Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-aarch64

Pull ARM64 update from Catalin Marinas:
 "Main features:
   - Ticket-based spinlock implementation and lockless lockref support
   - Big endian support
   - CPU hotplug support, currently for PSCI (Power State Coordination
     Interface) capable firmware
   - Virtual address space extended to 42-bit in the 64K page
     configuration (maximum VA space with 2 levels of page tables)
   - Compat (AArch32) kuser helpers updated to ARMv8 (make use of
     load-acquire/store-release instructions)
   - Code cleanup, defconfig update and minor fixes"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-aarch64: (43 commits)
  ARM64: /proc/interrupts: display IPIs of online CPUs only
  arm64: locks: Remove CONFIG_GENERIC_LOCKBREAK
  arm64: KVM: vgic: byteswap GICv2 access on world switch if BE
  arm64: KVM: initialize HYP mode following the kernel endianness
  arm64: compat: Clear the IT state independent of the 32-bit ARM or Thumb-2 mode
  arm64: Use 42-bit address space with 64K pages
  arm64: module: ensure instruction is little-endian before manipulation
  arm64: defconfig: Enable CONFIG_PREEMPT by default
  arm64: fix access to preempt_count from assembly code
  arm64: move enabling of GIC before CPUs are set online
  arm64: use generic RW_DATA_SECTION macro in linker script
  arm64: Slightly improve the warning on CPU0 enable-method
  ARM64: simplify cpu_read_bootcpu_ops using OF/DT helper
  ARM64: DT: define ARM64 specific arch_match_cpu_phys_id
  arm64: allow ioremap_cache() to use existing RAM mappings
  arm64: update 32-bit kuser helpers to ARMv8
  arm64: perf: fix event number mask
  arm64: kconfig: allow CPU_BIG_ENDIAN to be selected
  arm64: Fix the endianness of arch_spinlock_t
  arm64: big-endian: write CPU holding pen address as LE
  ...

Documentation/arm64/booting.txt

@@ -115,9 +115,10 @@ Before jumping into the kernel, the following conditions must be met:
   External caches (if present) must be configured and disabled.
 
 - Architected timers
-  CNTFRQ must be programmed with the timer frequency.
-  If entering the kernel at EL1, CNTHCTL_EL2 must have EL1PCTEN (bit 0)
-  set where available.
+  CNTFRQ must be programmed with the timer frequency and CNTVOFF must
+  be programmed with a consistent value on all CPUs.  If entering the
+  kernel at EL1, CNTHCTL_EL2 must have EL1PCTEN (bit 0) set where
+  available.
 
 - Coherency
   All CPUs to be booted by the kernel must be part of the same coherency
@@ -130,30 +131,46 @@ Before jumping into the kernel, the following conditions must be met:
   the kernel image will be entered must be initialised by software at a
   higher exception level to prevent execution in an UNKNOWN state.
 
+The requirements described above for CPU mode, caches, MMUs, architected
+timers, coherency and system registers apply to all CPUs.  All CPUs must
+enter the kernel in the same exception level.
+
 The boot loader is expected to enter the kernel on each CPU in the
 following manner:
 
 - The primary CPU must jump directly to the first instruction of the
   kernel image.  The device tree blob passed by this CPU must contain
-  for each CPU node:
-
-    1. An 'enable-method' property. Currently, the only supported value
-       for this field is the string "spin-table".
-
-    2. A 'cpu-release-addr' property identifying a 64-bit,
-       zero-initialised memory location.
+  an 'enable-method' property for each cpu node.  The supported
+  enable-methods are described below.
 
   It is expected that the bootloader will generate these device tree
   properties and insert them into the blob prior to kernel entry.
 
