Merge tag 'v4.7-rc6' into patchwork

Linux 4.7-rc6

* tag 'v4.7-rc6': (1245 commits)
  Linux 4.7-rc6
  ovl: warn instead of error if d_type is not supported
  MIPS: Fix possible corruption of cache mode by mprotect.
  locks: use file_inode()
  usb: dwc3: st: Use explicit reset_control_get_exclusive() API
  phy: phy-stih407-usb: Use explicit reset_control_get_exclusive() API
  phy: miphy28lp: Inform the reset framework that our reset line may be shared
  namespace: update event counter when umounting a deleted dentry
  9p: use file_dentry()
  lockd: unregister notifier blocks if the service fails to come up completely
  ACPI,PCI,IRQ: correct operator precedence
  fuse: serialize dirops by default
  drm/i915: Fix missing unlock on error in i915_ppgtt_info()
  powerpc: Initialise pci_io_base as early as possible
  mfd: da9053: Fix compiler warning message for uninitialised variable
  mfd: max77620: Fix FPS switch statements
  phy: phy-stih407-usb: Inform the reset framework that our reset line may be shared
  usb: dwc3: st: Inform the reset framework that our reset line may be shared
  usb: host: ehci-st: Inform the reset framework that our reset line may be shared
  usb: host: ohci-st: Inform the reset framework that our reset line may be shared
  ...

27 files changed, 264 insertions, 100 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 76747d92bc72..5a0a691d4220 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -113,6 +113,18 @@ config ARCH_PHYS_ADDR_T_64BIT
 config MMU
 	def_bool y
 
+config ARM64_PAGE_SHIFT
+	int
+	default 16 if ARM64_64K_PAGES
+	default 14 if ARM64_16K_PAGES
+	default 12
+
+config ARM64_CONT_SHIFT
+	int
+	default 5 if ARM64_64K_PAGES
+	default 7 if ARM64_16K_PAGES
+	default 4
+
 config ARCH_MMAP_RND_BITS_MIN
        default 14 if ARM64_64K_PAGES
        default 16 if ARM64_16K_PAGES
@@ -426,6 +438,15 @@ config CAVIUM_ERRATUM_22375
 
 	  If unsure, say Y.
 
+config CAVIUM_ERRATUM_23144
+	bool "Cavium erratum 23144: ITS SYNC hang on dual socket system"
+	depends on NUMA
+	default y
+	help
+	  ITS SYNC command hang for cross node io and collections/cpu mapping.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_23154
 	bool "Cavium erratum 23154: Access to ICC_IAR1_EL1 is not sync'ed"
 	default y
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index 710fde4ad0f0..0cc758cdd0dc 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -12,7 +12,8 @@ config ARM64_PTDUMP
 	  who are working in architecture specific areas of the kernel.
 	  It is probably not a good idea to enable this feature in a production
 	  kernel.
-	  If in doubt, say "N"
+
+	  If in doubt, say N.
 
 config PID_IN_CONTEXTIDR
 	bool "Write the current PID to the CONTEXTIDR register"
@@ -38,15 +39,15 @@ config ARM64_RANDOMIZE_TEXT_OFFSET
 	  value.
 
 config DEBUG_SET_MODULE_RONX
-        bool "Set loadable kernel module data as NX and text as RO"
-        depends on MODULES
-        help
-          This option helps catch unintended modifications to loadable
-          kernel module's text and read-only data. It also prevents execution
-          of module data. Such protection may interfere with run-time code
-          patching and dynamic kernel tracing - and they might also protect
-          against certain classes of kernel exploits.
-          If in doubt, say "N".
+	bool "Set loadable kernel module data as NX and text as RO"
+	depends on MODULES
+	default y
+	help
+	  Is this is set, kernel module text and rodata will be made read-only.
+	  This is to help catch accidental or malicious attempts to change the
+	  kernel's executable code.
+
+	  If in doubt, say Y.
 
 config DEBUG_RODATA
 	bool "Make kernel text and rodata read-only"
@@ -56,7 +57,7 @@ config DEBUG_RODATA
 	  is to help catch accidental or malicious attempts to change the
 	  kernel's executable code.
 
