAX_HUGEPAGE_LEVEL - PG_LEVEL_4K + 1) @@ -514,6 +512,7 @@ struct kvm_pmc { #define MSR_ARCH_PERFMON_PERFCTR_MAX (MSR_ARCH_PERFMON_PERFCTR0 + KVM_INTEL_PMC_MAX_GENERIC - 1) #define MSR_ARCH_PERFMON_EVENTSEL_MAX (MSR_ARCH_PERFMON_EVENTSEL0 + KVM_INTEL_PMC_MAX_GENERIC - 1) #define KVM_PMC_MAX_FIXED 3 +#define MSR_ARCH_PERFMON_FIXED_CTR_MAX (MSR_ARCH_PERFMON_FIXED_CTR0 + KVM_PMC_MAX_FIXED - 1) #define KVM_AMD_PMC_MAX_GENERIC 6 struct kvm_pmu { unsigned nr_arch_gp_counters; @@ -678,6 +677,11 @@ struct kvm_vcpu_hv { } nested; }; +struct kvm_hypervisor_cpuid { + u32 base; + u32 limit; +}; + /* Xen HVM per vcpu emulation context */ struct kvm_vcpu_xen { u64 hypercall_rip; @@ -698,6 +702,7 @@ struct kvm_vcpu_xen { struct hrtimer timer; int poll_evtchn; struct timer_list poll_timer; + struct kvm_hypervisor_cpuid cpuid; }; struct kvm_queued_exception { @@ -826,7 +831,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; - u32 kvm_cpuid_base; + struct kvm_hypervisor_cpuid kvm_cpuid; u64 reserved_gpa_bits; int maxphyaddr; @@ -1022,19 +1027,30 @@ struct kvm_arch_memory_slot { }; /* - * We use as the mode the number of bits allocated in the LDR for the - * logical processor ID. It happens that these are all powers of two. - * This makes it is very easy to detect cases where the APICs are - * configured for multiple modes; in that case, we cannot use the map and - * hence cannot use kvm_irq_delivery_to_apic_fast either. + * Track the mode of the optimized logical map, as the rules for decoding the + * destination vary per mode. Enabling the optimized logical map requires all + * software-enabled local APIs to be in the same mode, each addressable APIC to + * be mapped to only one MDA, and each MDA to map to at most one APIC. */ -#define KVM_APIC_MODE_XAPIC_CLUSTER 4 -#define KVM_APIC_MODE_XAPIC_FLAT 8 -#define KVM_APIC_MODE_X2APIC 16 +enum kvm_apic_logical_mode { + /* All local APICs are software disabled. */ + KVM_APIC_MODE_SW_DISABLED, + /* All software enabled local APICs in xAPIC cluster addressing mode. */ + KVM_APIC_MODE_XAPIC_CLUSTER, + /* All software enabled local APICs in xAPIC flat addressing mode. */ + KVM_APIC_MODE_XAPIC_FLAT, + /* All software enabled local APICs in x2APIC mode. */ + KVM_APIC_MODE_X2APIC, + /* + * Optimized map disabled, e.g. not all local APICs in the same logical + * mode, same logical ID assigned to multiple APICs, etc. + */ + KVM_APIC_MODE_MAP_DISABLED, +}; struct kvm_apic_map { struct rcu_head rcu; - u8 mode; + enum kvm_apic_logical_mode logical_mode; u32 max_apic_id; union { struct kvm_lapic *xapic_flat_map[8]; @@ -1088,6 +1104,7 @@ struct kvm_hv { u64 hv_reenlightenment_control; u64 hv_tsc_emulation_control; u64 hv_tsc_emulation_status; + u64 hv_invtsc_control; /* How many vCPUs have VP index != vCPU index */ atomic_t num_mismatched_vp_indexes; @@ -1133,6 +1150,18 @@ struct kvm_x86_msr_filter { struct msr_bitmap_range ranges[16]; }; +struct kvm_x86_pmu_event_filter { + __u32 action; + __u32 nevents; + __u32 fixed_counter_bitmap; + __u32 flags; + __u32 nr_includes; + __u32 nr_excludes; + __u64 *includes; + __u64 *excludes; + __u64 events[]; +}; + enum kvm_apicv_inhibit { /********************************************************************/ @@ -1164,6 +1193,12 @@ enum kvm_apicv_inhibit { APICV_INHIBIT_REASON_BLOCKIRQ, /* + * APICv is disabled because not all vCPUs have a 1:1 mapping between + * APIC ID and vCPU, _and_ KVM is not applying its x2APIC hotplug hack. + */ + APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED, + + /* * For simplicity, the APIC acceleration is inhibited * first time either APIC ID or APIC base are changed by the guest * from their reset values. @@ -1201,6 +1236,12 @@ enum kvm_apicv_inhibit { * AVIC is disabled because SEV doesn't support it. */ APICV_INHIBIT_REASON_SEV, + + /* + * AVIC is disabled because not all vCPUs with a valid LDR have a 1:1 + * mapping between logical ID and vCPU. + */ + APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED, }; struct kvm_arch { @@ -1249,10 +1290,11 @@ struct kvm_arch { struct kvm_apic_map __rcu *apic_map; atomic_t apic_map_dirty; - /* Protects apic_access_memslot_enabled and apicv_inhibit_reasons */ - struct rw_semaphore apicv_update_lock; - bool apic_access_memslot_enabled; + bool apic_access_memslot_inhibited; + + /* Protects apicv_inhibit_reasons */ + struct rw_semaphore apicv_update_lock; unsigned long apicv_inhibit_reasons; gpa_t wall_clock; @@ -1302,7 +1344,6 @@ struct kvm_arch { u32 bsp_vcpu_id; u64 disabled_quirks; - int cpu_dirty_logging_count; enum kvm_irqchip_mode irqchip_mode; u8 nr_reserved_ioapic_pins; @@ -1338,25 +1379,16 @@ struct kvm_arch { /* Guest can access the SGX PROVISIONKEY. */ bool sgx_provisioning_allowed; - struct kvm_pmu_event_filter __rcu *pmu_event_filter; + struct kvm_x86_pmu_event_filter __rcu *pmu_event_filter; struct task_struct *nx_huge_page_recovery_thread; #ifdef CONFIG_X86_64 - /* - * Whether the TDP MMU is enabled for this VM. This contains a - * snapshot of the TDP MMU module parameter from when the VM was - * created and remains unchanged for the life of the VM. If this is - * true, TDP MMU handler functions will run for various MMU - * operations. - */ - bool tdp_mmu_enabled; - /* The number of TDP MMU pages across all roots. */ atomic64_t tdp_mmu_pages; /* - * List of kvm_mmu_page structs being used as roots. - * All kvm_mmu_page structs in the list should have + * List of struct kvm_mmu_pages being used as roots. + * All struct kvm_mmu_pages in the list should have * tdp_mmu_page set. * * For reads, this list is protected by: @@ -1520,6 +1552,8 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical) struct kvm_x86_ops { const char *name; + int (*check_processor_compatibility)(void); + int (*hardware_enable)(void); void (*hardware_disable)(void); void (*hardware_unsetup)(void); @@ -1608,6 +1642,8 @@ struct kvm_x86_ops { void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); bool (*check_apicv_inhibit_reasons)(enum kvm_apicv_inhibit reason); + const unsigned long required_apicv_inhibits; + bool allow_apicv_in_x2apic_without_x2apic_virtualization; void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(int isr); @@ -1731,9 +1767,6 @@ struct kvm_x86_nested_ops { }; struct kvm_x86_init_ops { - int (*cpu_has_kvm_support)(void); - int (*disabled_by_bios)(void); - int (*check_processor_compatibility)(void); int (*hardware_setup)(void); unsigned int (*handle_intel_pt_intr)(void); @@ -1760,6 +1793,9 @@ extern struct kvm_x86_ops kvm_x86_ops; #define KVM_X86_OP_OPTIONAL_RET0 KVM_X86_OP #include <asm/kvm-x86-ops.h> +int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops); +void kvm_x86_vendor_exit(void); + #define __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) { @@ -1982,7 +2018,7 @@ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, bool kvm_apicv_activated(struct kvm *kvm); bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu); -void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu); +void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu); void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason, bool set); void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, @@ -2054,14 +2090,11 @@ enum { TASK_SWITCH_GATE = 3, }; -#define HF_GIF_MASK (1 << 0) -#define HF_NMI_MASK (1 << 3) -#define HF_IRET_MASK (1 << 4) -#define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ +#define HF_GUEST_MASK (1 << 0) /* VCPU is in guest-mode */ #ifdef CONFIG_KVM_SMM -#define HF_SMM_MASK (1 << 6) -#define HF_SMM_INSIDE_NMI_MASK (1 << 7) +#define HF_SMM_MASK (1 << 1) +#define HF_SMM_INSIDE_NMI_MASK (1 << 2) # define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE # define KVM_ADDRESS_SPACE_NUM 2 diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h index 6c5765192102..511b35069187 100644 --- a/arch/x86/include/asm/kvmclock.h +++ b/arch/x86/include/asm/kvmclock.h @@ -8,7 +8,7 @@ extern struct clocksource kvm_clock; DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); -static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) +static __always_inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) { return &this_cpu_read(hv_clock_per_cpu)->pvti; } diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 6e986088817d..9646ed6e8c0b 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -88,6 +88,9 @@ #define MCI_MISC_ADDR_MEM 3 /* memory address */ #define MCI_MISC_ADDR_GENERIC 7 /* generic */ +/* MCi_ADDR register defines */ +#define MCI_ADDR_PHYSADDR GENMASK_ULL(boot_cpu_data.x86_phys_bits - 1, 0) + /* CTL2 register defines */ #define MCI_CTL2_CMCI_EN BIT_ULL(30) #define MCI_CTL2_CMCI_THRESHOLD_MASK 0x7fffULL diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index d5a58bde091c..320566a0443d 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -125,13 +125,13 @@ static inline unsigned int x86_cpuid_family(void) #ifdef CONFIG_MICROCODE extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); -void reload_early_microcode(void); +void reload_early_microcode(unsigned int cpu); extern bool initrd_gone; void microcode_bsp_resume(void); #else static inline void __init load_ucode_bsp(void) { } static inline void load_ucode_ap(void) { } -static inline void reload_early_microcode(void) { } +static inline void reload_early_microcode(unsigned int cpu) { } static inline void microcode_bsp_resume(void) { } #endif diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index ac31f9140d07..e6662adf3af4 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -47,12 +47,12 @@ struct microcode_amd { extern void __init load_ucode_amd_bsp(unsigned int family); extern void load_ucode_amd_ap(unsigned int family); extern int __init save_microcode_in_initrd_amd(unsigned int family); -void reload_ucode_amd(void); +void reload_ucode_amd(unsigned int cpu); #else static inline void __init load_ucode_amd_bsp(unsigned int family) {} static inline void load_ucode_amd_ap(unsigned int family) {} static inline int __init save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; } -static inline void reload_ucode_amd(void) {} +static inline void reload_ucode_amd(unsigned int cpu) {} #endif #endif /* _ASM_X86_MICROCODE_AMD_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index b8d40ddeab00..e01aa74a6de7 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -12,6 +12,7 @@ #include <asm/tlbflush.h> #include <asm/paravirt.h> #include <asm/debugreg.h> +#include <asm/gsseg.h> extern atomic64_t last_mm_ctx_id; diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 6d502f3efb0f..4c4c0ec3b62e 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -72,10 +72,16 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) return hv_status; } +/* Hypercall to the L0 hypervisor */ +static inline u64 hv_do_nested_hypercall(u64 control, void *input, void *output) +{ + return hv_do_hypercall(control | HV_HYPERCALL_NESTED, input, output); +} + /* Fast hypercall with 8 bytes of input and no output */ -static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) +static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1) { - u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT; + u64 hv_status; #ifdef CONFIG_X86_64 { @@ -103,10 +109,24 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) return hv_status; } +static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) +{ + u64 control = (u64)code | HV_HYPERCALL_FAST_BIT; + + return _hv_do_fast_hypercall8(control, input1); +} + +static inline u64 hv_do_fast_nested_hypercall8(u16 code, u64 input1) +{ + u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED; + + return _hv_do_fast_hypercall8(control, input1); +} + /* Fast hypercall with 16 bytes of input */ -static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) +static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2) { - u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT; + u64 hv_status; #ifdef CONFIG_X86_64 { @@ -137,6 +157,20 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) return hv_status; } +static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) +{ + u64 control = (u64)code | HV_HYPERCALL_FAST_BIT; + + return _hv_do_fast_hypercall16(control, input1, input2); +} + +static inline u64 hv_do_fast_nested_hypercall16(u16 code, u64 input1, u64 input2) +{ + u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED; + + return _hv_do_fast_hypercall16(control, input1, input2); +} + extern struct hv_vp_assist_page **hv_vp_assist_page; static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu) @@ -190,36 +224,20 @@ extern bool hv_isolation_type_snp(void); static inline bool hv_is_synic_reg(unsigned int reg) { - if ((reg >= HV_REGISTER_SCONTROL) && - (reg <= HV_REGISTER_SINT15)) - return true; - return false; + return (reg >= HV_REGISTER_SCONTROL) && + (reg <= HV_REGISTER_SINT15); } -static inline u64 hv_get_register(unsigned int reg) +static inline bool hv_is_sint_reg(unsigned int reg) { - u64 value; - - if (hv_is_synic_reg(reg) && hv_isolation_type_snp()) - hv_ghcb_msr_read(reg, &value); - else - rdmsrl(reg, value); - return value; + return (reg >= HV_REGISTER_SINT0) && + (reg <= HV_REGISTER_SINT15); } -static inline void hv_set_register(unsigned int reg, u64 value) -{ - if (hv_is_synic_reg(reg) && hv_isolation_type_snp()) { - hv_ghcb_msr_write(reg, value); - - /* Write proxy bit via wrmsl instruction */ - if (reg >= HV_REGISTER_SINT0 && - reg <= HV_REGISTER_SINT15) - wrmsrl(reg, value | 1 << 20); - } else { - wrmsrl(reg, value); - } -} +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); #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} @@ -239,6 +257,8 @@ static inline int hyperv_flush_guest_mapping_range(u64 as, } 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 int hv_set_mem_host_visibility(unsigned long addr, int numpages, bool visible) { diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 37ff47552bcb..ad35355ee43e 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -25,6 +25,7 @@ #define _EFER_SVME 12 /* Enable virtualization */ #define _EFER_LMSLE 13 /* Long Mode Segment Limit Enable */ #define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */ +#define _EFER_AUTOIBRS 21 /* Enable Automatic IBRS */ #define EFER_SCE (1<<_EFER_SCE) #define EFER_LME (1<<_EFER_LME) @@ -33,6 +34,7 @@ #define EFER_SVME (1<<_EFER_SVME) #define EFER_LMSLE (1<<_EFER_LMSLE) #define EFER_FFXSR (1<<_EFER_FFXSR) +#define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) /* Intel MSRs. Some also available on other CPUs */ @@ -49,6 +51,10 @@ #define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ #define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) +/* A mask for bits which the kernel toggles when controlling mitigations */ +#define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \ + | SPEC_CTRL_RRSBA_DIS_S) + #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -189,6 +195,9 @@ #define MSR_TURBO_RATIO_LIMIT1 0x000001ae #define MSR_TURBO_RATIO_LIMIT2 0x000001af +#define MSR_SNOOP_RSP_0 0x00001328 +#define MSR_SNOOP_RSP_1 0x00001329 + #define MSR_LBR_SELECT 0x000001c8 #define MSR_LBR_TOS 0x000001c9 @@ -566,6 +575,26 @@ #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) #define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) +/* SNP feature bits enabled by the hypervisor */ +#define MSR_AMD64_SNP_VTOM BIT_ULL(3) +#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4) +#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5) +#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6) +#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7) +#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8) +#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9) +#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10) +#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11) +#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12) +#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14) +#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16) +#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17) + +/* SNP feature bits reserved for future use. */ +#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) +#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) +#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18) + #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f /* AMD Collaborative Processor Performance Control MSRs */ @@ -1061,6 +1090,8 @@ /* - AMD: */ #define MSR_IA32_MBA_BW_BASE 0xc0000200 +#define MSR_IA32_SMBA_BW_BASE 0xc0000280 +#define MSR_IA32_EVT_CFG_BASE 0xc0000400 /* MSR_IA32_VMX_MISC bits */ #define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14) diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 3a8fdf881313..778df05f8539 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -26,7 +26,7 @@ #define TPAUSE_C01_STATE 1 #define TPAUSE_C02_STATE 0 -static inline void __monitor(const void *eax, unsigned long ecx, +static __always_inline void __monitor(const void *eax, unsigned long ecx, unsigned long edx) { /* "monitor %eax, %ecx, %edx;" */ @@ -34,7 +34,7 @@ static inline void __monitor(const void *eax, unsigned long ecx, :: "a" (eax), "c" (ecx), "d"(edx)); } -static inline void __monitorx(const void *eax, unsigned long ecx, +static __always_inline void __monitorx(const void *eax, unsigned long ecx, unsigned long edx) { /* "monitorx %eax, %ecx, %edx;" */ @@ -42,7 +42,7 @@ static inline void __monitorx(const void *eax, unsigned long ecx, :: "a" (eax), "c" (ecx), "d"(edx)); } -static inline void __mwait(unsigned long eax, unsigned long ecx) +static __always_inline void __mwait(unsigned long eax, unsigned long ecx) { mds_idle_clear_cpu_buffers(); @@ -77,8 +77,8 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) * EAX (logical) address to monitor * ECX #GP if not zero */ -static inline void __mwaitx(unsigned long eax, unsigned long ebx, - unsigned long ecx) +static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx, + unsigned long ecx) { /* No MDS buffer clear as this is AMD/HYGON only */ @@ -87,7 +87,7 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx, :: "a" (eax), "b" (ebx), "c" (ecx)); } -static inline void __sti_mwait(unsigned long eax, unsigned long ecx) +static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx) { mds_idle_clear_cpu_buffers(); /* "mwait %eax, %ecx;" */ @@ -105,7 +105,7 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx) * New with Core Duo processors, MWAIT can take some hints based on CPU * capability. */ -static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx) +static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx) { if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) { if (static_cpu_has_bug(X86_BUG_CLFLUSH_MONITOR)) { diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 771b0a2b7a34..e04313e89f4f 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -564,7 +564,7 @@ static __always_inline void mds_user_clear_cpu_buffers(void) * * Clear CPU buffers if the corresponding static key is enabled */ -static inline void mds_idle_clear_cpu_buffers(void) +static __always_inline void mds_idle_clear_cpu_buffers(void) { if (static_branch_likely(&mds_idle_clear)) mds_clear_cpu_buffers(); diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h index 9cc82f305f4b..d18e5c332cb9 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -34,9 +34,8 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr, copy_page(to, from); } -#define alloc_zeroed_user_highpage_movable(vma, vaddr) \ - alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr) -#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE +#define vma_alloc_zeroed_movable_folio(vma, vaddr) \ + vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr, false) #ifndef __pa #define __pa(x) __phys_addr((unsigned long)(x)) diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h index df42f8aa99e4..580d71aca65a 100644 --- a/arch/x86/include/asm/page_32.h +++ b/arch/x86/include/asm/page_32.h @@ -15,10 +15,6 @@ extern unsigned long __phys_addr(unsigned long); #define __phys_addr_symbol(x) __phys_addr(x) #define __phys_reloc_hide(x) RELOC_HIDE((x), 0) -#ifdef CONFIG_FLATMEM -#define pfn_valid(pfn) ((pfn) < max_mapnr) -#endif /* CONFIG_FLATMEM */ - #include <linux/string.h> static inline void clear_page(void *page) diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index 198e03e59ca1..cc6b8e087192 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -39,10 +39,6 @@ extern unsigned long __phys_addr_symbol(unsigned long); #define __phys_reloc_hide(x) (x) -#ifdef CONFIG_FLATMEM -#define pfn_valid(pfn) ((pfn) < max_pfn) -#endif - void clear_page_orig(void *page); void clear_page_rep(void *page); void clear_page_erms(void *page); diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 73e9522db7c1..cf40e813b3d7 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -26,7 +26,7 @@ DECLARE_STATIC_CALL(pv_sched_clock, dummy_sched_clock); void paravirt_set_sched_clock(u64 (*func)(void)); -static inline u64 paravirt_sched_clock(void) +static __always_inline u64 paravirt_sched_clock(void) { return static_call(pv_sched_clock)(); } @@ -168,7 +168,7 @@ static inline void __write_cr4(unsigned long x) PVOP_VCALL1(cpu.write_cr4, x); } -static inline void arch_safe_halt(void) +static __always_inline void arch_safe_halt(void) { PVOP_VCALL0(irq.safe_halt); } @@ -178,7 +178,9 @@ static inline void halt(void) PVOP_VCALL0(irq.halt); } -static inline void wbinvd(void) +extern noinstr void pv_native_wbinvd(void); + +static __always_inline void wbinvd(void) { PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV)); } diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 5d0f6891ae61..8fc15ed5e60b 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -160,6 +160,14 @@ union cpuid10_edx { }; /* + * Intel "Architectural Performance Monitoring extension" CPUID + * detection/enumeration details: + */ +#define ARCH_PERFMON_EXT_LEAF 0x00000023 +#define ARCH_PERFMON_NUM_COUNTER_LEAF_BIT 0x1 +#define ARCH_PERFMON_NUM_COUNTER_LEAF 0x1 + +/* * Intel Architectural LBR CPUID detection/enumeration details: */ union cpuid28_eax { @@ -578,7 +586,7 @@ extern void perf_amd_brs_lopwr_cb(bool lopwr_in); DECLARE_STATIC_CALL(perf_lopwr_cb, perf_amd_brs_lopwr_cb); -static inline void perf_lopwr_cb(bool lopwr_in) +static __always_inline void perf_lopwr_cb(bool lopwr_in) { static_call_mod(perf_lopwr_cb)(lopwr_in); } diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 60d0f9015317..e9482a11ac52 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -80,21 +80,37 @@ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshi return ((value >> rightshift) & mask) << leftshift; } -/* Encode and de-code a swap entry */ +/* + * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that + * are !pte_none() && !pte_present(). + * + * Format of swap PTEs: + * + * 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 + * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 + * <----------------- offset ------------------> 0 E <- type --> 0 + * + * E is the exclusive marker that is not stored in swap entries. + */ #define SWP_TYPE_BITS 5 +#define _SWP_TYPE_MASK ((1U << SWP_TYPE_BITS) - 1) +#define _SWP_TYPE_SHIFT (_PAGE_BIT_PRESENT + 1) #define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1) -#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) +#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5) -#define __swp_type(x) (((x).val >> (_PAGE_BIT_PRESENT + 1)) \ - & ((1U << SWP_TYPE_BITS) - 1)) +#define __swp_type(x) (((x).val >> _SWP_TYPE_SHIFT) \ + & _SWP_TYPE_MASK) #define __swp_offset(x) ((x).val >> SWP_OFFSET_SHIFT) #define __swp_entry(type, offset) ((swp_entry_t) { \ - ((type) << (_PAGE_BIT_PRESENT + 1)) \ + (((type) & _SWP_TYPE_MASK) << _SWP_TYPE_SHIFT) \ | ((offset) << SWP_OFFSET_SHIFT) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_low }) #define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val }) +/* We borrow bit 7 to store the exclusive marker in swap PTEs. */ +#define _PAGE_SWP_EXCLUSIVE _PAGE_PSE + /* No inverted PFNs on 2 level page tables */ static inline u64 protnone_mask(u64 val) diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index 967b135fa2c0..9e7c0b719c3c 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -145,8 +145,24 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, } #endif -/* Encode and de-code a swap entry */ +/* + * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that + * are !pte_none() && !pte_present(). + * + * Format of swap PTEs: + * + * 6 6 6 6 5 5 5 5 5 5 5 5 5 5 4 4 4 4 4 4 4 4 4 4 3 3 3 3 3 3 3 3 + * 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 + * < type -> <---------------------- offset ---------------------- + * + * 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 + * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 + * --------------------------------------------> 0 E 0 0 0 0 0 0 0 + * + * E is the exclusive marker that is not stored in swap entries. + */ #define SWP_TYPE_BITS 5 +#define _SWP_TYPE_MASK ((1U << SWP_TYPE_BITS) - 1) #define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) @@ -154,9 +170,10 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, #define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT + SWP_TYPE_BITS) #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) -#define __swp_type(x) (((x).val) & ((1UL << SWP_TYPE_BITS) - 1)) +#define __swp_type(x) (((x).val) & _SWP_TYPE_MASK) #define __swp_offset(x) ((x).val >> SWP_TYPE_BITS) -#define __swp_entry(type, offset) ((swp_entry_t){(type) | (offset) << SWP_TYPE_BITS}) +#define __swp_entry(type, offset) ((swp_entry_t){((type) & _SWP_TYPE_MASK) \ + | (offset) << SWP_TYPE_BITS}) /* * Normally, __swp_entry() converts from arch-independent swp_entry_t to @@ -184,6 +201,9 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, #define __pte_to_swp_entry(pte) (__swp_entry(__pteval_swp_type(pte), \ __pteval_swp_offset(pte))) +/* We borrow bit 7 to store the exclusive marker in swap PTEs. */ +#define _PAGE_SWP_EXCLUSIVE _PAGE_PSE + #include <asm/pgtable-invert.h> #endif /* _ASM_X86_PGTABLE_3LEVEL_H */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 0564edd24ffb..7425f32e5293 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -289,6 +289,11 @@ static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear) return native_make_pte(v & ~clear); } +static inline pte_t pte_wrprotect(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_RW); +} + #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { @@ -313,7 +318,7 @@ static inline int pte_uffd_wp(pte_t pte) static inline pte_t pte_mkuffd_wp(pte_t pte) { - return pte_set_flags(pte, _PAGE_UFFD_WP); + return pte_wrprotect(pte_set_flags(pte, _PAGE_UFFD_WP)); } static inline pte_t pte_clear_uffd_wp(pte_t pte) @@ -332,11 +337,6 @@ static inline pte_t pte_mkold(pte_t pte) return pte_clear_flags(pte, _PAGE_ACCESSED); } -static inline pte_t pte_wrprotect(pte_t pte) -{ - return pte_clear_flags(pte, _PAGE_RW); -} - static inline pte_t pte_mkexec(pte_t pte) { return pte_clear_flags(pte, _PAGE_NX); @@ -401,6 +401,11 @@ static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) return native_make_pmd(v & ~clear); } +static inline pmd_t pmd_wrprotect(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_RW); +} + #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pmd_uffd_wp(pmd_t pmd) { @@ -409,7 +414,7 @@ static inline int pmd_uffd_wp(pmd_t pmd) static inline pmd_t pmd_mkuffd_wp(pmd_t pmd) { - return pmd_set_flags(pmd, _PAGE_UFFD_WP); + return pmd_wrprotect(pmd_set_flags(pmd, _PAGE_UFFD_WP)); } static inline pmd_t pmd_clear_uffd_wp(pmd_t pmd) @@ -428,11 +433,6 @@ static inline pmd_t pmd_mkclean(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_DIRTY); } -static inline pmd_t pmd_wrprotect(pmd_t pmd) -{ - return pmd_clear_flags(pmd, _PAGE_RW); -} - static inline pmd_t pmd_mkdirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); @@ -1299,8 +1299,6 @@ static inline void update_mmu_cache_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { } -#ifdef _PAGE_SWP_EXCLUSIVE -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline pte_t pte_swp_mkexclusive(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE); @@ -1315,7 +1313,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_EXCLUSIVE); } -#endif /* _PAGE_SWP_EXCLUSIVE */ #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 4e35c66edeb7..8d73004e4cac 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -542,7 +542,6 @@ enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT, IDLE_POLL}; extern void enable_sep_cpu(void); -extern int sysenter_setup(void); /* Defined in head.S */ @@ -697,7 +696,8 @@ bool xen_set_default_idle(void); #endif void __noreturn stop_this_cpu(void *dummy); -void microcode_check(void); +void microcode_check(struct cpuinfo_x86 *prev_info); +void store_cpu_caps(struct cpuinfo_x86 *info); enum l1tf_mitigations { L1TF_MITIGATION_OFF, diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 19b695ff2c68..0c92db84469d 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -7,6 +7,7 @@ /* some helper functions for xen and kvm pv clock sources */ u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src); +u64 pvclock_clocksource_read_nowd(struct pvclock_vcpu_time_info *src); u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src); void pvclock_set_flags(u8 flags); unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src); @@ -39,7 +40,7 @@ bool pvclock_read_retry(const struct pvclock_vcpu_time_info *src, * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction, * yielding a 64-bit result. */ -static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) +static __always_inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) { u64 product; #ifdef __i386__ diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index 04c17be9b5fd..bc5b4d788c08 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -25,6 +25,8 @@ void __noreturn machine_real_restart(unsigned int type); #define MRR_BIOS 0 #define MRR_APM 1 +void cpu_emergency_disable_virtualization(void); + typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); void nmi_panic_self_stop(struct pt_regs *regs); void nmi_shootdown_cpus(nmi_shootdown_cb callback); diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index aff774775c67..7ba1726b71c7 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -98,6 +98,7 @@ #define REQUIRED_MASK17 0 #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) +#define REQUIRED_MASK20 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index c390a672d560..794f69625780 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -96,7 +96,7 @@ * * 26 - ESPFIX small SS * 27 - per-cpu [ offset to per-cpu data area ] - * 28 - unused + * 28 - VDSO getcpu * 29 - unused * 30 - unused * 31 - TSS for double fault handler @@ -119,6 +119,7 @@ #define GDT_ENTRY_ESPFIX_SS 26 #define GDT_ENTRY_PERCPU 27 +#define GDT_ENTRY_CPUNODE 28 #define GDT_ENTRY_DOUBLEFAULT_TSS 31 @@ -159,6 +160,8 @@ # define __KERNEL_PERCPU 0 #endif +#define __CPUNODE_SEG (GDT_ENTRY_CPUNODE*8 + 3) + #else /* 64-bit: */ #include <asm/cache.h> @@ -226,8 +229,6 @@ #define GDT_ENTRY_TLS_ENTRIES 3 #define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES* 8) -#ifdef CONFIG_X86_64 - /* Bit size and mask of CPU number stored in the per CPU data (and TSC_AUX) */ #define VDSO_CPUNODE_BITS 12 #define VDSO_CPUNODE_MASK 0xfff @@ -265,7 +266,6 @@ static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node) } #endif /* !__ASSEMBLY__ */ -#endif /* CONFIG_X86_64 */ #ifdef __KERNEL__ diff --git a/arch/x86/include/asm/shared/io.h b/arch/x86/include/asm/shared/io.h index c0ef921c0586..8009d781c2f9 100644 --- a/arch/x86/include/asm/shared/io.h +++ b/arch/x86/include/asm/shared/io.h @@ -5,13 +5,13 @@ #include <linux/types.h> #define BUILDIO(bwl, bw, type) \ -static inline void __out##bwl(type value, u16 port) \ +static __always_inline void __out##bwl(type value, u16 port) \ { \ asm volatile("out" #bwl " %" #bw "0, %w1" \ : : "a"(value), "Nd"(port)); \ } \ \ -static inline type __in##bwl(u16 port) \ +static __always_inline type __in##bwl(u16 port) \ { \ type value; \ asm volatile("in" #bwl " %w1, %" #bw "0" \ diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index e53f26228fbb..4a03993e0785 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -8,7 +8,6 @@ #define TDX_HYPERCALL_STANDARD 0 #define TDX_HCALL_HAS_OUTPUT BIT(0) -#define TDX_HCALL_ISSUE_STI BIT(1) #define TDX_CPUID_LEAF_ID 0x21 #define TDX_IDENT "IntelTDX " @@ -22,12 +21,18 @@ * This is a software only structure and not part of the TDX module/VMM ABI. */ struct tdx_hypercall_args { + u64 r8; + u64 r9; u64 r10; u64 r11; u64 r12; u64 r13; u64 r14; u64 r15; + u64 rdi; + u64 rsi; + u64 rbx; + u64 rdx; }; /* Used to request services from the VMM */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 35f709f619fb..de48d1389936 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -115,22 +115,11 @@ static inline void wrpkru(u32 pkru) } #endif -static inline void native_wbinvd(void) +static __always_inline void native_wbinvd(void) { asm volatile("wbinvd": : :"memory"); } -extern asmlinkage void asm_load_gs_index(unsigned int selector); - -static inline void native_load_gs_index(unsigned int selector) -{ - unsigned long flags; - - local_irq_save(flags); - asm_load_gs_index(selector); - local_irq_restore(flags); -} - static inline unsigned long __read_cr4(void) { return native_read_cr4(); @@ -179,24 +168,14 @@ static inline void __write_cr4(unsigned long x) native_write_cr4(x); } -static inline void wbinvd(void) +static __always_inline void wbinvd(void) { native_wbinvd(); } - -static inline void load_gs_index(unsigned int selector) -{ -#ifdef CONFIG_X86_64 - native_load_gs_index(selector); -#else - loadsegment(gs, selector); -#endif -} - #endif /* CONFIG_PARAVIRT_XXL */ -static inline void clflush(volatile void *__p) +static __always_inline void clflush(volatile void *__p) { asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p)); } @@ -295,7 +274,7 @@ static inline int enqcmds(void __iomem *dst, const void *src) return 0; } -static inline void tile_release(void) +static __always_inline void tile_release(void) { /* * Instruction opcode for TILERELEASE; supported in binutils diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index f4b87f08f5c5..29832c338cdc 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -184,6 +184,37 @@ void int3_emulate_ret(struct pt_regs *regs) unsigned long ip = int3_emulate_pop(regs); int3_emulate_jmp(regs, ip); } + +static __always_inline +void int3_emulate_jcc(struct pt_regs *regs, u8 cc, unsigned long ip, unsigned long disp) +{ + static const unsigned long jcc_mask[6] = { + [0] = X86_EFLAGS_OF, + [1] = X86_EFLAGS_CF, + [2] = X86_EFLAGS_ZF, + [3] = X86_EFLAGS_CF | X86_EFLAGS_ZF, + [4] = X86_EFLAGS_SF, + [5] = X86_EFLAGS_PF, + }; + + bool invert = cc & 1; + bool match; + + if (cc < 0xc) { + match = regs->flags & jcc_mask[cc >> 1]; + } else { + match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^ + ((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT); + if (cc >= 0xe) + match = match || (regs->flags & X86_EFLAGS_ZF); + } + + if ((match && !invert) || (!match && invert)) + ip += disp; + + int3_emulate_jmp(regs, ip); +} + #endif /* !CONFIG_UML_X86 */ #endif /* _ASM_X86_TEXT_PATCHING_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index f0cb881c1d69..f1cccba52eb9 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -163,7 +163,12 @@ struct thread_info { * GOOD_FRAME if within a frame * BAD_STACK if placed across a frame boundary (or outside stack) * NOT_STACK unable to determine (no frame pointers, etc) + * + * This function reads pointers from the stack and dereferences them. The + * pointers may not have their KMSAN shadow set up properly, which may result + * in false positive reports. Disable instrumentation to avoid those. */ +__no_kmsan_checks static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, const void *obj, unsigned long len) diff --git a/arch/x86/include/asm/time.h b/arch/x86/include/asm/time.h index 8ac563abb567..a53961c64a56 100644 --- a/arch/x86/include/asm/time.h +++ b/arch/x86/include/asm/time.h @@ -8,6 +8,7 @@ extern void hpet_time_init(void); extern void time_init(void); extern bool pit_timer_init(void); +extern bool tsc_clocksource_watchdog_disabled(void); extern struct clock_event_device *global_clock_event; diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index 2963a2f5dbc4..d7f6592b74a9 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -45,7 +45,7 @@ extern const struct vdso_image vdso_image_x32; extern const struct vdso_image vdso_image_32; #endif -extern void __init init_vdso_image(const struct vdso_image *image); +extern int __init init_vdso_image(const struct vdso_image *image); extern int map_vdso_once(const struct vdso_image *image, unsigned long addr); diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h index 1936f21ed8cd..4cf6794f9d68 100644 --- a/arch/x86/include/asm/vdso/gettimeofday.h +++ b/arch/x86/include/asm/vdso/gettimeofday.h @@ -318,6 +318,8 @@ u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult) } #define vdso_calc_delta vdso_calc_delta +int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts); + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/x86/include/asm/vdso/processor.h b/arch/x86/include/asm/vdso/processor.h index 57b1a7034c64..2cbce97d29ea 100644 --- a/arch/x86/include/asm/vdso/processor.h +++ b/arch/x86/include/asm/vdso/processor.h @@ -18,6 +18,10 @@ static __always_inline void cpu_relax(void) rep_nop(); } +struct getcpu_cache; + +notrace long __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused); + #endif /* __ASSEMBLY__ */ #endif /* __ASM_VDSO_PROCESSOR_H */ diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index 8757078d4442..3b12e6b99412 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -126,7 +126,21 @@ static inline void cpu_svm_disable(void) wrmsrl(MSR_VM_HSAVE_PA, 0); rdmsrl(MSR_EFER, efer); - wrmsrl(MSR_EFER, efer & ~EFER_SVME); + if (efer & EFER_SVME) { + /* + * Force GIF=1 prior to disabling SVM to ensure INIT and NMI + * aren't blocked, e.g. if a fatal error occurred between CLGI + * and STGI. Note, STGI may #UD if SVM is disabled from NMI + * context between reading EFER and executing STGI. In that + * case, GIF must already be set, otherwise the NMI would have + * been blocked, so just eat the fault. + */ + asm_volatile_goto("1: stgi\n\t" + _ASM_EXTABLE(1b, %l[fault]) + ::: "memory" : fault); +fault: + wrmsrl(MSR_EFER, efer & ~EFER_SVME); + } } /** Makes sure SVM is disabled, if it is supported on the CPU diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index e5e0fe10c692..a2dd24947eb8 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -382,7 +382,7 @@ MULTI_stack_switch(struct multicall_entry *mcl, } #endif -static inline int +static __always_inline int HYPERVISOR_sched_op(int cmd, void *arg) { return _hypercall2(int, sched_op, cmd, arg); diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 16f548a661cf..5fc35f889cd1 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -38,9 +38,11 @@ extern struct start_info *xen_start_info; #include <asm/processor.h> +#define XEN_SIGNATURE "XenVMMXenVMM" + static inline uint32_t xen_cpuid_base(void) { - return hypervisor_cpuid_base("XenVMMXenVMM", 2); + return hypervisor_cpuid_base(XEN_SIGNATURE, 2); } struct pci_dev; diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index e48deab8901d..7f467fe05d42 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -9,6 +9,7 @@ #include <linux/types.h> #include <linux/ioctl.h> +#include <linux/stddef.h> #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 @@ -507,8 +508,8 @@ struct kvm_nested_state { * KVM_{GET,PUT}_NESTED_STATE ioctl values. */ union { - struct kvm_vmx_nested_state_data vmx[0]; - struct kvm_svm_nested_state_data svm[0]; + __DECLARE_FLEX_ARRAY(struct kvm_vmx_nested_state_data, vmx); + __DECLARE_FLEX_ARRAY(struct kvm_svm_nested_state_data, svm); } data; }; @@ -525,6 +526,35 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 +#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0) +#define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) + +/* + * Masked event layout. + * Bits Description + * ---- ----------- + * 7:0 event select (low bits) + * 15:8 umask match + * 31:16 unused + * 35:32 event select (high bits) + * 36:54 unused + * 55 exclude bit + * 63:56 umask mask + */ + +#define KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, exclude) \ + (((event_select) & 0xFFULL) | (((event_select) & 0XF00ULL) << 24) | \ + (((mask) & 0xFFULL) << 56) | \ + (((match) & 0xFFULL) << 8) | \ + ((__u64)(!!(exclude)) << 55)) + +#define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \ + (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8)) +#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56) + /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index f69c168391aa..80e1df482337 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -116,6 +116,12 @@ #define SVM_VMGEXIT_AP_CREATE 1 #define SVM_VMGEXIT_AP_DESTROY 2 #define SVM_VMGEXIT_HV_FEATURES 0x8000fffd +#define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe +#define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \ + /* SW_EXITINFO1[3:0] */ \ + (((((u64)reason_set) & 0xf)) | \ + /* SW_EXITINFO1[11:4] */ \ + ((((u64)reason_code) & 0xff) << 4)) #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff /* Exit code reserved for hypervisor/software use */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 96d51bbc2bd4..dd61752f4c96 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -45,7 +45,6 @@ obj-y += head$(BITS).o obj-y += ebda.o obj-y += platform-quirks.o obj-y += process_$(BITS).o signal.o signal_$(BITS).o -obj-$(CONFIG_COMPAT) += signal_compat.o obj-y += traps.o idt.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o dumpstack.o nmi.o obj-$(CONFIG_MODIFY_LDT_SYSCALL) += ldt.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 907cc98b1938..1c38174b5f01 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -188,6 +188,17 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled) return cpu; } +static bool __init acpi_is_processor_usable(u32 lapic_flags) +{ + if (lapic_flags & ACPI_MADT_ENABLED) + return true; + + if (acpi_support_online_capable && (lapic_flags & ACPI_MADT_ONLINE_CAPABLE)) + return true; + + return false; +} + static int __init acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end) { @@ -212,6 +223,10 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end) if (apic_id == 0xffffffff) return 0; + /* don't register processors that cannot be onlined */ + if (!acpi_is_processor_usable(processor->lapic_flags)) + return 0; + /* * We need to register disabled CPU as well to permit * counting disabled CPUs. This allows us to size @@ -250,9 +265,7 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) return 0; /* don't register processors that can not be onlined */ - if (acpi_support_online_capable && - !(processor->lapic_flags & ACPI_MADT_ENABLED) && - !(processor->lapic_flags & ACPI_MADT_ONLINE_CAPABLE)) + if (!acpi_is_processor_usable(processor->lapic_flags)) return 0; /* @@ -1840,23 +1853,23 @@ early_param("acpi_sci", setup_acpi_sci); int __acpi_acquire_global_lock(unsigned int *lock) { - unsigned int old, new, val; + unsigned int old, new; + + old = READ_ONCE(*lock); do { - old = *lock; new = (((old & ~0x3) + 2) + ((old >> 1) & 0x1)); - val = cmpxchg(lock, old, new); - } while (unlikely (val != old)); + } while (!try_cmpxchg(lock, &old, new)); return ((new & 0x3) < 3) ? -1 : 0; } int __acpi_release_global_lock(unsigned int *lock) { - unsigned int old, new, val; + unsigned int old, new; + + old = READ_ONCE(*lock); do { - old = *lock; new = old & ~0x3; - val = cmpxchg(lock, old, new); - } while (unlikely (val != old)); + } while (!try_cmpxchg(lock, &old, new)); return old & 0x1; } diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 7d8c3cbde368..f615e0cb6d93 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -282,27 +282,25 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, */ for (a = start; a < end; a++) { int insn_buff_sz = 0; - /* Mask away "NOT" flag bit for feature to test. */ - u16 feature = a->cpuid & ~ALTINSTR_FLAG_INV; instr = (u8 *)&a->instr_offset + a->instr_offset; replacement = (u8 *)&a->repl_offset + a->repl_offset; BUG_ON(a->instrlen > sizeof(insn_buff)); - BUG_ON(feature >= (NCAPINTS + NBUGINTS) * 32); + BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32); /* * Patch if either: * - feature is present - * - feature not present but ALTINSTR_FLAG_INV is set to mean, + * - feature not present but ALT_FLAG_NOT is set to mean, * patch if feature is *NOT* present. */ - if (!boot_cpu_has(feature) == !(a->cpuid & ALTINSTR_FLAG_INV)) + if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) goto next; DPRINTK("feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d)", - (a->cpuid & ALTINSTR_FLAG_INV) ? "!" : "", - feature >> 5, - feature & 0x1f, + (a->flags & ALT_FLAG_NOT) ? "!" : "", + a->cpuid >> 5, + a->cpuid & 0x1f, instr, instr, a->instrlen, replacement, a->replacementlen); @@ -340,6 +338,12 @@ next: } } +static inline bool is_jcc32(struct insn *insn) +{ + /* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */ + return insn->opcode.bytes[0] == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80; +} + #if defined(CONFIG_RETPOLINE) && defined(CONFIG_OBJTOOL) /* @@ -378,12 +382,6 @@ static int emit_indirect(int op, int reg, u8 *bytes) return i; } -static inline bool is_jcc32(struct insn *insn) -{ - /* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */ - return insn->opcode.bytes[0] == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80; -} - static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes) { u8 op = insn->opcode.bytes[0]; @@ -1772,6 +1770,11 @@ void text_poke_sync(void) on_each_cpu(do_sync_core, NULL, 1); } +/* + * NOTE: crazy scheme to allow patching Jcc.d32 but not increase the size of + * this thing. When len == 6 everything is prefixed with 0x0f and we map + * opcode to Jcc.d8, using len to distinguish. + */ struct text_poke_loc { /* addr := _stext + rel_addr */ s32 rel_addr; @@ -1893,6 +1896,10 @@ noinstr int poke_int3_handler(struct pt_regs *regs) int3_emulate_jmp(regs, (long)ip + tp->disp); break; + case 0x70 ... 0x7f: /* Jcc */ + int3_emulate_jcc(regs, tp->opcode & 0xf, (long)ip, tp->disp); + break; + default: BUG(); } @@ -1966,16 +1973,26 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries * Second step: update all but the first byte of the patched range. */ for (do_sync = 0, i = 0; i < nr_entries; i++) { - u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, }; + u8 old[POKE_MAX_OPCODE_SIZE+1] = { tp[i].old, }; + u8 _new[POKE_MAX_OPCODE_SIZE+1]; + const u8 *new = tp[i].text; int len = tp[i].len; if (len - INT3_INSN_SIZE > 0) { memcpy(old + INT3_INSN_SIZE, text_poke_addr(&tp[i]) + INT3_INSN_SIZE, len - INT3_INSN_SIZE); + + if (len == 6) { + _new[0] = 0x0f; + memcpy(_new + 1, new, 5); + new = _new; + } + text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE, - (const char *)tp[i].text + INT3_INSN_SIZE, + new + INT3_INSN_SIZE, len - INT3_INSN_SIZE); + do_sync++; } @@ -2003,8 +2020,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries * The old instruction is recorded so that the event can be * processed forwards or backwards. */ - perf_event_text_poke(text_poke_addr(&tp[i]), old, len, - tp[i].text, len); + perf_event_text_poke(text_poke_addr(&tp[i]), old, len, new, len); } if (do_sync) { @@ -2021,10 +2037,15 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries * replacing opcode. */ for (do_sync = 0, i = 0; i < nr_entries; i++) { - if (tp[i].text[0] == INT3_INSN_OPCODE) + u8 byte = tp[i].text[0]; + + if (tp[i].len == 6) + byte = 0x0f; + + if (byte == INT3_INSN_OPCODE) continue; - text_poke(text_poke_addr(&tp[i]), tp[i].text, INT3_INSN_SIZE); + text_poke(text_poke_addr(&tp[i]), &byte, INT3_INSN_SIZE); do_sync++; } @@ -2042,9 +2063,11 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, const void *opcode, size_t len, const void *emulate) { struct insn insn; - int ret, i; + int ret, i = 0; - memcpy((void *)tp->text, opcode, len); + if (len == 6) + i = 1; + memcpy((void *)tp->text, opcode+i, len-i); if (!emulate) emulate = opcode; @@ -2055,6 +2078,13 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, tp->len = len; tp->opcode = insn.opcode.bytes[0]; + if (is_jcc32(&insn)) { + /* + * Map Jcc.d32 onto Jcc.d8 and use len to distinguish. + */ + tp->opcode = insn.opcode.bytes[1] - 0x10; + } + switch (tp->opcode) { case RET_INSN_OPCODE: case JMP32_INSN_OPCODE: @@ -2071,7 +2101,6 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, BUG_ON(len != insn.length); } - switch (tp->opcode) { case INT3_INSN_OPCODE: case RET_INSN_OPCODE: @@ -2080,6 +2109,7 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, case CALL_INSN_OPCODE: case JMP32_INSN_OPCODE: case JMP8_INSN_OPCODE: + case 0x70 ... 