diff options
Diffstat (limited to 'arch/x86/boot/compressed')
27 files changed, 983 insertions, 1160 deletions
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 1acff356d97a..68f9d7a1683b 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -17,15 +17,6 @@ # (see scripts/Makefile.lib size_append) # compressed vmlinux.bin.all + u32 size of vmlinux.bin.all -# Sanitizer runtimes are unavailable and cannot be linked for early boot code. -KASAN_SANITIZE := n -KCSAN_SANITIZE := n -KMSAN_SANITIZE := n -OBJECT_FILES_NON_STANDARD := y - -# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. -KCOV_INSTRUMENT := n - targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4 vmlinux.bin.zst @@ -34,6 +25,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ # avoid errors with '-march=i386', and future flags may depend on the target to # be valid. KBUILD_CFLAGS := -m$(BITS) -O2 $(CLANG_FLAGS) +KBUILD_CFLAGS += -std=gnu11 -fms-extensions KBUILD_CFLAGS += -fno-strict-aliasing -fPIE KBUILD_CFLAGS += -Wundef KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING @@ -44,23 +36,23 @@ KBUILD_CFLAGS += -mno-mmx -mno-sse KBUILD_CFLAGS += -ffreestanding -fshort-wchar KBUILD_CFLAGS += -fno-stack-protector KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) -KBUILD_CFLAGS += $(call cc-disable-warning, gnu) +ifdef CONFIG_CC_IS_CLANG +KBUILD_CFLAGS += -Wno-gnu +KBUILD_CFLAGS += -Wno-microsoft-anon-tag +endif KBUILD_CFLAGS += -Wno-pointer-sign -KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables KBUILD_CFLAGS += -D__DISABLE_EXPORTS # Disable relocation relaxation in case the link is not PIE. -KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no) +KBUILD_CFLAGS += $(call cc-option,-Wa$(comma)-mrelax-relocations=no) KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h -# sev.c indirectly inludes inat-table.h which is generated during +# sev-decode-insn.c indirectly includes inat-table.c which is generated during # compilation and stored in $(objtree). Add the directory to the includes so # that the compiler finds it even with out-of-tree builds (make O=/some/path). -CFLAGS_sev.o += -I$(objtree)/arch/x86/lib/ +CFLAGS_sev-handle-vc.o += -I$(objtree)/arch/x86/lib/ KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ -GCOV_PROFILE := n -UBSAN_SANITIZE :=n KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE) KBUILD_LDFLAGS += $(call ld-option,--no-ld-generated-unwind-info) @@ -74,12 +66,17 @@ LDFLAGS_vmlinux += -z noexecstack ifeq ($(CONFIG_LD_IS_BFD),y) LDFLAGS_vmlinux += $(call ld-option,--no-warn-rwx-segments) endif +ifeq ($(CONFIG_EFI_STUB),y) +# ensure that the static EFI stub library will be pulled in, even if it is +# never referenced explicitly from the startup code +LDFLAGS_vmlinux += -u efi_pe_entry +endif LDFLAGS_vmlinux += -T hostprogs := mkpiggy HOST_EXTRACFLAGS += -I$(srctree)/tools/include -sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p' +sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABbCDGRSTtVW] \(_text\|__start_rodata\|_sinittext\|__inittext_end\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p' quiet_cmd_voffset = VOFFSET $@ cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@ @@ -102,17 +99,23 @@ ifdef CONFIG_X86_64 vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/mem_encrypt.o vmlinux-objs-y += $(obj)/pgtable_64.o - vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev.o + vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev.o $(obj)/sev-handle-vc.o endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o -vmlinux-objs-$(CONFIG_INTEL_TDX_GUEST) += $(obj)/tdx.o $(obj)/tdcall.o +vmlinux-objs-$(CONFIG_INTEL_TDX_GUEST) += $(obj)/tdx.o $(obj)/tdcall.o $(obj)/tdx-shared.o +vmlinux-objs-$(CONFIG_UNACCEPTED_MEMORY) += $(obj)/mem.o vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o -vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o -vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a +vmlinux-libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a +vmlinux-libs-$(CONFIG_X86_64) += $(objtree)/arch/x86/boot/startup/lib.a +vmlinux-objs-$(CONFIG_EFI_SBAT) += $(obj)/sbat.o -$(obj)/vmlinux: $(vmlinux-objs-y) FORCE +ifdef CONFIG_EFI_SBAT +$(obj)/sbat.o: $(CONFIG_EFI_SBAT_FILE) +endif + +$(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE $(call if_changed,ld) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S @@ -124,7 +127,8 @@ targets += $(patsubst $(obj)/%,%,$(vmlinux-objs-y)) vmlinux.bin.all vmlinux.relo CMD_RELOCS = arch/x86/tools/relocs quiet_cmd_relocs = RELOCS $@ cmd_relocs = $(CMD_RELOCS) $< > $@;$(CMD_RELOCS) --abs-relocs $< -$(obj)/vmlinux.relocs: vmlinux FORCE + +$(obj)/vmlinux.relocs: vmlinux.unstripped FORCE $(call if_changed,relocs) vmlinux.bin.all-y := $(obj)/vmlinux.bin diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 9caf89063e77..f196b1d1ddf8 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -5,6 +5,8 @@ #include "../string.h" #include "efi.h" +#include <asm/bootparam.h> + #include <linux/numa.h> /* @@ -30,13 +32,13 @@ __efi_get_rsdp_addr(unsigned long cfg_tbl_pa, unsigned int cfg_tbl_len) * Search EFI system tables for RSDP. Preferred is ACPI_20_TABLE_GUID to * ACPI_TABLE_GUID because it has more features. */ - rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + rsdp_addr = efi_find_vendor_table(boot_params_ptr, cfg_tbl_pa, cfg_tbl_len, ACPI_20_TABLE_GUID); if (rsdp_addr) return (acpi_physical_address)rsdp_addr; /* No ACPI_20_TABLE_GUID found, fallback to ACPI_TABLE_GUID. */ - rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + rsdp_addr = efi_find_vendor_table(boot_params_ptr, cfg_tbl_pa, cfg_tbl_len, ACPI_TABLE_GUID); if (rsdp_addr) return (acpi_physical_address)rsdp_addr; @@ -56,15 +58,15 @@ static acpi_physical_address efi_get_rsdp_addr(void) enum efi_type et; int ret; - et = efi_get_type(boot_params); + et = efi_get_type(boot_params_ptr); if (et == EFI_TYPE_NONE) return 0; - systab_pa = efi_get_system_table(boot_params); + systab_pa = efi_get_system_table(boot_params_ptr); if (!systab_pa) error("EFI support advertised, but unable to locate system table."); - ret = efi_get_conf_table(boot_params, &cfg_tbl_pa, &cfg_tbl_len); + ret = efi_get_conf_table(boot_params_ptr, &cfg_tbl_pa, &cfg_tbl_len); if (ret || !cfg_tbl_pa) error("EFI config table not found."); @@ -156,7 +158,7 @@ acpi_physical_address get_rsdp_addr(void) { acpi_physical_address pa; - pa = boot_params->acpi_rsdp_addr; + pa = boot_params_ptr->acpi_rsdp_addr; if (!pa) pa = efi_get_rsdp_addr(); @@ -178,7 +180,7 @@ static unsigned long get_cmdline_acpi_rsdp(void) { unsigned long addr = 0; -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE char val[MAX_ADDR_LEN] = { }; int ret; @@ -210,7 +212,7 @@ static unsigned long get_acpi_srat_table(void) rsdp = (struct acpi_table_rsdp *)get_cmdline_acpi_rsdp(); if (!rsdp) rsdp = (struct acpi_table_rsdp *)(long) - boot_params->acpi_rsdp_addr; + boot_params_ptr->acpi_rsdp_addr; if (!rsdp) return 0; diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index f1add5d85da9..e162d7f59cc5 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include "misc.h" +#include <asm/bootparam.h> + static unsigned long fs; static inline void set_fs(unsigned long seg) { @@ -14,9 +16,9 @@ static inline char rdfs8(addr_t addr) #include "../cmdline.c" unsigned long get_cmd_line_ptr(void) { - unsigned long cmd_line_ptr = boot_params->hdr.cmd_line_ptr; + unsigned long cmd_line_ptr = boot_params_ptr->hdr.cmd_line_ptr; - cmd_line_ptr |= (u64)boot_params->ext_cmd_line_ptr << 32; + cmd_line_ptr |= (u64)boot_params_ptr->ext_cmd_line_ptr << 32; return cmd_line_ptr; } diff --git a/arch/x86/boot/compressed/efi.c b/arch/x86/boot/compressed/efi.c index 6edd034b0b30..f2e50f9758e6 100644 --- a/arch/x86/boot/compressed/efi.c +++ b/arch/x86/boot/compressed/efi.c @@ -7,6 +7,8 @@ #include "misc.h" +#include <asm/bootparam.h> + /** * efi_get_type - Given a pointer to boot_params, determine the type of EFI environment. * diff --git a/arch/x86/boot/compressed/efi.h b/arch/x86/boot/compressed/efi.h index 7db2f41b54cd..b22300970f97 100644 --- a/arch/x86/boot/compressed/efi.h +++ b/arch/x86/boot/compressed/efi.h @@ -16,6 +16,7 @@ typedef guid_t efi_guid_t __aligned(__alignof__(u32)); #define ACPI_TABLE_GUID EFI_GUID(0xeb9d2d30, 0x2d88, 0x11d3, 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) #define ACPI_20_TABLE_GUID EFI_GUID(0x8868e871, 0xe4f1, 0x11d3, 0xbc, 0x22, 0x00, 0x80, 0xc7, 0x3c, 0x88, 0x81) #define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42) +#define LINUX_EFI_UNACCEPTED_MEM_TABLE_GUID EFI_GUID(0xd5d1de3c, 0x105c, 0x44f9, 0x9e, 0xa9, 0xbc, 0xef, 0x98, 0x12, 0x00, 0x31) #define EFI32_LOADER_SIGNATURE "EL32" #define EFI64_LOADER_SIGNATURE "EL64" @@ -32,6 +33,7 @@ typedef struct { } efi_table_hdr_t; #define EFI_CONVENTIONAL_MEMORY 7 +#define EFI_UNACCEPTED_MEMORY 15 #define EFI_MEMORY_MORE_RELIABLE \ ((u64)0x0000000000010000ULL) /* higher reliability */ @@ -95,13 +97,12 @@ typedef struct { u32 tables; } efi_system_table_32_t; -/* kexec external ABI */ -struct efi_setup_data { - u64 fw_vendor; - u64 __unused; - u64 tables; - u64 smbios; - u64 reserved[8]; +struct efi_unaccepted_memory { + u32 version; + u32 unit_size; + u64 phys_base; + u64 size; + unsigned long bitmap[]; }; static inline int efi_guidcmp (efi_guid_t left, efi_guid_t right) diff --git a/arch/x86/boot/compressed/efi_mixed.S b/arch/x86/boot/compressed/efi_mixed.S deleted file mode 100644 index 4ca70bf93dc0..000000000000 --- a/arch/x86/boot/compressed/efi_mixed.S +++ /dev/null @@ -1,345 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming - * - * Early support for invoking 32-bit EFI services from a 64-bit kernel. - * - * Because this thunking occurs before ExitBootServices() we have to - * restore the firmware's 32-bit GDT and IDT before we make EFI service - * calls. - * - * On the plus side, we don't have to worry about mangling 64-bit - * addresses into 32-bits because we're executing with an identity - * mapped pagetable and haven't transitioned to 64-bit virtual addresses - * yet. - */ - -#include <linux/linkage.h> -#include <asm/msr.h> -#include <asm/page_types.h> -#include <asm/processor-flags.h> -#include <asm/segment.h> - - .code64 - .text -/* - * When booting in 64-bit mode on 32-bit EFI firmware, startup_64_mixed_mode() - * is the first thing that runs after switching to long mode. Depending on - * whether the EFI handover protocol or the compat entry point was used to - * enter the kernel, it will either branch to the 64-bit EFI handover - * entrypoint at offset 0x390 in the image, or to the 64-bit EFI PE/COFF - * entrypoint efi_pe_entry(). In the former case, the bootloader must provide a - * struct bootparams pointer as the third argument, so the presence of such a - * pointer is used to disambiguate. - * - * +--------------+ - * +------------------+ +------------+ +------>| efi_pe_entry | - * | efi32_pe_entry |---->| | | +-----------+--+ - * +------------------+ | | +------+----------------+ | - * | startup_32 |---->| startup_64_mixed_mode | | - * +------------------+ | | +------+----------------+ V - * | efi32_stub_entry |---->| | | +------------------+ - * +------------------+ +------------+ +---->| efi64_stub_entry | - * +-------------+----+ - * +------------+ +----------+ | - * | startup_64 |<----| efi_main |<--------------+ - * +------------+ +----------+ - */ -SYM_FUNC_START(startup_64_mixed_mode) - lea efi32_boot_args(%rip), %rdx - mov 0(%rdx), %edi - mov 4(%rdx), %esi - mov 8(%rdx), %edx // saved bootparams pointer - test %edx, %edx - jnz efi64_stub_entry - /* - * efi_pe_entry uses MS calling convention, which requires 32 bytes of - * shadow space on the stack even if all arguments are passed in - * registers. We also need an additional 8 bytes for the space that - * would be occupied by the return address, and this also results in - * the correct stack alignment for entry. - */ - sub $40, %rsp - mov %rdi, %rcx // MS calling convention - mov %rsi, %rdx - jmp efi_pe_entry -SYM_FUNC_END(startup_64_mixed_mode) - -SYM_FUNC_START(__efi64_thunk) - push %rbp - push %rbx - - movl %ds, %eax - push %rax - movl %es, %eax - push %rax - movl %ss, %eax - push %rax - - /* Copy args passed on stack */ - movq 0x30(%rsp), %rbp - movq 0x38(%rsp), %rbx - movq 0x40(%rsp), %rax - - /* - * Convert x86-64 ABI params to i386 ABI - */ - subq $64, %rsp - movl %esi, 0x0(%rsp) - movl %edx, 0x4(%rsp) - movl %ecx, 0x8(%rsp) - movl %r8d, 0xc(%rsp) - movl %r9d, 0x10(%rsp) - movl %ebp, 0x14(%rsp) - movl %ebx, 0x18(%rsp) - movl %eax, 0x1c(%rsp) - - leaq 0x20(%rsp), %rbx - sgdt (%rbx) - sidt 16(%rbx) - - leaq 1f(%rip), %rbp - - /* - * Switch to IDT and GDT with 32-bit segments. These are the firmware - * GDT and IDT that were installed when the kernel started executing. - * The pointers were saved by the efi32_entry() routine below. - * - * Pass the saved DS selector to the 32-bit code, and use far return to - * restore the saved CS selector. - */ - lidt efi32_boot_idt(%rip) - lgdt efi32_boot_gdt(%rip) - - movzwl efi32_boot_ds(%rip), %edx - movzwq efi32_boot_cs(%rip), %rax - pushq %rax - leaq efi_enter32(%rip), %rax - pushq %rax - lretq - -1: addq $64, %rsp - movq %rdi, %rax - - pop %rbx - movl %ebx, %ss - pop %rbx - movl %ebx, %es - pop %rbx - movl %ebx, %ds - /* Clear out 32-bit selector from FS and GS */ - xorl %ebx, %ebx - movl %ebx, %fs - movl %ebx, %gs - - pop %rbx - pop %rbp - RET -SYM_FUNC_END(__efi64_thunk) - - .code32 -/* - * EFI service pointer must be in %edi. - * - * The stack should represent the 32-bit calling convention. - */ -SYM_FUNC_START_LOCAL(efi_enter32) - /* Load firmware selector into data and stack segment registers */ - movl %edx, %ds - movl %edx, %es - movl %edx, %fs - movl %edx, %gs - movl %edx, %ss - - /* Reload pgtables */ - movl %cr3, %eax - movl %eax, %cr3 - - /* Disable paging */ - movl %cr0, %eax - btrl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - - /* Disable long mode via EFER */ - movl $MSR_EFER, %ecx - rdmsr - btrl $_EFER_LME, %eax - wrmsr - - call *%edi - - /* We must preserve return value */ - movl %eax, %edi - - /* - * Some firmware will return with interrupts enabled. Be sure to - * disable them before we switch GDTs and IDTs. - */ - cli - - lidtl 16(%ebx) - lgdtl (%ebx) - - movl %cr4, %eax - btsl $(X86_CR4_PAE_BIT), %eax - movl %eax, %cr4 - - movl %cr3, %eax - movl %eax, %cr3 - - movl $MSR_EFER, %ecx - rdmsr - btsl $_EFER_LME, %eax - wrmsr - - xorl %eax, %eax - lldt %ax - - pushl $__KERNEL_CS - pushl %ebp - - /* Enable paging */ - movl %cr0, %eax - btsl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - lret -SYM_FUNC_END(efi_enter32) - -/* - * This is the common EFI stub entry point for mixed mode. - * - * Arguments: %ecx image handle - * %edx EFI system table pointer - * %esi struct bootparams pointer (or NULL when not using - * the EFI handover protocol) - * - * Since this is the point of no return for ordinary execution, no registers - * are considered live except for the function parameters. [Note that the EFI - * stub may still exit and return to the firmware using the Exit() EFI boot - * service.] - */ -SYM_FUNC_START(efi32_entry) - call 1f -1: pop %ebx - - /* Save firmware GDTR and code/data selectors */ - sgdtl (efi32_boot_gdt - 1b)(%ebx) - movw %cs, (efi32_boot_cs - 1b)(%ebx) - movw %ds, (efi32_boot_ds - 1b)(%ebx) - - /* Store firmware IDT descriptor */ - sidtl (efi32_boot_idt - 1b)(%ebx) - - /* Store boot arguments */ - leal (efi32_boot_args - 1b)(%ebx), %ebx - movl %ecx, 0(%ebx) - movl %edx, 4(%ebx) - movl %esi, 8(%ebx) - movb $0x0, 12(%ebx) // efi_is64 - - /* Disable paging */ - movl %cr0, %eax - btrl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - - jmp startup_32 -SYM_FUNC_END(efi32_entry) - -#define ST32_boottime 60 // offsetof(efi_system_table_32_t, boottime) -#define BS32_handle_protocol 88 // offsetof(efi_boot_services_32_t, handle_protocol) -#define LI32_image_base 32 // offsetof(efi_loaded_image_32_t, image_base) - -/* - * efi_status_t efi32_pe_entry(efi_handle_t image_handle, - * efi_system_table_32_t *sys_table) - */ -SYM_FUNC_START(efi32_pe_entry) - pushl %ebp - movl %esp, %ebp - pushl %eax // dummy push to allocate loaded_image - - pushl %ebx // save callee-save registers - pushl %edi - - call verify_cpu // check for long mode support - testl %eax, %eax - movl $0x80000003, %eax // EFI_UNSUPPORTED - jnz 2f - - call 1f -1: pop %ebx - - /* Get the loaded image protocol pointer from the image handle */ - leal -4(%ebp), %eax - pushl %eax // &loaded_image - leal (loaded_image_proto - 1b)(%ebx), %eax - pushl %eax // pass the GUID address - pushl 8(%ebp) // pass the image handle - - /* - * Note the alignment of the stack frame. - * sys_table - * handle <-- 16-byte aligned on entry by ABI - * return address - * frame pointer - * loaded_image <-- local variable - * saved %ebx <-- 16-byte aligned here - * saved %edi - * &loaded_image - * &loaded_image_proto - * handle <-- 16-byte aligned for call to handle_protocol - */ - - movl 12(%ebp), %eax // sys_table - movl ST32_boottime(%eax), %eax // sys_table->boottime - call *BS32_handle_protocol(%eax) // sys_table->boottime->handle_protocol - addl $12, %esp // restore argument space - testl %eax, %eax - jnz 2f - - movl 8(%ebp), %ecx // image_handle - movl 12(%ebp), %edx // sys_table - movl -4(%ebp), %esi // loaded_image - movl LI32_image_base(%esi), %esi // loaded_image->image_base - leal (startup_32 - 1b)(%ebx), %ebp // runtime address of startup_32 - /* - * We need to set the image_offset variable here since startup_32() will - * use it before we get to the 64-bit efi_pe_entry() in C code. - */ - subl %esi, %ebp // calculate image_offset - movl %ebp, (image_offset - 1b)(%ebx) // save image_offset - xorl %esi, %esi - jmp efi32_entry // pass %ecx, %edx, %esi - // no other registers remain live - -2: popl %edi // restore callee-save registers - popl %ebx - leave - RET -SYM_FUNC_END(efi32_pe_entry) - - .section ".rodata" - /* EFI loaded image protocol GUID */ - .balign 4 -SYM_DATA_START_LOCAL(loaded_image_proto) - .long 0x5b1b31a1 - .word 0x9562, 0x11d2 - .byte 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b -SYM_DATA_END(loaded_image_proto) - - .data - .balign 8 -SYM_DATA_START_LOCAL(efi32_boot_gdt) - .word 0 - .quad 0 -SYM_DATA_END(efi32_boot_gdt) - -SYM_DATA_START_LOCAL(efi32_boot_idt) - .word 0 - .quad 0 -SYM_DATA_END(efi32_boot_idt) - -SYM_DATA_LOCAL(efi32_boot_cs, .word 0) -SYM_DATA_LOCAL(efi32_boot_ds, .word 0) -SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0) -SYM_DATA(efi_is64, .byte 1) diff --git a/arch/x86/boot/compressed/error.c b/arch/x86/boot/compressed/error.c index c881878e56d3..19a8251de506 100644 --- a/arch/x86/boot/compressed/error.c +++ b/arch/x86/boot/compressed/error.c @@ -7,7 +7,7 @@ #include "misc.h" #include "error.h" -void warn(char *m) +void warn(const char *m) { error_putstr("\n\n"); error_putstr(m); @@ -22,3 +22,22 @@ void error(char *m) while (1) asm("hlt"); } + +/* EFI libstub provides vsnprintf() */ +#ifdef CONFIG_EFI_STUB +void panic(const char *fmt, ...) +{ + static char buf[1024]; + va_list args; + int len; + + va_start(args, fmt); + len = vsnprintf(buf, sizeof(buf), fmt, args); + va_end(args); + + if (len && buf[len - 1] == '\n') + buf[len - 1] = '\0'; + + error(buf); +} +#endif diff --git a/arch/x86/boot/compressed/error.h b/arch/x86/boot/compressed/error.h index 1de5821184f1..31f9e080d61a 100644 --- a/arch/x86/boot/compressed/error.h +++ b/arch/x86/boot/compressed/error.h @@ -4,7 +4,8 @@ #include <linux/compiler.h> -void warn(char *m); +void warn(const char *m); void error(char *m) __noreturn; +void panic(const char *fmt, ...) __noreturn __cold; #endif /* BOOT_COMPRESSED_ERROR_H */ diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 6589ddd4cfaf..1cfe9802a42f 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -84,19 +84,6 @@ SYM_FUNC_START(startup_32) #ifdef CONFIG_RELOCATABLE leal startup_32@GOTOFF(%edx), %ebx - -#ifdef CONFIG_EFI_STUB -/* - * If we were loaded via the EFI LoadImage service, startup_32() will be at an - * offset to the start of the space allocated for the image. efi_pe_entry() will - * set up image_offset to tell us where the image actually starts, so that we - * can use the full available buffer. - * image_offset = startup_32 - image_base - * Otherwise image_offset will be zero and has no effect on the calculations. - */ - subl image_offset@GOTOFF(%edx), %ebx -#endif - movl BP_kernel_alignment(%esi), %eax decl %eax addl %eax, %ebx @@ -150,17 +137,6 @@ SYM_FUNC_START(startup_32) jmp *%eax SYM_FUNC_END(startup_32) -#ifdef CONFIG_EFI_STUB -SYM_FUNC_START(efi32_stub_entry) - add $0x4, %esp - movl 8(%esp), %esi /* save boot_params pointer */ - call efi_main - /* efi_main returns the possibly relocated address of startup_32 */ - jmp *%eax -SYM_FUNC_END(efi32_stub_entry) -SYM_FUNC_ALIAS(efi_stub_entry, efi32_stub_entry) -#endif - .text SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) @@ -179,15 +155,9 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) */ /* push arguments for extract_kernel: */ - pushl output_len@GOTOFF(%ebx) /* decompressed length, end of relocs */ pushl %ebp /* output address */ - pushl input_len@GOTOFF(%ebx) /* input_len */ - leal input_data@GOTOFF(%ebx), %eax - pushl %eax /* input_data */ - 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 /* @@ -213,8 +183,6 @@ SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) */ .bss .balign 4 -boot_heap: - .fill BOOT_HEAP_SIZE, 1, 0 boot_stack: .fill BOOT_STACK_SIZE, 1, 0 boot_stack_end: diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index a75712991df3..d9dab940ff62 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -35,7 +35,6 @@ #include <asm/bootparam.h> #include <asm/desc_defs.h> #include <asm/trapnr.h> -#include "pgtable.h" /* * Fix alignment at 16 bytes. Following CONFIG_FUNCTION_ALIGNMENT will result @@ -146,19 +145,6 @@ SYM_FUNC_START(startup_32) #ifdef CONFIG_RELOCATABLE movl %ebp, %ebx - -#ifdef CONFIG_EFI_STUB -/* - * If we were loaded via the EFI LoadImage service, startup_32 will be at an - * offset to the start of the space allocated for the image. efi_pe_entry will - * set up image_offset to tell us where the image actually starts, so that we - * can use the full available buffer. - * image_offset = startup_32 - image_base - * Otherwise image_offset will be zero and has no effect on the calculations. - */ - subl rva(image_offset)(%ebp), %ebx -#endif - movl BP_kernel_alignment(%esi), %eax