From f5ba9d9e6a56d04405f06f14e3b8187e1b484ff8 Mon Sep 17 00:00:00 2001 From: Peter Jung Date: Fri, 27 Feb 2026 10:57:22 +0100 Subject: [PATCH 4/8] fixes Signed-off-by: Peter Jung --- arch/arm/include/asm/mmu_context.h | 2 +- arch/riscv/include/asm/sync_core.h | 2 +- arch/s390/include/asm/mmu_context.h | 2 +- arch/sparc/include/asm/mmu_context_64.h | 2 +- arch/x86/include/asm/mmu_context.h | 23 ++++++++- arch/x86/include/asm/sync_core.h | 2 +- arch/x86/kernel/cpu/amd.c | 6 +++ arch/x86/mm/tlb.c | 21 --------- drivers/bluetooth/btusb.c | 4 ++ drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 +- drivers/gpu/drm/i915/gt/intel_rc6.c | 13 ++++- drivers/iommu/iommu.c | 5 ++ drivers/usb/core/quirks.c | 9 ++++ include/linux/perf_event.h | 2 +- include/linux/sched/mm.h | 10 ++-- include/linux/sched/topology.h | 3 -- include/linux/tick.h | 4 +- include/linux/vtime.h | 8 ++-- include/net/netfilter/nf_tables.h | 2 + kernel/rcu/tree.c | 12 +++++ kernel/sched/core.c | 22 +++------ kernel/sched/ext.c | 4 +- kernel/sched/fair.c | 55 +++------------------- kernel/sched/features.h | 5 -- kernel/sched/sched.h | 31 ++++++------ kernel/sched/topology.c | 6 --- net/netfilter/nf_tables_api.c | 3 +- net/netfilter/nft_set_pipapo.c | 2 + sound/hda/codecs/realtek/alc269.c | 1 + 29 files changed, 126 insertions(+), 139 deletions(-) diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h index db2cb06aa8cf..bebde469f81a 100644 --- a/arch/arm/include/asm/mmu_context.h +++ b/arch/arm/include/asm/mmu_context.h @@ -80,7 +80,7 @@ static inline void check_and_switch_context(struct mm_struct *mm, #ifndef MODULE #define finish_arch_post_lock_switch \ finish_arch_post_lock_switch -static inline void finish_arch_post_lock_switch(void) +static __always_inline void finish_arch_post_lock_switch(void) { struct mm_struct *mm = current->mm; diff --git a/arch/riscv/include/asm/sync_core.h b/arch/riscv/include/asm/sync_core.h index 9153016da8f1..2fe6b7fe6b12 100644 --- a/arch/riscv/include/asm/sync_core.h +++ b/arch/riscv/include/asm/sync_core.h @@ -6,7 +6,7 @@ * RISC-V implements return to user-space through an xRET instruction, * which is not core serializing. */ -static inline void sync_core_before_usermode(void) +static __always_inline void sync_core_before_usermode(void) { asm volatile ("fence.i" ::: "memory"); } diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index d9b8501bc93d..c124ef6a01b3 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -97,7 +97,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, } #define finish_arch_post_lock_switch finish_arch_post_lock_switch -static inline void finish_arch_post_lock_switch(void) +static __always_inline void finish_arch_post_lock_switch(void) { struct task_struct *tsk = current; struct mm_struct *mm = tsk->mm; diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h index 78bbacc14d2d..d1967214ef25 100644 --- a/arch/sparc/include/asm/mmu_context_64.h +++ b/arch/sparc/include/asm/mmu_context_64.h @@ -160,7 +160,7 @@ static inline void arch_start_context_switch(struct task_struct *prev) } #define finish_arch_post_lock_switch finish_arch_post_lock_switch -static inline void finish_arch_post_lock_switch(void) +static __always_inline void finish_arch_post_lock_switch(void) { /* Restore the state of MCDPER register for the new process * just switched to. diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 73bf3b1b44e8..ecd134dcfb34 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -136,8 +136,29 @@ static inline void mm_reset_untag_mask(struct mm_struct *mm) } #endif +/* + * Please ignore the name of this function. It should be called + * switch_to_kernel_thread(). + * + * enter_lazy_tlb() is a hint from the scheduler that we are entering a + * kernel thread or other context without an mm. Acceptable implementations + * include doing nothing whatsoever, switching to init_mm, or various clever + * lazy tricks to try to minimize TLB flushes. + * + * The scheduler reserves the right to call enter_lazy_tlb() several times + * in a row. It will notify us that we're going back to a real mm by + * calling switch_mm_irqs_off(). + */ #define enter_lazy_tlb enter_lazy_tlb -extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); +#ifndef MODULE +static __always_inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) +{ + if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm) + return; + + this_cpu_write(cpu_tlbstate_shared.is_lazy, true); +} +#endif #define mm_init_global_asid mm_init_global_asid extern void mm_init_global_asid(struct mm_struct *mm); diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h index 96bda43538ee..4b55fa353bb5 100644 --- a/arch/x86/include/asm/sync_core.h +++ b/arch/x86/include/asm/sync_core.h @@ -93,7 +93,7 @@ static __always_inline void sync_core(void) * to user-mode. x86 implements return to user-space through sysexit, * sysrel, and sysretq, which are not core serializing. */ -static inline void sync_core_before_usermode(void) +static __always_inline void sync_core_before_usermode(void) { /* With PTI, we unconditionally serialize before running user code. */ if (static_cpu_has(X86_FEATURE_PTI)) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 86059f2c0fcd..7c5c488624e2 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1023,6 +1023,7 @@ static void init_amd_zen4(struct cpuinfo_x86 *c) } } +#ifndef CONFIG_CACHY static const struct x86_cpu_id zen5_rdseed_microcode[] = { ZEN_MODEL_STEP_UCODE(0x1a, 0x02, 0x1, 0x0b00215a), ZEN_MODEL_STEP_UCODE(0x1a, 0x08, 0x1, 0x0b008121), @@ -1044,6 +1045,11 @@ static void init_amd_zen5(struct cpuinfo_x86 *c) pr_emerg_once("RDSEED32 is broken. Disabling the corresponding CPUID bit.\n"); } } +#else +static void init_amd_zen5(struct cpuinfo_x86 *c) +{ +} +#endif /* !CONFIG_CACHY */ static void init_amd(struct cpuinfo_x86 *c) { diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index f5b93e01e347..71abaf0bdb91 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -971,27 +971,6 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next, } } -/* - * Please ignore the name of this function. It should be called - * switch_to_kernel_thread(). - * - * enter_lazy_tlb() is a hint from the scheduler that we are entering a - * kernel thread or other context without an mm. Acceptable implementations - * include doing nothing whatsoever, switching to init_mm, or various clever - * lazy tricks to try to minimize TLB flushes. - * - * The scheduler reserves the right to call enter_lazy_tlb() several times - * in a row. It will notify us that we're going back to a real mm by - * calling switch_mm_irqs_off(). - */ -void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) -{ - if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm) - return; - - this_cpu_write(cpu_tlbstate_shared.is_lazy, true); -} - /* * Using a temporary mm allows to set temporary mappings that are not accessible * by other CPUs. Such mappings are needed to perform sensitive memory writes diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 80ccfa8fd982..0d5eae8295d4 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -559,6 +559,8 @@ static const struct usb_device_id quirks_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3592), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0489, 0xe112), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0489, 0xe122), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, @@ -669,6 +671,8 @@ static const struct usb_device_id quirks_table[] = { BTUSB_WIDEBAND_SPEECH }, /* MediaTek MT7922 Bluetooth devices */ + { USB_DEVICE(0x13d3, 0x3625), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3585), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3610), .driver_info = BTUSB_MEDIATEK | diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d2c3885de711..8900e0dc8a61 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5068,7 +5068,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) * before ip_fini_early to prevent kfd locking refcount issues by calling * amdgpu_amdkfd_suspend() */ - if (drm_dev_is_unplugged(adev_to_drm(adev))) + if (pci_dev_is_disconnected(adev->pdev)) amdgpu_amdkfd_device_fini_sw(adev); amdgpu_device_ip_fini_early(adev); @@ -5080,7 +5080,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) amdgpu_gart_dummy_page_fini(adev); - if (drm_dev_is_unplugged(adev_to_drm(adev))) + if (pci_dev_is_disconnected(adev->pdev)) amdgpu_device_unmap_mmio(adev); } diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index 286d49ecc449..472c68b32516 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -2,9 +2,9 @@ /* * Copyright © 2019 Intel Corporation */ - #include #include +#include #include @@ -497,6 +497,17 @@ static bool rc6_supported(struct intel_rc6 *rc6) if (!HAS_RC6(i915)) return false; + if (dmi_match(DMI_PRODUCT_SKU, "IBP1XI08MK1") || + dmi_match(DMI_PRODUCT_SKU, "IBP14I08MK2") || + dmi_match(DMI_PRODUCT_SKU, "IBP1XI08MK2") || + dmi_match(DMI_PRODUCT_SKU, "IBP16I08MK2") || + dmi_match(DMI_PRODUCT_SKU, "OMNIA08IMK1") || + dmi_match(DMI_PRODUCT_SKU, "OMNIA08IMK2")) { + drm_notice(&i915->drm, + "RC6 disabled by quirk\n"); + return false; + } + if (intel_vgpu_active(i915)) return false; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 2ca990dfbb88..7c50e672dc84 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1218,6 +1218,11 @@ static int iommu_create_device_direct_mappings(struct iommu_domain *domain, ret = iommu_map(domain, addr - map_size, addr - map_size, map_size, entry->prot, GFP_KERNEL); + if (ret == -EADDRINUSE && addr - map_size == 0) { + dev_warn_once(dev, + "iommu: identity mapping at addr 0x0 already exists, skipping\n"); + ret = 0; + } if (ret) goto out; map_size = 0; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index c4d85089d19b..f4c80063864f 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -377,6 +377,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* SanDisk Extreme 55AE */ { USB_DEVICE(0x0781, 0x55ae), .driver_info = USB_QUIRK_NO_LPM }, + /* Avermedia Live Gamer Ultra 2.1 (GC553G2) - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x07ca, 0x2553), .driver_info = USB_QUIRK_NO_BOS }, + /* Realforce 87U Keyboard */ { USB_DEVICE(0x0853, 0x011b), .driver_info = USB_QUIRK_NO_LPM }, @@ -437,6 +440,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0b05, 0x17e0), .driver_info = USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* ASUS TUF 4K PRO - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x0b05, 0x1ab9), .driver_info = USB_QUIRK_NO_BOS }, + /* Realtek Semiconductor Corp. Mass Storage Device (Multicard Reader)*/ { USB_DEVICE(0x0bda, 0x0151), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, @@ -565,6 +571,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x2386, 0x350e), .driver_info = USB_QUIRK_NO_LPM }, + /* UGREEN 35871 - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x2b89, 0x5871), .driver_info = USB_QUIRK_NO_BOS }, + /* APTIV AUTOMOTIVE HUB */ { USB_DEVICE(0x2c48, 0x0132), .driver_info = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT }, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 9ded2e582c60..fbe94b65b30a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1624,7 +1624,7 @@ static inline void perf_event_task_migrate(struct task_struct *task) task->sched_migrated = 1; } -static inline void perf_event_task_sched_in(struct task_struct *prev, +static __always_inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { if (static_branch_unlikely(&perf_sched_events)) diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 95d0040df584..4a279ee2d026 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -44,7 +44,7 @@ static inline void smp_mb__after_mmgrab(void) extern void __mmdrop(struct mm_struct *mm); -static inline void mmdrop(struct mm_struct *mm) +static __always_inline void mmdrop(struct mm_struct *mm) { /* * The implicit full barrier implied by atomic_dec_and_test() is @@ -71,14 +71,14 @@ static inline void __mmdrop_delayed(struct rcu_head *rhp) * Invoked from finish_task_switch(). Delegates the heavy lifting on RT * kernels via RCU. */ -static inline void mmdrop_sched(struct mm_struct *mm) +static __always_inline void mmdrop_sched(struct mm_struct *mm) { /* Provides a full memory barrier. See mmdrop() */ if (atomic_dec_and_test(&mm->mm_count)) call_rcu(&mm->delayed_drop, __mmdrop_delayed); } #else -static inline void mmdrop_sched(struct mm_struct *mm) +static __always_inline void mmdrop_sched(struct mm_struct *mm) { mmdrop(mm); } @@ -104,7 +104,7 @@ static inline void