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

Pull arm64 updates from Will Deacon:
 "Here's the usual mixed bag of arm64 updates, also including some
  related EFI changes (Acked by Matt) and the MMU gather range cleanup
  (Acked by you).

  Changes include:
   - support for alternative instruction patching from Andre
   - seccomp from Akashi
   - some AArch32 instruction emulation, required by the Android folks
   - optimisations for exception entry/exit code, cmpxchg, pcpu atomics
   - mmu_gather range calculations moved into core code
   - EFI updates from Ard, including long-awaited SMBIOS support
   - /proc/cpuinfo fixes to align with the format used by arch/arm/
   - a few non-critical fixes across the architecture"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (70 commits)
  arm64: remove the unnecessary arm64_swiotlb_init()
  arm64: add module support for alternatives fixups
  arm64: perf: Prevent wraparound during overflow
  arm64/include/asm: Fixed a warning about 'struct pt_regs'
  arm64: Provide a namespace to NCAPS
  arm64: bpf: lift restriction on last instruction
  arm64: Implement support for read-mostly sections
  arm64: compat: align cacheflush syscall with arch/arm
  arm64: add seccomp support
  arm64: add SIGSYS siginfo for compat task
  arm64: add seccomp syscall for compat task
  asm-generic: add generic seccomp.h for secure computing mode 1
  arm64: ptrace: allow tracer to skip a system call
  arm64: ptrace: add NT_ARM_SYSTEM_CALL regset
  arm64: Move some head.text functions to executable section
  arm64: jump labels: NOP out NOP -> NOP replacement
  arm64: add support to dump the kernel page tables
  arm64: Add FIX_HOLE to permanent fixed addresses
  arm64: alternatives: fix pr_fmt string for consistency
  arm64: vmlinux.lds.S: don't discard .exit.* sections at link-time
  ...

Documentation/arm64/legacy_instructions.txt

+The arm64 port of the Linux kernel provides infrastructure to support
+emulation of instructions which have been deprecated, or obsoleted in
+the architecture. The infrastructure code uses undefined instruction
+hooks to support emulation. Where available it also allows turning on
+the instruction execution in hardware.
+
+The emulation mode can be controlled by writing to sysctl nodes
+(/proc/sys/abi). The following explains the different execution
+behaviours and the corresponding values of the sysctl nodes -
+
+* Undef
+  Value: 0
+  Generates undefined instruction abort. Default for instructions that
+  have been obsoleted in the architecture, e.g., SWP
+
+* Emulate
+  Value: 1
+  Uses software emulation. To aid migration of software, in this mode
+  usage of emulated instruction is traced as well as rate limited
+  warnings are issued. This is the default for deprecated
+  instructions, .e.g., CP15 barriers
+
+* Hardware Execution
+  Value: 2
+  Although marked as deprecated, some implementations may support the
+  enabling/disabling of hardware support for the execution of these
+  instructions. Using hardware execution generally provides better
+  performance, but at the loss of ability to gather runtime statistics
+  about the use of the deprecated instructions.
+
+The default mode depends on the status of the instruction in the
+architecture. Deprecated instructions should default to emulation
+while obsolete instructions must be undefined by default.
+
+Supported legacy instructions
+-----------------------------
+* SWP{B}
+Node: /proc/sys/abi/swp
+Status: Obsolete
+Default: Undef (0)
+
+* CP15 Barriers
+Node: /proc/sys/abi/cp15_barrier
+Status: Deprecated
+Default: Emulate (1)

arch/arm64/Kconfig

@@ -34,13 +34,16 @@ config ARM64
 	select GENERIC_TIME_VSYSCALL
 	select HANDLE_DOMAIN_IRQ
 	select HARDIRQS_SW_RESEND
+	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_BPF_JIT
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_CC_STACKPROTECTOR
+	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
@@ -193,6 +196,114 @@ endmenu
 
 menu "Kernel Features"
 