decl %eax addl %eax, %ebx @@ -276,13 +262,6 @@ SYM_FUNC_START(startup_32) * used to perform that far jump. */ leal rva(startup_64)(%ebp), %eax -#ifdef CONFIG_EFI_MIXED - cmpb $1, rva(efi_is64)(%ebp) - je 1f - leal rva(startup_64_mixed_mode)(%ebp), %eax -1: -#endif - pushl $__KERNEL_CS pushl %eax @@ -294,17 +273,6 @@ SYM_FUNC_START(startup_32) lret SYM_FUNC_END(startup_32) -#if IS_ENABLED(CONFIG_EFI_MIXED) && IS_ENABLED(CONFIG_EFI_HANDOVER_PROTOCOL) - .org 0x190 -SYM_FUNC_START(efi32_stub_entry) - add $0x4, %esp /* Discard return address */ - popl %ecx - popl %edx - popl %esi - jmp efi32_entry -SYM_FUNC_END(efi32_stub_entry) -#endif - .code64 .org 0x200 SYM_CODE_START(startup_64) @@ -346,20 +314,6 @@ SYM_CODE_START(startup_64) /* Start with the delta to where the kernel will run at. */ #ifdef CONFIG_RELOCATABLE leaq startup_32(%rip) /* - $startup_32 */, %rbp - -#ifdef CONFIG_EFI_STUB -/* - * If we were loaded via the EFI LoadImage service, startup_32 will be at an - * offset to the start of the space allocated for the image. efi_pe_entry will - * set up image_offset to tell us where the image actually starts, so that we - * can use the full available buffer. - * image_offset = startup_32 - image_base - * Otherwise image_offset will be zero and has no effect on the calculations. - */ - movl image_offset(%rip), %eax - subq %rax, %rbp -#endif - movl BP_kernel_alignment(%rsi), %eax decl %eax addq %rax, %rbp @@ -398,10 +352,6 @@ SYM_CODE_START(startup_64) * For the trampoline, we need the top page table to reside in lower * memory as we don't have a way to load 64-bit values into CR3 in * 32-bit mode. - * - * We go though the trampoline even if we don't have to: if we're - * already in a desired paging mode. This way the trampoline code gets - * tested on every boot. */ /* Make sure we have GDT with 32-bit code segment */ @@ -416,10 +366,14 @@ SYM_CODE_START(startup_64) lretq .Lon_kernel_cs: + /* + * RSI holds a pointer to a boot_params structure provided by the + * loader, and this needs to be preserved across C function calls. So + * move it into a callee saved register. + */ + movq %rsi, %r15 - pushq %rsi call load_stage1_idt - popq %rsi #ifdef CONFIG_AMD_MEM_ENCRYPT /* @@ -430,63 +384,29 @@ SYM_CODE_START(startup_64) * CPUID instructions being issued, so go ahead and do that now via * sev_enable(), which will also handle the rest of the SEV-related * detection/setup to ensure that has been done in advance of any dependent - * code. + * code. Pass the boot_params pointer as the first argument. */ - pushq %rsi - movq %rsi, %rdi /* real mode address */ + movq %r15, %rdi call sev_enable - popq %rsi #endif - /* - * paging_prepare() sets up the trampoline and checks if we need to - * enable 5-level paging. - * - * paging_prepare() returns a two-quadword structure which lands - * into RDX:RAX: - * - Address of the trampoline is returned in RAX. - * - Non zero RDX means trampoline needs to enable 5-level - * paging. - * - * RSI holds real mode data and needs to be preserved across - * this function call. - */ - pushq %rsi - movq %rsi, %rdi /* real mode address */ - call paging_prepare - popq %rsi - - /* Save the trampoline address in RCX */ - movq %rax, %rcx - - /* - * Load the address of trampoline_return() into RDI. - * It will be used by the trampoline to return to the main code. - */ - leaq trampoline_return(%rip), %rdi - - /* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */ - pushq $__KERNEL32_CS - leaq TRAMPOLINE_32BIT_CODE_OFFSET(%rax), %rax - pushq %rax - lretq -trampoline_return: - /* Restore the stack, the 32-bit trampoline uses its own stack */ - leaq rva(boot_stack_end)(%rbx), %rsp + /* Preserve only the CR4 bits that must be preserved, and clear the rest */ + movq %cr4, %rax + andl $(X86_CR4_PAE | X86_CR4_MCE | X86_CR4_LA57), %eax + movq %rax, %cr4 /* - * cleanup_trampoline() would restore trampoline memory. + * configure_5level_paging() updates the number of paging levels using + * a trampoline in 32-bit addressable memory if the current number does + * not match the desired number. * - * RDI is address of the page table to use instead of page table - * in trampoline memory (if required). - * - * RSI holds real mode data and needs to be preserved across - * this function call. + * Pass the boot_params pointer as the first argument. The second + * argument is the relocated address of the page table to use instead + * of the page table in trampoline memory (if required). */ - pushq %rsi - leaq rva(top_pgtable)(%rbx), %rdi - call cleanup_trampoline - popq %rsi + movq %r15, %rdi + leaq rva(top_pgtable)(%rbx), %rsi + call configure_5level_paging /* Zero EFLAGS */ pushq $0 @@ -496,7 +416,6 @@ trampoline_return: * Copy the compressed kernel to the end of our buffer * where decompression in place becomes safe. */ - pushq %rsi leaq (_bss-8)(%rip), %rsi leaq rva(_bss-8)(%rbx), %rdi movl $(_bss - startup_32), %ecx @@ -504,7 +423,6 @@ trampoline_return: std rep movsq cld - popq %rsi /* * The GDT may get overwritten either during the copy we just did or @@ -523,21 +441,6 @@ trampoline_return: jmp *%rax SYM_CODE_END(startup_64) -#ifdef CONFIG_EFI_STUB -#ifdef CONFIG_EFI_HANDOVER_PROTOCOL - .org 0x390 -#endif -SYM_FUNC_START(efi64_stub_entry) - and $~0xf, %rsp /* realign the stack */ - movq %rdx, %rbx /* save boot_params pointer */ - call efi_main - movq %rbx,%rsi - leaq rva(startup_64)(%rax), %rax - jmp *%rax -SYM_FUNC_END(efi64_stub_entry) -SYM_FUNC_ALIAS(efi_stub_entry, efi64_stub_entry) -#endif - .text SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) @@ -551,137 +454,28 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) shrq $3, %rcx rep stosq - pushq %rsi call load_stage2_idt /* Pass boot_params to initialize_identity_maps() */ - movq (%rsp), %rdi + movq %r15, %rdi call initialize_identity_maps - popq %rsi /* * Do the extraction, and jump to the new kernel.. */ - pushq %rsi /* Save the real mode argument */ - movq %rsi, %rdi /* real mode address */ - leaq boot_heap(%rip), %rsi /* malloc area for uncompression */ - leaq input_data(%rip), %rdx /* input_data */ - 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 */ - popq %rsi + /* pass struct boot_params pointer and output target address */ + movq %r15, %rdi + movq %rbp, %rsi + call extract_kernel /* returns kernel entry point in %rax */ /* * Jump to the decompressed kernel. */ + movq %r15, %rsi jmp *%rax SYM_FUNC_END(.Lrelocated) .code32 -/* - * This is the 32-bit trampoline that will be copied over to low memory. - * - * RDI contains the return address (might be above 4G). - * ECX contains the base address of the trampoline memory. - * Non zero RDX means trampoline needs to enable 5-level paging. - */ -SYM_CODE_START(trampoline_32bit_src) - /* Set up data and stack segments */ - movl $__KERNEL_DS, %eax - movl %eax, %ds - movl %eax, %ss - - /* Set up new stack */ - leal TRAMPOLINE_32BIT_STACK_END(%ecx), %esp - - /* Disable paging */ - movl %cr0, %eax - btrl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - - /* Check what paging mode we want to be in after the trampoline */ - testl %edx, %edx - jz 1f - - /* We want 5-level paging: don't touch CR3 if it already points to 5-level page tables */ - movl %cr4, %eax - testl $X86_CR4_LA57, %eax - jnz 3f - jmp 2f -1: - /* We want 4-level paging: don't touch CR3 if it already points to 4-level page tables */ - movl %cr4, %eax - testl $X86_CR4_LA57, %eax - jz 3f -2: - /* Point CR3 to the trampoline's new top level page table */ - leal TRAMPOLINE_32BIT_PGTABLE_OFFSET(%ecx), %eax - movl %eax, %cr3 -3: - /* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */ - pushl %ecx - pushl %edx - movl $MSR_EFER, %ecx - rdmsr - btsl $_EFER_LME, %eax - /* Avoid writing EFER if no change was made (for TDX guest) */ - jc 1f - wrmsr -1: popl %edx - popl %ecx - -#ifdef CONFIG_X86_MCE - /* - * Preserve CR4.MCE if the kernel will enable #MC support. - * Clearing MCE may fault in some environments (that also force #MC - * support). Any machine check that occurs before #MC support is fully - * configured will crash the system regardless of the CR4.MCE value set - * here. - */ - movl %cr4, %eax - andl $X86_CR4_MCE, %eax -#else - movl $0, %eax -#endif - - /* Enable PAE and LA57 (if required) paging modes */ - orl $X86_CR4_PAE, %eax - testl %edx, %edx - jz 1f - orl $X86_CR4_LA57, %eax -1: - movl %eax, %cr4 - - /* Calculate address of paging_enabled() once we are executing in the trampoline */ - leal .Lpaging_enabled - trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_OFFSET(%ecx), %eax - - /* Prepare the stack for far return to Long Mode */ - pushl $__KERNEL_CS - pushl %eax - - /* Enable paging again. */ - movl %cr0, %eax - btsl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - - lret -SYM_CODE_END(trampoline_32bit_src) - - .code64 -SYM_FUNC_START_LOCAL_NOALIGN(.Lpaging_enabled) - /* Return from the trampoline */ - jmp *%rdi -SYM_FUNC_END(.Lpaging_enabled) - - /* - * The trampoline code has a size limit. - * Make sure we fail to compile if the trampoline code grows - * beyond TRAMPOLINE_32BIT_CODE_SIZE bytes. - */ - .org trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE - - .code32 SYM_FUNC_START_LOCAL_NOALIGN(.Lno_longmode) /* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */ 1: @@ -726,8 +520,6 @@ SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end) */ .bss .balign 4 -SYM_DATA_LOCAL(boot_heap, .fill BOOT_HEAP_SIZE, 1, 0) - SYM_DATA_START_LOCAL(boot_stack) .fill BOOT_STACK_SIZE, 1, 0 .balign 16 diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 321a5011042d..dfb9c2deb77c 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -8,16 +8,8 @@ * Copyright (C) 2016 Kees Cook */ -/* - * Since we're dealing with identity mappings, physical and virtual - * addresses are the same, so override these defines which are ultimately - * used by the headers in misc.h. - */ -#define __pa(x) ((unsigned long)(x)) -#define __va(x) ((void *)((unsigned long)(x))) - -/* No PAGE_TABLE_ISOLATION support needed either: */ -#undef CONFIG_PAGE_TABLE_ISOLATION +/* No MITIGATION_PAGE_TABLE_ISOLATION support needed either: */ +#undef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION #include "error.h" #include "misc.h" @@ -67,6 +59,14 @@ static void *alloc_pgt_page(void *context) return NULL; } + /* Consumed more tables than expected? */ + if (pages->pgt_buf_offset == BOOT_PGT_SIZE_WARN) { + debug_putstr("pgt_buf running low in " __FILE__ "\n"); + debug_putstr("Need to raise BOOT_PGT_SIZE?