Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:
 "Here are the main arm64 updates for 4.6.  There are some relatively
  intrusive changes to support KASLR, the reworking of the kernel
  virtual memory layout and initial page table creation.

  Summary:

   - Initial page table creation reworked to avoid breaking large block
     mappings (huge pages) into smaller ones.  The ARM architecture
     requires break-before-make in such cases to avoid TLB conflicts but
     that's not always possible on live page tables

   - Kernel virtual memory layout: the kernel image is no longer linked
     to the bottom of the linear mapping (PAGE_OFFSET) but at the bottom
     of the vmalloc space, allowing the kernel to be loaded (nearly)
     anywhere in physical RAM

   - Kernel ASLR: position independent kernel Image and modules being
     randomly mapped in the vmalloc space with the randomness is
     provided by UEFI (efi_get_random_bytes() patches merged via the
     arm64 tree, acked by Matt Fleming)

   - Implement relative exception tables for arm64, required by KASLR
     (initial code for ARCH_HAS_RELATIVE_EXTABLE added to lib/extable.c
     but actual x86 conversion to deferred to 4.7 because of the merge
     dependencies)

   - Support for the User Access Override feature of ARMv8.2: this
     allows uaccess functions (get_user etc.) to be implemented using
     LDTR/STTR instructions.  Such instructions, when run by the kernel,
     perform unprivileged accesses adding an extra level of protection.
     The set_fs() macro is used to "upgrade" such instruction to
     privileged accesses via the UAO bit

   - Half-precision floating point support (part of ARMv8.2)

   - Optimisations for CPUs with or without a hardware prefetcher (using
     run-time code patching)

   - copy_page performance improvement to deal with 128 bytes at a time

   - Sanity checks on the CPU capabilities (via CPUID) to prevent
     incompatible secondary CPUs from being brought up (e.g.  weird
     big.LITTLE configurations)

   - valid_user_regs() reworked for better sanity check of the
     sigcontext information (restored pstate information)

   - ACPI parking protocol implementation

   - CONFIG_DEBUG_RODATA enabled by default

   - VDSO code marked as read-only

   - DEBUG_PAGEALLOC support

   - ARCH_HAS_UBSAN_SANITIZE_ALL enabled

   - Erratum workaround Cavium ThunderX SoC

   - set_pte_at() fix for PROT_NONE mappings

   - Code clean-ups"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (99 commits)
  arm64: kasan: Fix zero shadow mapping overriding kernel image shadow
  arm64: kasan: Use actual memory node when populating the kernel image shadow
  arm64: Update PTE_RDONLY in set_pte_at() for PROT_NONE permission
  arm64: Fix misspellings in comments.
  arm64: efi: add missing frame pointer assignment
  arm64: make mrs_s prefixing implicit in read_cpuid
  arm64: enable CONFIG_DEBUG_RODATA by default
  arm64: Rework valid_user_regs
  arm64: mm: check at build time that PAGE_OFFSET divides the VA space evenly
  arm64: KVM: Move kvm_call_hyp back to its original localtion
  arm64: mm: treat memstart_addr as a signed quantity
  arm64: mm: list kernel sections in order
  arm64: lse: deal with clobbered IP registers after branch via PLT
  arm64: mm: dump: Use VA_START directly instead of private LOWEST_ADDR
  arm64: kconfig: add submenu for 8.2 architectural features
  arm64: kernel: acpi: fix ioremap in ACPI parking protocol cpu_postboot
  arm64: Add support for Half precision floating point
  arm64: Remove fixmap include fragility
  arm64: Add workaround for Cavium erratum 27456
  arm64: mm: Mark .rodata as RO
  ...

1 files changed, 145 insertions, 22 deletions

diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 6f2f37743d3b..6ebd204da16a 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -29,12 +29,14 @@
 #include <asm/asm-offsets.h>
 #include <asm/cache.h>
 #include <asm/cputype.h>
+#include <asm/elf.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/kvm_arm.h>
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
+#include <asm/smp.h>
 #include <asm/sysreg.h>
 #include <asm/thread_info.h>
 #include <asm/virt.h>
@@ -68,12 +70,11 @@
  * in the entry routines.
  */
 	__HEAD
-
+_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.
@@ -84,9 +85,9 @@ efi_head:
 	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
+	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
 	.quad	0				// reserved
 	.quad	0				// reserved
 	.quad	0				// reserved
@@ -95,14 +96,14 @@ efi_head:
 	.byte	0x4d
 	.byte	0x64
 #ifdef CONFIG_EFI
-	.long	pe_header - efi_head		// Offset to the PE header.
+	.long	pe_header - _head		// Offset to the PE header.
 #else
 	.word	0				// reserved
 #endif
 
