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

Pull arm64 updates from Will Deacon:
 "The headline feature is the re-enablement of support for Arm's
  Scalable Matrix Extension (SME) thanks to a bumper crop of fixes
  from Mark Rutland.

  If matrices aren't your thing, then Ryan's page-table optimisation
  work is much more interesting.

  Summary:

  ACPI, EFI and PSCI:

   - Decouple Arm's "Software Delegated Exception Interface" (SDEI)
     support from the ACPI GHES code so that it can be used by platforms
     booted with device-tree

   - Remove unnecessary per-CPU tracking of the FPSIMD state across EFI
     runtime calls

   - Fix a node refcount imbalance in the PSCI device-tree code

  CPU Features:

   - Ensure register sanitisation is applied to fields in ID_AA64MMFR4

   - Expose AIDR_EL1 to userspace via sysfs, primarily so that KVM
     guests can reliably query the underlying CPU types from the VMM

   - Re-enabling of SME support (CONFIG_ARM64_SME) as a result of fixes
     to our context-switching, signal handling and ptrace code

  Entry code:

   - Hook up TIF_NEED_RESCHED_LAZY so that CONFIG_PREEMPT_LAZY can be
     selected

  Memory management:

   - Prevent BSS exports from being used by the early PI code

   - Propagate level and stride information to the low-level TLB
     invalidation routines when operating on hugetlb entries

   - Use the page-table contiguous hint for vmap() mappings with
     VM_ALLOW_HUGE_VMAP where possible

   - Optimise vmalloc()/vmap() page-table updates to use "lazy MMU mode"
     and hook this up on arm64 so that the trailing DSB (used to publish
     the updates to the hardware walker) can be deferred until the end
     of the mapping operation

   - Extend mmap() randomisation for 52-bit virtual addresses (on par
     with 48-bit addressing) and remove limited support for
     randomisation of the linear map

  Perf and PMUs:

   - Add support for probing the CMN-S3 driver using ACPI

   - Minor driver fixes to the CMN, Arm-NI and amlogic PMU drivers

  Selftests:

   - Fix FPSIMD and SME tests to align with the freshly re-enabled SME
     support

   - Fix default setting of the OUTPUT variable so that tests are
     installed in the right location

  vDSO:

   - Replace raw counter access from inline assembly code with a call to
     the the __arch_counter_get_cntvct() helper function

  Miscellaneous:

   - Add some missing header inclusions to the CCA headers

   - Rework rendering of /proc/cpuinfo to follow the x86-approach and
     avoid repeated buffer expansion (the user-visible format remains
     identical)

   - Remove redundant selection of CONFIG_CRC32

   - Extend early error message when failing to map the device-tree
     blob"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (83 commits)
  arm64: cputype: Add cputype definition for HIP12
  arm64: el2_setup.h: Make __init_el2_fgt labels consistent, again
  perf/arm-cmn: Add CMN S3 ACPI binding
  arm64/boot: Disallow BSS exports to startup code
  arm64/boot: Move global CPU override variables out of BSS
  arm64/boot: Move init_pgdir[] and init_idmap_pgdir[] into __pi_ namespace
  perf/arm-cmn: Initialise cmn->cpu earlier
  kselftest/arm64: Set default OUTPUT path when undefined
  arm64: Update comment regarding values in __boot_cpu_mode
  arm64: mm: Drop redundant check in pmd_trans_huge()
  arm64/mm: Re-organise setting up FEAT_S1PIE registers PIRE0_EL1 and PIR_EL1
  arm64/mm: Permit lazy_mmu_mode to be nested
  arm64/mm: Disable barrier batching in interrupt contexts
  arm64/cpuinfo: only show one cpu's info in c_show()
  arm64/mm: Batch barriers when updating kernel mappings
  mm/vmalloc: Enter lazy mmu mode while manipulating vmalloc ptes
  arm64/mm: Support huge pte-mapped pages in vmap
  mm/vmalloc: Gracefully unmap huge ptes
  mm/vmalloc: Warn on improper use of vunmap_range()
  arm64/mm: Hoist barriers out of set_ptes_anysz() loop
  ...