+menu "ARM errata workarounds via the alternatives framework"
+
+config ARM64_ERRATUM_826319
+	bool "Cortex-A53: 826319: System might deadlock if a write cannot complete until read data is accepted"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 826319 on Cortex-A53 parts up to r0p2 with an AMBA 4 ACE or
+	  AXI master interface and an L2 cache.
+
+	  If a Cortex-A53 uses an AMBA AXI4 ACE interface to other processors
+	  and is unable to accept a certain write via this interface, it will
+	  not progress on read data presented on the read data channel and the
+	  system can deadlock.
+
+	  The workaround promotes data cache clean instructions to
+	  data cache clean-and-invalidate.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_827319
+	bool "Cortex-A53: 827319: Data cache clean instructions might cause overlapping transactions to the interconnect"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 827319 on Cortex-A53 parts up to r0p2 with an AMBA 5 CHI
+	  master interface and an L2 cache.
+
+	  Under certain conditions this erratum can cause a clean line eviction
+	  to occur at the same time as another transaction to the same address
+	  on the AMBA 5 CHI interface, which can cause data corruption if the
+	  interconnect reorders the two transactions.
+
+	  The workaround promotes data cache clean instructions to
+	  data cache clean-and-invalidate.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_824069
+	bool "Cortex-A53: 824069: Cache line might not be marked as clean after a CleanShared snoop"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 824069 on Cortex-A53 parts up to r0p2 when it is connected
+	  to a coherent interconnect.
+
+	  If a Cortex-A53 processor is executing a store or prefetch for
+	  write instruction at the same time as a processor in another
+	  cluster is executing a cache maintenance operation to the same
+	  address, then this erratum might cause a clean cache line to be
+	  incorrectly marked as dirty.
+
+	  The workaround promotes data cache clean instructions to
+	  data cache clean-and-invalidate.
+	  Please note that this option does not necessarily enable the
+	  workaround, as it depends on the alternative framework, which will
+	  only patch the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_819472
+	bool "Cortex-A53: 819472: Store exclusive instructions might cause data corruption"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 819472 on Cortex-A53 parts up to r0p1 with an L2 cache
+	  present when it is connected to a coherent interconnect.
+
+	  If the processor is executing a load and store exclusive sequence at
+	  the same time as a processor in another cluster is executing a cache
+	  maintenance operation to the same address, then this erratum might
+	  cause data corruption.
+
+	  The workaround promotes data cache clean instructions to
+	  data cache clean-and-invalidate.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_832075
+	bool "Cortex-A57: 832075: possible deadlock on mixing exclusive memory accesses with device loads"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 832075 on Cortex-A57 parts up to r1p2.
+
+	  Affected Cortex-A57 parts might deadlock when exclusive load/store
+	  instructions to Write-Back memory are mixed with Device loads.
+
+	  The workaround is to promote device loads to use Load-Acquire
+	  semantics.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+endmenu
+
+
 choice
 	prompt "Page size"
 	default ARM64_4K_PAGES
@@ -345,6 +456,19 @@ config ARCH_HAS_CACHE_LINE_SIZE
 
 source "mm/Kconfig"
 
+config SECCOMP
+	bool "Enable seccomp to safely compute untrusted bytecode"
+	---help---
+	  This kernel feature is useful for number crunching applications
+	  that may need to compute untrusted bytecode during their
+	  execution. By using pipes or other transports made available to
+	  the process as file descriptors supporting the read/write
+	  syscalls, it's possible to isolate those applications in
+	  their own address space using seccomp. Once seccomp is
+	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
+	  and the task is only allowed to execute a few safe syscalls
+	  defined by each seccomp mode.
+
 config XEN_DOM0
 	def_bool y
 	depends on XEN
@@ -361,6 +485,58 @@ config FORCE_MAX_ZONEORDER
 	default "14" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
 	default "11"
 
