@ arch/arm/Kconfig:43 @ config ARM select ARCH_SUPPORTS_CFI_CLANG select ARCH_SUPPORTS_HUGETLBFS if ARM_LPAE select ARCH_SUPPORTS_PER_VMA_LOCK + select ARCH_SUPPORTS_RT if HAVE_POSIX_CPU_TIMERS_TASK_WORK select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_USE_MEMTEST @ arch/arm/Kconfig:83 @ config ARM select HAS_IOPORT select HAVE_ARCH_AUDITSYSCALL if AEABI && !OABI_COMPAT select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 - select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU + select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU && !PREEMPT_RT select HAVE_ARCH_KFENCE if MMU && !XIP_KERNEL select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL @ arch/arm/Kconfig:107 @ config ARM select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU select HAVE_EXIT_THREAD - select HAVE_GUP_FAST if ARM_LPAE + select HAVE_GUP_FAST if ARM_LPAE && !(PREEMPT_RT && HIGHPTE) select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_TRACER @ arch/arm/Kconfig:131 @ config ARM select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_POSIX_CPU_TIMERS_TASK_WORK if !KVM select MMU_GATHER_RCU_TABLE_FREE if SMP && ARM_LPAE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RSEQ @ arch/arm/mm/fault.c:477 @ do_translation_fault(unsigned long addr, unsigned int fsr, if (addr < TASK_SIZE) return do_page_fault(addr, fsr, regs); + if (interrupts_enabled(regs)) + local_irq_enable(); + if (user_mode(regs)) goto bad_area; @ arch/arm/mm/fault.c:550 @ do_translation_fault(unsigned long addr, unsigned int fsr, static int do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { + if (interrupts_enabled(regs)) + local_irq_enable(); + do_bad_area(addr, fsr, regs); return 0; } @ arch/arm/vfp/vfpmodule.c:58 @ extern unsigned int VFP_arch_feroceon __alias(VFP_arch); */ union vfp_state *vfp_current_hw_state[NR_CPUS]; +/* + * Claim ownership of the VFP unit. + * + * The caller may change VFP registers until vfp_state_release() is called. + * + * local_bh_disable() is used to disable preemption and to disable VFP + * processing in softirq context. On PREEMPT_RT kernels local_bh_disable() is + * not sufficient because it only serializes soft interrupt related sections + * via a local lock, but stays preemptible. Disabling preemption is the right + * choice here as bottom half processing is always in thread context on RT + * kernels so it implicitly prevents bottom half processing as well. + */ +static void vfp_state_hold(void) +{ + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_bh_disable(); + else + preempt_disable(); +} + +static void vfp_state_release(void) +{ + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_bh_enable(); + else + preempt_enable(); +} + /* * Is 'thread's most up to date state stored in this CPUs hardware? * Must be called from non-preemptible context. @ arch/arm/vfp/vfpmodule.c:271 @ static void vfp_panic(char *reason, u32 inst) /* * Process bitmask of exception conditions. */ -static void vfp_raise_exceptions(u32 exceptions, u32 inst, u32 fpscr, struct pt_regs *regs) +static int vfp_raise_exceptions(u32 exceptions, u32 inst, u32 fpscr) { int si_code = 0; @ arch/arm/vfp/vfpmodule.c:279 @ static void vfp_raise_exceptions(u32 exceptions, u32 inst, u32 fpscr, struct pt_ if (exceptions == VFP_EXCEPTION_ERROR) { vfp_panic("unhandled bounce", inst); - vfp_raise_sigfpe(FPE_FLTINV, regs); - return; + return FPE_FLTINV; } /* @ arch/arm/vfp/vfpmodule.c:307 @ static void vfp_raise_exceptions(u32 exceptions, u32 inst, u32 fpscr, struct pt_ RAISE(FPSCR_OFC, FPSCR_OFE, FPE_FLTOVF); RAISE(FPSCR_IOC, FPSCR_IOE, FPE_FLTINV); - if (si_code) - vfp_raise_sigfpe(si_code, regs); + return si_code; } /* @ arch/arm/vfp/vfpmodule.c:353 @ static u32 vfp_emulate_instruction(u32 inst, u32 fpscr, struct pt_regs *regs) static void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs) { u32 fpscr, orig_fpscr, fpsid, exceptions; + int si_code2 = 0; + int si_code = 0; pr_debug("VFP: bounce: trigger %08x fpexc %08x\n", trigger, fpexc); @ arch/arm/vfp/vfpmodule.c:400 @ static void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs) * unallocated VFP instruction but with FPSCR.IXE set and not * on VFP subarch 1. */ - vfp_raise_exceptions(VFP_EXCEPTION_ERROR, trigger, fpscr, regs); - return; + si_code = vfp_raise_exceptions(VFP_EXCEPTION_ERROR, trigger, fpscr); + goto exit; } /* @ arch/arm/vfp/vfpmodule.c:425 @ static void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs) */ exceptions = vfp_emulate_instruction(trigger, fpscr, regs); if (exceptions) - vfp_raise_exceptions(exceptions, trigger, orig_fpscr, regs); + si_code2 = vfp_raise_exceptions(exceptions, trigger, orig_fpscr); /* * If there isn't a second FP instruction, exit now. Note that * the FPEXC.FP2V bit is valid only if FPEXC.EX is 1. */ if ((fpexc & (FPEXC_EX | FPEXC_FP2V)) != (FPEXC_EX | FPEXC_FP2V)) - return; + goto exit; /* * The barrier() here prevents fpinst2 being read @ arch/arm/vfp/vfpmodule.c:444 @ static void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs) emulate: exceptions = vfp_emulate_instruction(trigger, orig_fpscr, regs); if (exceptions) - vfp_raise_exceptions(exceptions, trigger, orig_fpscr, regs); + si_code = vfp_raise_exceptions(exceptions, trigger, orig_fpscr); +exit: + vfp_state_release(); + if (si_code2) + vfp_raise_sigfpe(si_code2, regs); + if (si_code) + vfp_raise_sigfpe(si_code, regs); } static void vfp_enable(void *unused) @ arch/arm/vfp/vfpmodule.c:549 @ static inline void vfp_pm_init(void) { } */ void vfp_sync_hwstate(struct thread_info *thread) { - unsigned int cpu = get_cpu(); + vfp_state_hold(); - local_bh_disable(); - - if (vfp_state_in_hw(cpu, thread)) { + if (vfp_state_in_hw(raw_smp_processor_id(), thread)) { u32 fpexc = fmrx(FPEXC); /* @ arch/arm/vfp/vfpmodule.c:562 @ void vfp_sync_hwstate(struct thread_info *thread) fmxr(FPEXC, fpexc); } - local_bh_enable(); - put_cpu(); + vfp_state_release(); } /* Ensure that the thread reloads the hardware VFP state on the next use. */ @ arch/arm/vfp/vfpmodule.c:717 @ static int vfp_support_entry(struct pt_regs *regs, u32 trigger) if (!user_mode(regs)) return vfp_kmode_exception(regs, trigger); - local_bh_disable(); + vfp_state_hold(); fpexc = fmrx(FPEXC); /* @ arch/arm/vfp/vfpmodule.c:782 @ static int vfp_support_entry(struct pt_regs *regs, u32 trigger) * replay the instruction that trapped. */ fmxr(FPEXC, fpexc); + vfp_state_release(); } else { /* Check for synchronous or asynchronous exceptions */ if (!(fpexc & (FPEXC_EX | FPEXC_DEX))) { @ arch/arm/vfp/vfpmodule.c:797 @ static int vfp_support_entry(struct pt_regs *regs, u32 trigger) if (!(fpscr & FPSCR_IXE)) { if (!(fpscr & FPSCR_LENGTH_MASK)) { pr_debug("not VFP\n"); - local_bh_enable(); + vfp_state_release(); return -ENOEXEC; } fpexc |= FPEXC_DEX; } } bounce: regs->ARM_pc += 4; + /* VFP_bounce() will invoke vfp_state_release() */ VFP_bounce(trigger, fpexc, regs); } - local_bh_enable(); return 0; } @ arch/arm/vfp/vfpmodule.c:872 @ void kernel_neon_begin(void) unsigned int cpu; u32 fpexc; - local_bh_disable(); + vfp_state_hold(); /* * Kernel mode NEON is only allowed outside of hardirq context with @ arch/arm/vfp/vfpmodule.c:903 @ void kernel_neon_end(void) { /* Disable the NEON/VFP unit. */ fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN); - local_bh_enable(); + vfp_state_release(); } EXPORT_SYMBOL(kernel_neon_end); @ arch/powerpc/Kconfig:171 @ config PPC select ARCH_STACKWALK select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEBUG_PAGEALLOC if PPC_BOOK3S || PPC_8xx + select ARCH_SUPPORTS_RT if HAVE_POSIX_CPU_TIMERS_TASK_WORK select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if PPC64 select ARCH_USE_MEMTEST @ arch/powerpc/Kconfig:273 @ config PPC select HAVE_PERF_EVENTS_NMI if PPC64 select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_POSIX_CPU_TIMERS_TASK_WORK if !KVM select HAVE_RETHOOK if KPROBES select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE @ arch/powerpc/include/asm/stackprotector.h:22 @ */ static __always_inline void boot_init_stack_canary(void) { - unsigned long canary = get_random_canary(); + unsigned long canary; +#ifndef CONFIG_PREEMPT_RT + canary = get_random_canary(); +#else + canary = ((unsigned long)&canary) & CANARY_MASK; +#endif current->stack_canary = canary; #ifdef CONFIG_PPC64 get_paca()->canary = canary; @ arch/powerpc/kernel/traps.c:264 @ static char *get_mmu_str(void) static int __die(const char *str, struct pt_regs *regs, long err) { + const char *pr = ""; + printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); + if (IS_ENABLED(CONFIG_PREEMPTION)) + pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT"; + printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s %s\n", IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE", PAGE_SIZE / 1024, get_mmu_str(), - IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "", + pr, IS_ENABLED(CONFIG_SMP) ? " SMP" : "", IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "", debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "", @ arch/powerpc/kvm/Kconfig:224 @ config KVM_E500MC config KVM_MPIC bool "KVM in-kernel MPIC emulation" depends on KVM && PPC_E500 + depends on !PREEMPT_RT select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQ_ROUTING select HAVE_KVM_MSI @ arch/powerpc/platforms/pseries/Kconfig:5 @ config PPC_PSERIES depends on PPC64 && PPC_BOOK3S bool "IBM pSeries & new (POWER5-based) iSeries" + select GENERIC_ALLOCATOR select HAVE_PCSPKR_PLATFORM select MPIC select OF_DYNAMIC @ arch/powerpc/platforms/pseries/iommu.c:29 @ #include <linux/of_address.h> #include <linux/iommu.h> #include <linux/rculist.h> +#include <linux/local_lock.h> #include <asm/io.h> #include <asm/prom.h> #include <asm/rtas.h> @ arch/powerpc/platforms/pseries/iommu.c:248 @ static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift, return ret; } -static DEFINE_PER_CPU(__be64 *, tce_page); +struct tce_page { + __be64 * page; + local_lock_t lock; +}; +static DEFINE_PER_CPU(struct tce_page, tce_page) = { + .lock = INIT_LOCAL_LOCK(lock), +}; static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages, unsigned long uaddr, @ arch/powerpc/platforms/pseries/iommu.c:277 @ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, direction, attrs); } - local_irq_save(flags); /* to protect tcep and the page behind it */ + /* to protect tcep and the page behind it */ + local_lock_irqsave(&tce_page.lock, flags); - tcep = __this_cpu_read(tce_page); + tcep = __this_cpu_read(tce_page.page); /* This is safe to do since interrupts are off when we're called * from iommu_alloc{,_sg}() @ arch/powerpc/platforms/pseries/iommu.c:289 @ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, tcep = (__be64 *)__get_free_page(GFP_ATOMIC); /* If allocation fails, fall back to the loop implementation */ if (!tcep) { - local_irq_restore(flags); + local_unlock_irqrestore(&tce_page.lock, flags); return tce_build_pSeriesLP(tbl->it_index, tcenum, tceshift, npages, uaddr, direction, attrs); } - __this_cpu_write(tce_page, tcep); + __this_cpu_write(tce_page.page, tcep); } rpn = __pa(uaddr) >> tceshift; @ arch/powerpc/platforms/pseries/iommu.c:324 @ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, tcenum += limit; } while (npages > 0 && !rc); - local_irq_restore(flags); + local_unlock_irqrestore(&tce_page.lock, flags); if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) { ret = (int)rc; @ arch/powerpc/platforms/pseries/iommu.c:508 @ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, DMA_BIDIRECTIONAL, 0); } - local_irq_disable(); /* to protect tcep and the page behind it */ - tcep = __this_cpu_read(tce_page); + /* to protect tcep and the page behind it */ + local_lock_irq(&tce_page.lock); + tcep = __this_cpu_read(tce_page.page); if (!tcep) { tcep = (__be64 *)__get_free_page(GFP_ATOMIC); if (!tcep) { - local_irq_enable(); + local_unlock_irq(&tce_page.lock); return -ENOMEM; } - __this_cpu_write(tce_page, tcep); + __this_cpu_write(tce_page.page, tcep); } proto_tce = TCE_PCI_READ | TCE_PCI_WRITE; @ arch/powerpc/platforms/pseries/iommu.c:561 @ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, /* error cleanup: caller will clear whole range */ - local_irq_enable(); + local_unlock_irq(&tce_page.lock); return rc; } @ arch/riscv/Kconfig:42 @ config RISCV select ARCH_HAS_MMIOWB select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PMEM_API + select ARCH_HAS_PREEMPT_LAZY select ARCH_HAS_PREPARE_SYNC_CORE_CMD select ARCH_HAS_PTE_DEVMAP if 64BIT && MMU select ARCH_HAS_PTE_SPECIAL @ arch/riscv/include/asm/thread_info.h:110 @ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); * - pending work-to-be-done flags are in lowest half-word * - other flags in upper half-word(s) */ -#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ -#define TIF_SIGPENDING 2 /* signal pending */ -#define TIF_NEED_RESCHED 3 /* rescheduling necessary */ +#define TIF_NEED_RESCHED 0 /* rescheduling necessary */ +#define TIF_NEED_RESCHED_LAZY 1 /* Lazy rescheduling needed */ +#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ +#define TIF_SIGPENDING 3 /* signal pending */ #define TIF_RESTORE_SIGMASK 4 /* restore signal mask in do_signal() */ #define TIF_MEMDIE 5 /* is terminating due to OOM killer */ #define TIF_NOTIFY_SIGNAL 9 /* signal notifications exist */ @ arch/riscv/include/asm/thread_info.h:121 @ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #define TIF_32BIT 11 /* compat-mode 32bit process */ #define TIF_RISCV_V_DEFER_RESTORE 12 /* restore Vector before returing to user */ +#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) -#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_RISCV_V_DEFER_RESTORE (1 << TIF_RISCV_V_DEFER_RESTORE) @ arch/x86/Kconfig:96 @ config X86 select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PMEM_API if X86_64 + select ARCH_HAS_PREEMPT_LAZY select ARCH_HAS_PTE_DEVMAP if X86_64 select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_HW_PTE_YOUNG @ arch/x86/include/asm/thread_info.h:90 @ struct thread_info { #define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ -#define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/ -#define TIF_SSBD 5 /* Speculative store bypass disable */ +#define TIF_NEED_RESCHED_LAZY 4 /* rescheduling necessary */ +#define TIF_SINGLESTEP 5 /* reenable singlestep on user return*/ +#define TIF_SSBD 6 /* Speculative store bypass disable */ #define TIF_SPEC_IB 9 /* Indirect branch speculation mitigation */ #define TIF_SPEC_L1D_FLUSH 10 /* Flush L1D on mm switches (processes) */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ @ arch/x86/include/asm/thread_info.h:114 @ struct thread_info { #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_SSBD (1 << TIF_SSBD) #define _TIF_SPEC_IB (1 << TIF_SPEC_IB) @ drivers/gpu/drm/i915/Kconfig:6 @ config DRM_I915 tristate "Intel 8xx/9xx/G3x/G4x/HD Graphics" depends on DRM depends on X86 && PCI - depends on !PREEMPT_RT select INTEL_GTT if X86 select INTERVAL_TREE # we need shmfs for the swappable backing store, and in particular @ drivers/gpu/drm/i915/display/intel_crtc.c:524 @ void intel_pipe_update_start(struct intel_atomic_state *state, */ intel_psr_wait_for_idle_locked(new_crtc_state); - local_irq_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_disable(); crtc->debug.min_vbl = evade.min; crtc->debug.max_vbl = evade.max; @ drivers/gpu/drm/i915/display/intel_crtc.c:543 @ void intel_pipe_update_start(struct intel_atomic_state *state, return; irq_disable: - local_irq_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_disable(); } #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_VBLANK_EVADE) @ drivers/gpu/drm/i915/display/intel_crtc.c:673 @ void intel_pipe_update_end(struct intel_atomic_state *state, */ intel_vrr_send_push(new_crtc_state); - local_irq_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_enable(); if (intel_vgpu_active(dev_priv)) goto out; @ drivers/gpu/drm/i915/display/intel_cursor.c:898 @ intel_legacy_cursor_update(struct drm_plane *_plane, */ intel_psr_wait_for_idle_locked(crtc_state); - local_irq_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_disable(); intel_vblank_evade(&evade); drm_crtc_vblank_put(&crtc->base); } else { - local_irq_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_disable(); } if (new_plane_state->uapi.visible) { @ drivers/gpu/drm/i915/display/intel_cursor.c:916 @ intel_legacy_cursor_update(struct drm_plane *_plane, intel_plane_disable_arm(plane, crtc_state); } - local_irq_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_enable(); intel_psr_unlock(crtc_state); @ drivers/gpu/drm/i915/display/intel_display_trace.h:12 @ #if !defined(__INTEL_DISPLAY_TRACE_H__) || defined(TRACE_HEADER_MULTI_READ) #define __INTEL_DISPLAY_TRACE_H__ +#if defined(CONFIG_PREEMPT_RT) && !defined(NOTRACE) +#define NOTRACE +#endif + #include <linux/string_helpers.h> #include <linux/types.h> #include <linux/tracepoint.h> @ drivers/gpu/drm/i915/display/intel_vblank.c:311 @ static void intel_vblank_section_exit(struct intel_display *display) struct drm_i915_private *i915 = to_i915(display->drm); spin_unlock(&i915->uncore.lock); } + +static void intel_vblank_section_enter_irqf(struct intel_display *display, unsigned long *flags) + __acquires(i915->uncore.lock) +{ + struct drm_i915_private *i915 = to_i915(display->drm); + spin_lock_irqsave(&i915->uncore.lock, *flags); +} + +static void intel_vblank_section_exit_irqf(struct intel_display *display, unsigned long flags) + __releases(i915->uncore.lock) +{ + struct drm_i915_private *i915 = to_i915(display->drm); + spin_unlock_irqrestore(&i915->uncore.lock, flags); +} #else static void intel_vblank_section_enter(struct intel_display *display) { @ drivers/gpu/drm/i915/display/intel_vblank.c:333 @ static void intel_vblank_section_enter(struct intel_display *display) static void intel_vblank_section_exit(struct intel_display *display) { } + +static void intel_vblank_section_enter_irqf(struct intel_display *display, unsigned long *flags) +{ + *flags = 0; +} + +static void intel_vblank_section_exit_irqf(struct intel_display *display, unsigned long flags) +{ + if (flags) + return; +} #endif static bool i915_get_crtc_scanoutpos(struct drm_crtc *_crtc, @ drivers/gpu/drm/i915/display/intel_vblank.c:381 @ static bool i915_get_crtc_scanoutpos(struct drm_crtc *_crtc, * timing critical raw register reads, potentially with * preemption disabled, so the following code must not block. */ - local_irq_save(irqflags); - intel_vblank_section_enter(display); + intel_vblank_section_enter_irqf(display, &irqflags); - /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); /* Get optional system timestamp before query. */ if (stime) @ drivers/gpu/drm/i915/display/intel_vblank.c:448 @ static bool i915_get_crtc_scanoutpos(struct drm_crtc *_crtc, if (etime) *etime = ktime_get(); - /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); - intel_vblank_section_exit(display); - local_irq_restore(irqflags); + intel_vblank_section_exit_irqf(display, irqflags); /* * While in vblank, position will be negative @ drivers/gpu/drm/i915/display/intel_vblank.c:489 @ int intel_get_crtc_scanline(struct intel_crtc *crtc) unsigned long irqflags; int position; - local_irq_save(irqflags); - intel_vblank_section_enter(display); + intel_vblank_section_enter_irqf(display, &irqflags); position = __intel_get_crtc_scanline(crtc); - intel_vblank_section_exit(display); - local_irq_restore(irqflags); + intel_vblank_section_exit_irqf(display, irqflags); return position; } @ drivers/gpu/drm/i915/display/intel_vblank.c:714 @ int intel_vblank_evade(struct intel_vblank_evade_ctx *evade) break; } - local_irq_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_enable(); timeout = schedule_timeout(timeout); - local_irq_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_disable(); } finish_wait(wq, &wait); @ drivers/gpu/drm/i915/gt/intel_execlists_submission.c:1306 @ static void execlists_dequeue(struct intel_engine_cs *engine) * and context switches) submission. */ - spin_lock(&sched_engine->lock); + spin_lock_irq(&sched_engine->lock); /* * If the queue is higher priority than the last @ drivers/gpu/drm/i915/gt/intel_execlists_submission.c:1406 @ static void execlists_dequeue(struct intel_engine_cs *engine) * Even if ELSP[1] is occupied and not worthy * of timeslices, our queue might be. */ - spin_unlock(&sched_engine->lock); + spin_unlock_irq(&sched_engine->lock); return; } } @ drivers/gpu/drm/i915/gt/intel_execlists_submission.c:1432 @ static void execlists_dequeue(struct intel_engine_cs *engine) if (last && !can_merge_rq(last, rq)) { spin_unlock(&ve->base.sched_engine->lock); - spin_unlock(&engine->sched_engine->lock); + spin_unlock_irq(&engine->sched_engine->lock); return; /* leave this for another sibling */ } @ drivers/gpu/drm/i915/gt/intel_execlists_submission.c:1594 @ static void execlists_dequeue(struct intel_engine_cs *engine) */ sched_engine->queue_priority_hint = queue_prio(sched_engine); i915_sched_engine_reset_on_empty(sched_engine); - spin_unlock(&sched_engine->lock); + spin_unlock_irq(&sched_engine->lock); /* * We can skip poking the HW if we ended up with exactly the same set @ drivers/gpu/drm/i915/gt/intel_execlists_submission.c:1620 @ static void execlists_dequeue(struct intel_engine_cs *engine) } } -static void execlists_dequeue_irq(struct intel_engine_cs *engine) -{ - local_irq_disable(); /* Suspend interrupts across request submission */ - execlists_dequeue(engine); - local_irq_enable(); /* flush irq_work (e.g. breadcrumb enabling) */ -} - static void clear_ports(struct i915_request **ports, int count) { memset_p((void **)ports, NULL, count); @ drivers/gpu/drm/i915/gt/intel_execlists_submission.c:2474 @ static void execlists_submission_tasklet(struct tasklet_struct *t) } if (!engine->execlists.pending[0]) { - execlists_dequeue_irq(engine); + execlists_dequeue(engine); start_timeslice(engine); } @ drivers/gpu/drm/i915/gt/uc/intel_guc.h:365 @ static inline int intel_guc_send_busy_loop(struct intel_guc *guc, { int err; unsigned int sleep_period_ms = 1; - bool not_atomic = !in_atomic() && !irqs_disabled(); + bool not_atomic = !in_atomic() && !irqs_disabled() && !rcu_preempt_depth(); /* * FIXME: Have caller pass in if we are in an atomic context to avoid @ drivers/gpu/drm/i915/i915_request.c:611 @ bool __i915_request_submit(struct i915_request *request) RQ_TRACE(request, "\n"); - GEM_BUG_ON(!irqs_disabled()); lockdep_assert_held(&engine->sched_engine->lock); /* @ drivers/gpu/drm/i915/i915_request.c:719 @ void __i915_request_unsubmit(struct i915_request *request) */ RQ_TRACE(request, "\n"); - GEM_BUG_ON(!irqs_disabled()); lockdep_assert_held(&engine->sched_engine->lock); /* @ drivers/gpu/drm/i915/i915_trace.h:9 @ #if !defined(_I915_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) #define _I915_TRACE_H_ +#if defined(CONFIG_PREEMPT_RT) && !defined(NOTRACE) +#define NOTRACE +#endif + #include <linux/stringify.h> #include <linux/types.h> #include <linux/tracepoint.h> @ drivers/gpu/drm/i915/i915_utils.h:272 @ wait_remaining_ms_from_jiffies(unsigned long timestamp_jiffies, int to_wait_ms) (Wmax)) #define wait_for(COND, MS) _wait_for((COND), (MS) * 1000, 10, 1000) -/* If CONFIG_PREEMPT_COUNT is disabled, in_atomic() always reports false. */ -#if defined(CONFIG_DRM_I915_DEBUG) && defined(CONFIG_PREEMPT_COUNT) +/* + * If CONFIG_PREEMPT_COUNT is disabled, in_atomic() always reports false. + * On PREEMPT_RT the context isn't becoming atomic because it is used in an + * interrupt handler or because a spinlock_t is acquired. This leads to + * warnings which don't occur otherwise and therefore the check is disabled. + */ +#if defined(CONFIG_DRM_I915_DEBUG) && defined(CONFIG_PREEMPT_COUNT) && !defined(CONFIG_PREEMPT_RT) # define _WAIT_FOR_ATOMIC_CHECK(ATOMIC) WARN_ON_ONCE((ATOMIC) && !in_atomic()) #else # define _WAIT_FOR_ATOMIC_CHECK(ATOMIC) do { } while (0) @ drivers/tty/serial/8250/8250_core.c:391 @ void __init serial8250_register_ports(struct uart_driver *drv, struct device *de #ifdef CONFIG_SERIAL_8250_CONSOLE +#ifdef CONFIG_SERIAL_8250_LEGACY_CONSOLE static void univ8250_console_write(struct console *co, const char *s, unsigned int count) { @ drivers/tty/serial/8250/8250_core.c:399 @ static void univ8250_console_write(struct