Author: torvalds

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -544,6 +544,7 @@ What:		/sys/devices/system/cpu/cpuX/regs/
 		/sys/devices/system/cpu/cpuX/regs/identification/
 		/sys/devices/system/cpu/cpuX/regs/identification/midr_el1
 		/sys/devices/system/cpu/cpuX/regs/identification/revidr_el1
+		/sys/devices/system/cpu/cpuX/regs/identification/aidr_el1
 		/sys/devices/system/cpu/cpuX/regs/identification/smidr_el1
 Date:		June 2016
 Contact:	Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org>

Documentation/arch/arm64/cpu-feature-registers.rst

@@ -72,14 +72,15 @@ there are some issues with their usage.
     process could be migrated to another CPU by the time it uses the
     register value, unless the CPU affinity is set. Hence, there is no
     guarantee that the value reflects the processor that it is
-    currently executing on. The REVIDR is not exposed due to this
-    constraint, as REVIDR makes sense only in conjunction with the
-    MIDR. Alternately, MIDR_EL1 and REVIDR_EL1 are exposed via sysfs
-    at::
+    currently executing on. REVIDR and AIDR are not exposed due to this
+    constraint, as these registers only make sense in conjunction with
+    the MIDR. Alternately, MIDR_EL1, REVIDR_EL1, and AIDR_EL1 are exposed
+    via sysfs at::
 
 	/sys/devices/system/cpu/cpu$ID/regs/identification/
-	                                              \- midr
-	                                              \- revidr
+	                                              \- midr_el1
+	                                              \- revidr_el1
+	                                              \- aidr_el1
 
 3. Implementation
 --------------------

Documentation/arch/arm64/sme.rst

@@ -69,8 +69,8 @@ model features for SME is included in Appendix A.
   vectors from 0 to VL/8-1 stored in the same endianness invariant format as is
   used for SVE vectors.
 
-* On thread creation TPIDR2_EL0 is preserved unless CLONE_SETTLS is specified,
-  in which case it is set to 0.
+* On thread creation PSTATE.ZA and TPIDR2_EL0 are preserved unless CLONE_VM
+  is specified, in which case PSTATE.ZA is set to 0 and TPIDR2_EL0 is set to 0.
 
 2.  Vector lengths
 ------------------
@@ -115,7 +115,7 @@ be zeroed.
 5.  Signal handling
 -------------------
 
-* Signal handlers are invoked with streaming mode and ZA disabled.
+* Signal handlers are invoked with PSTATE.SM=0, PSTATE.ZA=0, and TPIDR2_EL0=0.
 
 * A new signal frame record TPIDR2_MAGIC is added formatted as a struct
   tpidr2_context to allow access to TPIDR2_EL0 from signal handlers.
@@ -241,7 +241,7 @@ prctl(PR_SME_SET_VL, unsigned long arg)
       length, or calling PR_SME_SET_VL with the PR_SME_SET_VL_ONEXEC flag,
       does not constitute a change to the vector length for this purpose.
 
-    * Changing the vector length causes PSTATE.ZA and PSTATE.SM to be cleared.
+    * Changing the vector length causes PSTATE.ZA to be cleared.
       Calling PR_SME_SET_VL with vl equal to the thread's current vector
       length, or calling PR_SME_SET_VL with the PR_SME_SET_VL_ONEXEC flag,
       does not constitute a change to the vector length for this purpose.