+menuconfig ARMV8_DEPRECATED
+	bool "Emulate deprecated/obsolete ARMv8 instructions"
+	depends on COMPAT
+	help
+	  Legacy software support may require certain instructions
+	  that have been deprecated or obsoleted in the architecture.
+
+	  Enable this config to enable selective emulation of these
+	  features.
+
+	  If unsure, say Y
+
+if ARMV8_DEPRECATED
+
+config SWP_EMULATION
+	bool "Emulate SWP/SWPB instructions"
+	help
+	  ARMv8 obsoletes the use of A32 SWP/SWPB instructions such that
+	  they are always undefined. Say Y here to enable software
+	  emulation of these instructions for userspace using LDXR/STXR.
+
+	  In some older versions of glibc [<=2.8] SWP is used during futex
+	  trylock() operations with the assumption that the code will not
+	  be preempted. This invalid assumption may be more likely to fail
+	  with SWP emulation enabled, leading to deadlock of the user
+	  application.
+
+	  NOTE: when accessing uncached shared regions, LDXR/STXR rely
+	  on an external transaction monitoring block called a global
+	  monitor to maintain update atomicity. If your system does not
+	  implement a global monitor, this option can cause programs that
+	  perform SWP operations to uncached memory to deadlock.
+
+	  If unsure, say Y
+
+config CP15_BARRIER_EMULATION
+	bool "Emulate CP15 Barrier instructions"
+	help
+	  The CP15 barrier instructions - CP15ISB, CP15DSB, and
+	  CP15DMB - are deprecated in ARMv8 (and ARMv7). It is
+	  strongly recommended to use the ISB, DSB, and DMB
+	  instructions instead.
+
+	  Say Y here to enable software emulation of these
+	  instructions for AArch32 userspace code. When this option is
+	  enabled, CP15 barrier usage is traced which can help
+	  identify software that needs updating.
+
+	  If unsure, say Y
+
+endif
+
 endmenu
 
 menu "Boot options"
@@ -401,6 +577,17 @@ config EFI
 	  allow the kernel to be booted as an EFI application. This
 	  is only useful on systems that have UEFI firmware.
 
+config DMI
+	bool "Enable support for SMBIOS (DMI) tables"
+	depends on EFI
+	default y
+	help
+	  This enables SMBIOS/DMI feature for systems.
+
+	  This option is only useful on systems that have UEFI firmware.
+	  However, even with this option, the resultant kernel should
+	  continue to boot on existing non-UEFI platforms.
+
 endmenu
 
 menu "Userspace binary formats"

arch/arm64/Kconfig.debug

@@ -6,6 +6,18 @@ config FRAME_POINTER
 	bool
 	default y
 
+config ARM64_PTDUMP
+	bool "Export kernel pagetable layout to userspace via debugfs"
+	depends on DEBUG_KERNEL
+	select DEBUG_FS
+        help
+	  Say Y here if you want to show the kernel pagetable layout in a
+	  debugfs file. This information is only useful for kernel developers
+	  who are working in architecture specific areas of the kernel.
+	  It is probably not a good idea to enable this feature in a production
+	  kernel.
+	  If in doubt, say "N"
+
 config STRICT_DEVMEM
 	bool "Filter access to /dev/mem"
 	depends on MMU

arch/arm64/crypto/Kconfig

@@ -27,20 +27,19 @@ config CRYPTO_AES_ARM64_CE
 	tristate "AES core cipher using ARMv8 Crypto Extensions"
 	depends on ARM64 && KERNEL_MODE_NEON
 	select CRYPTO_ALGAPI
-	select CRYPTO_AES
 
 config CRYPTO_AES_ARM64_CE_CCM
 	tristate "AES in CCM mode using ARMv8 Crypto Extensions"
 	depends on ARM64 && KERNEL_MODE_NEON
 	select CRYPTO_ALGAPI
-	select CRYPTO_AES
+	select CRYPTO_AES_ARM64_CE
 	select CRYPTO_AEAD
 
 config CRYPTO_AES_ARM64_CE_BLK
 	tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions"
 	depends on ARM64 && KERNEL_MODE_NEON
 	select CRYPTO_BLKCIPHER
-	select CRYPTO_AES
+	select CRYPTO_AES_ARM64_CE
 	select CRYPTO_ABLK_HELPER
 
 config CRYPTO_AES_ARM64_NEON_BLK

arch/arm64/crypto/aes-ce-ccm-glue.c

@@ -16,6 +16,8 @@
 #include <linux/crypto.h>
 #include <linux/module.h>
 
+#include "aes-ce-setkey.h"
+
 static int num_rounds(struct crypto_aes_ctx *ctx)
 {
 	/*
@@ -48,7 +50,7 @@ static int ccm_setkey(struct crypto_aead *tfm, const u8 *in_key,
 	struct crypto_aes_ctx *ctx = crypto_aead_ctx(tfm);
 	int ret;
 