console *co, const char *s, serial8250_console_write(up, s, count); } +#else +static void univ8250_console_write_atomic(struct console *co, + struct nbcon_write_context *wctxt) +{ + struct uart_8250_port *up = &serial8250_ports[co->index]; + + serial8250_console_write_atomic(up, wctxt); +} + +static void univ8250_console_write_thread(struct console *co, + struct nbcon_write_context *wctxt) +{ + struct uart_8250_port *up = &serial8250_ports[co->index]; + + serial8250_console_write_thread(up, wctxt); +} + +static void univ8250_console_device_lock(struct console *con, unsigned long *flags) +{ + struct uart_port *up = &serial8250_ports[con->index].port; + + __uart_port_lock_irqsave(up, flags); +} + +static void univ8250_console_device_unlock(struct console *con, unsigned long flags) +{ + struct uart_port *up = &serial8250_ports[con->index].port; + + __uart_port_unlock_irqrestore(up, flags); +} +#endif /* CONFIG_SERIAL_8250_LEGACY_CONSOLE */ static int univ8250_console_setup(struct console *co, char *options) { @ drivers/tty/serial/8250/8250_core.c:529 @ static int univ8250_console_match(struct console *co, char *name, int idx, static struct console univ8250_console = { .name = "ttyS", +#ifdef CONFIG_SERIAL_8250_LEGACY_CONSOLE .write = univ8250_console_write, + .flags = CON_PRINTBUFFER | CON_ANYTIME, +#else + .write_atomic = univ8250_console_write_atomic, + .write_thread = univ8250_console_write_thread, + .device_lock = univ8250_console_device_lock, + .device_unlock = univ8250_console_device_unlock, + .flags = CON_PRINTBUFFER | CON_ANYTIME | CON_NBCON, +#endif .device = uart_console_device, .setup = univ8250_console_setup, .exit = univ8250_console_exit, .match = univ8250_console_match, - .flags = CON_PRINTBUFFER | CON_ANYTIME, .index = -1, .data = &serial8250_reg, }; @ drivers/tty/serial/8250/8250_port.c:549 @ static int serial8250_em485_init(struct uart_8250_port *p) if (!p->em485) return -ENOMEM; +#ifndef CONFIG_SERIAL_8250_LEGACY_CONSOLE + if (uart_console(&p->port)) { + dev_warn(p->port.dev, "no atomic printing for rs485 consoles\n"); + p->port.cons->write_atomic = NULL; + } +#endif + hrtimer_init(&p->em485->stop_tx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer_init(&p->em485->start_tx_timer, CLOCK_MONOTONIC, @ drivers/tty/serial/8250/8250_port.c:701 @ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep) serial8250_rpm_put(p); } -static void serial8250_clear_IER(struct uart_8250_port *up) +/* + * Only to be used by write_atomic() and the legacy write(), which do not + * require port lock. + */ +static void __serial8250_clear_IER(struct uart_8250_port *up) { if (up->capabilities & UART_CAP_UUE) serial_out(up, UART_IER, UART_IER_UUE); @ drivers/tty/serial/8250/8250_port.c:713 @ static void serial8250_clear_IER(struct uart_8250_port *up) serial_out(up, UART_IER, 0); } +static inline void serial8250_clear_IER(struct uart_8250_port *up) +{ + /* Port locked to synchronize UART_IER access against the console. */ + lockdep_assert_held_once(&up->port.lock); + + __serial8250_clear_IER(up); +} + #ifdef CONFIG_SERIAL_8250_RSA /* * Attempts to turn on the RSA FIFO. Returns zero on failure. @ drivers/tty/serial/8250/8250_port.c:3291 @ static void serial8250_console_putchar(struct uart_port *port, unsigned char ch) wait_for_xmitr(up, UART_LSR_THRE); serial_port_out(port, UART_TX, ch); + + if (ch == '\n') + up->console_newline_needed = false; + else + up->console_newline_needed = true; } /* @ drivers/tty/serial/8250/8250_port.c:3324 @ static void serial8250_console_restore(struct uart_8250_port *up) serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS); } +#ifdef CONFIG_SERIAL_8250_LEGACY_CONSOLE /* * Print a string to the serial port using the device FIFO * @ drivers/tty/serial/8250/8250_port.c:3383 @ void serial8250_console_write(struct uart_8250_port *up, const char *s, * First save the IER then disable the interrupts */ ier = serial_port_in(port, UART_IER); - serial8250_clear_IER(up); + __serial8250_clear_IER(up); /* check scratch reg to see if port powered off during system sleep */ if (up->canary && (up->canary != serial_port_in(port, UART_SCR))) { @ drivers/tty/serial/8250/8250_port.c:3449 @ void serial8250_console_write(struct uart_8250_port *up, const char *s, if (locked) uart_port_unlock_irqrestore(port, flags); } +#else +void serial8250_console_write_thread(struct uart_8250_port *up, + struct nbcon_write_context *wctxt) +{ + struct uart_8250_em485 *em485 = up->em485; + struct uart_port *port = &up->port; + unsigned int ier; + + touch_nmi_watchdog(); + + if (!nbcon_enter_unsafe(wctxt)) + return; + + /* First save IER then disable the interrupts. */ + ier = serial_port_in(port, UART_IER); + serial8250_clear_IER(up); + + /* Check scratch reg if port powered off during system sleep. */ + if (up->canary && (up->canary != serial_port_in(port, UART_SCR))) { + serial8250_console_restore(up); + up->canary = 0; + } + + if (em485) { + if (em485->tx_stopped) + up->rs485_start_tx(up); + mdelay(port->rs485.delay_rts_before_send); + } + + if (nbcon_exit_unsafe(wctxt)) { + int len = READ_ONCE(wctxt->len); + int i; + + /* + * Write out the message. Toggle unsafe for each byte in order + * to give another (higher priority) context the opportunity + * for a friendly takeover. If such a takeover occurs, this + * context must reacquire ownership in order to perform final + * actions (such as re-enabling the interrupts). + * + * IMPORTANT: wctxt->outbuf and wctxt->len are no longer valid + * after a reacquire so writing the message must be + * aborted. + */ + for (i = 0; i < len; i++) { + if (!nbcon_enter_unsafe(wctxt)) { + nbcon_reacquire_nobuf(wctxt); + break; + } + + uart_console_write(port, wctxt->outbuf + i, 1, serial8250_console_putchar); + + if (!nbcon_exit_unsafe(wctxt)) { + nbcon_reacquire_nobuf(wctxt); + break; + } + } + } else { + nbcon_reacquire_nobuf(wctxt); + } + + while (!nbcon_enter_unsafe(wctxt)) + nbcon_reacquire_nobuf(wctxt); + + /* Finally, wait for transmitter to become empty and restore IER. */ + wait_for_xmitr(up, UART_LSR_BOTH_EMPTY); + if (em485) { + mdelay(port->rs485.delay_rts_after_send); + if (em485->tx_stopped) + up->rs485_stop_tx(up); + } + serial_port_out(port, UART_IER, ier); + + /* + * The receive handling will happen properly because the receive ready + * bit will still be set; it is not cleared on read. However, modem + * control will not, we must call it if we have saved something in the + * saved flags while processing with interrupts off. + */ + if (up->msr_saved_flags) + serial8250_modem_status(up); + + nbcon_exit_unsafe(wctxt); +} + +void serial8250_console_write_atomic(struct uart_8250_port *up, + struct nbcon_write_context *wctxt) +{ + struct uart_port *port = &up->port; + unsigned int ier; + + /* Atomic console not supported for rs485 mode. */ + if (WARN_ON_ONCE(up->em485)) + return; + + touch_nmi_watchdog(); + + if (!nbcon_enter_unsafe(wctxt)) + return; + + /* + * First save IER then disable the interrupts. The special variant to + * clear IER is used because atomic printing may occur without holding + * the port lock. + */ + ier = serial_port_in(port, UART_IER); + __serial8250_clear_IER(up); + + /* Check scratch reg if port powered off during system sleep. */ + if (up->canary && (up->canary != serial_port_in(port, UART_SCR))) { + serial8250_console_restore(up); + up->canary = 0; + } + + if (up->console_newline_needed) + uart_console_write(port, "\n", 1, serial8250_console_putchar); + uart_console_write(port, wctxt->outbuf, wctxt->len, serial8250_console_putchar); + + /* Finally, wait for transmitter to become empty and restore IER. */ + wait_for_xmitr(up, UART_LSR_BOTH_EMPTY); + serial_port_out(port, UART_IER, ier); + + nbcon_exit_unsafe(wctxt); +} +#endif /* CONFIG_SERIAL_8250_LEGACY_CONSOLE */ static unsigned int probe_baud(struct uart_port *port) { @ drivers/tty/serial/8250/8250_port.c:3592 @ static unsigned int probe_baud(struct uart_port *port) int serial8250_console_setup(struct uart_port *port, char *options, bool probe) { + struct uart_8250_port *up = up_to_u8250p(port); int baud = 9600; int bits = 8; int parity = 'n'; @ drivers/tty/serial/8250/8250_port.c:3602 @ int serial8250_console_setup(struct uart_port *port, char *options, bool probe) if (!port->iobase && !port->membase) return -ENODEV; + up->console_newline_needed = false; + if (options) uart_parse_options(options, &baud, &parity, &bits, &flow); else if (probe) @ include/linux/entry-common.h:67 @ #define EXIT_TO_USER_MODE_WORK \ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ - _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \ + _TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | \ + _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \ ARCH_EXIT_TO_USER_MODE_WORK) /** @ include/linux/entry-kvm.h:20 @ #endif #define XFER_TO_GUEST_MODE_WORK \ - (_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL | \ - _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK) + (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | _TIF_SIGPENDING | \ + _TIF_NOTIFY_SIGNAL | _TIF_NOTIFY_RESUME | \ + ARCH_XFER_TO_GUEST_MODE_WORK) struct kvm_vcpu; @ include/linux/interrupt.h:619 @ extern void __raise_softirq_irqoff(unsigned int nr); extern void raise_softirq_irqoff(unsigned int nr); extern void raise_softirq(unsigned int nr); +#ifdef CONFIG_PREEMPT_RT +DECLARE_PER_CPU(struct task_struct *, timersd); +DECLARE_PER_CPU(unsigned long, pending_timer_softirq); + +extern void raise_timer_softirq(void); +extern void raise_hrtimer_softirq(void); + +static inline unsigned int local_pending_timers(void) +{ + return __this_cpu_read(pending_timer_softirq); +} + +#else +static inline void raise_timer_softirq(void) +{ + raise_softirq(TIMER_SOFTIRQ); +} + +static inline void raise_hrtimer_softirq(void) +{ + raise_softirq_irqoff(HRTIMER_SOFTIRQ); +} + +static inline unsigned int local_pending_timers(void) +{ + return local_softirq_pending(); +} +#endif + DECLARE_PER_CPU(struct task_struct *, ksoftirqd); static inline struct task_struct *this_cpu_ksoftirqd(void) @ include/linux/percpu.h:44 @ PCPU_MIN_ALLOC_SHIFT) #ifdef CONFIG_RANDOM_KMALLOC_CACHES -#define PERCPU_DYNAMIC_SIZE_SHIFT 12 +# if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PAGE_SIZE_4KB) +# define PERCPU_DYNAMIC_SIZE_SHIFT 13 +# else +# define PERCPU_DYNAMIC_SIZE_SHIFT 12 +#endif /* LOCKDEP and PAGE_SIZE > 4KiB */ #else #define PERCPU_DYNAMIC_SIZE_SHIFT 10 #endif @ include/linux/preempt.h:489 @ DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable()) extern bool preempt_model_none(void); extern bool preempt_model_voluntary(void); extern bool preempt_model_full(void); +extern bool preempt_model_lazy(void); +extern bool preempt_model_laziest(void); #else @ include/linux/preempt.h:507 @ static inline bool preempt_model_full(void) return IS_ENABLED(CONFIG_PREEMPT); } +static inline bool preempt_model_lazy(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_LAZY); +} +static inline bool preempt_model_laziest(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_LAZIEST); +} + #endif static inline bool preempt_model_rt(void) @ include/linux/preempt.h:533 @ static inline bool preempt_model_rt(void) */ static inline bool preempt_model_preemptible(void) { - return preempt_model_full() || preempt_model_rt(); + return preempt_model_full() || + preempt_model_lazy() || + preempt_model_laziest() || + preempt_model_rt(); } #endif /* __LINUX_PREEMPT_H */ @ include/linux/rwlock_rt.h:27 @ do { \ __rt_rwlock_init(rwl, #rwl, &__key); \ } while (0) -extern void rt_read_lock(rwlock_t *rwlock); +extern void rt_read_lock(rwlock_t *rwlock) __acquires(rwlock); extern int rt_read_trylock(rwlock_t *rwlock); -extern void rt_read_unlock(rwlock_t *rwlock); -extern void rt_write_lock(rwlock_t *rwlock); -extern void rt_write_lock_nested(rwlock_t *rwlock, int subclass); +extern void rt_read_unlock(rwlock_t *rwlock) __releases(rwlock); +extern void rt_write_lock(rwlock_t *rwlock) __acquires(rwlock); +extern void rt_write_lock_nested(rwlock_t *rwlock, int subclass) __acquires(rwlock); extern int rt_write_trylock(rwlock_t *rwlock); -extern void rt_write_unlock(rwlock_t *rwlock); +extern void rt_write_unlock(rwlock_t *rwlock) __releases(rwlock); static __always_inline void read_lock(rwlock_t *rwlock) { @ include/linux/sched.h:2005 @ static inline void set_tsk_need_resched(struct task_struct *tsk) static inline void clear_tsk_need_resched(struct task_struct *tsk) { - clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED); + atomic_long_andnot(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY, + (atomic_long_t *)&task_thread_info(tsk)->flags); } static inline int test_tsk_need_resched(struct task_struct *tsk) @ include/linux/serial_8250.h:156 @ struct uart_8250_port { #define MSR_SAVE_FLAGS UART_MSR_ANY_DELTA unsigned char msr_saved_flags; + bool console_newline_needed; + struct uart_8250_dma *dma; const struct uart_8250_ops *ops; @ include/linux/serial_8250.h:209 @ void serial8250_init_port(struct uart_8250_port *up); void serial8250_set_defaults(struct uart_8250_port *up); void serial8250_console_write(struct uart_8250_port *up, const char *s, unsigned int count); +void serial8250_console_write_atomic(struct uart_8250_port *up, + struct nbcon_write_context *wctxt); +void serial8250_console_write_thread(struct uart_8250_port *up, + struct nbcon_write_context *wctxt); int serial8250_console_setup(struct uart_port *port, char *options, bool probe); int serial8250_console_exit(struct uart_port *port); @ include/linux/spinlock_rt.h:35 @ do { \ __rt_spin_lock_init(slock, #slock, &__key, true); \ } while (0) -extern void rt_spin_lock(spinlock_t *lock); -extern void rt_spin_lock_nested(spinlock_t *lock, int subclass); -extern void rt_spin_lock_nest_lock(spinlock_t *lock, struct lockdep_map *nest_lock); -extern void rt_spin_unlock(spinlock_t *lock); +extern void rt_spin_lock(spinlock_t *lock) __acquires(lock); +extern void rt_spin_lock_nested(spinlock_t *lock, int subclass) __acquires(lock); +extern void rt_spin_lock_nest_lock(spinlock_t *lock, struct lockdep_map *nest_lock) __acquires(lock); +extern void rt_spin_unlock(spinlock_t *lock) __releases(lock); extern void rt_spin_lock_unlock(spinlock_t *lock); extern int rt_spin_trylock_bh(spinlock_t *lock); extern int rt_spin_trylock(spinlock_t *lock); @ include/linux/spinlock_rt.h:135 @ static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, #define spin_trylock_irq(lock) \ __cond_lock(lock, rt_spin_trylock(lock)) -#define __spin_trylock_irqsave(lock, flags) \ +#define spin_trylock_irqsave(lock, flags) \ ({ \ int __locked; \ \ @ include/linux/spinlock_rt.h:145 @ static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, __locked; \ }) -#define spin_trylock_irqsave(lock, flags) \ - __cond_lock(lock, __spin_trylock_irqsave(lock, flags)) - #define spin_is_contended(lock) (((void)(lock), 0)) static inline int spin_is_locked(spinlock_t *lock) @ include/linux/thread_info.h:62 @ enum syscall_work_bit { #include <asm/thread_info.h> +#ifndef TIF_NEED_RESCHED_LAZY +#ifdef CONFIG_ARCH_HAS_PREEMPT_LAZY +#error Inconsistent PREEMPT_LAZY +#endif +#define TIF_NEED_RESCHED_LAZY TIF_NEED_RESCHED +#define _TIF_NEED_RESCHED_LAZY _TIF_NEED_RESCHED +#endif + #ifdef __KERNEL__ #ifndef arch_set_restart_data @ include/linux/thread_info.h:190 @ static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti #ifdef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H -static __always_inline bool tif_need_resched(void) +static __always_inline bool tif_test_bit(int bit) { - return arch_test_bit(TIF_NEED_RESCHED, + return arch_test_bit(bit, (unsigned long *)(¤t_thread_info()->flags)); } #else -static __always_inline bool tif_need_resched(void) +static __always_inline bool tif_test_bit(int bit) { - return test_bit(TIF_NEED_RESCHED, + return test_bit(bit, (unsigned long *)(¤t_thread_info()->flags)); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ +static __always_inline bool tif_need_resched(void) +{ + return tif_test_bit(TIF_NEED_RESCHED); +} + #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, @ include/linux/trace_events.h:187 @ unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status); enum trace_flag_type { TRACE_FLAG_IRQS_OFF = 0x01, - TRACE_FLAG_IRQS_NOSUPPORT = 0x02, - TRACE_FLAG_NEED_RESCHED = 0x04, + TRACE_FLAG_NEED_RESCHED = 0x02, + TRACE_FLAG_NEED_RESCHED_LAZY = 0x04, TRACE_FLAG_HARDIRQ = 0x08, TRACE_FLAG_SOFTIRQ = 0x10, TRACE_FLAG_PREEMPT_RESCHED = 0x20, @ include/linux/trace_events.h:214 @ static inline unsigned int tracing_gen_ctx(void) static inline unsigned int tracing_gen_ctx_flags(unsigned long irqflags) { - return tracing_gen_ctx_irq_test(TRACE_FLAG_IRQS_NOSUPPORT); + return tracing_gen_ctx_irq_test(0); } static inline unsigned int tracing_gen_ctx(void) { - return tracing_gen_ctx_irq_test(TRACE_FLAG_IRQS_NOSUPPORT); + return tracing_gen_ctx_irq_test(0); } #endif @ kernel/Kconfig.preempt:14 @ config PREEMPT_BUILD select PREEMPTION select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK +config ARCH_HAS_PREEMPT_LAZY + bool + choice prompt "Preemption Model" default PREEMPT_NONE config PREEMPT_NONE bool "No Forced Preemption (Server)" + depends on !PREEMPT_RT select PREEMPT_NONE_BUILD if !PREEMPT_DYNAMIC help This is the traditional Linux preemption model, geared towards @ kernel/Kconfig.preempt:39 @ config PREEMPT_NONE config PREEMPT_VOLUNTARY bool "Voluntary Kernel Preemption (Desktop)" depends on !ARCH_NO_PREEMPT + depends on !PREEMPT_RT select PREEMPT_VOLUNTARY_BUILD if !PREEMPT_DYNAMIC help This option reduces the latency of the kernel by adding more @ kernel/Kconfig.preempt:59 @ config PREEMPT_VOLUNTARY config PREEMPT bool "Preemptible Kernel (Low-Latency Desktop)" depends on !ARCH_NO_PREEMPT - select PREEMPT_BUILD + select PREEMPT_BUILD if !PREEMPT_DYNAMIC help This option reduces the latency of the kernel by making all kernel code (that is not executing in a critical section) @ kernel/Kconfig.preempt:75 @ config PREEMPT embedded system with latency requirements in the milliseconds range. +config PREEMPT_LAZY + bool "Scheduler controlled preemption model" + depends on !ARCH_NO_PREEMPT + depends on ARCH_HAS_PREEMPT_LAZY + select PREEMPT_BUILD if !PREEMPT_DYNAMIC + help + This option provides a scheduler driven preemption model that + is fundamentally similar to full preemption, but is less + eager to preempt SCHED_NORMAL tasks in an attempt to + reduce lock holder preemption and recover some of the performance + gains seen from using Voluntary preemption. + +config PREEMPT_LAZIEST + bool "Scheduler controlled preemption model" + depends on !ARCH_NO_PREEMPT + depends on ARCH_HAS_PREEMPT_LAZY + select PREEMPT_BUILD if !PREEMPT_DYNAMIC + help + This option provides a scheduler driven preemption model that + is fundamentally similar to full preemption, but is least + eager to preempt SCHED_NORMAL tasks in an attempt to + reduce lock holder preemption and recover some of the performance + gains seen from using no preemption. + +endchoice + config PREEMPT_RT bool "Fully Preemptible Kernel (Real-Time)" depends on EXPERT && ARCH_SUPPORTS_RT @ kernel/Kconfig.preempt:118 @ config PREEMPT_RT Select this if you are building a kernel for systems which require real-time guarantees. -endchoice - config PREEMPT_COUNT bool @ kernel/Kconfig.preempt:127 @ config PREEMPTION config PREEMPT_DYNAMIC bool "Preemption behaviour defined on boot" - depends on HAVE_PREEMPT_DYNAMIC && !PREEMPT_RT + depends on HAVE_PREEMPT_DYNAMIC select JUMP_LABEL if HAVE_PREEMPT_DYNAMIC_KEY select PREEMPT_BUILD default y if HAVE_PREEMPT_DYNAMIC_CALL @ kernel/entry/common.c:101 @ __always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs, local_irq_enable_exit_to_user(ti_work); - if (ti_work & _TIF_NEED_RESCHED) + if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) schedule(); if (ti_work & _TIF_UPROBE) @ kernel/entry/kvm.c:16 @ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) return -EINTR; } - if (ti_work & _TIF_NEED_RESCHED) + if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) schedule(); if (ti_work & _TIF_NOTIFY_RESUME) @ kernel/entry/kvm.c:27 @ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) return ret; ti_work = read_thread_flags(); - } while (ti_work & XFER_TO_GUEST_MODE_WORK || need_resched()); + } while (ti_work & XFER_TO_GUEST_MODE_WORK); return 0; } @ kernel/ksysfs.c:191 @ KERNEL_ATTR_RO(crash_elfcorehdr_size); #endif /* CONFIG_VMCORE_INFO */ +#if defined(CONFIG_PREEMPT_RT) +static ssize_t realtime_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", 1); +} +KERNEL_ATTR_RO(realtime); +#endif + /* whether file capabilities are enabled */ static ssize_t fscaps_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @ kernel/ksysfs.c:297 @ static struct attribute * kernel_attrs[] = { #ifndef CONFIG_TINY_RCU &rcu_expedited_attr.attr, &rcu_normal_attr.attr, +#endif +#ifdef CONFIG_PREEMPT_RT + &realtime_attr.attr, #endif NULL }; @ kernel/locking/rtmutex.c:1604 @ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock, unsigned int state, struct hrtimer_sleeper *timeout, struct rt_mutex_waiter *waiter) + __releases(&lock->wait_lock) __acquires(&lock->wait_lock) { struct rt_mutex *rtm = container_of(lock, struct rt_mutex, rtmutex); struct task_struct *owner; @ kernel/locking/rtmutex.c:1809 @ static __always_inline int __rt_mutex_lock(struct rt_mutex_base *lock, * @lock: The underlying RT mutex */ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock) + __releases(&lock->wait_lock) __acquires(&lock->wait_lock) { struct rt_mutex_waiter waiter; struct task_struct *owner; @ kernel/locking/spinlock_rt.c:54 @ static __always_inline void __rt_spin_lock(spinlock_t *lock) migrate_disable(); } -void __sched rt_spin_lock(spinlock_t *lock) +void __sched rt_spin_lock(spinlock_t *lock) __acquires(RCU) { spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); __rt_spin_lock(lock); @ kernel/locking/spinlock_rt.c:78 @ void __sched rt_spin_lock_nest_lock(spinlock_t *lock, EXPORT_SYMBOL(rt_spin_lock_nest_lock); #endif -void __sched rt_spin_unlock(spinlock_t *lock) +void __sched rt_spin_unlock(spinlock_t *lock) __releases(RCU) { spin_release(&lock->dep_map, _RET_IP_); migrate_enable(); @ kernel/locking/spinlock_rt.c:228 @ int __sched rt_write_trylock(rwlock_t *rwlock) } EXPORT_SYMBOL(rt_write_trylock); -void __sched rt_read_lock(rwlock_t *rwlock) +void __sched rt_read_lock(rwlock_t *rwlock) __acquires(RCU) { rtlock_might_resched(); rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_); @ kernel/locking/spinlock_rt.c:238 @ void __sched rt_read_lock(rwlock_t *rwlock) } EXPORT_SYMBOL(rt_read_lock); -void __sched rt_write_lock(rwlock_t *rwlock) +void __sched rt_write_lock(rwlock_t *rwlock) __acquires(RCU) { rtlock_might_resched(); rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); @ kernel/locking/spinlock_rt.c:249 @ void __sched rt_write_lock(rwlock_t *rwlock) EXPORT_SYMBOL(rt_write_lock); #ifdef CONFIG_DEBUG_LOCK_ALLOC -void __sched rt_write_lock_nested(rwlock_t *rwlock, int subclass) +void __sched rt_write_lock_nested(rwlock_t *rwlock, int subclass) __acquires(RCU) { rtlock_might_resched(); rwlock_acquire(&rwlock->dep_map, subclass, 0, _RET_IP_); @ kernel/locking/spinlock_rt.c:260 @ void __sched rt_write_lock_nested(rwlock_t *rwlock, int subclass) EXPORT_SYMBOL(rt_write_lock_nested); #endif -void __sched rt_read_unlock(rwlock_t *rwlock) +void __sched rt_read_unlock(rwlock_t *rwlock) __releases(RCU) { rwlock_release(&rwlock->dep_map, _RET_IP_); migrate_enable(); @ kernel/locking/spinlock_rt.c:269 @ void __sched rt_read_unlock(rwlock_t *rwlock) } EXPORT_SYMBOL(rt_read_unlock); -void __sched rt_write_unlock(rwlock_t *rwlock) +void __sched rt_write_unlock(rwlock_t *rwlock) __releases(RCU) { rwlock_release(&rwlock->dep_map, _RET_IP_); rcu_read_unlock(); @ kernel/rcu/rcutorture.c:2443 @ static int rcutorture_booster_init(unsigned int cpu) WARN_ON_ONCE(!t); sp.sched_priority = 2; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); +#ifdef CONFIG_PREEMPT_RT + t = per_cpu(timersd, cpu); + WARN_ON_ONCE(!t); + sp.sched_priority = 2; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); +#endif } /* Don't allow time recalculation while creating a new task. */ @ kernel/sched/core.c:939 @ static inline void hrtick_rq_init(struct rq *rq) * this avoids any races wrt polling state changes and thereby avoids * spurious IPIs. */ -static inline bool set_nr_and_not_polling(struct task_struct *p) +static inline bool set_nr_and_not_polling(struct thread_info *ti, int tif) { - struct thread_info *ti = task_thread_info(p); - return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG); + return !