arm64 updates for 4.18:

- 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
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEE5RElWfyWxS+3PLO2a9axLQDIXvEFAlsaoqsACgkQa9axLQDI
 XvH+8RAAqRCrEtkNPS7zxHyMK/D2cxSy9EVtlJ1sxhmsONEe5t5MDTWX9byobQ5A
 PAKMSQBQgUvecqHLOtD7SJWef1il30zgWmc/yPcgNv3OsA1Au7j2g3ht/Drw+N5I
 Vy0aOUEtw+Jzs7y/CJyl6lufSkkOzszOujt2Nybiz6omztOrwkW9isKnURzQBNj5
 gquZI35h604YJ9F0TqS6ZqU7tNcuB9q02FxvVBpLmb83jP4jSEjYACUJwVVxvEAB
 UXjdD4N130rRXDS5OMRWo5+4SAj+kPYhdVYEvaDx7xTOIRHhXK05GlJbsUAc5E6l
 xy810fH5Dm0diYpVvYWTA5J+BU1jNOvCys5zKWl7gs2P8YB59PdqY4M2YBPNGb5H
 PaVgq73TZAsww6ZInbZlK+wZOIxZZIOf//Z+QKn6EPtu3RmzIFWwyttTj01w1E3i
 LhjcUoGnvxJFcMoCr59ihDwfP9nkCVrNc4REOGaWDk6L/t/bOfaZfDz+OCGbwQdL
 akCFKZI6q5O/no+YfhtdtNFpCQb/Bo1J88KuotICRXq8z4vO41zIG53bi97W8QeG
 rCBiX0NxUxYJ3ybus7kZHTmMGieMyEHP28n12QffwvJj4vJBsUXQBrV8hclx0djZ
 HMt7iPi/0BW6nVV7ngIgN3cdCpaDCEGRsfO4Ch0rFZrC9UbYQnE=
 =uums
 -----END PGP SIGNATURE-----

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,
+armv6pmu_handle_irq(struct arm_pmu *cpu_pmu)
-		    void *dev)
 {
 	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
+		bic		\xtmp2, x\nxtmp, ZCR_ELx_LEN_MASK
-		orr		x\nxtmp, x\nxtmp, \xvqminus1
+		orr		\xtmp2, \xtmp2, \xvqminus1
-		msr_s		SYS_ZCR_EL1, x\nxtmp	// self-synchronising
+		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
+.macro hyp_adr_this_cpu reg, sym, tmp
-	adr_l	\reg, kvm_host_cpu_state
+	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)

arch/arm64/include/asm/topology.h

@@ -7,14 +7,16 @@
 struct cpu_topology {
 	int thread_id;
 	int core_id;
-	int cluster_id;
+	int package_id;
+	int llc_id;
 	cpumask_t thread_sibling;
 	cpumask_t core_sibling;
+	cpumask_t llc_siblings;
 };
 
 extern struct cpu_topology cpu_topology[NR_CPUS];
 
-#define topology_physical_package_id(cpu)	(cpu_topology[cpu].cluster_id)
+#define topology_physical_package_id(cpu)	(cpu_topology[cpu].package_id)
 #define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
 #define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)

arch/arm64/include/uapi/asm/auxvec.h

@@ -19,7 +19,8 @@
 
 /* vDSO location */
 #define AT_SYSINFO_EHDR	33
+#define AT_MINSIGSTKSZ	51	/* stack needed for signal delivery */
 
-#define AT_VECTOR_SIZE_ARCH 1 /* entries in ARCH_DLINFO */
+#define AT_VECTOR_SIZE_ARCH 2 /* entries in ARCH_DLINFO */
 
 #endif

arch/arm64/kernel/Makefile

@@ -54,6 +54,7 @@ arm64-obj-$(CONFIG_ARM64_RELOC_TEST)	+= arm64-reloc-test.o
 arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o
 arm64-obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o
 arm64-obj-$(CONFIG_ARM_SDE_INTERFACE)	+= sdei.o
+arm64-obj-$(CONFIG_ARM64_SSBD)		+= ssbd.o
 
 obj-y					+= $(arm64-obj-y) vdso/ probes/
 obj-m					+= $(arm64-obj-m)

arch/arm64/kernel/armv8_deprecated.c

@@ -13,6 +13,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/sysctl.h>
+#include <linux/uaccess.h>
 
 #include <asm/cpufeature.h>
 #include <asm/insn.h>
@@ -20,8 +21,6 @@
 #include <asm/system_misc.h>
 #include <asm/traps.h>
 #include <asm/kprobes.h>
-#include <linux/uaccess.h>
-#include <asm/cpufeature.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace-events-emulation.h"

arch/arm64/kernel/asm-offsets.c

@@ -136,6 +136,7 @@ int main(void)
 #ifdef CONFIG_KVM_ARM_HOST
   DEFINE(VCPU_CONTEXT,		offsetof(struct kvm_vcpu, arch.ctxt));
   DEFINE(VCPU_FAULT_DISR,	offsetof(struct kvm_vcpu, arch.fault.disr_el1));
+  DEFINE(VCPU_WORKAROUND_FLAGS,	offsetof(struct kvm_vcpu, arch.workaround_flags));
   DEFINE(CPU_GP_REGS,		offsetof(struct kvm_cpu_context, gp_regs));
   DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_regs, regs));
   DEFINE(CPU_FP_REGS,		offsetof(struct kvm_regs, fp_regs));

arch/arm64/kernel/cacheinfo.c

@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/acpi.h>
 #include <linux/cacheinfo.h>
 #include <linux/of.h>
 
@@ -46,7 +47,7 @@ static void ci_leaf_init(struct cacheinfo *this_leaf,
 
 static int __init_cache_level(unsigned int cpu)
 {
-	unsigned int ctype, level, leaves, of_level;
+	unsigned int ctype, level, leaves, fw_level;
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 
 	for (level = 1, leaves = 0; level <= MAX_CACHE_LEVEL; level++) {
@@ -59,15 +60,19 @@ static int __init_cache_level(unsigned int cpu)
 		leaves += (ctype == CACHE_TYPE_SEPARATE) ? 2 : 1;
 	}
 
-	of_level = of_find_last_cache_level(cpu);
+	if (acpi_disabled)
-	if (level < of_level) {
+		fw_level = of_find_last_cache_level(cpu);
+	else
+		fw_level = acpi_find_last_cache_level(cpu);
+
+	if (level < fw_level) {
 		/*
 		 * some external caches not specified in CLIDR_EL1
 		 * the information may be available in the device tree
 		 * only unified external caches are considered here
 		 */
-		leaves += (of_level - level);
+		leaves += (fw_level - level);
-		level = of_level;
+		level = fw_level;
 	}
 
 	this_cpu_ci->num_levels = level;

arch/arm64/kernel/cpu_errata.c

@@ -16,6 +16,8 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/arm-smccc.h>
+#include <linux/psci.h>
 #include <linux/types.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
@@ -232,6 +234,178 @@ enable_smccc_arch_workaround_1(const struct arm64_cpu_capabilities *entry)
 }
 #endif	/* CONFIG_HARDEN_BRANCH_PREDICTOR */
 
+#ifdef CONFIG_ARM64_SSBD
+DEFINE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required);
+
+int ssbd_state __read_mostly = ARM64_SSBD_KERNEL;
+
+static const struct ssbd_options {
+	const char	*str;
+	int		state;
+} ssbd_options[] = {
+	{ "force-on",	ARM64_SSBD_FORCE_ENABLE, },
+	{ "force-off",	ARM64_SSBD_FORCE_DISABLE, },
+	{ "kernel",	ARM64_SSBD_KERNEL, },
+};
+
+static int __init ssbd_cfg(char *buf)
+{
+	int i;
+
+	if (!buf || !buf[0])
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(ssbd_options); i++) {
+		int len = strlen(ssbd_options[i].str);
+
+		if (strncmp(buf, ssbd_options[i].str, len))
+			continue;
+
+		ssbd_state = ssbd_options[i].state;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+early_param("ssbd", ssbd_cfg);
+
+void __init arm64_update_smccc_conduit(struct alt_instr *alt,
+				       __le32 *origptr, __le32 *updptr,
+				       int nr_inst)
+{
+	u32 insn;
+
+	BUG_ON(nr_inst != 1);
+
+	switch (psci_ops.conduit) {
+	case PSCI_CONDUIT_HVC:
+		insn = aarch64_insn_get_hvc_value();
+		break;
+	case PSCI_CONDUIT_SMC:
+		insn = aarch64_insn_get_smc_value();
+		break;
+	default:
+		return;
+	}
+
+	*updptr = cpu_to_le32(insn);
+}
+
+void __init arm64_enable_wa2_handling(struct alt_instr *alt,
+				      __le32 *origptr, __le32 *updptr,
+				      int nr_inst)
+{
+	BUG_ON(nr_inst != 1);
+	/*
+	 * Only allow mitigation on EL1 entry/exit and guest
+	 * ARCH_WORKAROUND_2 handling if the SSBD state allows it to
+	 * be flipped.
+	 */
+	if (arm64_get_ssbd_state() == ARM64_SSBD_KERNEL)
+		*updptr = cpu_to_le32(aarch64_insn_gen_nop());
+}
+
+void arm64_set_ssbd_mitigation(bool state)
+{
+	switch (psci_ops.conduit) {
+	case PSCI_CONDUIT_HVC:
+		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
+		break;
+
+	case PSCI_CONDUIT_SMC:
+		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
+		break;
+
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+}
+
+static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
+				    int scope)
+{
+	struct arm_smccc_res res;
+	bool required = true;
+	s32 val;
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+
+	if (psci_ops.smccc_version == SMCCC_VERSION_1_0) {
+		ssbd_state = ARM64_SSBD_UNKNOWN;
+		return false;
+	}
+
+	switch (psci_ops.conduit) {
+	case PSCI_CONDUIT_HVC:
+		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+				  ARM_SMCCC_ARCH_WORKAROUND_2, &res);
+		break;
+
+	case PSCI_CONDUIT_SMC:
+		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+				  ARM_SMCCC_ARCH_WORKAROUND_2, &res);
+		break;
+
+	default:
+		ssbd_state = ARM64_SSBD_UNKNOWN;
+		return false;
+	}
+
+	val = (s32)res.a0;
+
+	switch (val) {
+	case SMCCC_RET_NOT_SUPPORTED:
+		ssbd_state = ARM64_SSBD_UNKNOWN;
+		return false;
+
+	case SMCCC_RET_NOT_REQUIRED:
+		pr_info_once("%s mitigation not required\n", entry->desc);
+		ssbd_state = ARM64_SSBD_MITIGATED;
+		return false;
+
+	case SMCCC_RET_SUCCESS:
+		required = true;
+		break;
+
+	case 1:	/* Mitigation not required on this CPU */
+		required = false;
+		break;
+
+	default:
+		WARN_ON(1);
+		return false;
+	}
+
+	switch (ssbd_state) {
+	case ARM64_SSBD_FORCE_DISABLE:
+		pr_info_once("%s disabled from command-line\n", entry->desc);
+		arm64_set_ssbd_mitigation(false);
+		required = false;
+		break;
+
+	case ARM64_SSBD_KERNEL:
+		if (required) {
+			__this_cpu_write(arm64_ssbd_callback_required, 1);
+			arm64_set_ssbd_mitigation(true);
+		}
+		break;
+
+	case ARM64_SSBD_FORCE_ENABLE:
+		pr_info_once("%s forced from command-line\n", entry->desc);
+		arm64_set_ssbd_mitigation(true);
+		required = true;
+		break;
+
+	default:
+		WARN_ON(1);
+		break;
+	}
+
+	return required;
+}
+#endif	/* CONFIG_ARM64_SSBD */
+
 #define CAP_MIDR_RANGE(model, v_min, r_min, v_max, r_max)	\
 	.matches = is_affected_midr_range,			\
 	.midr_range = MIDR_RANGE(model, v_min, r_min, v_max, r_max)
@@ -487,6 +661,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors),
 	},
+#endif
+#ifdef CONFIG_ARM64_SSBD
+	{
+		.desc = "Speculative Store Bypass Disable",
+		.capability = ARM64_SSBD,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = has_ssbd_mitigation,
+	},
 #endif
 	{
 	}

arch/arm64/kernel/cpufeature.c

@@ -1606,7 +1606,6 @@ static void __init setup_system_capabilities(void)
 void __init setup_cpu_features(void)
 {
 	u32 cwg;
-	int cls;
 
 	setup_system_capabilities();
 	mark_const_caps_ready();
@@ -1619,6 +1618,7 @@ void __init setup_cpu_features(void)
 		pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n");
 
 	sve_setup();
+	minsigstksz_setup();
 
