arm64 updates for 4.3:

- Support for new architectural features introduced in ARMv8.1:
   * Privileged Access Never (PAN) to catch user pointer dereferences in
     the kernel
   * Large System Extension (LSE) for building scalable atomics and locks
     (depends on locking/arch-atomic from tip, which is included here)
   * Hardware Dirty Bit Management (DBM) for updating clean PTEs
     automatically
 
 - Move our PSCI implementation out into drivers/firmware/, where it can
   be shared with arch/arm/. RMK has also pulled this component branch
   and has additional patches moving arch/arm/ over. MAINTAINERS is
   updated accordingly.
 
 - Better BUG implementation based on the BRK instruction for trapping
 
 - Leaf TLB invalidation for unmapping user pages
 
 - Support for PROBE_ONLY PCI configurations
 
 - Various cleanups and non-critical fixes, including:
   * Always flush FP/SIMD state over exec()
   * Restrict memblock additions based on range of linear mapping
   * Ensure *(LIST_POISON) generates a fatal fault
   * Context-tracking syscall return no longer corrupts return value when
     not forced on.
   * Alternatives patching synchronisation/stability improvements
   * Signed sub-word cmpxchg compare fix (tickled by HAVE_CMPXCHG_LOCAL)
   * Force SMP=y
   * Hide direct DCC access from userspace
   * Fix EFI stub memory allocation when DRAM starts at 0x0
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEcBAABAgAGBQJV5XXWAAoJELescNyEwWM0p4UIAIQwgoUnj01LvtImjMyG0NiY
 38GbAia7FsyIktSjuCaEhLsWjL8WSMscRsz6MLK01ir3iOoKdtXd/OptlsJTV5c5
 5POPAU6hvdfKj6MtsaOAOx4dz7bhM/HB9JSZmcbHqytOxIi4Tp1JoBrmM1mpNwmp
 VFy+GAOs5H6Lb/xUMm50pVUx+mjMXsH4Bo1c/0Y/gYsjhcvcRgE2iqnl7UExgDcW
 5sbhpsdw8zleDx+kzTmt5QoFWk/4l3d/F+0dzLCYfxzCLNYacksbQqEbGFVAsiIl
 aACK3Uqk7v7ZtFqqQLtNzE6Pfiw0CzajINPUyykoMCnDtMsyhYbxqezywCAPpSY=
 =8qHf
 -----END PGP SIGNATURE-----

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

Pull arm64 updates from Will Deacon:

 - Support for new architectural features introduced in ARMv8.1:
   * Privileged Access Never (PAN) to catch user pointer dereferences in
     the kernel
   * Large System Extension (LSE) for building scalable atomics and locks
     (depends on locking/arch-atomic from tip, which is included here)
   * Hardware Dirty Bit Management (DBM) for updating clean PTEs
     automatically

 - Move our PSCI implementation out into drivers/firmware/, where it can
   be shared with arch/arm/. RMK has also pulled this component branch
   and has additional patches moving arch/arm/ over. MAINTAINERS is
   updated accordingly.

 - Better BUG implementation based on the BRK instruction for trapping

 - Leaf TLB invalidation for unmapping user pages

 - Support for PROBE_ONLY PCI configurations

 - Various cleanups and non-critical fixes, including:
   * Always flush FP/SIMD state over exec()
   * Restrict memblock additions based on range of linear mapping
   * Ensure *(LIST_POISON) generates a fatal fault
   * Context-tracking syscall return no longer corrupts return value when
     not forced on.
   * Alternatives patching synchronisation/stability improvements
   * Signed sub-word cmpxchg compare fix (tickled by HAVE_CMPXCHG_LOCAL)
   * Force SMP=y
   * Hide direct DCC access from userspace
   * Fix EFI stub memory allocation when DRAM starts at 0x0

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (92 commits)
  arm64: flush FP/SIMD state correctly after execve()
  arm64: makefile: fix perf_callchain.o kconfig dependency
  arm64: set MAX_MEMBLOCK_ADDR according to linear region size
  of/fdt: make memblock maximum physical address arch configurable
  arm64: Fix source code file path in comments
  arm64: entry: always restore x0 from the stack on syscall return
  arm64: mdscr_el1: avoid exposing DCC to userspace
  arm64: kconfig: Move LIST_POISON to a safe value
  arm64: Add __exception_irq_entry definition for function graph
  arm64: mm: ensure patched kernel text is fetched from PoU
  arm64: alternatives: ensure secondary CPUs execute ISB after patching
  arm64: make ll/sc __cmpxchg_case_##name asm consistent
  arm64: dma-mapping: Simplify pgprot handling
  arm64: restore cpu suspend/resume functionality
  ARM64: PCI: do not enable resources on PROBE_ONLY systems
  arm64: cmpxchg: truncate sub-word signed types before comparison
  arm64: alternative: put secondary CPUs into polling loop during patch
  arm64/Documentation: clarify wording regarding memory below the Image
  arm64: lse: fix lse cmpxchg code indentation
  arm64: remove redundant object file list
  ...

Documentation/arm64/booting.txt

@@ -81,7 +81,7 @@ The decompressed kernel image contains a 64-byte header as follows:
   u64 res3	= 0;		/* reserved */
   u64 res4	= 0;		/* reserved */
   u32 magic	= 0x644d5241;	/* Magic number, little endian, "ARM\x64" */
-  u32 res5;      		/* reserved (used for PE COFF offset) */
+  u32 res5;			/* reserved (used for PE COFF offset) */
 
 
 Header notes:
@@ -103,7 +103,7 @@ Header notes:
 
 - The flags field (introduced in v3.17) is a little-endian 64-bit field
   composed as follows:
-  Bit 0: 	Kernel endianness.  1 if BE, 0 if LE.
+  Bit 0:	Kernel endianness.  1 if BE, 0 if LE.
   Bits 1-63:	Reserved.
 
 - When image_size is zero, a bootloader should attempt to keep as much
@@ -115,11 +115,14 @@ The Image must be placed text_offset bytes from a 2MB aligned base
 address near the start of usable system RAM and called there. Memory
 below that base address is currently unusable by Linux, and therefore it
 is strongly recommended that this location is the start of system RAM.
+The region between the 2 MB aligned base address and the start of the
+image has no special significance to the kernel, and may be used for
+other purposes.
 At least image_size bytes from the start of the image must be free for
 use by the kernel.
 
-Any memory described to the kernel (even that below the 2MB aligned base
+Any memory described to the kernel (even that below the start of the
-address) which is not marked as reserved from the kernel e.g. with a
+image) which is not marked as reserved from the kernel (e.g., with a
 memreserve region in the device tree) will be considered as available to
 the kernel.
 

arch/arm64/Kconfig

@@ -29,7 +29,7 @@ config ARM64
 	select EDAC_SUPPORT
 	select GENERIC_ALLOCATOR
 	select GENERIC_CLOCKEVENTS
-	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_CLOCKEVENTS_BROADCAST
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IRQ_PROBE
@@ -54,6 +54,7 @@ config ARM64
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_CC_STACKPROTECTOR
 	select HAVE_CMPXCHG_DOUBLE
+	select HAVE_CMPXCHG_LOCAL
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
@@ -105,6 +106,10 @@ config NO_IOPORT_MAP
 config STACKTRACE_SUPPORT
 	def_bool y
 
+config ILLEGAL_POINTER_VALUE
+	hex
+	default 0xdead000000000000
+
 config LOCKDEP_SUPPORT
 	def_bool y
 
@@ -114,6 +119,14 @@ config TRACE_IRQFLAGS_SUPPORT
 config RWSEM_XCHGADD_ALGORITHM
 	def_bool y
 
+config GENERIC_BUG
+	def_bool y
+	depends on BUG
+
+config GENERIC_BUG_RELATIVE_POINTERS
+	def_bool y
+	depends on GENERIC_BUG
+
 config GENERIC_HWEIGHT
 	def_bool y
 
@@ -138,6 +151,9 @@ config NEED_DMA_MAP_STATE
 config NEED_SG_DMA_LENGTH
 	def_bool y
 
+config SMP
+	def_bool y
+
 config SWIOTLB
 	def_bool y
 
@@ -372,22 +388,8 @@ config CPU_BIG_ENDIAN
        help
          Say Y if you plan on running a kernel in big-endian mode.
 
-config SMP
-	bool "Symmetric Multi-Processing"
-	help
-	  This enables support for systems with more than one CPU.  If
-	  you say N here, the kernel will run on single and
-	  multiprocessor machines, but will use only one CPU of a
-	  multiprocessor machine. If you say Y here, the kernel will run
-	  on many, but not all, single processor machines. On a single
-	  processor machine, the kernel will run faster if you say N
-	  here.
-
-	  If you don't know what to do here, say N.
-
 config SCHED_MC
 	bool "Multi-core scheduler support"
-	depends on SMP
 	help
 	  Multi-core scheduler support improves the CPU scheduler's decision
 	  making when dealing with multi-core CPU chips at a cost of slightly
@@ -395,7 +397,6 @@ config SCHED_MC
 
 config SCHED_SMT
 	bool "SMT scheduler support"
-	depends on SMP
 	help
 	  Improves the CPU scheduler's decision making when dealing with
 	  MultiThreading at a cost of slightly increased overhead in some
@@ -404,23 +405,17 @@ config SCHED_SMT
 config NR_CPUS
 	int "Maximum number of CPUs (2-4096)"
 	range 2 4096
-	depends on SMP
 	# These have to remain sorted largest to smallest
 	default "64"
 
 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 UP_LATE_INIT
-       def_bool y
-       depends on !SMP
-
 config HZ
 	int
 	default 100
@@ -562,6 +557,53 @@ config SETEND_EMULATION
 	  If unsure, say Y
 endif
 
+menu "ARMv8.1 architectural features"
+
+config ARM64_HW_AFDBM
+	bool "Support for hardware updates of the Access and Dirty page flags"
+	default y
+	help
+	  The ARMv8.1 architecture extensions introduce support for
+	  hardware updates of the access and dirty information in page
+	  table entries. When enabled in TCR_EL1 (HA and HD bits) on
+	  capable processors, accesses to pages with PTE_AF cleared will
+	  set this bit instead of raising an access flag fault.
+	  Similarly, writes to read-only pages with the DBM bit set will
+	  clear the read-only bit (AP[2]) instead of raising a
+	  permission fault.
+
+	  Kernels built with this configuration option enabled continue
+	  to work on pre-ARMv8.1 hardware and the performance impact is
+	  minimal. If unsure, say Y.
+
+config ARM64_PAN
+	bool "Enable support for Privileged Access Never (PAN)"
+	default y
+	help
+	 Privileged Access Never (PAN; part of the ARMv8.1 Extensions)
+	 prevents the kernel or hypervisor from accessing user-space (EL0)
+	 memory directly.
+
+	 Choosing this option will cause any unprotected (not using
+	 copy_to_user et al) memory access to fail with a permission fault.
+
+	 The feature is detected at runtime, and will remain as a 'nop'
+	 instruction if the cpu does not implement the feature.
+
+config ARM64_LSE_ATOMICS
+	bool "Atomic instructions"
+	help
+	  As part of the Large System Extensions, ARMv8.1 introduces new
+	  atomic instructions that are designed specifically to scale in
+	  very large systems.
+
+	  Say Y here to make use of these instructions for the in-kernel
+	  atomic routines. This incurs a small overhead on CPUs that do
+	  not support these instructions and requires the kernel to be
+	  built with binutils >= 2.25.
+
+endmenu
+
 endmenu
 
 menu "Boot options"

arch/arm64/Makefile

@@ -17,7 +17,18 @@ GZFLAGS		:=-9
 
 KBUILD_DEFCONFIG := defconfig
 
-KBUILD_CFLAGS	+= -mgeneral-regs-only
+# Check for binutils support for specific extensions
+lseinstr := $(call as-instr,.arch_extension lse,-DCONFIG_AS_LSE=1)
+
+ifeq ($(CONFIG_ARM64_LSE_ATOMICS), y)
+  ifeq ($(lseinstr),)
+$(warning LSE atomics not supported by binutils)
+  endif
+endif
+
+KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr)
+KBUILD_AFLAGS	+= $(lseinstr)
+
 ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 AS		+= -EB
@@ -58,7 +69,10 @@ all:	$(KBUILD_IMAGE) $(KBUILD_DTBS)
 
 boot := arch/arm64/boot
 
-Image Image.gz: vmlinux
+Image: vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+
+Image.%: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 zinstall install: vmlinux

arch/arm64/boot/Makefile

@@ -19,9 +19,21 @@ targets := Image Image.gz
 $(obj)/Image: vmlinux FORCE
 	$(call if_changed,objcopy)
 
+$(obj)/Image.bz2: $(obj)/Image FORCE
+	$(call if_changed,bzip2)
+
 $(obj)/Image.gz: $(obj)/Image FORCE
 	$(call if_changed,gzip)
 
+$(obj)/Image.lz4: $(obj)/Image FORCE
+	$(call if_changed,lz4)
+
+$(obj)/Image.lzma: $(obj)/Image FORCE
+	$(call if_changed,lzma)
+
+$(obj)/Image.lzo: $(obj)/Image FORCE
+	$(call if_changed,lzo)
+
 install: $(obj)/Image
 	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
 	$(obj)/Image System.map "$(INSTALL_PATH)"

arch/arm64/include/asm/alternative.h

@@ -3,6 +3,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/init.h>
+#include <linux/kconfig.h>
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/stringify.h>
@@ -15,7 +17,7 @@ struct alt_instr {
 	u8  alt_len;		/* size of new instruction(s), <= orig_len */
 };
 
-void apply_alternatives_all(void);
+void __init apply_alternatives_all(void);
 void apply_alternatives(void *start, size_t length);
 void free_alternatives_memory(void);
 
@@ -40,7 +42,8 @@ void free_alternatives_memory(void);
  * be fixed in a binutils release posterior to 2.25.51.0.2 (anything
  * containing commit 4e4d08cf7399b606 or c1baaddf8861).
  */
-#define ALTERNATIVE(oldinstr, newinstr, feature)			\
+#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled)	\
+	".if "__stringify(cfg_enabled)" == 1\n"				\
 	"661:\n\t"							\
 	oldinstr "\n"							\
 	"662:\n"							\
@@ -53,7 +56,11 @@ void free_alternatives_memory(void);
 	"664:\n\t"							\
 	".popsection\n\t"						\
 	".org	. - (664b-663b) + (662b-661b)\n\t"			\
-	".org	. - (662b-661b) + (664b-663b)\n"
+	".org	. - (662b-661b) + (664b-663b)\n"			\
+	".endif\n"
+
+#define _ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg, ...)	\
+	__ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg))
 
 #else
 
@@ -65,7 +72,8 @@ void free_alternatives_memory(void);
 	.byte \alt_len
 .endm
 
-.macro alternative_insn insn1 insn2 cap
+.macro alternative_insn insn1, insn2, cap, enable = 1
+	.if \enable
 661:	\insn1
 662:	.pushsection .altinstructions, "a"
 	altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
@@ -75,8 +83,70 @@ void free_alternatives_memory(void);
 664:	.popsection
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
+	.endif
 .endm
 
+/*
+ * Begin an alternative code sequence.
+ *
+ * The code that follows this macro will be assembled and linked as
+ * normal. There are no restrictions on this code.
+ */
+.macro alternative_if_not cap, enable = 1
+	.if \enable
+	.pushsection .altinstructions, "a"
+	altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f
+	.popsection
+661:
+	.endif
+.endm
+
+/*
+ * Provide the alternative code sequence.
+ *
+ * The code that follows this macro is assembled into a special
+ * section to be used for dynamic patching. Code that follows this
+ * macro must:
+ *
+ * 1. Be exactly the same length (in bytes) as the default code
+ *    sequence.
+ *
+ * 2. Not contain a branch target that is used outside of the
+ *    alternative sequence it is defined in (branches into an
+ *    alternative sequence are not fixed up).
+ */
+.macro alternative_else, enable = 1
+	.if \enable
+662:	.pushsection .altinstr_replacement, "ax"
+663:
+	.endif
+.endm
+
+/*
+ * Complete an alternative code sequence.
+ */
+.macro alternative_endif, enable = 1
+	.if \enable
+664:	.popsection
+	.org	. - (664b-663b) + (662b-661b)
+	.org	. - (662b-661b) + (664b-663b)
+	.endif
+.endm
+
+#define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...)	\
+	alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
+
+
 #endif  /*  __ASSEMBLY__  */
 
+/*
+ * Usage: asm(ALTERNATIVE(oldinstr, newinstr, feature));
+ *
+ * Usage: asm(ALTERNATIVE(oldinstr, newinstr, feature, CONFIG_FOO));
+ * N.B. If CONFIG_FOO is specified, but not selected, the whole block
+ *      will be omitted, including oldinstr.
+ */
+#define ALTERNATIVE(oldinstr, newinstr, ...)   \
+	_ALTERNATIVE_CFG(oldinstr, newinstr, __VA_ARGS__, 1)
+
 #endif /* __ASM_ALTERNATIVE_H */

arch/arm64/include/asm/assembler.h

@@ -49,18 +49,6 @@
 	msr	daifclr, #2
 	.endm
 
-/*
- * Save/disable and restore interrupts.
- */
-	.macro	save_and_disable_irqs, olddaif
-	mrs	\olddaif, daif
-	disable_irq
-	.endm
-
-	.macro	restore_irqs, olddaif
-	msr	daif, \olddaif
-	.endm
-
 /*
  * Enable and disable debug exceptions.
  */
@@ -103,9 +91,7 @@
  * SMP data memory barrier
  */
 	.macro	smp_dmb, opt
-#ifdef CONFIG_SMP
 	dmb	\opt
-#endif
 	.endm
 
 #define USER(l, x...)				\

arch/arm64/include/asm/atomic.h

@@ -24,247 +24,72 @@
 #include <linux/types.h>
 
 #include <asm/barrier.h>
-#include <asm/cmpxchg.h>
+#include <asm/lse.h>
-
-#define ATOMIC_INIT(i)	{ (i) }
 
 #ifdef __KERNEL__
 
-/*
+#define __ARM64_IN_ATOMIC_IMPL
- * On ARM, ordinary assignment (str instruction) doesn't clear the local
- * strex/ldrex monitor on some implementations. The reason we can use it for
- * atomic_set() is the clrex or dummy strex done on every exception return.
- */
-#define atomic_read(v)	ACCESS_ONCE((v)->counter)
-#define atomic_set(v,i)	(((v)->counter) = (i))
 
-/*
+#if defined(CONFIG_ARM64_LSE_ATOMICS) && defined(CONFIG_AS_LSE)
- * AArch64 UP and SMP safe atomic ops.  We use load exclusive and
+#include <asm/atomic_lse.h>
- * store exclusive to ensure that these are atomic.  We may loop
+#else
- * to ensure that the update happens.
+#include <asm/atomic_ll_sc.h>
- */
+#endif
 
-#define ATOMIC_OP(op, asm_op)						\
+#undef __ARM64_IN_ATOMIC_IMPL
-static inline void atomic_##op(int i, atomic_t *v)			\
+
-{									\
+#include <asm/cmpxchg.h>
-	unsigned long tmp;						\
+
-	int result;							\
+#define ___atomic_add_unless(v, a, u, sfx)				\
+({									\
+	typeof((v)->counter) c, old;					\
 									\
-	asm volatile("// atomic_" #op "\n"				\
+	c = atomic##sfx##_read(v);					\
-"1:	ldxr	%w0, %2\n"						\
+	while (c != (u) &&						\
-"	" #asm_op "	%w0, %w0, %w3\n"				\
+	      (old = atomic##sfx##_cmpxchg((v), c, c + (a))) != c)	\
-"	stxr	%w1, %w0, %2\n"						\
+		c = old;						\
-"	cbnz	%w1, 1b"						\
+	c;								\
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+ })
-	: "Ir" (i));							\
-}									\
 
-#define ATOMIC_OP_RETURN(op, asm_op)					\
+#define ATOMIC_INIT(i)	{ (i) }
-static inline int atomic_##op##_return(int i, atomic_t *v)		\
-{									\
-	unsigned long tmp;						\
-	int result;							\
-									\
-	asm volatile("// atomic_" #op "_return\n"			\
-"1:	ldxr	%w0, %2\n"						\
-"	" #asm_op "	%w0, %w0, %w3\n"				\
-"	stlxr	%w1, %w0, %2\n"						\
-"	cbnz	%w1, 1b"						\
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i)							\
-	: "memory");							\
-									\
-	smp_mb();							\
-	return result;							\
-}
 
-#define ATOMIC_OPS(op, asm_op)						\
+#define atomic_read(v)			READ_ONCE((v)->counter)
-	ATOMIC_OP(op, asm_op)						\
+#define atomic_set(v, i)		(((v)->counter) = (i))
-	ATOMIC_OP_RETURN(op, asm_op)
+#define atomic_xchg(v, new)		xchg(&((v)->counter), (new))
+#define atomic_cmpxchg(v, old, new)	cmpxchg(&((v)->counter), (old), (new))
 
