diff options
Diffstat (limited to 'arch/x86')
170 files changed, 2977 insertions, 1374 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/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/bioscall.S b/arch/x86/boot/bioscall.S index 5521ea12f44e..aa9b96457584 100644 --- a/arch/x86/boot/bioscall.S +++ b/arch/x86/boot/bioscall.S @@ -32,7 +32,7 @@ intcall: movw %dx, %si movw %sp, %di movw $11, %cx - rep; movsd + rep; movsl /* Pop full state from the stack */ popal @@ -67,7 +67,7 @@ intcall: jz 4f movw %sp, %si movw $11, %cx - rep; movsd + rep; movsl 4: addw $44, %sp /* Restore state and return */ 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..ad0d51f03cb4 100644 --- a/arch/x86/coco/tdx/tdcall.S +++ b/arch/x86/coco/tdx/tdcall.S @@ -31,6 +31,8 @@ TDX_R12 | TDX_R13 | \ TDX_R14 | TDX_R15 ) +.section .noinstr.text, "ax" + /* * __tdx_module_call() - Used by TDX guests to request services from * the TDX module (does not include VMM services) using TDCALL instruction. @@ -139,19 +141,6 @@ SYM_FUNC_START(__tdx_hypercall) 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 /* diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index cfd4c95b9f04..3bd111d5e6a0 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -64,8 +64,9 @@ 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 +76,7 @@ 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; } @@ -220,7 +221,7 @@ 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 +241,14 @@ 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 +256,12 @@ 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"); } @@ -386,8 +375,8 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) { unsigned long *reg, val, vaddr; char buffer[MAX_INSN_SIZE]; + enum insn_mmio_type mmio; struct insn insn = {}; - enum mmio_type mmio; int size, extend_size; u8 extend_val = 0; @@ -402,10 +391,10 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) return -EINVAL; mmio = insn_decode_mmio(&insn, &size); - if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED)) + if (WARN_ON_ONCE(mmio == INSN_MMIO_DECODE_FAILED)) return -EINVAL; - if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) { + if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) { reg = insn_get_modrm_reg_ptr(&insn, regs); if (!reg) return -EINVAL; @@ -426,23 +415,23 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) /* Handle writes first */ switch (mmio) { - case MMIO_WRITE: + case INSN_MMIO_WRITE: memcpy(&val, reg, size); if (!mmio_write(size, ve->gpa, val)) return -EIO; return insn.length; - case MMIO_WRITE_IMM: + case INSN_MMIO_WRITE_IMM: val = insn.immediate.value; if (!mmio_write(size, ve->gpa, val)) return -EIO; return insn.length; - case MMIO_READ: - case MMIO_READ_ZERO_EXTEND: - case MMIO_READ_SIGN_EXTEND: + case INSN_MMIO_READ: + case INSN_MMIO_READ_ZERO_EXTEND: + case INSN_MMIO_READ_SIGN_EXTEND: /* Reads are handled below */ break; - case MMIO_MOVS: - case MMIO_DECODE_FAILED: + case INSN_MMIO_MOVS: + case INSN_MMIO_DECODE_FAILED: /* * MMIO was accessed with an instruction that could not be * decoded or handled properly. It was likely not using io.h @@ -459,15 +448,15 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) return -EIO; switch (mmio) { - case MMIO_READ: + case INSN_MMIO_READ: /* Zero-extend for 32-bit operation */ extend_size = size == 4 ? sizeof(*reg) : 0; break; - case MMIO_READ_ZERO_EXTEND: + case INSN_MMIO_READ_ZERO_EXTEND: /* Zero extend based on operand size */ extend_size = insn.opnd_bytes; break; - case MMIO_READ_SIGN_EXTEND: + case INSN_MMIO_READ_SIGN_EXTEND: /* Sign extend based on operand size */ extend_size = insn.opnd_bytes; if (size == 1 && val & BIT(7)) 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..2738eb28cb2e 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; @@ -418,18 +421,4 @@ 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/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 d6f3703e4119..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); @@ -1387,7 +1385,7 @@ static int __init amd_core_pmu_init(void) * numbered counter following it. */ for (i = 0; i < x86_pmu.num_counters - 1; i += 2) - even_ctr_mask |= 1 << i; + even_ctr_mask |= BIT_ULL(i); pair_constraint = (struct event_constraint) __EVENT_CONSTRAINT(0, even_ctr_mask, 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..9fce2d1247a7 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)); @@ -6381,6 +6528,8 @@ __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 +6549,7 @@ __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 +6636,22 @@ __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 +6766,9 @@ __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 a2834bc93149..551741e79e03 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -41,6 +41,7 @@ * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL + * MTL * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 @@ -51,50 +52,50 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL,RPL,SPR + * TGL,TNT,RKL,ADL,RPL,SPR,MTL * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, - * ICL,TGL,RKL,ADL,RPL + * ICL,TGL,RKL,ADL,RPL,MTL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL, - * RPL,SPR + * RPL,SPR,MTL * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL, - * ADL,RPL + * ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL,RPL,SPR + * TGL,TNT,RKL,ADL,RPL,SPR,MTL * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, - * KBL,CML,ICL,TGL,RKL,ADL,RPL + * KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL,RPL + * ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL,RPL + * ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, - * TNT,RKL,ADL,RPL + * TNT,RKL,ADL,RPL,MTL * Scope: Package (physical package) * */ @@ -676,6 +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), @@ -686,6 +688,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &adl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 88e58b6ee73c..b0354dc869d2 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); } } 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 6f1ccc57a692..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 = { @@ -1832,7 +1862,10 @@ 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), {}, }; @@ -1852,7 +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; @@ -1860,7 +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/msr.c b/arch/x86/events/msr.c index ecced3a52668..c65d8906cbcf 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -69,6 +69,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_BROADWELL_G: case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_SAPPHIRERAPIDS_X: + case INTEL_FAM6_EMERALDRAPIDS_X: case INTEL_FAM6_ATOM_SILVERMONT: case INTEL_FAM6_ATOM_SILVERMONT_D: @@ -107,6 +108,8 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_RAPTORLAKE: case INTEL_FAM6_RAPTORLAKE_P: case INTEL_FAM6_RAPTORLAKE_S: + case INTEL_FAM6_METEORLAKE: + case INTEL_FAM6_METEORLAKE_L: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; 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/rapl.c b/arch/x86/events/rapl.c index a829492bca4c..52e6e7ed4f78 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -800,13 +800,18 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr), + X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &model_spr), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &model_skl), {}, }; MODULE_DEVICE_TABLE(x86cpu, rapl_model_match); 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/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..389ea336258f 