0x7f: /* Jcc */ tp->disp = insn.immediate.value; break; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index a868b76cd3d4..1f83b052bb74 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2364,9 +2364,8 @@ static int mp_irqdomain_create(int ioapic) return -ENODEV; } - ip->irqdomain = irq_domain_create_linear(fn, hwirqs, cfg->ops, - (void *)(long)ioapic); - + ip->irqdomain = irq_domain_create_hierarchy(parent, 0, hwirqs, fn, cfg->ops, + (void *)(long)ioapic); if (!ip->irqdomain) { /* Release fw handle if it was allocated above */ if (!cfg->dev) @@ -2374,8 +2373,6 @@ static int mp_irqdomain_create(int ioapic) return -ENOMEM; } - ip->irqdomain->parent = parent; - if (cfg->type == IOAPIC_DOMAIN_LEGACY || cfg->type == IOAPIC_DOMAIN_STRICT) ioapic_dynirq_base = max(ioapic_dynirq_base, diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 60e330cdbd17..c6c15ce1952f 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -609,7 +609,7 @@ static long __apm_bios_call(void *_call) apm_irq_save(flags); firmware_restrict_branch_speculation_start(); - ibt = ibt_save(); + ibt = ibt_save(true); APM_DO_SAVE_SEGS; apm_bios_call_asm(call->func, call->ebx, call->ecx, &call->eax, &call->ebx, &call->ecx, &call->edx, @@ -690,7 +690,7 @@ static long __apm_bios_call_simple(void *_call) apm_irq_save(flags); firmware_restrict_branch_speculation_start(); - ibt = ibt_save(); + ibt = ibt_save(true); APM_DO_SAVE_SEGS; error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx, &call->eax); diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 82c783da16a8..283dcd2f62c8 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -7,6 +7,7 @@ #define COMPILE_OFFSETS #include <linux/crypto.h> +#include <crypto/aria.h> #include <linux/sched.h> #include <linux/stddef.h> #include <linux/hardirq.h> @@ -75,12 +76,18 @@ static void __used common(void) OFFSET(TDX_MODULE_r11, tdx_module_output, r11); BLANK(); + OFFSET(TDX_HYPERCALL_r8, tdx_hypercall_args, r8); + OFFSET(TDX_HYPERCALL_r9, tdx_hypercall_args, r9); OFFSET(TDX_HYPERCALL_r10, tdx_hypercall_args, r10); OFFSET(TDX_HYPERCALL_r11, tdx_hypercall_args, r11); OFFSET(TDX_HYPERCALL_r12, tdx_hypercall_args, r12); OFFSET(TDX_HYPERCALL_r13, tdx_hypercall_args, r13); OFFSET(TDX_HYPERCALL_r14, tdx_hypercall_args, r14); OFFSET(TDX_HYPERCALL_r15, tdx_hypercall_args, r15); + OFFSET(TDX_HYPERCALL_rdi, tdx_hypercall_args, rdi); + OFFSET(TDX_HYPERCALL_rsi, tdx_hypercall_args, rsi); + OFFSET(TDX_HYPERCALL_rbx, tdx_hypercall_args, rbx); + OFFSET(TDX_HYPERCALL_rdx, tdx_hypercall_args, rdx); BLANK(); OFFSET(BP_scratch, boot_params, scratch); @@ -111,5 +118,12 @@ static void __used common(void) #ifdef CONFIG_CALL_DEPTH_TRACKING OFFSET(X86_call_depth, pcpu_hot, call_depth); #endif +#if IS_ENABLED(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64) + /* Offset for fields in aria_ctx */ + BLANK(); + OFFSET(ARIA_CTX_enc_key, aria_ctx, enc_key); + OFFSET(ARIA_CTX_dec_key, aria_ctx, dec_key); + OFFSET(ARIA_CTX_rounds, aria_ctx, rounds); +#endif } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f769d6d08b43..380753b14cab 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -956,7 +956,7 @@ static void init_amd(struct cpuinfo_x86 *c) init_amd_cacheinfo(c); - if (cpu_has(c, X86_FEATURE_XMM2)) { + if (!cpu_has(c, X86_FEATURE_LFENCE_RDTSC) && cpu_has(c, X86_FEATURE_XMM2)) { /* * Use LFENCE for execution serialization. On families which * don't have that MSR, LFENCE is already serializing. @@ -1158,24 +1158,43 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) return false; } -void set_dr_addr_mask(unsigned long mask, int dr) +static DEFINE_PER_CPU_READ_MOSTLY(unsigned long[4], amd_dr_addr_mask); + +static unsigned int amd_msr_dr_addr_masks[] = { + MSR_F16H_DR0_ADDR_MASK, + MSR_F16H_DR1_ADDR_MASK, + MSR_F16H_DR1_ADDR_MASK + 1, + MSR_F16H_DR1_ADDR_MASK + 2 +}; + +void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr) { - if (!boot_cpu_has(X86_FEATURE_BPEXT)) + int cpu = smp_processor_id(); + + if (!cpu_feature_enabled(X86_FEATURE_BPEXT)) return; - switch (dr) { - case 0: - wrmsr(MSR_F16H_DR0_ADDR_MASK, mask, 0); - break; - case 1: - case 2: - case 3: - wrmsr(MSR_F16H_DR1_ADDR_MASK - 1 + dr, mask, 0); - break; - default: - break; - } + if (WARN_ON_ONCE(dr >= ARRAY_SIZE(amd_msr_dr_addr_masks))) + return; + + if (per_cpu(amd_dr_addr_mask, cpu)[dr] == mask) + return; + + wrmsr(amd_msr_dr_addr_masks[dr], mask, 0); + per_cpu(amd_dr_addr_mask, cpu)[dr] = mask; +} + +unsigned long amd_get_dr_addr_mask(unsigned int dr) +{ + if (!cpu_feature_enabled(X86_FEATURE_BPEXT)) + return 0; + + if (WARN_ON_ONCE(dr >= ARRAY_SIZE(amd_msr_dr_addr_masks))) + return 0; + + return per_cpu(amd_dr_addr_mask[dr], smp_processor_id()); } +EXPORT_SYMBOL_GPL(amd_get_dr_addr_mask); u32 amd_get_highest_perf(void) { diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index 1f60a2b27936..fdbb5f07448f 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -330,7 +330,16 @@ static void __init bp_init_freq_invariance(void) static void disable_freq_invariance_workfn(struct work_struct *work) { + int cpu; + static_branch_disable(&arch_scale_freq_key); + + /* + * Set arch_freq_scale to a default value on all cpus + * This negates the effect of scaling + */ + for_each_possible_cpu(cpu) + per_cpu(arch_freq_scale, cpu) = SCHED_CAPACITY_SCALE; } static DECLARE_WORK(disable_freq_invariance_work, diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bca0bd8f4846..cf81848b72f4 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -33,6 +33,7 @@ #include <asm/e820/api.h> #include <asm/hypervisor.h> #include <asm/tlbflush.h> +#include <asm/cpu.h> #include "cpu.h" @@ -86,7 +87,7 @@ void update_spec_ctrl_cond(u64 val) wrmsrl(MSR_IA32_SPEC_CTRL, val); } -u64 spec_ctrl_current(void) +noinstr u64 spec_ctrl_current(void) { return this_cpu_read(x86_spec_ctrl_current); } @@ -144,9 +145,17 @@ void __init check_bugs(void) * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD * init code as it is not enumerated and depends on the family. */ - if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + if (cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) { rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + /* + * Previously running kernel (kexec), may have some controls + * turned ON. Clear them and let the mitigations setup below + * rediscover them based on configuration. + */ + x86_spec_ctrl_base &= ~SPEC_CTRL_MITIGATIONS_MASK; + } + /* Select the proper CPU mitigations before patching alternatives: */ spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); @@ -1229,9 +1238,9 @@ static const char * const spectre_v2_strings[] = { [SPECTRE_V2_NONE] = "Vulnerable", [SPECTRE_V2_RETPOLINE] = "Mitigation: Retpolines", [SPECTRE_V2_LFENCE] = "Mitigation: LFENCE", - [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced IBRS", - [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced IBRS + LFENCE", - [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced IBRS + Retpolines", + [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced / Automatic IBRS", + [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced / Automatic IBRS + LFENCE", + [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced / Automatic IBRS + Retpolines", [SPECTRE_V2_IBRS] = "Mitigation: IBRS", }; @@ -1300,7 +1309,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && !boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { - pr_err("%s selected but CPU doesn't have eIBRS. Switching to AUTO select\n", + pr_err("%s selected but CPU doesn't have Enhanced or Automatic IBRS. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } @@ -1486,8 +1495,12 @@ static void __init spectre_v2_select_mitigation(void) pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); if (spectre_v2_in_ibrs_mode(mode)) { - x86_spec_ctrl_base |= SPEC_CTRL_IBRS; - update_spec_ctrl(x86_spec_ctrl_base); + if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) { + msr_set_bit(MSR_EFER, _EFER_AUTOIBRS); + } else { + x86_spec_ctrl_base |= SPEC_CTRL_IBRS; + update_spec_ctrl(x86_spec_ctrl_base); + } } switch (mode) { @@ -1571,8 +1584,8 @@ static void __init spectre_v2_select_mitigation(void) /* * Retpoline protects the kernel, but doesn't protect firmware. IBRS * and Enhanced IBRS protect firmware too, so enable IBRS around - * firmware calls only when IBRS / Enhanced IBRS aren't otherwise - * enabled. + * firmware calls only when IBRS / Enhanced / Automatic IBRS aren't + * otherwise enabled. * * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because * the user might select retpoline on the kernel command line and if diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index f4e5aa27eec6..4063e8991211 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -734,7 +734,7 @@ void init_hygon_cacheinfo(struct cpuinfo_x86 *c) void init_intel_cacheinfo(struct cpuinfo_x86 *c) { /* Cache sizes */ - unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0; + unsigned int l1i = 0, l1d = 0, l2 = 0, l3 = 0; unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */ unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */ unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb; @@ -835,9 +835,6 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c) case LVL_3: l3 += cache_table[k].size; break; - case LVL_TRACE: - trace += cache_table[k].size; - break; } break; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9cfca3d7d0e2..8cd4126d8253 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -567,17 +567,18 @@ static __init int setup_disable_pku(char *arg) return 1; } __setup("nopku", setup_disable_pku); -#endif /* CONFIG_X86_64 */ +#endif #ifdef CONFIG_X86_KERNEL_IBT -__noendbr u64 ibt_save(void) +__noendbr u64 ibt_save(bool disable) { u64 msr = 0; if (cpu_feature_enabled(X86_FEATURE_IBT)) { rdmsrl(MSR_IA32_S_CET, msr); - wrmsrl(MSR_IA32_S_CET, msr & ~CET_ENDBR_EN); + if (disable) + wrmsrl(MSR_IA32_S_CET, msr & ~CET_ENDBR_EN); } return msr; @@ -1093,6 +1094,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x8000001f) c->x86_capability[CPUID_8000_001F_EAX] = cpuid_eax(0x8000001f); + if (c->extended_cpuid_level >= 0x80000021) + c->x86_capability[CPUID_8000_0021_EAX] = cpuid_eax(0x80000021); + init_scattered_cpuid_features(c); init_speculation_control(c); @@ -1226,8 +1230,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), /* Zhaoxin Family 7 */ VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), @@ -1256,6 +1260,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define MMIO_SBDS BIT(2) /* CPU is affected by RETbleed, speculating where you would not expect it */ #define RETBLEED BIT(3) +/* CPU is affected by SMT (cross-thread) return predictions */ +#define SMT_RSB BIT(4) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1287,8 +1293,8 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), - VULNBL_AMD(0x17, RETBLEED), - VULNBL_HYGON(0x18, RETBLEED), + VULNBL_AMD(0x17, RETBLEED | SMT_RSB), + VULNBL_HYGON(0x18, RETBLEED | SMT_RSB), {} }; @@ -1338,8 +1344,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); - if (ia32_cap & ARCH_CAP_IBRS_ALL) + /* + * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature + * flag and protect from vendor-specific bugs via the whitelist. + */ + if ((ia32_cap & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) { setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); + if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && + !(ia32_cap & ARCH_CAP_PBRSB_NO)) + setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); + } if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) { @@ -1401,10 +1415,8 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_RETBLEED); } - if (cpu_has(c, X86_FEATURE_IBRS_ENHANCED) && - !cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && - !(ia32_cap & ARCH_CAP_PBRSB_NO)) - setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); + if (cpu_matches(cpu_vuln_blacklist, SMT_RSB)) + setup_force_cpu_bug(X86_BUG_SMT_RSB); if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; @@ -1682,9 +1694,7 @@ void check_null_seg_clears_base(struct cpuinfo_x86 *c) if (!IS_ENABLED(CONFIG_X86_64)) return; - /* Zen3 CPUs advertise Null Selector Clears Base in CPUID. */ - if (c->extended_cpuid_level >= 0x80000021 && - cpuid_eax(0x80000021) & BIT(6)) + if (cpu_has(c, X86_FEATURE_NULL_SEL_CLR_BASE)) return; /* @@ -1953,13 +1963,13 @@ void __init identify_boot_cpu(void) if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT)) pr_info("CET detected: Indirect Branch Tracking enabled\n"); #ifdef CONFIG_X86_32 - sysenter_setup(); enable_sep_cpu(); #endif cpu_detect_tlb(&boot_cpu_data); setup_cr_pinning(); tsx_init(); + lkgs_init(); } void identify_secondary_cpu(struct cpuinfo_x86 *c) @@ -2125,7 +2135,6 @@ static void wait_for_master_cpu(int cpu) #endif } -#ifdef CONFIG_X86_64 static inline void setup_getcpu(int cpu) { unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu)); @@ -2147,6 +2156,7 @@ static inline void setup_getcpu(int cpu) write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_CPUNODE, &d, DESCTYPE_S); } +#ifdef CONFIG_X86_64 static inline void ucode_cpu_init(int cpu) { if (cpu) @@ -2166,8 +2176,6 @@ static inline void tss_setup_ist(struct tss_struct *tss) #else /* CONFIG_X86_64 */ -static inline void setup_getcpu(int cpu) { } - static inline void ucode_cpu_init(int cpu) { show_ucode_info_early(); @@ -2297,30 +2305,45 @@ void cpu_init_secondary(void) #endif #ifdef CONFIG_MICROCODE_LATE_LOADING -/* +/** + * store_cpu_caps() - Store a snapshot of CPU capabilities + * @curr_info: Pointer where to store it + * + * Returns: None + */ +void store_cpu_caps(struct cpuinfo_x86 *curr_info) +{ + /* Reload CPUID max function as it might've changed. */ + curr_info->cpuid_level = cpuid_eax(0); + + /* Copy all capability leafs and pick up the synthetic ones. */ + memcpy(&curr_info->x86_capability, &boot_cpu_data.x86_capability, + sizeof(curr_info->x86_capability)); + + /* Get the hardware CPUID leafs */ + get_cpu_cap(curr_info); +} + +/** + * microcode_check() - Check if any CPU capabilities changed after an update. + * @prev_info: CPU capabilities stored before an update. + * * The microcode loader calls this upon late microcode load to recheck features, * only when microcode has been updated. Caller holds microcode_mutex and CPU * hotplug lock. + * + * Return: None */ -void microcode_check(void) +void microcode_check(struct cpuinfo_x86 *prev_info) { - struct cpuinfo_x86 info; + struct cpuinfo_x86 curr_info; perf_check_microcode(); - /* Reload CPUID max function as it might've changed. */ - info.cpuid_level = cpuid_eax(0); - - /* - * Copy all capability leafs to pick up the synthetic ones so that - * memcmp() below doesn't fail on that. The ones coming from CPUID will - * get overwritten in get_cpu_cap(). - */ - memcpy(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability)); - - get_cpu_cap(&info); + store_cpu_caps(&curr_info); - if (!memcmp(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability))) + if (!memcmp(&prev_info->x86_capability, &curr_info.x86_capability, + sizeof(prev_info->x86_capability))) return; pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n"); diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 7c9b5893c30a..57a5349e6954 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -83,6 +83,4 @@ unsigned int aperfmperf_get_khz(int cpu); extern void x86_spec_ctrl_setup_ap(void); extern void update_srbds_msr(void); -extern u64 x86_read_arch_cap_msr(void); - #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index d95221117129..f6748c8bd647 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -68,6 +68,8 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_CQM_OCCUP_LLC, X86_FEATURE_CQM_LLC }, { X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC }, { X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC }, + { X86_FEATURE_BMEC, X86_FEATURE_CQM_MBM_TOTAL }, + { X86_FEATURE_BMEC, X86_FEATURE_CQM_MBM_LOCAL }, { X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_FP16, X86_FEATURE_AVX512BW }, { X86_FEATURE_ENQCMD, X86_FEATURE_XSAVES }, diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 10fb5b5c9efa..23c5072fbbb7 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -306,6 +306,8 @@ static void smca_configure(unsigned int bank, unsigned int cpu) if ((low & BIT(5)) && !((high >> 5) & 0x3)) high |= BIT(5); + this_cpu_ptr(mce_banks_array)[bank].lsb_in_status = !!(low & BIT(8)); + wrmsr(smca_config, low, high); } @@ -736,15 +738,7 @@ static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc) if (m.status & MCI_STATUS_ADDRV) { m.addr = addr; - /* - * Extract [55:<lsb>] where lsb is the least significant - * *valid* bit of the address bits. - */ - if (mce_flags.smca) { - u8 lsb = (m.addr >> 56) & 0x3f; - - m.addr &= GENMASK_ULL(55, lsb); - } + smca_extract_err_addr(&m); } if (mce_flags.smca) { diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 2c8ec5c71712..7832a69d170e 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -67,13 +67,7 @@ DEFINE_PER_CPU(unsigned, mce_exception_count); DEFINE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks); -struct mce_bank { - u64 ctl; /* subevents to enable */ - - __u64 init : 1, /* initialise bank? */ - __reserved_1 : 63; -}; -static DEFINE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array); +DEFINE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array); #define ATTR_LEN 16 /* One object for each MCE bank, shared by all CPUs */ @@ -579,7 +573,7 @@ static int uc_decode_notifier(struct notifier_block *nb, unsigned long val, mce->severity != MCE_DEFERRED_SEVERITY) return NOTIFY_DONE; - pfn = mce->addr >> PAGE_SHIFT; + pfn = (mce->addr & MCI_ADDR_PHYSADDR) >> PAGE_SHIFT; if (!memory_failure(pfn, 0)) { set_mce_nospec(pfn); mce->kflags |= MCE_HANDLED_UC; @@ -633,15 +627,7 @@ static noinstr void mce_read_aux(struct mce *m, int i) m->addr <<= shift; } - /* - * Extract [55:<lsb>] where lsb is the least significant - * *valid* bit of the address bits. - */ - if (mce_flags.smca) { - u8 lsb = (m->addr >> 56) & 0x3f; - - m->addr &= GENMASK_ULL(55, lsb); - } + smca_extract_err_addr(m); } if (mce_flags.smca) { @@ -1308,6 +1294,7 @@ static void kill_me_maybe(struct callback_head *cb) { struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me); int flags = MF_ACTION_REQUIRED; + unsigned long pfn; int ret; p->mce_count = 0; @@ -1316,9 +1303,10 @@ static void kill_me_maybe(struct callback_head *cb) if (!p->mce_ripv) flags |= MF_MUST_KILL; - ret = memory_failure(p->mce_addr >> PAGE_SHIFT, flags); + pfn = (p->mce_addr & MCI_ADDR_PHYSADDR) >> PAGE_SHIFT; + ret = memory_failure(pfn, flags); if (!ret) { - set_mce_nospec(p->mce_addr >> PAGE_SHIFT); + set_mce_nospec(pfn); sync_core(); return; } @@ -1340,11 +1328,13 @@ static void kill_me_maybe(struct callback_head *cb) static void kill_me_never(struct callback_head *cb) { struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me); + unsigned long pfn; p->mce_count = 0; pr_err("Kernel accessed poison in user space at %llx\n", p->mce_addr); - if (!memory_failure(p->mce_addr >> PAGE_SHIFT, 0)) - set_mce_nospec(p->mce_addr >> PAGE_SHIFT); + pfn = (p->mce_addr & MCI_ADDR_PHYSADDR) >> PAGE_SHIFT; + if (!memory_failure(pfn, 0)) + set_mce_nospec(pfn); } static void queue_task_work(struct mce *m, char *msg, void (*func)(struct callback_head *)) diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c index 100fbeebdc72..a05ac0716ecf 100644 --- a/arch/x86/kernel/cpu/mce/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c @@ -105,8 +105,7 @@ static ssize_t set_trigger(struct device *s, struct device_attribute *attr, { char *p; - strncpy(mce_helper, buf, sizeof(mce_helper)); - mce_helper[sizeof(mce_helper)-1] = 0; + strscpy(mce_helper, buf, sizeof(mce_helper)); p = strchr(mce_helper, '\n'); if (p) diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 7e03f5b7f6bd..91a415553c27 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -177,6 +177,24 @@ struct mce_vendor_flags { extern struct mce_vendor_flags mce_flags; +struct mce_bank { + /* subevents to enable */ + u64 ctl; + + /* initialise bank? */ + __u64 init : 1, + + /* + * (AMD) MCA_CONFIG[McaLsbInStatusSupported]: When set, this bit indicates + * the LSB field is found in MCA_STATUS and not in MCA_ADDR. + */ + lsb_in_status : 1, + + __reserved_1 : 62; +}; + +DECLARE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array); + enum mca_msr { MCA_CTL, MCA_STATUS, @@ -189,8 +207,34 @@ extern bool filter_mce(struct mce *m); #ifdef CONFIG_X86_MCE_AMD extern bool amd_filter_mce(struct mce *m); + +/* + * If MCA_CONFIG[McaLsbInStatusSupported] is set, extract ErrAddr in bits + * [56:0] of MCA_STATUS, else in bits [55:0] of MCA_ADDR. + */ +static __always_inline void smca_extract_err_addr(struct mce *m) +{ + u8 lsb; + + if (!mce_flags.smca) + return; + + if (this_cpu_ptr(mce_banks_array)[m->bank].lsb_in_status) { + lsb = (m->status >> 24) & 0x3f; + + m->addr &= GENMASK_ULL(56, lsb); + + return; + } + + lsb = (m->addr >> 56) & 0x3f; + + m->addr &= GENMASK_ULL(55, lsb); +} + #else static inline bool amd_filter_mce(struct mce *m) { return false; } +static inline void smca_extract_err_addr(struct mce *m) { } #endif #ifdef CONFIG_X86_ANCIENT_MCE diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 56471f750762..9eb457b10341 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -55,7 +55,9 @@ struct cont_desc { }; static u32 ucode_new_rev; -static u8 amd_ucode_patch[PATCH_MAX_SIZE]; + +/* One blob per node. */ +static u8 amd_ucode_patch[MAX_NUMNODES][PATCH_MAX_SIZE]; /* * Microcode patch container file is prepended to the initrd in cpio @@ -330,8 +332,9 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc) ret = verify_patch(x86_family(desc->cpuid_1_eax), buf, size, &patch_size, true); if (ret < 0) { /* - * Patch verification failed, skip to the next - * container, if there's one: + * Patch verification failed, skip to the next container, if + * there is one. Before exit, check whether that container has + * found a patch already. If so, use it. */ goto out; } else if (ret > 0) { @@ -350,6 +353,7 @@ skip: size -= patch_size + SECTION_HDR_SIZE; } +out: /* * If we have found a patch (desc->mc), it means we're looking at the * container which has a patch for this CPU so return 0 to mean, @ucode @@ -364,7 +368,6 @@ skip: return 0; } -out: return orig_size - size; } @@ -414,8 +417,7 @@ static int __apply_microcode_amd(struct microcode_amd *mc) * * Returns true if container found (sets @desc), false otherwise. */ -static bool -apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_patch) +static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size, bool save_patch) { struct cont_desc desc = { 0 }; u8 (*patch)[PATCH_MAX_SIZE]; @@ -428,7 +430,7 @@ apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_p patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch); #else new_rev = &ucode_new_rev; - patch = &amd_ucode_patch; + patch = &amd_ucode_patch[0]; #endif desc.cpuid_1_eax = cpuid_1_eax; @@ -481,7 +483,7 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) return false; } -static void __load_ucode_amd(unsigned int cpuid_1_eax, struct cpio_data *ret) +static void find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data *ret) { struct ucode_cpu_info *uci; struct cpio_data cp; @@ -511,11 +513,11 @@ void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax) { struct cpio_data cp = { }; - __load_ucode_amd(cpuid_1_eax, &cp); + find_blobs_in_containers(cpuid_1_eax, &cp); if (!(cp.data && cp.size)) return; - apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, true); + early_apply_microcode(cpuid_1_eax, cp.data, cp.size, true); } void load_ucode_amd_ap(unsigned int cpuid_1_eax) @@ -546,15 +548,14 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax) } } - __load_ucode_amd(cpuid_1_eax, &cp); + find_blobs_in_containers(cpuid_1_eax, &cp); if (!(cp.data && cp.size)) return; - apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, false); + early_apply_microcode(cpuid_1_eax, cp.data, cp.size, false); } -static enum ucode_state -load_microcode_amd(bool save, u8 family, const u8 *data, size_t size); +static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size); int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) { @@ -572,19 +573,19 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) if (!desc.mc) return -EINVAL; - ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size); + ret = load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size); if (ret > UCODE_UPDATED) return -EINVAL; return 0; } -void reload_ucode_amd(void) +void reload_ucode_amd(unsigned int cpu) { - struct microcode_amd *mc; u32 rev, dummy __always_unused; + struct microcode_amd *mc; - mc = (struct microcode_amd *)amd_ucode_patch; + mc = (struct microcode_amd *)amd_ucode_patch[cpu_to_node(cpu)]; rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); @@ -816,6 +817,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover, return 0; } +/* Scan the blob in @data and add microcode patches to the cache. */ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, size_t size) { @@ -850,9 +852,10 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, return UCODE_OK; } -static enum ucode_state -load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) +static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) { + struct cpuinfo_x86 *c; + unsigned int nid, cpu; struct ucode_patch *p; enum ucode_state ret; @@ -865,22 +868,22 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) return ret; } - p = find_patch(0); - if (!p) { - return ret; - } else { - if (boot_cpu_data.microcode >= p->patch_id) - return ret; + for_each_node(nid) { + cpu = cpumask_first(cpumask_of_node(nid)); + c = &cpu_data(cpu); - ret = UCODE_NEW; - } + p = find_patch(cpu); + if (!p) + continue; - /* save BSP's matching patch for early load */ - if (!save) - return ret; + if (c->microcode >= p->patch_id) + continue; - memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); - memcpy(amd_ucode_patch, p->data, min_t(u32, p->size, PATCH_MAX_SIZE)); + ret = UCODE_NEW; + + memset(&amd_ucode_patch[nid], 0, PATCH_MAX_SIZE); + memcpy(&amd_ucode_patch[nid], p->data, min_t(u32, p->size, PATCH_MAX_SIZE)); + } return ret; } @@ -905,14 +908,9 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device) { char fw_name[36] = "amd-ucode/microcode_amd.bin"; struct cpuinfo_x86 *c = &cpu_data(cpu); - bool bsp = c->cpu_index == boot_cpu_data.cpu_index; enum ucode_state ret = UCODE_NFOUND; const struct firmware *fw; - /* reload ucode container only on the boot cpu */ - if (!bsp) - return UCODE_OK; - if (c->x86 >= 0x15) snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); @@ -925,7 +923,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device) if (!verify_container(fw->data, fw->size, false)) goto fw_release; - ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size); + ret = load_microcode_amd(c->x86, fw->data, fw->size); fw_release: release_firmware(fw); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 712aafff96e0..7a329e561354 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -298,7 +298,7 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) #endif } -void reload_early_microcode(void) +void reload_early_microcode(unsigned int cpu) { int vendor, family; @@ -312,7 +312,7 @@ void reload_early_microcode(void) break; case X86_VENDOR_AMD: if (family >= 0x10) - reload_ucode_amd(); + reload_ucode_amd(cpu); break; default: break; @@ -409,10 +409,10 @@ static int __reload_late(void *info) goto wait_for_siblings; if (err >= UCODE_NFOUND) { - if (err == UCODE_ERROR) + if (err == UCODE_ERROR) { pr_warn("Error reloading microcode on CPU %d\n", cpu); - - ret = -1; + ret = -1; + } } wait_for_siblings: @@ -438,6 +438,7 @@ wait_for_siblings: static int microcode_reload_late(void) { int old = boot_cpu_data.microcode, ret; + struct cpuinfo_x86 prev_info; pr_err("Attempting late microcode loading - it is dangerous and taints the kernel.\n"); pr_err("You should switch to early loading, if possible.\n"); @@ -445,12 +446,21 @@ static int microcode_reload_late(void) atomic_set(&late_cpus_in, 0); atomic_set(&late_cpus_out, 0); - ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask); - if (ret == 0) - microcode_check(); + /* + * Take a snapshot before the microcode update in order to compare and + * check whether any bits changed after an update. + */ + store_cpu_caps(&prev_info); - pr_info("Reload completed, microcode revision: 0x%x -> 0x%x\n", - old, boot_cpu_data.microcode); + ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask); + if (!ret) { + pr_info("Reload succeeded, microcode revision: 0x%x -> 0x%x\n", + old, boot_cpu_data.microcode); + microcode_check(&prev_info); + } else { + pr_info("Reload failed, current microcode revision: 0x%x\n", + boot_cpu_data.microcode); + } return ret; } @@ -465,11 +475,8 @@ static ssize_t reload_store(struct device *dev, ssize_t ret = 0; ret = kstrtoul(buf, 0, &val); - if (ret) - return ret; - - if (val != 1) - return size; + if (ret || val != 1) + return -EINVAL; cpus_read_lock(); @@ -507,7 +514,7 @@ static ssize_t version_show(struct device *dev, return sprintf(buf, "0x%x\n", uci->cpu_sig.rev); } -static ssize_t pf_show(struct device *dev, +static ssize_t processor_flags_show(struct device *dev, struct device_attribute *attr, char *buf) { struct ucode_cpu_info *uci = ucode_cpu_info + dev->id; @@ -515,8 +522,8 @@ static ssize_t pf_show(struct device *dev, return sprintf(buf, "0x%x\n", uci->cpu_sig.pf); } -static DEVICE_ATTR(version, 0444, version_show, NULL); -static DEVICE_ATTR(processor_flags, 0444, pf_show, NULL); +static DEVICE_ATTR_RO(version); +static DEVICE_ATTR_RO(processor_flags); static struct attribute *mc_default_attrs[] = { &dev_attr_version.attr, @@ -557,7 +564,7 @@ void microcode_bsp_resume(void) if (uci->mc) microcode_ops->apply_microcode(cpu); else - reload_early_microcode(); + reload_early_microcode(cpu); } static struct syscore_ops mc_syscore_ops = { diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index cac2bdb57f0b..467cf37ea90a 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -305,14 +305,11 @@ static bool load_builtin_intel_microcode(struct cpio_data *cp) return false; } -/* - * Print ucode update info. - */ -static void -print_ucode_info(struct ucode_cpu_info *uci, unsigned int date) +static void print_ucode_info(int old_rev, int new_rev, unsigned int date) { - pr_info_once("microcode updated early to revision 0x%x, date = %04x-%02x-%02x\n", - uci->cpu_sig.rev, + pr_info_once("updated early: 0x%x -> 0x%x, date = %04x-%02x-%02x\n", + old_rev, + new_rev, date & 0xffff, date >> 24, (date >> 16) & 0xff); @@ -322,6 +319,7 @@ print_ucode_info(struct ucode_cpu_info *uci, unsigned int date) static int delay_ucode_info; static int current_mc_date; +static int early_old_rev; /* * Print early updated ucode info after printk works. This is delayed info dump. @@ -332,7 +330,7 @@ void show_ucode_info_early(void) if (delay_ucode_info) { intel_cpu_collect_info(&uci); - print_ucode_info(&uci, current_mc_date); + print_ucode_info(early_old_rev, uci.cpu_sig.rev, current_mc_date); delay_ucode_info = 0; } } @@ -341,40 +339,32 @@ void show_ucode_info_early(void) * At this point, we can not call printk() yet. Delay printing microcode info in * show_ucode_info_early() until printk() works. */ -static void print_ucode(struct ucode_cpu_info *uci) +static void print_ucode(int old_rev, int new_rev, int date) { - struct microcode_intel *mc; int *delay_ucode_info_p; int *current_mc_date_p; - - mc = uci->mc; - if (!mc) - return; + int *early_old_rev_p; delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info); current_mc_date_p = (int *)__pa_nodebug(¤t_mc_date); + early_old_rev_p = (int *)__pa_nodebug(&early_old_rev); *delay_ucode_info_p = 1; - *current_mc_date_p = mc->hdr.date; + *current_mc_date_p = date; + *early_old_rev_p = old_rev; } #else -static inline void print_ucode(struct ucode_cpu_info *uci) +static inline void print_ucode(int old_rev, int new_rev, int date) { - struct microcode_intel *mc; - - mc = uci->mc; - if (!mc) - return; - - print_ucode_info(uci, mc->hdr.date); + print_ucode_info(old_rev, new_rev, date); } #endif static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) { struct microcode_intel *mc; - u32 rev; + u32 rev, old_rev; mc = uci->mc; if (!mc) @@ -391,6 +381,8 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) return UCODE_OK; } + old_rev = rev; + /* * Writeback and invalidate caches before updating microcode to avoid * internal issues depending on what the microcode is updating. @@ -407,9 +399,9 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) uci->cpu_sig.rev = rev; if (early) - print_ucode(uci); + print_ucode(old_rev, uci->cpu_sig.rev, mc->hdr.date); else - print_ucode_info(uci, mc->hdr.date); + print_ucode_info(old_rev, uci->cpu_sig.rev, mc->hdr.date); return 0; } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 46668e255421..f36dc2f796c5 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -37,9 +37,76 @@ /* Is Linux running as the root partition? */ bool hv_root_partition; +/* Is Linux running on nested Microsoft Hypervisor */ +bool hv_nested; struct ms_hyperv_info ms_hyperv; #if IS_ENABLED(CONFIG_HYPERV) +static inline unsigned int hv_get_nested_reg(unsigned int reg) +{ + if (hv_is_sint_reg(reg)) + return reg - HV_REGISTER_SINT0 + HV_REGISTER_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; + default: + return reg; + } +} + +u64 hv_get_non_nested_register(unsigned int reg) +{ + u64 value; + + if (hv_is_synic_reg(reg) && hv_isolation_type_snp()) + hv_ghcb_msr_read(reg, &value); + else + rdmsrl(reg, value); + return value; +} +EXPORT_SYMBOL_GPL(hv_get_non_nested_register); + +void hv_set_non_nested_register(unsigned int reg, u64 value) +{ + if (hv_is_synic_reg(reg) && hv_isolation_type_snp()) { + hv_ghcb_msr_write(reg, value); + + /* Write proxy bit via wrmsl instruction */ + if (hv_is_sint_reg(reg)) + wrmsrl(reg, value | 1 << 20); + } else { + wrmsrl(reg, value); + } +} +EXPORT_SYMBOL_GPL(hv_set_non_nested_register); + +u64 hv_get_register(unsigned int reg) +{ + if (hv_nested) + reg = hv_get_nested_reg(reg); + + return hv_get_non_nested_register(reg); +} +EXPORT_SYMBOL_GPL(hv_get_register); + +void hv_set_register(unsigned int reg, u64 value) +{ + if (hv_nested) + reg = hv_get_nested_reg(reg); + + hv_set_non_nested_register(reg, value); +} +EXPORT_SYMBOL_GPL(hv_set_register); + static void (*vmbus_handler)(void); static void (*hv_stimer0_handler)(void); static void (*hv_kexec_handler)(void); @@ -301,6 +368,11 @@ static void __init ms_hyperv_init_platform(void) pr_info("Hyper-V: running as root partition\n"); } + if (ms_hyperv.hints & HV_X64_HYPERV_NESTED) { + hv_nested = true; + pr_info("Hyper-V: running on a nested hypervisor\n"); + } + /* * Extract host information. */ @@ -388,7 +460,7 @@ static void __init ms_hyperv_init_platform(void) * setting of this MSR bit should happen before init_intel() * is called. */ - wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, 0x1); + wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_EXPOSE_INVARIANT_TSC); setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); } diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index c98e52ff5f20..030d3b409768 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -100,6 +100,18 @@ struct rdt_hw_resource rdt_resources_all[] = { .fflags = RFTYPE_RES_MB, }, }, + [RDT_RESOURCE_SMBA] = + { + .r_resctrl = { + .rid = RDT_RESOURCE_SMBA, + .name = "SMBA", + .cache_level = 3, + .domains = domain_init(RDT_RESOURCE_SMBA), + .parse_ctrlval = parse_bw, + .format_str = "%d=%*u", + .fflags = RFTYPE_RES_MB, + }, + }, }; /* @@ -150,6 +162,13 @@ bool is_mba_sc(struct rdt_resource *r) if (!r) return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.mba_sc; + /* + * The software controller support is only applicable to MBA resource. + * Make sure to check for resource type. + */ + if (r->rid != RDT_RESOURCE_MBA) + return false; + return r->membw.mba_sc; } @@ -213,9 +232,15 @@ 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; + u32 ebx, ecx, subleaf; + + /* + * Query CPUID_Fn80000020_EDX_x01 for MBA and + * CPUID_Fn80000020_EDX_x02 for SMBA + */ + subleaf = (r->rid == RDT_RESOURCE_SMBA) ? 2 : 1; - cpuid_count(0x80000020, 1, &eax.full, &ebx, &ecx, &edx.full); + 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; @@ -647,6 +672,8 @@ enum { RDT_FLAG_L2_CAT, RDT_FLAG_L2_CDP, RDT_FLAG_MBA, + RDT_FLAG_SMBA, + RDT_FLAG_BMEC, }; #define RDT_OPT(idx, n, f) \ @@ -670,6 +697,8 @@ static struct rdt_options rdt_options[] __initdata = { RDT_OPT(RDT_FLAG_L2_CAT, "l2cat", X86_FEATURE_CAT_L2), RDT_OPT(RDT_FLAG_L2_CDP, "l2cdp", X86_FEATURE_CDP_L2), RDT_OPT(RDT_FLAG_MBA, "mba", X86_FEATURE_MBA), + RDT_OPT(RDT_FLAG_SMBA, "smba", X86_FEATURE_SMBA), + RDT_OPT(RDT_FLAG_BMEC, "bmec", X86_FEATURE_BMEC), }; #define NUM_RDT_OPTIONS ARRAY_SIZE(rdt_options) @@ -699,7 +728,7 @@ static int __init set_rdt_options(char *str) } __setup("rdt", set_rdt_options); -static bool __init rdt_cpu_has(int flag) +bool __init rdt_cpu_has(int flag) { bool ret = boot_cpu_has(flag); struct rdt_options *o; @@ -734,6 +763,19 @@ static __init bool get_mem_config(void) return false; } +static __init bool get_slow_mem_config(void) +{ + struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_SMBA]; + + if (!rdt_cpu_has(X86_FEATURE_SMBA)) + return false; + + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + return __rdt_get_mem_config_amd(&hw_res->r_resctrl); + + return false; +} + static __init bool get_rdt_alloc_resources(void) { struct rdt_resource *r; @@ -764,6 +806,9 @@ static __init bool get_rdt_alloc_resources(void) if (get_mem_config()) ret = true; + if (get_slow_mem_config()) + ret = true; + return ret; } @@ -853,6 +898,9 @@ static __init void rdt_init_res_defs_amd(void) } else if (r->rid == RDT_RESOURCE_MBA) { hw_res->msr_base = MSR_IA32_MBA_BW_BASE; hw_res->msr_update = mba_wrmsr_amd; + } else if (r->rid == RDT_RESOURCE_SMBA) { + hw_res->msr_base = MSR_IA32_SMBA_BW_BASE; + hw_res->msr_update = mba_wrmsr_amd; } } } diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 1df0e3262bca..eb07d4435391 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -209,7 +209,7 @@ static int parse_line(char *line, struct resctrl_schema *s, unsigned long dom_id; if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && - r->rid == RDT_RESOURCE_MBA) { + (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) { rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n"); return -EINVAL; } @@ -310,7 +310,6 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) enum resctrl_conf_type t; cpumask_var_t cpu_mask; struct rdt_domain *d; - int cpu; u32 idx; if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) @@ -341,13 +340,9 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) if (cpumask_empty(cpu_mask)) goto done; - cpu = get_cpu(); - /* Update resource control msr on this CPU if it's in cpu_mask. */ - if (cpumask_test_cpu(cpu, cpu_mask)) - rdt_ctrl_update(&msr_param); - /* Update resource control msr on other CPUs. */ - smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1); - put_cpu(); + + /* Update resource control msr on all the CPUs. */ + on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1); done: free_cpumask_var(cpu_mask); diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 5ebd28e6aa0c..8edecc5763d8 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -30,6 +30,29 @@ */ #define MBM_CNTR_WIDTH_OFFSET_MAX (62 - MBM_CNTR_WIDTH_BASE) +/* Reads to Local DRAM Memory */ +#define READS_TO_LOCAL_MEM BIT(0) + +/* Reads to Remote DRAM Memory */ +#define READS_TO_REMOTE_MEM BIT(1) + +/* Non-Temporal Writes to Local Memory */ +#define NON_TEMP_WRITE_TO_LOCAL_MEM BIT(2) + +/* Non-Temporal Writes to Remote Memory */ +#define NON_TEMP_WRITE_TO_REMOTE_MEM BIT(3) + +/* Reads to Local Memory the system identifies as "Slow Memory" */ +#define READS_TO_LOCAL_S_MEM BIT(4) + +/* Reads to Remote Memory the system identifies as "Slow Memory" */ +#define READS_TO_REMOTE_S_MEM BIT(5) + +/* Dirty Victims to All Types of Memory */ +#define DIRTY_VICTIMS_TO_ALL_MEM BIT(6) + +/* Max event bits supported */ +#define MAX_EVT_CONFIG_BITS GENMASK(6, 0) struct rdt_fs_context { struct kernfs_fs_context kfc; @@ -52,11 +75,13 @@ DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); * struct mon_evt - Entry in the event list of a resource * @evtid: event id * @name: name of the event + * @configurable: true if the event is configurable * @list: entry in &rdt_resource->evt_list */ struct mon_evt { enum resctrl_event_id evtid; char *name; + bool configurable; struct list_head list; }; @@ -409,6 +434,7 @@ enum resctrl_res_level { RDT_RESOURCE_L3, RDT_RESOURCE_L2, RDT_RESOURCE_MBA, + RDT_RESOURCE_SMBA, /* Must be the last */ RDT_NUM_RESOURCES, @@ -511,6 +537,7 @@ void closid_free(int closid); int alloc_rmid(void); void free_rmid(u32 rmid); int rdt_get_mon_l3_config(struct rdt_resource *r); +bool __init rdt_cpu_has(int flag); void mon_event_count(void *info); int rdtgroup_mondata_show(struct seq_file *m, void *arg); void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, @@ -527,5 +554,6 @@ bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); void __check_limbo(struct rdt_domain *d, bool force_free); void rdt_domain_reconfigure_cdp(struct rdt_resource *r); void __init thread_throttle_mode_init(void); +void __init mbm_config_rftype_init(const char *config); #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 77538abeb72a..7fe51488e136 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -204,6 +204,23 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, } } +/* + * Assumes that hardware counters are also reset and thus that there is + * no need to record initial non-zero counts. + */ +void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d) +{ + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); + + if (is_mbm_total_enabled()) + memset(hw_dom->arch_mbm_total, 0, + sizeof(*hw_dom->arch_mbm_total) * r->num_rmid); + + if (is_mbm_local_enabled()) + memset(hw_dom->arch_mbm_local, 0, + sizeof(*hw_dom->arch_mbm_local) * r->num_rmid); +} + static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) { u64 shift = 64 - width, chunks; @@ -763,7 +780,7 @@ static void l3_mon_evt_init(struct rdt_resource *r) list_add_tail(&mbm_local_event.list, &r->evt_list); } -int rdt_get_mon_l3_config(struct rdt_resource *r) +int __init rdt_get_mon_l3_config(struct rdt_resource *r) { unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset; struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); @@ -800,6 +817,17 @@ int rdt_get_mon_l3_config(struct rdt_resource *r) if (ret) return ret; + if (rdt_cpu_has(X86_FEATURE_BMEC)) { + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { + mbm_total_event.configurable = true; + mbm_config_rftype_init("mbm_total_bytes_config"); + } + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) { + mbm_local_event.configurable = true; + mbm_config_rftype_init("mbm_local_bytes_config"); + } + } + l3_mon_evt_init(r); r->mon_capable = true; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 5993da21d822..e2c1599d1b37 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -325,12 +325,7 @@ static void update_cpu_closid_rmid(void *info) static void update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r) { - int cpu = get_cpu(); - - if (cpumask_test_cpu(cpu, cpu_mask)) - update_cpu_closid_rmid(r); - smp_call_function_many(cpu_mask, update_cpu_closid_rmid, r, 1); - put_cpu(); + on_each_cpu_mask(cpu_mask, update_cpu_closid_rmid, r, 1); } static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, @@ -1003,8 +998,11 @@ static int rdt_mon_features_show(struct kernfs_open_file *of, struct rdt_resource *r = of->kn->parent->priv; struct mon_evt *mevt; - list_for_each_entry(mevt, &r->evt_list, list) + list_for_each_entry(mevt, &r->evt_list, list) { seq_printf(seq, "%s\n", mevt->name); + if (mevt->configurable) + seq_printf(seq, "%s_config\n", mevt->name); + } return 0; } @@ -1215,7 +1213,7 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; - if (r->rid == RDT_RESOURCE_MBA) + if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA) continue; has_cache = true; list_for_each_entry(d, &r->domains, list) { @@ -1404,7 +1402,8 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, ctrl = resctrl_arch_get_config(r, d, closid, type); - if (r->rid == RDT_RESOURCE_MBA) + if (r->rid == RDT_RESOURCE_MBA || + r->rid == RDT_RESOURCE_SMBA) size = ctrl; else size = rdtgroup_cbm_to_size(r, d, ctrl); @@ -1421,6 +1420,248 @@ out: return ret; } +struct mon_config_info { + u32 evtid; + u32 mon_config; +}; + +#define INVALID_CONFIG_INDEX UINT_MAX + +/** + * mon_event_config_index_get - get the hardware index for the + * configurable event + * @evtid: event id. + * + * Return: 0 for evtid == QOS_L3_MBM_TOTAL_EVENT_ID + * 1 for evtid == QOS_L3_MBM_LOCAL_EVENT_ID + * INVALID_CONFIG_INDEX for invalid evtid + */ +static inline unsigned int mon_event_config_index_get(u32 evtid) +{ + switch (evtid) { + case QOS_L3_MBM_TOTAL_EVENT_ID: + return 0; + case QOS_L3_MBM_LOCAL_EVENT_ID: + return 1; + default: + /* Should never reach here */ + return INVALID_CONFIG_INDEX; + } +} + +static void mon_event_config_read(void *info) +{ + struct mon_config_info *mon_info = info; + unsigned int index; + u64 msrval; + + index = mon_event_config_index_get(mon_info->evtid); + if (index == INVALID_CONFIG_INDEX) { + pr_warn_once("Invalid event id %d\n", mon_info->evtid); + return; + } + rdmsrl(MSR_IA32_EVT_CFG_BASE + index, msrval); + + /* Report only the valid event configuration bits */ + mon_info->mon_config = msrval & MAX_EVT_CONFIG_BITS; +} + +static void mondata_config_read(struct rdt_domain *d, struct mon_config_info *mon_info) +{ + smp_call_function_any(&d->cpu_mask, mon_event_config_read, mon_info, 1); +} + +static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid) +{ + struct mon_config_info mon_info = {0}; + struct rdt_domain *dom; + bool sep = false; + + mutex_lock(&rdtgroup_mutex); + + list_for_each_entry(dom, &r->domains, list) { + if (sep) + seq_puts(s, ";"); + + memset(&mon_info, 0, sizeof(struct mon_config_info)); + mon_info.evtid = evtid; + mondata_config_read(dom, &mon_info); + + seq_printf(s, "%d=0x%02x", dom->id, mon_info.mon_config); + sep = true; + } + seq_puts(s, "\n"); + + mutex_unlock(&rdtgroup_mutex); + + return 0; +} + +static int mbm_total_bytes_config_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID); + + return 0; +} + +static int mbm_local_bytes_config_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID); + + return 0; +} + +static void mon_event_config_write(void *info) +{ + struct mon_config_info *mon_info = info; + unsigned int index; + + index = mon_event_config_index_get(mon_info->evtid); + if (index == INVALID_CONFIG_INDEX) { + pr_warn_once("Invalid event id %d\n", mon_info->evtid); + return; + } + wrmsr(MSR_IA32_EVT_CFG_BASE + index, mon_info->mon_config, 0); +} + +static int mbm_config_write_domain(struct rdt_resource *r, + struct rdt_domain *d, u32 evtid, u32 val) +{ + 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. + */ + mon_info.evtid = evtid; + mondata_config_read(d, &mon_info); + if (mon_info.mon_config == val) + goto out; + + mon_info.mon_config = val; + + /* + * Update MSR_IA32_EVT_CFG_BASE MSR on one of the CPUs in the + * domain. The MSRs offset from MSR MSR_IA32_EVT_CFG_BASE + * are scoped at the domain level. Writing any of these MSRs + * on one CPU is observed by all the CPUs in the domain. + */ + smp_call_function_any(&d->cpu_mask, mon_event_config_write, + &mon_info, 1); + + /* + * When an Event Configuration is changed, the bandwidth counters + * for all RMIDs and Events will be cleared by the hardware. The + * hardware also sets MSR_IA32_QM_CTR.Unavailable (bit 62) for + * every RMID on the next read to any event for every RMID. + * Subsequent reads will have MSR_IA32_QM_CTR.Unavailable (bit 62) + * cleared while it is tracked by the hardware. Clear the + * mbm_local and mbm_total counts for all the RMIDs. + */ + resctrl_arch_reset_rmid_all(r, d); + +out: + return ret; +} + +static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) +{ + char *dom_str = NULL, *id_str; + unsigned long dom_id, val; + struct rdt_domain *d; + int ret = 0; + +next: + if (!tok || tok[0] == '\0') + return 0; + + /* Start processing the strings for each domain */ + dom_str = strim(strsep(&tok, ";")); + id_str = strsep(&dom_str, "="); + + if (!id_str || kstrtoul(id_str, 10, &dom_id)) { + rdt_last_cmd_puts("Missing '=' or non-numeric domain id\n"); + return -EINVAL; + } + + if (!dom_str || kstrtoul(dom_str, 16, &val)) { + rdt_last_cmd_puts("Non-numeric event configuration value\n"); + return -EINVAL; + } + + list_for_each_entry(d, &r->domains, list) { + if (d->id == dom_id) { + ret = mbm_config_write_domain(r, d, evtid, val); + if (ret) + return -EINVAL; + goto next; + } + } + + return -EINVAL; +} + +static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + struct rdt_resource *r = of->kn->parent->priv; + int ret; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + + mutex_lock(&rdtgroup_mutex); + + rdt_last_cmd_clear(); + + buf[nbytes - 1] = '\0'; + + ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID); + + mutex_unlock(&rdtgroup_mutex); + + return ret ?: nbytes; +} + +static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + struct rdt_resource *r = of->kn->parent->priv; + int ret; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + + mutex_lock(&rdtgroup_mutex); + + rdt_last_cmd_clear(); + + buf[nbytes - 1] = '\0'; + + ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID); + + mutex_unlock(&rdtgroup_mutex); + + return ret ?: nbytes; +} + /* rdtgroup information files for one cache resource. */ static struct rftype res_common_files[] = { { @@ -1520,6 +1761,20 @@ static struct rftype res_common_files[] = { .fflags = RF_MON_INFO | RFTYPE_RES_CACHE, }, { + .name = "mbm_total_bytes_config", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = mbm_total_bytes_config_show, + .write = mbm_total_bytes_config_write, + }, + { + .name = "mbm_local_bytes_config", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = mbm_local_bytes_config_show, + .write = mbm_local_bytes_config_write, + }, + { .name = "cpus", .mode = 0644, .kf_ops = &rdtgroup_kf_single_ops, @@ -1625,6 +1880,15 @@ void __init thread_throttle_mode_init(void) rft->fflags = RF_CTRL_INFO | RFTYPE_RES_MB; } +void __init mbm_config_rftype_init(const char *config) +{ + struct rftype *rft; + + rft = rdtgroup_get_rftype_by_name(config); + if (rft) + rft->fflags = RF_MON_INFO | RFTYPE_RES_CACHE; +} + /** * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file * @r: The resource group with which the file is associated. @@ -1866,13 +2130,9 @@ static int set_cache_qos_cfg(int level, bool enable) /* Pick one CPU from each domain instance to update MSR */ cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); } - cpu = get_cpu(); - /* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */ - if (cpumask_test_cpu(cpu, cpu_mask)) - update(&enable); - /* Update QOS_CFG MSR on all other cpus in cpu_mask. */ - smp_call_function_many(cpu_mask, update, &enable, 1); - put_cpu(); + + /* Update QOS_CFG MSR on all the CPUs in cpu_mask */ + on_each_cpu_mask(cpu_mask, update, &enable, 1); free_cpumask_var(cpu_mask); @@ -2349,7 +2609,7 @@ static int reset_all_ctrls(struct rdt_resource *r) struct msr_param msr_param; cpumask_var_t cpu_mask; struct rdt_domain *d; - int i, cpu; + int i; if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) return -ENOMEM; @@ -2370,13 +2630,9 @@ static int reset_all_ctrls(struct rdt_resource *r) for (i = 0; i < hw_res->num_closid; i++) hw_dom->ctrl_val[i] = r->default_ctrl; } - cpu = get_cpu(); - /* Update CBM on this cpu if it's in cpu_mask. */ - if (cpumask_test_cpu(cpu, cpu_mask)) - rdt_ctrl_update(&msr_param); - /* Update CBM on all other cpus in cpu_mask. */ - smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1); - put_cpu(); + + /* Update CBM on all the CPUs in cpu_mask */ + on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1); free_cpumask_var(cpu_mask); @@ -2855,7 +3111,8 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; - if (r->rid == RDT_RESOURCE_MBA) { + if (r->rid == RDT_RESOURCE_MBA || + r->rid == RDT_RESOURCE_SMBA) { rdtgroup_init_mba(r, rdtgrp->closid); if (is_mba_sc(r)) continue; diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index f53944fb8f7f..0dad49a09b7a 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -45,6 +45,8 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, + { X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 }, + { 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 }, { 0, 0, 0, 0, 0 } diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c index aa9b8b868867..262f5fb18d74 100644 --- a/arch/x86/kernel/cpu/sgx/driver.c +++ b/arch/x86/kernel/cpu/sgx/driver.c @@ -95,7 +95,7 @@ static int sgx_mmap(struct file *file, struct vm_area_struct *vma) return ret; vma->vm_ops = &sgx_vm_ops; - vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO; + vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO); vma->vm_private_data = encl; return 0; diff --git a/arch/x86/kernel/cpu/sgx/virt.c b/arch/x86/kernel/cpu/sgx/virt.c index 6a77a14eee38..c3e37eaec8ec 100644 --- a/arch/x86/kernel/cpu/sgx/virt.c +++ b/arch/x86/kernel/cpu/sgx/virt.c @@ -105,7 +105,7 @@ static int sgx_vepc_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_ops = &sgx_vepc_vm_ops; /* Don't copy VMA in fork() */ - vma->vm_flags |= VM_PFNMAP | VM_IO | VM_DONTDUMP | VM_DONTCOPY; + vm_flags_set(vma, VM_PFNMAP | VM_IO | VM_DONTDUMP | VM_DONTCOPY); vma->vm_private_data = vepc; return 0; diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c index 8009c8346d8f..b31ee4f1657a 100644 --- a/arch/x86/kernel/cpu/tsx.c +++ b/arch/x86/kernel/cpu/tsx.c @@ -11,6 +11,7 @@ #include <linux/cpufeature.h> #include <asm/cmdline.h> +#include <asm/cpu.h> #include "cpu.h" diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 02039ec3597d..11f83d07925e 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -143,7 +143,7 @@ static __init int parse_no_stealacc(char *arg) } early_param("no-steal-acc", parse_no_stealacc); -static unsigned long long notrace vmware_sched_clock(void) +static noinstr u64 vmware_sched_clock(void) { unsigned long long ns; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 305514431f26..cdd92ab43cda 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -37,7 +37,6 @@ #include <linux/kdebug.h> #include <asm/cpu.h> #include <asm/reboot.h> -#include <asm/virtext.h> #include <asm/intel_pt.h> #include <asm/crash.h> #include <asm/cmdline.h> @@ -81,15 +80,6 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) */ cpu_crash_vmclear_loaded_vmcss(); - /* Disable VMX or SVM if needed. - * - * We need to disable virtualization on all CPUs. - * Having VMX or SVM enabled on any CPU may break rebooting - * after the kdump kernel has finished its task. - */ - cpu_emergency_vmxoff(); - cpu_emergency_svm_disable(); - /* * Disable Intel PT to stop its logging */ @@ -148,12 +138,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs) */ cpu_crash_vmclear_loaded_vmcss(); - /* Booting kdump kernel with VMX or SVM enabled won't work, - * because (among other limitations) we can't disable paging - * with the virt flags. - */ - cpu_emergency_vmxoff(); - cpu_emergency_svm_disable(); + cpu_emergency_disable_virtualization(); /* * Disable Intel PT to stop its logging diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 9dac24680ff8..fb8cf953380d 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -53,7 +53,7 @@ * * Once the E820 map has been converted to the standard Linux memory layout * information its role stops - modifying it has no effect and does not get - * re-propagated. So itsmain role is a temporary bootstrap storage of firmware + * re-propagated. So its main role is a temporary bootstrap storage of firmware * specific memory layout data during early bootup. */ static struct e820_table e820_table_init __initdata; @@ -395,7 +395,7 @@ int __init e820__update_table(struct e820_table *table) /* Continue building up new map based on this information: */ if (current_type != last_type || e820_nomerge(current_type)) { - if (last_type != 0) { + if (last_type) { new_entries[new_nr_entries].size = change_point[chg_idx]->addr - last_addr; /* Move forward only if the new size was non-zero: */ if (new_entries[new_nr_entries].size != 0) @@ -403,7 +403,7 @@ int __init e820__update_table(struct e820_table *table) if (++new_nr_entries >= max_nr_entries) break; } - if (current_type != 0) { + if (current_type) { new_entries[new_nr_entries].addr = change_point[chg_idx]->addr; new_entries[new_nr_entries].type = current_type; last_addr = change_point[chg_idx]->addr; diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h index 958accf2ccf0..9fcfa5c4dad7 100644 --- a/arch/x86/kernel/fpu/context.h +++ b/arch/x86/kernel/fpu/context.h @@ -57,7 +57,7 @@ static inline void fpregs_restore_userregs(void) struct fpu *fpu = ¤t->thread.fpu; int cpu = smp_processor_id(); - if (WARN_ON_ONCE(current->flags & PF_KTHREAD)) + if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_IO_WORKER))) return; if (!fpregs_state_valid(fpu, cpu)) { diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 9baa89a8877d..caf33486dc5e 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -426,7 +426,7 @@ void kernel_fpu_begin_mask(unsigned int kfpu_mask) this_cpu_write(in_kernel_fpu, true); - if (!