-	  If in doubt, say Y
+	  If in doubt, say Y.
 
 config DEBUG_ALIGN_RODATA
 	depends on DEBUG_RODATA
@@ -69,7 +70,7 @@ config DEBUG_ALIGN_RODATA
 	  alignment and potentially wasted space. Turn on this option if
 	  performance is more important than memory pressure.
 
-	  If in doubt, say N
+	  If in doubt, say N.
 
 source "drivers/hwtracing/coresight/Kconfig"
 
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 354d75402ace..648a32c89541 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -60,7 +60,9 @@ 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%03x000\n", int(512 * rand())}')
+TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \
+		 int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \
+		 rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}")
 else
 TEXT_OFFSET := 0x00080000
 endif
@@ -93,7 +95,7 @@ boot := arch/arm64/boot
 Image: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
-Image.%: vmlinux
+Image.%: Image
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 zinstall install:
diff --git a/arch/arm64/boot/dts/lg/lg1312.dtsi b/arch/arm64/boot/dts/lg/lg1312.dtsi
index 3a4e9a2ab313..fbafa24cd533 100644
--- a/arch/arm64/boot/dts/lg/lg1312.dtsi
+++ b/arch/arm64/boot/dts/lg/lg1312.dtsi
@@ -125,7 +125,7 @@
 		#size-cells = <1>;
 		#interrupts-cells = <3>;
 
-		compatible = "arm,amba-bus";
+		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
 		ranges;
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 46f325a143b0..d7f8e06910bc 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -163,7 +163,7 @@
 	};
 
 	amba {
-		compatible = "arm,amba-bus";
+		compatible = "simple-bus";
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 7a09c48c0475..579b6e654f2d 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -160,14 +160,14 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 #define STACK_RND_MASK			(0x3ffff >> (PAGE_SHIFT - 12))
 #endif
 
-#ifdef CONFIG_COMPAT
-
 #ifdef __AARCH64EB__
 #define COMPAT_ELF_PLATFORM		("v8b")
 #else
 #define COMPAT_ELF_PLATFORM		("v8l")
 #endif
 
+#ifdef CONFIG_COMPAT
+
 #define COMPAT_ELF_ET_DYN_BASE		(2 * TASK_SIZE_32 / 3)
 
 /* AArch32 registers. */
diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h
index f69f69c8120c..da84645525b9 100644
--- a/arch/arm64/include/asm/kgdb.h
+++ b/arch/arm64/include/asm/kgdb.h
@@ -38,25 +38,54 @@ extern int kgdb_fault_expected;
 #endif /* !__ASSEMBLY__ */
 
 /*
- * gdb is expecting the following registers layout.
+ * gdb remote procotol (well most versions of it) expects the following
+ * register layout.
  *
  * General purpose regs:
  *     r0-r30: 64 bit
  *     sp,pc : 64 bit
- *     pstate  : 64 bit
- *     Total: 34
+ *     pstate  : 32 bit
+ *     Total: 33 + 1
  * FPU regs:
  *     f0-f31: 128 bit
- *     Total: 32
- * Extra regs
  *     fpsr & fpcr: 32 bit
- *     Total: 2
+ *     Total: 32 + 2
  *
+ * To expand a little on the "most versions of it"... when the gdb remote
+ * protocol for AArch64 was developed it depended on a statement in the
+ * Architecture Reference Manual that claimed "SPSR_ELx is a 32-bit register".
+ * and, as a result, allocated only 32-bits for the PSTATE in the remote
+ * protocol. In fact this statement is still present in ARM DDI 0487A.i.
+ *
+ * Unfortunately "is a 32-bit register" has a very special meaning for
+ * system registers. It means that "the upper bits, bits[63:32], are
+ * RES0.". RES0 is heavily used in the ARM architecture documents as a
+ * way to leave space for future architecture changes. So to translate a
+ * little for people who don't spend their spare time reading ARM architecture
+ * manuals, what "is a 32-bit register" actually means in this context is
+ * "is a 64-bit register but one with no meaning allocated to any of the
+ * upper 32-bits... *yet*".
+ *
+ * Perhaps then we should not be surprised that this has led to some
+ * confusion. Specifically a patch, influenced by the above translation,
+ * that extended PSTATE to 64-bit was accepted into gdb-7.7 but the patch
+ * was reverted in gdb-7.8.1 and all later releases, when this was
+ * discovered to be an undocumented protocol change.
+ *
+ * So... it is *not* wrong for us to only allocate 32-bits to PSTATE
+ * here even though the kernel itself allocates 64-bits for the same
+ * state. That is because this bit of code tells the kernel how the gdb
+ * remote protocol (well most versions of it) describes the register state.
+ *
+ * Note that if you are using one of the versions of gdb that supports
+ * the gdb-7.7 version of the protocol you cannot use kgdb directly
+ * without providing a custom register description (gdb can load new
+ * protocol descriptions at runtime).
  */
 