\n"); + debug_putaddr(pages->pgt_buf_offset); + debug_putaddr(pages->pgt_buf_size); + } + entry = pages->pgt_buf + pages->pgt_buf_offset; pages->pgt_buf_offset += PAGE_SIZE; @@ -159,8 +159,9 @@ void initialize_identity_maps(void *rmode) * or does not touch all the pages covering them. */ kernel_add_identity_map((unsigned long)_head, (unsigned long)_end); - boot_params = rmode; - kernel_add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1)); + boot_params_ptr = rmode; + kernel_add_identity_map((unsigned long)boot_params_ptr, + (unsigned long)(boot_params_ptr + 1)); cmdline = get_cmd_line_ptr(); kernel_add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); @@ -168,7 +169,7 @@ void initialize_identity_maps(void *rmode) * Also map the setup_data entries passed via boot_params in case they * need to be accessed by uncompressed kernel via the identity mapping. */ - sd = (struct setup_data *)boot_params->hdr.setup_data; + sd = (struct setup_data *)boot_params_ptr->hdr.setup_data; while (sd) { unsigned long sd_addr = (unsigned long)sd; @@ -283,7 +284,7 @@ static int set_clr_page_flags(struct x86_mapping_info *info, pudp = pud_offset(p4dp, address); pmdp = pmd_offset(pudp, address); - if (pmd_large(*pmdp)) + if (pmd_leaf(*pmdp)) ptep = split_large_pmd(info, pmdp, address); else ptep = pte_offset_kernel(pmdp, address); @@ -385,3 +386,8 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) */ kernel_add_identity_map(address, end); } + +void do_boot_nmi_trap(struct pt_regs *regs, unsigned long error_code) +{ + spurious_nmi_count++; +} diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 6debb816e83d..d100284bbef4 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -61,9 +61,17 @@ void load_stage2_idt(void) boot_idt_desc.address = (unsigned long)boot_idt; set_idt_entry(X86_TRAP_PF, boot_page_fault); + set_idt_entry(X86_TRAP_NMI, boot_nmi_trap); #ifdef CONFIG_AMD_MEM_ENCRYPT - set_idt_entry(X86_TRAP_VC, boot_stage2_vc); + /* + * Clear the second stage #VC handler in case guest types + * needing #VC have not been detected. + */ + if (sev_status & BIT(1)) + set_idt_entry(X86_TRAP_VC, boot_stage2_vc); + else + set_idt_entry(X86_TRAP_VC, NULL); #endif load_boot_idt(&boot_idt_desc); diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S index 22890e199f5b..4d03c8562f63 100644 --- a/arch/x86/boot/compressed/idt_handlers_64.S +++ b/arch/x86/boot/compressed/idt_handlers_64.S @@ -70,6 +70,7 @@ SYM_FUNC_END(\name) .code64 EXCEPTION_HANDLER boot_page_fault do_boot_page_fault error_code=1 +EXCEPTION_HANDLER boot_nmi_trap do_boot_nmi_trap error_code=0 #ifdef CONFIG_AMD_MEM_ENCRYPT EXCEPTION_HANDLER boot_stage1_vc do_vc_no_ghcb error_code=1 diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 454757fbdfe5..3b0948ad449f 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -25,10 +25,6 @@ #include "efi.h" #include <generated/compile.h> -#include <linux/module.h> -#include <linux/uts.h> -#include <linux/utsname.h> -#include <linux/ctype.h> #include <generated/utsversion.h> #include <generated/utsrelease.h> @@ -63,7 +59,7 @@ static unsigned long get_boot_seed(void) unsigned long hash = 0; hash = rotate_xor(hash, build_str, sizeof(build_str)); - hash = rotate_xor(hash, boot_params, sizeof(*boot_params)); + hash = rotate_xor(hash, boot_params_ptr, sizeof(*boot_params_ptr)); return hash; } @@ -119,13 +115,8 @@ char *skip_spaces(const char *str) #include "../../../../lib/ctype.c" #include "../../../../lib/cmdline.c" -enum parse_mode { - PARSE_MEMMAP, - PARSE_EFI, -}; - static int -parse_memmap(char *p, u64 *start, u64 *size, enum parse_mode mode) +parse_memmap(char *p, u64 *start, u64 *size) { char *oldp; @@ -148,29 +139,11 @@ parse_memmap(char *p, u64 *start, u64 *size, enum parse_mode mode) *start = memparse(p + 1, &p); return 0; case '@': - if (mode == PARSE_MEMMAP) { - /* - * memmap=nn@ss specifies usable region, should - * be skipped - */ - *size = 0; - } else { - u64 flags; - - /* - * efi_fake_mem=nn@ss:attr the attr specifies - * flags that might imply a soft-reservation. - */ - *start = memparse(p + 1, &p); - if (p && *p == ':') { - p++; - if (kstrtoull(p, 0, &flags) < 0) - *size = 0; - else if (flags & EFI_MEMORY_SP) - return 0; - } - *size = 0; - } + /* + * memmap=nn@ss specifies usable region, should + * be skipped + */ + *size = 0; fallthrough; default: /* @@ -185,7 +158,7 @@ parse_memmap(char *p, u64 *start, u64 *size, enum parse_mode mode) return -EINVAL; } -static void mem_avoid_memmap(enum parse_mode mode, char *str) +static void mem_avoid_memmap(char *str) { static int i; @@ -200,7 +173,7 @@ static void mem_avoid_memmap(enum parse_mode mode, char *str) if (k) *k++ = 0; - rc = parse_memmap(str, &start, &size, mode); + rc = parse_memmap(str, &start, &size); if (rc < 0) break; str = k; @@ -281,7 +254,7 @@ static void handle_mem_options(void) break; if (!strcmp(param, "memmap")) { - mem_avoid_memmap(PARSE_MEMMAP, val); + mem_avoid_memmap(val); } else if (IS_ENABLED(CONFIG_X86_64) && strstr(param, "hugepages")) { parse_gb_huge_pages(param, val); } else if (!strcmp(param, "mem")) { @@ -295,8 +268,6 @@ static void handle_mem_options(void) if (mem_size < mem_limit) mem_limit = mem_size; - } else if (!strcmp(param, "efi_fake_mem")) { - mem_avoid_memmap(PARSE_EFI, val); } } @@ -383,7 +354,7 @@ static void handle_mem_options(void) static void mem_avoid_init(unsigned long input, unsigned long input_size, unsigned long output) { - unsigned long init_size = boot_params->hdr.init_size; + unsigned long init_size = boot_params_ptr->hdr.init_size; u64 initrd_start, initrd_size; unsigned long cmd_line, cmd_line_size; @@ -395,10 +366,10 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input; /* Avoid initrd. */ - initrd_start = (u64)boot_params->ext_ramdisk_image << 32; - initrd_start |= boot_params->hdr.ramdisk_image; - initrd_size = (u64)boot_params->ext_ramdisk_size << 32; - initrd_size |= boot_params->hdr.ramdisk_size; + initrd_start = (u64)boot_params_ptr->ext_ramdisk_image << 32; + initrd_start |= boot_params_ptr->hdr.ramdisk_image; + initrd_size = (u64)boot_params_ptr->ext_ramdisk_size << 32; + initrd_size |= boot_params_ptr->hdr.ramdisk_size; mem_avoid[MEM_AVOID_INITRD].start = initrd_start; mem_avoid[MEM_AVOID_INITRD].size = initrd_size; /* No need to set mapping for initrd, it will be handled in VO. */ @@ -413,8 +384,8 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, } /* Avoid boot parameters. */ - mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params; - mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params); + mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params_ptr; + mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params_ptr); /* We don't need to set a mapping for setup_data. */ @@ -447,7 +418,7 @@ static bool mem_avoid_overlap(struct mem_vector *img, } /* Avoid all entries in the setup_data linked list. */ - ptr = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data; + ptr = (struct setup_data *)(unsigned long)boot_params_ptr->hdr.setup_data; while (ptr) { struct mem_vector avoid; @@ -672,6 +643,33 @@ static bool process_mem_region(struct mem_vector *region, } #ifdef CONFIG_EFI + +/* + * Only EFI_CONVENTIONAL_MEMORY and EFI_UNACCEPTED_MEMORY (if supported) are + * guaranteed to be free. + * + * Pick free memory more conservatively than the EFI spec allows: according to + * the spec, EFI_BOOT_SERVICES_{CODE|DATA} are also free memory and thus + * available to place the kernel image into, but in practice there's firmware + * where using that memory leads to crashes. Buggy vendor EFI code registers + * for an event that triggers on SetVirtualAddressMap(). The handler assumes + * that EFI_BOOT_SERVICES_DATA memory has not been touched by loader yet, which + * is probably true for Windows. + * + * Preserve EFI_BOOT_SERVICES_* regions until after SetVirtualAddressMap(). + */ +static inline bool memory_type_is_free(efi_memory_desc_t *md) +{ + if (md->type == EFI_CONVENTIONAL_MEMORY) + return true; + + if (IS_ENABLED(CONFIG_UNACCEPTED_MEMORY) && + md->type == EFI_UNACCEPTED_MEMORY) + return true; + + return false; +} + /* * Returns true if we processed the EFI memmap, which we prefer over the E820 * table if it is available. @@ -679,7 +677,7 @@ static bool process_mem_region(struct mem_vector *region, static bool process_efi_entries(unsigned long minimum, unsigned long image_size) { - struct efi_info *e = &boot_params->efi_info; + struct efi_info *e = &boot_params_ptr->efi_info; bool efi_mirror_found = false; struct mem_vector region; efi_memory_desc_t *md; @@ -716,18 +714,7 @@ process_efi_entries(unsigned long minimum, unsigned long image_size) for (i = 0; i < nr_desc; i++) { md = efi_early_memdesc_ptr(pmap, e->efi_memdesc_size, i); - /* - * Here we are more conservative in picking free memory than - * the EFI spec allows: - * - * According to the spec, EFI_BOOT_SERVICES_{CODE|DATA} are also - * free memory and thus available to place the kernel image into, - * but in practice there's firmware where using that memory leads - * to crashes. - * - * Only EFI_CONVENTIONAL_MEMORY is guaranteed to be free. - */ - if (md->type != EFI_CONVENTIONAL_MEMORY) + if (!memory_type_is_free(md)) continue; if (efi_soft_reserve_enabled() && @@ -761,8 +748,8 @@ static void process_e820_entries(unsigned long minimum, struct boot_e820_entry *entry; /* Verify potential e820 positions, appending to slots list. */ - for (i = 0; i < boot_params->e820_entries; i++) { - entry = &boot_params->e820_table[i]; + for (i = 0; i < boot_params_ptr->e820_entries; i++) { + entry = &boot_params_ptr->e820_table[i]; /* Skip non-RAM entries. */ if (entry->type != E820_TYPE_RAM) continue; @@ -773,6 +760,49 @@ static void process_e820_entries(unsigned long minimum, } } +/* + * If KHO is active, only process its scratch areas to ensure we are not + * stepping onto preserved memory. + */ +static bool process_kho_entries(unsigned long minimum, unsigned long image_size) +{ + struct kho_scratch *kho_scratch; + struct setup_data *ptr; + struct kho_data *kho; + int i, nr_areas = 0; + + if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER)) + return false; + + ptr = (struct setup_data *)(unsigned long)boot_params_ptr->hdr.setup_data; + while (ptr) { + if (ptr->type == SETUP_KEXEC_KHO) { + kho = (struct kho_data *)(unsigned long)ptr->data; + kho_scratch = (void *)(unsigned long)kho->scratch_addr; + nr_areas = kho->scratch_size / sizeof(*kho_scratch); + break; + } + + ptr = (struct setup_data *)(unsigned long)ptr->next; + } + + if (!nr_areas) + return false; + + for (i = 0; i < nr_areas; i++) { + struct kho_scratch *area = &kho_scratch[i]; + struct mem_vector region = { + .start = area->addr, + .size = area->size, + }; + + if (process_mem_region(®ion, minimum, image_size)) + break; + } + + return true; +} + static unsigned long find_random_phys_addr(unsigned long minimum, unsigned long image_size) { @@ -788,7 +818,12 @@ static unsigned long find_random_phys_addr(unsigned long minimum, return 0; } - if (!process_efi_entries(minimum, image_size)) + /* + * During kexec handover only process KHO scratch areas that are known + * not to contain any data that must be preserved. + */ + if (!process_kho_entries(minimum, image_size) && + !process_efi_entries(minimum, image_size)) process_e820_entries(minimum, image_size); phys_addr = slots_fetch_random(); @@ -836,7 +871,7 @@ void choose_random_location(unsigned long input, return; } - boot_params->hdr.loadflags |= KASLR_FLAG; + boot_params_ptr->hdr.loadflags |= KASLR_FLAG; if (IS_ENABLED(CONFIG_X86_32)) mem_limit = KERNEL_IMAGE_SIZE; diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c new file mode 100644 index 000000000000..0e9f84ab4bdc --- /dev/null +++ b/arch/x86/boot/compressed/mem.