diff --git a/Documentation/x86/boot.rst b/Documentation/x86/boot.rst index 08a2f100c0e6ac3a402f9a81b69eeac7d3c0d270..7cde724e9e42209bf7349321a1821e56440b24db 100644 --- a/Documentation/x86/boot.rst +++ b/Documentation/x86/boot.rst @@ -471,15 +471,11 @@ Protocol: 2.00+ kernel) to not write early messages that require accessing the display hardware directly. - Bit 6 (write): KEEP_SEGMENTS + Bit 6 (obsolete): KEEP_SEGMENTS Protocol: 2.07+ - - If 0, reload the segment registers in the 32bit entry point. - - If 1, do not reload the segment registers in the 32bit entry point. - - Assume that %cs %ds %ss %es are all set to flat segments with - a base of 0 (or the equivalent for their environment). + - This flag is obsolete. Bit 7 (write): CAN_USE_HEAP diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cdc3b4f600eddb14db0962cfc660e1909bb1dfd4..c0bb48595e40d1afe9ece0d8ce874e3262ad936e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1555,6 +1555,7 @@ config AMD_MEM_ENCRYPT select DYNAMIC_PHYSICAL_MASK select ARCH_USE_MEMREMAP_PROT select ARCH_HAS_FORCE_DMA_UNENCRYPTED + select INSTRUCTION_DECODER ---help--- Say yes to enable support for the encryption of system memory. This requires an AMD processor that supports Secure Memory diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index edfb1a718510979e104a2e6d39aefbdd516cab9f..0709b396f714395aa637ecd44ba6475e762b4309 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -30,7 +30,7 @@ KBUILD_CFLAGS := -m$(BITS) -O2 KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC) KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING cflags-$(CONFIG_X86_32) := -march=i386 -cflags-$(CONFIG_X86_64) := -mcmodel=small +cflags-$(CONFIG_X86_64) := -mcmodel=small -mno-red-zone KBUILD_CFLAGS += $(cflags-y) KBUILD_CFLAGS += -mno-mmx -mno-sse KBUILD_CFLAGS += $(call cc-option,-ffreestanding) @@ -40,6 +40,12 @@ KBUILD_CFLAGS += $(call cc-disable-warning, gnu) KBUILD_CFLAGS += -Wno-pointer-sign # Disable relocation relaxation in case the link is not PIE. KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no) +KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h + +# sev-es.c indirectly inludes inat-table.h which is generated during +# compilation and stored in $(objtree). Add the directory to the includes so +# that the compiler finds it even with out-of-tree builds (make O=/some/path). +CFLAGS_sev-es.o += -I$(objtree)/arch/x86/lib/ KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n @@ -85,9 +91,11 @@ vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \ vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o ifdef CONFIG_X86_64 - vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr_64.o + vmlinux-objs-y += $(obj)/ident_map_64.o + vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o vmlinux-objs-y += $(obj)/mem_encrypt.o vmlinux-objs-y += $(obj)/pgtable_64.o + vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev-es.o endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o diff --git a/arch/x86/boot/compressed/cpuflags.c b/arch/x86/boot/compressed/cpuflags.c index 6448a8196d3298b0fb06f7a31d14dee6086f8978..0cc1323896d19124475f817f574dd6810c4307bb 100644 --- a/arch/x86/boot/compressed/cpuflags.c +++ b/arch/x86/boot/compressed/cpuflags.c @@ -1,6 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -#ifdef CONFIG_RANDOMIZE_BASE - #include "../cpuflags.c" bool has_cpuflag(int flag) @@ -9,5 +7,3 @@ bool has_cpuflag(int flag) return test_bit(flag, cpu.flags); } - -#endif diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S index bff9ab7c6317af218c99bbf262f8a089865c8daa..6679b905074a72cb8d58543fcc2506fd4dc2eaa8 100644 --- a/arch/x86/boot/compressed/efi_thunk_64.S +++ b/arch/x86/boot/compressed/efi_thunk_64.S @@ -62,11 +62,16 @@ ENTRY(efi64_thunk) * Switch to gdt with 32-bit segments. This is the firmware GDT * that was installed when the kernel started executing. This * pointer was saved at the EFI stub entry point in head_64.S. + * + * Pass the saved DS selector to the 32-bit code, and use far return to + * restore the saved CS selector. */ leaq efi32_boot_gdt(%rip), %rax lgdt (%rax) - pushq $__KERNEL_CS + movzwl efi32_boot_ds(%rip), %edx + movzwq efi32_boot_cs(%rip), %rax + pushq %rax leaq efi_enter32(%rip), %rax pushq %rax lretq @@ -81,6 +86,10 @@ ENTRY(efi64_thunk) 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 /* * Convert 32-bit status code into 64-bit. @@ -113,10 +122,12 @@ ENDPROC(efi_exit32) * The stack should represent the 32-bit calling convention. */ ENTRY(efi_enter32) - movl $__KERNEL_DS, %eax - movl %eax, %ds - movl %eax, %es - movl %eax, %ss + /* 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 @@ -176,16 +187,27 @@ ENDPROC(efi_enter32) .data .balign 8 - .global efi32_boot_gdt -efi32_boot_gdt: .word 0 - .quad 0 +SYM_DATA_START(efi32_boot_gdt) + .word 0 + .quad 0 +SYM_DATA_END(efi32_boot_gdt) + +SYM_DATA_START(efi32_boot_cs) + .word 0 +SYM_DATA_END(efi32_boot_cs) + +SYM_DATA_START(efi32_boot_ds) + .word 0 +SYM_DATA_END(efi32_boot_ds) + +SYM_DATA_START_LOCAL(save_gdt) + .word 0 + .quad 0 +SYM_DATA_END(save_gdt) -save_gdt: .word 0 - .quad 0 -func_rt_ptr: .quad 0 +SYM_DATA_LOCAL(func_rt_ptr, .quad 0) - .global efi_gdt64 -efi_gdt64: +SYM_DATA_START(efi_gdt64) .word efi_gdt64_end - efi_gdt64 .long 0 /* Filled out by user */ .word 0 @@ -194,4 +216,4 @@ efi_gdt64: .quad 0x00cf92000000ffff /* __KERNEL_DS */ .quad 0x0080890000000000 /* TS descriptor */ .quad 0x0000000000000000 /* TS continued */ -efi_gdt64_end: +SYM_DATA_END_LABEL(efi_gdt64, SYM_L_LOCAL, efi_gdt64_end) diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index d7c0fcc1dbf9e74e333ae39117b2913ef7eb7d67..bd5b6473424d25b3ad7da8cfcf127d5347397932 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -49,28 +49,18 @@ * Position Independent Executable (PIE) so that linker won't optimize * R_386_GOT32X relocation to its fixed symbol address. Older * linkers generate R_386_32 relocations against locally defined symbols, - * _bss, _ebss, _got, _egot and _end, in PIE. It isn't wrong, just less - * optimal than R_386_RELATIVE. But the x86 kernel fails to properly handle - * R_386_32 relocations when relocating the kernel. To generate - * R_386_RELATIVE relocations, we mark _bss, _ebss, _got, _egot and _end as - * hidden: + * _bss, _ebss and _end, in PIE. It isn't wrong, just less optimal than + * R_386_RELATIVE. But the x86 kernel fails to properly handle R_386_32 + * relocations when relocating the kernel. To generate R_386_RELATIVE + * relocations, we mark _bss, _ebss and _end as hidden: */ .hidden _bss .hidden _ebss - .hidden _got - .hidden _egot .hidden _end __HEAD ENTRY(startup_32) cld - /* - * Test KEEP_SEGMENTS flag to see if the bootloader is asking - * us to not reload segments - */ - testb $KEEP_SEGMENTS, BP_loadflags(%esi) - jnz 1f - cli movl $__BOOT_DS, %eax movl %eax, %ds @@ -78,7 +68,6 @@ ENTRY(startup_32) movl %eax, %fs movl %eax, %gs movl %eax, %ss -1: /* * Calculate the delta between where we were compiled to run @@ -222,19 +211,6 @@ ENDPROC(efi32_stub_entry) shrl $2, %ecx rep stosl -/* - * Adjust our own GOT - */ - leal _got(%ebx), %edx - leal _egot(%ebx), %ecx -1: - cmpl %ecx, %edx - jae 2f - addl %ebx, (%edx) - addl $4, %edx - jmp 1b -2: - /* * Do the extraction, and jump to the new kernel.. */ diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 50c9eeb36f0d8a8cb54b4862909497bca6e0198d..835b28b673ab433ad5471fc98a6af6eb58b9812b 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -33,6 +33,7 @@ #include #include #include +#include #include "pgtable.h" /* @@ -40,8 +41,6 @@ */ .hidden _bss .hidden _ebss - .hidden _got - .hidden _egot .hidden _end __HEAD @@ -54,19 +53,7 @@ ENTRY(startup_32) * all need to be under the 4G limit. */ cld - /* - * Test KEEP_SEGMENTS flag to see if the bootloader is asking - * us to not reload segments - */ - testb $KEEP_SEGMENTS, BP_loadflags(%esi) - jnz 1f - cli - movl $(__BOOT_DS), %eax - movl %eax, %ds - movl %eax, %es - movl %eax, %ss -1: /* * Calculate the delta between where we were compiled to run @@ -81,10 +68,21 @@ ENTRY(startup_32) 1: popl %ebp subl $1b, %ebp + /* Load new GDT with the 64bit segments using 32bit descriptor */ + leal gdt(%ebp), %eax + movl %eax, 2(%eax) + lgdt (%eax) + + /* Load segment registers with our descriptors */ + movl $__BOOT_DS, %eax + movl %eax, %ds + movl %eax, %es + movl %eax, %fs + movl %eax, %gs + movl %eax, %ss + /* setup a stack and make sure cpu supports long mode. */ - movl $boot_stack_end, %eax - addl %ebp, %eax - movl %eax, %esp + leal boot_stack_end(%ebp), %esp call verify_cpu testl %eax, %eax @@ -121,10 +119,6 @@ ENTRY(startup_32) * Prepare for entering 64 bit mode */ - /* Load new GDT with the 64bit segments using 32bit descriptor */ - addl %ebp, gdt+2(%ebp) - lgdt gdt(%ebp) - /* Enable PAE mode */ movl %cr4, %eax orl $X86_CR4_PAE, %eax @@ -240,11 +234,15 @@ ENTRY(efi32_stub_entry) movl %ecx, efi32_config(%ebp) movl %edx, efi32_config+8(%ebp) - sgdtl efi32_boot_gdt(%ebp) leal efi32_config(%ebp), %eax movl %eax, efi_config(%ebp) + /* Save firmware code/data selectors */ + sgdtl efi32_boot_gdt(%ebp) + movw %cs, efi32_boot_cs(%ebp) + movw %ds, efi32_boot_ds(%ebp) + /* Disable paging */ movl %cr0, %eax btrl $X86_CR0_PG_BIT, %eax @@ -311,25 +309,6 @@ ENTRY(startup_64) /* Set up the stack */ leaq boot_stack_end(%rbx), %rsp - /* - * paging_prepare() and cleanup_trampoline() below can have GOT - * references. Adjust the table with address we are running at. - * - * Zero RAX for adjust_got: the GOT was not adjusted before; - * there's no adjustment to undo. - */ - xorq %rax, %rax - - /* - * Calculate the address the binary is loaded at and use it as - * a GOT adjustment. - */ - call 1f -1: popq %rdi - subq $1b, %rdi - - call .Ladjust_got - /* * At this point we are in long mode with 4-level paging enabled, * but we might want to enable 5-level paging or vice versa. @@ -356,9 +335,21 @@ ENTRY(startup_64) */ /* Make sure we have GDT with 32-bit code segment */ - leaq gdt(%rip), %rax - movq %rax, gdt64+2(%rip) - lgdt gdt64(%rip) + leaq gdt64(%rip), %rax + addq %rax, 2(%rax) + lgdt (%rax) + + /* Reload CS so IRET returns to a CS actually in the GDT */ + pushq $__KERNEL_CS + leaq .Lon_kernel_cs(%rip), %rax + pushq %rax + lretq + +.Lon_kernel_cs: + + pushq %rsi + call load_stage1_idt + popq %rsi /* * paging_prepare() sets up the trampoline and checks if we need to @@ -414,21 +405,6 @@ trampoline_return: pushq $0 popfq - /* - * Previously we've adjusted the GOT with address the binary was - * loaded at. Now we need to re-adjust for relocation address. - * - * Calculate the address the binary is loaded at, so that we can - * undo the previous GOT adjustment. - */ - call 1f -1: popq %rax - subq $1b, %rax - - /* The new adjustment is the relocation address */ - movq %rbx, %rdi - call .Ladjust_got - /* * Copy the compressed kernel to the end of our buffer * where decompression in place becomes safe. @@ -443,6 +419,16 @@ trampoline_return: cld popq %rsi + /* + * The GDT may get overwritten either during the copy we just did or + * during extract_kernel below. To avoid any issues, repoint the GDTR + * to the new copy of the GDT. + */ + leaq gdt64(%rbx), %rax + leaq gdt(%rbx), %rdx + movq %rdx, 2(%rax) + lgdt (%rax) + /* * Jump to the relocated address. */ @@ -529,6 +515,24 @@ ENDPROC(efi64_stub_entry) shrq $3, %rcx rep stosq +/* + * If running as an SEV guest, the encryption mask is required in the + * page-table setup code below. When the guest also has SEV-ES enabled + * set_sev_encryption_mask() will cause #VC exceptions, but the stage2 + * handler can't map its GHCB because the page-table is not set up yet. + * So set up the encryption mask here while still on the stage1 #VC + * handler. Then load stage2 IDT and switch to the kernel's own + * page-table. + */ + pushq %rsi + call set_sev_encryption_mask + call load_stage2_idt + + /* Pass boot_params to initialize_identity_maps() */ + movq (%rsp), %rdi + call initialize_identity_maps + popq %rsi + /* * Do the extraction, and jump to the new kernel.. */ @@ -538,7 +542,7 @@ ENDPROC(efi64_stub_entry) leaq input_data(%rip), %rdx /* input_data */ movl $z_input_len, %ecx /* input_len */ movq %rbp, %r8 /* output target address */ - movq $z_output_len, %r9 /* decompressed length, end of relocs */ + movl $z_output_len, %r9d /* decompressed length, end of relocs */ call extract_kernel /* returns kernel location in %rax */ popq %rsi @@ -547,27 +551,6 @@ ENDPROC(efi64_stub_entry) */ jmp *%rax -/* - * Adjust the global offset table - * - * RAX is the previous adjustment of the table to undo (use 0 if it's the - * first time we touch GOT). - * RDI is the new adjustment to apply. - */ -.Ladjust_got: - /* Walk through the GOT adding the address to the entries */ - leaq _got(%rip), %rdx - leaq _egot(%rip), %rcx -1: - cmpq %rcx, %rdx - jae 2f - subq %rax, (%rdx) /* Undo previous adjustment */ - addq %rdi, (%rdx) /* Apply the new adjustment */ - addq $8, %rdx - jmp 1b -2: - ret - .code32 /* * This is the 32-bit trampoline that will be copied over to low memory. @@ -662,38 +645,50 @@ ENTRY(trampoline_32bit_src) #include "../../kernel/verify_cpu.S" .data -gdt64: - .word gdt_end - gdt - .quad 0 +SYM_DATA_START_LOCAL(gdt64) + .word gdt_end - gdt - 1 + .quad gdt - gdt64 +SYM_DATA_END(gdt64) .balign 8 -gdt: - .word gdt_end - gdt - .long gdt +SYM_DATA_START_LOCAL(gdt) + .word gdt_end - gdt - 1 + .long 0 .word 0 .quad 0x00cf9a000000ffff /* __KERNEL32_CS */ .quad 0x00af9a000000ffff /* __KERNEL_CS */ .quad 0x00cf92000000ffff /* __KERNEL_DS */ .quad 0x0080890000000000 /* TS descriptor */ .quad 0x0000000000000000 /* TS continued */ -gdt_end: +SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) -#ifdef CONFIG_EFI_STUB -efi_config: +SYM_DATA_START(boot_idt_desc) + .word boot_idt_end - boot_idt - 1 + .quad 0 +SYM_DATA_END(boot_idt_desc) + .balign 8 +SYM_DATA_START(boot_idt) + .rept BOOT_IDT_ENTRIES + .quad 0 .quad 0 + .endr +SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end) + +#ifdef CONFIG_EFI_STUB +SYM_DATA_LOCAL(efi_config, .quad 0) #ifdef CONFIG_EFI_MIXED - .global efi32_config -efi32_config: +SYM_DATA_START(efi32_config) .fill 5,8,0 .quad efi64_thunk .byte 0 +SYM_DATA_END(efi32_config) #endif - .global efi64_config -efi64_config: +SYM_DATA_START(efi64_config) .fill 5,8,0 .quad efi_call .byte 1 +SYM_DATA_END(efi64_config) #endif /* CONFIG_EFI_STUB */ /* @@ -701,23 +696,21 @@ efi64_config: */ .bss .balign 4 -boot_heap: - .fill BOOT_HEAP_SIZE, 1, 0 -boot_stack: +SYM_DATA_LOCAL(boot_heap, .fill BOOT_HEAP_SIZE, 1, 0) + +SYM_DATA_START_LOCAL(boot_stack) .fill BOOT_STACK_SIZE, 1, 0 -boot_stack_end: +SYM_DATA_END_LABEL(boot_stack, SYM_L_LOCAL, boot_stack_end) /* * Space for page tables (not in .bss so not zeroed) */ .section ".pgtable","a",@nobits .balign 4096 -pgtable: - .fill BOOT_PGT_SIZE, 1, 0 +SYM_DATA_LOCAL(pgtable, .fill BOOT_PGT_SIZE, 1, 0) /* * The page table is going to be used instead of page table in the trampoline * memory. */ -top_pgtable: - .fill PAGE_SIZE, 1, 0 +SYM_DATA_LOCAL(top_pgtable, .fill PAGE_SIZE, 1, 0) diff --git a/arch/x86/boot/compressed/kaslr_64.c b/arch/x86/boot/compressed/ident_map_64.c similarity index 41% rename from arch/x86/boot/compressed/kaslr_64.c rename to arch/x86/boot/compressed/ident_map_64.c index 9557c5a15b91e29a6465e502599960aad87e3e60..e8851d437d75fda6636069959809bf32e72ae1be 100644 --- a/arch/x86/boot/compressed/kaslr_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -19,9 +19,13 @@ /* No PAGE_TABLE_ISOLATION support needed either: */ #undef CONFIG_PAGE_TABLE_ISOLATION +#include "error.h" #include "misc.h" /* These actually do the work of building the kernel identity maps. */ +#include +#include +#include #include #include /* Use the static base for this part of the boot process */ @@ -29,6 +33,15 @@ #define __PAGE_OFFSET __PAGE_OFFSET_BASE #include "../../mm/ident_map.c" +#define _SETUP +#include /* For COMMAND_LINE_SIZE */ +#undef _SETUP + +extern unsigned long get_cmd_line_ptr(void); + +/* Used by PAGE_KERN* macros: */ +pteval_t __default_kernel_pte_mask __read_mostly = ~0; + /* Used to track our page table allocation area. */ struct alloc_pgt_data { unsigned char *pgt_buf; @@ -74,11 +87,29 @@ phys_addr_t physical_mask = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; */ static struct x86_mapping_info mapping_info; +/* + * Adds the specified range to the identity mappings. + */ +static void add_identity_map(unsigned long start, unsigned long end) +{ + int ret; + + /* Align boundary to 2M. */ + start = round_down(start, PMD_SIZE); + end = round_up(end, PMD_SIZE); + if (start >= end) + return; + + /* Build the mapping. */ + ret = kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, start, end); + if (ret) + error("Error: kernel_ident_mapping_init() failed\n"); +} + /* Locates and clears a region for a new top level page table. */ -void initialize_identity_maps(void) +void initialize_identity_maps(void *rmode) { - /* If running as an SEV guest, the encryption mask is required. */ - set_sev_encryption_mask(); + unsigned long cmdline; /* Exclude the encryption mask from __PHYSICAL_MASK */ physical_mask &= ~sme_me_mask; @@ -109,37 +140,32 @@ void initialize_identity_maps(void) */ top_level_pgt = read_cr3_pa(); if (p4d_offset((pgd_t *)top_level_pgt, 0) == (p4d_t *)_pgtable) { - debug_putstr("booted via startup_32()\n"); pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE; pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE; memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); } else { - debug_putstr("booted via startup_64()\n"); pgt_data.pgt_buf = _pgtable; pgt_data.pgt_buf_size = BOOT_PGT_SIZE; memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); top_level_pgt = (unsigned long)alloc_pgt_page(&pgt_data); } -} - -/* - * Adds the specified range to what will become the new identity mappings. - * Once all ranges have been added, the new mapping is activated by calling - * finalize_identity_maps() below. - */ -void add_identity_map(unsigned long start, unsigned long size) -{ - unsigned long end = start + size; - /* Align boundary to 2M. */ - start = round_down(start, PMD_SIZE); - end = round_up(end, PMD_SIZE); - if (start >= end) - return; + /* + * New page-table is set up - map the kernel image, boot_params and the + * command line. The uncompressed kernel requires boot_params and the + * command line to be mapped in the identity mapping. Map them + * explicitly here in case the compressed kernel does not touch them, + * or does not touch all the pages covering them. + */ + add_identity_map((unsigned long)_head, (unsigned long)_end); + boot_params = rmode; + add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1)); + cmdline = get_cmd_line_ptr(); + add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); - /* Build the mapping. */ - kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, - start, end); + /* Load the new page-table. */ + sev_verify_cbit(top_level_pgt); + write_cr3(top_level_pgt); } /* @@ -151,3 +177,185 @@ void finalize_identity_maps(void) { write_cr3(top_level_pgt); } + +static pte_t *split_large_pmd(struct x86_mapping_info *info, + pmd_t *pmdp, unsigned long __address) +{ + unsigned long page_flags; + unsigned long address; + pte_t *pte; + pmd_t pmd; + int i; + + pte = (pte_t *)info->alloc_pgt_page(info->context); + if (!pte) + return NULL; + + address = __address & PMD_MASK; + /* No large page - clear PSE flag */ + page_flags = info->page_flag & ~_PAGE_PSE; + + /* Populate the PTEs */ + for (i = 0; i < PTRS_PER_PMD; i++) { + set_pte(&pte[i], __pte(address | page_flags)); + address += PAGE_SIZE; + } + + /* + * Ideally we need to clear the large PMD first and do a TLB + * flush before we write the new PMD. But the 2M range of the + * PMD might contain the code we execute and/or the stack + * we are on, so we can't do that. But that should be safe here + * because we are going from large to small mappings and we are + * also the only user of the page-table, so there is no chance + * of a TLB multihit. + */ + pmd = __pmd((unsigned long)pte | info->kernpg_flag); + set_pmd(pmdp, pmd); + /* Flush TLB to establish the new PMD */ + write_cr3(top_level_pgt); + + return pte + pte_index(__address); +} + +static void clflush_page(unsigned long address) +{ + unsigned int flush_size; + char *cl, *start, *end; + + /* + * Hardcode cl-size to 64 - CPUID can't be used here because that might + * cause another #VC exception and the GHCB is not ready to use yet. + */ + flush_size = 64; + start = (char *)(address & PAGE_MASK); + end = start + PAGE_SIZE; + + /* + * First make sure there are no pending writes on the cache-lines to + * flush. + */ + asm volatile("mfence" : : : "memory"); + + for (cl = start; cl != end; cl += flush_size) + clflush(cl); +} + +static int set_clr_page_flags(struct x86_mapping_info *info, + unsigned long address, + pteval_t set, pteval_t clr) +{ + pgd_t *pgdp = (pgd_t *)top_level_pgt; + p4d_t *p4dp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep, pte; + + /* + * First make sure there is a PMD mapping for 'address'. + * It should already exist, but keep things generic. + * + * To map the page just read from it and fault it in if there is no + * mapping yet. add_identity_map() can't be called here because that + * would unconditionally map the address on PMD level, destroying any + * PTE-level mappings that might already exist. Use assembly here so + * the access won't be optimized away. + */ + asm volatile("mov %[address], %%r9" + :: [address] "g" (*(unsigned long *)address) + : "r9", "memory"); + + /* + * The page is mapped at least with PMD size - so skip checks and walk + * directly to the PMD. + */ + p4dp = p4d_offset(pgdp, address); + pudp = pud_offset(p4dp, address); + pmdp = pmd_offset(pudp, address); + + if (pmd_large(*pmdp)) + ptep = split_large_pmd(info, pmdp, address); + else + ptep = pte_offset_kernel(pmdp, address); + + if (!ptep) + return -ENOMEM; + + /* + * Changing encryption attributes of a page requires to flush it from + * the caches. + */ + if ((set | clr) & _PAGE_ENC) + clflush_page(address); + + /* Update PTE */ + pte = *ptep; + pte = pte_set_flags(pte, set); + pte = pte_clear_flags(pte, clr); + set_pte(ptep, pte); + + /* Flush TLB after changing encryption attribute */ + write_cr3(top_level_pgt); + + return 0; +} + +int set_page_decrypted(unsigned long address) +{ + return set_clr_page_flags(&mapping_info, address, 0, _PAGE_ENC); +} + +int set_page_encrypted(unsigned long address) +{ + return set_clr_page_flags(&mapping_info, address, _PAGE_ENC, 0); +} + +int set_page_non_present(unsigned long address) +{ + return set_clr_page_flags(&mapping_info, address, 0, _PAGE_PRESENT); +} + +static void do_pf_error(const char *msg, unsigned long error_code, + unsigned long address, unsigned long ip) +{ + error_putstr(msg); + + error_putstr("\nError Code: "); + error_puthex(error_code); + error_putstr("\nCR2: 0x"); + error_puthex(address); + error_putstr("\nRIP relative to _head: 0x"); + error_puthex(ip - (unsigned long)_head); + error_putstr("\n"); + + error("Stopping.\n"); +} + +void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) +{ + unsigned long address = native_read_cr2(); + unsigned long end; + bool ghcb_fault; + + ghcb_fault = sev_es_check_ghcb_fault(address); + + address &= PMD_MASK; + end = address + PMD_SIZE; + + /* + * Check for unexpected error codes. Unexpected are: + * - Faults on present pages + * - User faults + * - Reserved bits set + */ + if (error_code & (X86_PF_PROT | X86_PF_USER | X86_PF_RSVD)) + do_pf_error("Unexpected page-fault:", error_code, address, regs->ip); + else if (ghcb_fault) + do_pf_error("Page-fault on GHCB page:", error_code, address, regs->ip); + + /* + * Error code is sane - now identity map the 2M region around + * the faulting address. + */ + add_identity_map(address, end); +} diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c new file mode 100644 index 0000000000000000000000000000000000000000..804a502ee0d28bae40d754a00d282a5aa8ffeb51 --- /dev/null +++ b/arch/x86/boot/compressed/idt_64.