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

Pull arm64 updates from Catalin Marinas:

 - Initial support for the ARMv9 Scalable Matrix Extension (SME).

   SME takes the approach used for vectors in SVE and extends this to
   provide architectural support for matrix operations. No KVM support
   yet, SME is disabled in guests.

 - Support for crashkernel reservations above ZONE_DMA via the
   'crashkernel=X,high' command line option.

 - btrfs search_ioctl() fix for live-lock with sub-page faults.

 - arm64 perf updates: support for the Hisilicon "CPA" PMU for
   monitoring coherent I/O traffic, support for Arm's CMN-650 and
   CMN-700 interconnect PMUs, minor driver fixes, kerneldoc cleanup.

 - Kselftest updates for SME, BTI, MTE.

 - Automatic generation of the system register macros from a 'sysreg'
   file describing the register bitfields.

 - Update the type of the function argument holding the ESR_ELx register
   value to unsigned long to match the architecture register size
   (originally 32-bit but extended since ARMv8.0).

 - stacktrace cleanups.

 - ftrace cleanups.

 - Miscellaneous updates, most notably: arm64-specific huge_ptep_get(),
   avoid executable mappings in kexec/hibernate code, drop TLB flushing
   from get_clear_flush() (and rename it to get_clear_contig()),
   ARCH_NR_GPIO bumped to 2048 for ARCH_APPLE.

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (145 commits)
  arm64/sysreg: Generate definitions for FAR_ELx
  arm64/sysreg: Generate definitions for DACR32_EL2
  arm64/sysreg: Generate definitions for CSSELR_EL1
  arm64/sysreg: Generate definitions for CPACR_ELx
  arm64/sysreg: Generate definitions for CONTEXTIDR_ELx
  arm64/sysreg: Generate definitions for CLIDR_EL1
  arm64/sve: Move sve_free() into SVE code section
  arm64: Kconfig.platforms: Add comments
  arm64: Kconfig: Fix indentation and add comments
  arm64: mm: avoid writable executable mappings in kexec/hibernate code
  arm64: lds: move special code sections out of kernel exec segment
  arm64/hugetlb: Implement arm64 specific huge_ptep_get()
  arm64/hugetlb: Use ptep_get() to get the pte value of a huge page
  arm64: kdump: Do not allocate crash low memory if not needed
  arm64/sve: Generate ZCR definitions
  arm64/sme: Generate defintions for SVCR
  arm64/sme: Generate SMPRI_EL1 definitions
  arm64/sme: Automatically generate SMPRIMAP_EL2 definitions
  arm64/sme: Automatically generate SMIDR_EL1 defines
  arm64/sme: Automatically generate defines for SMCR
  ...

6 files changed, 58 insertions, 19 deletions

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 5d31f6c64c8c..37d9f211c200 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -266,7 +266,7 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static inline bool esr_is_ptrauth_trap(u32 esr)
+static inline bool esr_is_ptrauth_trap(u64 esr)
 {
 	switch (esr_sys64_to_sysreg(esr)) {
 	case SYS_APIAKEYLO_EL1:
diff --git a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
index 5ad626527d41..fd55014b3497 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
@@ -159,20 +159,20 @@
  * No restrictions on instructions implemented in AArch64.
  */
 #define PVM_ID_AA64ISAR0_ALLOW (\
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_AES) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA1) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA2) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_CRC32) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_ATOMICS) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_RDM) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA3) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_SM3) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_SM4) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_DP) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_FHM) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_TS) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_TLB) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_RNDR) \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_AES) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SHA1) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SHA2) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_CRC32) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_ATOMIC) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_RDM) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SHA3) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SM3) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SM4) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_DP) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_FHM) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_TS) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_TLB) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_RNDR) \
 	)
 
 #define PVM_ID_AA64ISAR1_ALLOW (\
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 6410d21d8695..caace61ea459 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -47,10 +47,24 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		val |= CPTR_EL2_TFP | CPTR_EL2_TZ;
 		__activate_traps_fpsimd32(vcpu);
 	}
+	if (cpus_have_final_cap(ARM64_SME))
+		val |= CPTR_EL2_TSM;
 
 	write_sysreg(val, cptr_el2);
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2);
 
