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

Pull arm64 updates from Catalin Marinas:
 "Apart from the core arm64 and perf changes, the Spectre v4 mitigation
  touches the arm KVM code and the ACPI PPTT support touches drivers/
  (acpi and cacheinfo). I should have the maintainers' acks in place.

  Summary:

   - Spectre v4 mitigation (Speculative Store Bypass Disable) support
     for arm64 using SMC firmware call to set a hardware chicken bit

   - ACPI PPTT (Processor Properties Topology Table) parsing support and
     enable the feature for arm64

   - Report signal frame size to user via auxv (AT_MINSIGSTKSZ). The
     primary motivation is Scalable Vector Extensions which requires
     more space on the signal frame than the currently defined
     MINSIGSTKSZ

   - ARM perf patches: allow building arm-cci as module, demote
     dev_warn() to dev_dbg() in arm-ccn event_init(), miscellaneous
     cleanups

   - cmpwait() WFE optimisation to avoid some spurious wakeups

   - L1_CACHE_BYTES reverted back to 64 (for performance reasons that
     have to do with some network allocations) while keeping
     ARCH_DMA_MINALIGN to 128. cache_line_size() returns the actual
     hardware Cache Writeback Granule

   - Turn LSE atomics on by default in Kconfig

   - Kernel fault reporting tidying

   - Some #include and miscellaneous cleanups"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (53 commits)
  arm64: Fix syscall restarting around signal suppressed by tracer
  arm64: topology: Avoid checking numa mask for scheduler MC selection
  ACPI / PPTT: fix build when CONFIG_ACPI_PPTT is not enabled
  arm64: cpu_errata: include required headers
  arm64: KVM: Move VCPU_WORKAROUND_2_FLAG macros to the top of the file
  arm64: signal: Report signal frame size to userspace via auxv
  arm64/sve: Thin out initialisation sanity-checks for sve_max_vl
  arm64: KVM: Add ARCH_WORKAROUND_2 discovery through ARCH_FEATURES_FUNC_ID
  arm64: KVM: Handle guest's ARCH_WORKAROUND_2 requests
  arm64: KVM: Add ARCH_WORKAROUND_2 support for guests
  arm64: KVM: Add HYP per-cpu accessors
  arm64: ssbd: Add prctl interface for per-thread mitigation
  arm64: ssbd: Introduce thread flag to control userspace mitigation
  arm64: ssbd: Restore mitigation status on CPU resume
  arm64: ssbd: Skip apply_ssbd if not using dynamic mitigation
  arm64: ssbd: Add global mitigation state accessor
  arm64: Add 'ssbd' command-line option
  arm64: Add ARCH_WORKAROUND_2 probing
  arm64: Add per-cpu infrastructure to call ARCH_WORKAROUND_2
  arm64: Call ARCH_WORKAROUND_2 on transitions between EL0 and EL1
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -4106,6 +4106,23 @@
 			expediting.  Set to zero to disable automatic
 			expediting.
 
+	ssbd=		[ARM64,HW]
+			Speculative Store Bypass Disable control
+
+			On CPUs that are vulnerable to the Speculative
+			Store Bypass vulnerability and offer a
+			firmware based mitigation, this parameter
+			indicates how the mitigation should be used:
+
+			force-on:  Unconditionally enable mitigation for
+				   for both kernel and userspace
+			force-off: Unconditionally disable mitigation for
+				   for both kernel and userspace
+			kernel:    Always enable mitigation in the
+				   kernel, and offer a prctl interface
+				   to allow userspace to register its
+				   interest in being mitigated too.
+
 	stack_guard_gap=	[MM]
 			override the default stack gap protection. The value
 			is in page units and it defines how many pages prior

arch/arm/common/mcpm_entry.c

@@ -9,6 +9,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/irqflags.h>
@@ -174,6 +175,7 @@ bool mcpm_is_available(void)
 {
 	return (platform_ops) ? true : false;
 }
+EXPORT_SYMBOL_GPL(mcpm_is_available);
 