-	ret = crypto_aes_expand_key(ctx, in_key, key_len);
+	ret = ce_aes_expandkey(ctx, in_key, key_len);
 	if (!ret)
 		return 0;
 

arch/arm64/crypto/aes-ce-cipher.c

@@ -14,6 +14,8 @@
 #include <linux/crypto.h>
 #include <linux/module.h>
 
+#include "aes-ce-setkey.h"
+
 MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
@@ -124,6 +126,114 @@ static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 	kernel_neon_end();
 }
 
+/*
+ * aes_sub() - use the aese instruction to perform the AES sbox substitution
+ *             on each byte in 'input'
+ */
+static u32 aes_sub(u32 input)
+{
+	u32 ret;
+
+	__asm__("dup	v1.4s, %w[in]		;"
+		"movi	v0.16b, #0		;"
+		"aese	v0.16b, v1.16b		;"
+		"umov	%w[out], v0.4s[0]	;"
+
+	:	[out]	"=r"(ret)
+	:	[in]	"r"(input)
+	:		"v0","v1");
+
+	return ret;
+}
+
+int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
+		     unsigned int key_len)
+{
+	/*
+	 * The AES key schedule round constants
+	 */
+	static u8 const rcon[] = {
+		0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36,
+	};
+
+	u32 kwords = key_len / sizeof(u32);
+	struct aes_block *key_enc, *key_dec;
+	int i, j;
+
+	if (key_len != AES_KEYSIZE_128 &&
+	    key_len != AES_KEYSIZE_192 &&
+	    key_len != AES_KEYSIZE_256)
+		return -EINVAL;
+
+	memcpy(ctx->key_enc, in_key, key_len);
+	ctx->key_length = key_len;
+
+	kernel_neon_begin_partial(2);
+	for (i = 0; i < sizeof(rcon); i++) {
+		u32 *rki = ctx->key_enc + (i * kwords);
+		u32 *rko = rki + kwords;
+
+		rko[0] = ror32(aes_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
+		rko[1] = rko[0] ^ rki[1];
+		rko[2] = rko[1] ^ rki[2];
+		rko[3] = rko[2] ^ rki[3];
+
+		if (key_len == AES_KEYSIZE_192) {
+			if (i >= 7)
+				break;
+			rko[4] = rko[3] ^ rki[4];
+			rko[5] = rko[4] ^ rki[5];
+		} else if (key_len == AES_KEYSIZE_256) {
+			if (i >= 6)
+				break;
+			rko[4] = aes_sub(rko[3]) ^ rki[4];
+			rko[5] = rko[4] ^ rki[5];
+			rko[6] = rko[5] ^ rki[6];
+			rko[7] = rko[6] ^ rki[7];
+		}
+	}
+
+	/*
+	 * Generate the decryption keys for the Equivalent Inverse Cipher.
+	 * This involves reversing the order of the round keys, and applying
+	 * the Inverse Mix Columns transformation on all but the first and
+	 * the last one.
+	 */
+	key_enc = (struct aes_block *)ctx->key_enc;
+	key_dec = (struct aes_block *)ctx->key_dec;
+	j = num_rounds(ctx);
+
+	key_dec[0] = key_enc[j];
+	for (i = 1, j--; j > 0; i++, j--)
+		__asm__("ld1	{v0.16b}, %[in]		;"
+			"aesimc	v1.16b, v0.16b		;"
+			"st1	{v1.16b}, %[out]	;"
+
+		:	[out]	"=Q"(key_dec[i])
+		:	[in]	"Q"(key_enc[j])
+		:		"v0","v1");
+	key_dec[i] = key_enc[0];
+
+	kernel_neon_end();
+	return 0;
+}
+EXPORT_SYMBOL(ce_aes_expandkey);
+
+int ce_aes_setkey(struct crypto_tfm *tfm, const u8 *in_key,
+		  unsigned int key_len)
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+
+	ret = ce_aes_expandkey(ctx, in_key, key_len);
+	if (!ret)
+		return 0;
+
+	tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+	return -EINVAL;
+}
+EXPORT_SYMBOL(ce_aes_setkey);
+
 static struct crypto_alg aes_alg = {
 	.cra_name		= "aes",
 	.cra_driver_name	= "aes-ce",
@@ -135,7 +245,7 @@ static struct crypto_alg aes_alg = {
 	.cra_cipher = {
 		.cia_min_keysize	= AES_MIN_KEY_SIZE,
 		.cia_max_keysize	= AES_MAX_KEY_SIZE,
-		.cia_setkey		= crypto_aes_set_key,
+		.cia_setkey		= ce_aes_setkey,
 		.cia_encrypt		= aes_cipher_encrypt,
 		.cia_decrypt		= aes_cipher_decrypt
 	}

