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
  ...

22 files changed, 1746 insertions, 293 deletions

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 0029e13adb59..8265dd790895 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -11,8 +11,6 @@ CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_insn.o = -pg
 CFLAGS_REMOVE_return_address.o = -pg
 
-CFLAGS_setup.o = -DUTS_MACHINE='"$(UTS_MACHINE)"'
-
 # Object file lists.
 arm64-obj-y		:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index d06fbe4cd38d..c33b5e4010ab 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -228,15 +228,7 @@ ret:
 	return ret;
 }
 
-static struct ctl_table ctl_abi[] = {
-	{
-		.procname = "abi",
-		.mode = 0555,
-	},
-	{ }
-};
-
-static void __init register_insn_emulation_sysctl(struct ctl_table *table)
+static void __init register_insn_emulation_sysctl(void)
 {
 	unsigned long flags;
 	int i = 0;
@@ -262,8 +254,7 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
 	}
 	raw_spin_unlock_irqrestore(&insn_emulation_lock, flags);
 
-	table->child = insns_sysctl;
-	register_sysctl_table(table);
+	register_sysctl("abi", insns_sysctl);
 }
 
 /*
@@ -431,7 +422,7 @@ ret:
 	pr_warn_ratelimited("\"%s\" (%ld) uses obsolete SWP{B} instruction at 0x%llx\n",
 			current->comm, (unsigned long)current->pid, regs->pc);
 
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, 4);
 	return 0;
 
 fault:
@@ -512,7 +503,7 @@ ret:
 	pr_warn_ratelimited("\"%s\" (%ld) uses deprecated CP15 Barrier instruction at 0x%llx\n",
 			current->comm, (unsigned long)current->pid, regs->pc);
 
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, 4);
 	return 0;
 }
 
@@ -586,14 +577,14 @@ static int compat_setend_handler(struct pt_regs *regs, u32 big_endian)
 static int a32_setend_handler(struct pt_regs *regs, u32 instr)
 {
 	int rc = compat_setend_handler(regs, (instr >> 9) & 1);
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, 4);
 	return rc;
 }
 
 static int t16_setend_handler(struct pt_regs *regs, u32 instr)
 {
 	int rc = compat_setend_handler(regs, (instr >> 3) & 1);
-	regs->pc += 2;
+	arm64_skip_faulting_instruction(regs, 2);
 	return rc;
 }
 
@@ -644,7 +635,7 @@ static int __init armv8_deprecated_init(void)
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM64_ISNDEP_STARTING,
 				  "arm64/isndep:starting",
 				  run_all_insn_set_hw_mode, NULL);
-	register_insn_emulation_sysctl(ctl_abi);
+	register_insn_emulation_sysctl();
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 21e2c95d24e7..c5ba0097887f 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -27,6 +27,7 @@
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
+#include <asm/fpsimd.h>
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
 #include <asm/sysreg.h>
@@ -51,6 +52,21 @@ unsigned int compat_elf_hwcap2 __read_mostly;
 DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 EXPORT_SYMBOL(cpu_hwcaps);
 
+/*
+ * Flag to indicate if we have computed the system wide
+ * capabilities based on the boot time active CPUs. This
+ * will be used to determine if a new booting CPU should
+ * go through the verification process to make sure that it
+ * supports the system capabilities, without using a hotplug
+ * notifier.
+ */
+static bool sys_caps_initialised;
+
+static inline void set_sys_caps_initialised(void)
+{
+	sys_caps_initialised = true;
+}
+
 static int dump_cpu_hwcaps(struct notifier_block *self, unsigned long v, void *p)
 {
 	/* file-wide pr_fmt adds "CPU features: " prefix */
@@ -107,7 +123,11 @@ cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused)
  * sync with the documentation of the CPU feature register ABI.
  */
 static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_RDM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_DP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM4_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_RDM_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_ATOMICS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_CRC32_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA2_SHIFT, 4, 0),
@@ -117,34 +137,35 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_LRCPC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_FCMA_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_JSCVT_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_DPB_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_LRCPC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_FCMA_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_JSCVT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_DPB_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_GIC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0),
 	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI),
 	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI),
 	/* Linux doesn't care about the EL3 */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64PFR0_EL3_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL2_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0),
 	/* Linux shouldn't care about secure memory */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_BIGENDEL_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_ASID_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_ASID_SHIFT, 4, 0),
 	/*
 	 * Differing PARange is fine as long as all peripherals and memory are mapped
 	 * within the minimum PARange of all CPUs
@@ -155,20 +176,20 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_PAN_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_LOR_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_HPD_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_VHE_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_VMIDBITS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_HADBS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_LOR_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_HPD_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_VHE_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_VMIDBITS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_HADBS_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LVA_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_IESB_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LSM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_UAO_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_CNP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LVA_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IESB_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LSM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_UAO_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_CNP_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -193,14 +214,14 @@ struct arm64_ftr_reg arm64_ftr_reg_ctrel0 = {
 };
 
 static const struct arm64_ftr_bits ftr_id_mmfr0[] = {
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 28, 4, 0xf),	/* InnerShr */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 24, 4, 0),	/* FCSE */
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0xf),	/* InnerShr */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0),	/* FCSE */
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, 20, 4, 0),	/* AuxReg */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 16, 4, 0),	/* TCM */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 12, 4, 0),	/* ShareLvl */
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 8, 4, 0xf),	/* OuterShr */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0),	/* PMSA */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 0, 4, 0),	/* VMSA */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0),	/* TCM */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0),	/* ShareLvl */
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0xf),	/* OuterShr */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),	/* PMSA */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),	/* VMSA */
 	ARM64_FTR_END,
 };
 
@@ -221,8 +242,8 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_mvfr2[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0),		/* FPMisc */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 0, 4, 0),		/* SIMDMisc */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),		/* FPMisc */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),		/* SIMDMisc */
 	ARM64_FTR_END,
 };
 
@@ -234,25 +255,25 @@ static const struct arm64_ftr_bits ftr_dczid[] = {
 
 
 static const struct arm64_ftr_bits ftr_id_isar5[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_RDM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_CRC32_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_SHA2_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_SHA1_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_AES_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_SEVL_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_RDM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SEVL_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_mmfr4[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0),		/* ac2 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),	/* ac2 */
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_pfr0[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 12, 4, 0),	/* State3 */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 8, 4, 0),		/* State2 */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0),		/* State1 */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 0, 4, 0),		/* State0 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0),		/* State3 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0),		/* State2 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),		/* State1 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),		/* State0 */
 	ARM64_FTR_END,
 };
 
@@ -268,6 +289,12 @@ static const struct arm64_ftr_bits ftr_id_dfr0[] = {
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_zcr[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE,
+		ZCR_ELx_LEN_SHIFT, ZCR_ELx_LEN_SIZE, 0),	/* LEN */
+	ARM64_FTR_END,
+};
+
 /*
  * Common ftr bits for a 32bit register with all hidden, strict
  * attributes, with 4bit feature fields and a default safe value of
@@ -334,6 +361,7 @@ static const struct __ftr_reg_entry {
 	/* Op1 = 0, CRn = 0, CRm = 4 */
 	ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0),
 	ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_raz),
+	ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_raz),
 
 	/* Op1 = 0, CRn = 0, CRm = 5 */
 	ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0),
@@ -348,6 +376,9 @@ static const struct __ftr_reg_entry {
 	ARM64_FTR_REG(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1),
 	ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2),
 
+	/* Op1 = 0, CRn = 1, CRm = 2 */
+	ARM64_FTR_REG(SYS_ZCR_EL1, ftr_zcr),
+
 	/* Op1 = 3, CRn = 0, CRm = 0 */
 	{ SYS_CTR_EL0, &arm64_ftr_reg_ctrel0 },
 	ARM64_FTR_REG(SYS_DCZID_EL0, ftr_dczid),
@@ -485,6 +516,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 	init_cpu_ftr_reg(SYS_ID_AA64MMFR2_EL1, info->reg_id_aa64mmfr2);
 	init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0);
 	init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1);
+	init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0);
 
 	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
 		init_cpu_ftr_reg(SYS_ID_DFR0_EL1, info->reg_id_dfr0);
@@ -505,6 +537,10 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 		init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2);
 	}
 
+	if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) {
+		init_cpu_ftr_reg(SYS_ZCR_EL1, info->reg_zcr);
+		sve_init_vq_map();
+	}
 }
 
 static void update_cpu_ftr_reg(struct arm64_ftr_reg *reg, u64 new)
@@ -608,6 +644,9 @@ void update_cpu_features(int cpu,
 	taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu,
 				      info->reg_id_aa64pfr1, boot->reg_id_aa64pfr1);
 
+	taint |= check_update_ftr_reg(SYS_ID_AA64ZFR0_EL1, cpu,
+				      info->reg_id_aa64zfr0, boot->reg_id_aa64zfr0);
+
 	/*
 	 * If we have AArch32, we care about 32-bit features for compat.
 	 * If the system doesn't support AArch32, don't update them.
@@ -655,6 +694,16 @@ void update_cpu_features(int cpu,
 					info->reg_mvfr2, boot->reg_mvfr2);
 	}
 
+	if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) {
+		taint |= check_update_ftr_reg(SYS_ZCR_EL1, cpu,
+					info->reg_zcr, boot->reg_zcr);
+
+		/* Probe vector lengths, unless we already gave up on SVE */
+		if (id_aa64pfr0_sve(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1)) &&
+		    !sys_caps_initialised)
+			sve_update_vq_map();
+	}
+
 	/*
 	 * Mismatched CPU features are a recipe for disaster. Don't even
 	 * pretend to support them.
@@ -900,6 +949,19 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.min_field_value = 1,
 	},
 #endif
+#ifdef CONFIG_ARM64_SVE
+	{
+		.desc = "Scalable Vector Extension",
+		.capability = ARM64_SVE,
+		.def_scope = SCOPE_SYSTEM,
+		.sys_reg = SYS_ID_AA64PFR0_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64PFR0_SVE_SHIFT,
+		.min_field_value = ID_AA64PFR0_SVE,
+		.matches = has_cpuid_feature,
+		.enable = sve_kernel_enable,
+	},
+#endif /* CONFIG_ARM64_SVE */
 	{},
 };
 
@@ -921,9 +983,14 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_AES),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA1),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA2),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_SHA512),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_CRC32),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ATOMICS),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDRDM),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA3),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM3),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM4),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDDP),
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_FP),
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP),
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD),
@@ -932,6 +999,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_JSCVT),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FCMA),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_LRCPC),
+#ifdef CONFIG_ARM64_SVE
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, HWCAP_SVE),
+#endif
 	{},
 };
 
@@ -1041,21 +1111,6 @@ void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 }
 
 /*
- * Flag to indicate if we have computed the system wide
- * capabilities based on the boot time active CPUs. This
- * will be used to determine if a new booting CPU should
- * go through the verification process to make sure that it
- * supports the system capabilities, without using a hotplug
- * notifier.
- */
-static bool sys_caps_initialised;
-
-static inline void set_sys_caps_initialised(void)
-{
-	sys_caps_initialised = true;
-}
-
-/*
  * Check for CPU features that are used in early boot
  * based on the Boot CPU value.
  */
@@ -1097,6 +1152,23 @@ verify_local_cpu_features(const struct arm64_cpu_capabilities *caps)
 	}
 }
 
+static void verify_sve_features(void)
+{
+	u64 safe_zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1);
+	u64 zcr = read_zcr_features();
+
+	unsigned int safe_len = safe_zcr & ZCR_ELx_LEN_MASK;
+	unsigned int len = zcr & ZCR_ELx_LEN_MASK;
+
+	if (len < safe_len || sve_verify_vq_map()) {
+		pr_crit("CPU%d: SVE: required vector length(s) missing\n",
+			smp_processor_id());
+		cpu_die_early();
+	}
+
+	/* Add checks on other ZCR bits here if necessary */
+}
+
 /*
  * Run through the enabled system capabilities and enable() it on this CPU.
  * The capabilities were decided based on the available CPUs at the boot time.
@@ -1110,8 +1182,12 @@ static void verify_local_cpu_capabilities(void)
 	verify_local_cpu_errata_workarounds();
 	verify_local_cpu_features(arm64_features);
 	verify_local_elf_hwcaps(arm64_elf_hwcaps);
+
 	if (system_supports_32bit_el0())
 		verify_local_elf_hwcaps(compat_elf_hwcaps);
+
+	if (system_supports_sve())
+		verify_sve_features();
 }
 
 void check_local_cpu_capabilities(void)
@@ -1189,6 +1265,8 @@ void __init setup_cpu_features(void)
 	if (system_supports_32bit_el0())
 		setup_elf_hwcaps(compat_elf_hwcaps);
 
+	sve_setup();
+
 	/* Advertise that we have computed the system capabilities */
 	set_sys_caps_initialised();
 