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include "misc.h" + +static void set_idt_entry(int vector, void (*handler)(void)) +{ + unsigned long address = (unsigned long)handler; + gate_desc entry; + + memset(&entry, 0, sizeof(entry)); + + entry.offset_low = (u16)(address & 0xffff); + entry.segment = __KERNEL_CS; + entry.bits.type = GATE_TRAP; + entry.bits.p = 1; + entry.offset_middle = (u16)((address >> 16) & 0xffff); + entry.offset_high = (u32)(address >> 32); + + memcpy(&boot_idt[vector], &entry, sizeof(entry)); +} + +/* Have this here so we don't need to include */ +static void load_boot_idt(const struct desc_ptr *dtr) +{ + asm volatile("lidt %0"::"m" (*dtr)); +} + +/* Setup IDT before kernel jumping to .Lrelocated */ +void load_stage1_idt(void) +{ + boot_idt_desc.address = (unsigned long)boot_idt; + + + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) + set_idt_entry(X86_TRAP_VC, boot_stage1_vc); + + load_boot_idt(&boot_idt_desc); +} + +/* Setup IDT after kernel jumping to .Lrelocated */ +void load_stage2_idt(void) +{ + boot_idt_desc.address = (unsigned long)boot_idt; + + set_idt_entry(X86_TRAP_PF, boot_page_fault); + +#ifdef CONFIG_AMD_MEM_ENCRYPT + set_idt_entry(X86_TRAP_VC, boot_stage2_vc); +#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 new file mode 100644 index 0000000000000000000000000000000000000000..22890e199f5b44c7bc8f617f266e4364917c8efc --- /dev/null +++ b/arch/x86/boot/compressed/idt_handlers_64.S @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Early IDT handler entry points + * + * Copyright (C) 2019 SUSE + * + * Author: Joerg Roedel + */ + +#include + +/* For ORIG_RAX */ +#include "../../entry/calling.h" + +.macro EXCEPTION_HANDLER name function error_code=0 +SYM_FUNC_START(\name) + + /* Build pt_regs */ + .if \error_code == 0 + pushq $0 + .endif + + pushq %rdi + pushq %rsi + pushq %rdx + pushq %rcx + pushq %rax + pushq %r8 + pushq %r9 + pushq %r10 + pushq %r11 + pushq %rbx + pushq %rbp + pushq %r12 + pushq %r13 + pushq %r14 + pushq %r15 + + /* Call handler with pt_regs */ + movq %rsp, %rdi + /* Error code is second parameter */ + movq ORIG_RAX(%rsp), %rsi + call \function + + /* Restore regs */ + popq %r15 + popq %r14 + popq %r13 + popq %r12 + popq %rbp + popq %rbx + popq %r11 + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rcx + popq %rdx + popq %rsi + popq %rdi + + /* Remove error code and return */ + addq $8, %rsp + + iretq +SYM_FUNC_END(\name) + .endm + + .text + .code64 + +EXCEPTION_HANDLER boot_page_fault do_boot_page_fault error_code=1 + +#ifdef CONFIG_AMD_MEM_ENCRYPT +EXCEPTION_HANDLER boot_stage1_vc do_vc_no_ghcb error_code=1 +EXCEPTION_HANDLER boot_stage2_vc do_boot_stage2_vc error_code=1 +#endif diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 2e53c056ba20c16eda669d304e0da61346f56970..aa6537f6748dd50013ae6f199f147ecdccbf85e9 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -43,17 +43,8 @@ #define STATIC #include -#ifdef CONFIG_X86_5LEVEL -unsigned int __pgtable_l5_enabled; -unsigned int pgdir_shift __ro_after_init = 39; -unsigned int ptrs_per_p4d __ro_after_init = 1; -#endif - extern unsigned long get_cmd_line_ptr(void); -/* Used by PAGE_KERN* macros: */ -pteval_t __default_kernel_pte_mask __read_mostly = ~0; - /* Simplified build-specific string for starting entropy. */ static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION; @@ -380,8 +371,6 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, */ mem_avoid[MEM_AVOID_ZO_RANGE].start = input; mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input; - add_identity_map(mem_avoid[MEM_AVOID_ZO_RANGE].start, - mem_avoid[MEM_AVOID_ZO_RANGE].size); /* Avoid initrd. */ initrd_start = (u64)boot_params->ext_ramdisk_image << 32; @@ -401,14 +390,10 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, ; mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line; mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size; - add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start, - mem_avoid[MEM_AVOID_CMDLINE].size); /* Avoid boot parameters. */ mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params; mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params); - add_identity_map(mem_avoid[MEM_AVOID_BOOTPARAMS].start, - mem_avoid[MEM_AVOID_BOOTPARAMS].size); /* We don't need to set a mapping for setup_data. */ @@ -417,11 +402,6 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, /* Enumerate the immovable memory regions */ num_immovable_mem = count_immovable_mem_regions(); - -#ifdef CONFIG_X86_VERBOSE_BOOTUP - /* Make sure video RAM can be used. */ - add_identity_map(0, PMD_SIZE); -#endif } /* @@ -858,19 +838,8 @@ void choose_random_location(unsigned long input, return; } -#ifdef CONFIG_X86_5LEVEL - if (__read_cr4() & X86_CR4_LA57) { - __pgtable_l5_enabled = 1; - pgdir_shift = 48; - ptrs_per_p4d = 512; - } -#endif - boot_params->hdr.loadflags |= KASLR_FLAG; - /* Prepare to add new identity pagetables on demand. */ - initialize_identity_maps(); - /* Record the various known unsafe memory ranges. */ mem_avoid_init(input, input_size, *output); @@ -887,19 +856,8 @@ void choose_random_location(unsigned long input, warn("Physical KASLR disabled: no suitable memory region!"); } else { /* Update the new physical address location. */ - if (*output != random_addr) { - add_identity_map(random_addr, output_size); + if (*output != random_addr) *output = random_addr; - } - - /* - * This loads the identity mapping page table. - * This should only be done if a new physical address - * is found for the kernel, otherwise we should keep - * the old page table to make it be like the "nokaslr" - * case. - */ - finalize_identity_maps(); } diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index 6afb7130a38791570441d98b18fe2216306dbe26..47256ca5f00321861c6dc73cbe604204e76fdf1d 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -68,6 +68,9 @@ ENTRY(get_sev_encryption_bit) ENDPROC(get_sev_encryption_bit) .code64 + +#include "../../kernel/sev_verify_cbit.S" + ENTRY(set_sev_encryption_mask) #ifdef CONFIG_AMD_MEM_ENCRYPT push %rbp @@ -81,6 +84,19 @@ ENTRY(set_sev_encryption_mask) bts %rax, sme_me_mask(%rip) /* Create the encryption mask */ + /* + * Read MSR_AMD64_SEV again and store it to sev_status. Can't do this in + * get_sev_encryption_bit() because this function is 32-bit code and + * shared between 64-bit and 32-bit boot path. + */ + movl $MSR_AMD64_SEV, %ecx /* Read the SEV MSR */ + rdmsr + + /* Store MSR value in sev_status */ + shlq $32, %rdx + orq %rdx, %rax + movq %rax, sev_status(%rip) + .Lno_sev_mask: movq %rbp, %rsp /* Restore original stack pointer */ @@ -96,6 +112,7 @@ ENDPROC(set_sev_encryption_mask) #ifdef CONFIG_AMD_MEM_ENCRYPT .balign 8 -GLOBAL(sme_me_mask) - .quad 0 +SYM_DATA(sme_me_mask, .quad 0) +SYM_DATA(sev_status, .quad 0) +SYM_DATA(sev_check_data, .quad 0) #endif diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 9652d5c2afda84d5bf2dbfa6ad67f53f855609ff..dba49e75095a81450ae48d0e9bc4a2969d7effc4 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -441,6 +441,13 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, parse_elf(output); handle_relocations(output, output_len, virt_addr); debug_putstr("done.\nBooting the kernel.\n"); + + /* + * Flush GHCB from cache and map it encrypted again when running as + * SEV-ES guest. + */ + sev_es_shutdown_ghcb(); + return output; } diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index c8181392f70d7d19b8f806c667ea8770a1090664..60694f17705653a818c2a644b402f3f32a0fe175 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -23,6 +23,7 @@ #include #include #include +#include #define BOOT_CTYPE_H #include @@ -36,6 +37,9 @@ #define memptr unsigned #endif +/* boot/compressed/vmlinux start and end markers */ +extern char _head[], _end[]; + /* misc.c */ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; @@ -81,8 +85,6 @@ void choose_random_location(unsigned long input, unsigned long *output, unsigned long output_size, unsigned long *virt_addr); -/* cpuflags.c */ -bool has_cpuflag(int flag); #else static inline void choose_random_location(unsigned long input, unsigned long input_size, @@ -93,18 +95,14 @@ static inline void choose_random_location(unsigned long input, } #endif +/* cpuflags.c */ +bool has_cpuflag(int flag); + #ifdef CONFIG_X86_64 -void initialize_identity_maps(void); -void add_identity_map(unsigned long start, unsigned long size); -void finalize_identity_maps(void); +extern int set_page_decrypted(unsigned long address); +extern int set_page_encrypted(unsigned long address); +extern int set_page_non_present(unsigned long address); extern unsigned char _pgtable[]; -#else -static inline void initialize_identity_maps(void) -{ } -static inline void add_identity_map(unsigned long start, unsigned long size) -{ } -static inline void finalize_identity_maps(void) -{ } #endif #ifdef CONFIG_EARLY_PRINTK @@ -119,6 +117,17 @@ static inline void console_init(void) void set_sev_encryption_mask(void); +#ifdef CONFIG_AMD_MEM_ENCRYPT +void sev_es_shutdown_ghcb(void); +extern bool sev_es_check_ghcb_fault(unsigned long address); +#else +static inline void sev_es_shutdown_ghcb(void) { } +static inline bool sev_es_check_ghcb_fault(unsigned long address) +{ + return false; +} +#endif + /* acpi.c */ #ifdef CONFIG_ACPI acpi_physical_address get_rsdp_addr(void); @@ -133,4 +142,23 @@ int count_immovable_mem_regions(void); 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 + +/* Used by PAGE_KERN* macros: */ +extern pteval_t __default_kernel_pte_mask; + +/* idt_64.c */ +extern gate_desc boot_idt[BOOT_IDT_ENTRIES]; +extern struct desc_ptr boot_idt_desc; + +/* IDT Entry Points */ +void boot_page_fault(void); +void boot_stage1_vc(void); +void boot_stage2_vc(void); + +unsigned long sev_verify_cbit(unsigned long cr3); + #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 7d0394f4ebf978cc1b0051eb6adae702231daa47..5def1674d6f1990dd9bded8c4cd1267349f002d0 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -8,6 +8,13 @@ #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; @@ -198,4 +205,13 @@ void cleanup_trampoline(void *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/sev-es.c b/arch/x86/boot/compressed/sev-es.c new file mode 100644 index 0000000000000000000000000000000000000000..27826c265aab484770a3b82b7cde24116cb66d7b --- /dev/null +++ b/arch/x86/boot/compressed/sev-es.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AMD Encrypted Register State Support + * + * Author: Joerg Roedel + */ + +/* + * misc.h needs to be first because it knows how to include the other kernel + * headers in the pre-decompression code in a way that does not break + * compilation. + */ +#include "misc.h" + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "error.h" + +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) +{ + unsigned long low, high; + + asm volatile("rdmsr" : "=a" (low), "=d" (high) : + "c" (MSR_AMD64_SEV_ES_GHCB)); + + return ((high << 32) | low); +} + +static inline void sev_es_wr_ghcb_msr(u64 val) +{ + u32 low, high; + + low = val & 0xffffffffUL; + high = val >> 32; + + asm volatile("wrmsr" : : "c" (MSR_AMD64_SEV_ES_GHCB), + "a"(low), "d" (high) : "memory"); +} + +static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt) +{ + char buffer[MAX_INSN_SIZE]; + enum es_result ret; + + memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE); + + insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE, 1); + insn_get_length(&ctxt->insn); + + ret = ctxt->insn.immediate.got ? ES_OK : ES_DECODE_FAILED; + + return ret; +} + +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" + +/* Include code for early handlers */ +#include "../../kernel/sev-es-shared.c" + +static bool early_setup_sev_es(void) +{ + if (!sev_es_negotiate_protocol()) + sev_es_terminate(GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED); + + if (set_page_decrypted((unsigned long)&boot_ghcb_page)) + return false; + + /* Page is now mapped decrypted, clear it */ + memset(&boot_ghcb_page, 0, sizeof(boot_ghcb_page)); + + boot_ghcb = &boot_ghcb_page; + + /* Initialize lookup tables for the instruction decoder */ + inat_init_tables(); + + return true; +} + +void sev_es_shutdown_ghcb(void) +{ + if (!boot_ghcb) + return; + + if (!sev_es_check_cpu_features()) + error("SEV-ES CPU Features missing."); + + /* + * 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. + */ + if (set_page_encrypted((unsigned long)&boot_ghcb_page)) + error("Can't map GHCB page encrypted"); + + /* + * GHCB page is mapped encrypted again and flushed from the cache. + * Mark it non-present now to catch bugs when #VC exceptions trigger + * after this point. + */ + if (set_page_non_present((unsigned long)&boot_ghcb_page)) + error("Can't unmap GHCB page"); +} + +bool sev_es_check_ghcb_fault(unsigned long address) +{ + /* Check whether the fault was on the GHCB page */ + 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_sev_es()) + sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + + 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) { + /* + * For now, just halt the machine. That makes debugging easier, + * later we just call sev_es_terminate() here. + */ + while (true) + asm volatile("hlt\n"); + } +} diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index 508cfa6828c5d88cd8f616e28df686ec625dd5f5..3a017206535f105cb3d83baac0dc815103a50d64 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -43,11 +43,12 @@ SECTIONS _erodata = . ; } .got : { - _got = .; - KEEP(*(.got.plt)) - KEEP(*(.got)) - _egot = .; + *(.got) } + .got.plt : { + *(.got.plt) + } + .data : { _data = . ; *(.data) @@ -74,3 +75,10 @@ SECTIONS . = ALIGN(PAGE_SIZE); /* keep ZO size page aligned */ _end = .; } + +ASSERT(SIZEOF(.got) == 0, "Unexpected GOT entries detected!") +#ifdef CONFIG_X86_64 +ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, "Unexpected GOT/PLT entries detected!") +#else +ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0xc, "Unexpected GOT/PLT entries detected!") +#endif diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 47179aae68287ff748eea7bca8ea4b1a9dc9717c..f48d9d293f789446adb532a1f9d391958f8a2521 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -435,3 +435,106 @@ __visible long do_fast_syscall_32(struct pt_regs *regs) #endif } #endif + +/** + * idtentry_enter - Handle state tracking on idtentry + * @regs: Pointer to pt_regs of interrupted context + * + * Invokes: + * - lockdep irqflag state tracking as low level ASM entry disabled + * interrupts. + * + * - Context tracking if the exception hit user mode. + * + * - RCU notification if the exception hit kernel mode. + * + * - The hardirq tracer to keep the state consistent as low level ASM + * entry disabled interrupts. + */ +void noinstr idtentry_enter(struct pt_regs *regs) +{ + if (user_mode(regs)) { + enter_from_user_mode(); + } else { + lockdep_hardirqs_off(CALLER_ADDR0); + rcu_irq_enter(); + instrumentation_begin(); + trace_hardirqs_off_prepare(); + instrumentation_end(); + } +} + +/** + * idtentry_exit - Common code to handle return from exceptions + * @regs: Pointer to pt_regs (exception entry regs) + * + * Depending on the return target (kernel/user) this runs the necessary + * preemption and work checks if possible and required and returns to + * the caller with interrupts disabled and no further work pending. + * + * This is the last action before returning to the low level ASM code which + * just needs to return to the appropriate context. + * + * Invoked by all exception/interrupt IDTENTRY handlers which are not + * returning through the paranoid exit path (all except NMI, #DF and the IST + * variants of #MC and #DB) and are therefore on the thread stack. + */ +void noinstr idtentry_exit(struct pt_regs *regs) +{ + lockdep_assert_irqs_disabled(); + + /* Check whether this returns to user mode */ + if (user_mode(regs)) { + prepare_exit_to_usermode(regs); + } else if (regs->flags & X86_EFLAGS_IF) { + /* Check kernel preemption, if enabled */ + if (IS_ENABLED(CONFIG_PREEMPTION)) { + /* + * This needs to be done very carefully. + * idtentry_enter() invoked rcu_irq_enter(). This + * needs to be undone before scheduling. + * + * Preemption is disabled inside of RCU idle + * sections. When the task returns from + * preempt_schedule_irq(), RCU is still watching. + * + * rcu_irq_exit_preempt() has additional state + * checking if CONFIG_PROVE_RCU=y + * + * NOTE: this tree has no rcu_irq_exit_preempt(); + * the rcu_irq_exit() call below is logically + * equivalent. + */ + if (!preempt_count()) { + if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) + WARN_ON_ONCE(!on_thread_stack()); + instrumentation_begin(); + rcu_irq_exit(); + if (need_resched()) + preempt_schedule_irq(); + /* Covers both tracing and lockdep */ + trace_hardirqs_on(); + instrumentation_end(); + return; + } + } + /* + * If preemption is disabled then this needs to be done + * carefully with respect to RCU. The exception might come + * from a RCU idle section in the idle task due to the fact + * that safe_halt() enables interrupts. So this needs the + * same ordering of lockdep/tracing and RCU as the return + * to user mode path. + */ + instrumentation_begin(); + /* Tell the tracer that IRET will enable interrupts */ + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + instrumentation_end(); + rcu_irq_exit(); + lockdep_hardirqs_on(CALLER_ADDR0); + } else { + /* IRQ flags state is correct already. Just tell RCU */ + rcu_irq_exit(); + } +} diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 740df9cc219635ee312a61cb856d6750f93668ac..a9d20754afed5cacfc5993aaca331ad862f1bde5 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -726,6 +726,12 @@ .Lend_\@: .endm +/* + * Include the defines which emit the idt entries which are shared + * shared between 32 and 64 bit. + */ +#include + /* * %eax: prev task * %edx: next task diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 67cdca196aee1fadd97a3a1bdf1a78c5afc28efc..3ef08d52519b1f7b54268336f845f15383355df8 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -157,13 +157,15 @@ ENTRY(entry_SYSCALL_64) SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp +SYM_INNER_LABEL(entry_SYSCALL_64_safe_stack, SYM_L_GLOBAL) + /* Construct struct pt_regs on stack */ pushq $__USER_DS /* pt_regs->ss */ pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2) /* pt_regs->sp */ pushq %r11 /* pt_regs->flags */ pushq $__USER_CS /* pt_regs->cs */ pushq %rcx /* pt_regs->ip */ -GLOBAL(entry_SYSCALL_64_after_hwframe) +SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) pushq %rax /* pt_regs->orig_ax */ PUSH_AND_CLEAR_REGS rax=$-ENOSYS @@ -624,7 +626,7 @@ GLOBAL(retint_user) call prepare_exit_to_usermode TRACE_IRQS_IRETQ -GLOBAL(swapgs_restore_regs_and_return_to_usermode) +SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) IBRS_EXIT #ifdef CONFIG_DEBUG_ENTRY /* Assert that pt_regs indicates user mode. */ @@ -684,7 +686,7 @@ retint_kernel: */ TRACE_IRQS_IRETQ -GLOBAL(restore_regs_and_return_to_kernel) +SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL) #ifdef CONFIG_DEBUG_ENTRY /* Assert that pt_regs indicates kernel mode. */ testb $3, CS(%rsp) @@ -935,6 +937,84 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt .endm +#ifdef CONFIG_AMD_MEM_ENCRYPT +/** + * idtentry_vc - Macro to generate entry stub for #VC + * @vector: Vector number + * @asmsym: ASM symbol for the entry point + * @cfunc: C function to be called + * + * The macro emits code to set up the kernel context for #VC. The #VC handler + * runs on an IST stack and needs to be able to cause nested #VC exceptions. + * + * To make this work the #VC entry code tries its best to pretend it doesn't use + * an IST stack by switching to the task stack if coming from user-space (which + * includes early SYSCALL entry path) or back to the stack in the IRET frame if + * entered from kernel-mode. + * + * If entered from kernel-mode the return stack is validated first, and if it is + * not safe to use (e.g. because it points to the entry stack) the #VC handler + * will switch to a fall-back stack (VC2) and call a special handler function. + * + * The macro is only used for one vector, but it is planned to be extended in + * the future for the #HV exception. + */ +.macro idtentry_vc vector asmsym cfunc +SYM_CODE_START(\asmsym) + UNWIND_HINT_IRET_REGS + ASM_CLAC + + /* + * If the entry is from userspace, switch stacks and treat it as + * a normal entry. + */ + testb $3, CS-ORIG_RAX(%rsp) + jnz .Lfrom_usermode_switch_stack_\@ + + /* + * paranoid_entry returns SWAPGS flag for paranoid_exit in EBX. + * EBX == 0 -> SWAPGS, EBX == 1 -> no SWAPGS + */ + call paranoid_entry + + UNWIND_HINT_REGS + + /* + * Switch off the IST stack to make it free for nested exceptions. The + * vc_switch_off_ist() function will switch back to the interrupted + * stack if it is safe to do so. If not it switches to the VC fall-back + * stack. + */ + movq %rsp, %rdi /* pt_regs pointer */ + call vc_switch_off_ist + movq %rax, %rsp /* Switch to new stack */ + + UNWIND_HINT_REGS + + /* Update pt_regs */ + movq ORIG_RAX(%rsp), %rsi /* get error code into 2nd argument*/ + movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */ + + movq %rsp, %rdi /* pt_regs pointer */ + + call \cfunc + + /* + * No need to switch back to the IST stack. The current stack is either + * identical to the stack in the IRET frame or the VC fall-back stack, + * so it is definitly mapped even with PTI enabled. + */ + jmp paranoid_exit + + /* Switch to the regular task stack */ +.Lfrom_usermode_switch_stack_\@: + idtentry_part safe_stack_\cfunc, has_error_code=1, read_cr2=0, paranoid=0 + +_ASM_NOKPROBE(\asmsym) +SYM_CODE_END(\asmsym) +.endm +#endif + /** * idtentry - Generate an IDT entry stub * @sym: Name of the generated entry point @@ -1027,20 +1107,45 @@ _ASM_NOKPROBE(\sym) END(\sym) .endm +/* + * Include the defines which emit the idt entries which are shared + * shared between 32 and 64 bit. + */ +#include + idtentry divide_error do_divide_error has_error_code=0 idtentry overflow do_overflow has_error_code=0 +idtentry int3 do_int3 has_error_code=0 create_gap=1 idtentry bounds do_bounds has_error_code=0 idtentry invalid_op do_invalid_op has_error_code=0 idtentry device_not_available do_device_not_available has_error_code=0 -idtentry double_fault do_double_fault has_error_code=1 paranoid=2 read_cr2=1 idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0 idtentry invalid_TSS do_invalid_TSS has_error_code=1 idtentry segment_not_present do_segment_not_present has_error_code=1 +idtentry stack_segment do_stack_segment has_error_code=1 +idtentry general_protection do_general_protection has_error_code=1 idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0 idtentry coprocessor_error do_coprocessor_error has_error_code=0 idtentry alignment_check do_alignment_check has_error_code=1 idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0 +idtentry page_fault do_page_fault has_error_code=1 read_cr2=1 + +#ifdef CONFIG_KVM_GUEST +idtentry async_page_fault do_async_page_fault has_error_code=1 read_cr2=1 +#endif + +#ifdef CONFIG_X86_MCE +idtentry machine_check do_mce has_error_code=0 paranoid=1 +#endif +idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=IST_INDEX_DB ist_offset=DB_STACK_OFFSET +idtentry double_fault do_double_fault has_error_code=1 paranoid=2 read_cr2=1 + +#ifdef CONFIG_XEN_PV +idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0 +idtentry xennmi do_nmi has_error_code=0 +idtentry xendebug do_debug has_error_code=0 +#endif /* * Reload gs selector with exception handling @@ -1066,7 +1171,7 @@ EXPORT_SYMBOL(native_load_gs_index) _ASM_EXTABLE(.Lgs_change, .Lbad_gs) .section .fixup, "ax" /* running with kernelgs */ -.Lbad_gs: +SYM_CODE_START_LOCAL_NOALIGN(.Lbad_gs) SWAPGS /* switch back to user gs */ .macro ZAP_GS /* This can't be a string because the preprocessor needs to see it. */ @@ -1077,6 +1182,7 @@ EXPORT_SYMBOL(native_load_gs_index) xorl %eax, %eax movl %eax, %gs jmp 2b +SYM_CODE_END(.Lbad_gs) .previous /* Call softirq on interrupt stack. Interrupts are off. */ @@ -1091,8 +1197,6 @@ ENTRY(do_softirq_own_stack) ENDPROC(do_softirq_own_stack) #ifdef CONFIG_XEN_PV -idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0 - /* * A note on the "critical region" in our callback handler. * We want to avoid stacking callback handlers due to events occurring @@ -1194,26 +1298,6 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ acrn_hv_callback_vector acrn_hv_vector_handler #endif -idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=IST_INDEX_DB ist_offset=DB_STACK_OFFSET -idtentry int3 do_int3 has_error_code=0 create_gap=1 -idtentry stack_segment do_stack_segment has_error_code=1 - -#ifdef CONFIG_XEN_PV -idtentry xennmi do_nmi has_error_code=0 -idtentry xendebug do_debug has_error_code=0 -#endif - -idtentry general_protection do_general_protection has_error_code=1 -idtentry page_fault do_page_fault has_error_code=1 read_cr2=1 - -#ifdef CONFIG_KVM_GUEST -idtentry async_page_fault do_async_page_fault has_error_code=1 read_cr2=1 -#endif - -#ifdef CONFIG_X86_MCE -idtentry machine_check do_mce has_error_code=0 paranoid=1 -#endif - /* * Save all registers in pt_regs. Return GSBASE related information * in EBX depending on the availability of the FSGSBASE instructions: diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index c3c4ea4a6711aa4e03712cffeb1d3a03a3499e1f..a74deba50becd4637a7dc261a91f97ac5bc3fcf5 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -149,7 +149,7 @@ ENTRY(entry_SYSENTER_compat) pushq $X86_EFLAGS_FIXED popfq jmp .Lsysenter_flags_fixed -GLOBAL(__end_entry_SYSENTER_compat) +SYM_INNER_LABEL(__end_entry_SYSENTER_compat, SYM_L_GLOBAL) ENDPROC(entry_SYSENTER_compat) /* @@ -218,7 +218,7 @@ ENTRY(entry_SYSCALL_compat) pushq %r11 /* pt_regs->flags */ pushq $__USER32_CS /* pt_regs->cs */ pushq %rcx /* pt_regs->ip */ -GLOBAL(entry_SYSCALL_compat_after_hwframe) +SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) movl %eax, %eax /* discard orig_ax high bits */ pushq %rax /* pt_regs->orig_ax */ pushq %rdi /* pt_regs->di */ diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S index 263d7433dea8587b237aefc184a0247a4fac1fbf..de1fff7188aad1a5074f0823372ac97fb9f54b14 100644 --- a/arch/x86/entry/vdso/vdso32/system_call.S +++ b/arch/x86/entry/vdso/vdso32/system_call.S @@ -62,7 +62,7 @@ __kernel_vsyscall: /* Enter using int $0x80 */ int $0x80 -GLOBAL(int80_landing_pad) +SYM_INNER_LABEL(int80_landing_pad, SYM_L_GLOBAL) /* * Restore EDX and ECX in case they were clobbered. EBP is not diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h index 0d1d37d8b279f6e0c0d5a9e08523be8f84b32123..5c045d7627330bfd2e6c1f90ce88897421ded27d 100644 --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -10,7 +10,7 @@ #ifdef CONFIG_X86_64 /* Macro to enforce the same ordering and stack sizes */ -#define ESTACKS_MEMBERS(guardsize, db2_holesize)\ +#define ESTACKS_MEMBERS(guardsize, db2_holesize, optional_stack_size)\ char DF_stack_guard[guardsize]; \ char DF_stack[EXCEPTION_STKSZ]; \ char NMI_stack_guard[guardsize]; \ @@ -23,16 +23,20 @@ char DB_stack[EXCEPTION_STKSZ]; \ char MCE_stack_guard[guardsize]; \ char MCE_stack[EXCEPTION_STKSZ]; \ + char VC_stack_guard[guardsize]; \ + char VC_stack[optional_stack_size]; \ + char VC2_stack_guard[guardsize]; \ + char VC2_stack[optional_stack_size]; \ char IST_top_guard[guardsize]; \ /* The exception stacks' physical storage. No guard pages required */ struct exception_stacks { - ESTACKS_MEMBERS(0, 0) + ESTACKS_MEMBERS(0, 0, 0) }; /* The effective cpu entry area mapping with guard pages. */ struct cea_exception_stacks { - ESTACKS_MEMBERS(PAGE_SIZE, EXCEPTION_STKSZ) + ESTACKS_MEMBERS(PAGE_SIZE, EXCEPTION_STKSZ, EXCEPTION_STKSZ) }; /* @@ -45,6 +49,8 @@ enum exception_stack_ordering { ESTACK_DB1, ESTACK_DB, ESTACK_MCE, + ESTACK_VC, + ESTACK_VC2, N_EXCEPTION_STACKS }; @@ -141,4 +147,7 @@ static __always_inline struct entry_stack *cpu_entry_stack(int cpu) #define __this_cpu_ist_top_va(name) \ CEA_ESTACK_TOP(__this_cpu_read(cea_exception_stacks), name) +#define __this_cpu_ist_bottom_va(name) \ + CEA_ESTACK_BOT(__this_cpu_read(cea_exception_stacks), name) + #endif diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 68a99d2a5f335d6b6b059624e0e2aa1d38d60a4d..80bf63c080079960642d53f70e003c9404517ee3 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -389,6 +389,33 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) void update_intr_gate(unsigned int n, const void *addr); void alloc_intr_gate(unsigned int n, const void *addr); +static inline void init_idt_data(struct idt_data *data, unsigned int n, + const void *addr) +{ + BUG_ON(n > 0xFF); + + memset(data, 0, sizeof(*data)); + data->vector = n; + data->addr = addr; + data->segment = __KERNEL_CS; + data->bits.type = GATE_INTERRUPT; + data->bits.p = 1; +} + +static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d) +{ + unsigned long addr = (unsigned long) d->addr; + + gate->offset_low = (u16) addr; + gate->segment = (u16) d->segment; + gate->bits = d->bits; + gate->offset_middle = (u16) (addr >> 16); +#ifdef CONFIG_X86_64 + gate->offset_high = (u32) (addr >> 32); + gate->reserved = 0; +#endif +} + extern unsigned long system_vectors[]; #ifdef CONFIG_X86_64 diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h index a91f3b6e4f2a956bf1a23bb65ae13952e1633bb7..f7e7099af595c98aa53611949c008a7beae33cbb 100644 --- a/arch/x86/include/asm/desc_defs.h +++ b/arch/x86/include/asm/desc_defs.h @@ -74,6 +74,13 @@ struct idt_bits { p : 1; } __attribute__((packed)); +struct idt_data { + unsigned int vector; + unsigned int segment; + struct idt_bits bits; + const void *addr; +}; + struct gate_struct { u16 offset_low; u16 segment; @@ -109,6 +116,9 @@ struct desc_ptr { #endif /* !