head.S 21.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24
/*
 * 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>
25
#include <linux/irqchip/arm-gic-v3.h>
26 27 28 29

#include <asm/assembler.h>
#include <asm/ptrace.h>
#include <asm/asm-offsets.h>
30
#include <asm/cache.h>
31
#include <asm/cputype.h>
32
#include <asm/elf.h>
33
#include <asm/kernel-pgtable.h>
34
#include <asm/kvm_arm.h>
35 36 37 38
#include <asm/memory.h>
#include <asm/pgtable-hwdef.h>
#include <asm/pgtable.h>
#include <asm/page.h>
39
#include <asm/smp.h>
40 41
#include <asm/sysreg.h>
#include <asm/thread_info.h>
42
#include <asm/virt.h>
43

44
#define __PHYS_OFFSET	(KERNEL_START - TEXT_OFFSET)
45

46 47 48
#if (TEXT_OFFSET & 0xfff) != 0
#error TEXT_OFFSET must be at least 4KB aligned
#elif (PAGE_OFFSET & 0x1fffff) != 0
M
Mark Rutland 已提交
49
#error PAGE_OFFSET must be at least 2MB aligned
50
#elif TEXT_OFFSET > 0x1fffff
M
Mark Rutland 已提交
51
#error TEXT_OFFSET must be less than 2MB
52 53
#endif

54
#define KERNEL_START	_text
55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72
#define KERNEL_END	_end

/*
 * 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
73
_head:
74 75 76
	/*
	 * DO NOT MODIFY. Image header expected by Linux boot-loaders.
	 */
M
Mark Salter 已提交
77 78 79 80 81 82 83 84
#ifdef CONFIG_EFI
	/*
	 * 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
85 86
	b	stext				// branch to kernel start, magic
	.long	0				// reserved
M
Mark Salter 已提交
87
#endif
88 89 90
	le64sym	_kernel_offset_le		// Image load offset from start of RAM, little-endian
	le64sym	_kernel_size_le			// Effective size of kernel image, little-endian
	le64sym	_kernel_flags_le		// Informative flags, little-endian
R
Roy Franz 已提交
91 92 93 94 95 96 97
	.quad	0				// reserved
	.quad	0				// reserved
	.quad	0				// reserved
	.byte	0x41				// Magic number, "ARM\x64"
	.byte	0x52
	.byte	0x4d
	.byte	0x64
M
Mark Salter 已提交
98
#ifdef CONFIG_EFI
99
	.long	pe_header - _head		// Offset to the PE header.
M
Mark Salter 已提交
100
#else
R
Roy Franz 已提交
101
	.word	0				// reserved
M
Mark Salter 已提交
102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123
#endif

#ifdef CONFIG_EFI
	.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
124
	.long	_end - efi_header_end		// SizeOfCode
M
Mark Salter 已提交
125 126
	.long	0				// SizeOfInitializedData
	.long	0				// SizeOfUninitializedData
127
	.long	__efistub_entry - _head		// AddressOfEntryPoint
128
	.long	efi_header_end - _head		// BaseOfCode
M
Mark Salter 已提交
129 130 131

extra_header_fields:
	.quad	0				// ImageBase
132
	.long	0x1000				// SectionAlignment
133
	.long	PECOFF_FILE_ALIGNMENT		// FileAlignment
M
Mark Salter 已提交
134 135 136 137 138 139 140 141
	.short	0				// MajorOperatingSystemVersion
	.short	0				// MinorOperatingSystemVersion
	.short	0				// MajorImageVersion
	.short	0				// MinorImageVersion
	.short	0				// MajorSubsystemVersion
	.short	0				// MinorSubsystemVersion
	.long	0				// Win32VersionValue

142
	.long	_end - _head			// SizeOfImage
M
Mark Salter 已提交
143 144

	// Everything before the kernel image is considered part of the header
145
	.long	efi_header_end - _head		// SizeOfHeaders
M
Mark Salter 已提交
146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188
	.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
189 190 191 192
	.long	_end - efi_header_end	// VirtualSize
	.long	efi_header_end - _head	// VirtualAddress
	.long	_edata - efi_header_end	// SizeOfRawData
	.long	efi_header_end - _head	// PointerToRawData
M
Mark Salter 已提交
193 194 195 196 197 198