(current->flags & PF_KTHREAD) && + if (!(current->flags & (PF_KTHREAD | PF_IO_WORKER)) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); save_fpregs_to_fpstate(¤t->thread.fpu); @@ -853,12 +853,12 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr) * Initialize register state that may prevent from entering low-power idle. * This function will be invoked from the cpuidle driver only when needed. */ -void fpu_idle_fpregs(void) +noinstr void fpu_idle_fpregs(void) { /* Note: AMX_TILE being enabled implies XGETBV1 support */ if (cpu_feature_enabled(X86_FEATURE_AMX_TILE) && (xfeatures_in_use() & XFEATURE_MASK_XTILE)) { tile_release(); - fpregs_deactivate(¤t->thread.fpu); + __this_cpu_write(fpu_fpregs_owner_ctx, NULL); } } diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 71f336425e58..c8eb1ac5125a 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -1091,6 +1091,8 @@ int __init hpet_enable(void) if (!hpet_counting()) goto out_nohpet; + if (tsc_clocksource_watchdog_disabled()) + clocksource_hpet.flags |= CLOCK_SOURCE_MUST_VERIFY; clocksource_register_hz(&clocksource_hpet, (u32)hpet_freq); if (id & HPET_ID_LEGSUP) { diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index bbb0f737aab1..b01644c949b2 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -127,7 +127,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) set_debugreg(*dr7, 7); if (info->mask) - set_dr_addr_mask(info->mask, i); + amd_set_dr_addr_mask(info->mask, i); return 0; } @@ -166,7 +166,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) set_debugreg(dr7, 7); if (info->mask) - set_dr_addr_mask(0, i); + amd_set_dr_addr_mask(0, i); /* * Ensure the write to cpu_dr7 is after we've set the DR7 register. diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 3aa5304200c5..4d8aff05a509 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -114,6 +114,7 @@ static void make_8259A_irq(unsigned int irq) disable_irq_nosync(irq); io_apic_irqs &= ~(1<<irq); irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq); + irq_set_status_flags(irq, IRQ_LEVEL); enable_irq(irq); lapic_assign_legacy_vector(irq, true); } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index beb1bada1b0a..c683666876f1 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -65,8 +65,10 @@ void __init init_ISA_irqs(void) legacy_pic->init(0); - for (i = 0; i < nr_legacy_irqs(); i++) + for (i = 0; i < nr_legacy_irqs(); i++) { irq_set_chip_and_handler(i, chip, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); + } } void __init init_IRQ(void) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index b36f3c367cb2..f7f6042eb7e6 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -464,50 +464,26 @@ static void kprobe_emulate_call(struct kprobe *p, struct pt_regs *regs) } NOKPROBE_SYMBOL(kprobe_emulate_call); -static nokprobe_inline -void __kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs, bool cond) +static void kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs) { unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size; - if (cond) - ip += p->ainsn.rel32; + ip += p->ainsn.rel32; int3_emulate_jmp(regs, ip); } - -static void kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs) -{ - __kprobe_emulate_jmp(p, regs, true); -} NOKPROBE_SYMBOL(kprobe_emulate_jmp); -static const unsigned long jcc_mask[6] = { - [0] = X86_EFLAGS_OF, - [1] = X86_EFLAGS_CF, - [2] = X86_EFLAGS_ZF, - [3] = X86_EFLAGS_CF | X86_EFLAGS_ZF, - [4] = X86_EFLAGS_SF, - [5] = X86_EFLAGS_PF, -}; - static void kprobe_emulate_jcc(struct kprobe *p, struct pt_regs *regs) { - bool invert = p->ainsn.jcc.type & 1; - bool match; + unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size; - if (p->ainsn.jcc.type < 0xc) { - match = regs->flags & jcc_mask[p->ainsn.jcc.type >> 1]; - } else { - match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^ - ((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT); - if (p->ainsn.jcc.type >= 0xe) - match = match || (regs->flags & X86_EFLAGS_ZF); - } - __kprobe_emulate_jmp(p, regs, (match && !invert) || (!match && invert)); + int3_emulate_jcc(regs, p->ainsn.jcc.type, ip, p->ainsn.rel32); } NOKPROBE_SYMBOL(kprobe_emulate_jcc); static void kprobe_emulate_loop(struct kprobe *p, struct pt_regs *regs) { + unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size; bool match; if (p->ainsn.loop.type != 3) { /* LOOP* */ @@ -535,7 +511,9 @@ static void kprobe_emulate_loop(struct kprobe *p, struct pt_regs *regs) else if (p->ainsn.loop.type == 1) /* LOOPE */ match = match && (regs->flags & X86_EFLAGS_ZF); - __kprobe_emulate_jmp(p, regs, match); + if (match) + ip += p->ainsn.rel32; + int3_emulate_jmp(regs, ip); } NOKPROBE_SYMBOL(kprobe_emulate_loop); @@ -625,7 +603,7 @@ static int prepare_emulation(struct kprobe *p, struct insn *insn) /* 1 byte conditional jump */ p->ainsn.emulate_op = kprobe_emulate_jcc; p->ainsn.jcc.type = opcode & 0xf; - p->ainsn.rel32 = *(char *)insn->immediate.bytes; + p->ainsn.rel32 = insn->immediate.value; break; case 0x0f: opcode = insn->opcode.bytes[1]; @@ -659,17 +637,19 @@ static int prepare_emulation(struct kprobe *p, struct insn *insn) * is determined by the MOD/RM byte. */ opcode = insn->modrm.bytes[0]; - if ((opcode & 0x30) == 0x10) { - if ((opcode & 0x8) == 0x8) - return -EOPNOTSUPP; /* far call */ - /* call absolute, indirect */ + switch (X86_MODRM_REG(opcode)) { + case 0b010: /* FF /2, call near, absolute indirect */ p->ainsn.emulate_op = kprobe_emulate_call_indirect; - } else if ((opcode & 0x30) == 0x20) { - if ((opcode & 0x8) == 0x8) - return -EOPNOTSUPP; /* far jmp */ - /* jmp near absolute indirect */ + break; + case 0b100: /* FF /4, jmp near, absolute indirect */ p->ainsn.emulate_op = kprobe_emulate_jmp_indirect; - } else + break; + case 0b011: /* FF /3, call far, absolute indirect */ + case 0b101: /* FF /5, jmp far, absolute indirect */ + return -EOPNOTSUPP; + } + + if (!p->ainsn.emulate_op) break; if (insn->addr_bytes != sizeof(unsigned long)) @@ -990,20 +970,6 @@ int kprobe_int3_handler(struct pt_regs *regs) kprobe_post_process(p, regs, kcb); return 1; } - } - - if (*addr != INT3_INSN_OPCODE) { - /* - * The breakpoint instruction was removed right - * after we hit it. Another cpu has removed - * either a probepoint or a debugger breakpoint - * at this address. In either case, no further - * handling of this interrupt is appropriate. - * Back up over the (now missing) int3 and run - * the original instruction. - */ - regs->ip = (unsigned long)addr; - return 1; } /* else: not a kprobe fault; let the kernel handle it */ return 0; diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index e57e07b0edb6..57b0037d0a99 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -46,8 +46,8 @@ unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) /* This function only handles jump-optimized kprobe */ if (kp && kprobe_optimized(kp)) { op = container_of(kp, struct optimized_kprobe, kp); - /* If op->list is not empty, op is under optimizing */ - if (list_empty(&op->list)) + /* If op is optimized or under unoptimizing */ + if (list_empty(&op->list) || optprobe_queued_unopt(op)) goto found; } } @@ -353,7 +353,7 @@ int arch_check_optimized_kprobe(struct optimized_kprobe *op) for (i = 1; i < op->optinsn.size; i++) { p = get_kprobe(op->kp.addr + i); - if (p && !kprobe_disabled(p)) + if (p && !kprobe_disarmed(p)) return -EEXIST; } diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 16333ba1904b..0f35d44c56fe 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -71,12 +71,12 @@ static int kvm_set_wallclock(const struct timespec64 *now) return -ENODEV; } -static u64 kvm_clock_read(void) +static noinstr u64 kvm_clock_read(void) { u64 ret; preempt_disable_notrace(); - ret = pvclock_clocksource_read(this_cpu_pvti()); + ret = pvclock_clocksource_read_nowd(this_cpu_pvti()); preempt_enable_notrace(); return ret; } @@ -86,7 +86,7 @@ static u64 kvm_clock_get_cycles(struct clocksource *cs) return kvm_clock_read(); } -static u64 kvm_sched_clock_read(void) +static noinstr u64 kvm_sched_clock_read(void) { return kvm_clock_read() - kvm_sched_clock_offset; } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 705fb2a41d7d..84ad0e61ba6e 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -129,22 +129,27 @@ int apply_relocate(Elf32_Shdr *sechdrs, return 0; } #else /*X86_64*/ -static int __apply_relocate_add(Elf64_Shdr *sechdrs, +static int __write_relocate_add(Elf64_Shdr *sechdrs, const char *strtab, unsigned int symindex, unsigned int relsec, struct module *me, - void *(*write)(void *dest, const void *src, size_t len)) + void *(*write)(void *dest, const void *src, size_t len), + bool apply) { unsigned int i; Elf64_Rela *rel = (void *)sechdrs[relsec].sh_addr; Elf64_Sym *sym; void *loc; u64 val; + u64 zero = 0ULL; - DEBUGP("Applying relocate section %u to %u\n", + DEBUGP("%s relocate section %u to %u\n", + apply ? "Applying" : "Clearing", relsec, sechdrs[relsec].sh_info); for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { + size_t size; + /* This is where to make the change */ loc = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr + rel[i].r_offset; @@ -162,56 +167,53 @@ static int __apply_relocate_add(Elf64_Shdr *sechdrs, switch (ELF64_R_TYPE(rel[i].r_info)) { case R_X86_64_NONE: - break; + continue; /* nothing to write */ case R_X86_64_64: - if (*(u64 *)loc != 0) - goto invalid_relocation; - write(loc, &val, 8); + size = 8; break; case R_X86_64_32: - if (*(u32 *)loc != 0) - goto invalid_relocation; - write(loc, &val, 4); - if (val != *(u32 *)loc) + if (val != *(u32 *)&val) goto overflow; + size = 4; break; case R_X86_64_32S: - if (*(s32 *)loc != 0) - goto invalid_relocation; - write(loc, &val, 4); - if ((s64)val != *(s32 *)loc) + if ((s64)val != *(s32 *)&val) goto overflow; + size = 4; break; case R_X86_64_PC32: case R_X86_64_PLT32: - if (*(u32 *)loc != 0) - goto invalid_relocation; val -= (u64)loc; - write(loc, &val, 4); -#if 0 - if ((s64)val != *(s32 *)loc) - goto overflow; -#endif + size = 4; break; case R_X86_64_PC64: - if (*(u64 *)loc != 0) - goto invalid_relocation; val -= (u64)loc; - write(loc, &val, 8); + size = 8; break; default: pr_err("%s: Unknown rela relocation: %llu\n", me->name, ELF64_R_TYPE(rel[i].r_info)); return -ENOEXEC; } + + if (apply) { + if (memcmp(loc, &zero, size)) { + pr_err("x86/modules: Invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n", + (int)ELF64_R_TYPE(rel[i].r_info), loc, val); + return -ENOEXEC; + } + write(loc, &val, size); + } else { + if (memcmp(loc, &val, size)) { + pr_warn("x86/modules: Invalid relocation target, existing value does not match expected value for type %d, loc %p, val %Lx\n", + (int)ELF64_R_TYPE(rel[i].r_info), loc, val); + return -ENOEXEC; + } + write(loc, &zero, size); + } } return 0; -invalid_relocation: - pr_err("x86/modules: Skipping invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n", - (int)ELF64_R_TYPE(rel[i].r_info), loc, val); - return -ENOEXEC; - overflow: pr_err("overflow in relocation type %d val %Lx\n", (int)ELF64_R_TYPE(rel[i].r_info), val); @@ -220,11 +222,12 @@ overflow: return -ENOEXEC; } -int apply_relocate_add(Elf64_Shdr *sechdrs, - const char *strtab, - unsigned int symindex, - unsigned int relsec, - struct module *me) +static int write_relocate_add(Elf64_Shdr *sechdrs, + const char *strtab, + unsigned int symindex, + unsigned int relsec, + struct module *me, + bool apply) { int ret; bool early = me->state == MODULE_STATE_UNFORMED; @@ -235,8 +238,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, mutex_lock(&text_mutex); } - ret = __apply_relocate_add(sechdrs, strtab, symindex, relsec, me, - write); + ret = __write_relocate_add(sechdrs, strtab, symindex, relsec, me, + write, apply); if (!early) { text_poke_sync(); @@ -246,6 +249,26 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, return ret; } +int apply_relocate_add(Elf64_Shdr *sechdrs, + const char *strtab, + unsigned int symindex, + unsigned int relsec, + struct module *me) +{ + return write_relocate_add(sechdrs, strtab, symindex, relsec, me, true); +} + +#ifdef CONFIG_LIVEPATCH +void clear_relocate_add(Elf64_Shdr *sechdrs, + const char *strtab, + unsigned int symindex, + unsigned int relsec, + struct module *me) +{ + write_relocate_add(sechdrs, strtab, symindex, relsec, me, false); +} +#endif + #endif int module_finalize(const Elf_Ehdr *hdr, diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index cec0bfa3bc04..776f4b1e395b 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -69,6 +69,15 @@ struct nmi_stats { unsigned int unknown; unsigned int external; unsigned int swallow; + unsigned long recv_jiffies; + unsigned long idt_seq; + unsigned long idt_nmi_seq; + unsigned long idt_ignored; + atomic_long_t idt_calls; + unsigned long idt_seq_snap; + unsigned long idt_nmi_seq_snap; + unsigned long idt_ignored_snap; + long idt_calls_snap; }; static DEFINE_PER_CPU(struct nmi_stats, nmi_stats); @@ -479,12 +488,15 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7); DEFINE_IDTENTRY_RAW(exc_nmi) { irqentry_state_t irq_state; + struct nmi_stats *nsp = this_cpu_ptr(&nmi_stats); /* * Re-enable NMIs right here when running as an SEV-ES guest. This might * cause nested NMIs, but those can be handled safely. */ sev_es_nmi_complete(); + if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) + arch_atomic_long_inc(&nsp->idt_calls); if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) return; @@ -495,6 +507,11 @@ DEFINE_IDTENTRY_RAW(exc_nmi) } this_cpu_write(nmi_state, NMI_EXECUTING); this_cpu_write(nmi_cr2, read_cr2()); + if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) { + WRITE_ONCE(nsp->idt_seq, nsp->idt_seq + 1); + WARN_ON_ONCE(!(nsp->idt_seq & 0x1)); + WRITE_ONCE(nsp->recv_jiffies, jiffies); + } nmi_restart: /* @@ -509,8 +526,19 @@ nmi_restart: inc_irq_stat(__nmi_count); - if (!ignore_nmis) + if (IS_ENABLED(CONFIG_NMI_CHECK_CPU) && ignore_nmis) { + WRITE_ONCE(nsp->idt_ignored, nsp->idt_ignored + 1); + } else if (!ignore_nmis) { + if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) { + WRITE_ONCE(nsp->idt_nmi_seq, nsp->idt_nmi_seq + 1); + WARN_ON_ONCE(!(nsp->idt_nmi_seq & 0x1)); + } default_do_nmi(regs); + if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) { + WRITE_ONCE(nsp->idt_nmi_seq, nsp->idt_nmi_seq + 1); + WARN_ON_ONCE(nsp->idt_nmi_seq & 0x1); + } + } irqentry_nmi_exit(regs, irq_state); @@ -525,16 +553,94 @@ nmi_restart: if (user_mode(regs)) mds_user_clear_cpu_buffers(); + if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) { + WRITE_ONCE(nsp->idt_seq, nsp->idt_seq + 1); + WARN_ON_ONCE(nsp->idt_seq & 0x1); + WRITE_ONCE(nsp->recv_jiffies, jiffies); + } } -#if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL) -DEFINE_IDTENTRY_RAW(exc_nmi_noist) +#if IS_ENABLED(CONFIG_KVM_INTEL) +DEFINE_IDTENTRY_RAW(exc_nmi_kvm_vmx) { exc_nmi(regs); } -#endif #if IS_MODULE(CONFIG_KVM_INTEL) -EXPORT_SYMBOL_GPL(asm_exc_nmi_noist); +EXPORT_SYMBOL_GPL(asm_exc_nmi_kvm_vmx); +#endif +#endif + +#ifdef CONFIG_NMI_CHECK_CPU + +static char *nmi_check_stall_msg[] = { +/* */ +/* +--------- nsp->idt_seq_snap & 0x1: CPU is in NMI handler. */ +/* | +------ cpu_is_offline(cpu) */ +/* | | +--- nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls): */ +/* | | | NMI handler has been invoked. */ +/* | | | */ +/* V V V */ +/* 0 0 0 */ "NMIs are not reaching exc_nmi() handler", +/* 0 0 1 */ "exc_nmi() handler is ignoring NMIs", +/* 0 1 0 */ "CPU is offline and NMIs are not reaching exc_nmi() handler", +/* 0 1 1 */ "CPU is offline and exc_nmi() handler is legitimately ignoring NMIs", +/* 1 0 0 */ "CPU is in exc_nmi() handler and no further NMIs are reaching handler", +/* 1 0 1 */ "CPU is in exc_nmi() handler which is legitimately ignoring NMIs", +/* 1 1 0 */ "CPU is offline in exc_nmi() handler and no more NMIs are reaching exc_nmi() handler", +/* 1 1 1 */ "CPU is offline in exc_nmi() handler which is legitimately ignoring NMIs", +}; + +void nmi_backtrace_stall_snap(const struct cpumask *btp) +{ + int cpu; + struct nmi_stats *nsp; + + for_each_cpu(cpu, btp) { + nsp = per_cpu_ptr(&nmi_stats, cpu); + nsp->idt_seq_snap = READ_ONCE(nsp->idt_seq); + nsp->idt_nmi_seq_snap = READ_ONCE(nsp->idt_nmi_seq); + nsp->idt_ignored_snap = READ_ONCE(nsp->idt_ignored); + nsp->idt_calls_snap = atomic_long_read(&nsp->idt_calls); + } +} + +void nmi_backtrace_stall_check(const struct cpumask *btp) +{ + int cpu; + int idx; + unsigned long nmi_seq; + unsigned long j = jiffies; + char *modp; + char *msgp; + char *msghp; + struct nmi_stats *nsp; + + for_each_cpu(cpu, btp) { + nsp = per_cpu_ptr(&nmi_stats, cpu); + modp = ""; + msghp = ""; + 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) | + (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) + msghp = " (CPU exited one NMI handler function)"; + } + 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)); + } +} + #endif void stop_nmi(void) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 327757afb027..42e182868873 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -32,6 +32,7 @@ #include <asm/special_insns.h> #include <asm/tlb.h> #include <asm/io_bitmap.h> +#include <asm/gsseg.h> /* * nop stub, which must not clobber anything *including the stack* to @@ -216,6 +217,11 @@ static noinstr void pv_native_set_debugreg(int regno, unsigned long val) native_set_debugreg(regno, val); } +noinstr void pv_native_wbinvd(void) +{ + native_wbinvd(); +} + static noinstr void pv_native_irq_enable(void) { native_irq_enable(); @@ -225,6 +231,11 @@ static noinstr void pv_native_irq_disable(void) { native_irq_disable(); } + +static noinstr void pv_native_safe_halt(void) +{ + native_safe_halt(); +} #endif enum paravirt_lazy_mode paravirt_get_lazy_mode(void) @@ -256,7 +267,7 @@ struct paravirt_patch_template pv_ops = { .cpu.read_cr0 = native_read_cr0, .cpu.write_cr0 = native_write_cr0, .cpu.write_cr4 = native_write_cr4, - .cpu.wbinvd = native_wbinvd, + .cpu.wbinvd = pv_native_wbinvd, .cpu.read_msr = native_read_msr, .cpu.write_msr = native_write_msr, .cpu.read_msr_safe = native_read_msr_safe, @@ -290,7 +301,7 @@ struct paravirt_patch_template pv_ops = { .irq.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl), .irq.irq_disable = __PV_IS_CALLEE_SAVE(pv_native_irq_disable), .irq.irq_enable = __PV_IS_CALLEE_SAVE(pv_native_irq_enable), - .irq.safe_halt = native_safe_halt, + .irq.safe_halt = pv_native_safe_halt, .irq.halt = native_halt, #endif /* CONFIG_PARAVIRT_XXL */ diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 40d156a31676..b650cde3f64d 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -24,6 +24,7 @@ #include <linux/cpuidle.h> #include <linux/acpi.h> #include <linux/elf-randomize.h> +#include <linux/static_call.h> #include <trace/events/power.h> #include <linux/hw_breakpoint.h> #include <asm/cpu.h> @@ -694,7 +695,24 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p) unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE; EXPORT_SYMBOL(boot_option_idle_override); -static void (*x86_idle)(void); +/* + * We use this if we don't have any better idle routine.. + */ +void __cpuidle default_idle(void) +{ + raw_safe_halt(); + raw_local_irq_disable(); +} +#if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE) +EXPORT_SYMBOL(default_idle); +#endif + +DEFINE_STATIC_CALL_NULL(x86_idle, default_idle); + +static bool x86_idle_set(void) +{ + return !!static_call_query(x86_idle); +} #ifndef CONFIG_SMP static inline void play_dead(void) @@ -717,28 +735,18 @@ void arch_cpu_idle_dead(void) /* * Called from the generic idle code. */ -void arch_cpu_idle(void) -{ - x86_idle(); -} - -/* - * We use this if we don't have any better idle routine.. - */ -void __cpuidle default_idle(void) +void __cpuidle arch_cpu_idle(void) { - raw_safe_halt(); + static_call(x86_idle)(); } -#if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE) -EXPORT_SYMBOL(default_idle); -#endif +EXPORT_SYMBOL_GPL(arch_cpu_idle); #ifdef CONFIG_XEN bool xen_set_default_idle(void) { - bool ret = !!x86_idle; + bool ret = x86_idle_set(); - x86_idle = default_idle; + static_call_update(x86_idle, default_idle); return ret; } @@ -800,13 +808,7 @@ static void amd_e400_idle(void) default_idle(); - /* - * The switch back from broadcast mode needs to be called with - * interrupts disabled. - */ - raw_local_irq_disable(); tick_broadcast_exit(); - raw_local_irq_enable(); } /* @@ -864,12 +866,10 @@ static __cpuidle void mwait_idle(void) } __monitor((void *)¤t_thread_info()->flags, 0, 0); - if (!need_resched()) + if (!need_resched()) { __sti_mwait(0, 0); - else - raw_local_irq_enable(); - } else { - raw_local_irq_enable(); + raw_local_irq_disable(); + } } __current_clr_polling(); } @@ -880,20 +880,20 @@ void select_idle_routine(const struct cpuinfo_x86 *c) if (boot_option_idle_override == IDLE_POLL && smp_num_siblings > 1) pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); #endif - if (x86_idle || boot_option_idle_override == IDLE_POLL) + if (x86_idle_set() || boot_option_idle_override == IDLE_POLL) return; if (boot_cpu_has_bug(X86_BUG_AMD_E400)) { pr_info("using AMD E400 aware idle routine\n"); - x86_idle = amd_e400_idle; + static_call_update(x86_idle, amd_e400_idle); } else if (prefer_mwait_c1_over_halt(c)) { pr_info("using mwait in idle threads\n"); - x86_idle = mwait_idle; + static_call_update(x86_idle, mwait_idle); } else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { pr_info("using TDX aware idle routine\n"); - x86_idle = tdx_safe_halt; + static_call_update(x86_idle, tdx_safe_halt); } else - x86_idle = default_idle; + static_call_update(x86_idle, default_idle); } void amd_e400_c1e_apic_setup(void) @@ -946,7 +946,7 @@ static int __init idle_setup(char *str) * To continue to load the CPU idle driver, don't touch * the boot_option_idle_override. */ - x86_idle = default_idle; + static_call_update(x86_idle, default_idle); boot_option_idle_override = IDLE_HALT; } else if (!strcmp(str, "nomwait")) { /* diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index eda37df016f0..56acf53a782a 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -64,7 +64,8 @@ u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src) return flags & valid_flags; } -u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) +static __always_inline +u64 __pvclock_clocksource_read(struct pvclock_vcpu_time_info *src, bool dowd) { unsigned version; u64 ret; @@ -77,7 +78,7 @@ u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) flags = src->flags; } while (pvclock_read_retry(src, version)); - if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) { + if (dowd && unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) { src->flags &= ~PVCLOCK_GUEST_STOPPED; pvclock_touch_watchdogs(); } @@ -100,16 +101,25 @@ u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) * updating at the same time, and one of them could be slightly behind, * making the assumption that last_value always go forward fail to hold. */ - last = atomic64_read(&last_value); + last = arch_atomic64_read(&last_value); do { - if (ret < last) + if (ret <= last) return last; - last = atomic64_cmpxchg(&last_value, last, ret); - } while (unlikely(last != ret)); + } while (!arch_atomic64_try_cmpxchg(&last_value, &last, ret)); return ret; } +u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) +{ + return __pvclock_clocksource_read(src, true); +} + +noinstr u64 pvclock_clocksource_read_nowd(struct pvclock_vcpu_time_info *src) +{ + return __pvclock_clocksource_read(src, false); +} + void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, struct pvclock_vcpu_time_info *vcpu_time, struct timespec64 *ts) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index c3636ea4aa71..d03c551defcc 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -528,33 +528,29 @@ static inline void kb_wait(void) } } -static void vmxoff_nmi(int cpu, struct pt_regs *regs) -{ - cpu_emergency_vmxoff(); -} +static inline void nmi_shootdown_cpus_on_restart(void); -/* Use NMIs as IPIs to tell all CPUs to disable virtualization */ -static void emergency_vmx_disable_all(void) +static void emergency_reboot_disable_virtualization(void) { /* Just make sure we won't change CPUs while doing this */ local_irq_disable(); /* - * Disable VMX on all CPUs before rebooting, otherwise we risk hanging - * the machine, because the CPU blocks INIT when it's in VMX root. + * Disable virtualization on all CPUs before rebooting to avoid hanging + * the system, as VMX and SVM block INIT when running in the host. * * We can't take any locks and we may be on an inconsistent state, so - * use NMIs as IPIs to tell the other CPUs to exit VMX root and halt. + * use NMIs as IPIs to tell the other CPUs to disable VMX/SVM and halt. * - * Do the NMI shootdown even if VMX if off on _this_ CPU, as that - * doesn't prevent a different CPU from being in VMX root operation. + * Do the NMI shootdown even if virtualization is off on _this_ CPU, as + * other CPUs may have virtualization enabled. */ - if (cpu_has_vmx()) { - /* Safely force _this_ CPU out of VMX root operation. */ - __cpu_emergency_vmxoff(); + if (cpu_has_vmx() || cpu_has_svm(NULL)) { + /* Safely force _this_ CPU out of VMX/SVM operation. */ + cpu_emergency_disable_virtualization(); - /* Halt and exit VMX root operation on the other CPUs. */ - nmi_shootdown_cpus(vmxoff_nmi); + /* Disable VMX/SVM and halt on other CPUs. */ + nmi_shootdown_cpus_on_restart(); } } @@ -590,7 +586,7 @@ static void native_machine_emergency_restart(void) unsigned short mode; if (reboot_emergency) - emergency_vmx_disable_all(); + emergency_reboot_disable_virtualization(); tboot_shutdown(TB_SHUTDOWN_REBOOT); @@ -795,6 +791,17 @@ void machine_crash_shutdown(struct pt_regs *regs) /* This is the CPU performing the emergency shutdown work. */ int crashing_cpu = -1; +/* + * Disable virtualization, i.e. VMX or SVM, to ensure INIT is recognized during + * reboot. VMX blocks INIT if the CPU is post-VMXON, and SVM blocks INIT if + * GIF=0, i.e. if the crash occurred between CLGI and STGI. + */ +void cpu_emergency_disable_virtualization(void) +{ + cpu_emergency_vmxoff(); + cpu_emergency_svm_disable(); +} + #if defined(CONFIG_SMP) static nmi_shootdown_cb shootdown_callback; @@ -817,7 +824,14 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) return NMI_HANDLED; local_irq_disable(); - shootdown_callback(cpu, regs); + if (shootdown_callback) + shootdown_callback(cpu, regs); + + /* + * Prepare the CPU for reboot _after_ invoking the callback so that the + * callback can safely use virtualization instructions, e.g. VMCLEAR. + */ + cpu_emergency_disable_virtualization(); atomic_dec(&waiting_for_crash_ipi); /* Assume hlt works */ @@ -828,18 +842,32 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) return NMI_HANDLED; } -/* - * Halt all other CPUs, calling the specified function on each of them +/** + * nmi_shootdown_cpus - Stop other CPUs via NMI + * @callback: Optional callback to be invoked from the NMI handler + * + * The NMI handler on the remote CPUs invokes @callback, if not + * NULL, first and then disables virtualization to ensure that + * INIT is recognized during reboot. * - * This function can be used to halt all other CPUs on crash - * or emergency reboot time. The function passed as parameter - * will be called inside a NMI handler on all CPUs. + * nmi_shootdown_cpus() can only be invoked once. After the first + * invocation all other CPUs are stuck in crash_nmi_callback() and + * cannot respond to a second NMI. */ void nmi_shootdown_cpus(nmi_shootdown_cb callback) { unsigned long msecs; + local_irq_disable(); + /* + * Avoid certain doom if a shootdown already occurred; re-registering + * the NMI handler will cause list corruption, modifying the callback + * will do who knows what, etc... + */ + if (WARN_ON_ONCE(crash_ipi_issued)) + return; + /* Make a note of crashing cpu. Will be used in NMI callback. */ crashing_cpu = safe_smp_processor_id(); @@ -867,7 +895,17 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) msecs--; } - /* Leave the nmi callback set */ + /* + * Leave the nmi callback set, shootdown is a one-time thing. Clearing + * the callback could result in a NULL pointer dereference if a CPU + * (finally) responds after the timeout expires. + */ +} + +static inline void nmi_shootdown_cpus_on_restart(void) +{ + if (!crash_ipi_issued) + nmi_shootdown_cpus(NULL); } /* @@ -897,6 +935,8 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) /* No other CPUs to shoot down */ } +static inline void nmi_shootdown_cpus_on_restart(void) { } + void run_crash_ipi_callback(struct pt_regs *regs) { } diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 349046434513..1309b9b05338 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -138,15 +138,12 @@ static __init int add_rtc_cmos(void) static const char * const ids[] __initconst = { "PNP0b00", "PNP0b01", "PNP0b02", }; struct pnp_dev *dev; - struct pnp_id *id; int i; pnp_for_each_dev(dev) { - for (id = dev->id; id; id = id->next) { - for (i = 0; i < ARRAY_SIZE(ids); i++) { - if (compare_pnp_id(id, ids[i]) != 0) - return 0; - } + for (i = 0; i < ARRAY_SIZE(ids); i++) { + if (compare_pnp_id(dev->id, ids[i]) != 0) + return 0; } } #endif diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 88188549647c..16babff771bd 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -114,11 +114,6 @@ static struct resource bss_resource = { #ifdef CONFIG_X86_32 /* CPU data as detected by the assembly code in head_32.S */ struct cpuinfo_x86 new_cpu_data; - -/* Common CPU data for all CPUs */ -struct cpuinfo_x86 boot_cpu_data __read_mostly; -EXPORT_SYMBOL(boot_cpu_data); - unsigned int def_to_bigsmp; struct apm_info apm_info; @@ -132,11 +127,10 @@ EXPORT_SYMBOL(ist_info); struct ist_info ist_info; #endif -#else -struct cpuinfo_x86 boot_cpu_data __read_mostly; -EXPORT_SYMBOL(boot_cpu_data); #endif +struct cpuinfo_x86 boot_cpu_data __read_mostly; +EXPORT_SYMBOL(boot_cpu_data); #if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64) __visible unsigned long mmu_cr4_features __ro_after_init; diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 1504eb8d25aa..004cb30b7419 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -360,7 +360,7 @@ static bool strict_sigaltstack_size __ro_after_init = false; static int __init strict_sas_size(char *arg) { - return kstrtobool(arg, &strict_sigaltstack_size); + return kstrtobool(arg, &strict_sigaltstack_size) == 0; } __setup("strict_sas_size", strict_sas_size); diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c index 2553136cf39b..9027fc088f97 100644 --- a/arch/x86/kernel/signal_32.c +++ b/arch/x86/kernel/signal_32.c @@ -31,6 +31,7 @@ #include <asm/sigframe.h> #include <asm/sighandling.h> #include <asm/smap.h> +#include <asm/gsseg.h> #ifdef CONFIG_IA32_EMULATION #include <asm/ia32_unistd.h> @@ -54,12 +55,14 @@ static inline void reload_segments(struct sigcontext_32 *sc) } #define sigset32_t compat_sigset_t +#define siginfo32_t compat_siginfo_t #define restore_altstack32 compat_restore_altstack #define unsafe_save_altstack32 unsafe_compat_save_altstack #else #define sigset32_t sigset_t +#define siginfo32_t siginfo_t #define __NR_ia32_sigreturn __NR_sigreturn #define __NR_ia32_rt_sigreturn __NR_rt_sigreturn #define restore_altstack32 restore_altstack @@ -377,3 +380,128 @@ Efault: user_access_end(); return -EFAULT; } + +/* + * The siginfo_t structure and handing code is very easy + * to break in several ways. It must always be updated when new + * updates are made to the main siginfo_t, and + * copy_siginfo_to_user32() must be updated when the + * (arch-independent) copy_siginfo_to_user() is updated. + * + * It is also easy to put a new member in the siginfo_t + * which has implicit alignment which can move internal structure + * alignment around breaking the ABI. This can happen if you, + * for instance, put a plain 64-bit value in there. + */ + +/* +* If adding a new si_code, there is probably new data in +* the siginfo. Make sure folks bumping the si_code +* limits also have to look at this code. Make sure any +* new fields are handled in copy_siginfo_to_user32()! +*/ +static_assert(NSIGILL == 11); +static_assert(NSIGFPE == 15); +static_assert(NSIGSEGV == 9); +static_assert(NSIGBUS == 5); +static_assert(NSIGTRAP == 6); +static_assert(NSIGCHLD == 6); +static_assert(NSIGSYS == 2); + +/* This is part of the ABI and can never change in size: */ +static_assert(sizeof(siginfo32_t) == 128); + +/* This is a part of the ABI and can never change in alignment */ +static_assert(__alignof__(siginfo32_t) == 4); + +/* +* The offsets of all the (unioned) si_fields are fixed +* in the ABI, of course. Make sure none of them ever +* move and are always at the beginning: +*/ +static_assert(offsetof(siginfo32_t, _sifields) == 3 * sizeof(int)); + +static_assert(offsetof(siginfo32_t, si_signo) == 0); +static_assert(offsetof(siginfo32_t, si_errno) == 4); +static_assert(offsetof(siginfo32_t, si_code) == 8); + +/* +* Ensure that the size of each si_field never changes. +* If it does, it is a sign that the +* copy_siginfo_to_user32() code below needs to updated +* along with the size in the CHECK_SI_SIZE(). +* +* We repeat this check for both the generic and compat +* siginfos. +* +* Note: it is OK for these to grow as long as the whole +* structure stays within the padding size (checked +* above). +*/ + +#define CHECK_SI_OFFSET(name) \ + static_assert(offsetof(siginfo32_t, _sifields) == \ + offsetof(siginfo32_t, _sifields.name)) + +#define CHECK_SI_SIZE(name, size) \ + static_assert(sizeof_field(siginfo32_t, _sifields.name) == size) + +CHECK_SI_OFFSET(_kill); +CHECK_SI_SIZE (_kill, 2*sizeof(int)); +static_assert(offsetof(siginfo32_t, si_pid) == 0xC); +static_assert(offsetof(siginfo32_t, si_uid) == 0x10); + +CHECK_SI_OFFSET(_timer); +#ifdef CONFIG_COMPAT +/* compat_siginfo_t doesn't have si_sys_private */ +CHECK_SI_SIZE (_timer, 3*sizeof(int)); +#else +CHECK_SI_SIZE (_timer, 4*sizeof(int)); +#endif +static_assert(offsetof(siginfo32_t, si_tid) == 0x0C); +static_assert(offsetof(siginfo32_t, si_overrun) == 0x10); +static_assert(offsetof(siginfo32_t, si_value) == 0x14); + +CHECK_SI_OFFSET(_rt); +CHECK_SI_SIZE (_rt, 3*sizeof(int)); +static_assert(offsetof(siginfo32_t, si_pid) == 0x0C); +static_assert(offsetof(siginfo32_t, si_uid) == 0x10); +static_assert(offsetof(siginfo32_t, si_value) == 0x14); + +CHECK_SI_OFFSET(_sigchld); +CHECK_SI_SIZE (_sigchld, 5*sizeof(int)); +static_assert(offsetof(siginfo32_t, si_pid) == 0x0C); +static_assert(offsetof(siginfo32_t, si_uid) == 0x10); +static_assert(offsetof(siginfo32_t, si_status) == 0x14); +static_assert(offsetof(siginfo32_t, si_utime) == 0x18); +static_assert(offsetof(siginfo32_t, si_stime) == 0x1C); + +CHECK_SI_OFFSET(_sigfault); +CHECK_SI_SIZE (_sigfault, 4*sizeof(int)); +static_assert(offsetof(siginfo32_t, si_addr) == 0x0C); + +static_assert(offsetof(siginfo32_t, si_trapno) == 0x10); + +static_assert(offsetof(siginfo32_t, si_addr_lsb) == 0x10); + +static_assert(offsetof(siginfo32_t, si_lower) == 0x14); +static_assert(offsetof(siginfo32_t, si_upper) == 0x18); + +static_assert(offsetof(siginfo32_t, si_pkey) == 0x14); + +static_assert(offsetof(siginfo32_t, si_perf_data) == 0x10); +static_assert(offsetof(siginfo32_t, si_perf_type) == 0x14); +static_assert(offsetof(siginfo32_t, si_perf_flags) == 0x18); + +CHECK_SI_OFFSET(_sigpoll); +CHECK_SI_SIZE (_sigpoll, 2*sizeof(int)); +static_assert(offsetof(siginfo32_t, si_band) == 0x0C); +static_assert(offsetof(siginfo32_t, si_fd) == 0x10); + +CHECK_SI_OFFSET(_sigsys); +CHECK_SI_SIZE (_sigsys, 3*sizeof(int)); +static_assert(offsetof(siginfo32_t, si_call_addr) == 0x0C); +static_assert(offsetof(siginfo32_t, si_syscall) == 0x10); +static_assert(offsetof(siginfo32_t, si_arch) == 0x14); + +/* any new si_fields should be added here */ diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index ff9c55064223..13a1e6083837 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -381,3 +381,130 @@ badframe: return 0; } #endif /* CONFIG_X86_X32_ABI */ + +#ifdef CONFIG_COMPAT +void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact) +{ + if (!act) + return; + + if (in_ia32_syscall()) + act->sa.sa_flags |= SA_IA32_ABI; + if (in_x32_syscall()) + act->sa.sa_flags |= SA_X32_ABI; +} +#endif /* CONFIG_COMPAT */ + +/* +* If adding a new si_code, there is probably new data in +* the siginfo. Make sure folks bumping the si_code +* limits also have to look at this code. Make sure any +* new fields are handled in copy_siginfo_to_user32()! +*/ +static_assert(NSIGILL == 11); +static_assert(NSIGFPE == 15); +static_assert(NSIGSEGV == 9); +static_assert(NSIGBUS == 5); +static_assert(NSIGTRAP == 6); +static_assert(NSIGCHLD == 6); +static_assert(NSIGSYS == 2); + +/* This is part of the ABI and can never change in size: */ +static_assert(sizeof(siginfo_t) == 128); + +/* This is a part of the ABI and can never change in alignment */ +static_assert(__alignof__(siginfo_t) == 8); + +/* +* The offsets of all the (unioned) si_fields are fixed +* in the ABI, of course. Make sure none of them ever +* move and are always at the beginning: +*/ +static_assert(offsetof(siginfo_t, si_signo) == 0); +static_assert(offsetof(siginfo_t, si_errno) == 4); +static_assert(offsetof(siginfo_t, si_code) == 8); + +/* +* Ensure that the size of each si_field never changes. +* If it does, it is a sign that the +* copy_siginfo_to_user32() code below needs to updated +* along with the size in the CHECK_SI_SIZE(). +* +* We repeat this check for both the generic and compat +* siginfos. +* +* Note: it is OK for these to grow as long as the whole +* structure stays within the padding size (checked +* above). +*/ + +#define CHECK_SI_OFFSET(name) \ + static_assert(offsetof(siginfo_t, _sifields) == \ + offsetof(siginfo_t, _sifields.name)) +#define CHECK_SI_SIZE(name, size) \ + static_assert(sizeof_field(siginfo_t, _sifields.name) == size) + +CHECK_SI_OFFSET(_kill); +CHECK_SI_SIZE (_kill, 2*sizeof(int)); +static_assert(offsetof(siginfo_t, si_pid) == 0x10); +static_assert(offsetof(siginfo_t, si_uid) == 0x14); + +CHECK_SI_OFFSET(_timer); +CHECK_SI_SIZE (_timer, 6*sizeof(int)); +static_assert(offsetof(siginfo_t, si_tid) == 0x10); +static_assert(offsetof(siginfo_t, si_overrun) == 0x14); +static_assert(offsetof(siginfo_t, si_value) == 0x18); + +CHECK_SI_OFFSET(_rt); +CHECK_SI_SIZE (_rt, 4*sizeof(int)); +static_assert(offsetof(siginfo_t, si_pid) == 0x10); +static_assert(offsetof(siginfo_t, si_uid) == 0x14); +static_assert(offsetof(siginfo_t, si_value) == 0x18); + +CHECK_SI_OFFSET(_sigchld); +CHECK_SI_SIZE (_sigchld, 8*sizeof(int)); +static_assert(offsetof(siginfo_t, si_pid) == 0x10); +static_assert(offsetof(siginfo_t, si_uid) == 0x14); +static_assert(offsetof(siginfo_t, si_status) == 0x18); +static_assert(offsetof(siginfo_t, si_utime) == 0x20); +static_assert(offsetof(siginfo_t, si_stime) == 0x28); + +#ifdef CONFIG_X86_X32_ABI +/* no _sigchld_x32 in the generic siginfo_t */ +static_assert(sizeof_field(compat_siginfo_t, _sifields._sigchld_x32) == + 7*sizeof(int)); +static_assert(offsetof(compat_siginfo_t, _sifields) == + offsetof(compat_siginfo_t, _sifields._sigchld_x32)); +static_assert(offsetof(compat_siginfo_t, _sifields._sigchld_x32._utime) == 0x18); +static_assert(offsetof(compat_siginfo_t, _sifields._sigchld_x32._stime) == 0x20); +#endif + +CHECK_SI_OFFSET(_sigfault); +CHECK_SI_SIZE (_sigfault, 8*sizeof(int)); +static_assert(offsetof(siginfo_t, si_addr) == 0x10); + +static_assert(offsetof(siginfo_t, si_trapno) == 0x18); + +static_assert(offsetof(siginfo_t, si_addr_lsb) == 0x18); + +static_assert(offsetof(siginfo_t, si_lower) == 0x20); +static_assert(offsetof(siginfo_t, si_upper) == 0x28); + +static_assert(offsetof(siginfo_t, si_pkey) == 0x20); + +static_assert(offsetof(siginfo_t, si_perf_data) == 0x18); +static_assert(offsetof(siginfo_t, si_perf_type) == 0x20); +static_assert(offsetof(siginfo_t, si_perf_flags) == 0x24); + +CHECK_SI_OFFSET(_sigpoll); +CHECK_SI_SIZE (_sigpoll, 4*sizeof(int)); +static_assert(offsetof(siginfo_t, si_band) == 0x10); +static_assert(offsetof(siginfo_t, si_fd) == 0x18); + +CHECK_SI_OFFSET(_sigsys); +CHECK_SI_SIZE (_sigsys, 4*sizeof(int)); +static_assert(offsetof(siginfo_t, si_call_addr) == 0x10); +static_assert(offsetof(siginfo_t, si_syscall) == 0x18); +static_assert(offsetof(siginfo_t, si_arch) == 0x1C); + +/* any new si_fields should be added here */ diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c deleted file mode 100644 index 879ef8c72f5c..000000000000 --- a/arch/x86/kernel/signal_compat.c +++ /dev/null @@ -1,191 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/compat.h> -#include <linux/uaccess.h> -#include <linux/ptrace.h> - -/* - * The compat_siginfo_t structure and handing code is very easy - * to break in several ways. It must always be updated when new - * updates are made to the main siginfo_t, and - * copy_siginfo_to_user32() must be updated when the - * (arch-independent) copy_siginfo_to_user() is updated. - * - * It is also easy to put a new member in the compat_siginfo_t - * which has implicit alignment which can move internal structure - * alignment around breaking the ABI. This can happen if you, - * for instance, put a plain 64-bit value in there. - */ -static inline void signal_compat_build_tests(void) -{ - int _sifields_offset = offsetof(compat_siginfo_t, _sifields); - - /* - * If adding a new si_code, there is probably new data in - * the siginfo. Make sure folks bumping the si_code - * limits also have to look at this code. Make sure any - * new fields are handled in copy_siginfo_to_user32()! - */ - BUILD_BUG_ON(NSIGILL != 11); - BUILD_BUG_ON(NSIGFPE != 15); - BUILD_BUG_ON(NSIGSEGV != 9); - BUILD_BUG_ON(NSIGBUS != 5); - BUILD_BUG_ON(NSIGTRAP != 6); - BUILD_BUG_ON(NSIGCHLD != 6); - BUILD_BUG_ON(NSIGSYS != 2); - - /* This is part of the ABI and can never change in size: */ - BUILD_BUG_ON(sizeof(siginfo_t) != 128); - BUILD_BUG_ON(sizeof(compat_siginfo_t) != 128); - - /* This is a part of the ABI and can never change in alignment */ - BUILD_BUG_ON(__alignof__(siginfo_t) != 8); - BUILD_BUG_ON(__alignof__(compat_siginfo_t) != 4); - - /* - * The offsets of all the (unioned) si_fields are fixed - * in the ABI, of course. Make sure none of them ever - * move and are always at the beginning: - */ - BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields) != 3 * sizeof(int)); -#define CHECK_CSI_OFFSET(name) BUILD_BUG_ON(_sifields_offset != offsetof(compat_siginfo_t, _sifields.name)) - - BUILD_BUG_ON(offsetof(siginfo_t, si_signo) != 0); - BUILD_BUG_ON(offsetof(siginfo_t, si_errno) != 4); - BUILD_BUG_ON(offsetof(siginfo_t, si_code) != 8); - - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_signo) != 0); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_errno) != 4); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_code) != 8); - /* - * Ensure that the size of each si_field never changes. - * If it does, it is a sign that the - * copy_siginfo_to_user32() code below needs to updated - * along with the size in the CHECK_SI_SIZE(). - * - * We repeat this check for both the generic and compat - * siginfos. - * - * Note: it is OK for these to grow as long as the whole - * structure stays within the padding size (checked - * above). - */ -#define CHECK_CSI_SIZE(name, size) BUILD_BUG_ON(size != sizeof(((compat_siginfo_t *)0)->_sifields.name)) -#define CHECK_SI_SIZE(name, size) BUILD_BUG_ON(size != sizeof(((siginfo_t *)0)->_sifields.name)) - - CHECK_CSI_OFFSET(_kill); - CHECK_CSI_SIZE (_kill, 2*sizeof(int)); - CHECK_SI_SIZE (_kill, 2*sizeof(int)); - - BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); - BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0xC); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); - - CHECK_CSI_OFFSET(_timer); - CHECK_CSI_SIZE (_timer, 3*sizeof(int)); - CHECK_SI_SIZE (_timer, 6*sizeof(int)); - - BUILD_BUG_ON(offsetof(siginfo_t, si_tid) != 0x10); - BUILD_BUG_ON(offsetof(siginfo_t, si_overrun) != 0x14); - BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_tid) != 0x0C); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_overrun) != 0x10); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14); - - CHECK_CSI_OFFSET(_rt); - CHECK_CSI_SIZE (_rt, 3*sizeof(int)); - CHECK_SI_SIZE (_rt, 4*sizeof(int)); - - BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); - BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); - BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0x0C); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14); - - CHECK_CSI_OFFSET(_sigchld); - CHECK_CSI_SIZE (_sigchld, 5*sizeof(int)); - CHECK_SI_SIZE (_sigchld, 8*sizeof(int)); - - BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); - BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); - BUILD_BUG_ON(offsetof(siginfo_t, si_status) != 