 	/* Advertise that we have computed the system capabilities */
 	set_sys_caps_initialised();
@@ -1627,13 +1627,9 @@ void __init setup_cpu_features(void)
 	 * Check for sane CTR_EL0.CWG value.
 	 */
 	cwg = cache_type_cwg();
-	cls = cache_line_size();
 	if (!cwg)
-		pr_warn("No Cache Writeback Granule information, assuming cache line size %d\n",
+		pr_warn("No Cache Writeback Granule information, assuming %d\n",
-			cls);
+			ARCH_DMA_MINALIGN);
-	if (L1_CACHE_BYTES < cls)
-		pr_warn("L1_CACHE_BYTES smaller than the Cache Writeback Granule (%d < %d)\n",
-			L1_CACHE_BYTES, cls);
 }
 
 static bool __maybe_unused

arch/arm64/kernel/entry-fpsimd.S

@@ -49,7 +49,7 @@ ENTRY(sve_save_state)
 ENDPROC(sve_save_state)
 
 ENTRY(sve_load_state)
-	sve_load 0, x1, x2, 3
+	sve_load 0, x1, x2, 3, x4
 	ret
 ENDPROC(sve_load_state)
 

arch/arm64/kernel/entry.S

@@ -18,6 +18,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/arm-smccc.h>
 #include <linux/init.h>
 #include <linux/linkage.h>
 
@@ -137,6 +138,25 @@ alternative_else_nop_endif
 	add	\dst, \dst, #(\sym - .entry.tramp.text)
 	.endm
 
+	// This macro corrupts x0-x3. It is the caller's duty
+	// to save/restore them if required.
+	.macro	apply_ssbd, state, targ, tmp1, tmp2
+#ifdef CONFIG_ARM64_SSBD
+alternative_cb	arm64_enable_wa2_handling
+	b	\targ
+alternative_cb_end
+	ldr_this_cpu	\tmp2, arm64_ssbd_callback_required, \tmp1
+	cbz	\tmp2, \targ
+	ldr	\tmp2, [tsk, #TSK_TI_FLAGS]
+	tbnz	\tmp2, #TIF_SSBD, \targ
+	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_2
+	mov	w1, #\state
+alternative_cb	arm64_update_smccc_conduit
+	nop					// Patched to SMC/HVC #0
+alternative_cb_end
+#endif
+	.endm
+
 	.macro	kernel_entry, el, regsize = 64
 	.if	\regsize == 32
 	mov	w0, w0				// zero upper 32 bits of x0
@@ -163,6 +183,14 @@ alternative_else_nop_endif
 	ldr	x19, [tsk, #TSK_TI_FLAGS]	// since we can unmask debug
 	disable_step_tsk x19, x20		// exceptions when scheduling.
 
+	apply_ssbd 1, 1f, x22, x23
+
+#ifdef CONFIG_ARM64_SSBD
+	ldp	x0, x1, [sp, #16 * 0]
+	ldp	x2, x3, [sp, #16 * 1]
+#endif
+1:
+
 	mov	x29, xzr			// fp pointed to user-space
 	.else
 	add	x21, sp, #S_FRAME_SIZE
@@ -303,6 +331,8 @@ alternative_if ARM64_WORKAROUND_845719
 alternative_else_nop_endif
 #endif
 3:
+	apply_ssbd 0, 5f, x0, x1
+5:
 	.endif
 
 	msr	elr_el1, x21			// set up the return data

arch/arm64/kernel/fpsimd.c

@@ -31,7 +31,6 @@
 #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>
@@ -129,7 +128,7 @@ 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;
+int __ro_after_init sve_max_vl = SVE_VL_MIN;
 /* 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;
@@ -360,22 +359,13 @@ static int sve_proc_do_default_vl(struct ctl_table *table, int write,
 		return ret;
 
 	/* Writing -1 has the special meaning "set to max": */
-	if (vl == -1) {
+	if (vl == -1)
-		/* Fail safe if sve_max_vl wasn't initialised */
+		vl = sve_max_vl;
-		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);
+	sve_default_vl = find_supported_vector_length(vl);
-chosen:
-	sve_default_vl = vl;
 	return 0;
 }
 

arch/arm64/kernel/hibernate.c

@@ -313,6 +313,17 @@ int swsusp_arch_suspend(void)
 
 		sleep_cpu = -EINVAL;
 		__cpu_suspend_exit();
+
+		/*
+		 * Just in case the boot kernel did turn the SSBD
+		 * mitigation off behind our back, let's set the state
+		 * to what we expect it to be.
+		 */
+		switch (arm64_get_ssbd_state()) {
+		case ARM64_SSBD_FORCE_ENABLE:
+		case ARM64_SSBD_KERNEL:
+			arm64_set_ssbd_mitigation(true);
+		}
 	}
 
 	local_daif_restore(flags);

arch/arm64/kernel/perf_event.c

@@ -670,11 +670,10 @@ static void armv8pmu_disable_event(struct perf_event *event)
 	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
-static irqreturn_t armv8pmu_handle_irq(int irq_num, void *dev)
+static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 {
 	u32 pmovsr;
 	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/kernel/ptrace.c

@@ -766,9 +766,6 @@ static void sve_init_header_from_task(struct user_sve_header *header,
 	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);
@@ -1046,8 +1043,6 @@ static const struct user_regset_view user_aarch64_view = {
 };
 
 #ifdef CONFIG_COMPAT
-#include <linux/compat.h>
-
 enum compat_regset {
 	REGSET_COMPAT_GPR,
 	REGSET_COMPAT_VFP,

arch/arm64/kernel/signal.c

@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/cache.h>
 #include <linux/compat.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
@@ -570,8 +571,15 @@ badframe:
 	return 0;
 }
 
-/* Determine the layout of optional records in the signal frame */
+/*
-static int setup_sigframe_layout(struct rt_sigframe_user_layout *user)
+ * Determine the layout of optional records in the signal frame
+ *
+ * add_all: if true, lays out the biggest possible signal frame for
+ *	this task; otherwise, generates a layout for the current state
+ *	of the task.
+ */
+static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
+				 bool add_all)
 {
 	int err;
 
@@ -581,7 +589,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user)
 		return err;
 
 	/* fault information, if valid */
-	if (current->thread.fault_code) {
+	if (add_all || current->thread.fault_code) {
 		err = sigframe_alloc(user, &user->esr_offset,
 				     sizeof(struct esr_context));
 		if (err)
@@ -591,8 +599,14 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user)
 	if (system_supports_sve()) {
 		unsigned int vq = 0;
 
-		if (test_thread_flag(TIF_SVE))
+		if (add_all || test_thread_flag(TIF_SVE)) {
-			vq = sve_vq_from_vl(current->thread.sve_vl);
+			int vl = sve_max_vl;
+
+			if (!add_all)
+				vl = current->thread.sve_vl;
+
+			vq = sve_vq_from_vl(vl);
+		}
 
 		err = sigframe_alloc(user, &user->sve_offset,
 				     SVE_SIG_CONTEXT_SIZE(vq));
@@ -603,7 +617,6 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user)
 	return sigframe_alloc_end(user);
 }
 
-
 static int setup_sigframe(struct rt_sigframe_user_layout *user,
 			  struct pt_regs *regs, sigset_t *set)
 {
@@ -701,7 +714,7 @@ static int get_sigframe(struct rt_sigframe_user_layout *user,
 	int err;
 
 	init_user_layout(user);
-	err = setup_sigframe_layout(user);
+	err = setup_sigframe_layout(user, false);
 	if (err)
 		return err;
 
@@ -830,11 +843,12 @@ static void do_signal(struct pt_regs *regs)
 	unsigned long continue_addr = 0, restart_addr = 0;
 	int retval = 0;
 	struct ksignal ksig;
+	bool syscall = in_syscall(regs);
 
 	/*
 	 * If we were from a system call, check for system call restarting...
 	 */
-	if (in_syscall(regs)) {
+	if (syscall) {
 		continue_addr = regs->pc;
 		restart_addr = continue_addr - (compat_thumb_mode(regs) ? 2 : 4);
 		retval = regs->regs[0];
@@ -886,7 +900,7 @@ static void do_signal(struct pt_regs *regs)
 	 * Handle restarting a different system call. As above, if a debugger
 	 * has chosen to restart at a different PC, ignore the restart.
 	 */
-	if (in_syscall(regs) && regs->pc == restart_addr) {
+	if (syscall && regs->pc == restart_addr) {
 		if (retval == -ERESTART_RESTARTBLOCK)
 			setup_restart_syscall(regs);
 		user_rewind_single_step(current);
@@ -936,3 +950,28 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 		thread_flags = READ_ONCE(current_thread_info()->flags);
 	} while (thread_flags & _TIF_WORK_MASK);
 }
+
+unsigned long __ro_after_init signal_minsigstksz;
+
+/*
+ * Determine the stack space required for guaranteed signal devliery.
+ * This function is used to populate AT_MINSIGSTKSZ at process startup.
+ * cpufeatures setup is assumed to be complete.
+ */
+void __init minsigstksz_setup(void)
+{
+	struct rt_sigframe_user_layout user;
+
+	init_user_layout(&user);
+
+	/*
+	 * If this fails, SIGFRAME_MAXSZ needs to be enlarged.  It won't
+	 * be big enough, but it's our best guess:
+	 */
+	if (WARN_ON(setup_sigframe_layout(&user, true)))
+		return;
+
+	signal_minsigstksz = sigframe_size(&user) +
+		round_up(sizeof(struct frame_record), 16) +
+		16; /* max alignment padding */
+}

arch/arm64/kernel/ssbd.c

@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 ARM Ltd, All Rights Reserved.
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/thread_info.h>
+
+#include <asm/cpufeature.h>
+
+/*
+ * prctl interface for SSBD
+ * FIXME: Drop the below ifdefery once merged in 4.18.
+ */
+#ifdef PR_SPEC_STORE_BYPASS
+static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl)
+{
+	int state = arm64_get_ssbd_state();
+
+	/* Unsupported */
+	if (state == ARM64_SSBD_UNKNOWN)
+		return -EINVAL;
+
+	/* Treat the unaffected/mitigated state separately */
+	if (state == ARM64_SSBD_MITIGATED) {
+		switch (ctrl) {
+		case PR_SPEC_ENABLE:
+			return -EPERM;
+		case PR_SPEC_DISABLE:
+		case PR_SPEC_FORCE_DISABLE:
+			return 0;
+		}
+	}
+
+	/*
+	 * Things are a bit backward here: the arm64 internal API
+	 * *enables the mitigation* when the userspace API *disables
+	 * speculation*. So much fun.
+	 */
+	switch (ctrl) {
+	case PR_SPEC_ENABLE:
+		/* If speculation is force disabled, enable is not allowed */
+		if (state == ARM64_SSBD_FORCE_ENABLE ||
+		    task_spec_ssb_force_disable(task))
+			return -EPERM;
+		task_clear_spec_ssb_disable(task);
+		clear_tsk_thread_flag(task, TIF_SSBD);
+		break;
+	case PR_SPEC_DISABLE:
+		if (state == ARM64_SSBD_FORCE_DISABLE)
+			return -EPERM;
+		task_set_spec_ssb_disable(task);
+		set_tsk_thread_flag(task, TIF_SSBD);
+		break;
+	case PR_SPEC_FORCE_DISABLE:
+		if (state == ARM64_SSBD_FORCE_DISABLE)
+			return -EPERM;
+		task_set_spec_ssb_disable(task);
+		task_set_spec_ssb_force_disable(task);
+		set_tsk_thread_flag(task, TIF_SSBD);
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	return 0;
+}
+
+int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
+			     unsigned long ctrl)
+{
+	switch (which) {
+	case PR_SPEC_STORE_BYPASS:
+		return ssbd_prctl_set(task, ctrl);
+	default:
+		return -ENODEV;
+	}
+}
+
+static int ssbd_prctl_get(struct task_struct *task)
+{
+	switch (arm64_get_ssbd_state()) {
+	case ARM64_SSBD_UNKNOWN:
+		return -EINVAL;
+	case ARM64_SSBD_FORCE_ENABLE:
+		return PR_SPEC_DISABLE;
+	case ARM64_SSBD_KERNEL:
+		if (task_spec_ssb_force_disable(task))
+			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
+		if (task_spec_ssb_disable(task))
+			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
+		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
+	case ARM64_SSBD_FORCE_DISABLE:
+		return PR_SPEC_ENABLE;
+	default:
+		return PR_SPEC_NOT_AFFECTED;
+	}
+}
+
+int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
+{
+	switch (which) {
+	case PR_SPEC_STORE_BYPASS:
+		return ssbd_prctl_get(task);
+	default:
+		return -ENODEV;
+	}
+}
+#endif	/* PR_SPEC_STORE_BYPASS */

arch/arm64/kernel/suspend.c

@@ -62,6 +62,14 @@ void notrace __cpu_suspend_exit(void)
 	 */
 	if (hw_breakpoint_restore)
 		hw_breakpoint_restore(cpu);
+
+	/*
+	 * On resume, firmware implementing dynamic mitigation will
+	 * have turned the mitigation on. If the user has forcefully
+	 * disabled it, make sure their wishes are obeyed.
+	 */
+	if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE)
+		arm64_set_ssbd_mitigation(false);
 }
 