mmdrop_lazy_tlb(struct mm_struct *mm) } } -static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm) +static __always_inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) mmdrop_sched(mm); @@ -532,7 +532,7 @@ enum { #include #endif -static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) +static __always_inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { /* * The atomic_read() below prevents CSE. The following should diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 45c0022b91ce..bbcfdf12aa6e 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -92,9 +92,6 @@ struct sched_domain { unsigned int nr_balance_failed; /* initialise to 0 */ /* idle_balance() stats */ - unsigned int newidle_call; - unsigned int newidle_success; - unsigned int newidle_ratio; u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; diff --git a/include/linux/tick.h b/include/linux/tick.h index ac76ae9fa36d..fce16aa10ba2 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -175,7 +175,7 @@ extern cpumask_var_t tick_nohz_full_mask; #ifdef CONFIG_NO_HZ_FULL extern bool tick_nohz_full_running; -static inline bool tick_nohz_full_enabled(void) +static __always_inline bool tick_nohz_full_enabled(void) { if (!context_tracking_enabled()) return false; @@ -299,7 +299,7 @@ static inline void __tick_nohz_task_switch(void) { } static inline void tick_nohz_full_setup(cpumask_var_t cpumask) { } #endif -static inline void tick_nohz_task_switch(void) +static __always_inline void tick_nohz_task_switch(void) { if (tick_nohz_full_enabled()) __tick_nohz_task_switch(); diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 29dd5b91dd7d..428464bb81b3 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -67,24 +67,24 @@ static __always_inline void vtime_account_guest_exit(void) * For now vtime state is tied to context tracking. We might want to decouple * those later if necessary. */ -static inline bool vtime_accounting_enabled(void) +static __always_inline bool vtime_accounting_enabled(void) { return context_tracking_enabled(); } -static inline bool vtime_accounting_enabled_cpu(int cpu) +static __always_inline bool vtime_accounting_enabled_cpu(int cpu) { return context_tracking_enabled_cpu(cpu); } -static inline bool vtime_accounting_enabled_this_cpu(void) +static __always_inline bool vtime_accounting_enabled_this_cpu(void) { return context_tracking_enabled_this_cpu(); } extern void vtime_task_switch_generic(struct task_struct *prev); -static inline void vtime_task_switch(struct task_struct *prev) +static __always_inline void vtime_task_switch(struct task_struct *prev) { if (vtime_accounting_enabled_this_cpu()) vtime_task_switch_generic(prev); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 7eac73f9b4ce..05f57ba62244 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -456,6 +456,7 @@ struct nft_set_ext; * @init: initialize private data of new set instance * @destroy: destroy private data of set instance * @gc_init: initialize garbage collection + * @abort_skip_removal: skip removal of elements from abort path * @elemsize: element private size * * Operations lookup, update and delete have simpler interfaces, are faster @@ -513,6 +514,7 @@ struct nft_set_ops { const struct nft_set *set); void (*gc_init)(const struct nft_set *set); + bool abort_skip_removal; unsigned int elemsize; }; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 293bbd9ac3f4..2c1c9759e278 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -160,6 +160,7 @@ static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp, unsigned long gps, unsigned long flags); static void invoke_rcu_core(void); static void rcu_report_exp_rdp(struct rcu_data *rdp); +static void rcu_report_qs_rdp(struct rcu_data *rdp); static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp); static bool rcu_rdp_is_offloaded(struct rcu_data *rdp); static bool rcu_rdp_cpu_online(struct rcu_data *rdp); @@ -1983,6 +1984,17 @@ static noinline_for_stack bool rcu_gp_init(void) if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) on_each_cpu(rcu_strict_gp_boundary, NULL, 0); + /* + * Immediately report QS for the GP kthread's CPU. The GP kthread + * cannot be in an RCU read-side