0x18); - BUILD_BUG_ON(offsetof(siginfo_t, si_utime) != 0x20); - BUILD_BUG_ON(offsetof(siginfo_t, si_stime) != 0x28); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0x0C); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_status) != 0x14); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_utime) != 0x18); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_stime) != 0x1C); - -#ifdef CONFIG_X86_X32_ABI - CHECK_CSI_OFFSET(_sigchld_x32); - CHECK_CSI_SIZE (_sigchld_x32, 7*sizeof(int)); - /* no _sigchld_x32 in the generic siginfo_t */ - BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._utime) != 0x18); - BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._stime) != 0x20); -#endif - - CHECK_CSI_OFFSET(_sigfault); - CHECK_CSI_SIZE (_sigfault, 4*sizeof(int)); - CHECK_SI_SIZE (_sigfault, 8*sizeof(int)); - - BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x10); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr) != 0x0C); - - BUILD_BUG_ON(offsetof(siginfo_t, si_trapno) != 0x18); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_trapno) != 0x10); - - BUILD_BUG_ON(offsetof(siginfo_t, si_addr_lsb) != 0x18); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr_lsb) != 0x10); - - BUILD_BUG_ON(offsetof(siginfo_t, si_lower) != 0x20); - BUILD_BUG_ON(offsetof(siginfo_t, si_upper) != 0x28); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_lower) != 0x14); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_upper) != 0x18); - - BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14); - - BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x18); - BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x20); - BUILD_BUG_ON(offsetof(siginfo_t, si_perf_flags) != 0x24); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_data) != 0x10); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_type) != 0x14); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_flags) != 0x18); - - CHECK_CSI_OFFSET(_sigpoll); - CHECK_CSI_SIZE (_sigpoll, 2*sizeof(int)); - CHECK_SI_SIZE (_sigpoll, 4*sizeof(int)); - - BUILD_BUG_ON(offsetof(siginfo_t, si_band) != 0x10); - BUILD_BUG_ON(offsetof(siginfo_t, si_fd) != 0x18); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_band) != 0x0C); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_fd) != 0x10); - - CHECK_CSI_OFFSET(_sigsys); - CHECK_CSI_SIZE (_sigsys, 3*sizeof(int)); - CHECK_SI_SIZE (_sigsys, 4*sizeof(int)); - - BUILD_BUG_ON(offsetof(siginfo_t, si_call_addr) != 0x10); - BUILD_BUG_ON(offsetof(siginfo_t, si_syscall) != 0x18); - BUILD_BUG_ON(offsetof(siginfo_t, si_arch) != 0x1C); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_call_addr) != 0x0C); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_syscall) != 0x10); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_arch) != 0x14); - - /* any new si_fields should be added here */ -} - -void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact) -{ - signal_compat_build_tests(); - - if (!act) - return; - - if (in_ia32_syscall()) - act->sa.sa_flags |= SA_IA32_ABI; - if (in_x32_syscall()) - act->sa.sa_flags |= SA_X32_ABI; -} diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 06db901fabe8..375b33ecafa2 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -32,7 +32,7 @@ #include <asm/mce.h> #include <asm/trace/irq_vectors.h> #include <asm/kexec.h> -#include <asm/virtext.h> +#include <asm/reboot.h> /* * Some notes on x86 processor bugs affecting SMP operation: @@ -122,7 +122,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) if (raw_smp_processor_id() == atomic_read(&stopping_cpu)) return NMI_HANDLED; - cpu_emergency_vmxoff(); + cpu_emergency_disable_virtualization(); stop_this_cpu(NULL); return NMI_HANDLED; @@ -134,7 +134,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) DEFINE_IDTENTRY_SYSVEC(sysvec_reboot) { ack_APIC_irq(); - cpu_emergency_vmxoff(); + cpu_emergency_disable_virtualization(); stop_this_cpu(NULL); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 55cad72715d9..9013bb28255a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1833,7 +1833,7 @@ void native_play_dead(void) play_dead_common(); tboot_shutdown(TB_SHUTDOWN_WFS); - mwait_play_dead(); /* Only returns on failure */ + mwait_play_dead(); if (cpuidle_play_dead()) hlt_play_dead(); } diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 2ebc338980bc..b70670a98597 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -9,6 +9,7 @@ enum insn_type { NOP = 1, /* site cond-call */ JMP = 2, /* tramp / site tail-call */ RET = 3, /* tramp / site cond-tail-call */ + JCC = 4, }; /* @@ -25,12 +26,40 @@ static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 }; static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc }; +static u8 __is_Jcc(u8 *insn) /* Jcc.d32 */ +{ + u8 ret = 0; + + if (insn[0] == 0x0f) { + u8 tmp = insn[1]; + if ((tmp & 0xf0) == 0x80) + ret = tmp; + } + + return ret; +} + +extern void __static_call_return(void); + +asm (".global __static_call_return\n\t" + ".type __static_call_return, @function\n\t" + ASM_FUNC_ALIGN "\n\t" + "__static_call_return:\n\t" + ANNOTATE_NOENDBR + ANNOTATE_RETPOLINE_SAFE + "ret; int3\n\t" + ".size __static_call_return, . - __static_call_return \n\t"); + static void __ref __static_call_transform(void *insn, enum insn_type type, void *func, bool modinit) { const void *emulate = NULL; int size = CALL_INSN_SIZE; const void *code; + u8 op, buf[6]; + + if ((type == JMP || type == RET) && (op = __is_Jcc(insn))) + type = JCC; switch (type) { case CALL: @@ -57,6 +86,20 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, else code = &retinsn; break; + + case JCC: + if (!func) { + func = __static_call_return; + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + func = x86_return_thunk; + } + + buf[0] = 0x0f; + __text_gen_insn(buf+1, op, insn+1, func, 5); + code = buf; + size = 6; + + break; } if (memcmp(insn, code, size) == 0) @@ -68,9 +111,9 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, text_poke_bp(insn, code, size, emulate); } -static void __static_call_validate(void *insn, bool tail, bool tramp) +static void __static_call_validate(u8 *insn, bool tail, bool tramp) { - u8 opcode = *(u8 *)insn; + u8 opcode = insn[0]; if (tramp && memcmp(insn+5, tramp_ud, 3)) { pr_err("trampoline signature fail"); @@ -79,7 +122,8 @@ static void __static_call_validate(void *insn, bool tail, bool tramp) if (tail) { if (opcode == JMP32_INSN_OPCODE || - opcode == RET_INSN_OPCODE) + opcode == RET_INSN_OPCODE || + __is_Jcc(insn)) return; } else { if (opcode == CALL_INSN_OPCODE || diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 3c883e064242..3ffbab0081f4 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -12,6 +12,7 @@ #include <asm/ldt.h> #include <asm/processor.h> #include <asm/proto.h> +#include <asm/gsseg.h> #include "tls.h" diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index a78e73da4a74..344698852146 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -48,6 +48,8 @@ static DEFINE_STATIC_KEY_FALSE(__use_tsc); int tsc_clocksource_reliable; +static int __read_mostly tsc_force_recalibrate; + static u32 art_to_tsc_numerator; static u32 art_to_tsc_denominator; static u64 art_to_tsc_offset; @@ -215,7 +217,7 @@ static void __init cyc2ns_init_secondary_cpus(void) /* * Scheduler clock - returns current time in nanosec units. */ -u64 native_sched_clock(void) +noinstr u64 native_sched_clock(void) { if (static_branch_likely(&__use_tsc)) { u64 tsc_now = rdtsc(); @@ -248,7 +250,7 @@ u64 native_sched_clock_from_tsc(u64 tsc) /* We need to define a real function for sched_clock, to override the weak default version */ #ifdef CONFIG_PARAVIRT -unsigned long long sched_clock(void) +noinstr u64 sched_clock(void) { return paravirt_sched_clock(); } @@ -258,8 +260,7 @@ bool using_native_sched_clock(void) return static_call_query(pv_sched_clock) == native_sched_clock; } #else -unsigned long long -sched_clock(void) __attribute__((alias("native_sched_clock"))); +u64 sched_clock(void) __attribute__((alias("native_sched_clock"))); bool using_native_sched_clock(void) { return true; } #endif @@ -292,6 +293,7 @@ __setup("notsc", notsc_setup); static int no_sched_irq_time; static int no_tsc_watchdog; +static int tsc_as_watchdog; static int __init tsc_setup(char *str) { @@ -301,8 +303,22 @@ static int __init tsc_setup(char *str) no_sched_irq_time = 1; if (!strcmp(str, "unstable")) mark_tsc_unstable("boot parameter"); - if (!strcmp(str, "nowatchdog")) + if (!strcmp(str, "nowatchdog")) { no_tsc_watchdog = 1; + if (tsc_as_watchdog) + pr_alert("%s: Overriding earlier tsc=watchdog with tsc=nowatchdog\n", + __func__); + tsc_as_watchdog = 0; + } + if (!strcmp(str, "recalibrate")) + tsc_force_recalibrate = 1; + if (!strcmp(str, "watchdog")) { + if (no_tsc_watchdog) + pr_alert("%s: tsc=watchdog overridden by earlier tsc=nowatchdog\n", + __func__); + else + tsc_as_watchdog = 1; + } return 1; } @@ -912,8 +928,7 @@ void recalibrate_cpu_khz(void) cpu_khz_old, cpu_khz); #endif } - -EXPORT_SYMBOL(recalibrate_cpu_khz); +EXPORT_SYMBOL_GPL(recalibrate_cpu_khz); static unsigned long long cyc2ns_suspend; @@ -1186,6 +1201,12 @@ static void __init tsc_disable_clocksource_watchdog(void) clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; } +bool tsc_clocksource_watchdog_disabled(void) +{ + return !(clocksource_tsc.flags & CLOCK_SOURCE_MUST_VERIFY) && + tsc_as_watchdog && !no_tsc_watchdog; +} + static void __init check_system_tsc_reliable(void) { #if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC) @@ -1374,6 +1395,25 @@ restart: else freq = calc_pmtimer_ref(delta, ref_start, ref_stop); + /* Will hit this only if tsc_force_recalibrate has been set */ + if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { + + /* Warn if the deviation exceeds 500 ppm */ + if (abs(tsc_khz - freq) > (tsc_khz >> 11)) { + pr_warn("Warning: TSC freq calibrated by CPUID/MSR differs from what is calibrated by HW timer, please check with vendor!!\n"); + pr_info("Previous calibrated TSC freq:\t %lu.%03lu MHz\n", + (unsigned long)tsc_khz / 1000, + (unsigned long)tsc_khz % 1000); + } + + pr_info("TSC freq recalibrated by [%s]:\t %lu.%03lu MHz\n", + hpet ? "HPET" : "PM_TIMER", + (unsigned long)freq / 1000, + (unsigned long)freq % 1000); + + return; + } + /* Make sure we're within 1% */ if (abs(tsc_khz - freq) > tsc_khz/100) goto out; @@ -1407,8 +1447,10 @@ static int __init init_tsc_clocksource(void) if (!boot_cpu_has(X86_FEATURE_TSC) || !tsc_khz) return 0; - if (tsc_unstable) - goto unreg; + if (tsc_unstable) { + clocksource_unregister(&clocksource_tsc_early); + return 0; + } if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3)) clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; @@ -1421,9 +1463,10 @@ static int __init init_tsc_clocksource(void) if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; clocksource_register_khz(&clocksource_tsc, tsc_khz); -unreg: clocksource_unregister(&clocksource_tsc_early); - return 0; + + if (!tsc_force_recalibrate) + return 0; } schedule_delayed_work(&tsc_irqwork, 0); @@ -1510,6 +1553,11 @@ void __init tsc_early_init(void) void __init tsc_init(void) { + if (!cpu_feature_enabled(X86_FEATURE_TSC)) { + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); + return; + } + /* * native_calibrate_cpu_early can only calibrate using methods that are * available early in boot. @@ -1517,11 +1565,6 @@ void __init tsc_init(void) if (x86_platform.calibrate_cpu == native_calibrate_cpu_early) x86_platform.calibrate_cpu = native_calibrate_cpu; - if (!boot_cpu_has(X86_FEATURE_TSC)) { - setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); - return; - } - if (!tsc_khz) { /* We failed to determine frequencies earlier, try again */ if (!determine_cpu_tsc_frequencies(false)) { diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 2e0ee14229bf..25f155205770 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -129,7 +129,6 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT - CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT SOFTIRQENTRY_TEXT diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index fbeaa9ddef59..8e578311ca9d 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -49,6 +49,7 @@ config KVM select SRCU select INTERVAL_TREE select HAVE_KVM_PM_NOTIFIER if PM + select KVM_GENERIC_HARDWARE_ENABLING help Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 596061c1610e..599aebec2d52 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -8,6 +8,7 @@ * Copyright 2011 Red Hat, Inc. and/or its affiliates. * Copyright IBM Corporation, 2008 */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/export.h> @@ -25,6 +26,7 @@ #include "mmu.h" #include "trace.h" #include "pmu.h" +#include "xen.h" /* * Unlike "struct cpuinfo_x86.x86_capability", kvm_cpu_caps doesn't need to be @@ -180,15 +182,15 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 return 0; } -static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu) +static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, + const char *sig) { - u32 function; + struct kvm_hypervisor_cpuid cpuid = {}; struct kvm_cpuid_entry2 *entry; + u32 base; - vcpu->arch.kvm_cpuid_base = 0; - - for_each_possible_hypervisor_cpuid_base(function) { - entry = kvm_find_cpuid_entry(vcpu, function); + for_each_possible_hypervisor_cpuid_base(base) { + entry = kvm_find_cpuid_entry(vcpu, base); if (entry) { u32 signature[3]; @@ -197,19 +199,21 @@ static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu) signature[1] = entry->ecx; signature[2] = entry->edx; - BUILD_BUG_ON(sizeof(signature) > sizeof(KVM_SIGNATURE)); - if (!memcmp(signature, KVM_SIGNATURE, sizeof(signature))) { - vcpu->arch.kvm_cpuid_base = function; + if (!memcmp(signature, sig, sizeof(signature))) { + cpuid.base = base; + cpuid.limit = entry->eax; break; } } } + + return cpuid; } static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries, int nent) { - u32 base = vcpu->arch.kvm_cpuid_base; + u32 base = vcpu->arch.kvm_cpuid.base; if (!base) return NULL; @@ -439,7 +443,8 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, vcpu->arch.cpuid_entries = e2; vcpu->arch.cpuid_nent = nent; - kvm_update_kvm_cpuid_base(vcpu); + vcpu->arch.kvm_cpuid = kvm_get_hypervisor_cpuid(vcpu, KVM_SIGNATURE); + vcpu->arch.xen.cpuid = kvm_get_hypervisor_cpuid(vcpu, XEN_SIGNATURE); kvm_vcpu_after_set_cpuid(vcpu); return 0; @@ -663,8 +668,9 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD); kvm_cpu_cap_mask(CPUID_7_1_EAX, - F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) | F(AMX_FP16) | - F(AVX_IFMA) + F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) | + F(FZRM) | F(FSRS) | F(FSRC) | + F(AMX_FP16) | F(AVX_IFMA) ); kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX, @@ -701,6 +707,10 @@ void kvm_set_cpu_caps(void) if (!tdp_enabled && IS_ENABLED(CONFIG_X86_64)) kvm_cpu_cap_set(X86_FEATURE_GBPAGES); + kvm_cpu_cap_init_kvm_defined(CPUID_8000_0007_EDX, + SF(CONSTANT_TSC) + ); + kvm_cpu_cap_mask(CPUID_8000_0008_EBX, F(CLZERO) | F(XSAVEERPTR) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | @@ -741,6 +751,27 @@ void kvm_set_cpu_caps(void) 0 /* SME */ | F(SEV) | 0 /* VM_PAGE_FLUSH */ | F(SEV_ES) | F(SME_COHERENT)); + kvm_cpu_cap_mask(CPUID_8000_0021_EAX, + F(NO_NESTED_DATA_BP) | F(LFENCE_RDTSC) | 0 /* SmmPgCfgLock */ | + F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ + ); + + /* + * Synthesize "LFENCE is serializing" into the AMD-defined entry in + * KVM's supported CPUID if the feature is reported as supported by the + * kernel. LFENCE_RDTSC was a Linux-defined synthetic feature long + * before AMD joined the bandwagon, e.g. LFENCE is serializing on most + * CPUs that support SSE2. On CPUs that don't support AMD's leaf, + * kvm_cpu_cap_mask() will unfortunately drop the flag due to ANDing + * the mask with the raw host CPUID, and reporting support in AMD's + * leaf can make it easier for userspace to detect the feature. + */ + if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC)) + kvm_cpu_cap_set(X86_FEATURE_LFENCE_RDTSC); + if (!static_cpu_has_bug(X86_BUG_NULL_SEG)) + kvm_cpu_cap_set(X86_FEATURE_NULL_SEL_CLR_BASE); + kvm_cpu_cap_set(X86_FEATURE_NO_SMM_CTL_MSR); + kvm_cpu_cap_mask(CPUID_C000_0001_EDX, F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | @@ -1148,8 +1179,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->edx &= ~GENMASK(17, 16); break; case 0x80000007: /* Advanced power management */ - /* invariant TSC is CPUID.80000007H:EDX[8] */ - entry->edx &= (1 << 8); + cpuid_entry_override(entry, CPUID_8000_0007_EDX); + /* mask against host */ entry->edx &= boot_cpu_data.x86_power; entry->eax = entry->ebx = entry->ecx = 0; @@ -1222,25 +1253,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) break; case 0x80000021: entry->ebx = entry->ecx = entry->edx = 0; - /* - * Pass down these bits: - * EAX 0 NNDBP, Processor ignores nested data breakpoints - * EAX 2 LAS, LFENCE always serializing - * EAX 6 NSCB, Null selector clear base - * - * Other defined bits are for MSRs that KVM does not expose: - * EAX 3 SPCL, SMM page configuration lock - * EAX 13 PCMSR, Prefetch control MSR - * - * KVM doesn't support SMM_CTL. - * EAX 9 SMM_CTL MSR is not supported - */ - entry->eax &= BIT(0) | BIT(2) | BIT(6); - entry->eax |= BIT(9); - if (static_cpu_has(X86_FEATURE_LFENCE_RDTSC)) - entry->eax |= BIT(2); - if (!static_cpu_has_bug(X86_BUG_NULL_SEG)) - entry->eax |= BIT(6); + cpuid_entry_override(entry, CPUID_8000_0021_EAX); break; /*Add support for Centaur's CPUID instruction*/ case 0xC0000000: @@ -1482,6 +1495,9 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, if (!__kvm_get_msr(vcpu, MSR_IA32_TSX_CTRL, &data, true) && (data & TSX_CTRL_CPUID_CLEAR)) *ebx &= ~(F(RTM) | F(HLE)); + } else if (function == 0x80000007) { + if (kvm_hv_invtsc_suppressed(vcpu)) + *edx &= ~SF(CONSTANT_TSC); } } else { *eax = *ebx = *ecx = *edx = 0; diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index c1390357126a..ee8c4c3496ed 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -4,6 +4,8 @@ * * Copyright 2016 Red Hat, Inc. and/or its affiliates. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kvm_host.h> #include <linux/debugfs.h> #include "lapic.h" diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 5cc3efa0e21c..a20bec931764 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -17,6 +17,7 @@ * * From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4 */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "kvm_cache_regs.h" @@ -1633,7 +1634,7 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, case VCPU_SREG_SS: /* * segment is not a writable data segment or segment - * selector's RPL != CPL or segment selector's RPL != CPL + * selector's RPL != CPL or DPL != CPL */ if (rpl != cpl || (seg_desc.type & 0xa) != 0x2 || dpl != cpl) goto exception; @@ -1695,11 +1696,11 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, /* * segment is not a data or readable code segment or * ((segment is a data or nonconforming code segment) - * and (both RPL and CPL > DPL)) + * and ((RPL > DPL) or (CPL > DPL))) */ if ((seg_desc.type & 0xa) == 0x8 || (((seg_desc.type & 0xc) != 0xc) && - (rpl > dpl && cpl > dpl))) + (rpl > dpl || cpl > dpl))) goto exception; break; } @@ -2309,7 +2310,7 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt) static int em_rsm(struct x86_emulate_ctxt *ctxt) { - if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0) + if (!ctxt->ops->is_smm(ctxt)) return emulate_ud(ctxt); if (ctxt->ops->leave_smm(ctxt)) @@ -2615,8 +2616,8 @@ static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt, return true; } -static bool emulator_io_permited(struct x86_emulate_ctxt *ctxt, - u16 port, u16 len) +static bool emulator_io_permitted(struct x86_emulate_ctxt *ctxt, + u16 port, u16 len) { if (ctxt->perm_ok) return true; @@ -3961,7 +3962,7 @@ static int check_rdpmc(struct x86_emulate_ctxt *ctxt) static int check_perm_in(struct x86_emulate_ctxt *ctxt) { ctxt->dst.bytes = min(ctxt->dst.bytes, 4u); - if (!emulator_io_permited(ctxt, ctxt->src.val, ctxt->dst.bytes)) + if (!emulator_io_permitted(ctxt, ctxt->src.val, ctxt->dst.bytes)) return emulate_gp(ctxt, 0); return X86EMUL_CONTINUE; @@ -3970,7 +3971,7 @@ static int check_perm_in(struct x86_emulate_ctxt *ctxt) static int check_perm_out(struct x86_emulate_ctxt *ctxt) { ctxt->src.bytes = min(ctxt->src.bytes, 4u); - if (!emulator_io_permited(ctxt, ctxt->dst.val, ctxt->src.bytes)) + if (!emulator_io_permitted(ctxt, ctxt->dst.val, ctxt->src.bytes)) return emulate_gp(ctxt, 0); return X86EMUL_CONTINUE; @@ -5132,7 +5133,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) const struct x86_emulate_ops *ops = ctxt->ops; int rc = X86EMUL_CONTINUE; int saved_dst_type = ctxt->dst.type; - unsigned emul_flags; + bool is_guest_mode = ctxt->ops->is_guest_mode(ctxt); ctxt->mem_read.pos = 0; @@ -5147,7 +5148,6 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) goto done; } - emul_flags = ctxt->ops->get_hflags(ctxt); if (unlikely(ctxt->d & (No64|Undefined|Sse|Mmx|Intercept|CheckPerm|Priv|Prot|String))) { if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) || @@ -5181,7 +5181,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) fetch_possible_mmx_operand(&ctxt->dst); } - if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) { + if (unlikely(is_guest_mode) && ctxt->intercept) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_PRE_EXCEPT); if (rc != X86EMUL_CONTINUE) @@ -5210,7 +5210,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) goto done; } - if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { + if (unlikely(is_guest_mode) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_EXCEPT); if (rc != X86EMUL_CONTINUE) @@ -5264,7 +5264,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) special_insn: - if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { + if (unlikely(is_guest_mode) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_MEMACCESS); if (rc != X86EMUL_CONTINUE) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index e8296942a868..b28fd020066f 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -17,6 +17,7 @@ * Ben-Ami Yassour <benami@il.ibm.com> * Andrey Smetanin <asmetanin@virtuozzo.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "x86.h" #include "lapic.h" @@ -43,6 +44,24 @@ #define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, HV_VCPUS_PER_SPARSE_BANK) +/* + * As per Hyper-V TLFS, extended hypercalls start from 0x8001 + * (HvExtCallQueryCapabilities). Response of this hypercalls is a 64 bit value + * where each bit tells which extended hypercall is available besides + * HvExtCallQueryCapabilities. + * + * 0x8001 - First extended hypercall, HvExtCallQueryCapabilities, no bit + * assigned. + * + * 0x8002 - Bit 0 + * 0x8003 - Bit 1 + * .. + * 0x8041 - Bit 63 + * + * Therefore, HV_EXT_CALL_MAX = 0x8001 + 64 + */ +#define HV_EXT_CALL_MAX (HV_EXT_CALL_QUERY_CAPABILITIES + 64) + static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, bool vcpu_kick); @@ -999,6 +1018,7 @@ static bool kvm_hv_msr_partition_wide(u32 msr) case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: + case HV_X64_MSR_TSC_INVARIANT_CONTROL: case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: r = true; @@ -1283,6 +1303,9 @@ static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr) case HV_X64_MSR_TSC_EMULATION_STATUS: return hv_vcpu->cpuid_cache.features_eax & HV_ACCESS_REENLIGHTENMENT; + case HV_X64_MSR_TSC_INVARIANT_CONTROL: + return hv_vcpu->cpuid_cache.features_eax & + HV_ACCESS_TSC_INVARIANT; case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: return hv_vcpu->cpuid_cache.features_edx & @@ -1410,12 +1433,22 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, if (!host) return 1; break; + case HV_X64_MSR_TSC_INVARIANT_CONTROL: + /* Only bit 0 is supported */ + if (data & ~HV_EXPOSE_INVARIANT_TSC) + return 1; + + /* The feature can't be disabled from the guest */ + if (!host && hv->hv_invtsc_control && !data) + return 1; + + hv->hv_invtsc_control = data; + break; case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: return syndbg_set_msr(vcpu, msr, data, host); default: - vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", - msr, data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } return 0; @@ -1536,8 +1569,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; break; default: - vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", - msr, data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } @@ -1585,11 +1617,14 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, case HV_X64_MSR_TSC_EMULATION_STATUS: data = hv->hv_tsc_emulation_status; break; + case HV_X64_MSR_TSC_INVARIANT_CONTROL: + data = hv->hv_invtsc_control; + break; case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: return syndbg_get_msr(vcpu, msr, pdata, host); default: - vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + kvm_pr_unimpl_rdmsr(vcpu, msr); return 1; } @@ -1654,7 +1689,7 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, data = APIC_BUS_FREQUENCY; break; default: - vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + kvm_pr_unimpl_rdmsr(vcpu, msr); return 1; } *pdata = data; @@ -2420,6 +2455,9 @@ static bool hv_check_hypercall_access(struct kvm_vcpu_hv *hv_vcpu, u16 code) case HVCALL_SEND_IPI: return hv_vcpu->cpuid_cache.enlightenments_eax & HV_X64_CLUSTER_IPI_RECOMMENDED; + case HV_EXT_CALL_QUERY_CAPABILITIES ... HV_EXT_CALL_MAX: + return hv_vcpu->cpuid_cache.features_ebx & + HV_ENABLE_EXTENDED_HYPERCALLS; default: break; } @@ -2512,14 +2550,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - vcpu->run->exit_reason = KVM_EXIT_HYPERV; - vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; - vcpu->run->hyperv.u.hcall.input = hc.param; - vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa; - vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa; - vcpu->arch.complete_userspace_io = - kvm_hv_hypercall_complete_userspace; - return 0; + goto hypercall_userspace_exit; case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: if (unlikely(hc.var_cnt)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; @@ -2578,15 +2609,14 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) ret = HV_STATUS_OPERATION_DENIED; break; } - vcpu->run->exit_reason = KVM_EXIT_HYPERV; - vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; - vcpu->run->hyperv.u.hcall.input = hc.param; - vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa; - vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa; - vcpu->arch.complete_userspace_io = - kvm_hv_hypercall_complete_userspace; - return 0; + goto hypercall_userspace_exit; } + case HV_EXT_CALL_QUERY_CAPABILITIES ... HV_EXT_CALL_MAX: + if (unlikely(hc.fast)) { + ret = HV_STATUS_INVALID_PARAMETER; + break; + } + goto hypercall_userspace_exit; default: ret = HV_STATUS_INVALID_HYPERCALL_CODE; break; @@ -2594,6 +2624,15 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) hypercall_complete: return kvm_hv_hypercall_complete(vcpu, ret); + +hypercall_userspace_exit: + vcpu->run->exit_reason = KVM_EXIT_HYPERV; + vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; + vcpu->run->hyperv.u.hcall.input = hc.param; + vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa; + vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa; + vcpu->arch.complete_userspace_io = kvm_hv_hypercall_complete_userspace; + return 0; } void kvm_hv_init_vm(struct kvm *kvm) @@ -2733,9 +2772,11 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; ent->eax |= HV_ACCESS_FREQUENCY_MSRS; ent->eax |= HV_ACCESS_REENLIGHTENMENT; + ent->eax |= HV_ACCESS_TSC_INVARIANT; ent->ebx |= HV_POST_MESSAGES; ent->ebx |= HV_SIGNAL_EVENTS; + ent->ebx |= HV_ENABLE_EXTENDED_HYPERCALLS; ent->edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 9f96414a31c5..f83b8db72b11 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -136,6 +136,33 @@ static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu) HV_SYNIC_STIMER_COUNT); } +/* + * With HV_ACCESS_TSC_INVARIANT feature, invariant TSC (CPUID.80000007H:EDX[8]) + * is only observed after HV_X64_MSR_TSC_INVARIANT_CONTROL was written to. + */ +static inline bool kvm_hv_invtsc_suppressed(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + /* + * If Hyper-V's invariant TSC control is not exposed to the guest, + * the invariant TSC CPUID flag is not suppressed, Windows guests were + * observed to be able to handle it correctly. Going forward, VMMs are + * encouraged to enable Hyper-V's invariant TSC control when invariant + * TSC CPUID flag is set to make KVM's behavior match genuine Hyper-V. + */ + if (!hv_vcpu || + !(hv_vcpu->cpuid_cache.features_eax & HV_ACCESS_TSC_INVARIANT)) + return false; + + /* + * If Hyper-V's invariant TSC control is exposed to the guest, KVM is + * responsible for suppressing the invariant TSC CPUID flag if the + * Hyper-V control is not enabled. + */ + return !(to_kvm_hv(vcpu->kvm)->hv_invtsc_control & HV_EXPOSE_INVARIANT_TSC); +} + void kvm_hv_process_stimers(struct kvm_vcpu *vcpu); void kvm_hv_setup_tsc_page(struct kvm *kvm, diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index e0a7a0e7a73c..cd57a517d04a 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -30,7 +30,7 @@ * Based on QEMU and Xen. */ -#define pr_fmt(fmt) "pit: " fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/slab.h> @@ -351,7 +351,7 @@ static void create_pit_timer(struct kvm_pit *pit, u32 val, int is_period) if (ps->period < min_period) { pr_info_ratelimited( - "kvm: requested %lld ns " + "requested %lld ns " "i8254 timer period limited to %lld ns\n", ps->period, min_period); ps->period = min_period; diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index e1bb6218bb96..4756bcb5724f 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -26,6 +26,8 @@ * Yaozu (Eddie) Dong <Eddie.dong@intel.com> * Port from Qemu. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/mm.h> #include <linux/slab.h> #include <linux/bitops.h> @@ -35,7 +37,7 @@ #include "trace.h" #define pr_pic_unimpl(fmt, ...) \ - pr_err_ratelimited("kvm: pic: " fmt, ## __VA_ARGS__) + pr_err_ratelimited("pic: " fmt, ## __VA_ARGS__) static void pic_irq_request(struct kvm *kvm, int level); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 765943d7cfa5..042dee556125 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -26,6 +26,7 @@ * Yaozu (Eddie) Dong <eddie.dong@intel.com> * Based on Xen 3.1 code. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/kvm.h> diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index a70952eca905..b2c397dd2bc6 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -7,6 +7,7 @@ * Authors: * Yaozu (Eddie) Dong <Eddie.dong@intel.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/export.h> #include <linux/kvm_host.h> diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 3742d9adacfc..16d076a1b91a 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -8,6 +8,7 @@ * * Copyright 2010 Red Hat, Inc. and/or its affiliates. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/slab.h> @@ -56,7 +57,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, if (irq->dest_mode == APIC_DEST_PHYSICAL && irq->dest_id == 0xff && kvm_lowest_prio_delivery(irq)) { - printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); + pr_info("apic: phys broadcast and lowest prio\n"); irq->delivery_mode = APIC_DM_FIXED; } @@ -199,7 +200,7 @@ int kvm_request_irq_source_id(struct kvm *kvm) irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG); if (irq_source_id >= BITS_PER_LONG) { - printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n"); + pr_warn("exhausted allocatable IRQ sources!\n"); irq_source_id = -EFAULT; goto unlock; } @@ -221,7 +222,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) mutex_lock(&kvm->irq_lock); if (irq_source_id < 0 || irq_source_id >= BITS_PER_LONG) { - printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); + pr_err("IRQ source ID out of range!\n"); goto unlock; } clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index c09174f73a34..4c91f626c058 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -76,6 +76,18 @@ static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, } /* + * kvm_register_test_and_mark_available() is a special snowflake that uses an + * arch bitop directly to avoid the explicit instrumentation that comes with + * the generic bitops. This allows code that cannot be instrumented (noinstr + * functions), e.g. the low level VM-Enter/VM-Exit paths, to cache registers. + */ +static __always_inline bool kvm_register_test_and_mark_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + return arch___test_and_set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +/* * The "raw" register helpers are only for cases where the full 64 bits of a * register are read/written irrespective of current vCPU mode. In other words, * odds are good you shouldn't be using the raw variants. diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 2d9662be8333..ab65f3a47dfd 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -220,7 +220,8 @@ struct x86_emulate_ops { void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked); - unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt); + bool (*is_smm)(struct x86_emulate_ctxt *ctxt); + bool (*is_guest_mode)(struct x86_emulate_ctxt *ctxt); int (*leave_smm)(struct x86_emulate_ctxt *ctxt); void (*triple_fault)(struct x86_emulate_ctxt *ctxt); int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr); @@ -275,10 +276,6 @@ enum x86emul_mode { X86EMUL_MODE_PROT64, /* 64-bit (long) mode. */ }; -/* These match some of the HF_* flags defined in kvm_host.h */ -#define X86EMUL_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ -#define X86EMUL_SMM_MASK (1 << 6) - /* * fastop functions are declared as taking a never-defined fastop parameter, * so they can't be called from C directly. diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c index ee4f696a0782..482d6639ef88 100644 --- a/arch/x86/kvm/kvm_onhyperv.c +++ b/arch/x86/kvm/kvm_onhyperv.c @@ -2,6 +2,7 @@ /* * KVM L1 hypervisor optimizations on Hyper-V. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <asm/mshyperv.h> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4efdb4a4d72c..e542cf285b51 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -15,6 +15,7 @@ * * Based on Xen 3.1 code, Copyright (c) 2004, Intel Corporation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/kvm.h> @@ -166,9 +167,19 @@ static bool kvm_use_posted_timer_interrupt(struct kvm_vcpu *vcpu) return kvm_can_post_timer_interrupt(vcpu) && vcpu->mode == IN_GUEST_MODE; } +static inline u32 kvm_apic_calc_x2apic_ldr(u32 id) +{ + return ((id >> 4) << 16) | (1 << (id & 0xf)); +} + static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) { - switch (map->mode) { + switch (map->logical_mode) { + case KVM_APIC_MODE_SW_DISABLED: + /* Arbitrarily use the flat map so that @cluster isn't NULL. */ + *cluster = map->xapic_flat_map; + *mask = 0; + return true; case KVM_APIC_MODE_X2APIC: { u32 offset = (dest_id >> 16) * 16; u32 max_apic_id = map->max_apic_id; @@ -193,8 +204,10 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, *cluster = map->xapic_cluster_map[(dest_id >> 4) & 0xf]; *mask = dest_id & 0xf; return true; + case KVM_APIC_MODE_MAP_DISABLED: + return false; default: - /* Not optimized. */ + WARN_ON_ONCE(1); return false; } } @@ -206,6 +219,134 @@ static void kvm_apic_map_free(struct rcu_head *rcu) kvfree(map); } +static int kvm_recalculate_phys_map(struct kvm_apic_map *new, + struct kvm_vcpu *vcpu, + bool *xapic_id_mismatch) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + u32 x2apic_id = kvm_x2apic_id(apic); + u32 xapic_id = kvm_xapic_id(apic); + u32 physical_id; + + /* + * Deliberately truncate the vCPU ID when detecting a mismatched APIC + * ID to avoid false positives if the vCPU ID, i.e. x2APIC ID, is a + * 32-bit value. Any unwanted aliasing due to truncation results will + * be detected below. + */ + if (!apic_x2apic_mode(apic) && xapic_id != (u8)vcpu->vcpu_id) + *xapic_id_mismatch = true; + + /* + * Apply KVM's hotplug hack if userspace has enable 32-bit APIC IDs. + * Allow sending events to vCPUs by their x2APIC ID even if the target + * vCPU is in legacy xAPIC mode, and silently ignore aliased xAPIC IDs + * (the x2APIC ID is truncated to 8 bits, causing IDs > 0xff to wrap + * and collide). + * + * Honor the architectural (and KVM's non-optimized) behavior if + * userspace has not enabled 32-bit x2APIC IDs. Each APIC is supposed + * to process messages independently. If multiple vCPUs have the same + * effective APIC ID, e.g. due to the x2APIC wrap or because the guest + * manually modified its xAPIC IDs, events targeting that ID are + * supposed to be recognized by all vCPUs with said ID. + */ + if (vcpu->kvm->arch.x2apic_format) { + /* See also kvm_apic_match_physical_addr(). */ + if ((apic_x2apic_mode(apic) || x2apic_id > 0xff) && + x2apic_id <= new->max_apic_id) + new->phys_map[x2apic_id] = apic; + + if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id]) + new->phys_map[xapic_id] = apic; + } else { + /* + * Disable the optimized map if the physical APIC ID is already + * mapped, i.e. is aliased to multiple vCPUs. The optimized + * map requires a strict 1:1 mapping between IDs and vCPUs. + */ + if (apic_x2apic_mode(apic)) + physical_id = x2apic_id; + else + physical_id = xapic_id; + + if (new->phys_map[physical_id]) + return -EINVAL; + + new->phys_map[physical_id] = apic; + } + + return 0; +} + +static void kvm_recalculate_logical_map(struct kvm_apic_map *new, + struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + enum kvm_apic_logical_mode logical_mode; + struct kvm_lapic **cluster; + u16 mask; + u32 ldr; + + if (new->logical_mode == KVM_APIC_MODE_MAP_DISABLED) + return; + + if (!kvm_apic_sw_enabled(apic)) + return; + + ldr = kvm_lapic_get_reg(apic, APIC_LDR); + if (!ldr) + return; + + if (apic_x2apic_mode(apic)) { + logical_mode = KVM_APIC_MODE_X2APIC; + } else { + ldr = GET_APIC_LOGICAL_ID(ldr); + if (kvm_lapic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT) + logical_mode = KVM_APIC_MODE_XAPIC_FLAT; + else + logical_mode = KVM_APIC_MODE_XAPIC_CLUSTER; + } + + /* + * To optimize logical mode delivery, all software-enabled APICs must + * be configured for the same mode. + */ + if (new->logical_mode == KVM_APIC_MODE_SW_DISABLED) { + new->logical_mode = logical_mode; + } else if (new->logical_mode != logical_mode) { + new->logical_mode = KVM_APIC_MODE_MAP_DISABLED; + return; + } + + /* + * In x2APIC mode, the LDR is read-only and derived directly from the + * x2APIC ID, thus is guaranteed to be addressable. KVM reuses + * kvm_apic_map.phys_map to optimize logical mode x2APIC interrupts by + * reversing the LDR calculation to get cluster of APICs, i.e. no + * additional work is required. + */ + if (apic_x2apic_mode(apic)) { + WARN_ON_ONCE(ldr != kvm_apic_calc_x2apic_ldr(kvm_x2apic_id(apic))); + return; + } + + if (WARN_ON_ONCE(!kvm_apic_map_get_logical_dest(new, ldr, + &cluster, &mask))) { + new->logical_mode = KVM_APIC_MODE_MAP_DISABLED; + return; + } + + if (!mask) + return; + + ldr = ffs(mask) - 1; + if (!is_power_of_2(mask) || cluster[ldr]) + new->logical_mode = KVM_APIC_MODE_MAP_DISABLED; + else + cluster[ldr] = apic; +} + /* * CLEAN -> DIRTY and UPDATE_IN_PROGRESS -> DIRTY changes happen without a lock. * @@ -224,6 +365,7 @@ void kvm_recalculate_apic_map(struct kvm *kvm) struct kvm_vcpu *vcpu; unsigned long i; u32 max_id = 255; /* enough space for any xAPIC ID */ + bool xapic_id_mismatch = false; /* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map. */ if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN) @@ -256,54 +398,41 @@ void kvm_recalculate_apic_map(struct kvm *kvm) goto out; new->max_apic_id = max_id; + new->logical_mode = KVM_APIC_MODE_SW_DISABLED; kvm_for_each_vcpu(i, vcpu, kvm) { - struct kvm_lapic *apic = vcpu->arch.apic; - struct kvm_lapic **cluster; - u16 mask; - u32 ldr; - u8 xapic_id; - u32 x2apic_id; - if (!kvm_apic_present(vcpu)) continue; - xapic_id = kvm_xapic_id(apic); - x2apic_id = kvm_x2apic_id(apic); - - /* Hotplug hack: see kvm_apic_match_physical_addr(), ... */ - if ((apic_x2apic_mode(apic) || x2apic_id > 0xff) && - x2apic_id <= new->max_apic_id) - new->phys_map[x2apic_id] = apic; - /* - * ... xAPIC ID of VCPUs with APIC ID > 0xff will wrap-around, - * prevent them from masking VCPUs with APIC ID <= 0xff. - */ - if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id]) - new->phys_map[xapic_id] = apic; - - if (!kvm_apic_sw_enabled(apic)) - continue; - - ldr = kvm_lapic_get_reg(apic, APIC_LDR); - - if (apic_x2apic_mode(apic)) { - new->mode |= KVM_APIC_MODE_X2APIC; - } else if (ldr) { - ldr = GET_APIC_LOGICAL_ID(ldr); - if (kvm_lapic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT) - new->mode |= KVM_APIC_MODE_XAPIC_FLAT; - else - new->mode |= KVM_APIC_MODE_XAPIC_CLUSTER; + if (kvm_recalculate_phys_map(new, vcpu, &xapic_id_mismatch)) { + kvfree(new); + new = NULL; + goto out; } - if (!kvm_apic_map_get_logical_dest(new, ldr, &cluster, &mask)) - continue; - - if (mask) - cluster[ffs(mask) - 1] = apic; + kvm_recalculate_logical_map(new, vcpu); } out: + /* + * The optimized map is effectively KVM's internal version of APICv, + * and all unwanted aliasing that results in disabling the optimized + * map also applies to APICv. + */ + if (!new) + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED); + else + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED); + + if (!new || new->logical_mode == KVM_APIC_MODE_MAP_DISABLED) + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED); + else + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED); + + if (xapic_id_mismatch) + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED); + else + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED); + old = rcu_dereference_protected(kvm->arch.apic_map, lockdep_is_held(&kvm->arch.apic_map_lock)); rcu_assign_pointer(kvm->arch.apic_map, new); @@ -360,11 +489,6 @@ static inline void kvm_apic_set_dfr(struct kvm_lapic *apic, u32 val) atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } -static inline u32 kvm_apic_calc_x2apic_ldr(u32 id) -{ - return ((id >> 4) << 16) | (1 << (id & 0xf)); -} - static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id) { u32 ldr = kvm_apic_calc_x2apic_ldr(id); @@ -941,8 +1065,7 @@ static void kvm_apic_disabled_lapic_found(struct kvm *kvm) { if (!kvm->arch.disabled_lapic_found) { kvm->arch.disabled_lapic_found = true; - printk(KERN_INFO - "Disabled LAPIC found during irq injection\n"); + pr_info("Disabled LAPIC found during irq injection\n"); } } @@ -951,7 +1074,7 @@ static bool kvm_apic_is_broadcast_dest(struct kvm *kvm, struct kvm_lapic **src, { if (kvm->arch.x2apic_broadcast_quirk_disabled) { if ((irq->dest_id == APIC_BROADCAST && - map->mode != KVM_APIC_MODE_X2APIC)) + map->logical_mode != KVM_APIC_MODE_X2APIC)) return true; if (irq->dest_id == X2APIC_BROADCAST) return true; @@ -1364,7 +1487,6 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic) { ktime_t remaining, now; s64 ns; - u32 tmcct; ASSERT(apic != NULL); @@ -1379,10 +1501,7 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic) remaining = 0; ns = mod_64(ktime_to_ns(remaining), apic->lapic_timer.period); - tmcct = div64_u64(ns, - (APIC_BUS_CYCLE_NS * apic->divide_count)); - - return tmcct; + return div64_u64(ns, (APIC_BUS_CYCLE_NS * apic->divide_count)); } static void __report_tpr_access(struct kvm_lapic *apic, bool write) @@ -1442,19 +1561,15 @@ static inline struct kvm_lapic *to_lapic(struct kvm_io_device *dev) #define APIC_REGS_MASK(first, count) \ (APIC_REG_MASK(first) * ((1ull << (count)) - 1)) -static int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, - void *data) +u64 kvm_lapic_readable_reg_mask(struct kvm_lapic *apic) { - unsigned char alignment = offset & 0xf; - u32 result; - /* this bitmask has a bit cleared for each reserved register */ + /* Leave bits '0' for reserved and write-only registers. */ u64 valid_reg_mask = APIC_REG_MASK(APIC_ID) | APIC_REG_MASK(APIC_LVR) | APIC_REG_MASK(APIC_TASKPRI) | APIC_REG_MASK(APIC_PROCPRI) | APIC_REG_MASK(APIC_LDR) | - APIC_REG_MASK(APIC_DFR) | APIC_REG_MASK(APIC_SPIV) | APIC_REGS_MASK(APIC_ISR, APIC_ISR_NR) | APIC_REGS_MASK(APIC_TMR, APIC_ISR_NR) | @@ -1474,21 +1589,33 @@ static int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, if (kvm_lapic_lvt_supported(apic, LVT_CMCI)) valid_reg_mask |= APIC_REG_MASK(APIC_LVTCMCI); - /* - * ARBPRI and ICR2 are not valid in x2APIC mode. WARN if KVM reads ICR - * in x2APIC mode as it's an 8-byte register in x2APIC and needs to be - * manually handled by the caller. - */ + /* ARBPRI, DFR, and ICR2 are not valid in x2APIC mode. */ if (!apic_x2apic_mode(apic)) valid_reg_mask |= APIC_REG_MASK(APIC_ARBPRI) | + APIC_REG_MASK(APIC_DFR) | APIC_REG_MASK(APIC_ICR2); - else - WARN_ON_ONCE(offset == APIC_ICR); + + return valid_reg_mask; +} +EXPORT_SYMBOL_GPL(kvm_lapic_readable_reg_mask); + +static int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, + void *data) +{ + unsigned char alignment = offset & 0xf; + u32 result; + + /* + * WARN if KVM reads ICR in x2APIC mode, as it's an 8-byte register in + * x2APIC and needs to be manually handled by the caller. + */ + WARN_ON_ONCE(apic_x2apic_mode(apic) && offset == APIC_ICR); if (alignment + len > 4) return 1; - if (offset > 0x3f0 || !(valid_reg_mask & APIC_REG_MASK(offset))) + if (offset > 0x3f0 || + !(kvm_lapic_readable_reg_mask(apic) & APIC_REG_MASK(offset))) return 1; result = __apic_read(apic, offset & ~0xf); @@ -1560,7 +1687,7 @@ static void limit_periodic_timer_frequency(struct kvm_lapic *apic) if (apic->lapic_timer.period < min_period) { pr_info_ratelimited( - "kvm: vcpu %i: requested %lld ns " + "vcpu %i: requested %lld ns " "lapic timer period limited to %lld ns\n", apic->vcpu->vcpu_id, apic->lapic_timer.period, min_period); @@ -1841,11 +1968,15 @@ static bool set_target_expiration(struct kvm_lapic *apic, u32 count_reg) if (unlikely(count_reg != APIC_TMICT)) { deadline = tmict_to_ns(apic, kvm_lapic_get_reg(apic, count_reg)); - if (unlikely(deadline <= 0)) - deadline = apic->lapic_timer.period; + if (unlikely(deadline <= 0)) { + if (apic_lvtt_period(apic)) + deadline = apic->lapic_timer.period; + else + deadline = 0; + } else if (unlikely(deadline > apic->lapic_timer.period)) { pr_info_ratelimited( - "kvm: vcpu %i: requested lapic timer restore with " + "vcpu %i: requested lapic timer restore with " "starting count register %#x=%u (%lld ns) > initial count (%lld ns). " "Using initial count to start timer.