arch/arm64/crypto/aes-ce-setkey.h

+
+int ce_aes_setkey(struct crypto_tfm *tfm, const u8 *in_key,
+		  unsigned int key_len);
+int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
+		     unsigned int key_len);

arch/arm64/crypto/aes-glue.c

@@ -16,9 +16,13 @@
 #include <linux/module.h>
 #include <linux/cpufeature.h>
 
+#include "aes-ce-setkey.h"
+
 #ifdef USE_V8_CRYPTO_EXTENSIONS
 #define MODE			"ce"
 #define PRIO			300
+#define aes_setkey		ce_aes_setkey
+#define aes_expandkey		ce_aes_expandkey
 #define aes_ecb_encrypt		ce_aes_ecb_encrypt
 #define aes_ecb_decrypt		ce_aes_ecb_decrypt
 #define aes_cbc_encrypt		ce_aes_cbc_encrypt
@@ -30,6 +34,8 @@ MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
 #else
 #define MODE			"neon"
 #define PRIO			200
+#define aes_setkey		crypto_aes_set_key
+#define aes_expandkey		crypto_aes_expand_key
 #define aes_ecb_encrypt		neon_aes_ecb_encrypt
 #define aes_ecb_decrypt		neon_aes_ecb_decrypt
 #define aes_cbc_encrypt		neon_aes_cbc_encrypt
@@ -79,10 +85,10 @@ static int xts_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 	struct crypto_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
 	int ret;
 
-	ret = crypto_aes_expand_key(&ctx->key1, in_key, key_len / 2);
+	ret = aes_expandkey(&ctx->key1, in_key, key_len / 2);
 	if (!ret)
-		ret = crypto_aes_expand_key(&ctx->key2, &in_key[key_len / 2],
-					    key_len / 2);
+		ret = aes_expandkey(&ctx->key2, &in_key[key_len / 2],
+				    key_len / 2);
 	if (!ret)
 		return 0;
 
@@ -288,7 +294,7 @@ static struct crypto_alg aes_algs[] = { {
 		.min_keysize	= AES_MIN_KEY_SIZE,
 		.max_keysize	= AES_MAX_KEY_SIZE,
 		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= crypto_aes_set_key,
+		.setkey		= aes_setkey,
 		.encrypt	= ecb_encrypt,
 		.decrypt	= ecb_decrypt,
 	},
@@ -306,7 +312,7 @@ static struct crypto_alg aes_algs[] = { {
 		.min_keysize	= AES_MIN_KEY_SIZE,
 		.max_keysize	= AES_MAX_KEY_SIZE,
 		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= crypto_aes_set_key,
+		.setkey		= aes_setkey,
 		.encrypt	= cbc_encrypt,
 		.decrypt	= cbc_decrypt,
 	},
@@ -324,7 +330,7 @@ static struct crypto_alg aes_algs[] = { {
 		.min_keysize	= AES_MIN_KEY_SIZE,
 		.max_keysize	= AES_MAX_KEY_SIZE,
 		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= crypto_aes_set_key,
+		.setkey		= aes_setkey,
 		.encrypt	= ctr_encrypt,
 		.decrypt	= ctr_encrypt,
 	},