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 +307,15 @@ #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_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 +430,13 @@ #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 +477,6 @@ #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/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/insn-eval.h b/arch/x86/include/asm/insn-eval.h index f07faa61c7f3..54368a43abf6 100644 --- a/arch/x86/include/asm/insn-eval.h +++ b/arch/x86/include/asm/insn-eval.h @@ -32,16 +32,16 @@ int insn_fetch_from_user_inatomic(struct pt_regs *regs, bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE], int buf_size); -enum mmio_type { - MMIO_DECODE_FAILED, - MMIO_WRITE, - MMIO_WRITE_IMM, - MMIO_READ, - MMIO_READ_ZERO_EXTEND, - MMIO_READ_SIGN_EXTEND, - MMIO_MOVS, +enum insn_mmio_type { + INSN_MMIO_DECODE_FAILED, + INSN_MMIO_WRITE, + INSN_MMIO_WRITE_IMM, + INSN_MMIO_READ, + INSN_MMIO_READ_ZERO_EXTEND, + INSN_MMIO_READ_SIGN_EXTEND, + INSN_MMIO_MOVS, }; -enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes); +enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes); #endif /* _ASM_X86_INSN_EVAL_H */ 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_host.h b/arch/x86/include/asm/kvm_host.h index f35f1ff4427b..6aaae18f1854 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1111,6 +1111,7 @@ struct msr_bitmap_range { /* Xen emulation context */ struct kvm_xen { + struct mutex xen_lock; u32 xen_version; bool long_mode; bool runstate_update_flag; 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/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/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/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/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..559176887791 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 " 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/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/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/callthunks.c b/arch/x86/kernel/callthunks.c index 7d2c75ec9a8c..ffea98f9064b 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -119,7 +119,7 @@ static bool is_coretext(const struct core_text *ct, void *addr) return within_module_coretext(addr); } -static __init_or_module bool skip_addr(void *dest) +static bool skip_addr(void *dest) { if (dest == error_entry) return true; @@ -181,7 +181,7 @@ static const u8 nops[] = { 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, }; -static __init_or_module void *patch_dest(void *dest, bool direct) +static void *patch_dest(void *dest, bool direct) { unsigned int tsize = SKL_TMPL_SIZE; u8 *pad = dest - tsize; 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 d970ddb0cc65..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 @@ -1981,6 +1994,8 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) if (ctrl == PR_SPEC_FORCE_DISABLE) task_set_spec_ib_force_disable(task); task_update_spec_tif(task); + if (task == current) + indirect_branch_prediction_barrier(); break; default: return -ERANGE; 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..a394bbba7a4b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -567,7 +567,7 @@ 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 @@ -1093,6 +1093,9 @@ 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 +1229,8 @@ 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 +1259,8 @@ 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 +1292,8 @@ 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 +1343,16 @@ 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 +1414,8 @@ 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 +1693,7 @@ 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 +1962,13 @@ 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 +2134,6 @@ 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 +2155,7 @@ 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 +2175,6 @@ 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 +2304,45 @@ 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/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 efe0c30d3a12..7fe51488e136 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -146,6 +146,30 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid) return entry; } +static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val) +{ + u64 msr_val; + + /* + * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured + * with a valid event code for supported resource type and the bits + * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID, + * IA32_QM_CTR.data (bits 61:0) reports the monitored data. + * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62) + * are error bits. + */ + wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); + rdmsrl(MSR_IA32_QM_CTR, msr_val); + + if (msr_val & RMID_VAL_ERROR) + return -EIO; + if (msr_val & RMID_VAL_UNAVAIL) + return -EINVAL; + + *val = msr_val; + return 0; +} + static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom, u32 rmid, enum resctrl_event_id eventid) @@ -172,8 +196,29 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, struct arch_mbm_state *am; am = get_arch_mbm_state(hw_dom, rmid, eventid); - if (am) + if (am) { memset(am, 0, sizeof(*am)); + + /* Record any initial, non-zero count value. */ + __rmid_read(rmid, eventid, &am->prev_msr); + } +} + +/* + * 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) @@ -191,25 +236,14 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); struct arch_mbm_state *am; u64 msr_val, chunks; + int ret; if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask)) return -EINVAL; - /* - * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured - * with a valid event code for supported resource type and the bits - * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID, - * IA32_QM_CTR.data (bits 61:0) reports the monitored data. - * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62) - * are error bits. - */ - wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); - rdmsrl(MSR_IA32_QM_CTR, msr_val); - - if (msr_val & RMID_VAL_ERROR) - return -EIO; - if (msr_val & RMID_VAL_UNAVAIL) - return -EINVAL; + ret = __rmid_read(rmid, eventid, &msr_val); + if (ret) + return ret; am = get_arch_mbm_state(hw_dom, rmid, eventid); if (am) { @@ -746,7 +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); @@ -783,6 +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 e5a48f05e787..