 #ifdef CONFIG_EFI
 	.globl	__efistub_stext_offset
-	.set	__efistub_stext_offset, stext - efi_head
+	.set	__efistub_stext_offset, stext - _head
 	.align 3
 pe_header:
 	.ascii	"PE"
@@ -125,7 +126,7 @@ optional_header:
 	.long	_end - stext			// SizeOfCode
 	.long	0				// SizeOfInitializedData
 	.long	0				// SizeOfUninitializedData
-	.long	__efistub_entry - efi_head	// AddressOfEntryPoint
+	.long	__efistub_entry - _head		// AddressOfEntryPoint
 	.long	__efistub_stext_offset		// BaseOfCode
 
 extra_header_fields:
@@ -140,7 +141,7 @@ extra_header_fields:
 	.short	0				// MinorSubsystemVersion
 	.long	0				// Win32VersionValue
 
-	.long	_end - efi_head			// SizeOfImage
+	.long	_end - _head			// SizeOfImage
 
 	// Everything before the kernel image is considered part of the header
 	.long	__efistub_stext_offset		// SizeOfHeaders
@@ -211,6 +212,7 @@ section_table:
 ENTRY(stext)
 	bl	preserve_boot_args
 	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
+	mov	x23, xzr			// KASLR offset, defaults to 0
 	adrp	x24, __PHYS_OFFSET
 	bl	set_cpu_boot_mode_flag
 	bl	__create_page_tables		// x25=TTBR0, x26=TTBR1
@@ -220,11 +222,13 @@ ENTRY(stext)
 	 * 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
+	ldr	x27, 0f				// address to jump to after
 						// MMU has been enabled
 	adr_l	lr, __enable_mmu		// return (PIC) address
 	b	__cpu_setup			// initialise processor
 ENDPROC(stext)
+	.align	3
+0:	.quad	__mmap_switched - (_head - TEXT_OFFSET) + KIMAGE_VADDR
 
 /*
  * Preserve the arguments passed by the bootloader in x0 .. x3
@@ -312,7 +316,7 @@ ENDPROC(preserve_boot_args)
 __create_page_tables:
 	adrp	x25, idmap_pg_dir
 	adrp	x26, swapper_pg_dir
-	mov	x27, lr
+	mov	x28, lr
 
 	/*
 	 * Invalidate the idmap and swapper page tables to avoid potential
@@ -390,9 +394,11 @@ __create_page_tables:
 	 * Map the kernel image (starting with PHYS_OFFSET).
 	 */
 	mov	x0, x26				// swapper_pg_dir
-	mov	x5, #PAGE_OFFSET
+	ldr	x5, =KIMAGE_VADDR
+	add	x5, x5, x23			// add KASLR displacement
 	create_pgd_entry x0, x5, x3, x6
-	ldr	x6, =KERNEL_END			// __va(KERNEL_END)
+	ldr	w6, kernel_img_size
+	add	x6, x6, x5
 	mov	x3, x24				// phys offset
 	create_block_map x0, x7, x3, x5, x6
 
@@ -406,9 +412,11 @@ __create_page_tables:
 	dmb	sy
 	bl	__inval_cache_range
 
-	mov	lr, x27
-	ret
+	ret	x28
 ENDPROC(__create_page_tables)
+
+kernel_img_size:
+	.long	_end - (_head - TEXT_OFFSET)
 	.ltorg
 
 /*
@@ -416,23 +424,81 @@ ENDPROC(__create_page_tables)
  */
 	.set	initial_sp, init_thread_union + THREAD_START_SP
 __mmap_switched:
+	mov	x28, lr				// preserve LR
+	adr_l	x8, vectors			// load VBAR_EL1 with virtual
+	msr	vbar_el1, x8			// vector table address
+	isb
+
 	// Clear BSS
 	adr_l	x0, __bss_start
 	mov	x1, xzr
 	adr_l	x2, __bss_stop
 	sub	x2, x2, x0
 	bl	__pi_memset
+	dsb	ishst				// Make zero page visible to PTW
+
+#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
+	add	x13, x13, x23			// relocate
+	str	x13, [x11, x23]
+	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
+	ldrsh	w14, [x12, #6]			// Elf64_Sym::st_shndx
+	ldr	x15, [x12, #8]			// Elf64_Sym::st_value
+	cmp	w14, #-0xf			// SHN_ABS (0xfff1) ?
+	add	x14, x15, x23			// relocate
+	csel	x15, x14, x15, ne
+	add	x15, x13, x15
+	str	x15, [x11, x23]
+	b	0b
+
+2:	adr_l	x8, kimage_vaddr		// make relocated kimage_vaddr
+	dc	cvac, x8			// value visible to secondaries
+	dsb	sy				// with MMU off
+#endif
 
