Merge branches 'for-next/livepatch', 'for-next/user-contig-bbml2', 'for-next/misc', 'for-next/acpi', 'for-next/debug-entry', 'for-next/feat_mte_tagged_far', 'for-next/kselftest', 'for-next/mdscr-cleanup' and 'for-next/vmap-stack', remote-tracking branch 'arm64/for-next/perf' into for-next/core

* arm64/for-next/perf: (23 commits)
  drivers/perf: hisi: Support PMUs with no interrupt
  drivers/perf: hisi: Relax the event number check of v2 PMUs
  drivers/perf: hisi: Add support for HiSilicon SLLC v3 PMU driver
  drivers/perf: hisi: Use ACPI driver_data to retrieve SLLC PMU information
  drivers/perf: hisi: Add support for HiSilicon DDRC v3 PMU driver
  drivers/perf: hisi: Simplify the probe process for each DDRC version
  perf/arm-ni: Support sharing IRQs within an NI instance
  perf/arm-ni: Consolidate CPU affinity handling
  perf/cxlpmu: Fix typos in cxl_pmu.c comments and documentation
  perf/cxlpmu: Remove unintended newline from IRQ name format string
  perf/cxlpmu: Fix devm_kcalloc() argument order in cxl_pmu_probe()
  perf: arm_spe: Relax period restriction
  perf: arm_pmuv3: Add support for the Branch Record Buffer Extension (BRBE)
  KVM: arm64: nvhe: Disable branch generation in nVHE guests
  arm64: Handle BRBE booting requirements
  arm64/sysreg: Add BRBE registers and fields
  perf/arm: Add missing .suppress_bind_attrs
  perf/arm-cmn: Reduce stack usage during discovery
  perf: imx9_perf: make the read-only array mask static const
  perf/arm-cmn: Broaden module description for wider interconnect support
  ...

* for-next/livepatch:
  : Support for HAVE_LIVEPATCH on arm64
  arm64: Kconfig: Keep selects somewhat alphabetically ordered
  arm64: Implement HAVE_LIVEPATCH
  arm64: stacktrace: Implement arch_stack_walk_reliable()
  arm64: stacktrace: Check kretprobe_find_ret_addr() return value
  arm64/module: Use text-poke API for late relocations.

* for-next/user-contig-bbml2:
  : Optimise the TLBI when folding/unfolding contigous PTEs on hardware with BBML2 and no TLB conflict aborts
  arm64/mm: Elide tlbi in contpte_convert() under BBML2
  iommu/arm: Add BBM Level 2 smmu feature
  arm64: Add BBM Level 2 cpu feature
  arm64: cpufeature: Introduce MATCH_ALL_EARLY_CPUS capability type

* for-next/misc:
  : Miscellaneous arm64 patches
  arm64/gcs: task_gcs_el0_enable() should use passed task
  arm64: signal: Remove ISB when resetting POR_EL0
  arm64/mm: Drop redundant addr increment in set_huge_pte_at()
  arm64: Mark kernel as tainted on SAE and SError panic
  arm64/gcs: Don't call gcs_free() when releasing task_struct
  arm64: fix unnecessary rebuilding when CONFIG_DEBUG_EFI=y
  arm64/mm: Optimize loop to reduce redundant operations of contpte_ptep_get
  arm64: pi: use 'targets' instead of extra-y in Makefile

* for-next/acpi:
  : Various ACPI arm64 changes
  ACPI: Suppress misleading SPCR console message when SPCR table is absent
  ACPI: Return -ENODEV from acpi_parse_spcr() when SPCR support is disabled

* for-next/debug-entry:
  : Simplify the debug exception entry path
  arm64: debug: remove debug exception registration infrastructure
  arm64: debug: split bkpt32 exception entry
  arm64: debug: split brk64 exception entry
  arm64: debug: split hardware watchpoint exception entry
  arm64: debug: split single stepping exception entry
  arm64: debug: refactor reinstall_suspended_bps()
  arm64: debug: split hardware breakpoint exception entry
  arm64: entry: Add entry and exit functions for debug exceptions
  arm64: debug: remove break/step handler registration infrastructure
  arm64: debug: call step handlers statically
  arm64: debug: call software breakpoint handlers statically
  arm64: refactor aarch32_break_handler()
  arm64: debug: clean up single_step_handler logic