-- Any secondary CPUs must spin outside of the kernel in a reserved area
-  of memory (communicated to the kernel by a /memreserve/ region in the
+- CPUs with a "spin-table" enable-method must have a 'cpu-release-addr'
+  property in their cpu node.  This property identifies a
+  naturally-aligned 64-bit zero-initalised memory location.
+
+  These CPUs should spin outside of the kernel in a reserved area of
+  memory (communicated to the kernel by a /memreserve/ region in the
   device tree) polling their cpu-release-addr location, which must be
   contained in the reserved region.  A wfe instruction may be inserted
   to reduce the overhead of the busy-loop and a sev will be issued by
   the primary CPU.  When a read of the location pointed to by the
-  cpu-release-addr returns a non-zero value, the CPU must jump directly
-  to this value.
+  cpu-release-addr returns a non-zero value, the CPU must jump to this
+  value.  The value will be written as a single 64-bit little-endian
+  value, so CPUs must convert the read value to their native endianness
+  before jumping to it.
+
+- CPUs with a "psci" enable method should remain outside of
+  the kernel (i.e. outside of the regions of memory described to the
+  kernel in the memory node, or in a reserved area of memory described
+  to the kernel by a /memreserve/ region in the device tree).  The
+  kernel will issue CPU_ON calls as described in ARM document number ARM
+  DEN 0022A ("Power State Coordination Interface System Software on ARM
+  processors") to bring CPUs into the kernel.
+
+  The device tree should contain a 'psci' node, as described in
+  Documentation/devicetree/bindings/arm/psci.txt.
 
 - Secondary CPU general-purpose register settings
   x0 = 0 (reserved for future use)

Documentation/arm64/memory.txt

@@ -21,7 +21,7 @@ The swapper_pgd_dir address is written to TTBR1 and never written to
 TTBR0.
 
 
-AArch64 Linux memory layout:
+AArch64 Linux memory layout with 4KB pages:
 
 Start			End			Size		Use
 -----------------------------------------------------------------------
@@ -39,13 +39,38 @@ ffffffbffbc00000	ffffffbffbdfffff	   2MB		earlyprintk device
 
 ffffffbffbe00000	ffffffbffbe0ffff	  64KB		PCI I/O space
 
-ffffffbbffff0000	ffffffbcffffffff	  ~2MB		[guard]
+ffffffbffbe10000	ffffffbcffffffff	  ~2MB		[guard]
 
 ffffffbffc000000	ffffffbfffffffff	  64MB		modules
 
 ffffffc000000000	ffffffffffffffff	 256GB		kernel logical memory map
 
 
+AArch64 Linux memory layout with 64KB pages:
+
+Start			End			Size		Use
+-----------------------------------------------------------------------
+0000000000000000	000003ffffffffff	   4TB		user
+
+fffffc0000000000	fffffdfbfffeffff	  ~2TB		vmalloc
+
+fffffdfbffff0000	fffffdfbffffffff	  64KB		[guard page]
+
+fffffdfc00000000	fffffdfdffffffff	   8GB		vmemmap
+
+fffffdfe00000000	fffffdfffbbfffff	  ~8GB		[guard, future vmmemap]
+
+fffffdfffbc00000	fffffdfffbdfffff	   2MB		earlyprintk device
+
+fffffdfffbe00000	fffffdfffbe0ffff	  64KB		PCI I/O space
+
+fffffdfffbe10000	fffffdfffbffffff	  ~2MB		[guard]
+
+fffffdfffc000000	fffffdffffffffff	  64MB		modules
+
+fffffe0000000000	ffffffffffffffff	   2TB		kernel logical memory map
+
+
 Translation table lookup with 4KB pages:
 
 +--------+--------+--------+--------+--------+--------+--------+--------+

arch/arm64/Kconfig

@@ -1,6 +1,7 @@
 config ARM64
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select ARCH_WANT_FRAME_POINTERS
@@ -61,10 +62,6 @@ config LOCKDEP_SUPPORT
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-config GENERIC_LOCKBREAK
-	def_bool y
-	depends on SMP && PREEMPT
-
 config RWSEM_GENERIC_SPINLOCK
 	def_bool y
 
@@ -138,6 +135,11 @@ config ARM64_64K_PAGES
 	  look-up. AArch32 emulation is not available when this feature
 	  is enabled.
 
