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

…el/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "Once again, Catalin's off on holiday and I'm looking after the arm64
  tree.  Please can you pull the following arm64 updates for 3.17?

  Note that this branch also includes the new GICv3 driver (merged via a
  stable tag from Jason's irqchip tree), since there is a fix for older
  binutils on top.

  Changes include:
   - context tracking support (NO_HZ_FULL) which narrowly missed 3.16
   - vDSO layout rework following Andy's work on x86
   - TEXT_OFFSET fuzzing for bootloader testing
   - /proc/cpuinfo tidy-up
   - preliminary work to support 48-bit virtual addresses, but this is
     currently disabled until KVM has been ported to use it (the patches
     do, however, bring some nice clean-up)
   - boot-time CPU sanity checks (especially useful on heterogenous
     systems)
   - support for syscall auditing
   - support for CC_STACKPROTECTOR
   - defconfig updates"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (55 commits)
  arm64: add newline to I-cache policy string
  Revert "arm64: dmi: Add SMBIOS/DMI support"
  arm64: fpsimd: fix a typo in fpsimd_save_partial_state ENDPROC
  arm64: don't call break hooks for BRK exceptions from EL0
  arm64: defconfig: enable devtmpfs mount option
  arm64: vdso: fix build error when switching from LE to BE
  arm64: defconfig: add virtio support for running as a kvm guest
  arm64: gicv3: Allow GICv3 compilation with older binutils
  arm64: fix soft lockup due to large tlb flush range
  arm64/crypto: fix makefile rule for aes-glue-%.o
  arm64: Do not invoke audit_syscall_* functions if !CONFIG_AUDIT_SYSCALL
  arm64: Fix barriers used for page table modifications
  arm64: Add support for 48-bit VA space with 64KB page configuration
  arm64: asm/pgtable.h pmd/pud definitions clean-up
  arm64: Determine the vmalloc/vmemmap space at build time based on VA_BITS
  arm64: Clean up the initial page table creation in head.S
  arm64: Remove asm/pgtable-*level-types.h files
  arm64: Remove asm/pgtable-*level-hwdef.h files
  arm64: Convert bool ARM64_x_LEVELS to int ARM64_PGTABLE_LEVELS
  arm64: mm: Implement 4 levels of translation tables
  ...

Documentation/arm64/booting.txt

@@ -72,27 +72,54 @@ The decompressed kernel image contains a 64-byte header as follows:
 
   u32 code0;			/* Executable code */
   u32 code1;			/* Executable code */
-  u64 text_offset;		/* Image load offset */
-  u64 res0	= 0;		/* reserved */
-  u64 res1	= 0;		/* reserved */
+  u64 text_offset;		/* Image load offset, little endian */
+  u64 image_size;		/* Effective Image size, little endian */
+  u64 flags;			/* kernel flags, little endian */
   u64 res2	= 0;		/* reserved */
   u64 res3	= 0;		/* reserved */
   u64 res4	= 0;		/* reserved */
   u32 magic	= 0x644d5241;	/* Magic number, little endian, "ARM\x64" */
-  u32 res5 = 0;      		/* reserved */
+  u32 res5;      		/* reserved (used for PE COFF offset) */
 
 
 Header notes:
 
+- As of v3.17, all fields are little endian unless stated otherwise.
+
 - code0/code1 are responsible for branching to stext.
+
 - when booting through EFI, code0/code1 are initially skipped.
   res5 is an offset to the PE header and the PE header has the EFI
-  entry point (efi_stub_entry). When the stub has done its work, it
+  entry point (efi_stub_entry).  When the stub has done its work, it
   jumps to code0 to resume the normal boot process.
 
-The image must be placed at the specified offset (currently 0x80000)
-from the start of the system RAM and called there. The start of the
-system RAM must be aligned to 2MB.
+- Prior to v3.17, the endianness of text_offset was not specified.  In
+  these cases image_size is zero and text_offset is 0x80000 in the
+  endianness of the kernel.  Where image_size is non-zero image_size is
+  little-endian and must be respected.  Where image_size is zero,
+  text_offset can be assumed to be 0x80000.
+
+- 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.
+  Bits 1-63:	Reserved.
+
+- When image_size is zero, a bootloader should attempt to keep as much
+  memory as possible free for use by the kernel immediately after the
+  end of the kernel image. The amount of space required will vary
+  depending on selected features, and is effectively unbound.
+
+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.
+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
+address) 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.
 