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, @@ -580,8 +575,10 @@ static int __rdtgroup_move_task(struct task_struct *tsk, /* * Ensure the task's closid and rmid are written before determining if * the task is current that will decide if it will be interrupted. + * This pairs with the full barrier between the rq->curr update and + * resctrl_sched_in() during context switch. */ - barrier(); + smp_mb(); /* * By now, the task's closid and rmid are set. If the task is current @@ -1001,8 +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; } @@ -1213,7 +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) { @@ -1402,7 +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); @@ -1419,6 +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[] = { { @@ -1518,6 +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, @@ -1623,6 +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. @@ -1864,13 +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); @@ -2347,7 +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; @@ -2368,13 +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); @@ -2402,6 +2660,14 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, WRITE_ONCE(t->rmid, to->mon.rmid); /* + * Order the closid/rmid stores above before the loads + * in task_curr(). This pairs with the full barrier + * between the rq->curr update and resctrl_sched_in() + * during context switch. + */ + smp_mb(); + + /* * If the task is on a CPU, set the CPU in the mask. * The detection is inaccurate as tasks might move or * schedule before the smp function call takes place. @@ -2845,7 +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/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 9730c88530fc..305514431f26 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -401,10 +401,8 @@ int crash_load_segments(struct kimage *image) kbuf.buf_align = ELF_CORE_HEADER_ALIGN; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); - if (ret) { - vfree((void *)image->elf_headers); + if (ret) return ret; - } image->elf_load_addr = kbuf.mem; pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", image->elf_load_addr, kbuf.bufsz, kbuf.memsz); 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 66299682b6b7..f7f6042eb7e6 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -37,6 +37,7 @@ #include <linux/extable.h> #include <linux/kdebug.h> #include <linux/kallsyms.h> +#include <linux/kgdb.h> #include <linux/ftrace.h> #include <linux/kasan.h> #include <linux/moduleloader.h> @@ -281,12 +282,15 @@ static int can_probe(unsigned long paddr) if (ret < 0) return 0; +#ifdef CONFIG_KGDB /* - * Another debugging subsystem might insert this breakpoint. - * In that case, we can't recover it. + * If there is a dynamically installed kgdb sw breakpoint, + * this function should not be probed. */ - if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE && + kgdb_has_hit_break(addr)) return 0; +#endif addr += insn.length; } @@ -460,50 +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* */ @@ -531,7 +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); @@ -621,7 +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]; @@ -655,17 +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)) @@ -986,20 +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 e6b8c5362b94..e57e07b0edb6 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -15,6 +15,7 @@ #include <linux/extable.h> #include <linux/kdebug.h> #include <linux/kallsyms.h> +#include <linux/kgdb.h> #include <linux/ftrace.h> #include <linux/objtool.h> #include <linux/pgtable.h> @@ -279,19 +280,6 @@ static int insn_is_indirect_jump(struct insn *insn) return ret; } -static bool is_padding_int3(unsigned long addr, unsigned long eaddr) -{ - unsigned char ops; - - for (; addr < eaddr; addr++) { - if (get_kernel_nofault(ops, (void *)addr) < 0 || - ops != INT3_INSN_OPCODE) - return false; - } - - return true; -} - /* Decode whole function to ensure any instructions don't jump into target */ static int can_optimize(unsigned long paddr) { @@ -334,15 +322,15 @@ static int can_optimize(unsigned long paddr) ret = insn_decode_kernel(&insn, (void *)recovered_insn); if (ret < 0) return 0; - +#ifdef CONFIG_KGDB /* - * In the case of detecting unknown breakpoint, this could be - * a padding INT3 between functions. Let's check that all the - * rest of the bytes are also INT3. + * If there is a dynamically installed kgdb sw breakpoint, + * this function should not be probed. */ - if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) - return is_padding_int3(addr, paddr - offset + size) ? 1 : 0; - + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE && + kgdb_has_hit_break(addr)) + return 0; +#endif /* Recover address */ insn.kaddr = (void *)addr; insn.next_byte = (void *)(addr + insn.length); 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/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/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/sev.c b/arch/x86/kernel/sev.c index a428c62330d3..679026a640ef 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -1536,32 +1536,32 @@ static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt, static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct insn *insn = &ctxt->insn; + enum insn_mmio_type mmio; unsigned int bytes = 0; - enum mmio_type mmio; enum es_result ret; u8 sign_byte; long *reg_data; mmio = insn_decode_mmio(insn, &bytes); - if (mmio == MMIO_DECODE_FAILED) + if (mmio == INSN_MMIO_DECODE_FAILED) return ES_DECODE_FAILED; - if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) { + if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) { reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs); if (!reg_data) return ES_DECODE_FAILED; } switch (mmio) { - case MMIO_WRITE: + case INSN_MMIO_WRITE: memcpy(ghcb->shared_buffer, reg_data, bytes); ret = vc_do_mmio(ghcb, ctxt, bytes, false); break; - case MMIO_WRITE_IMM: + case INSN_MMIO_WRITE_IMM: memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes); ret = vc_do_mmio(ghcb, ctxt, bytes, false); break; - case MMIO_READ: + case INSN_MMIO_READ: ret = vc_do_mmio(ghcb, ctxt, bytes, true); if (ret) break; @@ -1572,7 +1572,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) memcpy(reg_data, ghcb->shared_buffer, bytes); break; - case MMIO_READ_ZERO_EXTEND: + case INSN_MMIO_READ_ZERO_EXTEND: ret = vc_do_mmio(ghcb, ctxt, bytes, true); if (ret) break; @@ -1581,7 +1581,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) memset(reg_data, 0, insn->opnd_bytes); memcpy(reg_data, ghcb->shared_buffer, bytes); break; - case MMIO_READ_SIGN_EXTEND: + case INSN_MMIO_READ_SIGN_EXTEND: ret = vc_do_mmio(ghcb, ctxt, bytes, true); if (ret) break; @@ -1600,7 +1600,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) memset(reg_data, sign_byte, insn->opnd_bytes); memcpy(reg_data, ghcb->shared_buffer, bytes); break; - case MMIO_MOVS: + case INSN_MMIO_MOVS: ret = vc_handle_mmio_movs(ctxt, bytes); break; default: 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/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/cpuid.c b/arch/x86/kvm/cpuid.c index b14653b61470..7f1b585f9a67 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -741,6 +741,27 @@ 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) | @@ -770,16 +791,22 @@ struct kvm_cpuid_array { int nent; }; +static struct kvm_cpuid_entry2 *get_next_cpuid(struct kvm_cpuid_array *array) +{ + if (array->nent >= array->maxnent) + return NULL; + + return &array->entries[array->nent++]; +} + static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, u32 function, u32 index) { - struct kvm_cpuid_entry2 *entry; + struct kvm_cpuid_entry2 *entry = get_next_cpuid(array); - if (array->nent >= array->maxnent) + if (!entry) return NULL; - entry = &array->entries[array->nent++]; - memset(entry, 0, sizeof(*entry)); entry->function = function; entry->index = index; @@ -956,22 +983,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->edx = edx.full; break; } - /* - * Per Intel's SDM, the 0x1f is a superset of 0xb, - * thus they can be handled by common code. - */ case 0x1f: case 0xb: /* - * Populate entries until the level type (ECX[15:8]) of the - * previous entry is zero. Note, CPUID EAX.