arch/arm64/include/asm/alternative-asm.h

+#ifndef __ASM_ALTERNATIVE_ASM_H
+#define __ASM_ALTERNATIVE_ASM_H
+
+#ifdef __ASSEMBLY__
+
+.macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len
+	.word \orig_offset - .
+	.word \alt_offset - .
+	.hword \feature
+	.byte \orig_len
+	.byte \alt_len
+.endm
+
+.macro alternative_insn insn1 insn2 cap
+661:	\insn1
+662:	.pushsection .altinstructions, "a"
+	altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
+	.popsection
+	.pushsection .altinstr_replacement, "ax"
+663:	\insn2
+664:	.popsection
+	.if ((664b-663b) != (662b-661b))
+		.error "Alternatives instruction length mismatch"
+	.endif
+.endm
+
+#endif  /*  __ASSEMBLY__  */
+
+#endif /* __ASM_ALTERNATIVE_ASM_H */

arch/arm64/include/asm/alternative.h

+#ifndef __ASM_ALTERNATIVE_H
+#define __ASM_ALTERNATIVE_H
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/stringify.h>
+
+struct alt_instr {
+	s32 orig_offset;	/* offset to original instruction */
+	s32 alt_offset;		/* offset to replacement instruction */
+	u16 cpufeature;		/* cpufeature bit set for replacement */
+	u8  orig_len;		/* size of original instruction(s) */
+	u8  alt_len;		/* size of new instruction(s), <= orig_len */
+};
+
+void apply_alternatives_all(void);
+void apply_alternatives(void *start, size_t length);
+void free_alternatives_memory(void);
+
+#define ALTINSTR_ENTRY(feature)						      \
+	" .word 661b - .\n"				/* label           */ \
+	" .word 663f - .\n"				/* new instruction */ \
+	" .hword " __stringify(feature) "\n"		/* feature bit     */ \
+	" .byte 662b-661b\n"				/* source len      */ \
+	" .byte 664f-663f\n"				/* replacement len */
+
+/* alternative assembly primitive: */
+#define ALTERNATIVE(oldinstr, newinstr, feature)			\
+	"661:\n\t"							\
+	oldinstr "\n"							\
+	"662:\n"							\
+	".pushsection .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(feature)						\
+	".popsection\n"							\
+	".pushsection .altinstr_replacement, \"a\"\n"			\
+	"663:\n\t"							\
+	newinstr "\n"							\
+	"664:\n\t"							\
+	".popsection\n\t"						\
+	".if ((664b-663b) != (662b-661b))\n\t"				\
+	"	.error \"Alternatives instruction length mismatch\"\n\t"\
+	".endif\n"
+
+#endif /* __ASM_ALTERNATIVE_H */

arch/arm64/include/asm/cache.h

@@ -32,6 +32,8 @@
 
 #ifndef __ASSEMBLY__
 
+#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+
 static inline int cache_line_size(void)
 {
 	u32 cwg = cache_type_cwg();

arch/arm64/include/asm/cacheflush.h

@@ -73,7 +73,7 @@ extern void flush_cache_all(void);
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 extern void flush_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);
-extern void __flush_cache_user_range(unsigned long start, unsigned long end);
+extern long __flush_cache_user_range(unsigned long start, unsigned long end);
 
 static inline void flush_cache_mm(struct mm_struct *mm)
 {

arch/arm64/include/asm/cmpxchg.h

@@ -19,6 +19,7 @@
 #define __ASM_CMPXCHG_H
 
 #include <linux/bug.h>
+#include <linux/mmdebug.h>
 
 #include <asm/barrier.h>
 
@@ -152,6 +153,51 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 	return oldval;
 }
 
