2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-29 15:43:59 +08:00
linux-next/arch/x86/kernel/head_32.S
Joerg Roedel e3238faf20 x86/pgtable/32: Allocate 8k page-tables when PTI is enabled
Allocate a kernel and a user page-table root when PTI is enabled. Also
allocate a full page per root for PAE because otherwise the bit to flip in
CR3 to switch between them would be non-constant, which creates a lot of
hassle.  Keep that for a later optimization.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-18-git-send-email-joro@8bytes.org
2018-07-20 01:11:41 +02:00

624 lines
15 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
/*
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* Enhanced CPU detection and feature setting code by Mike Jagdis
* and Martin Mares, November 1997.
*/
.text
#include <linux/threads.h>
#include <linux/init.h>
#include <linux/linkage.h>
#include <asm/segment.h>
#include <asm/page_types.h>
#include <asm/pgtable_types.h>
#include <asm/cache.h>
#include <asm/thread_info.h>
#include <asm/asm-offsets.h>
#include <asm/setup.h>
#include <asm/processor-flags.h>
#include <asm/msr-index.h>
#include <asm/cpufeatures.h>
#include <asm/percpu.h>
#include <asm/nops.h>
#include <asm/bootparam.h>
#include <asm/export.h>
#include <asm/pgtable_32.h>
/* Physical address */
#define pa(X) ((X) - __PAGE_OFFSET)
/*
* References to members of the new_cpu_data structure.
*/
#define X86 new_cpu_data+CPUINFO_x86
#define X86_VENDOR new_cpu_data+CPUINFO_x86_vendor
#define X86_MODEL new_cpu_data+CPUINFO_x86_model
#define X86_STEPPING new_cpu_data+CPUINFO_x86_stepping
#define X86_HARD_MATH new_cpu_data+CPUINFO_hard_math
#define X86_CPUID new_cpu_data+CPUINFO_cpuid_level
#define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability
#define X86_VENDOR_ID new_cpu_data+CPUINFO_x86_vendor_id
#define SIZEOF_PTREGS 17*4
/*
* Worst-case size of the kernel mapping we need to make:
* a relocatable kernel can live anywhere in lowmem, so we need to be able
* to map all of lowmem.
*/
KERNEL_PAGES = LOWMEM_PAGES
INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE
RESERVE_BRK(pagetables, INIT_MAP_SIZE)
/*
* 32-bit kernel entrypoint; only used by the boot CPU. On entry,
* %esi points to the real-mode code as a 32-bit pointer.
* CS and DS must be 4 GB flat segments, but we don't depend on
* any particular GDT layout, because we load our own as soon as we
* can.
*/
__HEAD
ENTRY(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.
*/
lgdt pa(boot_gdt_descr)
movl $(__BOOT_DS),%eax
movl %eax,%ds
movl %eax,%es
movl %eax,%fs
movl %eax,%gs
movl %eax,%ss
2:
leal -__PAGE_OFFSET(%ecx),%esp
/*
* Clear BSS first so that there are no surprises...
*/
cld
xorl %eax,%eax
movl $pa(__bss_start),%edi
movl $pa(__bss_stop),%ecx
subl %edi,%ecx
shrl $2,%ecx
rep ; stosl
/*
* Copy bootup parameters out of the way.
* Note: %esi still has the pointer to the real-mode data.
* With the kexec as boot loader, parameter segment might be loaded beyond
* kernel image and might not even be addressable by early boot page tables.
* (kexec on panic case). Hence copy out the parameters before initializing
* page tables.
*/
movl $pa(boot_params),%edi
movl $(PARAM_SIZE/4),%ecx
cld
rep
movsl
movl pa(boot_params) + NEW_CL_POINTER,%esi
andl %esi,%esi
jz 1f # No command line
movl $pa(boot_command_line),%edi
movl $(COMMAND_LINE_SIZE/4),%ecx
rep
movsl
1:
#ifdef CONFIG_OLPC
/* save OFW's pgdir table for later use when calling into OFW */
movl %cr3, %eax
movl %eax, pa(olpc_ofw_pgd)
#endif
#ifdef CONFIG_MICROCODE
/* Early load ucode on BSP. */
call load_ucode_bsp
#endif
/* Create early pagetables. */
call mk_early_pgtbl_32
/* Do early initialization of the fixmap area */
movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
#ifdef CONFIG_X86_PAE
#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
movl %eax,pa(initial_pg_pmd+0x1000*KPMDS-8)
#else
movl %eax,pa(initial_page_table+0xffc)
#endif
#ifdef CONFIG_PARAVIRT
/* This is can only trip for a broken bootloader... */
cmpw $0x207, pa(boot_params + BP_version)
jb .Ldefault_entry
/* Paravirt-compatible boot parameters. Look to see what architecture
we're booting under. */
movl pa(boot_params + BP_hardware_subarch), %eax
cmpl $num_subarch_entries, %eax
jae .Lbad_subarch
movl pa(subarch_entries)(,%eax,4), %eax
subl $__PAGE_OFFSET, %eax
jmp *%eax
.Lbad_subarch:
WEAK(xen_entry)
/* Unknown implementation; there's really
nothing we can do at this point. */
ud2a
__INITDATA
subarch_entries:
.long .Ldefault_entry /* normal x86/PC */
.long xen_entry /* Xen hypervisor */
.long .Ldefault_entry /* Moorestown MID */
num_subarch_entries = (. - subarch_entries) / 4
.previous
#else
jmp .Ldefault_entry
#endif /* CONFIG_PARAVIRT */
#ifdef CONFIG_HOTPLUG_CPU
/*
* Boot CPU0 entry point. It's called from play_dead(). Everything has been set
* up already except stack. We just set up stack here. Then call
* start_secondary().
*/
ENTRY(start_cpu0)
movl initial_stack, %ecx
movl %ecx, %esp
call *(initial_code)
1: jmp 1b
ENDPROC(start_cpu0)
#endif
/*
* Non-boot CPU entry point; entered from trampoline.S
* We can't lgdt here, because lgdt itself uses a data segment, but
* we know the trampoline has already loaded the boot_gdt for us.
*
* If cpu hotplug is not supported then this code can go in init section
* which will be freed later
*/
ENTRY(startup_32_smp)
cld
movl $(__BOOT_DS),%eax
movl %eax,%ds
movl %eax,%es
movl %eax,%fs
movl %eax,%gs
movl pa(initial_stack),%ecx
movl %eax,%ss
leal -__PAGE_OFFSET(%ecx),%esp
#ifdef CONFIG_MICROCODE
/* Early load ucode on AP. */
call load_ucode_ap
#endif
.Ldefault_entry:
movl $(CR0_STATE & ~X86_CR0_PG),%eax
movl %eax,%cr0
/*
* We want to start out with EFLAGS unambiguously cleared. Some BIOSes leave
* bits like NT set. This would confuse the debugger if this code is traced. So
* initialize them properly now before switching to protected mode. That means
* DF in particular (even though we have cleared it earlier after copying the
* command line) because GCC expects it.
*/
pushl $0
popfl
/*
* New page tables may be in 4Mbyte page mode and may be using the global pages.
*
* NOTE! If we are on a 486 we may have no cr4 at all! Specifically, cr4 exists
* if and only if CPUID exists and has flags other than the FPU flag set.
