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

Pull arm64 updates from Will Deacon:
 "The big highlight is support for the Scalable Vector Extension (SVE)
  which required extensive ABI work to ensure we don't break existing
  applications by blowing away their signal stack with the rather large
  new vector context (<= 2 kbit per vector register). There's further
  work to be done optimising things like exception return, but the ABI
  is solid now.

  Much of the line count comes from some new PMU drivers we have, but
  they're pretty self-contained and I suspect we'll have more of them in
  future.

  Plenty of acronym soup here:

   - initial support for the Scalable Vector Extension (SVE)

   - improved handling for SError interrupts (required to handle RAS
     events)

   - enable GCC support for 128-bit integer types

   - remove kernel text addresses from backtraces and register dumps

   - use of WFE to implement long delay()s

   - ACPI IORT updates from Lorenzo Pieralisi

   - perf PMU driver for the Statistical Profiling Extension (SPE)

   - perf PMU driver for Hisilicon's system PMUs

   - misc cleanups and non-critical fixes"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (97 commits)
  arm64: Make ARMV8_DEPRECATED depend on SYSCTL
  arm64: Implement __lshrti3 library function
  arm64: support __int128 on gcc 5+
  arm64/sve: Add documentation
  arm64/sve: Detect SVE and activate runtime support
  arm64/sve: KVM: Hide SVE from CPU features exposed to guests
  arm64/sve: KVM: Treat guest SVE use as undefined instruction execution
  arm64/sve: KVM: Prevent guests from using SVE
  arm64/sve: Add sysctl to set the default vector length for new processes
  arm64/sve: Add prctl controls for userspace vector length management
  arm64/sve: ptrace and ELF coredump support
  arm64/sve: Preserve SVE registers around EFI runtime service calls
  arm64/sve: Preserve SVE registers around kernel-mode NEON use
  arm64/sve: Probe SVE capabilities and usable vector lengths
  arm64: cpufeature: Move sys_caps_initialised declarations
  arm64/sve: Backend logic for setting the vector length
  arm64/sve: Signal handling support
  arm64/sve: Support vector length resetting for new processes
  arm64/sve: Core task context handling
  arm64/sve: Low-level CPU setup
  ...

24 files changed, 848 insertions, 73 deletions

diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index a652ce0a5cb2..bdedd8f748d1 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -144,6 +144,7 @@ static inline u32 arch_timer_get_cntkctl(void)
 static inline void arch_timer_set_cntkctl(u32 cntkctl)
 {
 	write_sysreg(cntkctl, cntkctl_el1);
+	isb();
 }
 
 static inline u64 arch_counter_get_cntpct(void)
diff --git a/arch/arm64/include/asm/asm-bug.h b/arch/arm64/include/asm/asm-bug.h
index 636e755bcdca..b3552c4a405f 100644
--- a/arch/arm64/include/asm/asm-bug.h
+++ b/arch/arm64/include/asm/asm-bug.h
@@ -22,10 +22,10 @@
 #define _BUGVERBOSE_LOCATION(file, line) __BUGVERBOSE_LOCATION(file, line)
 #define __BUGVERBOSE_LOCATION(file, line)			\
 		.pushsection .rodata.str,"aMS",@progbits,1;	\
-	2:	.string file;					\
+	14472:	.string file;					\
 		.popsection;					\
 								\
-		.long 2b - 0b;					\
+		.long 14472b - 14470b;				\
 		.short line;
 #else
 #define _BUGVERBOSE_LOCATION(file, line)
@@ -36,11 +36,11 @@
 #define __BUG_ENTRY(flags) 				\
 		.pushsection __bug_table,"aw";		\
 		.align 2;				\
-	0:	.long 1f - 0b;				\
+	14470:	.long 14471f - 14470b;			\
 _BUGVERBOSE_LOCATION(__FILE__, __LINE__)		\
 		.short flags; 				\
 		.popsection;				\
-	1:
+	14471:
 #else
 #define __BUG_ENTRY(flags)
 #endif
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index d58a6253c6ab..aef72d886677 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -25,12 +25,41 @@
 
