head.S 22.2 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

#include <asm/assembler.h>
28
#include <asm/boot.h>
29 30
#include <asm/ptrace.h>
#include <asm/asm-offsets.h>
31
#include <asm/cache.h>
32
#include <asm/cputype.h>
33
#include <asm/elf.h>
34
#include <asm/kernel-pgtable.h>
35
#include <asm/kvm_arm.h>
36 37 38 39
#include <asm/memory.h>
#include <asm/pgtable-hwdef.h>
#include <asm/pgtable.h>
#include <asm/page.h>
40
#include <asm/smp.h>
41 42
#include <asm/sysreg.h>
#include <asm/thread_info.h>
43
#include <asm/virt.h>
44

45
#define __PHYS_OFFSET	(KERNEL_START - TEXT_OFFSET)
46

47 48 49
#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
50
#error PAGE_OFFSET must be at least 2MB aligned
51
#elif TEXT_OFFSET > 0x1fffff
M
Mark Rutland 已提交
52
#error TEXT_OFFSET must be less than 2MB
53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70
#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
71
_head:
72 73 74
	/*
	 * DO NOT MODIFY. Image header expected by Linux boot-loaders.
	 */
M
Mark Salter 已提交
75 76 77 78 79 80 81 82
#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
83 84
	b	stext				// branch to kernel start, magic
	.long	0				// reserved
M
Mark Salter 已提交
85
#endif
86 87 88
	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
89 90 91 92 93 94 95
	.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
96
#ifdef CONFIG_EFI
97
	.long	pe_header - _head		// Offset to the PE header.
M
Mark Salter 已提交
98
#else
R
Roy Franz 已提交
99
	.word	0				// reserved
M
Mark Salter 已提交
100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121
#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
122
	.long	_end - efi_header_end		// SizeOfCode
M
Mark Salter 已提交
123 124
	.long	0				// SizeOfInitializedData
	.long	0				// SizeOfUninitializedData
125
	.long	__efistub_entry - _head		// AddressOfEntryPoint
126
	.long	efi_header_end - _head		// BaseOfCode
M
Mark Salter 已提交
127 128 129

extra_header_fields:
	.quad	0				// ImageBase
130
	.long	0x1000				// SectionAlignment
131
	.long	PECOFF_FILE_ALIGNMENT		// FileAlignment
M
Mark Salter 已提交
132 133 134 135 136 137 138 139
	.short	0				// MajorOperatingSystemVersion
	.short	0				// MinorOperatingSystemVersion
	.short	0				// MajorImageVersion
	.short	0				// MinorImageVersion
	.short	0				// MajorSubsystemVersion
	.short	0				// MinorSubsystemVersion
	.long	0				// Win32VersionValue

140
	.long	_end - _head			// SizeOfImage
M
Mark Salter 已提交
141 142

	// Everything before the kernel image is considered part of the header
143
	.long	efi_header_end - _head		// SizeOfHeaders
M
Mark Salter 已提交
144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186
	.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
187 188 189 190
	.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
191 192 193 194 195 196

	.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)
197 198

	/*
199
	 * EFI will load .text onwards at the 4k section alignment
200 201
	 * described in the PE/COFF header. To ensure that instruction
	 * sequences using an adrp and a :lo12: immediate will function
202
	 * correctly at this alignment, we must ensure that .text is
203 204 205
	 * placed at a 4k boundary in the Image to begin with.
	 */
	.align 12
206
efi_header_end:
M
Mark Salter 已提交
207
#endif
208

209 210
	__INIT

211
ENTRY(stext)
212
	bl	preserve_boot_args
213
	bl	el2_setup			// Drop to EL1, w0=cpu_boot_mode
214 215
	adrp	x23, __PHYS_OFFSET
	and	x23, x23, MIN_KIMG_ALIGN - 1	// KASLR offset, defaults to 0
216
	bl	set_cpu_boot_mode_flag
217
	bl	__create_page_tables
218
	/*
219 220
	 * The following calls CPU setup code, see arch/arm64/mm/proc.S for
	 * details.
221 222 223
	 * On return, the CPU will be ready for the MMU to be turned on and
	 * the TCR will have been set.
	 */
224
	bl	__cpu_setup			// initialise processor
225
	b	__primary_switch
226 227
ENDPROC(stext)

