linux/arch/arm64/kernel/head.S
Will Deacon 8ec4198743 arm64: mm: ensure patched kernel text is fetched from PoU
The arm64 booting document requires that the bootloader has cleaned the
kernel image to the PoC. However, when a CPU re-enters the kernel due to
either a CPU hotplug "on" event or resuming from a low-power state (e.g.
cpuidle), the kernel text may in-fact be dirty at the PoU due to things
like alternative patching or even module loading.

Thanks to I-cache speculation with the MMU off, stale instructions could
be fetched prior to enabling the MMU, potentially leading to crashes
when executing regions of code that have been modified at runtime.

This patch addresses the issue by ensuring that the local I-cache is
invalidated immediately after a CPU has enabled its MMU but before
jumping out of the identity mapping. Any stale instructions fetched from
the PoC will then be discarded and refetched correctly from the PoU.
Patching kernel text executed prior to the MMU being enabled is
prohibited, so the early entry code will always be clean.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
2015-08-05 10:05:20 +01:00

647 lines
18 KiB
ArmAsm

/*
* Low-level CPU initialisation
* Based on arch/arm/kernel/head.S
*
* Copyright (C) 1994-2002 Russell King
* Copyright (C) 2003-2012 ARM Ltd.
* Authors: Catalin Marinas <catalin.marinas@arm.com>
* Will Deacon <will.deacon@arm.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/linkage.h>
#include <linux/init.h>
#include <linux/irqchip/arm-gic-v3.h>
#include <asm/assembler.h>
#include <asm/ptrace.h>
#include <asm/asm-offsets.h>
#include <asm/cache.h>
#include <asm/cputype.h>
#include <asm/memory.h>
#include <asm/thread_info.h>
#include <asm/pgtable-hwdef.h>
#include <asm/pgtable.h>
#include <asm/page.h>
#include <asm/virt.h>
#define __PHYS_OFFSET (KERNEL_START - TEXT_OFFSET)
#if (TEXT_OFFSET & 0xfff) != 0
#error TEXT_OFFSET must be at least 4KB aligned
#elif (PAGE_OFFSET & 0x1fffff) != 0
#error PAGE_OFFSET must be at least 2MB aligned
#elif TEXT_OFFSET > 0x1fffff
#error TEXT_OFFSET must be less than 2MB
#endif
#ifdef CONFIG_ARM64_64K_PAGES
#define BLOCK_SHIFT PAGE_SHIFT
#define BLOCK_SIZE PAGE_SIZE
#define TABLE_SHIFT PMD_SHIFT
#else
#define BLOCK_SHIFT SECTION_SHIFT
#define BLOCK_SIZE SECTION_SIZE
#define TABLE_SHIFT PUD_SHIFT
#endif
#define KERNEL_START _text
#define KERNEL_END _end
/*
* Initial memory map attributes.
*/
#define PTE_FLAGS PTE_TYPE_PAGE | PTE_AF | PTE_SHARED
#define PMD_FLAGS PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S
#ifdef CONFIG_ARM64_64K_PAGES
#define MM_MMUFLAGS PTE_ATTRINDX(MT_NORMAL) | PTE_FLAGS
#else
#define MM_MMUFLAGS PMD_ATTRINDX(MT_NORMAL) | PMD_FLAGS
#endif
/*
* Kernel startup entry point.
* ---------------------------
*
* The requirements are:
* MMU = off, D-cache = off, I-cache = on or off,
* x0 = physical address to the FDT blob.
*
* This code is mostly position independent so you call this at
* __pa(PAGE_OFFSET + TEXT_OFFSET).
*
* Note that the callee-saved registers are used for storing variables
* that are useful before the MMU is enabled. The allocations are described
* in the entry routines.
*/
__HEAD
/*
* DO NOT MODIFY. Image header expected by Linux boot-loaders.
*/
#ifdef CONFIG_EFI
efi_head:
/*
* This add instruction has no meaningful effect except that
* its opcode forms the magic "MZ" signature required by UEFI.
*/
add x13, x18, #0x16
b stext
#else
b stext // branch to kernel start, magic
.long 0 // reserved
#endif
.quad _kernel_offset_le // Image load offset from start of RAM, little-endian
.quad _kernel_size_le // Effective size of kernel image, little-endian
.quad _kernel_flags_le // Informative flags, little-endian
.quad 0 // reserved
.quad 0 // reserved
.quad 0 // reserved
.byte 0x41 // Magic number, "ARM\x64"
.byte 0x52
.byte 0x4d
.byte 0x64
#ifdef CONFIG_EFI
.long pe_header - efi_head // Offset to the PE header.