__ASSEMBLY__ */ +/* Boot IDT definitions */ +#define BOOT_IDT_ENTRIES 32 + /* Access rights as returned by LAR */ #define AR_TYPE_RODATA (0 * (1 << 9)) #define AR_TYPE_RWDATA (1 * (1 << 9)) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 20e3f67845f17961e60233a54281ea36f37a034c..ee9658a3ec3743484ed9a7d4e6b2e21c908ce4c2 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -664,36 +665,4 @@ static inline void switch_kernel_fpu_finish(struct task_struct *next) } #endif -/* - * MXCSR and XCR definitions: - */ - -static inline void ldmxcsr(u32 mxcsr) -{ - asm volatile("ldmxcsr %0" :: "m" (mxcsr)); -} - -extern unsigned int mxcsr_feature_mask; - -#define XCR_XFEATURE_ENABLED_MASK 0x00000000 - -static inline u64 xgetbv(u32 index) -{ - u32 eax, edx; - - asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */ - : "=a" (eax), "=d" (edx) - : "c" (index)); - return eax + ((u64)edx << 32); -} - -static inline void xsetbv(u32 index, u64 value) -{ - u32 eax = value; - u32 edx = value >> 32; - - asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */ - : : "a" (eax), "d" (edx), "c" (index)); -} - #endif /* _ASM_X86_FPU_INTERNAL_H */ diff --git a/arch/x86/include/asm/fpu/xcr.h b/arch/x86/include/asm/fpu/xcr.h new file mode 100644 index 0000000000000000000000000000000000000000..1c7ab8d95da5ab2bef213081db153e5b7738a9c8 --- /dev/null +++ b/arch/x86/include/asm/fpu/xcr.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_FPU_XCR_H +#define _ASM_X86_FPU_XCR_H + +/* + * MXCSR and XCR definitions: + */ + +static inline void ldmxcsr(u32 mxcsr) +{ + asm volatile("ldmxcsr %0" :: "m" (mxcsr)); +} + +extern unsigned int mxcsr_feature_mask; + +#define XCR_XFEATURE_ENABLED_MASK 0x00000000 + +static inline u64 xgetbv(u32 index) +{ + u32 eax, edx; + + asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index)); + return eax + ((u64)edx << 32); +} + +static inline void xsetbv(u32 index, u64 value) +{ + u32 eax = value; + u32 edx = value >> 32; + + asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); +} + +#endif /* _ASM_X86_FPU_XCR_H */ diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h new file mode 100644 index 0000000000000000000000000000000000000000..acf7eee45e9182ee84606fb2fe4451e5bde19805 --- /dev/null +++ b/arch/x86/include/asm/idtentry.h @@ -0,0 +1,353 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_IDTENTRY_H +#define _ASM_X86_IDTENTRY_H + +/* Interrupts/Exceptions */ +#include + +#ifndef __ASSEMBLY__ + +void idtentry_enter(struct pt_regs *regs); +void idtentry_exit(struct pt_regs *regs); + +/** + * DECLARE_IDTENTRY - Declare functions for simple IDT entry points + * No error code pushed by hardware + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Declares three functions: + * - The ASM entry point: asm_##func + * - The XEN PV trap entry point: xen_##func (maybe unused) + * - The C handler called from the ASM entry point + * + * Note: This is the C variant of DECLARE_IDTENTRY(). As the name says it + * declares the entry points for usage in C code. There is an ASM variant + * as well which is used to emit the entry stubs in entry_32/64.S. + */ +#define DECLARE_IDTENTRY(vector, func) \ + asmlinkage void asm_##func(void); \ + asmlinkage void xen_asm_##func(void); \ + __visible void func(struct pt_regs *regs) + +/** + * DEFINE_IDTENTRY - Emit code for simple IDT entry points + * @func: Function name of the entry point + * + * @func is called from ASM entry code with interrupts disabled. + * + * The macro is written so it acts as function definition. Append the + * body with a pair of curly brackets. + * + * idtentry_enter() contains common code which has to be invoked before + * arbitrary code in the body. idtentry_exit() contains common code + * which has to run before returning to the low level assembly code. + */ +#define DEFINE_IDTENTRY(func) \ +static __always_inline void __##func(struct pt_regs *regs); \ + \ +__visible noinstr void func(struct pt_regs *regs) \ +{ \ + idtentry_enter(regs); \ + instrumentation_begin(); \ + __##func (regs); \ + instrumentation_end(); \ + idtentry_exit(regs); \ +} \ + \ +static __always_inline void __##func(struct pt_regs *regs) + +/** + * DECLARE_IDTENTRY_ERRORCODE - Declare functions for simple IDT entry points + * Error code pushed by hardware + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Declares three functions: + * - The ASM entry point: asm_##func + * - The XEN PV trap entry point: xen_##func (maybe unused) + * - The C handler called from the ASM entry point + * + * Same as DECLARE_IDTENTRY, but has an extra error_code argument for the + * C-handler. + */ +#define DECLARE_IDTENTRY_ERRORCODE(vector, func) \ + asmlinkage void asm_##func(void); \ + asmlinkage void xen_asm_##func(void); \ + __visible void func(struct pt_regs *regs, unsigned long error_code) + +/** + * DEFINE_IDTENTRY_ERRORCODE - Emit code for simple IDT entry points + * Error code pushed by hardware + * @func: Function name of the entry point + * + * Same as DEFINE_IDTENTRY, but has an extra error_code argument + */ +#define DEFINE_IDTENTRY_ERRORCODE(func) \ +static __always_inline void __##func(struct pt_regs *regs, \ + unsigned long error_code); \ + \ +__visible noinstr void func(struct pt_regs *regs, \ + unsigned long error_code) \ +{ \ + idtentry_enter(regs); \ + instrumentation_begin(); \ + __##func (regs, error_code); \ + instrumentation_end(); \ + idtentry_exit(regs); \ +} \ + \ +static __always_inline void __##func(struct pt_regs *regs, \ + unsigned long error_code) + +/** + * DECLARE_IDTENTRY_RAW - Declare functions for raw IDT entry points + * No error code pushed by hardware + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Maps to DECLARE_IDTENTRY(). + */ +#define DECLARE_IDTENTRY_RAW(vector, func) \ + DECLARE_IDTENTRY(vector, func) + +/** + * DEFINE_IDTENTRY_RAW - Emit code for raw IDT entry points + * @func: Function name of the entry point + * + * @func is called from ASM entry code with interrupts disabled. + * + * The macro is written so it acts as function definition. Append the + * body with a pair of curly brackets. + * + * Contrary to DEFINE_IDTENTRY() this does not invoke the + * idtentry_enter/exit() helpers before and after the body invocation. This + * needs to be done in the body itself if applicable. Use if extra work + * is required before the enter/exit() helpers are invoked. + */ +#define DEFINE_IDTENTRY_RAW(func) \ +__visible noinstr void func(struct pt_regs *regs) + +/** + * DECLARE_IDTENTRY_RAW_ERRORCODE - Declare functions for raw IDT entry points + * Error code pushed by hardware + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Maps to DECLARE_IDTENTRY_ERRORCODE() + */ +#define DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func) \ + DECLARE_IDTENTRY_ERRORCODE(vector, func) + +/** + * DEFINE_IDTENTRY_RAW_ERRORCODE - Emit code for raw IDT entry points + * @func: Function name of the entry point + * + * @func is called from ASM entry code with interrupts disabled. + * + * The macro is written so it acts as function definition. Append the + * body with a pair of curly brackets. + * + * Contrary to DEFINE_IDTENTRY_ERRORCODE() this does not invoke the + * idtentry_enter/exit() helpers before and after the body invocation. This + * needs to be done in the body itself if applicable. Use if extra work + * is required before the enter/exit() helpers are invoked. + */ +#define DEFINE_IDTENTRY_RAW_ERRORCODE(func) \ +__visible noinstr void func(struct pt_regs *regs, unsigned long error_code) + + +#ifdef CONFIG_X86_64 +/** + * DECLARE_IDTENTRY_IST - Declare functions for IST handling IDT entry points + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Maps to DECLARE_IDTENTRY_RAW, but declares also the NOIST C handler + * which is called from the ASM entry point on user mode entry + */ +#define DECLARE_IDTENTRY_IST(vector, func) \ + DECLARE_IDTENTRY_RAW(vector, func); \ + __visible void noist_##func(struct pt_regs *regs) + +/** + * DECLARE_IDTENTRY_VC - Declare functions for the VC entry point + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Maps to DECLARE_IDTENTRY_RAW_ERRORCODE, but declares also the + * safe_stack C handler. + */ +#define DECLARE_IDTENTRY_VC(vector, func) \ + DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func); \ + __visible noinstr void ist_##func(struct pt_regs *regs, unsigned long error_code); \ + __visible noinstr void safe_stack_##func(struct pt_regs *regs, unsigned long error_code) + +/** + * DEFINE_IDTENTRY_IST - Emit code for IST entry points + * @func: Function name of the entry point + * + * Maps to DEFINE_IDTENTRY_RAW + */ +#define DEFINE_IDTENTRY_IST(func) \ + DEFINE_IDTENTRY_RAW(func) + +/** + * DEFINE_IDTENTRY_NOIST - Emit code for NOIST entry points which + * belong to a IST entry point (MCE, DB) + * @func: Function name of the entry point. Must be the same as + * the function name of the corresponding IST variant + * + * Maps to DEFINE_IDTENTRY_RAW(). + */ +#define DEFINE_IDTENTRY_NOIST(func) \ + DEFINE_IDTENTRY_RAW(noist_##func) + +/** + * DECLARE_IDTENTRY_DF - Declare functions for double fault + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Maps to DECLARE_IDTENTRY_RAW_ERRORCODE + */ +#define DECLARE_IDTENTRY_DF(vector, func) \ + DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func) + +/** + * DEFINE_IDTENTRY_DF - Emit code for double fault + * @func: Function name of the entry point + * + * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE + */ +#define DEFINE_IDTENTRY_DF(func) \ + DEFINE_IDTENTRY_RAW_ERRORCODE(func) + +/** + * DEFINE_IDTENTRY_VC_SAFE_STACK - Emit code for VMM communication handler + which runs on a safe stack. + * @func: Function name of the entry point + * + * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE + */ +#define DEFINE_IDTENTRY_VC_SAFE_STACK(func) \ + DEFINE_IDTENTRY_RAW_ERRORCODE(safe_stack_##func) + +/** + * DEFINE_IDTENTRY_VC_IST - Emit code for VMM communication handler + which runs on the VC fall-back stack + * @func: Function name of the entry point + * + * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE + */ +#define DEFINE_IDTENTRY_VC_IST(func) \ + DEFINE_IDTENTRY_RAW_ERRORCODE(ist_##func) + +/** + * DEFINE_IDTENTRY_VC - Emit code for VMM communication handler + * @func: Function name of the entry point + * + * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE + */ +#define DEFINE_IDTENTRY_VC(func) \ + DEFINE_IDTENTRY_RAW_ERRORCODE(func) + +#else /* CONFIG_X86_64 */ + +/* Maps to a regular IDTENTRY on 32bit for now */ +# define DECLARE_IDTENTRY_IST DECLARE_IDTENTRY +# define DEFINE_IDTENTRY_IST DEFINE_IDTENTRY + +/** + * DECLARE_IDTENTRY_DF - Declare functions for double fault 32bit variant + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Declares two functions: + * - The ASM entry point: asm_##func + * - The C handler called from the C shim + */ +#define DECLARE_IDTENTRY_DF(vector, func) \ + asmlinkage void asm_##func(void); \ + __visible void func(struct pt_regs *regs, \ + unsigned long error_code, \ + unsigned long address) + +/** + * DEFINE_IDTENTRY_DF - Emit code for double fault on 32bit + * @func: Function name of the entry point + * + * This is called through the doublefault shim which already provides + * cr2 in the address argument. + */ +#define DEFINE_IDTENTRY_DF(func) \ +__visible noinstr void func(struct pt_regs *regs, \ + unsigned long error_code, \ + unsigned long address) + +#endif /* !CONFIG_X86_64 */ + +/* C-Code mapping */ +#define DECLARE_IDTENTRY_MCE DECLARE_IDTENTRY_IST +#define DEFINE_IDTENTRY_MCE DEFINE_IDTENTRY_IST +#define DEFINE_IDTENTRY_MCE_USER DEFINE_IDTENTRY_NOIST + +#define DECLARE_IDTENTRY_NMI DECLARE_IDTENTRY_IST +#define DEFINE_IDTENTRY_NMI DEFINE_IDTENTRY_IST + +#define DECLARE_IDTENTRY_DEBUG DECLARE_IDTENTRY_IST +#define DEFINE_IDTENTRY_DEBUG DEFINE_IDTENTRY_IST +#define DEFINE_IDTENTRY_DEBUG_USER DEFINE_IDTENTRY_NOIST + +#else /* !__ASSEMBLY__ */ + +/* + * The ASM variants for DECLARE_IDTENTRY*() which emit the ASM entry stubs. + */ +#define DECLARE_IDTENTRY(vector, func) \ + idtentry vector asm_##func func has_error_code=0 sane=1 + +#define DECLARE_IDTENTRY_ERRORCODE(vector, func) \ + idtentry vector asm_##func func has_error_code=1 sane=1 + +#define DECLARE_IDTENTRY_RAW(vector, func) \ + DECLARE_IDTENTRY(vector, func) + +#define DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func) \ + DECLARE_IDTENTRY_ERRORCODE(vector, func) + +#ifdef CONFIG_X86_64 +# define DECLARE_IDTENTRY_MCE(vector, func) \ + idtentry_mce_db vector asm_##func func + +# define DECLARE_IDTENTRY_DEBUG(vector, func) \ + idtentry_mce_db vector asm_##func func + +# define DECLARE_IDTENTRY_DF(vector, func) \ + idtentry_df vector asm_##func func + +# define DECLARE_IDTENTRY_VC(vector, func) \ + idtentry_vc vector asm_##func func + +#else +# define DECLARE_IDTENTRY_MCE(vector, func) \ + DECLARE_IDTENTRY(vector, func) + +# define DECLARE_IDTENTRY_DEBUG(vector, func) \ + DECLARE_IDTENTRY(vector, func) + +/* No ASM emitted for DF as this goes through a C shim */ +# define DECLARE_IDTENTRY_DF(vector, func) + +#endif + +/* No ASM code emitted for NMI */ +#define DECLARE_IDTENTRY_NMI(vector, func) + +#endif /* __ASSEMBLY__ */ + +/* #VC */ +#ifdef CONFIG_AMD_MEM_ENCRYPT +DECLARE_IDTENTRY_VC(X86_TRAP_VC, exc_vmm_communication); +#endif + +#endif diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h index 2b6ccf2c49f11c9c54fbe448ea7d33d997b99ca6..a0f839aa144d9eeb347247e7f79e07683b5564f8 100644 --- a/arch/x86/include/asm/insn-eval.h +++ b/arch/x86/include/asm/insn-eval.h @@ -15,9 +15,15 @@ #define INSN_CODE_SEG_OPND_SZ(params) (params & 0xf) #define INSN_CODE_SEG_PARAMS(oper_sz, addr_sz) (oper_sz | (addr_sz << 4)) +bool insn_has_rep_prefix(struct insn *insn); void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs); int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs); +int insn_get_modrm_reg_off(struct insn *insn, struct pt_regs *regs); unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx); int insn_get_code_seg_params(struct pt_regs *regs); +int insn_fetch_from_user(struct pt_regs *regs, + unsigned char buf[MAX_INSN_SIZE]); +bool insn_decode(struct insn *insn, struct pt_regs *regs, + unsigned char buf[MAX_INSN_SIZE], int buf_size); #endif /* _ASM_X86_INSN_EVAL_H */ diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 454939a0a95eb0242977994637a9d7fcc46b07db..03b6fdc474a5d37bfd5e6ff48e3c60e07e5dbfe9 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -19,6 +19,7 @@ #ifdef CONFIG_AMD_MEM_ENCRYPT extern u64 sme_me_mask; +extern u64 sev_status; extern bool sev_enabled; void sme_encrypt_execute(unsigned long encrypted_kernel_vaddr, @@ -36,6 +37,7 @@ void __init sme_map_bootdata(char *real_mode_data); void __init sme_unmap_bootdata(char *real_mode_data); void __init sme_early_init(void); +void __init sev_setup_arch(void); void __init sme_encrypt_kernel(struct boot_params *bp); void __init sme_enable(struct boot_params *bp); @@ -49,8 +51,10 @@ void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, void __init mem_encrypt_init(void); void __init mem_encrypt_free_decrypted_mem(void); +void __init sev_es_init_vc_handling(void); bool sme_active(void); bool sev_active(void); +bool sev_es_active(void); #define __bss_decrypted __attribute__((__section__(".bss..decrypted"))) @@ -67,12 +71,15 @@ static inline void __init sme_map_bootdata(char *real_mode_data) { } static inline void __init sme_unmap_bootdata(char *real_mode_data) { } static inline void __init sme_early_init(void) { } +static inline void __init sev_setup_arch(void) { } static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } static inline void __init sme_enable(struct boot_params *bp) { } +static inline void sev_es_init_vc_handling(void) { } static inline bool sme_active(void) { return false; } static inline bool sev_active(void) { return false; } +static inline bool sev_es_active(void) { return false; } static inline int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; } diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 220448e729b5545fcc27af62d6b6408d1e9fde43..3277e1f9af52fabe1f5aafffaae7b47939f3eb1b 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -499,9 +499,13 @@ #define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e +#define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 +#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) +#define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 9d0b4794527207e7f72d6674f5ce4428551834f5..b661e10fe189e470a82c806d3c99da6edadc3053 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -28,6 +28,7 @@ #define IST_INDEX_NMI 1 #define IST_INDEX_DB 2 #define IST_INDEX_MCE 3 +#define IST_INDEX_VC 4 /* * Set __PAGE_OFFSET to the most negative possible address + diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 60fe13c52b09d8353a1cdba44fc38558ef4ecc85..ef37dd64fe13ae98aab42414e21b3ba791ac2b2b 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -27,7 +27,7 @@ #include extern pgd_t early_top_pgt[PTRS_PER_PGD]; -int __init __early_make_pgtable(unsigned long address, pmdval_t pmd); +bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd); void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 258e54676f1ac597e9274f6490baf8342963518c..a7c796fc3cca562c013c08a73e9417975bee6d35 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -731,6 +731,7 @@ extern void load_direct_gdt(int); extern void load_fixmap_gdt(int); extern void load_percpu_segment(int); extern void cpu_init(void); +extern void cpu_init_exception_handling(void); extern void cr4_init(void); static inline unsigned long get_debugctlmsr(void) diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 0eaca7a130c9f2efe942b2bd6859a8b70695d96b..a27dcb4f4bcc6d1f2b6344cededfe5f08854bc17 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -12,6 +12,7 @@ void syscall_init(void); #ifdef CONFIG_X86_64 void entry_SYSCALL_64(void); +void entry_SYSCALL_64_safe_stack(void); long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2); #endif diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 52d7512ea91ab8426a46dfcd5bac8a0b02fc6a62..4c23d6b6eb4e69e8c20b3ac913e42e3147052401 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -21,6 +21,9 @@ struct real_mode_header { /* SMP trampoline */ u32 trampoline_start; u32 trampoline_header; +#ifdef CONFIG_AMD_MEM_ENCRYPT + u32 sev_es_trampoline_start; +#endif #ifdef CONFIG_X86_64 u32 trampoline_pgd; #endif @@ -57,6 +60,9 @@ extern unsigned char real_mode_blob_end[]; extern unsigned long initial_code; extern unsigned long initial_gs; extern unsigned long initial_stack; +#ifdef CONFIG_AMD_MEM_ENCRYPT +extern unsigned long initial_vc_handler; +#endif extern unsigned char real_mode_blob[]; extern unsigned char real_mode_relocs[]; @@ -66,6 +72,7 @@ extern unsigned char startup_32_smp[]; extern unsigned char boot_gdt[]; #else extern unsigned char secondary_startup_64[]; +extern unsigned char secondary_startup_64_no_verify[]; #endif static inline size_t real_mode_size_needed(void) diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 6669164abadcbd8a0b1b71e4a4ba40f800917dd5..5b648066504c81f78fcee6935d40b3ede6d0b330 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -230,7 +230,7 @@ #define NUM_EXCEPTION_VECTORS 32 /* Bitmask of exception vectors which push an error code on the stack: */ -#define EXCEPTION_ERRCODE_MASK 0x00027d00 +#define EXCEPTION_ERRCODE_MASK 0x20027d00 #define GDT_SIZE (GDT_ENTRIES*8) #define GDT_ENTRY_TLS_ENTRIES 3 diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index ed8ec011a9fdc6d3af834b67ed63d5a30d8f0adb..4801746c4af85e5af2929c701b55521f75ae4f0c 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -39,6 +39,8 @@ void vsmp_init(void); static inline void vsmp_init(void) { } #endif +struct pt_regs; + void setup_bios_corruption_check(void); void early_platform_quirks(void); @@ -48,7 +50,9 @@ extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp); extern unsigned long __startup_secondary_64(void); -extern int early_make_pgtable(unsigned long address); +extern void startup_64_setup_env(unsigned long physbase); +extern void early_setup_idt(void); +extern void __init do_early_exception(struct pt_regs *regs, int trapnr); #ifdef CONFIG_X86_INTEL_MID extern void x86_intel_mid_early_setup(void); diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h new file mode 100644 index 0000000000000000000000000000000000000000..cf1d957c7091949adde1237fdb656e3a5e927ff5 --- /dev/null +++ b/arch/x86/include/asm/sev-es.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD Encrypted Register State Support + * + * Author: Joerg Roedel + */ + +#ifndef __ASM_ENCRYPTED_STATE_H +#define __ASM_ENCRYPTED_STATE_H + +#include +#include + +#define GHCB_SEV_INFO 0x001UL +#define GHCB_SEV_INFO_REQ 0x002UL +#define GHCB_INFO(v) ((v) & 0xfffUL) +#define GHCB_PROTO_MAX(v) (((v) >> 48) & 0xffffUL) +#define GHCB_PROTO_MIN(v) (((v) >> 32) & 0xffffUL) +#define GHCB_PROTO_OUR 0x0001UL +#define GHCB_SEV_CPUID_REQ 0x004UL +#define GHCB_CPUID_REQ_EAX 0 +#define GHCB_CPUID_REQ_EBX 1 +#define GHCB_CPUID_REQ_ECX 2 +#define GHCB_CPUID_REQ_EDX 3 +#define GHCB_CPUID_REQ(fn, reg) (GHCB_SEV_CPUID_REQ | \ + (((unsigned long)reg & 3) << 30) | \ + (((unsigned long)fn) << 32)) + +#define GHCB_PROTOCOL_MAX 0x0001UL +#define GHCB_DEFAULT_USAGE 0x0000UL + +#define GHCB_SEV_CPUID_RESP 0x005UL +#define GHCB_SEV_TERMINATE 0x100UL +#define GHCB_SEV_TERMINATE_REASON(reason_set, reason_val) \ + (((((u64)reason_set) & 0x7) << 12) | \ + ((((u64)reason_val) & 0xff) << 16)) +#define GHCB_SEV_ES_REASON_GENERAL_REQUEST 0 +#define GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED 1 + +#define GHCB_SEV_GHCB_RESP_CODE(v) ((v) & 0xfff) +#define VMGEXIT() { asm volatile("rep; vmmcall\n\r"); } + +enum es_result { + ES_OK, /* All good */ + ES_UNSUPPORTED, /* Requested operation not supported */ + ES_VMM_ERROR, /* Unexpected state from the VMM */ + ES_DECODE_FAILED, /* Instruction decoding failed */ + ES_EXCEPTION, /* Instruction caused exception */ + ES_RETRY, /* Retry instruction emulation */ +}; + +struct es_fault_info { + unsigned long vector; + unsigned long error_code; + unsigned long cr2; +}; + +struct pt_regs; + +/* ES instruction emulation context */ +struct es_em_ctxt { + struct pt_regs *regs; + struct insn insn; + struct es_fault_info fi; +}; + +void do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code); + +static inline u64 lower_bits(u64 val, unsigned int bits) +{ + u64 mask = (1ULL << bits) - 1; + + return (val & mask); +} + +struct real_mode_header; +enum stack_type; + +/* Early IDT entry points for #VC handler */ +extern void vc_no_ghcb(void); +extern void vc_boot_ghcb(void); +extern bool handle_vc_boot_ghcb(struct pt_regs *regs); + +#ifdef CONFIG_AMD_MEM_ENCRYPT +extern struct static_key_false sev_es_enable_key; +extern void __sev_es_ist_enter(struct pt_regs *regs); +extern void __sev_es_ist_exit(void); +static __always_inline void sev_es_ist_enter(struct pt_regs *regs) +{ + if (static_branch_unlikely(&sev_es_enable_key)) + __sev_es_ist_enter(regs); +} +static __always_inline void sev_es_ist_exit(void) +{ + if (static_branch_unlikely(&sev_es_enable_key)) + __sev_es_ist_exit(); +} +extern int sev_es_setup_ap_jump_table(struct real_mode_header *rmh); +extern void __sev_es_nmi_complete(void); +static __always_inline void sev_es_nmi_complete(void) +{ + if (static_branch_unlikely(&sev_es_enable_key)) + __sev_es_nmi_complete(); +} +extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd); +#else +static inline void sev_es_ist_enter(struct pt_regs *regs) { } +static inline void sev_es_ist_exit(void) { } +static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; } +static inline void sev_es_nmi_complete(void) { } +static inline int sev_es_efi_map_ghcbs(pgd_t *pgd) { return 0; } +#endif + +#endif diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 14db05086bbf27198628785918ce3c2e627aa5c4..506873a8d5a445578d795d2c0e55534005971146 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -35,6 +35,8 @@ bool in_entry_stack(unsigned long *stack, struct stack_info *info); int get_stack_info(unsigned long *stack, struct task_struct *task, struct stack_info *info, unsigned long *visit_mask); +bool get_stack_info_noinstr(unsigned long *stack, struct task_struct *task, + struct stack_info *info); const char *stack_type_name(enum stack_type type); diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index c29d8fb0ffbe259341a830515b4ff86a9a6017e4..cb547c8226d34f8f039f66de81c2ead58fdee568 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -153,14 +153,14 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_NESTED_CTL_NP_ENABLE BIT(0) #define SVM_NESTED_CTL_SEV_ENABLE BIT(1) -struct __attribute__ ((__packed__)) vmcb_seg { +struct vmcb_seg { u16 selector; u16 attrib; u32 limit; u64 base; -}; +} __packed; -struct __attribute__ ((__packed__)) vmcb_save_area { +struct vmcb_save_area { struct vmcb_seg es; struct vmcb_seg cs; struct vmcb_seg ss; @@ -203,12 +203,66 @@ struct __attribute__ ((__packed__)) vmcb_save_area { u64 br_to; u64 last_excp_from; u64 last_excp_to; -}; -struct __attribute__ ((__packed__)) vmcb { + /* + * The following part of the save area is valid only for + * SEV-ES guests when referenced through the GHCB. + */ + u8 reserved_7[104]; + u64 reserved_8; /* rax already available at 0x01f8 */ + u64 rcx; + u64 rdx; + u64 rbx; + u64 reserved_9; /* rsp already available at 0x01d8 */ + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; + u8 reserved_10[16]; + u64 sw_exit_code; + u64 sw_exit_info_1; + u64 sw_exit_info_2; + u64 sw_scratch; + u8 reserved_11[56]; + u64 xcr0; + u8 valid_bitmap[16]; + u64 x87_state_gpa; +} __packed; + +struct ghcb { + struct vmcb_save_area save; + u8 reserved_save[2048 - sizeof(struct vmcb_save_area)]; + + u8 shared_buffer[2032]; + + u8 reserved_1[10]; + u16 protocol_version; /* negotiated SEV-ES/GHCB protocol version */ + u32 ghcb_usage; +} __packed; + + +#define EXPECTED_VMCB_SAVE_AREA_SIZE 1032 +#define EXPECTED_VMCB_CONTROL_AREA_SIZE 1024 +#define EXPECTED_GHCB_SIZE PAGE_SIZE + +static inline void __unused_size_checks(void) +{ + BUILD_BUG_ON(sizeof(struct vmcb_save_area) != EXPECTED_VMCB_SAVE_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE); +} + +struct vmcb { struct vmcb_control_area control; struct vmcb_save_area save; -}; +} __packed; #define SVM_CPUID_FUNC 0x8000000a @@ -293,4 +347,47 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP) +/* GHCB Accessor functions */ + +#define GHCB_BITMAP_IDX(field) \ + (offsetof(struct vmcb_save_area, field) / sizeof(u64)) + +#define DEFINE_GHCB_ACCESSORS(field) \ + static inline bool ghcb_##field##_is_valid(const struct ghcb *ghcb) \ + { \ + return test_bit(GHCB_BITMAP_IDX(field), \ + (unsigned long *)&ghcb->save.valid_bitmap); \ + } \ + \ + static inline void ghcb_set_##field(struct ghcb *ghcb, u64 value) \ + { \ + __set_bit(GHCB_BITMAP_IDX(field), \ + (unsigned long *)&ghcb->save.valid_bitmap); \ + ghcb->save.field = value; \ + } + +DEFINE_GHCB_ACCESSORS(cpl) +DEFINE_GHCB_ACCESSORS(rip) +DEFINE_GHCB_ACCESSORS(rsp) +DEFINE_GHCB_ACCESSORS(rax) +DEFINE_GHCB_ACCESSORS(rcx) +DEFINE_GHCB_ACCESSORS(rdx) +DEFINE_GHCB_ACCESSORS(rbx) +DEFINE_GHCB_ACCESSORS(rbp) +DEFINE_GHCB_ACCESSORS(rsi) +DEFINE_GHCB_ACCESSORS(rdi) +DEFINE_GHCB_ACCESSORS(r8) +DEFINE_GHCB_ACCESSORS(r9) +DEFINE_GHCB_ACCESSORS(r10) +DEFINE_GHCB_ACCESSORS(r11) +DEFINE_GHCB_ACCESSORS(r12) +DEFINE_GHCB_ACCESSORS(r13) +DEFINE_GHCB_ACCESSORS(r14) +DEFINE_GHCB_ACCESSORS(r15) +DEFINE_GHCB_ACCESSORS(sw_exit_code) +DEFINE_GHCB_ACCESSORS(sw_exit_info_1) +DEFINE_GHCB_ACCESSORS(sw_exit_info_2) +DEFINE_GHCB_ACCESSORS(sw_scratch) +DEFINE_GHCB_ACCESSORS(xcr0) + #endif diff --git a/arch/x86/include/asm/trap_pf.h b/arch/x86/include/asm/trap_pf.h new file mode 100644 index 0000000000000000000000000000000000000000..10b1de500ab1c298cfe9d092f6cc5435df3f0571 --- /dev/null +++ b/arch/x86/include/asm/trap_pf.