-ATOMIC_OPS(add, add)
+#define atomic_inc(v)			atomic_add(1, (v))
-ATOMIC_OPS(sub, sub)
+#define atomic_dec(v)			atomic_sub(1, (v))
-
+#define atomic_inc_return(v)		atomic_add_return(1, (v))
-#define atomic_andnot atomic_andnot
+#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-
+#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-ATOMIC_OP(and, and)
+#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
-ATOMIC_OP(andnot, bic)
+#define atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
-ATOMIC_OP(or, orr)
+#define atomic_add_negative(i, v)	(atomic_add_return((i), (v)) < 0)
-ATOMIC_OP(xor, eor)
+#define __atomic_add_unless(v, a, u)	___atomic_add_unless(v, a, u,)
-
+#define atomic_andnot			atomic_andnot
-#undef ATOMIC_OPS
-#undef ATOMIC_OP_RETURN
-#undef ATOMIC_OP
-
-static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
-{
-	unsigned long tmp;
-	int oldval;
-
-	smp_mb();
-
-	asm volatile("// atomic_cmpxchg\n"
-"1:	ldxr	%w1, %2\n"
-"	cmp	%w1, %w3\n"
-"	b.ne	2f\n"
-"	stxr	%w0, %w4, %2\n"
-"	cbnz	%w0, 1b\n"
-"2:"
-	: "=&r" (tmp), "=&r" (oldval), "+Q" (ptr->counter)
-	: "Ir" (old), "r" (new)
-	: "cc");
-
-	smp_mb();
-	return oldval;
-}
-
-#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
-
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-
-	c = atomic_read(v);
-	while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c)
-		c = old;
-	return c;
-}
-
-#define atomic_inc(v)		atomic_add(1, v)
-#define atomic_dec(v)		atomic_sub(1, v)
-
-#define atomic_inc_and_test(v)	(atomic_add_return(1, v) == 0)
-#define atomic_dec_and_test(v)	(atomic_sub_return(1, v) == 0)
-#define atomic_inc_return(v)    (atomic_add_return(1, v))
-#define atomic_dec_return(v)    (atomic_sub_return(1, v))
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-
-#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
 
 /*
  * 64-bit atomic operations.
  */
-#define ATOMIC64_INIT(i) { (i) }
+#define ATOMIC64_INIT			ATOMIC_INIT
+#define atomic64_read			atomic_read
+#define atomic64_set			atomic_set
+#define atomic64_xchg			atomic_xchg
+#define atomic64_cmpxchg		atomic_cmpxchg
 
-#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
+#define atomic64_inc(v)			atomic64_add(1, (v))
-#define atomic64_set(v,i)	(((v)->counter) = (i))
+#define atomic64_dec(v)			atomic64_sub(1, (v))
-
+#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
-#define ATOMIC64_OP(op, asm_op)						\
+#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
-static inline void atomic64_##op(long i, atomic64_t *v)			\
-{									\
-	long result;							\
-	unsigned long tmp;						\
-									\
-	asm volatile("// atomic64_" #op "\n"				\
-"1:	ldxr	%0, %2\n"						\
-"	" #asm_op "	%0, %0, %3\n"					\
-"	stxr	%w1, %0, %2\n"						\
-"	cbnz	%w1, 1b"						\
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i));							\
-}									\
-
-#define ATOMIC64_OP_RETURN(op, asm_op)					\
-static inline long atomic64_##op##_return(long i, atomic64_t *v)	\
-{									\
-	long result;							\
-	unsigned long tmp;						\
-									\
-	asm volatile("// atomic64_" #op "_return\n"			\
-"1:	ldxr	%0, %2\n"						\
-"	" #asm_op "	%0, %0, %3\n"					\
-"	stlxr	%w1, %0, %2\n"						\
-"	cbnz	%w1, 1b"						\
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i)							\
-	: "memory");							\
-									\
-	smp_mb();							\
-	return result;							\
-}
-
-#define ATOMIC64_OPS(op, asm_op)					\
-	ATOMIC64_OP(op, asm_op)						\
-	ATOMIC64_OP_RETURN(op, asm_op)
-
-ATOMIC64_OPS(add, add)
-ATOMIC64_OPS(sub, sub)
-
-#define atomic64_andnot atomic64_andnot
-
-ATOMIC64_OP(and, and)
-ATOMIC64_OP(andnot, bic)
-ATOMIC64_OP(or, orr)
-ATOMIC64_OP(xor, eor)
-
-#undef ATOMIC64_OPS
-#undef ATOMIC64_OP_RETURN
-#undef ATOMIC64_OP
-
-static inline long atomic64_cmpxchg(atomic64_t *ptr, long old, long new)
-{
-	long oldval;
-	unsigned long res;
-
-	smp_mb();
-
-	asm volatile("// atomic64_cmpxchg\n"
-"1:	ldxr	%1, %2\n"
-"	cmp	%1, %3\n"
-"	b.ne	2f\n"
-"	stxr	%w0, %4, %2\n"
-"	cbnz	%w0, 1b\n"
-"2:"
-	: "=&r" (res), "=&r" (oldval), "+Q" (ptr->counter)
-	: "Ir" (old), "r" (new)
-	: "cc");
-
-	smp_mb();
-	return oldval;
-}
-
-#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
-
-static inline long atomic64_dec_if_positive(atomic64_t *v)
-{
-	long result;
-	unsigned long tmp;
-
-	asm volatile("// atomic64_dec_if_positive\n"
-"1:	ldxr	%0, %2\n"
-"	subs	%0, %0, #1\n"
-"	b.mi	2f\n"
-"	stlxr	%w1, %0, %2\n"
-"	cbnz	%w1, 1b\n"
-"	dmb	ish\n"
-"2:"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	:
-	: "cc", "memory");
-
-	return result;
-}
-
-static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-
-	c = atomic64_read(v);
-	while (c != u && (old = atomic64_cmpxchg((v), c, c + a)) != c)
-		c = old;
-
-	return c != u;
-}
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-#define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
 #define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
+#define atomic64_dec_and_test(v)	(atomic64_dec_return(v) == 0)
-#define atomic64_dec(v)			atomic64_sub(1LL, (v))
+#define atomic64_sub_and_test(i, v)	(atomic64_sub_return((i), (v)) == 0)
-#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
+#define atomic64_add_negative(i, v)	(atomic64_add_return((i), (v)) < 0)
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
+#define atomic64_add_unless(v, a, u)	(___atomic_add_unless(v, a, u, 64) != u)
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
+#define atomic64_andnot			atomic64_andnot
+
+#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 
 #endif
 #endif

arch/arm64/include/asm/atomic_ll_sc.h

@@ -0,0 +1,247 @@
+/*
+ * Based on arch/arm/include/asm/atomic.h
+ *
+ * Copyright (C) 1996 Russell King.
+ * Copyright (C) 2002 Deep Blue Solutions Ltd.
+ * Copyright (C) 2012 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_ATOMIC_LL_SC_H
+#define __ASM_ATOMIC_LL_SC_H
+
+#ifndef __ARM64_IN_ATOMIC_IMPL
+#error "please don't include this file directly"
+#endif
+
+/*
+ * AArch64 UP and SMP safe atomic ops.  We use load exclusive and
+ * store exclusive to ensure that these are atomic.  We may loop
+ * to ensure that the update happens.
+ *
+ * NOTE: these functions do *not* follow the PCS and must explicitly
+ * save any clobbered registers other than x0 (regardless of return
+ * value).  This is achieved through -fcall-saved-* compiler flags for
+ * this file, which unfortunately don't work on a per-function basis
+ * (the optimize attribute silently ignores these options).
+ */
+
+#define ATOMIC_OP(op, asm_op)						\
+__LL_SC_INLINE void							\
+__LL_SC_PREFIX(atomic_##op(int i, atomic_t *v))				\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	asm volatile("// atomic_" #op "\n"				\
+"	prfm	pstl1strm, %2\n"					\
+"1:	ldxr	%w0, %2\n"						\
+"	" #asm_op "	%w0, %w0, %w3\n"				\
+"	stxr	%w1, %w0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i));							\
+}									\
+__LL_SC_EXPORT(atomic_##op);
+
+#define ATOMIC_OP_RETURN(op, asm_op)					\
+__LL_SC_INLINE int							\
+__LL_SC_PREFIX(atomic_##op##_return(int i, atomic_t *v))		\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	asm volatile("// atomic_" #op "_return\n"			\
+"	prfm	pstl1strm, %2\n"					\
+"1:	ldxr	%w0, %2\n"						\
+"	" #asm_op "	%w0, %w0, %w3\n"				\
+"	stlxr	%w1, %w0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i)							\
+	: "memory");							\
+									\
+	smp_mb();							\
+	return result;							\
+}									\
+__LL_SC_EXPORT(atomic_##op##_return);
+
+#define ATOMIC_OPS(op, asm_op)						\
+	ATOMIC_OP(op, asm_op)						\
+	ATOMIC_OP_RETURN(op, asm_op)
+
+ATOMIC_OPS(add, add)
+ATOMIC_OPS(sub, sub)
+
+ATOMIC_OP(and, and)
+ATOMIC_OP(andnot, bic)
+ATOMIC_OP(or, orr)
+ATOMIC_OP(xor, eor)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
+#define ATOMIC64_OP(op, asm_op)						\
+__LL_SC_INLINE void							\
+__LL_SC_PREFIX(atomic64_##op(long i, atomic64_t *v))			\
+{									\
+	long result;							\
+	unsigned long tmp;						\
+									\
+	asm volatile("// atomic64_" #op "\n"				\
+"	prfm	pstl1strm, %2\n"					\
+"1:	ldxr	%0, %2\n"						\
+"	" #asm_op "	%0, %0, %3\n"					\
+"	stxr	%w1, %0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i));							\
+}									\
+__LL_SC_EXPORT(atomic64_##op);
+
+#define ATOMIC64_OP_RETURN(op, asm_op)					\
+__LL_SC_INLINE long							\
+__LL_SC_PREFIX(atomic64_##op##_return(long i, atomic64_t *v))		\
+{									\
+	long result;							\
+	unsigned long tmp;						\
+									\
+	asm volatile("// atomic64_" #op "_return\n"			\
+"	prfm	pstl1strm, %2\n"					\
+"1:	ldxr	%0, %2\n"						\
+"	" #asm_op "	%0, %0, %3\n"					\
+"	stlxr	%w1, %0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i)							\
+	: "memory");							\
+									\
+	smp_mb();							\
+	return result;							\
+}									\
+__LL_SC_EXPORT(atomic64_##op##_return);
+
+#define ATOMIC64_OPS(op, asm_op)					\
+	ATOMIC64_OP(op, asm_op)						\
+	ATOMIC64_OP_RETURN(op, asm_op)
+
+ATOMIC64_OPS(add, add)
+ATOMIC64_OPS(sub, sub)
+
+ATOMIC64_OP(and, and)
+ATOMIC64_OP(andnot, bic)
+ATOMIC64_OP(or, orr)
+ATOMIC64_OP(xor, eor)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
+
+__LL_SC_INLINE long
+__LL_SC_PREFIX(atomic64_dec_if_positive(atomic64_t *v))
+{
+	long result;
+	unsigned long tmp;
+
+	asm volatile("// atomic64_dec_if_positive\n"
+"	prfm	pstl1strm, %2\n"
+"1:	ldxr	%0, %2\n"
+"	subs	%0, %0, #1\n"
+"	b.lt	2f\n"
+"	stlxr	%w1, %0, %2\n"
+"	cbnz	%w1, 1b\n"
+"	dmb	ish\n"
+"2:"
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
+	:
+	: "cc", "memory");
+
+	return result;
+}
+__LL_SC_EXPORT(atomic64_dec_if_positive);
+
+#define __CMPXCHG_CASE(w, sz, name, mb, rel, cl)			\
+__LL_SC_INLINE unsigned long						\
+__LL_SC_PREFIX(__cmpxchg_case_##name(volatile void *ptr,		\
+				     unsigned long old,			\
+				     unsigned long new))		\
+{									\
+	unsigned long tmp, oldval;					\
+									\
+	asm volatile(							\
+	"	prfm	pstl1strm, %[v]\n"				\
+	"1:	ldxr" #sz "\t%" #w "[oldval], %[v]\n"			\
+	"	eor	%" #w "[tmp], %" #w "[oldval], %" #w "[old]\n"	\
+	"	cbnz	%" #w "[tmp], 2f\n"				\
+	"	st" #rel "xr" #sz "\t%w[tmp], %" #w "[new], %[v]\n"	\
+	"	cbnz	%w[tmp], 1b\n"					\
+	"	" #mb "\n"						\
+	"	mov	%" #w "[oldval], %" #w "[old]\n"		\
+	"2:"								\
+	: [tmp] "=&r" (tmp), [oldval] "=&r" (oldval),			\
+	  [v] "+Q" (*(unsigned long *)ptr)				\
+	: [old] "Lr" (old), [new] "r" (new)				\
+	: cl);								\
+									\
+	return oldval;							\
+}									\
+__LL_SC_EXPORT(__cmpxchg_case_##name);
+
+__CMPXCHG_CASE(w, b,    1,        ,  ,         )
+__CMPXCHG_CASE(w, h,    2,        ,  ,         )
+__CMPXCHG_CASE(w,  ,    4,        ,  ,         )
+__CMPXCHG_CASE( ,  ,    8,        ,  ,         )
+__CMPXCHG_CASE(w, b, mb_1, dmb ish, l, "memory")
+__CMPXCHG_CASE(w, h, mb_2, dmb ish, l, "memory")
+__CMPXCHG_CASE(w,  , mb_4, dmb ish, l, "memory")
+__CMPXCHG_CASE( ,  , mb_8, dmb ish, l, "memory")
+
+#undef __CMPXCHG_CASE
+
+#define __CMPXCHG_DBL(name, mb, rel, cl)				\
+__LL_SC_INLINE int							\
+__LL_SC_PREFIX(__cmpxchg_double##name(unsigned long old1,		\
+				      unsigned long old2,		\
+				      unsigned long new1,		\
+				      unsigned long new2,		\
+				      volatile void *ptr))		\
+{									\
+	unsigned long tmp, ret;						\
+									\
+	asm volatile("// __cmpxchg_double" #name "\n"			\
+	"	prfm	pstl1strm, %2\n"				\
+	"1:	ldxp	%0, %1, %2\n"					\
+	"	eor	%0, %0, %3\n"					\
+	"	eor	%1, %1, %4\n"					\
+	"	orr	%1, %0, %1\n"					\
+	"	cbnz	%1, 2f\n"					\
+	"	st" #rel "xp	%w0, %5, %6, %2\n"			\
+	"	cbnz	%w0, 1b\n"					\
+	"	" #mb "\n"						\
+	"2:"								\
+	: "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr)	\
+	: "r" (old1), "r" (old2), "r" (new1), "r" (new2)		\
+	: cl);								\
+									\
+	return ret;							\
+}									\
+__LL_SC_EXPORT(__cmpxchg_double##name);
+
+__CMPXCHG_DBL(   ,        ,  ,         )
+__CMPXCHG_DBL(_mb, dmb ish, l, "memory")
+
+#undef __CMPXCHG_DBL
+
+#endif	/* __ASM_ATOMIC_LL_SC_H */

arch/arm64/include/asm/atomic_lse.h

@@ -0,0 +1,391 @@
+/*
+ * Based on arch/arm/include/asm/atomic.h
+ *
+ * Copyright (C) 1996 Russell King.
+ * Copyright (C) 2002 Deep Blue Solutions Ltd.
+ * Copyright (C) 2012 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_ATOMIC_LSE_H
+#define __ASM_ATOMIC_LSE_H
+
+#ifndef __ARM64_IN_ATOMIC_IMPL
+#error "please don't include this file directly"
+#endif
+
+#define __LL_SC_ATOMIC(op)	__LL_SC_CALL(atomic_##op)
+
+static inline void atomic_andnot(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(andnot),
+	"	stclr	%w[i], %[v]\n")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic_or(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(or),
+	"	stset	%w[i], %[v]\n")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic_xor(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(xor),
+	"	steor	%w[i], %[v]\n")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic_add(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(add),
+	"	stadd	%w[i], %[v]\n")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC(add_return),
+	/* LSE atomics */
+	"	ldaddal	%w[i], w30, %[v]\n"
+	"	add	%w[i], %w[i], w30")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30", "memory");
+
+	return w0;
+}
+
+static inline void atomic_and(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC(and),
+	/* LSE atomics */
+	"	mvn	%w[i], %w[i]\n"
+	"	stclr	%w[i], %[v]")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC(sub),
+	/* LSE atomics */
+	"	neg	%w[i], %w[i]\n"
+	"	stadd	%w[i], %[v]")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC(sub_return)
+	"	nop",
+	/* LSE atomics */
+	"	neg	%w[i], %w[i]\n"
+	"	ldaddal	%w[i], w30, %[v]\n"
+	"	add	%w[i], %w[i], w30")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30", "memory");
+
+	return w0;
+}
+
+#undef __LL_SC_ATOMIC
+
+#define __LL_SC_ATOMIC64(op)	__LL_SC_CALL(atomic64_##op)
+
+static inline void atomic64_andnot(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(andnot),
+	"	stclr	%[i], %[v]\n")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic64_or(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(or),
+	"	stset	%[i], %[v]\n")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic64_xor(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(xor),
+	"	steor	%[i], %[v]\n")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic64_add(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(add),
+	"	stadd	%[i], %[v]\n")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline long atomic64_add_return(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC64(add_return),
+	/* LSE atomics */
+	"	ldaddal	%[i], x30, %[v]\n"
+	"	add	%[i], %[i], x30")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30", "memory");
+
+	return x0;
+}
+
+static inline void atomic64_and(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC64(and),
+	/* LSE atomics */
+	"	mvn	%[i], %[i]\n"
+	"	stclr	%[i], %[v]")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic64_sub(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC64(sub),
+	/* LSE atomics */
+	"	neg	%[i], %[i]\n"
+	"	stadd	%[i], %[v]")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline long atomic64_sub_return(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC64(sub_return)
+	"	nop",
+	/* LSE atomics */
+	"	neg	%[i], %[i]\n"
+	"	ldaddal	%[i], x30, %[v]\n"
+	"	add	%[i], %[i], x30")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30", "memory");
+
+	return x0;
+}
+
+static inline long atomic64_dec_if_positive(atomic64_t *v)
+{
+	register long x0 asm ("x0") = (long)v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC64(dec_if_positive)
+	"	nop\n"
+	"	nop\n"
+	"	nop\n"
+	"	nop\n"
+	"	nop",
+	/* LSE atomics */
+	"1:	ldr	x30, %[v]\n"
+	"	subs	%[ret], x30, #1\n"
+	"	b.lt	2f\n"
+	"	casal	x30, %[ret], %[v]\n"
+	"	sub	x30, x30, #1\n"
+	"	sub	x30, x30, %[ret]\n"
+	"	cbnz	x30, 1b\n"
+	"2:")
+	: [ret] "+&r" (x0), [v] "+Q" (v->counter)
+	:
+	: "x30", "cc", "memory");
+
+	return x0;
+}
+
+#undef __LL_SC_ATOMIC64
+
+#define __LL_SC_CMPXCHG(op)	__LL_SC_CALL(__cmpxchg_case_##op)
+
+#define __CMPXCHG_CASE(w, sz, name, mb, cl...)				\
+static inline unsigned long __cmpxchg_case_##name(volatile void *ptr,	\
+						  unsigned long old,	\
+						  unsigned long new)	\
+{									\
+	register unsigned long x0 asm ("x0") = (unsigned long)ptr;	\
+	register unsigned long x1 asm ("x1") = old;			\
+	register unsigned long x2 asm ("x2") = new;			\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+		__LL_SC_CMPXCHG(name)					\
+	"	nop",							\
+	/* LSE atomics */						\
+	"	mov	" #w "30, %" #w "[old]\n"			\
+	"	cas" #mb #sz "\t" #w "30, %" #w "[new], %[v]\n"		\
+	"	mov	%" #w "[ret], " #w "30")			\
+	: [ret] "+r" (x0), [v] "+Q" (*(unsigned long *)ptr)		\
+	: [old] "r" (x1), [new] "r" (x2)				\
+	: "x30" , ##cl);						\
+									\
+	return x0;							\
+}
+
+__CMPXCHG_CASE(w, b,    1,   )
+__CMPXCHG_CASE(w, h,    2,   )
+__CMPXCHG_CASE(w,  ,    4,   )
+__CMPXCHG_CASE(x,  ,    8,   )
+__CMPXCHG_CASE(w, b, mb_1, al, "memory")
+__CMPXCHG_CASE(w, h, mb_2, al, "memory")
+__CMPXCHG_CASE(w,  , mb_4, al, "memory")
+__CMPXCHG_CASE(x,  , mb_8, al, "memory")
+
+#undef __LL_SC_CMPXCHG
+#undef __CMPXCHG_CASE
+
+#define __LL_SC_CMPXCHG_DBL(op)	__LL_SC_CALL(__cmpxchg_double##op)
+
+#define __CMPXCHG_DBL(name, mb, cl...)					\
+static inline int __cmpxchg_double##name(unsigned long old1,		\
+					 unsigned long old2,		\
+					 unsigned long new1,		\
+					 unsigned long new2,		\
+					 volatile void *ptr)		\
+{									\
+	unsigned long oldval1 = old1;					\
+	unsigned long oldval2 = old2;					\
+	register unsigned long x0 asm ("x0") = old1;			\
+	register unsigned long x1 asm ("x1") = old2;			\
+	register unsigned long x2 asm ("x2") = new1;			\
+	register unsigned long x3 asm ("x3") = new2;			\
+	register unsigned long x4 asm ("x4") = (unsigned long)ptr;	\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+	"	nop\n"							\
+	"	nop\n"							\
+	__LL_SC_CMPXCHG_DBL(name),					\
+	/* LSE atomics */						\
+	"	casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\
+	"	eor	%[old1], %[old1], %[oldval1]\n"			\
+	"	eor	%[old2], %[old2], %[oldval2]\n"			\
+	"	orr	%[old1], %[old1], %[old2]")			\
+	: [old1] "+r" (x0), [old2] "+r" (x1),				\
+	  [v] "+Q" (*(unsigned long *)ptr)				\
+	: [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4),		\
+	  [oldval1] "r" (oldval1), [oldval2] "r" (oldval2)		\
+	: "x30" , ##cl);						\
+									\
+	return x0;							\
+}
+
+__CMPXCHG_DBL(   ,   )
+__CMPXCHG_DBL(_mb, al, "memory")
+
+#undef __LL_SC_CMPXCHG_DBL
+#undef __CMPXCHG_DBL
+
+#endif	/* __ASM_ATOMIC_LSE_H */

arch/arm64/include/asm/barrier.h

@@ -35,28 +35,6 @@
 #define dma_rmb()	dmb(oshld)
 #define dma_wmb()	dmb(oshst)
 