 #include <asm/asm-offsets.h>
 #include <asm/cpufeature.h>
+#include <asm/debug-monitors.h>
 #include <asm/mmu_context.h>
 #include <asm/page.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 
+	.macro save_and_disable_daif, flags
+	mrs	\flags, daif
+	msr	daifset, #0xf
+	.endm
+
+	.macro disable_daif
+	msr	daifset, #0xf
+	.endm
+
+	.macro enable_daif
+	msr	daifclr, #0xf
+	.endm
+
+	.macro	restore_daif, flags:req
+	msr	daif, \flags
+	.endm
+
+	/* Only on aarch64 pstate, PSR_D_BIT is different for aarch32 */
+	.macro	inherit_daif, pstate:req, tmp:req
+	and	\tmp, \pstate, #(PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
+	msr	daif, \tmp
+	.endm
+
+	/* IRQ is the lowest priority flag, unconditionally unmask the rest. */
+	.macro enable_da_f
+	msr	daifclr, #(8 | 4 | 1)
+	.endm
+
 /*
  * Enable and disable interrupts.
  */
@@ -51,13 +80,6 @@
 	msr	daif, \flags
 	.endm
 
-/*
- * Enable and disable debug exceptions.
- */
-	.macro	disable_dbg
-	msr	daifset, #8
-	.endm
-
 	.macro	enable_dbg
 	msr	daifclr, #8
 	.endm
@@ -65,31 +87,22 @@
 	.macro	disable_step_tsk, flgs, tmp
 	tbz	\flgs, #TIF_SINGLESTEP, 9990f
 	mrs	\tmp, mdscr_el1
-	bic	\tmp, \tmp, #1
+	bic	\tmp, \tmp, #DBG_MDSCR_SS
 	msr	mdscr_el1, \tmp
 	isb	// Synchronise with enable_dbg
 9990:
 	.endm
 
+	/* call with daif masked */
 	.macro	enable_step_tsk, flgs, tmp
 	tbz	\flgs, #TIF_SINGLESTEP, 9990f
-	disable_dbg
 	mrs	\tmp, mdscr_el1
-	orr	\tmp, \tmp, #1
+	orr	\tmp, \tmp, #DBG_MDSCR_SS
 	msr	mdscr_el1, \tmp
 9990:
 	.endm
 
 /*
- * Enable both debug exceptions and interrupts. This is likely to be
- * faster than two daifclr operations, since writes to this register
- * are self-synchronising.
- */
-	.macro	enable_dbg_and_irq
-	msr	daifclr, #(8 | 2)
-	.endm
-
-/*
  * SMP data memory barrier
  */
 	.macro	smp_dmb, opt
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 0fe7e43b7fbc..77651c49ef44 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -31,6 +31,8 @@
 #define dmb(opt)	asm volatile("dmb " #opt : : : "memory")
 #define dsb(opt)	asm volatile("dsb " #opt : : : "memory")
 
+#define psb_csync()	asm volatile("hint #17" : : : "memory")
+
 #define mb()		dsb(sy)
 #define rmb()		dsb(ld)
 #define wmb()		dsb(st)
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index 889226b4c6e1..88392272250e 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -41,6 +41,7 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64mmfr2;
 	u64		reg_id_aa64pfr0;
 	u64		reg_id_aa64pfr1;
+	u64		reg_id_aa64zfr0;
 
 	u32		reg_id_dfr0;
 	u32		reg_id_isar0;
@@ -59,6 +60,9 @@ struct cpuinfo_arm64 {
 	u32		reg_mvfr0;
 	u32		reg_mvfr1;
 	u32		reg_mvfr2;
+
+	/* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */
+	u64		reg_zcr;
 };
 
 DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 8da621627d7c..2ff7c5e8efab 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -40,7 +40,8 @@
 #define ARM64_WORKAROUND_858921			19
 #define ARM64_WORKAROUND_CAVIUM_30115		20
 #define ARM64_HAS_DCPOP				21
+#define ARM64_SVE				22
 
-#define ARM64_NCAPS				22
+#define ARM64_NCAPS				23
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 428ee1f2468c..ac67cfc2585a 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -10,7 +10,9 @@
 #define __ASM_CPUFEATURE_H
 