\n", apic->vcpu->vcpu_id, @@ -2068,19 +2199,6 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) } } -static void kvm_lapic_xapic_id_updated(struct kvm_lapic *apic) -{ - struct kvm *kvm = apic->vcpu->kvm; - - if (KVM_BUG_ON(apic_x2apic_mode(apic), kvm)) - return; - - if (kvm_xapic_id(apic) == apic->vcpu->vcpu_id) - return; - - kvm_set_apicv_inhibit(apic->vcpu->kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED); -} - static int get_lvt_index(u32 reg) { if (reg == APIC_LVTCMCI) @@ -2101,7 +2219,6 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_ID: /* Local APIC ID */ if (!apic_x2apic_mode(apic)) { kvm_apic_set_xapic_id(apic, val >> 24); - kvm_lapic_xapic_id_updated(apic); } else { ret = 1; } @@ -2219,10 +2336,14 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) break; case APIC_SELF_IPI: - if (apic_x2apic_mode(apic)) - kvm_apic_send_ipi(apic, APIC_DEST_SELF | (val & APIC_VECTOR_MASK), 0); - else + /* + * Self-IPI exists only when x2APIC is enabled. Bits 7:0 hold + * the vector, everything else is reserved. + */ + if (!apic_x2apic_mode(apic) || (val & ~APIC_VECTOR_MASK)) ret = 1; + else + kvm_apic_send_ipi(apic, APIC_DEST_SELF | val, 0); break; default: ret = 1; @@ -2284,23 +2405,18 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) struct kvm_lapic *apic = vcpu->arch.apic; u64 val; - if (apic_x2apic_mode(apic)) { - if (KVM_BUG_ON(kvm_lapic_msr_read(apic, offset, &val), vcpu->kvm)) - return; - } else { - val = kvm_lapic_get_reg(apic, offset); - } - /* * ICR is a single 64-bit register when x2APIC is enabled. For legacy * xAPIC, ICR writes need to go down the common (slightly slower) path * to get the upper half from ICR2. */ if (apic_x2apic_mode(apic) && offset == APIC_ICR) { + val = kvm_lapic_get_reg64(apic, APIC_ICR); kvm_apic_send_ipi(apic, (u32)val, (u32)(val >> 32)); trace_kvm_apic_write(APIC_ICR, val); } else { /* TODO: optimize to just emulate side effect w/o one more write */ + val = kvm_lapic_get_reg(apic, offset); kvm_lapic_reg_write(apic, offset, (u32)val); } } @@ -2394,11 +2510,15 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) } } - if (((old_value ^ value) & X2APIC_ENABLE) && (value & X2APIC_ENABLE)) - kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); + if ((old_value ^ value) & X2APIC_ENABLE) { + if (value & X2APIC_ENABLE) + kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); + else if (value & MSR_IA32_APICBASE_ENABLE) + kvm_apic_set_xapic_id(apic, vcpu->vcpu_id); + } if ((old_value ^ value) & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) { - kvm_vcpu_update_apicv(vcpu); + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); static_call_cond(kvm_x86_set_virtual_apic_mode)(vcpu); } @@ -2429,6 +2549,78 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) */ apic->isr_count = count_vectors(apic->regs + APIC_ISR); } + apic->highest_isr_cache = -1; +} + +int kvm_alloc_apic_access_page(struct kvm *kvm) +{ + struct page *page; + void __user *hva; + int ret = 0; + + mutex_lock(&kvm->slots_lock); + if (kvm->arch.apic_access_memslot_enabled || + kvm->arch.apic_access_memslot_inhibited) + goto out; + + hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); + if (IS_ERR(hva)) { + ret = PTR_ERR(hva); + goto out; + } + + page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); + if (is_error_page(page)) { + ret = -EFAULT; + goto out; + } + + /* + * Do not pin the page in memory, so that memory hot-unplug + * is able to migrate it. + */ + put_page(page); + kvm->arch.apic_access_memslot_enabled = true; +out: + mutex_unlock(&kvm->slots_lock); + return ret; +} +EXPORT_SYMBOL_GPL(kvm_alloc_apic_access_page); + +void kvm_inhibit_apic_access_page(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + if (!kvm->arch.apic_access_memslot_enabled) + return; + + kvm_vcpu_srcu_read_unlock(vcpu); + + mutex_lock(&kvm->slots_lock); + + if (kvm->arch.apic_access_memslot_enabled) { + __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0); + /* + * Clear "enabled" after the memslot is deleted so that a + * different vCPU doesn't get a false negative when checking + * the flag out of slots_lock. No additional memory barrier is + * needed as modifying memslots requires waiting other vCPUs to + * drop SRCU (see above), and false positives are ok as the + * flag is rechecked after acquiring slots_lock. + */ + kvm->arch.apic_access_memslot_enabled = false; + + /* + * Mark the memslot as inhibited to prevent reallocating the + * memslot during vCPU creation, e.g. if a vCPU is hotplugged. + */ + kvm->arch.apic_access_memslot_inhibited = true; + } + + mutex_unlock(&kvm->slots_lock); + + kvm_vcpu_srcu_read_lock(vcpu); } void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -2484,7 +2676,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_lapic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } kvm_apic_update_apicv(vcpu); - apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); @@ -2756,9 +2947,6 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) } memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s)); - if (!apic_x2apic_mode(apic)) - kvm_lapic_xapic_id_updated(apic); - atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); kvm_recalculate_apic_map(vcpu->kvm); kvm_apic_set_version(vcpu); @@ -2772,7 +2960,6 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) __start_apic_timer(apic, APIC_TMCCT); kvm_lapic_set_reg(apic, APIC_TMCCT, 0); kvm_apic_update_apicv(vcpu); - apic->highest_isr_cache = -1; if (apic->apicv_active) { static_call_cond(kvm_x86_apicv_post_state_restore)(vcpu); static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, apic_find_highest_irr(apic)); @@ -2943,13 +3130,17 @@ static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data) static int kvm_lapic_msr_write(struct kvm_lapic *apic, u32 reg, u64 data) { /* - * ICR is a 64-bit register in x2APIC mode (and Hyper'v PV vAPIC) and + * ICR is a 64-bit register in x2APIC mode (and Hyper-V PV vAPIC) and * can be written as such, all other registers remain accessible only * through 32-bit reads/writes. */ if (reg == APIC_ICR) return kvm_x2apic_icr_write(apic, data); + /* Bits 63:32 are reserved in all other registers. */ + if (data >> 32) + return 1; + return kvm_lapic_reg_write(apic, reg, (u32)data); } @@ -2972,9 +3163,6 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data) if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(apic)) return 1; - if (reg == APIC_DFR) - return 1; - return kvm_lapic_msr_read(apic, reg, data); } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 58c3242fcc7a..0a0ea4b5dd8c 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -112,6 +112,8 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, struct dest_map *dest_map); int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type); void kvm_apic_update_apicv(struct kvm_vcpu *vcpu); +int kvm_alloc_apic_access_page(struct kvm *kvm); +void kvm_inhibit_apic_access_page(struct kvm_vcpu *vcpu); bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map); @@ -144,6 +146,8 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len); void kvm_lapic_exit(void); +u64 kvm_lapic_readable_reg_mask(struct kvm_lapic *apic); + #define VEC_POS(v) ((v) & (32 - 1)) #define REG_POS(v) (((v) >> 5) << 4) diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 6bdaacb6faa0..168c46fd8dd1 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -230,14 +230,14 @@ static inline bool kvm_shadow_root_allocated(struct kvm *kvm) } #ifdef CONFIG_X86_64 -static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return kvm->arch.tdp_mmu_enabled; } +extern bool tdp_mmu_enabled; #else -static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return false; } +#define tdp_mmu_enabled false #endif static inline bool kvm_memslots_have_rmaps(struct kvm *kvm) { - return !is_tdp_mmu_enabled(kvm) || kvm_shadow_root_allocated(kvm); + return !tdp_mmu_enabled || kvm_shadow_root_allocated(kvm); } static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 835426254e76..c8ebe542c565 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -14,6 +14,7 @@ * Yaniv Kamay <yaniv@qumranet.com> * Avi Kivity <avi@qumranet.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "irq.h" #include "ioapic.h" @@ -43,6 +44,7 @@ #include <linux/uaccess.h> #include <linux/hash.h> #include <linux/kern_levels.h> +#include <linux/kstrtox.h> #include <linux/kthread.h> #include <asm/page.h> @@ -99,6 +101,13 @@ module_param_named(flush_on_reuse, force_flush_and_sync_on_reuse, bool, 0644); */ bool tdp_enabled = false; +static bool __ro_after_init tdp_mmu_allowed; + +#ifdef CONFIG_X86_64 +bool __read_mostly tdp_mmu_enabled = true; +module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0444); +#endif + static int max_huge_page_level __read_mostly; static int tdp_root_level __read_mostly; static int max_tdp_level __read_mostly; @@ -261,6 +270,17 @@ void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, kvm_flush_remote_tlbs_with_range(kvm, &range); } +static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index); + +/* Flush the range of guest memory mapped by the given SPTE. */ +static void kvm_flush_remote_tlbs_sptep(struct kvm *kvm, u64 *sptep) +{ + struct kvm_mmu_page *sp = sptep_to_sp(sptep); + gfn_t gfn = kvm_mmu_page_get_gfn(sp, spte_index(sptep)); + + kvm_flush_remote_tlbs_gfn(kvm, gfn, sp->role.level); +} + static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, unsigned int access) { @@ -609,9 +629,14 @@ static bool mmu_spte_age(u64 *sptep) return true; } +static inline bool is_tdp_mmu_active(struct kvm_vcpu *vcpu) +{ + return tdp_mmu_enabled && vcpu->arch.mmu->root_role.direct; +} + static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu) { - if (is_tdp_mmu(vcpu->arch.mmu)) { + if (is_tdp_mmu_active(vcpu)) { kvm_tdp_mmu_walk_lockless_begin(); } else { /* @@ -630,7 +655,7 @@ static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu) static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu) { - if (is_tdp_mmu(vcpu->arch.mmu)) { + if (is_tdp_mmu_active(vcpu)) { kvm_tdp_mmu_walk_lockless_end(); } else { /* @@ -800,7 +825,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_disallow_lpage(slot, gfn); if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K)) - kvm_flush_remote_tlbs_with_address(kvm, gfn, 1); + kvm_flush_remote_tlbs_gfn(kvm, gfn, PG_LEVEL_4K); } void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) @@ -1174,8 +1199,7 @@ static void drop_large_spte(struct kvm *kvm, u64 *sptep, bool flush) drop_spte(kvm, sptep); if (flush) - kvm_flush_remote_tlbs_with_address(kvm, sp->gfn, - KVM_PAGES_PER_HPAGE(sp->role.level)); + kvm_flush_remote_tlbs_sptep(kvm, sptep); } /* @@ -1279,7 +1303,7 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, { struct kvm_rmap_head *rmap_head; - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, true); @@ -1312,7 +1336,7 @@ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, { struct kvm_rmap_head *rmap_head; - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, false); @@ -1395,7 +1419,7 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, } } - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) write_protected |= kvm_tdp_mmu_write_protect_gfn(kvm, slot, gfn, min_level); @@ -1456,7 +1480,7 @@ restart: } if (need_flush && kvm_available_flush_tlb_with_range()) { - kvm_flush_remote_tlbs_with_address(kvm, gfn, 1); + kvm_flush_remote_tlbs_gfn(kvm, gfn, level); return false; } @@ -1558,7 +1582,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) if (kvm_memslots_have_rmaps(kvm)) flush = kvm_handle_gfn_range(kvm, range, kvm_zap_rmap); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); return flush; @@ -1571,7 +1595,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (kvm_memslots_have_rmaps(kvm)) flush = kvm_handle_gfn_range(kvm, range, kvm_set_pte_rmap); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) flush |= kvm_tdp_mmu_set_spte_gfn(kvm, range); return flush; @@ -1626,8 +1650,7 @@ static void __rmap_add(struct kvm *kvm, kvm->stat.max_mmu_rmap_size = rmap_count; if (rmap_count > RMAP_RECYCLE_THRESHOLD) { kvm_zap_all_rmap_sptes(kvm, rmap_head); - kvm_flush_remote_tlbs_with_address( - kvm, sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level)); + kvm_flush_remote_tlbs_gfn(kvm, gfn, sp->role.level); } } @@ -1646,7 +1669,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (kvm_memslots_have_rmaps(kvm)) young = kvm_handle_gfn_range(kvm, range, kvm_age_rmap); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) young |= kvm_tdp_mmu_age_gfn_range(kvm, range); return young; @@ -1659,7 +1682,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (kvm_memslots_have_rmaps(kvm)) young = kvm_handle_gfn_range(kvm, range, kvm_test_age_rmap); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) young |= kvm_tdp_mmu_test_age_gfn(kvm, range); return young; @@ -1921,7 +1944,7 @@ static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) return true; /* TDP MMU pages do not use the MMU generation. */ - return !sp->tdp_mmu_page && + return !is_tdp_mmu_page(sp) && unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); } @@ -2355,7 +2378,16 @@ static void __link_shadow_page(struct kvm *kvm, mmu_page_add_parent_pte(cache, sp, sptep); - if (sp->unsync_children || sp->unsync) + /* + * The non-direct sub-pagetable must be updated before linking. For + * L1 sp, the pagetable is updated via kvm_sync_page() in + * kvm_mmu_find_shadow_page() without write-protecting the gfn, + * so sp->unsync can be true or false. For higher level non-direct + * sp, the pagetable is updated/synced via mmu_sync_children() in + * FNAME(fetch)(), so sp->unsync_children can only be false. + * WARN_ON_ONCE() if anything happens unexpectedly. + */ + if (WARN_ON_ONCE(sp->unsync_children) || sp->unsync) mark_unsync(sptep); } @@ -2383,7 +2415,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, return; drop_parent_pte(child, sptep); - kvm_flush_remote_tlbs_with_address(vcpu->kvm, child->gfn, 1); + kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep); } } @@ -2867,8 +2899,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, } if (flush) - kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn, - KVM_PAGES_PER_HPAGE(level)); + kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level); pgprintk("%s: setting spte %llx\n", __func__, *sptep); @@ -3116,11 +3147,11 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_ !is_large_pte(spte) && spte_to_child_sp(spte)->nx_huge_page_disallowed) { /* - * A small SPTE exists for this pfn, but FNAME(fetch) - * and __direct_map would like to create a large PTE - * instead: just force them to go down another level, - * patching back for them into pfn the next 9 bits of - * the address. + * A small SPTE exists for this pfn, but FNAME(fetch), + * direct_map(), or kvm_tdp_mmu_map() would like to create a + * large PTE instead: just force them to go down another level, + * patching back for them into pfn the next 9 bits of the + * address. */ u64 page_mask = KVM_PAGES_PER_HPAGE(cur_level) - KVM_PAGES_PER_HPAGE(cur_level - 1); @@ -3129,7 +3160,7 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_ } } -static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +static int direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; @@ -3147,7 +3178,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (fault->nx_huge_page_workaround_enabled) disallowed_hugepage_adjust(fault, *it.sptep, it.level); - base_gfn = fault->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + base_gfn = gfn_round_for_level(fault->gfn, it.level); if (it.level == fault->goal_level) break; @@ -3173,14 +3204,16 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) return ret; } -static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk) +static void kvm_send_hwpoison_signal(struct kvm_memory_slot *slot, gfn_t gfn) { - send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, PAGE_SHIFT, tsk); + unsigned long hva = gfn_to_hva_memslot(slot, gfn); + + send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva, PAGE_SHIFT, current); } -static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) +static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - if (is_sigpending_pfn(pfn)) { + if (is_sigpending_pfn(fault->pfn)) { kvm_handle_signal_exit(vcpu); return -EINTR; } @@ -3190,43 +3223,43 @@ static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) * into the spte otherwise read access on readonly gfn also can * caused mmio page fault and treat it as mmio access. */ - if (pfn == KVM_PFN_ERR_RO_FAULT) + if (fault->pfn == KVM_PFN_ERR_RO_FAULT) return RET_PF_EMULATE; - if (pfn == KVM_PFN_ERR_HWPOISON) { - kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current); + if (fault->pfn == KVM_PFN_ERR_HWPOISON) { + kvm_send_hwpoison_signal(fault->slot, fault->gfn); return RET_PF_RETRY; } return -EFAULT; } -static int handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, - unsigned int access) +static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault, + unsigned int access) { - /* The pfn is invalid, report the error! */ - if (unlikely(is_error_pfn(fault->pfn))) - return kvm_handle_error_pfn(vcpu, fault->gfn, fault->pfn); + gva_t gva = fault->is_tdp ? 0 : fault->addr; - if (unlikely(!fault->slot)) { - gva_t gva = fault->is_tdp ? 0 : fault->addr; + vcpu_cache_mmio_info(vcpu, gva, fault->gfn, + access & shadow_mmio_access_mask); - vcpu_cache_mmio_info(vcpu, gva, fault->gfn, - access & shadow_mmio_access_mask); - /* - * If MMIO caching is disabled, emulate immediately without - * touching the shadow page tables as attempting to install an - * MMIO SPTE will just be an expensive nop. Do not cache MMIO - * whose gfn is greater than host.MAXPHYADDR, any guest that - * generates such gfns is running nested and is being tricked - * by L0 userspace (you can observe gfn > L1.MAXPHYADDR if - * and only if L1's MAXPHYADDR is inaccurate with respect to - * the hardware's). - */ - if (unlikely(!enable_mmio_caching) || - unlikely(fault->gfn > kvm_mmu_max_gfn())) - return RET_PF_EMULATE; - } + /* + * If MMIO caching is disabled, emulate immediately without + * touching the shadow page tables as attempting to install an + * MMIO SPTE will just be an expensive nop. + */ + if (unlikely(!enable_mmio_caching)) + return RET_PF_EMULATE; + + /* + * Do not create an MMIO SPTE for a gfn greater than host.MAXPHYADDR, + * any guest that generates such gfns is running nested and is being + * tricked by L0 userspace (you can observe gfn > L1.MAXPHYADDR if and + * only if L1's MAXPHYADDR is inaccurate with respect to the + * hardware's). + */ + if (unlikely(fault->gfn > kvm_mmu_max_gfn())) + return RET_PF_EMULATE; return RET_PF_CONTINUE; } @@ -3350,7 +3383,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) do { u64 new_spte; - if (is_tdp_mmu(vcpu->arch.mmu)) + if (tdp_mmu_enabled) sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, fault->addr, &spte); else sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte); @@ -3433,8 +3466,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) } if (++retry_count > 4) { - printk_once(KERN_WARNING - "kvm: Fast #PF retrying more than 4 times.\n"); + pr_warn_once("Fast #PF retrying more than 4 times.\n"); break; } @@ -3596,7 +3628,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) if (r < 0) goto out_unlock; - if (is_tdp_mmu_enabled(vcpu->kvm)) { + if (tdp_mmu_enabled) { root = kvm_tdp_mmu_get_vcpu_root_hpa(vcpu); mmu->root.hpa = root; } else if (shadow_root_level >= PT64_ROOT_4LEVEL) { @@ -4026,7 +4058,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) walk_shadow_page_lockless_begin(vcpu); - if (is_tdp_mmu(vcpu->arch.mmu)) + if (is_tdp_mmu_active(vcpu)) leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root); else leaf = get_walk(vcpu, addr, sptes, &root); @@ -4174,7 +4206,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true); } -static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; bool async; @@ -4235,12 +4267,33 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) return RET_PF_CONTINUE; } +static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, + unsigned int access) +{ + int ret; + + fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq; + smp_rmb(); + + ret = __kvm_faultin_pfn(vcpu, fault); + if (ret != RET_PF_CONTINUE) + return ret; + + if (unlikely(is_error_pfn(fault->pfn))) + return kvm_handle_error_pfn(vcpu, fault); + + if (unlikely(!fault->slot)) + return kvm_handle_noslot_fault(vcpu, fault, access); + + return RET_PF_CONTINUE; +} + /* * Returns true if the page fault is stale and needs to be retried, i.e. if the * root was invalidated by a memslot update or a relevant mmu_notifier fired. */ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, - struct kvm_page_fault *fault, int mmu_seq) + struct kvm_page_fault *fault) { struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root.hpa); @@ -4260,19 +4313,13 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, return true; return fault->slot && - mmu_invalidate_retry_hva(vcpu->kvm, mmu_seq, fault->hva); + mmu_invalidate_retry_hva(vcpu->kvm, fault->mmu_seq, fault->hva); } static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu); - - unsigned long mmu_seq; int r; - fault->gfn = fault->addr >> PAGE_SHIFT; - fault->slot = kvm_vcpu_gfn_to_memslot(vcpu, fault->gfn); - if (page_fault_handle_page_track(vcpu, fault)) return RET_PF_EMULATE; @@ -4284,41 +4331,24 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (r) return r; - mmu_seq = vcpu->kvm->mmu_invalidate_seq; - smp_rmb(); - - r = kvm_faultin_pfn(vcpu, fault); - if (r != RET_PF_CONTINUE) - return r; - - r = handle_abnormal_pfn(vcpu, fault, ACC_ALL); + r = kvm_faultin_pfn(vcpu, fault, ACC_ALL); if (r != RET_PF_CONTINUE) return r; r = RET_PF_RETRY; + write_lock(&vcpu->kvm->mmu_lock); - if (is_tdp_mmu_fault) - read_lock(&vcpu->kvm->mmu_lock); - else - write_lock(&vcpu->kvm->mmu_lock); + if (is_page_fault_stale(vcpu, fault)) + goto out_unlock; - if (is_page_fault_stale(vcpu, fault, mmu_seq)) + r = make_mmu_pages_available(vcpu); + if (r) goto out_unlock; - if (is_tdp_mmu_fault) { - r = kvm_tdp_mmu_map(vcpu, fault); - } else { - r = make_mmu_pages_available(vcpu); - if (r) - goto out_unlock; - r = __direct_map(vcpu, fault); - } + r = direct_map(vcpu, fault); out_unlock: - if (is_tdp_mmu_fault) - read_unlock(&vcpu->kvm->mmu_lock); - else - write_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(fault->pfn); return r; } @@ -4366,6 +4396,42 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, } EXPORT_SYMBOL_GPL(kvm_handle_page_fault); +#ifdef CONFIG_X86_64 +static int kvm_tdp_mmu_page_fault(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + int r; + + if (page_fault_handle_page_track(vcpu, fault)) + return RET_PF_EMULATE; + + r = fast_page_fault(vcpu, fault); + if (r != RET_PF_INVALID) + return r; + + r = mmu_topup_memory_caches(vcpu, false); + if (r) + return r; + + r = kvm_faultin_pfn(vcpu, fault, ACC_ALL); + if (r != RET_PF_CONTINUE) + return r; + + r = RET_PF_RETRY; + read_lock(&vcpu->kvm->mmu_lock); + + if (is_page_fault_stale(vcpu, fault)) + goto out_unlock; + + r = kvm_tdp_mmu_map(vcpu, fault); + +out_unlock: + read_unlock(&vcpu->kvm->mmu_lock); + kvm_release_pfn_clean(fault->pfn); + return r; +} +#endif + int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { /* @@ -4383,13 +4449,19 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (shadow_memtype_mask && kvm_arch_has_noncoherent_dma(vcpu->kvm)) { for ( ; fault->max_level > PG_LEVEL_4K; --fault->max_level) { int page_num = KVM_PAGES_PER_HPAGE(fault->max_level); - gfn_t base = (fault->addr >> PAGE_SHIFT) & ~(page_num - 1); + gfn_t base = gfn_round_for_level(fault->gfn, + fault->max_level); if (kvm_mtrr_check_gfn_range_consistency(vcpu, base, page_num)) break; } } +#ifdef CONFIG_X86_64 + if (tdp_mmu_enabled) + return kvm_tdp_mmu_page_fault(vcpu, fault); +#endif + return direct_page_fault(vcpu, fault); } @@ -4494,10 +4566,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd) struct kvm_mmu *mmu = vcpu->arch.mmu; union kvm_mmu_page_role new_role = mmu->root_role; - if (!fast_pgd_switch(vcpu->kvm, mmu, new_pgd, new_role)) { - /* kvm_mmu_ensure_valid_pgd will set up a new root. */ + /* + * Return immediately if no usable root was found, kvm_mmu_reload() + * will establish a valid root prior to the next VM-Enter. + */ + if (!fast_pgd_switch(vcpu->kvm, mmu, new_pgd, new_role)) return; - } /* * It's possible that the cached previous root page is obsolete because @@ -5719,6 +5793,9 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, tdp_root_level = tdp_forced_root_level; max_tdp_level = tdp_max_root_level; +#ifdef CONFIG_X86_64 + tdp_mmu_enabled = tdp_mmu_allowed && tdp_enabled; +#endif /* * max_huge_page_level reflects KVM's MMU capabilities irrespective * of kernel support, e.g. KVM may be capable of using 1GB pages when @@ -5966,7 +6043,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) * write and in the same critical section as making the reload request, * e.g. before kvm_zap_obsolete_pages() could drop mmu_lock and yield. */ - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_invalidate_all_roots(kvm); /* @@ -5991,7 +6068,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) * Deferring the zap until the final reference to the root is put would * lead to use-after-free. */ - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_zap_invalidated_roots(kvm); } @@ -6017,9 +6094,11 @@ int kvm_mmu_init_vm(struct kvm *kvm) INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages); spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); - r = kvm_mmu_init_tdp_mmu(kvm); - if (r < 0) - return r; + if (tdp_mmu_enabled) { + r = kvm_mmu_init_tdp_mmu(kvm); + if (r < 0) + return r; + } node->track_write = kvm_mmu_pte_write; node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot; @@ -6049,7 +6128,8 @@ void kvm_mmu_uninit_vm(struct kvm *kvm) kvm_page_track_unregister_notifier(kvm, node); - kvm_mmu_uninit_tdp_mmu(kvm); + if (tdp_mmu_enabled) + kvm_mmu_uninit_tdp_mmu(kvm); mmu_free_vm_memory_caches(kvm); } @@ -6103,7 +6183,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); - if (is_tdp_mmu_enabled(kvm)) { + if (tdp_mmu_enabled) { for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start, gfn_end, true, flush); @@ -6136,7 +6216,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, write_unlock(&kvm->mmu_lock); } - if (is_tdp_mmu_enabled(kvm)) { + if (tdp_mmu_enabled) { read_lock(&kvm->mmu_lock); kvm_tdp_mmu_wrprot_slot(kvm, memslot, start_level); read_unlock(&kvm->mmu_lock); @@ -6379,7 +6459,7 @@ void kvm_mmu_try_split_huge_pages(struct kvm *kvm, u64 start, u64 end, int target_level) { - if (!is_tdp_mmu_enabled(kvm)) + if (!tdp_mmu_enabled) return; if (kvm_memslots_have_rmaps(kvm)) @@ -6400,7 +6480,7 @@ void kvm_mmu_slot_try_split_huge_pages(struct kvm *kvm, u64 start = memslot->base_gfn; u64 end = start + memslot->npages; - if (!is_tdp_mmu_enabled(kvm)) + if (!tdp_mmu_enabled) return; if (kvm_memslots_have_rmaps(kvm)) { @@ -6450,8 +6530,7 @@ restart: kvm_zap_one_rmap_spte(kvm, rmap_head, sptep); if (kvm_available_flush_tlb_with_range()) - kvm_flush_remote_tlbs_with_address(kvm, sp->gfn, - KVM_PAGES_PER_HPAGE(sp->role.level)); + kvm_flush_remote_tlbs_sptep(kvm, sptep); else need_tlb_flush = 1; @@ -6483,7 +6562,7 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, write_unlock(&kvm->mmu_lock); } - if (is_tdp_mmu_enabled(kvm)) { + if (tdp_mmu_enabled) { read_lock(&kvm->mmu_lock); kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot); read_unlock(&kvm->mmu_lock); @@ -6518,7 +6597,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, write_unlock(&kvm->mmu_lock); } - if (is_tdp_mmu_enabled(kvm)) { + if (tdp_mmu_enabled) { read_lock(&kvm->mmu_lock); kvm_tdp_mmu_clear_dirty_slot(kvm, memslot); read_unlock(&kvm->mmu_lock); @@ -6553,7 +6632,7 @@ restart: kvm_mmu_commit_zap_page(kvm, &invalid_list); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_zap_all(kvm); write_unlock(&kvm->mmu_lock); @@ -6579,7 +6658,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) * zap all shadow pages. */ if (unlikely(gen == 0)) { - kvm_debug_ratelimited("kvm: zapping shadow pages for mmio generation wraparound\n"); + kvm_debug_ratelimited("zapping shadow pages for mmio generation wraparound\n"); kvm_mmu_zap_all_fast(kvm); } } @@ -6684,7 +6763,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) new_val = 1; else if (sysfs_streq(val, "auto")) new_val = get_nx_auto_mode(); - else if (strtobool(val, &new_val) < 0) + else if (kstrtobool(val, &new_val) < 0) return -EINVAL; __set_nx_huge_pages(new_val); @@ -6718,6 +6797,13 @@ void __init kvm_mmu_x86_module_init(void) if (nx_huge_pages == -1) __set_nx_huge_pages(get_nx_auto_mode()); + /* + * Snapshot userspace's desire to enable the TDP MMU. Whether or not the + * TDP MMU is actually enabled is determined in kvm_configure_mmu() + * when the vendor module is loaded. + */ + tdp_mmu_allowed = tdp_mmu_enabled; + kvm_mmu_spte_module_init(); } diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index dbaf6755c5a7..cc58631e2336 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -156,6 +156,11 @@ static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp) return kvm_x86_ops.cpu_dirty_log_size && sp->role.guest_mode; } +static inline gfn_t gfn_round_for_level(gfn_t gfn, int level) +{ + return gfn & -KVM_PAGES_PER_HPAGE(level); +} + int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, bool can_unsync, bool prefetch); @@ -164,8 +169,17 @@ void kvm_mmu_gfn_allow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn, int min_level); + void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, u64 start_gfn, u64 pages); + +/* Flush the given page (huge or not) of guest memory. */ +static inline void kvm_flush_remote_tlbs_gfn(struct kvm *kvm, gfn_t gfn, int level) +{ + kvm_flush_remote_tlbs_with_address(kvm, gfn_round_for_level(gfn, level), + KVM_PAGES_PER_HPAGE(level)); +} + unsigned int pte_list_count(struct kvm_rmap_head *rmap_head); extern int nx_huge_pages; @@ -199,7 +213,7 @@ struct kvm_page_fault { /* * Maximum page size that can be created for this fault; input to - * FNAME(fetch), __direct_map and kvm_tdp_mmu_map. + * FNAME(fetch), direct_map() and kvm_tdp_mmu_map(). */ u8 max_level; @@ -222,6 +236,7 @@ struct kvm_page_fault { struct kvm_memory_slot *slot; /* Outputs of kvm_faultin_pfn. */ + unsigned long mmu_seq; kvm_pfn_t pfn; hva_t hva; bool map_writable; @@ -279,6 +294,11 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, }; int r; + if (vcpu->arch.mmu->root_role.direct) { + fault.gfn = fault.addr >> PAGE_SHIFT; + fault.slot = kvm_vcpu_gfn_to_memslot(vcpu, fault.gfn); + } + /* * Async #PF "faults", a.k.a. prefetch faults, are not faults from the * guest perspective and have already been counted at the time of the diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 2e09d1b6249f..0a2ac438d647 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -10,6 +10,7 @@ * Author: * Xiao Guangrong <guangrong.xiao@linux.intel.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/rculist.h> diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 0f6455072055..57f0b75c80f9 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -642,12 +642,12 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) goto out_gpte_changed; - for (shadow_walk_init(&it, vcpu, fault->addr); - shadow_walk_okay(&it) && it.level > gw->level; - shadow_walk_next(&it)) { + for_each_shadow_entry(vcpu, fault->addr, it) { gfn_t table_gfn; clear_sp_write_flooding_count(it.sptep); + if (it.level == gw->level) + break; table_gfn = gw->table_gfn[it.level - 2]; access = gw->pt_access[it.level - 2]; @@ -692,8 +692,6 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, trace_kvm_mmu_spte_requested(fault); for (; shadow_walk_okay(&it); shadow_walk_next(&it)) { - clear_sp_write_flooding_count(it.sptep); - /* * We cannot overwrite existing page tables with an NX * large page, as the leaf could be executable. @@ -701,7 +699,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (fault->nx_huge_page_workaround_enabled) disallowed_hugepage_adjust(fault, *it.sptep, it.level); - base_gfn = fault->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + base_gfn = gfn_round_for_level(fault->gfn, it.level); if (it.level == fault->goal_level) break; @@ -791,7 +789,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault { struct guest_walker walker; int r; - unsigned long mmu_seq; bool is_self_change_mapping; pgprintk("%s: addr %lx err %x\n", __func__, fault->addr, fault->error_code); @@ -838,14 +835,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault else fault->max_level = walker.level; - mmu_seq = vcpu->kvm->mmu_invalidate_seq; - smp_rmb(); - - r = kvm_faultin_pfn(vcpu, fault); - if (r != RET_PF_CONTINUE) - return r; - - r = handle_abnormal_pfn(vcpu, fault, walker.pte_access); + r = kvm_faultin_pfn(vcpu, fault, walker.pte_access); if (r != RET_PF_CONTINUE) return r; @@ -871,7 +861,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault r = RET_PF_RETRY; write_lock(&vcpu->kvm->mmu_lock); - if (is_page_fault_stale(vcpu, fault, mmu_seq)) + if (is_page_fault_stale(vcpu, fault)) goto out_unlock; r = make_mmu_pages_available(vcpu); @@ -937,8 +927,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) mmu_page_zap_pte(vcpu->kvm, sp, sptep, NULL); if (is_shadow_present_pte(old_spte)) - kvm_flush_remote_tlbs_with_address(vcpu->kvm, - sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level)); + kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep); if (!rmap_can_add(vcpu)) break; diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index c0fd7e049b4e..c15bfca3ed15 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -7,7 +7,7 @@ * Copyright (C) 2006 Qumranet, Inc. * Copyright 2020 Red Hat, Inc. and/or its affiliates. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "mmu.h" @@ -147,9 +147,9 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, WARN_ON_ONCE(!pte_access && !shadow_present_mask); if (sp->role.ad_disabled) - spte |= SPTE_TDP_AD_DISABLED_MASK; + spte |= SPTE_TDP_AD_DISABLED; else if (kvm_mmu_page_ad_need_write_protect(sp)) - spte |= SPTE_TDP_AD_WRPROT_ONLY_MASK; + spte |= SPTE_TDP_AD_WRPROT_ONLY; /* * For the EPT case, shadow_present_mask is 0 if hardware @@ -317,7 +317,7 @@ u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled) shadow_user_mask | shadow_x_mask | shadow_me_value; if (ad_disabled) - spte |= SPTE_TDP_AD_DISABLED_MASK; + spte |= SPTE_TDP_AD_DISABLED; else spte |= shadow_accessed_mask; @@ -352,7 +352,7 @@ u64 mark_spte_for_access_track(u64 spte) WARN_ONCE(spte & (SHADOW_ACC_TRACK_SAVED_BITS_MASK << SHADOW_ACC_TRACK_SAVED_BITS_SHIFT), - "kvm: Access Tracking saved bit locations are not zero\n"); + "Access Tracking saved bit locations are not zero\n"); spte |= (spte & SHADOW_ACC_TRACK_SAVED_BITS_MASK) << SHADOW_ACC_TRACK_SAVED_BITS_SHIFT; diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 6f54dc9409c9..1279db2eab44 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -28,10 +28,10 @@ */ #define SPTE_TDP_AD_SHIFT 52 #define SPTE_TDP_AD_MASK (3ULL << SPTE_TDP_AD_SHIFT) -#define SPTE_TDP_AD_ENABLED_MASK (0ULL << SPTE_TDP_AD_SHIFT) -#define SPTE_TDP_AD_DISABLED_MASK (1ULL << SPTE_TDP_AD_SHIFT) -#define SPTE_TDP_AD_WRPROT_ONLY_MASK (2ULL << SPTE_TDP_AD_SHIFT) -static_assert(SPTE_TDP_AD_ENABLED_MASK == 0); +#define SPTE_TDP_AD_ENABLED (0ULL << SPTE_TDP_AD_SHIFT) +#define SPTE_TDP_AD_DISABLED (1ULL << SPTE_TDP_AD_SHIFT) +#define SPTE_TDP_AD_WRPROT_ONLY (2ULL << SPTE_TDP_AD_SHIFT) +static_assert(SPTE_TDP_AD_ENABLED == 0); #ifdef CONFIG_DYNAMIC_PHYSICAL_MASK #define SPTE_BASE_ADDR_MASK (physical_mask & ~(u64)(PAGE_SIZE-1)) @@ -164,7 +164,7 @@ extern u64 __read_mostly shadow_me_value; extern u64 __read_mostly shadow_me_mask; /* - * SPTEs in MMUs without A/D bits are marked with SPTE_TDP_AD_DISABLED_MASK; + * SPTEs in MMUs without A/D bits are marked with SPTE_TDP_AD_DISABLED; * shadow_acc_track_mask is the set of bits to be cleared in non-accessed * pages. */ @@ -266,18 +266,18 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) static inline bool spte_ad_enabled(u64 spte) { MMU_WARN_ON(!is_shadow_present_pte(spte)); - return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_DISABLED_MASK; + return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_DISABLED; } static inline bool spte_ad_need_write_protect(u64 spte) { MMU_WARN_ON(!is_shadow_present_pte(spte)); /* - * This is benign for non-TDP SPTEs as SPTE_TDP_AD_ENABLED_MASK is '0', + * This is benign for non-TDP SPTEs as SPTE_TDP_AD_ENABLED is '0', * and non-TDP SPTEs will never set these bits. Optimize for 64-bit * TDP and do the A/D type check unconditionally. */ - return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_ENABLED_MASK; + return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_ENABLED; } static inline u64 spte_shadow_accessed_mask(u64 spte) @@ -435,11 +435,11 @@ static inline void check_spte_writable_invariants(u64 spte) { if (spte & shadow_mmu_writable_mask) WARN_ONCE(!(spte & shadow_host_writable_mask), - "kvm: MMU-writable SPTE is not Host-writable: %llx", + KBUILD_MODNAME ": MMU-writable SPTE is not Host-writable: %llx", spte); else WARN_ONCE(is_writable_pte(spte), - "kvm: Writable SPTE is not MMU-writable: %llx", spte); + KBUILD_MODNAME ": Writable SPTE is not MMU-writable: %llx", spte); } static inline bool is_mmu_writable_spte(u64 spte) diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index 39b48e7d7d1a..d2eb0d4f8710 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "mmu_internal.h" #include "tdp_iter.h" @@ -15,11 +16,6 @@ static void tdp_iter_refresh_sptep(struct tdp_iter *iter) iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep); } -static gfn_t round_gfn_for_level(gfn_t gfn, int level) -{ - return gfn & -KVM_PAGES_PER_HPAGE(level); -} - /* * Return the TDP iterator to the root PT and allow it to continue its * traversal over the paging structure from there. @@ -30,7 +26,7 @@ void tdp_iter_restart(struct tdp_iter *iter) iter->yielded_gfn = iter->next_last_level_gfn; iter->level = iter->root_level; - iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level); + iter->gfn = gfn_round_for_level(iter->next_last_level_gfn, iter->level); tdp_iter_refresh_sptep(iter); iter->valid = true; @@ -97,7 +93,7 @@ static bool try_step_down(struct tdp_iter *iter) iter->level--; iter->pt_path[iter->level - 1] = child_pt; - iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level); + iter->gfn = gfn_round_for_level(iter->next_last_level_gfn, iter->level); tdp_iter_refresh_sptep(iter); return true; @@ -139,7 +135,7 @@ static bool try_step_up(struct tdp_iter *iter) return false; iter->level++; - iter->gfn = round_gfn_for_level(iter->gfn, iter->level); + iter->gfn = gfn_round_for_level(iter->gfn, iter->level); tdp_iter_refresh_sptep(iter); return true; diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index d6df38d371a0..7c25dbf32ecc 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "mmu.h" #include "mmu_internal.h" @@ -10,23 +11,15 @@ #include <asm/cmpxchg.h> #include <trace/events/kvm.h> -static bool __read_mostly tdp_mmu_enabled = true; -module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644); - /* Initializes the TDP MMU for the VM, if enabled. */ int kvm_mmu_init_tdp_mmu(struct kvm *kvm) { struct workqueue_struct *wq; - if (!tdp_enabled || !READ_ONCE(tdp_mmu_enabled)) - return 0; - wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0); if (!wq) return -ENOMEM; - /* This should not be changed for the lifetime of the VM. */ - kvm->arch.tdp_mmu_enabled = true; INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); kvm->arch.tdp_mmu_zap_wq = wq; @@ -47,9 +40,6 @@ static __always_inline bool kvm_lockdep_assert_mmu_lock_held(struct kvm *kvm, void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) { - if (!kvm->arch.tdp_mmu_enabled) - return; - /* Also waits for any queued work items. */ destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); @@ -144,7 +134,7 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) return; - WARN_ON(!root->tdp_mmu_page); + WARN_ON(!is_tdp_mmu_page(root)); /* * The root now has refcount=0. It is valid, but readers already @@ -690,8 +680,7 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, if (ret) return ret; - kvm_flush_remote_tlbs_with_address(kvm, iter->gfn, - KVM_PAGES_PER_HPAGE(iter->level)); + kvm_flush_remote_tlbs_gfn(kvm, iter->gfn, iter->level); /* * No other thread can overwrite the removed SPTE as they must either @@ -1090,8 +1079,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, return RET_PF_RETRY; else if (is_shadow_present_pte(iter->old_spte) && !is_last_spte(iter->old_spte, iter->level)) - kvm_flush_remote_tlbs_with_address(vcpu->kvm, sp->gfn, - KVM_PAGES_PER_HPAGE(iter->level + 1)); + kvm_flush_remote_tlbs_gfn(vcpu->kvm, iter->gfn, iter->level); /* * If the page fault was caused by a write but the page is write diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index d3714200b932..0a63b1afabd3 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -7,6 +7,9 @@ #include "spte.h" +int kvm_mmu_init_tdp_mmu(struct kvm *kvm); +void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); + hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) @@ -68,31 +71,9 @@ u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, u64 addr, u64 *spte); #ifdef CONFIG_X86_64 -int kvm_mmu_init_tdp_mmu(struct kvm *kvm); -void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return sp->tdp_mmu_page; } - -static inline bool is_tdp_mmu(struct kvm_mmu *mmu) -{ - struct kvm_mmu_page *sp; - hpa_t hpa = mmu->root.hpa; - - if (WARN_ON(!VALID_PAGE(hpa))) - return false; - - /* - * A NULL shadow page is legal when shadowing a non-paging guest with - * PAE paging, as the MMU will be direct with root_hpa pointing at the - * pae_root page, not a shadow page. - */ - sp = to_shadow_page(hpa); - return sp && is_tdp_mmu_page(sp) && sp->root_count; -} #else -static inline int kvm_mmu_init_tdp_mmu(struct kvm *kvm) { return 0; } -static inline void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) {} static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; } -static inline bool is_tdp_mmu(struct kvm_mmu *mmu) { return false; } #endif #endif /* __KVM_X86_MMU_TDP_MMU_H */ diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index a8502e02f479..9fac1ec03463 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -13,6 +13,7 @@ * Paolo Bonzini <pbonzini@redhat.com> * Xiao Guangrong <guangrong.xiao@linux.intel.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <asm/mtrr.h> diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index eb594620dd75..612e6c70ce2e 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -9,6 +9,7 @@ * Gleb Natapov <gleb@redhat.com> * Wei Huang <wei@redhat.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/kvm_host.h> @@ -28,9 +29,18 @@ struct x86_pmu_capability __read_mostly kvm_pmu_cap; EXPORT_SYMBOL_GPL(kvm_pmu_cap); -static const struct x86_cpu_id vmx_icl_pebs_cpu[] = { +/* Precise Distribution of Instructions Retired (PDIR) */ +static const struct x86_cpu_id vmx_pebs_pdir_cpu[] = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, NULL), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, NULL), + /* Instruction-Accurate PDIR (PDIR++) */ + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, NULL), + {} +}; + +/* Precise Distribution (PDist) */ +static const struct x86_cpu_id vmx_pebs_pdist_cpu[] = { + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, NULL), {} }; @@ -155,6 +165,28 @@ static void kvm_perf_overflow(struct perf_event *perf_event, kvm_make_request(KVM_REQ_PMU, pmc->vcpu); } +static u64 pmc_get_pebs_precise_level(struct kvm_pmc *pmc) +{ + /* + * For some model specific pebs counters with special capabilities + * (PDIR, PDIR++, PDIST), KVM needs to raise the event precise + * level to the maximum value (currently 3, backwards compatible) + * so that the perf subsystem would assign specific hardware counter + * with that capability for vPMC. + */ + if ((pmc->idx == 0 && x86_match_cpu(vmx_pebs_pdist_cpu)) || + (pmc->idx == 32 && x86_match_cpu(vmx_pebs_pdir_cpu))) + return 3; + + /* + * The non-zero precision level of guest event makes the ordinary + * guest event becomes a guest PEBS event and triggers the host + * PEBS PMI handler to determine whether the PEBS overflow PMI + * comes from the host counters or the guest. + */ + return 1; +} + static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, bool exclude_user, bool exclude_kernel, bool intr) @@ -186,22 +218,12 @@ static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, } if (pebs) { /* - * The non-zero precision level of guest event makes the ordinary - * guest event becomes a guest PEBS event and triggers the host - * PEBS PMI handler to determine whether the PEBS overflow PMI - * comes from the host counters or the guest. - * * For most PEBS hardware events, the difference in the software * precision levels of guest and host PEBS events will not affect * the accuracy of the PEBS profiling result, because the "event IP" * in the PEBS record is calibrated on the guest side. - * - * On Icelake everything is fine. Other hardware (GLC+, TNT+) that - * could possibly care here is unsupported and needs changes. */ - attr.precise_ip = 1; - if (x86_match_cpu(vmx_icl_pebs_cpu) && pmc->idx == 32) - attr.precise_ip = 3; + attr.precise_ip = pmc_get_pebs_precise_level(pmc); } event = perf_event_create_kernel_counter(&attr, -1, current, @@ -254,48 +276,128 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) return true; } -static int cmp_u64(const void *pa, const void *pb) +static int filter_cmp(const void *pa, const void *pb, u64 mask) { - u64 a = *(u64 *)pa; - u64 b = *(u64 *)pb; + u64 a = *(u64 *)pa & mask; + u64 b = *(u64 *)pb & mask; return (a > b) - (a < b); } + +static int filter_sort_cmp(const void *pa, const void *pb) +{ + return filter_cmp(pa, pb, (KVM_PMU_MASKED_ENTRY_EVENT_SELECT | + KVM_PMU_MASKED_ENTRY_EXCLUDE)); +} + +/* + * For the event filter, searching is done on the 'includes' list and + * 'excludes' list separately rather than on the 'events' list (which + * has both). As a result the exclude bit can be ignored. + */ +static int filter_event_cmp(const void *pa, const void *pb) +{ + return filter_cmp(pa, pb, (KVM_PMU_MASKED_ENTRY_EVENT_SELECT)); +} + +static int find_filter_index(u64 *events, u64 nevents, u64 key) +{ + u64 *fe = bsearch(&key, events, nevents, sizeof(events[0]), + filter_event_cmp); + + if (!fe) + return -1; + + return fe - events; +} + +static bool is_filter_entry_match(u64 filter_event, u64 umask) +{ + u64 mask = filter_event >> (KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT - 8); + u64 match = filter_event & KVM_PMU_MASKED_ENTRY_UMASK_MATCH; + + BUILD_BUG_ON((KVM_PMU_ENCODE_MASKED_ENTRY(0, 0xff, 0, false) >> + (KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT - 8)) != + ARCH_PERFMON_EVENTSEL_UMASK); + + return (umask & mask) == match; +} + +static bool filter_contains_match(u64 *events, u64 nevents, u64 eventsel) +{ + u64 event_select = eventsel & kvm_pmu_ops.EVENTSEL_EVENT; + u64 umask = eventsel & ARCH_PERFMON_EVENTSEL_UMASK; + int i, index; + + index = find_filter_index(events, nevents, event_select); + if (index < 0) + return false; + + /* + * Entries are sorted by the event select. Walk the list in both + * directions to process all entries with the targeted event select. + */ + for (i = index; i < nevents; i++) { + if (filter_event_cmp(&events[i], &event_select)) + break; + + if (is_filter_entry_match(events[i], umask)) + return true; + } + + for (i = index - 1; i >= 0; i--) { + if (filter_event_cmp(&events[i], &event_select)) + break; + + if (is_filter_entry_match(events[i], umask)) + return true; + } + + return false; +} + +static bool is_gp_event_allowed(struct kvm_x86_pmu_event_filter *f, + u64 eventsel) +{ + if (filter_contains_match(f->includes, f->nr_includes, eventsel) && + !filter_contains_match(f->excludes, f->nr_excludes, eventsel)) + return f->action == KVM_PMU_EVENT_ALLOW; + + return f->action == KVM_PMU_EVENT_DENY; +} + +static bool is_fixed_event_allowed(struct kvm_x86_pmu_event_filter *filter, + int idx) +{ + int fixed_idx = idx - INTEL_PMC_IDX_FIXED; + + if (filter->action == KVM_PMU_EVENT_DENY && + test_bit(fixed_idx, (ulong *)&filter->fixed_counter_bitmap)) + return false; + if (filter->action == KVM_PMU_EVENT_ALLOW && + !test_bit(fixed_idx, (ulong *)&filter->fixed_counter_bitmap)) + return false; + + return true; +} + static bool check_pmu_event_filter(struct kvm_pmc *pmc) { - struct kvm_pmu_event_filter *filter; + struct kvm_x86_pmu_event_filter *filter; struct kvm *kvm = pmc->vcpu->kvm; - bool allow_event = true; - __u64 key; - int idx; if (!static_call(kvm_x86_pmu_hw_event_available)(pmc)) return false; filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu); if (!filter) - goto out; + return true; - if (pmc_is_gp(pmc)) { - key = pmc->eventsel & AMD64_RAW_EVENT_MASK_NB; - if (bsearch(&key, filter->events, filter->nevents, - sizeof(__u64), cmp_u64)) - allow_event = filter->action == KVM_PMU_EVENT_ALLOW; - else - allow_event = filter->action == KVM_PMU_EVENT_DENY; - } else { - idx = pmc->idx - INTEL_PMC_IDX_FIXED; - if (filter->action == KVM_PMU_EVENT_DENY && - test_bit(idx, (ulong *)&filter->fixed_counter_bitmap)) - allow_event = false; - if (filter->action == KVM_PMU_EVENT_ALLOW && - !test_bit(idx, (ulong *)&filter->fixed_counter_bitmap)) - allow_event = false; - } + if (pmc_is_gp(pmc)) + return is_gp_event_allowed(filter, pmc->eventsel); -out: - return allow_event; + return is_fixed_event_allowed(filter, pmc->idx); } static void reprogram_counter(struct kvm_pmc *pmc) @@ -592,47 +694,133 @@ void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id) } EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event); +static bool is_masked_filter_valid(const struct kvm_x86_pmu_event_filter *filter) +{ + u64 mask = kvm_pmu_ops.EVENTSEL_EVENT | + KVM_PMU_MASKED_ENTRY_UMASK_MASK | + KVM_PMU_MASKED_ENTRY_UMASK_MATCH | + KVM_PMU_MASKED_ENTRY_EXCLUDE; + int i; + + for (i = 0; i < filter->nevents; i++) { + if (filter->events[i] & ~mask) + return false; + } + + return true; +} + +static void convert_to_masked_filter(struct kvm_x86_pmu_event_filter *filter) +{ + int i, j; + + for (i = 0, j = 0; i < filter->nevents; i++) { + /* + * Skip events that are impossible to match against a guest + * event. When filtering, only the event select + unit mask + * of the guest event is used. To maintain backwards + * compatibility, impossible filters can't be rejected :-( + */ + if (filter->events[i] & ~(kvm_pmu_ops.EVENTSEL_EVENT | + ARCH_PERFMON_EVENTSEL_UMASK)) + continue; + /* + * Convert userspace events to a common in-kernel event so + * only one code path is needed to support both events. For + * the in-kernel events use masked events because they are + * flexible enough to handle both cases. To convert to masked + * events all that's needed is to add an "all ones" umask_mask, + * (unmasked filter events don't support EXCLUDE). + */ + filter->events[j++] = filter->events[i] | + (0xFFULL << KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT); + } + + filter->nevents = j; +} + +static int prepare_filter_lists(struct kvm_x86_pmu_event_filter *filter) +{ + int i; + + if (!