 	adr_l	sp, initial_sp, x4
 	mov	x4, sp
 	and	x4, x4, #~(THREAD_SIZE - 1)
 	msr	sp_el0, x4			// Save thread_info
 	str_l	x21, __fdt_pointer, x5		// Save FDT pointer
-	str_l	x24, memstart_addr, x6		// Save PHYS_OFFSET
+
+	ldr_l	x4, kimage_vaddr		// Save the offset between
+	sub	x4, x4, x24			// the kernel virtual and
+	str_l	x4, kimage_voffset, x5		// physical mappings
+
 	mov	x29, #0
 #ifdef CONFIG_KASAN
 	bl	kasan_early_init
 #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:
+#endif
 	b	start_kernel
 ENDPROC(__mmap_switched)
 
@@ -441,6 +507,10 @@ ENDPROC(__mmap_switched)
  * hotplug and needs to have the same protections as the text region
  */
 	.section ".text","ax"
+
+ENTRY(kimage_vaddr)
+	.quad		_text - TEXT_OFFSET
+
 /*
  * If we're fortunate enough to boot at EL2, ensure that the world is
  * sane before dropping to EL1.
@@ -631,13 +701,20 @@ ENTRY(secondary_startup)
 	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
+	ldr	x8, kimage_vaddr
+	ldr	w9, 0f
+	sub	x27, x8, w9, sxtw		// address to jump to after enabling the MMU
 	b	__enable_mmu
 ENDPROC(secondary_startup)
+0:	.long	(_text - TEXT_OFFSET) - __secondary_switched
 
 ENTRY(__secondary_switched)
-	ldr	x0, [x21]			// get secondary_data.stack
+	adr_l	x5, vectors
+	msr	vbar_el1, x5
+	isb
+
+	adr_l	x0, secondary_data
+	ldr	x0, [x0, #CPU_BOOT_STACK]	// get secondary_data.stack
 	mov	sp, x0
 	and	x0, x0, #~(THREAD_SIZE - 1)
 	msr	sp_el0, x0			// save thread_info
@@ -646,6 +723,29 @@ ENTRY(__secondary_switched)
 ENDPROC(__secondary_switched)
 
 /*
+ * 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
+
+/*
  * Enable the MMU.
  *
  *  x0  = SCTLR_EL1 value for turning on the MMU.
@@ -658,12 +758,12 @@ ENDPROC(__secondary_switched)
  */
 	.section	".idmap.text", "ax"
 __enable_mmu:
+	mrs	x18, sctlr_el1			// preserve old SCTLR_EL1 value
 	mrs	x1, ID_AA64MMFR0_EL1
 	ubfx	x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
 	cmp	x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
 	b.ne	__no_granule_support
-	ldr	x5, =vectors
-	msr	vbar_el1, x5
+	update_early_cpu_boot_status 0, x1, x2
 	msr	ttbr0_el1, x25			// load TTBR0
 	msr	ttbr1_el1, x26			// load TTBR1
 	isb
@@ -677,10 +777,33 @@ __enable_mmu:
 	ic	iallu
 	dsb	nsh
 	isb
+#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.
+	 */
+	msr	sctlr_el1, x18			// disable the MMU
+	isb
+	bl	__create_page_tables		// recreate kernel mapping
+
+	msr	sctlr_el1, x19			// re-enable the MMU
+	isb
+	ic	ialluis				// flush instructions fetched
+	isb					// via old mapping
+	add	x27, x27, x23			// relocated __mmap_switched
+#endif
 	br	x27
 ENDPROC(__enable_mmu)
 
 __no_granule_support:
+	/* 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:
 	wfe
-	b __no_granule_support
+	wfi
+	b 1b
 ENDPROC(__no_granule_support)