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_TRAP_PF_H +#define _ASM_X86_TRAP_PF_H + +/* + * Page fault error code bits: + * + * bit 0 == 0: no page found 1: protection fault + * bit 1 == 0: read access 1: write access + * bit 2 == 0: kernel-mode access 1: user-mode access + * bit 3 == 1: use of reserved bit detected + * bit 4 == 1: fault was an instruction fetch + * bit 5 == 1: protection keys block access + * bit 15 == 1: SGX MMU page-fault + */ +enum x86_pf_error_code { + X86_PF_PROT = 1 << 0, + X86_PF_WRITE = 1 << 1, + X86_PF_USER = 1 << 2, + X86_PF_RSVD = 1 << 3, + X86_PF_INSTR = 1 << 4, + X86_PF_PK = 1 << 5, + X86_PF_SGX = 1 << 15, +}; + +#endif /* _ASM_X86_TRAP_PF_H */ diff --git a/arch/x86/include/asm/trapnr.h b/arch/x86/include/asm/trapnr.h new file mode 100644 index 0000000000000000000000000000000000000000..f5d2325aa0b749db0b6743adb85c94cb0f303624 --- /dev/null +++ b/arch/x86/include/asm/trapnr.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_TRAPNR_H +#define _ASM_X86_TRAPNR_H + +/* Interrupts/Exceptions */ + +#define X86_TRAP_DE 0 /* Divide-by-zero */ +#define X86_TRAP_DB 1 /* Debug */ +#define X86_TRAP_NMI 2 /* Non-maskable Interrupt */ +#define X86_TRAP_BP 3 /* Breakpoint */ +#define X86_TRAP_OF 4 /* Overflow */ +#define X86_TRAP_BR 5 /* Bound Range Exceeded */ +#define X86_TRAP_UD 6 /* Invalid Opcode */ +#define X86_TRAP_NM 7 /* Device Not Available */ +#define X86_TRAP_DF 8 /* Double Fault */ +#define X86_TRAP_OLD_MF 9 /* Coprocessor Segment Overrun */ +#define X86_TRAP_TS 10 /* Invalid TSS */ +#define X86_TRAP_NP 11 /* Segment Not Present */ +#define X86_TRAP_SS 12 /* Stack Segment Fault */ +#define X86_TRAP_GP 13 /* General Protection Fault */ +#define X86_TRAP_PF 14 /* Page Fault */ +#define X86_TRAP_SPURIOUS 15 /* Spurious Interrupt */ +#define X86_TRAP_MF 16 /* x87 Floating-Point Exception */ +#define X86_TRAP_AC 17 /* Alignment Check */ +#define X86_TRAP_MC 18 /* Machine Check */ +#define X86_TRAP_XF 19 /* SIMD Floating-Point Exception */ +#define X86_TRAP_VE 20 /* Virtualization Exception */ +#define X86_TRAP_CP 21 /* Control Protection Exception */ +#define X86_TRAP_VC 29 /* VMM Communication Exception */ +#define X86_TRAP_IRET 32 /* IRET Exception */ + +#endif diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 71abccd78a4fb9736850a016298e903962d3df5f..63cfa2adffbd5c1bba19997966ce3596e8dbe06f 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -6,7 +6,9 @@ #include #include +#include #include /* TRAP_TRACE, ... */ +#include #define dotraplinkage __visible @@ -79,6 +81,7 @@ asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs); asmlinkage __visible notrace struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s); void __init trap_init(void); +asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs); #endif dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code); dotraplinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address); @@ -126,49 +129,4 @@ void __noreturn handle_stack_overflow(const char *message, unsigned long fault_address); #endif -/* Interrupts/Exceptions */ -enum { - X86_TRAP_DE = 0, /* 0, Divide-by-zero */ - X86_TRAP_DB, /* 1, Debug */ - X86_TRAP_NMI, /* 2, Non-maskable Interrupt */ - X86_TRAP_BP, /* 3, Breakpoint */ - X86_TRAP_OF, /* 4, Overflow */ - X86_TRAP_BR, /* 5, Bound Range Exceeded */ - X86_TRAP_UD, /* 6, Invalid Opcode */ - X86_TRAP_NM, /* 7, Device Not Available */ - X86_TRAP_DF, /* 8, Double Fault */ - X86_TRAP_OLD_MF, /* 9, Coprocessor Segment Overrun */ - X86_TRAP_TS, /* 10, Invalid TSS */ - X86_TRAP_NP, /* 11, Segment Not Present */ - X86_TRAP_SS, /* 12, Stack Segment Fault */ - X86_TRAP_GP, /* 13, General Protection Fault */ - X86_TRAP_PF, /* 14, Page Fault */ - X86_TRAP_SPURIOUS, /* 15, Spurious Interrupt */ - X86_TRAP_MF, /* 16, x87 Floating-Point Exception */ - X86_TRAP_AC, /* 17, Alignment Check */ - X86_TRAP_MC, /* 18, Machine Check */ - X86_TRAP_XF, /* 19, SIMD Floating-Point Exception */ - X86_TRAP_IRET = 32, /* 32, IRET Exception */ -}; - -/* - * Page fault error code bits: - * - * bit 0 == 0: no page found 1: protection fault - * bit 1 == 0: read access 1: write access - * bit 2 == 0: kernel-mode access 1: user-mode access - * bit 3 == 1: use of reserved bit detected - * bit 4 == 1: fault was an instruction fetch - * bit 5 == 1: protection keys block access - * bit 15 == 1: SGX MMU page-fault - */ -enum x86_pf_error_code { - X86_PF_PROT = 1 << 0, - X86_PF_WRITE = 1 << 1, - X86_PF_USER = 1 << 2, - X86_PF_RSVD = 1 << 3, - X86_PF_INSTR = 1 << 4, - X86_PF_PK = 1 << 5, - X86_PF_SGX = 1 << 15, -}; #endif /* _ASM_X86_TRAPS_H */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 96d9cd2086104c9cccddedec7a7bf1bc108d32be..c4790ec279cc3982faa1ed470bdafb273e13c20d 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -4,8 +4,10 @@ #include +struct ghcb; struct mpc_bus; struct mpc_cpu; +struct pt_regs; struct mpc_table; struct cpuinfo_x86; @@ -238,10 +240,22 @@ struct x86_legacy_features { /** * struct x86_hyper_runtime - x86 hypervisor specific runtime callbacks * - * @pin_vcpu: pin current vcpu to specified physical cpu (run rarely) + * @pin_vcpu: pin current vcpu to specified physical + * cpu (run rarely) + * @sev_es_hcall_prepare: Load additional hypervisor-specific + * state into the GHCB when doing a VMMCALL under + * SEV-ES. Called from the #VC exception handler. + * @sev_es_hcall_finish: Copies state from the GHCB back into the + * processor (or pt_regs). Also runs checks on the + * state returned from the hypervisor after a + * VMMCALL under SEV-ES. Needs to return 'false' + * if the checks fail. Called from the #VC + * exception handler. */ struct x86_hyper_runtime { void (*pin_vcpu)(int cpu); + void (*sev_es_hcall_prepare)(struct ghcb *ghcb, struct pt_regs *regs); + bool (*sev_es_hcall_finish)(struct ghcb *ghcb, struct pt_regs *regs); }; /** diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index 2e8a30f06c74641cead87f4f460089f081c63ea7..a7a3403645e59c106516c0ece61abd4b845f4434 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -29,6 +29,7 @@ #define SVM_EXIT_WRITE_DR6 0x036 #define SVM_EXIT_WRITE_DR7 0x037 #define SVM_EXIT_EXCP_BASE 0x040 +#define SVM_EXIT_LAST_EXCP 0x05f #define SVM_EXIT_INTR 0x060 #define SVM_EXIT_NMI 0x061 #define SVM_EXIT_SMI 0x062 @@ -80,6 +81,16 @@ #define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS 0x402 +/* SEV-ES software-defined VMGEXIT events */ +#define SVM_VMGEXIT_MMIO_READ 0x80000001 +#define SVM_VMGEXIT_MMIO_WRITE 0x80000002 +#define SVM_VMGEXIT_NMI_COMPLETE 0x80000003 +#define SVM_VMGEXIT_AP_HLT_LOOP 0x80000004 +#define SVM_VMGEXIT_AP_JUMP_TABLE 0x80000005 +#define SVM_VMGEXIT_SET_AP_JUMP_TABLE 0 +#define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1 +#define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff + #define SVM_EXIT_ERR -1 #define SVM_EXIT_REASONS \ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 52ce1e239525589c5e771d2c25243b438de1960f..a86cf5e7c57682c32323c67d96cb44595208644c 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -20,6 +20,7 @@ CFLAGS_REMOVE_kvmclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_head64.o = -pg +CFLAGS_REMOVE_sev-es.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n @@ -27,6 +28,7 @@ KASAN_SANITIZE_dumpstack.o := n KASAN_SANITIZE_dumpstack_$(BITS).o := n KASAN_SANITIZE_stacktrace.o := n KASAN_SANITIZE_paravirt.o := n +KASAN_SANITIZE_sev-es.o := n OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y @@ -42,6 +44,8 @@ endif # non-deterministic coverage. KCOV_INSTRUMENT := n +CFLAGS_head$(BITS).o += -fno-stack-protector + CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace obj-y := process_$(BITS).o signal.o @@ -140,6 +144,7 @@ obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o +obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev-es.o ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index b953bfc739b31a4f03c5f3c5a353b9a8e384294e..13b298e69be82bd01d4c5be362adb8ef5ca92fb3 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -649,7 +649,7 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) * If BIOS has not enabled SME then don't advertise the * SME feature (set in scattered.c). * For SEV: If BIOS has not enabled SEV then don't advertise the - * SEV feature (set in scattered.c). + * SEV and SEV_ES feature (set in scattered.c). * * In all cases, since support for SME and SEV requires long mode, * don't advertise the feature under CONFIG_X86_32. @@ -680,6 +680,7 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_SME); clear_sev: setup_clear_cpu_cap(X86_FEATURE_SEV); + setup_clear_cpu_cap(X86_FEATURE_SEV_ES); } } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 236de8d5155384092622a40e7d2c083dd93fea4e..97be80d4049c505862bb3485ab5bcef2dc11c50e 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1975,6 +1975,46 @@ static void setup_getcpu(int cpu) } #endif +/* + * Setup everything needed to handle exceptions from the IDT, including the IST + * exceptions which use paranoid_entry(). + */ +void cpu_init_exception_handling(void) +{ + struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); + int cpu = raw_smp_processor_id(); + int i; + +#ifdef CONFIG_X86_64 + /* paranoid_entry() gets the CPU number from the GDT */ + setup_getcpu(cpu); + + /* IST vectors need TSS to be set up. */ + tss->x86_tss.ist[IST_INDEX_DF] = __this_cpu_ist_top_va(DF); + tss->x86_tss.ist[IST_INDEX_NMI] = __this_cpu_ist_top_va(NMI); + tss->x86_tss.ist[IST_INDEX_DB] = __this_cpu_ist_top_va(DB); + tss->x86_tss.ist[IST_INDEX_MCE] = __this_cpu_ist_top_va(MCE); + /* Only mapped when SEV-ES is active */ + tss->x86_tss.ist[IST_INDEX_VC] = __this_cpu_ist_top_va(VC); +#endif + + tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; + + /* + * <= is required because the CPU will access up to + * 8 bits beyond the end of the IO permission bitmap. + */ + for (i = 0; i <= IO_BITMAP_LONGS; i++) + tss->io_bitmap[i] = ~0UL; + + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); + + load_TR_desc(); + + /* Finally load the IDT */ + load_current_idt(); +} + /* * cpu_init() initializes state that is per-CPU. Some data is already * initialized (naturally) in the bootstrap process, such as the GDT @@ -2038,6 +2078,8 @@ void cpu_init(void) t->x86_tss.ist[IST_INDEX_NMI] = __this_cpu_ist_top_va(NMI); t->x86_tss.ist[IST_INDEX_DB] = __this_cpu_ist_top_va(DB); t->x86_tss.ist[IST_INDEX_MCE] = __this_cpu_ist_top_va(MCE); + /* Only mapped when SEV-ES is active */ + t->x86_tss.ist[IST_INDEX_VC] = __this_cpu_ist_top_va(VC); } t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 46d732696c1c8b6c94652ce7e7b76e1284d50216..32cd52758d2d530b60b50fe6a0dfeaba2b316a19 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -31,6 +31,7 @@ #include #include #include +#include #undef pr_fmt #define pr_fmt(fmt) "vmware: " fmt @@ -263,10 +264,49 @@ static bool __init vmware_legacy_x2apic_available(void) (eax & (1 << VMWARE_CMD_LEGACY_X2APIC)) != 0; } +#ifdef CONFIG_AMD_MEM_ENCRYPT +static void vmware_sev_es_hcall_prepare(struct ghcb *ghcb, + struct pt_regs *regs) +{ + /* Copy VMWARE specific Hypercall parameters to the GHCB */ + ghcb_set_rip(ghcb, regs->ip); + ghcb_set_rbx(ghcb, regs->bx); + ghcb_set_rcx(ghcb, regs->cx); + ghcb_set_rdx(ghcb, regs->dx); + ghcb_set_rsi(ghcb, regs->si); + ghcb_set_rdi(ghcb, regs->di); + ghcb_set_rbp(ghcb, regs->bp); +} + +static bool vmware_sev_es_hcall_finish(struct ghcb *ghcb, struct pt_regs *regs) +{ + if (!(ghcb_rbx_is_valid(ghcb) && + ghcb_rcx_is_valid(ghcb) && + ghcb_rdx_is_valid(ghcb) && + ghcb_rsi_is_valid(ghcb) && + ghcb_rdi_is_valid(ghcb) && + ghcb_rbp_is_valid(ghcb))) + return false; + + regs->bx = ghcb->save.rbx; + regs->cx = ghcb->save.rcx; + regs->dx = ghcb->save.rdx; + regs->si = ghcb->save.rsi; + regs->di = ghcb->save.rdi; + regs->bp = ghcb->save.rbp; + + return true; +} +#endif + const __initconst struct hypervisor_x86 x86_hyper_vmware = { - .name = "VMware", - .detect = vmware_platform, - .type = X86_HYPER_VMWARE, - .init.init_platform = vmware_platform_setup, - .init.x2apic_available = vmware_legacy_x2apic_available, + .name = "VMware", + .detect = vmware_platform, + .type = X86_HYPER_VMWARE, + .init.init_platform = vmware_platform_setup, + .init.x2apic_available = vmware_legacy_x2apic_available, +#ifdef CONFIG_AMD_MEM_ENCRYPT + .runtime.sev_es_hcall_prepare = vmware_sev_es_hcall_prepare, + .runtime.sev_es_hcall_finish = vmware_sev_es_hcall_finish, +#endif }; diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index e72042dc9487c04a2b27ef9a162104800e14a2b3..73650f55bbbfd6acff9d3cfc1f229cec9f1bfd69 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -29,8 +29,8 @@ static int die_counter; static struct pt_regs exec_summary_regs; -bool in_task_stack(unsigned long *stack, struct task_struct *task, - struct stack_info *info) +bool noinstr in_task_stack(unsigned long *stack, struct task_struct *task, + struct stack_info *info) { unsigned long *begin = task_stack_page(task); unsigned long *end = task_stack_page(task) + THREAD_SIZE; @@ -46,7 +46,8 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task, return true; } -bool in_entry_stack(unsigned long *stack, struct stack_info *info) +/* Called from get_stack_info_noinstr - so must be noinstr too */ +bool noinstr in_entry_stack(unsigned long *stack, struct stack_info *info) { struct entry_stack *ss = cpu_entry_stack(smp_processor_id()); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 87b97897a881035966bbef4693df91e8d46b547e..b24c20913c08b01ed8c25b91d02b0125f56d71a1 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -26,11 +26,13 @@ static const char * const exception_stack_names[] = { [ ESTACK_DB1 ] = "#DB1", [ ESTACK_DB ] = "#DB", [ ESTACK_MCE ] = "#MC", + [ ESTACK_VC ] = "#VC", + [ ESTACK_VC2 ] = "#VC2", }; const char *stack_type_name(enum stack_type type) { - BUILD_BUG_ON(N_EXCEPTION_STACKS != 6); + BUILD_BUG_ON(N_EXCEPTION_STACKS != 8); if (type == STACK_TYPE_IRQ) return "IRQ"; @@ -82,16 +84,18 @@ struct estack_pages estack_pages[CEA_ESTACK_PAGES] ____cacheline_aligned = { EPAGERANGE(DB1), EPAGERANGE(DB), EPAGERANGE(MCE), + EPAGERANGE(VC), + EPAGERANGE(VC2), }; -static bool in_exception_stack(unsigned long *stack, struct stack_info *info) +static __always_inline bool in_exception_stack(unsigned long *stack, struct stack_info *info) { unsigned long begin, end, stk = (unsigned long)stack; const struct estack_pages *ep; struct pt_regs *regs; unsigned int k; - BUILD_BUG_ON(N_EXCEPTION_STACKS != 6); + BUILD_BUG_ON(N_EXCEPTION_STACKS != 8); begin = (unsigned long)__this_cpu_read(cea_exception_stacks); /* @@ -125,7 +129,7 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info) return true; } -static bool in_irq_stack(unsigned long *stack, struct stack_info *info) +static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info *info) { unsigned long *end = (unsigned long *)this_cpu_read(hardirq_stack_ptr); unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long)); @@ -150,32 +154,38 @@ static bool in_irq_stack(unsigned long *stack, struct stack_info *info) return true; } -int get_stack_info(unsigned long *stack, struct task_struct *task, - struct stack_info *info, unsigned long *visit_mask) +bool noinstr get_stack_info_noinstr(unsigned long *stack, struct task_struct *task, + struct stack_info *info) { - if (!stack) - goto unknown; - - task = task ? : current; - if (in_task_stack(stack, task, info)) - goto recursion_check; + return true; if (task != current) - goto unknown; + return false; if (in_exception_stack(stack, info)) - goto recursion_check; + return true; if (in_irq_stack(stack, info)) - goto recursion_check; + return true; if (in_entry_stack(stack, info)) - goto recursion_check; + return true; + + return false; +} + +int get_stack_info(unsigned long *stack, struct task_struct *task, + struct stack_info *info, unsigned long *visit_mask) +{ + task = task ? : current; - goto unknown; + if (!stack) + goto unknown; + + if (!get_stack_info_noinstr(stack, task, info)) + goto unknown; -recursion_check: /* * Make sure we don't iterate through any given stack more than once. * If it comes up a second time then there's something wrong going on: diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index 2cc0303522c99aded12608e4b4b49d1ab9cb5d08..083624bd0f6e8d1ab11ed9e2a011af06ea583c2b 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -138,7 +138,7 @@ SYM_CODE_START(ftrace_regs_caller) movl function_trace_op, %ecx # 3rd argument: ftrace_pos pushl %esp # 4th argument: pt_regs -GLOBAL(ftrace_regs_call) +SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) call ftrace_stub addl $4, %esp # skip 4th argument diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 809d54397dba1c4786f6e204deeda60b410c8066..3afaaf5556377e6d6adfaecbf0aa614938e0973d 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -140,14 +140,14 @@ ENTRY(ftrace_caller) /* save_mcount_regs fills in first two parameters */ save_mcount_regs -GLOBAL(ftrace_caller_op_ptr) +SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL) /* Load the ftrace_ops into the 3rd parameter */ movq function_trace_op(%rip), %rdx /* regs go into 4th parameter (but make it NULL) */ movq $0, %rcx -GLOBAL(ftrace_call) +SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) call ftrace_stub restore_mcount_regs @@ -157,10 +157,10 @@ GLOBAL(ftrace_call) * think twice before adding any new code or changing the * layout here. */ -GLOBAL(ftrace_epilogue) +SYM_INNER_LABEL(ftrace_epilogue, SYM_L_GLOBAL) #ifdef CONFIG_FUNCTION_GRAPH_TRACER -GLOBAL(ftrace_graph_call) +SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) jmp ftrace_stub #endif @@ -180,7 +180,7 @@ ENTRY(ftrace_regs_caller) save_mcount_regs 8 /* save_mcount_regs fills in first two parameters */ -GLOBAL(ftrace_regs_caller_op_ptr) +SYM_INNER_LABEL(ftrace_regs_caller_op_ptr, SYM_L_GLOBAL) /* Load the ftrace_ops into the 3rd parameter */ movq function_trace_op(%rip), %rdx @@ -209,7 +209,7 @@ GLOBAL(ftrace_regs_caller_op_ptr) /* regs go into 4th parameter */ leaq (%rsp), %rcx -GLOBAL(ftrace_regs_call) +SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) call ftrace_stub /* Copy flags back to SS, to restore them */ @@ -239,7 +239,7 @@ GLOBAL(ftrace_regs_call) * The trampoline will add the code to jump * to the return. */ -GLOBAL(ftrace_regs_caller_end) +SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) jmp ftrace_epilogue @@ -261,7 +261,7 @@ fgraph_trace: jnz ftrace_graph_caller #endif -GLOBAL(ftrace_stub) +SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL) retq trace: diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 950286016f63c616dfbe8a6a71a732a3f1d6e8ce..4f26a8d0a101c3611de3477a7b4c605ac216213a 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -36,6 +36,11 @@ #include #include #include +#include +#include +#include +#include +#include /* * Manage page tables very early on. @@ -61,6 +66,24 @@ unsigned long vmemmap_base __ro_after_init = __VMEMMAP_BASE_L4; EXPORT_SYMBOL(vmemmap_base); #endif +/* + * GDT used on the boot CPU before switching to virtual addresses. + */ +static struct desc_struct startup_gdt[GDT_ENTRIES] = { + [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff), + [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff), + [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc093, 0, 0xfffff), +}; + +/* + * Address needs to be set at runtime because it references the startup_gdt + * while the kernel still uses a direct mapping. + */ +static struct desc_ptr startup_gdt_descr = { + .size = sizeof(startup_gdt), + .address = 0, +}; + #define __head __section(.head.text) static void __head *fixup_pointer(void *ptr, unsigned long physaddr) @@ -297,7 +320,7 @@ static void __init reset_early_page_tables(void) } /* Create a new PMD entry */ -int __init __early_make_pgtable(unsigned long address, pmdval_t pmd) +bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd) { unsigned long physaddr = address - __PAGE_OFFSET; pgdval_t pgd, *pgd_p; @@ -307,7 +330,7 @@ int __init __early_make_pgtable(unsigned long address, pmdval_t pmd) /* Invalid address or early pgt is done ? */ if (physaddr >= MAXMEM || read_cr3_pa() != __pa_nodebug(early_top_pgt)) - return -1; + return false; again: pgd_p = &early_top_pgt[pgd_index(address)].pgd; @@ -364,10 +387,10 @@ int __init __early_make_pgtable(unsigned long address, pmdval_t pmd) } pmd_p[pmd_index(address)] = pmd; - return 0; + return true; } -int __init early_make_pgtable(unsigned long address) +static bool __init early_make_pgtable(unsigned long address) { unsigned long physaddr = address - __PAGE_OFFSET; pmdval_t pmd; @@ -377,6 +400,19 @@ int __init early_make_pgtable(unsigned long address) return __early_make_pgtable(address, pmd); } +void __init do_early_exception(struct pt_regs *regs, int trapnr) +{ + if (trapnr == X86_TRAP_PF && + early_make_pgtable(native_read_cr2())) + return; + + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT) && + trapnr == X86_TRAP_VC && handle_vc_boot_ghcb(regs)) + return; + + early_fixup_exception(regs, trapnr); +} + /* Don't add a printk in there. printk relies on the PDA which is not initialized yet. */ static void __init clear_bss(void) @@ -491,3 +527,81 @@ void __init x86_64_start_reservations(char *real_mode_data) start_kernel(); } + +/* + * Data structures and code used for IDT setup in head_64.S. The bringup-IDT is + * used until the idt_table takes over. On the boot CPU this happens in + * x86_64_start_kernel(), on secondary CPUs in start_secondary(). In both cases + * this happens in the functions called from head_64.S. + * + * The idt_table can't be used that early because all the code modifying it is + * in idt.c and can be instrumented by tracing or KASAN, which both don't work + * during early CPU bringup. Also the idt_table has the runtime vectors + * configured which require certain CPU state to be setup already (like TSS), + * which also hasn't happened yet in early CPU bringup. + */ +static gate_desc bringup_idt_table[NUM_EXCEPTION_VECTORS] __page_aligned_data; + +static struct desc_ptr bringup_idt_descr = { + .size = (NUM_EXCEPTION_VECTORS * sizeof(gate_desc)) - 1, + .address = 0, /* Set at runtime */ +}; + +static void set_bringup_idt_handler(gate_desc *idt, int n, void *handler) +{ +#ifdef CONFIG_AMD_MEM_ENCRYPT + struct idt_data data; + gate_desc desc; + + init_idt_data(&data, n, handler); + idt_init_desc(&desc, &data); + native_write_idt_entry(idt, n, &desc); +#endif +} + +/* This runs while still in the direct mapping */ +static void startup_64_load_idt(unsigned long physbase) +{ + struct desc_ptr *desc = fixup_pointer(&bringup_idt_descr, physbase); + gate_desc *idt = fixup_pointer(bringup_idt_table, physbase); + + + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) { + void *handler; + + /* VMM Communication Exception */ + handler = fixup_pointer(vc_no_ghcb, physbase); + set_bringup_idt_handler(idt, X86_TRAP_VC, handler); + } + + desc->address = (unsigned long)idt; + native_load_idt(desc); +} + +/* This is used when running on kernel addresses */ +void early_setup_idt(void) +{ + /* VMM Communication Exception */ + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) + set_bringup_idt_handler(bringup_idt_table, X86_TRAP_VC, vc_boot_ghcb); + + bringup_idt_descr.address = (unsigned long)bringup_idt_table; + native_load_idt(&bringup_idt_descr); +} + +/* + * Setup boot CPU state needed before kernel switches to virtual addresses. + */ +void __head startup_64_setup_env(unsigned long physbase) +{ + /* Load GDT */ + startup_gdt_descr.address = (unsigned long)fixup_pointer(startup_gdt, physbase); + native_load_gdt(&startup_gdt_descr); + + /* New GDT is live - reload data segment registers */ + asm volatile("movl %%eax, %%ds\n" + "movl %%eax, %%ss\n" + "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory"); + + startup_64_load_idt(physbase); +} diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 11a5d5ade52cecbe703372c548cb6c807e95899f..417319dabe9b8c6651247e243709a749af076838 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -67,11 +67,6 @@ __HEAD SYM_CODE_START(startup_32) movl pa(initial_stack),%ecx - /* test KEEP_SEGMENTS flag to see if the bootloader is asking - us to not reload segments */ - testb $KEEP_SEGMENTS, BP_loadflags(%esi) - jnz 2f - /* * Set segments to known values. */ @@ -82,7 +77,6 @@ SYM_CODE_START(startup_32) movl %eax,%fs movl %eax,%gs movl %eax,%ss -2: leal -__PAGE_OFFSET(%ecx),%esp /* @@ -410,7 +404,7 @@ ENTRY(early_idt_handler_array) .endr ENDPROC(early_idt_handler_array) -early_idt_handler_common: +SYM_CODE_START_LOCAL(early_idt_handler_common) /* * The stack is the hardware frame, an error code or zero, and the * vector number. @@ -461,7 +455,7 @@ early_idt_handler_common: decl %ss:early_recursion_flag addl $4, %esp /* pop pt_regs->orig_ax */ iret -ENDPROC(early_idt_handler_common) +SYM_CODE_END(early_idt_handler_common) /* This is the default interrupt "handler" :-) */ ENTRY(early_ignore_irq) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index f3d3e9646a99bafdc69257ecd1d2bcc5fae60067..d800c125e88d25bc2414eb2cc5a7c81bcf0211cb 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -73,6 +73,20 @@ startup_64: /* Set up the stack for verify_cpu(), similar to initial_stack below */ leaq (__end_init_task - SIZEOF_PTREGS)(%rip), %rsp + leaq _text(%rip), %rdi + pushq %rsi + call startup_64_setup_env + popq %rsi + + /* Now switch to __KERNEL_CS so IRET works reliably */ + pushq $__KERNEL_CS + leaq .Lon_kernel_cs(%rip), %rax + pushq %rax + lretq + +.Lon_kernel_cs: + UNWIND_HINT_EMPTY + /* Sanitize CPU configuration */ call verify_cpu @@ -109,6 +123,18 @@ ENTRY(secondary_startup_64) /* Sanitize CPU configuration */ call verify_cpu + /* + * The secondary_startup_64_no_verify entry point is only used by + * SEV-ES guests. In those guests the call to verify_cpu() would cause + * #VC exceptions which can not be handled at this stage of secondary + * CPU bringup. + * + * All non SEV-ES systems, especially Intel systems, need to execute + * verify_cpu() above to make sure NX is enabled. + */ +SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) + UNWIND_HINT_EMPTY + /* * Retrieve the modifier (SME encryption mask if SME is active) to be * added to the initial pgdir entry that will be programmed into CR3. @@ -133,6 +159,21 @@ ENTRY(secondary_startup_64) /* Setup early boot stage 4-/5-level pagetables. */ addq phys_base(%rip), %rax + + /* + * For SEV guests: Verify that the C-bit is correct. A malicious + * hypervisor could lie about the C-bit position to perform a ROP + * attack on the guest by writing to the unencrypted stack and wait for + * the next RET instruction. + * %rsi carries pointer to realmode data and is callee-clobbered. Save + * and restore it. + */ + pushq %rsi + movq %rax, %rdi + call sev_verify_cbit + popq %rsi + + /* Switch to new page-table */ movq %rax, %cr3 /* Ensure I am executing from virtual addresses */ @@ -142,33 +183,6 @@ ENTRY(secondary_startup_64) 1: UNWIND_HINT_EMPTY - /* Check if nx is implemented */ - movl $0x80000001, %eax - cpuid - movl %edx,%edi - - /* Setup EFER (Extended Feature Enable Register) */ - movl $MSR_EFER, %ecx - rdmsr - btsl $_EFER_SCE, %eax /* Enable System Call */ - btl $20,%edi /* No Execute supported? */ - jnc 1f - btsl $_EFER_NX, %eax - btsq $_PAGE_BIT_NX,early_pmd_flags(%rip) -1: wrmsr /* Make changes effective */ - - /* Setup cr0 */ - movl $CR0_STATE, %eax - /* Make changes effective */ - movq %rax, %cr0 - - /* Setup a boot time stack */ - movq initial_stack(%rip), %rsp - - /* zero EFLAGS after setting rsp */ - pushq $0 - popfq - /* * We must switch to a new descriptor in kernel space for the GDT * because soon the kernel won't have access anymore to the userspace @@ -203,6 +217,41 @@ ENTRY(secondary_startup_64) movl initial_gs+4(%rip),%edx wrmsr + /* + * Setup a boot time stack - Any secondary CPU will have lost its stack + * by now because the cr3-switch above unmaps the real-mode stack + */ + movq initial_stack(%rip), %rsp + + /* Setup and Load IDT */ + pushq %rsi + call early_setup_idt + popq %rsi + + /* Check if nx is implemented */ + movl $0x80000001, %eax + cpuid + movl %edx,%edi + + /* Setup EFER (Extended Feature Enable Register) */ + movl $MSR_EFER, %ecx + rdmsr + btsl $_EFER_SCE, %eax /* Enable System Call */ + btl $20,%edi /* No Execute supported? */ + jnc 1f + btsl $_EFER_NX, %eax + btsq $_PAGE_BIT_NX,early_pmd_flags(%rip) +1: wrmsr /* Make changes effective */ + + /* Setup cr0 */ + movl $CR0_STATE, %eax + /* Make changes effective */ + movq %rax, %cr0 + + /* zero EFLAGS after setting rsp */ + pushq $0 + popfq + /* rsi is pointer to real mode structure with interesting info. pass it to C */ movq %rsi, %rdi @@ -243,6 +292,7 @@ ENTRY(secondary_startup_64) END(secondary_startup_64) #include "verify_cpu.S" +#include "sev_verify_cbit.S" #ifdef CONFIG_HOTPLUG_CPU /* @@ -255,6 +305,39 @@ ENTRY(start_cpu0) movq initial_stack(%rip), %rsp jmp .Ljump_to_C_code END(start_cpu0) +#endif + +#ifdef CONFIG_AMD_MEM_ENCRYPT +/* + * VC Exception handler used during early boot when running on kernel + * addresses, but before the switch to the idt_table can be made. + * The early_idt_handler_array can't be used here because it calls into a lot + * of __init code and this handler is also used during CPU offlining/onlining. + * Therefore this handler ends up in the .text section so that it stays around + * when .init.text is freed. + */ +SYM_CODE_START_NOALIGN(vc_boot_ghcb) + UNWIND_HINT_IRET_REGS offset=8 + + /* Build pt_regs */ + PUSH_AND_CLEAR_REGS + + /* Call C handler */ + movq %rsp, %rdi + movq ORIG_RAX(%rsp), %rsi + movq initial_vc_handler(%rip), %rax + ANNOTATE_RETPOLINE_SAFE + call *%rax + + /* Unwind pt_regs */ + POP_REGS + + /* Remove Error Code */ + addq $8, %rsp + + /* Pure iret required here - don't use INTERRUPT_RETURN */ + iretq +SYM_CODE_END(vc_boot_ghcb) #endif /* Both SMP bootup and ACPI suspend change these variables */ @@ -264,6 +347,10 @@ END(start_cpu0) .quad x86_64_start_kernel GLOBAL(initial_gs) .quad INIT_PER_CPU_VAR(fixed_percpu_data) +#ifdef CONFIG_AMD_MEM_ENCRYPT + GLOBAL(initial_vc_handler) + .quad handle_vc_boot_ghcb +#endif GLOBAL(initial_stack) /* * The SIZEOF_PTREGS gap is a convention which helps the in-kernel @@ -291,7 +378,7 @@ ENTRY(early_idt_handler_array) UNWIND_HINT_IRET_REGS offset=16 END(early_idt_handler_array) -early_idt_handler_common: +SYM_CODE_START_LOCAL(early_idt_handler_common) /* * The stack is the hardware frame, an error code or zero, and the * vector number. @@ -319,21 +406,43 @@ early_idt_handler_common: pushq %r15 /* pt_regs->r15 */ UNWIND_HINT_REGS - cmpq $14,%rsi /* Page fault? */ - jnz 10f - GET_CR2_INTO(%rdi) /* can clobber %rax if pv */ - call early_make_pgtable - andl %eax,%eax - jz 20f /* All good */ - -10: movq %rsp,%rdi /* RDI = pt_regs; RSI is already trapnr */ - call early_fixup_exception + call do_early_exception -20: decl early_recursion_flag(%rip) jmp restore_regs_and_return_to_kernel -END(early_idt_handler_common) +SYM_CODE_END(early_idt_handler_common) + +#ifdef CONFIG_AMD_MEM_ENCRYPT +/* + * VC Exception handler used during very early boot. The + * early_idt_handler_array can't be used because it returns via the + * paravirtualized INTERRUPT_RETURN and pv-ops don't work that early. + * + * This handler will end up in the .init.text section and not be + * available to boot secondary CPUs. + */ +SYM_CODE_START_NOALIGN(vc_no_ghcb) + UNWIND_HINT_IRET_REGS offset=8 + + /* Build pt_regs */ + PUSH_AND_CLEAR_REGS + + /* Call C handler */ + movq %rsp, %rdi + movq ORIG_RAX(%rsp), %rsi + call do_vc_no_ghcb + + /* Unwind pt_regs */ + POP_REGS + + /* Remove Error Code */ + addq $8, %rsp + + /* Pure iret required here - don't use INTERRUPT_RETURN */ + iretq +SYM_CODE_END(vc_no_ghcb) +#endif __INITDATA diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 7bb4c3cbf4dcdf379f77acccf42cfd4f0812edaf..7b96a1c8da5635f750d878c34183e65249969e94 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -9,13 +9,6 @@ #include #include -struct idt_data { - unsigned int vector; - unsigned int segment; - struct idt_bits bits; - const void *addr; -}; - #define DPL0 0x0 #define DPL3 0x3 @@ -188,6 +181,9 @@ static const __initconst struct idt_data ist_idts[] = { #ifdef CONFIG_X86_MCE ISTG(X86_TRAP_MC, &machine_check, IST_INDEX_MCE), #endif +#ifdef CONFIG_AMD_MEM_ENCRYPT + ISTG(X86_TRAP_VC, asm_exc_vmm_communication, IST_INDEX_VC), +#endif }; /* @@ -200,20 +196,6 @@ const struct desc_ptr debug_idt_descr = { }; #endif -static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d) -{ - unsigned long addr = (unsigned long) d->addr; - - gate->offset_low = (u16) addr; - gate->segment = (u16) d->segment; - gate->bits = d->bits; - gate->offset_middle = (u16) (addr >> 16); -#ifdef CONFIG_X86_64 - gate->offset_high = (u32) (addr >> 32); - gate->reserved = 0; -#endif -} - static void idt_setup_from_table(gate_desc *idt, const struct idt_data *t, int size, bool sys) { @@ -231,14 +213,7 @@ static void set_intr_gate(unsigned int n, const void *addr) { struct idt_data data; - BUG_ON(n > 0xFF); - - memset(&data, 0, sizeof(data)); - data.vector = n; - data.addr = addr; - data.segment = __KERNEL_CS; - data.bits.type = GATE_INTERRUPT; - data.bits.p = 1; + init_idt_data(&data, n, addr); idt_setup_from_table(idt_table, &data, 1, false); } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 6e9a5abaafb4b04110fca42e7dc131ec0e9c78cf..74869b4be778c10b77c544a8d8d829ebb94d4687 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -37,6 +37,8 @@ #include #include #include +#include +#include static int kvmapf = 1; @@ -880,13 +882,34 @@ static void __init kvm_init_platform(void) x86_platform.apic_post_init = kvm_apic_init; } +#if defined(CONFIG_AMD_MEM_ENCRYPT) +static void kvm_sev_es_hcall_prepare(struct ghcb *ghcb, struct pt_regs *regs) +{ + /* RAX and CPL are already in the GHCB */ + ghcb_set_rbx(ghcb, regs->bx); + ghcb_set_rcx(ghcb, regs->cx); + ghcb_set_rdx(ghcb, regs->dx); + ghcb_set_rsi(ghcb, regs->si); +} + +static bool kvm_sev_es_hcall_finish(struct ghcb *ghcb, struct pt_regs *regs) +{ + /* No checking of the return state needed */ + return true; +} +#endif + const __initconst struct hypervisor_x86 x86_hyper_kvm = { - .name = "KVM", - .detect = kvm_detect, - .type = X86_HYPER_KVM, - .init.guest_late_init = kvm_guest_init, - .init.x2apic_available = kvm_para_available, - .init.init_platform = kvm_init_platform, + .name = "KVM", + .detect = kvm_detect, + .type = X86_HYPER_KVM, + .init.guest_late_init = kvm_guest_init, + .init.x2apic_available = kvm_para_available, + .init.init_platform = kvm_init_platform, +#if defined(CONFIG_AMD_MEM_ENCRYPT) + .runtime.sev_es_hcall_prepare = kvm_sev_es_hcall_prepare, + .runtime.sev_es_hcall_finish = kvm_sev_es_hcall_finish, +#endif }; static __init int activate_jump_labels(void) diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 5bb001c0c771a480c1cc2e2181e9130dba6cb976..c80a710f465b386d94c595ada92ef0ee0ae699de 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -37,6 +37,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -509,6 +510,12 @@ NOKPROBE_SYMBOL(is_debug_stack); dotraplinkage notrace void do_nmi(struct pt_regs *regs, long error_code) { + /* + * Re-enable NMIs right here when running as an SEV-ES guest. This might + * cause nested NMIs, but those can be handled safely. + */ + sev_es_nmi_complete(); + if (IS_ENABLED(CONFIG_SMP) && cpu_is_offline(smp_processor_id())) return; @@ -520,6 +527,12 @@ do_nmi(struct pt_regs *regs, long error_code) this_cpu_write(nmi_cr2, read_cr2()); nmi_restart: + /* + * Needs to happen before DR7 is accessed, because the hypervisor can + * intercept DR7 reads/writes, turning those into #VC exceptions. + */ + sev_es_ist_enter(regs); + #ifdef CONFIG_X86_64 /* * If we interrupted a breakpoint, it is possible that @@ -549,6 +562,8 @@ do_nmi(struct pt_regs *regs, long error_code) } #endif + sev_es_ist_exit(); + if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) write_cr2(this_cpu_read(nmi_cr2)); if (this_cpu_dec_return(nmi_state)) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c28587deda8d31abd58c64d48fae0be0e5b96e45..13e6b47c6ebff8baa16629db70bc9d4d67fc5627 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -964,6 +964,12 @@ void __init setup_arch(char **cmdline_p) memblock_set_current_limit(ISA_END_ADDRESS); e820__memblock_setup(); + /* + * Needs to run after memblock setup because it needs the physical + * memory size. + */ + sev_setup_arch(); + reserve_bios_regions(); if (efi_enabled(EFI_MEMMAP)) { diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c new file mode 100644 index 0000000000000000000000000000000000000000..7d04b356d44d3362b9d59c561f4c680514a56a2b --- /dev/null +++ b/arch/x86/kernel/sev-es-shared.c @@ -0,0 +1,533 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AMD Encrypted Register State Support + * + * Author: Joerg Roedel + * + * This file is not compiled stand-alone. It contains code shared + * between the pre-decompression boot code and the running Linux kernel + * and is included directly into both code-bases. + */ + +#ifndef __BOOT_COMPRESSED +#define error(v) pr_err(v) +#define has_cpuflag(f) boot_cpu_has(f) +#endif + +static bool __init sev_es_check_cpu_features(void) +{ + if (!has_cpuflag(X86_FEATURE_RDRAND)) { + error("RDRAND instruction not supported - no trusted source of randomness available\n"); + return false; + } + + return true; +} + +static void sev_es_terminate(unsigned int reason) +{ + u64 val = GHCB_SEV_TERMINATE; + + /* + * Tell the hypervisor what went wrong - only reason-set 0 is + * currently supported. + */ + val |= GHCB_SEV_TERMINATE_REASON(0, reason); + + /* Request Guest Termination from Hypvervisor */ + sev_es_wr_ghcb_msr(val); + VMGEXIT(); + + while (true) + asm volatile("hlt\n" : : : "memory"); +} + +static bool sev_es_negotiate_protocol(void) +{ + u64 val; + + /* Do the GHCB protocol version negotiation */ + sev_es_wr_ghcb_msr(GHCB_SEV_INFO_REQ); + VMGEXIT(); + val = sev_es_rd_ghcb_msr(); + + if (GHCB_INFO(val) != GHCB_SEV_INFO) + return false; + + if (GHCB_PROTO_MAX(val) < GHCB_PROTO_OUR || + GHCB_PROTO_MIN(val) > GHCB_PROTO_OUR) + return false; + + return true; +} + +static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb) +{ + memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); +} + +static bool vc_decoding_needed(unsigned long exit_code) +{ + /* Exceptions don't require to decode the instruction */ + return !(exit_code >= SVM_EXIT_EXCP_BASE && + exit_code <= SVM_EXIT_LAST_EXCP); +} + +static enum es_result vc_init_em_ctxt(struct es_em_ctxt *ctxt, + struct pt_regs *regs, + unsigned long exit_code) +{ + enum es_result ret = ES_OK; + + memset(ctxt, 0, sizeof(*ctxt)); + ctxt->regs = regs; + + if (vc_decoding_needed(exit_code)) + ret = vc_decode_insn(ctxt); + + return ret; +} + +static void vc_finish_insn(struct es_em_ctxt *ctxt) +{ + ctxt->regs->ip += ctxt->insn.length; +} + +static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, + struct es_em_ctxt *ctxt, + u64 exit_code, u64 exit_info_1, + u64 exit_info_2) +{ + enum es_result ret; + + /* Fill in protocol and format specifiers */ + ghcb->protocol_version = GHCB_PROTOCOL_MAX; + ghcb->ghcb_usage = GHCB_DEFAULT_USAGE; + + ghcb_set_sw_exit_code(ghcb, exit_code); + ghcb_set_sw_exit_info_1(ghcb, exit_info_1); + ghcb_set_sw_exit_info_2(ghcb, exit_info_2); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + if ((ghcb->save.sw_exit_info_1 & 0xffffffff) == 1) { + u64 info = ghcb->save.sw_exit_info_2; + unsigned long v; + + info = ghcb->save.sw_exit_info_2; + v = info & SVM_EVTINJ_VEC_MASK; + + /* Check if exception information from hypervisor is sane. */ + if ((info & SVM_EVTINJ_VALID) && + ((v == X86_TRAP_GP) || (v == X86_TRAP_UD)) && + ((info & SVM_EVTINJ_TYPE_MASK) == SVM_EVTINJ_TYPE_EXEPT)) { + ctxt->fi.vector = v; + if (info & SVM_EVTINJ_VALID_ERR) + ctxt->fi.error_code = info >> 32; + ret = ES_EXCEPTION; + } else { + ret = ES_VMM_ERROR; + } + } else { + ret = ES_OK; + } + + return ret; +} + +/* + * Boot VC Handler - This is the first VC handler during boot, there is no GHCB + * page yet, so it only supports the MSR based communication with the + * hypervisor and only the CPUID exit-code. + */ +void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) +{ + unsigned int fn = lower_bits(regs->ax, 32); + unsigned long val; + + /* Only CPUID is supported via MSR protocol */ + if (exit_code != SVM_EXIT_CPUID) + goto fail; + + sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EAX)); + VMGEXIT(); + val = sev_es_rd_ghcb_msr(); + if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + goto fail; + regs->ax = val >> 32; + + sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EBX)); + VMGEXIT(); + val = sev_es_rd_ghcb_msr(); + if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + goto fail; + regs->bx = val >> 32; + + sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_ECX)); + VMGEXIT(); + val = sev_es_rd_ghcb_msr(); + if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + goto fail; + regs->cx = val >> 32; + + sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EDX)); + VMGEXIT(); + val = sev_es_rd_ghcb_msr(); + if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + goto fail; + regs->dx = val >> 32; + + /* + * This is a VC handler and the #VC is only raised when SEV-ES is + * active, which means SEV must be active too. Do sanity checks on the + * CPUID results to make sure the hypervisor does not trick the kernel + * into the no-sev path. This could map sensitive data unencrypted and + * make it accessible to the hypervisor. + * + * In particular, check for: + * - Hypervisor CPUID bit + * - Availability of CPUID leaf 0x8000001f + * - SEV CPUID bit. + * + * The hypervisor might still report the wrong C-bit position, but this + * can't be checked here. + */ + + if ((fn == 1 && !(regs->cx & BIT(31)))) + /* Hypervisor bit */ + goto fail; + else if (fn == 0x80000000 && (regs->ax < 0x8000001f)) + /* SEV leaf check */ + goto fail; + else if ((fn == 0x8000001f && !(regs->ax & BIT(1)))) + /* SEV bit */ + goto fail; + + /* Skip over the CPUID two-byte opcode */ + regs->ip += 2; + + return; + +fail: + sev_es_wr_ghcb_msr(GHCB_SEV_TERMINATE); + VMGEXIT(); + + /* Shouldn't get here - if we do halt the machine */ + while (true) + asm volatile("hlt\n"); +} + +static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt, + void *src, char *buf, + unsigned int data_size, + unsigned int count, + bool backwards) +{ + int i, b = backwards ? -1 : 1; + enum es_result ret = ES_OK; + + for (i = 0; i < count; i++) { + void *s = src + (i * data_size * b); + char *d = buf + (i * data_size); + + ret = vc_read_mem(ctxt, s, d, data_size); + if (ret != ES_OK) + break; + } + + return ret; +} + +static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt, + void *dst, char *buf, + unsigned int data_size, + unsigned int count, + bool backwards) +{ + int i, s = backwards ? -1 : 1; + enum es_result ret = ES_OK; + + for (i = 0; i < count; i++) { + void *d = dst + (i * data_size * s); + char *b = buf + (i * data_size); + + ret = vc_write_mem(ctxt, d, b, data_size); + if (ret != ES_OK) + break; + } + + return ret; +} + +#define IOIO_TYPE_STR BIT(2) +#define IOIO_TYPE_IN 1 +#define IOIO_TYPE_INS (IOIO_TYPE_IN | IOIO_TYPE_STR) +#define IOIO_TYPE_OUT 0 +#define IOIO_TYPE_OUTS (IOIO_TYPE_OUT | IOIO_TYPE_STR) + +#define IOIO_REP BIT(3) + +#define IOIO_ADDR_64 BIT(9) +#define IOIO_ADDR_32 BIT(8) +#define IOIO_ADDR_16 BIT(7) + +#define IOIO_DATA_32 BIT(6) +#define IOIO_DATA_16 BIT(5) +#define IOIO_DATA_8 BIT(4) + +#define IOIO_SEG_ES (0 << 10) +#define IOIO_SEG_DS (3 << 10) + +static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) +{ + struct insn *insn = &ctxt->insn; + *exitinfo = 0; + + switch (insn->opcode.bytes[0]) { + /* INS opcodes */ + case 0x6c: + case 0x6d: + *exitinfo |= IOIO_TYPE_INS; + *exitinfo |= IOIO_SEG_ES; + *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + break; + + /* OUTS opcodes */ + case 0x6e: + case 0x6f: + *exitinfo |= IOIO_TYPE_OUTS; + *exitinfo |= IOIO_SEG_DS; + *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + break; + + /* IN immediate opcodes */ + case 0xe4: + case 0xe5: + *exitinfo |= IOIO_TYPE_IN; + *exitinfo |= (u64)insn->immediate.value << 16; + break; + + /* OUT immediate opcodes */ + case 0xe6: + case 0xe7: + *exitinfo |= IOIO_TYPE_OUT; + *exitinfo |= (u64)insn->immediate.value << 16; + break; + + /* IN register opcodes */ + case 0xec: + case 0xed: + *exitinfo |= IOIO_TYPE_IN; + *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + break; + + /* OUT register opcodes */ + case 0xee: + case 0xef: + *exitinfo |= IOIO_TYPE_OUT; + *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + break; + + default: + return ES_DECODE_FAILED; + } + + switch (insn->opcode.bytes[0]) { + case 0x6c: + case 0x6e: + case 0xe4: + case 0xe6: + case 0xec: + case 0xee: + /* Single byte opcodes */ + *exitinfo |= IOIO_DATA_8; + break; + default: + /* Length determined by instruction parsing */ + *exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16 + : IOIO_DATA_32; + } + switch (insn->addr_bytes) { + case 2: + *exitinfo |= IOIO_ADDR_16; + break; + case 4: + *exitinfo |= IOIO_ADDR_32; + break; + case 8: + *exitinfo |= IOIO_ADDR_64; + break; + } + + if (insn_has_rep_prefix(insn)) + *exitinfo |= IOIO_REP; + + return ES_OK; +} + +static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + struct pt_regs *regs = ctxt->regs; + u64 exit_info_1, exit_info_2; + enum es_result ret; + + ret = vc_ioio_exitinfo(ctxt, &exit_info_1); + if (ret != ES_OK) + return ret; + + if (exit_info_1 & IOIO_TYPE_STR) { + + /* (REP) INS/OUTS */ + + bool df = ((regs->flags & X86_EFLAGS_DF) == X86_EFLAGS_DF); + unsigned int io_bytes, exit_bytes; + unsigned int ghcb_count, op_count; + unsigned long es_base; + u64 sw_scratch; + + /* + * For the string variants with rep prefix the amount of in/out + * operations per #VC exception is limited so that the kernel + * has a chance to take interrupts and re-schedule while the + * instruction is emulated. + */ + io_bytes = (exit_info_1 >> 4) & 0x7; + ghcb_count = sizeof(ghcb->shared_buffer) / io_bytes; + + op_count = (exit_info_1 & IOIO_REP) ? regs->cx : 1; + exit_info_2 = min(op_count, ghcb_count); + exit_bytes = exit_info_2 * io_bytes; + + es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES); + + /* Read bytes of OUTS into the shared buffer */ + if (!(exit_info_1 & IOIO_TYPE_IN)) { + ret = vc_insn_string_read(ctxt, + (void *)(es_base + regs->si), + ghcb->shared_buffer, io_bytes, + exit_info_2, df); + if (ret) + return ret; + } + + /* + * Issue an VMGEXIT to the HV to consume the bytes from the + * shared buffer or to have it write them into the shared buffer + * depending on the instruction: OUTS or INS. + */ + sw_scratch = __pa(ghcb) + offsetof(struct ghcb, shared_buffer); + ghcb_set_sw_scratch(ghcb, sw_scratch); + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, + exit_info_1, exit_info_2); + if (ret != ES_OK) + return ret; + + /* Read bytes from shared buffer into the guest's destination. */ + if (exit_info_1 & IOIO_TYPE_IN) { + ret = vc_insn_string_write(ctxt, + (void *)(es_base + regs->di), + ghcb->shared_buffer, io_bytes, + exit_info_2, df); + if (ret) + return ret; + + if (df) + regs->di -= exit_bytes; + else + regs->di += exit_bytes; + } else { + if (df) + regs->si -= exit_bytes; + else + regs->si += exit_bytes; + } + + if (exit_info_1 & IOIO_REP) + regs->cx -= exit_info_2; + + ret = regs->cx ? ES_RETRY : ES_OK; + + } else { + + /* IN/OUT into/from rAX */ + + int bits = (exit_info_1 & 0x70) >> 1; + u64 rax = 0; + + if (!(exit_info_1 & IOIO_TYPE_IN)) + rax = lower_bits(regs->ax, bits); + + ghcb_set_rax(ghcb, rax); + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, exit_info_1, 0); + if (ret != ES_OK) + return ret; + + if (exit_info_1 & IOIO_TYPE_IN) { + if (!ghcb_rax_is_valid(ghcb)) + return ES_VMM_ERROR; + regs->ax = lower_bits(ghcb->save.rax, bits); + } + } + + return ret; +} + +static enum es_result vc_handle_cpuid(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + struct pt_regs *regs = ctxt->regs; + u32 cr4 = native_read_cr4(); + enum es_result ret; + + ghcb_set_rax(ghcb, regs->ax); + ghcb_set_rcx(ghcb, regs->cx); + + if (cr4 & X86_CR4_OSXSAVE) + /* Safe to read xcr0 */ + ghcb_set_xcr0(ghcb, xgetbv(XCR_XFEATURE_ENABLED_MASK)); + else + /* xgetbv will cause #GP - use reset value for xcr0 */ + ghcb_set_xcr0(ghcb, 1); + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0); + if (ret != ES_OK) + return ret; + + if (!