 /*

arch/arm64/kernel/topology.c

@@ -11,7 +11,9 @@
  * for more details.
  */
 
+#include <linux/acpi.h>
 #include <linux/arch_topology.h>
+#include <linux/cacheinfo.h>
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/init.h>
@@ -22,6 +24,7 @@
 #include <linux/sched.h>
 #include <linux/sched/topology.h>
 #include <linux/slab.h>
+#include <linux/smp.h>
 #include <linux/string.h>
 
 #include <asm/cpu.h>
@@ -47,7 +50,7 @@ static int __init get_cpu_for_node(struct device_node *node)
 	return cpu;
 }
 
-static int __init parse_core(struct device_node *core, int cluster_id,
+static int __init parse_core(struct device_node *core, int package_id,
 			     int core_id)
 {
 	char name[10];
@@ -63,7 +66,7 @@ static int __init parse_core(struct device_node *core, int cluster_id,
 			leaf = false;
 			cpu = get_cpu_for_node(t);
 			if (cpu >= 0) {
-				cpu_topology[cpu].cluster_id = cluster_id;
+				cpu_topology[cpu].package_id = package_id;
 				cpu_topology[cpu].core_id = core_id;
 				cpu_topology[cpu].thread_id = i;
 			} else {
@@ -85,7 +88,7 @@ static int __init parse_core(struct device_node *core, int cluster_id,
 			return -EINVAL;
 		}
 
-		cpu_topology[cpu].cluster_id = cluster_id;
+		cpu_topology[cpu].package_id = package_id;
 		cpu_topology[cpu].core_id = core_id;
 	} else if (leaf) {
 		pr_err("%pOF: Can't get CPU for leaf core\n", core);
@@ -101,7 +104,7 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 	bool leaf = true;
 	bool has_cores = false;
 	struct device_node *c;
-	static int cluster_id __initdata;
+	static int package_id __initdata;
 	int core_id = 0;
 	int i, ret;
 
@@ -140,7 +143,7 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 			}
 
 			if (leaf) {
-				ret = parse_core(c, cluster_id, core_id++);
+				ret = parse_core(c, package_id, core_id++);
 			} else {
 				pr_err("%pOF: Non-leaf cluster with core %s\n",
 				       cluster, name);
@@ -158,7 +161,7 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 		pr_warn("%pOF: empty cluster\n", cluster);
 
 	if (leaf)
-		cluster_id++;
+		package_id++;
 
 	return 0;
 }
@@ -194,7 +197,7 @@ static int __init parse_dt_topology(void)
 	 * only mark cores described in the DT as possible.
 	 */
 	for_each_possible_cpu(cpu)
-		if (cpu_topology[cpu].cluster_id == -1)
+		if (cpu_topology[cpu].package_id == -1)
 			ret = -EINVAL;
 
 out_map:
@@ -212,7 +215,14 @@ EXPORT_SYMBOL_GPL(cpu_topology);
 
 const struct cpumask *cpu_coregroup_mask(int cpu)
 {
-	return &cpu_topology[cpu].core_sibling;
+	const cpumask_t *core_mask = &cpu_topology[cpu].core_sibling;
+
+	if (cpu_topology[cpu].llc_id != -1) {
+		if (cpumask_subset(&cpu_topology[cpu].llc_siblings, core_mask))
+			core_mask = &cpu_topology[cpu].llc_siblings;
+	}
+
+	return core_mask;
 }
 
 static void update_siblings_masks(unsigned int cpuid)
@@ -224,7 +234,12 @@ static void update_siblings_masks(unsigned int cpuid)
 	for_each_possible_cpu(cpu) {
 		cpu_topo = &cpu_topology[cpu];
 
-		if (cpuid_topo->cluster_id != cpu_topo->cluster_id)
+		if (cpuid_topo->llc_id == cpu_topo->llc_id) {
+			cpumask_set_cpu(cpu, &cpuid_topo->llc_siblings);
+			cpumask_set_cpu(cpuid, &cpu_topo->llc_siblings);
+		}
+
+		if (cpuid_topo->package_id != cpu_topo->package_id)
 			continue;
 
 		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
@@ -245,7 +260,7 @@ void store_cpu_topology(unsigned int cpuid)
 	struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
 	u64 mpidr;
 
-	if (cpuid_topo->cluster_id != -1)
+	if (cpuid_topo->package_id != -1)
 		goto topology_populated;
 
 	mpidr = read_cpuid_mpidr();
@@ -259,19 +274,19 @@ void store_cpu_topology(unsigned int cpuid)
 		/* Multiprocessor system : Multi-threads per core */
 		cpuid_topo->thread_id  = MPIDR_AFFINITY_LEVEL(mpidr, 0);
 		cpuid_topo->core_id    = MPIDR_AFFINITY_LEVEL(mpidr, 1);
-		cpuid_topo->cluster_id = MPIDR_AFFINITY_LEVEL(mpidr, 2) |
+		cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 2) |
 					 MPIDR_AFFINITY_LEVEL(mpidr, 3) << 8;
 	} else {
 		/* Multiprocessor system : Single-thread per core */
 		cpuid_topo->thread_id  = -1;
 		cpuid_topo->core_id    = MPIDR_AFFINITY_LEVEL(mpidr, 0);
-		cpuid_topo->cluster_id = MPIDR_AFFINITY_LEVEL(mpidr, 1) |
+		cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 1) |
 					 MPIDR_AFFINITY_LEVEL(mpidr, 2) << 8 |
 					 MPIDR_AFFINITY_LEVEL(mpidr, 3) << 16;
 	}
 
 	pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n",
-		 cpuid, cpuid_topo->cluster_id, cpuid_topo->core_id,
+		 cpuid, cpuid_topo->package_id, cpuid_topo->core_id,
 		 cpuid_topo->thread_id, mpidr);
 
 topology_populated:
@@ -287,7 +302,11 @@ static void __init reset_cpu_topology(void)
 
 		cpu_topo->thread_id = -1;
 		cpu_topo->core_id = 0;
-		cpu_topo->cluster_id = -1;
+		cpu_topo->package_id = -1;
+
+		cpu_topo->llc_id = -1;
+		cpumask_clear(&cpu_topo->llc_siblings);
+		cpumask_set_cpu(cpu, &cpu_topo->llc_siblings);
 
 		cpumask_clear(&cpu_topo->core_sibling);
 		cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
@@ -296,6 +315,59 @@ static void __init reset_cpu_topology(void)
 	}
 }
 
+#ifdef CONFIG_ACPI
+/*
+ * Propagate the topology information of the processor_topology_node tree to the
+ * cpu_topology array.
+ */
+static int __init parse_acpi_topology(void)
+{
+	bool is_threaded;
+	int cpu, topology_id;
+
+	is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK;
+
+	for_each_possible_cpu(cpu) {
+		int i, cache_id;
+
+		topology_id = find_acpi_cpu_topology(cpu, 0);
+		if (topology_id < 0)
+			return topology_id;
+
+		if (is_threaded) {
+			cpu_topology[cpu].thread_id = topology_id;
+			topology_id = find_acpi_cpu_topology(cpu, 1);
+			cpu_topology[cpu].core_id   = topology_id;
+		} else {
+			cpu_topology[cpu].thread_id  = -1;
+			cpu_topology[cpu].core_id    = topology_id;
+		}
+		topology_id = find_acpi_cpu_topology_package(cpu);
+		cpu_topology[cpu].package_id = topology_id;
+
+		i = acpi_find_last_cache_level(cpu);
+
+		if (i > 0) {
+			/*
+			 * this is the only part of cpu_topology that has
+			 * a direct relationship with the cache topology
+			 */
+			cache_id = find_acpi_cpu_cache_topology(cpu, i);
+			if (cache_id > 0)
+				cpu_topology[cpu].llc_id = cache_id;
+		}
+	}
+
+	return 0;
+}
+
+#else
+static inline int __init parse_acpi_topology(void)
+{
+	return -EINVAL;
+}
+#endif
+
 void __init init_cpu_topology(void)
 {
 	reset_cpu_topology();
@@ -304,6 +376,8 @@ void __init init_cpu_topology(void)
 	 * Discard anything that was parsed if we hit an error so we
 	 * don't use partial information.
 	 */
-	if (of_have_populated_dt() && parse_dt_topology())
+	if (!acpi_disabled && parse_acpi_topology())
+		reset_cpu_topology();
+	else if (of_have_populated_dt() && parse_dt_topology())
 		reset_cpu_topology();
 }

arch/arm64/kernel/vmlinux.lds.S

@@ -34,25 +34,25 @@ jiffies = jiffies_64;
 	 *    4 KB (see related ASSERT() below)		\
 	 */						\
 	. = ALIGN(SZ_4K);				\
-	VMLINUX_SYMBOL(__hyp_idmap_text_start) = .;	\
+	__hyp_idmap_text_start = .;			\
 	*(.hyp.idmap.text)				\
-	VMLINUX_SYMBOL(__hyp_idmap_text_end) = .;	\
+	__hyp_idmap_text_end = .;			\
-	VMLINUX_SYMBOL(__hyp_text_start) = .;		\
+	__hyp_text_start = .;				\
 	*(.hyp.text)					\
-	VMLINUX_SYMBOL(__hyp_text_end) = .;
+	__hyp_text_end = .;
 
 #define IDMAP_TEXT					\
 	. = ALIGN(SZ_4K);				\
-	VMLINUX_SYMBOL(__idmap_text_start) = .;		\
+	__idmap_text_start = .;				\
 	*(.idmap.text)					\
-	VMLINUX_SYMBOL(__idmap_text_end) = .;
+	__idmap_text_end = .;
 