#else
.word 0 // reserved
#endif
#ifdef CONFIG_EFI
.globl stext_offset
.set stext_offset, stext - efi_head
.align 3
pe_header:
.ascii "PE"
.short 0
coff_header:
.short 0xaa64 // AArch64
.short 2 // nr_sections
.long 0 // TimeDateStamp
.long 0 // PointerToSymbolTable
.long 1 // NumberOfSymbols
.short section_table - optional_header // SizeOfOptionalHeader
.short 0x206 // Characteristics.
// IMAGE_FILE_DEBUG_STRIPPED |
// IMAGE_FILE_EXECUTABLE_IMAGE |
// IMAGE_FILE_LINE_NUMS_STRIPPED
optional_header:
.short 0x20b // PE32+ format
.byte 0x02 // MajorLinkerVersion
.byte 0x14 // MinorLinkerVersion
.long _end - stext // SizeOfCode
.long 0 // SizeOfInitializedData
.long 0 // SizeOfUninitializedData
.long efi_stub_entry - efi_head // AddressOfEntryPoint
.long stext_offset // BaseOfCode
extra_header_fields:
.quad 0 // ImageBase
.long 0x1000 // SectionAlignment
.long PECOFF_FILE_ALIGNMENT // FileAlignment
.short 0 // MajorOperatingSystemVersion
.short 0 // MinorOperatingSystemVersion
.short 0 // MajorImageVersion
.short 0 // MinorImageVersion
.short 0 // MajorSubsystemVersion
.short 0 // MinorSubsystemVersion
.long 0 // Win32VersionValue
.long _end - efi_head // SizeOfImage
// Everything before the kernel image is considered part of the header
.long stext_offset // SizeOfHeaders
.long 0 // CheckSum
.short 0xa // Subsystem (EFI application)
.short 0 // DllCharacteristics
.quad 0 // SizeOfStackReserve
.quad 0 // SizeOfStackCommit
.quad 0 // SizeOfHeapReserve
.quad 0 // SizeOfHeapCommit
.long 0 // LoaderFlags
.long 0x6 // NumberOfRvaAndSizes
.quad 0 // ExportTable
.quad 0 // ImportTable
.quad 0 // ResourceTable
.quad 0 // ExceptionTable
.quad 0 // CertificationTable
.quad 0 // BaseRelocationTable
// Section table
section_table:
/*
* The EFI application loader requires a relocation section
* because EFI applications must be relocatable. This is a
* dummy section as far as we are concerned.
*/
.ascii ".reloc"
.byte 0
.byte 0 // end of 0 padding of section name
.long 0
.long 0
.long 0 // SizeOfRawData
.long 0 // PointerToRawData
.long 0 // PointerToRelocations
.long 0 // PointerToLineNumbers
.short 0 // NumberOfRelocations
.short 0 // NumberOfLineNumbers
.long 0x42100040 // Characteristics (section flags)
.ascii ".text"
.byte 0
.byte 0
.byte 0 // end of 0 padding of section name
.long _end - stext // VirtualSize
.long stext_offset // VirtualAddress
.long _edata - stext // SizeOfRawData
.long stext_offset // PointerToRawData
.long 0 // PointerToRelocations (0 for executables)
.long 0 // PointerToLineNumbers (0 for executables)
.short 0 // NumberOfRelocations (0 for executables)
.short 0 // NumberOfLineNumbers (0 for executables)
.long 0xe0500020 // Characteristics (section flags)
/*
* EFI will load stext onwards at the 4k section alignment
* described in the PE/COFF header. To ensure that instruction
* sequences using an adrp and a :lo12: immediate will function
* correctly at this alignment, we must ensure that stext is
* placed at a 4k boundary in the Image to begin with.
*/
.align 12
#endif
ENTRY(stext)
bl preserve_boot_args
bl el2_setup // Drop to EL1, w20=cpu_boot_mode
adrp x24, __PHYS_OFFSET
bl set_cpu_boot_mode_flag
bl __create_page_tables // x25=TTBR0, x26=TTBR1
/*
* The following calls CPU setup code, see arch/arm64/mm/proc.S for
* details.
* On return, the CPU will be ready for the MMU to be turned on and
* the TCR will have been set.