	.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)
199 200

	/*
201
	 * EFI will load .text onwards at the 4k section alignment
202 203
	 * described in the PE/COFF header. To ensure that instruction
	 * sequences using an adrp and a :lo12: immediate will function
204
	 * correctly at this alignment, we must ensure that .text is
205 206 207
	 * placed at a 4k boundary in the Image to begin with.
	 */
	.align 12
208
efi_header_end:
M
Mark Salter 已提交
209
#endif
210

211 212
	__INIT

213
ENTRY(stext)
214
	bl	preserve_boot_args
215
	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
216
	mov	x23, xzr			// KASLR offset, defaults to 0
217
	adrp	x24, __PHYS_OFFSET
218
	bl	set_cpu_boot_mode_flag
219 220
	bl	__create_page_tables		// x25=TTBR0, x26=TTBR1
	/*
221 222
	 * The following calls CPU setup code, see arch/arm64/mm/proc.S for
	 * details.
223 224 225
	 * On return, the CPU will be ready for the MMU to be turned on and
	 * the TCR will have been set.
	 */
226
	ldr	x27, 0f				// address to jump to after
227
	neg	x27, x27			// MMU has been enabled
228
	adr_l	lr, __enable_mmu		// return (PIC) address
229
	b	__cpu_setup			// initialise processor
230
ENDPROC(stext)
231
	.align	3
232
0:	.quad	(_text - TEXT_OFFSET) - __mmap_switched - KIMAGE_VADDR
233

234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250
/*
 * 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)

251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280
/*
 * 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
281 282 283 284
#if SWAPPER_PGTABLE_LEVELS > 3
	create_table_entry \tbl, \virt, PUD_SHIFT, PTRS_PER_PUD, \tmp1, \tmp2
#endif
#if SWAPPER_PGTABLE_LEVELS > 2
285
	create_table_entry \tbl, \virt, SWAPPER_TABLE_SHIFT, PTRS_PER_PTE, \tmp1, \tmp2
286 287 288 289 290 291 292 293 294 295 296
#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
297 298
	lsr	\phys, \phys, #SWAPPER_BLOCK_SHIFT
	lsr	\start, \start, #SWAPPER_BLOCK_SHIFT
299
	and	\start, \start, #PTRS_PER_PTE - 1	// table index
300 301
	orr	\phys, \flags, \phys, lsl #SWAPPER_BLOCK_SHIFT	// table entry
	lsr	\end, \end, #SWAPPER_BLOCK_SHIFT
302 303 304
	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
305
	add	\phys, \phys, #SWAPPER_BLOCK_SIZE		// next block
306 307 308 309 310 311 312 313 314
	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
315
 *     been enabled
316 317
 */
__create_page_tables:
318 319
	adrp	x25, idmap_pg_dir
	adrp	x26, swapper_pg_dir
320
	mov	x28, lr
321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341

	/*
	 * 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

342
	ldr	x7, =SWAPPER_MM_MMUFLAGS
343 344 345 346 347

	/*
	 * Create the identity mapping.
	 */
	mov	x0, x25				// idmap_pg_dir
348
	adrp	x3, __idmap_text_start		// __pa(__idmap_text_start)
349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370

#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
371
	 * entire ID map region can be mapped. As T0SZ == (64 - #bits used),
372
	 * this number conveniently equals the number of leading zeroes in
373
	 * the physical address of __idmap_text_end.
374
	 */
375
	adrp	x5, __idmap_text_end
376 377 378 379
	clz	x5, x5
	cmp	x5, TCR_T0SZ(VA_BITS)	// default T0SZ small enough?
	b.ge	1f			// .. then skip additional level

380 381 382 383
	adr_l	x6, idmap_t0sz
	str	x5, [x6]
	dmb	sy
	dc	ivac, x6		// Invalidate potentially stale cache line
384 385 386 387 388

	create_table_entry x0, x3, EXTRA_SHIFT, EXTRA_PTRS, x5, x6
1:
#endif

389
	create_pgd_entry x0, x3, x5, x6
390 391
	mov	x5, x3				// __pa(__idmap_text_start)
	adr_l	x6, __idmap_text_end		// __pa(__idmap_text_end)
392 393 394 395 396 397
	create_block_map x0, x7, x3, x5, x6

	/*
	 * Map the kernel image (starting with PHYS_OFFSET).
	 */
	mov	x0, x26				// swapper_pg_dir
398
	ldr	x5, =KIMAGE_VADDR
399
	add	x5, x5, x23			// add KASLR displacement
400
	create_pgd_entry x0, x5, x3, x6
401
	ldr	w6, =kernel_img_size
402
	add	x6, x6, x5
403 404 405 406 407 408 409 410 411 412
	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
413
	dmb	sy
414 415
	bl	__inval_cache_range