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "error.h" +#include "misc.h" +#include "tdx.h" +#include "sev.h" +#include <asm/shared/tdx.h> + +/* + * accept_memory() and process_unaccepted_memory() called from EFI stub which + * runs before decompressor and its early_tdx_detect(). + * + * Enumerate TDX directly from the early users. + */ +static bool early_is_tdx_guest(void) +{ + static bool once; + static bool is_tdx; + + if (!IS_ENABLED(CONFIG_INTEL_TDX_GUEST)) + return false; + + if (!once) { + u32 eax, sig[3]; + + cpuid_count(TDX_CPUID_LEAF_ID, 0, &eax, + &sig[0], &sig[2], &sig[1]); + is_tdx = !memcmp(TDX_IDENT, sig, sizeof(sig)); + once = true; + } + + return is_tdx; +} + +void arch_accept_memory(phys_addr_t start, phys_addr_t end) +{ + /* Platform-specific memory-acceptance call goes here */ + if (early_is_tdx_guest()) { + if (!tdx_accept_memory(start, end)) + panic("TDX: Failed to accept memory\n"); + } else if (early_is_sevsnp_guest()) { + snp_accept_memory(start, end); + } else { + error("Cannot accept memory: unknown platform\n"); + } +} + +bool init_unaccepted_memory(void) +{ + guid_t guid = LINUX_EFI_UNACCEPTED_MEM_TABLE_GUID; + struct efi_unaccepted_memory *table; + unsigned long cfg_table_pa; + unsigned int cfg_table_len; + enum efi_type et; + int ret; + + et = efi_get_type(boot_params_ptr); + if (et == EFI_TYPE_NONE) + return false; + + ret = efi_get_conf_table(boot_params_ptr, &cfg_table_pa, &cfg_table_len); + if (ret) { + warn("EFI config table not found."); + return false; + } + + table = (void *)efi_find_vendor_table(boot_params_ptr, cfg_table_pa, + cfg_table_len, guid); + if (!table) + return false; + + if (table->version != 1) + error("Unknown version of unaccepted memory table\n"); + + /* + * In many cases unaccepted_table is already set by EFI stub, but it + * has to be initialized again to cover cases when the table is not + * allocated by EFI stub or EFI stub copied the kernel image with + * efi_relocate_kernel() before the variable is set. + * + * It must be initialized before the first usage of accept_memory(). + */ + unaccepted_table = table; + + return true; +} diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index cf690d8712f4..0f41ca0e52c0 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -14,7 +14,6 @@ #include "misc.h" #include "error.h" -#include "pgtable.h" #include "../string.h" #include "../voffset.h" #include <asm/bootparam_utils.h> @@ -46,12 +45,13 @@ void *memmove(void *dest, const void *src, size_t n); /* * This is set up by the setup-routine at boot-time */ -struct boot_params *boot_params; +struct boot_params *boot_params_ptr; struct port_io_ops pio_ops; memptr free_mem_ptr; memptr free_mem_end_ptr; +int spurious_nmi_count; static char *vidmem; static int vidport; @@ -132,8 +132,8 @@ void __putstr(const char *s) if (lines == 0 || cols == 0) return; - x = boot_params->screen_info.orig_x; - y = boot_params->screen_info.orig_y; + x = boot_params_ptr->screen_info.orig_x; + y = boot_params_ptr->screen_info.orig_y; while ((c = *s++) != '\0') { if (c == '\n') { @@ -154,8 +154,8 @@ void __putstr(const char *s) } } - boot_params->screen_info.orig_x = x; - boot_params->screen_info.orig_y = y; + boot_params_ptr->screen_info.orig_x = x; + boot_params_ptr->screen_info.orig_y = y; pos = (x + cols * y) * 2; /* Update cursor position */ outb(14, vidport); @@ -164,21 +164,34 @@ void __putstr(const char *s) outb(0xff & (pos >> 1), vidport+1); } -void __puthex(unsigned long value) +static noinline void __putnum(unsigned long value, unsigned int base, + int mindig) { - char alpha[2] = "0"; - int bits; + char buf[8*sizeof(value)+1]; + char *p; - for (bits = sizeof(value) * 8 - 4; bits >= 0; bits -= 4) { - unsigned long digit = (value >> bits) & 0xf; + p = buf + sizeof(buf); + *--p = '\0'; - if (digit < 0xA) - alpha[0] = '0' + digit; - else - alpha[0] = 'a' + (digit - 0xA); + while (mindig-- > 0 || value) { + unsigned char digit = value % base; + digit += (digit >= 10) ? ('a'-10) : '0'; + *--p = digit; - __putstr(alpha); + value /= base; } + + __putstr(p); +} + +void __puthex(unsigned long value) +{ + __putnum(value, 16, sizeof(value)*2); +} + +void __putdec(unsigned long value) +{ + __putnum(value, 10, 1); } #ifdef CONFIG_X86_NEED_RELOCS @@ -221,7 +234,7 @@ static void handle_relocations(void *output, unsigned long output_len, /* * Process relocations: 32 bit relocations first then 64 bit after. - * Three sets of binary relocations are added to the end of the kernel + * Two sets of binary relocations are added to the end of the kernel * before compression. Each relocation table entry is the kernel * address of the location which needs to be updated stored as a * 32-bit value which is sign extended to 64 bits. @@ -231,8 +244,6 @@ static void handle_relocations(void *output, unsigned long output_len, * kernel bits... * 0 - zero terminator for 64 bit relocations * 64 bit relocation repeated - * 0 - zero terminator for inverse 32 bit relocations - * 32 bit inverse relocation repeated * 0 - zero terminator for 32 bit relocations * 32 bit relocation repeated * @@ -249,16 +260,6 @@ static void handle_relocations(void *output, unsigned long output_len, *(uint32_t *)ptr += delta; } #ifdef CONFIG_X86_64 - while (*--reloc) { - long extended = *reloc; - extended += map; - - ptr = (unsigned long)extended; - if (ptr < min_addr || ptr > max_addr) - error("inverse 32-bit relocation outside of kernel!\n"); - - *(int32_t *)ptr -= delta; - } for (reloc--; *reloc; reloc--) { long extended = *reloc; extended += map; @@ -277,7 +278,7 @@ 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 +294,8 @@ 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 +327,64 @@ static void parse_elf(void *output) } free(phdrs); + + return ehdr.e_entry - LOAD_PHYSICAL_ADDR; +} + +const unsigned long kernel_text_size = VO___start_rodata - VO__text; +const unsigned long kernel_inittext_offset = VO__sinittext - VO__text; +const unsigned long kernel_inittext_size = VO___inittext_end - VO__sinittext; +const unsigned long kernel_total_size = VO__end - VO__text; + +static u8 boot_heap[BOOT_HEAP_SIZE] __aligned(4); + +extern unsigned char input_data[]; +extern unsigned int input_len, output_len; + +unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, + void (*error)(char *x)) +{ + unsigned long entry; + + if (!free_mem_ptr) { + free_mem_ptr = (unsigned long)boot_heap; + free_mem_end_ptr = (unsigned long)boot_heap + sizeof(boot_heap); + } + + if (__decompress(input_data, input_len, NULL, NULL, outbuf, output_len, + NULL, error) < 0) + return ULONG_MAX; + + entry = parse_elf(outbuf); + handle_relocations(outbuf, output_len, virt_addr); + + return entry; +} + +/* + * Set the memory encryption xloadflag based on the mem_encrypt= command line + * parameter, if provided. + */ +static void parse_mem_encrypt(struct setup_header *hdr) +{ + int on = cmdline_find_option_bool("mem_encrypt=on"); + int off = cmdline_find_option_bool("mem_encrypt=off"); + + if (on > off) + hdr->xloadflags |= XLF_MEM_ENCRYPTION; +} + +static void early_sev_detect(void) +{ + /* + * Accessing video memory causes guest termination because + * the boot stage2 #VC handler of SEV-ES/SNP guests does not + * support MMIO handling and kexec -c adds screen_info to the + * boot parameters passed to the kexec kernel, which causes + * console output to be dumped to both video and serial. + */ + if (sev_status & MSR_AMD64_SEV_ES_ENABLED) + lines = cols = 0; } /* @@ -347,25 +404,24 @@ static void parse_elf(void *output) * |-------uncompressed kernel image---------| * */ -asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, - unsigned char *input_data, - unsigned long input_len, - unsigned char *output, - unsigned long output_len) +asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) { - const unsigned long kernel_total_size = VO__end - VO__text; unsigned long virt_addr = LOAD_PHYSICAL_ADDR; + memptr heap = (memptr)boot_heap; unsigned long needed_size; + size_t entry_offset; /* Retain x86 boot parameters pointer passed from startup_32/64. */ - boot_params = rmode; + boot_params_ptr = rmode; /* Clear flags intended for solely in-kernel use. */ - boot_params->hdr.loadflags &= ~KASLR_FLAG; + boot_params_ptr->hdr.loadflags &= ~KASLR_FLAG; - sanitize_boot_params(boot_params); + parse_mem_encrypt(&boot_params_ptr->hdr); - if (boot_params->screen_info.orig_video_mode == 7) { + sanitize_boot_params(boot_params_ptr); + + if (boot_params_ptr->screen_info.orig_video_mode == 7) { vidmem = (char *) 0xb0000; vidport = 0x3b4; } else { @@ -373,8 +429,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, vidport = 0x3d4; } - lines = boot_params->screen_info.orig_video_lines; - cols = boot_params->screen_info.orig_video_cols; + lines = boot_params_ptr->screen_info.orig_video_lines; + cols = boot_params_ptr->screen_info.orig_video_cols; init_default_io_ops(); @@ -386,6 +442,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, */ early_tdx_detect(); + early_sev_detect(); + console_init(); /* @@ -393,7 +451,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, * so that early debugging output from the RSDP parsing code can be * collected. */ - boot_params->acpi_rsdp_addr = get_rsdp_addr(); + boot_params_ptr->acpi_rsdp_addr = get_rsdp_addr(); debug_putstr("early console in extract_kernel\n"); @@ -411,7 +469,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, * entries. This ensures the full mapped area is usable RAM * and doesn't include any reserved areas. */ - needed_size = max(output_len, kernel_total_size); + needed_size = max_t(unsigned long, output_len, kernel_total_size); #ifdef CONFIG_X86_64 needed_size = ALIGN(needed_size, MIN_KERNEL_ALIGN); #endif @@ -442,7 +500,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, #ifdef CONFIG_X86_64 if (heap > 0x3fffffffffffUL) error("Destination address too large"); - if (virt_addr + max(output_len, kernel_total_size) > KERNEL_IMAGE_SIZE) + if (virt_addr + needed_size > KERNEL_IMAGE_SIZE) error("Destination virtual address is beyond the kernel mapping area"); #else if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff)) @@ -454,19 +512,26 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, #endif debug_putstr("\nDecompressing Linux... "); - __decompress(input_data, input_len, NULL, NULL, output, output_len, - NULL, error); - parse_elf(output); - handle_relocations(output, output_len, virt_addr); - debug_putstr("done.\nBooting the kernel.