@@ -1287,7 +1365,7 @@ static int emulate_mrs(struct pt_regs *regs, u32 insn)
 	if (!rc) {
 		dst = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RT, insn);
 		pt_regs_write_reg(regs, dst, val);
-		regs->pc += 4;
+		arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 	}
 
 	return rc;
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 311885962830..1e2554543506 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -19,6 +19,7 @@
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
+#include <asm/fpsimd.h>
 
 #include <linux/bitops.h>
 #include <linux/bug.h>
@@ -69,6 +70,12 @@ static const char *const hwcap_str[] = {
 	"fcma",
 	"lrcpc",
 	"dcpop",
+	"sha3",
+	"sm3",
+	"sm4",
+	"asimddp",
+	"sha512",
+	"sve",
 	NULL
 };
 
@@ -326,6 +333,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_id_aa64mmfr2 = read_cpuid(ID_AA64MMFR2_EL1);
 	info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1);
 	info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1);
+	info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1);
 
 	/* Update the 32bit ID registers only if AArch32 is implemented */
 	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
@@ -348,6 +356,10 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 		info->reg_mvfr2 = read_cpuid(MVFR2_EL1);
 	}
 
+	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
+	    id_aa64pfr0_sve(info->reg_id_aa64pfr0))
+		info->reg_zcr = read_zcr_features();
+
 	cpuinfo_detect_icache_policy(info);
 }
 
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index c7ef99904934..a88b6ccebbb4 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -30,6 +30,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/cputype.h>
+#include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/system_misc.h>
 
@@ -46,9 +47,9 @@ u8 debug_monitors_arch(void)
 static void mdscr_write(u32 mdscr)
 {
 	unsigned long flags;
-	local_dbg_save(flags);
+	flags = local_daif_save();
 	write_sysreg(mdscr, mdscr_el1);
-	local_dbg_restore(flags);
+	local_daif_restore(flags);
 }
 NOKPROBE_SYMBOL(mdscr_write);
 
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index 6a27cd6dbfa6..73f17bffcd23 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -41,3 +41,20 @@ ENTRY(fpsimd_load_state)
 	fpsimd_restore x0, 8
 	ret
 ENDPROC(fpsimd_load_state)
+
+#ifdef CONFIG_ARM64_SVE
+ENTRY(sve_save_state)
+	sve_save 0, x1, 2
+	ret
+ENDPROC(sve_save_state)
+
+ENTRY(sve_load_state)
+	sve_load 0, x1, x2, 3
+	ret
+ENDPROC(sve_load_state)
+
+ENTRY(sve_get_vl)
+	_sve_rdvl	0, 1
+	ret
+ENDPROC(sve_get_vl)
+#endif /* CONFIG_ARM64_SVE */
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index e1be42e11ff5..1175f5827ae1 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -108,13 +108,8 @@ ENTRY(_mcount)
 	mcount_get_lr	x1		//       function's lr (= parent's pc)
 	blr	x2			//   (*ftrace_trace_function)(pc, lr);
 
-#ifndef CONFIG_FUNCTION_GRAPH_TRACER
-skip_ftrace_call:			//   return;
-	mcount_exit			// }
-#else
-	mcount_exit			//   return;
-					// }
-skip_ftrace_call:
+skip_ftrace_call:			// }
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	ldr_l	x2, ftrace_graph_return
 	cmp	x0, x2			//   if ((ftrace_graph_return
 	b.ne	ftrace_graph_caller	//        != ftrace_stub)
@@ -123,9 +118,8 @@ skip_ftrace_call:
 	adr_l	x0, ftrace_graph_entry_stub //     != ftrace_graph_entry_stub))
 	cmp	x0, x2
 	b.ne	ftrace_graph_caller	//     ftrace_graph_caller();
-
-	mcount_exit
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+	mcount_exit
 ENDPROC(_mcount)
 
 #else /* CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index e1c59d4008a8..6d14b8f29b5f 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -28,7 +28,7 @@
 #include <asm/errno.h>
 #include <asm/esr.h>
 #include <asm/irq.h>
-#include <asm/memory.h>
+#include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 #include <asm/asm-uaccess.h>
@@ -221,6 +221,8 @@ alternative_else_nop_endif
 
 	.macro	kernel_exit, el
 	.if	\el != 0
+	disable_daif
+
 	/* Restore the task's original addr_limit. */
 	ldr	x20, [sp, #S_ORIG_ADDR_LIMIT]
 	str	x20, [tsk, #TSK_TI_ADDR_LIMIT]
@@ -373,18 +375,18 @@ ENTRY(vectors)
 	kernel_ventry	el1_sync			// Synchronous EL1h
 	kernel_ventry	el1_irq				// IRQ EL1h
 	kernel_ventry	el1_fiq_invalid			// FIQ EL1h
-	kernel_ventry	el1_error_invalid		// Error EL1h
+	kernel_ventry	el1_error			// Error EL1h
 
 	kernel_ventry	el0_sync			// Synchronous 64-bit EL0
 	kernel_ventry	el0_irq				// IRQ 64-bit EL0
 	kernel_ventry	el0_fiq_invalid			// FIQ 64-bit EL0
-	kernel_ventry	el0_error_invalid		// Error 64-bit EL0
+	kernel_ventry	el0_error			// Error 64-bit EL0
 
 #ifdef CONFIG_COMPAT
 	kernel_ventry	el0_sync_compat			// Synchronous 32-bit EL0
 	kernel_ventry	el0_irq_compat			// IRQ 32-bit EL0
 	kernel_ventry	el0_fiq_invalid_compat		// FIQ 32-bit EL0
-	kernel_ventry	el0_error_invalid_compat	// Error 32-bit EL0
+	kernel_ventry	el0_error_compat		// Error 32-bit EL0
 #else
 	kernel_ventry	el0_sync_invalid		// Synchronous 32-bit EL0
 	kernel_ventry	el0_irq_invalid			// IRQ 32-bit EL0
@@ -453,10 +455,6 @@ ENDPROC(el0_error_invalid)
 el0_fiq_invalid_compat:
 	inv_entry 0, BAD_FIQ, 32
 ENDPROC(el0_fiq_invalid_compat)
-
-el0_error_invalid_compat:
-	inv_entry 0, BAD_ERROR, 32
-ENDPROC(el0_error_invalid_compat)
 #endif
 
 el1_sync_invalid:
@@ -508,24 +506,18 @@ el1_da:
 	 * Data abort handling
 	 */
 	mrs	x3, far_el1
-	enable_dbg
-	// re-enable interrupts if they were enabled in the aborted context
-	tbnz	x23, #7, 1f			// PSR_I_BIT
-	enable_irq
-1:
+	inherit_daif	pstate=x23, tmp=x2
 	clear_address_tag x0, x3
 	mov	x2, sp				// struct pt_regs
 	bl	do_mem_abort
 
-	// disable interrupts before pulling preserved data off the stack
-	disable_irq
 	kernel_exit 1
 el1_sp_pc:
 	/*
 	 * Stack or PC alignment exception handling
 	 */
 	mrs	x0, far_el1
-	enable_dbg
+	inherit_daif	pstate=x23, tmp=x2
 	mov	x2, sp
 	bl	do_sp_pc_abort
 	ASM_BUG()
@@ -533,7 +525,7 @@ el1_undef:
 	/*
 	 * Undefined instruction
 	 */
-	enable_dbg
+	inherit_daif	pstate=x23, tmp=x2
 	mov	x0, sp
 	bl	do_undefinstr
 	ASM_BUG()
@@ -550,7 +542,7 @@ el1_dbg:
 	kernel_exit 1
 el1_inv:
 	// TODO: add support for undefined instructions in kernel mode
-	enable_dbg
+	inherit_daif	pstate=x23, tmp=x2
 	mov	x0, sp
 	mov	x2, x1
 	mov	x1, #BAD_SYNC
@@ -561,7 +553,7 @@ ENDPROC(el1_sync)
 	.align	6
 el1_irq:
 	kernel_entry 1
-	enable_dbg
+	enable_da_f
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
@@ -607,6 +599,8 @@ el0_sync:
 	b.eq	el0_ia
 	cmp	x24, #ESR_ELx_EC_FP_ASIMD	// FP/ASIMD access
 	b.eq	el0_fpsimd_acc
+	cmp	x24, #ESR_ELx_EC_SVE		// SVE access
+	b.eq	el0_sve_acc
 	cmp	x24, #ESR_ELx_EC_FP_EXC64	// FP/ASIMD exception
 	b.eq	el0_fpsimd_exc
 	cmp	x24, #ESR_ELx_EC_SYS64		// configurable trap
@@ -658,6 +652,7 @@ el0_svc_compat:
 	/*
 	 * AArch32 syscall handling
 	 */
+	ldr	x16, [tsk, #TSK_TI_FLAGS]	// load thread flags
 	adrp	stbl, compat_sys_call_table	// load compat syscall table pointer
 	mov	wscno, w7			// syscall number in w7 (r7)
 	mov     wsc_nr, #__NR_compat_syscalls
@@ -667,6 +662,10 @@ el0_svc_compat:
 el0_irq_compat:
 	kernel_entry 0, 32
 	b	el0_irq_naked
+
+el0_error_compat:
+	kernel_entry 0, 32
+	b	el0_error_naked
 #endif
 
 el0_da:
@@ -674,8 +673,7 @@ el0_da:
 	 * Data abort handling
 	 */
 	mrs	x26, far_el1
-	// enable interrupts before calling the main handler
-	enable_dbg_and_irq
+	enable_daif
 	ct_user_exit
 	clear_address_tag x0, x26
 	mov	x1, x25
@@ -687,8 +685,7 @@ el0_ia:
 	 * Instruction abort handling
 	 */
 	mrs	x26, far_el1
-	// enable interrupts before calling the main handler
-	enable_dbg_and_irq
+	enable_daif
 	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
@@ -699,17 +696,27 @@ el0_fpsimd_acc:
 	/*
 	 * Floating Point or Advanced SIMD access
 	 */
-	enable_dbg
+	enable_daif
 	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_fpsimd_acc
 	b	ret_to_user
+el0_sve_acc:
+	/*
+	 * Scalable Vector Extension access
+	 */
+	enable_daif
+	ct_user_exit
+	mov	x0, x25
+	mov	x1, sp
+	bl	do_sve_acc
+	b	ret_to_user
 el0_fpsimd_exc:
 	/*
-	 * Floating Point or Advanced SIMD exception
+	 * Floating Point, Advanced SIMD or SVE exception
 	 */
-	enable_dbg
+	enable_daif
 	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
@@ -720,8 +727,7 @@ el0_sp_pc:
 	 * Stack or PC alignment exception handling
 	 */
 	mrs	x26, far_el1
-	// enable interrupts before calling the main handler
-	enable_dbg_and_irq
+	enable_daif
 	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
@@ -732,8 +738,7 @@ el0_undef:
 	/*
 	 * Undefined instruction
 	 */
-	// enable interrupts before calling the main handler
-	enable_dbg_and_irq
+	enable_daif
 	ct_user_exit
 	mov	x0, sp
 	bl	do_undefinstr
@@ -742,7 +747,7 @@ el0_sys:
 	/*
 	 * System instructions, for trapped cache maintenance instructions
 	 */
-	enable_dbg_and_irq
+	enable_daif
 	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
@@ -757,11 +762,11 @@ el0_dbg:
 	mov	x1, x25
 	mov	x2, sp
 	bl	do_debug_exception
-	enable_dbg
+	enable_daif
 	ct_user_exit
 	b	ret_to_user
 el0_inv:
-	enable_dbg
+	enable_daif
 	ct_user_exit
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
@@ -774,7 +779,7 @@ ENDPROC(el0_sync)
 el0_irq:
 	kernel_entry 0
 el0_irq_naked:
-	enable_dbg
+	enable_da_f
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
@@ -788,12 +793,34 @@ el0_irq_naked:
 	b	ret_to_user
 ENDPROC(el0_irq)
 
+el1_error:
+	kernel_entry 1
+	mrs	x1, esr_el1
+	enable_dbg
+	mov	x0, sp
+	bl	do_serror
+	kernel_exit 1
+ENDPROC(el1_error)
+
+el0_error:
+	kernel_entry 0
+el0_error_naked:
+	mrs	x1, esr_el1
+	enable_dbg
+	mov	x0, sp
+	bl	do_serror
+	enable_daif
+	ct_user_exit
+	b	ret_to_user
+ENDPROC(el0_error)
+
+
 /*
  * This is the fast syscall return path.  We do as little as possible here,
  * and this includes saving x0 back into the kernel stack.
  */
 ret_fast_syscall:
-	disable_irq				// disable interrupts
+	disable_daif
 	str	x0, [sp, #S_X0]			// returned x0
 	ldr	x1, [tsk, #TSK_TI_FLAGS]	// re-check for syscall tracing
 	and	x2, x1, #_TIF_SYSCALL_WORK
@@ -803,7 +830,7 @@ ret_fast_syscall:
 	enable_step_tsk x1, x2
 	kernel_exit 0
 ret_fast_syscall_trace:
-	enable_irq				// enable interrupts
+	enable_daif
 	b	__sys_trace_return_skipped	// we already saved x0
 
