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

Pull arm64 fixes from Will Deacon:

 - Fix bogus KASAN splat on EFI runtime stack

 - Select JUMP_LABEL unconditionally to avoid boot failure with pKVM and
   the legacy implementation of static keys

 - Avoid touching GCS registers when 'arm64.nogcs' has been passed on
   the command-line

 - Move a 'cpumask_t' off the stack in smp_send_stop()

 - Don't advertise SME-related hwcaps to userspace when ID_AA64PFR1_EL1
   indicates that SME is not implemented

 - Always check the VMA when handling an Overlay fault

 - Avoid corrupting TCR2_EL1 during boot

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64/mm: Drop wrong writes into TCR2_EL1
  arm64: poe: Handle spurious Overlay faults
  arm64: Filter out SME hwcaps when FEAT_SME isn't implemented
  arm64: move smp_send_stop() cpu mask off stack
  arm64/gcs: Don't try to access GCS registers if arm64.nogcs is enabled
  arm64: Unconditionally select CONFIG_JUMP_LABEL
  arm64: efi: Fix KASAN false positive for EFI runtime stack

Author: torvalds

arch/arm64/Kconfig

@@ -256,6 +256,7 @@ config ARM64
 	select HOTPLUG_SMT if HOTPLUG_CPU
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
+	select JUMP_LABEL
 	select KASAN_VMALLOC if KASAN
 	select LOCK_MM_AND_FIND_VMA
 	select MODULES_USE_ELF_RELA

arch/arm64/include/asm/el2_setup.h

@@ -287,17 +287,6 @@
 .Lskip_fgt2_\@:
 .endm
 
-.macro __init_el2_gcs
-	mrs_s	x1, SYS_ID_AA64PFR1_EL1
-	ubfx	x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4
-	cbz	x1, .Lskip_gcs_\@
-
-	/* Ensure GCS is not enabled when we start trying to do BLs */
-	msr_s	SYS_GCSCR_EL1, xzr
-	msr_s	SYS_GCSCRE0_EL1, xzr
-.Lskip_gcs_\@:
-.endm
-
 /**
  * Initialize EL2 registers to sane values. This should be called early on all
  * cores that were booted in EL2. Note that everything gets initialised as
@@ -319,7 +308,6 @@
 	__init_el2_cptr
 	__init_el2_fgt
 	__init_el2_fgt2
-        __init_el2_gcs
 .endm
 
 #ifndef __KVM_NVHE_HYPERVISOR__
@@ -371,6 +359,13 @@
 	msr_s   SYS_MPAMHCR_EL2, xzr		// clear TRAP_MPAMIDR_EL1 -> EL2
 
 .Lskip_mpam_\@:
+	check_override id_aa64pfr1, ID_AA64PFR1_EL1_GCS_SHIFT, .Linit_gcs_\@, .Lskip_gcs_\@, x1, x2
+
+.Linit_gcs_\@:
+	msr_s	SYS_GCSCR_EL1, xzr
+	msr_s	SYS_GCSCRE0_EL1, xzr
+
+.Lskip_gcs_\@:
 	check_override id_aa64pfr0, ID_AA64PFR0_EL1_SVE_SHIFT, .Linit_sve_\@, .Lskip_sve_\@, x1, x2
 
 .Linit_sve_\@:	/* SVE register access */

arch/arm64/kernel/Makefile

@@ -34,7 +34,7 @@ obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
 			   smp.o smp_spin_table.o topology.o smccc-call.o	\
 			   syscall.o proton-pack.o idle.o patching.o pi/	\
-			   rsi.o
+			   rsi.o jump_label.o
 
 obj-$(CONFIG_COMPAT)			+= sys32.o signal32.o			\
 					   sys_compat.o
@@ -47,7 +47,6 @@ obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o perf_callchain.o
 obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF)	+= watchdog_hld.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_CPU_PM)			+= sleep.o suspend.o
-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
 obj-$(CONFIG_KGDB)			+= kgdb.o
 obj-$(CONFIG_EFI)			+= efi.o efi-rt-wrapper.o
 obj-$(CONFIG_PCI)			+= pci.o

arch/arm64/kernel/cpufeature.c

@@ -3135,6 +3135,13 @@ static bool has_sve_feature(const struct arm64_cpu_capabilities *cap, int scope)
 }
 #endif
 