*/
movl $-1,pa(X86_CPUID) # preset CPUID level
movl $X86_EFLAGS_ID,%ecx
pushl %ecx
popfl # set EFLAGS=ID
pushfl
popl %eax # get EFLAGS
testl $X86_EFLAGS_ID,%eax # did EFLAGS.ID remained set?
jz .Lenable_paging # hw disallowed setting of ID bit
# which means no CPUID and no CR4
xorl %eax,%eax
cpuid
movl %eax,pa(X86_CPUID) # save largest std CPUID function
movl $1,%eax
cpuid
andl $~1,%edx # Ignore CPUID.FPU
jz .Lenable_paging # No flags or only CPUID.FPU = no CR4
movl pa(mmu_cr4_features),%eax
movl %eax,%cr4
testb $X86_CR4_PAE, %al # check if PAE is enabled
jz .Lenable_paging
/* Check if extended functions are implemented */
movl $0x80000000, %eax
cpuid
/* Value must be in the range 0x80000001 to 0x8000ffff */
subl $0x80000001, %eax
cmpl $(0x8000ffff-0x80000001), %eax
ja .Lenable_paging
/* Clear bogus XD_DISABLE bits */
call verify_cpu
mov $0x80000001, %eax
cpuid
/* Execute Disable bit supported? */
btl $(X86_FEATURE_NX & 31), %edx
jnc .Lenable_paging
/* Setup EFER (Extended Feature Enable Register) */
movl $MSR_EFER, %ecx
rdmsr
btsl $_EFER_NX, %eax
/* Make changes effective */
wrmsr
.Lenable_paging:
/*
* Enable paging
*/
movl $pa(initial_page_table), %eax
movl %eax,%cr3 /* set the page table pointer.. */
movl $CR0_STATE,%eax
movl %eax,%cr0 /* ..and set paging (PG) bit */
ljmp $__BOOT_CS,$1f /* Clear prefetch and normalize %eip */
1:
/* Shift the stack pointer to a virtual address */
addl $__PAGE_OFFSET, %esp
/*
* start system 32-bit setup. We need to re-do some of the things done
* in 16-bit mode for the "real" operations.
*/
movl setup_once_ref,%eax
andl %eax,%eax
jz 1f # Did we do this already?
call *%eax
1:
/*
* Check if it is 486
*/
movb $4,X86 # at least 486
cmpl $-1,X86_CPUID
je .Lis486
/* get vendor info */
xorl %eax,%eax # call CPUID with 0 -> return vendor ID
cpuid
movl %eax,X86_CPUID # save CPUID level
movl %ebx,X86_VENDOR_ID # lo 4 chars
movl %edx,X86_VENDOR_ID+4 # next 4 chars
movl %ecx,X86_VENDOR_ID+8 # last 4 chars
orl %eax,%eax # do we have processor info as well?
je .Lis486
movl $1,%eax # Use the CPUID instruction to get CPU type
cpuid
movb %al,%cl # save reg for future use
andb $0x0f,%ah # mask processor family
movb %ah,X86
andb $0xf0,%al # mask model
shrb $4,%al
movb %al,X86_MODEL
andb $0x0f,%cl # mask mask revision
movb %cl,X86_STEPPING
movl %edx,X86_CAPABILITY
.Lis486:
movl $0x50022,%ecx # set AM, WP, NE and MP
movl %cr0,%eax
andl $0x80000011,%eax # Save PG,PE,ET
orl %ecx,%eax
movl %eax,%cr0
lgdt early_gdt_descr
ljmp $(__KERNEL_CS),$1f
1: movl $(__KERNEL_DS),%eax # reload all the segment registers
movl %eax,%ss # after changing gdt.
movl $(__USER_DS),%eax # DS/ES contains default USER segment
movl %eax,%ds
movl %eax,%es
movl $(__KERNEL_PERCPU), %eax
movl %eax,%fs # set this cpu's percpu
movl $(__KERNEL_STACK_CANARY),%eax
movl %eax,%gs
xorl %eax,%eax # Clear LDT
lldt %ax
call *(initial_code)
1: jmp 1b
ENDPROC(startup_32_smp)
#include "verify_cpu.S"
/*
* setup_once
*
* The setup work we only want to run on the BSP.
*
* Warning: %esi is live across this function.
*/
__INIT
setup_once:
#ifdef CONFIG_STACKPROTECTOR
/*
* Configure the stack canary. The linker can't handle this by
* relocation. Manually set base address in stack canary
* segment descriptor.
