From 563de69949878104561be6bea944883ad72e09dd Mon Sep 17 00:00:00 2001 From: Peter Jung Date: Fri, 6 Feb 2026 18:45:27 +0100 Subject: [PATCH 07/11] 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/android/binder/thread.rs | 59 ++++++++++++++----------- drivers/bluetooth/btusb.c | 2 + drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 3 -- drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 58 +++++++----------------- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 7 --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 4 -- drivers/gpu/drm/i915/gt/intel_rc6.c | 13 +++++- drivers/usb/core/quirks.c | 9 ++++ include/linux/perf_event.h | 2 +- include/linux/sched/mm.h | 10 ++--- include/linux/tick.h | 4 +- include/linux/vtime.h | 8 ++-- kernel/sched/core.c | 19 +++----- kernel/sched/fair.c | 11 ++--- kernel/sched/sched.h | 24 +++++----- 23 files changed, 143 insertions(+), 150 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 5d46709c58d0..1bf7f64e321f 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 5d221709353e..cb715e8e75e4 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -970,27 +970,6 @@ 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/android/binder/thread.rs b/drivers/android/binder/thread.rs index 7e34ccd394f8..33a9053b6adf 100644 --- a/drivers/android/binder/thread.rs +++ b/drivers/android/binder/thread.rs @@ -69,17 +69,24 @@ struct ScatterGatherEntry { } /// This entry specifies that a fixup should happen at `target_offset` of the -/// buffer. If `skip` is nonzero, then the fixup is a `binder_fd_array_object` -/// and is applied later. Otherwise if `skip` is zero, then the size of the -/// fixup is `sizeof::()` and `pointer_value` is written to the buffer. -struct PointerFixupEntry { - /// The number of bytes to skip, or zero for a `binder_buffer_object` fixup. - skip: usize, - /// The translated pointer to write when `skip` is zero. - pointer_value: u64, - /// The offset at which the value should be written. The offset is relative - /// to the original buffer. - target_offset: usize, +/// buffer. +enum PointerFixupEntry { + /// A fixup for a `binder_buffer_object`. + Fixup { + /// The translated pointer to write. + pointer_value: u64, + /// The offset at which the value should be written. The offset is relative + /// to the original buffer. + target_offset: usize, + }, + /// A skip for a `binder_fd_array_object`. + Skip { + /// The number of bytes to skip. + skip: usize, + /// The offset at which the skip should happen. The offset is relative + /// to the original buffer. + target_offset: usize, + }, } /// Return type of `apply_and_validate_fixup_in_parent`. @@ -762,8 +769,7 @@ fn translate_object( parent_entry.fixup_min_offset = info.new_min_offset; parent_entry.pointer_fixups.push( - PointerFixupEntry { - skip: 0, + PointerFixupEntry::Fixup { pointer_value: buffer_ptr_in_user_space, target_offset: info.target_offset, }, @@ -807,9 +813,8 @@ fn translate_object( parent_entry .pointer_fixups .push( - PointerFixupEntry { + PointerFixupEntry::Skip { skip: fds_len, - pointer_value: 0, target_offset: info.target_offset, }, GFP_KERNEL, @@ -871,17 +876,21 @@ fn apply_sg(&self, alloc: &mut Allocation, sg_state: &mut ScatterGatherState) -> let mut reader = UserSlice::new(UserPtr::from_addr(sg_entry.sender_uaddr), sg_entry.length).reader(); for fixup in &mut sg_entry.pointer_fixups { - let fixup_len = if fixup.skip == 0 { - size_of::() - } else { - fixup.skip + let (fixup_len, fixup_offset) = match fixup { + PointerFixupEntry::Fixup { target_offset, .. } => { + (size_of::(), *target_offset) + } + PointerFixupEntry::Skip { + skip, + target_offset, + } => (*skip, *target_offset), }; - let target_offset_end = fixup.target_offset.checked_add(fixup_len).ok_or(EINVAL)?; - if fixup.target_offset < end_of_previous_fixup || offset_end < target_offset_end { + let target_offset_end = fixup_offset.checked_add(fixup_len).ok_or(EINVAL)?; + if fixup_offset < end_of_previous_fixup || offset_end < target_offset_end { pr_warn!