 /*
@@ -821,7 +848,7 @@ work_pending:
  * "slow" syscall return path.
  */
 ret_to_user:
-	disable_irq				// disable interrupts
+	disable_daif
 	ldr	x1, [tsk, #TSK_TI_FLAGS]
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, work_pending
@@ -835,16 +862,37 @@ ENDPROC(ret_to_user)
  */
 	.align	6
 el0_svc:
+	ldr	x16, [tsk, #TSK_TI_FLAGS]	// load thread flags
 	adrp	stbl, sys_call_table		// load syscall table pointer
 	mov	wscno, w8			// syscall number in w8
 	mov	wsc_nr, #__NR_syscalls
+
+#ifdef CONFIG_ARM64_SVE
+alternative_if_not ARM64_SVE
+	b	el0_svc_naked
+alternative_else_nop_endif
+	tbz	x16, #TIF_SVE, el0_svc_naked	// Skip unless TIF_SVE set:
+	bic	x16, x16, #_TIF_SVE		// discard SVE state
+	str	x16, [tsk, #TSK_TI_FLAGS]
+
+	/*
+	 * task_fpsimd_load() won't be called to update CPACR_EL1 in
+	 * ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only
+	 * happens if a context switch or kernel_neon_begin() or context
+	 * modification (sigreturn, ptrace) intervenes.
+	 * So, ensure that CPACR_EL1 is already correct for the fast-path case:
+	 */
+	mrs	x9, cpacr_el1
+	bic	x9, x9, #CPACR_EL1_ZEN_EL0EN	// disable SVE for el0
+	msr	cpacr_el1, x9			// synchronised by eret to el0
+#endif
+
 el0_svc_naked:					// compat entry point
 	stp	x0, xscno, [sp, #S_ORIG_X0]	// save the original x0 and syscall number
-	enable_dbg_and_irq
+	enable_daif
 	ct_user_exit 1
 
-	ldr	x16, [tsk, #TSK_TI_FLAGS]	// check for syscall hooks
-	tst	x16, #_TIF_SYSCALL_WORK
+	tst	x16, #_TIF_SYSCALL_WORK		// check for syscall hooks
 	b.ne	__sys_trace
 	cmp     wscno, wsc_nr			// check upper syscall limit
 	b.hs	ni_sys
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 5d547deb6996..143b3e72c25e 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -17,19 +17,34 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/bitmap.h>
 #include <linux/bottom_half.h>
+#include <linux/bug.h>
+#include <linux/cache.h>
+#include <linux/compat.h>
 #include <linux/cpu.h>
 #include <linux/cpu_pm.h>
 #include <linux/kernel.h>
+#include <linux/linkage.h>
+#include <linux/irqflags.h>
 #include <linux/init.h>
 #include <linux/percpu.h>
+#include <linux/prctl.h>
 #include <linux/preempt.h>
+#include <linux/prctl.h>
+#include <linux/ptrace.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task_stack.h>
 #include <linux/signal.h>
+#include <linux/slab.h>
+#include <linux/sysctl.h>
 
 #include <asm/fpsimd.h>
 #include <asm/cputype.h>
 #include <asm/simd.h>
+#include <asm/sigcontext.h>
+#include <asm/sysreg.h>
+#include <asm/traps.h>
 
 #define FPEXC_IOF	(1 << 0)
 #define FPEXC_DZF	(1 << 1)
@@ -39,6 +54,8 @@
 #define FPEXC_IDF	(1 << 7)
 
 /*
+ * (Note: in this discussion, statements about FPSIMD apply equally to SVE.)
+ *
  * In order to reduce the number of times the FPSIMD state is needlessly saved
  * and restored, we need to keep track of two things:
  * (a) for each task, we need to remember which CPU was the last one to have
@@ -99,10 +116,741 @@
  */
 static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state);
 