-#ifndef CONFIG_SMP
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-
-#define smp_store_release(p, v)						\
-do {									\
-	compiletime_assert_atomic_type(*p);				\
-	barrier();							\
-	WRITE_ONCE(*p, v);						\
-} while (0)
-
-#define smp_load_acquire(p)						\
-({									\
-	typeof(*p) ___p1 = READ_ONCE(*p);				\
-	compiletime_assert_atomic_type(*p);				\
-	barrier();							\
-	___p1;								\
-})
-
-#else
-
 #define smp_mb()	dmb(ish)
 #define smp_rmb()	dmb(ishld)
 #define smp_wmb()	dmb(ishst)
@@ -109,8 +87,6 @@ do {									\
 	___p1;								\
 })
 
-#endif
-
 #define read_barrier_depends()		do { } while(0)
 #define smp_read_barrier_depends()	do { } while(0)
 

arch/arm64/include/asm/bug.h

@@ -0,0 +1,64 @@
+/*
+ * Copyright (C) 2015  ARM Limited
+ * Author: Dave Martin <Dave.Martin@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/>.
+ */
+
+#ifndef _ARCH_ARM64_ASM_BUG_H
+#define _ARCH_ARM64_ASM_BUG_H
+
+#include <asm/debug-monitors.h>
+
+#ifdef CONFIG_GENERIC_BUG
+#define HAVE_ARCH_BUG
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define _BUGVERBOSE_LOCATION(file, line) __BUGVERBOSE_LOCATION(file, line)
+#define __BUGVERBOSE_LOCATION(file, line)				\
+		".pushsection .rodata.str,\"aMS\",@progbits,1\n"	\
+	"2:	.string \"" file "\"\n\t"				\
+		".popsection\n\t"					\
+									\
+		".long 2b - 0b\n\t"					\
+		".short " #line "\n\t"
+#else
+#define _BUGVERBOSE_LOCATION(file, line)
+#endif
+
+#define _BUG_FLAGS(flags) __BUG_FLAGS(flags)
+
+#define __BUG_FLAGS(flags) asm volatile (		\
+		".pushsection __bug_table,\"a\"\n\t"	\
+		".align 2\n\t"				\
+	"0:	.long 1f - 0b\n\t"			\
+_BUGVERBOSE_LOCATION(__FILE__, __LINE__)		\
+		".short " #flags "\n\t"			\
+		".popsection\n"				\
+							\
+	"1:	brk %[imm]"				\
+		:: [imm] "i" (BUG_BRK_IMM)		\
+)
+
+#define BUG() do {				\
+	_BUG_FLAGS(0);				\
+	unreachable();				\
+} while (0)
+
+#define __WARN_TAINT(taint) _BUG_FLAGS(BUGFLAG_TAINT(taint))
+
+#endif /* ! CONFIG_GENERIC_BUG */
+
+#include <asm-generic/bug.h>
+
+#endif /* ! _ARCH_ARM64_ASM_BUG_H */

arch/arm64/include/asm/cmpxchg.h

@@ -21,7 +21,9 @@
 #include <linux/bug.h>
 #include <linux/mmdebug.h>
 
+#include <asm/atomic.h>
 #include <asm/barrier.h>
+#include <asm/lse.h>
 
 static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
 {
@@ -29,37 +31,73 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 
 	switch (size) {
 	case 1:
-		asm volatile("//	__xchg1\n"
+		asm volatile(ARM64_LSE_ATOMIC_INSN(
+		/* LL/SC */
+		"	prfm	pstl1strm, %2\n"
 		"1:	ldxrb	%w0, %2\n"
 		"	stlxrb	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
+		"	dmb	ish",
+		/* LSE atomics */
+		"	nop\n"
+		"	nop\n"
+		"	swpalb	%w3, %w0, %2\n"
+		"	nop\n"
+		"	nop")
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr)
 			: "r" (x)
 			: "memory");
 		break;
 	case 2:
-		asm volatile("//	__xchg2\n"
+		asm volatile(ARM64_LSE_ATOMIC_INSN(
+		/* LL/SC */
+		"	prfm	pstl1strm, %2\n"
 		"1:	ldxrh	%w0, %2\n"
 		"	stlxrh	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
+		"	dmb	ish",
+		/* LSE atomics */
+		"	nop\n"
+		"	nop\n"
+		"	swpalh	%w3, %w0, %2\n"
+		"	nop\n"
+		"	nop")
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u16 *)ptr)
 			: "r" (x)
 			: "memory");
 		break;
 	case 4:
-		asm volatile("//	__xchg4\n"
+		asm volatile(ARM64_LSE_ATOMIC_INSN(
+		/* LL/SC */
+		"	prfm	pstl1strm, %2\n"
 		"1:	ldxr	%w0, %2\n"
 		"	stlxr	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
+		"	dmb	ish",
+		/* LSE atomics */
+		"	nop\n"
+		"	nop\n"
+		"	swpal	%w3, %w0, %2\n"
+		"	nop\n"
+		"	nop")
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u32 *)ptr)
 			: "r" (x)
 			: "memory");
 		break;
 	case 8:
-		asm volatile("//	__xchg8\n"
+		asm volatile(ARM64_LSE_ATOMIC_INSN(
+		/* LL/SC */
+		"	prfm	pstl1strm, %2\n"
 		"1:	ldxr	%0, %2\n"
 		"	stlxr	%w1, %3, %2\n"
 		"	cbnz	%w1, 1b\n"
+		"	dmb	ish",
+		/* LSE atomics */
+		"	nop\n"
+		"	nop\n"
+		"	swpal	%3, %0, %2\n"
+		"	nop\n"
+		"	nop")
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u64 *)ptr)
 			: "r" (x)
 			: "memory");
@@ -68,7 +106,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 		BUILD_BUG();
 	}
 
-	smp_mb();
 	return ret;
 }
 
@@ -83,131 +120,39 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 				      unsigned long new, int size)
 {
-	unsigned long oldval = 0, res;
-
 	switch (size) {
 	case 1:
-		do {
+		return __cmpxchg_case_1(ptr, (u8)old, new);
-			asm volatile("// __cmpxchg1\n"
-			"	ldxrb	%w1, %2\n"
-			"	mov	%w0, #0\n"
-			"	cmp	%w1, %w3\n"
-			"	b.ne	1f\n"
-			"	stxrb	%w0, %w4, %2\n"
-			"1:\n"
-				: "=&r" (res), "=&r" (oldval), "+Q" (*(u8 *)ptr)
-				: "Ir" (old), "r" (new)
-				: "cc");
-		} while (res);
-		break;
-
 	case 2:
-		do {
+		return __cmpxchg_case_2(ptr, (u16)old, new);
-			asm volatile("// __cmpxchg2\n"
-			"	ldxrh	%w1, %2\n"
-			"	mov	%w0, #0\n"
-			"	cmp	%w1, %w3\n"
-			"	b.ne	1f\n"
-			"	stxrh	%w0, %w4, %2\n"
-			"1:\n"
-				: "=&r" (res), "=&r" (oldval), "+Q" (*(u16 *)ptr)
-				: "Ir" (old), "r" (new)
-				: "cc");
-		} while (res);
-		break;
-
 	case 4:
-		do {
+		return __cmpxchg_case_4(ptr, old, new);
-			asm volatile("// __cmpxchg4\n"
-			"	ldxr	%w1, %2\n"
-			"	mov	%w0, #0\n"
-			"	cmp	%w1, %w3\n"
-			"	b.ne	1f\n"
-			"	stxr	%w0, %w4, %2\n"
-			"1:\n"
-				: "=&r" (res), "=&r" (oldval), "+Q" (*(u32 *)ptr)
-				: "Ir" (old), "r" (new)
-				: "cc");
-		} while (res);
-		break;
-
 	case 8:
-		do {
+		return __cmpxchg_case_8(ptr, old, new);
-			asm volatile("// __cmpxchg8\n"
-			"	ldxr	%1, %2\n"
-			"	mov	%w0, #0\n"
-			"	cmp	%1, %3\n"
-			"	b.ne	1f\n"
-			"	stxr	%w0, %4, %2\n"
-			"1:\n"
-				: "=&r" (res), "=&r" (oldval), "+Q" (*(u64 *)ptr)
-				: "Ir" (old), "r" (new)
-				: "cc");
-		} while (res);
-		break;
-
 	default:
 		BUILD_BUG();
 	}
 
-	return oldval;
+	unreachable();
-}
-
-#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)
 {
-	unsigned long ret;
+	switch (size) {
+	case 1:
+		return __cmpxchg_case_mb_1(ptr, (u8)old, new);
+	case 2:
+		return __cmpxchg_case_mb_2(ptr, (u16)old, new);
+	case 4:
+		return __cmpxchg_case_mb_4(ptr, old, new);
+	case 8:
+		return __cmpxchg_case_mb_8(ptr, old, new);
+	default:
+		BUILD_BUG();
+	}
 
-	smp_mb();
+	unreachable();
-	ret = __cmpxchg(ptr, old, new, size);
-	smp_mb();
-
-	return ret;
 }
 
 #define cmpxchg(ptr, o, n) \
@@ -228,21 +173,32 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 	__ret; \
 })
 
+#define system_has_cmpxchg_double()     1
+
+#define __cmpxchg_double_check(ptr1, ptr2)					\
+({										\
+	if (sizeof(*(ptr1)) != 8)						\
+		BUILD_BUG();							\
+	VM_BUG_ON((unsigned long *)(ptr2) - (unsigned long *)(ptr1) != 1);	\
+})
+
 #define cmpxchg_double(ptr1, ptr2, o1, o2, n1, n2) \
 ({\
 	int __ret;\
-	__ret = __cmpxchg_double_mb((ptr1), (ptr2), (unsigned long)(o1), \
+	__cmpxchg_double_check(ptr1, ptr2); \
-			(unsigned long)(o2), (unsigned long)(n1), \
+	__ret = !__cmpxchg_double_mb((unsigned long)(o1), (unsigned long)(o2), \
-			(unsigned long)(n2), sizeof(*(ptr1)));\
+				     (unsigned long)(n1), (unsigned long)(n2), \
+				     ptr1); \
 	__ret; \
 })
 
 #define cmpxchg_double_local(ptr1, ptr2, o1, o2, n1, n2) \
 ({\
 	int __ret;\
-	__ret = __cmpxchg_double((ptr1), (ptr2), (unsigned long)(o1), \
+	__cmpxchg_double_check(ptr1, ptr2); \
-			(unsigned long)(o2), (unsigned long)(n1), \
+	__ret = !__cmpxchg_double((unsigned long)(o1), (unsigned long)(o2), \
-			(unsigned long)(n2), sizeof(*(ptr1)));\
+				  (unsigned long)(n1), (unsigned long)(n2), \
+				  ptr1); \
 	__ret; \
 })
 

arch/arm64/include/asm/cpufeature.h

@@ -25,15 +25,20 @@
 #define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE	1
 #define ARM64_WORKAROUND_845719			2
 #define ARM64_HAS_SYSREG_GIC_CPUIF		3
+#define ARM64_HAS_PAN				4
+#define ARM64_HAS_LSE_ATOMICS			5
 
-#define ARM64_NCAPS				4
+#define ARM64_NCAPS				6
 
 #ifndef __ASSEMBLY__
 
+#include <linux/kernel.h>
+
 struct arm64_cpu_capabilities {
 	const char *desc;
 	u16 capability;
 	bool (*matches)(const struct arm64_cpu_capabilities *);
+	void (*enable)(void);
 	union {
 		struct {	/* To be used for erratum handling only */
 			u32 midr_model;
@@ -41,8 +46,8 @@ struct arm64_cpu_capabilities {
 		};
 
 		struct {	/* Feature register checking */
-			u64 register_mask;
+			int field_pos;
-			u64 register_value;
+			int min_field_value;
 		};
 	};
 };
@@ -70,6 +75,13 @@ static inline void cpus_set_cap(unsigned int num)
 		__set_bit(num, cpu_hwcaps);
 }
 
+static inline int __attribute_const__ cpuid_feature_extract_field(u64 features,
+								  int field)
+{
+	return (s64)(features << (64 - 4 - field)) >> (64 - 4);
+}
+
+
 void check_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 			    const char *info);
 void check_local_cpu_errata(void);

arch/arm64/include/asm/cputype.h

@@ -81,9 +81,6 @@
 #define ID_AA64MMFR0_BIGEND(mmfr0)	\
 	(((mmfr0) & ID_AA64MMFR0_BIGEND_MASK) >> ID_AA64MMFR0_BIGEND_SHIFT)
 
-#define SCTLR_EL1_CP15BEN	(0x1 << 5)
-#define SCTLR_EL1_SED		(0x1 << 8)
-
 #ifndef __ASSEMBLY__
 
 /*

arch/arm64/include/asm/debug-monitors.h

@@ -18,6 +18,12 @@
 
 #ifdef __KERNEL__
 
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <asm/esr.h>
+#include <asm/insn.h>
+#include <asm/ptrace.h>
+
 /* Low-level stepping controls. */
 #define DBG_MDSCR_SS		(1 << 0)
 #define DBG_SPSR_SS		(1 << 21)
@@ -38,12 +44,7 @@
 /*
  * Break point instruction encoding
  */
-#define BREAK_INSTR_SIZE		4
+#define BREAK_INSTR_SIZE		AARCH64_INSN_SIZE
-
-/*
- * ESR values expected for dynamic and compile time BRK instruction
- */
-#define DBG_ESR_VAL_BRK(x)	(0xf2000000 | ((x) & 0xfffff))
 
 /*
  * #imm16 values used for BRK instruction generation
@@ -51,10 +52,12 @@
  * 0x100: for triggering a fault on purpose (reserved)
  * 0x400: for dynamic BRK instruction
  * 0x401: for compile time BRK instruction
+ * 0x800: kernel-mode BUG() and WARN() traps
  */
 #define FAULT_BRK_IMM			0x100
 #define KGDB_DYN_DBG_BRK_IMM		0x400
 #define KGDB_COMPILED_DBG_BRK_IMM	0x401
+#define BUG_BRK_IMM			0x800
 
 /*
  * BRK instruction encoding
@@ -68,25 +71,10 @@
  */
 #define AARCH64_BREAK_FAULT	(AARCH64_BREAK_MON | (FAULT_BRK_IMM << 5))
 
-/*
+#define AARCH64_BREAK_KGDB_DYN_DBG	\
- * Extract byte from BRK instruction
+	(AARCH64_BREAK_MON | (KGDB_DYN_DBG_BRK_IMM << 5))
- */
+#define KGDB_DYN_BRK_INS_BYTE(x)	\
-#define KGDB_DYN_DBG_BRK_INS_BYTE(x) \
+	((AARCH64_BREAK_KGDB_DYN_DBG >> (8 * (x))) & 0xff)
-	((((AARCH64_BREAK_MON) & 0xffe0001f) >> (x * 8)) & 0xff)
-
-/*
- * Extract byte from BRK #imm16
- */
-#define KGBD_DYN_DBG_BRK_IMM_BYTE(x) \
-	(((((KGDB_DYN_DBG_BRK_IMM) & 0xffff) << 5) >> (x * 8)) & 0xff)
-
-#define KGDB_DYN_DBG_BRK_BYTE(x) \
-	(KGDB_DYN_DBG_BRK_INS_BYTE(x) | KGBD_DYN_DBG_BRK_IMM_BYTE(x))
-
-#define  KGDB_DYN_BRK_INS_BYTE0  KGDB_DYN_DBG_BRK_BYTE(0)
-#define  KGDB_DYN_BRK_INS_BYTE1  KGDB_DYN_DBG_BRK_BYTE(1)
-#define  KGDB_DYN_BRK_INS_BYTE2  KGDB_DYN_DBG_BRK_BYTE(2)
-#define  KGDB_DYN_BRK_INS_BYTE3  KGDB_DYN_DBG_BRK_BYTE(3)
 
 #define CACHE_FLUSH_IS_SAFE		1
 
@@ -127,13 +115,13 @@ void unregister_break_hook(struct break_hook *hook);
 
 u8 debug_monitors_arch(void);
 
-enum debug_el {
+enum dbg_active_el {
 	DBG_ACTIVE_EL0 = 0,
 	DBG_ACTIVE_EL1,
 };
 
-void enable_debug_monitors(enum debug_el el);
+void enable_debug_monitors(enum dbg_active_el el);
-void disable_debug_monitors(enum debug_el el);
+void disable_debug_monitors(enum dbg_active_el el);
 
 void user_rewind_single_step(struct task_struct *task);
 void user_fastforward_single_step(struct task_struct *task);

arch/arm64/include/asm/esr.h

@@ -18,6 +18,8 @@
 #ifndef __ASM_ESR_H
 #define __ASM_ESR_H
 
+#include <asm/memory.h>
+
 #define ESR_ELx_EC_UNKNOWN	(0x00)
 #define ESR_ELx_EC_WFx		(0x01)
 /* Unallocated EC: 0x02 */
@@ -99,6 +101,13 @@
 #define ESR_ELx_WFx_ISS_WFE	(UL(1) << 0)
 #define ESR_ELx_xVC_IMM_MASK	((1UL << 16) - 1)
 
+/* ESR value templates for specific events */
+
+/* BRK instruction trap from AArch64 state */
+#define ESR_ELx_VAL_BRK64(imm)					\
+	((ESR_ELx_EC_BRK64 << ESR_ELx_EC_SHIFT) | ESR_ELx_IL |	\
+	 ((imm) & 0xffff))
+
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
 

arch/arm64/include/asm/exception.h

@@ -18,7 +18,13 @@
 #ifndef __ASM_EXCEPTION_H
 #define __ASM_EXCEPTION_H
 
+#include <linux/ftrace.h>
+
 #define __exception	__attribute__((section(".exception.text")))
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#define __exception_irq_entry	__irq_entry
+#else
 #define __exception_irq_entry	__exception
+#endif
 
 #endif	/* __ASM_EXCEPTION_H */

arch/arm64/include/asm/fixmap.h

@@ -8,7 +8,7 @@
  * Copyright (C) 1998 Ingo Molnar
  * Copyright (C) 2013 Mark Salter <msalter@redhat.com>
  *
- * Adapted from arch/x86_64 version.
+ * Adapted from arch/x86 version.
  *
  */
 

arch/arm64/include/asm/futex.h

@@ -20,10 +20,17 @@
 
 #include <linux/futex.h>
 #include <linux/uaccess.h>
+
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
 #include <asm/errno.h>
+#include <asm/sysreg.h>
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
 	asm volatile(							\
+	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,		\
+		    CONFIG_ARM64_PAN)					\
+"	prfm	pstl1strm, %2\n"					\
 "1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
 "2:	stlxr	%w3, %w0, %2\n"						\
@@ -39,6 +46,8 @@
 "	.align	3\n"							\
 "	.quad	1b, 4b, 2b, 4b\n"					\
 "	.popsection\n"							\
+	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,		\
+		    CONFIG_ARM64_PAN)					\
 	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp)	\
 	: "r" (oparg), "Ir" (-EFAULT)					\
 	: "memory")
@@ -112,6 +121,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
+"	prfm	pstl1strm, %2\n"
 "1:	ldxr	%w1, %2\n"
 "	sub	%w3, %w1, %w4\n"
 "	cbnz	%w3, 3f\n"

arch/arm64/include/asm/hardirq.h

@@ -24,9 +24,7 @@
 
 typedef struct {
 	unsigned int __softirq_pending;
-#ifdef CONFIG_SMP
 	unsigned int ipi_irqs[NR_IPI];
-#endif
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
@@ -34,10 +32,8 @@ typedef struct {
 #define __inc_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)++
 #define __get_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)
 
-#ifdef CONFIG_SMP
 u64 smp_irq_stat_cpu(unsigned int cpu);
 #define arch_irq_stat_cpu	smp_irq_stat_cpu
-#endif
 
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
 

arch/arm64/include/asm/hugetlb.h

@@ -13,10 +13,6 @@
  * 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, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
 #ifndef __ASM_HUGETLB_H

arch/arm64/include/asm/irq_work.h

@@ -1,8 +1,6 @@
 #ifndef __ASM_IRQ_WORK_H
 #define __ASM_IRQ_WORK_H
 
-#ifdef CONFIG_SMP
-
 #include <asm/smp.h>
 
 static inline bool arch_irq_work_has_interrupt(void)
@@ -10,13 +8,4 @@ static inline bool arch_irq_work_has_interrupt(void)
 	return !!__smp_cross_call;
 }
 