(fetch_or(&ti->flags, 1 << tif) & _TIF_POLLING_NRFLAG); } /* @ kernel/sched/core.c:966 @ static bool set_nr_if_polling(struct task_struct *p) } #else -static inline bool set_nr_and_not_polling(struct task_struct *p) +static inline bool set_nr_and_not_polling(struct thread_info *ti, int tif) { - set_tsk_need_resched(p); + atomic_long_or(1 << tif, (atomic_long_t *)&ti->flags); return true; } @ kernel/sched/core.c:1073 @ void wake_up_q(struct wake_q_head *head) * might also involve a cross-CPU call to trigger the scheduler on * the target CPU. */ -void resched_curr(struct rq *rq) +static void __resched_curr(struct rq *rq, int tif) { struct task_struct *curr = rq->curr; + struct thread_info *cti = task_thread_info(curr); int cpu; lockdep_assert_rq_held(rq); - if (test_tsk_need_resched(curr)) + if (is_idle_task(curr) && tif == TIF_NEED_RESCHED_LAZY) + tif = TIF_NEED_RESCHED; + + if (cti->flags & ((1 << tif) | _TIF_NEED_RESCHED)) return; cpu = cpu_of(rq); if (cpu == smp_processor_id()) { - set_tsk_need_resched(curr); - set_preempt_need_resched(); + set_ti_thread_flag(cti, tif); + if (tif == TIF_NEED_RESCHED) + set_preempt_need_resched(); return; } - if (set_nr_and_not_polling(curr)) - smp_send_reschedule(cpu); - else + if (set_nr_and_not_polling(cti, tif)) { + if (tif == TIF_NEED_RESCHED) + smp_send_reschedule(cpu); + } else { trace_sched_wake_idle_without_ipi(cpu); + } +} + +void resched_curr(struct rq *rq) +{ + __resched_curr(rq, TIF_NEED_RESCHED); +} + +#ifdef CONFIG_PREEMPT_DYNAMIC +static DEFINE_STATIC_KEY_FALSE(sk_dynamic_preempt_lazy); +static DEFINE_STATIC_KEY_FALSE(sk_dynamic_preempt_promote); +static __always_inline bool dynamic_preempt_lazy(void) +{ + return static_branch_unlikely(&sk_dynamic_preempt_lazy); +} +static __always_inline bool dynamic_preempt_promote(void) +{ + return static_branch_unlikely(&sk_dynamic_preempt_promote); +} +#else +static __always_inline bool dynamic_preempt_lazy(void) +{ + return IS_ENABLED(PREEMPT_LAZY) | IS_ENABLED(PREEMPT_LAZIEST); +} +static __always_inline bool dynamic_preempt_promote(void) +{ + return IS_ENABLED(PREEMPT_LAZY); +} +#endif + +static __always_inline int tif_need_resched_lazy(void) +{ + if (dynamic_preempt_lazy()) + return TIF_NEED_RESCHED_LAZY; + + return TIF_NEED_RESCHED; +} + +void resched_curr_lazy(struct rq *rq) +{ + __resched_curr(rq, tif_need_resched_lazy()); } void resched_cpu(int cpu) @ kernel/sched/core.c:1236 @ static void wake_up_idle_cpu(int cpu) * and testing of the above solutions didn't appear to report * much benefits. */ - if (set_nr_and_not_polling(rq->idle)) + if (set_nr_and_not_polling(task_thread_info(rq->idle), TIF_NEED_RESCHED)) smp_send_reschedule(cpu); else trace_sched_wake_idle_without_ipi(cpu); @ kernel/sched/core.c:5639 @ void sched_tick(void) update_rq_clock(rq); hw_pressure = arch_scale_hw_pressure(cpu_of(rq)); update_hw_load_avg(rq_clock_task(rq), rq, hw_pressure); + + if (dynamic_preempt_promote() && tif_test_bit(TIF_NEED_RESCHED_LAZY)) + resched_curr(rq); + curr->sched_class->task_tick(rq, curr, 0); if (sched_feat(LATENCY_WARN)) resched_latency = cpu_resched_latency(rq); @ kernel/sched/core.c:7379 @ EXPORT_SYMBOL(__cond_resched_rwlock_write); * preempt_schedule <- NOP * preempt_schedule_notrace <- NOP * irqentry_exit_cond_resched <- NOP + * dynamic_preempt_lazy <- false + * dynamic_preempt_promote <- false * * VOLUNTARY: * cond_resched <- __cond_resched @ kernel/sched/core.c:7388 @ EXPORT_SYMBOL(__cond_resched_rwlock_write); * preempt_schedule <- NOP * preempt_schedule_notrace <- NOP * irqentry_exit_cond_resched <- NOP + * dynamic_preempt_lazy <- false + * dynamic_preempt_promote <- false * * FULL: * cond_resched <- RET0 @ kernel/sched/core.c:7397 @ EXPORT_SYMBOL(__cond_resched_rwlock_write); * preempt_schedule <- preempt_schedule * preempt_schedule_notrace <- preempt_schedule_notrace * irqentry_exit_cond_resched <- irqentry_exit_cond_resched + * dynamic_preempt_lazy <- false + * dynamic_preempt_promote <- false + * + * LAZY: + * cond_resched <- RET0 + * might_resched <- RET0 + * preempt_schedule <- preempt_schedule + * preempt_schedule_notrace <- preempt_schedule_notrace + * irqentry_exit_cond_resched <- irqentry_exit_cond_resched + * dynamic_preempt_lazy <- true + * dynamic_preempt_promote <- true + * + * LAZIEST: + * cond_resched <- RET0 + * might_resched <- RET0 + * preempt_schedule <- preempt_schedule + * preempt_schedule_notrace <- preempt_schedule_notrace + * irqentry_exit_cond_resched <- irqentry_exit_cond_resched + * dynamic_preempt_lazy <- true + * dynamic_preempt_promote <- false */ enum { @ kernel/sched/core.c:7424 @ enum { preempt_dynamic_none, preempt_dynamic_voluntary, preempt_dynamic_full, + preempt_dynamic_lazy, + preempt_dynamic_laziest, }; int preempt_dynamic_mode = preempt_dynamic_undefined; int sched_dynamic_mode(const char *str) { +#ifndef CONFIG_PREEMPT_RT if (!strcmp(str, "none")) return preempt_dynamic_none; if (!strcmp(str, "voluntary")) return preempt_dynamic_voluntary; +#endif if (!strcmp(str, "full")) return preempt_dynamic_full; +#ifdef CONFIG_ARCH_HAS_PREEMPT_LAZY + if (!strcmp(str, "lazy")) + return preempt_dynamic_lazy; + + if (!strcmp(str, "laziest")) + return preempt_dynamic_laziest; +#endif + return -EINVAL; } +#define preempt_dynamic_key_enable(f) static_key_enable(&sk_dynamic_##f.key) +#define preempt_dynamic_key_disable(f) static_key_disable(&sk_dynamic_##f.key) + #if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) #define preempt_dynamic_enable(f) static_call_update(f, f##_dynamic_enabled) #define preempt_dynamic_disable(f) static_call_update(f, f##_dynamic_disabled) #elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) -#define preempt_dynamic_enable(f) static_key_enable(&sk_dynamic_##f.key) -#define preempt_dynamic_disable(f) static_key_disable(&sk_dynamic_##f.key) +#define preempt_dynamic_enable(f) preempt_dynamic_key_enable(f) +#define preempt_dynamic_disable(f) preempt_dynamic_key_disable(f) #else #error "Unsupported PREEMPT_DYNAMIC mechanism" #endif @ kernel/sched/core.c:7482 @ static void __sched_dynamic_update(int mode) preempt_dynamic_enable(preempt_schedule); preempt_dynamic_enable(preempt_schedule_notrace); preempt_dynamic_enable(irqentry_exit_cond_resched); + preempt_dynamic_key_disable(preempt_lazy); + preempt_dynamic_key_disable(preempt_promote); switch (mode) { case preempt_dynamic_none: @ kernel/sched/core.c:7493 @ static void __sched_dynamic_update(int mode) preempt_dynamic_disable(preempt_schedule); preempt_dynamic_disable(preempt_schedule_notrace); preempt_dynamic_disable(irqentry_exit_cond_resched); + preempt_dynamic_key_disable(preempt_lazy); + preempt_dynamic_key_disable(preempt_promote); if (mode != preempt_dynamic_mode) pr_info("Dynamic Preempt: none\n"); break; @ kernel/sched/core.c:7506 @ static void __sched_dynamic_update(int mode) preempt_dynamic_disable(preempt_schedule); preempt_dynamic_disable(preempt_schedule_notrace); preempt_dynamic_disable(irqentry_exit_cond_resched); + preempt_dynamic_key_disable(preempt_lazy); + preempt_dynamic_key_disable(preempt_promote); if (mode != preempt_dynamic_mode) pr_info("Dynamic Preempt: voluntary\n"); break; @ kernel/sched/core.c:7519 @ static void __sched_dynamic_update(int mode) preempt_dynamic_enable(preempt_schedule); preempt_dynamic_enable(preempt_schedule_notrace); preempt_dynamic_enable(irqentry_exit_cond_resched); + preempt_dynamic_key_disable(preempt_lazy); + preempt_dynamic_key_disable(preempt_promote); if (mode != preempt_dynamic_mode) pr_info("Dynamic Preempt: full\n"); break; + + case preempt_dynamic_lazy: + if (!klp_override) + preempt_dynamic_disable(cond_resched); + preempt_dynamic_disable(might_resched); + preempt_dynamic_enable(preempt_schedule); + preempt_dynamic_enable(preempt_schedule_notrace); + preempt_dynamic_enable(irqentry_exit_cond_resched); + preempt_dynamic_key_enable(preempt_lazy); + preempt_dynamic_key_enable(preempt_promote); + if (mode != preempt_dynamic_mode) + pr_info("Dynamic Preempt: lazy\n"); + break; + + case preempt_dynamic_laziest: + if (!klp_override) + preempt_dynamic_disable(cond_resched); + preempt_dynamic_disable(might_resched); + preempt_dynamic_enable(preempt_schedule); + preempt_dynamic_enable(preempt_schedule_notrace); + preempt_dynamic_enable(irqentry_exit_cond_resched); + preempt_dynamic_key_enable(preempt_lazy); + preempt_dynamic_key_disable(preempt_promote); + if (mode != preempt_dynamic_mode) + pr_info("Dynamic Preempt: laziest\n"); + break; } preempt_dynamic_mode = mode; @ kernel/sched/core.c:7612 @ static void __init preempt_dynamic_init(void) sched_dynamic_update(preempt_dynamic_none); } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) { sched_dynamic_update(preempt_dynamic_voluntary); + } else if (IS_ENABLED(CONFIG_PREEMPT_LAZY)) { + sched_dynamic_update(preempt_dynamic_lazy); + } else if (IS_ENABLED(CONFIG_PREEMPT_LAZIEST)) { + sched_dynamic_update(preempt_dynamic_laziest); } else { /* Default static call setting, nothing to do */ WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT)); @ kernel/sched/core.c:7636 @ static void __init preempt_dynamic_init(void) PREEMPT_MODEL_ACCESSOR(none); PREEMPT_MODEL_ACCESSOR(voluntary); PREEMPT_MODEL_ACCESSOR(full); +PREEMPT_MODEL_ACCESSOR(lazy); +PREEMPT_MODEL_ACCESSOR(laziest); #else /* !CONFIG_PREEMPT_DYNAMIC: */ @ kernel/sched/debug.c:248 @ static ssize_t sched_dynamic_write(struct file *filp, const char __user *ubuf, static int sched_dynamic_show(struct seq_file *m, void *v) { static const char * preempt_modes[] = { - "none", "voluntary", "full" + "none", "voluntary", "full", "lazy", "laziest", }; - int i; + int j = ARRAY_SIZE(preempt_modes) - 2*!IS_ENABLED(CONFIG_ARCH_HAS_PREEMPT_LAZY); + int i = IS_ENABLED(CONFIG_PREEMPT_RT) * 2; - for (i = 0; i < ARRAY_SIZE(preempt_modes); i++) { + for (; i < j; i++) { if (preempt_dynamic_mode == i) seq_puts(m, "("); seq_puts(m, preempt_modes[i]); @ kernel/sched/fair.c:1254 @ static void update_curr(struct cfs_rq *cfs_rq) return; if (resched || did_preempt_short(cfs_rq, curr)) { - resched_curr(rq); + resched_curr_lazy(rq); clear_buddies(cfs_rq, curr); } } @ kernel/sched/fair.c:5680 @ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) * validating it and just reschedule. */ if (queued) { - resched_curr(rq_of(cfs_rq)); + resched_curr_lazy(rq_of(cfs_rq)); return; } /* @ kernel/sched/fair.c:8835 @ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int return; preempt: - resched_curr(rq); + resched_curr_lazy(rq); } static struct task_struct *pick_task_fair(struct rq *rq) @ kernel/sched/sched.h:2695 @ extern void init_sched_rt_class(void); extern void init_sched_fair_class(void); extern void resched_curr(struct rq *rq); +extern void resched_curr_lazy(struct rq *rq); extern void resched_cpu(int cpu); extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); @ kernel/softirq.c:627 @ static inline void tick_irq_exit(void) #endif } +#ifdef CONFIG_PREEMPT_RT +DEFINE_PER_CPU(struct task_struct *, timersd); +DEFINE_PER_CPU(unsigned long, pending_timer_softirq); + +static void wake_timersd(void) +{ + struct task_struct *tsk = __this_cpu_read(timersd); + + if (tsk) + wake_up_process(tsk); +} + +#else + +static inline void wake_timersd(void) { } + +#endif + static inline void __irq_exit_rcu(void) { #ifndef __ARCH_IRQ_EXIT_IRQS_DISABLED @ kernel/softirq.c:657 @ static inline void __irq_exit_rcu(void) if (!in_interrupt() && local_softirq_pending()) invoke_softirq(); + if (IS_ENABLED(CONFIG_PREEMPT_RT) && local_pending_timers() && + !(in_nmi() | in_hardirq())) + wake_timersd(); + tick_irq_exit(); } @ kernel/softirq.c:996 @ static struct smp_hotplug_thread softirq_threads = { .thread_comm = "ksoftirqd/%u", }; +#ifdef CONFIG_PREEMPT_RT +static void timersd_setup(unsigned int cpu) +{ + sched_set_fifo_low(current); +} + +static int timersd_should_run(unsigned int cpu) +{ + return local_pending_timers(); +} + +static void run_timersd(unsigned int cpu) +{ + unsigned int timer_si; + + ksoftirqd_run_begin(); + + timer_si = local_pending_timers(); + __this_cpu_write(pending_timer_softirq, 0); + or_softirq_pending(timer_si); + + __do_softirq(); + + ksoftirqd_run_end(); +} + +static void raise_ktimers_thread(unsigned int nr) +{ + trace_softirq_raise(nr); + __this_cpu_or(pending_timer_softirq, 1 << nr); +} + +void raise_hrtimer_softirq(void) +{ + raise_ktimers_thread(HRTIMER_SOFTIRQ); +} + +void raise_timer_softirq(void) +{ + unsigned long flags; + + local_irq_save(flags); + raise_ktimers_thread(TIMER_SOFTIRQ); + wake_timersd(); + local_irq_restore(flags); +} + +static struct smp_hotplug_thread timer_threads = { + .store = &timersd, + .setup = timersd_setup, + .thread_should_run = timersd_should_run, + .thread_fn = run_timersd, + .thread_comm = "ktimers/%u", +}; +#endif + static __init int spawn_ksoftirqd(void) { cpuhp_setup_state_nocalls(CPUHP_SOFTIRQ_DEAD, "softirq:dead", NULL, takeover_tasklets); BUG_ON(smpboot_register_percpu_thread(&softirq_threads)); - +#ifdef CONFIG_PREEMPT_RT + BUG_ON(smpboot_register_percpu_thread(&timer_threads)); +#endif return 0; } early_initcall(spawn_ksoftirqd); @ kernel/time/hrtimer.c:1814 @ void hrtimer_interrupt(struct clock_event_device *dev) if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; - raise_softirq_irqoff(HRTIMER_SOFTIRQ); + raise_hrtimer_softirq(); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); @ kernel/time/hrtimer.c:1909 @ void hrtimer_run_queues(void) if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; - raise_softirq_irqoff(HRTIMER_SOFTIRQ); + raise_hrtimer_softirq(); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); @ kernel/time/tick-sched.c:862 @ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) static inline bool local_timer_softirq_pending(void) { - return local_softirq_pending() & BIT(TIMER_SOFTIRQ); + return local_pending_timers() & BIT(TIMER_SOFTIRQ); } /* @ kernel/time/timer.c:2502 @ static void run_local_timers(void) */ if (time_after_eq(jiffies, READ_ONCE(base->next_expiry)) || (i == BASE_DEF && tmigr_requires_handle_remote())) { - raise_softirq(TIMER_SOFTIRQ); + raise_timer_softirq(); return; } } @ kernel/trace/trace.c:2547 @ unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status) trace_flags |= TRACE_FLAG_NEED_RESCHED; if (test_preempt_need_resched()) trace_flags |= TRACE_FLAG_PREEMPT_RESCHED; + if (IS_ENABLED(CONFIG_ARCH_HAS_PREEMPT_LAZY) && tif_test_bit(TIF_NEED_RESCHED_LAZY)) + trace_flags |= TRACE_FLAG_NEED_RESCHED_LAZY; return (trace_flags << 16) | (min_t(unsigned int, pc & 0xff, 0xf)) | (min_t(unsigned int, migration_disable_value(), 0xf)) << 4; } @ kernel/trace/trace_output.c:463 @ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) (entry->flags & TRACE_FLAG_IRQS_OFF && bh_off) ? 'D' : (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : bh_off ? 'b' : - (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' : + !IS_ENABLED(CONFIG_TRACE_IRQFLAGS_SUPPORT) ? 'X' : '.'; - switch (entry->flags & (TRACE_FLAG_NEED_RESCHED | + switch (entry->flags & (TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY | TRACE_FLAG_PREEMPT_RESCHED)) { + case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY | TRACE_FLAG_PREEMPT_RESCHED: + need_resched = 'B'; + break; case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_PREEMPT_RESCHED: need_resched = 'N'; break; + case TRACE_FLAG_NEED_RESCHED_LAZY | TRACE_FLAG_PREEMPT_RESCHED: + need_resched = 'L'; + break; + case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY: + need_resched = 'b'; + break; case TRACE_FLAG_NEED_RESCHED: need_resched = 'n'; break; case TRACE_FLAG_PREEMPT_RESCHED: need_resched = 'p'; break; + case TRACE_FLAG_NEED_RESCHED_LAZY: + need_resched = 'l'; + break; default: need_resched = '.'; break; @ localversion-rt:1 @ +-rt4