+#ifdef CONFIG_ARM64_SME
+static bool has_sme_feature(const struct arm64_cpu_capabilities *cap, int scope)
+{
+	return system_supports_sme() && has_user_cpuid_feature(cap, scope);
+}
+#endif
+
 static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL),
 	HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES),
@@ -3223,31 +3230,31 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64ISAR2_EL1, BC, IMP, CAP_HWCAP, KERNEL_HWCAP_HBC),
 #ifdef CONFIG_ARM64_SME
 	HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, STMOP, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_STMOP),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SMOP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SMOP4),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, STMOP, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_STMOP),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMOP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SMOP4),
 #endif /* CONFIG_ARM64_SME */
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT),
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA),

arch/arm64/kernel/efi.c

@@ -15,6 +15,7 @@
 
 #include <asm/efi.h>
 #include <asm/stacktrace.h>
+#include <asm/vmap_stack.h>
 
 static bool region_is_misaligned(const efi_memory_desc_t *md)
 {
@@ -214,9 +215,13 @@ static int __init arm64_efi_rt_init(void)
 	if (!efi_enabled(EFI_RUNTIME_SERVICES))
 		return 0;
 
-	p = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, GFP_KERNEL,
-			   NUMA_NO_NODE, &&l);
-l:	if (!p) {
+	if (!IS_ENABLED(CONFIG_VMAP_STACK)) {
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return -ENOMEM;
+	}
+
+	p = arch_alloc_vmap_stack(THREAD_SIZE, NUMA_NO_NODE);
+	if (!p) {
 		pr_warn("Failed to allocate EFI runtime stack\n");
 		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 		return -ENOMEM;

arch/arm64/kernel/process.c

@@ -673,6 +673,11 @@ static void permission_overlay_switch(struct task_struct *next)
 	current->thread.por_el0 = read_sysreg_s(SYS_POR_EL0);
 	if (current->thread.por_el0 != next->thread.por_el0) {
 		write_sysreg_s(next->thread.por_el0, SYS_POR_EL0);
+		/*
+		 * No ISB required as we can tolerate spurious Overlay faults -
+		 * the fault handler will check again based on the new value
+		 * of POR_EL0.
+		 */
 	}
 }
 

arch/arm64/kernel/smp.c

@@ -1143,7 +1143,7 @@ static inline unsigned int num_other_online_cpus(void)
 void smp_send_stop(void)
 {
 	static unsigned long stop_in_progress;
-	cpumask_t mask;
+	static cpumask_t mask;
 	unsigned long timeout;
 
 	/*

arch/arm64/mm/fault.c

@@ -487,17 +487,29 @@ static void do_bad_area(unsigned long far, unsigned long esr,
 	}
 }
 
-static bool fault_from_pkey(unsigned long esr, struct vm_area_struct *vma,
-			unsigned int mm_flags)
+static bool fault_from_pkey(struct vm_area_struct *vma, unsigned int mm_flags)
 {
-	unsigned long iss2 = ESR_ELx_ISS2(esr);
-
 	if (!system_supports_poe())
 		return false;
 
-	if (esr_fsc_is_permission_fault(esr) && (iss2 & ESR_ELx_Overlay))
-		return true;
-
+	/*
+	 * We do not check whether an Overlay fault has occurred because we
+	 * cannot make a decision based solely on its value:
+	 *
+	 * - If Overlay is set, a fault did occur due to POE, but it may be
+	 *   spurious in those cases where we update POR_EL0 without ISB (e.g.
+	 *   on context-switch). We would then need to manually check POR_EL0
+	 *   against vma_pkey(vma), which is exactly what
+	 *   arch_vma_access_permitted() does.
+	 *
+	 * - If Overlay is not set, we may still need to report a pkey fault.
+	 *   This is the case if an access was made within a mapping but with no
+	 *   page mapped, and POR_EL0 forbids the access (according to
+	 *   vma_pkey()). Such access will result in a SIGSEGV regardless
+	 *   because core code checks arch_vma_access_permitted(), but in order
+	 *   to report the correct error code - SEGV_PKUERR - we must handle
+	 *   that case here.
+	 */
 	return !arch_vma_access_permitted(vma,
 			mm_flags & FAULT_FLAG_WRITE,
 			mm_flags & FAULT_FLAG_INSTRUCTION,
@@ -635,7 +647,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 		goto bad_area;
 	}
 
-	if (fault_from_pkey(esr, vma, mm_flags)) {
+	if (fault_from_pkey(vma, mm_flags)) {
 		pkey = vma_pkey(vma);
 		vma_end_read(vma);
 		fault = 0;
@@ -679,7 +691,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 		goto bad_area;
 	}
 
-	if (fault_from_pkey(esr, vma, mm_flags)) {
+	if (fault_from_pkey(vma, mm_flags)) {
 		pkey = vma_pkey(vma);
 		mmap_read_unlock(mm);
 		fault = 0;

arch/arm64/mm/proc.S

@@ -518,7 +518,6 @@ alternative_else_nop_endif
 	msr	REG_PIR_EL1, x0
 
 	orr	tcr2, tcr2, TCR2_EL1_PIE
-	msr	REG_TCR2_EL1, x0
 
 .Lskip_indirection: