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

…el/git/arm64/linux

Pull ARM64 updates from Catalin Marinas:
 - KGDB support for arm64
 - PCI I/O space extended to 16M (in preparation of PCIe support
   patches)
 - Dropping ZONE_DMA32 in favour of ZONE_DMA (we only need one for the
   time being), together with swiotlb late initialisation to correctly
   setup the bounce buffer
 - DMA API cache maintenance support (not all ARMv8 platforms have
   hardware cache coherency)
 - Crypto extensions advertising via ELF_HWCAP2 for compat user space
 - Perf support for dwarf unwinding in compat mode
 - asm/tlb.h converted to the generic mmu_gather code
 - asm-generic rwsem implementation
 - Code clean-up

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (42 commits)
  arm64: Remove pgprot_dmacoherent()
  arm64: Support DMA_ATTR_WRITE_COMBINE
  arm64: Implement custom mmap functions for dma mapping
  arm64: Fix __range_ok macro
  arm64: Fix duplicated Kconfig entries
  arm64: mm: Route pmd thp functions through pte equivalents
  arm64: rwsem: use asm-generic rwsem implementation
  asm-generic: rwsem: de-PPCify rwsem.h
  arm64: enable generic CPU feature modalias matching for this architecture
  arm64: smp: make local symbol static
  arm64: debug: make local symbols static
  ARM64: perf: support dwarf unwinding in compat mode
  ARM64: perf: add support for frame pointer unwinding in compat mode
  ARM64: perf: add support for perf registers API
  arm64: Add boot time configuration of Intermediate Physical Address size
  arm64: Do not synchronise I and D caches for special ptes
  arm64: Make DMA coherent and strongly ordered mappings not executable
  arm64: barriers: add dmb barrier
  arm64: topology: Implement basic CPU topology support
  arm64: advertise ARMv8 extensions to 32-bit compat ELF binaries
  ...

Documentation/arm64/memory.txt

@@ -35,11 +35,13 @@ ffffffbc00000000	ffffffbdffffffff	   8GB		vmemmap
 
 ffffffbe00000000	ffffffbffbbfffff	  ~8GB		[guard, future vmmemap]
 
-ffffffbffbc00000	ffffffbffbdfffff	   2MB		earlyprintk device
+ffffffbffa000000	ffffffbffaffffff	  16MB		PCI I/O space
+
+ffffffbffb000000	ffffffbffbbfffff	  12MB		[guard]
 
-ffffffbffbe00000	ffffffbffbe0ffff	  64KB		PCI I/O space
+ffffffbffbc00000	ffffffbffbdfffff	   2MB		earlyprintk device
 
-ffffffbffbe10000	ffffffbcffffffff	  ~2MB		[guard]
+ffffffbffbe00000	ffffffbffbffffff	   2MB		[guard]
 
 ffffffbffc000000	ffffffbfffffffff	  64MB		modules
 
@@ -60,11 +62,13 @@ fffffdfc00000000	fffffdfdffffffff	   8GB		vmemmap
 
 fffffdfe00000000	fffffdfffbbfffff	  ~8GB		[guard, future vmmemap]
 
-fffffdfffbc00000	fffffdfffbdfffff	   2MB		earlyprintk device
+fffffdfffa000000	fffffdfffaffffff	  16MB		PCI I/O space
+
+fffffdfffb000000	fffffdfffbbfffff	  12MB		[guard]
 
-fffffdfffbe00000	fffffdfffbe0ffff	  64KB		PCI I/O space
+fffffdfffbc00000	fffffdfffbdfffff	   2MB		earlyprintk device
 
-fffffdfffbe10000	fffffdfffbffffff	  ~2MB		[guard]
+fffffdfffbe00000	fffffdfffbffffff	   2MB		[guard]
 
 fffffdfffc000000	fffffdffffffffff	  64MB		modules
 

arch/arm64/Kconfig

@@ -16,6 +16,7 @@ config ARM64
 	select DCACHE_WORD_ACCESS
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_IOMAP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
@@ -26,6 +27,7 @@ config ARM64
 	select GENERIC_TIME_VSYSCALL
 	select HARDIRQS_SW_RESEND
 	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
@@ -38,6 +40,8 @@ config ARM64
 	select HAVE_MEMBLOCK
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
 	select IRQ_DOMAIN
 	select MODULES_USE_ELF_RELA
 	select NO_BOOTMEM
@@ -73,7 +77,7 @@ config LOCKDEP_SUPPORT
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
+config RWSEM_XCHGADD_ALGORITHM
 	def_bool y
 
 config GENERIC_HWEIGHT
@@ -85,7 +89,7 @@ config GENERIC_CSUM
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
-config ZONE_DMA32
+config ZONE_DMA
 	def_bool y
 
 config ARCH_DMA_ADDR_T_64BIT
@@ -164,6 +168,22 @@ config SMP
 
 	  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
+	  increased overhead in some places. If unsure say N here.
+
+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
+	  places. If unsure say N here.
+
 config NR_CPUS
 	int "Maximum number of CPUs (2-32)"
 	range 2 32
@@ -301,6 +321,8 @@ menu "CPU Power Management"
 
 source "drivers/cpuidle/Kconfig"
 