(filter->flags & KVM_PMU_EVENT_FLAG_MASKED_EVENTS)) + convert_to_masked_filter(filter); + else if (!is_masked_filter_valid(filter)) + return -EINVAL; + + /* + * Sort entries by event select and includes vs. excludes so that all + * entries for a given event select can be processed efficiently during + * filtering. The EXCLUDE flag uses a more significant bit than the + * event select, and so the sorted list is also effectively split into + * includes and excludes sub-lists. + */ + sort(&filter->events, filter->nevents, sizeof(filter->events[0]), + filter_sort_cmp, NULL); + + i = filter->nevents; + /* Find the first EXCLUDE event (only supported for masked events). */ + if (filter->flags & KVM_PMU_EVENT_FLAG_MASKED_EVENTS) { + for (i = 0; i < filter->nevents; i++) { + if (filter->events[i] & KVM_PMU_MASKED_ENTRY_EXCLUDE) + break; + } + } + + filter->nr_includes = i; + filter->nr_excludes = filter->nevents - filter->nr_includes; + filter->includes = filter->events; + filter->excludes = filter->events + filter->nr_includes; + + return 0; +} + int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) { - struct kvm_pmu_event_filter tmp, *filter; + struct kvm_pmu_event_filter __user *user_filter = argp; + struct kvm_x86_pmu_event_filter *filter; + struct kvm_pmu_event_filter tmp; struct kvm_vcpu *vcpu; unsigned long i; size_t size; int r; - if (copy_from_user(&tmp, argp, sizeof(tmp))) + if (copy_from_user(&tmp, user_filter, sizeof(tmp))) return -EFAULT; if (tmp.action != KVM_PMU_EVENT_ALLOW && tmp.action != KVM_PMU_EVENT_DENY) return -EINVAL; - if (tmp.flags != 0) + if (tmp.flags & ~KVM_PMU_EVENT_FLAGS_VALID_MASK) return -EINVAL; if (tmp.nevents > KVM_PMU_EVENT_FILTER_MAX_EVENTS) return -E2BIG; size = struct_size(filter, events, tmp.nevents); - filter = kmalloc(size, GFP_KERNEL_ACCOUNT); + filter = kzalloc(size, GFP_KERNEL_ACCOUNT); if (!filter) return -ENOMEM; + filter->action = tmp.action; + filter->nevents = tmp.nevents; + filter->fixed_counter_bitmap = tmp.fixed_counter_bitmap; + filter->flags = tmp.flags; + r = -EFAULT; - if (copy_from_user(filter, argp, size)) + if (copy_from_user(filter->events, user_filter->events, + sizeof(filter->events[0]) * filter->nevents)) goto cleanup; - /* Ensure nevents can't be changed between the user copies. */ - *filter = tmp; - - /* - * Sort the in-kernel list so that we can search it with bsearch. - */ - sort(&filter->events, filter->nevents, sizeof(__u64), cmp_u64, NULL); + r = prepare_filter_lists(filter); + if (r) + goto cleanup; mutex_lock(&kvm->lock); filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter, mutex_is_locked(&kvm->lock)); + mutex_unlock(&kvm->lock); synchronize_srcu_expedited(&kvm->srcu); BUILD_BUG_ON(sizeof(((struct kvm_pmu *)0)->reprogram_pmi) > @@ -643,8 +831,6 @@ int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) kvm_make_all_cpus_request(kvm, KVM_REQ_PMU); - mutex_unlock(&kvm->lock); - r = 0; cleanup: kfree(filter); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index cdb91009701d..be62c16f2265 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -18,12 +18,6 @@ #define VMWARE_BACKDOOR_PMC_REAL_TIME 0x10001 #define VMWARE_BACKDOOR_PMC_APPARENT_TIME 0x10002 -struct kvm_event_hw_type_mapping { - u8 eventsel; - u8 unit_mask; - unsigned event_type; -}; - struct kvm_pmu_ops { bool (*hw_event_available)(struct kvm_pmc *pmc); bool (*pmc_is_enabled)(struct kvm_pmc *pmc); @@ -40,6 +34,9 @@ struct kvm_pmu_ops { void (*reset)(struct kvm_vcpu *vcpu); void (*deliver_pmi)(struct kvm_vcpu *vcpu); void (*cleanup)(struct kvm_vcpu *vcpu); + + const u64 EVENTSEL_EVENT; + const int MAX_NR_GP_COUNTERS; }; void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops); @@ -161,25 +158,39 @@ static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc) extern struct x86_pmu_capability kvm_pmu_cap; -static inline void kvm_init_pmu_capability(void) +static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops) { bool is_intel = boot_cpu_data.x86_vendor == X86_VENDOR_INTEL; - perf_get_x86_pmu_capability(&kvm_pmu_cap); - - /* - * For Intel, only support guest architectural pmu - * on a host with architectural pmu. - */ - if ((is_intel && !kvm_pmu_cap.version) || !kvm_pmu_cap.num_counters_gp) + /* + * Hybrid PMUs don't play nice with virtualization without careful + * configuration by userspace, and KVM's APIs for reporting supported + * vPMU features do not account for hybrid PMUs. Disable vPMU support + * for hybrid PMUs until KVM gains a way to let userspace opt-in. + */ + if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) enable_pmu = false; + if (enable_pmu) { + perf_get_x86_pmu_capability(&kvm_pmu_cap); + + /* + * For Intel, only support guest architectural pmu + * on a host with architectural pmu. + */ + if ((is_intel && !kvm_pmu_cap.version) || + !kvm_pmu_cap.num_counters_gp) + enable_pmu = false; + } + if (!enable_pmu) { memset(&kvm_pmu_cap, 0, sizeof(kvm_pmu_cap)); return; } kvm_pmu_cap.version = min(kvm_pmu_cap.version, 2); + kvm_pmu_cap.num_counters_gp = min(kvm_pmu_cap.num_counters_gp, + pmu_ops->MAX_NR_GP_COUNTERS); kvm_pmu_cap.num_counters_fixed = min(kvm_pmu_cap.num_counters_fixed, KVM_PMC_MAX_FIXED); } diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 042d0aca3c92..a5717282bb9c 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -14,6 +14,7 @@ enum kvm_only_cpuid_leafs { CPUID_12_EAX = NCAPINTS, CPUID_7_1_EDX, + CPUID_8000_0007_EDX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, @@ -43,6 +44,9 @@ enum kvm_only_cpuid_leafs { #define X86_FEATURE_AVX_NE_CONVERT KVM_X86_FEATURE(CPUID_7_1_EDX, 5) #define X86_FEATURE_PREFETCHITI KVM_X86_FEATURE(CPUID_7_1_EDX, 14) +/* CPUID level 0x80000007 (EDX). */ +#define KVM_X86_FEATURE_CONSTANT_TSC KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8) + struct cpuid_reg { u32 function; u32 index; @@ -68,6 +72,8 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_12_EAX] = {0x00000012, 0, CPUID_EAX}, [CPUID_8000_001F_EAX] = {0x8000001f, 0, CPUID_EAX}, [CPUID_7_1_EDX] = { 7, 1, CPUID_EDX}, + [CPUID_8000_0007_EDX] = {0x80000007, 0, CPUID_EDX}, + [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, }; /* @@ -100,6 +106,8 @@ static __always_inline u32 __feature_translate(int x86_feature) 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; return x86_feature; } diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index a9c1c2af8d94..b42111a24cc2 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "x86.h" @@ -110,8 +111,6 @@ static void check_smram_offsets(void) void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) { - BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); - trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm); if (entering_smm) { diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 6919dee69f18..ca684979e90d 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -12,7 +12,7 @@ * Avi Kivity <avi@qumranet.com> */ -#define pr_fmt(fmt) "SVM: " fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_types.h> #include <linux/hashtable.h> @@ -53,7 +53,7 @@ static DEFINE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS); static u32 next_vm_id = 0; static bool next_vm_id_wrapped = 0; static DEFINE_SPINLOCK(svm_vm_data_hash_lock); -enum avic_modes avic_mode; +bool x2avic_enabled; /* * This is a wrapper of struct amd_iommu_ir_data. @@ -72,20 +72,25 @@ static void avic_activate_vmcb(struct vcpu_svm *svm) vmcb->control.int_ctl |= AVIC_ENABLE_MASK; - /* Note: - * KVM can support hybrid-AVIC mode, where KVM emulates x2APIC - * MSR accesses, while interrupt injection to a running vCPU - * can be achieved using AVIC doorbell. The AVIC hardware still - * accelerate MMIO accesses, but this does not cause any harm - * as the guest is not supposed to access xAPIC mmio when uses x2APIC. + /* + * Note: KVM supports hybrid-AVIC mode, where KVM emulates x2APIC MSR + * accesses, while interrupt injection to a running vCPU can be + * achieved using AVIC doorbell. KVM disables the APIC access page + * (deletes the memslot) if any vCPU has x2APIC enabled, thus enabling + * AVIC in hybrid mode activates only the doorbell mechanism. */ - if (apic_x2apic_mode(svm->vcpu.arch.apic) && - avic_mode == AVIC_MODE_X2) { + if (x2avic_enabled && apic_x2apic_mode(svm->vcpu.arch.apic)) { vmcb->control.int_ctl |= X2APIC_MODE_MASK; vmcb->control.avic_physical_id |= X2AVIC_MAX_PHYSICAL_ID; /* Disabling MSR intercept for x2APIC registers */ svm_set_x2apic_msr_interception(svm, false); } else { + /* + * Flush the TLB, the guest may have inserted a non-APIC + * mapping into the TLB while AVIC was disabled. + */ + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, &svm->vcpu); + /* For xAVIC and hybrid-xAVIC modes */ vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID; /* Enabling MSR intercept for x2APIC registers */ @@ -241,8 +246,8 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, u64 *avic_physical_id_table; struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); - if ((avic_mode == AVIC_MODE_X1 && index > AVIC_MAX_PHYSICAL_ID) || - (avic_mode == AVIC_MODE_X2 && index > X2AVIC_MAX_PHYSICAL_ID)) + if ((!x2avic_enabled && index > AVIC_MAX_PHYSICAL_ID) || + (index > X2AVIC_MAX_PHYSICAL_ID)) return NULL; avic_physical_id_table = page_address(kvm_svm->avic_physical_id_table_page); @@ -250,47 +255,14 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, return &avic_physical_id_table[index]; } -/* - * Note: - * AVIC hardware walks the nested page table to check permissions, - * but does not use the SPA address specified in the leaf page - * table entry since it uses address in the AVIC_BACKING_PAGE pointer - * field of the VMCB. Therefore, we set up the - * APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (4KB) here. - */ -static int avic_alloc_access_page(struct kvm *kvm) -{ - void __user *ret; - int r = 0; - - mutex_lock(&kvm->slots_lock); - - if (kvm->arch.apic_access_memslot_enabled) - goto out; - - ret = __x86_set_memory_region(kvm, - APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, - APIC_DEFAULT_PHYS_BASE, - PAGE_SIZE); - if (IS_ERR(ret)) { - r = PTR_ERR(ret); - goto out; - } - - kvm->arch.apic_access_memslot_enabled = true; -out: - mutex_unlock(&kvm->slots_lock); - return r; -} - static int avic_init_backing_page(struct kvm_vcpu *vcpu) { u64 *entry, new_entry; int id = vcpu->vcpu_id; struct vcpu_svm *svm = to_svm(vcpu); - if ((avic_mode == AVIC_MODE_X1 && id > AVIC_MAX_PHYSICAL_ID) || - (avic_mode == AVIC_MODE_X2 && id > X2AVIC_MAX_PHYSICAL_ID)) + if ((!x2avic_enabled && id > AVIC_MAX_PHYSICAL_ID) || + (id > X2AVIC_MAX_PHYSICAL_ID)) return -EINVAL; if (!vcpu->arch.apic->regs) @@ -299,7 +271,13 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) if (kvm_apicv_activated(vcpu->kvm)) { int ret; - ret = avic_alloc_access_page(vcpu->kvm); + /* + * Note, AVIC hardware walks the nested page table to check + * permissions, but does not use the SPA address specified in + * the leaf SPTE since it uses address in the AVIC_BACKING_PAGE + * pointer field of the VMCB. + */ + ret = kvm_alloc_apic_access_page(vcpu->kvm); if (ret) return ret; } @@ -339,6 +317,60 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu) put_cpu(); } + +static void avic_kick_vcpu(struct kvm_vcpu *vcpu, u32 icrl) +{ + vcpu->arch.apic->irr_pending = true; + svm_complete_interrupt_delivery(vcpu, + icrl & APIC_MODE_MASK, + icrl & APIC_INT_LEVELTRIG, + icrl & APIC_VECTOR_MASK); +} + +static void avic_kick_vcpu_by_physical_id(struct kvm *kvm, u32 physical_id, + u32 icrl) +{ + /* + * KVM inhibits AVIC if any vCPU ID diverges from the vCPUs APIC ID, + * i.e. APIC ID == vCPU ID. + */ + struct kvm_vcpu *target_vcpu = kvm_get_vcpu_by_id(kvm, physical_id); + + /* Once again, nothing to do if the target vCPU doesn't exist. */ + if (unlikely(!target_vcpu)) + return; + + avic_kick_vcpu(target_vcpu, icrl); +} + +static void avic_kick_vcpu_by_logical_id(struct kvm *kvm, u32 *avic_logical_id_table, + u32 logid_index, u32 icrl) +{ + u32 physical_id; + + if (avic_logical_id_table) { + u32 logid_entry = avic_logical_id_table[logid_index]; + + /* Nothing to do if the logical destination is invalid. */ + if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK))) + return; + + physical_id = logid_entry & + AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; + } else { + /* + * For x2APIC, the logical APIC ID is a read-only value that is + * derived from the x2APIC ID, thus the x2APIC ID can be found + * by reversing the calculation (stored in logid_index). Note, + * bits 31:20 of the x2APIC ID aren't propagated to the logical + * ID, but KVM limits the x2APIC ID limited to KVM_MAX_VCPU_IDS. + */ + physical_id = logid_index; + } + + avic_kick_vcpu_by_physical_id(kvm, physical_id, icrl); +} + /* * A fast-path version of avic_kick_target_vcpus(), which attempts to match * destination APIC ID to vCPU without looping through all vCPUs. @@ -346,11 +378,10 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu) static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh, u32 index) { - u32 l1_physical_id, dest; - struct kvm_vcpu *target_vcpu; int dest_mode = icrl & APIC_DEST_MASK; int shorthand = icrl & APIC_SHORT_MASK; struct kvm_svm *kvm_svm = to_kvm_svm(kvm); + u32 dest; if (shorthand != APIC_DEST_NOSHORT) return -EINVAL; @@ -367,18 +398,18 @@ static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source if (!apic_x2apic_mode(source) && dest == APIC_BROADCAST) return -EINVAL; - l1_physical_id = dest; - - if (WARN_ON_ONCE(l1_physical_id != index)) + if (WARN_ON_ONCE(dest != index)) return -EINVAL; + avic_kick_vcpu_by_physical_id(kvm, dest, icrl); } else { - u32 bitmap, cluster; - int logid_index; + u32 *avic_logical_id_table; + unsigned long bitmap, i; + u32 cluster; if (apic_x2apic_mode(source)) { /* 16 bit dest mask, 16 bit cluster id */ - bitmap = dest & 0xFFFF0000; + bitmap = dest & 0xFFFF; cluster = (dest >> 16) << 4; } else if (kvm_lapic_get_reg(source, APIC_DFR) == APIC_DFR_FLAT) { /* 8 bit dest mask*/ @@ -390,67 +421,32 @@ static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source cluster = (dest >> 4) << 2; } + /* Nothing to do if there are no destinations in the cluster. */ if (unlikely(!bitmap)) - /* guest bug: nobody to send the logical interrupt to */ return 0; - if (!is_power_of_2(bitmap)) - /* multiple logical destinations, use slow path */ - return -EINVAL; - - logid_index = cluster + __ffs(bitmap); - - if (!apic_x2apic_mode(source)) { - u32 *avic_logical_id_table = - page_address(kvm_svm->avic_logical_id_table_page); - - u32 logid_entry = avic_logical_id_table[logid_index]; - - if (WARN_ON_ONCE(index != logid_index)) - return -EINVAL; - - /* guest bug: non existing/reserved logical destination */ - if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK))) - return 0; - - l1_physical_id = logid_entry & - AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; - } else { - /* - * For x2APIC logical mode, cannot leverage the index. - * Instead, calculate physical ID from logical ID in ICRH. - */ - int cluster = (icrh & 0xffff0000) >> 16; - int apic = ffs(icrh & 0xffff) - 1; - - /* - * If the x2APIC logical ID sub-field (i.e. icrh[15:0]) - * contains anything but a single bit, we cannot use the - * fast path, because it is limited to a single vCPU. - */ - if (apic < 0 || icrh != (1 << apic)) - return -EINVAL; + if (apic_x2apic_mode(source)) + avic_logical_id_table = NULL; + else + avic_logical_id_table = page_address(kvm_svm->avic_logical_id_table_page); - l1_physical_id = (cluster << 4) + apic; - } + /* + * AVIC is inhibited if vCPUs aren't mapped 1:1 with logical + * IDs, thus each bit in the destination is guaranteed to map + * to at most one vCPU. + */ + for_each_set_bit(i, &bitmap, 16) + avic_kick_vcpu_by_logical_id(kvm, avic_logical_id_table, + cluster + i, icrl); } - target_vcpu = kvm_get_vcpu_by_id(kvm, l1_physical_id); - if (unlikely(!target_vcpu)) - /* guest bug: non existing vCPU is a target of this IPI*/ - return 0; - - target_vcpu->arch.apic->irr_pending = true; - svm_complete_interrupt_delivery(target_vcpu, - icrl & APIC_MODE_MASK, - icrl & APIC_INT_LEVELTRIG, - icrl & APIC_VECTOR_MASK); return 0; } static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh, u32 index) { + u32 dest = apic_x2apic_mode(source) ? icrh : GET_XAPIC_DEST_FIELD(icrh); unsigned long i; struct kvm_vcpu *vcpu; @@ -466,21 +462,9 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, * since entered the guest will have processed pending IRQs at VMRUN. */ kvm_for_each_vcpu(i, vcpu, kvm) { - u32 dest; - - if (apic_x2apic_mode(vcpu->arch.apic)) - dest = icrh; - else - dest = GET_XAPIC_DEST_FIELD(icrh); - if (kvm_apic_match_dest(vcpu, source, icrl & APIC_SHORT_MASK, - dest, icrl & APIC_DEST_MASK)) { - vcpu->arch.apic->irr_pending = true; - svm_complete_interrupt_delivery(vcpu, - icrl & APIC_MODE_MASK, - icrl & APIC_INT_LEVELTRIG, - icrl & APIC_VECTOR_MASK); - } + dest, icrl & APIC_DEST_MASK)) + avic_kick_vcpu(vcpu, icrl); } } @@ -496,14 +480,18 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) trace_kvm_avic_incomplete_ipi(vcpu->vcpu_id, icrh, icrl, id, index); switch (id) { + case AVIC_IPI_FAILURE_INVALID_TARGET: case AVIC_IPI_FAILURE_INVALID_INT_TYPE: /* * Emulate IPIs that are not handled by AVIC hardware, which - * only virtualizes Fixed, Edge-Triggered INTRs. The exit is - * a trap, e.g. ICR holds the correct value and RIP has been - * advanced, KVM is responsible only for emulating the IPI. - * Sadly, hardware may sometimes leave the BUSY flag set, in - * which case KVM needs to emulate the ICR write as well in + * only virtualizes Fixed, Edge-Triggered INTRs, and falls over + * if _any_ targets are invalid, e.g. if the logical mode mask + * is a superset of running vCPUs. + * + * The exit is a trap, e.g. ICR holds the correct value and RIP + * has been advanced, KVM is responsible only for emulating the + * IPI. Sadly, hardware may sometimes leave the BUSY flag set, + * in which case KVM needs to emulate the ICR write as well in * order to clear the BUSY flag. */ if (icrl & APIC_ICR_BUSY) @@ -519,8 +507,6 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) */ avic_kick_target_vcpus(vcpu->kvm, apic, icrl, icrh, index); break; - case AVIC_IPI_FAILURE_INVALID_TARGET: - break; case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: WARN_ONCE(1, "Invalid backing page\n"); break; @@ -541,33 +527,33 @@ unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu) static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat) { struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); - int index; u32 *logical_apic_id_table; - int dlid = GET_APIC_LOGICAL_ID(ldr); - - if (!dlid) - return NULL; + u32 cluster, index; - if (flat) { /* flat */ - index = ffs(dlid) - 1; - if (index > 7) - return NULL; - } else { /* cluster */ - int cluster = (dlid & 0xf0) >> 4; - int apic = ffs(dlid & 0x0f) - 1; + ldr = GET_APIC_LOGICAL_ID(ldr); - if ((apic < 0) || (apic > 7) || - (cluster >= 0xf)) + if (flat) { + cluster = 0; + } else { + cluster = (ldr >> 4); + if (cluster >= 0xf) return NULL; - index = (cluster << 2) + apic; + ldr &= 0xf; } + if (!ldr || !is_power_of_2(ldr)) + return NULL; + + index = __ffs(ldr); + if (WARN_ON_ONCE(index > 7)) + return NULL; + index += (cluster << 2); logical_apic_id_table = (u32 *) page_address(kvm_svm->avic_logical_id_table_page); return &logical_apic_id_table[index]; } -static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) +static void avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) { bool flat; u32 *entry, new_entry; @@ -575,15 +561,13 @@ static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) flat = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR) == APIC_DFR_FLAT; entry = avic_get_logical_id_entry(vcpu, ldr, flat); if (!entry) - return -EINVAL; + return; new_entry = READ_ONCE(*entry); new_entry &= ~AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; new_entry |= (g_physical_id & AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK); new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK; WRITE_ONCE(*entry, new_entry); - - return 0; } static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu) @@ -601,29 +585,23 @@ static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu) clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry); } -static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) +static void avic_handle_ldr_update(struct kvm_vcpu *vcpu) { - int ret = 0; struct vcpu_svm *svm = to_svm(vcpu); u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR); u32 id = kvm_xapic_id(vcpu->arch.apic); /* AVIC does not support LDR update for x2APIC */ if (apic_x2apic_mode(vcpu->arch.apic)) - return 0; + return; if (ldr == svm->ldr_reg) - return 0; + return; avic_invalidate_logical_id_entry(vcpu); - if (ldr) - ret = avic_ldr_write(vcpu, id, ldr); - - if (!ret) - svm->ldr_reg = ldr; - - return ret; + svm->ldr_reg = ldr; + avic_ldr_write(vcpu, id, ldr); } static void avic_handle_dfr_update(struct kvm_vcpu *vcpu) @@ -645,12 +623,14 @@ static int avic_unaccel_trap_write(struct kvm_vcpu *vcpu) switch (offset) { case APIC_LDR: - if (avic_handle_ldr_update(vcpu)) - return 0; + avic_handle_ldr_update(vcpu); break; case APIC_DFR: avic_handle_dfr_update(vcpu); break; + case APIC_RRR: + /* Ignore writes to Read Remote Data, it's read-only. */ + return 1; default: break; } @@ -739,18 +719,6 @@ void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu) avic_handle_ldr_update(vcpu); } -void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu) -{ - if (!lapic_in_kernel(vcpu) || avic_mode == AVIC_MODE_NONE) - return; - - if (kvm_get_apic_mode(vcpu) == LAPIC_MODE_INVALID) { - WARN_ONCE(true, "Invalid local APIC state (vcpu_id=%d)", vcpu->vcpu_id); - return; - } - avic_refresh_apicv_exec_ctrl(vcpu); -} - static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate) { int ret = 0; @@ -995,23 +963,6 @@ out: return ret; } -bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) -{ - ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | - BIT(APICV_INHIBIT_REASON_ABSENT) | - BIT(APICV_INHIBIT_REASON_HYPERV) | - BIT(APICV_INHIBIT_REASON_NESTED) | - BIT(APICV_INHIBIT_REASON_IRQWIN) | - BIT(APICV_INHIBIT_REASON_PIT_REINJ) | - BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | - BIT(APICV_INHIBIT_REASON_SEV) | - BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | - BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); - - return supported & BIT(reason); -} - - static inline int avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) { @@ -1064,6 +1015,7 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) return; entry = READ_ONCE(*(svm->avic_physical_id_cache)); + WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK; entry |= (h_physical_id & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK); @@ -1092,17 +1044,15 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu) WRITE_ONCE(*(svm->avic_physical_id_cache), entry); } - -void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb01.ptr; - bool activated = kvm_vcpu_apicv_active(vcpu); - if (!enable_apicv) + if (!lapic_in_kernel(vcpu) || !enable_apicv) return; - if (activated) { + if (kvm_vcpu_apicv_active(vcpu)) { /** * During AVIC temporary deactivation, guest could update * APIC ID, DFR and LDR registers, which would not be trapped @@ -1116,6 +1066,16 @@ void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) avic_deactivate_vmcb(svm); } vmcb_mark_dirty(vmcb, VMCB_AVIC); +} + +void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +{ + bool activated = kvm_vcpu_apicv_active(vcpu); + + if (!enable_apicv) + return; + + avic_refresh_virtual_apic_mode(vcpu); if (activated) avic_vcpu_load(vcpu, vcpu->cpu); @@ -1160,37 +1120,37 @@ void avic_vcpu_unblocking(struct kvm_vcpu *vcpu) * - Hypervisor can support both xAVIC and x2AVIC in the same guest. * - The mode can be switched at run-time. */ -bool avic_hardware_setup(struct kvm_x86_ops *x86_ops) +bool avic_hardware_setup(void) { if (!npt_enabled) return false; + /* AVIC is a prerequisite for x2AVIC. */ + if (!boot_cpu_has(X86_FEATURE_AVIC) && !force_avic) { + if (boot_cpu_has(X86_FEATURE_X2AVIC)) { + pr_warn(FW_BUG "Cannot support x2AVIC due to AVIC is disabled"); + pr_warn(FW_BUG "Try enable AVIC using force_avic option"); + } + return false; + } + if (boot_cpu_has(X86_FEATURE_AVIC)) { - avic_mode = AVIC_MODE_X1; pr_info("AVIC enabled\n"); } else if (force_avic) { /* * Some older systems does not advertise AVIC support. * See Revision Guide for specific AMD processor for more detail. */ - avic_mode = AVIC_MODE_X1; pr_warn("AVIC is not supported in CPUID but force enabled"); pr_warn("Your system might crash and burn"); } /* AVIC is a prerequisite for x2AVIC. */ - if (boot_cpu_has(X86_FEATURE_X2AVIC)) { - if (avic_mode == AVIC_MODE_X1) { - avic_mode = AVIC_MODE_X2; - pr_info("x2AVIC enabled\n"); - } else { - pr_warn(FW_BUG "Cannot support x2AVIC due to AVIC is disabled"); - pr_warn(FW_BUG "Try enable AVIC using force_avic option"); - } - } + x2avic_enabled = boot_cpu_has(X86_FEATURE_X2AVIC); + if (x2avic_enabled) + pr_info("x2AVIC enabled\n"); - if (avic_mode != AVIC_MODE_NONE) - amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); + amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); - return !!avic_mode; + return true; } diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index add65dd59756..05d38944a6c0 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -12,7 +12,7 @@ * Avi Kivity <avi@qumranet.com> */ -#define pr_fmt(fmt) "SVM: " fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_types.h> #include <linux/kvm_host.h> @@ -1008,7 +1008,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm) vmcb12->control.next_rip = vmcb02->control.next_rip; vmcb12->control.int_ctl = svm->nested.ctl.int_ctl; - vmcb12->control.tlb_ctl = svm->nested.ctl.tlb_ctl; vmcb12->control.event_inj = svm->nested.ctl.event_inj; vmcb12->control.event_inj_err = svm->nested.ctl.event_inj_err; @@ -1104,7 +1103,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) * to benefit from it right away. */ if (kvm_apicv_activated(vcpu->kvm)) - kvm_vcpu_update_apicv(vcpu); + __kvm_vcpu_update_apicv(vcpu); return 0; } diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 0e313fbae055..cc77a0681800 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -9,6 +9,8 @@ * * Implementation is based on pmu_intel.c file */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/types.h> #include <linux/kvm_host.h> #include <linux/perf_event.h> @@ -229,4 +231,6 @@ struct kvm_pmu_ops amd_pmu_ops __initdata = { .refresh = amd_pmu_refresh, .init = amd_pmu_init, .reset = amd_pmu_reset, + .EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT, + .MAX_NR_GP_COUNTERS = KVM_AMD_PMC_MAX_GENERIC, }; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 86d6897f4806..c25aeb550cd9 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -6,6 +6,7 @@ * * Copyright 2010 Red Hat, Inc. and/or its affiliates. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_types.h> #include <linux/kvm_host.h> @@ -812,7 +813,7 @@ static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, if (!IS_ALIGNED(dst_paddr, 16) || !IS_ALIGNED(paddr, 16) || !IS_ALIGNED(size, 16)) { - tpage = (void *)alloc_page(GFP_KERNEL | __GFP_ZERO); + tpage = (void *)alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!tpage) return -ENOMEM; @@ -1293,7 +1294,7 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Check if we are crossing the page boundary */ offset = params.guest_uaddr & (PAGE_SIZE - 1); - if ((params.guest_len + offset > PAGE_SIZE)) + if (params.guest_len > PAGE_SIZE || (params.guest_len + offset) > PAGE_SIZE) return -EINVAL; /* Pin guest memory */ @@ -1473,7 +1474,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Check if we are crossing the page boundary */ offset = params.guest_uaddr & (PAGE_SIZE - 1); - if ((params.guest_len + offset > PAGE_SIZE)) + if (params.guest_len > PAGE_SIZE || (params.guest_len + offset) > PAGE_SIZE) return -EINVAL; hdr = psp_copy_user_blob(params.hdr_uaddr, params.hdr_len); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9a194aa1a75a..252e7f37e4e2 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1,4 +1,4 @@ -#define pr_fmt(fmt) "SVM: " fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> @@ -519,21 +519,37 @@ static void svm_init_osvw(struct kvm_vcpu *vcpu) vcpu->arch.osvw.status |= 1; } -static int has_svm(void) +static bool kvm_is_svm_supported(void) { + int cpu = raw_smp_processor_id(); const char *msg; + u64 vm_cr; if (!cpu_has_svm(&msg)) { - printk(KERN_INFO "has_svm: %s\n", msg); - return 0; + pr_err("SVM not supported by CPU %d, %s\n", cpu, msg); + return false; } if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { pr_info("KVM is unsupported when running as an SEV guest\n"); - return 0; + return false; } - return 1; + rdmsrl(MSR_VM_CR, vm_cr); + if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE)) { + pr_err("SVM disabled (by BIOS) in MSR_VM_CR on CPU %d\n", cpu); + return false; + } + + return true; +} + +static int svm_check_processor_compat(void) +{ + if (!kvm_is_svm_supported()) + return -EIO; + + return 0; } void __svm_write_tsc_multiplier(u64 multiplier) @@ -572,10 +588,6 @@ static int svm_hardware_enable(void) if (efer & EFER_SVME) return -EBUSY; - if (!has_svm()) { - pr_err("%s: err EOPNOTSUPP on %d\n", __func__, me); - return -EINVAL; - } sd = per_cpu_ptr(&svm_data, me); sd->asid_generation = 1; sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; @@ -813,7 +825,7 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) if (intercept == svm->x2avic_msrs_intercepted) return; - if (avic_mode != AVIC_MODE_X2 || + if (!x2avic_enabled || !apic_x2apic_mode(svm->vcpu.arch.apic)) return; @@ -1326,6 +1338,9 @@ static void __svm_vcpu_reset(struct kvm_vcpu *vcpu) vcpu->arch.microcode_version = 0x01000065; svm->tsc_ratio_msr = kvm_caps.default_tsc_scaling_ratio; + svm->nmi_masked = false; + svm->awaiting_iret_completion = false; + if (sev_es_guest(vcpu->kvm)) sev_es_vcpu_reset(svm); } @@ -2076,7 +2091,7 @@ static void svm_handle_mce(struct kvm_vcpu *vcpu) * Erratum 383 triggered. Guest state is corrupt so kill the * guest. */ - pr_err("KVM: Guest triggered AMD Erratum 383\n"); + pr_err("Guest triggered AMD Erratum 383\n"); kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); @@ -2470,7 +2485,7 @@ static int iret_interception(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); ++vcpu->stat.nmi_window_exits; - vcpu->arch.hflags |= HF_IRET_MASK; + svm->awaiting_iret_completion = true; if (!sev_es_guest(vcpu->kvm)) { svm_clr_intercept(svm, INTERCEPT_IRET); svm->nmi_iret_rip = kvm_rip_read(vcpu); @@ -3003,8 +3018,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_DEBUGCTLMSR: if (!lbrv) { - vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", - __func__, data); + kvm_pr_unimpl_wrmsr(vcpu, ecx, data); break; } if (data & DEBUGCTL_RESERVED_BITS) @@ -3033,7 +3047,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_CR: return svm_set_vm_cr(vcpu, data); case MSR_VM_IGNNE: - vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); + kvm_pr_unimpl_wrmsr(vcpu, ecx, data); break; case MSR_AMD64_DE_CFG: { struct kvm_msr_entry msr_entry; @@ -3466,7 +3480,7 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) if (svm->nmi_l1_to_l2) return; - vcpu->arch.hflags |= HF_NMI_MASK; + svm->nmi_masked = true; if (!sev_es_guest(vcpu->kvm)) svm_set_intercept(svm, INTERCEPT_IRET); ++vcpu->stat.nmi_injections; @@ -3571,7 +3585,6 @@ bool svm_nmi_blocked(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - bool ret; if (!gif_set(svm)) return true; @@ -3579,10 +3592,8 @@ bool svm_nmi_blocked(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu) && nested_exit_on_nmi(svm)) return false; - ret = (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || - (vcpu->arch.hflags & HF_NMI_MASK); - - return ret; + return (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || + svm->nmi_masked; } static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) @@ -3602,7 +3613,7 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) { - return !!(vcpu->arch.hflags & HF_NMI_MASK); + return to_svm(vcpu)->nmi_masked; } static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) @@ -3610,11 +3621,11 @@ static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) struct vcpu_svm *svm = to_svm(vcpu); if (masked) { - vcpu->arch.hflags |= HF_NMI_MASK; + svm->nmi_masked = true; if (!sev_es_guest(vcpu->kvm)) svm_set_intercept(svm, INTERCEPT_IRET); } else { - vcpu->arch.hflags &= ~HF_NMI_MASK; + svm->nmi_masked = false; if (!sev_es_guest(vcpu->kvm)) svm_clr_intercept(svm, INTERCEPT_IRET); } @@ -3700,7 +3711,7 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - if ((vcpu->arch.hflags & (HF_NMI_MASK | HF_IRET_MASK)) == HF_NMI_MASK) + if (svm->nmi_masked && !svm->awaiting_iret_completion) return; /* IRET will cause a vm exit */ if (!gif_set(svm)) { @@ -3824,10 +3835,11 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu) * If we've made progress since setting HF_IRET_MASK, we've * executed an IRET and can allow NMI injection. */ - if ((vcpu->arch.hflags & HF_IRET_MASK) && + if (svm->awaiting_iret_completion && (sev_es_guest(vcpu->kvm) || kvm_rip_read(vcpu) != svm->nmi_iret_rip)) { - vcpu->arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK); + svm->awaiting_iret_completion = false; + svm->nmi_masked = false; kvm_make_request(KVM_REQ_EVENT, vcpu); } @@ -4076,17 +4088,6 @@ static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, vmcb_mark_dirty(svm->vmcb, VMCB_CR); } -static int is_disabled(void) -{ - u64 vm_cr; - - rdmsrl(MSR_VM_CR, vm_cr); - if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE)) - return 1; - - return 0; -} - static void svm_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) { @@ -4098,11 +4099,6 @@ svm_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) hypercall[2] = 0xd9; } -static int __init svm_check_processor_compat(void) -{ - return 0; -} - /* * The kvm parameter can be NULL (module initialization, or invocation before * VM creation). Be sure to check the kvm parameter before using it. @@ -4629,7 +4625,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, smap = cr4 & X86_CR4_SMAP; is_user = svm_get_cpl(vcpu) == 3; if (smap && (!smep || is_user)) { - pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n"); + pr_err_ratelimited("SEV Guest triggered AMD Erratum 1096\n"); /* * If the fault occurred in userspace, arbitrarily inject #GP @@ -4701,7 +4697,9 @@ static int svm_vm_init(struct kvm *kvm) } static struct kvm_x86_ops svm_x86_ops __initdata = { - .name = "kvm_amd", + .name = KBUILD_MODNAME, + + .check_processor_compatibility = svm_check_processor_compat, .hardware_unsetup = svm_hardware_unsetup, .hardware_enable = svm_hardware_enable, @@ -4771,10 +4769,10 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .enable_nmi_window = svm_enable_nmi_window, .enable_irq_window = svm_enable_irq_window, .update_cr8_intercept = svm_update_cr8_intercept, - .set_virtual_apic_mode = avic_set_virtual_apic_mode, + .set_virtual_apic_mode = avic_refresh_virtual_apic_mode, .refresh_apicv_exec_ctrl = avic_refresh_apicv_exec_ctrl, - .check_apicv_inhibit_reasons = avic_check_apicv_inhibit_reasons, .apicv_post_state_restore = avic_apicv_post_state_restore, + .required_apicv_inhibits = AVIC_REQUIRED_APICV_INHIBITS, .get_exit_info = svm_get_exit_info, @@ -4969,6 +4967,9 @@ static __init int svm_hardware_setup(void) tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX); + if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) + kvm_enable_efer_bits(EFER_AUTOIBRS); + /* Check for pause filtering support */ if (!boot_cpu_has(X86_FEATURE_PAUSEFILTER)) { pause_filter_count = 0; @@ -4978,7 +4979,7 @@ static __init int svm_hardware_setup(void) } if (nested) { - printk(KERN_INFO "kvm: Nested Virtualization enabled\n"); + pr_info("Nested Virtualization enabled\n"); kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE); } @@ -4996,7 +4997,7 @@ static __init int svm_hardware_setup(void) /* Force VM NPT level equal to the host's paging level */ kvm_configure_mmu(npt_enabled, get_npt_level(), get_npt_level(), PG_LEVEL_1G); - pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); + pr_info("Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); /* Setup shadow_me_value and shadow_me_mask */ kvm_mmu_set_me_spte_mask(sme_me_mask, sme_me_mask); @@ -5022,12 +5023,14 @@ static __init int svm_hardware_setup(void) nrips = false; } - enable_apicv = avic = avic && avic_hardware_setup(&svm_x86_ops); + enable_apicv = avic = avic && avic_hardware_setup(); if (!enable_apicv) { svm_x86_ops.vcpu_blocking = NULL; svm_x86_ops.vcpu_unblocking = NULL; svm_x86_ops.vcpu_get_apicv_inhibit_reasons = NULL; + } else if (!x2avic_enabled) { + svm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization = true; } if (vls) { @@ -5086,10 +5089,7 @@ err: static struct kvm_x86_init_ops svm_init_ops __initdata = { - .cpu_has_kvm_support = has_svm, - .disabled_by_bios = is_disabled, .hardware_setup = svm_hardware_setup, - .check_processor_compatibility = svm_check_processor_compat, .runtime_ops = &svm_x86_ops, .pmu_ops = &amd_pmu_ops, @@ -5097,15 +5097,37 @@ static struct kvm_x86_init_ops svm_init_ops __initdata = { static int __init svm_init(void) { + int r; + __unused_size_checks(); - return kvm_init(&svm_init_ops, sizeof(struct vcpu_svm), - __alignof__(struct vcpu_svm), THIS_MODULE); + if (!kvm_is_svm_supported()) + return -EOPNOTSUPP; + + r = kvm_x86_vendor_init(&svm_init_ops); + if (r) + return r; + + /* + * Common KVM initialization _must_ come last, after this, /dev/kvm is + * exposed to userspace! + */ + r = kvm_init(sizeof(struct vcpu_svm), __alignof__(struct vcpu_svm), + THIS_MODULE); + if (r) + goto err_kvm_init; + + return 0; + +err_kvm_init: + kvm_x86_vendor_exit(); + return r; } static void __exit svm_exit(void) { kvm_exit(); + kvm_x86_vendor_exit(); } module_init(svm_init) diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 4826e6cc611b..839809972da1 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -35,14 +35,7 @@ extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; extern int vgif; extern bool intercept_smi; - -enum avic_modes { - AVIC_MODE_NONE = 0, - AVIC_MODE_X1, - AVIC_MODE_X2, -}; - -extern enum avic_modes avic_mode; +extern bool x2avic_enabled; /* * Clean bits in VMCB. @@ -237,8 +230,26 @@ struct vcpu_svm { struct svm_nested_state nested; + /* NMI mask value, used when vNMI is not enabled */ + bool nmi_masked; + + /* + * True when NMIs are still masked but guest IRET was just intercepted + * and KVM is waiting for RIP to change, which will signal that the + * intercepted IRET was retired and thus NMI can be unmasked. + */ + bool awaiting_iret_completion; + + /* + * Set when KVM is awaiting IRET completion and needs to inject NMIs as + * soon as the IRET completes (e.g. NMI is pending injection). KVM + * temporarily steals RFLAGS.TF to single-step the guest in this case + * in order to regain control as soon as the NMI-blocking condition + * goes away. + */ bool nmi_singlestep; u64 nmi_singlestep_guest_rflags; + bool nmi_l1_to_l2; unsigned long soft_int_csbase; @@ -280,6 +291,9 @@ struct vcpu_svm { bool guest_state_loaded; bool x2avic_msrs_intercepted; + + /* Guest GIF value, used when vGIF is not enabled */ + bool guest_gif; }; struct svm_cpu_data { @@ -497,7 +511,7 @@ static inline void enable_gif(struct vcpu_svm *svm) if (vmcb) vmcb->control.int_ctl |= V_GIF_MASK; else - svm->vcpu.arch.hflags |= HF_GIF_MASK; + svm->guest_gif = true; } static inline void disable_gif(struct vcpu_svm *svm) @@ -507,7 +521,7 @@ static inline void disable_gif(struct vcpu_svm *svm) if (vmcb) vmcb->control.int_ctl &= ~V_GIF_MASK; else - svm->vcpu.arch.hflags &= ~HF_GIF_MASK; + svm->guest_gif = false; } static inline bool gif_set(struct vcpu_svm *svm) @@ -517,7 +531,7 @@ static inline bool gif_set(struct vcpu_svm *svm) if (vmcb) return !!(vmcb->control.int_ctl & V_GIF_MASK); else - return !!(svm->vcpu.arch.hflags & HF_GIF_MASK); + return svm->guest_gif; } static inline bool nested_npt_enabled(struct vcpu_svm *svm) @@ -628,8 +642,23 @@ void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb); extern struct kvm_x86_nested_ops svm_nested_ops; /* avic.c */ - -bool avic_hardware_setup(struct kvm_x86_ops *ops); +#define AVIC_REQUIRED_APICV_INHIBITS \ +( \ + BIT(APICV_INHIBIT_REASON_DISABLE) | \ + BIT(APICV_INHIBIT_REASON_ABSENT) | \ + BIT(APICV_INHIBIT_REASON_HYPERV) | \ + BIT(APICV_INHIBIT_REASON_NESTED) | \ + BIT(APICV_INHIBIT_REASON_IRQWIN) | \ + BIT(APICV_INHIBIT_REASON_PIT_REINJ) | \ + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ + BIT(APICV_INHIBIT_REASON_SEV) | \ + BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED) \ +) + +bool avic_hardware_setup(void); int avic_ga_log_notifier(u32 ga_tag); void avic_vm_destroy(struct kvm *kvm); int avic_vm_init(struct kvm *kvm); @@ -641,14 +670,13 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void avic_vcpu_put(struct kvm_vcpu *vcpu); void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu); void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); -bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason); int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void avic_vcpu_blocking(struct kvm_vcpu *vcpu); void avic_vcpu_unblocking(struct kvm_vcpu *vcpu); void avic_ring_doorbell(struct kvm_vcpu *vcpu); unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu); -void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu); +void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu); /* sev.c */ diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c index 26a89d0da93e..7af8422d3382 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.c +++ b/arch/x86/kvm/svm/svm_onhyperv.c @@ -2,6 +2,7 @@ /* * KVM L1 hypervisor optimizations on Hyper-V for SVM. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h index 45faf84476ce..cff838f15db5 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.h +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -30,11 +30,11 @@ static inline void svm_hv_init_vmcb(struct vmcb *vmcb) hve->hv_enlightenments_control.msr_bitmap = 1; } -static inline void svm_hv_hardware_setup(void) +static inline __init void svm_hv_hardware_setup(void) { if (npt_enabled && ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) { - pr_info("kvm: Hyper-V enlightened NPT TLB flush enabled\n"); + pr_info(KBUILD_MODNAME ": Hyper-V enlightened NPT TLB flush enabled\n"); svm_x86_ops.tlb_remote_flush = hv_remote_flush_tlb; svm_x86_ops.tlb_remote_flush_with_range = hv_remote_flush_tlb_with_range; @@ -43,7 +43,7 @@ static inline void svm_hv_hardware_setup(void) if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) { int cpu; - pr_info("kvm: Hyper-V Direct TLB Flush enabled\n"); + pr_info(KBUILD_MODNAME ": Hyper-V Direct TLB Flush enabled\n"); for_each_online_cpu(cpu) { struct hv_vp_assist_page *vp_ap = hv_get_vp_assist_page(cpu); @@ -84,7 +84,7 @@ static inline void svm_hv_init_vmcb(struct vmcb *vmcb) { } -static inline void svm_hv_hardware_setup(void) +static inline __init void svm_hv_hardware_setup(void) { } diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index cd2ac9536c99..45162c1bcd8f 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -66,13 +66,13 @@ struct vmcs_config { u64 misc; struct nested_vmx_msrs nested; }; -extern struct vmcs_config vmcs_config; +extern struct vmcs_config vmcs_config __ro_after_init; struct vmx_capability { u32 ept; u32 vpid; }; -extern struct vmx_capability vmx_capability; +extern struct vmx_capability vmx_capability __ro_after_init; static inline bool cpu_has_vmx_basic_inout(void) { diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index ae03d1fe0355..22daca752797 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/errno.h> #include <linux/smp.h> @@ -361,35 +362,43 @@ enum evmcs_revision { enum evmcs_ctrl_type { EVMCS_EXIT_CTRLS, EVMCS_ENTRY_CTRLS, + EVMCS_EXEC_CTRL, EVMCS_2NDEXEC, + EVMCS_3RDEXEC, EVMCS_PINCTRL, EVMCS_VMFUNC, NR_EVMCS_CTRLS, }; -static const u32 evmcs_unsupported_ctrls[NR_EVMCS_CTRLS][NR_EVMCS_REVISIONS] = { +static const u32 evmcs_supported_ctrls[NR_EVMCS_CTRLS][NR_EVMCS_REVISIONS] = { [EVMCS_EXIT_CTRLS] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMEXIT_CTRL, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_VMEXIT_CTRL, }, [EVMCS_ENTRY_CTRLS] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMENTRY_CTRL, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_VMENTRY_CTRL, + }, + [EVMCS_EXEC_CTRL] = { + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_EXEC_CTRL, }, [EVMCS_2NDEXEC] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_2NDEXEC, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_2NDEXEC & ~SECONDARY_EXEC_TSC_SCALING, + }, + [EVMCS_3RDEXEC] = { + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_3RDEXEC, }, [EVMCS_PINCTRL] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_PINCTRL, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_PINCTRL, }, [EVMCS_VMFUNC] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMFUNC, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_VMFUNC, }, }; -static u32 evmcs_get_unsupported_ctls(enum evmcs_ctrl_type ctrl_type) +static u32 evmcs_get_supported_ctls(enum evmcs_ctrl_type ctrl_type) { enum evmcs_revision evmcs_rev = EVMCSv1_LEGACY; - return evmcs_unsupported_ctrls[ctrl_type][evmcs_rev]; + return evmcs_supported_ctrls[ctrl_type][evmcs_rev]; } static bool evmcs_has_perf_global_ctrl(struct kvm_vcpu *vcpu) @@ -413,7 +422,7 @@ void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 * { u32 ctl_low = (u32)*pdata; u32 ctl_high = (u32)(*pdata >> 32); - u32 unsupported_ctrls; + u32 supported_ctrls; /* * Hyper-V 2016 and 2019 try using these features even when eVMCS @@ -422,27 +431,31 @@ void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 * switch (msr_index) { case MSR_IA32_VMX_EXIT_CTLS: case MSR_IA32_VMX_TRUE_EXIT_CTLS: - unsupported_ctrls = evmcs_get_unsupported_ctls(EVMCS_EXIT_CTRLS); + supported_ctrls = evmcs_get_supported_ctls(EVMCS_EXIT_CTRLS); if (!evmcs_has_perf_global_ctrl(vcpu)) - unsupported_ctrls |= VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; - ctl_high &= ~unsupported_ctrls; + supported_ctrls &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= supported_ctrls; break; case MSR_IA32_VMX_ENTRY_CTLS: case MSR_IA32_VMX_TRUE_ENTRY_CTLS: - unsupported_ctrls = evmcs_get_unsupported_ctls(EVMCS_ENTRY_CTRLS); + supported_ctrls = evmcs_get_supported_ctls(EVMCS_ENTRY_CTRLS); if (!evmcs_has_perf_global_ctrl(vcpu)) - unsupported_ctrls |= VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; - ctl_high &= ~unsupported_ctrls; + supported_ctrls &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= supported_ctrls; + break; + case MSR_IA32_VMX_PROCBASED_CTLS: + case MSR_IA32_VMX_TRUE_PROCBASED_CTLS: + ctl_high &= evmcs_get_supported_ctls(EVMCS_EXEC_CTRL); break; case MSR_IA32_VMX_PROCBASED_CTLS2: - ctl_high &= ~evmcs_get_unsupported_ctls(EVMCS_2NDEXEC); + ctl_high &= evmcs_get_supported_ctls(EVMCS_2NDEXEC); break; case MSR_IA32_VMX_TRUE_PINBASED_CTLS: case MSR_IA32_VMX_PINBASED_CTLS: - ctl_high &= ~evmcs_get_unsupported_ctls(EVMCS_PINCTRL); + ctl_high &= evmcs_get_supported_ctls(EVMCS_PINCTRL); break; case MSR_IA32_VMX_VMFUNC: - ctl_low &= ~evmcs_get_unsupported_ctls(EVMCS_VMFUNC); + ctl_low &= evmcs_get_supported_ctls(EVMCS_VMFUNC); break; } @@ -452,7 +465,7 @@ void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 * static bool nested_evmcs_is_valid_controls(enum evmcs_ctrl_type ctrl_type, u32 val) { - return !(val & evmcs_get_unsupported_ctls(ctrl_type)); + return !