{0x1f,0xb}.0 is - * the starting entry, filled by the primary do_host_cpuid(). + * No topology; a valid topology is indicated by the presence + * of subleaf 1. */ - for (i = 1; entry->ecx & 0xff00; ++i) { - entry = do_host_cpuid(array, function, i); - if (!entry) - goto out; - } + entry->eax = entry->ebx = entry->ecx = 0; break; case 0xd: { u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm(); @@ -1202,6 +1220,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ebx = entry->ecx = entry->edx = 0; break; case 0x8000001e: + /* Do not return host topology information. */ + entry->eax = entry->ebx = entry->ecx = 0; + entry->edx = 0; /* reserved */ break; case 0x8000001F: if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) { @@ -1222,25 +1243,7 @@ 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: diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 2c7f2a26421e..e8296942a868 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1769,6 +1769,7 @@ static bool hv_is_vp_in_sparse_set(u32 vp_id, u64 valid_bank_mask, u64 sparse_ba } struct kvm_hv_hcall { + /* Hypercall input data */ u64 param; u64 ingpa; u64 outgpa; @@ -1779,12 +1780,21 @@ struct kvm_hv_hcall { bool fast; bool rep; sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS]; + + /* + * Current read offset when KVM reads hypercall input data gradually, + * either offset in bytes from 'ingpa' for regular hypercalls or the + * number of already consumed 'XMM halves' for 'fast' hypercalls. + */ + union { + gpa_t data_offset; + int consumed_xmm_halves; + }; }; static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, - u16 orig_cnt, u16 cnt_cap, u64 *data, - int consumed_xmm_halves, gpa_t offset) + u16 orig_cnt, u16 cnt_cap, u64 *data) { /* * Preserve the original count when ignoring entries via a "cap", KVM @@ -1799,11 +1809,11 @@ static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, * Each XMM holds two sparse banks, but do not count halves that * have already been consumed for hypercall parameters. */ - if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - consumed_xmm_halves) + if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - hc->consumed_xmm_halves) return HV_STATUS_INVALID_HYPERCALL_INPUT; for (i = 0; i < cnt; i++) { - j = i + consumed_xmm_halves; + j = i + hc->consumed_xmm_halves; if (j % 2) data[i] = sse128_hi(hc->xmm[j / 2]); else @@ -1812,27 +1822,24 @@ static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, return 0; } - return kvm_read_guest(kvm, hc->ingpa + offset, data, + return kvm_read_guest(kvm, hc->ingpa + hc->data_offset, data, cnt * sizeof(*data)); } static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc, - u64 *sparse_banks, int consumed_xmm_halves, - gpa_t offset) + u64 *sparse_banks) { if (hc->var_cnt > HV_MAX_SPARSE_VCPU_BANKS) return -EINVAL; /* Cap var_cnt to ignore banks that cannot contain a legal VP index. */ return kvm_hv_get_hc_data(kvm, hc, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS, - sparse_banks, consumed_xmm_halves, offset); + sparse_banks); } -static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[], - int consumed_xmm_halves, gpa_t offset) +static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[]) { - return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, - entries, consumed_xmm_halves, offset); + return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, entries); } static void hv_tlb_flush_enqueue(struct kvm_vcpu *vcpu, @@ -1926,8 +1933,6 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) struct kvm_vcpu *v; unsigned long i; bool all_cpus; - int consumed_xmm_halves = 0; - gpa_t data_offset; /* * The Hyper-V TLFS doesn't allow more than HV_MAX_SPARSE_VCPU_BANKS @@ -1955,12 +1960,12 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) flush.address_space = hc->ingpa; flush.flags = hc->outgpa; flush.processor_mask = sse128_lo(hc->xmm[0]); - consumed_xmm_halves = 1; + hc->consumed_xmm_halves = 1; } else { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush, sizeof(flush)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; - data_offset = sizeof(flush); + hc->data_offset = sizeof(flush); } trace_kvm_hv_flush_tlb(flush.processor_mask, @@ -1985,12 +1990,12 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) flush_ex.flags = hc->outgpa; memcpy(&flush_ex.hv_vp_set, &hc->xmm[0], sizeof(hc->xmm[0])); - consumed_xmm_halves = 2; + hc->consumed_xmm_halves = 2; } else { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush_ex, sizeof(flush_ex)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; - data_offset = sizeof(flush_ex); + hc->data_offset = sizeof(flush_ex); } trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask, @@ -2009,8 +2014,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) if (!hc->var_cnt) goto ret_success; - if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, - consumed_xmm_halves, data_offset)) + if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks)) return HV_STATUS_INVALID_HYPERCALL_INPUT; } @@ -2021,8 +2025,10 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) * consumed_xmm_halves to make sure TLB flush entries are read * from the correct offset. */ - data_offset += hc->var_cnt * sizeof(sparse_banks[0]); - consumed_xmm_halves += hc->var_cnt; + if (hc->fast) + hc->consumed_xmm_halves += hc->var_cnt; + else + hc->data_offset += hc->var_cnt * sizeof(sparse_banks[0]); } if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE || @@ -2030,8 +2036,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) hc->rep_cnt > ARRAY_SIZE(__tlb_flush_entries)) { tlb_flush_entries = NULL; } else { - if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries, - consumed_xmm_halves, data_offset)) + if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries)) return HV_STATUS_INVALID_HYPERCALL_INPUT; tlb_flush_entries = __tlb_flush_entries; } @@ -2180,9 +2185,13 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) if (!hc->var_cnt) goto ret_success; - if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, 1, - offsetof(struct hv_send_ipi_ex, - vp_set.bank_contents))) + if (!hc->fast) + hc->data_offset = offsetof(struct hv_send_ipi_ex, + vp_set.bank_contents); + else + hc->consumed_xmm_halves = 1; + + if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks)) return HV_STATUS_INVALID_HYPERCALL_INPUT; } diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 0687162c4f22..3742d9adacfc 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -426,8 +426,9 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm_set_msi_irq(vcpu->kvm, entry, &irq); if (irq.trig_mode && - kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, - irq.dest_id, irq.dest_mode)) + (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, + irq.dest_id, irq.dest_mode) || + kvm_apic_pending_eoi(vcpu, irq.vector))) __set_bit(irq.vector, ioapic_handled_vectors); } } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 28e3769066e2..58c3242fcc7a 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -188,11 +188,11 @@ static inline bool lapic_in_kernel(struct kvm_vcpu *vcpu) extern struct static_key_false_deferred apic_hw_disabled; -static inline int kvm_apic_hw_enabled(struct kvm_lapic *apic) +static inline bool kvm_apic_hw_enabled(struct kvm_lapic *apic) { if (static_branch_unlikely(&apic_hw_disabled.key)) return apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE; - return MSR_IA32_APICBASE_ENABLE; + return true; } extern struct static_key_false_deferred apic_sw_disabled; diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 1f03701b943a..6f54dc9409c9 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -363,7 +363,7 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check, * A shadow-present leaf SPTE may be non-writable for 4 possible reasons: * * 1. To intercept writes for dirty logging. KVM write-protects huge pages - * so