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

Pull arm64 updates from Will Deacon:
 "A sizeable pile of arm64 updates for 5.8.

  Summary below, but the big two features are support for Branch Target
  Identification and Clang's Shadow Call stack. The latter is currently
  arm64-only, but the high-level parts are all in core code so it could
  easily be adopted by other architectures pending toolchain support

  Branch Target Identification (BTI):

   - Support for ARMv8.5-BTI in both user- and kernel-space. This allows
     branch targets to limit the types of branch from which they can be
     called and additionally prevents branching to arbitrary code,
     although kernel support requires a very recent toolchain.

   - Function annotation via SYM_FUNC_START() so that assembly functions
     are wrapped with the relevant "landing pad" instructions.

   - BPF and vDSO updates to use the new instructions.

   - Addition of a new HWCAP and exposure of BTI capability to userspace
     via ID register emulation, along with ELF loader support for the
     BTI feature in .note.gnu.property.

   - Non-critical fixes to CFI unwind annotations in the sigreturn
     trampoline.

  Shadow Call Stack (SCS):

   - Support for Clang's Shadow Call Stack feature, which reserves
     platform register x18 to point at a separate stack for each task
     that holds only return addresses. This protects function return
     control flow from buffer overruns on the main stack.

   - Save/restore of x18 across problematic boundaries (user-mode,
     hypervisor, EFI, suspend, etc).

   - Core support for SCS, should other architectures want to use it
     too.

   - SCS overflow checking on context-switch as part of the existing
     stack limit check if CONFIG_SCHED_STACK_END_CHECK=y.

  CPU feature detection:

   - Removed numerous "SANITY CHECK" errors when running on a system
     with mismatched AArch32 support at EL1. This is primarily a concern
     for KVM, which disabled support for 32-bit guests on such a system.

   - Addition of new ID registers and fields as the architecture has
     been extended.

  Perf and PMU drivers:

   - Minor fixes and cleanups to system PMU drivers.

  Hardware errata:

   - Unify KVM workarounds for VHE and nVHE configurations.

   - Sort vendor errata entries in Kconfig.

  Secure Monitor Call Calling Convention (SMCCC):

   - Update to the latest specification from Arm (v1.2).

   - Allow PSCI code to query the SMCCC version.

  Software Delegated Exception Interface (SDEI):

   - Unexport a bunch of unused symbols.

   - Minor fixes to handling of firmware data.

  Pointer authentication:

   - Add support for dumping the kernel PAC mask in vmcoreinfo so that
     the stack can be unwound by tools such as kdump.

   - Simplification of key initialisation during CPU bringup.

  BPF backend:

   - Improve immediate generation for logical and add/sub instructions.

  vDSO:

   - Minor fixes to the linker flags for consistency with other
     architectures and support for LLVM's unwinder.

   - Clean up logic to initialise and map the vDSO into userspace.

  ACPI:

   - Work around for an ambiguity in the IORT specification relating to
     the "num_ids" field.

   - Support _DMA method for all named components rather than only PCIe
     root complexes.

   - Minor other IORT-related fixes.

  Miscellaneous:

   - Initialise debug traps early for KGDB and fix KDB cacheflushing
     deadlock.

   - Minor tweaks to early boot state (documentation update, set
     TEXT_OFFSET to 0x0, increase alignment of PE/COFF sections).

