head.S 18.2 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 33 34 35 36
#include <asm/memory.h>
#include <asm/thread_info.h>
#include <asm/pgtable-hwdef.h>
#include <asm/pgtable.h>
#include <asm/page.h>
37
#include <asm/virt.h>
38

39
#define __PHYS_OFFSET	(KERNEL_START - TEXT_OFFSET)
40

41 42 43
#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
44
#error PAGE_OFFSET must be at least 2MB aligned
45
#elif TEXT_OFFSET > 0x1fffff
M
Mark Rutland 已提交
46
#error TEXT_OFFSET must be less than 2MB
47 48 49 50 51
#endif

#ifdef CONFIG_ARM64_64K_PAGES
#define BLOCK_SHIFT	PAGE_SHIFT
#define BLOCK_SIZE	PAGE_SIZE
52
#define TABLE_SHIFT	PMD_SHIFT
53 54 55
#else
#define BLOCK_SHIFT	SECTION_SHIFT
#define BLOCK_SIZE	SECTION_SIZE
56
#define TABLE_SHIFT	PUD_SHIFT
57 58
#endif

59
#define KERNEL_START	_text
60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98
#define KERNEL_END	_end

/*
 * Initial memory map attributes.
 */
#ifndef CONFIG_SMP
#define PTE_FLAGS	PTE_TYPE_PAGE | PTE_AF
#define PMD_FLAGS	PMD_TYPE_SECT | PMD_SECT_AF
#else
#define PTE_FLAGS	PTE_TYPE_PAGE | PTE_AF | PTE_SHARED
#define PMD_FLAGS	PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S
#endif

#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.
	 */
M
Mark Salter 已提交
99 100 101 102 103 104 105 106 107
#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
108 109
	b	stext				// branch to kernel start, magic
	.long	0				// reserved
M
Mark Salter 已提交
110
#endif
M
Mark Rutland 已提交
111 112 113
	.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
R
Roy Franz 已提交
114 115 116 117 118 119 120
	.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
121 122 123
#ifdef CONFIG_EFI
	.long	pe_header - efi_head		// Offset to the PE header.
#else
R
Roy Franz 已提交
124
	.word	0				// reserved
M
Mark Salter 已提交
125 126 127
#endif

#ifdef CONFIG_EFI
128 129
	.globl	stext_offset
	.set	stext_offset, stext - efi_head
M
Mark Salter 已提交
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148
	.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
149
	.long	_end - stext			// SizeOfCode
M
Mark Salter 已提交
150 151 152
	.long	0				// SizeOfInitializedData
	.long	0				// SizeOfUninitializedData
	.long	efi_stub_entry - efi_head	// AddressOfEntryPoint
153
	.long	stext_offset			// BaseOfCode
M
Mark Salter 已提交
154 155 156

extra_header_fields:
	.quad	0				// ImageBase
157
	.long	0x1000				// SectionAlignment
158
	.long	PECOFF_FILE_ALIGNMENT		// FileAlignment
M
Mark Salter 已提交
159 160 161 162 163 164 165 166
	.short	0				// MajorOperatingSystemVersion
	.short	0				// MinorOperatingSystemVersion
	.short	0				// MajorImageVersion
	.short	0				// MinorImageVersion
	.short	0				// MajorSubsystemVersion
	.short	0				// MinorSubsystemVersion
	.long	0				// Win32VersionValue

167
	.long	_end - efi_head			// SizeOfImage
M
Mark Salter 已提交
168 169

	// Everything before the kernel image is considered part of the header
170
	.long	stext_offset			// SizeOfHeaders
M
Mark Salter 已提交
171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213
	.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
214
	.long	_end - stext		// VirtualSize
215
	.long	stext_offset		// VirtualAddress
M
Mark Salter 已提交
216
	.long	_edata - stext		// SizeOfRawData
217
	.long	stext_offset		// PointerToRawData
M
Mark Salter 已提交
218 219 220 221 222 223

	.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)
224 225 226 227 228 229 230 231 232

	/*
	 * 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
M
Mark Salter 已提交
233
#endif
234 235

ENTRY(stext)
236
	bl	preserve_boot_args
237
	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
238
	adrp	x24, __PHYS_OFFSET
239
	bl	set_cpu_boot_mode_flag
240