-#define _GP_REGS		34
+#define _GP_REGS		33
 #define _FP_REGS		32
-#define _EXTRA_REGS		2
+#define _EXTRA_REGS		3
 /*
  * general purpose registers size in bytes.
  * pstate is only 4 bytes. subtract 4 bytes
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 72a3025bb583..31b73227b41f 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -55,8 +55,9 @@
 #define VMEMMAP_SIZE (UL(1) << (VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT))
 
 /*
- * PAGE_OFFSET - the virtual address of the start of the kernel image (top
+ * PAGE_OFFSET - the virtual address of the start of the linear map (top
  *		 (VA_BITS - 1))
+ * KIMAGE_VADDR - the virtual address of the start of the kernel image
  * VA_BITS - the maximum number of bits for virtual addresses.
  * VA_START - the first kernel virtual address.
  * TASK_SIZE - the maximum size of a user space task.
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 17b45f7d96d3..8472c6def5ef 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -23,16 +23,8 @@
 
 /* PAGE_SHIFT determines the page size */
 /* CONT_SHIFT determines the number of pages which can be tracked together  */
-#ifdef CONFIG_ARM64_64K_PAGES
-#define PAGE_SHIFT		16
-#define CONT_SHIFT		5
-#elif defined(CONFIG_ARM64_16K_PAGES)
-#define PAGE_SHIFT		14
-#define CONT_SHIFT		7
-#else
-#define PAGE_SHIFT		12
-#define CONT_SHIFT		4
-#endif
+#define PAGE_SHIFT		CONFIG_ARM64_PAGE_SHIFT
+#define CONT_SHIFT		CONFIG_ARM64_CONT_SHIFT
 #define PAGE_SIZE		(_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK		(~(PAGE_SIZE-1))
 
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index ff98585d085a..d25f4f137c2a 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -26,7 +26,7 @@
 
 #define check_pgt_cache()		do { } while (0)
 
-#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 #define PGD_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
 
 #if CONFIG_PGTABLE_LEVELS > 2
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 433e50405274..022644704a93 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -124,6 +124,18 @@ static inline void cpu_panic_kernel(void)
 	cpu_park_loop();
 }
 
+/*
+ * If a secondary CPU enters the kernel but fails to come online,
+ * (e.g. due to mismatched features), and cannot exit the kernel,
+ * we increment cpus_stuck_in_kernel and leave the CPU in a
+ * quiesecent loop within the kernel text. The memory containing
+ * this loop must not be re-used for anything else as the 'stuck'
+ * core is executing it.
+ *
+ * This function is used to inhibit features like kexec and hibernate.
+ */
+bool cpus_are_stuck_in_kernel(void);
+
 #endif /* ifndef __ASSEMBLY__ */
 