-#else
-
-static inline bool arch_irq_work_has_interrupt(void)
-{
-	return false;
-}
-
-#endif
-
 #endif /* __ASM_IRQ_WORK_H */

arch/arm64/include/asm/lse.h

@@ -0,0 +1,53 @@
+#ifndef __ASM_LSE_H
+#define __ASM_LSE_H
+
+#if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS)
+
+#include <linux/stringify.h>
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
+
+#ifdef __ASSEMBLER__
+
+.arch_extension	lse
+
+.macro alt_lse, llsc, lse
+	alternative_insn "\llsc", "\lse", ARM64_HAS_LSE_ATOMICS
+.endm
+
+#else	/* __ASSEMBLER__ */
+
+__asm__(".arch_extension	lse");
+
+/* Move the ll/sc atomics out-of-line */
+#define __LL_SC_INLINE
+#define __LL_SC_PREFIX(x)	__ll_sc_##x
+#define __LL_SC_EXPORT(x)	EXPORT_SYMBOL(__LL_SC_PREFIX(x))
+
+/* Macro for constructing calls to out-of-line ll/sc atomics */
+#define __LL_SC_CALL(op)	"bl\t" __stringify(__LL_SC_PREFIX(op)) "\n"
+
+/* In-line patching at runtime */
+#define ARM64_LSE_ATOMIC_INSN(llsc, lse)				\
+	ALTERNATIVE(llsc, lse, ARM64_HAS_LSE_ATOMICS)
+
+#endif	/* __ASSEMBLER__ */
+#else	/* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
+
+#ifdef __ASSEMBLER__
+
+.macro alt_lse, llsc, lse
+	\llsc
+.endm
+
+#else	/* __ASSEMBLER__ */
+
+#define __LL_SC_INLINE		static inline
+#define __LL_SC_PREFIX(x)	x
+#define __LL_SC_EXPORT(x)
+
+#define ARM64_LSE_ATOMIC_INSN(llsc, lse)	llsc
+
+#endif	/* __ASSEMBLER__ */
+#endif	/* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
+#endif	/* __ASM_LSE_H */

arch/arm64/include/asm/memory.h

@@ -113,6 +113,14 @@ extern phys_addr_t		memstart_addr;
 /* PHYS_OFFSET - the physical address of the start of memory. */
 #define PHYS_OFFSET		({ memstart_addr; })
 
+/*
+ * The maximum physical address that the linear direct mapping
+ * of system RAM can cover. (PAGE_OFFSET can be interpreted as
+ * a 2's complement signed quantity and negated to derive the
+ * maximum size of the linear mapping.)
+ */
+#define MAX_MEMBLOCK_ADDR	({ memstart_addr - PAGE_OFFSET - 1; })
+
 /*
  * PFNs are used to describe any physical page; this means
  * PFN 0 == physical address 0.

arch/arm64/include/asm/mmu.h

@@ -28,7 +28,6 @@ typedef struct {
 #define ASID(mm)	((mm)->context.id & 0xffff)
 
 extern void paging_init(void);
-extern void setup_mm_for_reboot(void);
 extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
 extern void init_mem_pgprot(void);
 extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,

arch/arm64/include/asm/percpu.h

@@ -16,8 +16,6 @@
 #ifndef __ASM_PERCPU_H
 #define __ASM_PERCPU_H
 
-#ifdef CONFIG_SMP
-
 static inline void set_my_cpu_offset(unsigned long off)
 {
 	asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory");
@@ -38,12 +36,6 @@ static inline unsigned long __my_cpu_offset(void)
 }
 #define __my_cpu_offset __my_cpu_offset()
 
-#else	/* !CONFIG_SMP */
-
-#define set_my_cpu_offset(x)	do { } while (0)
-
-#endif /* CONFIG_SMP */
-
 #define PERCPU_OP(op, asm_op)						\
 static inline unsigned long __percpu_##op(void *ptr,			\
 			unsigned long val, int size)			\

arch/arm64/include/asm/perf_event.h

@@ -17,7 +17,7 @@
 #ifndef __ASM_PERF_EVENT_H
 #define __ASM_PERF_EVENT_H
 
-#ifdef CONFIG_HW_PERF_EVENTS
+#ifdef CONFIG_PERF_EVENTS
 struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);

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

@@ -104,6 +104,7 @@
 #define PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
 #define PTE_AF			(_AT(pteval_t, 1) << 10)	/* Access Flag */
 #define PTE_NG			(_AT(pteval_t, 1) << 11)	/* nG */
+#define PTE_DBM			(_AT(pteval_t, 1) << 51)	/* Dirty Bit Management */
 #define PTE_PXN			(_AT(pteval_t, 1) << 53)	/* Privileged XN */
 #define PTE_UXN			(_AT(pteval_t, 1) << 54)	/* User XN */
 
@@ -168,5 +169,7 @@
 #define TCR_TG1_64K		(UL(3) << 30)
 #define TCR_ASID16		(UL(1) << 36)
 #define TCR_TBI0		(UL(1) << 37)
+#define TCR_HA			(UL(1) << 39)
+#define TCR_HD			(UL(1) << 40)
 
 #endif

arch/arm64/include/asm/pgtable.h

@@ -16,6 +16,7 @@
 #ifndef __ASM_PGTABLE_H
 #define __ASM_PGTABLE_H
 
+#include <asm/bug.h>
 #include <asm/proc-fns.h>
 
 #include <asm/memory.h>
@@ -27,7 +28,11 @@
 #define PTE_VALID		(_AT(pteval_t, 1) << 0)
 #define PTE_DIRTY		(_AT(pteval_t, 1) << 55)
 #define PTE_SPECIAL		(_AT(pteval_t, 1) << 56)
+#ifdef CONFIG_ARM64_HW_AFDBM
+#define PTE_WRITE		(PTE_DBM)		 /* same as DBM */
+#else
 #define PTE_WRITE		(_AT(pteval_t, 1) << 57)
+#endif
 #define PTE_PROT_NONE		(_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */
 
 /*
@@ -48,18 +53,16 @@
 #define FIRST_USER_ADDRESS	0UL
 
 #ifndef __ASSEMBLY__
+
+#include <linux/mmdebug.h>
+
 extern void __pte_error(const char *file, int line, unsigned long val);
 extern void __pmd_error(const char *file, int line, unsigned long val);
 extern void __pud_error(const char *file, int line, unsigned long val);
 extern void __pgd_error(const char *file, int line, unsigned long val);
 
-#ifdef CONFIG_SMP
 #define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
 #define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
-#else
-#define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF)
-#define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF)
-#endif
 
 #define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
 #define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC))
@@ -137,12 +140,20 @@ extern struct page *empty_zero_page;
  * The following only work if pte_present(). Undefined behaviour otherwise.
  */
 #define pte_present(pte)	(!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)))
-#define pte_dirty(pte)		(!!(pte_val(pte) & PTE_DIRTY))
 #define pte_young(pte)		(!!(pte_val(pte) & PTE_AF))
 #define pte_special(pte)	(!!(pte_val(pte) & PTE_SPECIAL))
 #define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
 #define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
 
+#ifdef CONFIG_ARM64_HW_AFDBM
+#define pte_hw_dirty(pte)	(!(pte_val(pte) & PTE_RDONLY))
+#else
+#define pte_hw_dirty(pte)	(0)
+#endif
+#define pte_sw_dirty(pte)	(!!(pte_val(pte) & PTE_DIRTY))
+#define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
+
+#define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
 #define pte_valid_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
 #define pte_valid_not_user(pte) \
@@ -209,20 +220,49 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 	}
 }
 
+struct mm_struct;
+struct vm_area_struct;
+
 extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
 
+/*
+ * PTE bits configuration in the presence of hardware Dirty Bit Management
+ * (PTE_WRITE == PTE_DBM):
+ *
+ * Dirty  Writable | PTE_RDONLY  PTE_WRITE  PTE_DIRTY (sw)
+ *   0      0      |   1           0          0
+ *   0      1      |   1           1          0
+ *   1      0      |   1           0          1
+ *   1      1      |   0           1          x
+ *
+ * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via
+ * the page fault mechanism. Checking the dirty status of a pte becomes:
+ *
+ *   PTE_DIRTY || !PTE_RDONLY
+ */
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
 {
 	if (pte_valid_user(pte)) {
 		if (!pte_special(pte) && pte_exec(pte))
 			__sync_icache_dcache(pte, addr);
-		if (pte_dirty(pte) && pte_write(pte))
+		if (pte_sw_dirty(pte) && pte_write(pte))
 			pte_val(pte) &= ~PTE_RDONLY;
 		else
 			pte_val(pte) |= PTE_RDONLY;
 	}
 
+	/*
+	 * If the existing pte is valid, check for potential race with
+	 * hardware updates of the pte (ptep_set_access_flags safely changes
+	 * valid ptes without going through an invalid entry).
+	 */
+	if (IS_ENABLED(CONFIG_DEBUG_VM) && IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
+	    pte_valid(*ptep)) {
+		BUG_ON(!pte_young(pte));
+		BUG_ON(pte_write(*ptep) && !pte_dirty(pte));
+	}
+
 	set_pte(ptep, pte);
 }
 
@@ -461,6 +501,9 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
 			      PTE_PROT_NONE | PTE_WRITE | PTE_TYPE_MASK;
+	/* preserve the hardware dirty information */
+	if (pte_hw_dirty(pte))
+		newprot |= PTE_DIRTY;
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
 	return pte;
 }
@@ -470,6 +513,101 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 	return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
 }
 
+#ifdef CONFIG_ARM64_HW_AFDBM
+/*
+ * Atomic pte/pmd modifications.
+ */
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+					    unsigned long address,
+					    pte_t *ptep)
+{
+	pteval_t pteval;
+	unsigned int tmp, res;
+
+	asm volatile("//	ptep_test_and_clear_young\n"
+	"	prfm	pstl1strm, %2\n"
+	"1:	ldxr	%0, %2\n"
+	"	ubfx	%w3, %w0, %5, #1	// extract PTE_AF (young)\n"
+	"	and	%0, %0, %4		// clear PTE_AF\n"
+	"	stxr	%w1, %0, %2\n"
+	"	cbnz	%w1, 1b\n"
+	: "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)), "=&r" (res)
+	: "L" (~PTE_AF), "I" (ilog2(PTE_AF)));
+
+	return res;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+					    unsigned long address,
+					    pmd_t *pmdp)
+{
+	return ptep_test_and_clear_young(vma, address, (pte_t *)pmdp);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
+				       unsigned long address, pte_t *ptep)
+{
+	pteval_t old_pteval;
+	unsigned int tmp;
+
+	asm volatile("//	ptep_get_and_clear\n"
+	"	prfm	pstl1strm, %2\n"
+	"1:	ldxr	%0, %2\n"
+	"	stxr	%w1, xzr, %2\n"
+	"	cbnz	%w1, 1b\n"
+	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)));
+
+	return __pte(old_pteval);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
+static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
+				       unsigned long address, pmd_t *pmdp)
+{
+	return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp));
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+/*
+ * ptep_set_wrprotect - mark read-only while trasferring potential hardware
+ * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit.
+ */
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
+{
+	pteval_t pteval;
+	unsigned long tmp;
+
+	asm volatile("//	ptep_set_wrprotect\n"
+	"	prfm	pstl1strm, %2\n"
+	"1:	ldxr	%0, %2\n"
+	"	tst	%0, %4			// check for hw dirty (!PTE_RDONLY)\n"
+	"	csel	%1, %3, xzr, eq		// set PTE_DIRTY|PTE_RDONLY if dirty\n"
+	"	orr	%0, %0, %1		// if !dirty, PTE_RDONLY is already set\n"
+	"	and	%0, %0, %5		// clear PTE_WRITE/PTE_DBM\n"
+	"	stxr	%w1, %0, %2\n"
+	"	cbnz	%w1, 1b\n"
+	: "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
+	: "r" (PTE_DIRTY|PTE_RDONLY), "L" (PTE_RDONLY), "L" (~PTE_WRITE)
+	: "cc");
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_SET_WRPROTECT
+static inline void pmdp_set_wrprotect(struct mm_struct *mm,
+				      unsigned long address, pmd_t *pmdp)
+{
+	ptep_set_wrprotect(mm, address, (pte_t *)pmdp);
+}
+#endif
+#endif	/* CONFIG_ARM64_HW_AFDBM */
+
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
 
@@ -505,6 +643,21 @@ extern int kern_addr_valid(unsigned long addr);
 
 #define pgtable_cache_init() do { } while (0)
 
+/*
+ * On AArch64, the cache coherency is handled via the set_pte_at() function.
+ */
+static inline void update_mmu_cache(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep)
+{
+	/*
+	 * set_pte() does not have a DSB for user mappings, so make sure that
+	 * the page table write is visible.
+	 */
+	dsb(ishst);
+}
+
+#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_PGTABLE_H */

arch/arm64/include/asm/processor.h

@@ -186,4 +186,6 @@ static inline void spin_lock_prefetch(const void *x)
 
 #endif
 
+void cpu_enable_pan(void);
+
 #endif /* __ASM_PROCESSOR_H */

arch/arm64/include/asm/ptrace.h

@@ -183,11 +183,7 @@ static inline int valid_user_regs(struct user_pt_regs *regs)
 
 #define instruction_pointer(regs)	((unsigned long)(regs)->pc)
 
-#ifdef CONFIG_SMP
 extern unsigned long profile_pc(struct pt_regs *regs);
-#else
-#define profile_pc(regs) instruction_pointer(regs)
-#endif
 
 #endif /* __ASSEMBLY__ */
 #endif

arch/arm64/include/asm/smp.h

@@ -20,10 +20,6 @@
 #include <linux/cpumask.h>
 #include <linux/thread_info.h>
 
-#ifndef CONFIG_SMP
-# error "<asm/smp.h> included in non-SMP build"
-#endif
-
 #define raw_smp_processor_id() (current_thread_info()->cpu)
 
 struct seq_file;

arch/arm64/include/asm/smp_plat.h

@@ -56,6 +56,4 @@ static inline int get_logical_index(u64 mpidr)
 	return -EINVAL;
 }
 
-void __init do_post_cpus_up_work(void);
-
 #endif /* __ASM_SMP_PLAT_H */

arch/arm64/include/asm/spinlock.h

@@ -16,6 +16,7 @@
 #ifndef __ASM_SPINLOCK_H
 #define __ASM_SPINLOCK_H
 
+#include <asm/lse.h>
 #include <asm/spinlock_types.h>
 #include <asm/processor.h>
 
@@ -38,11 +39,21 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 
 	asm volatile(
 	/* Atomically increment the next ticket. */
+	ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
 "	prfm	pstl1strm, %3\n"
 "1:	ldaxr	%w0, %3\n"
 "	add	%w1, %w0, %w5\n"
 "	stxr	%w2, %w1, %3\n"
-"	cbnz	%w2, 1b\n"
+"	cbnz	%w2, 1b\n",
+	/* LSE atomics */
+"	mov	%w2, %w5\n"
+"	ldadda	%w2, %w0, %3\n"
+"	nop\n"
+"	nop\n"
+"	nop\n"
+	)
+
 	/* Did we get the lock? */
 "	eor	%w1, %w0, %w0, ror #16\n"
 "	cbz	%w1, 3f\n"
@@ -67,15 +78,25 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 	unsigned int tmp;
 	arch_spinlock_t lockval;
 
-	asm volatile(
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
-"	prfm	pstl1strm, %2\n"
+	/* LL/SC */
-"1:	ldaxr	%w0, %2\n"
+	"	prfm	pstl1strm, %2\n"
-"	eor	%w1, %w0, %w0, ror #16\n"
+	"1:	ldaxr	%w0, %2\n"
-"	cbnz	%w1, 2f\n"
+	"	eor	%w1, %w0, %w0, ror #16\n"
-"	add	%w0, %w0, %3\n"
+	"	cbnz	%w1, 2f\n"
-"	stxr	%w1, %w0, %2\n"
+	"	add	%w0, %w0, %3\n"
-"	cbnz	%w1, 1b\n"
+	"	stxr	%w1, %w0, %2\n"
-"2:"
+	"	cbnz	%w1, 1b\n"
+	"2:",
+	/* LSE atomics */
+	"	ldr	%w0, %2\n"
+	"	eor	%w1, %w0, %w0, ror #16\n"
+	"	cbnz	%w1, 1f\n"
+	"	add	%w1, %w0, %3\n"
+	"	casa	%w0, %w1, %2\n"
+	"	and	%w1, %w1, #0xffff\n"
+	"	eor	%w1, %w1, %w0, lsr #16\n"
+	"1:")
 	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
 	: "I" (1 << TICKET_SHIFT)
 	: "memory");
@@ -85,10 +106,19 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	asm volatile(
+	unsigned long tmp;
-"	stlrh	%w1, %0\n"
+
-	: "=Q" (lock->owner)
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	: "r" (lock->owner + 1)
+	/* LL/SC */
+	"	ldrh	%w1, %0\n"
+	"	add	%w1, %w1, #1\n"
+	"	stlrh	%w1, %0",
+	/* LSE atomics */
+	"	mov	%w1, #1\n"
+	"	nop\n"
+	"	staddlh	%w1, %0")
+	: "=Q" (lock->owner), "=&r" (tmp)
+	:
 	: "memory");
 }
 
@@ -123,13 +153,24 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 {
 	unsigned int tmp;
 
-	asm volatile(
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
 	"	sevl\n"
 	"1:	wfe\n"
 	"2:	ldaxr	%w0, %1\n"
 	"	cbnz	%w0, 1b\n"
 	"	stxr	%w0, %w2, %1\n"
 	"	cbnz	%w0, 2b\n"
+	"	nop",
+	/* LSE atomics */
+	"1:	mov	%w0, wzr\n"
+	"2:	casa	%w0, %w2, %1\n"
+	"	cbz	%w0, 3f\n"
+	"	ldxr	%w0, %1\n"
+	"	cbz	%w0, 2b\n"
+	"	wfe\n"
+	"	b	1b\n"
+	"3:")
 	: "=&r" (tmp), "+Q" (rw->lock)
 	: "r" (0x80000000)
 	: "memory");
@@ -139,11 +180,18 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
 	unsigned int tmp;
 
-	asm volatile(
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	"	ldaxr	%w0, %1\n"
+	/* LL/SC */
-	"	cbnz	%w0, 1f\n"
+	"1:	ldaxr	%w0, %1\n"
+	"	cbnz	%w0, 2f\n"
 	"	stxr	%w0, %w2, %1\n"
-	"1:\n"
+	"	cbnz	%w0, 1b\n"
+	"2:",
+	/* LSE atomics */
+	"	mov	%w0, wzr\n"
+	"	casa	%w0, %w2, %1\n"
+	"	nop\n"
+	"	nop")
 	: "=&r" (tmp), "+Q" (rw->lock)
 	: "r" (0x80000000)
 	: "memory");
@@ -153,9 +201,10 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 
 static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
-	asm volatile(
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	"	stlr	%w1, %0\n"
+	"	stlr	wzr, %0",
-	: "=Q" (rw->lock) : "r" (0) : "memory");
+	"	swpl	wzr, wzr, %0")
+	: "=Q" (rw->lock) :: "memory");
 }
 
 /* write_can_lock - would write_trylock() succeed? */
@@ -172,6 +221,10 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
  *
  * The memory barriers are implicit with the load-acquire and store-release
  * instructions.
+ *
+ * Note that in UNDEFINED cases, such as unlocking a lock twice, the LL/SC
+ * and LSE implementations may exhibit different behaviour (although this
+ * will have no effect on lockdep).
  */
 static inline void arch_read_lock(arch_rwlock_t *rw)
 {
@@ -179,26 +232,43 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 
 	asm volatile(
 	"	sevl\n"
+	ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
 	"1:	wfe\n"
 	"2:	ldaxr	%w0, %2\n"
 	"	add	%w0, %w0, #1\n"
 	"	tbnz	%w0, #31, 1b\n"
 	"	stxr	%w1, %w0, %2\n"
-	"	cbnz	%w1, 2b\n"
+	"	nop\n"
+	"	cbnz	%w1, 2b",
+	/* LSE atomics */
+	"1:	wfe\n"
+	"2:	ldxr	%w0, %2\n"
+	"	adds	%w1, %w0, #1\n"
+	"	tbnz	%w1, #31, 1b\n"
+	"	casa	%w0, %w1, %2\n"
+	"	sbc	%w0, %w1, %w0\n"
+	"	cbnz	%w0, 2b")
 	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
-	: "memory");
+	: "cc", "memory");
 }
 
 static inline void arch_read_unlock(arch_rwlock_t *rw)
 {
 	unsigned int tmp, tmp2;
 
-	asm volatile(
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
 	"1:	ldxr	%w0, %2\n"
 	"	sub	%w0, %w0, #1\n"
 	"	stlxr	%w1, %w0, %2\n"
-	"	cbnz	%w1, 1b\n"
+	"	cbnz	%w1, 1b",
+	/* LSE atomics */
+	"	movn	%w0, #0\n"
+	"	nop\n"
+	"	nop\n"
+	"	staddl	%w0, %2")
 	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
 	: "memory");
@@ -206,17 +276,28 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
-	unsigned int tmp, tmp2 = 1;
+	unsigned int tmp, tmp2;
 