(ghcb_rax_is_valid(ghcb) && + ghcb_rbx_is_valid(ghcb) && + ghcb_rcx_is_valid(ghcb) && + ghcb_rdx_is_valid(ghcb))) + return ES_VMM_ERROR; + + regs->ax = ghcb->save.rax; + regs->bx = ghcb->save.rbx; + regs->cx = ghcb->save.rcx; + regs->dx = ghcb->save.rdx; + + return ES_OK; +} + +static enum es_result vc_handle_rdtsc(struct ghcb *ghcb, + struct es_em_ctxt *ctxt, + unsigned long exit_code) +{ + bool rdtscp = (exit_code == SVM_EXIT_RDTSCP); + enum es_result ret; + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0); + if (ret != ES_OK) + return ret; + + if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb) && + (!rdtscp || ghcb_rcx_is_valid(ghcb)))) + return ES_VMM_ERROR; + + ctxt->regs->ax = ghcb->save.rax; + ctxt->regs->dx = ghcb->save.rdx; + if (rdtscp) + ctxt->regs->cx = ghcb->save.rcx; + + return ES_OK; +} diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c new file mode 100644 index 0000000000000000000000000000000000000000..d74bb2ba4b7d977404e145d542c3b82477bd21e6 --- /dev/null +++ b/arch/x86/kernel/sev-es.c @@ -0,0 +1,1420 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2019 SUSE + * + * Author: Joerg Roedel + */ + +#define pr_fmt(fmt) "SEV-ES: " fmt + +#include /* For show_regs() */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DR7_RESET_VALUE 0x400 + +/* For early boot hypervisor communication in SEV-ES enabled guests */ +static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); + +/* + * Needs to be in the .data section because we need it NULL before bss is + * cleared + */ +static struct ghcb __initdata *boot_ghcb; + +/* #VC handler runtime per-CPU data */ +struct sev_es_runtime_data { + struct ghcb ghcb_page; + + /* Physical storage for the per-CPU IST stack of the #VC handler */ + char ist_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE); + + /* + * Physical storage for the per-CPU fall-back stack of the #VC handler. + * The fall-back stack is used when it is not safe to switch back to the + * interrupted stack in the #VC entry code. + */ + char fallback_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE); + + /* + * Reserve one page per CPU as backup storage for the unencrypted GHCB. + * It is needed when an NMI happens while the #VC handler uses the real + * GHCB, and the NMI handler itself is causing another #VC exception. In + * that case the GHCB content of the first handler needs to be backed up + * and restored. + */ + struct ghcb backup_ghcb; + + /* + * Mark the per-cpu GHCBs as in-use to detect nested #VC exceptions. + * There is no need for it to be atomic, because nothing is written to + * the GHCB between the read and the write of ghcb_active. So it is safe + * to use it when a nested #VC exception happens before the write. + * + * This is necessary for example in the #VC->NMI->#VC case when the NMI + * happens while the first #VC handler uses the GHCB. When the NMI code + * raises a second #VC handler it might overwrite the contents of the + * GHCB written by the first handler. To avoid this the content of the + * GHCB is saved and restored when the GHCB is detected to be in use + * already. + */ + bool ghcb_active; + bool backup_ghcb_active; + + /* + * Cached DR7 value - write it on DR7 writes and return it on reads. + * That value will never make it to the real hardware DR7 as debugging + * is currently unsupported in SEV-ES guests. + */ + unsigned long dr7; +}; + +struct ghcb_state { + struct ghcb *ghcb; +}; + +static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data); +DEFINE_STATIC_KEY_FALSE(sev_es_enable_key); + +/* Needed in vc_early_forward_exception */ +void do_early_exception(struct pt_regs *regs, int trapnr); + +static void __init setup_vc_stacks(int cpu) +{ + struct sev_es_runtime_data *data; + struct cpu_entry_area *cea; + unsigned long vaddr; + phys_addr_t pa; + + data = per_cpu(runtime_data, cpu); + cea = get_cpu_entry_area(cpu); + + /* Map #VC IST stack */ + vaddr = CEA_ESTACK_BOT(&cea->estacks, VC); + pa = __pa(data->ist_stack); + cea_set_pte((void *)vaddr, pa, PAGE_KERNEL); + + /* Map VC fall-back stack */ + vaddr = CEA_ESTACK_BOT(&cea->estacks, VC2); + pa = __pa(data->fallback_stack); + cea_set_pte((void *)vaddr, pa, PAGE_KERNEL); +} + +static __always_inline bool on_vc_stack(unsigned long sp) +{ + return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC))); +} + +/* + * This function handles the case when an NMI is raised in the #VC exception + * handler entry code. In this case, the IST entry for #VC must be adjusted, so + * that any subsequent #VC exception will not overwrite the stack contents of the + * interrupted #VC handler. + * + * The IST entry is adjusted unconditionally so that it can be also be + * unconditionally adjusted back in sev_es_ist_exit(). Otherwise a nested + * sev_es_ist_exit() call may adjust back the IST entry too early. + */ +void noinstr __sev_es_ist_enter(struct pt_regs *regs) +{ + unsigned long old_ist, new_ist; + + /* Read old IST entry */ + old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]); + + /* Make room on the IST stack */ + if (on_vc_stack(regs->sp)) + new_ist = ALIGN_DOWN(regs->sp, 8) - sizeof(old_ist); + else + new_ist = old_ist - sizeof(old_ist); + + /* Store old IST entry */ + *(unsigned long *)new_ist = old_ist; + + /* Set new IST entry */ + this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], new_ist); +} + +void noinstr __sev_es_ist_exit(void) +{ + unsigned long ist; + + /* Read IST entry */ + ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]); + + if (WARN_ON(ist == __this_cpu_ist_top_va(VC))) + return; + + /* Read back old IST entry and write it to the TSS */ + this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], *(unsigned long *)ist); +} + +static __always_inline struct ghcb *sev_es_get_ghcb(struct ghcb_state *state) +{ + struct sev_es_runtime_data *data; + struct ghcb *ghcb; + + data = this_cpu_read(runtime_data); + ghcb = &data->ghcb_page; + + if (unlikely(data->ghcb_active)) { + /* GHCB is already in use - save its contents */ + + if (unlikely(data->backup_ghcb_active)) + return NULL; + + /* Mark backup_ghcb active before writing to it */ + data->backup_ghcb_active = true; + + state->ghcb = &data->backup_ghcb; + + /* Backup GHCB content */ + *state->ghcb = *ghcb; + } else { + state->ghcb = NULL; + data->ghcb_active = true; + } + + return ghcb; +} + +static __always_inline void sev_es_put_ghcb(struct ghcb_state *state) +{ + struct sev_es_runtime_data *data; + struct ghcb *ghcb; + + data = this_cpu_read(runtime_data); + ghcb = &data->ghcb_page; + + if (state->ghcb) { + /* Restore GHCB from Backup */ + *ghcb = *state->ghcb; + data->backup_ghcb_active = false; + state->ghcb = NULL; + } else { + data->ghcb_active = false; + } +} + +/* Needed in vc_early_forward_exception */ +void do_early_exception(struct pt_regs *regs, int trapnr); + +static inline u64 sev_es_rd_ghcb_msr(void) +{ + return __rdmsr(MSR_AMD64_SEV_ES_GHCB); +} + +static inline void sev_es_wr_ghcb_msr(u64 val) +{ + u32 low, high; + + low = (u32)(val); + high = (u32)(val >> 32); + + native_wrmsr(MSR_AMD64_SEV_ES_GHCB, low, high); +} + +static int vc_fetch_insn_kernel(struct es_em_ctxt *ctxt, + unsigned char *buffer) +{ + return probe_kernel_read(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE); +} + +static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt) +{ + char buffer[MAX_INSN_SIZE]; + enum es_result ret; + int res; + + if (user_mode(ctxt->regs)) { + res = insn_fetch_from_user(ctxt->regs, buffer); + if (!res) { + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER; + ctxt->fi.cr2 = ctxt->regs->ip; + return ES_EXCEPTION; + } + + if (!insn_decode(&ctxt->insn, ctxt->regs, buffer, res)) + return ES_DECODE_FAILED; + } else { + res = vc_fetch_insn_kernel(ctxt, buffer); + if (res) { + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.error_code = X86_PF_INSTR; + ctxt->fi.cr2 = ctxt->regs->ip; + return ES_EXCEPTION; + } + + insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE - res, 1); + insn_get_length(&ctxt->insn); + } + + ret = ctxt->insn.immediate.got ? ES_OK : ES_DECODE_FAILED; + + return ret; +} + +static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, + char *dst, char *buf, size_t size) +{ + unsigned long error_code = X86_PF_PROT | X86_PF_WRITE; + char __user *target = (char __user *)dst; + u64 d8; + u32 d4; + u16 d2; + u8 d1; + + switch (size) { + case 1: + memcpy(&d1, buf, 1); + if (put_user(d1, target)) + goto fault; + break; + case 2: + memcpy(&d2, buf, 2); + if (put_user(d2, target)) + goto fault; + break; + case 4: + memcpy(&d4, buf, 4); + if (put_user(d4, target)) + goto fault; + break; + case 8: + memcpy(&d8, buf, 8); + if (put_user(d8, target)) + goto fault; + break; + default: + WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size); + return ES_UNSUPPORTED; + } + + return ES_OK; + +fault: + if (user_mode(ctxt->regs)) + error_code |= X86_PF_USER; + + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.error_code = error_code; + ctxt->fi.cr2 = (unsigned long)dst; + + return ES_EXCEPTION; +} + +static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, + char *src, char *buf, size_t size) +{ + unsigned long error_code = X86_PF_PROT; + char __user *s = (char __user *)src; + u64 d8; + u32 d4; + u16 d2; + u8 d1; + + switch (size) { + case 1: + if (get_user(d1, s)) + goto fault; + memcpy(buf, &d1, 1); + break; + case 2: + if (get_user(d2, s)) + goto fault; + memcpy(buf, &d2, 2); + break; + case 4: + if (get_user(d4, s)) + goto fault; + memcpy(buf, &d4, 4); + break; + case 8: + if (get_user(d8, s)) + goto fault; + memcpy(buf, &d8, 8); + break; + default: + WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size); + return ES_UNSUPPORTED; + } + + return ES_OK; + +fault: + if (user_mode(ctxt->regs)) + error_code |= X86_PF_USER; + + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.error_code = error_code; + ctxt->fi.cr2 = (unsigned long)src; + + return ES_EXCEPTION; +} + +static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, + unsigned long vaddr, phys_addr_t *paddr) +{ + unsigned long va = (unsigned long)vaddr; + unsigned int level; + phys_addr_t pa; + pgd_t *pgd; + pte_t *pte; + + pgd = __va(read_cr3_pa()); + pgd = &pgd[pgd_index(va)]; + pte = lookup_address_in_pgd(pgd, va, &level); + if (!pte) { + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.cr2 = vaddr; + ctxt->fi.error_code = 0; + + if (user_mode(ctxt->regs)) + ctxt->fi.error_code |= X86_PF_USER; + + return ES_EXCEPTION; + } + + if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC)) + /* Emulated MMIO to/from encrypted memory not supported */ + return ES_UNSUPPORTED; + + pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; + pa |= va & ~page_level_mask(level); + + *paddr = pa; + + return ES_OK; +} + +/* Include code shared with pre-decompression boot stage */ +#include "sev-es-shared.c" + +void noinstr __sev_es_nmi_complete(void) +{ + struct ghcb_state state; + struct ghcb *ghcb; + + ghcb = sev_es_get_ghcb(&state); + + vc_ghcb_invalidate(ghcb); + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_NMI_COMPLETE); + ghcb_set_sw_exit_info_1(ghcb, 0); + ghcb_set_sw_exit_info_2(ghcb, 0); + + sev_es_wr_ghcb_msr(__pa_nodebug(ghcb)); + VMGEXIT(); + + sev_es_put_ghcb(&state); +} + +static u64 get_jump_table_addr(void) +{ + struct ghcb_state state; + unsigned long flags; + struct ghcb *ghcb; + u64 ret = 0; + + local_irq_save(flags); + + ghcb = sev_es_get_ghcb(&state); + + vc_ghcb_invalidate(ghcb); + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_JUMP_TABLE); + ghcb_set_sw_exit_info_1(ghcb, SVM_VMGEXIT_GET_AP_JUMP_TABLE); + ghcb_set_sw_exit_info_2(ghcb, 0); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + if (ghcb_sw_exit_info_1_is_valid(ghcb) && + ghcb_sw_exit_info_2_is_valid(ghcb)) + ret = ghcb->save.sw_exit_info_2; + + sev_es_put_ghcb(&state); + + local_irq_restore(flags); + + return ret; +} + +int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) +{ + u16 startup_cs, startup_ip; + phys_addr_t jump_table_pa; + u64 jump_table_addr; + u16 __iomem *jump_table; + + jump_table_addr = get_jump_table_addr(); + + /* On UP guests there is no jump table so this is not a failure */ + if (!jump_table_addr) + return 0; + + /* Check if AP Jump Table is page-aligned */ + if (jump_table_addr & ~PAGE_MASK) + return -EINVAL; + + jump_table_pa = jump_table_addr & PAGE_MASK; + + startup_cs = (u16)(rmh->trampoline_start >> 4); + startup_ip = (u16)(rmh->sev_es_trampoline_start - + rmh->trampoline_start); + + jump_table = ioremap_encrypted(jump_table_pa, PAGE_SIZE); + if (!jump_table) + return -EIO; + + writew(startup_ip, &jump_table[0]); + writew(startup_cs, &jump_table[1]); + + iounmap(jump_table); + + return 0; +} + +/* + * This is needed by the OVMF UEFI firmware which will use whatever it finds in + * the GHCB MSR as its GHCB to talk to the hypervisor. So make sure the per-cpu + * runtime GHCBs used by the kernel are also mapped in the EFI page-table. + */ +int __init sev_es_efi_map_ghcbs(pgd_t *pgd) +{ + struct sev_es_runtime_data *data; + unsigned long address, pflags; + int cpu; + u64 pfn; + + if (!sev_es_active()) + return 0; + + pflags = _PAGE_NX | _PAGE_RW; + + for_each_possible_cpu(cpu) { + data = per_cpu(runtime_data, cpu); + + address = __pa(&data->ghcb_page); + pfn = address >> PAGE_SHIFT; + + if (kernel_map_pages_in_pgd(pgd, pfn, address, 1, pflags)) + return 1; + } + + return 0; +} + +static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + struct pt_regs *regs = ctxt->regs; + enum es_result ret; + u64 exit_info_1; + + /* Is it a WRMSR? */ + exit_info_1 = (ctxt->insn.opcode.bytes[1] == 0x30) ? 1 : 0; + + ghcb_set_rcx(ghcb, regs->cx); + if (exit_info_1) { + ghcb_set_rax(ghcb, regs->ax); + ghcb_set_rdx(ghcb, regs->dx); + } + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, exit_info_1, 0); + + if ((ret == ES_OK) && (!exit_info_1)) { + regs->ax = ghcb->save.rax; + regs->dx = ghcb->save.rdx; + } + + return ret; +} + +/* + * This function runs on the first #VC exception after the kernel + * switched to virtual addresses. + */ +static bool __init sev_es_setup_ghcb(void) +{ + /* First make sure the hypervisor talks a supported protocol. */ + if (!sev_es_negotiate_protocol()) + return false; + + /* + * Clear the boot_ghcb. The first exception comes in before the bss + * section is cleared. + */ + memset(&boot_ghcb_page, 0, PAGE_SIZE); + + /* Alright - Make the boot-ghcb public */ + boot_ghcb = &boot_ghcb_page; + + return true; +} + +#ifdef CONFIG_HOTPLUG_CPU +static void sev_es_ap_hlt_loop(void) +{ + struct ghcb_state state; + struct ghcb *ghcb; + + ghcb = sev_es_get_ghcb(&state); + + while (true) { + vc_ghcb_invalidate(ghcb); + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_HLT_LOOP); + ghcb_set_sw_exit_info_1(ghcb, 0); + ghcb_set_sw_exit_info_2(ghcb, 0); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + /* Wakeup signal? */ + if (ghcb_sw_exit_info_2_is_valid(ghcb) && + ghcb->save.sw_exit_info_2) + break; + } + + sev_es_put_ghcb(&state); +} + +/* + * Play_dead handler when running under SEV-ES. This is needed because + * the hypervisor can't deliver an SIPI request to restart the AP. + * Instead the kernel has to issue a VMGEXIT to halt the VCPU until the + * hypervisor wakes it up again. + */ +static void sev_es_play_dead(void) +{ + play_dead_common(); + + /* IRQs now disabled */ + + sev_es_ap_hlt_loop(); + + /* + * If we get here, the VCPU was woken up again. Jump to CPU + * startup code to get it back online. + */ + start_cpu0(); +} +#else /* CONFIG_HOTPLUG_CPU */ +#define sev_es_play_dead native_play_dead +#endif /* CONFIG_HOTPLUG_CPU */ + +#ifdef CONFIG_SMP +static void __init sev_es_setup_play_dead(void) +{ + smp_ops.play_dead = sev_es_play_dead; +} +#else +static inline void sev_es_setup_play_dead(void) { } +#endif + +static void __init alloc_runtime_data(int cpu) +{ + struct sev_es_runtime_data *data; + + data = memblock_alloc(sizeof(*data), PAGE_SIZE); + if (!data) + panic("Can't allocate SEV-ES runtime data"); + + per_cpu(runtime_data, cpu) = data; +} + +static void __init init_ghcb(int cpu) +{ + struct sev_es_runtime_data *data; + int err; + + data = per_cpu(runtime_data, cpu); + + err = early_set_memory_decrypted((unsigned long)&data->ghcb_page, + sizeof(data->ghcb_page)); + if (err) + panic("Can't map GHCBs unencrypted"); + + memset(&data->ghcb_page, 0, sizeof(data->ghcb_page)); + + data->ghcb_active = false; + data->backup_ghcb_active = false; +} + +void __init sev_es_init_vc_handling(void) +{ + int cpu; + + BUILD_BUG_ON(offsetof(struct sev_es_runtime_data, ghcb_page) % PAGE_SIZE); + + if (!sev_es_active()) + return; + + if (!sev_es_check_cpu_features()) + panic("SEV-ES CPU Features missing"); + + /* Enable SEV-ES special handling */ + static_branch_enable(&sev_es_enable_key); + + /* Initialize per-cpu GHCB pages */ + for_each_possible_cpu(cpu) { + alloc_runtime_data(cpu); + init_ghcb(cpu); + setup_vc_stacks(cpu); + } + + sev_es_setup_play_dead(); + + /* Secondary CPUs use the runtime #VC handler */ + initial_vc_handler = (unsigned long)safe_stack_exc_vmm_communication; +} + +static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt) +{ + int trapnr = ctxt->fi.vector; + + if (trapnr == X86_TRAP_PF) + native_write_cr2(ctxt->fi.cr2); + + ctxt->regs->orig_ax = ctxt->fi.error_code; + do_early_exception(ctxt->regs, trapnr); +} + +static long *vc_insn_get_reg(struct es_em_ctxt *ctxt) +{ + long *reg_array; + int offset; + + reg_array = (long *)ctxt->regs; + offset = insn_get_modrm_reg_off(&ctxt->insn, ctxt->regs); + + if (offset < 0) + return NULL; + + offset /= sizeof(long); + + return reg_array + offset; +} + +static long *vc_insn_get_rm(struct es_em_ctxt *ctxt) +{ + long *reg_array; + int offset; + + reg_array = (long *)ctxt->regs; + offset = insn_get_modrm_rm_off(&ctxt->insn, ctxt->regs); + + if (offset < 0) + return NULL; + + offset /= sizeof(long); + + return reg_array + offset; +} +static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, + unsigned int bytes, bool read) +{ + u64 exit_code, exit_info_1, exit_info_2; + unsigned long ghcb_pa = __pa(ghcb); + enum es_result res; + phys_addr_t paddr; + void __user *ref; + + ref = insn_get_addr_ref(&ctxt->insn, ctxt->regs); + if (ref == (void __user *)-1L) + return ES_UNSUPPORTED; + + exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE; + + res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr); + if (res != ES_OK) { + if (res == ES_EXCEPTION && !read) + ctxt->fi.error_code |= X86_PF_WRITE; + + return res; + } + + exit_info_1 = paddr; + /* Can never be greater than 8 */ + exit_info_2 = bytes; + + ghcb_set_sw_scratch(ghcb, ghcb_pa + offsetof(struct ghcb, shared_buffer)); + + return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2); +} + +static enum es_result vc_handle_mmio_twobyte_ops(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + struct insn *insn = &ctxt->insn; + unsigned int bytes = 0; + enum es_result ret; + int sign_byte; + long *reg_data; + + switch (insn->opcode.bytes[1]) { + /* MMIO Read w/ zero-extension */ + case 0xb6: + bytes = 1; + fallthrough; + case 0xb7: + if (!bytes) + bytes = 2; + + ret = vc_do_mmio(ghcb, ctxt, bytes, true); + if (ret) + break; + + /* Zero extend based on operand size */ + reg_data = vc_insn_get_reg(ctxt); + if (!reg_data) + return ES_DECODE_FAILED; + + memset(reg_data, 0, insn->opnd_bytes); + + memcpy(reg_data, ghcb->shared_buffer, bytes); + break; + + /* MMIO Read w/ sign-extension */ + case 0xbe: + bytes = 1; + fallthrough; + case 0xbf: + if (!bytes) + bytes = 2; + + ret = vc_do_mmio(ghcb, ctxt, bytes, true); + if (ret) + break; + + /* Sign extend based on operand size */ + reg_data = vc_insn_get_reg(ctxt); + if (!reg_data) + return ES_DECODE_FAILED; + + if (bytes == 1) { + u8 *val = (u8 *)ghcb->shared_buffer; + + sign_byte = (*val & 0x80) ? 0xff : 0x00; + } else { + u16 *val = (u16 *)ghcb->shared_buffer; + + sign_byte = (*val & 0x8000) ? 0xff : 0x00; + } + memset(reg_data, sign_byte, insn->opnd_bytes); + + memcpy(reg_data, ghcb->shared_buffer, bytes); + break; + + default: + ret = ES_UNSUPPORTED; + } + + return ret; +} + +/* + * The MOVS instruction has two memory operands, which raises the + * problem that it is not known whether the access to the source or the + * destination caused the #VC exception (and hence whether an MMIO read + * or write operation needs to be emulated). + * + * Instead of playing games with walking page-tables and trying to guess + * whether the source or destination is an MMIO range, split the move + * into two operations, a read and a write with only one memory operand. + * This will cause a nested #VC exception on the MMIO address which can + * then be handled. + * + * This implementation has the benefit that it also supports MOVS where + * source _and_ destination are MMIO regions. + * + * It will slow MOVS on MMIO down a lot, but in SEV-ES guests it is a + * rare operation. If it turns out to be a performance problem the split + * operations can be moved to memcpy_fromio() and memcpy_toio(). + */ +static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt, + unsigned int bytes) +{ + unsigned long ds_base, es_base; + unsigned char *src, *dst; + unsigned char buffer[8]; + enum es_result ret; + bool rep; + int off; + + ds_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_DS); + es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES); + + if (ds_base == -1L || es_base == -1L) { + ctxt->fi.vector = X86_TRAP_GP; + ctxt->fi.error_code = 0; + return ES_EXCEPTION; + } + + src = ds_base + (unsigned char *)ctxt->regs->si; + dst = es_base + (unsigned char *)ctxt->regs->di; + + ret = vc_read_mem(ctxt, src, buffer, bytes); + if (ret != ES_OK) + return ret; + + ret = vc_write_mem(ctxt, dst, buffer, bytes); + if (ret != ES_OK) + return ret; + + if (ctxt->regs->flags & X86_EFLAGS_DF) + off = -bytes; + else + off = bytes; + + ctxt->regs->si += off; + ctxt->regs->di += off; + + rep = insn_has_rep_prefix(&ctxt->insn); + if (rep) + ctxt->regs->cx -= 1; + + if (!rep || ctxt->regs->cx == 0) + return ES_OK; + else + return ES_RETRY; +} + +static enum es_result vc_handle_mmio(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + struct insn *insn = &ctxt->insn; + unsigned int bytes = 0; + enum es_result ret; + long *reg_data; + + switch (insn->opcode.bytes[0]) { + /* MMIO Write */ + case 0x88: + bytes = 1; + fallthrough; + case 0x89: + if (!bytes) + bytes = insn->opnd_bytes; + + reg_data = vc_insn_get_reg(ctxt); + if (!reg_data) + return ES_DECODE_FAILED; + + memcpy(ghcb->shared_buffer, reg_data, bytes); + + ret = vc_do_mmio(ghcb, ctxt, bytes, false); + break; + + case 0xc6: + bytes = 1; + fallthrough; + case 0xc7: + if (!bytes) + bytes = insn->opnd_bytes; + + memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes); + + ret = vc_do_mmio(ghcb, ctxt, bytes, false); + break; + + /* MMIO Read */ + case 0x8a: + bytes = 1; + fallthrough; + case 0x8b: + if (!bytes) + bytes = insn->opnd_bytes; + + ret = vc_do_mmio(ghcb, ctxt, bytes, true); + if (ret) + break; + + reg_data = vc_insn_get_reg(ctxt); + if (!reg_data) + return ES_DECODE_FAILED; + + /* Zero-extend for 32-bit operation */ + if (bytes == 4) + *reg_data = 0; + + memcpy(reg_data, ghcb->shared_buffer, bytes); + break; + + /* MOVS instruction */ + case 0xa4: + bytes = 1; + fallthrough; + case 0xa5: + if (!bytes) + bytes = insn->opnd_bytes; + + ret = vc_handle_mmio_movs(ctxt, bytes); + break; + /* Two-Byte Opcodes */ + case 0x0f: + ret = vc_handle_mmio_twobyte_ops(ghcb, ctxt); + break; + default: + ret = ES_UNSUPPORTED; + } + + return ret; +} + +static enum es_result vc_handle_dr7_write(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + struct sev_es_runtime_data *data = this_cpu_read(runtime_data); + long val, *reg = vc_insn_get_rm(ctxt); + enum es_result ret; + + if (!reg) + return ES_DECODE_FAILED; + + val = *reg; + + /* Upper 32 bits must be written as zeroes */ + if (val >> 32) { + ctxt->fi.vector = X86_TRAP_GP; + ctxt->fi.error_code = 0; + return ES_EXCEPTION; + } + + /* Clear out other reserved bits and set bit 10 */ + val = (val & 0xffff23ffL) | BIT(10); + + /* Early non-zero writes to DR7 are not supported */ + if (!data && (val & ~DR7_RESET_VALUE)) + return ES_UNSUPPORTED; + + /* Using a value of 0 for ExitInfo1 means RAX holds the value */ + ghcb_set_rax(ghcb, val); + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0); + if (ret != ES_OK) + return ret; + + if (data) + data->dr7 = val; + + return ES_OK; +} + +static enum es_result vc_handle_dr7_read(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + struct sev_es_runtime_data *data = this_cpu_read(runtime_data); + long *reg = vc_insn_get_rm(ctxt); + + if (!reg) + return ES_DECODE_FAILED; + + if (data) + *reg = data->dr7; + else + *reg = DR7_RESET_VALUE; + + return ES_OK; +} + +static enum es_result vc_handle_wbinvd(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0); +} + +static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + enum es_result ret; + + ghcb_set_rcx(ghcb, ctxt->regs->cx); + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0); + if (ret != ES_OK) + return ret; + + if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb))) + return ES_VMM_ERROR; + + ctxt->regs->ax = ghcb->save.rax; + ctxt->regs->dx = ghcb->save.rdx; + + return ES_OK; +} + +static enum es_result vc_handle_monitor(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + /* + * Treat it as a NOP and do not leak a physical address to the + * hypervisor. + */ + return ES_OK; +} + +static enum es_result vc_handle_mwait(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + /* Treat the same as MONITOR/MONITORX */ + return ES_OK; +} + +static enum es_result vc_handle_vmmcall(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + enum es_result ret; + + ghcb_set_rax(ghcb, ctxt->regs->ax); + ghcb_set_cpl(ghcb, user_mode(ctxt->regs) ? 