+/* Default VL for tasks that don't set it explicitly: */
+static int sve_default_vl = -1;
+
+#ifdef CONFIG_ARM64_SVE
+
+/* Maximum supported vector length across all CPUs (initially poisoned) */
+int __ro_after_init sve_max_vl = -1;
+/* Set of available vector lengths, as vq_to_bit(vq): */
+static __ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
+static void __percpu *efi_sve_state;
+
+#else /* ! CONFIG_ARM64_SVE */
+
+/* Dummy declaration for code that will be optimised out: */
+extern __ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
+extern void __percpu *efi_sve_state;
+
+#endif /* ! CONFIG_ARM64_SVE */
+
+/*
+ * Call __sve_free() directly only if you know task can't be scheduled
+ * or preempted.
+ */
+static void __sve_free(struct task_struct *task)
+{
+	kfree(task->thread.sve_state);
+	task->thread.sve_state = NULL;
+}
+
+static void sve_free(struct task_struct *task)
+{
+	WARN_ON(test_tsk_thread_flag(task, TIF_SVE));
+
+	__sve_free(task);
+}
+
+
+/* Offset of FFR in the SVE register dump */
+static size_t sve_ffr_offset(int vl)
+{
+	return SVE_SIG_FFR_OFFSET(sve_vq_from_vl(vl)) - SVE_SIG_REGS_OFFSET;
+}
+
+static void *sve_pffr(struct task_struct *task)
+{
+	return (char *)task->thread.sve_state +
+		sve_ffr_offset(task->thread.sve_vl);
+}
+
+static void change_cpacr(u64 val, u64 mask)
+{
+	u64 cpacr = read_sysreg(CPACR_EL1);
+	u64 new = (cpacr & ~mask) | val;
+
+	if (new != cpacr)
+		write_sysreg(new, CPACR_EL1);
+}
+
+static void sve_user_disable(void)
+{
+	change_cpacr(0, CPACR_EL1_ZEN_EL0EN);
+}
+
+static void sve_user_enable(void)
+{
+	change_cpacr(CPACR_EL1_ZEN_EL0EN, CPACR_EL1_ZEN_EL0EN);
+}
+
+/*
+ * TIF_SVE controls whether a task can use SVE without trapping while
+ * in userspace, and also the way a task's FPSIMD/SVE state is stored
+ * in thread_struct.
+ *
+ * The kernel uses this flag to track whether a user task is actively
+ * using SVE, and therefore whether full SVE register state needs to
+ * be tracked.  If not, the cheaper FPSIMD context handling code can
+ * be used instead of the more costly SVE equivalents.
+ *
+ *  * TIF_SVE set:
+ *
+ *    The task can execute SVE instructions while in userspace without
+ *    trapping to the kernel.
+ *
+ *    When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the
+ *    corresponding Zn), P0-P15 and FFR are encoded in in
+ *    task->thread.sve_state, formatted appropriately for vector
+ *    length task->thread.sve_vl.
+ *
+ *    task->thread.sve_state must point to a valid buffer at least
+ *    sve_state_size(task) bytes in size.
+ *
+ *    During any syscall, the kernel may optionally clear TIF_SVE and
+ *    discard the vector state except for the FPSIMD subset.
+ *
+ *  * TIF_SVE clear:
+ *
+ *    An attempt by the user task to execute an SVE instruction causes
+ *    do_sve_acc() to be called, which does some preparation and then
+ *    sets TIF_SVE.
+ *
+ *    When stored, FPSIMD registers V0-V31 are encoded in
+ *    task->fpsimd_state; bits [max : 128] for each of Z0-Z31 are
+ *    logically zero but not stored anywhere; P0-P15 and FFR are not
+ *    stored and have unspecified values from userspace's point of
+ *    view.  For hygiene purposes, the kernel zeroes them on next use,
+ *    but userspace is discouraged from relying on this.
+ *
+ *    task->thread.sve_state does not need to be non-NULL, valid or any
+ *    particular size: it must not be dereferenced.
+ *
+ *  * FPSR and FPCR are always stored in task->fpsimd_state irrespctive of
+ *    whether TIF_SVE is clear or set, since these are not vector length
+ *    dependent.
+ */
+
+/*
+ * Update current's FPSIMD/SVE registers from thread_struct.
+ *
+ * This function should be called only when the FPSIMD/SVE state in
+ * thread_struct is known to be up to date, when preparing to enter
+ * userspace.
+ *
+ * Softirqs (and preemption) must be disabled.
+ */
+static void task_fpsimd_load(void)
+{
+	WARN_ON(!in_softirq() && !irqs_disabled());
+
+	if (system_supports_sve() && test_thread_flag(TIF_SVE))
+		sve_load_state(sve_pffr(current),
+			       &current->thread.fpsimd_state.fpsr,
+			       sve_vq_from_vl(current->thread.sve_vl) - 1);
+	else
+		fpsimd_load_state(&current->thread.fpsimd_state);
+
+	if (system_supports_sve()) {
+		/* Toggle SVE trapping for userspace if needed */
+		if (test_thread_flag(TIF_SVE))
+			sve_user_enable();
+		else
+			sve_user_disable();
+
+		/* Serialised by exception return to user */
+	}
+}
+
+/*
+ * Ensure current's FPSIMD/SVE storage in thread_struct is up to date
+ * with respect to the CPU registers.
+ *
+ * Softirqs (and preemption) must be disabled.
+ */
+static void task_fpsimd_save(void)
+{
+	WARN_ON(!in_softirq() && !irqs_disabled());
+
+	if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
+		if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
+			if (WARN_ON(sve_get_vl() != current->thread.sve_vl)) {
+				/*
+				 * Can't save the user regs, so current would
+				 * re-enter user with corrupt state.
+				 * There's no way to recover, so kill it:
+				 */
+				force_signal_inject(
+					SIGKILL, 0, current_pt_regs(), 0);
+				return;
+			}
+
+			sve_save_state(sve_pffr(current),
+				       &current->thread.fpsimd_state.fpsr);
+		} else
+			fpsimd_save_state(&current->thread.fpsimd_state);
+	}
+}
+
+/*
+ * Helpers to translate bit indices in sve_vq_map to VQ values (and
+ * vice versa).  This allows find_next_bit() to be used to find the
+ * _maximum_ VQ not exceeding a certain value.
+ */
+
+static unsigned int vq_to_bit(unsigned int vq)
+{
+	return SVE_VQ_MAX - vq;
+}
+
+static unsigned int bit_to_vq(unsigned int bit)
+{
+	if (WARN_ON(bit >= SVE_VQ_MAX))
+		bit = SVE_VQ_MAX - 1;
+
+	return SVE_VQ_MAX - bit;
+}
+
+/*
+ * All vector length selection from userspace comes through here.
+ * We're on a slow path, so some sanity-checks are included.
+ * If things go wrong there's a bug somewhere, but try to fall back to a
+ * safe choice.
+ */
+static unsigned int find_supported_vector_length(unsigned int vl)
+{
+	int bit;
+	int max_vl = sve_max_vl;
+
+	if (WARN_ON(!sve_vl_valid(vl)))
+		vl = SVE_VL_MIN;
+
+	if (WARN_ON(!sve_vl_valid(max_vl)))
+		max_vl = SVE_VL_MIN;
+
+	if (vl > max_vl)
+		vl = max_vl;
+
+	bit = find_next_bit(sve_vq_map, SVE_VQ_MAX,
+			    vq_to_bit(sve_vq_from_vl(vl)));
+	return sve_vl_from_vq(bit_to_vq(bit));
+}
+
+#ifdef CONFIG_SYSCTL
+
+static int sve_proc_do_default_vl(struct ctl_table *table, int write,
+				  void __user *buffer, size_t *lenp,
+				  loff_t *ppos)
+{
+	int ret;
+	int vl = sve_default_vl;
+	struct ctl_table tmp_table = {
+		.data = &vl,
+		.maxlen = sizeof(vl),
+	};
+
+	ret = proc_dointvec(&tmp_table, write, buffer, lenp, ppos);
+	if (ret || !write)
+		return ret;
+
+	/* Writing -1 has the special meaning "set to max": */
+	if (vl == -1) {
+		/* Fail safe if sve_max_vl wasn't initialised */
+		if (WARN_ON(!sve_vl_valid(sve_max_vl)))
+			vl = SVE_VL_MIN;
+		else
+			vl = sve_max_vl;
+
+		goto chosen;
+	}
+
+	if (!sve_vl_valid(vl))
+		return -EINVAL;
+
+	vl = find_supported_vector_length(vl);
+chosen:
+	sve_default_vl = vl;
+	return 0;
+}
+
+static struct ctl_table sve_default_vl_table[] = {
+	{
+		.procname	= "sve_default_vector_length",
+		.mode		= 0644,
+		.proc_handler	= sve_proc_do_default_vl,
+	},
+	{ }
+};
+
+static int __init sve_sysctl_init(void)
+{
+	if (system_supports_sve())
+		if (!register_sysctl("abi", sve_default_vl_table))
+			return -EINVAL;
+
+	return 0;
+}
+
+#else /* ! CONFIG_SYSCTL */
+static int __init sve_sysctl_init(void) { return 0; }
+#endif /* ! CONFIG_SYSCTL */
+
+#define ZREG(sve_state, vq, n) ((char *)(sve_state) +		\
+	(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
+
+/*
+ * Transfer the FPSIMD state in task->thread.fpsimd_state to
+ * task->thread.sve_state.
+ *
+ * Task can be a non-runnable task, or current.  In the latter case,
+ * softirqs (and preemption) must be disabled.
+ * task->thread.sve_state must point to at least sve_state_size(task)
+ * bytes of allocated kernel memory.
+ * task->thread.fpsimd_state must be up to date before calling this function.
+ */
+static void fpsimd_to_sve(struct task_struct *task)
+{
+	unsigned int vq;
+	void *sst = task->thread.sve_state;
+	struct fpsimd_state const *fst = &task->thread.fpsimd_state;
+	unsigned int i;
+
+	if (!system_supports_sve())
+		return;
+
+	vq = sve_vq_from_vl(task->thread.sve_vl);
+	for (i = 0; i < 32; ++i)
+		memcpy(ZREG(sst, vq, i), &fst->vregs[i],
+		       sizeof(fst->vregs[i]));
+}
+
+/*
+ * Transfer the SVE state in task->thread.sve_state to
+ * task->thread.fpsimd_state.
+ *
+ * Task can be a non-runnable task, or current.  In the latter case,
+ * softirqs (and preemption) must be disabled.
+ * task->thread.sve_state must point to at least sve_state_size(task)
+ * bytes of allocated kernel memory.
+ * task->thread.sve_state must be up to date before calling this function.
+ */
+static void sve_to_fpsimd(struct task_struct *task)
+{
+	unsigned int vq;
+	void const *sst = task->thread.sve_state;
+	struct fpsimd_state *fst = &task->thread.fpsimd_state;
+	unsigned int i;
+
+	if (!system_supports_sve())
+		return;
+
+	vq = sve_vq_from_vl(task->thread.sve_vl);
+	for (i = 0; i < 32; ++i)
+		memcpy(&fst->vregs[i], ZREG(sst, vq, i),
+		       sizeof(fst->vregs[i]));
+}
+
+#ifdef CONFIG_ARM64_SVE
+
+/*
+ * Return how many bytes of memory are required to store the full SVE
+ * state for task, given task's currently configured vector length.
+ */
+size_t sve_state_size(struct task_struct const *task)
+{
+	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(task->thread.sve_vl));
+}
+
+/*
+ * Ensure that task->thread.sve_state is allocated and sufficiently large.
+ *
+ * This function should be used only in preparation for replacing
+ * task->thread.sve_state with new data.  The memory is always zeroed
+ * here to prevent stale data from showing through: this is done in
+ * the interest of testability and predictability: except in the
+ * do_sve_acc() case, there is no ABI requirement to hide stale data
+ * written previously be task.
+ */
+void sve_alloc(struct task_struct *task)
+{
+	if (task->thread.sve_state) {
+		memset(task->thread.sve_state, 0, sve_state_size(current));
+		return;
+	}
+
+	/* This is a small allocation (maximum ~8KB) and Should Not Fail. */
+	task->thread.sve_state =
+		kzalloc(sve_state_size(task), GFP_KERNEL);
+
+	/*
+	 * If future SVE revisions can have larger vectors though,
+	 * this may cease to be true:
+	 */
+	BUG_ON(!task->thread.sve_state);
+}
+
+
+/*
+ * Ensure that task->thread.sve_state is up to date with respect to
+ * the user task, irrespective of when SVE is in use or not.
+ *
+ * This should only be called by ptrace.  task must be non-runnable.
+ * task->thread.sve_state must point to at least sve_state_size(task)
+ * bytes of allocated kernel memory.
+ */
+void fpsimd_sync_to_sve(struct task_struct *task)
+{
+	if (!test_tsk_thread_flag(task, TIF_SVE))
+		fpsimd_to_sve(task);
+}
+
+/*
+ * Ensure that task->thread.fpsimd_state is up to date with respect to
+ * the user task, irrespective of whether SVE is in use or not.
+ *
+ * This should only be called by ptrace.  task must be non-runnable.
+ * task->thread.sve_state must point to at least sve_state_size(task)
+ * bytes of allocated kernel memory.
+ */
+void sve_sync_to_fpsimd(struct task_struct *task)
+{
+	if (test_tsk_thread_flag(task, TIF_SVE))
+		sve_to_fpsimd(task);
+}
+
+/*
+ * Ensure that task->thread.sve_state is up to date with respect to
+ * the task->thread.fpsimd_state.
+ *
+ * This should only be called by ptrace to merge new FPSIMD register
+ * values into a task for which SVE is currently active.
+ * task must be non-runnable.
+ * task->thread.sve_state must point to at least sve_state_size(task)
+ * bytes of allocated kernel memory.
+ * task->thread.fpsimd_state must already have been initialised with
+ * the new FPSIMD register values to be merged in.
+ */
+void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
+{
+	unsigned int vq;
+	void *sst = task->thread.sve_state;
+	struct fpsimd_state const *fst = &task->thread.fpsimd_state;
+	unsigned int i;
+
+	if (!test_tsk_thread_flag(task, TIF_SVE))
+		return;
+
+	vq = sve_vq_from_vl(task->thread.sve_vl);
+
+	memset(sst, 0, SVE_SIG_REGS_SIZE(vq));
+
+	for (i = 0; i < 32; ++i)
+		memcpy(ZREG(sst, vq, i), &fst->vregs[i],
+		       sizeof(fst->vregs[i]));
+}
+
+int sve_set_vector_length(struct task_struct *task,
+			  unsigned long vl, unsigned long flags)
+{
+	if (flags & ~(unsigned long)(PR_SVE_VL_INHERIT |
+				     PR_SVE_SET_VL_ONEXEC))
+		return -EINVAL;
+
+	if (!sve_vl_valid(vl))
+		return -EINVAL;
+
+	/*
+	 * Clamp to the maximum vector length that VL-agnostic SVE code can
+	 * work with.  A flag may be assigned in the future to allow setting
+	 * of larger vector lengths without confusing older software.
+	 */
+	if (vl > SVE_VL_ARCH_MAX)
+		vl = SVE_VL_ARCH_MAX;
+
+	vl = find_supported_vector_length(vl);
+
+	if (flags & (PR_SVE_VL_INHERIT |
+		     PR_SVE_SET_VL_ONEXEC))
+		task->thread.sve_vl_onexec = vl;
+	else
+		/* Reset VL to system default on next exec: */
+		task->thread.sve_vl_onexec = 0;
+
+	/* Only actually set the VL if not deferred: */
+	if (flags & PR_SVE_SET_VL_ONEXEC)
+		goto out;
+
+	if (vl == task->thread.sve_vl)
+		goto out;
+
+	/*
+	 * To ensure the FPSIMD bits of the SVE vector registers are preserved,
+	 * write any live register state back to task_struct, and convert to a
+	 * non-SVE thread.
+	 */
+	if (task == current) {
+		local_bh_disable();
+
+		task_fpsimd_save();
+		set_thread_flag(TIF_FOREIGN_FPSTATE);
+	}
+
+	fpsimd_flush_task_state(task);
+	if (test_and_clear_tsk_thread_flag(task, TIF_SVE))
+		sve_to_fpsimd(task);
+
+	if (task == current)
+		local_bh_enable();
+
+	/*
+	 * Force reallocation of task SVE state to the correct size
+	 * on next use:
+	 */
+	sve_free(task);
+
+	task->thread.sve_vl = vl;
+
+out:
+	if (flags & PR_SVE_VL_INHERIT)
+		set_tsk_thread_flag(task, TIF_SVE_VL_INHERIT);
+	else
+		clear_tsk_thread_flag(task, TIF_SVE_VL_INHERIT);
+
+	return 0;
+}
+
+/*
+ * Encode the current vector length and flags for return.
+ * This is only required for prctl(): ptrace has separate fields
+ *
+ * flags are as for sve_set_vector_length().
+ */
+static int sve_prctl_status(unsigned long flags)
+{
+	int ret;
+
+	if (flags & PR_SVE_SET_VL_ONEXEC)
+		ret = current->thread.sve_vl_onexec;
+	else
+		ret = current->thread.sve_vl;
+
+	if (test_thread_flag(TIF_SVE_VL_INHERIT))
+		ret |= PR_SVE_VL_INHERIT;
+
+	return ret;
+}
+
+/* PR_SVE_SET_VL */
+int sve_set_current_vl(unsigned long arg)
+{
+	unsigned long vl, flags;
+	int ret;
+
+	vl = arg & PR_SVE_VL_LEN_MASK;
+	flags = arg & ~vl;
+
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	ret = sve_set_vector_length(current, vl, flags);
+	if (ret)
+		return ret;
+
+	return sve_prctl_status(flags);
+}
+
+/* PR_SVE_GET_VL */
+int sve_get_current_vl(void)
+{
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	return sve_prctl_status(0);
+}
+
+/*
+ * Bitmap for temporary storage of the per-CPU set of supported vector lengths
+ * during secondary boot.
+ */
+static DECLARE_BITMAP(sve_secondary_vq_map, SVE_VQ_MAX);
+
+static void sve_probe_vqs(DECLARE_BITMAP(map, SVE_VQ_MAX))
+{
+	unsigned int vq, vl;
+	unsigned long zcr;
+
+	bitmap_zero(map, SVE_VQ_MAX);
+
+	zcr = ZCR_ELx_LEN_MASK;
+	zcr = read_sysreg_s(SYS_ZCR_EL1) & ~zcr;
+
+	for (vq = SVE_VQ_MAX; vq >= SVE_VQ_MIN; --vq) {
+		write_sysreg_s(zcr | (vq - 1), SYS_ZCR_EL1); /* self-syncing */
+		vl = sve_get_vl();
+		vq = sve_vq_from_vl(vl); /* skip intervening lengths */
+		set_bit(vq_to_bit(vq), map);
+	}
+}
+
+void __init sve_init_vq_map(void)
+{
+	sve_probe_vqs(sve_vq_map);
+}
+
+/*
+ * If we haven't committed to the set of supported VQs yet, filter out
+ * those not supported by the current CPU.
+ */
+void sve_update_vq_map(void)
+{
+	sve_probe_vqs(sve_secondary_vq_map);
+	bitmap_and(sve_vq_map, sve_vq_map, sve_secondary_vq_map, SVE_VQ_MAX);
+}
+
+/* Check whether the current CPU supports all VQs in the committed set */
+int sve_verify_vq_map(void)
+{
+	int ret = 0;
+
+	sve_probe_vqs(sve_secondary_vq_map);
+	bitmap_andnot(sve_secondary_vq_map, sve_vq_map, sve_secondary_vq_map,
+		      SVE_VQ_MAX);
+	if (!bitmap_empty(sve_secondary_vq_map, SVE_VQ_MAX)) {
+		pr_warn("SVE: cpu%d: Required vector length(s) missing\n",
+			smp_processor_id());
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static void __init sve_efi_setup(void)
+{
+	if (!IS_ENABLED(CONFIG_EFI))
+		return;
+
+	/*
+	 * alloc_percpu() warns and prints a backtrace if this goes wrong.
+	 * This is evidence of a crippled system and we are returning void,
+	 * so no attempt is made to handle this situation here.
+	 */
+	if (!sve_vl_valid(sve_max_vl))
+		goto fail;
+
+	efi_sve_state = __alloc_percpu(
+		SVE_SIG_REGS_SIZE(sve_vq_from_vl(sve_max_vl)), SVE_VQ_BYTES);
+	if (!efi_sve_state)
+		goto fail;
+
+	return;
+
+fail:
+	panic("Cannot allocate percpu memory for EFI SVE save/restore");
+}
+
+/*
+ * Enable SVE for EL1.
+ * Intended for use by the cpufeatures code during CPU boot.
+ */
+int sve_kernel_enable(void *__always_unused p)
+{
+	write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_ZEN_EL1EN, CPACR_EL1);
+	isb();
+
+	return 0;
+}
+
+void __init sve_setup(void)
+{
+	u64 zcr;
+
+	if (!system_supports_sve())
+		return;
+
+	/*
+	 * The SVE architecture mandates support for 128-bit vectors,
+	 * so sve_vq_map must have at least SVE_VQ_MIN set.
+	 * If something went wrong, at least try to patch it up:
+	 */
+	if (WARN_ON(!test_bit(vq_to_bit(SVE_VQ_MIN), sve_vq_map)))
+		set_bit(vq_to_bit(SVE_VQ_MIN), sve_vq_map);
+
+	zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1);
+	sve_max_vl = sve_vl_from_vq((zcr & ZCR_ELx_LEN_MASK) + 1);
+
+	/*
+	 * Sanity-check that the max VL we determined through CPU features
+	 * corresponds properly to sve_vq_map.  If not, do our best:
+	 */
+	if (WARN_ON(sve_max_vl != find_supported_vector_length(sve_max_vl)))
+		sve_max_vl = find_supported_vector_length(sve_max_vl);
+
+	/*
+	 * For the default VL, pick the maximum supported value <= 64.
+	 * VL == 64 is guaranteed not to grow the signal frame.
+	 */
+	sve_default_vl = find_supported_vector_length(64);
+
+	pr_info("SVE: maximum available vector length %u bytes per vector\n",
+		sve_max_vl);
+	pr_info("SVE: default vector length %u bytes per vector\n",
+		sve_default_vl);
+
+	sve_efi_setup();
+}
+
+/*
+ * Called from the put_task_struct() path, which cannot get here
+ * unless dead_task is really dead and not schedulable.
+ */
+void fpsimd_release_task(struct task_struct *dead_task)
+{
+	__sve_free(dead_task);
+}
+
+#endif /* CONFIG_ARM64_SVE */
+
+/*
+ * Trapped SVE access
+ *
+ * Storage is allocated for the full SVE state, the current FPSIMD
+ * register contents are migrated across, and TIF_SVE is set so that
+ * the SVE access trap will be disabled the next time this task
+ * reaches ret_to_user.
+ *
+ * TIF_SVE should be clear on entry: otherwise, task_fpsimd_load()
+ * would have disabled the SVE access trap for userspace during
+ * ret_to_user, making an SVE access trap impossible in that case.
+ */
+asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs)
+{
+	/* Even if we chose not to use SVE, the hardware could still trap: */
+	if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) {
+		force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
+		return;
+	}
+
+	sve_alloc(current);
+
+	local_bh_disable();
+
+	task_fpsimd_save();
+	fpsimd_to_sve(current);
+
+	/* Force ret_to_user to reload the registers: */
+	fpsimd_flush_task_state(current);
+	set_thread_flag(TIF_FOREIGN_FPSTATE);
+
+	if (test_and_set_thread_flag(TIF_SVE))
+		WARN_ON(1); /* SVE access shouldn't have trapped */
+
+	local_bh_enable();
+}
+
 /*
  * Trapped FP/ASIMD access.
  */
-void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
+asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
 {
 	/* TODO: implement lazy context saving/restoring */
 	WARN_ON(1);
@@ -111,7 +859,7 @@ void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
 /*
  * Raise a SIGFPE for the current process.
  */
-void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
+asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
 {
 	siginfo_t info;
 	unsigned int si_code = 0;
@@ -144,8 +892,8 @@ void fpsimd_thread_switch(struct task_struct *next)
 	 * the registers is in fact the most recent userland FPSIMD state of
 	 * 'current'.
 	 */
-	if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE))
-		fpsimd_save_state(&current->thread.fpsimd_state);
+	if (current->mm)
+		task_fpsimd_save();
 