+config CPU_BIG_ENDIAN
+       bool "Build big-endian kernel"
+       help
+         Say Y if you plan on running a kernel in big-endian mode.
+
 config SMP
 	bool "Symmetric Multi-Processing"
 	select USE_GENERIC_SMP_HELPERS
@@ -160,6 +162,13 @@ config NR_CPUS
 	default "8" if ARCH_XGENE
 	default "4"
 
+config HOTPLUG_CPU
+	bool "Support for hot-pluggable CPUs"
+	depends on SMP
+	help
+	  Say Y here to experiment with turning CPUs off and on.  CPUs
+	  can be controlled through /sys/devices/system/cpu.
+
 source kernel/Kconfig.preempt
 
 config HZ

arch/arm64/Makefile

@@ -20,9 +20,15 @@ LIBGCC 		:= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
 KBUILD_DEFCONFIG := defconfig
 
 KBUILD_CFLAGS	+= -mgeneral-regs-only
+ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
+KBUILD_CPPFLAGS	+= -mbig-endian
+AS		+= -EB
+LD		+= -EB
+else
 KBUILD_CPPFLAGS	+= -mlittle-endian
 AS		+= -EL
 LD		+= -EL
+endif
 
 comma = ,
 

arch/arm64/configs/defconfig

@@ -26,7 +26,7 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_ARCH_VEXPRESS=y
 CONFIG_ARCH_XGENE=y
 CONFIG_SMP=y
-CONFIG_PREEMPT_VOLUNTARY=y
+CONFIG_PREEMPT=y
 CONFIG_CMDLINE="console=ttyAMA0"
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_COMPAT=y

arch/arm64/include/asm/assembler.h

@@ -115,3 +115,34 @@ lr	.req	x30		// link register
 	.align	7
 	b	\label
 	.endm
+
+/*
+ * Select code when configured for BE.
+ */
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define CPU_BE(code...) code
+#else
+#define CPU_BE(code...)
+#endif
+
+/*
+ * Select code when configured for LE.
+ */
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define CPU_LE(code...)
+#else
+#define CPU_LE(code...) code
+#endif
+
+/*
+ * Define a macro that constructs a 64-bit value by concatenating two
+ * 32-bit registers. Note that on big endian systems the order of the
+ * registers is swapped.
+ */
+#ifndef CONFIG_CPU_BIG_ENDIAN
+	.macro	regs_to_64, rd, lbits, hbits
+#else
+	.macro	regs_to_64, rd, hbits, lbits
+#endif
+	orr	\rd, \lbits, \hbits, lsl #32
+	.endm

arch/arm64/include/asm/cmpxchg.h

@@ -173,4 +173,6 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 #define cmpxchg64(ptr,o,n)		cmpxchg((ptr),(o),(n))
 #define cmpxchg64_local(ptr,o,n)	cmpxchg_local((ptr),(o),(n))
 
+#define cmpxchg64_relaxed(ptr,o,n)	cmpxchg_local((ptr),(o),(n))
+
 #endif	/* __ASM_CMPXCHG_H */

arch/arm64/include/asm/compat.h

@@ -26,7 +26,11 @@
 #include <linux/ptrace.h>
 
 #define COMPAT_USER_HZ		100
+#ifdef __AARCH64EB__
+#define COMPAT_UTS_MACHINE	"armv8b\0\0"
+#else
 #define COMPAT_UTS_MACHINE	"armv8l\0\0"
+#endif
 
 typedef u32		compat_size_t;
 typedef s32		compat_ssize_t;
@@ -73,13 +77,23 @@ struct compat_timeval {
 };
 
 struct compat_stat {
+#ifdef __AARCH64EB__
+	short		st_dev;
+	short		__pad1;
+#else
 	compat_dev_t	st_dev;
+#endif
 	compat_ino_t	st_ino;
 	compat_mode_t	st_mode;
 	compat_ushort_t	st_nlink;
 	__compat_uid16_t	st_uid;
 	__compat_gid16_t	st_gid;
+#ifdef __AARCH64EB__
+	short		st_rdev;
+	short		__pad2;
+#else
 	compat_dev_t	st_rdev;
+#endif
 	compat_off_t	st_size;
 	compat_off_t	st_blksize;
 	compat_off_t	st_blocks;