+#define system_has_cmpxchg_double()     1
+
+static inline int __cmpxchg_double(volatile void *ptr1, volatile void *ptr2,
+		unsigned long old1, unsigned long old2,
+		unsigned long new1, unsigned long new2, int size)
+{
+	unsigned long loop, lost;
+
+	switch (size) {
+	case 8:
+		VM_BUG_ON((unsigned long *)ptr2 - (unsigned long *)ptr1 != 1);
+		do {
+			asm volatile("// __cmpxchg_double8\n"
+			"	ldxp	%0, %1, %2\n"
+			"	eor	%0, %0, %3\n"
+			"	eor	%1, %1, %4\n"
+			"	orr	%1, %0, %1\n"
+			"	mov	%w0, #0\n"
+			"	cbnz	%1, 1f\n"
+			"	stxp	%w0, %5, %6, %2\n"
+			"1:\n"
+				: "=&r"(loop), "=&r"(lost), "+Q" (*(u64 *)ptr1)
+				: "r" (old1), "r"(old2), "r"(new1), "r"(new2));
+		} while (loop);
+		break;
+	default:
+		BUILD_BUG();
+	}
+
+	return !lost;
+}
+
+static inline int __cmpxchg_double_mb(volatile void *ptr1, volatile void *ptr2,
+			unsigned long old1, unsigned long old2,
+			unsigned long new1, unsigned long new2, int size)
+{
+	int ret;
+
+	smp_mb();
+	ret = __cmpxchg_double(ptr1, ptr2, old1, old2, new1, new2, size);
+	smp_mb();
+
+	return ret;
+}
+
 static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 					 unsigned long new, int size)
 {
@@ -182,6 +228,33 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 	__ret; \
 })
 
+#define cmpxchg_double(ptr1, ptr2, o1, o2, n1, n2) \
+({\
+	int __ret;\
+	__ret = __cmpxchg_double_mb((ptr1), (ptr2), (unsigned long)(o1), \
+			(unsigned long)(o2), (unsigned long)(n1), \
+			(unsigned long)(n2), sizeof(*(ptr1)));\
+	__ret; \
+})
+
+#define cmpxchg_double_local(ptr1, ptr2, o1, o2, n1, n2) \
+({\
+	int __ret;\
+	__ret = __cmpxchg_double((ptr1), (ptr2), (unsigned long)(o1), \
+			(unsigned long)(o2), (unsigned long)(n1), \
+			(unsigned long)(n2), sizeof(*(ptr1)));\
+	__ret; \
+})
+
+#define this_cpu_cmpxchg_1(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
+#define this_cpu_cmpxchg_2(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
+#define this_cpu_cmpxchg_4(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
+#define this_cpu_cmpxchg_8(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
+
+#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \
+	cmpxchg_double_local(raw_cpu_ptr(&(ptr1)), raw_cpu_ptr(&(ptr2)), \
+				o1, o2, n1, n2)
+
 #define cmpxchg64(ptr,o,n)		cmpxchg((ptr),(o),(n))
 #define cmpxchg64_local(ptr,o,n)	cmpxchg_local((ptr),(o),(n))
 

arch/arm64/include/asm/compat.h

@@ -205,6 +205,13 @@ typedef struct compat_siginfo {
 			compat_long_t _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
 			int _fd;
 		} _sigpoll;
+
+		/* SIGSYS */
+		struct {
+			compat_uptr_t _call_addr; /* calling user insn */
+			int _syscall;	/* triggering system call number */
+			compat_uint_t _arch;	/* AUDIT_ARCH_* of syscall */
+		} _sigsys;
 	} _sifields;
 } compat_siginfo_t;
 

arch/arm64/include/asm/cpu.h

@@ -30,6 +30,8 @@ struct cpuinfo_arm64 {
 	u32		reg_dczid;
 	u32		reg_midr;
 
+	u64		reg_id_aa64dfr0;
+	u64		reg_id_aa64dfr1;
 	u64		reg_id_aa64isar0;
 	u64		reg_id_aa64isar1;
 	u64		reg_id_aa64mmfr0;

arch/arm64/include/asm/cpufeature.h

@@ -21,9 +21,38 @@
 #define MAX_CPU_FEATURES	(8 * sizeof(elf_hwcap))
 #define cpu_feature(x)		ilog2(HWCAP_ ## x)
 