 	if (next->mm) {
 		/*
@@ -159,16 +907,16 @@ void fpsimd_thread_switch(struct task_struct *next)
 
 		if (__this_cpu_read(fpsimd_last_state) == st
 		    && st->cpu == smp_processor_id())
-			clear_ti_thread_flag(task_thread_info(next),
-					     TIF_FOREIGN_FPSTATE);
+			clear_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE);
 		else
-			set_ti_thread_flag(task_thread_info(next),
-					   TIF_FOREIGN_FPSTATE);
+			set_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE);
 	}
 }
 
 void fpsimd_flush_thread(void)
 {
+	int vl, supported_vl;
+
 	if (!system_supports_fpsimd())
 		return;
 
@@ -176,6 +924,42 @@ void fpsimd_flush_thread(void)
 
 	memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
 	fpsimd_flush_task_state(current);
+
+	if (system_supports_sve()) {
+		clear_thread_flag(TIF_SVE);
+		sve_free(current);
+
+		/*
+		 * Reset the task vector length as required.
+		 * This is where we ensure that all user tasks have a valid
+		 * vector length configured: no kernel task can become a user
+		 * task without an exec and hence a call to this function.
+		 * By the time the first call to this function is made, all
+		 * early hardware probing is complete, so sve_default_vl
+		 * should be valid.
+		 * If a bug causes this to go wrong, we make some noise and
+		 * try to fudge thread.sve_vl to a safe value here.
+		 */
+		vl = current->thread.sve_vl_onexec ?
+			current->thread.sve_vl_onexec : sve_default_vl;
+
+		if (WARN_ON(!sve_vl_valid(vl)))
+			vl = SVE_VL_MIN;
+
+		supported_vl = find_supported_vector_length(vl);
+		if (WARN_ON(supported_vl != vl))
+			vl = supported_vl;
+
+		current->thread.sve_vl = vl;
+
+		/*
+		 * If the task is not set to inherit, ensure that the vector
+		 * length will be reset by a subsequent exec:
+		 */
+		if (!test_thread_flag(TIF_SVE_VL_INHERIT))
+			current->thread.sve_vl_onexec = 0;
+	}
+
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
 
 	local_bh_enable();
@@ -191,14 +975,23 @@ void fpsimd_preserve_current_state(void)
 		return;
 
 	local_bh_disable();
-
-	if (!test_thread_flag(TIF_FOREIGN_FPSTATE))
-		fpsimd_save_state(&current->thread.fpsimd_state);
-
+	task_fpsimd_save();
 	local_bh_enable();
 }
 
 /*
+ * Like fpsimd_preserve_current_state(), but ensure that
+ * current->thread.fpsimd_state is updated so that it can be copied to
+ * the signal frame.
+ */
+void fpsimd_signal_preserve_current_state(void)
+{
+	fpsimd_preserve_current_state();
+	if (system_supports_sve() && test_thread_flag(TIF_SVE))
+		sve_to_fpsimd(current);
+}
+
+/*
  * Load the userland FPSIMD state of 'current' from memory, but only if the
  * FPSIMD state already held in the registers is /not/ the most recent FPSIMD
  * state of 'current'
@@ -213,7 +1006,7 @@ void fpsimd_restore_current_state(void)
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		struct fpsimd_state *st = &current->thread.fpsimd_state;
 
-		fpsimd_load_state(st);
+		task_fpsimd_load();
 		__this_cpu_write(fpsimd_last_state, st);
 		st->cpu = smp_processor_id();
 	}
@@ -233,7 +1026,12 @@ void fpsimd_update_current_state(struct fpsimd_state *state)
 
 	local_bh_disable();
 
-	fpsimd_load_state(state);
+	if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
+		current->thread.fpsimd_state = *state;
+		fpsimd_to_sve(current);
+	}
+	task_fpsimd_load();
+
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		struct fpsimd_state *st = &current->thread.fpsimd_state;
 
@@ -252,6 +1050,33 @@ void fpsimd_flush_task_state(struct task_struct *t)
 	t->thread.fpsimd_state.cpu = NR_CPUS;
 }
 
+static inline void fpsimd_flush_cpu_state(void)
+{
+	__this_cpu_write(fpsimd_last_state, NULL);
+}
+
+/*
+ * Invalidate any task SVE state currently held in this CPU's regs.
+ *
+ * This is used to prevent the kernel from trying to reuse SVE register data
+ * that is detroyed by KVM guest enter/exit.  This function should go away when
+ * KVM SVE support is implemented.  Don't use it for anything else.
+ */
+#ifdef CONFIG_ARM64_SVE
+void sve_flush_cpu_state(void)
+{
+	struct fpsimd_state *const fpstate = __this_cpu_read(fpsimd_last_state);
+	struct task_struct *tsk;
+
+	if (!fpstate)
+		return;
+
+	tsk = container_of(fpstate, struct task_struct, thread.fpsimd_state);
+	if (test_tsk_thread_flag(tsk, TIF_SVE))
+		fpsimd_flush_cpu_state();
+}
+#endif /* CONFIG_ARM64_SVE */
+
 #ifdef CONFIG_KERNEL_MODE_NEON
 
 DEFINE_PER_CPU(bool, kernel_neon_busy);
@@ -286,11 +1111,13 @@ void kernel_neon_begin(void)
 	__this_cpu_write(kernel_neon_busy, true);
 
 	/* Save unsaved task fpsimd state, if any: */
-	if (current->mm && !test_and_set_thread_flag(TIF_FOREIGN_FPSTATE))
-		fpsimd_save_state(&current->thread.fpsimd_state);
+	if (current->mm) {
+		task_fpsimd_save();
+		set_thread_flag(TIF_FOREIGN_FPSTATE);
+	}
 
 	/* Invalidate any task state remaining in the fpsimd regs: */
-	__this_cpu_write(fpsimd_last_state, NULL);
+	fpsimd_flush_cpu_state();
 
 	preempt_disable();
 
@@ -325,6 +1152,7 @@ EXPORT_SYMBOL(kernel_neon_end);
 
 static DEFINE_PER_CPU(struct fpsimd_state, efi_fpsimd_state);
 static DEFINE_PER_CPU(bool, efi_fpsimd_state_used);
+static DEFINE_PER_CPU(bool, efi_sve_state_used);
 
 /*
  * EFI runtime services support functions
@@ -350,10 +1178,24 @@ void __efi_fpsimd_begin(void)
 
 	WARN_ON(preemptible());
 
-	if (may_use_simd())
+	if (may_use_simd()) {
 		kernel_neon_begin();
-	else {
-		fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
+	} else {
+		/*
+		 * If !efi_sve_state, SVE can't be in use yet and doesn't need
+		 * preserving:
+		 */
+		if (system_supports_sve() && likely(efi_sve_state)) {
+			char *sve_state = this_cpu_ptr(efi_sve_state);
+
+			__this_cpu_write(efi_sve_state_used, true);
+
+			sve_save_state(sve_state + sve_ffr_offset(sve_max_vl),
+				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr);
+		} else {
+			fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
+		}
+
 		__this_cpu_write(efi_fpsimd_state_used, true);
 	}
 }
@@ -366,10 +1208,22 @@ void __efi_fpsimd_end(void)
 	if (!system_supports_fpsimd())
 		return;
 
-	if (__this_cpu_xchg(efi_fpsimd_state_used, false))
-		fpsimd_load_state(this_cpu_ptr(&efi_fpsimd_state));
-	else
+	if (!__this_cpu_xchg(efi_fpsimd_state_used, false)) {
 		kernel_neon_end();
+	} else {
+		if (system_supports_sve() &&
+		    likely(__this_cpu_read(efi_sve_state_used))) {
+			char const *sve_state = this_cpu_ptr(efi_sve_state);
+
+			sve_load_state(sve_state + sve_ffr_offset(sve_max_vl),
+				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr,
+				       sve_vq_from_vl(sve_get_vl()) - 1);
+
+			__this_cpu_write(efi_sve_state_used, false);
+		} else {
+			fpsimd_load_state(this_cpu_ptr(&efi_fpsimd_state));
+		}
+	}
 }
 
 #endif /* CONFIG_EFI */
@@ -382,9 +1236,9 @@ static int fpsimd_cpu_pm_notifier(struct notifier_block *self,
 {
 	switch (cmd) {
 	case CPU_PM_ENTER:
-		if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE))
-			fpsimd_save_state(&current->thread.fpsimd_state);
-		this_cpu_write(fpsimd_last_state, NULL);
+		if (current->mm)
+			task_fpsimd_save();
+		fpsimd_flush_cpu_state();
 		break;
 	case CPU_PM_EXIT:
 		if (current->mm)
@@ -442,6 +1296,6 @@ static int __init fpsimd_init(void)
 	if (!(elf_hwcap & HWCAP_ASIMD))
 		pr_notice("Advanced SIMD is not implemented\n");
 
-	return 0;
+	return sve_sysctl_init();
 }
 core_initcall(fpsimd_init);
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 0b243ecaf7ac..67e86a0f57ac 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -480,14 +480,21 @@ set_hcr:
 
 	/* Statistical profiling */
 	ubfx	x0, x1, #32, #4			// Check ID_AA64DFR0_EL1 PMSVer
-	cbz	x0, 6f				// Skip if SPE not present
-	cbnz	x2, 5f				// VHE?
+	cbz	x0, 7f				// Skip if SPE not present
+	cbnz	x2, 6f				// VHE?
+	mrs_s	x4, SYS_PMBIDR_EL1		// If SPE available at EL2,
+	and	x4, x4, #(1 << SYS_PMBIDR_EL1_P_SHIFT)
+	cbnz	x4, 5f				// then permit sampling of physical
+	mov	x4, #(1 << SYS_PMSCR_EL2_PCT_SHIFT | \
+		      1 << SYS_PMSCR_EL2_PA_SHIFT)
+	msr_s	SYS_PMSCR_EL2, x4		// addresses and physical counter
+5:
 	mov	x1, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
 	orr	x3, x3, x1			// If we don't have VHE, then
-	b	6f				// use EL1&0 translation.
-5:						// For VHE, use EL2 translation
+	b	7f				// use EL1&0 translation.
+6:						// For VHE, use EL2 translation
 	orr	x3, x3, #MDCR_EL2_TPMS		// and disable access from EL1
-6:
+7:
 	msr	mdcr_el2, x3			// Configure debug traps
 