(val & ~evmcs_get_supported_ctls(ctrl_type)); } int nested_evmcs_check_controls(struct vmcs12 *vmcs12) @@ -461,6 +474,10 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12) vmcs12->pin_based_vm_exec_control))) return -EINVAL; + if (CC(!nested_evmcs_is_valid_controls(EVMCS_EXEC_CTRL, + vmcs12->cpu_based_vm_exec_control))) + return -EINVAL; + if (CC(!nested_evmcs_is_valid_controls(EVMCS_2NDEXEC, vmcs12->secondary_vm_exec_control))) return -EINVAL; @@ -488,6 +505,38 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12) return 0; } +#if IS_ENABLED(CONFIG_HYPERV) +/* + * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption + * is: in case a feature has corresponding fields in eVMCS described and it was + * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a + * feature which has no corresponding eVMCS field, this likely means that KVM + * needs to be updated. + */ +#define evmcs_check_vmcs_conf(field, ctrl) \ + do { \ + typeof(vmcs_conf->field) unsupported; \ + \ + unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl; \ + if (unsupported) { \ + pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\ + (u64)unsupported); \ + vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl; \ + } \ + } \ + while (0) + +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) +{ + evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL); + evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL); + evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC); + evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC); + evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL); + evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL); +} +#endif + int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version) { diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index 571e7929d14e..78d17667e7ec 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -48,22 +48,84 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs); * Currently unsupported in KVM: * GUEST_IA32_RTIT_CTL = 0x00002814, */ -#define EVMCS1_UNSUPPORTED_PINCTRL (PIN_BASED_POSTED_INTR | \ - PIN_BASED_VMX_PREEMPTION_TIMER) -#define EVMCS1_UNSUPPORTED_EXEC_CTRL (CPU_BASED_ACTIVATE_TERTIARY_CONTROLS) -#define EVMCS1_UNSUPPORTED_2NDEXEC \ - (SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | \ - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | \ - SECONDARY_EXEC_APIC_REGISTER_VIRT | \ - SECONDARY_EXEC_ENABLE_PML | \ - SECONDARY_EXEC_ENABLE_VMFUNC | \ - SECONDARY_EXEC_SHADOW_VMCS | \ +#define EVMCS1_SUPPORTED_PINCTRL \ + (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + PIN_BASED_EXT_INTR_MASK | \ + PIN_BASED_NMI_EXITING | \ + PIN_BASED_VIRTUAL_NMIS) + +#define EVMCS1_SUPPORTED_EXEC_CTRL \ + (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + CPU_BASED_HLT_EXITING | \ + CPU_BASED_CR3_LOAD_EXITING | \ + CPU_BASED_CR3_STORE_EXITING | \ + CPU_BASED_UNCOND_IO_EXITING | \ + CPU_BASED_MOV_DR_EXITING | \ + CPU_BASED_USE_TSC_OFFSETTING | \ + CPU_BASED_MWAIT_EXITING | \ + CPU_BASED_MONITOR_EXITING | \ + CPU_BASED_INVLPG_EXITING | \ + CPU_BASED_RDPMC_EXITING | \ + CPU_BASED_INTR_WINDOW_EXITING | \ + CPU_BASED_CR8_LOAD_EXITING | \ + CPU_BASED_CR8_STORE_EXITING | \ + CPU_BASED_RDTSC_EXITING | \ + CPU_BASED_TPR_SHADOW | \ + CPU_BASED_USE_IO_BITMAPS | \ + CPU_BASED_MONITOR_TRAP_FLAG | \ + CPU_BASED_USE_MSR_BITMAPS | \ + CPU_BASED_NMI_WINDOW_EXITING | \ + CPU_BASED_PAUSE_EXITING | \ + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) + +#define EVMCS1_SUPPORTED_2NDEXEC \ + (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ + SECONDARY_EXEC_WBINVD_EXITING | \ + SECONDARY_EXEC_ENABLE_VPID | \ + SECONDARY_EXEC_ENABLE_EPT | \ + SECONDARY_EXEC_UNRESTRICTED_GUEST | \ + SECONDARY_EXEC_DESC | \ + SECONDARY_EXEC_ENABLE_RDTSCP | \ + SECONDARY_EXEC_ENABLE_INVPCID | \ + SECONDARY_EXEC_XSAVES | \ + SECONDARY_EXEC_RDSEED_EXITING | \ + SECONDARY_EXEC_RDRAND_EXITING | \ SECONDARY_EXEC_TSC_SCALING | \ - SECONDARY_EXEC_PAUSE_LOOP_EXITING) -#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL \ - (VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) -#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (0) -#define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING) + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ + SECONDARY_EXEC_PT_USE_GPA | \ + SECONDARY_EXEC_PT_CONCEAL_VMX | \ + SECONDARY_EXEC_BUS_LOCK_DETECTION | \ + SECONDARY_EXEC_NOTIFY_VM_EXITING | \ + SECONDARY_EXEC_ENCLS_EXITING) + +#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) + +#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ + (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_EXIT_SAVE_DEBUG_CONTROLS | \ + VM_EXIT_ACK_INTR_ON_EXIT | \ + VM_EXIT_HOST_ADDR_SPACE_SIZE | \ + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_IA32_PAT | \ + VM_EXIT_LOAD_IA32_PAT | \ + VM_EXIT_SAVE_IA32_EFER | \ + VM_EXIT_LOAD_IA32_EFER | \ + VM_EXIT_CLEAR_BNDCFGS | \ + VM_EXIT_PT_CONCEAL_PIP | \ + VM_EXIT_CLEAR_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ + (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_ENTRY_LOAD_DEBUG_CONTROLS | \ + VM_ENTRY_IA32E_MODE | \ + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_IA32_PAT | \ + VM_ENTRY_LOAD_IA32_EFER | \ + VM_ENTRY_LOAD_BNDCFGS | \ + VM_ENTRY_PT_CONCEAL_PIP | \ + VM_ENTRY_LOAD_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMFUNC (0) struct evmcs_field { u16 offset; @@ -117,9 +179,7 @@ static __always_inline int get_evmcs_offset(unsigned long field, { int offset = evmcs_field_offset(field, clean_field); - WARN_ONCE(offset < 0, "KVM: accessing unsupported EVMCS field %lx\n", - field); - + WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field); return offset; } @@ -136,7 +196,7 @@ static __always_inline void evmcs_write64(unsigned long field, u64 value) current_evmcs->hv_clean_fields &= ~clean_field; } -static inline void evmcs_write32(unsigned long field, u32 value) +static __always_inline void evmcs_write32(unsigned long field, u32 value) { u16 clean_field; int offset = get_evmcs_offset(field, &clean_field); @@ -148,7 +208,7 @@ static inline void evmcs_write32(unsigned long field, u32 value) current_evmcs->hv_clean_fields &= ~clean_field; } -static inline void evmcs_write16(unsigned long field, u16 value) +static __always_inline void evmcs_write16(unsigned long field, u16 value) { u16 clean_field; int offset = get_evmcs_offset(field, &clean_field); @@ -160,7 +220,7 @@ static inline void evmcs_write16(unsigned long field, u16 value) current_evmcs->hv_clean_fields &= ~clean_field; } -static inline u64 evmcs_read64(unsigned long field) +static __always_inline u64 evmcs_read64(unsigned long field) { int offset = get_evmcs_offset(field, NULL); @@ -170,7 +230,7 @@ static inline u64 evmcs_read64(unsigned long field) return *(u64 *)((char *)current_evmcs + offset); } -static inline u32 evmcs_read32(unsigned long field) +static __always_inline u32 evmcs_read32(unsigned long field) { int offset = get_evmcs_offset(field, NULL); @@ -180,7 +240,7 @@ static inline u32 evmcs_read32(unsigned long field) return *(u32 *)((char *)current_evmcs + offset); } -static inline u16 evmcs_read16(unsigned long field) +static __always_inline u16 evmcs_read16(unsigned long field) { int offset = get_evmcs_offset(field, NULL); @@ -190,16 +250,6 @@ static inline u16 evmcs_read16(unsigned long field) return *(u16 *)((char *)current_evmcs + offset); } -static inline void evmcs_touch_msr_bitmap(void) -{ - if (unlikely(!current_evmcs)) - return; - - if (current_evmcs->hv_enlightenments_control.msr_bitmap) - current_evmcs->hv_clean_fields &= - ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; -} - static inline void evmcs_load(u64 phys_addr) { struct hv_vp_assist_page *vp_ap = @@ -211,15 +261,15 @@ static inline void evmcs_load(u64 phys_addr) vp_ap->enlighten_vmentry = 1; } +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); #else /* !IS_ENABLED(CONFIG_HYPERV) */ static __always_inline void evmcs_write64(unsigned long field, u64 value) {} -static inline void evmcs_write32(unsigned long field, u32 value) {} -static inline void evmcs_write16(unsigned long field, u16 value) {} -static inline u64 evmcs_read64(unsigned long field) { return 0; } -static inline u32 evmcs_read32(unsigned long field) { return 0; } -static inline u16 evmcs_read16(unsigned long field) { return 0; } +static __always_inline void evmcs_write32(unsigned long field, u32 value) {} +static __always_inline void evmcs_write16(unsigned long field, u16 value) {} +static __always_inline u64 evmcs_read64(unsigned long field) { return 0; } +static __always_inline u32 evmcs_read32(unsigned long field) { return 0; } +static __always_inline u16 evmcs_read16(unsigned long field) { return 0; } static inline void evmcs_load(u64 phys_addr) {} -static inline void evmcs_touch_msr_bitmap(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ #define EVMPTR_INVALID (-1ULL) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d93c715cda6a..7c4f5ca405c7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/objtool.h> #include <linux/percpu.h> @@ -203,7 +204,7 @@ static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator) { /* TODO: not to reset guest simply here. */ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); - pr_debug_ratelimited("kvm: nested vmx abort, indicator %d\n", indicator); + pr_debug_ratelimited("nested vmx abort, indicator %d\n", indicator); } static inline bool vmx_control_verify(u32 control, u32 low, u32 high) @@ -5863,11 +5864,10 @@ static int handle_vmfunc(struct kvm_vcpu *vcpu) u32 function = kvm_rax_read(vcpu); /* - * VMFUNC is only supported for nested guests, but we always enable the - * secondary control for simplicity; for non-nested mode, fake that we - * didn't by injecting #UD. + * VMFUNC should never execute cleanly while L1 is active; KVM supports + * VMFUNC for nested VMs, but not for L1. */ - if (!is_guest_mode(vcpu)) { + if (WARN_ON_ONCE(!is_guest_mode(vcpu))) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -6880,6 +6880,7 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_RDRAND_EXITING | SECONDARY_EXEC_ENABLE_INVPCID | + SECONDARY_EXEC_ENABLE_VMFUNC | SECONDARY_EXEC_RDSEED_EXITING | SECONDARY_EXEC_XSAVES | SECONDARY_EXEC_TSC_SCALING | @@ -6912,18 +6913,13 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) SECONDARY_EXEC_ENABLE_PML; msrs->ept_caps |= VMX_EPT_AD_BIT; } - } - if (cpu_has_vmx_vmfunc()) { - msrs->secondary_ctls_high |= - SECONDARY_EXEC_ENABLE_VMFUNC; /* - * Advertise EPTP switching unconditionally - * since we emulate it + * Advertise EPTP switching irrespective of hardware support, + * KVM emulates it in software so long as VMFUNC is supported. */ - if (enable_ept) - msrs->vmfunc_controls = - VMX_VMFUNC_EPTP_SWITCHING; + if (cpu_has_vmx_vmfunc()) + msrs->vmfunc_controls = VMX_VMFUNC_EPTP_SWITCHING; } /* diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index e5cec07ca8d9..e8a3be0b9df9 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -8,6 +8,8 @@ * Avi Kivity <avi@redhat.com> * Gleb Natapov <gleb@redhat.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/types.h> #include <linux/kvm_host.h> #include <linux/perf_event.h> @@ -20,16 +22,19 @@ #define MSR_PMC_FULL_WIDTH_BIT (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0) -static struct kvm_event_hw_type_mapping intel_arch_events[] = { - [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES }, - [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, - [2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES }, - [3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES }, - [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, - [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, - [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, +static struct { + u8 eventsel; + u8 unit_mask; +} const intel_arch_events[] = { + [0] = { 0x3c, 0x00 }, + [1] = { 0xc0, 0x00 }, + [2] = { 0x3c, 0x01 }, + [3] = { 0x2e, 0x4f }, + [4] = { 0x2e, 0x41 }, + [5] = { 0xc4, 0x00 }, + [6] = { 0xc5, 0x00 }, /* The above index must match CPUID 0x0A.EBX bit vector */ - [7] = { 0x00, 0x03, PERF_COUNT_HW_REF_CPU_CYCLES }, + [7] = { 0x00, 0x03 }, }; /* mapping between fixed pmc index and intel_arch_events array */ @@ -762,8 +767,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu) return; warn: - pr_warn_ratelimited("kvm: vcpu-%d: fail to passthrough LBR.\n", - vcpu->vcpu_id); + pr_warn_ratelimited("vcpu-%d: fail to passthrough LBR.\n", vcpu->vcpu_id); } static void intel_pmu_cleanup(struct kvm_vcpu *vcpu) @@ -810,4 +814,6 @@ struct kvm_pmu_ops intel_pmu_ops __initdata = { .reset = intel_pmu_reset, .deliver_pmi = intel_pmu_deliver_pmi, .cleanup = intel_pmu_cleanup, + .EVENTSEL_EVENT = ARCH_PERFMON_EVENTSEL_EVENT, + .MAX_NR_GP_COUNTERS = KVM_INTEL_PMC_MAX_GENERIC, }; diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 1b56c5e5c9fb..94c38bea60e7 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -1,4 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kvm_host.h> #include <asm/irq_remapping.h> diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index b12da2a6dec9..aa53c98034bf 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2021 Intel Corporation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <asm/sgx.h> @@ -164,7 +165,7 @@ static int __handle_encls_ecreate(struct kvm_vcpu *vcpu, if (!vcpu->kvm->arch.sgx_provisioning_allowed && (attributes & SGX_ATTR_PROVISIONKEY)) { if (sgx_12_1->eax & SGX_ATTR_PROVISIONKEY) - pr_warn_once("KVM: SGX PROVISIONKEY advertised but not allowed\n"); + pr_warn_once("SGX PROVISIONKEY advertised but not allowed\n"); kvm_inject_gp(vcpu, 0); return 1; } @@ -381,7 +382,7 @@ int handle_encls(struct kvm_vcpu *vcpu) return handle_encls_ecreate(vcpu); if (leaf == EINIT) return handle_encls_einit(vcpu); - WARN(1, "KVM: unexpected exit on ENCLS[%u]", leaf); + WARN_ONCE(1, "unexpected exit on ENCLS[%u]", leaf); vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; vcpu->run->hw.hardware_exit_reason = EXIT_REASON_ENCLS; return 0; diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index ac290a44a693..7c1996b433e2 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -75,7 +75,7 @@ struct loaded_vmcs { struct vmcs_controls_shadow controls_shadow; }; -static inline bool is_intr_type(u32 intr_info, u32 type) +static __always_inline bool is_intr_type(u32 intr_info, u32 type) { const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK; @@ -146,7 +146,7 @@ static inline bool is_icebp(u32 intr_info) return is_intr_type(intr_info, INTR_TYPE_PRIV_SW_EXCEPTION); } -static inline bool is_nmi(u32 intr_info) +static __always_inline bool is_nmi(u32 intr_info) { return is_intr_type(intr_info, INTR_TYPE_NMI_INTR); } diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c index 2251b60920f8..106a72c923ca 100644 --- a/arch/x86/kvm/vmx/vmcs12.c +++ b/arch/x86/kvm/vmx/vmcs12.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "vmcs12.h" diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 766c6b3ef5ed..f550540ed54e 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -31,6 +31,39 @@ #define VCPU_R15 __VCPU_REGS_R15 * WORD_SIZE #endif +.macro VMX_DO_EVENT_IRQOFF call_insn call_target + /* + * Unconditionally create a stack frame, getting the correct RSP on the + * stack (for x86-64) would take two instructions anyways, and RBP can + * be used to restore RSP to make objtool happy (see below). + */ + push %_ASM_BP + mov %_ASM_SP, %_ASM_BP + +#ifdef CONFIG_X86_64 + /* + * Align RSP to a 16-byte boundary (to emulate CPU behavior) before + * creating the synthetic interrupt stack frame for the IRQ/NMI. + */ + and $-16, %rsp + push $__KERNEL_DS + push %rbp +#endif + pushf + push $__KERNEL_CS + \call_insn \call_target + + /* + * "Restore" RSP from RBP, even though IRET has already unwound RSP to + * the correct value. objtool doesn't know the callee will IRET and, + * without the explicit restore, thinks the stack is getting walloped. + * Using an unwind hint is problematic due to x86-64's dynamic alignment. + */ + mov %_ASM_BP, %_ASM_SP + pop %_ASM_BP + RET +.endm + .section .noinstr.text, "ax" /** @@ -69,8 +102,8 @@ SYM_FUNC_START(__vmx_vcpu_run) */ push %_ASM_ARG2 - /* Copy @flags to BL, _ASM_ARG3 is volatile. */ - mov %_ASM_ARG3B, %bl + /* Copy @flags to EBX, _ASM_ARG3 is volatile. */ + mov %_ASM_ARG3L, %ebx lea (%_ASM_SP), %_ASM_ARG2 call vmx_update_host_rsp @@ -106,7 +139,7 @@ SYM_FUNC_START(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX /* Check if vmlaunch or vmresume is needed */ - testb $VMX_RUN_VMRESUME, %bl + test $VMX_RUN_VMRESUME, %ebx /* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX @@ -128,7 +161,7 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX - /* Check EFLAGS.ZF from 'testb' above */ + /* Check EFLAGS.ZF from 'test VMX_RUN_VMRESUME' above */ jz .Lvmlaunch /* @@ -266,6 +299,10 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) SYM_FUNC_END(__vmx_vcpu_run) +SYM_FUNC_START(vmx_do_nmi_irqoff) + VMX_DO_EVENT_IRQOFF call asm_exc_nmi_kvm_vmx +SYM_FUNC_END(vmx_do_nmi_irqoff) + .section .text, "ax" @@ -320,35 +357,6 @@ SYM_FUNC_START(vmread_error_trampoline) SYM_FUNC_END(vmread_error_trampoline) #endif -SYM_FUNC_START(vmx_do_interrupt_nmi_irqoff) - /* - * Unconditionally create a stack frame, getting the correct RSP on the - * stack (for x86-64) would take two instructions anyways, and RBP can - * be used to restore RSP to make objtool happy (see below). - */ - push %_ASM_BP - mov %_ASM_SP, %_ASM_BP - -#ifdef CONFIG_X86_64 - /* - * Align RSP to a 16-byte boundary (to emulate CPU behavior) before - * creating the synthetic interrupt stack frame for the IRQ/NMI. - */ - and $-16, %rsp - push $__KERNEL_DS - push %rbp -#endif - pushf - push $__KERNEL_CS - CALL_NOSPEC _ASM_ARG1 - - /* - * "Restore" RSP from RBP, even though IRET has already unwound RSP to - * the correct value. objtool doesn't know the callee will IRET and, - * without the explicit restore, thinks the stack is getting walloped. - * Using an unwind hint is problematic due to x86-64's dynamic alignment. - */ - mov %_ASM_BP, %_ASM_SP - pop %_ASM_BP - RET -SYM_FUNC_END(vmx_do_interrupt_nmi_irqoff) +SYM_FUNC_START(vmx_do_interrupt_irqoff) + VMX_DO_EVENT_IRQOFF CALL_NOSPEC _ASM_ARG1 +SYM_FUNC_END(vmx_do_interrupt_irqoff) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index fc9008dbed33..bcac3efcde41 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -12,6 +12,7 @@ * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/highmem.h> #include <linux/hrtimer.h> @@ -444,36 +445,36 @@ void vmread_error(unsigned long field, bool fault) if (fault) kvm_spurious_fault(); else - vmx_insn_failed("kvm: vmread failed: field=%lx\n", field); + vmx_insn_failed("vmread failed: field=%lx\n", field); } noinline void vmwrite_error(unsigned long field, unsigned long value) { - vmx_insn_failed("kvm: vmwrite failed: field=%lx val=%lx err=%u\n", + vmx_insn_failed("vmwrite failed: field=%lx val=%lx err=%u\n", field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void vmclear_error(struct vmcs *vmcs, u64 phys_addr) { - vmx_insn_failed("kvm: vmclear failed: %p/%llx err=%u\n", + vmx_insn_failed("vmclear failed: %p/%llx err=%u\n", vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void vmptrld_error(struct vmcs *vmcs, u64 phys_addr) { - vmx_insn_failed("kvm: vmptrld failed: %p/%llx err=%u\n", + vmx_insn_failed("vmptrld failed: %p/%llx err=%u\n", vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva) { - vmx_insn_failed("kvm: invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n", + vmx_insn_failed("invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n", ext, vpid, gva); } noinline void invept_error(unsigned long ext, u64 eptp, gpa_t gpa) { - vmx_insn_failed("kvm: invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n", + vmx_insn_failed("invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n", ext, eptp, gpa); } @@ -488,8 +489,8 @@ static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu); static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS); static DEFINE_SPINLOCK(vmx_vpid_lock); -struct vmcs_config vmcs_config; -struct vmx_capability vmx_capability; +struct vmcs_config vmcs_config __ro_after_init; +struct vmx_capability vmx_capability __ro_after_init; #define VMX_SEGMENT_FIELD(seg) \ [VCPU_SREG_##seg] = { \ @@ -523,6 +524,8 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) static unsigned long host_idt_base; #if IS_ENABLED(CONFIG_HYPERV) +static struct kvm_x86_ops vmx_x86_ops __initdata; + static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); @@ -551,6 +554,71 @@ static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) return 0; } +static __init void hv_init_evmcs(void) +{ + int cpu; + + if (!enlightened_vmcs) + return; + + /* + * Enlightened VMCS usage should be recommended and the host needs + * to support eVMCS v1 or above. + */ + if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED && + (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >= + KVM_EVMCS_VERSION) { + + /* Check that we have assist pages on all online CPUs */ + for_each_online_cpu(cpu) { + if (!hv_get_vp_assist_page(cpu)) { + enlightened_vmcs = false; + break; + } + } + + if (enlightened_vmcs) { + pr_info("Using Hyper-V Enlightened VMCS\n"); + static_branch_enable(&enable_evmcs); + } + + if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) + vmx_x86_ops.enable_l2_tlb_flush + = hv_enable_l2_tlb_flush; + + } else { + enlightened_vmcs = false; + } +} + +static void hv_reset_evmcs(void) +{ + struct hv_vp_assist_page *vp_ap; + + if (!static_branch_unlikely(&enable_evmcs)) + return; + + /* + * KVM should enable eVMCS if and only if all CPUs have a VP assist + * page, and should reject CPU onlining if eVMCS is enabled the CPU + * doesn't have a VP assist page allocated. + */ + vp_ap = hv_get_vp_assist_page(smp_processor_id()); + if (WARN_ON_ONCE(!vp_ap)) + return; + + /* + * Reset everything to support using non-enlightened VMCS access later + * (e.g. when we reload the module with enlightened_vmcs=0) + */ + vp_ap->nested_control.features.directhypercall = 0; + vp_ap->current_nested_vmcs = 0; + vp_ap->enlighten_vmentry = 0; +} + +#else /* IS_ENABLED(CONFIG_HYPERV) */ +static void hv_init_evmcs(void) {} +static void hv_reset_evmcs(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ /* @@ -1613,8 +1681,8 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) if (!instr_len) goto rip_updated; - WARN(exit_reason.enclave_mode, - "KVM: skipping instruction after SGX enclave VM-Exit"); + WARN_ONCE(exit_reason.enclave_mode, + "skipping instruction after SGX enclave VM-Exit"); orig_rip = kvm_rip_read(vcpu); rip = orig_rip + instr_len; @@ -2138,9 +2206,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { - if (report_ignored_msrs) - vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n", - __func__, data); + kvm_pr_unimpl_wrmsr(vcpu, msr_index, data); data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); } @@ -2448,88 +2514,6 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) } } -static __init int cpu_has_kvm_support(void) -{ - return cpu_has_vmx(); -} - -static __init int vmx_disabled_by_bios(void) -{ - return !boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || - !boot_cpu_has(X86_FEATURE_VMX); -} - -static int kvm_cpu_vmxon(u64 vmxon_pointer) -{ - u64 msr; - - cr4_set_bits(X86_CR4_VMXE); - - asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" - _ASM_EXTABLE(1b, %l[fault]) - : : [vmxon_pointer] "m"(vmxon_pointer) - : : fault); - return 0; - -fault: - WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n", - rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); - cr4_clear_bits(X86_CR4_VMXE); - - return -EFAULT; -} - -static int vmx_hardware_enable(void) -{ - int cpu = raw_smp_processor_id(); - u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); - int r; - - if (cr4_read_shadow() & X86_CR4_VMXE) - return -EBUSY; - - /* - * This can happen if we hot-added a CPU but failed to allocate - * VP assist page for it. - */ - if (static_branch_unlikely(&enable_evmcs) && - !hv_get_vp_assist_page(cpu)) - return -EFAULT; - - intel_pt_handle_vmx(1); - - r = kvm_cpu_vmxon(phys_addr); - if (r) { - intel_pt_handle_vmx(0); - return r; - } - - if (enable_ept) - ept_sync_global(); - - return 0; -} - -static void vmclear_local_loaded_vmcss(void) -{ - int cpu = raw_smp_processor_id(); - struct loaded_vmcs *v, *n; - - list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu), - loaded_vmcss_on_cpu_link) - __loaded_vmcs_clear(v); -} - -static void vmx_hardware_disable(void) -{ - vmclear_local_loaded_vmcss(); - - if (cpu_vmxoff()) - kvm_spurious_fault(); - - intel_pt_handle_vmx(0); -} - /* * There is no X86_FEATURE for SGX yet, but anyway we need to query CPUID * directly instead of going through cpu_has(), to ensure KVM is trapping @@ -2565,8 +2549,7 @@ static bool cpu_has_perf_global_ctrl_bug(void) return false; } -static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, - u32 msr, u32 *result) +static int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, u32 msr, u32 *result) { u32 vmx_msr_low, vmx_msr_high; u32 ctl = ctl_min | ctl_opt; @@ -2584,7 +2567,7 @@ static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, return 0; } -static __init u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) +static u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) { u64 allowed; @@ -2593,8 +2576,8 @@ static __init u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) return ctl_opt & allowed; } -static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, - struct vmx_capability *vmx_cap) +static int setup_vmcs_config(struct vmcs_config *vmcs_conf, + struct vmx_capability *vmx_cap) { u32 vmx_msr_low, vmx_msr_high; u32 _pin_based_exec_control = 0; @@ -2752,9 +2735,127 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, vmcs_conf->vmentry_ctrl = _vmentry_control; vmcs_conf->misc = misc_msr; +#if IS_ENABLED(CONFIG_HYPERV) + if (enlightened_vmcs) + evmcs_sanitize_exec_ctrls(vmcs_conf); +#endif + + return 0; +} + +static bool kvm_is_vmx_supported(void) +{ + int cpu = raw_smp_processor_id(); + + if (!cpu_has_vmx()) { + pr_err("VMX not supported by CPU %d\n", cpu); + return false; + } + + if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || + !this_cpu_has(X86_FEATURE_VMX)) { + pr_err("VMX not enabled (by BIOS) in MSR_IA32_FEAT_CTL on CPU %d\n", cpu); + return false; + } + + return true; +} + +static int vmx_check_processor_compat(void) +{ + int cpu = raw_smp_processor_id(); + struct vmcs_config vmcs_conf; + struct vmx_capability vmx_cap; + + if (!kvm_is_vmx_supported()) + return -EIO; + + if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) { + pr_err("Failed to setup VMCS config on CPU %d\n", cpu); + return -EIO; + } + if (nested) + nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept); + if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config))) { + pr_err("Inconsistent VMCS config on CPU %d\n", cpu); + return -EIO; + } + return 0; +} + +static int kvm_cpu_vmxon(u64 vmxon_pointer) +{ + u64 msr; + + cr4_set_bits(X86_CR4_VMXE); + + asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" + _ASM_EXTABLE(1b, %l[fault]) + : : [vmxon_pointer] "m"(vmxon_pointer) + : : fault); + return 0; + +fault: + WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n", + rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); + cr4_clear_bits(X86_CR4_VMXE); + + return -EFAULT; +} + +static int vmx_hardware_enable(void) +{ + int cpu = raw_smp_processor_id(); + u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); + int r; + + if (cr4_read_shadow() & X86_CR4_VMXE) + return -EBUSY; + + /* + * This can happen if we hot-added a CPU but failed to allocate + * VP assist page for it. + */ + if (static_branch_unlikely(&enable_evmcs) && + !hv_get_vp_assist_page(cpu)) + return -EFAULT; + + intel_pt_handle_vmx(1); + + r = kvm_cpu_vmxon(phys_addr); + if (r) { + intel_pt_handle_vmx(0); + return r; + } + + if (enable_ept) + ept_sync_global(); + return 0; } +static void vmclear_local_loaded_vmcss(void) +{ + int cpu = raw_smp_processor_id(); + struct loaded_vmcs *v, *n; + + list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu), + loaded_vmcss_on_cpu_link) + __loaded_vmcs_clear(v); +} + +static void vmx_hardware_disable(void) +{ + vmclear_local_loaded_vmcss(); + + if (cpu_vmxoff()) + kvm_spurious_fault(); + + hv_reset_evmcs(); + + intel_pt_handle_vmx(0); +} + struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) { int node = cpu_to_node(cpu); @@ -2950,9 +3051,8 @@ static void fix_rmode_seg(int seg, struct kvm_segment *save) var.type = 0x3; var.avl = 0; if (save->base & 0xf) - printk_once(KERN_WARNING "kvm: segment base is not " - "paragraph aligned when entering " - "protected mode (seg=%d)", seg); + pr_warn_once("segment base is not paragraph aligned " + "when entering protected mode (seg=%d)", seg); } vmcs_write16(sf->selector, var.selector); @@ -2982,8 +3082,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu) * vcpu. Warn the user that an update is overdue. */ if (!kvm_vmx->tss_addr) - printk_once(KERN_WARNING "kvm: KVM_SET_TSS_ADDR need to be " - "called before entering vcpu\n"); + pr_warn_once("KVM_SET_TSS_ADDR needs to be called before running vCPU\n"); vmx_segment_cache_clear(vmx); @@ -3440,18 +3539,15 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; - if (var->unusable || !var->present) - ar = 1 << 16; - else { - ar = var->type & 15; - ar |= (var->s & 1) << 4; - ar |= (var->dpl & 3) << 5; - ar |= (var->present & 1) << 7; - ar |= (var->avl & 1) << 12; - ar |= (var->l & 1) << 13; - ar |= (var->db & 1) << 14; - ar |= (var->g & 1) << 15; - } + ar = var->type & 15; + ar |= (var->s & 1) << 4; + ar |= (var->dpl & 3) << 5; + ar |= (var->present & 1) << 7; + ar |= (var->avl & 1) << 12; + ar |= (var->l & 1) << 13; + ar |= (var->db & 1) << 14; + ar |= (var->g & 1) << 15; + ar |= (var->unusable || !var->present) << 16; return ar; } @@ -3803,39 +3899,6 @@ static void seg_setup(int seg) vmcs_write32(sf->ar_bytes, ar); } -static int alloc_apic_access_page(struct kvm *kvm) -{ - struct page *page; - void __user *hva; - int ret = 0; - - mutex_lock(&kvm->slots_lock); - if (kvm->arch.apic_access_memslot_enabled) - goto out; - hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, - APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); - if (IS_ERR(hva)) { - ret = PTR_ERR(hva); - goto out; - } - - page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); - if (is_error_page(page)) { - ret = -EFAULT; - goto out; - } - - /* - * Do not pin the page in memory, so that memory hot-unplug - * is able to migrate it. - */ - put_page(page); - kvm->arch.apic_access_memslot_enabled = true; -out: - mutex_unlock(&kvm->slots_lock); - return ret; -} - int allocate_vpid(void) { int vpid; @@ -3868,8 +3931,13 @@ static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR * bitmap has changed. */ - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs)) { + struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; + + if (evmcs->hv_enlightenments_control.msr_bitmap) + evmcs->hv_clean_fields &= + ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; + } vmx->nested.force_msr_bitmap_recalc = true; } @@ -3950,29 +4018,20 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) vmx_set_msr_bitmap_write(msr_bitmap, msr); } -static void vmx_reset_x2apic_msrs(struct kvm_vcpu *vcpu, u8 mode) -{ - unsigned long *msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; - unsigned long read_intercept; - int msr; - - read_intercept = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0; - - for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { - unsigned int read_idx = msr / BITS_PER_LONG; - unsigned int write_idx = read_idx + (0x800 / sizeof(long)); - - msr_bitmap[read_idx] = read_intercept; - msr_bitmap[write_idx] = ~0ul; - } -} - static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu) { + /* + * x2APIC indices for 64-bit accesses into the RDMSR and WRMSR halves + * of the MSR bitmap. KVM emulates APIC registers up through 0x3f0, + * i.e. MSR 0x83f, and so only needs to dynamically manipulate 64 bits. + */ + const int read_idx = APIC_BASE_MSR / BITS_PER_LONG_LONG; + const int write_idx = read_idx + (0x800 / sizeof(u64)); struct vcpu_vmx *vmx = to_vmx(vcpu); + u64 *msr_bitmap = (u64 *)vmx->vmcs01.msr_bitmap; u8 mode; - if (!cpu_has_vmx_msr_bitmap()) + if (!cpu_has_vmx_msr_bitmap() || WARN_ON_ONCE(!lapic_in_kernel(vcpu))) return; if (cpu_has_secondary_exec_ctrls() && @@ -3990,7 +4049,18 @@ static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu) vmx->x2apic_msr_bitmap_mode = mode; - vmx_reset_x2apic_msrs(vcpu, mode); + /* + * Reset the bitmap for MSRs 0x800 - 0x83f. Leave AMD's uber-extended + * registers (0x840 and above) intercepted, KVM doesn't support them. + * Intercept all writes by default and poke holes as needed. Pass + * through reads for all valid registers by default in x2APIC+APICv + * mode, only the current timer count needs on-demand emulation by KVM. + */ + if (mode & MSR_BITMAP_MODE_X2APIC_APICV) + msr_bitmap[read_idx] = ~kvm_lapic_readable_reg_mask(vcpu->arch.apic); + else + msr_bitmap[read_idx] = ~0ull; + msr_bitmap[write_idx] = ~0ull; /* * TPR reads and writes can be virtualized even if virtual interrupt @@ -4522,6 +4592,12 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; + /* + * KVM doesn't support VMFUNC for L1, but the control is set in KVM's + * base configuration as KVM emulates VMFUNC[EPTP_SWITCHING] for L2. + */ + exec_control &= ~SECONDARY_EXEC_ENABLE_VMFUNC; + /* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP, * in vmx_set_cr4. */ exec_control &= ~SECONDARY_EXEC_DESC; @@ -4538,7 +4614,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) * it needs to be set here when dirty logging is already active, e.g. * if this vCPU was created after dirty logging was enabled. */ - if (!vcpu->kvm->arch.cpu_dirty_logging_count) + if (!enable_pml || !atomic_read(&vcpu->kvm->nr_memslots_dirty_logging)) exec_control &= ~SECONDARY_EXEC_ENABLE_PML; if (cpu_has_vmx_xsaves()) { @@ -5102,8 +5178,13 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) vect_info = vmx->idt_vectoring_info; intr_info = vmx_get_intr_info(vcpu); + /* + * Machine checks are handled by handle_exception_irqoff(), or by + * vmx_vcpu_run() if a #MC occurs on VM-Entry. NMIs are handled by + * vmx_vcpu_enter_exit(). + */ if (is_machine_check(intr_info) || is_nmi(intr_info)) - return 1; /* handled by handle_exception_nmi_irqoff() */ + return 1; /* * Queue the exception here instead of in handle_nm_fault_irqoff(). @@ -6793,17 +6874,8 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir)); } -void vmx_do_interrupt_nmi_irqoff(unsigned long entry); - -static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu, - unsigned long entry) -{ - bool is_nmi = entry == (unsigned long)asm_exc_nmi_noist; - - kvm_before_interrupt(vcpu, is_nmi ? KVM_HANDLING_NMI : KVM_HANDLING_IRQ); - vmx_do_interrupt_nmi_irqoff(entry); - kvm_after_interrupt(vcpu); -} +void vmx_do_interrupt_irqoff(unsigned long entry); +void vmx_do_nmi_irqoff(void); static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) { @@ -6825,9 +6897,8 @@ static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); } -static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) +static void handle_exception_irqoff(struct vcpu_vmx *vmx) { - const unsigned long nmi_entry = (unsigned long)asm_exc_nmi_noist; u32 intr_info = vmx_get_intr_info(&vmx->vcpu); /* if exit due to PF check for async PF */ @@ -6839,9 +6910,6 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) /* Handle machine checks before interrupts are enabled */ else if (is_machine_check(intr_info)) kvm_machine_check(); - /* We need to handle NMIs before interrupts are enabled */ - else if (is_nmi(intr_info)) - handle_interrupt_nmi_irqoff(&vmx->vcpu, nmi_entry); } static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) @@ -6851,10 +6919,13 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) gate_desc *desc = (gate_desc *)host_idt_base + vector; if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, - "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info)) + "unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; - handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc)); + kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); + vmx_do_interrupt_irqoff(gate_offset(desc)); + kvm_after_interrupt(vcpu); + vcpu->arch.at_instruction_boundary = true; } @@ -6868,7 +6939,7 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) handle_external_interrupt_irqoff(vcpu); else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI) - handle_exception_nmi_irqoff(vmx); + handle_exception_irqoff(vmx); } /* @@ -7103,9 +7174,10 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) } static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, - struct vcpu_vmx *vmx, - unsigned long flags) + unsigned int flags) { + struct vcpu_vmx *vmx = to_vmx(vcpu); + guest_state_enter_irqoff(); /* L1D Flush includes CPU buffer clear to mitigate MDS */ @@ -7129,6 +7201,18 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, vmx_enable_fb_clear(vmx); + if (unlikely(vmx->fail)) + vmx->exit_reason.full = 0xdead; + else + vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON); + + if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI && + is_nmi(vmx_get_intr_info(vcpu))) { + kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); + vmx_do_nmi_irqoff(); + kvm_after_interrupt(vcpu); + } + guest_state_exit_irqoff(); } @@ -7223,7 +7307,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) kvm_wait_lapic_expire(vcpu); /* The actual VMENTER/EXIT is in the .noinstr.text section. */ - vmx_vcpu_enter_exit(vcpu, vmx, __vmx_vcpu_run_flags(vmx)); + vmx_vcpu_enter_exit(vcpu, __vmx_vcpu_run_flags(vmx)); /* All fields are clean at this point */ if (static_branch_unlikely(&enable_evmcs)) { @@ -7270,12 +7354,9 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->idt_vectoring_info = 0; - if (unlikely(vmx->fail)) { - vmx->exit_reason.full = 0xdead; + if (unlikely(vmx->fail)) return EXIT_FASTPATH_NONE; - } - vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON); if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY)) kvm_machine_check(); @@ -7389,7 +7470,7 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) vmx->loaded_vmcs = &vmx->vmcs01; if (cpu_need_virtualize_apic_accesses(vcpu)) { - err = alloc_apic_access_page(vcpu->kvm); + err = kvm_alloc_apic_access_page(vcpu->kvm); if (err) goto free_vmcs; } @@ -7449,29 +7530,6 @@ static int vmx_vm_init(struct kvm *kvm) return 0; } -static int __init vmx_check_processor_compat(void) -{ - struct vmcs_config vmcs_conf; - struct vmx_capability vmx_cap; - - if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || - !this_cpu_has(X86_FEATURE_VMX)) { - pr_err("kvm: VMX is disabled on CPU %d\n", smp_processor_id()); - return -EIO; - } - - if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) - return -EIO; - if (nested) - nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept); - if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { - printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", - smp_processor_id()); - return -EIO; - } - return 0; -} - static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { u8 cache; @@ -7943,17 +8001,20 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + if (WARN_ON_ONCE(!enable_pml)) + return; + if (is_guest_mode(vcpu)) { vmx->nested.update_vmcs01_cpu_dirty_logging = true; return; } /* - * Note, cpu_dirty_logging_count can be changed concurrent with this + * Note, nr_memslots_dirty_logging can be changed concurrent with this * code, but in that case another update request will be made and so * the guest will never run with a stale PML value. */ - if (vcpu->kvm->arch.cpu_dirty_logging_count) + if (atomic_read(&vcpu->kvm->nr_memslots_dirty_logging)) secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_ENABLE_PML); else secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML); @@ -8051,17 +8112,16 @@ static void vmx_hardware_unsetup(void) free_kvm_area(); } -static bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) -{ - ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | - BIT(APICV_INHIBIT_REASON_ABSENT) | - BIT(APICV_INHIBIT_REASON_HYPERV) | - BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | - BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | - BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); - - return supported & BIT(reason); -} +#define VMX_REQUIRED_APICV_INHIBITS \ +( \ + BIT(APICV_INHIBIT_REASON_DISABLE)| \ + BIT(APICV_INHIBIT_REASON_ABSENT) | \ + BIT(APICV_INHIBIT_REASON_HYPERV) | \ + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ + BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) \ +) static void vmx_vm_destroy(struct kvm *kvm) { @@ -8071,7 +8131,9 @@ static void vmx_vm_destroy(struct kvm *kvm) } static struct kvm_x86_ops vmx_x86_ops __initdata = { - .name = "kvm_intel", + .name = KBUILD_MODNAME, + + .check_processor_compatibility = vmx_check_processor_compat, .hardware_unsetup = vmx_hardware_unsetup, @@ -8145,7 +8207,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, .apicv_post_state_restore = vmx_apicv_post_state_restore, - .check_apicv_inhibit_reasons = vmx_check_apicv_inhibit_reasons, + .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, @@ -8291,7 +8353,7 @@ static __init int hardware_setup(void) return -EIO; if (cpu_has_perf_global_ctrl_bug()) - pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " + pr_warn_once("VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " "does not work properly. Using workaround\n"); if (boot_cpu_has(X86_FEATURE_NX)) @@ -8299,7 +8361,7 @@ static __init int hardware_setup(void) if (boot_cpu_has(X86_FEATURE_MPX)) { rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs); - WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost"); + WARN_ONCE(host_bndcfgs, "BNDCFGS in host will be lost"); } if (!cpu_has_vmx_mpx()) @@ -8318,7 +8380,7 @@ static __init int hardware_setup(void) /* NX support is required for shadow paging. */ if (!enable_ept && !boot_cpu_has(X86_FEATURE_NX)) { - pr_err_ratelimited("kvm: NX (Execute Disable) not supported\n"); + pr_err_ratelimited("NX (Execute Disable) not supported\n"); return -EOPNOTSUPP; } @@ -8470,9 +8532,6 @@ static __init int hardware_setup(void) } static struct kvm_x86_init_ops vmx_init_ops __initdata = { - .cpu_has_kvm_support = cpu_has_kvm_support, - .disabled_by_bios = vmx_disabled_by_bios, - .check_processor_compatibility = vmx_check_processor_compat, .hardware_setup = hardware_setup, .handle_intel_pt_intr = NULL, @@ -8490,41 +8549,23 @@ static void vmx_cleanup_l1d_flush(void) l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; } -static void vmx_exit(void) +static void __vmx_exit(void) { + allow_smaller_maxphyaddr = false; + #ifdef CONFIG_KEXEC_CORE RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); synchronize_rcu(); #endif + vmx_cleanup_l1d_flush(); +} +static void vmx_exit(void) +{ kvm_exit(); + kvm_x86_vendor_exit(); -#if IS_ENABLED(CONFIG_HYPERV) - if (static_branch_unlikely(&enable_evmcs)) { - int cpu; - struct hv_vp_assist_page *vp_ap; - /* - * Reset everything to support using non-enlightened VMCS - * access later (e.g. when we reload the module with - * enlightened_vmcs=0) - */ - for_each_online_cpu(cpu) { - vp_ap = hv_get_vp_assist_page(cpu); - - if (!vp_ap) - continue; - - vp_ap->nested_control.features.directhypercall = 0; - vp_ap->current_nested_vmcs = 0; - vp_ap->enlighten_vmentry = 0; - } - - static_branch_disable(&enable_evmcs); - } -#endif - vmx_cleanup_l1d_flush(); - - allow_smaller_maxphyaddr = false; + __vmx_exit(); } module_exit(vmx_exit); @@ -8532,56 +8573,29 @@ static int __init vmx_init(void) { int r, cpu; -#if IS_ENABLED(CONFIG_HYPERV) + if (!kvm_is_vmx_supported()) + return -EOPNOTSUPP; + /* - * Enlightened VMCS usage should be recommended and the host needs - * to support eVMCS v1 or above. We can also disable eVMCS support - * with module parameter. + * Note, hv_init_evmcs() touches only VMX knobs, i.e. there's nothing + * to unwind if a later step fails. */ - if (enlightened_vmcs && - ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED && - (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >= - KVM_EVMCS_VERSION) { - - /* Check that we have assist pages on all online CPUs */ - for_each_online_cpu(cpu) { - if (!hv_get_vp_assist_page(cpu)) { - enlightened_vmcs = false; - break; - } - } + hv_init_evmcs(); - if (enlightened_vmcs) { - pr_info("KVM: vmx: using Hyper-V Enlightened VMCS\n"); - static_branch_enable(&enable_evmcs); - } - - if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) - vmx_x86_ops.enable_l2_tlb_flush - = hv_enable_l2_tlb_flush; - - } else { - enlightened_vmcs = false; - } -#endif - - r = kvm_init(&vmx_init_ops, sizeof(struct vcpu_vmx), - __alignof__(struct vcpu_vmx), THIS_MODULE); + r = kvm_x86_vendor_init(&vmx_init_ops); if (r) return r; /* - * Must be called after kvm_init() so enable_ept is properly set + * Must be called after common x86 init so enable_ept is properly set * up. Hand the parameter mitigation value in which was stored in * the pre module init parser. If no parameter was given, it will * contain 'auto' which will be turned into the default 'cond' * mitigation mode. */ r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); - if (r) { - vmx_exit(); - return r; - } + if (r) + goto err_l1d_flush; vmx_setup_fb_clear_ctrl(); @@ -8605,6 +8619,21 @@ static int __init vmx_init(void) if (!enable_ept) allow_smaller_maxphyaddr = true; + /* + * Common KVM initialization _must_ come last, after this, /dev/kvm is + * exposed to userspace! + */ + r = kvm_init(sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx), + THIS_MODULE); + if (r) + goto err_kvm_init; + return 0; + +err_kvm_init: + __vmx_exit(); +err_l1d_flush: + kvm_x86_vendor_exit(); + return r; } module_init(vmx_init); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index a3da84f4ea45..2acdc54bc34b 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -640,12 +640,12 @@ BUILD_CONTROLS_SHADOW(tertiary_exec, TERTIARY_VM_EXEC_CONTROL, 64) (1 << VCPU_EXREG_EXIT_INFO_1) | \ (1 << VCPU_EXREG_EXIT_INFO_2)) -static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) +static __always_inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) { return container_of(kvm, struct kvm_vmx, kvm); } -static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) +static __always_inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) { return container_of(vcpu, struct vcpu_vmx, vcpu); } @@ -669,25 +669,23 @@ void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu); int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu); void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu); -static inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu) +static __always_inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!kvm_register_is_available(vcpu, VCPU_EXREG_EXIT_INFO_1)) { - kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1); + if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1)) vmx->exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - } + return vmx->exit_qualification; } -static inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu) +static __always_inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!kvm_register_is_available(vcpu, VCPU_EXREG_EXIT_INFO_2)) { - kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2); + if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2)) vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - } + return vmx->exit_intr_info; } diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 842dc898c972..db95bde52998 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -100,8 +100,10 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) return value; do_fail: - WARN_ONCE(1, "kvm: vmread failed: field=%lx\n", field); - pr_warn_ratelimited("kvm: vmread failed: field=%lx\n", field); + instrumentation_begin(); + WARN_ONCE(1, KBUILD_MODNAME ": vmread failed: field=%lx\n", field); + pr_warn_ratelimited(KBUILD_MODNAME ": vmread failed: field=%lx\n", field); + instrumentation_end(); return 0; do_exception: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index da4bbd043a7b..7713420abab0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -15,6 +15,7 @@ * Amit Shah <amit.shah@qumranet.com> * Ben-Ami Yassour <benami@il.ibm.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "irq.h" @@ -128,6 +129,7 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu); static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); +static DEFINE_MUTEX(vendor_module_lock); struct kvm_x86_ops kvm_x86_ops __read_mostly; #define KVM_X86_OP(func) \ @@ -191,6 +193,10 @@ module_param(enable_pmu, bool, 0444); bool __read_mostly eager_page_split = true; module_param(eager_page_split, bool, 0644); +/* Enable/disable SMT_RSB bug mitigation */ +bool __read_mostly mitigate_smt_rsb; +module_param(mitigate_smt_rsb, bool, 0444); + /* * Restoring the host value for MSRs that are only consumed when running in * usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU @@ -1417,7 +1423,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc); * may depend on host virtualization features rather than host cpu features. */ -static const u32 msrs_to_save_all[] = { +static const u32 msrs_to_save_base[] = { MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 @@ -1434,6 +1440,10 @@ static const u32 msrs_to_save_all[] = { MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, MSR_IA32_UMWAIT_CONTROL, + MSR_IA32_XFD, MSR_IA32_XFD_ERR, +}; + +static const u32 msrs_to_save_pmu[] = { MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, @@ -1458,11 +1468,10 @@ static const u32 msrs_to_save_all[] = { MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, - - MSR_IA32_XFD, MSR_IA32_XFD_ERR, }; -static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)]; +static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + + ARRAY_SIZE(msrs_to_save_pmu)]; static unsigned num_msrs_to_save; static const u32 emulated_msrs_all[] = { @@ -1480,7 +1489,7 @@ static const u32 emulated_msrs_all[] = { HV_X64_MSR_STIMER0_CONFIG, HV_X64_MSR_VP_ASSIST_PAGE, HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, - HV_X64_MSR_TSC_EMULATION_STATUS, + HV_X64_MSR_TSC_EMULATION_STATUS, HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_X64_MSR_SYNDBG_OPTIONS, HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, @@ -1685,6 +1694,9 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { + if (efer & EFER_AUTOIBRS && !guest_cpuid_has(vcpu, X86_FEATURE_AUTOIBRS)) + return false; + if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT)) return false; @@ -2086,7 +2098,7 @@ static int kvm_emulate_monitor_mwait(struct kvm_vcpu *vcpu, const char *insn) !guest_cpuid_has(vcpu, X86_FEATURE_MWAIT)) return kvm_handle_invalid_op(vcpu); - pr_warn_once("kvm: %s instruction emulated as NOP!\n", insn); + pr_warn_once("%s instruction emulated as NOP!