 #ifdef CONFIG_HIBERNATION
 #define HIBERNATE_TEXT					\
 	. = ALIGN(SZ_4K);				\
-	VMLINUX_SYMBOL(__hibernate_exit_text_start) = .;\
+	__hibernate_exit_text_start = .;		\
 	*(.hibernate_exit.text)				\
-	VMLINUX_SYMBOL(__hibernate_exit_text_end) = .;
+	__hibernate_exit_text_end = .;
 #else
 #define HIBERNATE_TEXT
 #endif
@@ -60,10 +60,10 @@ jiffies = jiffies_64;
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 #define TRAMP_TEXT					\
 	. = ALIGN(PAGE_SIZE);				\
-	VMLINUX_SYMBOL(__entry_tramp_text_start) = .;	\
+	__entry_tramp_text_start = .;			\
 	*(.entry.tramp.text)				\
 	. = ALIGN(PAGE_SIZE);				\
-	VMLINUX_SYMBOL(__entry_tramp_text_end) = .;
+	__entry_tramp_text_end = .;
 #else
 #define TRAMP_TEXT
 #endif

arch/arm64/kvm/hyp/hyp-entry.S

@@ -106,8 +106,44 @@ el1_hvc_guest:
 	 */
 	ldr	x1, [sp]				// Guest's x0
 	eor	w1, w1, #ARM_SMCCC_ARCH_WORKAROUND_1
+	cbz	w1, wa_epilogue
+
+	/* ARM_SMCCC_ARCH_WORKAROUND_2 handling */
+	eor	w1, w1, #(ARM_SMCCC_ARCH_WORKAROUND_1 ^ \
+			  ARM_SMCCC_ARCH_WORKAROUND_2)
 	cbnz	w1, el1_trap
-	mov	x0, x1
+
+#ifdef CONFIG_ARM64_SSBD
+alternative_cb	arm64_enable_wa2_handling
+	b	wa2_end
+alternative_cb_end
+	get_vcpu_ptr	x2, x0
+	ldr	x0, [x2, #VCPU_WORKAROUND_FLAGS]
+
+	// Sanitize the argument and update the guest flags
+	ldr	x1, [sp, #8]			// Guest's x1
+	clz	w1, w1				// Murphy's device:
+	lsr	w1, w1, #5			// w1 = !!w1 without using
+	eor	w1, w1, #1			// the flags...
+	bfi	x0, x1, #VCPU_WORKAROUND_2_FLAG_SHIFT, #1
+	str	x0, [x2, #VCPU_WORKAROUND_FLAGS]
+
+	/* Check that we actually need to perform the call */
+	hyp_ldr_this_cpu x0, arm64_ssbd_callback_required, x2
+	cbz	x0, wa2_end
+
+	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_2
+	smc	#0
+
+	/* Don't leak data from the SMC call */
+	mov	x3, xzr
+wa2_end:
+	mov	x2, xzr
+	mov	x1, xzr
+#endif
+
+wa_epilogue:
+	mov	x0, xzr
 	add	sp, sp, #16
 	eret
 

arch/arm64/kvm/hyp/switch.c

@@ -15,6 +15,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/arm-smccc.h>
 #include <linux/types.h>
 #include <linux/jump_label.h>
 #include <uapi/linux/psci.h>
@@ -389,6 +390,39 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	return false;
 }
 
+static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu)
+{
+	if (!cpus_have_const_cap(ARM64_SSBD))
+		return false;
+
+	return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
+}
+
+static void __hyp_text __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_ARM64_SSBD
+	/*
+	 * The host runs with the workaround always present. If the
+	 * guest wants it disabled, so be it...
+	 */
+	if (__needs_ssbd_off(vcpu) &&
+	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
+		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL);
+#endif
+}
+
+static void __hyp_text __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_ARM64_SSBD
+	/*
+	 * If the guest has disabled the workaround, bring it back on.
+	 */
+	if (__needs_ssbd_off(vcpu) &&
+	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
+		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL);
+#endif
+}
+
 /* Switch to the guest for VHE systems running in EL2 */
 int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 {
@@ -409,6 +443,8 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	sysreg_restore_guest_state_vhe(guest_ctxt);
 	__debug_switch_to_guest(vcpu);
 
+	__set_guest_arch_workaround_state(vcpu);
+
 	do {
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu, host_ctxt);
@@ -416,6 +452,8 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 		/* And we're baaack! */
 	} while (fixup_guest_exit(vcpu, &exit_code));
 
+	__set_host_arch_workaround_state(vcpu);
+
 	fp_enabled = fpsimd_enabled_vhe();
 
 	sysreg_save_guest_state_vhe(guest_ctxt);
@@ -465,6 +503,8 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 	__sysreg_restore_state_nvhe(guest_ctxt);
 	__debug_switch_to_guest(vcpu);
 
+	__set_guest_arch_workaround_state(vcpu);
+
 	do {
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu, host_ctxt);
@@ -472,6 +512,8 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 		/* And we're baaack! */
 	} while (fixup_guest_exit(vcpu, &exit_code));
 
+	__set_host_arch_workaround_state(vcpu);
+
 	fp_enabled = __fpsimd_enabled_nvhe();
 
 	__sysreg_save_state_nvhe(guest_ctxt);

arch/arm64/kvm/reset.c

@@ -122,6 +122,10 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	/* Reset PMU */
 	kvm_pmu_vcpu_reset(vcpu);
 
+	/* Default workaround setup is enabled (if supported) */
+	if (kvm_arm_have_ssbd() == KVM_SSBD_KERNEL)
+		vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG;
+
 	/* Reset timer */
 	return kvm_timer_vcpu_reset(vcpu);
 }

arch/arm64/mm/dma-mapping.c

@@ -504,6 +504,11 @@ static int __init arm64_dma_init(void)
 	    max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
 		swiotlb = 1;
 
+	WARN_TAINT(ARCH_DMA_MINALIGN < cache_line_size(),
+		   TAINT_CPU_OUT_OF_SPEC,
+		   "ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)",
+		   ARCH_DMA_MINALIGN, cache_line_size());
+
 	return atomic_pool_init();
 }
 arch_initcall(arm64_dma_init);

arch/arm64/mm/fault.c

@@ -235,8 +235,9 @@ static bool is_el1_instruction_abort(unsigned int esr)
 	return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR;
 }
 
-static inline bool is_permission_fault(unsigned int esr, struct pt_regs *regs,
+static inline bool is_el1_permission_fault(unsigned int esr,
-				       unsigned long addr)
+					   struct pt_regs *regs,
+					   unsigned long addr)
 {
 	unsigned int ec       = ESR_ELx_EC(esr);
 	unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
@@ -254,6 +255,22 @@ static inline bool is_permission_fault(unsigned int esr, struct pt_regs *regs,
 	return false;
 }
 
+static void die_kernel_fault(const char *msg, unsigned long addr,
+			     unsigned int esr, struct pt_regs *regs)
+{
+	bust_spinlocks(1);
+
+	pr_alert("Unable to handle kernel %s at virtual address %016lx\n", msg,
+		 addr);
+
+	mem_abort_decode(esr);
+
+	show_pte(addr);
+	die("Oops", regs, esr);
+	bust_spinlocks(0);
+	do_exit(SIGKILL);
+}
+
 static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 			      struct pt_regs *regs)
 {
@@ -266,9 +283,7 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 	if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
 		return;
 
-	bust_spinlocks(1);
+	if (is_el1_permission_fault(esr, regs, addr)) {
-
-	if (is_permission_fault(esr, regs, addr)) {
 		if (esr & ESR_ELx_WNR)
 			msg = "write to read-only memory";
 		else
@@ -279,15 +294,7 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 		msg = "paging request";
 	}
 
-	pr_alert("Unable to handle kernel %s at virtual address %08lx\n", msg,
+	die_kernel_fault(msg, addr, esr, regs);
-		 addr);
-
-	mem_abort_decode(esr);
-
-	show_pte(addr);
-	die("Oops", regs, esr);
-	bust_spinlocks(0);
-	do_exit(SIGKILL);
 }
 
 static void __do_user_fault(struct siginfo *info, unsigned int esr)
@@ -447,16 +454,19 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 		mm_flags |= FAULT_FLAG_WRITE;
 	}
 
-	if (addr < TASK_SIZE && is_permission_fault(esr, regs, addr)) {
+	if (addr < TASK_SIZE && is_el1_permission_fault(esr, regs, addr)) {
 		/* regs->orig_addr_limit may be 0 if we entered from EL0 */
 		if (regs->orig_addr_limit == KERNEL_DS)
-			die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
+			die_kernel_fault("access to user memory with fs=KERNEL_DS",
+					 addr, esr, regs);
 
 		if (is_el1_instruction_abort(esr))
-			die("Attempting to execute userspace memory", regs, esr);
+			die_kernel_fault("execution of user memory",
+					 addr, esr, regs);
 
 		if (!search_exception_tables(regs->pc))
-			die("Accessing user space memory outside uaccess.h routines", regs, esr);
+			die_kernel_fault("access to user memory outside uaccess routines",
+					 addr, esr, regs);
 	}
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);

arch/riscv/kernel/cacheinfo.c

@@ -20,7 +20,6 @@ static void ci_leaf_init(struct cacheinfo *this_leaf,
 			 struct device_node *node,
 			 enum cache_type type, unsigned int level)
 {
-	this_leaf->of_node = node;
 	this_leaf->level = level;
 	this_leaf->type = type;
 	/* not a sector cache */

drivers/acpi/Kconfig

@@ -547,6 +547,9 @@ config ACPI_CONFIGFS
 
 if ARM64
 source "drivers/acpi/arm64/Kconfig"
+
+config ACPI_PPTT
+	bool
 endif
 
 config TPS68470_PMIC_OPREGION

drivers/acpi/Makefile

@@ -88,6 +88,7 @@ obj-$(CONFIG_ACPI_BGRT)		+= bgrt.o
 obj-$(CONFIG_ACPI_CPPC_LIB)	+= cppc_acpi.o
 obj-$(CONFIG_ACPI_SPCR_TABLE)	+= spcr.o
 obj-$(CONFIG_ACPI_DEBUGGER_USER) += acpi_dbg.o
+obj-$(CONFIG_ACPI_PPTT) 	+= pptt.o
 