arch/arm64/Kconfig

@@ -42,6 +42,7 @@ config ARM64
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_NONLEAF_PMD_YOUNG if ARM64_HAFT
+	select ARCH_HAS_PREEMPT_LAZY
 	select ARCH_HAS_PTDUMP
 	select ARCH_HAS_PTE_DEVMAP
 	select ARCH_HAS_PTE_SPECIAL
@@ -134,7 +135,6 @@ config ARM64
 	select COMMON_CLK
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select CPUMASK_OFFSTACK if NR_CPUS > 256
-	select CRC32
 	select DCACHE_WORD_ACCESS
 	select DYNAMIC_FTRACE if FUNCTION_TRACER
 	select DMA_BOUNCE_UNALIGNED_KMALLOC
@@ -333,9 +333,9 @@ config ARCH_MMAP_RND_BITS_MAX
 	default 24 if ARM64_VA_BITS=39
 	default 27 if ARM64_VA_BITS=42
 	default 30 if ARM64_VA_BITS=47
-	default 29 if ARM64_VA_BITS=48 && ARM64_64K_PAGES
-	default 31 if ARM64_VA_BITS=48 && ARM64_16K_PAGES
-	default 33 if ARM64_VA_BITS=48
+	default 29 if (ARM64_VA_BITS=48 || ARM64_VA_BITS=52) && ARM64_64K_PAGES
+	default 31 if (ARM64_VA_BITS=48 || ARM64_VA_BITS=52) && ARM64_16K_PAGES
+	default 33 if (ARM64_VA_BITS=48 || ARM64_VA_BITS=52)
 	default 14 if ARM64_64K_PAGES
 	default 16 if ARM64_16K_PAGES
 	default 18
@@ -2285,7 +2285,6 @@ config ARM64_SME
 	bool "ARM Scalable Matrix Extension support"
 	default y
 	depends on ARM64_SVE
-	depends on BROKEN
 	help
 	  The Scalable Matrix Extension (SME) is an extension to the AArch64
 	  execution state which utilises a substantial subset of the SVE

arch/arm64/include/asm/cpu.h

@@ -44,6 +44,7 @@ struct cpuinfo_arm64 {
 	u64		reg_dczid;
 	u64		reg_midr;
 	u64		reg_revidr;
+	u64		reg_aidr;
 	u64		reg_gmid;
 	u64		reg_smidr;
 	u64		reg_mpamidr;

arch/arm64/include/asm/cputype.h

@@ -134,6 +134,7 @@
 
 #define HISI_CPU_PART_TSV110		0xD01
 #define HISI_CPU_PART_HIP09			0xD02
+#define HISI_CPU_PART_HIP12		0xD06
 
 #define APPLE_CPU_PART_M1_ICESTORM	0x022
 #define APPLE_CPU_PART_M1_FIRESTORM	0x023
@@ -222,6 +223,7 @@
 #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)
 #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110)
 #define MIDR_HISI_HIP09 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP09)
+#define MIDR_HISI_HIP12 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP12)
 #define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM)
 #define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM)
 #define MIDR_APPLE_M1_ICESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_PRO)

arch/arm64/include/asm/el2_setup.h

@@ -204,19 +204,21 @@
 	orr	x0, x0, #(1 << 62)
 
 .Lskip_spe_fgt_\@:
+
+.Lset_debug_fgt_\@:
 	msr_s	SYS_HDFGRTR_EL2, x0
 	msr_s	SYS_HDFGWTR_EL2, x0
 
 	mov	x0, xzr
 	mrs	x1, id_aa64pfr1_el1
 	ubfx	x1, x1, #ID_AA64PFR1_EL1_SME_SHIFT, #4
-	cbz	x1, .Lskip_debug_fgt_\@
+	cbz	x1, .Lskip_sme_fgt_\@
 
 	/* Disable nVHE traps of TPIDR2 and SMPRI */
 	orr	x0, x0, #HFGxTR_EL2_nSMPRI_EL1_MASK
 	orr	x0, x0, #HFGxTR_EL2_nTPIDR2_EL0_MASK
 
-.Lskip_debug_fgt_\@:
+.Lskip_sme_fgt_\@:
 	mrs_s	x1, SYS_ID_AA64MMFR3_EL1
 	ubfx	x1, x1, #ID_AA64MMFR3_EL1_S1PIE_SHIFT, #4
 	cbz	x1, .Lskip_pie_fgt_\@
@@ -237,12 +239,14 @@
 	/* GCS depends on PIE so we don't check it if PIE is absent */
 	mrs_s	x1, SYS_ID_AA64PFR1_EL1
 	ubfx	x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4
-	cbz	x1, .Lset_fgt_\@
+	cbz	x1, .Lskip_gce_fgt_\@
 
 	/* Disable traps of access to GCS registers at EL0 and EL1 */
 	orr	x0, x0, #HFGxTR_EL2_nGCS_EL1_MASK
 	orr	x0, x0, #HFGxTR_EL2_nGCS_EL0_MASK
 