\n"); + + if (init_unaccepted_memory()) { + debug_putstr("Accepting memory... "); + accept_memory(__pa(output), needed_size); + } + + entry_offset = decompress_kernel(output, virt_addr, error); + + 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; -} + if (spurious_nmi_count) { + error_putstr("Spurious early NMIs ignored: "); + error_putdec(spurious_nmi_count); + error_putstr("\n"); + } -void fortify_panic(const char *name) -{ - error("detected buffer overflow"); + return output + entry_offset; } diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 20118fb7c53b..fd855e32c9b9 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -19,6 +19,15 @@ /* cpu_feature_enabled() cannot be used this early */ #define USE_EARLY_PGTABLE_L5 +/* + * Boot stub deals with identity mappings, physical and virtual addresses are + * the same, so override these defines. + * + * <asm/page.h> will not define them if they are already defined. + */ +#define __pa(x) ((unsigned long)(x)) +#define __va(x) ((void *)((unsigned long)(x))) + #include <linux/linkage.h> #include <linux/screen_info.h> #include <linux/elf.h> @@ -50,13 +59,15 @@ extern char _head[], _end[]; /* misc.c */ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; +extern int spurious_nmi_count; void *malloc(int size); void free(void *where); -extern struct boot_params *boot_params; void __putstr(const char *s); void __puthex(unsigned long value); +void __putdec(unsigned long value); #define error_putstr(__x) __putstr(__x) #define error_puthex(__x) __puthex(__x) +#define error_putdec(__x) __putdec(__x) #ifdef CONFIG_X86_VERBOSE_BOOTUP @@ -125,6 +136,9 @@ static inline void console_init(void) #endif #ifdef CONFIG_AMD_MEM_ENCRYPT +struct es_em_ctxt; +struct insn; + void sev_enable(struct boot_params *bp); void snp_check_features(void); void sev_es_shutdown_ghcb(void); @@ -132,18 +146,12 @@ extern bool sev_es_check_ghcb_fault(unsigned long address); void snp_set_page_private(unsigned long paddr); void snp_set_page_shared(unsigned long paddr); void sev_prep_identity_maps(unsigned long top_level_pgt); + +enum es_result vc_decode_insn(struct es_em_ctxt *ctxt); +bool insn_has_rep_prefix(struct insn *insn); +void sev_insn_decode_init(void); +bool early_setup_ghcb(void); #else -static inline void sev_enable(struct boot_params *bp) -{ - /* - * bp->cc_blob_address should only be set by boot/compressed kernel. - * Initialize it to 0 unconditionally (thus here in this stub too) to - * ensure that uninitialized values from buggy bootloaders aren't - * propagated. - */ - 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) @@ -170,9 +178,7 @@ static inline int count_immovable_mem_regions(void) { return 0; } #endif /* ident_map_64.c */ -#ifdef CONFIG_X86_5LEVEL extern unsigned int __pgtable_l5_enabled, pgdir_shift, ptrs_per_p4d; -#endif extern void kernel_add_identity_map(unsigned long start, unsigned long end); /* Used by PAGE_KERN* macros: */ @@ -190,6 +196,7 @@ static inline void cleanup_exception_handling(void) { } /* IDT Entry Points */ void boot_page_fault(void); +void boot_nmi_trap(void); void boot_stage1_vc(void); void boot_stage2_vc(void); @@ -238,4 +245,14 @@ static inline unsigned long efi_find_vendor_table(struct boot_params *bp, } #endif /* CONFIG_EFI */ +#ifdef CONFIG_UNACCEPTED_MEMORY +bool init_unaccepted_memory(void); +#else +static inline bool init_unaccepted_memory(void) { return false; } +#endif + +/* Defined in EFI stub */ +extern struct efi_unaccepted_memory *unaccepted_table; +void accept_memory(phys_addr_t start, unsigned long size); + #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h deleted file mode 100644 index cc9b2529a086..000000000000 --- a/arch/x86/boot/compressed/pgtable.h +++ /dev/null @@ -1,20 +0,0 @@ -#ifndef BOOT_COMPRESSED_PAGETABLE_H -#define BOOT_COMPRESSED_PAGETABLE_H - -#define TRAMPOLINE_32BIT_SIZE (2 * PAGE_SIZE) - -#define TRAMPOLINE_32BIT_PGTABLE_OFFSET 0 - -#define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE -#define TRAMPOLINE_32BIT_CODE_SIZE 0x80 - -#define TRAMPOLINE_32BIT_STACK_END TRAMPOLINE_32BIT_SIZE - -#ifndef __ASSEMBLER__ - -extern unsigned long *trampoline_32bit; - -extern void trampoline_32bit_src(void *return_ptr); - -#endif /* __ASSEMBLER__ */ -#endif /* BOOT_COMPRESSED_PAGETABLE_H */ diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 2ac12ff4111b..0e89e197e112 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -1,25 +1,20 @@ // SPDX-License-Identifier: GPL-2.0 #include "misc.h" +#include <asm/bootparam.h> +#include <asm/bootparam_utils.h> #include <asm/e820/types.h> +#include <asm/pgtable.h> #include <asm/processor.h> -#include "pgtable.h" #include "../string.h" #include "efi.h" #define BIOS_START_MIN 0x20000U /* 128K, less than this is insane */ #define BIOS_START_MAX 0x9f000U /* 640K, absolute maximum */ -#ifdef CONFIG_X86_5LEVEL /* __pgtable_l5_enabled needs to be in .data to avoid being cleared along with .bss */ unsigned int __section(".data") __pgtable_l5_enabled; unsigned int __section(".data") pgdir_shift = 39; unsigned int __section(".data") ptrs_per_p4d = 1; -#endif - -struct paging_config { - unsigned long trampoline_start; - unsigned long l5_required; -}; /* Buffer to preserve trampoline memory */ static char trampoline_save[TRAMPOLINE_32BIT_SIZE]; @@ -29,11 +24,10 @@ static char trampoline_save[TRAMPOLINE_32BIT_SIZE]; * purposes. * * Avoid putting the pointer into .bss as it will be cleared between - * paging_prepare() and extract_kernel(). + * configure_5level_paging() and extract_kernel(). */ unsigned long *trampoline_32bit __section(".data"); -extern struct boot_params *boot_params; int cmdline_find_option_bool(const char *option); static unsigned long find_trampoline_placement(void) @@ -54,7 +48,7 @@ static unsigned long find_trampoline_placement(void) * * Only look for values in the legacy ROM for non-EFI system. */ - signature = (char *)&boot_params->efi_info.efi_loader_signature; + signature = (char *)&boot_params_ptr->efi_info.efi_loader_signature; if (strncmp(signature, EFI32_LOADER_SIGNATURE, 4) && strncmp(signature, EFI64_LOADER_SIGNATURE, 4)) { ebda_start = *(unsigned short *)0x40e << 4; @@ -70,10 +64,10 @@ static unsigned long find_trampoline_placement(void) bios_start = round_down(bios_start, PAGE_SIZE); /* Find the first usable memory region under bios_start. */ - for (i = boot_params->e820_entries - 1; i >= 0; i--) { + for (i = boot_params_ptr->e820_entries - 1; i >= 0; i--) { unsigned long new = bios_start; - entry = &boot_params->e820_table[i]; + entry = &boot_params_ptr->e820_table[i]; /* Skip all entries above bios_start. */ if (bios_start <= entry->addr) @@ -106,35 +100,42 @@ static unsigned long find_trampoline_placement(void) return bios_start - TRAMPOLINE_32BIT_SIZE; } -struct paging_config paging_prepare(void *rmode) +asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable) { - struct paging_config paging_config = {}; + void (*toggle_la57)(void *cr3); + bool l5_required = false; /* Initialize boot_params. Required for cmdline_find_option_bool(). */ - boot_params = rmode; + sanitize_boot_params(bp); + boot_params_ptr = bp; /* * Check if LA57 is desired and supported. * * There are several parts to the check: - * - if the kernel supports 5-level paging: CONFIG_X86_5LEVEL=y * - if user asked to disable 5-level paging: no5lvl in cmdline * - if the machine supports 5-level paging: * + CPUID leaf 7 is supported * + the leaf has the feature bit set - * - * That's substitute for boot_cpu_has() in early boot code. */ - if (IS_ENABLED(CONFIG_X86_5LEVEL) && - !cmdline_find_option_bool("no5lvl") && - native_cpuid_eax(0) >= 7 && - (native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) { - paging_config.l5_required = 1; + if (!cmdline_find_option_bool("no5lvl") && + native_cpuid_eax(0) >= 7 && (native_cpuid_ecx(7) & BIT(16))) { + l5_required = true; + + /* Initialize variables for 5-level paging */ + __pgtable_l5_enabled = 1; + pgdir_shift = 48; + ptrs_per_p4d = 512; } - paging_config.trampoline_start = find_trampoline_placement(); + /* + * The trampoline will not be used if the paging mode is already set to + * the desired one. + */ + if (l5_required == !!(native_read_cr4() & X86_CR4_LA57)) + return; - trampoline_32bit = (unsigned long *)paging_config.trampoline_start; + trampoline_32bit = (unsigned long *)find_trampoline_placement(); /* Preserve trampoline memory */ memcpy(trampoline_save, trampoline_32bit, TRAMPOLINE_32BIT_SIZE); @@ -143,34 +144,35 @@ struct paging_config paging_prepare(void *rmode) memset(trampoline_32bit, 0, TRAMPOLINE_32BIT_SIZE); /* Copy trampoline code in place */ - memcpy(trampoline_32bit + TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long), + toggle_la57 = memcpy(trampoline_32bit + + TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long), &trampoline_32bit_src, TRAMPOLINE_32BIT_CODE_SIZE); /* + * Avoid the need for a stack in the 32-bit trampoline code, by using + * LJMP rather than LRET to return back to long mode. LJMP takes an + * immediate absolute address, which needs to be adjusted based on the + * placement of the trampoline. + */ + *(u32 *)((u8 *)toggle_la57 + trampoline_ljmp_imm_offset) += + (unsigned long)toggle_la57; + + /* * The code below prepares page table in trampoline memory. * * The new page table will be used by trampoline code for switching * from 4- to 5-level paging or vice versa. - * - * If switching is not required, the page table is unused: trampoline - * code wouldn't touch CR3. */ - /* - * We are not going to use the page table in trampoline memory if we - * are already in the desired paging mode. - */ - if (paging_config.l5_required == !!(native_read_cr4() & X86_CR4_LA57)) - goto out; - - if (paging_config.l5_required) { + if (l5_required) { /* * For 4- to 5-level paging transition, set up current CR3 as * the first and the only entry in a new top-level page table. */ - trampoline_32bit[TRAMPOLINE_32BIT_PGTABLE_OFFSET] = __native_read_cr3() | _PAGE_TABLE_NOENC; + *trampoline_32bit = native_read_cr3_pa() | _PAGE_TABLE_NOENC; } else { - unsigned long src; + u64 *new_cr3; + pgd_t *pgdp; /* * For 5- to 4-level paging transition, copy page table pointed @@ -180,39 +182,19 @@ struct paging_config paging_prepare(void *rmode) * We cannot just point to the page table from trampoline as it * may be above 4G. */ - src = *(unsigned long *)__native_read_cr3() & PAGE_MASK; - memcpy(trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long), - (void *)src, PAGE_SIZE); + pgdp = (pgd_t *)native_read_cr3_pa(); + new_cr3 = (u64 *)(native_pgd_val(pgdp[0]) & PTE_PFN_MASK); + memcpy(trampoline_32bit, new_cr3, PAGE_SIZE); } -out: - return paging_config; -} - -void cleanup_trampoline(void *pgtable) -{ - void *trampoline_pgtable; - - trampoline_pgtable = trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long); + toggle_la57(trampoline_32bit); /* - * Move the top level page table out of trampoline memory, - * if it's there. + * Move the top level page table out of trampoline memory. */ - if ((void *)__native_read_cr3() == trampoline_pgtable) { - memcpy(pgtable, trampoline_pgtable, PAGE_SIZE); - native_write_cr3((unsigned long)pgtable); - } + memcpy(pgtable, trampoline_32bit, PAGE_SIZE); + native_write_cr3((unsigned long)pgtable); /* Restore trampoline memory */ memcpy(trampoline_32bit, trampoline_save, TRAMPOLINE_32BIT_SIZE); - - /* Initialize variables for 5-level paging */ -#ifdef CONFIG_X86_5LEVEL - if (__read_cr4() & X86_CR4_LA57) { - __pgtable_l5_enabled = 1; - pgdir_shift = 48; - ptrs_per_p4d = 512; - } -#endif } diff --git a/arch/x86/boot/compressed/sbat.S b/arch/x86/boot/compressed/sbat.S new file mode 100644 index 000000000000..838f70a997dd --- /dev/null +++ b/arch/x86/boot/compressed/sbat.S @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Embed SBAT data in the kernel. + */ + .pushsection ".sbat", "a", @progbits + .incbin CONFIG_EFI_SBAT_FILE + .popsection diff --git a/arch/x86/boot/compressed/sev-handle-vc.c b/arch/x86/boot/compressed/sev-handle-vc.c new file mode 100644 index 000000000000..030001b46554 --- /dev/null +++ b/arch/x86/boot/compressed/sev-handle-vc.