* for-next/feat_mte_tagged_far:
  : Support for reporting the non-address bits during a synchronous MTE tag check fault
  kselftest/arm64/mte: Add mtefar tests on check_mmap_options
  kselftest/arm64/mte: Refactor check_mmap_option test
  kselftest/arm64/mte: Add verification for address tag in signal handler
  kselftest/arm64/mte: Add address tag related macro and function
  kselftest/arm64/mte: Check MTE_FAR feature is supported
  kselftest/arm64/mte: Register mte signal handler with SA_EXPOSE_TAGBITS
  kselftest/arm64: Add MTE_FAR hwcap test
  KVM: arm64: Expose FEAT_MTE_TAGGED_FAR feature to guest
  arm64: Report address tag when FEAT_MTE_TAGGED_FAR is supported
  arm64/cpufeature: Add FEAT_MTE_TAGGED_FAR feature

* for-next/kselftest:
  : Kselftest updates for arm64
  kselftest/arm64: Handle attempts to disable SM on SME only systems
  kselftest/arm64: Fix SVE write data generation for SME only systems
  kselftest/arm64: Test SME on SME only systems in fp-ptrace
  kselftest/arm64: Test FPSIMD format data writes via NT_ARM_SVE in fp-ptrace
  kselftest/arm64: Allow sve-ptrace to run on SME only systems
  kselftest/arm4: Provide local defines for AT_HWCAP3
  kselftest/arm64: Specify SVE data when testing VL set in sve-ptrace
  kselftest/arm64: Fix test for streaming FPSIMD write in sve-ptrace
  kselftest/arm64: Fix check for setting new VLs in sve-ptrace
  kselftest/arm64: Convert tpidr2 test to use kselftest.h

* for-next/mdscr-cleanup:
  : Drop redundant DBG_MDSCR_* macros
  KVM: selftests: Change MDSCR_EL1 register holding variables as uint64_t
  arm64/debug: Drop redundant DBG_MDSCR_* macros

* for-next/vmap-stack:
  : Force VMAP_STACK on arm64
  arm64: remove CONFIG_VMAP_STACK checks from entry code
  arm64: remove CONFIG_VMAP_STACK checks from SDEI stack handling
  arm64: remove CONFIG_VMAP_STACK checks from stacktrace overflow logic
  arm64: remove CONFIG_VMAP_STACK conditionals from traps overflow stack
  arm64: remove CONFIG_VMAP_STACK conditionals from irq stack setup
  arm64: Remove CONFIG_VMAP_STACK conditionals from THREAD_SHIFT and THREAD_ALIGN
  arm64: efi: Remove CONFIG_VMAP_STACK check
  arm64: Mandate VMAP_STACK
  arm64: efi: Fix KASAN false positive for EFI runtime stack
  arm64/ptrace: Fix stack-out-of-bounds read in regs_get_kernel_stack_nth()
  arm64/gcs: Don't call gcs_free() during flush_gcs()
  arm64: Restrict pagetable teardown to avoid false warning
  docs: arm64: Fix ICC_SRE_EL2 register typo in booting.rst

Author: ctmarinas

Documentation/arch/arm64/booting.rst

@@ -234,7 +234,7 @@ Before jumping into the kernel, the following conditions must be met:
 
   - If the kernel is entered at EL1:
 
-      - ICC.SRE_EL2.Enable (bit 3) must be initialised to 0b1
+      - ICC_SRE_EL2.Enable (bit 3) must be initialised to 0b1
       - ICC_SRE_EL2.SRE (bit 0) must be initialised to 0b1.
 
   - The DT or ACPI tables must describe a GICv3 interrupt controller.

Documentation/arch/arm64/elf_hwcaps.rst

@@ -435,6 +435,9 @@ HWCAP2_SME_SF8DP4
 HWCAP2_POE
     Functionality implied by ID_AA64MMFR3_EL1.S1POE == 0b0001.
 
+HWCAP3_MTE_FAR
+    Functionality implied by ID_AA64PFR2_EL1.MTEFAR == 0b0001.
+
 4. Unused AT_HWCAP bits
 -----------------------
 

Documentation/arch/arm64/tagged-pointers.rst

@@ -60,11 +60,12 @@ that signal handlers in applications making use of tags cannot rely
 on the tag information for user virtual addresses being maintained
 in these fields unless the flag was set.
 
-Due to architecture limitations, bits 63:60 of the fault address
-are not preserved in response to synchronous tag check faults
-(SEGV_MTESERR) even if SA_EXPOSE_TAGBITS was set. Applications should
-treat the values of these bits as undefined in order to accommodate
-future architecture revisions which may preserve the bits.
+If FEAT_MTE_TAGGED_FAR (Armv8.9) is supported, bits 63:60 of the fault address
+are preserved in response to synchronous tag check faults (SEGV_MTESERR)
+otherwise not preserved even if SA_EXPOSE_TAGBITS was set.
+Applications should interpret the values of these bits based on
+the support for the HWCAP3_MTE_FAR. If the support is not present,
+the values of these bits should be considered as undefined otherwise valid.
 