416
	ret	x28
417 418 419 420
ENDPROC(__create_page_tables)
	.ltorg

/*
421
 * The following fragment of code is executed with the MMU enabled.
422
 */
423
	.set	initial_sp, init_thread_union + THREAD_START_SP
424
__mmap_switched:
425
	mov	x28, lr				// preserve LR
426 427 428 429
	adr_l	x8, vectors			// load VBAR_EL1 with virtual
	msr	vbar_el1, x8			// vector table address
	isb

430 431 432 433 434 435
	// Clear BSS
	adr_l	x0, __bss_start
	mov	x1, xzr
	adr_l	x2, __bss_stop
	sub	x2, x2, x0
	bl	__pi_memset
436
	dsb	ishst				// Make zero page visible to PTW
437

438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453
#ifdef CONFIG_RELOCATABLE

	/*
	 * Iterate over each entry in the relocation table, and apply the
	 * relocations in place.
	 */
	adr_l	x8, __dynsym_start		// start of symbol table
	adr_l	x9, __reloc_start		// start of reloc table
	adr_l	x10, __reloc_end		// end of reloc table

0:	cmp	x9, x10
	b.hs	2f
	ldp	x11, x12, [x9], #24
	ldr	x13, [x9, #-8]
	cmp	w12, #R_AARCH64_RELATIVE
	b.ne	1f
454 455
	add	x13, x13, x23			// relocate
	str	x13, [x11, x23]
456 457 458 459 460 461
	b	0b

1:	cmp	w12, #R_AARCH64_ABS64
	b.ne	0b
	add	x12, x12, x12, lsl #1		// symtab offset: 24x top word
	add	x12, x8, x12, lsr #(32 - 3)	// ... shifted into bottom word
462
	ldrsh	w14, [x12, #6]			// Elf64_Sym::st_shndx
463
	ldr	x15, [x12, #8]			// Elf64_Sym::st_value
464 465 466
	cmp	w14, #-0xf			// SHN_ABS (0xfff1) ?
	add	x14, x15, x23			// relocate
	csel	x15, x14, x15, ne
467
	add	x15, x13, x15
468
	str	x15, [x11, x23]
469 470
	b	0b

471 472 473
2:	adr_l	x8, kimage_vaddr		// make relocated kimage_vaddr
	dc	cvac, x8			// value visible to secondaries
	dsb	sy				// with MMU off
474
#endif
475

476
	adr_l	sp, initial_sp, x4
477 478 479
	mov	x4, sp
	and	x4, x4, #~(THREAD_SIZE - 1)
	msr	sp_el0, x4			// Save thread_info
480
	str_l	x21, __fdt_pointer, x5		// Save FDT pointer
481

482
	ldr_l	x4, kimage_vaddr		// Save the offset between
483 484 485
	sub	x4, x4, x24			// the kernel virtual and
	str_l	x4, kimage_voffset, x5		// physical mappings

486
	mov	x29, #0
A
Andrey Ryabinin 已提交
487 488
#ifdef CONFIG_KASAN
	bl	kasan_early_init
489 490 491 492 493 494 495 496 497 498
#endif
#ifdef CONFIG_RANDOMIZE_BASE
	cbnz	x23, 0f				// already running randomized?
	mov	x0, x21				// pass FDT address in x0
	bl	kaslr_early_init		// parse FDT for KASLR options
	cbz	x0, 0f				// KASLR disabled? just proceed
	mov	x23, x0				// record KASLR offset
	ret	x28				// we must enable KASLR, return
						// to __enable_mmu()
0:
A
Andrey Ryabinin 已提交
499
#endif
500 501 502 503 504 505 506 507
	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"
508 509 510 511

ENTRY(kimage_vaddr)
	.quad		_text - TEXT_OFFSET

512 513 514
/*
 * If we're fortunate enough to boot at EL2, ensure that the world is
 * sane before dropping to EL1.
515 516 517
 *
 * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in x20 if
 * booted in EL1 or EL2 respectively.
518 519 520
 */
ENTRY(el2_setup)
	mrs	x0, CurrentEL
521
	cmp	x0, #CurrentEL_EL2
522 523 524 525 526 527 528 529 530 531
	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
532
	mov	w20, #BOOT_CPU_MODE_EL1		// This cpu booted in EL1
533
	isb
534 535
	ret