 	/* Stage-2 translation */
@@ -517,8 +524,19 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	mov	x0, #0x33ff
 	msr	cptr_el2, x0			// Disable copro. traps to EL2
 
+	/* SVE register access */
+	mrs	x1, id_aa64pfr0_el1
+	ubfx	x1, x1, #ID_AA64PFR0_SVE_SHIFT, #4
+	cbz	x1, 7f
+
+	bic	x0, x0, #CPTR_EL2_TZ		// Also disable SVE traps
+	msr	cptr_el2, x0			// Disable copro. traps to EL2
+	isb
+	mov	x1, #ZCR_ELx_LEN_MASK		// SVE: Enable full vector
+	msr_s	SYS_ZCR_EL2, x1			// length for EL1.
+
 	/* Hypervisor stub */
-	adr_l	x0, __hyp_stub_vectors
+7:	adr_l	x0, __hyp_stub_vectors
 	msr	vbar_el2, x0
 
 	/* spsr */
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 095d3c170f5d..3009b8b80f08 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -27,6 +27,7 @@
 #include <asm/barrier.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
+#include <asm/daifflags.h>
 #include <asm/irqflags.h>
 #include <asm/kexec.h>
 #include <asm/memory.h>
@@ -285,7 +286,7 @@ int swsusp_arch_suspend(void)
 		return -EBUSY;
 	}
 
-	local_dbg_save(flags);
+	flags = local_daif_save();
 
 	if (__cpu_suspend_enter(&state)) {
 		/* make the crash dump kernel image visible/saveable */
@@ -315,7 +316,7 @@ int swsusp_arch_suspend(void)
 		__cpu_suspend_exit();
 	}
 
-	local_dbg_restore(flags);
+	local_daif_restore(flags);
 
 	return ret;
 }
diff --git a/arch/arm64/kernel/io.c b/arch/arm64/kernel/io.c
index 354be2a872ae..79b17384effa 100644
--- a/arch/arm64/kernel/io.c
+++ b/arch/arm64/kernel/io.c
@@ -25,8 +25,7 @@
  */
 void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count)
 {
-	while (count && (!IS_ALIGNED((unsigned long)from, 8) ||
-			 !IS_ALIGNED((unsigned long)to, 8))) {
+	while (count && !IS_ALIGNED((unsigned long)from, 8)) {
 		*(u8 *)to = __raw_readb(from);
 		from++;
 		to++;
@@ -54,23 +53,22 @@ EXPORT_SYMBOL(__memcpy_fromio);
  */
 void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count)
 {
-	while (count && (!IS_ALIGNED((unsigned long)to, 8) ||
-			 !IS_ALIGNED((unsigned long)from, 8))) {
-		__raw_writeb(*(volatile u8 *)from, to);
+	while (count && !IS_ALIGNED((unsigned long)to, 8)) {
+		__raw_writeb(*(u8 *)from, to);
 		from++;
 		to++;
 		count--;
 	}
 
 	while (count >= 8) {
-		__raw_writeq(*(volatile u64 *)from, to);
+		__raw_writeq(*(u64 *)from, to);
 		from += 8;
 		to += 8;
 		count -= 8;
 	}
 
 	while (count) {
-		__raw_writeb(*(volatile u8 *)from, to);
+		__raw_writeb(*(u8 *)from, to);
 		from++;
 		to++;
 		count--;
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 11121f608eb5..f76ea92dff91 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -18,6 +18,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/cpu_ops.h>
+#include <asm/daifflags.h>
 #include <asm/memory.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
@@ -195,8 +196,7 @@ void machine_kexec(struct kimage *kimage)
 
 	pr_info("Bye!\n");
 
-	/* Disable all DAIF exceptions. */
-	asm volatile ("msr daifset, #0xf" : : : "memory");
+	local_daif_mask();
 
 	/*
 	 * cpu_soft_restart will shutdown the MMU, disable data caches, then
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 2dc0f8482210..b2adcce7bc18 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -49,6 +49,7 @@
 #include <linux/notifier.h>
 #include <trace/events/power.h>
 #include <linux/percpu.h>
+#include <linux/thread_info.h>
 
 #include <asm/alternative.h>
 #include <asm/compat.h>
@@ -170,6 +171,39 @@ void machine_restart(char *cmd)
 	while (1);
 }
 
+static void print_pstate(struct pt_regs *regs)
+{
+	u64 pstate = regs->pstate;
+
+	if (compat_user_mode(regs)) {
+		printk("pstate: %08llx (%c%c%c%c %c %s %s %c%c%c)\n",
+			pstate,
+			pstate & COMPAT_PSR_N_BIT ? 'N' : 'n',
+			pstate & COMPAT_PSR_Z_BIT ? 'Z' : 'z',
+			pstate & COMPAT_PSR_C_BIT ? 'C' : 'c',
+			pstate & COMPAT_PSR_V_BIT ? 'V' : 'v',
+			pstate & COMPAT_PSR_Q_BIT ? 'Q' : 'q',
+			pstate & COMPAT_PSR_T_BIT ? "T32" : "A32",
+			pstate & COMPAT_PSR_E_BIT ? "BE" : "LE",
+			pstate & COMPAT_PSR_A_BIT ? 'A' : 'a',
+			pstate & COMPAT_PSR_I_BIT ? 'I' : 'i',
+			pstate & COMPAT_PSR_F_BIT ? 'F' : 'f');
+	} else {
+		printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO)\n",
+			pstate,
+			pstate & PSR_N_BIT ? 'N' : 'n',
+			pstate & PSR_Z_BIT ? 'Z' : 'z',
+			pstate & PSR_C_BIT ? 'C' : 'c',
+			pstate & PSR_V_BIT ? 'V' : 'v',
+			pstate & PSR_D_BIT ? 'D' : 'd',
+			pstate & PSR_A_BIT ? 'A' : 'a',
+			pstate & PSR_I_BIT ? 'I' : 'i',
+			pstate & PSR_F_BIT ? 'F' : 'f',
+			pstate & PSR_PAN_BIT ? '+' : '-',
+			pstate & PSR_UAO_BIT ? '+' : '-');
+	}
+}
+
 void __show_regs(struct pt_regs *regs)
 {
 	int i, top_reg;
@@ -186,10 +220,9 @@ void __show_regs(struct pt_regs *regs)
 	}
 
 	show_regs_print_info(KERN_DEFAULT);
-	print_symbol("PC is at %s\n", instruction_pointer(regs));
-	print_symbol("LR is at %s\n", lr);
-	printk("pc : [<%016llx>] lr : [<%016llx>] pstate: %08llx\n",
-	       regs->pc, lr, regs->pstate);
+	print_pstate(regs);
+	print_symbol("pc : %s\n", regs->pc);
+	print_symbol("lr : %s\n", lr);
 	printk("sp : %016llx\n", sp);
 
 	i = top_reg;
@@ -241,11 +274,27 @@ void release_thread(struct task_struct *dead_task)
 {
 }
 
+void arch_release_task_struct(struct task_struct *tsk)
+{
+	fpsimd_release_task(tsk);
+}
+
+/*
+ * src and dst may temporarily have aliased sve_state after task_struct
+ * is copied.  We cannot fix this properly here, because src may have
+ * live SVE state and dst's thread_info may not exist yet, so tweaking
+ * either src's or dst's TIF_SVE is not safe.
+ *
+ * The unaliasing is done in copy_thread() instead.  This works because
+ * dst is not schedulable or traceable until both of these functions
+ * have been called.
+ */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	if (current->mm)
 		fpsimd_preserve_current_state();
 	*dst = *src;
+
 	return 0;
 }
 
@@ -258,6 +307,13 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
 
+	/*
+	 * Unalias p->thread.sve_state (if any) from the parent task
+	 * and disable discard SVE state for p:
+	 */
+	clear_tsk_thread_flag(p, TIF_SVE);
+	p->thread.sve_state = NULL;
+
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
 		childregs->regs[0] = 0;
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 9cbb6123208f..7c44658b316d 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -32,6 +32,7 @@
 #include <linux/security.h>
 #include <linux/init.h>
 #include <linux/signal.h>
+#include <linux/string.h>
 #include <linux/uaccess.h>
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
@@ -40,6 +41,7 @@
 #include <linux/elf.h>
 
 #include <asm/compat.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
 #include <asm/pgtable.h>
 #include <asm/stacktrace.h>
@@ -618,17 +620,56 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
 /*
  * TODO: update fp accessors for lazy context switching (sync/flush hwstate)
  */
-static int fpr_get(struct task_struct *target, const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   void *kbuf, void __user *ubuf)
+static int __fpr_get(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     void *kbuf, void __user *ubuf, unsigned int start_pos)
 {
 	struct user_fpsimd_state *uregs;
+
+	sve_sync_to_fpsimd(target);
+
 	uregs = &target->thread.fpsimd_state.user_fpsimd;
 
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs,
+				   start_pos, start_pos + sizeof(*uregs));
+}
+
+static int fpr_get(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   void *kbuf, void __user *ubuf)
+{
 	if (target == current)
 		fpsimd_preserve_current_state();
 
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0, -1);
+	return __fpr_get(target, regset, pos, count, kbuf, ubuf, 0);
+}
+
+static int __fpr_set(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf,
+		     unsigned int start_pos)
+{
+	int ret;
+	struct user_fpsimd_state newstate;
+
+	/*
+	 * Ensure target->thread.fpsimd_state is up to date, so that a
+	 * short copyin can't resurrect stale data.
+	 */
+	sve_sync_to_fpsimd(target);
+
+	newstate = target->thread.fpsimd_state.user_fpsimd;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate,
+				 start_pos, start_pos + sizeof(newstate));
+	if (ret)
+		return ret;
+
+	target->thread.fpsimd_state.user_fpsimd = newstate;
+
+	return ret;
 }
 
 static int fpr_set(struct task_struct *target, const struct user_regset *regset,
@@ -636,15 +677,14 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct user_fpsimd_state newstate =
-		target->thread.fpsimd_state.user_fpsimd;
 
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, 0, -1);
+	ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, 0);
 	if (ret)
 		return ret;
 
-	target->thread.fpsimd_state.user_fpsimd = newstate;
+	sve_sync_from_fpsimd_zeropad(target);
 	fpsimd_flush_task_state(target);
+
 	return ret;
 }
 
@@ -702,6 +742,215 @@ static int system_call_set(struct task_struct *target,
 	return ret;
 }
 