228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244
/*
 * 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)

245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274
/*
 * 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
275 276 277 278
#if SWAPPER_PGTABLE_LEVELS > 3
	create_table_entry \tbl, \virt, PUD_SHIFT, PTRS_PER_PUD, \tmp1, \tmp2
#endif
#if SWAPPER_PGTABLE_LEVELS > 2
279
	create_table_entry \tbl, \virt, SWAPPER_TABLE_SHIFT, PTRS_PER_PTE, \tmp1, \tmp2
280 281 282 283 284 285 286 287 288 289 290
#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
291 292
	lsr	\phys, \phys, #SWAPPER_BLOCK_SHIFT
	lsr	\start, \start, #SWAPPER_BLOCK_SHIFT
293
	and	\start, \start, #PTRS_PER_PTE - 1	// table index
294 295
	orr	\phys, \flags, \phys, lsl #SWAPPER_BLOCK_SHIFT	// table entry
	lsr	\end, \end, #SWAPPER_BLOCK_SHIFT
296 297 298
	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
299
	add	\phys, \phys, #SWAPPER_BLOCK_SIZE		// next block
300 301 302 303 304 305 306 307 308
	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
309
 *     been enabled
310 311
 */
__create_page_tables:
312
	mov	x28, lr
313 314 315 316 317

	/*
	 * Invalidate the idmap and swapper page tables to avoid potential
	 * dirty cache lines being evicted.
	 */
318 319
	adrp	x0, idmap_pg_dir
	adrp	x1, swapper_pg_dir + SWAPPER_DIR_SIZE
320 321 322 323 324
	bl	__inval_cache_range

	/*
	 * Clear the idmap and swapper page tables.
	 */
325 326
	adrp	x0, idmap_pg_dir
	adrp	x6, swapper_pg_dir + SWAPPER_DIR_SIZE
327 328 329 330 331 332 333
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

334
	mov	x7, SWAPPER_MM_MMUFLAGS
335 336 337 338

	/*
	 * Create the identity mapping.
	 */
339
	adrp	x0, idmap_pg_dir
340
	adrp	x3, __idmap_text_start		// __pa(__idmap_text_start)
341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362

#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
363
	 * entire ID map region can be mapped. As T0SZ == (64 - #bits used),
364
	 * this number conveniently equals the number of leading zeroes in
365
	 * the physical address of __idmap_text_end.
366
	 */
367
	adrp	x5, __idmap_text_end
368 369 370 371
	clz	x5, x5
	cmp	x5, TCR_T0SZ(VA_BITS)	// default T0SZ small enough?
	b.ge	1f			// .. then skip additional level

372 373 374 375
	adr_l	x6, idmap_t0sz
	str	x5, [x6]
	dmb	sy
	dc	ivac, x6		// Invalidate potentially stale cache line
376 377 378 379 380

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

381
	create_pgd_entry x0, x3, x5, x6
382 383
	mov	x5, x3				// __pa(__idmap_text_start)
	adr_l	x6, __idmap_text_end		// __pa(__idmap_text_end)
384 385 386 387 388
	create_block_map x0, x7, x3, x5, x6

	/*
	 * Map the kernel image (starting with PHYS_OFFSET).
	 */
389
	adrp	x0, swapper_pg_dir
390
	mov_q	x5, KIMAGE_VADDR + TEXT_OFFSET	// compile time __va(_text)
391
	add	x5, x5, x23			// add KASLR displacement
392
	create_pgd_entry x0, x5, x3, x6
393 394 395 396
	adrp	x6, _end			// runtime __pa(_end)
	adrp	x3, _text			// runtime __pa(_text)
	sub	x6, x6, x3			// _end - _text
	add	x6, x6, x5			// runtime __va(_end)
397 398 399 400 401 402 403
	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.
	 */
404 405
	adrp	x0, idmap_pg_dir
	adrp	x1, swapper_pg_dir + SWAPPER_DIR_SIZE
406
	dmb	sy
407 408
	bl	__inval_cache_range