\n", insn); return kvm_emulate_as_nop(vcpu); } int kvm_emulate_mwait(struct kvm_vcpu *vcpu) @@ -2433,7 +2445,8 @@ static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm); thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm); if (user_tsc_khz < thresh_lo || user_tsc_khz > thresh_hi) { - pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", user_tsc_khz, thresh_lo, thresh_hi); + pr_debug("requested TSC rate %u falls outside tolerance [%u,%u]\n", + user_tsc_khz, thresh_lo, thresh_hi); use_scaling = 1; } return set_tsc_khz(vcpu, user_tsc_khz, use_scaling); @@ -3158,6 +3171,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) &vcpu->hv_clock.tsc_shift, &vcpu->hv_clock.tsc_to_system_mul); vcpu->hw_tsc_khz = tgt_tsc_khz; + kvm_xen_update_tsc_info(v); } vcpu->hv_clock.tsc_timestamp = tsc_timestamp; @@ -3555,9 +3569,20 @@ static void record_steal_time(struct kvm_vcpu *vcpu) mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } +static bool kvm_is_msr_to_save(u32 msr_index) +{ + unsigned int i; + + for (i = 0; i < num_msrs_to_save; i++) { + if (msrs_to_save[i] == msr_index) + return true; + } + + return false; +} + int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - bool pr = false; u32 msr = msr_info->index; u64 data = msr_info->data; @@ -3603,15 +3628,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data == BIT_ULL(18)) { vcpu->arch.msr_hwcr = data; } else if (data != 0) { - vcpu_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", - data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } break; case MSR_FAM10H_MMIO_CONF_BASE: if (data != 0) { - vcpu_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: " - "0x%llx\n", data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } break; @@ -3791,16 +3814,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: - pr = true; - fallthrough; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); - if (pr || data != 0) - vcpu_unimpl(vcpu, "disabled perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); + if (data) + kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_K7_CLK_CTL: /* @@ -3821,15 +3841,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: + case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_set_msr_common(vcpu, msr, data, msr_info->host_initiated); case MSR_IA32_BBL_CR_CTL3: /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. */ - if (report_ignored_msrs) - vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", - msr, data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_AMD64_OSVW_ID_LENGTH: if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) @@ -3877,20 +3896,18 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.guest_fpu.xfd_err = data; break; #endif - case MSR_IA32_PEBS_ENABLE: - case MSR_IA32_DS_AREA: - case MSR_PEBS_DATA_CFG: - case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: + default: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); + /* * Userspace is allowed to write '0' to MSRs that KVM reports * as to-be-saved, even if an MSRs isn't fully supported. */ - return !msr_info->host_initiated || data; - default: - if (kvm_pmu_is_valid_msr(vcpu, msr)) - return kvm_pmu_set_msr(vcpu, msr_info); + if (msr_info->host_initiated && !data && + kvm_is_msr_to_save(msr)) + break; + return KVM_MSR_RET_INVALID; } return 0; @@ -3980,20 +3997,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_DRAM_ENERGY_STATUS: /* DRAM controller */ msr_info->data = 0; break; - case MSR_IA32_PEBS_ENABLE: - case MSR_IA32_DS_AREA: - case MSR_PEBS_DATA_CFG: - case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: - if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) - return kvm_pmu_get_msr(vcpu, msr_info); - /* - * Userspace is allowed to read MSRs that KVM reports as - * to-be-saved, even if an MSR isn't fully supported. - */ - if (!msr_info->host_initiated) - return 1; - msr_info->data = 0; - break; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: @@ -4191,6 +4194,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: + case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); @@ -4248,6 +4252,17 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); + + /* + * Userspace is allowed to read MSRs that KVM reports as + * to-be-saved, even if an MSR isn't fully supported. + */ + if (msr_info->host_initiated && + kvm_is_msr_to_save(msr_info->index)) { + msr_info->data = 0; + break; + } + return KVM_MSR_RET_INVALID; } return 0; @@ -4285,8 +4300,8 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, { struct kvm_msrs msrs; struct kvm_msr_entry *entries; - int r, n; unsigned size; + int r; r = -EFAULT; if (copy_from_user(&msrs, user_msrs, sizeof(msrs))) @@ -4303,17 +4318,11 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, goto out; } - r = n = __msr_io(vcpu, &msrs, entries, do_msr); - if (r < 0) - goto out_free; + r = __msr_io(vcpu, &msrs, entries, do_msr); - r = -EFAULT; if (writeback && copy_to_user(user_msrs->entries, entries, size)) - goto out_free; - - r = n; + r = -EFAULT; -out_free: kfree(entries); out: return r; @@ -4401,6 +4410,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_PMU_EVENT_FILTER: + case KVM_CAP_PMU_EVENT_MASKED_EVENTS: case KVM_CAP_GET_MSR_FEATURES: case KVM_CAP_MSR_PLATFORM_INFO: case KVM_CAP_EXCEPTION_PAYLOAD: @@ -4448,10 +4458,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_CLOCK_VALID_FLAGS; break; case KVM_CAP_X86_DISABLE_EXITS: - r |= KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE | - KVM_X86_DISABLE_EXITS_CSTATE; - if(kvm_can_mwait_in_guest()) - r |= KVM_X86_DISABLE_EXITS_MWAIT; + r = KVM_X86_DISABLE_EXITS_PAUSE; + + if (!mitigate_smt_rsb) { + r |= KVM_X86_DISABLE_EXITS_HLT | + KVM_X86_DISABLE_EXITS_CSTATE; + + if (kvm_can_mwait_in_guest()) + r |= KVM_X86_DISABLE_EXITS_MWAIT; + } break; case KVM_CAP_X86_SMM: if (!IS_ENABLED(CONFIG_KVM_SMM)) @@ -5254,12 +5269,11 @@ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, { unsigned long val; + memset(dbgregs, 0, sizeof(*dbgregs)); memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); kvm_get_dr(vcpu, 6, &val); dbgregs->dr6 = val; dbgregs->dr7 = vcpu->arch.dr7; - dbgregs->flags = 0; - memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved)); } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, @@ -6227,15 +6241,26 @@ split_irqchip_unlock: if (cap->args[0] & ~KVM_X86_DISABLE_VALID_EXITS) break; - if ((cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) && - kvm_can_mwait_in_guest()) - kvm->arch.mwait_in_guest = true; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT) - kvm->arch.hlt_in_guest = true; if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE) kvm->arch.pause_in_guest = true; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE) - kvm->arch.cstate_in_guest = true; + +#define SMT_RSB_MSG "This processor is affected by the Cross-Thread Return Predictions vulnerability. " \ + "KVM_CAP_X86_DISABLE_EXITS should only be used with SMT disabled or trusted guests." + + if (!mitigate_smt_rsb) { + if (boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible() && + (cap->args[0] & ~KVM_X86_DISABLE_EXITS_PAUSE)) + pr_warn_once(SMT_RSB_MSG); + + if ((cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) && + kvm_can_mwait_in_guest()) + kvm->arch.mwait_in_guest = true; + if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT) + kvm->arch.hlt_in_guest = true; + if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE) + kvm->arch.cstate_in_guest = true; + } + r = 0; break; case KVM_CAP_MSR_PLATFORM_INFO: @@ -6460,7 +6485,7 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, struct kvm_x86_msr_filter *new_filter, *old_filter; bool default_allow; bool empty = true; - int r = 0; + int r; u32 i; if (filter->flags & ~KVM_MSR_FILTER_VALID_MASK) @@ -6486,17 +6511,14 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, } mutex_lock(&kvm->lock); - - /* The per-VM filter is protected by kvm->lock... */ - old_filter = srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1); - - rcu_assign_pointer(kvm->arch.msr_filter, new_filter); + old_filter = rcu_replace_pointer(kvm->arch.msr_filter, new_filter, + mutex_is_locked(&kvm->lock)); + mutex_unlock(&kvm->lock); synchronize_srcu(&kvm->srcu); kvm_free_msr_filter(old_filter); kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED); - mutex_unlock(&kvm->lock); return 0; } @@ -6996,83 +7018,98 @@ out: return r; } -static void kvm_init_msr_list(void) +static void kvm_probe_msr_to_save(u32 msr_index) { u32 dummy[2]; + + if (rdmsr_safe(msr_index, &dummy[0], &dummy[1])) + return; + + /* + * Even MSRs that are valid in the host may not be exposed to guests in + * some cases. + */ + switch (msr_index) { + case MSR_IA32_BNDCFGS: + if (!kvm_mpx_supported()) + return; + break; + case MSR_TSC_AUX: + if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && + !kvm_cpu_cap_has(X86_FEATURE_RDPID)) + return; + break; + case MSR_IA32_UMWAIT_CONTROL: + if (!kvm_cpu_cap_has(X86_FEATURE_WAITPKG)) + return; + break; + case MSR_IA32_RTIT_CTL: + case MSR_IA32_RTIT_STATUS: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) + return; + break; + case MSR_IA32_RTIT_CR3_MATCH: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || + !intel_pt_validate_hw_cap(PT_CAP_cr3_filtering)) + return; + break; + case MSR_IA32_RTIT_OUTPUT_BASE: + case MSR_IA32_RTIT_OUTPUT_MASK: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || + (!intel_pt_validate_hw_cap(PT_CAP_topa_output) && + !intel_pt_validate_hw_cap(PT_CAP_single_range_output))) + return; + break; + case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || + (msr_index - MSR_IA32_RTIT_ADDR0_A >= + intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)) + return; + break; + case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX: + if (msr_index - MSR_ARCH_PERFMON_PERFCTR0 >= + kvm_pmu_cap.num_counters_gp) + return; + break; + case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX: + if (msr_index - MSR_ARCH_PERFMON_EVENTSEL0 >= + kvm_pmu_cap.num_counters_gp) + return; + break; + case MSR_ARCH_PERFMON_FIXED_CTR0 ... MSR_ARCH_PERFMON_FIXED_CTR_MAX: + if (msr_index - MSR_ARCH_PERFMON_FIXED_CTR0 >= + kvm_pmu_cap.num_counters_fixed) + return; + break; + case MSR_IA32_XFD: + case MSR_IA32_XFD_ERR: + if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) + return; + break; + default: + break; + } + + msrs_to_save[num_msrs_to_save++] = msr_index; +} + +static void kvm_init_msr_list(void) +{ unsigned i; BUILD_BUG_ON_MSG(KVM_PMC_MAX_FIXED != 3, - "Please update the fixed PMCs in msrs_to_saved_all[]"); + "Please update the fixed PMCs in msrs_to_save_pmu[]"); num_msrs_to_save = 0; num_emulated_msrs = 0; num_msr_based_features = 0; - for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) { - if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0) - continue; + for (i = 0; i < ARRAY_SIZE(msrs_to_save_base); i++) + kvm_probe_msr_to_save(msrs_to_save_base[i]); - /* - * Even MSRs that are valid in the host may not be exposed - * to the guests in some cases. - */ - switch (msrs_to_save_all[i]) { - case MSR_IA32_BNDCFGS: - if (!kvm_mpx_supported()) - continue; - break; - case MSR_TSC_AUX: - if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && - !kvm_cpu_cap_has(X86_FEATURE_RDPID)) - continue; - break; - case MSR_IA32_UMWAIT_CONTROL: - if (!kvm_cpu_cap_has(X86_FEATURE_WAITPKG)) - continue; - break; - case MSR_IA32_RTIT_CTL: - case MSR_IA32_RTIT_STATUS: - if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) - continue; - break; - case MSR_IA32_RTIT_CR3_MATCH: - if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || - !intel_pt_validate_hw_cap(PT_CAP_cr3_filtering)) - continue; - break; - case MSR_IA32_RTIT_OUTPUT_BASE: - case MSR_IA32_RTIT_OUTPUT_MASK: - if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || - (!intel_pt_validate_hw_cap(PT_CAP_topa_output) && - !intel_pt_validate_hw_cap(PT_CAP_single_range_output))) - continue; - break; - case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: - if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || - msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >= - intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) - continue; - break; - case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX: - if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >= - min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) - continue; - break; - case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX: - if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= - min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) - continue; - break; - case MSR_IA32_XFD: - case MSR_IA32_XFD_ERR: - if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) - continue; - break; - default: - break; - } - - msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i]; + if (enable_pmu) { + for (i = 0; i < ARRAY_SIZE(msrs_to_save_pmu); i++) + kvm_probe_msr_to_save(msrs_to_save_pmu[i]); } for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { @@ -7699,7 +7736,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, return X86EMUL_CONTINUE; emul_write: - printk_once(KERN_WARNING "kvm: emulating exchange as write\n"); + pr_warn_once("emulating exchange as write\n"); return emulator_write_emulated(ctxt, addr, new, bytes, exception); } @@ -8145,9 +8182,14 @@ static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked) static_call(kvm_x86_set_nmi_mask)(emul_to_vcpu(ctxt), masked); } -static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) +static bool emulator_is_smm(struct x86_emulate_ctxt *ctxt) +{ + return is_smm(emul_to_vcpu(ctxt)); +} + +static bool emulator_is_guest_mode(struct x86_emulate_ctxt *ctxt) { - return emul_to_vcpu(ctxt)->arch.hflags; + return is_guest_mode(emul_to_vcpu(ctxt)); } #ifndef CONFIG_KVM_SMM @@ -8216,7 +8258,8 @@ static const struct x86_emulate_ops emulate_ops = { .guest_has_fxsr = emulator_guest_has_fxsr, .guest_has_rdpid = emulator_guest_has_rdpid, .set_nmi_mask = emulator_set_nmi_mask, - .get_hflags = emulator_get_hflags, + .is_smm = emulator_is_smm, + .is_guest_mode = emulator_is_guest_mode, .leave_smm = emulator_leave_smm, .triple_fault = emulator_triple_fault, .set_xcr = emulator_set_xcr, @@ -8260,7 +8303,7 @@ static struct x86_emulate_ctxt *alloc_emulate_ctxt(struct kvm_vcpu *vcpu) ctxt = kmem_cache_zalloc(x86_emulator_cache, GFP_KERNEL_ACCOUNT); if (!ctxt) { - pr_err("kvm: failed to allocate vcpu's emulator\n"); + pr_err("failed to allocate vcpu's emulator\n"); return NULL; } @@ -8288,8 +8331,6 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) (cs_l && is_long_mode(vcpu)) ? X86EMUL_MODE_PROT64 : cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK); - ctxt->interruptibility = 0; ctxt->have_exception = false; ctxt->exception.vector = -1; @@ -9271,35 +9312,66 @@ static struct notifier_block pvclock_gtod_notifier = { }; #endif -int kvm_arch_init(void *opaque) +static inline void kvm_ops_update(struct kvm_x86_init_ops *ops) +{ + memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); + +#define __KVM_X86_OP(func) \ + static_call_update(kvm_x86_##func, kvm_x86_ops.func); +#define KVM_X86_OP(func) \ + WARN_ON(!kvm_x86_ops.func); __KVM_X86_OP(func) +#define KVM_X86_OP_OPTIONAL __KVM_X86_OP +#define KVM_X86_OP_OPTIONAL_RET0(func) \ + static_call_update(kvm_x86_##func, (void *)kvm_x86_ops.func ? : \ + (void *)__static_call_return0); +#include <asm/kvm-x86-ops.h> +#undef __KVM_X86_OP + + kvm_pmu_ops_update(ops->pmu_ops); +} + +static int kvm_x86_check_processor_compatibility(void) +{ + int cpu = smp_processor_id(); + struct cpuinfo_x86 *c = &cpu_data(cpu); + + /* + * Compatibility checks are done when loading KVM and when enabling + * hardware, e.g. during CPU hotplug, to ensure all online CPUs are + * compatible, i.e. KVM should never perform a compatibility check on + * an offline CPU. + */ + WARN_ON(!cpu_online(cpu)); + + if (__cr4_reserved_bits(cpu_has, c) != + __cr4_reserved_bits(cpu_has, &boot_cpu_data)) + return -EIO; + + return static_call(kvm_x86_check_processor_compatibility)(); +} + +static void kvm_x86_check_cpu_compat(void *ret) +{ + *(int *)ret = kvm_x86_check_processor_compatibility(); +} + +static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) { - struct kvm_x86_init_ops *ops = opaque; u64 host_pat; - int r; + int r, cpu; if (kvm_x86_ops.hardware_enable) { - pr_err("kvm: already loaded vendor module '%s'\n", kvm_x86_ops.name); + pr_err("already loaded vendor module '%s'\n", kvm_x86_ops.name); return -EEXIST; } - if (!ops->cpu_has_kvm_support()) { - pr_err_ratelimited("kvm: no hardware support for '%s'\n", - ops->runtime_ops->name); - return -EOPNOTSUPP; - } - if (ops->disabled_by_bios()) { - pr_err_ratelimited("kvm: support for '%s' disabled by bios\n", - ops->runtime_ops->name); - return -EOPNOTSUPP; - } - /* * KVM explicitly assumes that the guest has an FPU and * FXSAVE/FXRSTOR. For example, the KVM_GET_FPU explicitly casts the * vCPU's FPU state as a fxregs_state struct. */ if (!boot_cpu_has(X86_FEATURE_FPU) || !boot_cpu_has(X86_FEATURE_FXSR)) { - printk(KERN_ERR "kvm: inadequate fpu\n"); + pr_err("inadequate fpu\n"); return -EOPNOTSUPP; } @@ -9317,19 +9389,19 @@ int kvm_arch_init(void *opaque) */ if (rdmsrl_safe(MSR_IA32_CR_PAT, &host_pat) || (host_pat & GENMASK(2, 0)) != 6) { - pr_err("kvm: host PAT[0] is not WB\n"); + pr_err("host PAT[0] is not WB\n"); return -EIO; } x86_emulator_cache = kvm_alloc_emulator_cache(); if (!x86_emulator_cache) { - pr_err("kvm: failed to allocate cache for x86 emulator\n"); + pr_err("failed to allocate cache for x86 emulator\n"); return -ENOMEM; } user_return_msrs = alloc_percpu(struct kvm_user_return_msrs); if (!user_return_msrs) { - printk(KERN_ERR "kvm: failed to allocate percpu kvm_user_return_msrs\n"); + pr_err("failed to allocate percpu kvm_user_return_msrs\n"); r = -ENOMEM; goto out_free_x86_emulator_cache; } @@ -9339,13 +9411,37 @@ int kvm_arch_init(void *opaque) if (r) goto out_free_percpu; - kvm_timer_init(); - if (boot_cpu_has(X86_FEATURE_XSAVE)) { host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); kvm_caps.supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; } + rdmsrl_safe(MSR_EFER, &host_efer); + + if (boot_cpu_has(X86_FEATURE_XSAVES)) + rdmsrl(MSR_IA32_XSS, host_xss); + + kvm_init_pmu_capability(ops->pmu_ops); + + r = ops->hardware_setup(); + if (r != 0) + goto out_mmu_exit; + + kvm_ops_update(ops); + + for_each_online_cpu(cpu) { + smp_call_function_single(cpu, kvm_x86_check_cpu_compat, &r, 1); + if (r < 0) + goto out_unwind_ops; + } + + /* + * Point of no return! DO NOT add error paths below this point unless + * absolutely necessary, as most operations from this point forward + * require unwinding. + */ + kvm_timer_init(); + if (pi_inject_timer == -1) pi_inject_timer = housekeeping_enabled(HK_TYPE_TIMER); #ifdef CONFIG_X86_64 @@ -9355,8 +9451,35 @@ int kvm_arch_init(void *opaque) set_hv_tscchange_cb(kvm_hyperv_tsc_notifier); #endif + kvm_register_perf_callbacks(ops->handle_intel_pt_intr); + + if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) + kvm_caps.supported_xss = 0; + +#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) + cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); +#undef __kvm_cpu_cap_has + + if (kvm_caps.has_tsc_control) { + /* + * Make sure the user can only configure tsc_khz values that + * fit into a signed integer. + * A min value is not calculated because it will always + * be 1 on all machines. + */ + u64 max = min(0x7fffffffULL, + __scale_tsc(kvm_caps.max_tsc_scaling_ratio, tsc_khz)); + kvm_caps.max_guest_tsc_khz = max; + } + kvm_caps.default_tsc_scaling_ratio = 1ULL << kvm_caps.tsc_scaling_ratio_frac_bits; + kvm_init_msr_list(); return 0; +out_unwind_ops: + kvm_x86_ops.hardware_enable = NULL; + static_call(kvm_x86_hardware_unsetup)(); +out_mmu_exit: + kvm_mmu_vendor_module_exit(); out_free_percpu: free_percpu(user_return_msrs); out_free_x86_emulator_cache: @@ -9364,8 +9487,22 @@ out_free_x86_emulator_cache: return r; } -void kvm_arch_exit(void) +int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) { + int r; + + mutex_lock(&vendor_module_lock); + r = __kvm_x86_vendor_init(ops); + mutex_unlock(&vendor_module_lock); + + return r; +} +EXPORT_SYMBOL_GPL(kvm_x86_vendor_init); + +void kvm_x86_vendor_exit(void) +{ + kvm_unregister_perf_callbacks(); + #ifdef CONFIG_X86_64 if (hypervisor_is_type(X86_HYPER_MS_HYPERV)) clear_hv_tscchange_cb(); @@ -9382,7 +9519,7 @@ void kvm_arch_exit(void) irq_work_sync(&pvclock_irq_work); cancel_work_sync(&pvclock_gtod_work); #endif - kvm_x86_ops.hardware_enable = NULL; + static_call(kvm_x86_hardware_unsetup)(); kvm_mmu_vendor_module_exit(); free_percpu(user_return_msrs); kmem_cache_destroy(x86_emulator_cache); @@ -9390,7 +9527,11 @@ void kvm_arch_exit(void) static_key_deferred_flush(&kvm_xen_enabled); WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key)); #endif + mutex_lock(&vendor_module_lock); + kvm_x86_ops.hardware_enable = NULL; + mutex_unlock(&vendor_module_lock); } +EXPORT_SYMBOL_GPL(kvm_x86_vendor_exit); static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) { @@ -10043,7 +10184,7 @@ void kvm_make_scan_ioapic_request(struct kvm *kvm) kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); } -void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) +void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; bool activate; @@ -10078,7 +10219,30 @@ out: preempt_enable(); up_read(&vcpu->kvm->arch.apicv_update_lock); } -EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); +EXPORT_SYMBOL_GPL(__kvm_vcpu_update_apicv); + +static void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) +{ + if (!lapic_in_kernel(vcpu)) + return; + + /* + * Due to sharing page tables across vCPUs, the xAPIC memslot must be + * deleted if any vCPU has xAPIC virtualization and x2APIC enabled, but + * and hardware doesn't support x2APIC virtualization. E.g. some AMD + * CPUs support AVIC but not x2APIC. KVM still allows enabling AVIC in + * this case so that KVM can the AVIC doorbell to inject interrupts to + * running vCPUs, but KVM must not create SPTEs for the APIC base as + * the vCPU would incorrectly be able to access the vAPIC page via MMIO + * despite being in x2APIC mode. For simplicity, inhibiting the APIC + * access page is sticky. + */ + if (apic_x2apic_mode(vcpu->arch.apic) && + kvm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization) + kvm_inhibit_apic_access_page(vcpu); + + __kvm_vcpu_update_apicv(vcpu); +} void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason, bool set) @@ -10087,7 +10251,7 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, lockdep_assert_held_write(&kvm->arch.apicv_update_lock); - if (!static_call(kvm_x86_check_apicv_inhibit_reasons)(reason)) + if (!(kvm_x86_ops.required_apicv_inhibits & BIT(reason))) return; old = new = kvm->arch.apicv_inhibit_reasons; @@ -11531,7 +11695,7 @@ static int sync_regs(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { if (kvm_check_tsc_unstable() && kvm->created_vcpus) - pr_warn_once("kvm: SMP vm created on host with unstable TSC; " + pr_warn_once("SMP vm created on host with unstable TSC; " "guest TSC will not be reliable\n"); if (!kvm->arch.max_vcpu_ids) @@ -11608,7 +11772,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) goto free_wbinvd_dirty_mask; if (!fpu_alloc_guest_fpstate(&vcpu->arch.guest_fpu)) { - pr_err("kvm: failed to allocate vcpu's fpu\n"); + pr_err("failed to allocate vcpu's fpu\n"); goto free_emulate_ctxt; } @@ -11882,6 +12046,11 @@ int kvm_arch_hardware_enable(void) bool stable, backwards_tsc = false; kvm_user_return_msr_cpu_online(); + + ret = kvm_x86_check_processor_compatibility(); + if (ret) + return ret; + ret = static_call(kvm_x86_hardware_enable)(); if (ret != 0) return ret; @@ -11968,88 +12137,6 @@ void kvm_arch_hardware_disable(void) drop_user_return_notifiers(); } -static inline void kvm_ops_update(struct kvm_x86_init_ops *ops) -{ - memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); - -#define __KVM_X86_OP(func) \ - static_call_update(kvm_x86_##func, kvm_x86_ops.func); -#define KVM_X86_OP(func) \ - WARN_ON(!kvm_x86_ops.func); __KVM_X86_OP(func) -#define KVM_X86_OP_OPTIONAL __KVM_X86_OP -#define KVM_X86_OP_OPTIONAL_RET0(func) \ - static_call_update(kvm_x86_##func, (void *)kvm_x86_ops.func ? : \ - (void *)__static_call_return0); -#include <asm/kvm-x86-ops.h> -#undef __KVM_X86_OP - - kvm_pmu_ops_update(ops->pmu_ops); -} - -int kvm_arch_hardware_setup(void *opaque) -{ - struct kvm_x86_init_ops *ops = opaque; - int r; - - rdmsrl_safe(MSR_EFER, &host_efer); - - if (boot_cpu_has(X86_FEATURE_XSAVES)) - rdmsrl(MSR_IA32_XSS, host_xss); - - kvm_init_pmu_capability(); - - r = ops->hardware_setup(); - if (r != 0) - return r; - - kvm_ops_update(ops); - - kvm_register_perf_callbacks(ops->handle_intel_pt_intr); - - if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) - kvm_caps.supported_xss = 0; - -#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) - cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); -#undef __kvm_cpu_cap_has - - if (kvm_caps.has_tsc_control) { - /* - * Make sure the user can only configure tsc_khz values that - * fit into a signed integer. - * A min value is not calculated because it will always - * be 1 on all machines. - */ - u64 max = min(0x7fffffffULL, - __scale_tsc(kvm_caps.max_tsc_scaling_ratio, tsc_khz)); - kvm_caps.max_guest_tsc_khz = max; - } - kvm_caps.default_tsc_scaling_ratio = 1ULL << kvm_caps.tsc_scaling_ratio_frac_bits; - kvm_init_msr_list(); - return 0; -} - -void kvm_arch_hardware_unsetup(void) -{ - kvm_unregister_perf_callbacks(); - - static_call(kvm_x86_hardware_unsetup)(); -} - -int kvm_arch_check_processor_compat(void *opaque) -{ - struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); - struct kvm_x86_init_ops *ops = opaque; - - WARN_ON(!irqs_disabled()); - - if (__cr4_reserved_bits(cpu_has, c) != - __cr4_reserved_bits(cpu_has, &boot_cpu_data)) - return -EIO; - - return ops->check_processor_compatibility(); -} - bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) { return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id; @@ -12222,7 +12309,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, */ hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, 0); - if (IS_ERR((void *)hva)) + if (IS_ERR_VALUE(hva)) return (void __user *)hva; } else { if (!slot || !slot->npages) @@ -12437,16 +12524,14 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable) { - struct kvm_arch *ka = &kvm->arch; + int nr_slots; if (!kvm_x86_ops.cpu_dirty_log_size) return; - if ((enable && ++ka->cpu_dirty_logging_count == 1) || - (!enable && --ka->cpu_dirty_logging_count == 0)) + nr_slots = atomic_read(&kvm->nr_memslots_dirty_logging); + if ((enable && nr_slots == 1) || !nr_slots) kvm_make_all_cpus_request(kvm, KVM_REQ_UPDATE_CPU_DIRTY_LOGGING); - - WARN_ON_ONCE(ka->cpu_dirty_logging_count < 0); } static void kvm_mmu_slot_apply_flags(struct kvm *kvm, @@ -13456,6 +13541,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit); static int __init kvm_x86_init(void) { kvm_mmu_x86_module_init(); + mitigate_smt_rsb &= boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible(); return 0; } module_init(kvm_x86_init); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 9de72586f406..a8167b47b8c8 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -331,6 +331,18 @@ extern bool report_ignored_msrs; extern bool eager_page_split; +static inline void kvm_pr_unimpl_wrmsr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + if (report_ignored_msrs) + vcpu_unimpl(vcpu, "Unhandled WRMSR(0x%x) = 0x%llx\n", msr, data); +} + +static inline void kvm_pr_unimpl_rdmsr(struct kvm_vcpu *vcpu, u32 msr) +{ + if (report_ignored_msrs) + vcpu_unimpl(vcpu, "Unhandled RDMSR(0x%x)\n", msr); +} + static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) { return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, @@ -382,13 +394,13 @@ enum kvm_intr_type { KVM_HANDLING_NMI, }; -static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu, - enum kvm_intr_type intr) +static __always_inline void kvm_before_interrupt(struct kvm_vcpu *vcpu, + enum kvm_intr_type intr) { WRITE_ONCE(vcpu->arch.handling_intr_from_guest, (u8)intr); } -static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu) +static __always_inline void kvm_after_interrupt(struct kvm_vcpu *vcpu) { WRITE_ONCE(vcpu->arch.handling_intr_from_guest, 0); } diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 8fd41f5deae3..40edf4d1974c 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -5,6 +5,7 @@ * * KVM Xen emulation */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "x86.h" #include "xen.h" @@ -22,6 +23,9 @@ #include <xen/interface/event_channel.h> #include <xen/interface/sched.h> +#include <asm/xen/cpuid.h> + +#include "cpuid.h" #include "trace.h" static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm); @@ -2076,6 +2080,29 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) del_timer_sync(&vcpu->arch.xen.poll_timer); } +void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *entry; + u32 function; + + if (!vcpu->arch.xen.cpuid.base) + return; + + function = vcpu->arch.xen.cpuid.base | XEN_CPUID_LEAF(3); + if (function > vcpu->arch.xen.cpuid.limit) + return; + + entry = kvm_find_cpuid_entry_index(vcpu, function, 1); + if (entry) { + entry->ecx = vcpu->arch.hv_clock.tsc_to_system_mul; + entry->edx = vcpu->arch.hv_clock.tsc_shift; + } + + entry = kvm_find_cpuid_entry_index(vcpu, function, 2); + if (entry) + entry->eax = vcpu->arch.hw_tsc_khz; +} + void kvm_xen_init_vm(struct kvm *kvm) { mutex_init(&kvm->arch.xen.xen_lock); diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index ea33d80a0c51..f8f1fe22d090 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -9,6 +9,8 @@ #ifndef __ARCH_X86_KVM_XEN_H__ #define __ARCH_X86_KVM_XEN_H__ +#include <asm/xen/hypervisor.h> + #ifdef CONFIG_KVM_XEN #include <linux/jump_label_ratelimit.h> @@ -32,6 +34,7 @@ int kvm_xen_set_evtchn_fast(struct kvm_xen_evtchn *xe, int kvm_xen_setup_evtchn(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue); +void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu); static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { @@ -135,6 +138,10 @@ static inline bool kvm_xen_timer_enabled(struct kvm_vcpu *vcpu) { return false; } + +static inline void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu) +{ +} #endif int kvm_xen_hypercall(struct kvm_vcpu *vcpu); diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c index b6da09339308..80570eb3c89b 100644 --- a/arch/x86/lib/cmdline.c +++ b/arch/x86/lib/cmdline.c @@ -7,16 +7,18 @@ #include <linux/string.h> #include <linux/ctype.h> #include <asm/setup.h> +#include <asm/cmdline.h> static inline int myisspace(u8 c) { return c <= ' '; /* Close enough approximation */ } -/** +/* * Find a boolean option (like quiet,noapic,nosmp....) * * @cmdline: the cmdline string + * @max_cmdline_size: the maximum size of cmdline * @option: option string to look for * * Returns the position of that @option (starts counting with 1) diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index dd8cd8831251..a64017602010 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -8,7 +8,7 @@ #include <asm/alternative.h> #include <asm/export.h> -.pushsection .noinstr.text, "ax" +.section .noinstr.text, "ax" /* * We build a jump to memcpy_orig by default which gets NOPped out on @@ -43,7 +43,7 @@ SYM_TYPED_FUNC_START(__memcpy) SYM_FUNC_END(__memcpy) EXPORT_SYMBOL(__memcpy) -SYM_FUNC_ALIAS_WEAK(memcpy, __memcpy) +SYM_FUNC_ALIAS(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) /* @@ -184,4 +184,3 @@ SYM_FUNC_START_LOCAL(memcpy_orig) RET SYM_FUNC_END(memcpy_orig) -.popsection diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 724bbf83eb5b..02661861e5dd 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -13,6 +13,8 @@ #undef memmove +.section .noinstr.text, "ax" + /* * Implement memmove(). This can handle overlap between src and dst. * @@ -213,5 +215,5 @@ SYM_FUNC_START(__memmove) SYM_FUNC_END(__memmove) EXPORT_SYMBOL(__memmove) -SYM_FUNC_ALIAS_WEAK(memmove, __memmove) +SYM_FUNC_ALIAS(memmove, __memmove) EXPORT_SYMBOL(memmove) diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index fc9ffd3ff3b2..6143b1a6fa2c 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -6,6 +6,8 @@ #include <asm/alternative.h> #include <asm/export.h> +.section .noinstr.text, "ax" + /* * ISO C memset - set a memory block to a byte value. This function uses fast * string to get better performance than the original function. The code is @@ -43,7 +45,7 @@ SYM_FUNC_START(__memset) SYM_FUNC_END(__memset) EXPORT_SYMBOL(__memset) -SYM_FUNC_ALIAS_WEAK(memset, __memset) +SYM_FUNC_ALIAS(memset, __memset) EXPORT_SYMBOL(memset) /* diff --git a/arch/x86/lib/misc.c b/arch/x86/lib/misc.c index a018ec4fba53..92cd8ecc3a2c 100644 --- a/arch/x86/lib/misc.c +++ b/arch/x86/lib/misc.c @@ -1,4 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 +#include <asm/misc.h> + /* * Count the digits of @val including a possible sign. * diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index d12d1358f96d..5168ee0360b2 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -1047,6 +1047,7 @@ GrpTable: Grp6 3: LTR Ew 4: VERR Ew 5: VERW Ew +6: LKGS Ew (F2) EndTable GrpTable: Grp7 diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 7b0d4ab894c8..a498ae1fbe66 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -260,7 +260,7 @@ static noinline int vmalloc_fault(unsigned long address) } NOKPROBE_SYMBOL(vmalloc_fault); -static void __arch_sync_kernel_mappings(unsigned long start, unsigned long end) +void arch_sync_kernel_mappings(unsigned long start, unsigned long end) { unsigned long addr; @@ -284,27 +284,6 @@ static void __arch_sync_kernel_mappings(unsigned long start, unsigned long end) } } -void arch_sync_kernel_mappings(unsigned long start, unsigned long end) -{ - __arch_sync_kernel_mappings(start, end); -#ifdef CONFIG_KMSAN - /* - * KMSAN maintains two additional metadata page mappings for the - * [VMALLOC_START, VMALLOC_END) range. These mappings start at - * KMSAN_VMALLOC_SHADOW_START and KMSAN_VMALLOC_ORIGIN_START and - * have to be synced together with the vmalloc memory mapping. - */ - if (start >= VMALLOC_START && end < VMALLOC_END) { - __arch_sync_kernel_mappings( - start - VMALLOC_START + KMSAN_VMALLOC_SHADOW_START, - end - VMALLOC_START + KMSAN_VMALLOC_SHADOW_START); - __arch_sync_kernel_mappings( - start - VMALLOC_START + KMSAN_VMALLOC_ORIGIN_START, - end - VMALLOC_START + KMSAN_VMALLOC_ORIGIN_START); - } -#endif -} - static bool low_pfn(unsigned long pfn) { return pfn < max_low_pfn; diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index fb4b1b5e0dea..46a00aa858b6 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -159,10 +159,10 @@ static inline void set_page_memtype(struct page *pg, break; } + old_flags = READ_ONCE(pg->flags); do { - old_flags = pg->flags; new_flags = (old_flags & _PGMT_CLEAR_MASK) | memtype_flags; - } while (cmpxchg(&pg->flags, old_flags, new_flags) != old_flags); + } while (!try_cmpxchg(&pg->flags, &old_flags, new_flags)); } #else static inline enum page_cache_mode get_page_memtype(struct page *pg) @@ -387,8 +387,7 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, u8 mtrr_type, uniform; mtrr_type = mtrr_type_lookup(start, end, &uniform); - if (mtrr_type != MTRR_TYPE_WRBACK && - mtrr_type != MTRR_TYPE_INVALID) + if (mtrr_type != MTRR_TYPE_WRBACK) return _PAGE_CACHE_MODE_UC_MINUS; return _PAGE_CACHE_MODE_WB; @@ -1000,7 +999,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, ret = reserve_pfn_range(paddr, size, prot, 0); if (ret == 0 && vma) - vma->vm_flags |= VM_PAT; + vm_flags_set(vma, VM_PAT); return ret; } @@ -1046,7 +1045,7 @@ void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn) * can be for the entire vma (in which case pfn, size are zero). */ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, - unsigned long size) + unsigned long size, bool mm_wr_locked) { resource_size_t paddr; unsigned long prot; @@ -1065,8 +1064,12 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, size = vma->vm_end - vma->vm_start; } free_pfn_range(paddr, size); - if (vma) - vma->vm_flags &= ~VM_PAT; + if (vma) { + if (mm_wr_locked) + vm_flags_clear(vma, VM_PAT); + else + __vm_flags_mod(vma, 0, VM_PAT); + } } /* @@ -1076,7 +1079,7 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, */ void untrack_pfn_moved(struct vm_area_struct *vma) { - vma->vm_flags &= ~VM_PAT; + vm_flags_clear(vma, VM_PAT); } pgprot_t pgprot_writecombine(pgprot_t prot) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index c1e31e9a85d7..92d73ccede70 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -1205,7 +1205,7 @@ void __flush_tlb_all(void) */ VM_WARN_ON_ONCE(preemptible()); - if (boot_cpu_has(X86_FEATURE_PGE)) { + if (cpu_feature_enabled(X86_FEATURE_PGE)) { __flush_tlb_global(); } else { /* diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index b808be77635e..1056bbf55b17 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1003,6 +1003,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image u8 b2 = 0, b3 = 0; u8 *start_of_ldx; s64 jmp_offset; + s16 insn_off; u8 jmp_cond; u8 *func; int nops; @@ -1369,57 +1370,52 @@ st: if (is_imm8(insn->off)) case BPF_LDX | BPF_PROBE_MEM | BPF_W: case BPF_LDX | BPF_MEM | BPF_DW: case BPF_LDX | BPF_PROBE_MEM | BPF_DW: + insn_off = insn->off; + if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { - /* Though the verifier prevents negative insn->off in BPF_PROBE_MEM - * add abs(insn->off) to the limit to make sure that negative - * offset won't be an issue. - * insn->off is s16, so it won't affect valid pointers. + /* Conservatively check that src_reg + insn->off is a kernel address: + * src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE + * src_reg is used as scratch for src_reg += insn->off and restored + * after emit_ldx if necessary */ - u64 limit = TASK_SIZE_MAX + PAGE_SIZE + abs(insn->off); - u8 *end_of_jmp1, *end_of_jmp2; - /* Conservatively check that src_reg + insn->off is a kernel address: - * 1. src_reg + insn->off >= limit - * 2. src_reg + insn->off doesn't become small positive. - * Cannot do src_reg + insn->off >= limit in one branch, - * since it needs two spare registers, but JIT has only one. + u64 limit = TASK_SIZE_MAX + PAGE_SIZE; + u8 *end_of_jmp; + + /* At end of these emitted checks, insn->off will have been added + * to src_reg, so no need to do relative load with insn->off offset */ + insn_off = 0; /* movabsq r11, limit */ EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG)); EMIT((u32)limit, 4); EMIT(limit >> 32, 4); + + if (insn->off) { + /* add src_reg, insn->off */ + maybe_emit_1mod(&prog, src_reg, true); + EMIT2_off32(0x81, add_1reg(0xC0, src_reg), insn->off); + } + /* cmp src_reg, r11 */ maybe_emit_mod(&prog, src_reg, AUX_REG, true); EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG)); - /* if unsigned '<' goto end_of_jmp2 */ - EMIT2(X86_JB, 0); - end_of_jmp1 = prog; - - /* mov r11, src_reg */ - emit_mov_reg(&prog, true, AUX_REG, src_reg); - /* add r11, insn->off */ - maybe_emit_1mod(&prog, AUX_REG, true); - EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off); - /* jmp if not carry to start_of_ldx - * Otherwise ERR_PTR(-EINVAL) + 128 will be the user addr - * that has to be rejected. - */ - EMIT2(0x73 /* JNC */, 0); - end_of_jmp2 = prog; + + /* if unsigned '>=', goto load */ + EMIT2(X86_JAE, 0); + end_of_jmp = prog; /* xor dst_reg, dst_reg */ emit_mov_imm32(&prog, false, dst_reg, 0); /* jmp byte_after_ldx */ EMIT2(0xEB, 0); - /* populate jmp_offset for JB above to jump to xor dst_reg */ - end_of_jmp1[-1] = end_of_jmp2 - end_of_jmp1; - /* populate jmp_offset for JNC above to jump to start_of_ldx */ + /* populate jmp_offset for JAE above to jump to start_of_ldx */ start_of_ldx = prog; - end_of_jmp2[-1] = start_of_ldx - end_of_jmp2; + end_of_jmp[-1] = start_of_ldx - end_of_jmp; } - emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); + emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn_off); if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { struct exception_table_entry *ex; u8 *_insn = image + proglen + (start_of_ldx - temp); @@ -1428,6 +1424,18 @@ st: if (is_imm8(insn->off)) /* populate jmp_offset for JMP above */ start_of_ldx[-1] = prog - start_of_ldx; + if (insn->off && src_reg != dst_reg) { + /* sub src_reg, insn->off + * Restore src_reg after "add src_reg, insn->off" in prev + * if statement. But if src_reg == dst_reg, emit_ldx + * above already clobbered src_reg, so no need to restore. + * If add src_reg, insn->off was unnecessary, no need to + * restore either. + */ + maybe_emit_1mod(&prog, src_reg, true); + EMIT2_off32(0x81, add_1reg(0xE8, src_reg), insn->off); + } + if (!bpf_prog->aux->extable) break; @@ -1849,62 +1857,59 @@ emit_jmp: return proglen; } -static void save_regs(const struct btf_func_model *m, u8 **prog, int nr_args, +static void save_regs(const struct btf_func_model *m, u8 **prog, int nr_regs, int stack_size) { - int i, j, arg_size, nr_regs; + int i, j, arg_size; + bool next_same_struct = false; + /* Store function arguments to stack. * For a function that accepts two pointers the sequence will be: * mov QWORD PTR [rbp-0x10],rdi * mov QWORD PTR [rbp-0x8],rsi */ - for (i = 0, j = 0; i < min(nr_args, 6); i++) { - if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) { - nr_regs = (m->arg_size[i] + 7) / 8; + for (i = 0, j = 0; i < min(nr_regs, 6); i++) { + /* The arg_size is at most 16 bytes, enforced by the verifier. */ + arg_size = m->arg_size[j]; + if (arg_size > 8) { arg_size = 8; - } else { - nr_regs = 1; - arg_size = m->arg_size[i]; + next_same_struct = !next_same_struct; } - while (nr_regs) { - emit_stx(prog, bytes_to_bpf_size(arg_size), - BPF_REG_FP, - j == 5 ? X86_REG_R9 : BPF_REG_1 + j, - -(stack_size - j * 8)); - nr_regs--; - j++; - } + emit_stx(prog, bytes_to_bpf_size(arg_size), + BPF_REG_FP, + i == 5 ? X86_REG_R9 : BPF_REG_1 + i, + -(stack_size - i * 8)); + + j = next_same_struct ? j : j + 1; } } -static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args, +static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_regs, int stack_size) { - int i, j, arg_size, nr_regs; + int i, j, arg_size; + bool next_same_struct = false; /* Restore function arguments from stack. * For a function that accepts two pointers the sequence will be: * EMIT4(0x48, 0x8B, 0x7D, 0xF0); mov rdi,QWORD PTR [rbp-0x10] * EMIT4(0x48, 0x8B, 0x75, 0xF8); mov rsi,QWORD PTR [rbp-0x8] */ - for (i = 0, j = 0; i < min(nr_args, 6); i++) { - if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) { - nr_regs = (m->arg_size[i] + 7) / 8; + for (i = 0, j = 0; i < min(nr_regs, 6); i++) { + /* The arg_size is at most 16 bytes, enforced by the verifier. */ + arg_size = m->arg_size[j]; + if (arg_size > 8) { arg_size = 8; - } else { - nr_regs = 1; - arg_size = m->arg_size[i]; + next_same_struct = !next_same_struct; } - while (nr_regs) { - emit_ldx(prog, bytes_to_bpf_size(arg_size), - j == 5 ? X86_REG_R9 : BPF_REG_1 + j, - BPF_REG_FP, - -(stack_size - j * 8)); - nr_regs--; - j++; - } + emit_ldx(prog, bytes_to_bpf_size(arg_size), + i == 5 ? X86_REG_R9 : BPF_REG_1 + i, + BPF_REG_FP, + -(stack_size - i * 8)); + + j = next_same_struct ? j : j + 1; } } @@ -2130,8 +2135,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i struct bpf_tramp_links *tlinks, void *func_addr) { - int ret, i, nr_args = m->nr_args, extra_nregs = 0; - int regs_off, ip_off, args_off, stack_size = nr_args * 8, run_ctx_off; + int i, ret, nr_regs = m->nr_args, stack_size = 0; + int regs_off, nregs_off, ip_off, run_ctx_off; struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT]; struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN]; @@ -2140,17 +2145,14 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i u8 *prog; bool save_ret; - /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ - if (nr_args > 6) - return -ENOTSUPP; - - for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) { + /* extra registers for struct arguments */ + for (i = 0; i < m->nr_args; i++) if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) - extra_nregs += (m->arg_size[i] + 7) / 8 - 1; - } - if (nr_args + extra_nregs > 6) + nr_regs += (m->arg_size[i] + 7) / 8 - 1; + + /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ + if (nr_regs > 6) return -ENOTSUPP; - stack_size += extra_nregs * 8; /* Generated trampoline stack layout: * @@ -2164,7 +2166,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i * [ ... ] * RBP - regs_off [ reg_arg1 ] program's ctx pointer * - * RBP - args_off [ arg regs count ] always + * RBP - nregs_off [ regs count ] always * * RBP - ip_off [ traced function ] BPF_TRAMP_F_IP_ARG flag * @@ -2176,11 +2178,12 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (save_ret) stack_size += 8; + stack_size += nr_regs * 8; regs_off = stack_size; - /* args count */ + /* regs count */ stack_size += 8; - args_off = stack_size; + nregs_off = stack_size; if (flags & BPF_TRAMP_F_IP_ARG) stack_size += 8; /* room for IP address argument */ @@ -2213,11 +2216,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i EMIT1(0x53); /* push rbx */ /* Store number of argument registers of the traced function: - * mov rax, nr_args + extra_nregs - * mov QWORD PTR [rbp - args_off], rax + * mov rax, nr_regs + * mov QWORD PTR [rbp - nregs_off], rax */ - emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_args + extra_nregs); - emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -args_off); + emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_regs); + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -nregs_off); if (flags & BPF_TRAMP_F_IP_ARG) { /* Store IP address of the traced function: @@ -2228,7 +2231,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -ip_off); } - save_regs(m, &prog, nr_args, regs_off); + save_regs(m, &prog, nr_regs, regs_off); if (flags & BPF_TRAMP_F_CALL_ORIG) { /* arg1: mov rdi, im */ @@ -2258,7 +2261,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (flags & BPF_TRAMP_F_CALL_ORIG) { - restore_regs(m, &prog, nr_args, regs_off); + restore_regs(m, &prog, nr_regs, regs_off); if (flags & BPF_TRAMP_F_ORIG_STACK) { emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8); @@ -2299,7 +2302,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (flags & BPF_TRAMP_F_RESTORE_REGS) - restore_regs(m, &prog, nr_args, regs_off); + restore_regs(m, &prog, nr_regs, regs_off); /* This needs to be done regardless. If there were fmod_ret programs, * the return value is only updated on the stack and still needs to be diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index b94f727251b6..8babce71915f 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -392,6 +392,7 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev) msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_ASSOCIATED) { for (i = 0; i < msidesc->nvec_used; i++) xen_destroy_irq(msidesc->irq + i); + msidesc->irq = 0; } } @@ -433,6 +434,7 @@ static struct msi_domain_ops xen_pci_msi_domain_ops = { }; static struct msi_domain_info xen_pci_msi_domain_info = { + .flags = MSI_FLAG_PCI_MSIX | MSI_FLAG_FREE_MSI_DESCS | MSI_FLAG_DEV_SYSFS, .ops = &xen_pci_msi_domain_ops, }; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 55d9caf66401..f3f2d87cce1b 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -380,7 +380,7 @@ static int __init efi_systab_init(unsigned long phys) return -ENOMEM; } - ret = efi_systab_check_header(hdr, 1); + ret = efi_systab_check_header(hdr); if (ret) { early_memunmap(p, size); return ret; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index b36596bf0fc3..232acf418cfb 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -389,10 +389,15 @@ static int __init efi_update_mappings(efi_memory_desc_t *md, unsigned long pf) return err1 || err2; } -static int __init efi_update_mem_attr(struct mm_struct *mm, efi_memory_desc_t *md) +bool efi_disable_ibt_for_runtime __ro_after_init = true; + +static int __init efi_update_mem_attr(struct mm_struct *mm, efi_memory_desc_t *md, + bool has_ibt) { unsigned long pf = 0; + efi_disable_ibt_for_runtime |= !has_ibt; + if (md->attribute & EFI_MEMORY_XP) pf |= _PAGE_NX; @@ -414,6 +419,7 @@ void __init efi_runtime_update_mappings(void) * exists, since it is intended to supersede EFI_PROPERTIES_TABLE. */ if (efi_enabled(EFI_MEM_ATTR)) { + efi_disable_ibt_for_runtime = false; efi_memattr_apply_permissions(NULL, efi_update_mem_attr); return; } diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index 1a536a187d74..ee21d6a36a80 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -166,10 +166,9 @@ static struct irq_domain *uv_get_irq_domain(void) if (!fn) goto out; - uv_domain = irq_domain_create_tree(fn, &uv_domain_ops, NULL); - if (uv_domain) - uv_domain->parent = x86_vector_domain; - else + uv_domain = irq_domain_create_hierarchy(x86_vector_domain, 0, 0, fn, + &uv_domain_ops, NULL); + if (!uv_domain) irq_domain_free_fwnode(fn); out: mutex_unlock(&uv_lock); diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c index cafd01f730da..29b2203bc82c 100644 --- a/arch/x86/um/mem_32.c +++ b/arch/x86/um/mem_32.c @@ -16,7 +16,7 @@ static int __init gate_vma_init(void) vma_init(&gate_vma, NULL); gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; - gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; + vm_flags_init(&gate_vma, VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC); gate_vma.vm_page_prot = PAGE_READONLY; return 0; diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 5b1379662877..bb59cc6ddb2d 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -276,6 +276,7 @@ static void __init xen_init_capabilities(void) setup_clear_cpu_cap(X86_FEATURE_ACC); setup_clear_cpu_cap(X86_FEATURE_X2APIC); setup_clear_cpu_cap(X86_FEATURE_SME); + setup_clear_cpu_cap(X86_FEATURE_LKGS); /* * Xen PV would need some work to support PCID: CR3 handling as well @@ -1068,7 +1069,7 @@ static const typeof(pv_ops) xen_cpu_ops __initconst = { .write_cr4 = xen_write_cr4, - .wbinvd = native_wbinvd, + .wbinvd = pv_native_wbinvd, .read_msr = xen_read_msr, .write_msr = xen_write_msr, diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 06c3c2fb4b06..6092fea7d651 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -24,7 +24,7 @@ noinstr void xen_force_evtchn_callback(void) (void)HYPERVISOR_xen_version(0, NULL); } -static void xen_safe_halt(void) +static noinstr void xen_safe_halt(void) { /* Blocking includes an implicit local_irq_enable(). */ if (HYPERVISOR_sched_op(SCHEDOP_block, NULL) != 0) diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 8db26f10fb1d..c2be3efb2ba0 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -934,12 +934,8 @@ void xen_enable_syscall(void) static void __init xen_pvmmu_arch_setup(void) { - HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments); HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_writable_pagetables); - HYPERVISOR_vm_assist(VMASST_CMD_enable, - VMASST_TYPE_pae_extended_cr3); - if (register_callback(CALLBACKTYPE_event, xen_asm_exc_xen_hypervisor_callback) || register_callback(CALLBACKTYPE_failsafe, xen_failsafe_callback)) diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h index bd02f9d50107..22fb982ff971 100644 --- a/arch/x86/xen/smp.h +++ b/arch/x86/xen/smp.h @@ -21,6 +21,8 @@ void xen_smp_send_reschedule(int cpu); void xen_smp_send_call_function_ipi(const struct cpumask *mask); void xen_smp_send_call_function_single_ipi(int cpu); +void __noreturn xen_cpu_bringup_again(unsigned long stack); + struct xen_common_irq { int irq; char *name; diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 6175f2c5c822..a9cf8c8fa074 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -381,21 +381,12 @@ static void xen_pv_cpu_die(unsigned int cpu) } } -static void xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */ +static void __noreturn xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */ { play_dead_common(); HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(smp_processor_id()), NULL); - cpu_bringup(); - /* - * commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down) - * clears certain data that the cpu_idle loop (which called us - * and that we return from) expects. The only way to get that - * data back is to call: - */ - tick_nohz_idle_enter(); - tick_nohz_idle_stop_tick_protected(); - - cpuhp_online_idle(CPUHP_AP_ONLINE_IDLE); + xen_cpu_bringup_again((unsigned long)task_pt_regs(current)); + BUG(); } #else /* !CONFIG_HOTPLUG_CPU */ @@ -409,7 +400,7 @@ static void xen_pv_cpu_die(unsigned int cpu) BUG(); } -static void xen_pv_play_dead(void) +static void __noreturn xen_pv_play_dead(void) { BUG(); } diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 9ef0a5cca96e..1d597364b49d 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -60,9 +60,17 @@ static u64 xen_clocksource_get_cycles(struct clocksource *cs) return xen_clocksource_read(); } -static u64 xen_sched_clock(void) +static noinstr u64 xen_sched_clock(void) { - return xen_clocksource_read() - xen_sched_clock_offset; + struct pvclock_vcpu_time_info *src; + u64 ret; + + preempt_disable_notrace(); + src = &__this_cpu_read(xen_vcpu)->time; + ret = pvclock_clocksource_read_nowd(src); + ret -= xen_sched_clock_offset; + preempt_enable_notrace(); + return ret; } static void xen_read_wallclock(struct timespec64 *ts) @@ -474,15 +482,51 @@ static void xen_setup_vsyscall_time_info(void) xen_clocksource.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK; } +/* + * Check if it is possible to safely use the tsc as a clocksource. This is + * only true if the hypervisor notifies the guest that its tsc is invariant, + * the tsc is stable, and the tsc instruction will never be emulated. + */ +static int __init xen_tsc_safe_clocksource(void) +{ + u32 eax, ebx, ecx, edx; + + if (!(boot_cpu_has(X86_FEATURE_CONSTANT_TSC))) + return 0; + + if (!(boot_cpu_has(X86_FEATURE_NONSTOP_TSC))) + return 0; + + if (check_tsc_unstable()) + return 0; + + /* Leaf 4, sub-leaf 0 (0x40000x03) */ + cpuid_count(xen_cpuid_base() + 3, 0, &eax, &ebx, &ecx, &edx); + + /* tsc_mode = no_emulate (2) */ + if (ebx != 2) + return 0; + + return 1; +} + static void __init xen_time_init(void) { struct pvclock_vcpu_time_info *pvti; int cpu = smp_processor_id(); struct timespec64 tp; - /* As Dom0 is never moved, no penalty on using TSC there */ + /* + * As Dom0 is never moved, no penalty on using TSC there. + * + * If it is possible for the guest to determine that the tsc is a safe + * clocksource, then set xen_clocksource rating below that of the tsc + * so that the system prefers tsc instead. + */ if (xen_initial_domain()) xen_clocksource.rating = 275; + else if (xen_tsc_safe_clocksource()) + xen_clocksource.rating = 299; clocksource_register_hz(&xen_clocksource, NSEC_PER_SEC); diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index ffaa62167f6e..e36ea4268bd2 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -76,6 +76,13 @@ SYM_CODE_START(asm_cpu_bringup_and_idle) call cpu_bringup_and_idle SYM_CODE_END(asm_cpu_bringup_and_idle) + +SYM_CODE_START(xen_cpu_bringup_again) + UNWIND_HINT_FUNC + mov %rdi, %rsp + UNWIND_HINT_REGS + call cpu_bringup_and_idle +SYM_CODE_END(xen_cpu_bringup_again) .popsection #endif #endif |