+#ifdef CONFIG_ARM64_SVE
+
+static void sve_init_header_from_task(struct user_sve_header *header,
+				      struct task_struct *target)
+{
+	unsigned int vq;
+
+	memset(header, 0, sizeof(*header));
+
+	header->flags = test_tsk_thread_flag(target, TIF_SVE) ?
+		SVE_PT_REGS_SVE : SVE_PT_REGS_FPSIMD;
+	if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT))
+		header->flags |= SVE_PT_VL_INHERIT;
+
+	header->vl = target->thread.sve_vl;
+	vq = sve_vq_from_vl(header->vl);
+
+	header->max_vl = sve_max_vl;
+	if (WARN_ON(!sve_vl_valid(sve_max_vl)))
+		header->max_vl = header->vl;
+
+	header->size = SVE_PT_SIZE(vq, header->flags);
+	header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl),
+				      SVE_PT_REGS_SVE);
+}
+
+static unsigned int sve_size_from_header(struct user_sve_header const *header)
+{
+	return ALIGN(header->size, SVE_VQ_BYTES);
+}
+
+static unsigned int sve_get_size(struct task_struct *target,
+				 const struct user_regset *regset)
+{
+	struct user_sve_header header;
+
+	if (!system_supports_sve())
+		return 0;
+
+	sve_init_header_from_task(&header, target);
+	return sve_size_from_header(&header);
+}
+
+static int sve_get(struct task_struct *target,
+		   const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   void *kbuf, void __user *ubuf)
+{
+	int ret;
+	struct user_sve_header header;
+	unsigned int vq;
+	unsigned long start, end;
+
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	/* Header */
+	sve_init_header_from_task(&header, target);
+	vq = sve_vq_from_vl(header.vl);
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &header,
+				  0, sizeof(header));
+	if (ret)
+		return ret;
+
+	if (target == current)
+		fpsimd_preserve_current_state();
+
+	/* Registers: FPSIMD-only case */
+
+	BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header));
+	if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD)
+		return __fpr_get(target, regset, pos, count, kbuf, ubuf,
+				 SVE_PT_FPSIMD_OFFSET);
+
+	/* Otherwise: full SVE case */
+
+	BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
+	start = SVE_PT_SVE_OFFSET;
+	end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq);
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  target->thread.sve_state,
+				  start, end);
+	if (ret)
+		return ret;
+
+	start = end;
+	end = SVE_PT_SVE_FPSR_OFFSET(vq);
+	ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+				       start, end);
+	if (ret)
+		return ret;
+
+	/*
+	 * Copy fpsr, and fpcr which must follow contiguously in
+	 * struct fpsimd_state:
+	 */
+	start = end;
+	end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE;
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.fpsimd_state.fpsr,
+				  start, end);
+	if (ret)
+		return ret;
+
+	start = end;
+	end = sve_size_from_header(&header);
+	return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+					start, end);
+}
+
+static int sve_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;
+	struct user_sve_header header;
+	unsigned int vq;
+	unsigned long start, end;
+
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	/* Header */
+	if (count < sizeof(header))
+		return -EINVAL;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header,
+				 0, sizeof(header));
+	if (ret)
+		goto out;
+
+	/*
+	 * Apart from PT_SVE_REGS_MASK, all PT_SVE_* flags are consumed by
+	 * sve_set_vector_length(), which will also validate them for us:
+	 */
+	ret = sve_set_vector_length(target, header.vl,
+		((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16);
+	if (ret)
+		goto out;
+
+	/* Actual VL set may be less than the user asked for: */
+	vq = sve_vq_from_vl(target->thread.sve_vl);
+
+	/* Registers: FPSIMD-only case */
+
+	BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header));
+	if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD) {
+		ret = __fpr_set(target, regset, pos, count, kbuf, ubuf,
+				SVE_PT_FPSIMD_OFFSET);
+		clear_tsk_thread_flag(target, TIF_SVE);
+		goto out;
+	}
+
+	/* Otherwise: full SVE case */
+
+	/*
+	 * If setting a different VL from the requested VL and there is
+	 * register data, the data layout will be wrong: don't even
+	 * try to set the registers in this case.
+	 */
+	if (count && vq != sve_vq_from_vl(header.vl)) {
+		ret = -EIO;
+		goto out;
+	}
+
+	sve_alloc(target);
+
+	/*
+	 * Ensure target->thread.sve_state is up to date with target's
+	 * FPSIMD regs, so that a short copyin leaves trailing registers
+	 * unmodified.
+	 */
+	fpsimd_sync_to_sve(target);
+	set_tsk_thread_flag(target, TIF_SVE);
+
+	BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
+	start = SVE_PT_SVE_OFFSET;
+	end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq);
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 target->thread.sve_state,
+				 start, end);
+	if (ret)
+		goto out;
+
+	start = end;
+	end = SVE_PT_SVE_FPSR_OFFSET(vq);
+	ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+					start, end);
+	if (ret)
+		goto out;
+
+	/*
+	 * Copy fpsr, and fpcr which must follow contiguously in
+	 * struct fpsimd_state:
+	 */
+	start = end;
+	end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &target->thread.fpsimd_state.fpsr,
+				 start, end);
+
+out:
+	fpsimd_flush_task_state(target);
+	return ret;
+}
+
+#endif /* CONFIG_ARM64_SVE */
+
 enum aarch64_regset {
 	REGSET_GPR,
 	REGSET_FPR,
@@ -711,6 +960,9 @@ enum aarch64_regset {
 	REGSET_HW_WATCH,
 #endif
 	REGSET_SYSTEM_CALL,
+#ifdef CONFIG_ARM64_SVE
+	REGSET_SVE,
+#endif
 };
 
 static const struct user_regset aarch64_regsets[] = {
@@ -768,6 +1020,18 @@ static const struct user_regset aarch64_regsets[] = {
 		.get = system_call_get,
 		.set = system_call_set,
 	},
+#ifdef CONFIG_ARM64_SVE
+	[REGSET_SVE] = { /* Scalable Vector Extension */
+		.core_note_type = NT_ARM_SVE,
+		.n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE),
+				  SVE_VQ_BYTES),
+		.size = SVE_VQ_BYTES,
+		.align = SVE_VQ_BYTES,
+		.get = sve_get,
+		.set = sve_set,
+		.get_size = sve_get_size,
+	},
+#endif
 };
 
 static const struct user_regset_view user_aarch64_view = {
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index d4b740538ad5..30ad2f085d1f 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -23,7 +23,6 @@
 #include <linux/stddef.h>
 #include <linux/ioport.h>
 #include <linux/delay.h>
-#include <linux/utsname.h>
 #include <linux/initrd.h>
 #include <linux/console.h>
 #include <linux/cache.h>
@@ -48,6 +47,7 @@
 #include <asm/fixmap.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
+#include <asm/daifflags.h>
 #include <asm/elf.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
@@ -103,7 +103,8 @@ void __init smp_setup_processor_id(void)
 	 * access percpu variable inside lock_release
 	 */
 	set_my_cpu_offset(0);
-	pr_info("Booting Linux on physical CPU 0x%lx\n", (unsigned long)mpidr);
+	pr_info("Booting Linux on physical CPU 0x%010lx [0x%08x]\n",
+		(unsigned long)mpidr, read_cpuid_id());
 }
 
 bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
@@ -244,9 +245,6 @@ u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
 
 void __init setup_arch(char **cmdline_p)
 {
-	pr_info("Boot CPU: AArch64 Processor [%08x]\n", read_cpuid_id());
-
-	sprintf(init_utsname()->machine, UTS_MACHINE);
 	init_mm.start_code = (unsigned long) _text;
 	init_mm.end_code   = (unsigned long) _etext;
 	init_mm.end_data   = (unsigned long) _edata;
@@ -262,10 +260,11 @@ void __init setup_arch(char **cmdline_p)
 	parse_early_param();
 
 	/*
-	 *  Unmask asynchronous aborts after bringing up possible earlycon.
-	 * (Report possible System Errors once we can report this occurred)
+	 * Unmask asynchronous aborts and fiq after bringing up possible
+	 * earlycon. (Report possible System Errors once we can report this
+	 * occurred).
 	 */
-	local_async_enable();
+	local_daif_restore(DAIF_PROCCTX_NOIRQ);
 
 	/*
 	 * TTBR0 is only used for the identity mapping at this stage. Make it
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 0bdc96c61bc0..b120111a46be 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -31,6 +31,7 @@
 #include <linux/ratelimit.h>
 #include <linux/syscalls.h>
 
+#include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/elf.h>
 #include <asm/cacheflush.h>
@@ -63,6 +64,7 @@ struct rt_sigframe_user_layout {
 
 	unsigned long fpsimd_offset;
 	unsigned long esr_offset;
+	unsigned long sve_offset;
 	unsigned long extra_offset;
 	unsigned long end_offset;
 };
@@ -179,9 +181,6 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 	struct fpsimd_state *fpsimd = &current->thread.fpsimd_state;
 	int err;
 
-	/* dump the hardware registers to the fpsimd_state structure */
-	fpsimd_preserve_current_state();
-
 	/* copy the FP and status/control registers */
 	err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs));
 	__put_user_error(fpsimd->fpsr, &ctx->fpsr, err);
@@ -214,6 +213,8 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 	__get_user_error(fpsimd.fpsr, &ctx->fpsr, err);
 	__get_user_error(fpsimd.fpcr, &ctx->fpcr, err);
 
+	clear_thread_flag(TIF_SVE);
+
 	/* load the hardware registers from the fpsimd_state structure */
 	if (!err)
 		fpsimd_update_current_state(&fpsimd);
@@ -221,10 +222,118 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 	return err ? -EFAULT : 0;
 }
 
+
 struct user_ctxs {
 	struct fpsimd_context __user *fpsimd;
+	struct sve_context __user *sve;
 };
 
+#ifdef CONFIG_ARM64_SVE
+
+static int preserve_sve_context(struct sve_context __user *ctx)
+{
+	int err = 0;
+	u16 reserved[ARRAY_SIZE(ctx->__reserved)];
+	unsigned int vl = current->thread.sve_vl;
+	unsigned int vq = 0;
+
+	if (test_thread_flag(TIF_SVE))
+		vq = sve_vq_from_vl(vl);
+
+	memset(reserved, 0, sizeof(reserved));
+
+	__put_user_error(SVE_MAGIC, &ctx->head.magic, err);
+	__put_user_error(round_up(SVE_SIG_CONTEXT_SIZE(vq), 16),
+			 &ctx->head.size, err);
+	__put_user_error(vl, &ctx->vl, err);
+	BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
+	err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
+
+	if (vq) {
+		/*
+		 * This assumes that the SVE state has already been saved to
+		 * the task struct by calling preserve_fpsimd_context().
+		 */
+		err |= __copy_to_user((char __user *)ctx + SVE_SIG_REGS_OFFSET,
+				      current->thread.sve_state,
+				      SVE_SIG_REGS_SIZE(vq));
+	}
+
+	return err ? -EFAULT : 0;
+}
+
+static int restore_sve_fpsimd_context(struct user_ctxs *user)
+{
+	int err;
+	unsigned int vq;
+	struct fpsimd_state fpsimd;
+	struct sve_context sve;
+
+	if (__copy_from_user(&sve, user->sve, sizeof(sve)))
+		return -EFAULT;
+
+	if (sve.vl != current->thread.sve_vl)
+		return -EINVAL;
+
+	if (sve.head.size <= sizeof(*user->sve)) {
+		clear_thread_flag(TIF_SVE);
+		goto fpsimd_only;
+	}
+
+	vq = sve_vq_from_vl(sve.vl);
+
+	if (sve.head.size < SVE_SIG_CONTEXT_SIZE(vq))
+		return -EINVAL;
+
+	/*
+	 * Careful: we are about __copy_from_user() directly into
+	 * thread.sve_state with preemption enabled, so protection is
+	 * needed to prevent a racing context switch from writing stale
+	 * registers back over the new data.
+	 */
+
+	fpsimd_flush_task_state(current);
+	barrier();
+	/* From now, fpsimd_thread_switch() won't clear TIF_FOREIGN_FPSTATE */
+
+	set_thread_flag(TIF_FOREIGN_FPSTATE);
+	barrier();
+	/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
+
+	sve_alloc(current);
+	err = __copy_from_user(current->thread.sve_state,
+			       (char __user const *)user->sve +
+					SVE_SIG_REGS_OFFSET,
+			       SVE_SIG_REGS_SIZE(vq));
+	if (err)
+		return -EFAULT;
+
+	set_thread_flag(TIF_SVE);
+
+fpsimd_only:
+	/* copy the FP and status/control registers */
+	/* restore_sigframe() already checked that user->fpsimd != NULL. */
+	err = __copy_from_user(fpsimd.vregs, user->fpsimd->vregs,
+			       sizeof(fpsimd.vregs));
+	__get_user_error(fpsimd.fpsr, &user->fpsimd->fpsr, err);
+	__get_user_error(fpsimd.fpcr, &user->fpsimd->fpcr, err);
+
+	/* load the hardware registers from the fpsimd_state structure */
+	if (!err)
+		fpsimd_update_current_state(&fpsimd);
+
+	return err ? -EFAULT : 0;
+}
+
+#else /* ! CONFIG_ARM64_SVE */
+
+/* Turn any non-optimised out attempts to use these into a link error: */
+extern int preserve_sve_context(void __user *ctx);
+extern int restore_sve_fpsimd_context(struct user_ctxs *user);
+
+#endif /* ! CONFIG_ARM64_SVE */
+
+
 static int parse_user_sigframe(struct user_ctxs *user,
 			       struct rt_sigframe __user *sf)
 {
@@ -237,6 +346,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
 	char const __user *const sfp = (char const __user *)sf;
 
 	user->fpsimd = NULL;
+	user->sve = NULL;
 
 	if (!IS_ALIGNED((unsigned long)base, 16))
 		goto invalid;
@@ -287,6 +397,19 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			/* ignore */
 			break;
 
+		case SVE_MAGIC:
+			if (!system_supports_sve())
+				goto invalid;
+
+			if (user->sve)
+				goto invalid;
+
+			if (size < sizeof(*user->sve))
+				goto invalid;
+
+			user->sve = (struct sve_context __user *)head;
+			break;
+
 		case EXTRA_MAGIC:
 			if (have_extra_context)
 				goto invalid;
@@ -343,6 +466,10 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			 */
 			offset = 0;
 			limit = extra_size;
+
+			if (!access_ok(VERIFY_READ, base, limit))
+				goto invalid;
+
 			continue;
 
 		default:
@@ -359,9 +486,6 @@ static int parse_user_sigframe(struct user_ctxs *user,
 	}
 
 done:
-	if (!user->fpsimd)
-		goto invalid;
-
 	return 0;
 
 invalid:
@@ -395,8 +519,19 @@ static int restore_sigframe(struct pt_regs *regs,
 	if (err == 0)
 		err = parse_user_sigframe(&user, sf);
 