 /*
  * We can't use regular spinlocks. In the switcher case, it is possible

arch/arm/include/asm/kvm_host.h

@@ -325,6 +325,18 @@ static inline bool kvm_arm_harden_branch_predictor(void)
 	}
 }
 
+#define KVM_SSBD_UNKNOWN		-1
+#define KVM_SSBD_FORCE_DISABLE		0
+#define KVM_SSBD_KERNEL		1
+#define KVM_SSBD_FORCE_ENABLE		2
+#define KVM_SSBD_MITIGATED		3
+
+static inline int kvm_arm_have_ssbd(void)
+{
+	/* No way to detect it yet, pretend it is not there. */
+	return KVM_SSBD_UNKNOWN;
+}
+
 static inline void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu) {}
 static inline void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu) {}
 

arch/arm/include/asm/kvm_mmu.h

@@ -356,6 +356,11 @@ static inline int kvm_map_vectors(void)
 	return 0;
 }
 
+static inline int hyp_map_aux_data(void)
+{
+	return 0;
+}
+
 #define kvm_phys_to_vttbr(addr)		(addr)
 
 #endif	/* !__ASSEMBLY__ */

arch/arm/kernel/perf_event_v6.c

@@ -303,12 +303,10 @@ static void armv6pmu_enable_event(struct perf_event *event)
 }
 
 static irqreturn_t
-armv6pmu_handle_irq(int irq_num,
-		    void *dev)
+armv6pmu_handle_irq(struct arm_pmu *cpu_pmu)
 {
 	unsigned long pmcr = armv6_pmcr_read();
 	struct perf_sample_data data;
-	struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev;
 	struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
 	struct pt_regs *regs;
 	int idx;

arch/arm/kernel/perf_event_v7.c

@@ -946,11 +946,10 @@ static void armv7pmu_disable_event(struct perf_event *event)
 	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
-static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
+static irqreturn_t armv7pmu_handle_irq(struct arm_pmu *cpu_pmu)
 {
 	u32 pmnc;
 	struct perf_sample_data data;
-	struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev;
 	struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
 	struct pt_regs *regs;
 	int idx;

arch/arm/kernel/perf_event_xscale.c

@@ -142,11 +142,10 @@ xscale1_pmnc_counter_has_overflowed(unsigned long pmnc,
 }
 
 static irqreturn_t
-xscale1pmu_handle_irq(int irq_num, void *dev)
+xscale1pmu_handle_irq(struct arm_pmu *cpu_pmu)
 {
 	unsigned long pmnc;
 	struct perf_sample_data data;
-	struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev;
 	struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
 	struct pt_regs *regs;
 	int idx;
@@ -489,11 +488,10 @@ xscale2_pmnc_counter_has_overflowed(unsigned long of_flags,
 }
 
 static irqreturn_t
-xscale2pmu_handle_irq(int irq_num, void *dev)
+xscale2pmu_handle_irq(struct arm_pmu *cpu_pmu)
 {
 	unsigned long pmnc, of_flags;
 	struct perf_sample_data data;
-	struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev;
 	struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
 	struct pt_regs *regs;
 	int idx;

arch/arm64/Kconfig

@@ -7,11 +7,13 @@ config ARM64
 	select ACPI_REDUCED_HARDWARE_ONLY if ACPI
 	select ACPI_MCFG if ACPI
 	select ACPI_SPCR_TABLE if ACPI
+	select ACPI_PPTT if ACPI
 	select ARCH_CLOCKSOURCE_DATA
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
 	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
@@ -923,6 +925,15 @@ config HARDEN_EL2_VECTORS
 
 	  If unsure, say Y.
 
+config ARM64_SSBD
+	bool "Speculative Store Bypass Disable" if EXPERT
+	default y
+	help
+	  This enables mitigation of the bypassing of previous stores
+	  by speculative loads.
+
+	  If unsure, say Y.
+
 menuconfig ARMV8_DEPRECATED
 	bool "Emulate deprecated/obsolete ARMv8 instructions"
 	depends on COMPAT
@@ -1034,6 +1045,7 @@ config ARM64_PAN
 
 config ARM64_LSE_ATOMICS
 	bool "Atomic instructions"
+	default y
 	help
 	  As part of the Large System Extensions, ARMv8.1 introduces new
 	  atomic instructions that are designed specifically to scale in
@@ -1042,7 +1054,8 @@ config ARM64_LSE_ATOMICS
 	  Say Y here to make use of these instructions for the in-kernel
 	  atomic routines. This incurs a small overhead on CPUs that do
 	  not support these instructions and requires the kernel to be
-	  built with binutils >= 2.25.
+	  built with binutils >= 2.25 in order for the new instructions
+	  to be used.
 
 config ARM64_VHE
 	bool "Enable support for Virtualization Host Extensions (VHE)"

arch/arm64/include/asm/acpi.h

@@ -86,6 +86,10 @@ static inline bool acpi_has_cpu_in_madt(void)
 }
 
 struct acpi_madt_generic_interrupt *acpi_cpu_get_madt_gicc(int cpu);
+static inline u32 get_acpi_id_for_cpu(unsigned int cpu)
+{
+	return	acpi_cpu_get_madt_gicc(cpu)->uid;
+}
 
 static inline void arch_fix_phys_package_id(int num, u32 slot) { }
 void __init acpi_init_cpus(void);

arch/arm64/include/asm/cache.h

@@ -33,7 +33,7 @@
 #define ICACHE_POLICY_VIPT	2
 #define ICACHE_POLICY_PIPT	3
 
-#define L1_CACHE_SHIFT		7
+#define L1_CACHE_SHIFT		(6)
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 
 /*
@@ -43,7 +43,7 @@
  * cache before the transfer is done, causing old data to be seen by
  * the CPU.
  */
-#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
+#define ARCH_DMA_MINALIGN	(128)
 
 #ifndef __ASSEMBLY__
 
@@ -77,7 +77,7 @@ static inline u32 cache_type_cwg(void)
 static inline int cache_line_size(void)
 {
 	u32 cwg = cache_type_cwg();
-	return cwg ? 4 << cwg : L1_CACHE_BYTES;
+	return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
 }
 
 #endif	/* __ASSEMBLY__ */

arch/arm64/include/asm/cmpxchg.h

@@ -204,7 +204,9 @@ static inline void __cmpwait_case_##name(volatile void *ptr,		\
 	unsigned long tmp;						\
 									\
 	asm volatile(							\
-	"	ldxr" #sz "\t%" #w "[tmp], %[v]\n"		\
+	"	sevl\n"							\
+	"	wfe\n"							\
+	"	ldxr" #sz "\t%" #w "[tmp], %[v]\n"			\
 	"	eor	%" #w "[tmp], %" #w "[tmp], %" #w "[val]\n"	\
 	"	cbnz	%" #w "[tmp], 1f\n"				\
 	"	wfe\n"							\

arch/arm64/include/asm/cpucaps.h

@@ -48,7 +48,8 @@
 #define ARM64_HAS_CACHE_IDC			27
 #define ARM64_HAS_CACHE_DIC			28
 #define ARM64_HW_DBM				29
+#define ARM64_SSBD				30
 
-#define ARM64_NCAPS				30
+#define ARM64_NCAPS				31
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/include/asm/cpufeature.h

@@ -537,6 +537,28 @@ static inline u64 read_zcr_features(void)
 	return zcr;
 }
 
+#define ARM64_SSBD_UNKNOWN		-1
+#define ARM64_SSBD_FORCE_DISABLE	0
+#define ARM64_SSBD_KERNEL		1
+#define ARM64_SSBD_FORCE_ENABLE		2
+#define ARM64_SSBD_MITIGATED		3
+
+static inline int arm64_get_ssbd_state(void)
+{
+#ifdef CONFIG_ARM64_SSBD
+	extern int ssbd_state;
+	return ssbd_state;
+#else
+	return ARM64_SSBD_UNKNOWN;
+#endif
+}
+
+#ifdef CONFIG_ARM64_SSBD
+void arm64_set_ssbd_mitigation(bool state);
+#else
+static inline void arm64_set_ssbd_mitigation(bool state) {}
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif

arch/arm64/include/asm/elf.h

@@ -121,6 +121,9 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/bug.h>
+#include <asm/processor.h> /* for signal_minsigstksz, used by ARCH_DLINFO */
+
 typedef unsigned long elf_greg_t;
 