 #include <asm/cpucaps.h>
+#include <asm/fpsimd.h>
 #include <asm/hwcap.h>
+#include <asm/sigcontext.h>
 #include <asm/sysreg.h>
 
 /*
@@ -223,6 +225,13 @@ static inline bool id_aa64pfr0_32bit_el0(u64 pfr0)
 	return val == ID_AA64PFR0_EL0_32BIT_64BIT;
 }
 
+static inline bool id_aa64pfr0_sve(u64 pfr0)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_SVE_SHIFT);
+
+	return val > 0;
+}
+
 void __init setup_cpu_features(void);
 
 void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
@@ -262,6 +271,39 @@ static inline bool system_uses_ttbr0_pan(void)
 		!cpus_have_const_cap(ARM64_HAS_PAN);
 }
 
+static inline bool system_supports_sve(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SVE) &&
+		cpus_have_const_cap(ARM64_SVE);
+}
+
+/*
+ * Read the pseudo-ZCR used by cpufeatures to identify the supported SVE
+ * vector length.
+ *
+ * Use only if SVE is present.
+ * This function clobbers the SVE vector length.
+ */
+static inline u64 read_zcr_features(void)
+{
+	u64 zcr;
+	unsigned int vq_max;
+
+	/*
+	 * Set the maximum possible VL, and write zeroes to all other
+	 * bits to see if they stick.
+	 */
+	sve_kernel_enable(NULL);
+	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1);
+
+	zcr = read_sysreg_s(SYS_ZCR_EL1);
+	zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */
+	vq_max = sve_vq_from_vl(sve_get_vl());
+	zcr |= vq_max - 1; /* set LEN field to maximum effective value */
+
+	return zcr;
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h
new file mode 100644
index 000000000000..22e4c83de5a5
--- /dev/null
+++ b/arch/arm64/include/asm/daifflags.h
@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 2017 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_DAIFFLAGS_H
+#define __ASM_DAIFFLAGS_H
+
+#include <linux/irqflags.h>
+
+#define DAIF_PROCCTX		0
+#define DAIF_PROCCTX_NOIRQ	PSR_I_BIT
+
+/* mask/save/unmask/restore all exceptions, including interrupts. */
+static inline void local_daif_mask(void)
+{
+	asm volatile(
+		"msr	daifset, #0xf		// local_daif_mask\n"
+		:
+		:
+		: "memory");
+	trace_hardirqs_off();
+}
+
+static inline unsigned long local_daif_save(void)
+{
+	unsigned long flags;
+
+	asm volatile(
+		"mrs	%0, daif		// local_daif_save\n"
+		: "=r" (flags)
+		:
+		: "memory");
+	local_daif_mask();
+
+	return flags;
+}
+
+static inline void local_daif_unmask(void)
+{
+	trace_hardirqs_on();
+	asm volatile(
+		"msr	daifclr, #0xf		// local_daif_unmask"
+		:
+		:
+		: "memory");
+}
+
+static inline void local_daif_restore(unsigned long flags)
+{
+	if (!arch_irqs_disabled_flags(flags))
+		trace_hardirqs_on();
+	asm volatile(
+		"msr	daif, %0		// local_daif_restore"
+		:
+		: "r" (flags)
+		: "memory");
+	if (arch_irqs_disabled_flags(flags))
+		trace_hardirqs_off();
+}
+
+#endif
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 33be513ef24c..fac1c4de7898 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -188,8 +188,8 @@ typedef compat_elf_greg_t		compat_elf_gregset_t[COMPAT_ELF_NGREG];
 