-	if (err == 0)
-		err = restore_fpsimd_context(user.fpsimd);
+	if (err == 0) {
+		if (!user.fpsimd)
+			return -EINVAL;
+
+		if (user.sve) {
+			if (!system_supports_sve())
+				return -EINVAL;
+
+			err = restore_sve_fpsimd_context(&user);
+		} else {
+			err = restore_fpsimd_context(user.fpsimd);
+		}
+	}
 
 	return err;
 }
@@ -455,6 +590,18 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user)
 			return err;
 	}
 
+	if (system_supports_sve()) {
+		unsigned int vq = 0;
+
+		if (test_thread_flag(TIF_SVE))
+			vq = sve_vq_from_vl(current->thread.sve_vl);
+
+		err = sigframe_alloc(user, &user->sve_offset,
+				     SVE_SIG_CONTEXT_SIZE(vq));
+		if (err)
+			return err;
+	}
+
 	return sigframe_alloc_end(user);
 }
 
@@ -496,6 +643,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 		__put_user_error(current->thread.fault_code, &esr_ctx->esr, err);
 	}
 
+	/* Scalable Vector Extension state, if present */
+	if (system_supports_sve() && err == 0 && user->sve_offset) {
+		struct sve_context __user *sve_ctx =
+			apply_user_offset(user, user->sve_offset);
+		err |= preserve_sve_context(sve_ctx);
+	}
+
 	if (err == 0 && user->extra_offset) {
 		char __user *sfp = (char __user *)user->sigframe;
 		char __user *userp =
@@ -595,6 +749,8 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
 	struct rt_sigframe __user *frame;
 	int err = 0;
 
+	fpsimd_signal_preserve_current_state();
+
 	if (get_sigframe(&user, ksig, regs))
 		return 1;
 
@@ -756,9 +912,12 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 		addr_limit_user_check();
 
 		if (thread_flags & _TIF_NEED_RESCHED) {
+			/* Unmask Debug and SError for the next task */
+			local_daif_restore(DAIF_PROCCTX_NOIRQ);
+
 			schedule();
 		} else {
-			local_irq_enable();
+			local_daif_restore(DAIF_PROCCTX);
 
 			if (thread_flags & _TIF_UPROBE)
 				uprobe_notify_resume(regs);
@@ -775,7 +934,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 				fpsimd_restore_current_state();
 		}
 
-		local_irq_disable();
+		local_daif_mask();
 		thread_flags = READ_ONCE(current_thread_info()->flags);
 	} while (thread_flags & _TIF_WORK_MASK);
 }
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index e09bf5d15606..22711ee8e36c 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -239,7 +239,7 @@ static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame)
 	 * Note that this also saves V16-31, which aren't visible
 	 * in AArch32.
 	 */
-	fpsimd_preserve_current_state();
+	fpsimd_signal_preserve_current_state();
 
 	/* Place structure header on the stack */
 	__put_user_error(magic, &frame->magic, err);
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 9f7195a5773e..551eb07c53b6 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -47,6 +47,7 @@
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpu_ops.h>
+#include <asm/daifflags.h>
 #include <asm/mmu_context.h>
 #include <asm/numa.h>
 #include <asm/pgtable.h>
@@ -216,6 +217,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
  */
 asmlinkage void secondary_start_kernel(void)
 {
+	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
 	struct mm_struct *mm = &init_mm;
 	unsigned int cpu;
 
@@ -265,14 +267,14 @@ asmlinkage void secondary_start_kernel(void)
 	 * the CPU migration code to notice that the CPU is online
 	 * before we continue.
 	 */
-	pr_info("CPU%u: Booted secondary processor [%08x]\n",
-					 cpu, read_cpuid_id());
+	pr_info("CPU%u: Booted secondary processor 0x%010lx [0x%08x]\n",
+					 cpu, (unsigned long)mpidr,
+					 read_cpuid_id());
 	update_cpu_boot_status(CPU_BOOT_SUCCESS);
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
-	local_irq_enable();
-	local_async_enable();
+	local_daif_restore(DAIF_PROCCTX);
 
 	/*
 	 * OK, it's off to the idle thread for us
@@ -368,10 +370,6 @@ void __cpu_die(unsigned int cpu)
 /*
  * Called from the idle thread for the CPU which has been shutdown.
  *
- * Note that we disable IRQs here, but do not re-enable them
- * before returning to the caller. This is also the behaviour
- * of the other hotplug-cpu capable cores, so presumably coming
- * out of idle fixes this.
  */
 void cpu_die(void)
 {
@@ -379,7 +377,7 @@ void cpu_die(void)
 
 	idle_task_exit();
 
-	local_irq_disable();
+	local_daif_mask();
 
 	/* Tell __cpu_die() that this CPU is now safe to dispose of */
 	(void)cpu_report_death();
@@ -837,7 +835,7 @@ static void ipi_cpu_stop(unsigned int cpu)
 {
 	set_cpu_online(cpu, false);
 
-	local_irq_disable();
+	local_daif_mask();
 
 	while (1)
 		cpu_relax();
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 77cd655e6eb7..3fe5ad884418 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -5,6 +5,7 @@
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
+#include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/exec.h>
 #include <asm/pgtable.h>
@@ -12,7 +13,6 @@
 #include <asm/mmu_context.h>
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
-#include <asm/tlbflush.h>
 
 /*
  * This is allocated by cpu_suspend_init(), and used to store a pointer to
@@ -58,7 +58,7 @@ void notrace __cpu_suspend_exit(void)
 	/*
 	 * Restore HW breakpoint registers to sane values
 	 * before debug exceptions are possibly reenabled
-	 * through local_dbg_restore.
+	 * by cpu_suspend()s local_daif_restore() call.
 	 */
 	if (hw_breakpoint_restore)
 		hw_breakpoint_restore(cpu);
@@ -82,7 +82,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	 * updates to mdscr register (saved and restored along with
 	 * general purpose registers) from kernel debuggers.
 	 */
-	local_dbg_save(flags);
+	flags = local_daif_save();
 
 	/*
 	 * Function graph tracer state gets incosistent when the kernel
@@ -115,7 +115,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	 * restored, so from this point onwards, debugging is fully
 	 * renabled if it was enabled when core started shutdown.
 	 */
-	local_dbg_restore(flags);
+	local_daif_restore(flags);
 
 	return ret;
 }
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 8383af15a759..3d3588fcd1c7 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -38,6 +38,7 @@
 
 #include <asm/atomic.h>
 #include <asm/bug.h>
+#include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
 #include <asm/insn.h>
@@ -58,55 +59,9 @@ static const char *handler[]= {
 
 int show_unhandled_signals = 1;
 
-/*
- * Dump out the contents of some kernel memory nicely...
- */
-static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
-		     unsigned long top)
-{
-	unsigned long first;
-	mm_segment_t fs;
-	int i;
-
-	/*
-	 * We need to switch to kernel mode so that we can use __get_user
-	 * to safely read from kernel space.
-	 */
-	fs = get_fs();
-	set_fs(KERNEL_DS);
-
-	printk("%s%s(0x%016lx to 0x%016lx)\n", lvl, str, bottom, top);
-
-	for (first = bottom & ~31; first < top; first += 32) {
-		unsigned long p;
-		char str[sizeof(" 12345678") * 8 + 1];
-
-		memset(str, ' ', sizeof(str));
-		str[sizeof(str) - 1] = '\0';
-
-		for (p = first, i = 0; i < (32 / 8)
-					&& p < top; i++, p += 8) {
-			if (p >= bottom && p < top) {
-				unsigned long val;
-
-				if (__get_user(val, (unsigned long *)p) == 0)
-					sprintf(str + i * 17, " %016lx", val);
-				else
-					sprintf(str + i * 17, " ????????????????");
-			}
-		}
-		printk("%s%04lx:%s\n", lvl, first & 0xffff, str);
-	}
-
-	set_fs(fs);
-}
-
 static void dump_backtrace_entry(unsigned long where)
 {
-	/*
-	 * Note that 'where' can have a physical address, but it's not handled.
-	 */
-	print_ip_sym(where);
+	printk(" %pS\n", (void *)where);
 }
 
 static void __dump_instr(const char *lvl, struct pt_regs *regs)
@@ -171,10 +126,7 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 
 	skip = !!regs;
 	printk("Call trace:\n");
-	while (1) {
-		unsigned long stack;
-		int ret;
-
+	do {
 		/* skip until specified stack frame */
 		if (!skip) {
 			dump_backtrace_entry(frame.pc);
@@ -189,17 +141,7 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 			 */
 			dump_backtrace_entry(regs->pc);
 		}
-		ret = unwind_frame(tsk, &frame);
-		if (ret < 0)
-			break;
-		if (in_entry_text(frame.pc)) {
-			stack = frame.fp - offsetof(struct pt_regs, stackframe);
-
-			if (on_accessible_stack(tsk, stack))
-				dump_mem("", "Exception stack", stack,
-					 stack + sizeof(struct pt_regs));
-		}
-	}
+	} while (!unwind_frame(tsk, &frame));
 
 	put_task_stack(tsk);
 }
@@ -293,6 +235,17 @@ void arm64_notify_die(const char *str, struct pt_regs *regs,
 	}
 }
 
+void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size)
+{
+	regs->pc += size;
+
+	/*
+	 * If we were single stepping, we want to get the step exception after
+	 * we return from the trap.
+	 */
+	user_fastforward_single_step(current);
+}
+
 static LIST_HEAD(undef_hook);
 static DEFINE_RAW_SPINLOCK(undef_lock);
 
@@ -358,8 +311,8 @@ exit:
 	return fn ? fn(regs, instr) : 1;
 }
 
-static void force_signal_inject(int signal, int code, struct pt_regs *regs,
-				unsigned long address)
+void force_signal_inject(int signal, int code, struct pt_regs *regs,
+			 unsigned long address)
 {
 	siginfo_t info;
 	void __user *pc = (void __user *)instruction_pointer(regs);
@@ -373,7 +326,7 @@ static void force_signal_inject(int signal, int code, struct pt_regs *regs,
 		desc = "illegal memory access";
 		break;
 	default:
-		desc = "bad mode";
+		desc = "unknown or unrecoverable error";
 		break;
 	}
 
@@ -480,7 +433,7 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
 	if (ret)
 		arm64_notify_segfault(regs, address);
 	else
-		regs->pc += 4;
+		arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
 static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
@@ -490,7 +443,7 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
 
 	pt_regs_write_reg(regs, rt, val);
 
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
 static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
@@ -498,7 +451,7 @@ static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
 	int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
 
 	pt_regs_write_reg(regs, rt, arch_counter_get_cntvct());
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
 static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
@@ -506,7 +459,7 @@ static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
 	int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
 
 	pt_regs_write_reg(regs, rt, arch_timer_get_rate());
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
 struct sys64_hook {
@@ -603,6 +556,7 @@ static const char *esr_class_str[] = {
 	[ESR_ELx_EC_HVC64]		= "HVC (AArch64)",
 	[ESR_ELx_EC_SMC64]		= "SMC (AArch64)",
 	[ESR_ELx_EC_SYS64]		= "MSR/MRS (AArch64)",
+	[ESR_ELx_EC_SVE]		= "SVE",
 	[ESR_ELx_EC_IMP_DEF]		= "EL3 IMP DEF",
 	[ESR_ELx_EC_IABT_LOW]		= "IABT (lower EL)",
 	[ESR_ELx_EC_IABT_CUR]		= "IABT (current EL)",
@@ -642,7 +596,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 		esr_get_class_string(esr));
 
 	die("Oops - bad mode", regs, 0);
-	local_irq_disable();
+	local_daif_mask();
 	panic("bad mode");
 }
 
@@ -708,6 +662,19 @@ asmlinkage void handle_bad_stack(struct pt_regs *regs)
 }
 #endif
 
+asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr)
+{
+	nmi_enter();
+
+	console_verbose();
+
+	pr_crit("SError Interrupt on CPU%d, code 0x%08x -- %s\n",
+		smp_processor_id(), esr, esr_get_class_string(esr));
+	__show_regs(regs);
+
+	panic("Asynchronous SError Interrupt");
+}
+
 void __pte_error(const char *file, int line, unsigned long val)
 {
 	pr_err("%s:%d: bad pte %016lx.\n", file, line, val);
@@ -761,7 +728,7 @@ static int bug_handler(struct pt_regs *regs, unsigned int esr)
 	}
 
 	/* If thread survives, skip over the BUG instruction and continue: */
-	regs->pc += AARCH64_INSN_SIZE;	/* skip BRK and resume */
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 	return DBG_HOOK_HANDLED;
 }
 
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index 76320e920965..c39872a7b03c 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -309,7 +309,7 @@ ENTRY(__kernel_clock_getres)
 	b.ne	4f
 	ldr	x2, 6f
 2:
-	cbz	w1, 3f
+	cbz	x1, 3f
 	stp	xzr, x2, [x1]
 
 3:	/* res == NULL. */