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "misc.h" +#include "error.h" +#include "sev.h" + +#include <linux/kernel.h> +#include <linux/string.h> +#include <asm/insn.h> +#include <asm/pgtable_types.h> +#include <asm/ptrace.h> +#include <asm/sev.h> +#include <asm/trapnr.h> +#include <asm/trap_pf.h> +#include <asm/fpu/xcr.h> + +#define __BOOT_COMPRESSED +#undef __init +#define __init + +/* Basic instruction decoding support needed */ +#include "../../lib/inat.c" +#include "../../lib/insn.c" + +/* + * Copy a version of this function here - insn-eval.c can't be used in + * pre-decompression code. + */ +bool insn_has_rep_prefix(struct insn *insn) +{ + insn_byte_t p; + + insn_get_prefixes(insn); + + for_each_insn_prefix(insn, p) { + if (p == 0xf2 || p == 0xf3) + return true; + } + + return false; +} + +enum es_result vc_decode_insn(struct es_em_ctxt *ctxt) +{ + char buffer[MAX_INSN_SIZE]; + int ret; + + memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE); + + ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64); + if (ret < 0) + return ES_DECODE_FAILED; + + return ES_OK; +} + +extern void sev_insn_decode_init(void) __alias(inat_init_tables); + +/* + * Only a dummy for insn_get_seg_base() - Early boot-code is 64bit only and + * doesn't use segments. + */ +static unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx) +{ + return 0UL; +} + +static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, + void *dst, char *buf, size_t size) +{ + memcpy(dst, buf, size); + + return ES_OK; +} + +static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, + void *src, char *buf, size_t size) +{ + memcpy(buf, src, size); + + return ES_OK; +} + +static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size) +{ + return ES_OK; +} + +static bool fault_in_kernel_space(unsigned long address) +{ + return false; +} + +#define sev_printk(fmt, ...) + +#include "../../coco/sev/vc-shared.c" + +void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) +{ + struct es_em_ctxt ctxt; + enum es_result result; + + if (!boot_ghcb && !early_setup_ghcb()) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); + + vc_ghcb_invalidate(boot_ghcb); + result = vc_init_em_ctxt(&ctxt, regs, exit_code); + if (result != ES_OK) + goto finish; + + result = vc_check_opcode_bytes(&ctxt, exit_code); + if (result != ES_OK) + goto finish; + + switch (exit_code) { + case SVM_EXIT_RDTSC: + case SVM_EXIT_RDTSCP: + result = vc_handle_rdtsc(boot_ghcb, &ctxt, exit_code); + break; + case SVM_EXIT_IOIO: + result = vc_handle_ioio(boot_ghcb, &ctxt); + break; + case SVM_EXIT_CPUID: + result = vc_handle_cpuid(boot_ghcb, &ctxt); + break; + default: + result = ES_UNSUPPORTED; + break; + } + +finish: + if (result == ES_OK) + vc_finish_insn(&ctxt); + else if (result != ES_RETRY) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); +} diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index d63ad8f99f83..c8c1464b3a56 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -12,7 +12,9 @@ */ #include "misc.h" +#include <asm/bootparam.h> #include <asm/pgtable_types.h> +#include <asm/shared/msr.h> #include <asm/sev.h> #include <asm/trapnr.h> #include <asm/trap_pf.h> @@ -20,150 +22,61 @@ #include <asm/fpu/xcr.h> #include <asm/ptrace.h> #include <asm/svm.h> -#include <asm/cpuid.h> +#include <asm/cpuid/api.h> #include "error.h" -#include "../msr.h" +#include "sev.h" -struct ghcb boot_ghcb_page __aligned(PAGE_SIZE); +static struct ghcb boot_ghcb_page __aligned(PAGE_SIZE); struct ghcb *boot_ghcb; -/* - * Copy a version of this function here - insn-eval.c can't be used in - * pre-decompression code. - */ -static bool insn_has_rep_prefix(struct insn *insn) -{ - insn_byte_t p; - int i; - - insn_get_prefixes(insn); - - for_each_insn_prefix(insn, i, p) { - if (p == 0xf2 || p == 0xf3) - return true; - } - - return false; -} - -/* - * Only a dummy for insn_get_seg_base() - Early boot-code is 64bit only and - * doesn't use segments. - */ -static unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx) -{ - return 0UL; -} - -static inline u64 sev_es_rd_ghcb_msr(void) -{ - struct msr m; - - boot_rdmsr(MSR_AMD64_SEV_ES_GHCB, &m); - - return m.q; -} - -static inline void sev_es_wr_ghcb_msr(u64 val) -{ - struct msr m; - - m.q = val; - boot_wrmsr(MSR_AMD64_SEV_ES_GHCB, &m); -} - -static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt) -{ - char buffer[MAX_INSN_SIZE]; - int ret; - - memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE); - - ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64); - if (ret < 0) - return ES_DECODE_FAILED; - - return ES_OK; -} - -static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, - void *dst, char *buf, size_t size) -{ - memcpy(dst, buf, size); - - return ES_OK; -} - -static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, - void *src, char *buf, size_t size) -{ - memcpy(buf, src, size); - - return ES_OK; -} - #undef __init -#undef __pa #define __init -#define __pa(x) ((unsigned long)(x)) #define __BOOT_COMPRESSED -/* Basic instruction decoding support needed */ -#include "../../lib/inat.c" -#include "../../lib/insn.c" +u8 snp_vmpl; +u16 ghcb_version; + +u64 boot_svsm_caa_pa; /* Include code for early handlers */ -#include "../../kernel/sev-shared.c" +#include "../../boot/startup/sev-shared.c" -static inline bool sev_snp_enabled(void) +static bool sev_snp_enabled(void) { return sev_status & MSR_AMD64_SEV_SNP_ENABLED; } -static void __page_state_change(unsigned long paddr, enum psc_op op) +void snp_set_page_private(unsigned long paddr) { - u64 val; + struct psc_desc d = { + SNP_PAGE_STATE_PRIVATE, + (struct svsm_ca *)boot_svsm_caa_pa, + boot_svsm_caa_pa + }; if (!sev_snp_enabled()) return; - /* - * If private -> shared then invalidate the page before requesting the - * state change in the RMP table. - */ - if (op == SNP_PAGE_STATE_SHARED && pvalidate(paddr, RMP_PG_SIZE_4K, 0)) - sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); - - /* Issue VMGEXIT to change the page state in RMP table. */ - sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op)); - VMGEXIT(); - - /* Read the response of the VMGEXIT. */ - val = sev_es_rd_ghcb_msr(); - if ((GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP) || GHCB_MSR_PSC_RESP_VAL(val)) - sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); - - /* - * Now that page state is changed in the RMP table, validate it so that it is - * consistent with the RMP entry. - */ - if (op == SNP_PAGE_STATE_PRIVATE && pvalidate(paddr, RMP_PG_SIZE_4K, 1)) - sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); -} - -void snp_set_page_private(unsigned long paddr) -{ - __page_state_change(paddr, SNP_PAGE_STATE_PRIVATE); + __page_state_change(paddr, paddr, &d); } void snp_set_page_shared(unsigned long paddr) { - __page_state_change(paddr, SNP_PAGE_STATE_SHARED); + struct psc_desc d = { + SNP_PAGE_STATE_SHARED, + (struct svsm_ca *)boot_svsm_caa_pa, + boot_svsm_caa_pa + }; + + if (!sev_snp_enabled()) + return; + + __page_state_change(paddr, paddr, &d); } -static bool early_setup_ghcb(void) +bool early_setup_ghcb(void) { if (set_page_decrypted((unsigned long)&boot_ghcb_page)) return false; @@ -174,7 +87,7 @@ static bool early_setup_ghcb(void) boot_ghcb = &boot_ghcb_page; /* Initialize lookup tables for the instruction decoder */ - inat_init_tables(); + sev_insn_decode_init(); /* SNP guest requires the GHCB GPA must be registered */ if (sev_snp_enabled()) @@ -183,6 +96,18 @@ static bool early_setup_ghcb(void) return true; } +void snp_accept_memory(phys_addr_t start, phys_addr_t end) +{ + struct psc_desc d = { + SNP_PAGE_STATE_PRIVATE, + (struct svsm_ca *)boot_svsm_caa_pa, + boot_svsm_caa_pa + }; + + for (phys_addr_t pa = start; pa < end; pa += PAGE_SIZE) + __page_state_change(pa, pa, &d); +} + void sev_es_shutdown_ghcb(void) { if (!boot_ghcb) @@ -192,6 +117,16 @@ void sev_es_shutdown_ghcb(void) error("SEV-ES CPU Features missing."); /* + * This denotes whether to use the GHCB MSR protocol or the GHCB + * shared page to perform a GHCB request. Since the GHCB page is + * being changed to encrypted, it can't be used to perform GHCB + * requests. Clear the boot_ghcb variable so that the GHCB MSR + * protocol is used to change the GHCB page over to an encrypted + * page. + */ + boot_ghcb = NULL; + + /* * GHCB Page must be flushed from the cache and mapped encrypted again. * Otherwise the running kernel will see strange cache effects when * trying to use that page. @@ -231,62 +166,6 @@ bool sev_es_check_ghcb_fault(unsigned long address) return ((address & PAGE_MASK) == (unsigned long)&boot_ghcb_page); } -void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) -{ - struct es_em_ctxt ctxt; - enum es_result result; - - if (!boot_ghcb && !early_setup_ghcb()) - sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); - - vc_ghcb_invalidate(boot_ghcb); - result = vc_init_em_ctxt(&ctxt, regs, exit_code); - if (result != ES_OK) - goto finish; - - switch (exit_code) { - case SVM_EXIT_RDTSC: - case SVM_EXIT_RDTSCP: - result = vc_handle_rdtsc(boot_ghcb, &ctxt, exit_code); - break; - case SVM_EXIT_IOIO: - result = vc_handle_ioio(boot_ghcb, &ctxt); - break; - case SVM_EXIT_CPUID: - result = vc_handle_cpuid(boot_ghcb, &ctxt); - break; - default: - result = ES_UNSUPPORTED; - break; - } - -finish: - if (result == ES_OK) - vc_finish_insn(&ctxt); - else if (result != ES_RETRY) - sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); -} - -static void enforce_vmpl0(void) -{ - u64 attrs; - int err; - - /* - * RMPADJUST modifies RMP permissions of a lesser-privileged (numerically - * higher) privilege level. Here, clear the VMPL1 permission mask of the - * GHCB page. If the guest is not running at VMPL0, this will fail. - * - * If the guest is running at VMPL0, it will succeed. Even if that operation - * modifies permission bits, it is still ok to do so currently because Linux - * SNP guests are supported only on VMPL0 so VMPL1 or higher permission masks - * changing is a don't-care. - */ - attrs = 1; - if (rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, attrs)) - 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 @@ -305,32 +184,46 @@ static void enforce_vmpl0(void) MSR_AMD64_SNP_VMPL_SSS | \ MSR_AMD64_SNP_SECURE_TSC | \ MSR_AMD64_SNP_VMGEXIT_PARAM | \ - MSR_AMD64_SNP_VMSA_REG_PROTECTION | \ + MSR_AMD64_SNP_VMSA_REG_PROT | \ MSR_AMD64_SNP_RESERVED_BIT13 | \ MSR_AMD64_SNP_RESERVED_BIT15 | \ + MSR_AMD64_SNP_SECURE_AVIC | \ MSR_AMD64_SNP_RESERVED_MASK) +#ifdef CONFIG_AMD_SECURE_AVIC +#define SNP_FEATURE_SECURE_AVIC MSR_AMD64_SNP_SECURE_AVIC +#else +#define SNP_FEATURE_SECURE_AVIC 0 +#endif + /* * 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) +#define SNP_FEATURES_PRESENT (MSR_AMD64_SNP_DEBUG_SWAP | \ + MSR_AMD64_SNP_SECURE_TSC | \ + SNP_FEATURE_SECURE_AVIC) + +u64 snp_get_unsupported_features(u64 status) +{ + if (!