 #define compat_start_thread		compat_start_thread
 /*
- * Unlike the native SET_PERSONALITY macro, the compat version inherits
- * READ_IMPLIES_EXEC across a fork() since this is the behaviour on
+ * Unlike the native SET_PERSONALITY macro, the compat version maintains
+ * READ_IMPLIES_EXEC across an execve() since this is the behaviour on
  * arch/arm/.
  */
 #define COMPAT_SET_PERSONALITY(ex)					\
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 66ed8b6b9976..014d7d8edcf9 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -43,7 +43,8 @@
 #define ESR_ELx_EC_HVC64	(0x16)
 #define ESR_ELx_EC_SMC64	(0x17)
 #define ESR_ELx_EC_SYS64	(0x18)
-/* Unallocated EC: 0x19 - 0x1E */
+#define ESR_ELx_EC_SVE		(0x19)
+/* Unallocated EC: 0x1A - 0x1E */
 #define ESR_ELx_EC_IMP_DEF	(0x1f)
 #define ESR_ELx_EC_IABT_LOW	(0x20)
 #define ESR_ELx_EC_IABT_CUR	(0x21)
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 410c48163c6a..74f34392a531 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -17,9 +17,13 @@
 #define __ASM_FP_H
 
 #include <asm/ptrace.h>
+#include <asm/errno.h>
 
 #ifndef __ASSEMBLY__
 
+#include <linux/cache.h>
+#include <linux/stddef.h>
+
 /*
  * FP/SIMD storage area has:
  *  - FPSR and FPCR
@@ -35,13 +39,16 @@ struct fpsimd_state {
 			__uint128_t vregs[32];
 			u32 fpsr;
 			u32 fpcr;
+			/*
+			 * For ptrace compatibility, pad to next 128-bit
+			 * boundary here if extending this struct.
+			 */
 		};
 	};
 	/* the id of the last cpu to have restored this state */
 	unsigned int cpu;
 };
 
-
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /* Masks for extracting the FPSR and FPCR from the FPSCR */
 #define VFP_FPSCR_STAT_MASK	0xf800009f
@@ -61,11 +68,73 @@ extern void fpsimd_load_state(struct fpsimd_state *state);
 extern void fpsimd_thread_switch(struct task_struct *next);
 extern void fpsimd_flush_thread(void);
 
+extern void fpsimd_signal_preserve_current_state(void);
 extern void fpsimd_preserve_current_state(void);
 extern void fpsimd_restore_current_state(void);
 extern void fpsimd_update_current_state(struct fpsimd_state *state);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
+extern void sve_flush_cpu_state(void);
+
+/* Maximum VL that SVE VL-agnostic software can transparently support */
+#define SVE_VL_ARCH_MAX 0x100
+
+extern void sve_save_state(void *state, u32 *pfpsr);
+extern void sve_load_state(void const *state, u32 const *pfpsr,
+			   unsigned long vq_minus_1);
+extern unsigned int sve_get_vl(void);
+extern int sve_kernel_enable(void *);
+
+extern int __ro_after_init sve_max_vl;
+
+#ifdef CONFIG_ARM64_SVE
+
+extern size_t sve_state_size(struct task_struct const *task);
+
+extern void sve_alloc(struct task_struct *task);
+extern void fpsimd_release_task(struct task_struct *task);
+extern void fpsimd_sync_to_sve(struct task_struct *task);
+extern void sve_sync_to_fpsimd(struct task_struct *task);
+extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task);
+
+extern int sve_set_vector_length(struct task_struct *task,
+				 unsigned long vl, unsigned long flags);
+
+extern int sve_set_current_vl(unsigned long arg);
+extern int sve_get_current_vl(void);
+
+/*
+ * Probing and setup functions.
+ * Calls to these functions must be serialised with one another.
+ */
+extern void __init sve_init_vq_map(void);
+extern void sve_update_vq_map(void);
+extern int sve_verify_vq_map(void);
+extern void __init sve_setup(void);
+
+#else /* ! CONFIG_ARM64_SVE */
+
+static inline void sve_alloc(struct task_struct *task) { }
+static inline void fpsimd_release_task(struct task_struct *task) { }
+static inline void sve_sync_to_fpsimd(struct task_struct *task) { }
+static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { }
+
+static inline int sve_set_current_vl(unsigned long arg)
+{
+	return -EINVAL;
+}
+
+static inline int sve_get_current_vl(void)
+{
+	return -EINVAL;
+}
+
+static inline void sve_init_vq_map(void) { }
+static inline void sve_update_vq_map(void) { }
+static inline int sve_verify_vq_map(void) { return 0; }
+static inline void sve_setup(void) { }
+
+#endif /* ! CONFIG_ARM64_SVE */
 