3 : 0); + + if (x86_platform.hyper.sev_es_hcall_prepare) + x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs); + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0); + if (ret != ES_OK) + return ret; + + if (!ghcb_rax_is_valid(ghcb)) + return ES_VMM_ERROR; + + ctxt->regs->ax = ghcb->save.rax; + + /* + * Call sev_es_hcall_finish() after regs->ax is already set. + * This allows the hypervisor handler to overwrite it again if + * necessary. + */ + if (x86_platform.hyper.sev_es_hcall_finish && + !x86_platform.hyper.sev_es_hcall_finish(ghcb, ctxt->regs)) + return ES_VMM_ERROR; + + return ES_OK; +} + +static enum es_result vc_handle_trap_ac(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + /* + * Calling ecx_alignment_check() directly does not work, because it + * enables IRQs and the GHCB is active. Forward the exception and call + * it later from vc_forward_exception(). + */ + ctxt->fi.vector = X86_TRAP_AC; + ctxt->fi.error_code = 0; + return ES_EXCEPTION; +} + +static __always_inline void vc_handle_trap_db(struct pt_regs *regs) +{ + /* + * The #VC handled here is caused by a #DB in the guest. Upstream + * cb1ad3ecea95 handles it by calling the kernel's debug exception + * handler - noist_exc_debug() or exc_debug(), both noinstr - because + * those "must be handled outside of instrumentation_begin()/end() so + * that the handler will not be raised recursively". + * + * This tree has no noinstr #DB handler yet, only the monolithic + * do_debug(). It is plain dotraplinkage (i.e. __visible), neither + * noinstr nor notrace, and objtool does not validate noinstr at + * all. So the guarantee upstream relies on - that the #DB handler + * is not instrumented - does not hold here. + */ + do_debug(regs, 0); +} + +static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, + struct ghcb *ghcb, + unsigned long exit_code) +{ + enum es_result result; + + switch (exit_code) { + case SVM_EXIT_READ_DR7: + result = vc_handle_dr7_read(ghcb, ctxt); + break; + case SVM_EXIT_WRITE_DR7: + result = vc_handle_dr7_write(ghcb, ctxt); + break; + case SVM_EXIT_EXCP_BASE + X86_TRAP_AC: + result = vc_handle_trap_ac(ghcb, ctxt); + break; + case SVM_EXIT_RDTSC: + case SVM_EXIT_RDTSCP: + result = vc_handle_rdtsc(ghcb, ctxt, exit_code); + break; + case SVM_EXIT_RDPMC: + result = vc_handle_rdpmc(ghcb, ctxt); + break; + case SVM_EXIT_INVD: + pr_err_ratelimited("#VC exception for INVD??? Seriously???\n"); + result = ES_UNSUPPORTED; + break; + case SVM_EXIT_CPUID: + result = vc_handle_cpuid(ghcb, ctxt); + break; + case SVM_EXIT_IOIO: + result = vc_handle_ioio(ghcb, ctxt); + break; + case SVM_EXIT_MSR: + result = vc_handle_msr(ghcb, ctxt); + break; + case SVM_EXIT_VMMCALL: + result = vc_handle_vmmcall(ghcb, ctxt); + break; + case SVM_EXIT_WBINVD: + result = vc_handle_wbinvd(ghcb, ctxt); + break; + case SVM_EXIT_MONITOR: + result = vc_handle_monitor(ghcb, ctxt); + break; + case SVM_EXIT_MWAIT: + result = vc_handle_mwait(ghcb, ctxt); + break; + case SVM_EXIT_NPF: + result = vc_handle_mmio(ghcb, ctxt); + break; + default: + /* + * Unexpected #VC exception + */ + result = ES_UNSUPPORTED; + } + + return result; +} + +static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt) +{ + long error_code = ctxt->fi.error_code; + int trapnr = ctxt->fi.vector; + + ctxt->regs->orig_ax = ctxt->fi.error_code; + + switch (trapnr) { + case X86_TRAP_GP: + do_general_protection(ctxt->regs, error_code); + break; + case X86_TRAP_UD: + do_invalid_op(ctxt->regs, error_code); + break; + case X86_TRAP_AC: + do_alignment_check(ctxt->regs, error_code); + break; + default: + pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n"); + BUG(); + } +} + +static __always_inline bool on_vc_fallback_stack(struct pt_regs *regs) +{ + unsigned long sp = (unsigned long)regs; + + return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2)); +} + +/* + * Main #VC exception handler. It is called when the entry code was able to + * switch off the IST to a safe kernel stack. + * + * With the current implementation it is always possible to switch to a safe + * stack because #VC exceptions only happen at known places, like intercepted + * instructions or accesses to MMIO areas/IO ports. They can also happen with + * code instrumentation when the hypervisor intercepts #DB, but the critical + * paths are forbidden to be instrumented, so #DB exceptions currently also + * only happen in safe places. + */ +DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication) +{ + struct sev_es_runtime_data *data = this_cpu_read(runtime_data); + struct ghcb_state state; + struct es_em_ctxt ctxt; + enum es_result result; + struct ghcb *ghcb; + + lockdep_assert_irqs_disabled(); + + /* + * Handle #DB before calling into !noinstr code to avoid recursive #DB. + */ + if (error_code == SVM_EXIT_EXCP_BASE + X86_TRAP_DB) { + vc_handle_trap_db(regs); + return; + } + + instrumentation_begin(); + + /* + * This is invoked through an interrupt gate, so IRQs are disabled. The + * code below might walk page-tables for user or kernel addresses, so + * keep the IRQs disabled to protect us against concurrent TLB flushes. + */ + + ghcb = sev_es_get_ghcb(&state); + if (!ghcb) { + /* + * Mark GHCBs inactive so that panic() is able to print the + * message. + */ + data->ghcb_active = false; + data->backup_ghcb_active = false; + + panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use"); + } + + vc_ghcb_invalidate(ghcb); + result = vc_init_em_ctxt(&ctxt, regs, error_code); + + if (result == ES_OK) + result = vc_handle_exitcode(&ctxt, ghcb, error_code); + + sev_es_put_ghcb(&state); + + /* Done - now check the result */ + switch (result) { + case ES_OK: + vc_finish_insn(&ctxt); + break; + case ES_UNSUPPORTED: + pr_err_ratelimited("Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n", + error_code, regs->ip); + goto fail; + case ES_VMM_ERROR: + pr_err_ratelimited("Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n", + error_code, regs->ip); + goto fail; + case ES_DECODE_FAILED: + pr_err_ratelimited("Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n", + error_code, regs->ip); + goto fail; + case ES_EXCEPTION: + vc_forward_exception(&ctxt); + break; + case ES_RETRY: + /* Nothing to do */ + break; + default: + pr_emerg("Unknown result in %s():%d\n", __func__, result); + /* + * Emulating the instruction which caused the #VC exception + * failed - can't continue so print debug information + */ + BUG(); + } + +out: + instrumentation_end(); + + return; + +fail: + if (user_mode(regs)) { + /* + * Do not kill the machine if user-space triggered the + * exception. Send SIGBUS instead and let user-space deal with + * it. + */ + force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)0); + } else { + pr_emerg("PANIC: Unhandled #VC exception in kernel space (result=%d)\n", + result); + + /* Show some debug info */ + show_regs(regs); + + /* Ask hypervisor to sev_es_terminate */ + sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + + /* If that fails and we get here - just panic */ + panic("Returned from Terminate-Request to Hypervisor\n"); + } + + goto out; +} + +/* This handler runs on the #VC fall-back stack. It can cause further #VC exceptions */ +DEFINE_IDTENTRY_VC_IST(exc_vmm_communication) +{ + instrumentation_begin(); + panic("Can't handle #VC exception from unsupported context\n"); + instrumentation_end(); +} + +DEFINE_IDTENTRY_VC(exc_vmm_communication) +{ + if (likely(!on_vc_fallback_stack(regs))) + safe_stack_exc_vmm_communication(regs, error_code); + else + ist_exc_vmm_communication(regs, error_code); +} + +bool __init handle_vc_boot_ghcb(struct pt_regs *regs) +{ + unsigned long exit_code = regs->orig_ax; + struct es_em_ctxt ctxt; + enum es_result result; + + /* Do initial setup or terminate the guest */ + if (unlikely(boot_ghcb == NULL && !sev_es_setup_ghcb())) + sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + + vc_ghcb_invalidate(boot_ghcb); + + result = vc_init_em_ctxt(&ctxt, regs, exit_code); + if (result == ES_OK) + result = vc_handle_exitcode(&ctxt, boot_ghcb, exit_code); + + /* Done - now check the result */ + switch (result) { + case ES_OK: + vc_finish_insn(&ctxt); + break; + case ES_UNSUPPORTED: + early_printk("PANIC: Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n", + exit_code, regs->ip); + goto fail; + case ES_VMM_ERROR: + early_printk("PANIC: Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n", + exit_code, regs->ip); + goto fail; + case ES_DECODE_FAILED: + early_printk("PANIC: Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n", + exit_code, regs->ip); + goto fail; + case ES_EXCEPTION: + vc_early_forward_exception(&ctxt); + break; + case ES_RETRY: + /* Nothing to do */ + break; + default: + BUG(); + } + + return true; + +fail: + show_regs(regs); + + while (true) + halt(); +} diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S new file mode 100644 index 0000000000000000000000000000000000000000..ee04941a6546aaf7845d08dfbebdba49fbbf55c4 --- /dev/null +++ b/arch/x86/kernel/sev_verify_cbit.S @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * sev_verify_cbit.S - Code for verification of the C-bit position reported + * by the Hypervisor when running with SEV enabled. + * + * Copyright (c) 2020 Joerg Roedel (jroedel@suse.de) + * + * sev_verify_cbit() is called before switching to a new long-mode page-table + * at boot. + * + * Verify that the C-bit position is correct by writing a random value to + * an encrypted memory location while on the current page-table. Then it + * switches to the new page-table to verify the memory content is still the + * same. After that it switches back to the current page-table and when the + * check succeeded it returns. If the check failed the code invalidates the + * stack pointer and goes into a hlt loop. The stack-pointer is invalidated to + * make sure no interrupt or exception can get the CPU out of the hlt loop. + * + * New page-table pointer is expected in %rdi (first parameter) + * + */ +SYM_FUNC_START(sev_verify_cbit) +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* First check if a C-bit was detected */ + movq sme_me_mask(%rip), %rsi + testq %rsi, %rsi + jz 3f + + /* sme_me_mask != 0 could mean SME or SEV - Check also for SEV */ + movq sev_status(%rip), %rsi + testq %rsi, %rsi + jz 3f + + /* Save CR4 in %rsi */ + movq %cr4, %rsi + + /* Disable Global Pages */ + movq %rsi, %rdx + andq $(~X86_CR4_PGE), %rdx + movq %rdx, %cr4 + + /* + * Verified that running under SEV - now get a random value using + * RDRAND. This instruction is mandatory when running as an SEV guest. + * + * Don't bail out of the loop if RDRAND returns errors. It is better to + * prevent forward progress than to work with a non-random value here. + */ +1: rdrand %rdx + jnc 1b + + /* Store value to memory and keep it in %rdx */ + movq %rdx, sev_check_data(%rip) + + /* Backup current %cr3 value to restore it later */ + movq %cr3, %rcx + + /* Switch to new %cr3 - This might unmap the stack */ + movq %rdi, %cr3 + + /* + * Compare value in %rdx with memory location. If C-bit is incorrect + * this would read the encrypted data and make the check fail. + */ + cmpq %rdx, sev_check_data(%rip) + + /* Restore old %cr3 */ + movq %rcx, %cr3 + + /* Restore previous CR4 */ + movq %rsi, %cr4 + + /* Check CMPQ result */ + je 3f + + /* + * The check failed, prevent any forward progress to prevent ROP + * attacks, invalidate the stack and go into a hlt loop. + */ + xorq %rsp, %rsp + subq $0x1000, %rsp +2: hlt + jmp 2b +3: +#endif + /* Return page-table pointer */ + movq %rdi, %rax + ret +SYM_FUNC_END(sev_verify_cbit) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9c939380df887c43da33155d765dcfff61804ed4..060cbbbcc9e5753dedf1618fe6e210946cb4ce29 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -230,7 +230,7 @@ static void notrace start_secondary(void *unused) load_cr3(swapper_pg_dir); __flush_tlb_all(); #endif - load_current_idt(); + cpu_init_exception_handling(); cpu_init(); rcu_cpu_starting(raw_smp_processor_id()); x86_cpuinit.early_percpu_clock_init(); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 18648baeccf7402046ccc45d2ed23d31e7854917..6aa394c9884477a3d78aa4ca59ee141d914fada9 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include #include @@ -556,6 +557,50 @@ asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs) } NOKPROBE_SYMBOL(sync_regs); +#ifdef CONFIG_AMD_MEM_ENCRYPT +asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *regs) +{ + unsigned long sp, *stack; + struct stack_info info; + struct pt_regs *regs_ret; + + /* + * In the SYSCALL entry path the RSP value comes from user-space - don't + * trust it and switch to the current kernel stack + */ + if (regs->ip >= (unsigned long)entry_SYSCALL_64 && + regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack) { + sp = this_cpu_read(cpu_current_top_of_stack); + goto sync; + } + + /* + * From here on the RSP value is trusted. Now check whether entry + * happened from a safe stack. Not safe are the entry or unknown stacks, + * use the fall-back stack instead in this case. + */ + sp = regs->sp; + stack = (unsigned long *)sp; + + if (!get_stack_info_noinstr(stack, current, &info) || info.type == STACK_TYPE_ENTRY || + info.type >= STACK_TYPE_EXCEPTION_LAST) + sp = __this_cpu_ist_top_va(VC2); + +sync: + /* + * Found a safe stack - switch to it as if the entry didn't happen via + * IST stack. The code below only copies pt_regs, the real switch happens + * in assembly code. + */ + sp = ALIGN_DOWN(sp, 8) - sizeof(*regs_ret); + + regs_ret = (struct pt_regs *)sp; + *regs_ret = *regs; + + return regs_ret; +} +#endif + struct bad_iret_stack { void *error_entry_ret; struct pt_regs regs; @@ -858,6 +903,9 @@ void __init trap_init(void) /* Init cpu_entry_area before IST entries are set up */ setup_cpu_entry_areas(); + /* Init GHCB memory pages when running as an SEV-ES guest */ + sev_es_init_vc_handling(); + idt_setup_traps(); /* diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c index 548fefed71eecdcfcd2437341ae7f7f4dfa7197e..8547d338914d778330999e8c4978798e6792548a 100644 --- a/arch/x86/kernel/umip.c +++ b/arch/x86/kernel/umip.c @@ -317,63 +317,28 @@ static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs) */ bool fixup_umip_exception(struct pt_regs *regs) { - int not_copied, nr_copied, reg_offset, dummy_data_size, umip_inst; - unsigned long seg_base = 0, *reg_addr; + int nr_copied, reg_offset, dummy_data_size, umip_inst; /* 10 bytes is the maximum size of the result of UMIP instructions */ unsigned char dummy_data[10] = { 0 }; unsigned char buf[MAX_INSN_SIZE]; + unsigned long *reg_addr; void __user *uaddr; struct insn insn; - int seg_defs; if (!regs) return false; - /* - * If not in user-space long mode, a custom code segment could be in - * use. This is true in protected mode (if the process defined a local - * descriptor table), or virtual-8086 mode. In most of the cases - * seg_base will be zero as in USER_CS. - */ - if (!user_64bit_mode(regs)) - seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS); - - if (seg_base == -1L) - return false; - - not_copied = copy_from_user(buf, (void __user *)(seg_base + regs->ip), - sizeof(buf)); - nr_copied = sizeof(buf) - not_copied; + nr_copied = insn_fetch_from_user(regs, buf); /* - * The copy_from_user above could have failed if user code is protected - * by a memory protection key. Give up on emulation in such a case. - * Should we issue a page fault? + * The insn_fetch_from_user above could have failed if user code + * is protected by a memory protection key. Give up on emulation + * in such a case. Should we issue a page fault? */ if (!nr_copied) return false; - insn_init(&insn, buf, nr_copied, user_64bit_mode(regs)); - - /* - * Override the default operand and address sizes with what is specified - * in the code segment descriptor. The instruction decoder only sets - * the address size it to either 4 or 8 address bytes and does nothing - * for the operand bytes. This OK for most of the cases, but we could - * have special cases where, for instance, a 16-bit code segment - * descriptor is used. - * If there is an address override prefix, the instruction decoder - * correctly updates these values, even for 16-bit defaults. - */ - seg_defs = insn_get_code_seg_params(regs); - if (seg_defs == -EINVAL) - return false; - - insn.addr_bytes = INSN_CODE_SEG_ADDR_SZ(seg_defs); - insn.opnd_bytes = INSN_CODE_SEG_OPND_SZ(seg_defs); - - insn_get_length(&insn); - if (nr_copied < insn.length) + if (!insn_decode(&insn, regs, buf, nr_copied)) return false; umip_inst = identify_insn(&insn); diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S index a024c4f7ba56105d0693189740ce536b2bf6c70f..641f0fe1e5b4abbc612967c1028c9421e0966294 100644 --- a/arch/x86/kernel/verify_cpu.S +++ b/arch/x86/kernel/verify_cpu.S @@ -31,7 +31,7 @@ #include #include -ENTRY(verify_cpu) +SYM_FUNC_START_LOCAL(verify_cpu) pushf # Save caller passed flags push $0 # Kill any dangerous flags popf @@ -137,4 +137,4 @@ ENTRY(verify_cpu) popf # Restore caller passed flags xorl %eax, %eax ret -ENDPROC(verify_cpu) +SYM_FUNC_END(verify_cpu) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 033b7bb1c4769ee7fea84006abba843d49e89af6..89beecad9f085bc98204ff43ec6806371c7ee9ab 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2025,7 +2025,8 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, int write) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - unsigned long npages, npinned, size; + unsigned long npages, size; + int npinned; unsigned long locked, lock_limit; struct page **pages; unsigned long first, last; @@ -2047,6 +2048,9 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, return NULL; } + if (WARN_ON_ONCE(npages > INT_MAX)) + return NULL; + /* Avoid using vmalloc for smaller buffers. */ size = npages * sizeof(struct page *); if (size > PAGE_SIZE) @@ -8240,6 +8244,8 @@ void sev_install_hooks(void) static int __init svm_init(void) { + __unused_size_checks(); + /* Register CSV specific interface for Hygon CPUs */ if (is_x86_vendor_hygon()) csv_init(&svm_x86_ops); diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 9578eb88fc878ce265defa0eb89d8ca318c1248a..f9f59eb85635078d6b715feb4b8a46f7604ebbcb 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -115,21 +115,23 @@ ENDPROC(__get_user_8) EXPORT_SYMBOL(__get_user_8) -.Lbad_get_user_clac: +SYM_CODE_START_LOCAL(.Lbad_get_user_clac) ASM_CLAC bad_get_user: xor %edx,%edx mov $(-EFAULT),%_ASM_AX ret +SYM_CODE_END(.Lbad_get_user_clac) #ifdef CONFIG_X86_32 -.Lbad_get_user_8_clac: +SYM_CODE_START_LOCAL(.Lbad_get_user_8_clac) ASM_CLAC bad_get_user_8: xor %edx,%edx xor %ecx,%ecx mov $(-EFAULT),%_ASM_AX ret +SYM_CODE_END(.Lbad_get_user_8_clac) #endif _ASM_EXTABLE_UA(1b, .Lbad_get_user_clac) diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index ecdd7b5beda5e5e962594394cc6ed4295cc51ae2..9475b26363ec2b5a220d209469d4264f35aa72ad 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -20,6 +20,7 @@ enum reg_type { REG_TYPE_RM = 0, + REG_TYPE_REG, REG_TYPE_INDEX, REG_TYPE_BASE, }; @@ -52,6 +53,29 @@ static bool is_string_insn(struct insn *insn) } } +/** + * insn_has_rep_prefix() - Determine if instruction has a REP prefix + * @insn: Instruction containing the prefix to inspect + * + * Returns: + * + * true if the instruction has a REP prefix, false if not. + */ +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; +} + /** * get_seg_reg_override_idx() - obtain segment register override index * @insn: Valid instruction with segment override prefixes @@ -442,6 +466,13 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, regno += 8; break; + case REG_TYPE_REG: + regno = X86_MODRM_REG(insn->modrm.value); + + if (X86_REX_R(insn->rex_prefix.value)) + regno += 8; + break; + case REG_TYPE_INDEX: regno = X86_SIB_INDEX(insn->sib.value); if (X86_REX_X(insn->rex_prefix.value)) @@ -810,6 +841,21 @@ int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs) return get_reg_offset(insn, regs, REG_TYPE_RM); } +/** + * insn_get_modrm_reg_off() - Obtain register in reg part of the ModRM byte + * @insn: Instruction containing the ModRM byte + * @regs: Register values as seen when entering kernel mode + * + * Returns: + * + * The register indicated by the reg part of the ModRM byte. The + * register is obtained as an offset from the base of pt_regs. + */ +int insn_get_modrm_reg_off(struct insn *insn, struct pt_regs *regs) +{ + return get_reg_offset(insn, regs, REG_TYPE_REG); +} + /** * get_seg_base_limit() - obtain base address and limit of a segment * @insn: Instruction. Must be valid. @@ -1370,3 +1416,86 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs) return (void __user *)-1L; } } + +/** + * insn_fetch_from_user() - Copy instruction bytes from user-space memory + * @regs: Structure with register values as seen when entering kernel mode + * @buf: Array to store the fetched instruction + * + * Gets the linear address of the instruction and copies the instruction bytes + * to the buf. + * + * Returns: + * + * Number of instruction bytes copied. + * + * 0 if nothing was copied. + */ +int insn_fetch_from_user(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE]) +{ + unsigned long seg_base = 0; + int not_copied; + + /* + * If not in user-space long mode, a custom code segment could be in + * use. This is true in protected mode (if the process defined a local + * descriptor table), or virtual-8086 mode. In most of the cases + * seg_base will be zero as in USER_CS. + */ + if (!user_64bit_mode(regs)) { + seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS); + if (seg_base == -1L) + return 0; + } + + + not_copied = copy_from_user(buf, (void __user *)(seg_base + regs->ip), + MAX_INSN_SIZE); + + return MAX_INSN_SIZE - not_copied; +} + +/** + * insn_decode() - Decode an instruction + * @insn: Structure to store decoded instruction + * @regs: Structure with register values as seen when entering kernel mode + * @buf: Buffer containing the instruction bytes + * @buf_size: Number of instruction bytes available in buf + * + * Decodes the instruction provided in buf and stores the decoding results in + * insn. Also determines the correct address and operand sizes. + * + * Returns: + * + * True if instruction was decoded, False otherwise. + */ +bool insn_decode(struct insn *insn, struct pt_regs *regs, + unsigned char buf[MAX_INSN_SIZE], int buf_size) +{ + int seg_defs; + + insn_init(insn, buf, buf_size, user_64bit_mode(regs)); + + /* + * Override the default operand and address sizes with what is specified + * in the code segment descriptor. The instruction decoder only sets + * the address size it to either 4 or 8 address bytes and does nothing + * for the operand bytes. This OK for most of the cases, but we could + * have special cases where, for instance, a 16-bit code segment + * descriptor is used. + * If there is an address override prefix, the instruction decoder + * correctly updates these values, even for 16-bit defaults. + */ + seg_defs = insn_get_code_seg_params(regs); + if (seg_defs == -EINVAL) + return false; + + insn->addr_bytes = INSN_CODE_SEG_ADDR_SZ(seg_defs); + insn->opnd_bytes = INSN_CODE_SEG_OPND_SZ(seg_defs); + + insn_get_length(insn); + if (buf_size < insn->length) + return false; + + return true; +} diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index 126dd6a9ec9b54c69e7ab2e25ee6ecae2151ee34..a9391d772c8112a44575a61d50b9f43f2d46e3c0 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -91,11 +91,12 @@ ENTRY(__put_user_8) ENDPROC(__put_user_8) EXPORT_SYMBOL(__put_user_8) -.Lbad_put_user_clac: +SYM_CODE_START_LOCAL(.Lbad_put_user_clac) ASM_CLAC .Lbad_put_user: movl $-EFAULT,%eax RET +SYM_CODE_END(.Lbad_put_user_clac) _ASM_EXTABLE_UA(1b, .Lbad_put_user_clac) _ASM_EXTABLE_UA(2b, .Lbad_put_user_clac) diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c index d9643647a9ce57e94e8e54172ec6117b0445a55e..e724f173a1bdd17a2498578531ac6ae7df2d8a2c 100644 --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -17,7 +17,8 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks); DEFINE_PER_CPU(struct cea_exception_stacks*, cea_exception_stacks); #endif -struct cpu_entry_area *get_cpu_entry_area(int cpu) +/* Is called from entry code, so must be noinstr */ +noinstr struct cpu_entry_area *get_cpu_entry_area(int cpu) { unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE; BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0); diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 615264b2e55e72eac92fe456b806a3232b93c3aa..5aaad4d7adf73fc630d827040477dbd381db25b7 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -5,6 +5,7 @@ #include #include +#include #include #include diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 86aa3d2f14c5cbc4e403ef0abc6f87562adfdc86..a23d1c62e7fb32b41ae6c6e3e8a4edc6180b3ffc 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -40,6 +40,8 @@ * section is later cleared. */ u64 sme_me_mask __section(.data) = 0; +u64 sev_status __section(.data) = 0; +u64 sev_check_data __section(.data) = 0; EXPORT_SYMBOL(sme_me_mask); DEFINE_STATIC_KEY_FALSE(sev_enable_key); EXPORT_SYMBOL_GPL(sev_enable_key); @@ -198,6 +200,37 @@ void __init sme_early_init(void) swiotlb_force = SWIOTLB_FORCE; } +void __init sev_setup_arch(void) +{ + phys_addr_t total_mem = memblock_phys_mem_size(); + unsigned long size; + + if (!sev_active()) + return; + + /* + * For SEV, all DMA has to occur via shared/unencrypted pages. + * SEV uses SWIOTLB to make this happen without changing device + * drivers. However, depending on the workload being run, the + * default 64MB of SWIOTLB may not be enough and SWIOTLB may + * run out of buffers for DMA, resulting in I/O errors and/or + * performance degradation especially with high I/O workloads. + * + * Adjust the default size of SWIOTLB for SEV guests using + * a percentage of guest memory for SWIOTLB buffers. + * Also, as the SWIOTLB bounce buffer memory is allocated + * from low memory, ensure that the adjusted size is within + * the limits of low available memory. + * + * The percentage of guest memory used here for SWIOTLB buffers + * is more of an approximation of the static adjustment which + * 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6% + */ + size = total_mem * 6 / 100; + size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G); + swiotlb_adjust_size(size); +} + static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot) { unsigned long pfn = 0; @@ -403,7 +436,13 @@ bool sme_active(void) bool sev_active(void) { - return sme_me_mask && sev_enabled; + return sev_status & MSR_AMD64_SEV_ENABLED; +} + +/* Needs to be called from non-instrumentable code */ +bool noinstr sev_es_active(void) +{ + return sev_status & MSR_AMD64_SEV_ES_ENABLED; } /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ @@ -458,6 +497,32 @@ void __init mem_encrypt_free_decrypted_mem(void) free_init_pages("unused decrypted", vaddr, vaddr_end); } +static void print_mem_encrypt_feature_info(void) +{ + pr_info("AMD Memory Encryption Features active:"); + + /* Secure Memory Encryption */ + if (sme_active()) { + /* + * SME is mutually exclusive with any of the SEV + * features below. + */ + pr_cont(" SME\n"); + return; + } + + /* Secure Encrypted Virtualization */ + if (sev_active()) + pr_cont(" SEV"); + + /* Encrypted Register State */ + if (sev_es_active()) + pr_cont(" SEV-ES"); + + pr_cont("\n"); +} + +/* Architecture __weak replacement functions */ void __init mem_encrypt_init(void) { if (!sme_me_mask) @@ -477,8 +542,6 @@ void __init mem_encrypt_init(void) return; } - pr_info("AMD %s active\n", - sev_active() ? "Secure Encrypted Virtualization (SEV)" - : "Secure Memory Encryption (SME)"); + print_mem_encrypt_feature_info(); } diff --git a/arch/x86/mm/mem_encrypt_hygon.c b/arch/x86/mm/mem_encrypt_hygon.c index cc5e5f2e63444d83558c8d215cf7ae280bf2cc1b..6a278764d3b0dc38a4edbf29f9ef61bf88af5bd5 100644 --- a/arch/x86/mm/mem_encrypt_hygon.c +++ b/arch/x86/mm/mem_encrypt_hygon.c @@ -32,4 +32,8 @@ void print_hygon_cc_feature_info(void) /* Secure Encrypted Virtualization */ pr_info(" HYGON CSV"); } + + /* Encrypted Register State */ + if (sev_es_active()) + pr_info(" HYGON CSV2"); } diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index 77d4aa57fd35e21507ccd587fb0ca4525204de1a..a7cd0466c0fc67f03aa62cc6b3eee3556271d308 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -549,6 +549,9 @@ void __init sme_enable(struct boot_params *bp) if (!