*/
ldr x27, =__mmap_switched // address to jump to after
// MMU has been enabled
adr_l lr, __enable_mmu // return (PIC) address
b __cpu_setup // initialise processor
ENDPROC(stext)
/*
* Preserve the arguments passed by the bootloader in x0 .. x3
*/
preserve_boot_args:
mov x21, x0 // x21=FDT
adr_l x0, boot_args // record the contents of
stp x21, x1, [x0] // x0 .. x3 at kernel entry
stp x2, x3, [x0, #16]
dmb sy // needed before dc ivac with
// MMU off
add x1, x0, #0x20 // 4 x 8 bytes
b __inval_cache_range // tail call
ENDPROC(preserve_boot_args)
/*
* Macro to create a table entry to the next page.
*
* tbl: page table address
* virt: virtual address
* shift: #imm page table shift
* ptrs: #imm pointers per table page
*
* Preserves: virt
* Corrupts: tmp1, tmp2
* Returns: tbl -> next level table page address
*/
.macro create_table_entry, tbl, virt, shift, ptrs, tmp1, tmp2
lsr \tmp1, \virt, #\shift
and \tmp1, \tmp1, #\ptrs - 1 // table index
add \tmp2, \tbl, #PAGE_SIZE
orr \tmp2, \tmp2, #PMD_TYPE_TABLE // address of next table and entry type
str \tmp2, [\tbl, \tmp1, lsl #3]
add \tbl, \tbl, #PAGE_SIZE // next level table page
.endm
/*
* Macro to populate the PGD (and possibily PUD) for the corresponding
* block entry in the next level (tbl) for the given virtual address.
*
* Preserves: tbl, next, virt
* Corrupts: tmp1, tmp2
*/
.macro create_pgd_entry, tbl, virt, tmp1, tmp2
create_table_entry \tbl, \virt, PGDIR_SHIFT, PTRS_PER_PGD, \tmp1, \tmp2
#if SWAPPER_PGTABLE_LEVELS == 3
create_table_entry \tbl, \virt, TABLE_SHIFT, PTRS_PER_PTE, \tmp1, \tmp2
#endif
.endm
/*
* Macro to populate block entries in the page table for the start..end
* virtual range (inclusive).
*
* Preserves: tbl, flags
* Corrupts: phys, start, end, pstate
*/
.macro create_block_map, tbl, flags, phys, start, end
lsr \phys, \phys, #BLOCK_SHIFT
lsr \start, \start, #BLOCK_SHIFT
and \start, \start, #PTRS_PER_PTE - 1 // table index
orr \phys, \flags, \phys, lsl #BLOCK_SHIFT // table entry
lsr \end, \end, #BLOCK_SHIFT
and \end, \end, #PTRS_PER_PTE - 1 // table end index
9999: str \phys, [\tbl, \start, lsl #3] // store the entry
add \start, \start, #1 // next entry
add \phys, \phys, #BLOCK_SIZE // next block
cmp \start, \end
b.ls 9999b
.endm
/*
* Setup the initial page tables. We only setup the barest amount which is
* required to get the kernel running. The following sections are required:
* - identity mapping to enable the MMU (low address, TTBR0)
* - first few MB of the kernel linear mapping to jump to once the MMU has
* been enabled
*/
__create_page_tables:
adrp x25, idmap_pg_dir
adrp x26, swapper_pg_dir
mov x27, lr
/*
* Invalidate the idmap and swapper page tables to avoid potential
* dirty cache lines being evicted.
*/
mov x0, x25
add x1, x26, #SWAPPER_DIR_SIZE
bl __inval_cache_range
/*
* Clear the idmap and swapper page tables.
*/
mov x0, x25
add x6, x26, #SWAPPER_DIR_SIZE
1: stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
cmp x0, x6
b.lo 1b
ldr x7, =MM_MMUFLAGS
/*
* Create the identity mapping.
*/
mov x0, x25 // idmap_pg_dir
adrp x3, __idmap_text_start // __pa(__idmap_text_start)
#ifndef CONFIG_ARM64_VA_BITS_48
#define EXTRA_SHIFT (PGDIR_SHIFT + PAGE_SHIFT - 3)
#define EXTRA_PTRS (1 << (48 - EXTRA_SHIFT))
/*
* If VA_BITS < 48, it may be too small to allow for an ID mapping to be
* created that covers system RAM if that is located sufficiently high
* in the physical address space. So for the ID map, use an extended
* virtual range in that case, by configuring an additional translation
* level.