536 537 538 539 540 541 542 543 544 545 546 547 548
2:
#ifdef CONFIG_ARM64_VHE
	/*
	 * Check for VHE being present. For the rest of the EL2 setup,
	 * x2 being non-zero indicates that we do have VHE, and that the
	 * kernel is intended to run at EL2.
	 */
	mrs	x2, id_aa64mmfr1_el1
	ubfx	x2, x2, #8, #4
#else
	mov	x2, xzr
#endif

549
	/* Hyp configuration. */
550 551 552 553 554
	mov	x0, #HCR_RW			// 64-bit EL1
	cbz	x2, set_hcr
	orr	x0, x0, #HCR_TGE		// Enable Host Extensions
	orr	x0, x0, #HCR_E2H
set_hcr:
555
	msr	hcr_el2, x0
556
	isb
557 558 559 560 561

	/* Generic timers. */
	mrs	x0, cnthctl_el2
	orr	x0, x0, #3			// Enable EL1 physical timers
	msr	cnthctl_el2, x0
562
	msr	cntvoff_el2, xzr		// Clear virtual offset
563

564 565 566 567 568 569 570
#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

571
	mrs_s	x0, ICC_SRE_EL2
572 573
	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
574
	msr_s	ICC_SRE_EL2, x0
575
	isb					// Make sure SRE is now set
576 577
	mrs_s	x0, ICC_SRE_EL2			// Read SRE back,
	tbz	x0, #0, 3f			// and check that it sticks
578
	msr_s	ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
579 580 581 582

3:
#endif

583 584 585 586 587 588 589 590
	/* 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
591 592
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
593 594 595 596 597 598 599 600 601 602
	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

603
	/* EL2 debug */
604 605 606 607
	mrs	x0, id_aa64dfr0_el1		// Check ID_AA64DFR0_EL1 PMUVer
	sbfx	x0, x0, #8, #4
	cmp	x0, #1
	b.lt	4f				// Skip if no PMU present
608 609 610
	mrs	x0, pmcr_el0			// Disable debug access traps
	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
	msr	mdcr_el2, x0			// all PMU counters from EL1
611
4:
612

613 614 615
	/* Stage-2 translation */
	msr	vttbr_el2, xzr

616 617 618 619 620 621 622
	cbz	x2, install_el2_stub

	mov	w20, #BOOT_CPU_MODE_EL2		// This CPU booted in EL2
	isb
	ret

install_el2_stub:
M
Marc Zyngier 已提交
623
	/* Hypervisor stub */
624 625
	adrp	x0, __hyp_stub_vectors
	add	x0, x0, #:lo12:__hyp_stub_vectors
M
Marc Zyngier 已提交
626 627
	msr	vbar_el2, x0

628 629 630 631 632
	/* 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
633
	mov	w20, #BOOT_CPU_MODE_EL2		// This CPU booted in EL2
634 635 636
	eret
ENDPROC(el2_setup)

637 638 639 640 641
/*
 * 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)
642
	adr_l	x1, __boot_cpu_mode
643 644 645
	cmp	w20, #BOOT_CPU_MODE_EL2
	b.ne	1f
	add	x1, x1, #4
646 647 648
1:	str	w20, [x1]			// This CPU has booted in EL1
	dmb	sy
	dc	ivac, x1			// Invalidate potentially stale cache line
649 650 651
	ret
ENDPROC(set_cpu_boot_mode_flag)

652 653 654 655 656 657 658
/*
 * 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.
 */
659 660
	.pushsection	.data..cacheline_aligned
	.align	L1_CACHE_SHIFT
661
ENTRY(__boot_cpu_mode)
662
	.long	BOOT_CPU_MODE_EL2
663
	.long	BOOT_CPU_MODE_EL1
664 665
	.popsection

666 667 668 669 670
	/*
	 * 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)
671 672
	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
	bl	set_cpu_boot_mode_flag
673
	mrs	x0, mpidr_el1
674 675
	ldr     x1, =MPIDR_HWID_BITMASK
	and	x0, x0, x1
676
	adr_l	x3, secondary_holding_pen_release
677 678 679 680 681 682
pen:	ldr	x4, [x3]
	cmp	x4, x0
	b.eq	secondary_startup
	wfe
	b	pen
ENDPROC(secondary_holding_pen)
683 684 685 686 687 688 689