 #endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index fc9682bfe002..e875a5a551d7 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -30,22 +30,53 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
 	unsigned int tmp;
 	arch_spinlock_t lockval;
+	u32 owner;
+
+	/*
+	 * Ensure prior spin_lock operations to other locks have completed
+	 * on this CPU before we test whether "lock" is locked.
+	 */
+	smp_mb();
+	owner = READ_ONCE(lock->owner) << 16;
 
 	asm volatile(
 "	sevl\n"
 "1:	wfe\n"
 "2:	ldaxr	%w0, %2\n"
+	/* Is the lock free? */
 "	eor	%w1, %w0, %w0, ror #16\n"
-"	cbnz	%w1, 1b\n"
+"	cbz	%w1, 3f\n"
+	/* Lock taken -- has there been a subsequent unlock->lock transition? */
+"	eor	%w1, %w3, %w0, lsl #16\n"
+"	cbz	%w1, 1b\n"
+	/*
+	 * The owner has been updated, so there was an unlock->lock
+	 * transition that we missed. That means we can rely on the
+	 * store-release of the unlock operation paired with the
+	 * load-acquire of the lock operation to publish any of our
+	 * previous stores to the new lock owner and therefore don't
+	 * need to bother with the writeback below.
+	 */
+"	b	4f\n"
+"3:\n"
+	/*
+	 * Serialise against any concurrent lockers by writing back the
+	 * unlocked lock value
+	 */
 	ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
 "	stxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 2b\n", /* Serialise against any concurrent lockers */
-	/* LSE atomics */
 "	nop\n"
-"	nop\n")
+"	nop\n",
+	/* LSE atomics */
+"	mov	%w1, %w0\n"
+"	cas	%w0, %w0, %2\n"
+"	eor	%w1, %w1, %w0\n")
+	/* Somebody else wrote to the lock, GOTO 10 and reload the value */
+"	cbnz	%w1, 2b\n"
+"4:"
 	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
-	:
+	: "r" (owner)
 	: "memory");
 }
 
@@ -148,6 +179,7 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
+	smp_mb(); /* See arch_spin_unlock_wait */
 	return !arch_spin_value_unlocked(READ_ONCE(*lock));
 }
 
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 0685d74572af..9e397a542756 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -81,19 +81,6 @@ static inline void set_fs(mm_segment_t fs)
 #define segment_eq(a, b)	((a) == (b))
 
 /*
- * Return 1 if addr < current->addr_limit, 0 otherwise.
- */
-#define __addr_ok(addr)							\
-({									\
-	unsigned long flag;						\
-	asm("cmp %1, %0; cset %0, lo"					\
-		: "=&r" (flag)						\
-		: "r" (addr), "0" (current_thread_info()->addr_limit)	\
-		: "cc");						\
-	flag;								\
-})
-
-/*
  * Test whether a block of memory is a valid user space address.
  * Returns 1 if the range is valid, 0 otherwise.
  *
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 41e58fe3c041..e78ac26324bd 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -44,7 +44,7 @@
 #define __ARM_NR_compat_cacheflush	(__ARM_NR_COMPAT_BASE+2)
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE+5)
 
-#define __NR_compat_syscalls		390
+#define __NR_compat_syscalls		394
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 5b925b761a2a..b7e8ef16ff0d 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -801,6 +801,14 @@ __SYSCALL(__NR_execveat, compat_sys_execveat)
 __SYSCALL(__NR_userfaultfd, sys_userfaultfd)
 #define __NR_membarrier 389
 __SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 390
+__SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 391
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
+#define __NR_preadv2 392
+__SYSCALL(__NR_preadv2, compat_sys_preadv2)
+#define __NR_pwritev2 393
+__SYSCALL(__NR_pwritev2, compat_sys_pwritev2)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 3808470486f3..c173d329397f 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -22,6 +22,8 @@
 
 #include <linux/bitops.h>
 #include <linux/bug.h>
+#include <linux/compat.h>
+#include <linux/elf.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/personality.h>
@@ -104,6 +106,7 @@ static const char *const compat_hwcap2_str[] = {
 static int c_show(struct seq_file *m, void *v)
 {
 	int i, j;
+	bool compat = personality(current->personality) == PER_LINUX32;
 
 	for_each_online_cpu(i) {
 		struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
@@ -115,6 +118,9 @@ static int c_show(struct seq_file *m, void *v)
 		 * "processor".  Give glibc what it expects.
 		 */
 		seq_printf(m, "processor\t: %d\n", i);
+		if (compat)
+			seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n",
+				   MIDR_REVISION(midr), COMPAT_ELF_PLATFORM);
 