241 242 243
	bl	__vet_fdt
	bl	__create_page_tables		// x25=TTBR0, x26=TTBR1
	/*
244 245
	 * The following calls CPU setup code, see arch/arm64/mm/proc.S for
	 * details.
246 247 248
	 * On return, the CPU will be ready for the MMU to be turned on and
	 * the TCR will have been set.
	 */
249
	ldr	x27, =__mmap_switched		// address to jump to after
250
						// MMU has been enabled
251
	adr_l	lr, __enable_mmu		// return (PIC) address
252
	b	__cpu_setup			// initialise processor
253 254
ENDPROC(stext)

255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271
/*
 * 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)

272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354
/*
 * Determine validity of the x21 FDT pointer.
 * The dtb must be 8-byte aligned and live in the first 512M of memory.
 */
__vet_fdt:
	tst	x21, #0x7
	b.ne	1f
	cmp	x21, x24
	b.lt	1f
	mov	x0, #(1 << 29)
	add	x0, x0, x24
	cmp	x21, x0
	b.ge	1f
	ret
1:
	mov	x21, #0
	ret
ENDPROC(__vet_fdt)
/*
 * 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, including the FDT blob (TTBR1)
 *   - pgd entry for fixed mappings (TTBR1)
 */
__create_page_tables:
355 356
	adrp	x25, idmap_pg_dir
	adrp	x26, swapper_pg_dir
357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384
	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
385
	adrp	x3, KERNEL_START		// __pa(KERNEL_START)
386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422

#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 kernel image can be ID mapped. As T0SZ == (64 - #bits used),
	 * this number conveniently equals the number of leading zeroes in
	 * the physical address of KERNEL_END.
	 */
	adrp	x5, KERNEL_END
	clz	x5, x5
	cmp	x5, TCR_T0SZ(VA_BITS)	// default T0SZ small enough?
	b.ge	1f			// .. then skip additional level

	str_l	x5, idmap_t0sz, x6

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

423 424
	create_pgd_entry x0, x3, x5, x6
	mov	x5, x3				// __pa(KERNEL_START)
425
	adr_l	x6, KERNEL_END			// __pa(KERNEL_END)
426 427 428 429 430 431 432 433
	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
434
	ldr	x6, =KERNEL_END			// __va(KERNEL_END)
435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460
	mov	x3, x24				// phys offset
	create_block_map x0, x7, x3, x5, x6

	/*
	 * Map the FDT blob (maximum 2MB; must be within 512MB of
	 * PHYS_OFFSET).
	 */
	mov	x3, x21				// FDT phys address
	and	x3, x3, #~((1 << 21) - 1)	// 2MB aligned
	mov	x6, #PAGE_OFFSET
	sub	x5, x3, x24			// subtract PHYS_OFFSET
	tst	x5, #~((1 << 29) - 1)		// within 512MB?
	csel	x21, xzr, x21, ne		// zero the FDT pointer
	b.ne	1f
	add	x5, x5, x6			// __va(FDT blob)
	add	x6, x5, #1 << 21		// 2MB for the FDT blob
	sub	x6, x6, #1			// inclusive range
	create_block_map x0, x7, x3, x5, x6
1:
	/*
	 * 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
461
	dmb	sy
462 463 464 465 466 467 468 469
	bl	__inval_cache_range

	mov	lr, x27
	ret
ENDPROC(__create_page_tables)
	.ltorg

/*
470
 * The following fragment of code is executed with the MMU enabled.
471
 */
472
	.set	initial_sp, init_thread_union + THREAD_START_SP
473
__mmap_switched:
474 475
	adr_l	x6, __bss_start
	adr_l	x7, __bss_stop
476 477 478 479 480 481