409
	ret	x28
410 411 412 413
ENDPROC(__create_page_tables)
	.ltorg

/*
414
 * The following fragment of code is executed with the MMU enabled.
415 416
 *
 *   x0 = __PHYS_OFFSET
417
 */
418
	.set	initial_sp, init_thread_union + THREAD_START_SP
419
__primary_switched:
420
	mov	x28, lr				// preserve LR
421 422 423 424
	adr_l	x8, vectors			// load VBAR_EL1 with virtual
	msr	vbar_el1, x8			// vector table address
	isb

425 426 427 428 429 430
	str_l	x21, __fdt_pointer, x5		// Save FDT pointer

	ldr_l	x4, kimage_vaddr		// Save the offset between
	sub	x4, x4, x0			// the kernel virtual and
	str_l	x4, kimage_voffset, x5		// physical mappings

431 432 433 434 435 436
	// Clear BSS
	adr_l	x0, __bss_start
	mov	x1, xzr
	adr_l	x2, __bss_stop
	sub	x2, x2, x0
	bl	__pi_memset
437
	dsb	ishst				// Make zero page visible to PTW
438

439
	adr_l	sp, initial_sp, x4
440 441 442
	mov	x4, sp
	and	x4, x4, #~(THREAD_SIZE - 1)
	msr	sp_el0, x4			// Save thread_info
443
	mov	x29, #0
A
Andrey Ryabinin 已提交
444 445
#ifdef CONFIG_KASAN
	bl	kasan_early_init
446 447
#endif
#ifdef CONFIG_RANDOMIZE_BASE
448 449
	tst	x23, ~(MIN_KIMG_ALIGN - 1)	// already running randomized?
	b.ne	0f
450
	mov	x0, x21				// pass FDT address in x0
451
	mov	x1, x23				// pass modulo offset in x1
452 453
	bl	kaslr_early_init		// parse FDT for KASLR options
	cbz	x0, 0f				// KASLR disabled? just proceed
454
	orr	x23, x23, x0			// record KASLR offset
455
	ret	x28				// we must enable KASLR, return
456
						// to __primary_switch()
457
0:
A
Andrey Ryabinin 已提交
458
#endif
459
	b	start_kernel
460
ENDPROC(__primary_switched)
461 462 463 464 465

/*
 * end early head section, begin head code that is also used for
 * hotplug and needs to have the same protections as the text region
 */
466
	.section ".idmap.text","ax"
467 468 469 470

ENTRY(kimage_vaddr)
	.quad		_text - TEXT_OFFSET

471 472 473
/*
 * If we're fortunate enough to boot at EL2, ensure that the world is
 * sane before dropping to EL1.
474 475 476
 *
 * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in x20 if
 * booted in EL1 or EL2 respectively.
477 478 479
 */
ENTRY(el2_setup)
	mrs	x0, CurrentEL
480
	cmp	x0, #CurrentEL_EL2
481 482 483 484 485 486 487 488 489 490
	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
491
	mov	w0, #BOOT_CPU_MODE_EL1		// This cpu booted in EL1
492
	isb
493 494
	ret

495 496 497 498 499 500 501 502 503 504 505 506 507
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

508
	/* Hyp configuration. */
509 510 511 512 513
	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:
514
	msr	hcr_el2, x0
515
	isb
516 517 518 519 520

	/* Generic timers. */
	mrs	x0, cnthctl_el2
	orr	x0, x0, #3			// Enable EL1 physical timers
	msr	cnthctl_el2, x0
521
	msr	cntvoff_el2, xzr		// Clear virtual offset
522

523 524 525 526 527 528 529
#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

530
	mrs_s	x0, ICC_SRE_EL2
531 532
	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
533
	msr_s	ICC_SRE_EL2, x0
534
	isb					// Make sure SRE is now set
535 536
	mrs_s	x0, ICC_SRE_EL2			// Read SRE back,
	tbz	x0, #0, 3f			// and check that it sticks
537
	msr_s	ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
538 539 540 541

3:
#endif

542 543 544 545 546 547
	/* Populate ID registers. */
	mrs	x0, midr_el1
	mrs	x1, mpidr_el1
	msr	vpidr_el2, x0
	msr	vmpidr_el2, x1

548 549 550 551 552 553 554 555 556
	/*
	 * When VHE is not in use, early init of EL2 and EL1 needs to be
	 * done here.
	 * When VHE _is_ in use, EL1 will not be used in the host and
	 * requires no configuration, and all non-hyp-specific EL2 setup
	 * will be done via the _EL1 system register aliases in __cpu_setup.
	 */
	cbnz	x2, 1f