 # processor has its own "processor." module_param namespace
 processor-y			:= processor_driver.o

drivers/acpi/pptt.c

@@ -0,0 +1,655 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * pptt.c - parsing of Processor Properties Topology Table (PPTT)
+ *
+ * Copyright (C) 2018, ARM
+ *
+ * This file implements parsing of the Processor Properties Topology Table
+ * which is optionally used to describe the processor and cache topology.
+ * Due to the relative pointers used throughout the table, this doesn't
+ * leverage the existing subtable parsing in the kernel.
+ *
+ * The PPTT structure is an inverted tree, with each node potentially
+ * holding one or two inverted tree data structures describing
+ * the caches available at that level. Each cache structure optionally
+ * contains properties describing the cache at a given level which can be
+ * used to override hardware probed values.
+ */
+#define pr_fmt(fmt) "ACPI PPTT: " fmt
+
+#include <linux/acpi.h>
+#include <linux/cacheinfo.h>
+#include <acpi/processor.h>
+
+static struct acpi_subtable_header *fetch_pptt_subtable(struct acpi_table_header *table_hdr,
+							u32 pptt_ref)
+{
+	struct acpi_subtable_header *entry;
+
+	/* there isn't a subtable at reference 0 */
+	if (pptt_ref < sizeof(struct acpi_subtable_header))
+		return NULL;
+
+	if (pptt_ref + sizeof(struct acpi_subtable_header) > table_hdr->length)
+		return NULL;
+
+	entry = ACPI_ADD_PTR(struct acpi_subtable_header, table_hdr, pptt_ref);
+
+	if (entry->length == 0)
+		return NULL;
+
+	if (pptt_ref + entry->length > table_hdr->length)
+		return NULL;
+
+	return entry;
+}
+
+static struct acpi_pptt_processor *fetch_pptt_node(struct acpi_table_header *table_hdr,
+						   u32 pptt_ref)
+{
+	return (struct acpi_pptt_processor *)fetch_pptt_subtable(table_hdr, pptt_ref);
+}
+
+static struct acpi_pptt_cache *fetch_pptt_cache(struct acpi_table_header *table_hdr,
+						u32 pptt_ref)
+{
+	return (struct acpi_pptt_cache *)fetch_pptt_subtable(table_hdr, pptt_ref);
+}
+
+static struct acpi_subtable_header *acpi_get_pptt_resource(struct acpi_table_header *table_hdr,
+							   struct acpi_pptt_processor *node,
+							   int resource)
+{
+	u32 *ref;
+
+	if (resource >= node->number_of_priv_resources)
+		return NULL;
+
+	ref = ACPI_ADD_PTR(u32, node, sizeof(struct acpi_pptt_processor));
+	ref += resource;
+
+	return fetch_pptt_subtable(table_hdr, *ref);
+}
+
+static inline bool acpi_pptt_match_type(int table_type, int type)
+{
+	return ((table_type & ACPI_PPTT_MASK_CACHE_TYPE) == type ||
+		table_type & ACPI_PPTT_CACHE_TYPE_UNIFIED & type);
+}
+
+/**
+ * acpi_pptt_walk_cache() - Attempt to find the requested acpi_pptt_cache
+ * @table_hdr: Pointer to the head of the PPTT table
+ * @local_level: passed res reflects this cache level
+ * @res: cache resource in the PPTT we want to walk
+ * @found: returns a pointer to the requested level if found
+ * @level: the requested cache level
+ * @type: the requested cache type
+ *
+ * Attempt to find a given cache level, while counting the max number
+ * of cache levels for the cache node.
+ *
+ * Given a pptt resource, verify that it is a cache node, then walk
+ * down each level of caches, counting how many levels are found
+ * as well as checking the cache type (icache, dcache, unified). If a
+ * level & type match, then we set found, and continue the search.
+ * Once the entire cache branch has been walked return its max
+ * depth.
+ *
+ * Return: The cache structure and the level we terminated with.
+ */
+static int acpi_pptt_walk_cache(struct acpi_table_header *table_hdr,
+				int local_level,
+				struct acpi_subtable_header *res,
+				struct acpi_pptt_cache **found,
+				int level, int type)
+{
+	struct acpi_pptt_cache *cache;
+
+	if (res->type != ACPI_PPTT_TYPE_CACHE)
+		return 0;
+
+	cache = (struct acpi_pptt_cache *) res;
+	while (cache) {
+		local_level++;
+
+		if (local_level == level &&
+		    cache->flags & ACPI_PPTT_CACHE_TYPE_VALID &&
+		    acpi_pptt_match_type(cache->attributes, type)) {
+			if (*found != NULL && cache != *found)
+				pr_warn("Found duplicate cache level/type unable to determine uniqueness\n");
+
+			pr_debug("Found cache @ level %d\n", level);
+			*found = cache;
+			/*
+			 * continue looking at this node's resource list
+			 * to verify that we don't find a duplicate
+			 * cache node.
+			 */
+		}
+		cache = fetch_pptt_cache(table_hdr, cache->next_level_of_cache);
+	}
+	return local_level;
+}
+
+static struct acpi_pptt_cache *acpi_find_cache_level(struct acpi_table_header *table_hdr,
+						     struct acpi_pptt_processor *cpu_node,
+						     int *starting_level, int level,
+						     int type)
+{
+	struct acpi_subtable_header *res;
+	int number_of_levels = *starting_level;
+	int resource = 0;
+	struct acpi_pptt_cache *ret = NULL;
+	int local_level;
+
+	/* walk down from processor node */
+	while ((res = acpi_get_pptt_resource(table_hdr, cpu_node, resource))) {
+		resource++;
+
+		local_level = acpi_pptt_walk_cache(table_hdr, *starting_level,
+						   res, &ret, level, type);
+		/*
+		 * we are looking for the max depth. Since its potentially
+		 * possible for a given node to have resources with differing
+		 * depths verify that the depth we have found is the largest.
+		 */
+		if (number_of_levels < local_level)
+			number_of_levels = local_level;
+	}
+	if (number_of_levels > *starting_level)
+		*starting_level = number_of_levels;
+
+	return ret;
+}
+
+/**
+ * acpi_count_levels() - Given a PPTT table, and a cpu node, count the caches
+ * @table_hdr: Pointer to the head of the PPTT table
+ * @cpu_node: processor node we wish to count caches for
+ *
+ * Given a processor node containing a processing unit, walk into it and count
+ * how many levels exist solely for it, and then walk up each level until we hit
+ * the root node (ignore the package level because it may be possible to have
+ * caches that exist across packages). Count the number of cache levels that
+ * exist at each level on the way up.
+ *
+ * Return: Total number of levels found.
+ */
+static int acpi_count_levels(struct acpi_table_header *table_hdr,
+			     struct acpi_pptt_processor *cpu_node)
+{
+	int total_levels = 0;
+
+	do {
+		acpi_find_cache_level(table_hdr, cpu_node, &total_levels, 0, 0);
+		cpu_node = fetch_pptt_node(table_hdr, cpu_node->parent);
+	} while (cpu_node);
+
+	return total_levels;
+}
+
+/**
+ * acpi_pptt_leaf_node() - Given a processor node, determine if its a leaf
+ * @table_hdr: Pointer to the head of the PPTT table
+ * @node: passed node is checked to see if its a leaf
+ *
+ * Determine if the *node parameter is a leaf node by iterating the
+ * PPTT table, looking for nodes which reference it.
+ *
+ * Return: 0 if we find a node referencing the passed node (or table error),
+ * or 1 if we don't.
+ */
+static int acpi_pptt_leaf_node(struct acpi_table_header *table_hdr,
+			       struct acpi_pptt_processor *node)
+{
+	struct acpi_subtable_header *entry;
+	unsigned long table_end;
+	u32 node_entry;
+	struct acpi_pptt_processor *cpu_node;
+	u32 proc_sz;
+
+	table_end = (unsigned long)table_hdr + table_hdr->length;
+	node_entry = ACPI_PTR_DIFF(node, table_hdr);
+	entry = ACPI_ADD_PTR(struct acpi_subtable_header, table_hdr,
+			     sizeof(struct acpi_table_pptt));
+	proc_sz = sizeof(struct acpi_pptt_processor *);
+
+	while ((unsigned long)entry + proc_sz < table_end) {
+		cpu_node = (struct acpi_pptt_processor *)entry;
+		if (entry->type == ACPI_PPTT_TYPE_PROCESSOR &&
+		    cpu_node->parent == node_entry)
+			return 0;
+		if (entry->length == 0)
+			return 0;
+		entry = ACPI_ADD_PTR(struct acpi_subtable_header, entry,
+				     entry->length);
+
+	}
+	return 1;
+}
+
+/**
+ * acpi_find_processor_node() - Given a PPTT table find the requested processor
+ * @table_hdr:  Pointer to the head of the PPTT table
+ * @acpi_cpu_id: cpu we are searching for
+ *
+ * Find the subtable entry describing the provided processor.
+ * This is done by iterating the PPTT table looking for processor nodes
+ * which have an acpi_processor_id that matches the acpi_cpu_id parameter
+ * passed into the function. If we find a node that matches this criteria
+ * we verify that its a leaf node in the topology rather than depending
+ * on the valid flag, which doesn't need to be set for leaf nodes.
+ *
+ * Return: NULL, or the processors acpi_pptt_processor*
+ */
+static struct acpi_pptt_processor *acpi_find_processor_node(struct acpi_table_header *table_hdr,
+							    u32 acpi_cpu_id)
+{
+	struct acpi_subtable_header *entry;
+	unsigned long table_end;
+	struct acpi_pptt_processor *cpu_node;
+	u32 proc_sz;
+
+	table_end = (unsigned long)table_hdr + table_hdr->length;
+	entry = ACPI_ADD_PTR(struct acpi_subtable_header, table_hdr,
+			     sizeof(struct acpi_table_pptt));
+	proc_sz = sizeof(struct acpi_pptt_processor *);
+
+	/* find the processor structure associated with this cpuid */
+	while ((unsigned long)entry + proc_sz < table_end) {
+		cpu_node = (struct acpi_pptt_processor *)entry;
+
+		if (entry->length == 0) {
+			pr_warn("Invalid zero length subtable\n");
+			break;
+		}
+		if (entry->type == ACPI_PPTT_TYPE_PROCESSOR &&
+		    acpi_cpu_id == cpu_node->acpi_processor_id &&
+		     acpi_pptt_leaf_node(table_hdr, cpu_node)) {
+			return (struct acpi_pptt_processor *)entry;
+		}
+
+		entry = ACPI_ADD_PTR(struct acpi_subtable_header, entry,
+				     entry->length);
+	}
+
+	return NULL;
+}
+
+static int acpi_find_cache_levels(struct acpi_table_header *table_hdr,
+				  u32 acpi_cpu_id)
+{
+	int number_of_levels = 0;
+	struct acpi_pptt_processor *cpu;
+
+	cpu = acpi_find_processor_node(table_hdr, acpi_cpu_id);
+	if (cpu)
+		number_of_levels = acpi_count_levels(table_hdr, cpu);
+
+	return number_of_levels;
+}
+
+static u8 acpi_cache_type(enum cache_type type)
+{
+	switch (type) {
+	case CACHE_TYPE_DATA:
+		pr_debug("Looking for data cache\n");
+		return ACPI_PPTT_CACHE_TYPE_DATA;
+	case CACHE_TYPE_INST:
+		pr_debug("Looking for instruction cache\n");
+		return ACPI_PPTT_CACHE_TYPE_INSTR;
+	default:
+	case CACHE_TYPE_UNIFIED:
+		pr_debug("Looking for unified cache\n");
+		/*
+		 * It is important that ACPI_PPTT_CACHE_TYPE_UNIFIED
+		 * contains the bit pattern that will match both
+		 * ACPI unified bit patterns because we use it later
+		 * to match both cases.
+		 */
+		return ACPI_PPTT_CACHE_TYPE_UNIFIED;
+	}
+}
+
+static struct acpi_pptt_cache *acpi_find_cache_node(struct acpi_table_header *table_hdr,
+						    u32 acpi_cpu_id,
+						    enum cache_type type,
+						    unsigned int level,
+						    struct acpi_pptt_processor **node)
+{
+	int total_levels = 0;
+	struct acpi_pptt_cache *found = NULL;
+	struct acpi_pptt_processor *cpu_node;
+	u8 acpi_type = acpi_cache_type(type);
+
+	pr_debug("Looking for CPU %d's level %d cache type %d\n",
+		 acpi_cpu_id, level, acpi_type);
+
+	cpu_node = acpi_find_processor_node(table_hdr, acpi_cpu_id);
+
+	while (cpu_node && !found) {
+		found = acpi_find_cache_level(table_hdr, cpu_node,
+					      &total_levels, level, acpi_type);
+		*node = cpu_node;
+		cpu_node = fetch_pptt_node(table_hdr, cpu_node->parent);
+	}
+
+	return found;
+}
+
+/* total number of attributes checked by the properties code */
+#define PPTT_CHECKED_ATTRIBUTES 4
+
+/**
+ * update_cache_properties() - Update cacheinfo for the given processor
+ * @this_leaf: Kernel cache info structure being updated
+ * @found_cache: The PPTT node describing this cache instance
+ * @cpu_node: A unique reference to describe this cache instance
+ *
+ * The ACPI spec implies that the fields in the cache structures are used to
+ * extend and correct the information probed from the hardware. Lets only
+ * set fields that we determine are VALID.
+ *
+ * Return: nothing. Side effect of updating the global cacheinfo
+ */
+static void update_cache_properties(struct cacheinfo *this_leaf,
+				    struct acpi_pptt_cache *found_cache,
+				    struct acpi_pptt_processor *cpu_node)
+{
+	int valid_flags = 0;
+
+	this_leaf->fw_token = cpu_node;
+	if (found_cache->flags & ACPI_PPTT_SIZE_PROPERTY_VALID) {
+		this_leaf->size = found_cache->size;
+		valid_flags++;
+	}
+	if (found_cache->flags & ACPI_PPTT_LINE_SIZE_VALID) {
+		this_leaf->coherency_line_size = found_cache->line_size;
+		valid_flags++;
+	}
+	if (found_cache->flags & ACPI_PPTT_NUMBER_OF_SETS_VALID) {
+		this_leaf->number_of_sets = found_cache->number_of_sets;
+		valid_flags++;
+	}
+	if (found_cache->flags & ACPI_PPTT_ASSOCIATIVITY_VALID) {
+		this_leaf->ways_of_associativity = found_cache->associativity;
+		valid_flags++;
+	}
+	if (found_cache->flags & ACPI_PPTT_WRITE_POLICY_VALID) {
+		switch (found_cache->attributes & ACPI_PPTT_MASK_WRITE_POLICY) {
+		case ACPI_PPTT_CACHE_POLICY_WT:
+			this_leaf->attributes = CACHE_WRITE_THROUGH;
+			break;
+		case ACPI_PPTT_CACHE_POLICY_WB:
+			this_leaf->attributes = CACHE_WRITE_BACK;
+			break;
+		}
+	}
+	if (found_cache->flags & ACPI_PPTT_ALLOCATION_TYPE_VALID) {
+		switch (found_cache->attributes & ACPI_PPTT_MASK_ALLOCATION_TYPE) {
+		case ACPI_PPTT_CACHE_READ_ALLOCATE:
+			this_leaf->attributes |= CACHE_READ_ALLOCATE;
+			break;
+		case ACPI_PPTT_CACHE_WRITE_ALLOCATE:
+			this_leaf->attributes |= CACHE_WRITE_ALLOCATE;
+			break;
+		case ACPI_PPTT_CACHE_RW_ALLOCATE:
+		case ACPI_PPTT_CACHE_RW_ALLOCATE_ALT:
+			this_leaf->attributes |=
+				CACHE_READ_ALLOCATE | CACHE_WRITE_ALLOCATE;
+			break;
+		}
+	}
+	/*
+	 * If the above flags are valid, and the cache type is NOCACHE
+	 * update the cache type as well.
+	 */
+	if (this_leaf->type == CACHE_TYPE_NOCACHE &&
+	    valid_flags == PPTT_CHECKED_ATTRIBUTES)
+		this_leaf->type = CACHE_TYPE_UNIFIED;
+}
+
+static void cache_setup_acpi_cpu(struct acpi_table_header *table,
+				 unsigned int cpu)
+{
+	struct acpi_pptt_cache *found_cache;
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	u32 acpi_cpu_id = get_acpi_id_for_cpu(cpu);
+	struct cacheinfo *this_leaf;
+	unsigned int index = 0;
+	struct acpi_pptt_processor *cpu_node = NULL;
+
+	while (index < get_cpu_cacheinfo(cpu)->num_leaves) {
+		this_leaf = this_cpu_ci->info_list + index;
+		found_cache = acpi_find_cache_node(table, acpi_cpu_id,
+						   this_leaf->type,
+						   this_leaf->level,
+						   &cpu_node);
+		pr_debug("found = %p %p\n", found_cache, cpu_node);
+		if (found_cache)
+			update_cache_properties(this_leaf,
+						found_cache,
+						cpu_node);
+
+		index++;
+	}
+}
+
+/* Passing level values greater than this will result in search termination */
+#define PPTT_ABORT_PACKAGE 0xFF
+
+static struct acpi_pptt_processor *acpi_find_processor_package_id(struct acpi_table_header *table_hdr,
+								  struct acpi_pptt_processor *cpu,
+								  int level, int flag)
+{
+	struct acpi_pptt_processor *prev_node;
+
+	while (cpu && level) {
+		if (cpu->flags & flag)
+			break;
+		pr_debug("level %d\n", level);
+		prev_node = fetch_pptt_node(table_hdr, cpu->parent);
+		if (prev_node == NULL)
+			break;
+		cpu = prev_node;
+		level--;
+	}
+	return cpu;
+}
+
+/**
+ * topology_get_acpi_cpu_tag() - Find a unique topology value for a feature
+ * @table: Pointer to the head of the PPTT table
+ * @cpu: Kernel logical cpu number
+ * @level: A level that terminates the search
+ * @flag: A flag which terminates the search
+ *
+ * Get a unique value given a cpu, and a topology level, that can be
+ * matched to determine which cpus share common topological features
+ * at that level.
+ *
+ * Return: Unique value, or -ENOENT if unable to locate cpu
+ */
+static int topology_get_acpi_cpu_tag(struct acpi_table_header *table,
+				     unsigned int cpu, int level, int flag)
+{
+	struct acpi_pptt_processor *cpu_node;
+	u32 acpi_cpu_id = get_acpi_id_for_cpu(cpu);
+
+	cpu_node = acpi_find_processor_node(table, acpi_cpu_id);
+	if (cpu_node) {
+		cpu_node = acpi_find_processor_package_id(table, cpu_node,
+							  level, flag);
+		/* Only the first level has a guaranteed id */
+		if (level == 0)
+			return cpu_node->acpi_processor_id;
+		return ACPI_PTR_DIFF(cpu_node, table);
+	}
+	pr_warn_once("PPTT table found, but unable to locate core %d (%d)\n",
+		    cpu, acpi_cpu_id);
+	return -ENOENT;
+}
+
+static int find_acpi_cpu_topology_tag(unsigned int cpu, int level, int flag)
+{
+	struct acpi_table_header *table;
+	acpi_status status;
+	int retval;
+
+	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
+	if (ACPI_FAILURE(status)) {
+		pr_warn_once("No PPTT table found, cpu topology may be inaccurate\n");
+		return -ENOENT;
+	}
+	retval = topology_get_acpi_cpu_tag(table, cpu, level, flag);
+	pr_debug("Topology Setup ACPI cpu %d, level %d ret = %d\n",
+		 cpu, level, retval);
+	acpi_put_table(table);
+
+	return retval;
+}
+
+/**
+ * acpi_find_last_cache_level() - Determines the number of cache levels for a PE
+ * @cpu: Kernel logical cpu number
+ *
+ * Given a logical cpu number, returns the number of levels of cache represented
+ * in the PPTT. Errors caused by lack of a PPTT table, or otherwise, return 0
+ * indicating we didn't find any cache levels.
+ *
+ * Return: Cache levels visible to this core.
+ */
+int acpi_find_last_cache_level(unsigned int cpu)
+{
+	u32 acpi_cpu_id;
+	struct acpi_table_header *table;
+	int number_of_levels = 0;
+	acpi_status status;
+
+	pr_debug("Cache Setup find last level cpu=%d\n", cpu);
+
+	acpi_cpu_id = get_acpi_id_for_cpu(cpu);
+	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
+	if (ACPI_FAILURE(status)) {
+		pr_warn_once("No PPTT table found, cache topology may be inaccurate\n");
+	} else {
+		number_of_levels = acpi_find_cache_levels(table, acpi_cpu_id);
+		acpi_put_table(table);
+	}
+	pr_debug("Cache Setup find last level level=%d\n", number_of_levels);
+
+	return number_of_levels;
+}
+
+/**
+ * cache_setup_acpi() - Override CPU cache topology with data from the PPTT
+ * @cpu: Kernel logical cpu number
+ *
+ * Updates the global cache info provided by cpu_get_cacheinfo()
+ * when there are valid properties in the acpi_pptt_cache nodes. A
+ * successful parse may not result in any updates if none of the
+ * cache levels have any valid flags set.  Futher, a unique value is
+ * associated with each known CPU cache entry. This unique value
+ * can be used to determine whether caches are shared between cpus.
+ *
+ * Return: -ENOENT on failure to find table, or 0 on success
+ */
+int cache_setup_acpi(unsigned int cpu)
+{
+	struct acpi_table_header *table;
+	acpi_status status;
+
+	pr_debug("Cache Setup ACPI cpu %d\n", cpu);
+
+	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
+	if (ACPI_FAILURE(status)) {
+		pr_warn_once("No PPTT table found, cache topology may be inaccurate\n");
+		return -ENOENT;
+	}
+
+	cache_setup_acpi_cpu(table, cpu);
+	acpi_put_table(table);
+
+	return status;
+}
+
+/**
+ * find_acpi_cpu_topology() - Determine a unique topology value for a given cpu
+ * @cpu: Kernel logical cpu number
+ * @level: The topological level for which we would like a unique ID
+ *
+ * Determine a topology unique ID for each thread/core/cluster/mc_grouping
+ * /socket/etc. This ID can then be used to group peers, which will have
+ * matching ids.
+ *
+ * The search terminates when either the requested level is found or
+ * we reach a root node. Levels beyond the termination point will return the
+ * same unique ID. The unique id for level 0 is the acpi processor id. All
+ * other levels beyond this use a generated value to uniquely identify
+ * a topological feature.
+ *
+ * Return: -ENOENT if the PPTT doesn't exist, or the cpu cannot be found.
+ * Otherwise returns a value which represents a unique topological feature.
+ */
+int find_acpi_cpu_topology(unsigned int cpu, int level)
+{
+	return find_acpi_cpu_topology_tag(cpu, level, 0);
+}
+
+/**
+ * find_acpi_cpu_cache_topology() - Determine a unique cache topology value
+ * @cpu: Kernel logical cpu number
+ * @level: The cache level for which we would like a unique ID
+ *
+ * Determine a unique ID for each unified cache in the system
+ *
+ * Return: -ENOENT if the PPTT doesn't exist, or the cpu cannot be found.
+ * Otherwise returns a value which represents a unique topological feature.
+ */
+int find_acpi_cpu_cache_topology(unsigned int cpu, int level)
+{
+	struct acpi_table_header *table;
+	struct acpi_pptt_cache *found_cache;
+	acpi_status status;
+	u32 acpi_cpu_id = get_acpi_id_for_cpu(cpu);
+	struct acpi_pptt_processor *cpu_node = NULL;
+	int ret = -1;
+
+	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
+	if (ACPI_FAILURE(status)) {
+		pr_warn_once("No PPTT table found, topology may be inaccurate\n");
+		return -ENOENT;
+	}
+
+	found_cache = acpi_find_cache_node(table, acpi_cpu_id,
+					   CACHE_TYPE_UNIFIED,
+					   level,
+					   &cpu_node);
+	if (found_cache)
+		ret = ACPI_PTR_DIFF(cpu_node, table);
+
+	acpi_put_table(table);
+
+	return ret;
+}
+
+
+/**
+ * find_acpi_cpu_topology_package() - Determine a unique cpu package value
+ * @cpu: Kernel logical cpu number
+ *
+ * Determine a topology unique package ID for the given cpu.
+ * This ID can then be used to group peers, which will have matching ids.
+ *
+ * The search terminates when either a level is found with the PHYSICAL_PACKAGE
+ * flag set or we reach a root node.
+ *
+ * Return: -ENOENT if the PPTT doesn't exist, or the cpu cannot be found.
+ * Otherwise returns a value which represents the package for this cpu.
+ */
+int find_acpi_cpu_topology_package(unsigned int cpu)
+{
+	return find_acpi_cpu_topology_tag(cpu, PPTT_ABORT_PACKAGE,
+					  ACPI_PPTT_PHYSICAL_PACKAGE);
+}