 /* For use by EFI runtime services calls only */
 extern void __efi_fpsimd_begin(void);
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index 0f5fdd388b0d..e050d765ca9e 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -75,3 +75,151 @@
 	ldr	w\tmpnr, [\state, #16 * 2 + 4]
 	fpsimd_restore_fpcr x\tmpnr, \state
 .endm
+
+/* Sanity-check macros to help avoid encoding garbage instructions */
+
+.macro _check_general_reg nr
+	.if (\nr) < 0 || (\nr) > 30
+		.error "Bad register number \nr."
+	.endif
+.endm
+
+.macro _sve_check_zreg znr
+	.if (\znr) < 0 || (\znr) > 31
+		.error "Bad Scalable Vector Extension vector register number \znr."
+	.endif
+.endm
+
+.macro _sve_check_preg pnr
+	.if (\pnr) < 0 || (\pnr) > 15
+		.error "Bad Scalable Vector Extension predicate register number \pnr."
+	.endif
+.endm
+
+.macro _check_num n, min, max
+	.if (\n) < (\min) || (\n) > (\max)
+		.error "Number \n out of range [\min,\max]"
+	.endif
+.endm
+
+/* SVE instruction encodings for non-SVE-capable assemblers */
+
+/* STR (vector): STR Z\nz, [X\nxbase, #\offset, MUL VL] */
+.macro _sve_str_v nz, nxbase, offset=0
+	_sve_check_zreg \nz
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0xe5804000			\
+		| (\nz)				\
+		| ((\nxbase) << 5)		\
+		| (((\offset) & 7) << 10)	\
+		| (((\offset) & 0x1f8) << 13)
+.endm
+
+/* LDR (vector): LDR Z\nz, [X\nxbase, #\offset, MUL VL] */
+.macro _sve_ldr_v nz, nxbase, offset=0
+	_sve_check_zreg \nz
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0x85804000			\
+		| (\nz)				\
+		| ((\nxbase) << 5)		\
+		| (((\offset) & 7) << 10)	\
+		| (((\offset) & 0x1f8) << 13)
+.endm
+
+/* STR (predicate): STR P\np, [X\nxbase, #\offset, MUL VL] */
+.macro _sve_str_p np, nxbase, offset=0
+	_sve_check_preg \np
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0xe5800000			\
+		| (\np)				\
+		| ((\nxbase) << 5)		\
+		| (((\offset) & 7) << 10)	\
+		| (((\offset) & 0x1f8) << 13)
+.endm
+
+/* LDR (predicate): LDR P\np, [X\nxbase, #\offset, MUL VL] */
+.macro _sve_ldr_p np, nxbase, offset=0
+	_sve_check_preg \np
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0x85800000			\
+		| (\np)				\
+		| ((\nxbase) << 5)		\
+		| (((\offset) & 7) << 10)	\
+		| (((\offset) & 0x1f8) << 13)
+.endm
+
+/* RDVL X\nx, #\imm */
+.macro _sve_rdvl nx, imm
+	_check_general_reg \nx
+	_check_num (\imm), -0x20, 0x1f
+	.inst	0x04bf5000			\
+		| (\nx)				\
+		| (((\imm) & 0x3f) << 5)
+.endm
+
+/* RDFFR (unpredicated): RDFFR P\np.B */
+.macro _sve_rdffr np
+	_sve_check_preg \np
+	.inst	0x2519f000			\
+		| (\np)
+.endm
+
+/* WRFFR P\np.B */
+.macro _sve_wrffr np
+	_sve_check_preg \np
+	.inst	0x25289000			\
+		| ((\np) << 5)
+.endm
+
+.macro __for from:req, to:req
+	.if (\from) == (\to)
+		_for__body \from
+	.else
+		__for \from, (\from) + ((\to) - (\from)) / 2
+		__for (\from) + ((\to) - (\from)) / 2 + 1, \to
+	.endif
+.endm
+
+.macro _for var:req, from:req, to:req, insn:vararg
+	.macro _for__body \var:req
+		\insn
+	.endm
+
+	__for \from, \to
+
+	.purgem _for__body
+.endm
+
+.macro sve_save nxbase, xpfpsr, nxtmp
+ _for n, 0, 31,	_sve_str_v	\n, \nxbase, \n - 34
+ _for n, 0, 15,	_sve_str_p	\n, \nxbase, \n - 16
+		_sve_rdffr	0
+		_sve_str_p	0, \nxbase
+		_sve_ldr_p	0, \nxbase, -16
+
+		mrs		x\nxtmp, fpsr
+		str		w\nxtmp, [\xpfpsr]
+		mrs		x\nxtmp, fpcr
+		str		w\nxtmp, [\xpfpsr, #4]
+.endm
+
+.macro sve_load nxbase, xpfpsr, xvqminus1, nxtmp
+		mrs_s		x\nxtmp, SYS_ZCR_EL1
+		bic		x\nxtmp, x\nxtmp, ZCR_ELx_LEN_MASK
+		orr		x\nxtmp, x\nxtmp, \xvqminus1
+		msr_s		SYS_ZCR_EL1, x\nxtmp	// self-synchronising
+
+ _for n, 0, 31,	_sve_ldr_v	\n, \nxbase, \n - 34
+		_sve_ldr_p	0, \nxbase
+		_sve_wrffr	0
+ _for n, 0, 15,	_sve_ldr_p	\n, \nxbase, \n - 16
+
+		ldr		w\nxtmp, [\xpfpsr]
+		msr		fpsr, x\nxtmp
+		ldr		w\nxtmp, [\xpfpsr, #4]
+		msr		fpcr, x\nxtmp
+.endm
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index 8c581281fa12..24692edf1a69 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -21,6 +21,19 @@
 #include <asm/ptrace.h>
 