* First, we have to verify our assumption that the current value of
* VA_BITS was chosen such that all translation levels are fully
* utilised, and that lowering T0SZ will always result in an additional
* translation level to be configured.
*/
#if VA_BITS != EXTRA_SHIFT
#error "Mismatch between VA_BITS and page size/number of translation levels"
#endif
/*
* Calculate the maximum allowed value for TCR_EL1.T0SZ so that the
* entire ID map region can be mapped. As T0SZ == (64 - #bits used),
* this number conveniently equals the number of leading zeroes in
* the physical address of __idmap_text_end.
*/
adrp x5, __idmap_text_end
clz x5, x5
cmp x5, TCR_T0SZ(VA_BITS) // default T0SZ small enough?
b.ge 1f // .. then skip additional level
adr_l x6, idmap_t0sz
str x5, [x6]
dmb sy
dc ivac, x6 // Invalidate potentially stale cache line
create_table_entry x0, x3, EXTRA_SHIFT, EXTRA_PTRS, x5, x6
1:
#endif
create_pgd_entry x0, x3, x5, x6
mov x5, x3 // __pa(__idmap_text_start)
adr_l x6, __idmap_text_end // __pa(__idmap_text_end)
create_block_map x0, x7, x3, x5, x6
/*
* Map the kernel image (starting with PHYS_OFFSET).
*/
mov x0, x26 // swapper_pg_dir
mov x5, #PAGE_OFFSET
create_pgd_entry x0, x5, x3, x6
ldr x6, =KERNEL_END // __va(KERNEL_END)
mov x3, x24 // phys offset
create_block_map x0, x7, x3, x5, x6
/*
* Since the page tables have been populated with non-cacheable
* accesses (MMU disabled), invalidate the idmap and swapper page
* tables again to remove any speculatively loaded cache lines.
*/
mov x0, x25
add x1, x26, #SWAPPER_DIR_SIZE
dmb sy
bl __inval_cache_range
mov lr, x27
ret
ENDPROC(__create_page_tables)
.ltorg
/*
* The following fragment of code is executed with the MMU enabled.
*/
.set initial_sp, init_thread_union + THREAD_START_SP
__mmap_switched:
adr_l x6, __bss_start
adr_l x7, __bss_stop
1: cmp x6, x7
b.hs 2f
str xzr, [x6], #8 // Clear BSS
b 1b
2:
adr_l sp, initial_sp, x4
str_l x21, __fdt_pointer, x5 // Save FDT pointer
str_l x24, memstart_addr, x6 // Save PHYS_OFFSET
mov x29, #0
b start_kernel
ENDPROC(__mmap_switched)
/*
* end early head section, begin head code that is also used for
* hotplug and needs to have the same protections as the text region
*/
.section ".text","ax"
/*
* If we're fortunate enough to boot at EL2, ensure that the world is
* sane before dropping to EL1.
*
* Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in x20 if
* booted in EL1 or EL2 respectively.
*/
ENTRY(el2_setup)
mrs x0, CurrentEL
cmp x0, #CurrentEL_EL2
b.ne 1f
mrs x0, sctlr_el2
CPU_BE( orr x0, x0, #(1 << 25) ) // Set the EE bit for EL2
CPU_LE( bic x0, x0, #(1 << 25) ) // Clear the EE bit for EL2
msr sctlr_el2, x0
b 2f
1: mrs x0, sctlr_el1
CPU_BE( orr x0, x0, #(3 << 24) ) // Set the EE and E0E bits for EL1
CPU_LE( bic x0, x0, #(3 << 24) ) // Clear the EE and E0E bits for EL1
msr sctlr_el1, x0
mov w20, #BOOT_CPU_MODE_EL1 // This cpu booted in EL1
isb
ret
/* Hyp configuration. */
2: mov x0, #(1 << 31) // 64-bit EL1
msr hcr_el2, x0
/* Generic timers. */
mrs x0, cnthctl_el2
orr x0, x0, #3 // Enable EL1 physical timers
msr cnthctl_el2, x0
msr cntvoff_el2, xzr // Clear virtual offset
#ifdef CONFIG_ARM_GIC_V3
/* GICv3 system register access */
mrs x0, id_aa64pfr0_el1
ubfx x0, x0, #24, #4
cmp x0, #1
b.ne 3f
mrs_s x0, ICC_SRE_EL2
orr x0, x0, #ICC_SRE_EL2_SRE // Set ICC_SRE_EL2.SRE==1
orr x0, x0, #ICC_SRE_EL2_ENABLE // Set ICC_SRE_EL2.Enable==1
msr_s ICC_SRE_EL2, x0