557 558
	/* sctlr_el1 */
	mov	x0, #0x0800			// Set/clear RES{1,0} bits
559 560
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
561 562 563 564 565
	msr	sctlr_el1, x0

	/* Coprocessor traps. */
	mov	x0, #0x33ff
	msr	cptr_el2, x0			// Disable copro. traps to EL2
566
1:
567 568 569 570 571

#ifdef CONFIG_COMPAT
	msr	hstr_el2, xzr			// Disable CP15 traps to EL2
#endif

572
	/* EL2 debug */
573 574 575 576
	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
577 578 579
	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
580
4:
581

582 583 584
	/* Stage-2 translation */
	msr	vttbr_el2, xzr

585 586
	cbz	x2, install_el2_stub

587
	mov	w0, #BOOT_CPU_MODE_EL2		// This CPU booted in EL2
588 589 590 591
	isb
	ret

install_el2_stub:
M
Marc Zyngier 已提交
592
	/* Hypervisor stub */
593 594
	adrp	x0, __hyp_stub_vectors
	add	x0, x0, #:lo12:__hyp_stub_vectors
M
Marc Zyngier 已提交
595 596
	msr	vbar_el2, x0

597 598 599 600 601
	/* 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
602
	mov	w0, #BOOT_CPU_MODE_EL2		// This CPU booted in EL2
603 604 605
	eret
ENDPROC(el2_setup)

606 607 608 609
/*
 * 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.
 */
610
set_cpu_boot_mode_flag:
611
	adr_l	x1, __boot_cpu_mode
612
	cmp	w0, #BOOT_CPU_MODE_EL2
613 614
	b.ne	1f
	add	x1, x1, #4
615
1:	str	w0, [x1]			// This CPU has booted in EL1
616 617
	dmb	sy
	dc	ivac, x1			// Invalidate potentially stale cache line
618 619 620
	ret
ENDPROC(set_cpu_boot_mode_flag)

621 622 623 624 625 626 627
/*
 * These values are written with the MMU off, but read with the MMU on.
 * Writers will invalidate the corresponding address, discarding up to a
 * 'Cache Writeback Granule' (CWG) worth of data. The linker script ensures
 * sufficient alignment that the CWG doesn't overlap another section.
 */
	.pushsection ".mmuoff.data.write", "aw"
628 629 630 631 632 633 634
/*
 * 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.
 */
635
ENTRY(__boot_cpu_mode)
636
	.long	BOOT_CPU_MODE_EL2
637
	.long	BOOT_CPU_MODE_EL1
638 639 640 641 642 643 644
/*
 * The booting CPU updates the failed status @__early_cpu_boot_status,
 * with MMU turned off.
 */
ENTRY(__early_cpu_boot_status)
	.long 	0

645 646
	.popsection

647 648 649 650 651
	/*
	 * 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)
652
	bl	el2_setup			// Drop to EL1, w0=cpu_boot_mode
653
	bl	set_cpu_boot_mode_flag
654
	mrs	x0, mpidr_el1
655
	mov_q	x1, MPIDR_HWID_BITMASK
656
	and	x0, x0, x1
657
	adr_l	x3, secondary_holding_pen_release
658 659 660 661 662 663
pen:	ldr	x4, [x3]
	cmp	x4, x0
	b.eq	secondary_startup
	wfe
	b	pen
ENDPROC(secondary_holding_pen)
664 665 666 667 668 669 670

	/*
	 * 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
671
	bl	set_cpu_boot_mode_flag
672 673
	b	secondary_startup
ENDPROC(secondary_entry)
674

675
secondary_startup:
676 677 678
	/*
	 * Common entry point for secondary CPUs.
	 */
679
	bl	__cpu_setup			// initialise processor
680 681 682
	bl	__enable_mmu
	ldr	x8, =__secondary_switched
	br	x8
683 684
ENDPROC(secondary_startup)

685
__secondary_switched:
686 687 688 689
	adr_l	x5, vectors
	msr	vbar_el1, x5
	isb