that they can be split be split down into the dirty logging + * so that they can be split down into the dirty logging * granularity (4KiB) whenever the guest writes to them. KVM also * write-protects 4KiB pages so that writes can be recorded in the dirty log * (e.g. if not using PML). SPTEs are write-protected for dirty logging diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 771210ce5181..d6df38d371a0 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1074,7 +1074,9 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int ret = RET_PF_FIXED; bool wrprot = false; - WARN_ON(sp->role.level != fault->goal_level); + if (WARN_ON_ONCE(sp->role.level != fault->goal_level)) + return RET_PF_RETRY; + if (unlikely(!fault->slot)) new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL); else @@ -1173,9 +1175,6 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (fault->nx_huge_page_workaround_enabled) disallowed_hugepage_adjust(fault, iter.old_spte, iter.level); - if (iter.level == fault->goal_level) - break; - /* * If SPTE has been frozen by another thread, just give up and * retry, avoiding unnecessary page table allocation and free. @@ -1183,6 +1182,9 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (is_removed_spte(iter.old_spte)) goto retry; + if (iter.level == fault->goal_level) + goto map_target_level; + /* Step down into the lower level page table if it exists. */ if (is_shadow_present_pte(iter.old_spte) && !is_large_pte(iter.old_spte)) @@ -1203,8 +1205,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) r = tdp_mmu_link_sp(kvm, &iter, sp, true); /* - * Also force the guest to retry the access if the upper level SPTEs - * aren't in place. + * Force the guest to retry if installing an upper level SPTE + * failed, e.g. because a different task modified the SPTE. */ if (r) { tdp_mmu_free_sp(sp); @@ -1214,11 +1216,20 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (fault->huge_page_disallowed && fault->req_level >= iter.level) { spin_lock(&kvm->arch.tdp_mmu_pages_lock); - track_possible_nx_huge_page(kvm, sp); + if (sp->nx_huge_page_disallowed) + track_possible_nx_huge_page(kvm, sp); spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } } + /* + * The walk aborted before reaching the target level, e.g. because the + * iterator detected an upper level SPTE was frozen during traversal. + */ + WARN_ON_ONCE(iter.level == fault->goal_level); + goto retry; + +map_target_level: ret = tdp_mmu_map_handle_target_level(vcpu, fault, &iter); retry: diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 684393c22105..eb594620dd75 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -238,7 +238,8 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) return false; /* recalibrate sample period and check if it's accepted by perf core */ - if (perf_event_period(pmc->perf_event, + if (is_sampling_event(pmc->perf_event) && + perf_event_period(pmc->perf_event, get_sample_period(pmc, pmc->counter))) return false; diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 85ff3c0588ba..ee67ba625094 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -140,7 +140,8 @@ static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) static inline void pmc_update_sample_period(struct kvm_pmc *pmc) { - if (!pmc->perf_event || pmc->is_paused) + if (!pmc->perf_event || pmc->is_paused || + !is_sampling_event(pmc->perf_event)) return; perf_event_period(pmc->perf_event, @@ -164,15 +165,27 @@ static inline void kvm_init_pmu_capability(void) { 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; diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 042d0aca3c92..81f4e9ce0c77 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -68,6 +68,7 @@ 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_0021_EAX] = {0x80000021, 0, CPUID_EAX}, }; /* diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index bc9cd7086fa9..add65dd59756 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -138,15 +138,13 @@ void recalc_intercepts(struct vcpu_svm *svm) c->intercepts[i] = h->intercepts[i]; if (g->int_ctl & V_INTR_MASKING_MASK) { - /* We only want the cr8 intercept bits of L1 */ - vmcb_clr_intercept(c, INTERCEPT_CR8_READ); - vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE); - /* - * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not - * affect any interrupt we may want to inject; therefore, - * interrupt window vmexits are irrelevant to L0. + * Once running L2 with HF_VINTR_MASK, EFLAGS.IF and CR8 + * does not affect any interrupt we may want to inject; + * therefore, writes to CR8 are irrelevant to L0, as are + * interrupt window vmexits. */ + vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE); vmcb_clr_intercept(c, INTERCEPT_VINTR); } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9a194aa1a75a..60c7c880266b 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4969,6 +4969,9 @@ 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; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index b6f4411b613e..d93c715cda6a 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -5296,10 +5296,19 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); - kvm_vcpu_write_guest(vcpu, - vmptr + offsetof(struct vmcs12, - launch_state), - &zero, sizeof(zero)); + /* + * Silently ignore memory errors on VMCLEAR, Intel's pseudocode + * for VMCLEAR includes a "ensure that data for VMCS referenced + * by the operand is in memory" clause that guards writes to + * memory, i.e. doing nothing for I/O is architecturally valid. + * + * FIXME: Suppress failures if and only if no memslot is found, + * i.e. exit to userspace if __copy_to_user() fails. + */ + (void)kvm_vcpu_write_guest(vcpu, + vmptr + offsetof(struct vmcs12, + launch_state), + &zero, sizeof(zero)); } else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) { nested_release_evmcs(vcpu); } @@ -6873,7 +6882,8 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_RDSEED_EXITING | SECONDARY_EXEC_XSAVES | - SECONDARY_EXEC_TSC_SCALING; + SECONDARY_EXEC_TSC_SCALING | + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; /* * We can emulate "VMCS shadowing," even if the hardware diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index fe5615fd8295..7eec0226d56a 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -3440,18 +3440,15 @@ 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; } @@ -4459,6 +4456,13 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, * controls for features that are/aren't exposed to the guest. */ if (nested) { + /* + * All features that can be added or removed to VMX MSRs must + * be supported in the first place for nested virtualization. + */ + if (WARN_ON_ONCE(!