Merge branches 'for-next/sve-remove-pseudo-regs', 'for-next/backtrace-ipi', 'for-next/kselftest', 'for-next/misc' and 'for-next/cpufeat-display-cores', remote-tracking branch 'arm64/for-next/perf' into for-next/core

* arm64/for-next/perf:
  perf: hisi: Fix use-after-free when register pmu fails
  drivers/perf: hisi_pcie: Initialize event->cpu only on success
  drivers/perf: hisi_pcie: Check the type first in pmu::event_init()
  perf/arm-cmn: Enable per-DTC counter allocation
  perf/arm-cmn: Rework DTC counters (again)
  perf/arm-cmn: Fix DTC domain detection
  drivers: perf: arm_pmuv3: Drop some unused arguments from armv8_pmu_init()
  drivers: perf: arm_pmuv3: Read PMMIR_EL1 unconditionally
  drivers/perf: hisi: use cpuhp_state_remove_instance_nocalls() for hisi_hns3_pmu uninit process
  drivers/perf: xgene: Use device_get_match_data()
  perf/amlogic: add missing MODULE_DEVICE_TABLE
  docs/perf: Add ampere_cspmu to toctree to fix a build warning
  perf: arm_cspmu: ampere_cspmu: Add support for Ampere SoC PMU
  perf: arm_cspmu: Support implementation specific validation
  perf: arm_cspmu: Support implementation specific filters
  perf: arm_cspmu: Split 64-bit write to 32-bit writes
  perf: arm_cspmu: Separate Arm and vendor module

* for-next/sve-remove-pseudo-regs:
  : arm64/fpsimd: Remove the vector length pseudo registers
  arm64/sve: Remove SMCR pseudo register from cpufeature code
  arm64/sve: Remove ZCR pseudo register from cpufeature code

* for-next/backtrace-ipi:
  : Add IPI for backtraces/kgdb, use NMI
  arm64: smp: Don't directly call arch_smp_send_reschedule() for wakeup
  arm64: smp: avoid NMI IPIs with broken MediaTek FW
  arm64: smp: Mark IPI globals as __ro_after_init
  arm64: kgdb: Implement kgdb_roundup_cpus() to enable pseudo-NMI roundup
  arm64: smp: IPI_CPU_STOP and IPI_CPU_CRASH_STOP should try for NMI
  arm64: smp: Add arch support for backtrace using pseudo-NMI
  arm64: smp: Remove dedicated wakeup IPI
  arm64: idle: Tag the arm64 idle functions as __cpuidle
  irqchip/gic-v3: Enable support for SGIs to act as NMIs

* for-next/kselftest:
  : Various arm64 kselftest updates
  kselftest/arm64: Validate SVCR in streaming SVE stress test

* for-next/misc:
  : Miscellaneous patches
  arm64: Restrict CPU_BIG_ENDIAN to GNU as or LLVM IAS 15.x or newer
  arm64: module: Fix PLT counting when CONFIG_RANDOMIZE_BASE=n
  arm64, irqchip/gic-v3, ACPI: Move MADT GICC enabled check into a helper
  clocksource/drivers/arm_arch_timer: limit XGene-1 workaround
  arm64: Remove system_uses_lse_atomics()
  arm64: Mark the 'addr' argument to set_ptes() and __set_pte_at() as unused
  arm64/mm: Hoist synchronization out of set_ptes() loop
  arm64: swiotlb: Reduce the default size if no ZONE_DMA bouncing needed

* for-next/cpufeat-display-cores:
  : arm64 cpufeature display enabled cores
  arm64: cpufeature: Change DBM to display enabled cores
  arm64: cpufeature: Display the set of cores with a feature

Author: ctmarinas

arch/arm64/Kconfig

@@ -1355,6 +1355,8 @@ choice
 config CPU_BIG_ENDIAN
 	bool "Build big-endian kernel"
 	depends on !LD_IS_LLD || LLD_VERSION >= 130000
+	# https://github.com/llvm/llvm-project/commit/1379b150991f70a5782e9a143c2ba5308da1161c
+	depends on AS_IS_GNU || AS_VERSION >= 150000
 	help
 	  Say Y if you plan on running a kernel with a big-endian userspace.
 

arch/arm64/include/asm/cpu.h

@@ -63,12 +63,6 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64smfr0;
 
 	struct cpuinfo_32bit	aarch32;
-
-	/* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */
-	u64		reg_zcr;
-
-	/* pseudo-SMCR for recording maximum SMCR_EL1 LEN value: */
-	u64		reg_smcr;
 };
 
 DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);

arch/arm64/include/asm/cpufeature.h

@@ -23,6 +23,7 @@
 #include <linux/bug.h>
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
+#include <linux/cpumask.h>
 
 /*
  * CPU feature register tracking
@@ -380,6 +381,7 @@ struct arm64_cpu_capabilities {
 	 * method is robust against being called multiple times.
 	 */
 	const struct arm64_cpu_capabilities *match_list;
+	const struct cpumask *cpus;
 };
 
 static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap)

arch/arm64/include/asm/cputype.h

@@ -85,7 +85,8 @@
 #define ARM_CPU_PART_NEOVERSE_N2	0xD49
 #define ARM_CPU_PART_CORTEX_A78C	0xD4B
 
-#define APM_CPU_PART_POTENZA		0x000
+#define APM_CPU_PART_XGENE		0x000
+#define APM_CPU_VAR_POTENZA		0x00
 
