diff options
Diffstat (limited to 'arch/x86/kernel/head64.c')
| -rw-r--r-- | arch/x86/kernel/head64.c | 298 |
1 files changed, 75 insertions, 223 deletions
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 16b1cbd3a61e..fd28b53dbac5 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -5,8 +5,6 @@ * 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 @@ -19,14 +17,16 @@ #include <linux/start_kernel.h> #include <linux/io.h> #include <linux/memblock.h> -#include <linux/mem_encrypt.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> @@ -36,237 +36,36 @@ #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 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); -#ifdef CONFIG_X86_5LEVEL 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); -#endif +SYM_PIC_ALIAS(ptrs_per_p4d); -#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT 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); -#endif - -#define __head __section(.head.text) - -static void __head *fixup_pointer(void *ptr, unsigned long physaddr) -{ - return ptr - (void *)_text + (void *)physaddr; -} - -static unsigned long __head *fixup_long(void *ptr, unsigned long physaddr) -{ - return fixup_pointer(ptr, physaddr); -} - -#ifdef CONFIG_X86_5LEVEL -static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr) -{ - return fixup_pointer(ptr, physaddr); -} - -static bool __head check_la57_support(unsigned long physaddr) -{ - /* - * 5-level paging is detected and enabled at kernel decomression - * stage. Only check if it has been enabled there. - */ - if (!(native_read_cr4() & X86_CR4_LA57)) - return false; - - *fixup_int(&__pgtable_l5_enabled, physaddr) = 1; - *fixup_int(&pgdir_shift, physaddr) = 48; - *fixup_int(&ptrs_per_p4d, physaddr) = 512; - *fixup_long(&page_offset_base, physaddr) = __PAGE_OFFSET_BASE_L5; - *fixup_long(&vmalloc_base, physaddr) = __VMALLOC_BASE_L5; - *fixup_long(&vmemmap_base, physaddr) = __VMEMMAP_BASE_L5; - - return true; -} -#else -static bool __head check_la57_support(unsigned long physaddr) -{ - return false; -} -#endif - -/* Code in __startup_64() can be relocated during execution, but the compiler - * doesn't have to generate PC-relative relocations when accessing globals from - * that function. Clang actually does not generate them, which leads to - * boot-time crashes. To work around this problem, every global pointer must - * be adjusted using fixup_pointer(). - */ -unsigned long __head __startup_64(unsigned long physaddr, - struct boot_params *bp) -{ - unsigned long vaddr, vaddr_end; - unsigned long load_delta, *p; - unsigned long pgtable_flags; - pgdval_t *pgd; - p4dval_t *p4d; - pudval_t *pud; - pmdval_t *pmd, pmd_entry; - pteval_t *mask_ptr; - bool la57; - int i; - unsigned int *next_pgt_ptr; - - la57 = check_la57_support(physaddr); - - /* 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 (;;); - - /* Activate Secure Memory Encryption (SME) if supported and enabled */ - sme_enable(bp); - - /* Include the SME encryption mask in the fixup value */ - load_delta += sme_get_me_mask(); - - /* Fixup the physical addresses in the page table */ - - pgd = fixup_pointer(&early_top_pgt, physaddr); - p = pgd + pgd_index(__START_KERNEL_map); - if (la57) - *p = (unsigned long)level4_kernel_pgt; - else - *p = (unsigned long)level3_kernel_pgt; - *p += _PAGE_TABLE_NOENC - __START_KERNEL_map + load_delta; - - if (la57) { - 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); - for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--) - pmd[i] += 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. - */ - - next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr); - pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); - pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); - - pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask(); - - if (la57) { - p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); - - i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; - pgd[i + 0] = (pgdval_t)p4d + pgtable_flags; - pgd[i + 1] = (pgdval_t)p4d + pgtable_flags; - - i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D; - p4d[i + 0] = (pgdval_t)pud + pgtable_flags; - p4d[i + 1] = (pgdval_t)pud + pgtable_flags; - } else { - i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; - pgd[i + 0] = (pgdval_t)pud + pgtable_flags; - pgd[i + 1] = (pgdval_t)pud + pgtable_flags; - } - - i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD; - pud[i + 0] = (pudval_t)pmd + pgtable_flags; - pud[i + 1] = (pudval_t)pmd + pgtable_flags; - - pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; - /* Filter out unsupported __PAGE_KERNEL_* bits: */ - mask_ptr = fixup_pointer(&__supported_pte_mask, physaddr); - pmd_entry &= *mask_ptr; - pmd_entry += sme_get_me_mask(); - 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 - remove the memory encryption mask to obtain - * the true physical address. - */ - *fixup_long(&phys_base, physaddr) += load_delta - sme_get_me_mask(); - - /* Encrypt the kernel and related (if SME is active) */ - sme_encrypt_kernel(bp); - - /* - * Clear the memory encryption mask from the .bss..decrypted section. - * The bss section will be memset to zero later in the initialization so - * there is no need to zero it after changing the memory encryption - * attribute. - */ - if (mem_encrypt_active()) { - vaddr = (unsigned long)__start_bss_decrypted; - vaddr_end = (unsigned long)__end_bss_decrypted; - for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { - i = pmd_index(vaddr); - pmd[i] -= sme_get_me_mask(); - } - } - - /* - * Return the SME encryption mask (if SME is active) to be used as a - * modifier for the initial pgdir entry programmed into CR3. - */ - return sme_get_me_mask(); -} - -unsigned long __startup_secondary_64(void) -{ - /* - * Return the SME encryption mask (if SME is active) to be used as a - * modifier for the initial pgdir entry programmed into CR3. - */ - return sme_get_me_mask(); -} /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) @@ -277,7 +76,7 @@ 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; @@ -287,7 +86,7 @@ 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; @@ -344,10 +143,10 @@ again: } 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; @@ -357,12 +156,30 @@ 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; + + 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) @@ -402,7 +219,7 @@ static void __init copy_bootdata(char *real_mode_data) 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) { /* * Build-time sanity checks on the kernel image and module @@ -423,8 +240,18 @@ 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); /* @@ -436,8 +263,21 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) kasan_early_init(); + /* + * 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)); /* @@ -451,7 +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) @@ -469,3 +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); +} |