-	asm volatile(
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	"	ldaxr	%w0, %2\n"
+	/* LL/SC */
+	"	mov	%w1, #1\n"
+	"1:	ldaxr	%w0, %2\n"
 	"	add	%w0, %w0, #1\n"
-	"	tbnz	%w0, #31, 1f\n"
+	"	tbnz	%w0, #31, 2f\n"
 	"	stxr	%w1, %w0, %2\n"
-	"1:\n"
+	"	cbnz	%w1, 1b\n"
-	: "=&r" (tmp), "+r" (tmp2), "+Q" (rw->lock)
+	"2:",
+	/* LSE atomics */
+	"	ldr	%w0, %2\n"
+	"	adds	%w1, %w0, #1\n"
+	"	tbnz	%w1, #31, 1f\n"
+	"	casa	%w0, %w1, %2\n"
+	"	sbc	%w1, %w1, %w0\n"
+	"	nop\n"
+	"1:")
+	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
-	: "memory");
+	: "cc", "memory");
 
 	return !tmp2;
 }

arch/arm64/include/asm/spinlock_types.h

@@ -20,6 +20,8 @@
 # error "please don't include this file directly"
 #endif
 
+#include <linux/types.h>
+
 #define TICKET_SHIFT	16
 
 typedef struct {

arch/arm64/include/asm/sysreg.h

@@ -20,8 +20,29 @@
 #ifndef __ASM_SYSREG_H
 #define __ASM_SYSREG_H
 
+#include <asm/opcodes.h>
+
+#define SCTLR_EL1_CP15BEN	(0x1 << 5)
+#define SCTLR_EL1_SED		(0x1 << 8)
+
+/*
+ * ARMv8 ARM reserves the following encoding for system registers:
+ * (Ref: ARMv8 ARM, Section: "System instruction class encoding overview",
+ *  C5.2, version:ARM DDI 0487A.f)
+ *	[20-19] : Op0
+ *	[18-16] : Op1
+ *	[15-12] : CRn
+ *	[11-8]  : CRm
+ *	[7-5]   : Op2
+ */
 #define sys_reg(op0, op1, crn, crm, op2) \
-	((((op0)-2)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5))
+	((((op0)&3)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5))
+
+#define REG_PSTATE_PAN_IMM                     sys_reg(0, 0, 4, 0, 4)
+#define SCTLR_EL1_SPAN                         (1 << 23)
+
+#define SET_PSTATE_PAN(x) __inst_arm(0xd5000000 | REG_PSTATE_PAN_IMM |\
+				     (!!x)<<8 | 0x1f)
 
 #ifdef __ASSEMBLY__
 
@@ -31,11 +52,11 @@
 	.equ	__reg_num_xzr, 31
 
 	.macro	mrs_s, rt, sreg
-	.inst	0xd5300000|(\sreg)|(__reg_num_\rt)
+	.inst	0xd5200000|(\sreg)|(__reg_num_\rt)
 	.endm
 
 	.macro	msr_s, sreg, rt
-	.inst	0xd5100000|(\sreg)|(__reg_num_\rt)
+	.inst	0xd5000000|(\sreg)|(__reg_num_\rt)
 	.endm
 
 #else
@@ -47,14 +68,23 @@ asm(
 "	.equ	__reg_num_xzr, 31\n"
 "\n"
 "	.macro	mrs_s, rt, sreg\n"
-"	.inst	0xd5300000|(\\sreg)|(__reg_num_\\rt)\n"
+"	.inst	0xd5200000|(\\sreg)|(__reg_num_\\rt)\n"
 "	.endm\n"
 "\n"
 "	.macro	msr_s, sreg, rt\n"
-"	.inst	0xd5100000|(\\sreg)|(__reg_num_\\rt)\n"
+"	.inst	0xd5000000|(\\sreg)|(__reg_num_\\rt)\n"
 "	.endm\n"
 );
 
+static inline void config_sctlr_el1(u32 clear, u32 set)
+{
+	u32 val;
+
+	asm volatile("mrs %0, sctlr_el1" : "=r" (val));
+	val &= ~clear;
+	val |= set;
+	asm volatile("msr sctlr_el1, %0" : : "r" (val));
+}
 #endif
 
 #endif	/* __ASM_SYSREG_H */

arch/arm64/include/asm/tlb.h

@@ -41,7 +41,12 @@ static inline void tlb_flush(struct mmu_gather *tlb)
 		flush_tlb_mm(tlb->mm);
 	} else {
 		struct vm_area_struct vma = { .vm_mm = tlb->mm, };
-		flush_tlb_range(&vma, tlb->start, tlb->end);
+		/*
+		 * The intermediate page table levels are already handled by
+		 * the __(pte|pmd|pud)_free_tlb() functions, so last level
+		 * TLBI is sufficient here.
+		 */
+		__flush_tlb_range(&vma, tlb->start, tlb->end, true);
 	}
 }
 

arch/arm64/include/asm/tlbflush.h

@@ -87,58 +87,64 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 		((unsigned long)ASID(vma->vm_mm) << 48);
 
 	dsb(ishst);
-	asm("tlbi	vae1is, %0" : : "r" (addr));
+	asm("tlbi	vale1is, %0" : : "r" (addr));
 	dsb(ish);
 }
 
-static inline void __flush_tlb_range(struct vm_area_struct *vma,
-				     unsigned long start, unsigned long end)
-{
-	unsigned long asid = (unsigned long)ASID(vma->vm_mm) << 48;
-	unsigned long addr;
-	start = asid | (start >> 12);
-	end = asid | (end >> 12);
-
-	dsb(ishst);
-	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
-		asm("tlbi vae1is, %0" : : "r"(addr));
-	dsb(ish);
-}
-
-static inline void __flush_tlb_kernel_range(unsigned long start, unsigned long end)
-{
-	unsigned long addr;
-	start >>= 12;
-	end >>= 12;
-
-	dsb(ishst);
-	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
-		asm("tlbi vaae1is, %0" : : "r"(addr));
-	dsb(ish);
-	isb();
-}
-
 /*
  * This is meant to avoid soft lock-ups on large TLB flushing ranges and not
  * necessarily a performance improvement.
  */
 #define MAX_TLB_RANGE	(1024UL << PAGE_SHIFT)
 
+static inline void __flush_tlb_range(struct vm_area_struct *vma,
+				     unsigned long start, unsigned long end,
+				     bool last_level)
+{
+	unsigned long asid = (unsigned long)ASID(vma->vm_mm) << 48;
+	unsigned long addr;
+
+	if ((end - start) > MAX_TLB_RANGE) {
+		flush_tlb_mm(vma->vm_mm);
+		return;
+	}
+
+	start = asid | (start >> 12);
+	end = asid | (end >> 12);
+
+	dsb(ishst);
+	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) {
+		if (last_level)
+			asm("tlbi vale1is, %0" : : "r"(addr));
+		else
+			asm("tlbi vae1is, %0" : : "r"(addr));
+	}
+	dsb(ish);
+}
+
 static inline void flush_tlb_range(struct vm_area_struct *vma,
 				   unsigned long start, unsigned long end)
 {
-	if ((end - start) <= MAX_TLB_RANGE)
+	__flush_tlb_range(vma, start, end, false);
-		__flush_tlb_range(vma, start, end);
-	else
-		flush_tlb_mm(vma->vm_mm);
 }
 
 static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-	if ((end - start) <= MAX_TLB_RANGE)
+	unsigned long addr;
-		__flush_tlb_kernel_range(start, end);
+
-	else
+	if ((end - start) > MAX_TLB_RANGE) {
 		flush_tlb_all();
+		return;
+	}
+
+	start >>= 12;
+	end >>= 12;
+
+	dsb(ishst);
+	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
+		asm("tlbi vaae1is, %0" : : "r"(addr));
+	dsb(ish);
+	isb();
 }
 
 /*
@@ -154,20 +160,6 @@ static inline void __flush_tlb_pgtable(struct mm_struct *mm,
 	asm("tlbi	vae1is, %0" : : "r" (addr));
 	dsb(ish);
 }
-/*
- * On AArch64, the cache coherency is handled via the set_pte_at() function.
- */
-static inline void update_mmu_cache(struct vm_area_struct *vma,
-				    unsigned long addr, pte_t *ptep)
-{
-	/*
-	 * set_pte() does not have a DSB for user mappings, so make sure that
-	 * the page table write is visible.
-	 */
-	dsb(ishst);
-}
-
-#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
 
 #endif
 

arch/arm64/include/asm/topology.h

@@ -1,8 +1,6 @@
 #ifndef __ASM_TOPOLOGY_H
 #define __ASM_TOPOLOGY_H
 
-#ifdef CONFIG_SMP
-
 #include <linux/cpumask.h>
 
 struct cpu_topology {
@@ -24,13 +22,6 @@ void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
 
-#else
-
-static inline void init_cpu_topology(void) { }
-static inline void store_cpu_topology(unsigned int cpuid) { }
-
-#endif
-
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_ARM_TOPOLOGY_H */

arch/arm64/include/asm/traps.h

@@ -34,13 +34,32 @@ struct undef_hook {
 void register_undef_hook(struct undef_hook *hook);
 void unregister_undef_hook(struct undef_hook *hook);
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static inline int __in_irqentry_text(unsigned long ptr)
+{
+	extern char __irqentry_text_start[];
+	extern char __irqentry_text_end[];
+
+	return ptr >= (unsigned long)&__irqentry_text_start &&
+	       ptr < (unsigned long)&__irqentry_text_end;
+}
+#else
+static inline int __in_irqentry_text(unsigned long ptr)
+{
+	return 0;
+}
+#endif
+
 static inline int in_exception_text(unsigned long ptr)
 {
 	extern char __exception_text_start[];
 	extern char __exception_text_end[];
+	int in;
 
-	return ptr >= (unsigned long)&__exception_text_start &&
+	in = ptr >= (unsigned long)&__exception_text_start &&
-	       ptr < (unsigned long)&__exception_text_end;
+	     ptr < (unsigned long)&__exception_text_end;
+
+	return in ? : __in_irqentry_text(ptr);
 }
 
 #endif

arch/arm64/include/asm/uaccess.h

@@ -24,7 +24,10 @@
 #include <linux/string.h>
 #include <linux/thread_info.h>
 
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
 #include <asm/ptrace.h>
+#include <asm/sysreg.h>
 #include <asm/errno.h>
 #include <asm/memory.h>
 #include <asm/compiler.h>
@@ -131,6 +134,8 @@ static inline void set_fs(mm_segment_t fs)
 do {									\
 	unsigned long __gu_val;						\
 	__chk_user_ptr(ptr);						\
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,	\
+			CONFIG_ARM64_PAN));				\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
 		__get_user_asm("ldrb", "%w", __gu_val, (ptr), (err));	\
@@ -148,6 +153,8 @@ do {									\
 		BUILD_BUG();						\
 	}								\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
+			CONFIG_ARM64_PAN));				\
 } while (0)
 
 #define __get_user(x, ptr)						\
@@ -194,6 +201,8 @@ do {									\
 do {									\
 	__typeof__(*(ptr)) __pu_val = (x);				\
 	__chk_user_ptr(ptr);						\
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,	\
+			CONFIG_ARM64_PAN));				\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
 		__put_user_asm("strb", "%w", __pu_val, (ptr), (err));	\
@@ -210,6 +219,8 @@ do {									\
 	default:							\
 		BUILD_BUG();						\
 	}								\
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
+			CONFIG_ARM64_PAN));				\
 } while (0)
 
 #define __put_user(x, ptr)						\

arch/arm64/include/uapi/asm/hwcap.h

@@ -27,5 +27,6 @@
 #define HWCAP_SHA1		(1 << 5)
 #define HWCAP_SHA2		(1 << 6)
 #define HWCAP_CRC32		(1 << 7)
+#define HWCAP_ATOMICS		(1 << 8)
 
 #endif /* _UAPI__ASM_HWCAP_H */

arch/arm64/include/uapi/asm/ptrace.h

@@ -44,6 +44,7 @@
 #define PSR_I_BIT	0x00000080
 #define PSR_A_BIT	0x00000100
 #define PSR_D_BIT	0x00000200
+#define PSR_PAN_BIT	0x00400000
 #define PSR_Q_BIT	0x08000000
 #define PSR_V_BIT	0x10000000
 #define PSR_C_BIT	0x20000000

arch/arm64/kernel/Makefile

@@ -17,15 +17,15 @@ arm64-obj-y		:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
 			   hyp-stub.o psci.o psci-call.o cpu_ops.o insn.o	\
 			   return_address.o cpuinfo.o cpu_errata.o		\
-			   cpufeature.o alternative.o cacheinfo.o
+			   cpufeature.o alternative.o cacheinfo.o		\
+			   smp.o smp_spin_table.o topology.o
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
 					   sys_compat.o entry32.o		\
 					   ../../arm/kernel/opcodes.o
 arm64-obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o entry-ftrace.o
 arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
-arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o topology.o
+arm64-obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o perf_callchain.o
-arm64-obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 arm64-obj-$(CONFIG_CPU_PM)		+= sleep.o suspend.o

arch/arm64/kernel/alternative.c

@@ -85,7 +85,7 @@ static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr)
 	return insn;
 }
 
-static int __apply_alternatives(void *alt_region)
+static void __apply_alternatives(void *alt_region)
 {
 	struct alt_instr *alt;
 	struct alt_region *region = alt_region;
@@ -114,19 +114,39 @@ static int __apply_alternatives(void *alt_region)
 		flush_icache_range((uintptr_t)origptr,
 				   (uintptr_t)(origptr + nr_inst));
 	}
-
-	return 0;
 }
 
-void apply_alternatives_all(void)
+/*
+ * We might be patching the stop_machine state machine, so implement a
+ * really simple polling protocol here.
+ */
+static int __apply_alternatives_multi_stop(void *unused)
 {
+	static int patched = 0;
 	struct alt_region region = {
 		.begin	= __alt_instructions,
 		.end	= __alt_instructions_end,
 	};
 
+	/* We always have a CPU 0 at this point (__init) */
+	if (smp_processor_id()) {
+		while (!READ_ONCE(patched))
+			cpu_relax();
+		isb();
+	} else {
+		BUG_ON(patched);
+		__apply_alternatives(&region);
+		/* Barriers provided by the cache flushing */
+		WRITE_ONCE(patched, 1);
+	}
+
+	return 0;
+}
+
+void __init apply_alternatives_all(void)
+{
 	/* better not try code patching on a live SMP system */
-	stop_machine(__apply_alternatives, &region, NULL);
+	stop_machine(__apply_alternatives_multi_stop, NULL, cpu_online_mask);
 }
 
 void apply_alternatives(void *start, size_t length)

arch/arm64/kernel/armv8_deprecated.c

@@ -14,8 +14,11 @@
 #include <linux/slab.h>
 #include <linux/sysctl.h>
 
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
 #include <asm/insn.h>
 #include <asm/opcodes.h>
+#include <asm/sysreg.h>
 #include <asm/system_misc.h>
 #include <asm/traps.h>
 #include <asm/uaccess.h>
@@ -279,6 +282,8 @@ static void register_insn_emulation_sysctl(struct ctl_table *table)
  */
 #define __user_swpX_asm(data, addr, res, temp, B)		\
 	__asm__ __volatile__(					\
+	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,	\
+		    CONFIG_ARM64_PAN)				\
 	"	mov		%w2, %w1\n"			\
 	"0:	ldxr"B"		%w1, [%3]\n"			\
 	"1:	stxr"B"		%w0, %w2, [%3]\n"		\
@@ -294,7 +299,9 @@ static void register_insn_emulation_sysctl(struct ctl_table *table)
 	"	.align		3\n"				\
 	"	.quad		0b, 3b\n"			\
 	"	.quad		1b, 3b\n"			\
-	"	.popsection"					\
+	"	.popsection\n"					\
+	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
+		CONFIG_ARM64_PAN)				\
 	: "=&r" (res), "+r" (data), "=&r" (temp)		\
 	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)		\
 	: "memory")
@@ -504,16 +511,6 @@ ret:
 	return 0;
 }
 
-static inline void config_sctlr_el1(u32 clear, u32 set)
-{
-	u32 val;
-
-	asm volatile("mrs %0, sctlr_el1" : "=r" (val));
-	val &= ~clear;
-	val |= set;
-	asm volatile("msr sctlr_el1, %0" : : "r" (val));
-}
-
 static int cp15_barrier_set_hw_mode(bool enable)
 {
 	if (enable)

arch/arm64/kernel/cpu_ops.c

@@ -30,9 +30,7 @@ extern const struct cpu_operations cpu_psci_ops;
 const struct cpu_operations *cpu_ops[NR_CPUS];
 
 static const struct cpu_operations *supported_cpu_ops[] __initconst = {
-#ifdef CONFIG_SMP
 	&smp_spin_table_ops,
-#endif
 	&cpu_psci_ops,
 	NULL,
 };

arch/arm64/kernel/cpufeature.c

@@ -21,24 +21,57 @@
 #include <linux/types.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
+#include <asm/processor.h>
 
 static bool
-has_id_aa64pfr0_feature(const struct arm64_cpu_capabilities *entry)
+feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry)
 {
-	u64 val;
+	int val = cpuid_feature_extract_field(reg, entry->field_pos);
 
-	val = read_cpuid(id_aa64pfr0_el1);
+	return val >= entry->min_field_value;
-	return (val & entry->register_mask) == entry->register_value;
 }
 
+#define __ID_FEAT_CHK(reg)						\
+static bool __maybe_unused						\
+has_##reg##_feature(const struct arm64_cpu_capabilities *entry)		\
+{									\
+	u64 val;							\
+									\
+	val = read_cpuid(reg##_el1);					\
+	return feature_matches(val, entry);				\
+}
+
+__ID_FEAT_CHK(id_aa64pfr0);
+__ID_FEAT_CHK(id_aa64mmfr1);
+__ID_FEAT_CHK(id_aa64isar0);
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
 		.capability = ARM64_HAS_SYSREG_GIC_CPUIF,
 		.matches = has_id_aa64pfr0_feature,
-		.register_mask = (0xf << 24),
+		.field_pos = 24,
-		.register_value = (1 << 24),
+		.min_field_value = 1,
 	},
+#ifdef CONFIG_ARM64_PAN
+	{
+		.desc = "Privileged Access Never",
+		.capability = ARM64_HAS_PAN,
+		.matches = has_id_aa64mmfr1_feature,
+		.field_pos = 20,
+		.min_field_value = 1,
+		.enable = cpu_enable_pan,
+	},
+#endif /* CONFIG_ARM64_PAN */
+#if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS)
+	{
+		.desc = "LSE atomic instructions",
+		.capability = ARM64_HAS_LSE_ATOMICS,
+		.matches = has_id_aa64isar0_feature,
+		.field_pos = 20,
+		.min_field_value = 2,
+	},
+#endif /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
 	{},
 };
 
@@ -55,9 +88,15 @@ void check_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 			pr_info("%s %s\n", info, caps[i].desc);
 		cpus_set_cap(caps[i].capability);
 	}
+
+	/* second pass allows enable() to consider interacting capabilities */
+	for (i = 0; caps[i].desc; i++) {
+		if (cpus_have_cap(caps[i].capability) && caps[i].enable)
+			caps[i].enable();
+	}
 }
 
 void check_local_cpu_features(void)
 {
-	check_cpu_capabilities(arm64_features, "detected feature");
+	check_cpu_capabilities(arm64_features, "detected feature:");
 }

arch/arm64/kernel/debug-monitors.c

@@ -82,7 +82,7 @@ early_param("nodebugmon", early_debug_disable);
 static DEFINE_PER_CPU(int, mde_ref_count);
 static DEFINE_PER_CPU(int, kde_ref_count);
 
-void enable_debug_monitors(enum debug_el el)
+void enable_debug_monitors(enum dbg_active_el el)
 {
 	u32 mdscr, enable = 0;
 
@@ -102,7 +102,7 @@ void enable_debug_monitors(enum debug_el el)
 	}
 }
 
-void disable_debug_monitors(enum debug_el el)
+void disable_debug_monitors(enum dbg_active_el el)
 {
 	u32 mdscr, disable = 0;
 

arch/arm64/kernel/efi-stub.c

@@ -13,7 +13,7 @@
 #include <asm/efi.h>
 #include <asm/sections.h>
 
-efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table,
+efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table_arg,
 					unsigned long *image_addr,
 					unsigned long *image_size,
 					unsigned long *reserve_addr,
@@ -23,21 +23,44 @@ efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table,
 {
 	efi_status_t status;
 	unsigned long kernel_size, kernel_memsize = 0;
+	unsigned long nr_pages;
+	void *old_image_addr = (void *)*image_addr;
 
 	/* Relocate the image, if required. */
 	kernel_size = _edata - _text;
 	if (*image_addr != (dram_base + TEXT_OFFSET)) {
 		kernel_memsize = kernel_size + (_end - _edata);
-		status = efi_low_alloc(sys_table, kernel_memsize + TEXT_OFFSET,
+
-				       SZ_2M, reserve_addr);
+		/*
+		 * First, try a straight allocation at the preferred offset.
+		 * This will work around the issue where, if dram_base == 0x0,
+		 * efi_low_alloc() refuses to allocate at 0x0 (to prevent the
+		 * address of the allocation to be mistaken for a FAIL return
+		 * value or a NULL pointer). It will also ensure that, on
+		 * platforms where the [dram_base, dram_base + TEXT_OFFSET)
+		 * interval is partially occupied by the firmware (like on APM
+		 * Mustang), we can still place the kernel at the address
+		 * 'dram_base + TEXT_OFFSET'.
+		 */
+		*image_addr = *reserve_addr = dram_base + TEXT_OFFSET;
+		nr_pages = round_up(kernel_memsize, EFI_ALLOC_ALIGN) /
+			   EFI_PAGE_SIZE;
+		status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS,
+					EFI_LOADER_DATA, nr_pages,
+					(efi_physical_addr_t *)reserve_addr);
 		if (status != EFI_SUCCESS) {
-			pr_efi_err(sys_table, "Failed to relocate kernel\n");
+			kernel_memsize += TEXT_OFFSET;
-			return status;
+			status = efi_low_alloc(sys_table_arg, kernel_memsize,
+					       SZ_2M, reserve_addr);
+
+			if (status != EFI_SUCCESS) {
+				pr_efi_err(sys_table_arg, "Failed to relocate kernel\n");
+				return status;
+			}
+			*image_addr = *reserve_addr + TEXT_OFFSET;
 		}
-		memcpy((void *)*reserve_addr + TEXT_OFFSET, (void *)*image_addr,
+		memcpy((void *)*image_addr, old_image_addr, kernel_size);
-		       kernel_size);
+		*reserve_size = kernel_memsize;
-		*image_addr = *reserve_addr + TEXT_OFFSET;
-		*reserve_size = kernel_memsize + TEXT_OFFSET;
 	}
 