(vmcs_config.nested.secondary_ctls_high & control))) + enabled = false; + if (enabled) vmx->nested.msrs.secondary_ctls_high |= control; else diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 312aea1854ae..0735fbc9ba8c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -191,6 +191,10 @@ 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 @@ -1685,6 +1689,9 @@ 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; @@ -4448,10 +4455,15 @@ 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 +5266,11 @@ 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 +6238,26 @@ 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: @@ -13132,6 +13154,9 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, struct x86_exception *e) { if (r == X86EMUL_PROPAGATE_FAULT) { + if (KVM_BUG_ON(!e, vcpu->kvm)) + return -EIO; + kvm_inject_emulated_page_fault(vcpu, e); return 1; } @@ -13453,6 +13478,7 @@ 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/xen.c b/arch/x86/kvm/xen.c index d7af40240248..8fd41f5deae3 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -41,7 +41,7 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) int ret = 0; int idx = srcu_read_lock(&kvm->srcu); - if (gfn == GPA_INVALID) { + if (gfn == KVM_XEN_INVALID_GFN) { kvm_gpc_deactivate(gpc); goto out; } @@ -271,7 +271,15 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) * Attempt to obtain the GPC lock on *both* (if there are two) * gfn_to_pfn caches that cover the region. */ - read_lock_irqsave(&gpc1->lock, flags); + if (atomic) { + local_irq_save(flags); + if (!read_trylock(&gpc1->lock)) { + local_irq_restore(flags); + return; + } + } else { + read_lock_irqsave(&gpc1->lock, flags); + } while (!kvm_gpc_check(gpc1, user_len1)) { read_unlock_irqrestore(&gpc1->lock, flags); @@ -304,9 +312,18 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) * The guest's runstate_info is split across two pages and we * need to hold and validate both GPCs simultaneously. We can * declare a lock ordering GPC1 > GPC2 because nothing else - * takes them more than one at a time. + * takes them more than one at a time. Set a subclass on the + * gpc1 lock to make lockdep shut up about it. */ - read_lock(&gpc2->lock); + lock_set_subclass(&gpc1->lock.dep_map, 1, _THIS_IP_); + if (atomic) { + if (!read_trylock(&gpc2->lock)) { + read_unlock_irqrestore(&gpc1->lock, flags); + return; + } + } else { + read_lock(&gpc2->lock); + } if (!kvm_gpc_check(gpc2, user_len2)) { read_unlock(&gpc2->lock); @@ -590,26 +607,26 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) { r = -EINVAL; } else { - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); kvm->arch.xen.long_mode = !!data->u.long_mode; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); r = 0; } break; case KVM_XEN_ATTR_TYPE_SHARED_INFO: - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); break; case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR: if (data->u.vector && data->u.vector < 0x10) r = -EINVAL; else { - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); kvm->arch.xen.upcall_vector = data->u.vector; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); r = 0; } break; @@ -619,9 +636,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) break; case KVM_XEN_ATTR_TYPE_XEN_VERSION: - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); kvm->arch.xen.xen_version = data->u.xen_version; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); r = 0; break; @@ -630,9 +647,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) r = -EOPNOTSUPP; break; } - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); kvm->arch.xen.runstate_update_flag = !!data->u.runstate_update_flag; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); r = 0; break; @@ -647,7 +664,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) { int r = -ENOENT; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); switch (data->type) { case KVM_XEN_ATTR_TYPE_LONG_MODE: @@ -659,7 +676,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) if (kvm->arch.xen.shinfo_cache.active) data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_cache.gpa); else - data->u.shared_info.gfn = GPA_INVALID; + data->u.shared_info.gfn = KVM_XEN_INVALID_GFN; r = 0; break; @@ -686,7 +703,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) break; } - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); return r; } @@ -694,7 +711,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) { int idx, r = -ENOENT; - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.xen.xen_lock); idx = srcu_read_lock(&vcpu->kvm->srcu); switch (data->type) { @@ -705,7 +722,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) BUILD_BUG_ON(offsetof(struct vcpu_info, time) != offsetof(struct compat_vcpu_info, time)); - if (data->u.gpa == GPA_INVALID) { + if (data->u.gpa == KVM_XEN_INVALID_GPA) { kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache); r = 0; break; @@ -719,7 +736,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO: - if (data->u.gpa == GPA_INVALID) { + if (data->u.gpa == KVM_XEN_INVALID_GPA) { kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_time_info_cache); r = 0; break; @@ -739,7 +756,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) r = -EOPNOTSUPP; break; } - if (data->u.gpa == GPA_INVALID) { + if (data->u.gpa == KVM_XEN_INVALID_GPA) { r = 0; deactivate_out: kvm_gpc_deactivate(&vcpu->arch.xen.runstate_cache); @@ -922,7 +939,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) } srcu_read_unlock(&vcpu->kvm->srcu, idx); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.xen.xen_lock); return r; } @@ -930,14 +947,14 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) { int r = -ENOENT; - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.xen.xen_lock); switch (data->type) { case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO: if (vcpu->arch.xen.vcpu_info_cache.active) data->u.gpa = vcpu->arch.xen.vcpu_info_cache.gpa; else - data->u.gpa = GPA_INVALID; + data->u.gpa = KVM_XEN_INVALID_GPA; r = 0; break; @@ -945,7 +962,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) if (vcpu->arch.xen.vcpu_time_info_cache.active) data->u.gpa = vcpu->arch.xen.vcpu_time_info_cache.gpa; else - data->u.gpa = GPA_INVALID; + data->u.gpa = KVM_XEN_INVALID_GPA; r = 0; break; @@ -1013,7 +1030,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.xen.xen_lock); return r; } @@ -1069,6 +1086,7 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 : kvm->arch.xen_hvm_config.blob_size_32; u8 *page; + int ret; if (page_num >= blob_size) return 1; @@ -1079,10 +1097,10 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) if (IS_ERR(page)) return PTR_ERR(page); - if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) { - kfree(page); + ret = kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE); + kfree(page); + if (ret) return 1; - } } return 0; } @@ -1105,7 +1123,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) xhc->blob_size_32 || xhc->blob_size_64)) return -EINVAL; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); if (xhc->msr && !kvm->arch.xen_hvm_config.msr) static_branch_inc(&kvm_xen_enabled.key); @@ -1114,7 +1132,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc)); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); return 0; } @@ -1183,30 +1201,22 @@ static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports, static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, u64 param, u64 *r) { - int idx, i; struct sched_poll sched_poll; evtchn_port_t port, *ports; - gpa_t gpa; + struct x86_exception e; + int i; if (!lapic_in_kernel(vcpu) || !