 		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
 			   loops_per_jiffy / (500000UL/HZ),
@@ -127,7 +133,7 @@ static int c_show(struct seq_file *m, void *v)
 		 * software which does already (at least for 32-bit).
 		 */
 		seq_puts(m, "Features\t:");
-		if (personality(current->personality) == PER_LINUX32) {
+		if (compat) {
 #ifdef CONFIG_COMPAT
 			for (j = 0; compat_hwcap_str[j]; j++)
 				if (compat_elf_hwcap & (1 << j))
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index f8df75d740f4..21ab5df9fa76 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -33,6 +33,7 @@
 #include <asm/pgtable.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/sections.h>
+#include <asm/smp.h>
 #include <asm/suspend.h>
 #include <asm/virt.h>
 
@@ -236,6 +237,11 @@ int swsusp_arch_suspend(void)
 	unsigned long flags;
 	struct sleep_stack_data state;
 
+	if (cpus_are_stuck_in_kernel()) {
+		pr_err("Can't hibernate: no mechanism to offline secondary CPUs.\n");
+		return -EBUSY;
+	}
+
 	local_dbg_save(flags);
 
 	if (__cpu_suspend_enter(&state)) {
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index b67531a13136..b5f063e5eff7 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -58,7 +58,17 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
 	{ "x30", 8, offsetof(struct pt_regs, regs[30])},
 	{ "sp", 8, offsetof(struct pt_regs, sp)},
 	{ "pc", 8, offsetof(struct pt_regs, pc)},
-	{ "pstate", 8, offsetof(struct pt_regs, pstate)},
+	/*
+	 * struct pt_regs thinks PSTATE is 64-bits wide but gdb remote
+	 * protocol disagrees. Therefore we must extract only the lower
+	 * 32-bits. Look for the big comment in asm/kgdb.h for more
+	 * detail.
+	 */
+	{ "pstate", 4, offsetof(struct pt_regs, pstate)
+#ifdef CONFIG_CPU_BIG_ENDIAN
+							+ 4
+#endif
+	},
 	{ "v0", 16, -1 },
 	{ "v1", 16, -1 },
 	{ "v2", 16, -1 },
@@ -128,6 +138,8 @@ sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
 	memset((char *)gdb_regs, 0, NUMREGBYTES);
 	thread_regs = task_pt_regs(task);
 	memcpy((void *)gdb_regs, (void *)thread_regs->regs, GP_REG_BYTES);
+	/* Special case for PSTATE (check comments in asm/kgdb.h for details) */
+	dbg_get_reg(33, gdb_regs + GP_REG_BYTES, thread_regs);
 }
 
 void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 678e0842cb3b..62ff3c0622e2 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -909,3 +909,21 @@ int setup_profiling_timer(unsigned int multiplier)
 {
 	return -EINVAL;
 }
+
+static bool have_cpu_die(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	int any_cpu = raw_smp_processor_id();
+
+	if (cpu_ops[any_cpu]->cpu_die)
+		return true;
+#endif
+	return false;
+}
+
+bool cpus_are_stuck_in_kernel(void)
+{
+	bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die());
+
+	return !!cpus_stuck_in_kernel || smp_spin_tables;
+}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index c5392081b49b..2a43012616b7 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -64,8 +64,7 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
 
 	/*
 	 * We need to switch to kernel mode so that we can use __get_user
-	 * to safely read from kernel space.  Note that we now dump the
-	 * code first, just in case the backtrace kills us.
+	 * to safely read from kernel space.
 	 */
 	fs = get_fs();
 	set_fs(KERNEL_DS);
@@ -111,21 +110,12 @@ static void dump_backtrace_entry(unsigned long where)
 	print_ip_sym(where);
 }
 
-static void dump_instr(const char *lvl, struct pt_regs *regs)
+static void __dump_instr(const char *lvl, struct pt_regs *regs)
 {
 	unsigned long addr = instruction_pointer(regs);
-	mm_segment_t fs;
 	char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str;
 	int i;
 