 

arch/arm64/kernel/entry.S

@@ -116,41 +116,34 @@
 	*/
 	.endm
 
-	.macro	kernel_exit, el, ret = 0
+	.macro	kernel_exit, el
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
 	ct_user_enter
 	ldr	x23, [sp, #S_SP]		// load return stack pointer
 	msr	sp_el0, x23
-
 #ifdef CONFIG_ARM64_ERRATUM_845719
-
+alternative_if_not ARM64_WORKAROUND_845719
-#undef SEQUENCE_ORG
+	nop
-#undef SEQUENCE_ALT
+	nop
-
 #ifdef CONFIG_PID_IN_CONTEXTIDR
-
+	nop
-#define SEQUENCE_ORG	"nop ; nop ; nop"
-#define SEQUENCE_ALT	"tbz x22, #4, 1f ; mrs x29, contextidr_el1; msr contextidr_el1, x29; 1:"
-
-#else
-
-#define SEQUENCE_ORG	"nop ; nop"
-#define SEQUENCE_ALT	"tbz x22, #4, 1f ; msr contextidr_el1, xzr; 1:"
-
 #endif
-
+alternative_else
-	alternative_insn SEQUENCE_ORG, SEQUENCE_ALT, ARM64_WORKAROUND_845719
+	tbz	x22, #4, 1f
-
+#ifdef CONFIG_PID_IN_CONTEXTIDR
+	mrs	x29, contextidr_el1
+	msr	contextidr_el1, x29
+#else
+	msr contextidr_el1, xzr
+#endif
+1:
+alternative_endif
 #endif
 	.endif
 	msr	elr_el1, x21			// set up the return data
 	msr	spsr_el1, x22
-	.if	\ret
-	ldr	x1, [sp, #S_X1]			// preserve x0 (syscall return)
-	.else
 	ldp	x0, x1, [sp, #16 * 0]
-	.endif
 	ldp	x2, x3, [sp, #16 * 1]
 	ldp	x4, x5, [sp, #16 * 2]
 	ldp	x6, x7, [sp, #16 * 3]
@@ -613,22 +606,21 @@ ENDPROC(cpu_switch_to)
  */
 ret_fast_syscall:
 	disable_irq				// disable interrupts
+	str	x0, [sp, #S_X0]			// returned x0
 	ldr	x1, [tsk, #TI_FLAGS]		// re-check for syscall tracing
 	and	x2, x1, #_TIF_SYSCALL_WORK
 	cbnz	x2, ret_fast_syscall_trace
 	and	x2, x1, #_TIF_WORK_MASK
-	cbnz	x2, fast_work_pending
+	cbnz	x2, work_pending
 	enable_step_tsk x1, x2
-	kernel_exit 0, ret = 1
+	kernel_exit 0
 ret_fast_syscall_trace:
 	enable_irq				// enable interrupts
-	b	__sys_trace_return
+	b	__sys_trace_return_skipped	// we already saved x0
 
 /*
  * Ok, we need to do extra processing, enter the slow path.
  */
-fast_work_pending:
-	str	x0, [sp, #S_X0]			// returned x0
 work_pending:
 	tbnz	x1, #TIF_NEED_RESCHED, work_resched
 	/* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
@@ -652,7 +644,7 @@ ret_to_user:
 	cbnz	x2, work_pending
 	enable_step_tsk x1, x2
 no_work_pending:
-	kernel_exit 0, ret = 0
+	kernel_exit 0
 ENDPROC(ret_to_user)
 
 /*

arch/arm64/kernel/fpsimd.c

@@ -158,6 +158,7 @@ void fpsimd_thread_switch(struct task_struct *next)
 void fpsimd_flush_thread(void)
 {
 	memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
+	fpsimd_flush_task_state(current);
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
 }
 

arch/arm64/kernel/head.S

@@ -62,13 +62,8 @@
 /*
  * 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
@@ -574,7 +569,6 @@ ENTRY(__boot_cpu_mode)
 	.long	BOOT_CPU_MODE_EL1
 	.popsection
 
-#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.
@@ -622,7 +616,6 @@ ENTRY(__secondary_switched)
 	mov	x29, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)
-#endif	/* CONFIG_SMP */
 
 /*
  * Enable the MMU.
@@ -641,5 +634,13 @@ __enable_mmu:
 	isb
 	msr	sctlr_el1, x0
 	isb
+	/*
+	 * 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
 	br	x27
 ENDPROC(__enable_mmu)

arch/arm64/kernel/hw_breakpoint.c

@@ -156,7 +156,7 @@ static void write_wb_reg(int reg, int n, u64 val)
  * Convert a breakpoint privilege level to the corresponding exception
  * level.
  */
-static enum debug_el debug_exception_level(int privilege)
+static enum dbg_active_el debug_exception_level(int privilege)
 {
 	switch (privilege) {
 	case AARCH64_BREAKPOINT_EL0:
@@ -230,7 +230,7 @@ static int hw_breakpoint_control(struct perf_event *bp,
 	struct perf_event **slots;
 	struct debug_info *debug_info = &current->thread.debug;
 	int i, max_slots, ctrl_reg, val_reg, reg_enable;
-	enum debug_el dbg_el = debug_exception_level(info->ctrl.privilege);
+	enum dbg_active_el dbg_el = debug_exception_level(info->ctrl.privilege);
 	u32 ctrl;
 
 	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
@@ -537,7 +537,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
  * exception level at the register level.
  * This is used when single-stepping after a breakpoint exception.
  */
-static void toggle_bp_registers(int reg, enum debug_el el, int enable)
+static void toggle_bp_registers(int reg, enum dbg_active_el el, int enable)
 {
 	int i, max_slots, privilege;
 	u32 ctrl;

arch/arm64/kernel/insn.c

@@ -101,9 +101,8 @@ static void __kprobes *patch_map(void *addr, int fixmap)
 		return addr;
 
 	BUG_ON(!page);
-	set_fixmap(fixmap, page_to_phys(page));
+	return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
-
+			(uintaddr & ~PAGE_MASK));
-	return (void *) (__fix_to_virt(fixmap) + (uintaddr & ~PAGE_MASK));
 }
 
 static void __kprobes patch_unmap(int fixmap)

arch/arm64/kernel/irq.c

@@ -33,9 +33,7 @@ unsigned long irq_err_count;
 
 int arch_show_interrupts(struct seq_file *p, int prec)
 {
-#ifdef CONFIG_SMP
 	show_ipi_list(p, prec);
-#endif
 	seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
 	return 0;
 }

arch/arm64/kernel/kgdb.c

@@ -235,13 +235,13 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 
 static struct break_hook kgdb_brkpt_hook = {
 	.esr_mask	= 0xffffffff,
-	.esr_val	= DBG_ESR_VAL_BRK(KGDB_DYN_DBG_BRK_IMM),
+	.esr_val	= (u32)ESR_ELx_VAL_BRK64(KGDB_DYN_DBG_BRK_IMM),
 	.fn		= kgdb_brk_fn
 };
 
 static struct break_hook kgdb_compiled_brkpt_hook = {
 	.esr_mask	= 0xffffffff,
-	.esr_val	= DBG_ESR_VAL_BRK(KGDB_COMPILED_DBG_BRK_IMM),
+	.esr_val	= (u32)ESR_ELx_VAL_BRK64(KGDB_COMPILED_DBG_BRK_IMM),
 	.fn		= kgdb_compiled_brk_fn
 };
 
@@ -328,9 +328,9 @@ void kgdb_arch_exit(void)
  */
 struct kgdb_arch arch_kgdb_ops = {
 	.gdb_bpt_instr = {
-		KGDB_DYN_BRK_INS_BYTE0,
+		KGDB_DYN_BRK_INS_BYTE(0),
-		KGDB_DYN_BRK_INS_BYTE1,
+		KGDB_DYN_BRK_INS_BYTE(1),
-		KGDB_DYN_BRK_INS_BYTE2,
+		KGDB_DYN_BRK_INS_BYTE(2),
-		KGDB_DYN_BRK_INS_BYTE3,
+		KGDB_DYN_BRK_INS_BYTE(3),
 	}
 };

arch/arm64/kernel/pci.c

@@ -38,6 +38,19 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 	return res->start;
 }
 
+/**
+ * pcibios_enable_device - Enable I/O and memory.
+ * @dev: PCI device to be enabled
+ * @mask: bitmask of BARs to enable
+ */
+int pcibios_enable_device(struct pci_dev *dev, int mask)
+{
+	if (pci_has_flag(PCI_PROBE_ONLY))
+		return 0;
+
+	return pci_enable_resources(dev, mask);
+}
+
 /*
  * Try to assign the IRQ number from DT when adding a new device
  */

arch/arm64/kernel/perf_callchain.c

@@ -0,0 +1,196 @@
+/*
+ * arm64 callchain support
+ *
+ * Copyright (C) 2015 ARM Limited
+ *
+ * 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/perf_event.h>
+#include <linux/uaccess.h>
+
+#include <asm/stacktrace.h>
+
+struct frame_tail {
+	struct frame_tail	__user *fp;
+	unsigned long		lr;
+} __attribute__((packed));
+
+/*
+ * Get the return address for a single stackframe and return a pointer to the
+ * next frame tail.
+ */
+static struct frame_tail __user *
+user_backtrace(struct frame_tail __user *tail,
+	       struct perf_callchain_entry *entry)
+{
+	struct frame_tail buftail;
+	unsigned long err;
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
+		return NULL;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
+		return NULL;
+
+	perf_callchain_store(entry, buftail.lr);
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail >= buftail.fp)
+		return NULL;
+
+	return buftail.fp;
+}
+
+#ifdef CONFIG_COMPAT
+/*
+ * The registers we're interested in are at the end of the variable
+ * length saved register structure. The fp points at the end of this
+ * structure so the address of this struct is:
+ * (struct compat_frame_tail *)(xxx->fp)-1
+ *
+ * This code has been adapted from the ARM OProfile support.
+ */
+struct compat_frame_tail {
+	compat_uptr_t	fp; /* a (struct compat_frame_tail *) in compat mode */
+	u32		sp;
+	u32		lr;
+} __attribute__((packed));
+
+static struct compat_frame_tail __user *
+compat_user_backtrace(struct compat_frame_tail __user *tail,
+		      struct perf_callchain_entry *entry)
+{
+	struct compat_frame_tail buftail;
+	unsigned long err;
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
+		return NULL;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
+		return NULL;
+
+	perf_callchain_store(entry, buftail.lr);
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail + 1 >= (struct compat_frame_tail __user *)
+			compat_ptr(buftail.fp))
+		return NULL;
+
+	return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
+}
+#endif /* CONFIG_COMPAT */
+
+void perf_callchain_user(struct perf_callchain_entry *entry,
+			 struct pt_regs *regs)
+{
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* We don't support guest os callchain now */
+		return;
+	}
+
+	perf_callchain_store(entry, regs->pc);
+
+	if (!compat_user_mode(regs)) {
+		/* AARCH64 mode */
+		struct frame_tail __user *tail;
+
+		tail = (struct frame_tail __user *)regs->regs[29];
+
+		while (entry->nr < PERF_MAX_STACK_DEPTH &&
+		       tail && !((unsigned long)tail & 0xf))
+			tail = user_backtrace(tail, entry);
+	} else {
+#ifdef CONFIG_COMPAT
+		/* AARCH32 compat mode */
+		struct compat_frame_tail __user *tail;
+
+		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
+
+		while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+			tail && !((unsigned long)tail & 0x3))
+			tail = compat_user_backtrace(tail, entry);
+#endif
+	}
+}
+
+/*
+ * Gets called by walk_stackframe() for every stackframe. This will be called
+ * whist unwinding the stackframe and is like a subroutine return so we use
+ * the PC.
+ */
+static int callchain_trace(struct stackframe *frame, void *data)
+{
+	struct perf_callchain_entry *entry = data;
+	perf_callchain_store(entry, frame->pc);
+	return 0;
+}
+
+void perf_callchain_kernel(struct perf_callchain_entry *entry,
+			   struct pt_regs *regs)
+{
+	struct stackframe frame;
+
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* We don't support guest os callchain now */
+		return;
+	}
+
+	frame.fp = regs->regs[29];
+	frame.sp = regs->sp;
+	frame.pc = regs->pc;
+
+	walk_stackframe(&frame, callchain_trace, entry);
+}
+
+unsigned long perf_instruction_pointer(struct pt_regs *regs)
+{
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
+		return perf_guest_cbs->get_guest_ip();
+
+	return instruction_pointer(regs);
+}
+
+unsigned long perf_misc_flags(struct pt_regs *regs)
+{
+	int misc = 0;
+
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		if (perf_guest_cbs->is_user_mode())
+			misc |= PERF_RECORD_MISC_GUEST_USER;
+		else
+			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
+	} else {
+		if (user_mode(regs))
+			misc |= PERF_RECORD_MISC_USER;
+		else
+			misc |= PERF_RECORD_MISC_KERNEL;
+	}
+
+	return misc;
+}

arch/arm64/kernel/perf_event.c

@@ -25,7 +25,7 @@
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
-#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/perf_event.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
@@ -36,7 +36,6 @@
 #include <asm/irq.h>
 #include <asm/irq_regs.h>
 #include <asm/pmu.h>
-#include <asm/stacktrace.h>
 
 /*
  * ARMv8 supports a maximum of 32 events.
@@ -78,6 +77,16 @@ EXPORT_SYMBOL_GPL(perf_num_counters);
 
 #define CACHE_OP_UNSUPPORTED		0xFFFF
 
+#define PERF_MAP_ALL_UNSUPPORTED					\
+	[0 ... PERF_COUNT_HW_MAX - 1] = HW_OP_UNSUPPORTED
+
+#define PERF_CACHE_MAP_ALL_UNSUPPORTED					\
+[0 ... C(MAX) - 1] = {							\
+	[0 ... C(OP_MAX) - 1] = {					\
+		[0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED,	\
+	},								\
+}
+
 static int
 armpmu_map_cache_event(const unsigned (*cache_map)
 				      [PERF_COUNT_HW_CACHE_MAX]
@@ -435,10 +444,8 @@ armpmu_reserve_hardware(struct arm_pmu *armpmu)
 	unsigned int i, irqs;
 	struct platform_device *pmu_device = armpmu->plat_device;
 
-	if (!pmu_device) {
+	if (!pmu_device)
-		pr_err("no PMU device registered\n");
 		return -ENODEV;
-	}
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 	if (!irqs) {
@@ -703,118 +710,28 @@ enum armv8_pmuv3_perf_types {
 
 /* PMUv3 HW events mapping. */
 static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
 	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
-	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 						[PERF_COUNT_HW_CACHE_OP_MAX]
 						[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
-		[C(OP_READ)] = {
+
-			[C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
-		},
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
-		[C(OP_WRITE)] = {
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
-			[C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+
-			[C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
-		},
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
-		[C(OP_PREFETCH)] = {
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(DTLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
 };
 
 /*
@@ -1337,7 +1254,7 @@ static int armpmu_device_probe(struct platform_device *pdev)
 		}
 
 		for_each_possible_cpu(cpu)
-			if (arch_find_n_match_cpu_physical_id(dn, cpu, NULL))
+			if (dn == of_cpu_device_node_get(cpu))
 				break;
 
 		if (cpu >= nr_cpu_ids) {
@@ -1415,180 +1332,3 @@ static int __init init_hw_perf_events(void)
 }
 early_initcall(init_hw_perf_events);
 
-/*
- * Callchain handling code.
- */
-struct frame_tail {
-	struct frame_tail	__user *fp;
-	unsigned long		lr;
-} __attribute__((packed));
-
-/*
- * Get the return address for a single stackframe and return a pointer to the
- * next frame tail.
- */
-static struct frame_tail __user *
-user_backtrace(struct frame_tail __user *tail,
-	       struct perf_callchain_entry *entry)
-{
-	struct frame_tail buftail;
-	unsigned long err;
-
-	/* Also check accessibility of one struct frame_tail beyond */
-	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
-		return NULL;
-
-	pagefault_disable();
-	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
-	pagefault_enable();
-
-	if (err)
-		return NULL;
-
-	perf_callchain_store(entry, buftail.lr);
-
-	/*
-	 * Frame pointers should strictly progress back up the stack
-	 * (towards higher addresses).
-	 */
-	if (tail >= buftail.fp)
-		return NULL;
-
-	return buftail.fp;
-}
-
-#ifdef CONFIG_COMPAT
-/*
- * The registers we're interested in are at the end of the variable
- * length saved register structure. The fp points at the end of this
- * structure so the address of this struct is:
- * (struct compat_frame_tail *)(xxx->fp)-1
- *
- * This code has been adapted from the ARM OProfile support.
- */
-struct compat_frame_tail {
-	compat_uptr_t	fp; /* a (struct compat_frame_tail *) in compat mode */
-	u32		sp;
-	u32		lr;
-} __attribute__((packed));
-
-static struct compat_frame_tail __user *
-compat_user_backtrace(struct compat_frame_tail __user *tail,
-		      struct perf_callchain_entry *entry)
-{
-	struct compat_frame_tail buftail;
-	unsigned long err;
-
-	/* Also check accessibility of one struct frame_tail beyond */
-	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
-		return NULL;
-
-	pagefault_disable();
-	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
-	pagefault_enable();
-
-	if (err)
-		return NULL;
-
-	perf_callchain_store(entry, buftail.lr);
-
-	/*
-	 * Frame pointers should strictly progress back up the stack
-	 * (towards higher addresses).
-	 */
-	if (tail + 1 >= (struct compat_frame_tail __user *)
-			compat_ptr(buftail.fp))
-		return NULL;
-
-	return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
-}
-#endif /* CONFIG_COMPAT */
-
-void perf_callchain_user(struct perf_callchain_entry *entry,
-			 struct pt_regs *regs)
-{
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* We don't support guest os callchain now */
-		return;
-	}
-
-	perf_callchain_store(entry, regs->pc);
-
-	if (!compat_user_mode(regs)) {
-		/* AARCH64 mode */
-		struct frame_tail __user *tail;
-
-		tail = (struct frame_tail __user *)regs->regs[29];
-
-		while (entry->nr < PERF_MAX_STACK_DEPTH &&
-		       tail && !((unsigned long)tail & 0xf))
-			tail = user_backtrace(tail, entry);
-	} else {
-#ifdef CONFIG_COMPAT
-		/* AARCH32 compat mode */
-		struct compat_frame_tail __user *tail;
-
-		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
-
-		while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
-			tail && !((unsigned long)tail & 0x3))
-			tail = compat_user_backtrace(tail, entry);
-#endif
-	}
-}
-
-/*
- * Gets called by walk_stackframe() for every stackframe. This will be called
- * whist unwinding the stackframe and is like a subroutine return so we use
- * the PC.
- */
-static int callchain_trace(struct stackframe *frame, void *data)
-{
-	struct perf_callchain_entry *entry = data;
-	perf_callchain_store(entry, frame->pc);
-	return 0;
-}
-
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
-			   struct pt_regs *regs)
-{
-	struct stackframe frame;
-
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* We don't support guest os callchain now */
-		return;
-	}
-
-	frame.fp = regs->regs[29];
-	frame.sp = regs->sp;
-	frame.pc = regs->pc;
-
-	walk_stackframe(&frame, callchain_trace, entry);
-}
-
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
-{
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
-		return perf_guest_cbs->get_guest_ip();
-
-	return instruction_pointer(regs);
-}
-
-unsigned long perf_misc_flags(struct pt_regs *regs)
-{
-	int misc = 0;
-
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		if (perf_guest_cbs->is_user_mode())
-			misc |= PERF_RECORD_MISC_GUEST_USER;
-		else
-			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
-	} else {
-		if (user_mode(regs))
-			misc |= PERF_RECORD_MISC_USER;
-		else
-			misc |= PERF_RECORD_MISC_KERNEL;
-	}
-
-	return misc;
-}

arch/arm64/kernel/psci.c

@@ -110,8 +110,6 @@ free_mem:
 	return ret;
 }
 
-#ifdef CONFIG_SMP
-
 static int __init cpu_psci_cpu_init(unsigned int cpu)
 {
 	return 0;
@@ -193,7 +191,6 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 	return -ETIMEDOUT;
 }
 #endif
-#endif
 
 static int psci_suspend_finisher(unsigned long index)
 {
@@ -228,7 +225,6 @@ const struct cpu_operations cpu_psci_ops = {
 	.cpu_init_idle	= cpu_psci_cpu_init_idle,
 	.cpu_suspend	= cpu_psci_cpu_suspend,
 #endif
-#ifdef CONFIG_SMP
 	.cpu_init	= cpu_psci_cpu_init,
 	.cpu_prepare	= cpu_psci_cpu_prepare,
 	.cpu_boot	= cpu_psci_cpu_boot,
@@ -237,6 +233,5 @@ const struct cpu_operations cpu_psci_ops = {
 	.cpu_die	= cpu_psci_cpu_die,
 	.cpu_kill	= cpu_psci_cpu_kill,
 #endif
-#endif
 };
 

arch/arm64/kernel/ptrace.c

@@ -826,6 +826,30 @@ static int compat_vfp_set(struct task_struct *target,
 	return ret;
 }
 