(msr & MSR_AMD64_SEV_ENABLED)) return; + /* Save SEV_STATUS to avoid reading MSR again */ + sev_status = msr; + /* SEV state cannot be controlled by a command line option */ sme_me_mask = me_mask; sev_enabled = true; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 52839781811033ed8c234617373b0650b0e8274c..b1b94e5dedff494c5d3140cc1ecefab994b2515e 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -48,6 +48,7 @@ #include #include #include +#include /* * We allocate runtime services regions top-down, starting from -4G, i.e. @@ -381,6 +382,15 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 1; } + /* + * When SEV-ES is active, the GHCB as set by the kernel will be used + * by firmware. Create a 1:1 unencrypted mapping for each GHCB. + */ + if (sev_es_efi_map_ghcbs(pgd)) { + pr_err("Failed to create 1:1 mapping for the GHCBs!\n"); + return 1; + } + /* * When making calls to the firmware everything needs to be 1:1 * mapped and addressable with 32-bit pointers. Map the kernel diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index fac50ebb122b5471966f34ecf474ff834da420eb..35267f71c277930c797a3b45596246c75db6039a 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -9,6 +9,7 @@ #include #include #include +#include struct real_mode_header *real_mode_header; u32 *trampoline_cr4_features; @@ -64,6 +65,25 @@ void __init reserve_real_mode(void) crash_reserve_low_1M(); } +static void sme_sev_setup_real_mode(struct trampoline_header *th) +{ +#ifdef CONFIG_AMD_MEM_ENCRYPT + if (sme_active()) + th->flags |= TH_FLAGS_SME_ACTIVE; + + if (sev_es_active()) { + /* + * Skip the call to verify_cpu() in secondary_startup_64 as it + * will cause #VC exceptions when the AP can't handle them yet. + */ + th->start = (u64) secondary_startup_64_no_verify; + + if (sev_es_setup_ap_jump_table(real_mode_header)) + panic("Failed to get/update SEV-ES AP Jump Table"); + } +#endif +} + static void __init setup_real_mode(void) { u16 real_mode_seg; @@ -131,8 +151,6 @@ static void __init setup_real_mode(void) *trampoline_cr4_features = mmu_cr4_features; trampoline_header->flags = 0; - if (sme_active()) - trampoline_header->flags |= TH_FLAGS_SME_ACTIVE; trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); @@ -147,6 +165,8 @@ static void __init setup_real_mode(void) for (i = pgd_index(__PAGE_OFFSET); i < PTRS_PER_PGD; i++) trampoline_pgd[i] = init_top_pgt[i].pgd; #endif + + sme_sev_setup_real_mode(trampoline_header); } /* diff --git a/arch/x86/realmode/rm/header.S b/arch/x86/realmode/rm/header.S index 6363761cc74cf59b22b9c896590b06afdf30721b..6a7e2b183f62c1fd77795efc812d07919b05ac47 100644 --- a/arch/x86/realmode/rm/header.S +++ b/arch/x86/realmode/rm/header.S @@ -20,6 +20,9 @@ GLOBAL(real_mode_header) /* SMP trampoline */ .long pa_trampoline_start .long pa_trampoline_header +#ifdef CONFIG_AMD_MEM_ENCRYPT + .long pa_sev_es_trampoline_start +#endif #ifdef CONFIG_X86_64 .long pa_trampoline_pgd; #endif diff --git a/arch/x86/realmode/rm/reboot.S b/arch/x86/realmode/rm/reboot.S index cd2f97b9623baeec44b4d3128d613f82802e439b..f91425a01f8f9186a50c33c648cc35ca3d915dc8 100644 --- a/arch/x86/realmode/rm/reboot.S +++ b/arch/x86/realmode/rm/reboot.S @@ -33,7 +33,7 @@ ENTRY(machine_real_restart_asm) movl %eax, %cr0 ljmpl $__KERNEL32_CS, $pa_machine_real_restart_paging_off -GLOBAL(machine_real_restart_paging_off) +SYM_INNER_LABEL(machine_real_restart_paging_off, SYM_L_GLOBAL) xorl %eax, %eax xorl %edx, %edx movl $MSR_EFER, %ecx diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index aee2b45d83b879ac7475024de38c9b9cfca7f45b..ee5e9d2f265b3c3ab6249fc262cc315d815001fb 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -56,6 +56,7 @@ ENTRY(trampoline_start) testl %eax, %eax # Check for return code jnz no_longmode +.Lswitch_to_protected: /* * GDT tables in non default location kernel can be beyond 16MB and * lgdt will not be able to load the address as in real mode default @@ -78,6 +79,26 @@ ENTRY(trampoline_start) no_longmode: hlt jmp no_longmode + +#ifdef CONFIG_AMD_MEM_ENCRYPT +/* SEV-ES supports non-zero IP for entry points - no alignment needed */ +SYM_CODE_START(sev_es_trampoline_start) + cli # We should be safe anyway + + LJMPW_RM(1f) +1: + mov %cs, %ax # Code and data in the same place + mov %ax, %ds + mov %ax, %es + mov %ax, %ss + + # Setup stack + movl $rm_stack_end, %esp + + jmp .Lswitch_to_protected +SYM_CODE_END(sev_es_trampoline_start) +#endif /* CONFIG_AMD_MEM_ENCRYPT */ + #include "../kernel/verify_cpu.S" .section ".text32","ax" diff --git a/arch/x86/realmode/rm/wakeup_asm.S b/arch/x86/realmode/rm/wakeup_asm.S index 05ac9c17c8111b9c9672386fcddaa5dcca1dd98e..2ddabef839bcd07cf164d1bb3c615fab5b0cd609 100644 --- a/arch/x86/realmode/rm/wakeup_asm.S +++ b/arch/x86/realmode/rm/wakeup_asm.S @@ -171,8 +171,8 @@ END(wakeup_gdt) /* This is the standard real-mode IDT */ .balign 16 -GLOBAL(wakeup_idt) +SYM_DATA_START(wakeup_idt) .word 0xffff /* limit */ .long 0 /* address */ .word 0 -END(wakeup_idt) +SYM_DATA_END(wakeup_idt) diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index a42015b305f406ee2b48a40df81daeee628f1832..af38469afd148c4f307d9b3ba529689266f0c78b 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -362,6 +362,9 @@ function convert_operands(count,opnd, i,j,imm,mod) END { if (awkchecked != "") exit 1 + + print "#ifndef __BOOT_COMPRESSED\n" + # print escape opcode map's array print "/* Escape opcode map array */" print "const insn_attr_t * const inat_escape_tables[INAT_ESC_MAX + 1]" \ @@ -388,6 +391,51 @@ END { for (j = 0; j < max_lprefix; j++) if (atable[i,j]) print " ["i"]["j"] = "atable[i,j]"," - print "};" + print "};\n" + + print "#else /* !__BOOT_COMPRESSED */\n" + + print "/* Escape opcode map array */" + print "static const insn_attr_t *inat_escape_tables[INAT_ESC_MAX + 1]" \ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "/* Group opcode map array */" + print "static const insn_attr_t *inat_group_tables[INAT_GRP_MAX + 1]"\ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "/* AVX opcode map array */" + print "static const insn_attr_t *inat_avx_tables[X86_VEX_M_MAX + 1]"\ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "static void inat_init_tables(void)" + print "{" + + # print escape opcode map's array + print "\t/* Print Escape opcode map array */" + for (i = 0; i < geid; i++) + for (j = 0; j < max_lprefix; j++) + if (etable[i,j]) + print "\tinat_escape_tables["i"]["j"] = "etable[i,j]";" + print "" + + # print group opcode map's array + print "\t/* Print Group opcode map array */" + for (i = 0; i < ggid; i++) + for (j = 0; j < max_lprefix; j++) + if (gtable[i,j]) + print "\tinat_group_tables["i"]["j"] = "gtable[i,j]";" + print "" + # print AVX opcode map's array + print "\t/* Print AVX opcode map array */" + for (i = 0; i < gaid; i++) + for (j = 0; j < max_lprefix; j++) + if (atable[i,j]) + print "\tinat_avx_tables["i"]["j"] = "atable[i,j]";" + + print "}" + print "#endif" } diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 99eb5d35fb6610c3f4095000abb5847d034db23a..ad87742b5136431d606e0aa2a9f4f776f8b03d31 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -20,6 +20,7 @@ #include #include #include +#include #include @@ -51,6 +52,14 @@ MODULE_FIRMWARE("amd/amd_sev_fam19h_model0xh.sbin"); /* 3rd gen EPYC */ static bool psp_dead; static int psp_timeout; +/* Trusted Memory Region (TMR): + * The TMR is a 1MB area that must be 1MB aligned. Use the page allocator + * to allocate the memory, which will return aligned memory for the specified + * allocation order. + */ +#define SEV_ES_TMR_SIZE (1024 * 1024) +static void *sev_es_tmr; + static inline bool sev_version_greater_or_equal(u8 maj, u8 min) { struct sev_device *sev = psp_master->sev_data; @@ -236,6 +245,20 @@ static int __sev_platform_init_locked(int *error) if (sev->state == SEV_STATE_INIT) return 0; + if (sev_es_tmr) { + u64 tmr_pa; + + /* + * Do not include the encryption mask on the physical + * address of the TMR (firmware should clear it anyway). + */ + tmr_pa = __pa(sev_es_tmr); + + sev->init_cmd_buf.flags |= SEV_INIT_FLAGS_SEV_ES; + sev->init_cmd_buf.tmr_address = tmr_pa; + sev->init_cmd_buf.tmr_len = SEV_ES_TMR_SIZE; + } + rc = __sev_do_cmd_locked(SEV_CMD_INIT, &sev->init_cmd_buf, error); if (rc) return rc; @@ -1069,6 +1092,7 @@ EXPORT_SYMBOL_GPL(sev_issue_cmd_external_user); void sev_pci_init(void) { struct sev_device *sev = psp_master->sev_data; + struct page *tmr_page; int error, rc; if (!sev) @@ -1098,6 +1122,16 @@ void sev_pci_init(void) sev_update_firmware(sev->dev) == 0) sev_get_api_version(); + /* Obtain the TMR memory area for SEV-ES use */ + tmr_page = alloc_pages(GFP_KERNEL, get_order(SEV_ES_TMR_SIZE)); + if (tmr_page) { + sev_es_tmr = page_address(tmr_page); + } else { + sev_es_tmr = NULL; + dev_warn(sev->dev, + "SEV: TMR allocation failed, SEV-ES support unavailable\n"); + } + /* Initialize the platform */ rc = sev_platform_init(&error); if (rc && (error == SEV_RET_SECURE_DATA_INVALID)) { @@ -1136,4 +1170,13 @@ void sev_pci_exit(void) return; sev_platform_shutdown(NULL); + + if (sev_es_tmr) { + /* The TMR area was encrypted, flush it from the cache */ + wbinvd_on_all_cpus(); + + free_pages((unsigned long)sev_es_tmr, + get_order(SEV_ES_TMR_SIZE)); + sev_es_tmr = NULL; + } } diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index 8c5b5529dbc05d7cec1f08bc58450d451e13d78e..bf5a03c9b1ee6015abe33b727e38faa15f0fffe0 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -25,6 +25,7 @@ cflags-$(CONFIG_ARM) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \ cflags-$(CONFIG_EFI_ARMSTUB) += -I$(srctree)/scripts/dtc/libfdt KBUILD_CFLAGS := $(cflags-y) -DDISABLE_BRANCH_PROFILING \ + -include $(srctree)/include/linux/hidden.h \ -D__NO_FORTIFY \ $(call cc-option,-ffreestanding) \ $(call cc-option,-fno-stack-protector) \ diff --git a/include/linux/hidden.h b/include/linux/hidden.h new file mode 100644 index 0000000000000000000000000000000000000000..49a17b6b5962a90c4004923de568849204d674c9 --- /dev/null +++ b/include/linux/hidden.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * When building position independent code with GCC using the -fPIC option, + * (or even the -fPIE one on older versions), it will assume that we are + * building a dynamic object (either a shared library or an executable) that + * may have symbol references that can only be resolved at load time. For a + * variety of reasons (ELF symbol preemption, the CoW footprint of the section + * that is modified by the loader), this results in all references to symbols + * with external linkage to go via entries in the Global Offset Table (GOT), + * which carries absolute addresses which need to be fixed up when the + * executable image is loaded at an offset which is different from its link + * time offset. + * + * Fortunately, there is a way to inform the compiler that such symbol + * references will be satisfied at link time rather than at load time, by + * giving them 'hidden' visibility. + */ + +#pragma GCC visibility push(hidden) diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index cba728fad8aedbede6932d590d85a006acd53089..93e62a85fa284b50d7bfedefb44788cb94f30381 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -20,16 +20,20 @@ #ifdef CONFIG_PROVE_LOCKING extern void trace_softirqs_on(unsigned long ip); extern void trace_softirqs_off(unsigned long ip); + extern void lockdep_hardirqs_on_prepare(unsigned long ip); extern void lockdep_hardirqs_on(unsigned long ip); extern void lockdep_hardirqs_off(unsigned long ip); #else static inline void trace_softirqs_on(unsigned long ip) { } static inline void trace_softirqs_off(unsigned long ip) { } + static inline void lockdep_hardirqs_on_prepare(unsigned long ip) { } static inline void lockdep_hardirqs_on(unsigned long ip) { } static inline void lockdep_hardirqs_off(unsigned long ip) { } #endif #ifdef CONFIG_TRACE_IRQFLAGS + extern void trace_hardirqs_on_prepare(void); + extern void trace_hardirqs_off_prepare(void); extern void trace_hardirqs_on(void); extern void trace_hardirqs_off(void); # define trace_hardirq_context(p) ((p)->hardirq_context) @@ -53,6 +57,8 @@ do { \ current->softirq_context--; \ } while (0) #else +# define trace_hardirqs_on_prepare() do { } while (0) +# define trace_hardirqs_off_prepare() do { } while (0) # define trace_hardirqs_on() do { } while (0) # define trace_hardirqs_off() do { } while (0) # define trace_hardirq_context(p) 0 diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index e226ecf702a03e9e1bcf4adc92c14d01c7dc89a3..3dad7eea8df67ad705be81b8d37f05e6ca6e96f7 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -102,6 +102,8 @@ struct sev_data_init { u32 tmr_len; /* In */ } __packed; +#define SEV_INIT_FLAGS_SEV_ES 0x01 + /** * struct sev_data_pek_csr - PEK_CSR command parameters * @@ -388,6 +390,7 @@ struct sev_data_send_update_data { */ struct sev_data_send_update_vmsa { u32 handle; /* In */ + u32 reserved1; u64 hdr_address; /* In */ u32 hdr_len; /* In/Out */ u32 reserved2; diff --git a/include/linux/sched.h b/include/linux/sched.h index 2e7048f23f89049bead355a4430e2bc816ba301f..bc6fb6e391fc548461ed2957376cb74ecb40f22e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1115,6 +1115,7 @@ struct task_struct { unsigned int hardirq_disable_event; int hardirqs_enabled; int hardirq_context; + u64 hardirq_chain_key; unsigned long softirq_disable_ip; unsigned long softirq_enable_ip; unsigned int softirq_disable_event; diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 0a8fced6aaec4834d9a2edda370f394f63c9808d..3e154b8a48aa8e8a03477f9f6724bcf8281e769e 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -24,6 +24,9 @@ enum swiotlb_force { */ #define IO_TLB_SEGSIZE 128 +/* default to 64MB */ +#define IO_TLB_DEFAULT_SIZE (64UL<<20) + /* * log of the size of each IO TLB slab. The number of slabs is command line * controllable. @@ -80,6 +83,7 @@ void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); bool is_swiotlb_active(void); +void __init swiotlb_adjust_size(unsigned long new_size); #else #define swiotlb_force SWIOTLB_NO_FORCE static inline bool is_swiotlb_buffer(phys_addr_t paddr) @@ -108,6 +112,10 @@ static inline bool is_swiotlb_active(void) { return false; } + +static inline void swiotlb_adjust_size(unsigned long new_size) +{ +} #endif /* CONFIG_SWIOTLB */ extern void swiotlb_print_info(void); diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index 0549a5c622bf33a9c3c96999d1f2f0a4f0747e87..91b4c63d5cbf4f5f319aa5e342172ae1aa7aa9dd 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -83,6 +83,8 @@ struct sev_user_data_status { __u32 guest_count; /* Out */ } __packed; +#define SEV_STATUS_FLAGS_CONFIG_ES 0x0100 + /** * struct sev_user_data_pek_csr - PEK_CSR command parameters * diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 913cb71198af4699cb0f72ea11317d5390dc8366..4a1fd00c4534fec71255f214c089970ede4c0e3b 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -151,8 +151,6 @@ void swiotlb_set_max_segment(unsigned int val) max_segment = rounddown(val, PAGE_SIZE); } -/* default to 64MB */ -#define IO_TLB_DEFAULT_SIZE (64UL<<20) unsigned long swiotlb_size_or_default(void) { unsigned long size; @@ -162,6 +160,24 @@ unsigned long swiotlb_size_or_default(void) return size ? size : (IO_TLB_DEFAULT_SIZE); } +void __init swiotlb_adjust_size(unsigned long new_size) +{ + unsigned long size; + + /* + * If swiotlb parameter has not been specified, give a chance to + * architectures such as those supporting memory encryption to + * adjust/expand SWIOTLB size for their use. + */ + if (!io_tlb_nslabs) { + size = ALIGN(new_size, 1 << IO_TLB_SHIFT); + io_tlb_nslabs = size >> IO_TLB_SHIFT; + io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + + pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20); + } +} + void swiotlb_print_info(void) { unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 6f66ee8d0aeb1c2ac59e39594e234e6e5242bba3..96c036f834638f9a2be5071f8e5c646d916feb86 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3489,13 +3489,10 @@ mark_held_locks(struct task_struct *curr, enum lock_usage_bit base_bit) /* * Hardirqs will be enabled: */ -static void __trace_hardirqs_on_caller(unsigned long ip) +static void __trace_hardirqs_on_caller(void) { struct task_struct *curr = current; - /* we'll do an OFF -> ON transition: */ - curr->hardirqs_enabled = 1; - /* * We are going to turn hardirqs on, so set the * usage bit for all held locks: @@ -3508,15 +3505,19 @@ static void __trace_hardirqs_on_caller(unsigned long ip) * this bit from being set before) */ if (curr->softirqs_enabled) - if (!mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ)) - return; - - curr->hardirq_enable_ip = ip; - curr->hardirq_enable_event = ++curr->irq_events; - debug_atomic_inc(hardirqs_on_events); + mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ); } -void lockdep_hardirqs_on(unsigned long ip) +/** + * lockdep_hardirqs_on_prepare - Prepare for enabling interrupts + * @ip: Caller address + * + * Invoked before a possible transition to RCU idle from exit to user or + * guest mode. This ensures that all RCU operations are done before RCU + * stops watching. After the RCU transition lockdep_hardirqs_on() has to be + * invoked to set the final state. + */ +void lockdep_hardirqs_on_prepare(unsigned long ip) { if (unlikely(!debug_locks || current->lockdep_recursion)) return; @@ -3552,20 +3553,62 @@ void lockdep_hardirqs_on(unsigned long ip) if (DEBUG_LOCKS_WARN_ON(current->hardirq_context)) return; + current->hardirq_chain_key = current->curr_chain_key; + current->lockdep_recursion = 1; - __trace_hardirqs_on_caller(ip); + __trace_hardirqs_on_caller(); current->lockdep_recursion = 0; } -NOKPROBE_SYMBOL(lockdep_hardirqs_on); +EXPORT_SYMBOL_GPL(lockdep_hardirqs_on_prepare); + +void noinstr lockdep_hardirqs_on(unsigned long ip) +{ + struct task_struct *curr = current; + + if (unlikely(!debug_locks || curr->lockdep_recursion)) + return; + + if (curr->hardirqs_enabled) { + /* + * Neither irq nor preemption are disabled here + * so this is racy by nature but losing one hit + * in a stat is not a big deal. + */ + __debug_atomic_inc(redundant_hardirqs_on); + return; + } + + /* + * We're enabling irqs and according to our state above irqs weren't + * already enabled, yet we find the hardware thinks they are in fact + * enabled.. someone messed up their IRQ state tracing. + */ + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return; + + /* + * Ensure the lock stack remained unchanged between + * lockdep_hardirqs_on_prepare() and lockdep_hardirqs_on(). + */ + DEBUG_LOCKS_WARN_ON(current->hardirq_chain_key != + current->curr_chain_key); + + /* we'll do an OFF -> ON transition: */ + curr->hardirqs_enabled = 1; + curr->hardirq_enable_ip = ip; + curr->hardirq_enable_event = ++curr->irq_events; + debug_atomic_inc(hardirqs_on_events); +} +EXPORT_SYMBOL_GPL(lockdep_hardirqs_on); /* * Hardirqs were disabled: */ -void lockdep_hardirqs_off(unsigned long ip) +void noinstr lockdep_hardirqs_off(unsigned long ip) { struct task_struct *curr = current; - if (unlikely(!debug_locks || current->lockdep_recursion)) + if (unlikely(!debug_locks || curr->lockdep_recursion)) return; /* @@ -3583,10 +3626,11 @@ void lockdep_hardirqs_off(unsigned long ip) curr->hardirq_disable_ip = ip; curr->hardirq_disable_event = ++curr->irq_events; debug_atomic_inc(hardirqs_off_events); - } else + } else { debug_atomic_inc(redundant_hardirqs_off); + } } -NOKPROBE_SYMBOL(lockdep_hardirqs_off); +EXPORT_SYMBOL_GPL(lockdep_hardirqs_off); /* * Softirqs will be enabled: @@ -4131,8 +4175,8 @@ static void print_unlock_imbalance_bug(struct task_struct *curr, dump_stack(); } -static int match_held_lock(const struct held_lock *hlock, - const struct lockdep_map *lock) +static noinstr int match_held_lock(const struct held_lock *hlock, + const struct lockdep_map *lock) { if (hlock->instance == lock) return 1; @@ -4419,7 +4463,7 @@ __lock_release(struct lockdep_map *lock, unsigned long ip) return 0; } -static nokprobe_inline +static __always_inline int __lock_is_held(const struct lockdep_map *lock, int read) { struct task_struct *curr = current; @@ -4633,7 +4677,7 @@ void lock_release(struct lockdep_map *lock, int nested, } EXPORT_SYMBOL_GPL(lock_release); -int lock_is_held_type(const struct lockdep_map *lock, int read) +noinstr int lock_is_held_type(const struct lockdep_map *lock, int read) { unsigned long flags; int ret = 0; diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c index e9645f829b94cd2989010f8be5d7ff3018facbe2..465e261abbbd715d062cd3edcc1be41fdf8537f9 100644 --- a/kernel/trace/trace_preemptirq.c +++ b/kernel/trace/trace_preemptirq.c @@ -19,6 +19,24 @@ /* Per-cpu variable to prevent redundant calls when IRQs already off */ static DEFINE_PER_CPU(int, tracing_irq_cpu); +/* + * Like trace_hardirqs_on() but without the lockdep invocation. This is + * used in the low level entry code where the ordering vs. RCU is important + * and lockdep uses a staged approach which splits the lockdep hardirq + * tracking into a RCU on and a RCU off section. + */ +void trace_hardirqs_on_prepare(void) +{ + if (this_cpu_read(tracing_irq_cpu)) { + if (!in_nmi()) + trace_irq_enable(CALLER_ADDR0, CALLER_ADDR1); + tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1); + this_cpu_write(tracing_irq_cpu, 0); + } +} +EXPORT_SYMBOL(trace_hardirqs_on_prepare); +NOKPROBE_SYMBOL(trace_hardirqs_on_prepare); + void trace_hardirqs_on(void) { if (this_cpu_read(tracing_irq_cpu)) { @@ -28,11 +46,31 @@ void trace_hardirqs_on(void) this_cpu_write(tracing_irq_cpu, 0); } + lockdep_hardirqs_on_prepare(CALLER_ADDR0); lockdep_hardirqs_on(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_on); NOKPROBE_SYMBOL(trace_hardirqs_on); +/* + * Like trace_hardirqs_off() but without the lockdep invocation. This is + * used in the low level entry code where the ordering vs. RCU is important + * and lockdep uses a staged approach which splits the lockdep hardirq + * tracking into a RCU on and a RCU off section. + */ +void trace_hardirqs_off_prepare(void) +{ + if (!this_cpu_read(tracing_irq_cpu)) { + this_cpu_write(tracing_irq_cpu, 1); + tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1); + if (!in_nmi()) + trace_irq_disable(CALLER_ADDR0, CALLER_ADDR1); + } + +} +EXPORT_SYMBOL(trace_hardirqs_off_prepare); +NOKPROBE_SYMBOL(trace_hardirqs_off_prepare); + void trace_hardirqs_off(void) { if (!this_cpu_read(tracing_irq_cpu)) { @@ -56,6 +94,7 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr) this_cpu_write(tracing_irq_cpu, 0); } + lockdep_hardirqs_on_prepare(caller_addr); lockdep_hardirqs_on(caller_addr); } EXPORT_SYMBOL(trace_hardirqs_on_caller); diff --git a/lib/debug_locks.c b/lib/debug_locks.c index a75ee30b77cb8dd70d792d36e17ec74b0385852f..06d3135bd184c498ae02a60a9da4b5ba502e442d 100644 --- a/lib/debug_locks.c +++ b/lib/debug_locks.c @@ -36,7 +36,7 @@ EXPORT_SYMBOL_GPL(debug_locks_silent); /* * Generic 'turn off all lock debugging' function: */ -int debug_locks_off(void) +noinstr int debug_locks_off(void) { if (debug_locks && __debug_locks_off()) { if (!debug_locks_silent) { diff --git a/tools/arch/x86/tools/gen-insn-attr-x86.awk b/tools/arch/x86/tools/gen-insn-attr-x86.awk index a42015b305f406ee2b48a40df81daeee628f1832..af38469afd148c4f307d9b3ba529689266f0c78b 100644 --- a/tools/arch/x86/tools/gen-insn-attr-x86.awk +++ b/tools/arch/x86/tools/gen-insn-attr-x86.awk @@ -362,6 +362,9 @@ function convert_operands(count,opnd, i,j,imm,mod) END { if (awkchecked != "") exit 1 + + print "#ifndef __BOOT_COMPRESSED\n" + # print escape opcode map's array print "/* Escape opcode map array */" print "const insn_attr_t * const inat_escape_tables[INAT_ESC_MAX + 1]" \ @@ -388,6 +391,51 @@ END { for (j = 0; j < max_lprefix; j++) if (atable[i,j]) print " ["i"]["j"] = "atable[i,j]"," - print "};" + print "};\n" + + print "#else /* !__BOOT_COMPRESSED */\n" + + print "/* Escape opcode map array */" + print "static const insn_attr_t *inat_escape_tables[INAT_ESC_MAX + 1]" \ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "/* Group opcode map array */" + print "static const insn_attr_t *inat_group_tables[INAT_GRP_MAX + 1]"\ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "/* AVX opcode map array */" + print "static const insn_attr_t *inat_avx_tables[X86_VEX_M_MAX + 1]"\ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "static void inat_init_tables(void)" + print "{" + + # print escape opcode map's array + print "\t/* Print Escape opcode map array */" + for (i = 0; i < geid; i++) + for (j = 0; j < max_lprefix; j++) + if (etable[i,j]) + print "\tinat_escape_tables["i"]["j"] = "etable[i,j]";" + print "" + + # print group opcode map's array + print "\t/* Print Group opcode map array */" + for (i = 0; i < ggid; i++) + for (j = 0; j < max_lprefix; j++) + if (gtable[i,j]) + print "\tinat_group_tables["i"]["j"] = "gtable[i,j]";" + print "" + # print AVX opcode map's array + print "\t/* Print AVX opcode map array */" + for (i = 0; i < gaid; i++) + for (j = 0; j < max_lprefix; j++) + if (atable[i,j]) + print "\tinat_avx_tables["i"]["j"] = "atable[i,j]";" + + print "}" + print "#endif" }