*/
movl $gdt_page,%eax
movl $stack_canary,%ecx
movw %cx, 8 * GDT_ENTRY_STACK_CANARY + 2(%eax)
shrl $16, %ecx
movb %cl, 8 * GDT_ENTRY_STACK_CANARY + 4(%eax)
movb %ch, 8 * GDT_ENTRY_STACK_CANARY + 7(%eax)
#endif
andl $0,setup_once_ref /* Once is enough, thanks */
ret
ENTRY(early_idt_handler_array)
# 36(%esp) %eflags
# 32(%esp) %cs
# 28(%esp) %eip
# 24(%rsp) error code
i = 0
.rept NUM_EXCEPTION_VECTORS
.if ((EXCEPTION_ERRCODE_MASK >> i) & 1) == 0
pushl $0 # Dummy error code, to make stack frame uniform
.endif
pushl $i # 20(%esp) Vector number
jmp early_idt_handler_common
i = i + 1
.fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
.endr
ENDPROC(early_idt_handler_array)
early_idt_handler_common:
/*
* The stack is the hardware frame, an error code or zero, and the
* vector number.
*/
cld
incl %ss:early_recursion_flag
/* The vector number is in pt_regs->gs */
cld
pushl %fs /* pt_regs->fs (__fsh varies by model) */
pushl %es /* pt_regs->es (__esh varies by model) */
pushl %ds /* pt_regs->ds (__dsh varies by model) */
pushl %eax /* pt_regs->ax */
pushl %ebp /* pt_regs->bp */
pushl %edi /* pt_regs->di */
pushl %esi /* pt_regs->si */
pushl %edx /* pt_regs->dx */
pushl %ecx /* pt_regs->cx */
pushl %ebx /* pt_regs->bx */
/* Fix up DS and ES */
movl $(__KERNEL_DS), %ecx
movl %ecx, %ds
movl %ecx, %es
/* Load the vector number into EDX */
movl PT_GS(%esp), %edx
/* Load GS into pt_regs->gs (and maybe clobber __gsh) */
movw %gs, PT_GS(%esp)
movl %esp, %eax /* args are pt_regs (EAX), trapnr (EDX) */
call early_fixup_exception
popl %ebx /* pt_regs->bx */
popl %ecx /* pt_regs->cx */
popl %edx /* pt_regs->dx */
popl %esi /* pt_regs->si */
popl %edi /* pt_regs->di */
popl %ebp /* pt_regs->bp */
popl %eax /* pt_regs->ax */
popl %ds /* pt_regs->ds (always ignores __dsh) */
popl %es /* pt_regs->es (always ignores __esh) */
popl %fs /* pt_regs->fs (always ignores __fsh) */
popl %gs /* pt_regs->gs (always ignores __gsh) */
decl %ss:early_recursion_flag
addl $4, %esp /* pop pt_regs->orig_ax */
iret
ENDPROC(early_idt_handler_common)
/* This is the default interrupt "handler" :-) */
ENTRY(early_ignore_irq)
cld
#ifdef CONFIG_PRINTK
pushl %eax
pushl %ecx
pushl %edx
pushl %es
pushl %ds
movl $(__KERNEL_DS),%eax
movl %eax,%ds
movl %eax,%es
cmpl $2,early_recursion_flag
je hlt_loop
incl early_recursion_flag
pushl 16(%esp)
pushl 24(%esp)
pushl 32(%esp)
pushl 40(%esp)
pushl $int_msg
call printk
call dump_stack
addl $(5*4),%esp
popl %ds
popl %es
popl %edx
popl %ecx
popl %eax
#endif
iret
hlt_loop:
hlt
jmp hlt_loop
ENDPROC(early_ignore_irq)
__INITDATA
.align 4
GLOBAL(early_recursion_flag)
.long 0
__REFDATA
.align 4
ENTRY(initial_code)
.long i386_start_kernel
ENTRY(setup_once_ref)
.long setup_once
#ifdef CONFIG_PAGE_TABLE_ISOLATION
#define PGD_ALIGN (2 * PAGE_SIZE)
#define PTI_USER_PGD_FILL 1024
#else
#define PGD_ALIGN (PAGE_SIZE)
#define PTI_USER_PGD_FILL 0
#endif
/*
* BSS section
*/
__PAGE_ALIGNED_BSS
.align PGD_ALIGN
#ifdef CONFIG_X86_PAE
.globl initial_pg_pmd
initial_pg_pmd:
.fill 1024*KPMDS,4,0
#else
.globl initial_page_table
initial_page_table:
.fill 1024,4,0
#endif
.align PGD_ALIGN
initial_pg_fixmap:
.fill 1024,4,0
.globl swapper_pg_dir
.align PGD_ALIGN
swapper_pg_dir:
.fill 1024,4,0
.fill PTI_USER_PGD_FILL,4,0
.globl empty_zero_page
empty_zero_page:
.fill 4096,1,0
EXPORT_SYMBOL(empty_zero_page)
/*
* This starts the data section.