arch/arm64/include/asm/cpu_ops.h

@@ -0,0 +1,59 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * 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/>.
+ */
+#ifndef __ASM_CPU_OPS_H
+#define __ASM_CPU_OPS_H
+
+#include <linux/init.h>
+#include <linux/threads.h>
+
+struct device_node;
+
+/**
+ * struct cpu_operations - Callback operations for hotplugging CPUs.
+ *
+ * @name:	Name of the property as appears in a devicetree cpu node's
+ *		enable-method property.
+ * @cpu_init:	Reads any data necessary for a specific enable-method from the
+ *		devicetree, for a given cpu node and proposed logical id.
+ * @cpu_prepare: Early one-time preparation step for a cpu. If there is a
+ *		mechanism for doing so, tests whether it is possible to boot
+ *		the given CPU.
+ * @cpu_boot:	Boots a cpu into the kernel.
+ * @cpu_postboot: Optionally, perform any post-boot cleanup or necesary
+ *		synchronisation. Called from the cpu being booted.
+ * @cpu_disable: Prepares a cpu to die. May fail for some mechanism-specific
+ * 		reason, which will cause the hot unplug to be aborted. Called
+ * 		from the cpu to be killed.
+ * @cpu_die:	Makes a cpu leave the kernel. Must not fail. Called from the
+ *		cpu being killed.
+ */
+struct cpu_operations {
+	const char	*name;
+	int		(*cpu_init)(struct device_node *, unsigned int);
+	int		(*cpu_prepare)(unsigned int);
+	int		(*cpu_boot)(unsigned int);
+	void		(*cpu_postboot)(void);
+#ifdef CONFIG_HOTPLUG_CPU
+	int		(*cpu_disable)(unsigned int cpu);
+	void		(*cpu_die)(unsigned int cpu);
+#endif
+};
+
+extern const struct cpu_operations *cpu_ops[NR_CPUS];
+extern int __init cpu_read_ops(struct device_node *dn, int cpu);
+extern void __init cpu_read_bootcpu_ops(void);
+
+#endif /* ifndef __ASM_CPU_OPS_H */

arch/arm64/include/asm/elf.h

@@ -90,11 +90,24 @@ typedef struct user_fpsimd_state elf_fpregset_t;
  * These are used to set parameters in the core dumps.
  */
 #define ELF_CLASS	ELFCLASS64
+#ifdef __AARCH64EB__
+#define ELF_DATA	ELFDATA2MSB
+#else
 #define ELF_DATA	ELFDATA2LSB
+#endif
 #define ELF_ARCH	EM_AARCH64
 
+/*
+ * This yields a string that ld.so will use to load implementation
+ * specific libraries for optimization.  This is more specific in
+ * intent than poking at uname or /proc/cpuinfo.
+ */
 #define ELF_PLATFORM_SIZE	16
+#ifdef __AARCH64EB__
+#define ELF_PLATFORM		("aarch64_be")
+#else
 #define ELF_PLATFORM		("aarch64")
+#endif
 
 /*
  * This is used to ensure we don't load something for the wrong architecture.
@@ -149,7 +162,12 @@ extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
 #ifdef CONFIG_COMPAT
+
+#ifdef __AARCH64EB__
+#define COMPAT_ELF_PLATFORM		("v8b")
+#else
 #define COMPAT_ELF_PLATFORM		("v8l")
+#endif
 
 #define COMPAT_ELF_ET_DYN_BASE		(randomize_et_dyn(2 * TASK_SIZE_32 / 3))
 

arch/arm64/include/asm/io.h

@@ -224,6 +224,7 @@ extern void __memset_io(volatile void __iomem *, int, size_t);
  */
 extern void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot);
 extern void __iounmap(volatile void __iomem *addr);
+extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 
 #define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_DIRTY)
 #define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
@@ -233,7 +234,6 @@ extern void __iounmap(volatile void __iomem *addr);
 #define ioremap(addr, size)		__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_nocache(addr, size)	__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_wc(addr, size)		__ioremap((addr), (size), __pgprot(PROT_NORMAL_NC))
-#define ioremap_cached(addr, size)	__ioremap((addr), (size), __pgprot(PROT_NORMAL))
 #define iounmap				__iounmap
 
 #define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF)

arch/arm64/include/asm/irq.h

@@ -4,6 +4,7 @@
 #include <asm-generic/irq.h>
 
 extern void (*handle_arch_irq)(struct pt_regs *);
+extern void migrate_irqs(void);
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 
 #endif

arch/arm64/include/asm/memory.h

@@ -33,18 +33,23 @@
 #define UL(x) _AC(x, UL)
 