 /*
+ * Aarch64 has flags for masking: Debug, Asynchronous (serror), Interrupts and
+ * FIQ exceptions, in the 'daif' register. We mask and unmask them in 'dai'
+ * order:
+ * Masking debug exceptions causes all other exceptions to be masked too/
+ * Masking SError masks irq, but not debug exceptions. Masking irqs has no
+ * side effects for other flags. Keeping to this order makes it easier for
+ * entry.S to know which exceptions should be unmasked.
+ *
+ * FIQ is never expected, but we mask it when we disable debug exceptions, and
+ * unmask it at all other times.
+ */
+
+/*
  * CPU interrupt mask handling.
  */
 static inline unsigned long arch_local_irq_save(void)
@@ -53,12 +66,6 @@ static inline void arch_local_irq_disable(void)
 		: "memory");
 }
 
-#define local_fiq_enable()	asm("msr	daifclr, #1" : : : "memory")
-#define local_fiq_disable()	asm("msr	daifset, #1" : : : "memory")
-
-#define local_async_enable()	asm("msr	daifclr, #4" : : : "memory")
-#define local_async_disable()	asm("msr	daifset, #4" : : : "memory")
-
 /*
  * Save the current interrupt enable state.
  */
@@ -89,26 +96,5 @@ 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)
-
 #endif
 #endif
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 61d694c2eae5..7f069ff37f06 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -185,7 +185,9 @@
 #define CPTR_EL2_TCPAC	(1 << 31)
 #define CPTR_EL2_TTA	(1 << 20)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
-#define CPTR_EL2_DEFAULT	0x000033ff
+#define CPTR_EL2_TZ	(1 << 8)
+#define CPTR_EL2_RES1	0x000032ff /* known RES1 bits in CPTR_EL2 */
+#define CPTR_EL2_DEFAULT	CPTR_EL2_RES1
 
 /* Hyp Debug Configuration Register bits */
 #define MDCR_EL2_TPMS		(1 << 14)
@@ -236,5 +238,6 @@
 
 #define CPACR_EL1_FPEN		(3 << 20)
 #define CPACR_EL1_TTA		(1 << 28)
+#define CPACR_EL1_DEFAULT	(CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN)
 
 #endif /* __ARM64_KVM_ARM_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e923b58606e2..674912d7a571 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -25,6 +25,7 @@
 #include <linux/types.h>
 #include <linux/kvm_types.h>
 #include <asm/cpufeature.h>
+#include <asm/fpsimd.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
@@ -384,4 +385,14 @@ static inline void __cpu_init_stage2(void)
 		  "PARange is %d bits, unsupported configuration!", parange);
 }
 