+static int compat_tls_get(struct task_struct *target,
+			  const struct user_regset *regset, unsigned int pos,
+			  unsigned int count, void *kbuf, void __user *ubuf)
+{
+	compat_ulong_t tls = (compat_ulong_t)target->thread.tp_value;
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
+}
+
+static int compat_tls_set(struct task_struct *target,
+			  const struct user_regset *regset, unsigned int pos,
+			  unsigned int count, const void *kbuf,
+			  const void __user *ubuf)
+{
+	int ret;
+	compat_ulong_t tls;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
+	if (ret)
+		return ret;
+
+	target->thread.tp_value = tls;
+	return ret;
+}
+
 static const struct user_regset aarch32_regsets[] = {
 	[REGSET_COMPAT_GPR] = {
 		.core_note_type = NT_PRSTATUS,
@@ -850,6 +874,64 @@ static const struct user_regset_view user_aarch32_view = {
 	.regsets = aarch32_regsets, .n = ARRAY_SIZE(aarch32_regsets)
 };
 
+static const struct user_regset aarch32_ptrace_regsets[] = {
+	[REGSET_GPR] = {
+		.core_note_type = NT_PRSTATUS,
+		.n = COMPAT_ELF_NGREG,
+		.size = sizeof(compat_elf_greg_t),
+		.align = sizeof(compat_elf_greg_t),
+		.get = compat_gpr_get,
+		.set = compat_gpr_set
+	},
+	[REGSET_FPR] = {
+		.core_note_type = NT_ARM_VFP,
+		.n = VFP_STATE_SIZE / sizeof(compat_ulong_t),
+		.size = sizeof(compat_ulong_t),
+		.align = sizeof(compat_ulong_t),
+		.get = compat_vfp_get,
+		.set = compat_vfp_set
+	},
+	[REGSET_TLS] = {
+		.core_note_type = NT_ARM_TLS,
+		.n = 1,
+		.size = sizeof(compat_ulong_t),
+		.align = sizeof(compat_ulong_t),
+		.get = compat_tls_get,
+		.set = compat_tls_set,
+	},
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	[REGSET_HW_BREAK] = {
+		.core_note_type = NT_ARM_HW_BREAK,
+		.n = sizeof(struct user_hwdebug_state) / sizeof(u32),
+		.size = sizeof(u32),
+		.align = sizeof(u32),
+		.get = hw_break_get,
+		.set = hw_break_set,
+	},
+	[REGSET_HW_WATCH] = {
+		.core_note_type = NT_ARM_HW_WATCH,
+		.n = sizeof(struct user_hwdebug_state) / sizeof(u32),
+		.size = sizeof(u32),
+		.align = sizeof(u32),
+		.get = hw_break_get,
+		.set = hw_break_set,
+	},
+#endif
+	[REGSET_SYSTEM_CALL] = {
+		.core_note_type = NT_ARM_SYSTEM_CALL,
+		.n = 1,
+		.size = sizeof(int),
+		.align = sizeof(int),
+		.get = system_call_get,
+		.set = system_call_set,
+	},
+};
+
+static const struct user_regset_view user_aarch32_ptrace_view = {
+	.name = "aarch32", .e_machine = EM_ARM,
+	.regsets = aarch32_ptrace_regsets, .n = ARRAY_SIZE(aarch32_ptrace_regsets)
+};
+
 static int compat_ptrace_read_user(struct task_struct *tsk, compat_ulong_t off,
 				   compat_ulong_t __user *ret)
 {
@@ -1109,8 +1191,16 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 {
 #ifdef CONFIG_COMPAT
-	if (is_compat_thread(task_thread_info(task)))
+	/*
+	 * Core dumping of 32-bit tasks or compat ptrace requests must use the
+	 * user_aarch32_view compatible with arm32. Native ptrace requests on
+	 * 32-bit children use an extended user_aarch32_ptrace_view to allow
+	 * access to the TLS register.
+	 */
+	if (is_compat_task())
 		return &user_aarch32_view;
+	else if (is_compat_thread(task_thread_info(task)))
+		return &user_aarch32_ptrace_view;
 #endif
 	return &user_aarch64_view;
 }

arch/arm64/kernel/setup.c

@@ -62,7 +62,6 @@
 #include <asm/traps.h>
 #include <asm/memblock.h>
 #include <asm/efi.h>
-#include <asm/virt.h>
 #include <asm/xen/hypervisor.h>
 
 unsigned long elf_hwcap __read_mostly;
@@ -130,7 +129,6 @@ bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 }
 
 struct mpidr_hash mpidr_hash;
-#ifdef CONFIG_SMP
 /**
  * smp_build_mpidr_hash - Pre-compute shifts required at each affinity
  *			  level in order to build a linear index from an
@@ -196,35 +194,11 @@ static void __init smp_build_mpidr_hash(void)
 		pr_warn("Large number of MPIDR hash buckets detected\n");
 	__flush_dcache_area(&mpidr_hash, sizeof(struct mpidr_hash));
 }
-#endif
-
-static void __init hyp_mode_check(void)
-{
-	if (is_hyp_mode_available())
-		pr_info("CPU: All CPU(s) started at EL2\n");
-	else if (is_hyp_mode_mismatched())
-		WARN_TAINT(1, TAINT_CPU_OUT_OF_SPEC,
-			   "CPU: CPUs started in inconsistent modes");
-	else
-		pr_info("CPU: All CPU(s) started at EL1\n");
-}
-
-void __init do_post_cpus_up_work(void)
-{
-	hyp_mode_check();
-	apply_alternatives_all();
-}
-
-#ifdef CONFIG_UP_LATE_INIT
-void __init up_late_init(void)
-{
-	do_post_cpus_up_work();
-}
-#endif /* CONFIG_UP_LATE_INIT */
 
 static void __init setup_processor(void)
 {
-	u64 features, block;
+	u64 features;
+	s64 block;
 	u32 cwg;
 	int cls;
 
@@ -254,8 +228,8 @@ static void __init setup_processor(void)
 	 * for non-negative values. Negative values are reserved.
 	 */
 	features = read_cpuid(ID_AA64ISAR0_EL1);
-	block = (features >> 4) & 0xf;
+	block = cpuid_feature_extract_field(features, 4);
-	if (!(block & 0x8)) {
+	if (block > 0) {
 		switch (block) {
 		default:
 		case 2:
@@ -267,26 +241,36 @@ static void __init setup_processor(void)
 		}
 	}
 
-	block = (features >> 8) & 0xf;
+	if (cpuid_feature_extract_field(features, 8) > 0)
-	if (block && !(block & 0x8))
 		elf_hwcap |= HWCAP_SHA1;
 
-	block = (features >> 12) & 0xf;
+	if (cpuid_feature_extract_field(features, 12) > 0)
-	if (block && !(block & 0x8))
 		elf_hwcap |= HWCAP_SHA2;
 
-	block = (features >> 16) & 0xf;
+	if (cpuid_feature_extract_field(features, 16) > 0)
-	if (block && !(block & 0x8))
 		elf_hwcap |= HWCAP_CRC32;
 
+	block = cpuid_feature_extract_field(features, 20);
+	if (block > 0) {
+		switch (block) {
+		default:
+		case 2:
+			elf_hwcap |= HWCAP_ATOMICS;
+		case 1:
+			/* RESERVED */
+		case 0:
+			break;
+		}
+	}
+
 #ifdef CONFIG_COMPAT
 	/*
 	 * ID_ISAR5_EL1 carries similar information as above, but pertaining to
-	 * the Aarch32 32-bit execution state.
+	 * the AArch32 32-bit execution state.
 	 */
 	features = read_cpuid(ID_ISAR5_EL1);
-	block = (features >> 4) & 0xf;
+	block = cpuid_feature_extract_field(features, 4);
-	if (!(block & 0x8)) {
+	if (block > 0) {
 		switch (block) {
 		default:
 		case 2:
@@ -298,16 +282,13 @@ static void __init setup_processor(void)
 		}
 	}
 
-	block = (features >> 8) & 0xf;
+	if (cpuid_feature_extract_field(features, 8) > 0)
-	if (block && !(block & 0x8))
 		compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA1;
 
-	block = (features >> 12) & 0xf;
+	if (cpuid_feature_extract_field(features, 12) > 0)
-	if (block && !(block & 0x8))
 		compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA2;
 
-	block = (features >> 16) & 0xf;
+	if (cpuid_feature_extract_field(features, 16) > 0)
-	if (block && !(block & 0x8))
 		compat_elf_hwcap2 |= COMPAT_HWCAP2_CRC32;
 #endif
 }
@@ -404,10 +385,8 @@ void __init setup_arch(char **cmdline_p)
 	xen_early_init();
 
 	cpu_read_bootcpu_ops();
-#ifdef CONFIG_SMP
 	smp_init_cpus();
 	smp_build_mpidr_hash();
-#endif
 
 #ifdef CONFIG_VT
 #if defined(CONFIG_VGA_CONSOLE)
@@ -426,8 +405,13 @@ void __init setup_arch(char **cmdline_p)
 
 static int __init arm64_device_init(void)
 {
-	of_iommu_init();
+	if (of_have_populated_dt()) {
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+		of_iommu_init();
+		of_platform_populate(NULL, of_default_bus_match_table,
+				     NULL, NULL);
+	} else if (acpi_disabled) {
+		pr_crit("Device tree not populated\n");
+	}
 	return 0;
 }
 arch_initcall_sync(arm64_device_init);
@@ -455,6 +439,7 @@ static const char *hwcap_str[] = {
 	"sha1",
 	"sha2",
 	"crc32",
+	"atomics",
 	NULL
 };
 
@@ -507,9 +492,7 @@ static int c_show(struct seq_file *m, void *v)
 		 * online processors, looking for lines beginning with
 		 * "processor".  Give glibc what it expects.
 		 */
-#ifdef CONFIG_SMP
 		seq_printf(m, "processor\t: %d\n", i);
-#endif
 
 		/*
 		 * Dump out the common processor features in a single line.

arch/arm64/kernel/sleep.S

@@ -82,7 +82,6 @@ ENTRY(__cpu_suspend_enter)
 	str	x2, [x0, #CPU_CTX_SP]
 	ldr	x1, =sleep_save_sp
 	ldr	x1, [x1, #SLEEP_SAVE_SP_VIRT]
-#ifdef CONFIG_SMP
 	mrs	x7, mpidr_el1
 	ldr	x9, =mpidr_hash
 	ldr	x10, [x9, #MPIDR_HASH_MASK]
@@ -94,7 +93,6 @@ ENTRY(__cpu_suspend_enter)
 	ldp	w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)]
 	compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10
 	add	x1, x1, x8, lsl #3
-#endif
 	bl	__cpu_suspend_save
 	/*
 	 * Grab suspend finisher in x20 and its argument in x19
@@ -135,6 +133,14 @@ ENTRY(cpu_resume_mmu)
 	ldr	x3, =cpu_resume_after_mmu
 	msr	sctlr_el1, x0		// restore sctlr_el1
 	isb
+	/*
+	 * 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
 	br	x3			// global jump to virtual address
 ENDPROC(cpu_resume_mmu)
 	.popsection
@@ -151,7 +157,6 @@ ENDPROC(cpu_resume_after_mmu)
 
 ENTRY(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
-#ifdef CONFIG_SMP
 	mrs	x1, mpidr_el1
 	adrp	x8, mpidr_hash
 	add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address
@@ -161,9 +166,6 @@ ENTRY(cpu_resume)
 	ldp	w5, w6, [x8, #(MPIDR_HASH_SHIFTS + 8)]
 	compute_mpidr_hash x7, x3, x4, x5, x6, x1, x2
         /* x7 contains hash index, let's use it to grab context pointer */
-#else
-	mov	x7, xzr
-#endif
 	ldr_l	x0, sleep_save_sp + SLEEP_SAVE_SP_PHYS
 	ldr	x0, [x0, x7, lsl #3]
 	/* load sp from context */

arch/arm64/kernel/smp.c

@@ -52,6 +52,7 @@
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
+#include <asm/virt.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/ipi.h>
@@ -310,10 +311,22 @@ void cpu_die(void)
 }
 #endif
 
+static void __init hyp_mode_check(void)
+{
+	if (is_hyp_mode_available())
+		pr_info("CPU: All CPU(s) started at EL2\n");
+	else if (is_hyp_mode_mismatched())
+		WARN_TAINT(1, TAINT_CPU_OUT_OF_SPEC,
+			   "CPU: CPUs started in inconsistent modes");
+	else
+		pr_info("CPU: All CPU(s) started at EL1\n");
+}
+
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
-	do_post_cpus_up_work();
+	hyp_mode_check();
+	apply_alternatives_all();
 }
 
 void __init smp_prepare_boot_cpu(void)

arch/arm64/kernel/time.c

@@ -42,7 +42,6 @@
 #include <asm/thread_info.h>
 #include <asm/stacktrace.h>
 
-#ifdef CONFIG_SMP
 unsigned long profile_pc(struct pt_regs *regs)
 {
 	struct stackframe frame;
@@ -62,7 +61,6 @@ unsigned long profile_pc(struct pt_regs *regs)
 	return frame.pc;
 }
 EXPORT_SYMBOL(profile_pc);
-#endif
 
 void __init time_init(void)
 {

arch/arm64/kernel/topology.c

@@ -300,6 +300,6 @@ void __init init_cpu_topology(void)
 	 * Discard anything that was parsed if we hit an error so we
 	 * don't use partial information.
 	 */
-	if (parse_dt_topology())
+	if (of_have_populated_dt() && parse_dt_topology())
 		reset_cpu_topology();
 }

arch/arm64/kernel/traps.c

@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/bug.h>
 #include <linux/signal.h>
 #include <linux/personality.h>
 #include <linux/kallsyms.h>
@@ -32,8 +33,10 @@
 #include <linux/syscalls.h>
 
 #include <asm/atomic.h>
+#include <asm/bug.h>
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
+#include <asm/insn.h>
 #include <asm/traps.h>
 #include <asm/stacktrace.h>
 #include <asm/exception.h>
@@ -52,11 +55,12 @@ int show_unhandled_signals = 1;
  * Dump out the contents of some memory nicely...
  */
 static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
-		     unsigned long top)
+		     unsigned long top, bool compat)
 {
 	unsigned long first;
 	mm_segment_t fs;
 	int i;
+	unsigned int width = compat ? 4 : 8;
 
 	/*
 	 * We need to switch to kernel mode so that we can use __get_user
@@ -75,13 +79,22 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
 		memset(str, ' ', sizeof(str));
 		str[sizeof(str) - 1] = '\0';
 
-		for (p = first, i = 0; i < 8 && p < top; i++, p += 4) {
+		for (p = first, i = 0; i < (32 / width)
+					&& p < top; i++, p += width) {
 			if (p >= bottom && p < top) {
-				unsigned int val;
+				unsigned long val;
-				if (__get_user(val, (unsigned int *)p) == 0)
+
-					sprintf(str + i * 9, " %08x", val);
+				if (width == 8) {
-				else
+					if (__get_user(val, (unsigned long *)p) == 0)
-					sprintf(str + i * 9, " ????????");
+						sprintf(str + i * 17, " %016lx", val);
+					else
+						sprintf(str + i * 17, " ????????????????");
+				} else {
+					if (__get_user(val, (unsigned int *)p) == 0)
+						sprintf(str + i * 9, " %08lx", val);
+					else
+						sprintf(str + i * 9, " ????????");
+				}
 			}
 		}
 		printk("%s%04lx:%s\n", lvl, first & 0xffff, str);
@@ -95,7 +108,7 @@ static void dump_backtrace_entry(unsigned long where, unsigned long stack)
 	print_ip_sym(where);
 	if (in_exception_text(where))
 		dump_mem("", "Exception stack", stack,
-			 stack + sizeof(struct pt_regs));
+			 stack + sizeof(struct pt_regs), false);
 }
 
 static void dump_instr(const char *lvl, struct pt_regs *regs)
@@ -179,11 +192,7 @@ void show_stack(struct task_struct *tsk, unsigned long *sp)
 #else
 #define S_PREEMPT ""
 #endif
-#ifdef CONFIG_SMP
 #define S_SMP " SMP"
-#else
-#define S_SMP ""
-#endif
 
 static int __die(const char *str, int err, struct thread_info *thread,
 		 struct pt_regs *regs)
@@ -207,7 +216,8 @@ static int __die(const char *str, int err, struct thread_info *thread,
 
 	if (!user_mode(regs) || in_interrupt()) {
 		dump_mem(KERN_EMERG, "Stack: ", regs->sp,
-			 THREAD_SIZE + (unsigned long)task_stack_page(tsk));
+			 THREAD_SIZE + (unsigned long)task_stack_page(tsk),
+			 compat_user_mode(regs));
 		dump_backtrace(regs, tsk);
 		dump_instr(KERN_EMERG, regs);
 	}
@@ -459,7 +469,63 @@ void __pgd_error(const char *file, int line, unsigned long val)
 	pr_crit("%s:%d: bad pgd %016lx.\n", file, line, val);
 }
 
+/* GENERIC_BUG traps */
+
+int is_valid_bugaddr(unsigned long addr)
+{
+	/*
+	 * bug_handler() only called for BRK #BUG_BRK_IMM.
+	 * So the answer is trivial -- any spurious instances with no
+	 * bug table entry will be rejected by report_bug() and passed
+	 * back to the debug-monitors code and handled as a fatal
+	 * unexpected debug exception.
+	 */
+	return 1;
+}
+
+static int bug_handler(struct pt_regs *regs, unsigned int esr)
+{
+	if (user_mode(regs))
+		return DBG_HOOK_ERROR;
+
+	switch (report_bug(regs->pc, regs)) {
+	case BUG_TRAP_TYPE_BUG:
+		die("Oops - BUG", regs, 0);
+		break;
+
+	case BUG_TRAP_TYPE_WARN:
+		/* Ideally, report_bug() should backtrace for us... but no. */
+		dump_backtrace(regs, NULL);
+		break;
+
+	default:
+		/* unknown/unrecognised bug trap type */
+		return DBG_HOOK_ERROR;
+	}
+
+	/* If thread survives, skip over the BUG instruction and continue: */
+	regs->pc += AARCH64_INSN_SIZE;	/* skip BRK and resume */
+	return DBG_HOOK_HANDLED;
+}
+
+static struct break_hook bug_break_hook = {
+	.esr_val = 0xf2000000 | BUG_BRK_IMM,
+	.esr_mask = 0xffffffff,
+	.fn = bug_handler,
+};
+
+/*
+ * Initial handler for AArch64 BRK exceptions
+ * This handler only used until debug_traps_init().
+ */
+int __init early_brk64(unsigned long addr, unsigned int esr,
+		struct pt_regs *regs)
+{
+	return bug_handler(regs, esr) != DBG_HOOK_HANDLED;
+}
+
+/* This registration must happen early, before debug_traps_init(). */
 void __init trap_init(void)
 {
-	return;
+	register_break_hook(&bug_break_hook);
 }

arch/arm64/kvm/hyp.S

@@ -810,7 +810,11 @@
  * Call into the vgic backend for state saving
  */
 .macro save_vgic_state
-	alternative_insn "bl __save_vgic_v2_state", "bl __save_vgic_v3_state", ARM64_HAS_SYSREG_GIC_CPUIF
+alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF
+	bl	__save_vgic_v2_state
+alternative_else
+	bl	__save_vgic_v3_state
+alternative_endif
 	mrs	x24, hcr_el2
 	mov	x25, #HCR_INT_OVERRIDE
 	neg	x25, x25
@@ -827,7 +831,11 @@
 	orr	x24, x24, #HCR_INT_OVERRIDE
 	orr	x24, x24, x25
 	msr	hcr_el2, x24
-	alternative_insn "bl __restore_vgic_v2_state", "bl __restore_vgic_v3_state", ARM64_HAS_SYSREG_GIC_CPUIF
+alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF
+	bl	__restore_vgic_v2_state
+alternative_else
+	bl	__restore_vgic_v3_state
+alternative_endif
 .endm
 
 .macro save_timer_state

arch/arm64/lib/Makefile

@@ -3,3 +3,16 @@ lib-y		:= bitops.o clear_user.o delay.o copy_from_user.o	\
 		   clear_page.o memchr.o memcpy.o memmove.o memset.o	\
 		   memcmp.o strcmp.o strncmp.o strlen.o strnlen.o	\
 		   strchr.o strrchr.o
+
+# Tell the compiler to treat all general purpose registers as
+# callee-saved, which allows for efficient runtime patching of the bl
+# instruction in the caller with an atomic instruction when supported by
+# the CPU. Result and argument registers are handled correctly, based on
+# the function prototype.
+lib-$(CONFIG_ARM64_LSE_ATOMICS) += atomic_ll_sc.o
+CFLAGS_atomic_ll_sc.o	:= -fcall-used-x0 -ffixed-x1 -ffixed-x2		\
+		   -ffixed-x3 -ffixed-x4 -ffixed-x5 -ffixed-x6		\
+		   -ffixed-x7 -fcall-saved-x8 -fcall-saved-x9		\
+		   -fcall-saved-x10 -fcall-saved-x11 -fcall-saved-x12	\
+		   -fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15	\
+		   -fcall-saved-x16 -fcall-saved-x17 -fcall-saved-x18

arch/arm64/lib/atomic_ll_sc.c

@@ -0,0 +1,3 @@
+#include <asm/atomic.h>
+#define __ARM64_IN_ATOMIC_IMPL
+#include <asm/atomic_ll_sc.h>

arch/arm64/lib/bitops.S

@@ -18,52 +18,59 @@
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <asm/lse.h>
 