+source "drivers/cpufreq/Kconfig"
+
 endmenu
 
 source "net/Kconfig"

arch/arm64/include/asm/Kbuild

@@ -32,6 +32,7 @@ generic-y += poll.h
 generic-y += posix_types.h
 generic-y += preempt.h
 generic-y += resource.h
+generic-y += rwsem.h
 generic-y += scatterlist.h
 generic-y += sections.h
 generic-y += segment.h

arch/arm64/include/asm/barrier.h

@@ -25,6 +25,7 @@
 #define wfi()		asm volatile("wfi" : : : "memory")
 
 #define isb()		asm volatile("isb" : : : "memory")
+#define dmb(opt)	asm volatile("dmb sy" : : : "memory")
 #define dsb(opt)	asm volatile("dsb sy" : : : "memory")
 
 #define mb()		dsb()

arch/arm64/include/asm/cacheflush.h

@@ -84,6 +84,13 @@ static inline void flush_cache_page(struct vm_area_struct *vma,
 {
 }
 
+/*
+ * Cache maintenance functions used by the DMA API. No to be used directly.
+ */
+extern void __dma_map_area(const void *, size_t, int);
+extern void __dma_unmap_area(const void *, size_t, int);
+extern void __dma_flush_range(const void *, const void *);
+
 /*
  * Copy user data from/to a page which is mapped into a different
  * processes address space.  Really, we want to allow our "user

arch/arm64/include/asm/compat.h

@@ -228,7 +228,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
 	return (u32)(unsigned long)uptr;
 }
 
-#define compat_user_stack_pointer() (current_pt_regs()->compat_sp)
+#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs()))
 
 static inline void __user *arch_compat_alloc_user_space(long len)
 {

arch/arm64/include/asm/cpufeature.h

@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#ifndef __ASM_CPUFEATURE_H
+#define __ASM_CPUFEATURE_H
+
+#include <asm/hwcap.h>
+
+/*
+ * In the arm64 world (as in the ARM world), elf_hwcap is used both internally
+ * in the kernel and for user space to keep track of which optional features
+ * are supported by the current system. So let's map feature 'x' to HWCAP_x.
+ * Note that HWCAP_x constants are bit fields so we need to take the log.
+ */
+
+#define MAX_CPU_FEATURES	(8 * sizeof(elf_hwcap))
+#define cpu_feature(x)		ilog2(HWCAP_ ## x)
+
+static inline bool cpu_have_feature(unsigned int num)
+{
+	return elf_hwcap & (1UL << num);
+}
+
+#endif

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

@@ -26,6 +26,53 @@
 #define DBG_ESR_EVT_HWWP	0x2
 #define DBG_ESR_EVT_BRK		0x6
 
+/*
+ * Break point instruction encoding
+ */
+#define BREAK_INSTR_SIZE		4
+
+/*
+ * 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
+ * Allowed values for kgbd are 0x400 - 0x7ff
+ * 0x400: for dynamic BRK instruction
+ * 0x401: for compile time BRK instruction
+ */
+#define KGDB_DYN_DGB_BRK_IMM		0x400
+#define KDBG_COMPILED_DBG_BRK_IMM	0x401
+
+/*
+ * BRK instruction encoding
+ * The #imm16 value should be placed at bits[20:5] within BRK ins
+ */
+#define AARCH64_BREAK_MON	0xd4200000
+
+/*
+ * Extract byte from BRK instruction
+ */
+#define KGDB_DYN_DGB_BRK_INS_BYTE(x) \
+	((((AARCH64_BREAK_MON) & 0xffe0001f) >> (x * 8)) & 0xff)
+
+/*
+ * Extract byte from BRK #imm16
+ */
+#define KGBD_DYN_DGB_BRK_IMM_BYTE(x) \
+	(((((KGDB_DYN_DGB_BRK_IMM) & 0xffff) << 5) >> (x * 8)) & 0xff)
+
+#define KGDB_DYN_DGB_BRK_BYTE(x) \
+	(KGDB_DYN_DGB_BRK_INS_BYTE(x) | KGBD_DYN_DGB_BRK_IMM_BYTE(x))
+
+#define  KGDB_DYN_BRK_INS_BYTE0  KGDB_DYN_DGB_BRK_BYTE(0)
+#define  KGDB_DYN_BRK_INS_BYTE1  KGDB_DYN_DGB_BRK_BYTE(1)
+#define  KGDB_DYN_BRK_INS_BYTE2  KGDB_DYN_DGB_BRK_BYTE(2)
+#define  KGDB_DYN_BRK_INS_BYTE3  KGDB_DYN_DGB_BRK_BYTE(3)
+
+#define CACHE_FLUSH_IS_SAFE		1
+
 enum debug_el {
 	DBG_ACTIVE_EL0 = 0,
 	DBG_ACTIVE_EL1,
@@ -43,23 +90,6 @@ enum debug_el {
 #ifndef __ASSEMBLY__
 struct task_struct;
 
