From 934914e8d5925aa992068cfe1ba4163dde0da814 Mon Sep 17 00:00:00 2001 From: Peter Jung Date: Fri, 13 Feb 2026 16:52:51 +0100 Subject: [PATCH 4/9] 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 | 6 ++++ drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 +-- drivers/gpu/drm/i915/gt/intel_rc6.c | 13 ++++++++- drivers/net/wireless/realtek/rtl8xxxu/core.c | 1 + drivers/usb/core/quirks.c | 9 ++++++ fs/xfs/scrub/btree.c | 7 +++-- include/linux/perf_event.h | 2 +- include/linux/sched/mm.h | 10 +++---- include/linux/tick.h | 4 +-- include/linux/vtime.h | 8 +++--- io_uring/io-wq.c | 27 ++++++++++++++++-- io_uring/io-wq.h | 1 + io_uring/tctx.c | 11 +++++++ kernel/rcu/tree.c | 12 ++++++++ kernel/sched/core.c | 26 +++++++---------- kernel/sched/ext.c | 4 +-- kernel/sched/fair.c | 11 ++----- kernel/sched/sched.h | 30 ++++++++++++-------- sound/hda/codecs/realtek/alc269.c | 1 + 27 files changed, 163 insertions(+), 84 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 bc94ff1e250a..fcc1a954ccb3 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1035,6 +1035,7 @@ 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), @@ -1056,6 +1057,11 @@ 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 ded09e94d296..0d5eae8295d4 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -527,6 +527,8 @@ static const struct usb_device_id quirks_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x2001, 0x332a), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x7392, 0xe611), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek 8852AE Bluetooth devices */ { USB_DEVICE(0x0bda, 0x2852), .driver_info = BTUSB_REALTEK | @@ -557,6 +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 }, @@ -667,6 +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/net/wireless/realtek/rtl8xxxu/core.c b/drivers/net/wireless/realtek/rtl8xxxu/core.c index c06ad064f37c..f9a527f6a175 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/core.c @@ -7826,6 +7826,7 @@ static int rtl8xxxu_probe(struct usb_interface *interface, goto err_set_intfdata; hw->vif_data_size = sizeof(struct rtl8xxxu_vif); + hw->sta_data_size = sizeof(struct rtl8xxxu_sta_info); hw->wiphy->max_scan_ssids = 1; hw->wiphy->max_scan_ie_len = IEEE80211_MAX_DATA_LEN; 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/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index cd6f0ff382a7..acade92c5fce 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -370,12 +370,15 @@ xchk_btree_check_block_owner( { xfs_agnumber_t agno; xfs_agblock_t agbno; + bool is_bnobt, is_rmapbt; bool init_sa; int error = 0; if (!bs->cur) return 0; + is_bnobt = xfs_btree_is_bno(bs->cur->bc_ops); + is_rmapbt = xfs_btree_is_rmap(bs->cur->bc_ops); agno = xfs_daddr_to_agno(bs->cur->bc_mp, daddr); agbno = xfs_daddr_to_agbno(bs->cur->bc_mp, daddr); @@ -398,11 +401,11 @@ xchk_btree_check_block_owner( * have to nullify it (to shut down further block owner checks) if * self-xref encounters problems. */ - if (!bs->sc->sa.bno_cur && xfs_btree_is_bno(bs->cur->bc_ops)) + if (!bs->sc->sa.bno_cur && is_bnobt) bs->cur = NULL; xchk_xref_is_only_owned_by(bs->sc, agbno, 1, bs->oinfo); - if (!bs->sc->sa.rmap_cur && xfs_btree_is_rmap(bs->cur->bc_ops)) + if (!bs->sc->sa.rmap_cur && is_rmapbt) bs->cur = NULL; out_free: 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/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/io_uring/io-wq.c b/io_uring/io-wq.c index 2fa7d3601edb..f42d573b5b17 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -34,6 +34,7 @@ enum { enum { IO_WQ_BIT_EXIT = 0, /* wq exiting */ + IO_WQ_BIT_EXIT_ON_IDLE = 1, /* allow all workers to exit on idle */ }; enum { @@ -706,9 +707,13 @@ static int io_wq_worker(void *data) raw_spin_lock(&acct->workers_lock); /* * Last sleep timed out. Exit if we're not the last worker, - * or if someone modified our affinity. + * or if someone modified our affinity. If wq is marked + * idle-exit, drop the worker as well. This is used to avoid + * keeping io-wq workers around for tasks that no longer have + * any active io_uring instances. */ - if (last_timeout && (exit_mask || acct->nr_workers > 1)) { + if ((last_timeout && (exit_mask || acct->nr_workers > 1)) || + test_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state)) { acct->nr_workers--; raw_spin_unlock(&acct->workers_lock); __set_current_state(TASK_RUNNING); @@ -963,6 +968,24 @@ static bool io_wq_worker_wake(struct io_worker *worker, void *data) return false; } +void io_wq_set_exit_on_idle(struct io_wq *wq, bool enable) +{ + if (!wq->task) + return; + + if (!enable) { + clear_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state); + return; + } + + if (test_and_set_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state)) + return; + + rcu_read_lock(); + io_wq_for_each_worker(wq, io_wq_worker_wake, NULL); + rcu_read_unlock(); +} + static void io_run_cancel(struct io_wq_work *work, struct io_wq *wq) { do { diff --git a/io_uring/io-wq.h b/io_uring/io-wq.h index 774abab54732..94b14742b703 100644 --- a/io_uring/io-wq.h +++ b/io_uring/io-wq.h @@ -41,6 +41,7 @@ struct io_wq_data { struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data); void io_wq_exit_start(struct io_wq *wq); void io_wq_put_and_exit(struct io_wq *wq); +void io_wq_set_exit_on_idle(struct io_wq *wq, bool enable); void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); void io_wq_hash_work(struct io_wq_work *work, void *val); diff --git a/io_uring/tctx.c b/io_uring/tctx.c index 6d6f44215ec8..91f4b830b77b 100644 --- a/io_uring/tctx.c +++ b/io_uring/tctx.c @@ -122,6 +122,14 @@ int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) return ret; } } + + /* + * Re-activate io-wq keepalive on any new io_uring usage. The wq may have + * been marked for idle-exit when the task temporarily had no active + * io_uring instances. + */ + if (tctx->io_wq) + io_wq_set_exit_on_idle(tctx->io_wq, false); if (!xa_load(&tctx->xa, (unsigned long)ctx)) { node = kmalloc(sizeof(*node), GFP_KERNEL); if (!node) @@ -183,6 +191,9 @@ __cold void io_uring_del_tctx_node(unsigned long index) if (tctx->last == node->ctx) tctx->last = NULL; kfree(node); + + if (xa_empty(&tctx->xa) && tctx->io_wq) + io_wq_set_exit_on_idle(tctx->io_wq, true); } __cold void io_uring_clean_tctx(struct io_uring_task *tctx) 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 854984967fe2..9dc6e37dcad1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -678,11 +678,6 @@ 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 */ @@ -4869,7 +4864,7 @@ 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 @@ -4885,7 +4880,7 @@ 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; @@ -4920,7 +4915,7 @@ 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; @@ -4950,7 +4945,7 @@ 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); @@ -4987,7 +4982,7 @@ 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 @@ -5019,7 +5014,7 @@ 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)) @@ -5072,7 +5067,7 @@ 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(); @@ -10729,10 +10724,9 @@ void sched_mm_cid_exit(struct task_struct *t) return; /* * Mode change. The task has the CID unset - * already. The CPU CID is still valid and - * does not have MM_CID_TRANSIT set as the - * mode change has just taken effect under - * mm::mm_cid::lock. Drop it. + * already and dealt with an eventually set + * TRANSIT bit. If the CID is owned by the CPU + * then drop it. */ mm_drop_cid_on_cpu(mm, this_cpu_ptr(mm->mm_cid.pcpu)); } 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..3263819effb7 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 */ diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 816db1bc5629..c00b1be1224a 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1403,12 +1403,12 @@ 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 +1417,7 @@ 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 +1425,7 @@ 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 +1519,12 @@ 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 +1573,24 @@ 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(); @@ -3758,8 +3762,10 @@ static __always_inline void mm_unset_cid_on_task(struct task_struct *t) static __always_inline void mm_drop_cid_on_cpu(struct mm_struct *mm, struct mm_cid_pcpu *pcp) { /* Clear the ONCPU bit, but do not set UNSET in the per CPU storage */ - pcp->cid = cpu_cid_to_cid(pcp->cid); - mm_drop_cid(mm, pcp->cid); + if (cid_on_cpu(pcp->cid)) { + pcp->cid = cpu_cid_to_cid(pcp->cid); + mm_drop_cid(mm, pcp->cid); + } } static inline unsigned int __mm_get_cid(struct mm_struct *mm, unsigned int max_cids) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index b66965a52107..9afa52ff5e0c 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -7057,6 +7057,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc886, "Samsung Galaxy Book3 Pro (NP964XFG)", ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS), SND_PCI_QUIRK(0x144d, 0xc1ca, "Samsung Galaxy Book3 Pro 360 (NP960QFG)", ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS), SND_PCI_QUIRK(0x144d, 0xc1cc, "Samsung Galaxy Book3 Ultra (NT960XFH)", ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS), + SND_PCI_QUIRK(0x1458, 0x900e, "Gigabyte G5 KF5 (2023)", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), -- 2.53.0