+/*
+ * All host FP/SIMD state is restored on guest exit, so nothing needs
+ * doing here except in the SVE case:
+*/
+static inline void kvm_fpsimd_flush_cpu_state(void)
+{
+	if (system_supports_sve())
+		sve_flush_cpu_state();
+}
+
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index f7c4d2146aed..d4bae7d6e0d8 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -61,8 +61,6 @@
  * 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.
- * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
  */
 #define VA_BITS			(CONFIG_ARM64_VA_BITS)
 #define VA_START		(UL(0xffffffffffffffff) - \
@@ -77,19 +75,6 @@
 #define PCI_IO_END		(VMEMMAP_START - SZ_2M)
 #define PCI_IO_START		(PCI_IO_END - PCI_IO_SIZE)
 #define FIXADDR_TOP		(PCI_IO_START - SZ_2M)
-#define TASK_SIZE_64		(UL(1) << VA_BITS)
-
-#ifdef CONFIG_COMPAT
-#define TASK_SIZE_32		UL(0x100000000)
-#define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
-				TASK_SIZE_32 : TASK_SIZE_64)
-#define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \
-				TASK_SIZE_32 : TASK_SIZE_64)
-#else
-#define TASK_SIZE		TASK_SIZE_64
-#endif /* CONFIG_COMPAT */
-
-#define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 4))
 
 #define KERNEL_START      _text
 #define KERNEL_END        _end
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b46e54c2399b..c9530b5b5ca8 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -98,6 +98,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 	((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN))
 #define pte_valid_young(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
+#define pte_valid_user(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
 
 /*
  * Could the pte be present in the TLB? We must check mm_tlb_flush_pending
@@ -107,6 +109,18 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_accessible(mm, pte)	\
 	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte))
 
+/*
+ * p??_access_permitted() is true for valid user mappings (subject to the
+ * write permission check) other than user execute-only which do not have the
+ * PTE_USER bit set. PROT_NONE mappings do not have the PTE_VALID bit set.
+ */
+#define pte_access_permitted(pte, write) \
+	(pte_valid_user(pte) && (!(write) || pte_write(pte)))
+#define pmd_access_permitted(pmd, write) \
+	(pte_access_permitted(pmd_pte(pmd), (write)))
+#define pud_access_permitted(pud, write) \
+	(pte_access_permitted(pud_pte(pud), (write)))
+
 static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot)
 {
 	pte_val(pte) &= ~pgprot_val(prot);
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 29adab8138c3..023cacb946c3 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -19,6 +19,10 @@
 #ifndef __ASM_PROCESSOR_H
 #define __ASM_PROCESSOR_H
 
+#define TASK_SIZE_64		(UL(1) << VA_BITS)
+
+#ifndef __ASSEMBLY__
+
 /*
  * Default implementation of macro that returns current
  * instruction pointer ("program counter").
@@ -37,6 +41,22 @@
 #include <asm/ptrace.h>
 #include <asm/types.h>
 
+/*
+ * TASK_SIZE - the maximum size of a user space task.
+ * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
+ */
+#ifdef CONFIG_COMPAT
+#define TASK_SIZE_32		UL(0x100000000)
+#define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
+				TASK_SIZE_32 : TASK_SIZE_64)
+#define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \
+				TASK_SIZE_32 : TASK_SIZE_64)
+#else
+#define TASK_SIZE		TASK_SIZE_64
+#endif /* CONFIG_COMPAT */
+
+#define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 4))
+
 #define STACK_TOP_MAX		TASK_SIZE_64
 #ifdef CONFIG_COMPAT
 #define AARCH32_VECTORS_BASE	0xffff0000
@@ -85,6 +105,9 @@ struct thread_struct {
 	unsigned long		tp2_value;
 #endif
 	struct fpsimd_state	fpsimd_state;
+	void			*sve_state;	/* SVE registers, if any */
+	unsigned int		sve_vl;		/* SVE vector length */
+	unsigned int		sve_vl_onexec