drivers/acpi/tables.c

@@ -462,7 +462,7 @@ static const char * const table_sigs[] = {
 	ACPI_SIG_UEFI, ACPI_SIG_WAET, ACPI_SIG_WDAT, ACPI_SIG_WDDT,
 	ACPI_SIG_WDRT, ACPI_SIG_DSDT, ACPI_SIG_FADT, ACPI_SIG_PSDT,
 	ACPI_SIG_RSDT, ACPI_SIG_XSDT, ACPI_SIG_SSDT, ACPI_SIG_IORT,
-	ACPI_SIG_NFIT, ACPI_SIG_HMAT, NULL };
+	ACPI_SIG_NFIT, ACPI_SIG_HMAT, ACPI_SIG_PPTT, NULL };
 
 #define ACPI_HEADER_SIZE sizeof(struct acpi_table_header)
 

drivers/base/cacheinfo.c

@@ -32,50 +32,10 @@ struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu)
 }
 
 #ifdef CONFIG_OF
-static int cache_setup_of_node(unsigned int cpu)
-{
-	struct device_node *np;
-	struct cacheinfo *this_leaf;
-	struct device *cpu_dev = get_cpu_device(cpu);
-	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
-	unsigned int index = 0;
-
-	/* skip if of_node is already populated */
-	if (this_cpu_ci->info_list->of_node)
-		return 0;
-
-	if (!cpu_dev) {
-		pr_err("No cpu device for CPU %d\n", cpu);
-		return -ENODEV;
-	}
-	np = cpu_dev->of_node;
-	if (!np) {
-		pr_err("Failed to find cpu%d device node\n", cpu);
-		return -ENOENT;
-	}
-
-	while (index < cache_leaves(cpu)) {
-		this_leaf = this_cpu_ci->info_list + index;
-		if (this_leaf->level != 1)
-			np = of_find_next_cache_node(np);
-		else
-			np = of_node_get(np);/* cpu node itself */
-		if (!np)
-			break;
-		this_leaf->of_node = np;
-		index++;
-	}
-
-	if (index != cache_leaves(cpu)) /* not all OF nodes populated */
-		return -ENOENT;
-
-	return 0;
-}
-
 static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf,
 					   struct cacheinfo *sib_leaf)
 {
-	return sib_leaf->of_node == this_leaf->of_node;
+	return sib_leaf->fw_token == this_leaf->fw_token;
 }
 
 /* OF properties to query for a given cache type */
@@ -111,7 +71,7 @@ static inline int get_cacheinfo_idx(enum cache_type type)
 	return type;
 }
 
-static void cache_size(struct cacheinfo *this_leaf)
+static void cache_size(struct cacheinfo *this_leaf, struct device_node *np)
 {
 	const char *propname;
 	const __be32 *cache_size;
@@ -120,13 +80,14 @@ static void cache_size(struct cacheinfo *this_leaf)
 	ct_idx = get_cacheinfo_idx(this_leaf->type);
 	propname = cache_type_info[ct_idx].size_prop;
 
-	cache_size = of_get_property(this_leaf->of_node, propname, NULL);
+	cache_size = of_get_property(np, propname, NULL);
 	if (cache_size)
 		this_leaf->size = of_read_number(cache_size, 1);
 }
 
 /* not cache_line_size() because that's a macro in include/linux/cache.h */
-static void cache_get_line_size(struct cacheinfo *this_leaf)
+static void cache_get_line_size(struct cacheinfo *this_leaf,
+				struct device_node *np)
 {
 	const __be32 *line_size;
 	int i, lim, ct_idx;
@@ -138,7 +99,7 @@ static void cache_get_line_size(struct cacheinfo *this_leaf)
 		const char *propname;
 
 		propname = cache_type_info[ct_idx].line_size_props[i];
-		line_size = of_get_property(this_leaf->of_node, propname, NULL);
+		line_size = of_get_property(np, propname, NULL);
 		if (line_size)
 			break;
 	}
@@ -147,7 +108,7 @@ static void cache_get_line_size(struct cacheinfo *this_leaf)
 		this_leaf->coherency_line_size = of_read_number(line_size, 1);
 }
 
-static void cache_nr_sets(struct cacheinfo *this_leaf)
+static void cache_nr_sets(struct cacheinfo *this_leaf, struct device_node *np)
 {
 	const char *propname;
 	const __be32 *nr_sets;
@@ -156,7 +117,7 @@ static void cache_nr_sets(struct cacheinfo *this_leaf)
 	ct_idx = get_cacheinfo_idx(this_leaf->type);
 	propname = cache_type_info[ct_idx].nr_sets_prop;
 
-	nr_sets = of_get_property(this_leaf->of_node, propname, NULL);
+	nr_sets = of_get_property(np, propname, NULL);
 	if (nr_sets)
 		this_leaf->number_of_sets = of_read_number(nr_sets, 1);
 }
@@ -175,41 +136,77 @@ static void cache_associativity(struct cacheinfo *this_leaf)
 		this_leaf->ways_of_associativity = (size / nr_sets) / line_size;
 }
 
-static bool cache_node_is_unified(struct cacheinfo *this_leaf)
+static bool cache_node_is_unified(struct cacheinfo *this_leaf,
+				  struct device_node *np)
 {
-	return of_property_read_bool(this_leaf->of_node, "cache-unified");
+	return of_property_read_bool(np, "cache-unified");
 }
 
-static void cache_of_override_properties(unsigned int cpu)
+static void cache_of_set_props(struct cacheinfo *this_leaf,
+			       struct device_node *np)
 {
-	int index;
+	/*
-	struct cacheinfo *this_leaf;
+	 * init_cache_level must setup the cache level correctly
-	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	 * overriding the architecturally specified levels, so
+	 * if type is NONE at this stage, it should be unified
+	 */
+	if (this_leaf->type == CACHE_TYPE_NOCACHE &&
+	    cache_node_is_unified(this_leaf, np))
+		this_leaf->type = CACHE_TYPE_UNIFIED;
+	cache_size(this_leaf, np);
+	cache_get_line_size(this_leaf, np);
+	cache_nr_sets(this_leaf, np);
+	cache_associativity(this_leaf);
+}
 
-	for (index = 0; index < cache_leaves(cpu); index++) {
+static int cache_setup_of_node(unsigned int cpu)
-		this_leaf = this_cpu_ci->info_list + index;
+{
-		/*
+	struct device_node *np;
-		 * init_cache_level must setup the cache level correctly
+	struct cacheinfo *this_leaf;
-		 * overriding the architecturally specified levels, so
+	struct device *cpu_dev = get_cpu_device(cpu);
-		 * if type is NONE at this stage, it should be unified
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
-		 */
+	unsigned int index = 0;
-		if (this_leaf->type == CACHE_TYPE_NOCACHE &&
+
-		    cache_node_is_unified(this_leaf))
+	/* skip if fw_token is already populated */
-			this_leaf->type = CACHE_TYPE_UNIFIED;
+	if (this_cpu_ci->info_list->fw_token) {
-		cache_size(this_leaf);
+		return 0;
-		cache_get_line_size(this_leaf);
-		cache_nr_sets(this_leaf);
-		cache_associativity(this_leaf);
 	}
+
+	if (!cpu_dev) {
+		pr_err("No cpu device for CPU %d\n", cpu);
+		return -ENODEV;
+	}
+	np = cpu_dev->of_node;
+	if (!np) {
+		pr_err("Failed to find cpu%d device node\n", cpu);
+		return -ENOENT;
+	}
+
+	while (index < cache_leaves(cpu)) {
+		this_leaf = this_cpu_ci->info_list + index;
+		if (this_leaf->level != 1)
+			np = of_find_next_cache_node(np);
+		else
+			np = of_node_get(np);/* cpu node itself */
+		if (!np)
+			break;
+		cache_of_set_props(this_leaf, np);
+		this_leaf->fw_token = np;
+		index++;
+	}
+
+	if (index != cache_leaves(cpu)) /* not all OF nodes populated */
+		return -ENOENT;
+
+	return 0;
 }
 #else
-static void cache_of_override_properties(unsigned int cpu) { }
 static inline int cache_setup_of_node(unsigned int cpu) { return 0; }
 static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf,
 					   struct cacheinfo *sib_leaf)
 {
 	/*
-	 * For non-DT systems, assume unique level 1 cache, system-wide
+	 * For non-DT/ACPI systems, assume unique level 1 caches, system-wide
 	 * shared caches for all other levels. This will be used only if
 	 * arch specific code has not populated shared_cpu_map
 	 */
@@ -217,6 +214,11 @@ static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf,
 }
 #endif
 
+int __weak cache_setup_acpi(unsigned int cpu)
+{
+	return -ENOTSUPP;
+}
+
 static int cache_shared_cpu_map_setup(unsigned int cpu)
 {
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
@@ -230,8 +232,8 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
 	if (of_have_populated_dt())
 		ret = cache_setup_of_node(cpu);
 	else if (!acpi_disabled)
-		/* No cache property/hierarchy support yet in ACPI */
+		ret = cache_setup_acpi(cpu);
-		ret = -ENOTSUPP;
+
 	if (ret)
 		return ret;
 
@@ -282,16 +284,11 @@ static void cache_shared_cpu_map_remove(unsigned int cpu)
 			cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
 			cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
 		}
-		of_node_put(this_leaf->of_node);
+		if (of_have_populated_dt())
+			of_node_put(this_leaf->fw_token);
 	}
 }
 
-static void cache_override_properties(unsigned int cpu)
-{
-	if (of_have_populated_dt())
-		return cache_of_override_properties(cpu);
-}
-
 static void free_cache_attributes(unsigned int cpu)
 {
 	if (!per_cpu_cacheinfo(cpu))
@@ -325,12 +322,17 @@ static int detect_cache_attributes(unsigned int cpu)
 	if (per_cpu_cacheinfo(cpu) == NULL)
 		return -ENOMEM;
 
+	/*
+	 * populate_cache_leaves() may completely setup the cache leaves and
+	 * shared_cpu_map or it may leave it partially setup.
+	 */
 	ret = populate_cache_leaves(cpu);
 	if (ret)
 		goto free_ci;
 	/*
-	 * For systems using DT for cache hierarchy, of_node and shared_cpu_map
+	 * For systems using DT for cache hierarchy, fw_token
-	 * will be set up here only if they are not populated already
+	 * and shared_cpu_map will be set up here only if they are
+	 * not populated already
 	 */
 	ret = cache_shared_cpu_map_setup(cpu);
 	if (ret) {
@@ -338,7 +340,6 @@ static int detect_cache_attributes(unsigned int cpu)
 		goto free_ci;
 	}
 
-	cache_override_properties(cpu);
 	return 0;
 
 free_ci:

drivers/perf/Kconfig

@@ -6,30 +6,32 @@ menu "Performance monitor support"
 	depends on PERF_EVENTS
 
 config ARM_CCI_PMU
-	bool
+	tristate "ARM CCI PMU driver"
+	depends on (ARM && CPU_V7) || ARM64
 	select ARM_CCI
+	help
+	  Support for PMU events monitoring on the ARM CCI (Cache Coherent
+	  Interconnect) family of products.
+
+	  If compiled as a module, it will be called arm-cci.
 
 config ARM_CCI400_PMU
-	bool "ARM CCI400 PMU support"
+	bool "support CCI-400"
-	depends on (ARM && CPU_V7) || ARM64
+	default y
+	depends on ARM_CCI_PMU
 	select ARM_CCI400_COMMON
-	select ARM_CCI_PMU
 	help
-	  Support for PMU events monitoring on the ARM CCI-400 (cache coherent
+	  CCI-400 provides 4 independent event counters counting events related
-	  interconnect). CCI-400 supports counting events related to the
+	  to the connected slave/master interfaces, plus a cycle counter.
-	  connected slave/master interfaces.
 
 config ARM_CCI5xx_PMU
-	bool "ARM CCI-500/CCI-550 PMU support"
+	bool "support CCI-500/CCI-550"
-	depends on (ARM && CPU_V7) || ARM64
+	default y
-	select ARM_CCI_PMU
+	depends on ARM_CCI_PMU
 	help
-	  Support for PMU events monitoring on the ARM CCI-500/CCI-550 cache
+	  CCI-500/CCI-550 both provide 8 independent event counters, which can
-	  coherent interconnects. Both of them provide 8 independent event counters,
+	  count events pertaining to the slave/master interfaces as well as the
-	  which can count events pertaining to the slave/master interfaces as well
+	  internal events to the CCI.
-	  as the internal events to the CCI.
-
-	  If unsure, say Y
 
 config ARM_CCN
 	tristate "ARM CCN driver support"
@@ -94,7 +96,7 @@ config XGENE_PMU
 
 config ARM_SPE_PMU
 	tristate "Enable support for the ARMv8.2 Statistical Profiling Extension"
-	depends on PERF_EVENTS && ARM64
+	depends on ARM64
 	help
 	  Enable perf support for the ARMv8.2 Statistical Profiling
 	  Extension, which provides periodic sampling of operations in

drivers/perf/arm-cci.c

@@ -120,9 +120,9 @@ enum cci_models {
 
 static void pmu_write_counters(struct cci_pmu *cci_pmu,
 				 unsigned long *mask);
-static ssize_t cci_pmu_format_show(struct device *dev,
+static ssize_t __maybe_unused cci_pmu_format_show(struct device *dev,
 			struct device_attribute *attr, char *buf);
-static ssize_t cci_pmu_event_show(struct device *dev,
+static ssize_t __maybe_unused cci_pmu_event_show(struct device *dev,
 			struct device_attribute *attr, char *buf);
 
 #define CCI_EXT_ATTR_ENTRY(_name, _func, _config) 				\
@@ -1184,16 +1184,11 @@ static int cci_pmu_add(struct perf_event *event, int flags)
 	struct cci_pmu_hw_events *hw_events = &cci_pmu->hw_events;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx;
-	int err = 0;
-
-	perf_pmu_disable(event->pmu);
 
 	/* If we don't have a space for the counter then finish early. */
 	idx = pmu_get_event_idx(hw_events, event);
-	if (idx < 0) {
+	if (idx < 0)
-		err = idx;
+		return idx;
-		goto out;
-	}
 
 	event->hw.idx = idx;
 	hw_events->events[idx] = event;
@@ -1205,9 +1200,7 @@ static int cci_pmu_add(struct perf_event *event, int flags)
 	/* Propagate our changes to the userspace mapping. */
 	perf_event_update_userpage(event);
 
-out:
+	return 0;
-	perf_pmu_enable(event->pmu);
-	return err;
 }
 
 static void cci_pmu_del(struct perf_event *event, int flags)
@@ -1304,15 +1297,6 @@ static int __hw_perf_event_init(struct perf_event *event)
 	 */
 	hwc->config_base	    |= (unsigned long)mapping;
 
-	/*
-	 * Limit the sample_period to half of the counter width. That way, the
-	 * new counter value is far less likely to overtake the previous one
-	 * unless you have some serious IRQ latency issues.
-	 */
-	hwc->sample_period  = CCI_PMU_CNTR_MASK >> 1;
-	hwc->last_period    = hwc->sample_period;
-	local64_set(&hwc->period_left, hwc->sample_period);
-
 	if (event->group_leader != event) {
 		if (validate_group(event) != 0)
 			return -EINVAL;
@@ -1423,6 +1407,7 @@ static int cci_pmu_init(struct cci_pmu *cci_pmu, struct platform_device *pdev)
 	pmu_format_attr_group.attrs = model->format_attrs;
 
 	cci_pmu->pmu = (struct pmu) {
+		.module		= THIS_MODULE,
 		.name		= cci_pmu->model->name,
 		.task_ctx_nr	= perf_invalid_context,
 		.pmu_enable	= cci_pmu_enable,
@@ -1466,7 +1451,7 @@ static int cci_pmu_offline_cpu(unsigned int cpu)
 	return 0;
 }
 
-static struct cci_pmu_model cci_pmu_models[] = {
+static __maybe_unused struct cci_pmu_model cci_pmu_models[] = {
 #ifdef CONFIG_ARM_CCI400_PMU
 	[CCI400_R0] = {
 		.name = "CCI_400",
@@ -1588,6 +1573,7 @@ static const struct of_device_id arm_cci_pmu_matches[] = {
 #endif
 	{},
 };
+MODULE_DEVICE_TABLE(of, arm_cci_pmu_matches);
 
 static bool is_duplicate_irq(int irq, int *irqs, int nr_irqs)
 {
@@ -1709,14 +1695,27 @@ static int cci_pmu_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static int cci_pmu_remove(struct platform_device *pdev)
+{
+	if (!g_cci_pmu)
+		return 0;
+
+	cpuhp_remove_state(CPUHP_AP_PERF_ARM_CCI_ONLINE);
+	perf_pmu_unregister(&g_cci_pmu->pmu);
+	g_cci_pmu = NULL;
+
+	return 0;
+}
+
 static struct platform_driver cci_pmu_driver = {
 	.driver = {
 		   .name = DRIVER_NAME,
 		   .of_match_table = arm_cci_pmu_matches,
 		  },
 	.probe = cci_pmu_probe,
+	.remove = cci_pmu_remove,
 };
 
-builtin_platform_driver(cci_pmu_driver);
+module_platform_driver(cci_pmu_driver);
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("ARM CCI PMU support");

drivers/perf/arm-ccn.c

@@ -736,7 +736,7 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 	ccn = pmu_to_arm_ccn(event->pmu);
 
 	if (hw->sample_period) {
-		dev_warn(ccn->dev, "Sampling not supported!\n");
+		dev_dbg(ccn->dev, "Sampling not supported!\n");
 		return -EOPNOTSUPP;
 	}
 
@@ -744,12 +744,12 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 			event->attr.exclude_kernel || event->attr.exclude_hv ||
 			event->attr.exclude_idle || event->attr.exclude_host ||
 			event->attr.exclude_guest) {
-		dev_warn(ccn->dev, "Can't exclude execution levels!\n");
+		dev_dbg(ccn->dev, "Can't exclude execution levels!\n");
 		return -EINVAL;
 	}
 
 	if (event->cpu < 0) {
-		dev_warn(ccn->dev, "Can't provide per-task data!\n");
+		dev_dbg(ccn->dev, "Can't provide per-task data!\n");
 		return -EOPNOTSUPP;
 	}
 	/*
@@ -771,13 +771,13 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 	switch (type) {
 	case CCN_TYPE_MN:
 		if (node_xp != ccn->mn_id) {
-			dev_warn(ccn->dev, "Invalid MN ID %d!\n", node_xp);
+			dev_dbg(ccn->dev, "Invalid MN ID %d!\n", node_xp);
 			return -EINVAL;
 		}
 		break;
 	case CCN_TYPE_XP:
 		if (node_xp >= ccn->num_xps) {
-			dev_warn(ccn->dev, "Invalid XP ID %d!\n", node_xp);
+			dev_dbg(ccn->dev, "Invalid XP ID %d!\n", node_xp);
 			return -EINVAL;
 		}
 		break;
@@ -785,11 +785,11 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 		break;
 	default:
 		if (node_xp >= ccn->num_nodes) {
-			dev_warn(ccn->dev, "Invalid node ID %d!\n", node_xp);
+			dev_dbg(ccn->dev, "Invalid node ID %d!\n", node_xp);
 			return -EINVAL;
 		}
 		if (!arm_ccn_pmu_type_eq(type, ccn->node[node_xp].type)) {
-			dev_warn(ccn->dev, "Invalid type 0x%x for node %d!\n",
+			dev_dbg(ccn->dev, "Invalid type 0x%x for node %d!\n",
 					type, node_xp);
 			return -EINVAL;
 		}
@@ -808,19 +808,19 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 		if (event_id != e->event)
 			continue;
 		if (e->num_ports && port >= e->num_ports) {
-			dev_warn(ccn->dev, "Invalid port %d for node/XP %d!\n",
+			dev_dbg(ccn->dev, "Invalid port %d for node/XP %d!\n",
 					port, node_xp);
 			return -EINVAL;
 		}
 		if (e->num_vcs && vc >= e->num_vcs) {
-			dev_warn(ccn->dev, "Invalid vc %d for node/XP %d!\n",
+			dev_dbg(ccn->dev, "Invalid vc %d for node/XP %d!\n",
 					vc, node_xp);
 			return -EINVAL;
 		}
 		valid = 1;
 	}
 	if (!valid) {
-		dev_warn(ccn->dev, "Invalid event 0x%x for node/XP %d!\n",
+		dev_dbg(ccn->dev, "Invalid event 0x%x for node/XP %d!\n",
 				event_id, node_xp);
 		return -EINVAL;
 	}
@@ -1594,4 +1594,4 @@ module_init(arm_ccn_init);
 module_exit(arm_ccn_exit);
 
 MODULE_AUTHOR("Pawel Moll <pawel.moll@arm.com>");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");

drivers/perf/arm_pmu.c

@@ -339,7 +339,7 @@ static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
 		return IRQ_NONE;
 
 	start_clock = sched_clock();
-	ret = armpmu->handle_irq(irq, armpmu);
+	ret = armpmu->handle_irq(armpmu);
 	finish_clock = sched_clock();
 
 	perf_sample_event_took(finish_clock - start_clock);

drivers/perf/arm_spe_pmu.c

@@ -131,8 +131,7 @@ static ssize_t arm_spe_pmu_cap_show(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
 {
-	struct platform_device *pdev = to_platform_device(dev);
+	struct arm_spe_pmu *spe_pmu = dev_get_drvdata(dev);
-	struct arm_spe_pmu *spe_pmu = platform_get_drvdata(pdev);
 	struct dev_ext_attribute *ea =
 		container_of(attr, struct dev_ext_attribute, attr);
 	int cap = (long)ea->var;
@@ -247,8 +246,7 @@ static ssize_t arm_spe_pmu_get_attr_cpumask(struct device *dev,
 					    struct device_attribute *attr,
 					    char *buf)
 {
-	struct platform_device *pdev = to_platform_device(dev);
+	struct arm_spe_pmu *spe_pmu = dev_get_drvdata(dev);
-	struct arm_spe_pmu *spe_pmu = platform_get_drvdata(pdev);
 
 	return cpumap_print_to_pagebuf(true, buf, &spe_pmu->supported_cpus);
 }

include/linux/acpi.h

@@ -1299,4 +1299,23 @@ static inline int lpit_read_residency_count_address(u64 *address)
 }
 #endif
 
+#ifdef CONFIG_ACPI_PPTT
+int find_acpi_cpu_topology(unsigned int cpu, int level);
+int find_acpi_cpu_topology_package(unsigned int cpu);
+int find_acpi_cpu_cache_topology(unsigned int cpu, int level);
+#else
+static inline int find_acpi_cpu_topology(unsigned int cpu, int level)
+{
+	return -EINVAL;
+}
+static inline int find_acpi_cpu_topology_package(unsigned int cpu)
+{
+	return -EINVAL;
+}
+static inline int find_acpi_cpu_cache_topology(unsigned int cpu, int level)
+{
+	return -EINVAL;
+}
+#endif
+
 #endif	/*_LINUX_ACPI_H*/

include/linux/arm-smccc.h

@@ -80,6 +80,11 @@
 			   ARM_SMCCC_SMC_32,				\
 			   0, 0x8000)
 
+#define ARM_SMCCC_ARCH_WORKAROUND_2					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_32,				\
+			   0, 0x7fff)
+
 #ifndef __ASSEMBLY__
 
 #include <linux/linkage.h>
@@ -291,5 +296,10 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
  */
 #define arm_smccc_1_1_hvc(...)	__arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__)
 
+/* Return codes defined in ARM DEN 0070A */
+#define SMCCC_RET_SUCCESS			0
+#define SMCCC_RET_NOT_SUPPORTED			-1
+#define SMCCC_RET_NOT_REQUIRED			-2
+
 #endif /*__ASSEMBLY__*/
 #endif /*__LINUX_ARM_SMCCC_H*/

include/linux/cacheinfo.h

@@ -34,9 +34,8 @@ enum cache_type {
  * @shared_cpu_map: logical cpumask representing all the cpus sharing
  *	this cache node
  * @attributes: bitfield representing various cache attributes
- * @of_node: if devicetree is used, this represents either the cpu node in
+ * @fw_token: Unique value used to determine if different cacheinfo
- *	case there's no explicit cache node or the cache node itself in the
+ *	structures represent a single hardware cache instance.
- *	device tree
  * @disable_sysfs: indicates whether this node is visible to the user via
  *	sysfs or not
  * @priv: pointer to any private data structure specific to particular
@@ -65,8 +64,7 @@ struct cacheinfo {
 #define CACHE_ALLOCATE_POLICY_MASK	\
 	(CACHE_READ_ALLOCATE | CACHE_WRITE_ALLOCATE)
 #define CACHE_ID		BIT(4)
-
+	void *fw_token;
-	struct device_node *of_node;
 	bool disable_sysfs;
 	void *priv;
 };
@@ -99,6 +97,23 @@ int func(unsigned int cpu)					\
 struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu);
 int init_cache_level(unsigned int cpu);
 int populate_cache_leaves(unsigned int cpu);
+int cache_setup_acpi(unsigned int cpu);
+#ifndef CONFIG_ACPI_PPTT
+/*
+ * acpi_find_last_cache_level is only called on ACPI enabled
+ * platforms using the PPTT for topology. This means that if
+ * the platform supports other firmware configuration methods
+ * we need to stub out the call when ACPI is disabled.
+ * ACPI enabled platforms not using PPTT won't be making calls
+ * to this function so we need not worry about them.
+ */
+static inline int acpi_find_last_cache_level(unsigned int cpu)
+{
+	return 0;
+}
+#else
+int acpi_find_last_cache_level(unsigned int cpu);
+#endif
 
 const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf);
 

include/linux/perf/arm_pmu.h

@@ -78,7 +78,7 @@ struct arm_pmu {
 	struct pmu	pmu;
 	cpumask_t	supported_cpus;
 	char		*name;
-	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
+	irqreturn_t	(*handle_irq)(struct arm_pmu *pmu);
 	void		(*enable)(struct perf_event *event);
 	void		(*disable)(struct perf_event *event);
 	int		(*get_event_idx)(struct pmu_hw_events *hw_events,

virt/kvm/arm/arm.c

@@ -1490,6 +1490,10 @@ static int init_hyp_mode(void)
 		}
 	}
 
+	err = hyp_map_aux_data();
+	if (err)
+		kvm_err("Cannot map host auxilary data: %d\n", err);
+
 	return 0;
 
 out_err:

virt/kvm/arm/psci.c

@@ -405,7 +405,7 @@ static int kvm_psci_call(struct kvm_vcpu *vcpu)
 int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 {
 	u32 func_id = smccc_get_function(vcpu);
-	u32 val = PSCI_RET_NOT_SUPPORTED;
+	u32 val = SMCCC_RET_NOT_SUPPORTED;
 	u32 feature;
 
 	switch (func_id) {
@@ -417,7 +417,21 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 		switch(feature) {
 		case ARM_SMCCC_ARCH_WORKAROUND_1:
 			if (kvm_arm_harden_branch_predictor())
-				val = 0;
+				val = SMCCC_RET_SUCCESS;
+			break;
+		case ARM_SMCCC_ARCH_WORKAROUND_2:
+			switch (kvm_arm_have_ssbd()) {
+			case KVM_SSBD_FORCE_DISABLE:
+			case KVM_SSBD_UNKNOWN:
+				break;
+			case KVM_SSBD_KERNEL:
+				val = SMCCC_RET_SUCCESS;
+				break;
+			case KVM_SSBD_FORCE_ENABLE:
+			case KVM_SSBD_MITIGATED:
+				val = SMCCC_RET_NOT_REQUIRED;
+				break;
+			}
 			break;
 		}
 		break;