+#define ARM64_WORKAROUND_CLEAN_CACHE		0
+#define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE	1
+
+#define ARM64_NCAPS				2
+
+#ifndef __ASSEMBLY__
+
+extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
+
 static inline bool cpu_have_feature(unsigned int num)
 {
 	return elf_hwcap & (1UL << num);
 }
 
+static inline bool cpus_have_cap(unsigned int num)
+{
+	if (num >= ARM64_NCAPS)
+		return false;
+	return test_bit(num, cpu_hwcaps);
+}
+
+static inline void cpus_set_cap(unsigned int num)
+{
+	if (num >= ARM64_NCAPS)
+		pr_warn("Attempt to set an illegal CPU capability (%d >= %d)\n",
+			num, ARM64_NCAPS);
+	else
+		__set_bit(num, cpu_hwcaps);
+}
+
+void check_local_cpu_errata(void);
+
+#endif /* __ASSEMBLY__ */
+
 #endif

arch/arm64/include/asm/cputype.h

@@ -57,6 +57,11 @@
 #define MIDR_IMPLEMENTOR(midr)	\
 	(((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT)
 
+#define MIDR_CPU_PART(imp, partnum) \
+	(((imp)			<< MIDR_IMPLEMENTOR_SHIFT) | \
+	(0xf			<< MIDR_ARCHITECTURE_SHIFT) | \
+	((partnum)		<< MIDR_PARTNUM_SHIFT))
+
 #define ARM_CPU_IMP_ARM		0x41
 #define ARM_CPU_IMP_APM		0x50
 

arch/arm64/include/asm/dmi.h

+/*
+ * arch/arm64/include/asm/dmi.h
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ * Written by: Yi Li (yi.li@linaro.org)
+ *
+ * based on arch/ia64/include/asm/dmi.h
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#ifndef __ASM_DMI_H
+#define __ASM_DMI_H
+
+#include <linux/io.h>
+#include <linux/slab.h>
+
+/*
+ * According to section 2.3.6 of the UEFI spec, the firmware should not
+ * request a virtual mapping for configuration tables such as SMBIOS.
+ * This means we have to map them before use.
+ */
+#define dmi_early_remap(x, l)		ioremap_cache(x, l)
+#define dmi_early_unmap(x, l)		iounmap(x)
+#define dmi_remap(x, l)			ioremap_cache(x, l)
+#define dmi_unmap(x)			iounmap(x)
+#define dmi_alloc(l)			kzalloc(l, GFP_KERNEL)
+
+#endif

arch/arm64/include/asm/fixmap.h

@@ -31,6 +31,7 @@
  *
  */
 enum fixed_addresses {
+	FIX_HOLE,
 	FIX_EARLYCON_MEM_BASE,
 	__end_of_permanent_fixed_addresses,
 
@@ -56,10 +57,11 @@ enum fixed_addresses {
 
 #define FIXMAP_PAGE_IO     __pgprot(PROT_DEVICE_nGnRE)
 
-extern void __early_set_fixmap(enum fixed_addresses idx,
-			       phys_addr_t phys, pgprot_t flags);
+void __init early_fixmap_init(void);
 
-#define __set_fixmap __early_set_fixmap
+#define __early_set_fixmap __set_fixmap
+
+extern void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot);
 
 #include <asm-generic/fixmap.h>
 

arch/arm64/include/asm/hwcap.h

@@ -30,6 +30,7 @@
 #define COMPAT_HWCAP_IDIVA	(1 << 17)
 #define COMPAT_HWCAP_IDIVT	(1 << 18)
 #define COMPAT_HWCAP_IDIV	(COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT)
+#define COMPAT_HWCAP_LPAE	(1 << 20)
 #define COMPAT_HWCAP_EVTSTRM	(1 << 21)
 
 #define COMPAT_HWCAP2_AES	(1 << 0)