From: Joerg Roedel <jroe...@suse.de> Handling exceptions during boot requires a working GDT. The kernel GDT can't be used on the direct mapping, so load a startup GDT and setup segments.
Signed-off-by: Joerg Roedel <jroe...@suse.de> Link: https://lore.kernel.org/r/20200724160336.5435-30-j...@8bytes.org --- arch/x86/include/asm/setup.h | 1 + arch/x86/kernel/head64.c | 33 +++++++++++++++++++++++++++++++++ arch/x86/kernel/head_64.S | 14 ++++++++++++++ 3 files changed, 48 insertions(+) diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 84b645cc8bc9..5c2fd05bd52c 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -48,6 +48,7 @@ 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 void startup_64_setup_env(unsigned long physbase); extern int early_make_pgtable(unsigned long address); #ifdef CONFIG_X86_INTEL_MID diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index cbb71c1b574f..8c82be44be94 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -61,6 +61,24 @@ 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) @@ -489,3 +507,18 @@ void __init x86_64_start_reservations(char *real_mode_data) start_kernel(); } + +/* + * 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"); +} diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 16da4ac01597..2b2e91627221 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -73,6 +73,20 @@ SYM_CODE_START_NOALIGN(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 -- 2.28.0