( "Fixups oob {} {} {} {}", - fixup.target_offset, + fixup_offset, end_of_previous_fixup, offset_end, target_offset_end @@ -890,13 +899,13 @@ fn apply_sg(&self, alloc: &mut Allocation, sg_state: &mut ScatterGatherState) -> } let copy_off = end_of_previous_fixup; - let copy_len = fixup.target_offset - end_of_previous_fixup; + let copy_len = fixup_offset - end_of_previous_fixup; if let Err(err) = alloc.copy_into(&mut reader, copy_off, copy_len) { pr_warn!("Failed copying into alloc: {:?}", err); return Err(err.into()); } - if fixup.skip == 0 { - let res = alloc.write::(fixup.target_offset, &fixup.pointer_value); + if let PointerFixupEntry::Fixup { pointer_value, .. } = fixup { + let res = alloc.write::(fixup_offset, pointer_value); if let Err(err) = res { pr_warn!("Failed copying ptr into alloc: {:?}", err); return Err(err.into()); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 3420f711f0f0..41445e328cce 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -557,6 +557,8 @@ 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 }, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 8410822097b7..7d5317c0778b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2344,9 +2344,6 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, return -ENODEV; } - if (amdgpu_aspm == -1 && !pcie_aspm_enabled(pdev)) - amdgpu_aspm = 0; - if (amdgpu_virtual_display || amdgpu_device_asic_has_dc_support(pdev, flags & AMD_ASIC_MASK)) supports_atomic = true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index 3ef5bc95642c..9cab36322c16 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -201,58 +201,34 @@ static int amdgpu_vmid_grab_idle(struct amdgpu_ring *ring, struct amdgpu_device *adev = ring->adev; unsigned vmhub = ring->vm_hub; struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub]; - struct dma_fence **fences; - unsigned i; + /* If anybody is waiting for a VMID let everybody wait for fairness */ if (!dma_fence_is_signaled(ring->vmid_wait)) { *fence = dma_fence_get(ring->vmid_wait); return 0; } - fences = kmalloc_array(id_mgr->num_ids, sizeof(void *), GFP_NOWAIT); - if (!fences) - return -ENOMEM; - /* Check if we have an idle VMID */ - i = 0; - list_for_each_entry((*idle), &id_mgr->ids_lru, list) { + list_for_each_entry_reverse((*idle), &id_mgr->ids_lru, list) { /* Don't use per engine and per process VMID at the same time */ struct amdgpu_ring *r = adev->vm_manager.concurrent_flush ? NULL : ring; - fences[i] = amdgpu_sync_peek_fence(&(*idle)->active, r); - if (!fences[i]) - break; - ++i; + *fence = amdgpu_sync_peek_fence(&(*idle)->active, r); + if (!(*fence)) + return 0; } - /* If we can't find a idle VMID to use, wait till one becomes available */ - if (&(*idle)->list == &id_mgr->ids_lru) { - u64 fence_context = adev->vm_manager.fence_context + ring->idx; - unsigned seqno = ++adev->vm_manager.seqno[ring->idx]; - struct dma_fence_array *array; - unsigned j; - - *idle = NULL; - for (j = 0; j < i; ++j) - dma_fence_get(fences[j]); - - array = dma_fence_array_create(i, fences, fence_context, - seqno, true); - if (!array) { - for (j = 0; j < i; ++j) - dma_fence_put(fences[j]); - kfree(fences); - return -ENOMEM; - } - - *fence = dma_fence_get(&array->base); - dma_fence_put(ring->vmid_wait); - ring->vmid_wait = &array->base; - return 0; - } - kfree(fences); + /* + * If we can't find a idle VMID to use, wait on a fence from the least + * recently used in the hope that it will be available soon. + */ + *idle = NULL; + dma_fence_put(ring->vmid_wait); + ring->vmid_wait = dma_fence_get(*fence); + /* This is the reference we return */ + dma_fence_get(*fence); return 0; } @@ -313,7 +289,7 @@ static int amdgpu_vmid_grab_reserved(struct amdgpu_vm *vm, * user of the VMID. */ r = amdgpu_sync_fence(&(*id)->active, &job->base.s_fence->finished, - GFP_NOWAIT); + GFP_ATOMIC); if (r) return r; @@ -373,7 +349,7 @@ static int amdgpu_vmid_grab_used(struct amdgpu_vm *vm, */ r = amdgpu_sync_fence(&(*id)->active, &job->base.s_fence->finished, - GFP_NOWAIT); + GFP_ATOMIC); if (r) return r; @@ -426,7 +402,7 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring, /* Remember this submission as user of the VMID */ r = amdgpu_sync_fence(&id->active, &job->base.s_fence->finished, - GFP_NOWAIT); + GFP_ATOMIC); if (r) goto error; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 