(vcpu->kvm->arch.xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_EVTCHN_SEND)) return false; - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - if (!gpa) { - *r = -EFAULT; - return true; - } - if (IS_ENABLED(CONFIG_64BIT) && !longmode) { struct compat_sched_poll sp32; /* Sanity check that the compat struct definition is correct */ BUILD_BUG_ON(sizeof(sp32) != 16); - if (kvm_vcpu_read_guest(vcpu, gpa, &sp32, sizeof(sp32))) { + if (kvm_read_guest_virt(vcpu, param, &sp32, sizeof(sp32), &e)) { *r = -EFAULT; return true; } @@ -1220,8 +1230,8 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, sched_poll.nr_ports = sp32.nr_ports; sched_poll.timeout = sp32.timeout; } else { - if (kvm_vcpu_read_guest(vcpu, gpa, &sched_poll, - sizeof(sched_poll))) { + if (kvm_read_guest_virt(vcpu, param, &sched_poll, + sizeof(sched_poll), &e)) { *r = -EFAULT; return true; } @@ -1243,18 +1253,13 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, } else ports = &port; + if (kvm_read_guest_virt(vcpu, (gva_t)sched_poll.ports, ports, + sched_poll.nr_ports * sizeof(*ports), &e)) { + *r = -EFAULT; + return true; + } + for (i = 0; i < sched_poll.nr_ports; i++) { - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, - (gva_t)(sched_poll.ports + i), - NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - - if (!gpa || kvm_vcpu_read_guest(vcpu, gpa, - &ports[i], sizeof(port))) { - *r = -EFAULT; - goto out; - } if (ports[i] >= max_evtchn_port(vcpu->kvm)) { *r = -EINVAL; goto out; @@ -1330,9 +1335,8 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, int vcpu_id, u64 param, u64 *r) { struct vcpu_set_singleshot_timer oneshot; + struct x86_exception e; s64 delta; - gpa_t gpa; - int idx; if (!kvm_xen_timer_enabled(vcpu)) return false; @@ -1343,9 +1347,6 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, *r = -EINVAL; return true; } - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); /* * The only difference for 32-bit compat is the 4 bytes of @@ -1363,9 +1364,8 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, BUILD_BUG_ON(sizeof_field(struct compat_vcpu_set_singleshot_timer, flags) != sizeof_field(struct vcpu_set_singleshot_timer, flags)); - if (!gpa || - kvm_vcpu_read_guest(vcpu, gpa, &oneshot, longmode ? sizeof(oneshot) : - sizeof(struct compat_vcpu_set_singleshot_timer))) { + if (kvm_read_guest_virt(vcpu, param, &oneshot, longmode ? sizeof(oneshot) : + sizeof(struct compat_vcpu_set_singleshot_timer), &e)) { *r = -EFAULT; return true; } @@ -1675,15 +1675,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm) mm_borrowed = true; } - /* - * For the irqfd workqueue, using the main kvm->lock mutex is - * fine since this function is invoked from kvm_set_irq() with - * no other lock held, no srcu. In future if it will be called - * directly from a vCPU thread (e.g. on hypercall for an IPI) - * then it may need to switch to using a leaf-node mutex for - * serializing the shared_info mapping. - */ - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); /* * It is theoretically possible for the page to be unmapped @@ -1712,7 +1704,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm) srcu_read_unlock(&kvm->srcu, idx); } while(!rc); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); if (mm_borrowed) kthread_unuse_mm(kvm->mm); @@ -1825,20 +1817,20 @@ static int kvm_xen_eventfd_update(struct kvm *kvm, { u32 port = data->u.evtchn.send_port; struct evtchnfd *evtchnfd; + int ret; - if (!port || port >= max_evtchn_port(kvm)) - return -EINVAL; - - mutex_lock(&kvm->lock); + /* Protect writes to evtchnfd as well as the idr lookup. */ + mutex_lock(&kvm->arch.xen.xen_lock); evtchnfd = idr_find(&kvm->arch.xen.evtchn_ports, port); - mutex_unlock(&kvm->lock); + ret = -ENOENT; if (!evtchnfd) - return -ENOENT; + goto out_unlock; /* For an UPDATE, nothing may change except the priority/vcpu */ + ret = -EINVAL; if (evtchnfd->type != data->u.evtchn.type) - return -EINVAL; + goto out_unlock; /* * Port cannot change, and if it's zero that was an eventfd @@ -1846,20 +1838,21 @@ static int kvm_xen_eventfd_update(struct kvm *kvm, */ if (!evtchnfd->deliver.port.port || evtchnfd->deliver.port.port != data->u.evtchn.deliver.port.port) - return -EINVAL; + goto out_unlock; /* We only support 2 level event channels for now */ if (data->u.evtchn.deliver.port.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL) - return -EINVAL; + goto out_unlock; - mutex_lock(&kvm->lock); evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority; if (evtchnfd->deliver.port.vcpu_id != data->u.evtchn.deliver.port.vcpu) { evtchnfd->deliver.port.vcpu_id = data->u.evtchn.deliver.port.vcpu; evtchnfd->deliver.port.vcpu_idx = -1; } - mutex_unlock(&kvm->lock); - return 0; + ret = 0; +out_unlock: + mutex_unlock(&kvm->arch.xen.xen_lock); + return ret; } /* @@ -1871,12 +1864,9 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm, { u32 port = data->u.evtchn.send_port; struct eventfd_ctx *eventfd = NULL; - struct evtchnfd *evtchnfd = NULL; + struct evtchnfd *evtchnfd; int ret = -EINVAL; - if (!port || port >= max_evtchn_port(kvm)) - return -EINVAL; - evtchnfd = kzalloc(sizeof(struct evtchnfd), GFP_KERNEL); if (!evtchnfd) return -ENOMEM; @@ -1924,10 +1914,10 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm, evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority; } - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); ret = idr_alloc(&kvm->arch.xen.evtchn_ports, evtchnfd, port, port + 1, GFP_KERNEL); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); if (ret >= 0) return 0; @@ -1945,15 +1935,14 @@ static int kvm_xen_eventfd_deassign(struct kvm *kvm, u32 port) { struct evtchnfd *evtchnfd; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); evtchnfd = idr_remove(&kvm->arch.xen.evtchn_ports, port); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); if (!evtchnfd) return -ENOENT; - if (kvm) - synchronize_srcu(&kvm->srcu); + synchronize_srcu(&kvm->srcu); if (!evtchnfd->deliver.port.port) eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx); kfree(evtchnfd); @@ -1962,18 +1951,42 @@ static int kvm_xen_eventfd_deassign(struct kvm *kvm, u32 port) static int kvm_xen_eventfd_reset(struct kvm *kvm) { - struct evtchnfd *evtchnfd; + struct evtchnfd *evtchnfd, **all_evtchnfds; int i; + int n = 0; + + mutex_lock(&kvm->arch.xen.xen_lock); - mutex_lock(&kvm->lock); + /* + * Because synchronize_srcu() cannot be called inside the + * critical section, first collect all the evtchnfd objects + * in an array as they are removed from evtchn_ports. + */ + idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) + n++; + + all_evtchnfds = kmalloc_array(n, sizeof(struct evtchnfd *), GFP_KERNEL); + if (!all_evtchnfds) { + mutex_unlock(&kvm->arch.xen.xen_lock); + return -ENOMEM; + } + + n = 0; idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) { + all_evtchnfds[n++] = evtchnfd; idr_remove(&kvm->arch.xen.evtchn_ports, evtchnfd->send_port); - synchronize_srcu(&kvm->srcu); + } + mutex_unlock(&kvm->arch.xen.xen_lock); + + synchronize_srcu(&kvm->srcu); + + while (n--) { + evtchnfd = all_evtchnfds[n]; if (!evtchnfd->deliver.port.port) eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx); kfree(evtchnfd); } - mutex_unlock(&kvm->lock); + kfree(all_evtchnfds); return 0; } @@ -2002,20 +2015,22 @@ static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r) { struct evtchnfd *evtchnfd; struct evtchn_send send; - gpa_t gpa; - int idx; + struct x86_exception e; - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - - if (!gpa || kvm_vcpu_read_guest(vcpu, gpa, &send, sizeof(send))) { + /* Sanity check: this structure is the same for 32-bit and 64-bit */ + BUILD_BUG_ON(sizeof(send) != 4); + if (kvm_read_guest_virt(vcpu, param, &send, sizeof(send), &e)) { *r = -EFAULT; return true; } - /* The evtchn_ports idr is protected by vcpu->kvm->srcu */ + /* + * evtchnfd is protected by kvm->srcu; the idr lookup instead + * is protected by RCU. + */ + rcu_read_lock(); evtchnfd = idr_find(&vcpu->kvm->arch.xen.evtchn_ports, send.port); + rcu_read_unlock(); if (!evtchnfd) return false; @@ -2063,6 +2078,7 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) void kvm_xen_init_vm(struct kvm *kvm) { + mutex_init(&kvm->arch.xen.xen_lock); idr_init(&kvm->arch.xen.evtchn_ports); kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm, NULL, KVM_HOST_USES_PFN); } 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/insn-eval.c b/arch/x86/lib/insn-eval.c index 21104c41cba0..558a605929db 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -1595,16 +1595,16 @@ bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs, * Returns: * * Type of the instruction. Size of the memory operand is stored in - * @bytes. If decode failed, MMIO_DECODE_FAILED returned. + * @bytes. If decode failed, INSN_MMIO_DECODE_FAILED returned. */ -enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) +enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes) { - enum mmio_type type = MMIO_DECODE_FAILED; + enum insn_mmio_type type = INSN_MMIO_DECODE_FAILED; *bytes = 0; if (insn_get_opcode(insn)) - return MMIO_DECODE_FAILED; + return INSN_MMIO_DECODE_FAILED; switch (insn->opcode.bytes[0]) { case 0x88: /* MOV m8,r8 */ @@ -1613,7 +1613,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0x89: /* MOV m16/m32/m64, r16/m32/m64 */ if (!