diff options
Diffstat (limited to 'arch/x86/kernel/head64.c')
| -rw-r--r-- | arch/x86/kernel/head64.c | 251 |
1 files changed, 128 insertions, 123 deletions
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 46c3c73e7f43..fd28b53dbac5 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -1,10 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 /* * prepare to run common code * * Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE */ -#define DISABLE_BRANCH_PROFILING +/* cpu_feature_enabled() cannot be used this early */ +#define USE_EARLY_PGTABLE_L5 + #include <linux/init.h> #include <linux/linkage.h> #include <linux/types.h> @@ -14,13 +17,16 @@ #include <linux/start_kernel.h> #include <linux/io.h> #include <linux/memblock.h> +#include <linux/cc_platform.h> +#include <linux/pgtable.h> +#include <asm/asm.h> +#include <asm/page_64.h> #include <asm/processor.h> #include <asm/proto.h> #include <asm/smp.h> #include <asm/setup.h> #include <asm/desc.h> -#include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/sections.h> #include <asm/kdebug.h> @@ -29,138 +35,58 @@ #include <asm/bootparam_utils.h> #include <asm/microcode.h> #include <asm/kasan.h> +#include <asm/fixmap.h> +#include <asm/realmode.h> +#include <asm/extable.h> +#include <asm/trapnr.h> +#include <asm/sev.h> +#include <asm/tdx.h> +#include <asm/init.h> /* * Manage page tables very early on. */ -extern pgd_t early_top_pgt[PTRS_PER_PGD]; extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; -static unsigned int __initdata next_early_pgt; +unsigned int __initdata next_early_pgt; +SYM_PIC_ALIAS(next_early_pgt); pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); -#define __head __section(.head.text) - -static void __head *fixup_pointer(void *ptr, unsigned long physaddr) -{ - return ptr - (void *)_text + (void *)physaddr; -} - -void __head __startup_64(unsigned long physaddr) -{ - unsigned long load_delta, *p; - pgdval_t *pgd; - p4dval_t *p4d; - pudval_t *pud; - pmdval_t *pmd, pmd_entry; - int i; - - /* Is the address too large? */ - if (physaddr >> MAX_PHYSMEM_BITS) - for (;;); - - /* - * Compute the delta between the address I am compiled to run at - * and the address I am actually running at. - */ - load_delta = physaddr - (unsigned long)(_text - __START_KERNEL_map); - - /* Is the address not 2M aligned? */ - if (load_delta & ~PMD_PAGE_MASK) - for (;;); - - /* Fixup the physical addresses in the page table */ - - pgd = fixup_pointer(&early_top_pgt, physaddr); - pgd[pgd_index(__START_KERNEL_map)] += load_delta; - - if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d = fixup_pointer(&level4_kernel_pgt, physaddr); - p4d[511] += load_delta; - } - - pud = fixup_pointer(&level3_kernel_pgt, physaddr); - pud[510] += load_delta; - pud[511] += load_delta; - - pmd = fixup_pointer(level2_fixmap_pgt, physaddr); - pmd[506] += load_delta; - - /* - * Set up the identity mapping for the switchover. These - * entries should *NOT* have the global bit set! This also - * creates a bunch of nonsense entries but that is fine -- - * it avoids problems around wraparound. - */ - - pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); - pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); - - if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); - - i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; - pgd[i + 0] = (pgdval_t)p4d + _KERNPG_TABLE; - pgd[i + 1] = (pgdval_t)p4d + _KERNPG_TABLE; - - i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D; - p4d[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; - p4d[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; - } else { - i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; - pgd[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; - pgd[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; - } - - i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD; - pud[i + 0] = (pudval_t)pmd + _KERNPG_TABLE; - pud[i + 1] = (pudval_t)pmd + _KERNPG_TABLE; - - pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; - pmd_entry += physaddr; - - for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) { - int idx = i + (physaddr >> PMD_SHIFT) % PTRS_PER_PMD; - pmd[idx] = pmd_entry + i * PMD_SIZE; - } - - /* - * Fixup the kernel text+data virtual addresses. Note that - * we might write invalid pmds, when the kernel is relocated - * cleanup_highmap() fixes this up along with the mappings - * beyond _end. - */ - - pmd = fixup_pointer(level2_kernel_pgt, physaddr); - for (i = 0; i < PTRS_PER_PMD; i++) { - if (pmd[i] & _PAGE_PRESENT) - pmd[i] += load_delta; - } - - /* Fixup phys_base */ - p = fixup_pointer(&phys_base, physaddr); - *p += load_delta; -} +unsigned int __pgtable_l5_enabled __ro_after_init; +SYM_PIC_ALIAS(__pgtable_l5_enabled); +unsigned int pgdir_shift __ro_after_init = 39; +EXPORT_SYMBOL(pgdir_shift); +SYM_PIC_ALIAS(pgdir_shift); +unsigned int ptrs_per_p4d __ro_after_init = 1; +EXPORT_SYMBOL(ptrs_per_p4d); +SYM_PIC_ALIAS(ptrs_per_p4d); + +unsigned long page_offset_base __ro_after_init = __PAGE_OFFSET_BASE_L4; +EXPORT_SYMBOL(page_offset_base); +unsigned long vmalloc_base __ro_after_init = __VMALLOC_BASE_L4; +EXPORT_SYMBOL(vmalloc_base); +unsigned long vmemmap_base __ro_after_init = __VMEMMAP_BASE_L4; +EXPORT_SYMBOL(vmemmap_base); /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) { memset(early_top_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1)); next_early_pgt = 0; - write_cr3(__pa_nodebug(early_top_pgt)); + write_cr3(__sme_pa_nodebug(early_top_pgt)); } /* Create a new PMD entry */ -int __init early_make_pgtable(unsigned long address) +bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd) { unsigned long physaddr = address - __PAGE_OFFSET; pgdval_t pgd, *pgd_p; p4dval_t p4d, *p4d_p; pudval_t pud, *pud_p; - pmdval_t pmd, *pmd_p; + pmdval_t *pmd_p; /* 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; @@ -171,7 +97,7 @@ again: * critical -- __PAGE_OFFSET would point us back into the dynamic * range and we might end up looping forever... */ - if (!IS_ENABLED(CONFIG_X86_5LEVEL)) + if (!pgtable_l5_enabled()) p4d_p = pgd_p; else if (pgd) p4d_p = (p4dval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); @@ -215,18 +141,45 @@ again: memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD); *pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; } - pmd = (physaddr & PMD_MASK) + early_pmd_flags; pmd_p[pmd_index(address)] = pmd; - return 0; + return true; +} + +static bool __init early_make_pgtable(unsigned long address) +{ + unsigned long physaddr = address - __PAGE_OFFSET; + pmdval_t pmd; + + pmd = (physaddr & PMD_MASK) + early_pmd_flags; + + 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; + + if (trapnr == X86_TRAP_VE && tdx_early_handle_ve(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) +void __init clear_bss(void) { memset(__bss_start, 0, (unsigned long) __bss_stop - (unsigned long) __bss_start); + memset(__brk_base, 0, + (unsigned long) __brk_limit - (unsigned long) __brk_base); } static unsigned long get_cmd_line_ptr(void) @@ -243,19 +196,31 @@ static void __init copy_bootdata(char *real_mode_data) char * command_line; unsigned long cmd_line_ptr; - memcpy(&boot_params, real_mode_data, sizeof boot_params); + /* + * If SME is active, this will create decrypted mappings of the + * boot data in advance of the copy operations. + */ + sme_map_bootdata(real_mode_data); + + memcpy(&boot_params, real_mode_data, sizeof(boot_params)); sanitize_boot_params(&boot_params); cmd_line_ptr = get_cmd_line_ptr(); if (cmd_line_ptr) { command_line = __va(cmd_line_ptr); memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); } + + /* + * The old boot data is no longer needed and won't be reserved, + * freeing up that memory for use by the system. If SME is active, + * we need to remove the mappings that were created so that the + * memory doesn't remain mapped as decrypted. + */ + sme_unmap_bootdata(real_mode_data); } -asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) +asmlinkage __visible void __init __noreturn x86_64_start_kernel(char * real_mode_data) { - int i; - /* * Build-time sanity checks on the kernel image and module * area mappings. (these are purely build-time and produce no code) @@ -266,7 +231,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) BUILD_BUG_ON((__START_KERNEL_map & ~PMD_MASK) != 0); BUILD_BUG_ON((MODULES_VADDR & ~PMD_MASK) != 0); BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL)); - BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) == + MAYBE_BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) == (__START_KERNEL & PGDIR_MASK))); BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END); @@ -275,15 +240,43 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) /* Kill off the identity-map trampoline */ reset_early_page_tables(); + if (pgtable_l5_enabled()) { + page_offset_base = __PAGE_OFFSET_BASE_L5; + vmalloc_base = __VMALLOC_BASE_L5; + vmemmap_base = __VMEMMAP_BASE_L5; + } + clear_bss(); + /* + * This needs to happen *before* kasan_early_init() because latter maps stuff + * into that page. + */ clear_page(init_top_pgt); + /* + * SME support may update early_pmd_flags to include the memory + * encryption mask, so it needs to be called before anything + * that may generate a page fault. + */ + sme_early_init(); + kasan_early_init(); - for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) - set_intr_gate(i, early_idt_handler_array[i]); - load_idt((const struct desc_ptr *)&idt_descr); + /* + * Flush global TLB entries which could be left over from the trampoline page + * table. + * + * This needs to happen *after* kasan_early_init() as KASAN-enabled .configs + * instrument native_write_cr4() so KASAN must be initialized for that + * instrumentation to work. + */ + __native_tlb_flush_global(this_cpu_read(cpu_tlbstate.cr4)); + + idt_setup_early_handler(); + + /* Needed before cc_platform_has() can be used for TDX */ + tdx_early_init(); copy_bootdata(__va(real_mode_data)); @@ -298,7 +291,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) x86_64_start_reservations(real_mode_data); } -void __init x86_64_start_reservations(char *real_mode_data) +void __init __noreturn x86_64_start_reservations(char *real_mode_data) { /* version is always not zero if it is copied */ if (!boot_params.hdr.version) @@ -316,3 +309,15 @@ void __init x86_64_start_reservations(char *real_mode_data) start_kernel(); } + +void early_setup_idt(void) +{ + void *handler = NULL; + + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) { + setup_ghcb(); + handler = vc_boot_ghcb; + } + + __pi_startup_64_load_idt(handler); +} |