3d2f9d0e2d23..63e49577a5b2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2830,8 +2830,6 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) */ void amdgpu_vm_manager_init(struct amdgpu_device *adev) { - unsigned i; - /* Concurrent flushes are only possible starting with Vega10 and * are broken on Navi10 and Navi14. */ @@ -2840,11 +2838,6 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev) adev->asic_type == CHIP_NAVI14); amdgpu_vmid_mgr_init(adev); - adev->vm_manager.fence_context = - dma_fence_context_alloc(AMDGPU_MAX_RINGS); - for (i = 0; i < AMDGPU_MAX_RINGS; ++i) - adev->vm_manager.seqno[i] = 0; - spin_lock_init(&adev->vm_manager.prt_lock); atomic_set(&adev->vm_manager.num_prt_users, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index cf0ec94e8a07..15d757c016cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -453,10 +453,6 @@ struct amdgpu_vm_manager { unsigned int first_kfd_vmid; bool concurrent_flush; - /* Handling of VM fences */ - u64 fence_context; - unsigned seqno[AMDGPU_MAX_RINGS]; - uint64_t max_pfn; uint32_t num_level; uint32_t block_size; diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index bf38cc5fe872..787b3fd2925c 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 "gem/i915_gem_region.h" #include "i915_drv.h" @@ -494,6 +494,17 @@ 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/usb/core/quirks.c b/drivers/usb/core/quirks.c index c4d85089d19b..3c09bb61ed41 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -453,6 +453,15 @@ static const struct usb_device_id usb_quirk_list[] = { /* Elgato 4K X - BOS descriptor fetch hangs at SuperSpeed Plus */ { USB_DEVICE(0x0fd9, 0x009b), .driver_info = USB_QUIRK_NO_BOS }, + /* ASUS TUF 4K PRO - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x0b05, 0x1ab9), .driver_info = USB_QUIRK_NO_BOS }, + + /* Avermedia Live Gamer Ultra 2.1 (GC553G2) + { USB_DEVICE(0x07ca, 0x2553), .driver_info = USB_QUIRK_NO_BOS }, + + /* UGREEN 35871 - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x2b89, 0x5871), .driver_info = USB_QUIRK_NO_BOS }, + /* Sony Xperia XZ1 Compact (lilac) smartphone in fastboot mode */ { USB_DEVICE(0x0fce, 0x0dde), .driver_info = USB_QUIRK_NO_LPM }, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index fd1d91017b99..2b1c752af207 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 a3094379b579..03c68d7fd565 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); @@ -530,7 +530,7 @@ 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/kernel/sched/core.c b/kernel/sched/core.c index e460c22de8ad..3f02e0846e92 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 */ @@ -4948,7 +4943,7 @@ 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 @@ -4964,7 +4959,7 @@ 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; @@ -4999,7 +4994,7 @@ 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; @@ -5029,7 +5024,7 @@ struct balance_callback *splice_balance_callbacks(struct rq *rq) return __splice_balance_callbacks(rq, true); } -static void __balance_callbacks(struct rq *rq) +static __always_inline void __balance_callbacks(struct rq *rq) { do_balance_callbacks(rq, __splice_balance_callbacks(rq, false)); } @@ -5062,7 +5057,7 @@ 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 @@ -5094,7 +5089,7 @@ 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)) @@ -5148,7 +5143,7 @@ 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(); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c975e04753f3..f29c544a6d69 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2460,11 +2460,8 @@ 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; @@ -8383,9 +8380,7 @@ 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 f75ded301e07..a3f52e493b42 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1380,12 +1380,12 @@ 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); } @@ -1394,7 +1394,7 @@ 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; @@ -1402,7 +1402,7 @@ 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; @@ -1493,12 +1493,12 @@ 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; } @@ -1547,20 +1547,24 @@ 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(); -- 2.53.0