From: Linus Torvalds Date: Tue, 14 Apr 2026 23:48:56 +0000 (-0700) Subject: Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64... X-Git-Url: http://git.ipfire.org/index.cgi?a=commitdiff_plain;h=c43267e6794a;p=thirdparty%2Fkernel%2Flinux.git Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux Pull arm64 updates from Catalin Marinas: "The biggest changes are MPAM enablement in drivers/resctrl and new PMU support under drivers/perf. On the core side, FEAT_LSUI lets futex atomic operations with EL0 permissions, avoiding PAN toggling. The rest is mostly TLB invalidation refactoring, further generic entry work, sysreg updates and a few fixes. Core features: - Add support for FEAT_LSUI, allowing futex atomic operations without toggling Privileged Access Never (PAN) - Further refactor the arm64 exception handling code towards the generic entry infrastructure - Optimise __READ_ONCE() with CONFIG_LTO=y and allow alias analysis through it Memory management: - Refactor the arm64 TLB invalidation API and implementation for better control over barrier placement and level-hinted invalidation - Enable batched TLB flushes during memory hot-unplug - Fix rodata=full block mapping support for realm guests (when BBML2_NOABORT is available) Perf and PMU: - Add support for a whole bunch of system PMUs featured in NVIDIA's Tegra410 SoC (cspmu extensions for the fabric and PCIe, new drivers for CPU/C2C memory latency PMUs) - Clean up iomem resource handling in the Arm CMN driver - Fix signedness handling of AA64DFR0.{PMUVer,PerfMon} MPAM (Memory Partitioning And Monitoring): - Add architecture context-switch and hiding of the feature from KVM - Add interface to allow MPAM to be exposed to user-space using resctrl - Add errata workaround for some existing platforms - Add documentation for using MPAM and what shape of platforms can use resctrl Miscellaneous: - Check DAIF (and PMR, where relevant) at task-switch time - Skip TFSR_EL1 checks and barriers in synchronous MTE tag check mode (only relevant to asynchronous or asymmetric tag check modes) - Remove a duplicate allocation in the kexec code - Remove redundant save/restore of SCS SP on entry to/from EL0 - Generate the KERNEL_HWCAP_ definitions from the arm64 hwcap descriptions - Add kselftest coverage for cmpbr_sigill() - Update sysreg definitions" * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (109 commits) arm64: rsi: use linear-map alias for realm config buffer arm64: Kconfig: fix duplicate word in CMDLINE help text arm64: mte: Skip TFSR_EL1 checks and barriers in synchronous tag check mode arm64/sysreg: Update ID_AA64SMFR0_EL1 description to DDI0601 2025-12 arm64/sysreg: Update ID_AA64ZFR0_EL1 description to DDI0601 2025-12 arm64/sysreg: Update ID_AA64FPFR0_EL1 description to DDI0601 2025-12 arm64/sysreg: Update ID_AA64ISAR2_EL1 description to DDI0601 2025-12 arm64/sysreg: Update ID_AA64ISAR0_EL1 description to DDI0601 2025-12 arm64/hwcap: Generate the KERNEL_HWCAP_ definitions for the hwcaps arm64: kexec: Remove duplicate allocation for trans_pgd ACPI: AGDI: fix missing newline in error message arm64: Check DAIF (and PMR) at task-switch time arm64: entry: Use split preemption logic arm64: entry: Use irqentry_{enter_from,exit_to}_kernel_mode() arm64: entry: Consistently prefix arm64-specific wrappers arm64: entry: Don't preempt with SError or Debug masked entry: Split preemption from irqentry_exit_to_kernel_mode() entry: Split kernel mode logic from irqentry_{enter,exit}() entry: Move irqentry_enter() prototype later entry: Remove local_irq_{enable,disable}_exit_to_user() ... --- c43267e6794a36013fd495a4d81bf7f748fe4615 diff --cc arch/arm64/kernel/rsi.c index 9e846ce4ef9ca,6e883bc431864..92160f2e57ff7 --- a/arch/arm64/kernel/rsi.c +++ b/arch/arm64/kernel/rsi.c @@@ -145,9 -144,9 +145,9 @@@ void __init arm64_rsi_init(void return; if (!rsi_version_matches()) return; - if (WARN_ON(rsi_get_realm_config(&config))) + if (WARN_ON(rsi_get_realm_config(lm_alias(&config)))) return; - prot_ns_shared = BIT(config.ipa_bits - 1); + prot_ns_shared = __phys_to_pte_val(BIT(config.ipa_bits - 1)); if (arm64_ioremap_prot_hook_register(realm_ioremap_hook)) return; diff --cc arch/arm64/kvm/at.c index a024d9a770dc7,1adf88a573284..9f8f0ae8e86e8 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@@ -1753,8 -1785,10 +1783,10 @@@ int __kvm_at_swap_desc(struct kvm *kvm if (!writable) return -EPERM; - ptep = (u64 __user *)hva + offset; + ptep = (void __user *)hva + offset; - if (cpus_have_final_cap(ARM64_HAS_LSE_ATOMICS)) + if (cpus_have_final_cap(ARM64_HAS_LSUI)) + r = __lsui_swap_desc(ptep, old, new); + else if (cpus_have_final_cap(ARM64_HAS_LSE_ATOMICS)) r = __lse_swap_desc(ptep, old, new); else r = __llsc_swap_desc(ptep, old, new); diff --cc include/linux/irq-entry-common.h index b976946b3cdbb,384520217bfe3..7ab41eec549fe --- a/include/linux/irq-entry-common.h +++ b/include/linux/irq-entry-common.h @@@ -378,6 -336,205 +349,207 @@@ typedef struct irqentry_state } irqentry_state_t; #endif + /** + * irqentry_exit_cond_resched - Conditionally reschedule on return from interrupt + * + * Conditional reschedule with additional sanity checks. + */ + void raw_irqentry_exit_cond_resched(void); + + #ifdef CONFIG_PREEMPT_DYNAMIC + #if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) + #define irqentry_exit_cond_resched_dynamic_enabled raw_irqentry_exit_cond_resched + #define irqentry_exit_cond_resched_dynamic_disabled NULL + DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched); + #define irqentry_exit_cond_resched() static_call(irqentry_exit_cond_resched)() + #elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) + DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); + void dynamic_irqentry_exit_cond_resched(void); + #define irqentry_exit_cond_resched() dynamic_irqentry_exit_cond_resched() + #endif + #else /* CONFIG_PREEMPT_DYNAMIC */ + #define irqentry_exit_cond_resched() raw_irqentry_exit_cond_resched() + #endif /* CONFIG_PREEMPT_DYNAMIC */ + + /** + * irqentry_enter_from_kernel_mode - Establish state before invoking the irq handler + * @regs: Pointer to currents pt_regs + * + * Invoked from architecture specific entry code with interrupts disabled. + * Can only be called when the interrupt entry came from kernel mode. The + * calling code must be non-instrumentable. When the function returns all + * state is correct and the subsequent functions can be instrumented. + * + * The function establishes state (lockdep, RCU (context tracking), tracing) and + * is provided for architectures which require a strict split between entry from + * kernel and user mode and therefore cannot use irqentry_enter() which handles + * both entry modes. + * + * Returns: An opaque object that must be passed to irqentry_exit_to_kernel_mode(). + */ + static __always_inline irqentry_state_t irqentry_enter_from_kernel_mode(struct pt_regs *regs) + { + irqentry_state_t ret = { + .exit_rcu = false, + }; + + /* + * If this entry hit the idle task invoke ct_irq_enter() whether + * RCU is watching or not. + * + * Interrupts can nest when the first interrupt invokes softirq + * processing on return which enables interrupts. + * + * Scheduler ticks in the idle task can mark quiescent state and + * terminate a grace period, if and only if the timer interrupt is + * not nested into another interrupt. + * + * Checking for rcu_is_watching() here would prevent the nesting + * interrupt to invoke ct_irq_enter(). If that nested interrupt is + * the tick then rcu_flavor_sched_clock_irq() would wrongfully + * assume that it is the first interrupt and eventually claim + * quiescent state and end grace periods prematurely. + * + * Unconditionally invoke ct_irq_enter() so RCU state stays + * consistent. + * + * TINY_RCU does not support EQS, so let the compiler eliminate + * this part when enabled. + */ + if (!IS_ENABLED(CONFIG_TINY_RCU) && + (is_idle_task(current) || arch_in_rcu_eqs())) { + /* + * If RCU is not watching then the same careful + * sequence vs. lockdep and tracing is required + * as in irqentry_enter_from_user_mode(). + */ + lockdep_hardirqs_off(CALLER_ADDR0); + ct_irq_enter(); + instrumentation_begin(); + kmsan_unpoison_entry_regs(regs); + trace_hardirqs_off_finish(); + instrumentation_end(); + + ret.exit_rcu = true; + return ret; + } + + /* + * If RCU is watching then RCU only wants to check whether it needs + * to restart the tick in NOHZ mode. rcu_irq_enter_check_tick() + * already contains a warning when RCU is not watching, so no point + * in having another one here. + */ + lockdep_hardirqs_off(CALLER_ADDR0); + instrumentation_begin(); + kmsan_unpoison_entry_regs(regs); + rcu_irq_enter_check_tick(); + trace_hardirqs_off_finish(); + instrumentation_end(); + + return ret; + } + + /** + * irqentry_exit_to_kernel_mode_preempt - Run preempt checks on return to kernel mode + * @regs: Pointer to current's pt_regs + * @state: Return value from matching call to irqentry_enter_from_kernel_mode() + * + * This is to be invoked before irqentry_exit_to_kernel_mode_after_preempt() to + * allow kernel preemption on return from interrupt. + * + * Must be invoked with interrupts disabled and CPU state which allows kernel + * preemption. + * + * After returning from this function, the caller can modify CPU state before + * invoking irqentry_exit_to_kernel_mode_after_preempt(), which is required to + * re-establish the tracing, lockdep and RCU state for returning to the + * interrupted context. + */ + static inline void irqentry_exit_to_kernel_mode_preempt(struct pt_regs *regs, + irqentry_state_t state) + { + if (regs_irqs_disabled(regs) || state.exit_rcu) + return; + + if (IS_ENABLED(CONFIG_PREEMPTION)) + irqentry_exit_cond_resched(); ++ ++ hrtimer_rearm_deferred(); + } + + /** + * irqentry_exit_to_kernel_mode_after_preempt - Establish trace, lockdep and RCU state + * @regs: Pointer to current's pt_regs + * @state: Return value from matching call to irqentry_enter_from_kernel_mode() + * + * This is to be invoked after irqentry_exit_to_kernel_mode_preempt() and before + * actually returning to the interrupted context. + * + * There are no requirements for the CPU state other than being able to complete + * the tracing, lockdep and RCU state transitions. After this function returns + * the caller must return directly to the interrupted context. + */ + static __always_inline void + irqentry_exit_to_kernel_mode_after_preempt(struct pt_regs *regs, irqentry_state_t state) + { + if (!regs_irqs_disabled(regs)) { + /* + * If RCU was not watching on entry this needs to be done + * carefully and needs the same ordering of lockdep/tracing + * and RCU as the return to user mode path. + */ + if (state.exit_rcu) { + instrumentation_begin(); + /* Tell the tracer that IRET will enable interrupts */ + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(); + instrumentation_end(); + ct_irq_exit(); + lockdep_hardirqs_on(CALLER_ADDR0); + return; + } + + instrumentation_begin(); + /* Covers both tracing and lockdep */ + trace_hardirqs_on(); + instrumentation_end(); + } else { + /* + * IRQ flags state is correct already. Just tell RCU if it + * was not watching on entry. + */ + if (state.exit_rcu) + ct_irq_exit(); + } + } + + /** + * irqentry_exit_to_kernel_mode - Run preempt checks and establish state after + * invoking the interrupt handler + * @regs: Pointer to current's pt_regs + * @state: Return value from matching call to irqentry_enter_from_kernel_mode() + * + * This is the counterpart of irqentry_enter_from_kernel_mode() and combines + * the calls to irqentry_exit_to_kernel_mode_preempt() and + * irqentry_exit_to_kernel_mode_after_preempt(). + * + * The requirement for the CPU state is that it can schedule. After the function + * returns the tracing, lockdep and RCU state transitions are completed and the + * caller must return directly to the interrupted context. + */ + static __always_inline void irqentry_exit_to_kernel_mode(struct pt_regs *regs, + irqentry_state_t state) + { + lockdep_assert_irqs_disabled(); + + instrumentation_begin(); + irqentry_exit_to_kernel_mode_preempt(regs, state); + instrumentation_end(); + + irqentry_exit_to_kernel_mode_after_preempt(regs, state); + } + /** * irqentry_enter - Handle state tracking on ordinary interrupt entries * @regs: Pointer to pt_regs of interrupted context diff --cc kernel/entry/common.c index 9e1a6afb07f22,1034be02eae84..19d2244a9fefc --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@@ -47,10 -47,10 +47,10 @@@ static __always_inline unsigned long __ */ while (ti_work & EXIT_TO_USER_MODE_WORK_LOOP) { - local_irq_enable_exit_to_user(ti_work); + local_irq_enable(); if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) { - if (!rseq_grant_slice_extension(ti_work & TIF_SLICE_EXT_DENY)) + if (!rseq_grant_slice_extension(ti_work, TIF_SLICE_EXT_DENY)) schedule(); }