critical section while running + * the FQS scan. This eliminates the need for a second FQS wait + * when all CPUs are idle. + */ + preempt_disable(); + rcu_qs(); + rcu_report_qs_rdp(this_cpu_ptr(&rcu_data)); + preempt_enable(); + return true; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index dbf4e32a063f..1a6b1bfdb497 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -124,7 +124,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_exit_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_set_need_resched_tp); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); -DEFINE_PER_CPU(struct rnd_state, sched_rnd_state); #ifdef CONFIG_SCHED_PROXY_EXEC DEFINE_STATIC_KEY_TRUE(__sched_proxy_exec); @@ -681,11 +680,6 @@ bool raw_spin_rq_trylock(struct rq *rq) } } -void raw_spin_rq_unlock(struct rq *rq) -{ - raw_spin_unlock(rq_lockp(rq)); -} - /* * double_rq_lock - safely lock two runqueues */ @@ -4873,7 +4867,7 @@ static inline void prepare_task(struct task_struct *next) WRITE_ONCE(next->on_cpu, 1); } -static inline void finish_task(struct task_struct *prev) +static __always_inline void finish_task(struct task_struct *prev) { /* * This must be the very last reference to @prev from this CPU. After @@ -4889,7 +4883,7 @@ static inline void finish_task(struct task_struct *prev) smp_store_release(&prev->on_cpu, 0); } -static void do_balance_callbacks(struct rq *rq, struct balance_callback *head) +static __always_inline void do_balance_callbacks(struct rq *rq, struct balance_callback *head) { void (*func)(struct rq *rq); struct balance_callback *next; @@ -4924,7 +4918,7 @@ struct balance_callback balance_push_callback = { .func = balance_push, }; -static inline struct balance_callback * +static __always_inline struct balance_callback * __splice_balance_callbacks(struct rq *rq, bool split) { struct balance_callback *head = rq->balance_callback; @@ -4954,7 +4948,7 @@ struct balance_callback *splice_balance_callbacks(struct rq *rq) return __splice_balance_callbacks(rq, true); } -void __balance_callbacks(struct rq *rq, struct rq_flags *rf) +__always_inline void __balance_callbacks(struct rq *rq, struct rq_flags *rf) { if (rf) rq_unpin_lock(rq, rf); @@ -4991,7 +4985,7 @@ prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf #endif } -static inline void finish_lock_switch(struct rq *rq) +static __always_inline void finish_lock_switch(struct rq *rq) { /* * If we are tracking spinlock dependencies then we have to @@ -5023,7 +5017,7 @@ static inline void kmap_local_sched_out(void) #endif } -static inline void kmap_local_sched_in(void) +static __always_inline void kmap_local_sched_in(void) { #ifdef CONFIG_KMAP_LOCAL if (unlikely(current->kmap_ctrl.idx)) @@ -5076,7 +5070,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev, * past. 'prev == current' is still correct but we need to recalculate this_rq * because prev may have moved to another CPU. */ -static struct rq *finish_task_switch(struct task_struct *prev) +static __always_inline struct rq *finish_task_switch(struct task_struct *prev) __releases(rq->lock) { struct rq *rq = this_rq(); @@ -8495,8 +8489,6 @@ void __init sched_init_smp(void) { sched_init_numa(NUMA_NO_NODE); - prandom_init_once(&sched_rnd_state); - /* * There's no userspace yet to cause hotplug operations; hence all the * CPU masks are stable and all blatant races in the below code cannot diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 0bb8fa927e9e..94d75bf0c119 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -3488,8 +3488,8 @@ static void destroy_dsq(struct scx_sched *sch, u64 dsq_id) * operations inside scheduler locks. */ dsq->id = SCX_DSQ_INVALID; - llist_add(&dsq->free_node, &dsqs_to_free); - irq_work_queue(&free_dsq_irq_work); + if (llist_add(&dsq->free_node, &dsqs_to_free)) + irq_work_queue(&free_dsq_irq_work); out_unlock_dsq: raw_spin_unlock_irqrestore(&dsq->lock, flags); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 66289244f71e..b859f1f314cf 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2471,11 +2471,8 @@ static void task_numa_find_cpu(struct task_numa_env *env, maymove = !load_too_imbalanced(src_load, dst_load, env); } - for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) { - /* Skip