 /*
- * PAGE_OFFSET - the virtual address of the start of the kernel image.
+ * PAGE_OFFSET - the virtual address of the start of the kernel image (top
+ *		 (VA_BITS - 1))
  * VA_BITS - the maximum number of bits for virtual addresses.
  * TASK_SIZE - the maximum size of a user space task.
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
  * The module space lives between the addresses given by TASK_SIZE
  * and PAGE_OFFSET - it must be within 128MB of the kernel text.
  */
-#define PAGE_OFFSET		UL(0xffffffc000000000)
+#ifdef CONFIG_ARM64_64K_PAGES
+#define VA_BITS			(42)
+#else
+#define VA_BITS			(39)
+#endif
+#define PAGE_OFFSET		(UL(0xffffffffffffffff) << (VA_BITS - 1))
 #define MODULES_END		(PAGE_OFFSET)
 #define MODULES_VADDR		(MODULES_END - SZ_64M)
 #define EARLYCON_IOBASE		(MODULES_VADDR - SZ_4M)
-#define VA_BITS			(39)
 #define TASK_SIZE_64		(UL(1) << VA_BITS)
 
 #ifdef CONFIG_COMPAT

arch/arm64/include/asm/pgtable-2level-hwdef.h

@@ -21,10 +21,10 @@
  * 8192 entries of 8 bytes each, occupying a 64KB page. Levels 0 and 1 are not
  * used. The 2nd level table (PGD for Linux) can cover a range of 4TB, each
  * entry representing 512MB. The user and kernel address spaces are limited to
- * 512GB and therefore we only use 1024 entries in the PGD.
+ * 4TB in the 64KB page configuration.
  */
 #define PTRS_PER_PTE		8192
-#define PTRS_PER_PGD		1024
+#define PTRS_PER_PGD		8192
 
 /*
  * PGDIR_SHIFT determines the size a top-level page table entry can map.

arch/arm64/include/asm/pgtable.h

@@ -33,7 +33,7 @@
 /*
  * VMALLOC and SPARSEMEM_VMEMMAP ranges.
  */
-#define VMALLOC_START		UL(0xffffff8000000000)
+#define VMALLOC_START		(UL(0xffffffffffffffff) << VA_BITS)
 #define VMALLOC_END		(PAGE_OFFSET - UL(0x400000000) - SZ_64K)
 
 #define vmemmap			((struct page *)(VMALLOC_END + SZ_64K))

arch/arm64/include/asm/processor.h

@@ -107,6 +107,11 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
 	regs->pstate = COMPAT_PSR_MODE_USR;
 	if (pc & 1)
 		regs->pstate |= COMPAT_PSR_T_BIT;
+
+#ifdef __AARCH64EB__
+	regs->pstate |= COMPAT_PSR_E_BIT;
+#endif
+
 	regs->compat_sp = sp;
 }
 #endif

arch/arm64/include/asm/psci.h

@@ -14,25 +14,6 @@
 #ifndef __ASM_PSCI_H
 #define __ASM_PSCI_H
 
-#define PSCI_POWER_STATE_TYPE_STANDBY		0
-#define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
-
-struct psci_power_state {
-	u16	id;
-	u8	type;
-	u8	affinity_level;
-};
-
-struct psci_operations {
-	int (*cpu_suspend)(struct psci_power_state state,
-			   unsigned long entry_point);
-	int (*cpu_off)(struct psci_power_state state);
-	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
-	int (*migrate)(unsigned long cpuid);
-};
-
-extern struct psci_operations psci_ops;
-
 int psci_init(void);
 
 #endif /* __ASM_PSCI_H */

arch/arm64/include/asm/ptrace.h

@@ -42,6 +42,7 @@
 #define COMPAT_PSR_MODE_UND	0x0000001b
 #define COMPAT_PSR_MODE_SYS	0x0000001f
 #define COMPAT_PSR_T_BIT	0x00000020
+#define COMPAT_PSR_E_BIT	0x00000200
 #define COMPAT_PSR_F_BIT	0x00000040
 #define COMPAT_PSR_I_BIT	0x00000080
 #define COMPAT_PSR_A_BIT	0x00000100

arch/arm64/include/asm/smp.h

@@ -60,21 +60,14 @@ struct secondary_data {
 	void *stack;
 };
 extern struct secondary_data secondary_data;
-extern void secondary_holding_pen(void);
-extern volatile unsigned long secondary_holding_pen_release;
+extern void secondary_entry(void);
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
-struct device_node;
+extern int __cpu_disable(void);
 