+.Lskip_gce_fgt_\@:
+
 .Lset_fgt_\@:
 	msr_s	SYS_HFGRTR_EL2, x0
 	msr_s	SYS_HFGWTR_EL2, x0

arch/arm64/include/asm/esr.h

@@ -378,12 +378,14 @@
 /*
  * ISS values for SME traps
  */
-
-#define ESR_ELx_SME_ISS_SME_DISABLED	0
-#define ESR_ELx_SME_ISS_ILL		1
-#define ESR_ELx_SME_ISS_SM_DISABLED	2
-#define ESR_ELx_SME_ISS_ZA_DISABLED	3
-#define ESR_ELx_SME_ISS_ZT_DISABLED	4
+#define ESR_ELx_SME_ISS_SMTC_MASK		GENMASK(2, 0)
+#define ESR_ELx_SME_ISS_SMTC(esr)		((esr) & ESR_ELx_SME_ISS_SMTC_MASK)
+
+#define ESR_ELx_SME_ISS_SMTC_SME_DISABLED	0
+#define ESR_ELx_SME_ISS_SMTC_ILL		1
+#define ESR_ELx_SME_ISS_SMTC_SM_DISABLED	2
+#define ESR_ELx_SME_ISS_SMTC_ZA_DISABLED	3
+#define ESR_ELx_SME_ISS_SMTC_ZT_DISABLED	4
 
 /* ISS field definitions for MOPS exceptions */
 #define ESR_ELx_MOPS_ISS_MEM_INST	(UL(1) << 24)

arch/arm64/include/asm/fpsimd.h

@@ -6,6 +6,7 @@
 #define __ASM_FP_H
 
 #include <asm/errno.h>
+#include <asm/percpu.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
 #include <asm/sigcontext.h>
@@ -76,7 +77,6 @@ extern void fpsimd_load_state(struct user_fpsimd_state *state);
 extern void fpsimd_thread_switch(struct task_struct *next);
 extern void fpsimd_flush_thread(void);
 
-extern void fpsimd_signal_preserve_current_state(void);
 extern void fpsimd_preserve_current_state(void);
 extern void fpsimd_restore_current_state(void);
 extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
@@ -93,9 +93,12 @@ struct cpu_fp_state {
 	enum fp_type to_save;
 };
 
+DECLARE_PER_CPU(struct cpu_fp_state, fpsimd_last_state);
+
 extern void fpsimd_bind_state_to_cpu(struct cpu_fp_state *fp_state);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
+extern void fpsimd_save_and_flush_current_state(void);
 extern void fpsimd_save_and_flush_cpu_state(void);
 
 static inline bool thread_sm_enabled(struct thread_struct *thread)
@@ -108,6 +111,8 @@ static inline bool thread_za_enabled(struct thread_struct *thread)
 	return system_supports_sme() && (thread->svcr & SVCR_ZA_MASK);
 }
 
+extern void task_smstop_sm(struct task_struct *task);
+
 /* Maximum VL that SVE/SME VL-agnostic software can transparently support */
 #define VL_ARCH_MAX 0x100
 
@@ -195,10 +200,8 @@ struct vl_info {
 
 extern void sve_alloc(struct task_struct *task, bool flush);
 extern void fpsimd_release_task(struct task_struct *task);
-extern void fpsimd_sync_to_sve(struct task_struct *task);
-extern void fpsimd_force_sync_to_sve(struct task_struct *task);
-extern void sve_sync_to_fpsimd(struct task_struct *task);
-extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task);
+extern void fpsimd_sync_from_effective_state(struct task_struct *task);
+extern void fpsimd_sync_to_effective_state_zeropad(struct task_struct *task);
 
 extern int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 				 unsigned long vl, unsigned long flags);
@@ -292,14 +295,29 @@ static inline bool sve_vq_available(unsigned int vq)
 	return vq_available(ARM64_VEC_SVE, vq);
 }
 
-size_t sve_state_size(struct task_struct const *task);
+static inline size_t __sve_state_size(unsigned int sve_vl, unsigned int sme_vl)
+{
+	unsigned int vl = max(sve_vl, sme_vl);
+	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl));
+}
+
+/*
+ * Return how many bytes of memory are required to store the full SVE
+ * state for task, given task's currently configured vector length.
+ */
+static inline size_t sve_state_size(struct task_struct const *task)
+{
+	unsigned int sve_vl = task_get_sve_vl(task);
+	unsigned int sme_vl = task_get_sme_vl(task);
+	return __sve_state_size(sve_vl, sme_vl);
+}
 