this CPU if the source task cannot migrate */ - if (!cpumask_test_cpu(cpu, env->p->cpus_ptr)) - continue; - + /* Skip CPUs if the source task cannot migrate */ + for_each_cpu_and(cpu, cpumask_of_node(env->dst_nid), env->p->cpus_ptr) { env->dst_cpu = cpu; if (task_numa_compare(env, taskimp, groupimp, maymove)) break; @@ -8391,9 +8388,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) int max_spare_cap_cpu = -1; int fits, max_fits = -1; - cpumask_and(cpus, perf_domain_span(pd), cpu_online_mask); - - if (cpumask_empty(cpus)) + if (!cpumask_and(cpus, perf_domain_span(pd), cpu_online_mask)) continue; /* Account external pressure for the energy estimation */ @@ -12241,27 +12236,11 @@ void update_max_interval(void) max_load_balance_interval = HZ*num_online_cpus()/10; } -static inline void update_newidle_stats(struct sched_domain *sd, unsigned int success) -{ - sd->newidle_call++; - sd->newidle_success += success; - - if (sd->newidle_call >= 1024) { - sd->newidle_ratio = sd->newidle_success; - sd->newidle_call /= 2; - sd->newidle_success /= 2; - } -} - -static inline bool -update_newidle_cost(struct sched_domain *sd, u64 cost, unsigned int success) +static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost) { unsigned long next_decay = sd->last_decay_max_lb_cost + HZ; unsigned long now = jiffies; - if (cost) - update_newidle_stats(sd, success); - if (cost > sd->max_newidle_lb_cost) { /* * Track max cost of a domain to make sure to not delay the @@ -12309,7 +12288,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle) * Decay the newidle max times here because this is a regular * visit to all the domains. */ - need_decay = update_newidle_cost(sd, 0, 0); + need_decay = update_newidle_cost(sd, 0); max_cost += sd->max_newidle_lb_cost; /* @@ -12945,22 +12924,6 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf) break; if (sd->flags & SD_BALANCE_NEWIDLE) { - unsigned int weight = 1; - - if (sched_feat(NI_RANDOM)) { - /* - * Throw a 1k sided dice; and only run - * newidle_balance according to the success - * rate. - */ - u32 d1k = sched_rng() % 1024; - weight = 1 + sd->newidle_ratio; - if (d1k > weight) { - update_newidle_stats(sd, 0); - continue; - } - weight = (1024 + weight/2) / weight; - } pulled_task = sched_balance_rq(this_cpu, this_rq, sd, CPU_NEWLY_IDLE, @@ -12968,14 +12931,10 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf) t1 = sched_clock_cpu(this_cpu); domain_cost = t1 - t0; + update_newidle_cost(sd, domain_cost); + curr_cost += domain_cost; t0 = t1; - - /* - * Track max cost of a domain to make sure to not delay the - * next wakeup on the CPU. - */ - update_newidle_cost(sd, domain_cost, weight * !!pulled_task); } /* diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 136a6584be79..3c12d9f93331 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -121,8 +121,3 @@ SCHED_FEAT(WA_BIAS, true) SCHED_FEAT(UTIL_EST, true) SCHED_FEAT(LATENCY_WARN, false) - -/* - * Do newidle balancing proportional to its success rate using randomization. - */ -SCHED_FEAT(NI_RANDOM, true) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 7294157bfadc..18503287e561 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -5,7 +5,6 @@ #ifndef _KERNEL_SCHED_SCHED_H #define _KERNEL_SCHED_SCHED_H -#include #include #include #include @@ -1351,12 +1350,6 @@ static inline bool is_migration_disabled(struct task_struct *p) } DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); -DECLARE_PER_CPU(struct rnd_state, sched_rnd_state); - -static inline u32 sched_rng(void) -{ - return prandom_u32_state(this_cpu_ptr(&sched_rnd_state)); -} #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) #define this_rq() this_cpu_ptr(&runqueues) @@ -1403,12 +1396,12 @@ static inline struct cpumask *sched_group_span(struct sched_group *sg); DECLARE_STATIC_KEY_FALSE(__sched_core_enabled); -static inline bool sched_core_enabled(struct rq *rq) +static __always_inline bool sched_core_enabled(struct rq *rq) { return static_branch_unlikely(&__sched_core_enabled) && rq->core_enabled; } -static inline bool sched_core_disabled(void) +static __always_inline bool sched_core_disabled(void) { return !static_branch_unlikely(&__sched_core_enabled); } @@ -1417,7 +1410,7 @@ static inline bool sched_core_disabled(void) * Be careful with this function; not for general use. The return value isn't * stable unless you actually hold a relevant rq->__lock. */ -static inline raw_spinlock_t *rq_lockp(struct rq *rq) +static __always_inline raw_spinlock_t *rq_lockp(struct rq *rq) { if (sched_core_enabled(rq)) return &rq->core->__lock; @@ -1425,7 +1418,7 @@ static inline raw_spinlock_t *rq_lockp(struct rq *rq) return &rq->__lock; } -static inline raw_spinlock_t *__rq_lockp(struct rq *rq) +static __always_inline raw_spinlock_t *__rq_lockp(struct rq *rq) { if (rq->core_enabled) return &rq->core->__lock; @@ -1519,12 +1512,12 @@ static inline bool sched_core_disabled(void) return true; } -static inline raw_spinlock_t *rq_lockp(struct rq *rq) +static __always_inline raw_spinlock_t *rq_lockp(struct rq *rq) { return &rq->__lock; } -static inline raw_spinlock_t *__rq_lockp(struct rq *rq) +static __always_inline raw_spinlock_t *__rq_lockp(struct rq *rq) { return &rq->__lock; } @@ -1573,20 +1566,24 @@ static inline void lockdep_assert_rq_held(struct rq *rq) extern void raw_spin_rq_lock_nested(struct rq *rq, int subclass); extern bool raw_spin_rq_trylock(struct rq *rq); -extern void raw_spin_rq_unlock(struct rq *rq); -static inline void raw_spin_rq_lock(struct rq *rq) +static __always_inline void raw_spin_rq_lock(struct rq *rq) { raw_spin_rq_lock_nested(rq, 0); } -static inline void raw_spin_rq_lock_irq(struct rq *rq) +static __always_inline void raw_spin_rq_unlock(struct rq *rq) +{ + raw_spin_unlock(rq_lockp(rq)); +} + +static __always_inline void raw_spin_rq_lock_irq(struct rq *rq) { local_irq_disable(); raw_spin_rq_lock(rq); } -static inline void raw_spin_rq_unlock_irq(struct rq *rq) +static __always_inline void raw_spin_rq_unlock_irq(struct rq *rq) { raw_spin_rq_unlock(rq); local_irq_enable(); diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index cf643a5ddedd..711076aa4980 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1669,12 +1669,6 @@ sd_init(struct sched_domain_topology_level *tl, .last_balance = jiffies, .balance_interval = sd_weight, - - /* 50% success rate */ - .newidle_call = 512, - .newidle_success = 256, - .newidle_ratio = 512, - .max_newidle_lb_cost = 0, .last_decay_max_lb_cost = jiffies, .child = child, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8dae197c7faf..3b9c559ab123 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7702,7 +7702,8 @@ static bool nft_trans_elems_new_abort(const struct nft_ctx *ctx, continue; } - if (!te->set->ops->abort || nft_setelem_is_catchall(te->set, te->elems[i].priv)) + if (!te->set->ops->abort_skip_removal || + nft_setelem_is_catchall(te->set, te->elems[i].priv)) nft_setelem_remove(ctx->net, te->set, te->elems[i].priv); if (!nft_setelem_is_catchall(te->set, te->elems[i].priv)) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 6d77a5f0088a..18e1903b1d3d 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -2370,6 +2370,7 @@ const struct nft_set_type nft_set_pipapo_type = { .gc_init = nft_pipapo_gc_init, .commit = nft_pipapo_commit, .abort = nft_pipapo_abort, + .abort_skip_removal = true, .elemsize = offsetof(struct nft_pipapo_elem, ext), }, }; @@ -2394,6 +2395,7 @@ const struct nft_set_type nft_set_pipapo_avx2_type = { .gc_init = nft_pipapo_gc_init, .commit = nft_pipapo_commit, .abort = nft_pipapo_abort, + .abort_skip_removal = true, .elemsize = offsetof(struct nft_pipapo_elem, ext), }, }; diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 15203c5855eb..c1791b136620 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -6321,6 +6321,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS), SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x0840, "Acer Aspire E1", ALC269VB_FIXUP_ASPIRE_E1_COEF), + SND_PCI_QUIRK(0x1025, 0x0943, "Acer Aspire V3-572G", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x100c, "Acer Aspire E5-574G", ALC255_FIXUP_ACER_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1025, 0x101c, "Acer Veriton N2510G", ALC269_FIXUP_LIFEBOOK), SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE), -- 2.53.0