 For signals raised in response to watchpoint debug exceptions, the
 tag information will be preserved regardless of the SA_EXPOSE_TAGBITS

arch/arm64/Kconfig

@@ -234,6 +234,7 @@ config ARM64
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_IOREMAP_PROT
 	select HAVE_IRQ_TIME_ACCOUNTING
+	select HAVE_LIVEPATCH
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
 	select HAVE_PERF_EVENTS
@@ -242,6 +243,7 @@ config ARM64
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_PREEMPT_DYNAMIC_KEY
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_RELIABLE_STACKTRACE
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select MMU_GATHER_RCU_TABLE_FREE
@@ -279,6 +281,7 @@ config ARM64
 	select HAVE_SOFTIRQ_ON_OWN_STACK
 	select USER_STACKTRACE_SUPPORT
 	select VDSO_GETRANDOM
+	select VMAP_STACK
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
@@ -2499,3 +2502,4 @@ source "drivers/acpi/Kconfig"
 
 source "arch/arm64/kvm/Kconfig"
 
+source "kernel/livepatch/Kconfig"

arch/arm64/include/asm/assembler.h

@@ -53,7 +53,7 @@
 	.macro	disable_step_tsk, flgs, tmp
 	tbz	\flgs, #TIF_SINGLESTEP, 9990f
 	mrs	\tmp, mdscr_el1
-	bic	\tmp, \tmp, #DBG_MDSCR_SS
+	bic	\tmp, \tmp, #MDSCR_EL1_SS
 	msr	mdscr_el1, \tmp
 	isb	// Take effect before a subsequent clear of DAIF.D
 9990:
@@ -63,7 +63,7 @@
 	.macro	enable_step_tsk, flgs, tmp
 	tbz	\flgs, #TIF_SINGLESTEP, 9990f
 	mrs	\tmp, mdscr_el1
-	orr	\tmp, \tmp, #DBG_MDSCR_SS
+	orr	\tmp, \tmp, #MDSCR_EL1_SS
 	msr	mdscr_el1, \tmp
 9990:
 	.endm

arch/arm64/include/asm/cpufeature.h

@@ -275,6 +275,14 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
 #define ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU	((u16)BIT(5))
 /* Panic when a conflict is detected */
 #define ARM64_CPUCAP_PANIC_ON_CONFLICT		((u16)BIT(6))
+/*
+ * When paired with SCOPE_LOCAL_CPU, all early CPUs must satisfy the
+ * condition. This is different from SCOPE_SYSTEM where the check is performed
+ * only once at the end of the SMP boot on the sanitised ID registers.
+ * SCOPE_SYSTEM is not suitable for cases where the capability depends on
+ * properties local to a CPU like MIDR_EL1.
+ */
+#define ARM64_CPUCAP_MATCH_ALL_EARLY_CPUS	((u16)BIT(7))
 
 /*
  * CPU errata workarounds that need to be enabled at boot time if one or
@@ -304,6 +312,16 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
 	(ARM64_CPUCAP_SCOPE_LOCAL_CPU		|	\
 	 ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU	|	\
 	 ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU)
+/*
+ * CPU feature detected at boot time and present on all early CPUs. Late CPUs
+ * are permitted to have the feature even if it hasn't been enabled, although
+ * the feature will not be used by Linux in this case. If all early CPUs have
+ * the feature, then every late CPU must have it.
+ */
+#define ARM64_CPUCAP_EARLY_LOCAL_CPU_FEATURE		\
+	 (ARM64_CPUCAP_SCOPE_LOCAL_CPU		|	\
+	  ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU	|	\
+	  ARM64_CPUCAP_MATCH_ALL_EARLY_CPUS)
 
 /*
  * CPU feature detected at boot time, on one or more CPUs. A late CPU
@@ -391,6 +409,11 @@ static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap)
 	return cap->type & ARM64_CPUCAP_SCOPE_MASK;
 }
 
+static inline bool cpucap_match_all_early_cpus(const struct arm64_cpu_capabilities *cap)
+{
+	return cap->type & ARM64_CPUCAP_MATCH_ALL_EARLY_CPUS;
+}
+
 /*
  * Generic helper for handling capabilities with multiple (match,enable) pairs
  * of call backs, sharing the same capability bit.
@@ -848,6 +871,11 @@ static inline bool system_supports_pmuv3(void)
 	return cpus_have_final_cap(ARM64_HAS_PMUV3);
 }
 
+static inline bool system_supports_bbml2_noabort(void)
+{
+	return alternative_has_cap_unlikely(ARM64_HAS_BBML2_NOABORT);
+}
+
 int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
 bool try_emulate_mrs(struct pt_regs *regs, u32 isn);
 

arch/arm64/include/asm/debug-monitors.h

@@ -13,14 +13,8 @@
 #include <asm/ptrace.h>
 
 /* Low-level stepping controls. */
-#define DBG_MDSCR_SS		(1 << 0)
 #define DBG_SPSR_SS		(1 << 21)
 
-/* MDSCR_EL1 enabling bits */
-#define DBG_MDSCR_KDE		(1 << 13)
-#define DBG_MDSCR_MDE		(1 << 15)
-#define DBG_MDSCR_MASK		~(DBG_MDSCR_KDE | DBG_MDSCR_MDE)
-
 #define	DBG_ESR_EVT(x)		(((x) >> 27) & 0x7)
 
 /* AArch64 */
@@ -62,30 +56,6 @@ struct task_struct;
 #define DBG_HOOK_HANDLED	0
 #define DBG_HOOK_ERROR		1
 
-struct step_hook {
-	struct list_head node;
-	int (*fn)(struct pt_regs *regs, unsigned long esr);
-};
-
-void register_user_step_hook(struct step_hook *hook);
-void unregister_user_step_hook(struct step_hook *hook);
-
-void register_kernel_step_hook(struct step_hook *hook);
-void unregister_kernel_step_hook(struct step_hook *hook);
-
-struct break_hook {
-	struct list_head node;
-	int (*fn)(struct pt_regs *regs, unsigned long esr);
-	u16 imm;
-	u16 mask; /* These bits are ignored when comparing with imm */
-};
-
-void register_user_break_hook(struct break_hook *hook);
-void unregister_user_break_hook(struct break_hook *hook);
-
-void register_kernel_break_hook(struct break_hook *hook);
-void unregister_kernel_break_hook(struct break_hook *hook);
-
 u8 debug_monitors_arch(void);
 
 enum dbg_active_el {
@@ -108,17 +78,15 @@ void kernel_rewind_single_step(struct pt_regs *regs);
 void kernel_fastforward_single_step(struct pt_regs *regs);
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
-int reinstall_suspended_bps(struct pt_regs *regs);
+bool try_step_suspended_breakpoints(struct pt_regs *regs);
 #else
-static inline int reinstall_suspended_bps(struct pt_regs *regs)
+static inline bool try_step_suspended_breakpoints(struct pt_regs *regs)
 {
-	return -ENODEV;
+	return false;
 }
 #endif
 
-int aarch32_break_handler(struct pt_regs *regs);
-
-void debug_traps_init(void);
+bool try_handle_aarch32_break(struct pt_regs *regs);
 
 #endif	/* __ASSEMBLY */
 #endif	/* __ASM_DEBUG_MONITORS_H */

arch/arm64/include/asm/exception.h

@@ -59,8 +59,20 @@ void do_el0_bti(struct pt_regs *regs);
 void do_el1_bti(struct pt_regs *regs, unsigned long esr);
 void do_el0_gcs(struct pt_regs *regs, unsigned long esr);
 void do_el1_gcs(struct pt_regs *regs, unsigned long esr);
-void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr,
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+void do_breakpoint(unsigned long esr, struct pt_regs *regs);
+void do_watchpoint(unsigned long addr, unsigned long esr,
 			struct pt_regs *regs);
+#else
+static inline void do_breakpoint(unsigned long esr, struct pt_regs *regs) {}
+static inline void do_watchpoint(unsigned long addr, unsigned long esr,
+			struct pt_regs *regs) {}
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+void do_el0_softstep(unsigned long esr, struct pt_regs *regs);
+void do_el1_softstep(unsigned long esr, struct pt_regs *regs);
+void do_el0_brk64(unsigned long esr, struct pt_regs *regs);
+void do_el1_brk64(unsigned long esr, struct pt_regs *regs);
+void do_bkpt32(unsigned long esr, struct pt_regs *regs);
 void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs);
 void do_sve_acc(unsigned long esr, struct pt_regs *regs);
 void do_sme_acc(unsigned long esr, struct pt_regs *regs);

arch/arm64/include/asm/gcs.h

@@ -58,7 +58,7 @@ static inline u64 gcsss2(void)
 
 static inline bool task_gcs_el0_enabled(struct task_struct *task)
 {
-	return current->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE;
+	return task->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE;
 }
 
 void gcs_set_el0_mode(struct task_struct *task);

arch/arm64/include/asm/hwcap.h

@@ -176,6 +176,7 @@
 #define KERNEL_HWCAP_POE		__khwcap2_feature(POE)
 
 #define __khwcap3_feature(x)		(const_ilog2(HWCAP3_ ## x) + 128)
+#define KERNEL_HWCAP_MTE_FAR		__khwcap3_feature(MTE_FAR)
 
 /*
  * This yields a mask that user programs can use to figure out what