*bytes) *bytes = insn->opnd_bytes; - type = MMIO_WRITE; + type = INSN_MMIO_WRITE; break; case 0xc6: /* MOV m8, imm8 */ @@ -1622,7 +1622,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0xc7: /* MOV m16/m32/m64, imm16/imm32/imm64 */ if (!*bytes) *bytes = insn->opnd_bytes; - type = MMIO_WRITE_IMM; + type = INSN_MMIO_WRITE_IMM; break; case 0x8a: /* MOV r8, m8 */ @@ -1631,7 +1631,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0x8b: /* MOV r16/r32/r64, m16/m32/m64 */ if (!*bytes) *bytes = insn->opnd_bytes; - type = MMIO_READ; + type = INSN_MMIO_READ; break; case 0xa4: /* MOVS m8, m8 */ @@ -1640,7 +1640,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0xa5: /* MOVS m16/m32/m64, m16/m32/m64 */ if (!*bytes) *bytes = insn->opnd_bytes; - type = MMIO_MOVS; + type = INSN_MMIO_MOVS; break; case 0x0f: /* Two-byte instruction */ @@ -1651,7 +1651,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0xb7: /* MOVZX r32/r64, m16 */ if (!*bytes) *bytes = 2; - type = MMIO_READ_ZERO_EXTEND; + type = INSN_MMIO_READ_ZERO_EXTEND; break; case 0xbe: /* MOVSX r16/r32/r64, m8 */ @@ -1660,7 +1660,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0xbf: /* MOVSX r32/r64, m16 */ if (!*bytes) *bytes = 2; - type = MMIO_READ_SIGN_EXTEND; + type = INSN_MMIO_READ_SIGN_EXTEND; break; } break; diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S index a1f9416bf67a..6ff2f56cb0f7 100644 --- a/arch/x86/lib/iomap_copy_64.S +++ b/arch/x86/lib/iomap_copy_64.S @@ -10,6 +10,6 @@ */ SYM_FUNC_START(__iowrite32_copy) movl %edx,%ecx - rep movsd + rep movsl RET SYM_FUNC_END(__iowrite32_copy) 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/init.c b/arch/x86/mm/init.c index d3987359d441..cb258f58fdc8 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -26,6 +26,7 @@ #include <asm/pti.h> #include <asm/text-patching.h> #include <asm/memtype.h> +#include <asm/paravirt.h> /* * We need to define the tracepoints somewhere, and tlb.c @@ -804,6 +805,9 @@ void __init poking_init(void) poking_mm = mm_alloc(); BUG_ON(!poking_mm); + /* Xen PV guests need the PGD to be pinned. */ + paravirt_arch_dup_mmap(NULL, poking_mm); + /* * Randomize the poking address, but make sure that the following page * will be mapped at the same PMD. We need 2 pages, so find space for 3, diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 46de9cf5c91d..004b37f026d1 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) 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/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 758cbfe55daa..4b3efaa82ab7 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -12,6 +12,7 @@ */ #include <linux/acpi.h> +#include <linux/efi.h> #include <linux/pci.h> #include <linux/init.h> #include <linux/bitmap.h> @@ -442,17 +443,42 @@ static bool is_acpi_reserved(u64 start, u64 end, enum e820_type not_used) return mcfg_res.flags; } +static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used) +{ +#ifdef CONFIG_EFI + efi_memory_desc_t *md; + u64 size, mmio_start, mmio_end; + + for_each_efi_memory_desc(md) { + if (md->type == EFI_MEMORY_MAPPED_IO) { + size = md->num_pages << EFI_PAGE_SHIFT; + mmio_start = md->phys_addr; + mmio_end = mmio_start + size; + + /* + * N.B. Caller supplies (start, start + size), + * so to match, mmio_end is the first address + * *past* the EFI_MEMORY_MAPPED_IO area. + */ + if (mmio_start <= start && end <= mmio_end) + return true; + } + } +#endif + + return false; +} + typedef bool (*check_reserved_t)(u64 start, u64 end, enum e820_type type); static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, struct pci_mmcfg_region *cfg, - struct device *dev, int with_e820) + struct device *dev, const char *method) { u64 addr = cfg->res.start; u64 size = resource_size(&cfg->res); u64 old_size = size; int num_buses; - char *method = with_e820 ? "E820" : "ACPI motherboard resources"; while (!is_reserved(addr, addr + size, E820_TYPE_RESERVED)) { size >>= 1; @@ -464,10 +490,10 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, return false; if (dev) - dev_info(dev, "MMCONFIG at %pR reserved in %s\n", + dev_info(dev, "MMCONFIG at %pR reserved as %s\n", &cfg->res, method); else - pr_info(PREFIX "MMCONFIG at %pR reserved in %s\n", + pr_info(PREFIX "MMCONFIG at %pR reserved as %s\n", &cfg->res, method); if (old_size != size) { @@ -500,7 +526,8 @@ static bool __ref pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early) { if (!early && !acpi_disabled) { - if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0)) + if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, + "ACPI motherboard resource")) return true; if (dev) @@ -513,6 +540,10 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e "MMCONFIG at %pR not reserved in " "ACPI motherboard resources\n", &cfg->res); + + if (is_mmconf_reserved(is_efi_mmio, cfg, dev, + "EfiMemoryMappedIO")) + return true; } /* @@ -527,7 +558,8 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e /* Don't try to do this check unless configuration type 1 is available. how about type 2 ?*/ if (raw_pci_ops) - return is_mmconf_reserved(e820__mapped_all, cfg, dev, 1); + return is_mmconf_reserved(e820__mapped_all, cfg, dev, + "E820 entry"); return false; } 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/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/elfcore.c b/arch/x86/um/elfcore.c index 48a3eb09d951..650cdbbdaf45 100644 --- a/arch/x86/um/elfcore.c +++ b/arch/x86/um/elfcore.c @@ -7,7 +7,7 @@ #include <asm/elf.h> -Elf32_Half elf_core_extra_phdrs(void) +Elf32_Half elf_core_extra_phdrs(struct coredump_params *cprm) { return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0; } @@ -60,7 +60,7 @@ int elf_core_write_extra_data(struct coredump_params *cprm) return 1; } -size_t elf_core_extra_data_size(void) +size_t elf_core_extra_data_size(struct coredump_params *cprm) { if ( vsyscall_ehdr ) { const struct elfhdr *const ehdrp = 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/p2m.c b/arch/x86/xen/p2m.c index 58db86f7b384..9bdc3b656b2c 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -134,11 +134,6 @@ static inline unsigned p2m_mid_index(unsigned long pfn) return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE; } -static inline unsigned p2m_index(unsigned long pfn) -{ - return pfn % P2M_PER_PAGE; -} - static void p2m_top_mfn_init(unsigned long *top) { unsigned i; diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 9ef0a5cca96e..6b8836deb738 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) |