-#define local_dbg_save(flags)							\
-	do {									\
-		typecheck(unsigned long, flags);				\
-		asm volatile(							\
-		"mrs	%0, daif			// local_dbg_save\n"	\
-		"msr	daifset, #8"						\
-		: "=r" (flags) : : "memory");					\
-	} while (0)
-
-#define local_dbg_restore(flags)						\
-	do {									\
-		typecheck(unsigned long, flags);				\
-		asm volatile(							\
-		"msr	daif, %0			// local_dbg_restore\n"	\
-		: : "r" (flags) : "memory");					\
-	} while (0)
-
 #define DBG_ARCH_ID_RESERVED	0	/* In case of ptrace ABI updates. */
 
 #define DBG_HOOK_HANDLED	0

arch/arm64/include/asm/dma-mapping.h

@@ -30,6 +30,8 @@
 
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
 extern struct dma_map_ops *dma_ops;
+extern struct dma_map_ops coherent_swiotlb_dma_ops;
+extern struct dma_map_ops noncoherent_swiotlb_dma_ops;
 
 static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
@@ -47,6 +49,11 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 		return __generic_dma_ops(dev);
 }
 
+static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
+{
+	dev->archdata.dma_ops = ops;
+}
+
 #include <asm-generic/dma-mapping-common.h>
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)

arch/arm64/include/asm/hwcap.h

@@ -32,6 +32,12 @@
 #define COMPAT_HWCAP_IDIV	(COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT)
 #define COMPAT_HWCAP_EVTSTRM	(1 << 21)
 
+#define COMPAT_HWCAP2_AES	(1 << 0)
+#define COMPAT_HWCAP2_PMULL	(1 << 1)
+#define COMPAT_HWCAP2_SHA1	(1 << 2)
+#define COMPAT_HWCAP2_SHA2	(1 << 3)
+#define COMPAT_HWCAP2_CRC32	(1 << 4)
+
 #ifndef __ASSEMBLY__
 /*
  * This yields a mask that user programs can use to figure out what
@@ -41,7 +47,8 @@
 
 #ifdef CONFIG_COMPAT
 #define COMPAT_ELF_HWCAP	(compat_elf_hwcap)
-extern unsigned int compat_elf_hwcap;
+#define COMPAT_ELF_HWCAP2	(compat_elf_hwcap2)
+extern unsigned int compat_elf_hwcap, compat_elf_hwcap2;
 #endif
 
 extern unsigned long elf_hwcap;

arch/arm64/include/asm/io.h

@@ -121,7 +121,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
  *  I/O port access primitives.
  */
 #define IO_SPACE_LIMIT		0xffff
-#define PCI_IOBASE		((void __iomem *)(MODULES_VADDR - SZ_2M))
+#define PCI_IOBASE		((void __iomem *)(MODULES_VADDR - SZ_32M))
 
 static inline u8 inb(unsigned long addr)
 {

arch/arm64/include/asm/irqflags.h

@@ -90,5 +90,28 @@ static inline int arch_irqs_disabled_flags(unsigned long flags)
 	return flags & PSR_I_BIT;
 }
 
+/*
+ * save and restore debug state
+ */
+#define local_dbg_save(flags)						\
+	do {								\
+		typecheck(unsigned long, flags);			\
+		asm volatile(						\
+		"mrs    %0, daif		// local_dbg_save\n"	\
+		"msr    daifset, #8"					\
+		: "=r" (flags) : : "memory");				\
+	} while (0)
+
+#define local_dbg_restore(flags)					\
+	do {								\
+		typecheck(unsigned long, flags);			\
+		asm volatile(						\
+		"msr    daif, %0		// local_dbg_restore\n"	\
+		: : "r" (flags) : "memory");				\
+	} while (0)
+
+#define local_dbg_enable()	asm("msr	daifclr, #8" : : : "memory")
+#define local_dbg_disable()	asm("msr	daifset, #8" : : : "memory")
+
 #endif
 #endif