 #define ELF_NGREG (sizeof(struct user_pt_regs) / sizeof(elf_greg_t))
@@ -148,6 +151,16 @@ typedef struct user_fpsimd_state elf_fpregset_t;
 do {									\
 	NEW_AUX_ENT(AT_SYSINFO_EHDR,					\
 		    (elf_addr_t)current->mm->context.vdso);		\
+									\
+	/*								\
+	 * Should always be nonzero unless there's a kernel bug.	\
+	 * If we haven't determined a sensible value to give to		\
+	 * userspace, omit the entry:					\
+	 */								\
+	if (likely(signal_minsigstksz))					\
+		NEW_AUX_ENT(AT_MINSIGSTKSZ, signal_minsigstksz);	\
+	else								\
+		NEW_AUX_ENT(AT_IGNORE, 0);				\
 } while (0)
 
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES

arch/arm64/include/asm/fpsimdmacros.h

@@ -207,12 +207,14 @@
 		str		w\nxtmp, [\xpfpsr, #4]
 .endm
 
-.macro sve_load nxbase, xpfpsr, xvqminus1, nxtmp
+.macro sve_load nxbase, xpfpsr, xvqminus1, nxtmp, xtmp2
 		mrs_s		x\nxtmp, SYS_ZCR_EL1
-		bic		x\nxtmp, x\nxtmp, ZCR_ELx_LEN_MASK
-		orr		x\nxtmp, x\nxtmp, \xvqminus1
-		msr_s		SYS_ZCR_EL1, x\nxtmp	// self-synchronising
-
+		bic		\xtmp2, x\nxtmp, ZCR_ELx_LEN_MASK
+		orr		\xtmp2, \xtmp2, \xvqminus1
+		cmp		\xtmp2, x\nxtmp
+		b.eq		921f
+		msr_s		SYS_ZCR_EL1, \xtmp2	// self-synchronising
+921:
  _for n, 0, 31,	_sve_ldr_v	\n, \nxbase, \n - 34
 		_sve_ldr_p	0, \nxbase
 		_sve_wrffr	0

arch/arm64/include/asm/kvm_asm.h

@@ -20,6 +20,9 @@
 
 #include <asm/virt.h>
 
+#define	VCPU_WORKAROUND_2_FLAG_SHIFT	0
+#define	VCPU_WORKAROUND_2_FLAG		(_AC(1, UL) << VCPU_WORKAROUND_2_FLAG_SHIFT)
+
 #define ARM_EXIT_WITH_SERROR_BIT  31
 #define ARM_EXCEPTION_CODE(x)	  ((x) & ~(1U << ARM_EXIT_WITH_SERROR_BIT))
 #define ARM_SERROR_PENDING(x)	  !!((x) & (1U << ARM_EXIT_WITH_SERROR_BIT))
@@ -71,14 +74,37 @@ extern u32 __kvm_get_mdcr_el2(void);
 
 extern u32 __init_stage2_translation(void);
 
+/* Home-grown __this_cpu_{ptr,read} variants that always work at HYP */
+#define __hyp_this_cpu_ptr(sym)						\
+	({								\
+		void *__ptr = hyp_symbol_addr(sym);			\
+		__ptr += read_sysreg(tpidr_el2);			\
+		(typeof(&sym))__ptr;					\
+	 })
+
+#define __hyp_this_cpu_read(sym)					\
+	({								\
+		*__hyp_this_cpu_ptr(sym);				\
+	 })
+
 #else /* __ASSEMBLY__ */
 
-.macro get_host_ctxt reg, tmp
-	adr_l	\reg, kvm_host_cpu_state
+.macro hyp_adr_this_cpu reg, sym, tmp
+	adr_l	\reg, \sym
 	mrs	\tmp, tpidr_el2
 	add	\reg, \reg, \tmp
 .endm
 