-	/*
-	 * We need to switch to kernel mode so that we can use __get_user
-	 * to safely read from kernel space.  Note that we now dump the
-	 * code first, just in case the backtrace kills us.
-	 */
-	fs = get_fs();
-	set_fs(KERNEL_DS);
-
 	for (i = -4; i < 1; i++) {
 		unsigned int val, bad;
 
@@ -139,8 +129,18 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 		}
 	}
 	printk("%sCode: %s\n", lvl, str);
+}
 
-	set_fs(fs);
+static void dump_instr(const char *lvl, struct pt_regs *regs)
+{
+	if (!user_mode(regs)) {
+		mm_segment_t fs = get_fs();
+		set_fs(KERNEL_DS);
+		__dump_instr(lvl, regs);
+		set_fs(fs);
+	} else {
+		__dump_instr(lvl, regs);
+	}
 }
 
 static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
@@ -477,8 +477,9 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 	void __user *pc = (void __user *)instruction_pointer(regs);
 	console_verbose();
 
-	pr_crit("Bad mode in %s handler detected, code 0x%08x -- %s\n",
-		handler[reason], esr, esr_get_class_string(esr));
+	pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n",
+		handler[reason], smp_processor_id(), esr,
+		esr_get_class_string(esr));
 	__show_regs(regs);
 
 	info.si_signo = SIGILL;
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index fff7cd42b3a3..5f8f80b4a224 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -169,7 +169,8 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 	 * Make sure stores to the GIC via the memory mapped interface
 	 * are now visible to the system register interface.
 	 */
-	dsb(st);
+	if (!cpu_if->vgic_sre)
+		dsb(st);
 
 	cpu_if->vgic_vmcr  = read_gicreg(ICH_VMCR_EL2);
 
@@ -190,12 +191,11 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 			if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
 				continue;
 
-			if (cpu_if->vgic_elrsr & (1 << i)) {
+			if (cpu_if->vgic_elrsr & (1 << i))
 				cpu_if->vgic_lr[i] &= ~ICH_LR_STATE;
-				continue;
-			}
+			else
+				cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
 
-			cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
 			__gic_v3_set_lr(0, i);
 		}
 
@@ -236,8 +236,12 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 
 	val = read_gicreg(ICC_SRE_EL2);
 	write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2);
-	isb(); /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */
-	write_gicreg(1, ICC_SRE_EL1);
+
+	if (!cpu_if->vgic_sre) {
+		/* Make sure ENABLE is set at EL2 before setting SRE at EL1 */
+		isb();
+		write_gicreg(1, ICC_SRE_EL1);
+	}
 }
 
 void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
@@ -256,8 +260,10 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	 * been actually programmed with the value we want before
 	 * starting to mess with the rest of the GIC.
 	 */
-	write_gicreg(cpu_if->vgic_sre, ICC_SRE_EL1);
-	isb();
+	if (!cpu_if->vgic_sre) {
+		write_gicreg(0, ICC_SRE_EL1);
+		isb();
+	}
 
 	val = read_gicreg(ICH_VTR_EL2);
 	max_lr_idx = vtr_to_max_lr_idx(val);
@@ -306,18 +312,18 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	 * (re)distributors. This ensure the guest will read the
 	 * correct values from the memory-mapped interface.
 	 */
-	isb();
-	dsb(sy);
+	if (!cpu_if->vgic_sre) {
+		isb();
+		dsb(sy);
+	}
 	vcpu->arch.vgic_cpu.live_lrs = live_lrs;
 
 	/*
 	 * Prevent the guest from touching the GIC system registers if
 	 * SRE isn't enabled for GICv3 emulation.
 	 */
-	if (!cpu_if->vgic_sre) {
-		write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE,
-			     ICC_SRE_EL2);
-	}
+	write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE,
+		     ICC_SRE_EL2);
 }
 
 void __hyp_text __vgic_v3_init_lrs(void)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 7bbe3ff02602..a57d650f552c 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -134,6 +134,17 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool access_gic_sre(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	p->regval = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre;
+	return true;
+}
+
 static bool trap_raz_wi(struct kvm_vcpu *vcpu,
 			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
@@ -958,7 +969,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  access_gic_sgi },
 	/* ICC_SRE_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1100), Op2(0b101),
-	  trap_raz_wi },
+	  access_gic_sre },
 