+	if (cpus_have_final_cap(ARM64_SME)) {
+		val = read_sysreg_s(SYS_HFGRTR_EL2);
+		val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK |
+			 HFGxTR_EL2_nSMPRI_EL1_MASK);
+		write_sysreg_s(val, SYS_HFGRTR_EL2);
+
+		val = read_sysreg_s(SYS_HFGWTR_EL2);
+		val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK |
+			 HFGxTR_EL2_nSMPRI_EL1_MASK);
+		write_sysreg_s(val, SYS_HFGWTR_EL2);
+	}
+
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
 
@@ -94,9 +108,25 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 
 	write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2);
 
+	if (cpus_have_final_cap(ARM64_SME)) {
+		u64 val;
+
+		val = read_sysreg_s(SYS_HFGRTR_EL2);
+		val |= HFGxTR_EL2_nTPIDR2_EL0_MASK |
+			HFGxTR_EL2_nSMPRI_EL1_MASK;
+		write_sysreg_s(val, SYS_HFGRTR_EL2);
+
+		val = read_sysreg_s(SYS_HFGWTR_EL2);
+		val |= HFGxTR_EL2_nTPIDR2_EL0_MASK |
+			HFGxTR_EL2_nSMPRI_EL1_MASK;
+		write_sysreg_s(val, SYS_HFGWTR_EL2);
+	}
+
 	cptr = CPTR_EL2_DEFAULT;
 	if (vcpu_has_sve(vcpu) && (vcpu->arch.flags & KVM_ARM64_FP_ENABLED))
 		cptr |= CPTR_EL2_TZ;
+	if (cpus_have_final_cap(ARM64_SME))
+		cptr &= ~CPTR_EL2_TSM;
 
 	write_sysreg(cptr, cptr_el2);
 	write_sysreg(__kvm_hyp_host_vector, vbar_el2);
diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
index 33f5181af330..619f94fc95fa 100644
--- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c
+++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
@@ -33,7 +33,7 @@ u64 id_aa64mmfr2_el1_sys_val;
  */
 static void inject_undef64(struct kvm_vcpu *vcpu)
 {
-	u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
+	u64 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
 
 	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
 	*vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR);
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 4fb419f7b8b6..6cb638b184b1 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -473,7 +473,7 @@ static int __vgic_v3_bpr_min(void)
 
 static int __vgic_v3_get_group(struct kvm_vcpu *vcpu)
 {
-	u32 esr = kvm_vcpu_get_esr(vcpu);
+	u64 esr = kvm_vcpu_get_esr(vcpu);
 	u8 crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
 
 	return crm != 8;
@@ -1016,7 +1016,7 @@ static void __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
 {
 	int rt;
-	u32 esr;
+	u64 esr;
 	u32 vmcr;
 	void (*fn)(struct kvm_vcpu *, u32, int);
 	bool is_read;
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 262dfe03134d..969f20daf97a 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -41,7 +41,8 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 
 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_EL1_TTA;
-	val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN);
+	val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN |
+		 CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN);
 
 	/*
 	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
@@ -62,6 +63,10 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		__activate_traps_fpsimd32(vcpu);
 	}
 
+	if (cpus_have_final_cap(ARM64_SME))
+		write_sysreg(read_sysreg(sctlr_el2) & ~SCTLR_ELx_ENTP2,
+			     sctlr_el2);
+
 	write_sysreg(val, cpacr_el1);
 
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1);
@@ -83,6 +88,10 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 	 */
 	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
 
+	if (cpus_have_final_cap(ARM64_SME))
+		write_sysreg(read_sysreg(sctlr_el2) | SCTLR_ELx_ENTP2,
+			     sctlr_el2);
+
 	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
 
 	if (!arm64_kernel_unmapped_at_el0())