+.macro hyp_ldr_this_cpu reg, sym, tmp
+	adr_l	\reg, \sym
+	mrs	\tmp, tpidr_el2
+	ldr	\reg,  [\reg, \tmp]
+.endm
+
+.macro get_host_ctxt reg, tmp
+	hyp_adr_this_cpu \reg, kvm_host_cpu_state, \tmp
+.endm
+
 .macro get_vcpu_ptr vcpu, ctxt
 	get_host_ctxt \ctxt, \vcpu
 	ldr	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]

arch/arm64/include/asm/kvm_host.h

@@ -216,6 +216,9 @@ struct kvm_vcpu_arch {
 	/* Exception Information */
 	struct kvm_vcpu_fault_info fault;
 
+	/* State of various workarounds, see kvm_asm.h for bit assignment */
+	u64 workaround_flags;
+
 	/* Guest debug state */
 	u64 debug_flags;
 
@@ -452,6 +455,29 @@ static inline bool kvm_arm_harden_branch_predictor(void)
 	return cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR);
 }
 
+#define KVM_SSBD_UNKNOWN		-1
+#define KVM_SSBD_FORCE_DISABLE		0
+#define KVM_SSBD_KERNEL		1
+#define KVM_SSBD_FORCE_ENABLE		2
+#define KVM_SSBD_MITIGATED		3
+
+static inline int kvm_arm_have_ssbd(void)
+{
+	switch (arm64_get_ssbd_state()) {
+	case ARM64_SSBD_FORCE_DISABLE:
+		return KVM_SSBD_FORCE_DISABLE;
+	case ARM64_SSBD_KERNEL:
+		return KVM_SSBD_KERNEL;
+	case ARM64_SSBD_FORCE_ENABLE:
+		return KVM_SSBD_FORCE_ENABLE;
+	case ARM64_SSBD_MITIGATED:
+		return KVM_SSBD_MITIGATED;
+	case ARM64_SSBD_UNKNOWN:
+	default:
+		return KVM_SSBD_UNKNOWN;
+	}
+}
+
 void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu);
 void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu);
 

arch/arm64/include/asm/kvm_mmu.h

@@ -72,7 +72,6 @@
 #ifdef __ASSEMBLY__
 
 #include <asm/alternative.h>
-#include <asm/cpufeature.h>
 
 /*
  * Convert a kernel VA into a HYP VA.
@@ -473,6 +472,30 @@ static inline int kvm_map_vectors(void)
 }
 #endif
 
+#ifdef CONFIG_ARM64_SSBD
+DECLARE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required);
+
+static inline int hyp_map_aux_data(void)
+{
+	int cpu, err;
+
+	for_each_possible_cpu(cpu) {
+		u64 *ptr;
+
+		ptr = per_cpu_ptr(&arm64_ssbd_callback_required, cpu);
+		err = create_hyp_mappings(ptr, ptr + 1, PAGE_HYP);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+#else
+static inline int hyp_map_aux_data(void)
+{
+	return 0;
+}
+#endif
+
 #define kvm_phys_to_vttbr(addr)		phys_to_ttbr(addr)
 
 #endif /* __ASSEMBLY__ */

arch/arm64/include/asm/processor.h

@@ -35,6 +35,8 @@
 #ifdef __KERNEL__
 
 #include <linux/build_bug.h>
+#include <linux/cache.h>
+#include <linux/init.h>
 #include <linux/stddef.h>
 #include <linux/string.h>
 
@@ -244,6 +246,9 @@ void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused);
 void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused);
 void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused);
 
+extern unsigned long __ro_after_init signal_minsigstksz; /* sigframe size */
+extern void __init minsigstksz_setup(void);
+
 /* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */
 #define SVE_SET_VL(arg)	sve_set_current_vl(arg)
 #define SVE_GET_VL()	sve_get_current_vl()

arch/arm64/include/asm/thread_info.h

@@ -94,6 +94,7 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define TIF_32BIT		22	/* 32bit process */
 #define TIF_SVE			23	/* Scalable Vector Extension in use */
 #define TIF_SVE_VL_INHERIT	24	/* Inherit sve_vl_onexec across exec */
+#define TIF_SSBD		25	/* Wants SSB mitigation */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)