 	/* CONTEXTIDR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001),
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index b7b397802088..efcf1f7ef1e4 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -179,7 +179,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 						 &asid_generation);
 	flush_context(cpu);
 
-	/* We have at least 1 ASID per CPU, so this will always succeed */
+	/* We have more ASIDs than CPUs, so this will always succeed */
 	asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
 
 set_asid:
@@ -227,8 +227,11 @@ switch_mm_fastpath:
 static int asids_init(void)
 {
 	asid_bits = get_cpu_asid_bits();
-	/* If we end up with more CPUs than ASIDs, expect things to crash */
-	WARN_ON(NUM_USER_ASIDS < num_possible_cpus());
+	/*
+	 * Expect allocation after rollover to fail if we don't have at least
+	 * one more ASID than CPUs. ASID #0 is reserved for init_mm.
+	 */
+	WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus());
 	atomic64_set(&asid_generation, ASID_FIRST_VERSION);
 	asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map),
 			   GFP_KERNEL);
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 8404190fe2bd..ccfde237d6e6 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -150,6 +150,7 @@ static const struct prot_bits pte_bits[] = {
 
 struct pg_level {
 	const struct prot_bits *bits;
+	const char *name;
 	size_t num;
 	u64 mask;
 };
@@ -157,15 +158,19 @@ struct pg_level {
 static struct pg_level pg_level[] = {
 	{
 	}, { /* pgd */
+		.name	= "PGD",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	}, { /* pud */
+		.name	= (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	}, { /* pmd */
+		.name	= (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	}, { /* pte */
+		.name	= "PTE",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	},
@@ -214,7 +219,8 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
 				delta >>= 10;
 				unit++;
 			}
-			seq_printf(st->seq, "%9lu%c", delta, *unit);
+			seq_printf(st->seq, "%9lu%c %s", delta, *unit,
+				   pg_level[st->level].name);
 			if (pg_level[st->level].bits)
 				dump_prot(st, pg_level[st->level].bits,
 					  pg_level[st->level].num);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 5954881a35ac..013e2cbe7924 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -109,7 +109,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	 * PTE_RDONLY is cleared by default in the asm below, so set it in
 	 * back if necessary (read-only or clean PTE).
 	 */
-	if (!pte_write(entry) || !dirty)
+	if (!pte_write(entry) || !pte_sw_dirty(entry))
 		pte_val(entry) |= PTE_RDONLY;
 
 	/*
@@ -441,7 +441,7 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 	return 1;
 }
 
-static struct fault_info {
+static const struct fault_info {
 	int	(*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
 	int	sig;
 	int	code;
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index dbd12ea8ce68..43a76b07eb32 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -71,10 +71,6 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr)
 {
 	struct page *page = pte_page(pte);
 
-	/* no flushing needed for anonymous pages */
-	if (!page_mapping(page))
-		return;
-
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
 		sync_icache_aliases(page_address(page),
 				    PAGE_SIZE << compound_order(page));
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index aa8aee7d6929..2e49bd252fe7 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -306,6 +306,10 @@ static __init int setup_hugepagesz(char *opt)
 		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
 	} else if (ps == PUD_SIZE) {
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+	} else if (ps == (PAGE_SIZE * CONT_PTES)) {
+		hugetlb_add_hstate(CONT_PTE_SHIFT);
+	} else if (ps == (PMD_SIZE * CONT_PMDS)) {
+		hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
 	} else {
 		hugetlb_bad_size();
 		pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
@@ -314,3 +318,13 @@ static __init int setup_hugepagesz(char *opt)
 	return 1;
 }
 __setup("hugepagesz=", setup_hugepagesz);
+
+#ifdef CONFIG_ARM64_64K_PAGES
+static __init int add_default_hugepagesz(void)
+{
+	if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
+		hugetlb_add_hstate(CONT_PMD_SHIFT);
+	return 0;
+}
+arch_initcall(add_default_hugepagesz);
+#endif