	/*
	 * 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
690
	bl	set_cpu_boot_mode_flag
691 692
	b	secondary_startup
ENDPROC(secondary_entry)
693 694 695 696 697

ENTRY(secondary_startup)
	/*
	 * Common entry point for secondary CPUs.
	 */
698 699
	adrp	x25, idmap_pg_dir
	adrp	x26, swapper_pg_dir
700
	bl	__cpu_setup			// initialise processor
701

702
	ldr	x8, kimage_vaddr
703 704
	ldr	w9, 0f
	sub	x27, x8, w9, sxtw		// address to jump to after enabling the MMU
705 706
	b	__enable_mmu
ENDPROC(secondary_startup)
707
0:	.long	(_text - TEXT_OFFSET) - __secondary_switched
708 709

ENTRY(__secondary_switched)
710 711 712 713
	adr_l	x5, vectors
	msr	vbar_el1, x5
	isb

714 715
	adr_l	x0, secondary_data
	ldr	x0, [x0, #CPU_BOOT_STACK]	// get secondary_data.stack
716
	mov	sp, x0
717 718
	and	x0, x0, #~(THREAD_SIZE - 1)
	msr	sp_el0, x0			// save thread_info
719 720 721 722
	mov	x29, #0
	b	secondary_start_kernel
ENDPROC(__secondary_switched)

723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745
/*
 * The booting CPU updates the failed status @__early_cpu_boot_status,
 * with MMU turned off.
 *
 * update_early_cpu_boot_status tmp, status
 *  - Corrupts tmp1, tmp2
 *  - Writes 'status' to __early_cpu_boot_status and makes sure
 *    it is committed to memory.
 */

	.macro	update_early_cpu_boot_status status, tmp1, tmp2
	mov	\tmp2, #\status
	str_l	\tmp2, __early_cpu_boot_status, \tmp1
	dmb	sy
	dc	ivac, \tmp1			// Invalidate potentially stale cache line
	.endm

	.pushsection	.data..cacheline_aligned
	.align	L1_CACHE_SHIFT
ENTRY(__early_cpu_boot_status)
	.long 	0
	.popsection

746
/*
747
 * Enable the MMU.
748
 *
749 750 751
 *  x0  = SCTLR_EL1 value for turning on the MMU.
 *  x27 = *virtual* address to jump to upon completion
 *
752 753 754 755
 * Other registers depend on the function called upon completion.
 *
 * Checks if the selected granule size is supported by the CPU.
 * If it isn't, park the CPU
756
 */
757
	.section	".idmap.text", "ax"
758
__enable_mmu:
759
	mrs	x22, sctlr_el1			// preserve old SCTLR_EL1 value
760 761 762 763
	mrs	x1, ID_AA64MMFR0_EL1
	ubfx	x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
	cmp	x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
	b.ne	__no_granule_support
764
	update_early_cpu_boot_status 0, x1, x2
765 766 767 768 769
	msr	ttbr0_el1, x25			// load TTBR0
	msr	ttbr1_el1, x26			// load TTBR1
	isb
	msr	sctlr_el1, x0
	isb
770 771 772 773 774 775 776 777
	/*
	 * 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
778 779 780 781 782 783 784 785 786
#ifdef CONFIG_RANDOMIZE_BASE
	mov	x19, x0				// preserve new SCTLR_EL1 value
	blr	x27

	/*
	 * If we return here, we have a KASLR displacement in x23 which we need
	 * to take into account by discarding the current kernel mapping and
	 * creating a new one.
	 */
787
	msr	sctlr_el1, x22			// disable the MMU
788 789 790 791 792
	isb
	bl	__create_page_tables		// recreate kernel mapping

	msr	sctlr_el1, x19			// re-enable the MMU
	isb
793 794 795
	ic	iallu				// flush instructions fetched
	dsb	nsh				// via old mapping
	isb
796 797
	add	x27, x27, x23			// relocated __mmap_switched
#endif
798
	br	x27
799
ENDPROC(__enable_mmu)
800 801

__no_granule_support:
802 803 804
	/* Indicate that this CPU can't boot and is stuck in the kernel */
	update_early_cpu_boot_status CPU_STUCK_IN_KERNEL, x1, x2
1:
805
	wfe
806 807
	wfi
	b 1b
808
ENDPROC(__no_granule_support)