(status & MSR_AMD64_SEV_SNP_ENABLED)) + return 0; + + return status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT; +} 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; + unsupported = snp_get_unsupported_features(sev_status); if (unsupported) { if (ghcb_version < 2 || (!boot_ghcb && !early_setup_ghcb())) sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); @@ -340,80 +233,6 @@ void snp_check_features(void) } } -void sev_enable(struct boot_params *bp) -{ - unsigned int eax, ebx, ecx, edx; - struct msr m; - bool snp; - - /* - * bp->cc_blob_address should only be set by boot/compressed kernel. - * Initialize it to 0 to ensure that uninitialized values from - * buggy bootloaders aren't propagated. - */ - if (bp) - bp->cc_blob_address = 0; - - /* - * Setup/preliminary detection of SNP. This will be sanity-checked - * against CPUID/MSR values later. - */ - snp = snp_init(bp); - - /* Check for the SME/SEV support leaf */ - eax = 0x80000000; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - if (eax < 0x8000001f) - return; - - /* - * Check for the SME/SEV feature: - * CPUID Fn8000_001F[EAX] - * - Bit 0 - Secure Memory Encryption support - * - Bit 1 - Secure Encrypted Virtualization support - * CPUID Fn8000_001F[EBX] - * - Bits 5:0 - Pagetable bit position used to indicate encryption - */ - eax = 0x8000001f; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - /* Check whether SEV is supported */ - if (!(eax & BIT(1))) { - if (snp) - error("SEV-SNP support indicated by CC blob, but not CPUID."); - return; - } - - /* Set the SME mask if this is an SEV guest. */ - boot_rdmsr(MSR_AMD64_SEV, &m); - sev_status = m.q; - if (!(sev_status & MSR_AMD64_SEV_ENABLED)) - return; - - /* Negotiate the GHCB protocol version. */ - if (sev_status & MSR_AMD64_SEV_ES_ENABLED) { - if (!sev_es_negotiate_protocol()) - sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_PROT_UNSUPPORTED); - } - - /* - * SNP is supported in v2 of the GHCB spec which mandates support for HV - * features. - */ - if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) { - if (!(get_hv_features() & GHCB_HV_FT_SNP)) - sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); - - enforce_vmpl0(); - } - - if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) - error("SEV-SNP supported indicated by CC blob, but not SEV status MSR."); - - sme_me_mask = BIT_ULL(ebx & 0x3f); -} - /* Search for Confidential Computing blob in the EFI config table. */ static struct cc_blob_sev_info *find_cc_blob_efi(struct boot_params *bp) { @@ -463,7 +282,7 @@ found_cc_info: * Indicate SNP based on presence of SNP-specific CC blob. Subsequent checks * will verify the SNP CPUID/MSR bits. */ -bool snp_init(struct boot_params *bp) +static bool early_snp_init(struct boot_params *bp) { struct cc_blob_sev_info *cc_info; @@ -484,6 +303,13 @@ bool snp_init(struct boot_params *bp) setup_cpuid_table(cc_info); /* + * Record the SVSM Calling Area (CA) address if the guest is not + * running at VMPL0. The CA will be used to communicate with the + * SVSM and request its services. + */ + svsm_setup_ca(cc_info, rip_rel_ptr(&boot_ghcb_page)); + + /* * Pass run-time kernel a pointer to CC info via boot_params so EFI * config table doesn't need to be searched again during early startup * phase. @@ -493,6 +319,138 @@ bool snp_init(struct boot_params *bp) return true; } +/* + * sev_check_cpu_support - Check for SEV support in the CPU capabilities + * + * Returns < 0 if SEV is not supported, otherwise the position of the + * encryption bit in the page table descriptors. + */ +static int sev_check_cpu_support(void) +{ + unsigned int eax, ebx, ecx, edx; + + /* Check for the SME/SEV support leaf */ + eax = 0x80000000; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (eax < 0x8000001f) + return -ENODEV; + + /* + * Check for the SME/SEV feature: + * CPUID Fn8000_001F[EAX] + * - Bit 0 - Secure Memory Encryption support + * - Bit 1 - Secure Encrypted Virtualization support + * CPUID Fn8000_001F[EBX] + * - Bits 5:0 - Pagetable bit position used to indicate encryption + */ + eax = 0x8000001f; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + /* Check whether SEV is supported */ + if (!(eax & BIT(1))) + return -ENODEV; + + sev_snp_needs_sfw = !(ebx & BIT(31)); + + return ebx & 0x3f; +} + +void sev_enable(struct boot_params *bp) +{ + struct msr m; + int bitpos; + bool snp; + + /* + * bp->cc_blob_address should only be set by boot/compressed kernel. + * Initialize it to 0 to ensure that uninitialized values from + * buggy bootloaders aren't propagated. + */ + if (bp) + bp->cc_blob_address = 0; + + /* + * Do an initial SEV capability check before early_snp_init() which + * loads the CPUID page and the same checks afterwards are done + * without the hypervisor and are trustworthy. + * + * If the HV fakes SEV support, the guest will crash'n'burn + * which is good enough. + */ + + if (sev_check_cpu_support() < 0) + return; + + /* + * Setup/preliminary detection of SNP. This will be sanity-checked + * against CPUID/MSR values later. + */ + snp = early_snp_init(bp); + + /* Now repeat the checks with the SNP CPUID table. */ + + bitpos = sev_check_cpu_support(); + if (bitpos < 0) { + if (snp) + error("SEV-SNP support indicated by CC blob, but not CPUID."); + return; + } + + /* Set the SME mask if this is an SEV guest. */ + raw_rdmsr(MSR_AMD64_SEV, &m); + sev_status = m.q; + if (!(sev_status & MSR_AMD64_SEV_ENABLED)) + return; + + /* Negotiate the GHCB protocol version. */ + if (sev_status & MSR_AMD64_SEV_ES_ENABLED) { + if (!sev_es_negotiate_protocol()) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_PROT_UNSUPPORTED); + } + + /* + * SNP is supported in v2 of the GHCB spec which mandates support for HV + * features. + */ + if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) { + u64 hv_features; + + hv_features = get_hv_features(); + if (!(hv_features & GHCB_HV_FT_SNP)) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + + /* + * Running at VMPL0 is required unless an SVSM is present and + * the hypervisor supports the required SVSM GHCB events. + */ + if (snp_vmpl && !(hv_features & GHCB_HV_FT_SNP_MULTI_VMPL)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0); + } + + if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + error("SEV-SNP supported indicated by CC blob, but not SEV status MSR."); + + sme_me_mask = BIT_ULL(bitpos); +} + +/* + * sev_get_status - Retrieve the SEV status mask + * + * Returns 0 if the CPU is not SEV capable, otherwise the value of the + * AMD64_SEV MSR. + */ +u64 sev_get_status(void) +{ + struct msr m; + + if (sev_check_cpu_support() < 0) + return 0; + + raw_rdmsr(MSR_AMD64_SEV, &m); + return m.q; +} + void sev_prep_identity_maps(unsigned long top_level_pgt) { /* @@ -502,7 +460,7 @@ void sev_prep_identity_maps(unsigned long top_level_pgt) * accessed after switchover. */ if (sev_snp_enabled()) { - unsigned long cc_info_pa = boot_params->cc_blob_address; + unsigned long cc_info_pa = boot_params_ptr->cc_blob_address; struct cc_blob_sev_info *cc_info; kernel_add_identity_map(cc_info_pa, cc_info_pa + sizeof(*cc_info)); @@ -513,3 +471,42 @@ void sev_prep_identity_maps(unsigned long top_level_pgt) sev_verify_cbit(top_level_pgt); } + +bool early_is_sevsnp_guest(void) +{ + static bool sevsnp; + + if (sevsnp) + return true; + + if (!(sev_get_status() & MSR_AMD64_SEV_SNP_ENABLED)) + return false; + + sevsnp = true; + + if (!snp_vmpl) { + unsigned int eax, ebx, ecx, edx; + + /* + * CPUID Fn8000_001F_EAX[28] - SVSM support + */ + eax = 0x8000001f; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (eax & BIT(28)) { + struct msr m; + + /* Obtain the address of the calling area to use */ + raw_rdmsr(MSR_SVSM_CAA, &m); + boot_svsm_caa_pa = m.q; + + /* + * The real VMPL level cannot be discovered, but the + * memory acceptance routines make no use of that so + * any non-zero value suffices here. + */ + snp_vmpl = U8_MAX; + } + } + return true; +} diff --git a/arch/x86/boot/compressed/sev.h b/arch/x86/boot/compressed/sev.h new file mode 100644 index 000000000000..22637b416b46 --- /dev/null +++ b/arch/x86/boot/compressed/sev.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD SEV header for early boot related functions. + * + * Author: Tom Lendacky <thomas.lendacky@amd.com> + */ + +#ifndef BOOT_COMPRESSED_SEV_H +#define BOOT_COMPRESSED_SEV_H + +#ifdef CONFIG_AMD_MEM_ENCRYPT + +#include <asm/shared/msr.h> + +void snp_accept_memory(phys_addr_t start, phys_addr_t end); +u64 sev_get_status(void); +bool early_is_sevsnp_guest(void); + +static inline u64 sev_es_rd_ghcb_msr(void) +{ + struct msr m; + + raw_rdmsr(MSR_AMD64_SEV_ES_GHCB, &m); + + return m.q; +} + +static inline void sev_es_wr_ghcb_msr(u64 val) +{ + struct msr m; + + m.q = val; + raw_wrmsr(MSR_AMD64_SEV_ES_GHCB, &m); +} + +#else + +static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { } +static inline u64 sev_get_status(void) { return 0; } +static inline bool early_is_sevsnp_guest(void) { return false; } + +#endif + +#endif diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c index 81fc1eaa3229..9af19d9614cb 100644 --- a/arch/x86/boot/compressed/string.c +++ b/arch/x86/boot/compressed/string.c @@ -15,9 +15,9 @@ static void *____memcpy(void *dest, const void *src, size_t n) { int d0, d1, d2; asm volatile( - "rep ; movsl\n\t" + "rep movsl\n\t" "movl %4,%%ecx\n\t" - "rep ; movsb\n\t" + "rep movsb" : "=&c" (d0), "=&D" (d1), "=&S" (d2) : "0" (n >> 2), "g" (n & 3), "1" (dest), "2" (src) : "memory"); @@ -29,9 +29,9 @@ static void *____memcpy(void *dest, const void *src, size_t n) { long d0, d1, d2; asm volatile( - "rep ; movsq\n\t" + "rep movsq\n\t" "movq %4,%%rcx\n\t" - "rep ; movsb\n\t" + "rep movsb" : "=&c" (d0), "=&D" (d1), "=&S" (d2) : "0" (n >> 3), "g" (n & 7), "1" (dest), "2" (src) : "memory"); diff --git a/arch/x86/boot/compressed/tdx-shared.c b/arch/x86/boot/compressed/tdx-shared.c new file mode 100644 index 000000000000..5ac43762fe13 --- /dev/null +++ b/arch/x86/boot/compressed/tdx-shared.c @@ -0,0 +1,2 @@ +#include "error.h" +#include "../../coco/tdx/tdx-shared.c" diff --git a/arch/x86/boot/compressed/tdx.c b/arch/x86/boot/compressed/tdx.c index 918a7606f53c..8451d6a1030c 100644 --- a/arch/x86/boot/compressed/tdx.c +++ b/arch/x86/boot/compressed/tdx.c @@ -18,15 +18,15 @@ void __tdx_hypercall_failed(void) static inline unsigned int tdx_io_in(int size, u16 port) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = TDX_HYPERCALL_STANDARD, - .r11 = EXIT_REASON_IO_INSTRUCTION, + .r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION), .r12 = size, .r13 = 0, .r14 = port, }; - if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + if (__tdx_hypercall(&args)) return UINT_MAX; return args.r11; @@ -34,16 +34,16 @@ static inline unsigned int tdx_io_in(int size, u16 port) static inline void tdx_io_out(int size, u16 port, u32 value) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = TDX_HYPERCALL_STANDARD, - .r11 = EXIT_REASON_IO_INSTRUCTION, + .r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION), .r12 = size, .r13 = 1, .r14 = port, .r15 = value, }; - __tdx_hypercall(&args, 0); + __tdx_hypercall(&args); } static inline u8 tdx_inb(u16 port) diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index 112b2375d021..587ce3e7c504 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 : { @@ -42,11 +43,21 @@ SECTIONS *(.rodata.*) _erodata = . ; } - .data : { +#ifdef CONFIG_EFI_SBAT + .sbat : ALIGN(0x1000) { + _sbat = . ; + *(.sbat) + _esbat = ALIGN(0x1000); + . = _esbat; + } +#endif + .data : ALIGN(0x1000) { _data = . ; *(.data) *(.data.*) - *(.bss.efistub) + + /* Add 4 bytes of extra space for the obsolete CRC-32 checksum */ + . = ALIGN(. + 4, 0x200); _edata = . ; } . = ALIGN(L1_CACHE_BYTES); |