 #define CAVIUM_CPU_PART_THUNDERX	0x0A1
 #define CAVIUM_CPU_PART_THUNDERX_81XX	0x0A2

arch/arm64/include/asm/fpsimd.h

@@ -128,7 +128,6 @@ extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused);
 extern void sme2_kernel_enable(const struct arm64_cpu_capabilities *__unused);
 extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused);
 
-extern u64 read_zcr_features(void);
 extern u64 read_smcr_features(void);
 
 /*

arch/arm64/include/asm/irq.h

@@ -6,6 +6,9 @@
 
 #include <asm-generic/irq.h>
 
+void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu);
+#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
+
 struct pt_regs;
 
 int set_handle_irq(void (*handle_irq)(struct pt_regs *));

arch/arm64/include/asm/lse.h

@@ -16,14 +16,9 @@
 #include <asm/atomic_lse.h>
 #include <asm/cpucaps.h>
 
-static __always_inline bool system_uses_lse_atomics(void)
-{
-	return alternative_has_cap_likely(ARM64_HAS_LSE_ATOMICS);
-}
-
 #define __lse_ll_sc_body(op, ...)					\
 ({									\
-	system_uses_lse_atomics() ?					\
+	alternative_has_cap_likely(ARM64_HAS_LSE_ATOMICS) ?		\
 		__lse_##op(__VA_ARGS__) :				\
 		__ll_sc_##op(__VA_ARGS__);				\
 })
@@ -34,8 +29,6 @@ static __always_inline bool system_uses_lse_atomics(void)
 
 #else	/* CONFIG_ARM64_LSE_ATOMICS */
 
-static inline bool system_uses_lse_atomics(void) { return false; }
-
 #define __lse_ll_sc_body(op, ...)		__ll_sc_##op(__VA_ARGS__)
 
 #define ARM64_LSE_ATOMIC_INSN(llsc, lse)	llsc

arch/arm64/include/asm/mte.h

@@ -90,7 +90,7 @@ static inline bool try_page_mte_tagging(struct page *page)
 }
 
 void mte_zero_clear_page_tags(void *addr);
-void mte_sync_tags(pte_t pte);
+void mte_sync_tags(pte_t pte, unsigned int nr_pages);
 void mte_copy_page_tags(void *kto, const void *kfrom);
 void mte_thread_init_user(void);
 void mte_thread_switch(struct task_struct *next);
@@ -122,7 +122,7 @@ static inline bool try_page_mte_tagging(struct page *page)
 static inline void mte_zero_clear_page_tags(void *addr)
 {
 }
-static inline void mte_sync_tags(pte_t pte)
+static inline void mte_sync_tags(pte_t pte, unsigned int nr_pages)
 {
 }
 static inline void mte_copy_page_tags(void *kto, const void *kfrom)

arch/arm64/include/asm/pgtable.h

@@ -325,8 +325,7 @@ static inline void __check_safe_pte_update(struct mm_struct *mm, pte_t *ptep,
 		     __func__, pte_val(old_pte), pte_val(pte));
 }
 
-static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
-				pte_t *ptep, pte_t pte)
+static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages)
 {
 	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
 		__sync_icache_dcache(pte);
@@ -339,24 +338,22 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 */
 	if (system_supports_mte() && pte_access_permitted(pte, false) &&
 	    !pte_special(pte) && pte_tagged(pte))
-		mte_sync_tags(pte);
-
-	__check_safe_pte_update(mm, ptep, pte);
-
-	set_pte(ptep, pte);
+		mte_sync_tags(pte, nr_pages);
 }
 
-static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t pte, unsigned int nr)
+static inline void set_ptes(struct mm_struct *mm,
+			    unsigned long __always_unused addr,
+			    pte_t *ptep, pte_t pte, unsigned int nr)
 {
 	page_table_check_ptes_set(mm, ptep, pte, nr);
+	__sync_cache_and_tags(pte, nr);
 
 	for (;;) {
-		__set_pte_at(mm, addr, ptep, pte);
+		__check_safe_pte_update(mm, ptep, pte);
+		set_pte(ptep, pte);
 		if (--nr == 0)
 			break;
 		ptep++;
-		addr += PAGE_SIZE;
 		pte_val(pte) += PAGE_SIZE;
 	}
 }
@@ -531,18 +528,29 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 #define pud_pfn(pud)		((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
 #define pfn_pud(pfn,prot)	__pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 
+static inline void __set_pte_at(struct mm_struct *mm,
+				unsigned long __always_unused addr,
+				pte_t *ptep, pte_t pte, unsigned int nr)
+{
+	__sync_cache_and_tags(pte, nr);
+	__check_safe_pte_update(mm, ptep, pte);
+	set_pte(ptep, pte);
+}
+
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			      pmd_t *pmdp, pmd_t pmd)
 {
 	page_table_check_pmd_set(mm, pmdp, pmd);
-	return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd));
+	return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd),
+						PMD_SIZE >> PAGE_SHIFT);
 }
 
 static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
 			      pud_t *pudp, pud_t pud)
 {
 	page_table_check_pud_set(mm, pudp, pud);
-	return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud));
+	return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud),
+						PUD_SIZE >> PAGE_SHIFT);
 }
 
 #define __p4d_to_phys(p4d)	__pte_to_phys(p4d_pte(p4d))

arch/arm64/include/asm/smp.h

@@ -89,9 +89,9 @@ extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 #ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
-extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask);
+extern void arch_send_wakeup_ipi(unsigned int cpu);
 #else
-static inline void arch_send_wakeup_ipi_mask(const struct cpumask *mask)
+static inline void arch_send_wakeup_ipi(unsigned int cpu)
 {
 	BUILD_BUG();
 }