   - Refactoring and cleanup"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (148 commits)
  KVM: arm64: Move __load_guest_stage2 to kvm_mmu.h
  KVM: arm64: Check advertised Stage-2 page size capability
  arm64/cpufeature: Add get_arm64_ftr_reg_nowarn()
  ACPI/IORT: Remove the unused __get_pci_rid()
  arm64/cpuinfo: Add ID_MMFR4_EL1 into the cpuinfo_arm64 context
  arm64/cpufeature: Add remaining feature bits in ID_AA64PFR1 register
  arm64/cpufeature: Add remaining feature bits in ID_AA64PFR0 register
  arm64/cpufeature: Add remaining feature bits in ID_AA64ISAR0 register
  arm64/cpufeature: Add remaining feature bits in ID_MMFR4 register
  arm64/cpufeature: Add remaining feature bits in ID_PFR0 register
  arm64/cpufeature: Introduce ID_MMFR5 CPU register
  arm64/cpufeature: Introduce ID_DFR1 CPU register
  arm64/cpufeature: Introduce ID_PFR2 CPU register
  arm64/cpufeature: Make doublelock a signed feature in ID_AA64DFR0
  arm64/cpufeature: Drop TraceFilt feature exposure from ID_DFR0 register
  arm64/cpufeature: Add explicit ftr_id_isar0[] for ID_ISAR0 register
  arm64: mm: Add asid_gen_match() helper
  firmware: smccc: Fix missing prototype warning for arm_smccc_version_init
  arm64: vdso: Fix CFI directives in sigreturn trampoline
  arm64: vdso: Don't prefix sigreturn trampoline with a BTI C instruction
  ...

5 files changed, 66 insertions, 28 deletions

diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 8a1e81a400e0..1336e6f0acdf 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -138,7 +138,7 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
 
 	write_sysreg(val, cptr_el2);
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
 
 		isb();
@@ -181,7 +181,7 @@ static void deactivate_traps_vhe(void)
 	 * above before we can switch to the EL2/EL0 translation regime used by
 	 * the host.
 	 */
-	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT_VHE));
+	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
 
 	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
 	write_sysreg(vectors, vbar_el1);
@@ -192,7 +192,7 @@ static void __hyp_text __deactivate_traps_nvhe(void)
 {
 	u64 mdcr_el2 = read_sysreg(mdcr_el2);
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		u64 val;
 
 		/*
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 6d2df9fe0b5d..ea5d22fbdacf 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -107,7 +107,8 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
 	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
 
-	if (!cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (has_vhe() ||
+	    !cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
 		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
 	} else	if (!ctxt->__hyp_running_vcpu) {
@@ -138,7 +139,8 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL1],		tpidr_el1);
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE) &&
+	if (!has_vhe() &&
+	    cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT) &&
 	    ctxt->__hyp_running_vcpu) {
 		/*
 		 * Must only be done for host registers, hence the context
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index ceaddbe4279f..d063a576d511 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -23,7 +23,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
 
 	local_irq_save(cxt->flags);
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		/*
 		 * For CPUs that are affected by ARM errata 1165522 or 1530923,
 		 * we cannot trust stage-1 to be in a correct state at that
@@ -63,7 +63,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
 static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
 						  struct tlb_inv_context *cxt)
 {
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		u64 val;
 
 		/*
@@ -79,8 +79,9 @@ static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
 		isb();
 	}
 
+	/* __load_guest_stage2() includes an ISB for the workaround. */
 	__load_guest_stage2(kvm);
-	isb();
+	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
 }
 
 static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
@@ -103,7 +104,7 @@ static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm,
 	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
 	isb();
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		/* Restore the registers to what they were */
 		write_sysreg_el1(cxt->tcr, SYS_TCR);
 		write_sysreg_el1(cxt->sctlr, SYS_SCTLR);
@@ -117,7 +118,7 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
 {
 	write_sysreg(0, vttbr_el2);
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		/* Ensure write of the host VMID */
 		isb();
 		/* Restore the host's TCR_EL1 */
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 30b7ea680f66..70cd7bcca433 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -46,14 +46,6 @@ static const struct kvm_regs default_regs_reset32 = {
 			PSR_AA32_I_BIT | PSR_AA32_F_BIT),
 };
 
-static bool cpu_has_32bit_el1(void)
-{
-	u64 pfr0;
-
-	pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
-	return !!(pfr0 & 0x20);
-}
-
 /**
  * kvm_arch_vm_ioctl_check_extension
  *
@@ -66,7 +58,7 @@ int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 
 	switch (ext) {
 	case KVM_CAP_ARM_EL1_32BIT:
-		r = cpu_has_32bit_el1();
+		r = cpus_have_const_cap(ARM64_HAS_32BIT_EL1);
 		break;
 	case KVM_CAP_GUEST_DEBUG_HW_BPS:
 		r = get_num_brps();
@@ -288,7 +280,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	switch (vcpu->arch.target) {
 	default:
 		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
-			if (!cpu_has_32bit_el1())
+			if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1))
 				goto out;
 			cpu_reset = &default_regs_reset32;
 		} else {
@@ -340,11 +332,50 @@ out:
 	return ret;
 }
 