 Before jumping into the kernel, the following conditions must be met:
 

Documentation/arm64/memory.txt

@@ -2,77 +2,59 @@
 		     ==============================
 
 Author: Catalin Marinas <catalin.marinas@arm.com>
-Date  : 20 February 2012
 
 This document describes the virtual memory layout used by the AArch64
 Linux kernel. The architecture allows up to 4 levels of translation
 tables with a 4KB page size and up to 3 levels with a 64KB page size.
 
-AArch64 Linux uses 3 levels of translation tables with the 4KB page
-configuration, allowing 39-bit (512GB) virtual addresses for both user
-and kernel. With 64KB pages, only 2 levels of translation tables are
-used but the memory layout is the same.
+AArch64 Linux uses either 3 levels or 4 levels of translation tables
+with the 4KB page configuration, allowing 39-bit (512GB) or 48-bit
+(256TB) virtual addresses, respectively, for both user and kernel. With
+64KB pages, only 2 levels of translation tables, allowing 42-bit (4TB)
+virtual address, are used but the memory layout is the same.
 
-User addresses have bits 63:39 set to 0 while the kernel addresses have
+User addresses have bits 63:48 set to 0 while the kernel addresses have
 the same bits set to 1. TTBRx selection is given by bit 63 of the
 virtual address. The swapper_pg_dir contains only kernel (global)
 mappings while the user pgd contains only user (non-global) mappings.
 The swapper_pgd_dir address is written to TTBR1 and never written to
 TTBR0.
 
 
-AArch64 Linux memory layout with 4KB pages:
+AArch64 Linux memory layout with 4KB pages + 3 levels:
 
 Start			End			Size		Use
 -----------------------------------------------------------------------
 0000000000000000	0000007fffffffff	 512GB		user
+ffffff8000000000	ffffffffffffffff	 512GB		kernel
 
-ffffff8000000000	ffffffbbfffeffff	~240GB		vmalloc
 
-ffffffbbffff0000	ffffffbbffffffff	  64KB		[guard page]
+AArch64 Linux memory layout with 4KB pages + 4 levels:
 
-ffffffbc00000000	ffffffbdffffffff	   8GB		vmemmap
-
-ffffffbe00000000	ffffffbffbbfffff	  ~8GB		[guard, future vmmemap]
-
-ffffffbffa000000	ffffffbffaffffff	  16MB		PCI I/O space
-
-ffffffbffb000000	ffffffbffbbfffff	  12MB		[guard]
-
-ffffffbffbc00000	ffffffbffbdfffff	   2MB		fixed mappings
-
-ffffffbffbe00000	ffffffbffbffffff	   2MB		[guard]
-
-ffffffbffc000000	ffffffbfffffffff	  64MB		modules
-
-ffffffc000000000	ffffffffffffffff	 256GB		kernel logical memory map
+Start			End			Size		Use
+-----------------------------------------------------------------------
+0000000000000000	0000ffffffffffff	 256TB		user
+ffff000000000000	ffffffffffffffff	 256TB		kernel
 
 
-AArch64 Linux memory layout with 64KB pages:
+AArch64 Linux memory layout with 64KB pages + 2 levels:
 
 Start			End			Size		Use
 -----------------------------------------------------------------------
 0000000000000000	000003ffffffffff	   4TB		user
+fffffc0000000000	ffffffffffffffff	   4TB		kernel
 
-fffffc0000000000	fffffdfbfffeffff	  ~2TB		vmalloc
 
-fffffdfbffff0000	fffffdfbffffffff	  64KB		[guard page]
+AArch64 Linux memory layout with 64KB pages + 3 levels:
 
-fffffdfc00000000	fffffdfdffffffff	   8GB		vmemmap
-
-fffffdfe00000000	fffffdfffbbfffff	  ~8GB		[guard, future vmmemap]
-
-fffffdfffa000000	fffffdfffaffffff	  16MB		PCI I/O space
-
-fffffdfffb000000	fffffdfffbbfffff	  12MB		[guard]
-
-fffffdfffbc00000	fffffdfffbdfffff	   2MB		fixed mappings
-
-fffffdfffbe00000	fffffdfffbffffff	   2MB		[guard]
+Start			End			Size		Use
+-----------------------------------------------------------------------
+0000000000000000	0000ffffffffffff	 256TB		user
+ffff000000000000	ffffffffffffffff	 256TB		kernel
 
-fffffdfffc000000	fffffdffffffffff	  64MB		modules
 
-fffffe0000000000	ffffffffffffffff	   2TB		kernel logical memory map
+For details of the virtual kernel memory layout please see the kernel
+booting log.
 
 
 Translation table lookup with 4KB pages:
@@ -86,7 +68,7 @@ Translation table lookup with 4KB pages:
  |                 |         |         |         +-> [20:12] L3 index
  |                 |         |         +-----------> [29:21] L2 index
  |                 |         +---------------------> [38:30] L1 index
- |                 +-------------------------------> [47:39] L0 index (not used)
+ |                 +-------------------------------> [47:39] L0 index
  +-------------------------------------------------> [63] TTBR0/1
 
 
@@ -99,10 +81,11 @@ Translation table lookup with 64KB pages:
  |                 |    |               |              v
  |                 |    |               |            [15:0]  in-page offset
  |                 |    |               +----------> [28:16] L3 index
- |                 |    +--------------------------> [41:29] L2 index (only 38:29 used)
- |                 +-------------------------------> [47:42] L1 index (not used)
+ |                 |    +--------------------------> [41:29] L2 index
+ |                 +-------------------------------> [47:42] L1 index
  +-------------------------------------------------> [63] TTBR0/1
 
+
 When using KVM, the hypervisor maps kernel pages in EL2, at a fixed
 offset from the kernel VA (top 24bits of the kernel VA set to zero):
 

arch/arm64/Kconfig

@@ -1,7 +1,6 @@
 config ARM64
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
-	select ARCH_HAS_OPP
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_SUPPORTS_ATOMIC_RMW
@@ -11,6 +10,8 @@ config ARM64
 	select ARM_AMBA
 	select ARM_ARCH_TIMER
 	select ARM_GIC
+	select AUDIT_ARCH_COMPAT_GENERIC
+	select ARM_GIC_V3
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
@@ -29,10 +30,12 @@ config ARM64
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
 	select HARDIRQS_SW_RESEND
+	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_C_RECORDMCOUNT
+	select HAVE_CC_STACKPROTECTOR
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
@@ -63,6 +66,7 @@ config ARM64
 	select RTC_LIB
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
+	select HAVE_CONTEXT_TRACKING
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
@@ -155,14 +159,63 @@ endmenu
 
 menu "Kernel Features"
 
+choice
+	prompt "Page size"
+	default ARM64_4K_PAGES
+	help
+	  Page size (translation granule) configuration.
+
+config ARM64_4K_PAGES
+	bool "4KB"
+	help
+	  This feature enables 4KB pages support.
+
 config ARM64_64K_PAGES
-	bool "Enable 64KB pages support"
+	bool "64KB"
 	help
 	  This feature enables 64KB pages support (4KB by default)
 	  allowing only two levels of page tables and faster TLB
 	  look-up. AArch32 emulation is not available when this feature
 	  is enabled.
 
+endchoice
+
+choice
+	prompt "Virtual address space size"
+	default ARM64_VA_BITS_39 if ARM64_4K_PAGES
+	default ARM64_VA_BITS_42 if ARM64_64K_PAGES
+	help
+	  Allows choosing one of multiple possible virtual address
+	  space sizes. The level of translation table is determined by
+	  a combination of page size and virtual address space size.
+
+config ARM64_VA_BITS_39
+	bool "39-bit"
+	depends on ARM64_4K_PAGES
+
+config ARM64_VA_BITS_42
+	bool "42-bit"
+	depends on ARM64_64K_PAGES
+
+config ARM64_VA_BITS_48
+	bool "48-bit"
+	depends on BROKEN
+
+endchoice
+
+config ARM64_VA_BITS
+	int
+	default 39 if ARM64_VA_BITS_39
+	default 42 if ARM64_VA_BITS_42
+	default 48 if ARM64_VA_BITS_48
+
+config ARM64_PGTABLE_LEVELS
+	int
+	default 2 if ARM64_64K_PAGES && ARM64_VA_BITS_42
+	default 3 if ARM64_64K_PAGES && ARM64_VA_BITS_48
+	default 3 if ARM64_4K_PAGES && ARM64_VA_BITS_39
+	default 4 if ARM64_4K_PAGES && ARM64_VA_BITS_48
+
 config CPU_BIG_ENDIAN
        bool "Build big-endian kernel"
        help

arch/arm64/Kconfig.debug

@@ -28,4 +28,19 @@ config PID_IN_CONTEXTIDR
 	  instructions during context switch. Say Y here only if you are
 	  planning to use hardware trace tools with this kernel.
 
+config ARM64_RANDOMIZE_TEXT_OFFSET
+	bool "Randomize TEXT_OFFSET at build time"
+	help
+	  Say Y here if you want the image load offset (AKA TEXT_OFFSET)
+	  of the kernel to be randomized at build-time. When selected,
+	  this option will cause TEXT_OFFSET to be randomized upon any
+	  build of the kernel, and the offset will be reflected in the
+	  text_offset field of the resulting Image. This can be used to
+	  fuzz-test bootloaders which respect text_offset.
+
+	  This option is intended for bootloader and/or kernel testing
+	  only. Bootloaders must make no assumptions regarding the value
+	  of TEXT_OFFSET and platforms must not require a specific
+	  value.
+
 endmenu

arch/arm64/Makefile

@@ -38,7 +38,11 @@ CHECKFLAGS	+= -D__aarch64__
 head-y		:= arch/arm64/kernel/head.o
 
 # The byte offset of the kernel image in RAM from the start of RAM.
+ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y)
+TEXT_OFFSET := $(shell awk 'BEGIN {srand(); printf "0x%04x0\n", int(65535 * rand())}')
+else
 TEXT_OFFSET := 0x00080000
+endif
 
 export	TEXT_OFFSET GZFLAGS
 

arch/arm64/configs/defconfig

@@ -52,8 +52,11 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
+CONFIG_NET_9P=y
+CONFIG_NET_9P_VIRTIO=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_DMA_CMA=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_VIRTIO_BLK=y
@@ -65,6 +68,7 @@ CONFIG_PATA_PLATFORM=y
 CONFIG_PATA_OF_PLATFORM=y
 CONFIG_NETDEVICES=y
 CONFIG_TUN=y
+CONFIG_VIRTIO_NET=y
 CONFIG_SMC91X=y
 CONFIG_SMSC911X=y
 # CONFIG_WLAN is not set
@@ -76,6 +80,7 @@ CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_VIRTIO_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 CONFIG_REGULATOR=y
@@ -90,6 +95,7 @@ CONFIG_USB_ISP1760_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_MMC=y
 CONFIG_MMC_ARMMMCI=y
+CONFIG_VIRTIO_BALLOON=y
 CONFIG_VIRTIO_MMIO=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT2_FS=y
@@ -107,6 +113,7 @@ CONFIG_HUGETLBFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
+CONFIG_9P_FS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_VIRTUALIZATION=y

arch/arm64/crypto/Makefile

@@ -35,4 +35,4 @@ AFLAGS_aes-neon.o	:= -DINTERLEAVE=4
 CFLAGS_aes-glue-ce.o	:= -DUSE_V8_CRYPTO_EXTENSIONS
 
 $(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE
-	$(call if_changed_dep,cc_o_c)
+	$(call if_changed_rule,cc_o_c)

arch/arm64/include/asm/cacheflush.h

@@ -138,19 +138,10 @@ static inline void __flush_icache_all(void)
 #define flush_icache_page(vma,page)	do { } while (0)
 
 /*
- * flush_cache_vmap() is used when creating mappings (eg, via vmap,
- * vmalloc, ioremap etc) in kernel space for pages.  On non-VIPT
- * caches, since the direct-mappings of these pages may contain cached
- * data, we need to do a full cache flush to ensure that writebacks
- * don't corrupt data placed into these pages via the new mappings.
+ * Not required on AArch64 (PIPT or VIPT non-aliasing D-cache).
  */
 static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 {
-	/*
-	 * set_pte_at() called from vmap_pte_range() does not
-	 * have a DSB after cleaning the cache line.
-	 */
-	dsb(ish);
 }
 
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)