 #else /* ! CONFIG_ARM64_SVE */
 
 static inline void sve_alloc(struct task_struct *task, bool flush) { }
 static inline void fpsimd_release_task(struct task_struct *task) { }
-static inline void sve_sync_to_fpsimd(struct task_struct *task) { }
-static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { }
+static inline void fpsimd_sync_from_effective_state(struct task_struct *task) { }
+static inline void fpsimd_sync_to_effective_state_zeropad(struct task_struct *task) { }
 
 static inline int sve_max_virtualisable_vl(void)
 {
@@ -333,6 +351,11 @@ static inline void vec_update_vq_map(enum vec_type t) { }
 static inline int vec_verify_vq_map(enum vec_type t) { return 0; }
 static inline void sve_setup(void) { }
 
+static inline size_t __sve_state_size(unsigned int sve_vl, unsigned int sme_vl)
+{
+	return 0;
+}
+
 static inline size_t sve_state_size(struct task_struct const *task)
 {
 	return 0;
@@ -385,22 +408,24 @@ extern int sme_set_current_vl(unsigned long arg);
 extern int sme_get_current_vl(void);
 extern void sme_suspend_exit(void);
 
+static inline size_t __sme_state_size(unsigned int sme_vl)
+{
+	size_t size = ZA_SIG_REGS_SIZE(sve_vq_from_vl(sme_vl));
+
+	if (system_supports_sme2())
+		size += ZT_SIG_REG_SIZE;
+
+	return size;
+}
+
 /*
  * Return how many bytes of memory are required to store the full SME
  * specific state for task, given task's currently configured vector
  * length.
  */
 static inline size_t sme_state_size(struct task_struct const *task)
 {
-	unsigned int vl = task_get_sme_vl(task);
-	size_t size;
-
-	size = ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl));
-
-	if (system_supports_sme2())
-		size += ZT_SIG_REG_SIZE;
-
-	return size;
+	return __sme_state_size(task_get_sme_vl(task));
 }
 
 #else
@@ -421,6 +446,11 @@ static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; }
 static inline int sme_get_current_vl(void) { return -EINVAL; }
 static inline void sme_suspend_exit(void) { }
 
+static inline size_t __sme_state_size(unsigned int sme_vl)
+{
+	return 0;
+}
+
 static inline size_t sme_state_size(struct task_struct const *task)
 {
 	return 0;

arch/arm64/include/asm/hugetlb.h

@@ -69,29 +69,38 @@ extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 
 #include <asm-generic/hugetlb.h>
 
-#define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
-static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma,
-					   unsigned long start,
-					   unsigned long end)
+static inline void __flush_hugetlb_tlb_range(struct vm_area_struct *vma,
+					     unsigned long start,
+					     unsigned long end,
+					     unsigned long stride,
+					     bool last_level)
 {
-	unsigned long stride = huge_page_size(hstate_vma(vma));
-
 	switch (stride) {
 #ifndef __PAGETABLE_PMD_FOLDED
 	case PUD_SIZE:
-		__flush_tlb_range(vma, start, end, PUD_SIZE, false, 1);
+		__flush_tlb_range(vma, start, end, PUD_SIZE, last_level, 1);
 		break;
 #endif
 	case CONT_PMD_SIZE:
 	case PMD_SIZE:
-		__flush_tlb_range(vma, start, end, PMD_SIZE, false, 2);
+		__flush_tlb_range(vma, start, end, PMD_SIZE, last_level, 2);
 		break;
 	case CONT_PTE_SIZE:
-		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 3);
+		__flush_tlb_range(vma, start, end, PAGE_SIZE, last_level, 3);
 		break;
 	default:
-		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, TLBI_TTL_UNKNOWN);
+		__flush_tlb_range(vma, start, end, PAGE_SIZE, last_level, TLBI_TTL_UNKNOWN);
 	}
 }
 
+#define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
+static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma,
+					   unsigned long start,
+					   unsigned long end)
+{
+	unsigned long stride = huge_page_size(hstate_vma(vma));
+
+	__flush_hugetlb_tlb_range(vma, start, end, stride, false);
+}
+
 #endif /* __ASM_HUGETLB_H */