-void kvm_set_ipa_limit(void)
+u32 get_kvm_ipa_limit(void)
+{
+	return kvm_ipa_limit;
+}
+
+int kvm_set_ipa_limit(void)
 {
-	unsigned int ipa_max, pa_max, va_max, parange;
+	unsigned int ipa_max, pa_max, va_max, parange, tgran_2;
+	u64 mmfr0;
+
+	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	parange = cpuid_feature_extract_unsigned_field(mmfr0,
+				ID_AA64MMFR0_PARANGE_SHIFT);
+
+	/*
+	 * Check with ARMv8.5-GTG that our PAGE_SIZE is supported at
+	 * Stage-2. If not, things will stop very quickly.
+	 */
+	switch (PAGE_SIZE) {
+	default:
+	case SZ_4K:
+		tgran_2 = ID_AA64MMFR0_TGRAN4_2_SHIFT;
+		break;
+	case SZ_16K:
+		tgran_2 = ID_AA64MMFR0_TGRAN16_2_SHIFT;
+		break;
+	case SZ_64K:
+		tgran_2 = ID_AA64MMFR0_TGRAN64_2_SHIFT;
+		break;
+	}
+
+	switch (cpuid_feature_extract_unsigned_field(mmfr0, tgran_2)) {
+	default:
+	case 1:
+		kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n");
+		return -EINVAL;
+	case 0:
+		kvm_debug("PAGE_SIZE supported at Stage-2 (default)\n");
+		break;
+	case 2:
+		kvm_debug("PAGE_SIZE supported at Stage-2 (advertised)\n");
+		break;
+	}
 
-	parange = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1) & 0x7;
 	pa_max = id_aa64mmfr0_parange_to_phys_shift(parange);
 
 	/* Clamp the IPA limit to the PA size supported by the kernel */
@@ -378,6 +409,8 @@ void kvm_set_ipa_limit(void)
 	     "KVM IPA limit (%d bit) is smaller than default size\n", ipa_max);
 	kvm_ipa_limit = ipa_max;
 	kvm_info("IPA Size Limit: %dbits\n", kvm_ipa_limit);
+
+	return 0;
 }
 
 /*
@@ -390,7 +423,7 @@ void kvm_set_ipa_limit(void)
  */
 int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
 {
-	u64 vtcr = VTCR_EL2_FLAGS;
+	u64 vtcr = VTCR_EL2_FLAGS, mmfr0;
 	u32 parange, phys_shift;
 	u8 lvls;
 
@@ -406,7 +439,9 @@ int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
 		phys_shift = KVM_PHYS_SHIFT;
 	}
 
-	parange = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1) & 7;
+	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	parange = cpuid_feature_extract_unsigned_field(mmfr0,
+				ID_AA64MMFR0_PARANGE_SHIFT);
 	if (parange > ID_AA64MMFR0_PARANGE_MAX)
 		parange = ID_AA64MMFR0_PARANGE_MAX;
 	vtcr |= parange << VTCR_EL2_PS_SHIFT;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 51db934702b6..7d7a39b01135 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1456,9 +1456,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	ID_SANITISED(MVFR1_EL1),
 	ID_SANITISED(MVFR2_EL1),
 	ID_UNALLOCATED(3,3),
-	ID_UNALLOCATED(3,4),
-	ID_UNALLOCATED(3,5),
-	ID_UNALLOCATED(3,6),
+	ID_SANITISED(ID_PFR2_EL1),
+	ID_HIDDEN(ID_DFR1_EL1),
+	ID_SANITISED(ID_MMFR5_EL1),
 	ID_UNALLOCATED(3,7),
 
 	/* AArch64 ID registers */