 /*
  * x0: bits 5:0  bit offset
  *     bits 31:6 word offset
  * x1: address
  */
-	.macro	bitop, name, instr
+	.macro	bitop, name, llsc, lse
 ENTRY(	\name	)
 	and	w3, w0, #63		// Get bit offset
 	eor	w0, w0, w3		// Clear low bits
 	mov	x2, #1
 	add	x1, x1, x0, lsr #3	// Get word offset
+alt_lse "	prfm	pstl1strm, [x1]",	"nop"
 	lsl	x3, x2, x3		// Create mask
-1:	ldxr	x2, [x1]
+
-	\instr	x2, x2, x3
+alt_lse	"1:	ldxr	x2, [x1]",		"\lse	x3, [x1]"
-	stxr	w0, x2, [x1]
+alt_lse	"	\llsc	x2, x2, x3",		"nop"
-	cbnz	w0, 1b
+alt_lse	"	stxr	w0, x2, [x1]",		"nop"
+alt_lse	"	cbnz	w0, 1b",		"nop"
+
 	ret
 ENDPROC(\name	)
 	.endm
 
-	.macro	testop, name, instr
+	.macro	testop, name, llsc, lse
 ENTRY(	\name	)
 	and	w3, w0, #63		// Get bit offset
 	eor	w0, w0, w3		// Clear low bits
 	mov	x2, #1
 	add	x1, x1, x0, lsr #3	// Get word offset
+alt_lse "	prfm	pstl1strm, [x1]",	"nop"
 	lsl	x4, x2, x3		// Create mask
-1:	ldxr	x2, [x1]
+
-	lsr	x0, x2, x3		// Save old value of bit
+alt_lse	"1:	ldxr	x2, [x1]",		"\lse	x4, x2, [x1]"
-	\instr	x2, x2, x4		// toggle bit
+	lsr	x0, x2, x3
-	stlxr	w5, x2, [x1]
+alt_lse	"	\llsc	x2, x2, x4",		"nop"
-	cbnz	w5, 1b
+alt_lse	"	stlxr	w5, x2, [x1]",		"nop"
-	dmb	ish
+alt_lse	"	cbnz	w5, 1b",		"nop"
+alt_lse	"	dmb	ish",			"nop"
+
 	and	x0, x0, #1
-3:	ret
+	ret
 ENDPROC(\name	)
 	.endm
 
 /*
  * Atomic bit operations.
  */
-	bitop	change_bit, eor
+	bitop	change_bit, eor, steor
-	bitop	clear_bit, bic
+	bitop	clear_bit, bic, stclr
-	bitop	set_bit, orr
+	bitop	set_bit, orr, stset
 
-	testop	test_and_change_bit, eor
+	testop	test_and_change_bit, eor, ldeoral
-	testop	test_and_clear_bit, bic
+	testop	test_and_clear_bit, bic, ldclral
-	testop	test_and_set_bit, orr
+	testop	test_and_set_bit, orr, ldsetal

arch/arm64/lib/clear_user.S

@@ -16,7 +16,11 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #include <linux/linkage.h>
+
+#include <asm/alternative.h>
 #include <asm/assembler.h>
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
 
 	.text
 
@@ -29,6 +33,8 @@
  * Alignment fixed up by hardware.
  */
 ENTRY(__clear_user)
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \
+	    CONFIG_ARM64_PAN)
 	mov	x2, x1			// save the size for fixup return
 	subs	x1, x1, #8
 	b.mi	2f
@@ -48,6 +54,8 @@ USER(9f, strh	wzr, [x0], #2	)
 	b.mi	5f
 USER(9f, strb	wzr, [x0]	)
 5:	mov	x0, #0
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \
+	    CONFIG_ARM64_PAN)
 	ret
 ENDPROC(__clear_user)
 

arch/arm64/lib/copy_from_user.S

@@ -15,7 +15,11 @@
  */
 
 #include <linux/linkage.h>
+
+#include <asm/alternative.h>
 #include <asm/assembler.h>
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
 
 /*
  * Copy from user space to a kernel buffer (alignment handled by the hardware)
@@ -28,14 +32,21 @@
  *	x0 - bytes not copied
  */
 ENTRY(__copy_from_user)
-	add	x4, x1, x2			// upper user buffer boundary
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \
-	subs	x2, x2, #8
+	    CONFIG_ARM64_PAN)
+	add	x5, x1, x2			// upper user buffer boundary
+	subs	x2, x2, #16
+	b.mi	1f
+0:
+USER(9f, ldp	x3, x4, [x1], #16)
+	subs	x2, x2, #16
+	stp	x3, x4, [x0], #16
+	b.pl	0b
+1:	adds	x2, x2, #8
 	b.mi	2f
-1:
 USER(9f, ldr	x3, [x1], #8	)
-	subs	x2, x2, #8
+	sub	x2, x2, #8
 	str	x3, [x0], #8
-	b.pl	1b
 2:	adds	x2, x2, #4
 	b.mi	3f
 USER(9f, ldr	w3, [x1], #4	)
@@ -51,12 +62,14 @@ USER(9f, ldrh	w3, [x1], #2	)
 USER(9f, ldrb	w3, [x1]	)
 	strb	w3, [x0]
 5:	mov	x0, #0
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \
+	    CONFIG_ARM64_PAN)
 	ret
 ENDPROC(__copy_from_user)
 
 	.section .fixup,"ax"
 	.align	2
-9:	sub	x2, x4, x1
+9:	sub	x2, x5, x1
 	mov	x3, x2
 10:	strb	wzr, [x0], #1			// zero remaining buffer space
 	subs	x3, x3, #1

arch/arm64/lib/copy_in_user.S

@@ -17,7 +17,11 @@
  */
 
 #include <linux/linkage.h>
+
+#include <asm/alternative.h>
 #include <asm/assembler.h>
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
 
 /*
  * Copy from user space to user space (alignment handled by the hardware)
@@ -30,14 +34,21 @@
  *	x0 - bytes not copied
  */
 ENTRY(__copy_in_user)
-	add	x4, x0, x2			// upper user buffer boundary
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \
-	subs	x2, x2, #8
+	    CONFIG_ARM64_PAN)
+	add	x5, x0, x2			// upper user buffer boundary
+	subs	x2, x2, #16
+	b.mi	1f
+0:
+USER(9f, ldp	x3, x4, [x1], #16)
+	subs	x2, x2, #16
+USER(9f, stp	x3, x4, [x0], #16)
+	b.pl	0b
+1:	adds	x2, x2, #8
 	b.mi	2f
-1:
 USER(9f, ldr	x3, [x1], #8	)
-	subs	x2, x2, #8
+	sub	x2, x2, #8
 USER(9f, str	x3, [x0], #8	)
-	b.pl	1b
 2:	adds	x2, x2, #4
 	b.mi	3f
 USER(9f, ldr	w3, [x1], #4	)
@@ -53,11 +64,13 @@ USER(9f, strh	w3, [x0], #2	)
 USER(9f, ldrb	w3, [x1]	)
 USER(9f, strb	w3, [x0]	)
 5:	mov	x0, #0
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \
+	    CONFIG_ARM64_PAN)
 	ret
 ENDPROC(__copy_in_user)
 
 	.section .fixup,"ax"
 	.align	2
-9:	sub	x0, x4, x0			// bytes not copied
+9:	sub	x0, x5, x0			// bytes not copied
 	ret
 	.previous

arch/arm64/lib/copy_to_user.S

@@ -15,7 +15,11 @@
  */
 
 #include <linux/linkage.h>
+
+#include <asm/alternative.h>
 #include <asm/assembler.h>
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
 
 /*
  * Copy to user space from a kernel buffer (alignment handled by the hardware)
@@ -28,14 +32,21 @@
  *	x0 - bytes not copied
  */
 ENTRY(__copy_to_user)
-	add	x4, x0, x2			// upper user buffer boundary
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \
-	subs	x2, x2, #8
+	    CONFIG_ARM64_PAN)
+	add	x5, x0, x2			// upper user buffer boundary
+	subs	x2, x2, #16
+	b.mi	1f
+0:
+	ldp	x3, x4, [x1], #16
+	subs	x2, x2, #16
+USER(9f, stp	x3, x4, [x0], #16)
+	b.pl	0b
+1:	adds	x2, x2, #8
 	b.mi	2f
-1:
 	ldr	x3, [x1], #8
-	subs	x2, x2, #8
+	sub	x2, x2, #8
 USER(9f, str	x3, [x0], #8	)
-	b.pl	1b
 2:	adds	x2, x2, #4
 	b.mi	3f
 	ldr	w3, [x1], #4
@@ -51,11 +62,13 @@ USER(9f, strh	w3, [x0], #2	)
 	ldrb	w3, [x1]
 USER(9f, strb	w3, [x0]	)
 5:	mov	x0, #0
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \
+	    CONFIG_ARM64_PAN)
 	ret
 ENDPROC(__copy_to_user)
 
 	.section .fixup,"ax"
 	.align	2
-9:	sub	x0, x4, x0			// bytes not copied
+9:	sub	x0, x5, x0			// bytes not copied
 	ret
 	.previous

arch/arm64/mm/cache.S

@@ -143,7 +143,12 @@ __dma_clean_range:
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	bic	x0, x0, x3
-1:	alternative_insn "dc cvac, x0", "dc civac, x0", ARM64_WORKAROUND_CLEAN_CACHE
+1:
+alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
+	dc	cvac, x0
+alternative_else
+	dc	civac, x0
+alternative_endif
 	add	x0, x0, x2
 	cmp	x0, x1
 	b.lo	1b

arch/arm64/mm/context.c

@@ -53,8 +53,6 @@ static void flush_context(void)
 		__flush_icache_all();
 }
 
-#ifdef CONFIG_SMP
-
 static void set_mm_context(struct mm_struct *mm, unsigned int asid)
 {
 	unsigned long flags;
@@ -110,23 +108,12 @@ static void reset_context(void *info)
 	cpu_switch_mm(mm->pgd, mm);
 }
 
-#else
-
-static inline void set_mm_context(struct mm_struct *mm, unsigned int asid)
-{
-	mm->context.id = asid;
-	cpumask_copy(mm_cpumask(mm), cpumask_of(smp_processor_id()));
-}
-
-#endif
-
 void __new_context(struct mm_struct *mm)
 {
 	unsigned int asid;
 	unsigned int bits = asid_bits();
 
 	raw_spin_lock(&cpu_asid_lock);
-#ifdef CONFIG_SMP
 	/*
 	 * Check the ASID again, in case the change was broadcast from another
 	 * CPU before we acquired the lock.
@@ -136,7 +123,6 @@ void __new_context(struct mm_struct *mm)
 		raw_spin_unlock(&cpu_asid_lock);
 		return;
 	}
-#endif
 	/*
 	 * At this point, it is guaranteed that the current mm (with an old
 	 * ASID) isn't active on any other CPU since the ASIDs are changed
@@ -155,10 +141,8 @@ void __new_context(struct mm_struct *mm)
 			cpu_last_asid = ASID_FIRST_VERSION;
 		asid = cpu_last_asid + smp_processor_id();
 		flush_context();
-#ifdef CONFIG_SMP
 		smp_wmb();
 		smp_call_function(reset_context, NULL, 1);
-#endif
 		cpu_last_asid += NR_CPUS - 1;
 	}
 

arch/arm64/mm/dma-mapping.c

@@ -144,6 +144,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
 	struct page *page;
 	void *ptr, *coherent_ptr;
 	bool coherent = is_device_dma_coherent(dev);
+	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, false);
 
 	size = PAGE_ALIGN(size);
 
@@ -171,9 +172,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
 	/* create a coherent mapping */
 	page = virt_to_page(ptr);
 	coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP,
-				__get_dma_pgprot(attrs,
+						   prot, NULL);
-					__pgprot(PROT_NORMAL_NC), false),
-					NULL);
 	if (!coherent_ptr)
 		goto no_map;
 
@@ -303,9 +302,10 @@ static void __swiotlb_sync_sg_for_device(struct device *dev,
 				       sg->length, dir);
 }
 
-/* vma->vm_page_prot must be set appropriately before calling this function */
+static int __swiotlb_mmap(struct device *dev,
-static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+			  struct vm_area_struct *vma,
-			     void *cpu_addr, dma_addr_t dma_addr, size_t size)
+			  void *cpu_addr, dma_addr_t dma_addr, size_t size,
+			  struct dma_attrs *attrs)
 {
 	int ret = -ENXIO;
 	unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >>
@@ -314,6 +314,9 @@ static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 	unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
 	unsigned long off = vma->vm_pgoff;
 
+	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
+					     is_device_dma_coherent(dev));
+
 	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
 		return ret;
 
@@ -327,20 +330,24 @@ static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 	return ret;
 }
 
-static int __swiotlb_mmap(struct device *dev,
+static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
-			  struct vm_area_struct *vma,
+				 void *cpu_addr, dma_addr_t handle, size_t size,
-			  void *cpu_addr, dma_addr_t dma_addr, size_t size,
+				 struct dma_attrs *attrs)
-			  struct dma_attrs *attrs)
 {
-	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
+	int ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
-					     is_device_dma_coherent(dev));
+
-	return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+	if (!ret)
+		sg_set_page(sgt->sgl, phys_to_page(dma_to_phys(dev, handle)),
+			    PAGE_ALIGN(size), 0);
+
+	return ret;
 }
 
 static struct dma_map_ops swiotlb_dma_ops = {
 	.alloc = __dma_alloc,
 	.free = __dma_free,
 	.mmap = __swiotlb_mmap,
+	.get_sgtable = __swiotlb_get_sgtable,
 	.map_page = __swiotlb_map_page,
 	.unmap_page = __swiotlb_unmap_page,
 	.map_sg = __swiotlb_map_sg_attrs,

arch/arm64/mm/fault.c

@@ -30,9 +30,11 @@
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
 
+#include <asm/cpufeature.h>
 #include <asm/exception.h>
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
+#include <asm/sysreg.h>
 #include <asm/system_misc.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -223,6 +225,13 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 		mm_flags |= FAULT_FLAG_WRITE;
 	}
 
+	/*
+	 * PAN bit set implies the fault happened in kernel space, but not
+	 * in the arch's user access functions.
+	 */
+	if (IS_ENABLED(CONFIG_ARM64_PAN) && (regs->pstate & PSR_PAN_BIT))
+		goto no_context;
+
 	/*
 	 * As per x86, we may deadlock here. However, since the kernel only
 	 * validly references user space from well defined areas of the code,
@@ -492,14 +501,22 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
 	arm64_notify_die("Oops - SP/PC alignment exception", regs, &info, esr);
 }
 
-static struct fault_info debug_fault_info[] = {
+int __init early_brk64(unsigned long addr, unsigned int esr,
+		       struct pt_regs *regs);
+
+/*
+ * __refdata because early_brk64 is __init, but the reference to it is
+ * clobbered at arch_initcall time.
+ * See traps.c and debug-monitors.c:debug_traps_init().
+ */
+static struct fault_info __refdata debug_fault_info[] = {
 	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware breakpoint"	},
 	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware single-step"	},
 	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware watchpoint"	},
 	{ do_bad,	SIGBUS,		0,		"unknown 3"		},
 	{ do_bad,	SIGTRAP,	TRAP_BRKPT,	"aarch32 BKPT"		},
 	{ do_bad,	SIGTRAP,	0,		"aarch32 vector catch"	},
-	{ do_bad,	SIGTRAP,	TRAP_BRKPT,	"aarch64 BRK"		},
+	{ early_brk64,	SIGTRAP,	TRAP_BRKPT,	"aarch64 BRK"		},
 	{ do_bad,	SIGBUS,		0,		"unknown 7"		},
 };
 
@@ -536,3 +553,10 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 
 	return 0;
 }
+
+#ifdef CONFIG_ARM64_PAN
+void cpu_enable_pan(void)
+{
+	config_sctlr_el1(SCTLR_EL1_SPAN, 0);
+}
+#endif /* CONFIG_ARM64_PAN */

arch/arm64/mm/flush.c

@@ -60,14 +60,10 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 		       unsigned long uaddr, void *dst, const void *src,
 		       unsigned long len)
 {
-#ifdef CONFIG_SMP
 	preempt_disable();
-#endif
 	memcpy(dst, src, len);
 	flush_ptrace_access(vma, page, uaddr, dst, len);
-#ifdef CONFIG_SMP
 	preempt_enable();
-#endif
 }
 
 void __sync_icache_dcache(pte_t pte, unsigned long addr)

arch/arm64/mm/hugetlbpage.c

@@ -13,10 +13,6 @@
  * 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, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
 #include <linux/init.h>

arch/arm64/mm/init.c

@@ -358,9 +358,9 @@ void free_initmem(void)
 
 #ifdef CONFIG_BLK_DEV_INITRD
 
-static int keep_initrd;
+static int keep_initrd __initdata;
 
-void free_initrd_mem(unsigned long start, unsigned long end)
+void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
 	if (!keep_initrd)
 		free_reserved_area((void *)start, (void *)end, 0, "initrd");

arch/arm64/mm/mmu.c

@@ -267,7 +267,7 @@ static void *late_alloc(unsigned long size)
 	return ptr;
 }
 
-static void __ref create_mapping(phys_addr_t phys, unsigned long virt,
+static void __init create_mapping(phys_addr_t phys, unsigned long virt,
 				  phys_addr_t size, pgprot_t prot)
 {
 	if (virt < VMALLOC_START) {
@@ -460,17 +460,6 @@ void __init paging_init(void)
 	cpu_set_default_tcr_t0sz();
 }
 
-/*
- * Enable the identity mapping to allow the MMU disabling.
- */
-void setup_mm_for_reboot(void)
-{
-	cpu_set_reserved_ttbr0();
-	flush_tlb_all();
-	cpu_set_idmap_tcr_t0sz();
-	cpu_switch_mm(idmap_pg_dir, &init_mm);
-}
-
 /*
  * Check whether a kernel address is valid (derived from arch/x86/).
  */

arch/arm64/mm/proc.S

@@ -34,11 +34,7 @@
 #define TCR_TG_FLAGS	TCR_TG0_4K | TCR_TG1_4K
 #endif
 
-#ifdef CONFIG_SMP
 #define TCR_SMP_FLAGS	TCR_SHARED
-#else
-#define TCR_SMP_FLAGS	0
-#endif
 
 /* PTWs cacheable, inner/outer WBWA */
 #define TCR_CACHE_FLAGS	TCR_IRGN_WBWA | TCR_ORGN_WBWA
@@ -150,13 +146,13 @@ ENDPROC(cpu_do_switch_mm)
  *	value of the SCTLR_EL1 register.
  */
 ENTRY(__cpu_setup)
-	ic	iallu				// I+BTB cache invalidate
 	tlbi	vmalle1is			// invalidate I + D TLBs
 	dsb	ish
 
 	mov	x0, #3 << 20
 	msr	cpacr_el1, x0			// Enable FP/ASIMD
-	msr	mdscr_el1, xzr			// Reset mdscr_el1
+	mov	x0, #1 << 12			// Reset mdscr_el1 and disable
+	msr	mdscr_el1, x0			// access to the DCC from EL0
 	/*
 	 * Memory region attributes for LPAE:
 	 *
@@ -196,6 +192,19 @@ ENTRY(__cpu_setup)
 	 */
 	mrs	x9, ID_AA64MMFR0_EL1
 	bfi	x10, x9, #32, #3
+#ifdef CONFIG_ARM64_HW_AFDBM
+	/*
+	 * Hardware update of the Access and Dirty bits.
+	 */
+	mrs	x9, ID_AA64MMFR1_EL1
+	and	x9, x9, #0xf
+	cbz	x9, 2f
+	cmp	x9, #2
+	b.lt	1f
+	orr	x10, x10, #TCR_HD		// hardware Dirty flag update
+1:	orr	x10, x10, #TCR_HA		// hardware Access flag update
+2:
+#endif	/* CONFIG_ARM64_HW_AFDBM */
 	msr	tcr_el1, x10
 	ret					// return to head.S
 ENDPROC(__cpu_setup)

drivers/of/fdt.c

@@ -967,7 +967,9 @@ int __init early_init_dt_scan_chosen(unsigned long node, const char *uname,
 }
 
 #ifdef CONFIG_HAVE_MEMBLOCK
-#define MAX_PHYS_ADDR	((phys_addr_t)~0)
+#ifndef MAX_MEMBLOCK_ADDR
+#define MAX_MEMBLOCK_ADDR	((phys_addr_t)~0)
+#endif
 
 void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
 {
@@ -984,16 +986,16 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
 	}
 	size &= PAGE_MASK;
 
-	if (base > MAX_PHYS_ADDR) {
+	if (base > MAX_MEMBLOCK_ADDR) {
 		pr_warning("Ignoring memory block 0x%llx - 0x%llx\n",
 				base, base + size);
 		return;
 	}
 
-	if (base + size - 1 > MAX_PHYS_ADDR) {
+	if (base + size - 1 > MAX_MEMBLOCK_ADDR) {
 		pr_warning("Ignoring memory range 0x%llx - 0x%llx\n",
-				((u64)MAX_PHYS_ADDR) + 1, base + size);
+				((u64)MAX_MEMBLOCK_ADDR) + 1, base + size);
-		size = MAX_PHYS_ADDR - base + 1;
+		size = MAX_MEMBLOCK_ADDR - base + 1;
 	}
 
 	if (base + size < phys_offset) {