1:	cmp	x6, x7
	b.hs	2f
	str	xzr, [x6], #8			// Clear BSS
	b	1b
2:
482 483 484
	adr_l	sp, initial_sp, x4
	str_l	x21, __fdt_pointer, x5		// Save FDT pointer
	str_l	x24, memstart_addr, x6		// Save PHYS_OFFSET
485 486 487 488 489 490 491 492 493
	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"
494 495 496
/*
 * If we're fortunate enough to boot at EL2, ensure that the world is
 * sane before dropping to EL1.
497 498 499
 *
 * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in x20 if
 * booted in EL1 or EL2 respectively.
500 501 502
 */
ENTRY(el2_setup)
	mrs	x0, CurrentEL
503
	cmp	x0, #CurrentEL_EL2
504 505 506 507 508 509 510 511 512 513
	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
514
	mov	w20, #BOOT_CPU_MODE_EL1		// This cpu booted in EL1
515
	isb
516 517 518
	ret

	/* Hyp configuration. */
519
2:	mov	x0, #(1 << 31)			// 64-bit EL1
520 521 522 523 524 525
	msr	hcr_el2, x0

	/* Generic timers. */
	mrs	x0, cnthctl_el2
	orr	x0, x0, #3			// Enable EL1 physical timers
	msr	cnthctl_el2, x0
526
	msr	cntvoff_el2, xzr		// Clear virtual offset
527

528 529 530 531 532 533 534
#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

535
	mrs_s	x0, ICC_SRE_EL2
536 537
	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
538
	msr_s	ICC_SRE_EL2, x0
539
	isb					// Make sure SRE is now set
540
	msr_s	ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
541 542 543 544

3:
#endif

545 546 547 548 549 550 551 552
	/* 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
553 554
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
555 556 557 558 559 560 561 562 563 564
	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

565 566 567
	/* Stage-2 translation */
	msr	vttbr_el2, xzr

M
Marc Zyngier 已提交
568
	/* Hypervisor stub */
569 570
	adrp	x0, __hyp_stub_vectors
	add	x0, x0, #:lo12:__hyp_stub_vectors
M
Marc Zyngier 已提交
571 572
	msr	vbar_el2, x0

573 574 575 576 577
	/* 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
578
	mov	w20, #BOOT_CPU_MODE_EL2		// This CPU booted in EL2
579 580 581
	eret
ENDPROC(el2_setup)

582 583 584 585 586
/*
 * 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)
587
	adr_l	x1, __boot_cpu_mode
588 589 590
	cmp	w20, #BOOT_CPU_MODE_EL2
	b.ne	1f
	add	x1, x1, #4
591 592 593
1:	str	w20, [x1]			// This CPU has booted in EL1
	dmb	sy
	dc	ivac, x1			// Invalidate potentially stale cache line
594 595 596
	ret
ENDPROC(set_cpu_boot_mode_flag)

597 598 599 600 601 602 603
/*
 * 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.
 */
604 605
	.pushsection	.data..cacheline_aligned
	.align	L1_CACHE_SHIFT
606
ENTRY(__boot_cpu_mode)
607
	.long	BOOT_CPU_MODE_EL2
608
	.long	BOOT_CPU_MODE_EL1
609 610
	.popsection

611 612 613 614 615 616
#ifdef CONFIG_SMP
	/*
	 * 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)
617 618
	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
	bl	set_cpu_boot_mode_flag
619
	mrs	x0, mpidr_el1
620 621
	ldr     x1, =MPIDR_HWID_BITMASK
	and	x0, x0, x1
622
	adr_l	x3, secondary_holding_pen_release
623 624 625 626 627 628
pen:	ldr	x4, [x3]
	cmp	x4, x0
	b.eq	secondary_startup
	wfe
	b	pen
ENDPROC(secondary_holding_pen)
629 630 631 632 633 634 635

	/*
	 * 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
636
	bl	set_cpu_boot_mode_flag
637 638
	b	secondary_startup
ENDPROC(secondary_entry)
639 640 641 642 643

ENTRY(secondary_startup)
	/*
	 * Common entry point for secondary CPUs.
	 */
644 645
	adrp	x25, idmap_pg_dir
	adrp	x26, swapper_pg_dir
646
	bl	__cpu_setup			// initialise processor
647 648 649 650 651 652 653 654 655 656 657 658 659 660 661

	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)
#endif	/* CONFIG_SMP */

/*
662
 * Enable the MMU.
663
 *
664 665 666 667
 *  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
668 669 670 671 672 673 674 675 676 677
 */
__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
	br	x27
678
ENDPROC(__enable_mmu)