-struct smp_enable_ops {
-	const char	*name;
-	int		(*init_cpu)(struct device_node *, int);
-	int		(*prepare_cpu)(int);
-};
-
-extern const struct smp_enable_ops smp_spin_table_ops;
-extern const struct smp_enable_ops smp_psci_ops;
+extern void __cpu_die(unsigned int cpu);
+extern void cpu_die(void);
 
 #endif /* ifndef __ASM_SMP_H */

arch/arm64/include/asm/spinlock.h

@@ -22,17 +22,10 @@
 /*
  * Spinlock implementation.
  *
- * The old value is read exclusively and the new one, if unlocked, is written
- * exclusively. In case of failure, the loop is restarted.
- *
  * The memory barriers are implicit with the load-acquire and store-release
  * instructions.
- *
- * Unlocked value: 0
- * Locked value: 1
  */
 
-#define arch_spin_is_locked(x)		((x)->lock != 0)
 #define arch_spin_unlock_wait(lock) \
 	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
 
@@ -41,32 +34,51 @@
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned int tmp;
+	arch_spinlock_t lockval, newval;
 
 	asm volatile(
-	"	sevl\n"
-	"1:	wfe\n"
-	"2:	ldaxr	%w0, %1\n"
-	"	cbnz	%w0, 1b\n"
-	"	stxr	%w0, %w2, %1\n"
-	"	cbnz	%w0, 2b\n"
-	: "=&r" (tmp), "+Q" (lock->lock)
-	: "r" (1)
-	: "cc", "memory");
+	/* Atomically increment the next ticket. */
+"	prfm	pstl1strm, %3\n"
+"1:	ldaxr	%w0, %3\n"
+"	add	%w1, %w0, %w5\n"
+"	stxr	%w2, %w1, %3\n"
+"	cbnz	%w2, 1b\n"
+	/* Did we get the lock? */
+"	eor	%w1, %w0, %w0, ror #16\n"
+"	cbz	%w1, 3f\n"
+	/*
+	 * No: spin on the owner. Send a local event to avoid missing an
+	 * unlock before the exclusive load.
+	 */
+"	sevl\n"
+"2:	wfe\n"
+"	ldaxrh	%w2, %4\n"
+"	eor	%w1, %w2, %w0, lsr #16\n"
+"	cbnz	%w1, 2b\n"
+	/* We got the lock. Critical section starts here. */
+"3:"
+	: "=&r" (lockval), "=&r" (newval), "=&r" (tmp), "+Q" (*lock)
+	: "Q" (lock->owner), "I" (1 << TICKET_SHIFT)
+	: "memory");
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned int tmp;
+	arch_spinlock_t lockval;
 
 	asm volatile(
-	"2:	ldaxr	%w0, %1\n"
-	"	cbnz	%w0, 1f\n"
-	"	stxr	%w0, %w2, %1\n"
-	"	cbnz	%w0, 2b\n"
-	"1:\n"
-	: "=&r" (tmp), "+Q" (lock->lock)
-	: "r" (1)
-	: "cc", "memory");
+"	prfm	pstl1strm, %2\n"
+"1:	ldaxr	%w0, %2\n"
+"	eor	%w1, %w0, %w0, ror #16\n"
+"	cbnz	%w1, 2f\n"
+"	add	%w0, %w0, %3\n"
+"	stxr	%w1, %w0, %2\n"
+"	cbnz	%w1, 1b\n"
+"2:"
+	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
+	: "I" (1 << TICKET_SHIFT)
+	: "memory");
 
 	return !tmp;
 }
@@ -74,10 +86,29 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	asm volatile(
-	"	stlr	%w1, %0\n"
-	: "=Q" (lock->lock) : "r" (0) : "memory");
+"	stlrh	%w1, %0\n"
+	: "=Q" (lock->owner)
+	: "r" (lock->owner + 1)
+	: "memory");
 }
 
+static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+	return lock.owner == lock.next;
+}
+
+static inline int arch_spin_is_locked(arch_spinlock_t *lock)
+{
+	return !arch_spin_value_unlocked(ACCESS_ONCE(*lock));
+}
+
+static inline int arch_spin_is_contended(arch_spinlock_t *lock)
+{
+	arch_spinlock_t lockval = ACCESS_ONCE(*lock);
+	return (lockval.next - lockval.owner) > 1;
+}
+#define arch_spin_is_contended	arch_spin_is_contended
+
 /*
  * Write lock implementation.
  *