690 691
	adr_l	x0, secondary_data
	ldr	x0, [x0, #CPU_BOOT_STACK]	// get secondary_data.stack
692
	mov	sp, x0
693 694
	and	x0, x0, #~(THREAD_SIZE - 1)
	msr	sp_el0, x0			// save thread_info
695 696 697 698
	mov	x29, #0
	b	secondary_start_kernel
ENDPROC(__secondary_switched)

699 700 701 702 703 704 705 706 707 708 709 710
/*
 * 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
711 712
	adr_l	\tmp1, __early_cpu_boot_status
	str	\tmp2, [\tmp1]
713 714 715 716
	dmb	sy
	dc	ivac, \tmp1			// Invalidate potentially stale cache line
	.endm

717
/*
718
 * Enable the MMU.
719
 *
720 721
 *  x0  = SCTLR_EL1 value for turning on the MMU.
 *
722 723
 * Returns to the caller via x30/lr. This requires the caller to be covered
 * by the .idmap.text section.
724 725 726
 *
 * Checks if the selected granule size is supported by the CPU.
 * If it isn't, park the CPU
727
 */
728
ENTRY(__enable_mmu)
729 730 731 732
	mrs	x1, ID_AA64MMFR0_EL1
	ubfx	x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
	cmp	x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
	b.ne	__no_granule_support
733
	update_early_cpu_boot_status 0, x1, x2
734 735 736 737
	adrp	x1, idmap_pg_dir
	adrp	x2, swapper_pg_dir
	msr	ttbr0_el1, x1			// load TTBR0
	msr	ttbr1_el1, x2			// load TTBR1
738 739 740
	isb
	msr	sctlr_el1, x0
	isb
741 742 743 744 745 746 747 748
	/*
	 * 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
749
	ret
750
ENDPROC(__enable_mmu)
751 752

__no_granule_support:
753 754 755
	/* 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:
756
	wfe
757
	wfi
758
	b	1b
759
ENDPROC(__no_granule_support)
760

761
#ifdef CONFIG_RELOCATABLE
762
__relocate_kernel:
763 764 765 766 767 768 769
	/*
	 * Iterate over each entry in the relocation table, and apply the
	 * relocations in place.
	 */
	ldr	w9, =__rela_offset		// offset to reloc table
	ldr	w10, =__rela_size		// size of reloc table

770
	mov_q	x11, KIMAGE_VADDR		// default virtual offset
771 772 773 774 775
	add	x11, x11, x23			// actual virtual offset
	add	x9, x9, x11			// __va(.rela)
	add	x10, x9, x10			// __va(.rela) + sizeof(.rela)

0:	cmp	x9, x10
776
	b.hs	1f
777 778 779
	ldp	x11, x12, [x9], #24
	ldr	x13, [x9, #-8]
	cmp	w12, #R_AARCH64_RELATIVE
780
	b.ne	0b
781 782 783
	add	x13, x13, x23			// relocate
	str	x13, [x11, x23]
	b	0b
784 785 786
1:	ret
ENDPROC(__relocate_kernel)
#endif
787

788 789 790 791 792 793
__primary_switch:
#ifdef CONFIG_RANDOMIZE_BASE
	mov	x19, x0				// preserve new SCTLR_EL1 value
	mrs	x20, sctlr_el1			// preserve old SCTLR_EL1 value
#endif

794
	bl	__enable_mmu
795 796 797 798
#ifdef CONFIG_RELOCATABLE
	bl	__relocate_kernel
#ifdef CONFIG_RANDOMIZE_BASE
	ldr	x8, =__primary_switched
799
	adrp	x0, __PHYS_OFFSET
800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821
	blr	x8

	/*
	 * 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.
	 */
	msr	sctlr_el1, x20			// disable the MMU
	isb
	bl	__create_page_tables		// recreate kernel mapping

	tlbi	vmalle1				// Remove any stale TLB entries
	dsb	nsh

	msr	sctlr_el1, x19			// re-enable the MMU
	isb
	ic	iallu				// flush instructions fetched
	dsb	nsh				// via old mapping
	isb

	bl	__relocate_kernel
#endif
822 823
#endif
	ldr	x8, =__primary_switched
824
	adrp	x0, __PHYS_OFFSET
825 826
	br	x8
ENDPROC(__primary_switch)