*/
#ifdef CONFIG_X86_PAE
__PAGE_ALIGNED_DATA
/* Page-aligned for the benefit of paravirt? */
.align PGD_ALIGN
ENTRY(initial_page_table)
.long pa(initial_pg_pmd+PGD_IDENT_ATTR),0 /* low identity map */
# if KPMDS == 3
.long pa(initial_pg_pmd+PGD_IDENT_ATTR),0
.long pa(initial_pg_pmd+PGD_IDENT_ATTR+0x1000),0
.long pa(initial_pg_pmd+PGD_IDENT_ATTR+0x2000),0
# elif KPMDS == 2
.long 0,0
.long pa(initial_pg_pmd+PGD_IDENT_ATTR),0
.long pa(initial_pg_pmd+PGD_IDENT_ATTR+0x1000),0
# elif KPMDS == 1
.long 0,0
.long 0,0
.long pa(initial_pg_pmd+PGD_IDENT_ATTR),0
# else
# error "Kernel PMDs should be 1, 2 or 3"
# endif
.align PAGE_SIZE /* needs to be page-sized too */
#endif
.data
.balign 4
ENTRY(initial_stack)
/*
* The SIZEOF_PTREGS gap is a convention which helps the in-kernel
* unwinder reliably detect the end of the stack.
*/
.long init_thread_union + THREAD_SIZE - SIZEOF_PTREGS - \
TOP_OF_KERNEL_STACK_PADDING;
__INITRODATA
int_msg:
.asciz "Unknown interrupt or fault at: %p %p %p\n"
#include "../../x86/xen/xen-head.S"
/*
* The IDT and GDT 'descriptors' are a strange 48-bit object
* only used by the lidt and lgdt instructions. They are not
* like usual segment descriptors - they consist of a 16-bit
* segment size, and 32-bit linear address value:
*/
.data
.globl boot_gdt_descr
ALIGN
# early boot GDT descriptor (must use 1:1 address mapping)
.word 0 # 32 bit align gdt_desc.address
boot_gdt_descr:
.word __BOOT_DS+7
.long boot_gdt - __PAGE_OFFSET
# boot GDT descriptor (later on used by CPU#0):
.word 0 # 32 bit align gdt_desc.address
ENTRY(early_gdt_descr)
.word GDT_ENTRIES*8-1
.long gdt_page /* Overwritten for secondary CPUs */
/*
* The boot_gdt must mirror the equivalent in setup.S and is
* used only for booting.
*/
.align L1_CACHE_BYTES
ENTRY(boot_gdt)
.fill GDT_ENTRY_BOOT_CS,8,0
.quad 0x00cf9a000000ffff /* kernel 4GB code at 0x00000000 */
.quad 0x00cf92000000ffff /* kernel 4GB data at 0x00000000 */