isb // Make sure SRE is now set
msr_s ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults
3:
#endif
/* Populate ID registers. */
mrs x0, midr_el1
mrs x1, mpidr_el1
msr vpidr_el2, x0
msr vmpidr_el2, x1
/* sctlr_el1 */
mov x0, #0x0800 // Set/clear RES{1,0} bits
CPU_BE( movk x0, #0x33d0, lsl #16 ) // Set EE and E0E on BE systems
CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems
msr sctlr_el1, x0
/* Coprocessor traps. */
mov x0, #0x33ff
msr cptr_el2, x0 // Disable copro. traps to EL2
#ifdef CONFIG_COMPAT
msr hstr_el2, xzr // Disable CP15 traps to EL2
#endif
/* Stage-2 translation */
msr vttbr_el2, xzr
/* Hypervisor stub */
adrp x0, __hyp_stub_vectors
add x0, x0, #:lo12:__hyp_stub_vectors
msr vbar_el2, x0
/* spsr */
mov x0, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
PSR_MODE_EL1h)
msr spsr_el2, x0
msr elr_el2, lr
mov w20, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2
eret
ENDPROC(el2_setup)
/*
* Sets the __boot_cpu_mode flag depending on the CPU boot mode passed
* in x20. See arch/arm64/include/asm/virt.h for more info.
*/
ENTRY(set_cpu_boot_mode_flag)
adr_l x1, __boot_cpu_mode
cmp w20, #BOOT_CPU_MODE_EL2
b.ne 1f
add x1, x1, #4
1: str w20, [x1] // This CPU has booted in EL1
dmb sy
dc ivac, x1 // Invalidate potentially stale cache line
ret
ENDPROC(set_cpu_boot_mode_flag)
/*
* We need to find out the CPU boot mode long after boot, so we need to
* store it in a writable variable.
*
* This is not in .bss, because we set it sufficiently early that the boot-time
* zeroing of .bss would clobber it.
*/
.pushsection .data..cacheline_aligned
.align L1_CACHE_SHIFT
ENTRY(__boot_cpu_mode)
.long BOOT_CPU_MODE_EL2
.long BOOT_CPU_MODE_EL1
.popsection
/*
* This provides a "holding pen" for platforms to hold all secondary
* cores are held until we're ready for them to initialise.
*/
ENTRY(secondary_holding_pen)
bl el2_setup // Drop to EL1, w20=cpu_boot_mode
bl set_cpu_boot_mode_flag
mrs x0, mpidr_el1
ldr x1, =MPIDR_HWID_BITMASK
and x0, x0, x1
adr_l x3, secondary_holding_pen_release
pen: ldr x4, [x3]
cmp x4, x0
b.eq secondary_startup
wfe
b pen
ENDPROC(secondary_holding_pen)
/*
* Secondary entry point that jumps straight into the kernel. Only to
* be used where CPUs are brought online dynamically by the kernel.
*/
ENTRY(secondary_entry)
bl el2_setup // Drop to EL1
bl set_cpu_boot_mode_flag
b secondary_startup
ENDPROC(secondary_entry)
ENTRY(secondary_startup)
/*
* Common entry point for secondary CPUs.
*/
adrp x25, idmap_pg_dir
adrp x26, swapper_pg_dir
bl __cpu_setup // initialise processor
ldr x21, =secondary_data
ldr x27, =__secondary_switched // address to jump to after enabling the MMU
b __enable_mmu
ENDPROC(secondary_startup)
ENTRY(__secondary_switched)
ldr x0, [x21] // get secondary_data.stack
mov sp, x0
mov x29, #0
b secondary_start_kernel
ENDPROC(__secondary_switched)
/*
* Enable the MMU.
*
* x0 = SCTLR_EL1 value for turning on the MMU.
* x27 = *virtual* address to jump to upon completion
*
* other registers depend on the function called upon completion
*/
.section ".idmap.text", "ax"
__enable_mmu:
ldr x5, =vectors
msr vbar_el1, x5
msr ttbr0_el1, x25 // load TTBR0
msr ttbr1_el1, x26 // load TTBR1
isb
msr sctlr_el1, x0
isb
/*
* Invalidate the local I-cache so that any instructions fetched
* speculatively from the PoC are discarded, since they may have
* been dynamically patched at the PoU.
*/
ic iallu
dsb nsh
isb
br x27
ENDPROC(__enable_mmu)